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>
15 ;;; Copyright © 2019 Maxim Cournoyer <maxim.cournoyer@gmail.com>
17 ;;; This file is part of GNU Guix.
19 ;;; GNU Guix is free software; you can redistribute it and/or modify it
20 ;;; under the terms of the GNU General Public License as published by
21 ;;; the Free Software Foundation; either version 3 of the License, or (at
22 ;;; your option) any later version.
24 ;;; GNU Guix is distributed in the hope that it will be useful, but
25 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
26 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
27 ;;; GNU General Public License for more details.
29 ;;; You should have received a copy of the GNU General Public License
30 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
32 (define-module (gnu packages bioinformatics)
33 #:use-module ((guix licenses) #:prefix license:)
34 #:use-module (guix packages)
35 #:use-module (guix utils)
36 #:use-module (guix download)
37 #:use-module (guix git-download)
38 #:use-module (guix hg-download)
39 #:use-module (guix build-system ant)
40 #:use-module (guix build-system gnu)
41 #:use-module (guix build-system cmake)
42 #:use-module (guix build-system haskell)
43 #:use-module (guix build-system ocaml)
44 #:use-module (guix build-system perl)
45 #:use-module (guix build-system python)
46 #:use-module (guix build-system r)
47 #:use-module (guix build-system ruby)
48 #:use-module (guix build-system scons)
49 #:use-module (guix build-system trivial)
50 #:use-module (gnu packages)
51 #:use-module (gnu packages autotools)
52 #:use-module (gnu packages algebra)
53 #:use-module (gnu packages base)
54 #:use-module (gnu packages bash)
55 #:use-module (gnu packages bison)
56 #:use-module (gnu packages bioconductor)
57 #:use-module (gnu packages boost)
58 #:use-module (gnu packages check)
59 #:use-module (gnu packages compression)
60 #:use-module (gnu packages cpio)
61 #:use-module (gnu packages cran)
62 #:use-module (gnu packages curl)
63 #:use-module (gnu packages documentation)
64 #:use-module (gnu packages databases)
65 #:use-module (gnu packages datastructures)
66 #:use-module (gnu packages file)
67 #:use-module (gnu packages flex)
68 #:use-module (gnu packages gawk)
69 #:use-module (gnu packages gcc)
70 #:use-module (gnu packages gd)
71 #:use-module (gnu packages gtk)
72 #:use-module (gnu packages glib)
73 #:use-module (gnu packages graph)
74 #:use-module (gnu packages groff)
75 #:use-module (gnu packages guile)
76 #:use-module (gnu packages guile-xyz)
77 #:use-module (gnu packages haskell)
78 #:use-module (gnu packages haskell-check)
79 #:use-module (gnu packages haskell-web)
80 #:use-module (gnu packages image)
81 #:use-module (gnu packages imagemagick)
82 #:use-module (gnu packages java)
83 #:use-module (gnu packages java-compression)
84 #:use-module (gnu packages jemalloc)
85 #:use-module (gnu packages dlang)
86 #:use-module (gnu packages linux)
87 #:use-module (gnu packages lisp)
88 #:use-module (gnu packages logging)
89 #:use-module (gnu packages machine-learning)
90 #:use-module (gnu packages man)
91 #:use-module (gnu packages maths)
92 #:use-module (gnu packages mpi)
93 #:use-module (gnu packages ncurses)
94 #:use-module (gnu packages ocaml)
95 #:use-module (gnu packages pcre)
96 #:use-module (gnu packages parallel)
97 #:use-module (gnu packages pdf)
98 #:use-module (gnu packages perl)
99 #:use-module (gnu packages perl-check)
100 #:use-module (gnu packages pkg-config)
101 #:use-module (gnu packages popt)
102 #:use-module (gnu packages protobuf)
103 #:use-module (gnu packages python)
104 #:use-module (gnu packages python-compression)
105 #:use-module (gnu packages python-web)
106 #:use-module (gnu packages python-xyz)
107 #:use-module (gnu packages readline)
108 #:use-module (gnu packages ruby)
109 #:use-module (gnu packages serialization)
110 #:use-module (gnu packages shells)
111 #:use-module (gnu packages statistics)
112 #:use-module (gnu packages swig)
113 #:use-module (gnu packages tbb)
114 #:use-module (gnu packages tex)
115 #:use-module (gnu packages texinfo)
116 #:use-module (gnu packages textutils)
117 #:use-module (gnu packages time)
118 #:use-module (gnu packages tls)
119 #:use-module (gnu packages vim)
120 #:use-module (gnu packages web)
121 #:use-module (gnu packages xml)
122 #:use-module (gnu packages xorg)
123 #:use-module (srfi srfi-1)
124 #:use-module (ice-9 match))
126 (define-public aragorn
133 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
137 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
138 (build-system gnu-build-system)
140 `(#:tests? #f ; there are no tests
142 (modify-phases %standard-phases
152 (string-append "aragorn" ,version ".c"))
155 (lambda* (#:key outputs #:allow-other-keys)
156 (let* ((out (assoc-ref outputs "out"))
157 (bin (string-append out "/bin"))
158 (man (string-append out "/share/man/man1")))
159 (install-file "aragorn" bin)
160 (install-file "aragorn.1" man))
162 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
163 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
165 "Aragorn identifies transfer RNA, mitochondrial RNA and
166 transfer-messenger RNA from nucleotide sequences, based on homology to known
167 tRNA consensus sequences and RNA structure. It also outputs the secondary
168 structure of the predicted RNA.")
169 (license license:gpl2)))
177 ;; BamM is not available on pypi.
179 (url "https://github.com/Ecogenomics/BamM.git")
182 (file-name (git-file-name name version))
185 "1p83ahi984ipslxlg4yqy1gdnya9rkn1v71z8djgxkm9d2chw4c5"))
186 (modules '((guix build utils)))
189 ;; Delete bundled htslib.
190 (delete-file-recursively "c/htslib-1.3.1")
192 (build-system python-build-system)
194 `(#:python ,python-2 ; BamM is Python 2 only.
195 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
196 ;; been modified from its original form.
198 (let ((htslib (assoc-ref %build-inputs "htslib")))
199 (list "--with-libhts-lib" (string-append htslib "/lib")
200 "--with-libhts-inc" (string-append htslib "/include/htslib")))
202 (modify-phases %standard-phases
203 (add-after 'unpack 'autogen
205 (with-directory-excursion "c"
206 (let ((sh (which "sh")))
207 (for-each make-file-writable (find-files "." ".*"))
208 ;; Use autogen so that 'configure' works.
209 (substitute* "autogen.sh" (("/bin/sh") sh))
210 (setenv "CONFIG_SHELL" sh)
211 (invoke "./autogen.sh")))
214 ;; Run tests after installation so compilation only happens once.
216 (add-after 'install 'wrap-executable
217 (lambda* (#:key outputs #:allow-other-keys)
218 (let* ((out (assoc-ref outputs "out"))
219 (path (getenv "PATH")))
220 (wrap-program (string-append out "/bin/bamm")
221 `("PATH" ":" prefix (,path))))
223 (add-after 'wrap-executable 'post-install-check
224 (lambda* (#:key inputs outputs #:allow-other-keys)
226 (string-append (assoc-ref outputs "out")
231 (assoc-ref outputs "out")
233 (string-take (string-take-right
234 (assoc-ref inputs "python") 5) 3)
236 (getenv "PYTHONPATH")))
237 ;; There are 2 errors printed, but they are safe to ignore:
238 ;; 1) [E::hts_open_format] fail to open file ...
239 ;; 2) samtools view: failed to open ...
243 `(("autoconf" ,autoconf)
244 ("automake" ,automake)
247 ("python-nose" ,python2-nose)
248 ("python-pysam" ,python2-pysam)))
250 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
251 ("samtools" ,samtools)
255 ("coreutils" ,coreutils)))
257 `(("python-numpy" ,python2-numpy)))
258 (home-page "http://ecogenomics.github.io/BamM/")
259 (synopsis "Metagenomics-focused BAM file manipulator")
261 "BamM is a C library, wrapped in python, to efficiently generate and
262 parse BAM files, specifically for the analysis of metagenomic data. For
263 instance, it implements several methods to assess contig-wise read coverage.")
264 (license license:lgpl3+)))
266 (define-public bamtools
273 (url "https://github.com/pezmaster31/bamtools.git")
274 (commit (string-append "v" version))))
275 (file-name (git-file-name name version))
278 "0nfb2ypcx9959xnbz6wxh6py3xfizgmg8nrknxl95c507m9hmq8b"))))
279 (build-system cmake-build-system)
281 `(#:tests? #f ;no "check" target
283 (modify-phases %standard-phases
285 'configure 'set-ldflags
286 (lambda* (#:key outputs #:allow-other-keys)
290 (assoc-ref outputs "out") "/lib/bamtools"))
292 (inputs `(("zlib" ,zlib)))
293 (home-page "https://github.com/pezmaster31/bamtools")
294 (synopsis "C++ API and command-line toolkit for working with BAM data")
296 "BamTools provides both a C++ API and a command-line toolkit for handling
298 (license license:expat)))
300 (define-public bcftools
306 (uri (string-append "https://github.com/samtools/bcftools/"
308 version "/bcftools-" version ".tar.bz2"))
311 "1j3h638i8kgihzyrlnpj82xg1b23sijibys9hvwari3fy7kd0dkg"))
312 (modules '((guix build utils)))
314 ;; Delete bundled htslib.
315 (delete-file-recursively "htslib-1.9")
317 (build-system gnu-build-system)
320 (list "--enable-libgsl")
323 (modify-phases %standard-phases
324 (add-before 'check 'patch-tests
326 (substitute* "test/test.pl"
327 (("/bin/bash") (which "bash")))
335 (home-page "https://samtools.github.io/bcftools/")
336 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
338 "BCFtools is a set of utilities that manipulate variant calls in the
339 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
340 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
341 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
342 (license (list license:gpl3+ license:expat))))
344 (define-public bedops
351 (url "https://github.com/bedops/bedops.git")
352 (commit (string-append "v" version))))
353 (file-name (git-file-name name version))
356 "0mmgsgwz5r9w76hzgxkxc9s9lkdhhaf7vr6i02b09vbswvs1fyqx"))))
357 (build-system gnu-build-system)
360 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
362 (modify-phases %standard-phases
363 (add-after 'unpack 'unpack-tarballs
365 ;; FIXME: Bedops includes tarballs of minimally patched upstream
366 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
367 ;; libraries because at least one of the libraries (zlib) is
368 ;; patched to add a C++ function definition (deflateInit2cpp).
369 ;; Until the Bedops developers offer a way to link against system
370 ;; libraries we have to build the in-tree copies of these three
373 ;; See upstream discussion:
374 ;; https://github.com/bedops/bedops/issues/124
376 ;; Unpack the tarballs to benefit from shebang patching.
377 (with-directory-excursion "third-party"
378 (invoke "tar" "xvf" "jansson-2.6.tar.bz2")
379 (invoke "tar" "xvf" "zlib-1.2.7.tar.bz2")
380 (invoke "tar" "xvf" "bzip2-1.0.6.tar.bz2"))
381 ;; Disable unpacking of tarballs in Makefile.
382 (substitute* "system.mk/Makefile.linux"
383 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
384 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
385 (substitute* "third-party/zlib-1.2.7/Makefile.in"
386 (("^SHELL=.*$") "SHELL=bash\n"))
388 (delete 'configure))))
389 (home-page "https://github.com/bedops/bedops")
390 (synopsis "Tools for high-performance genomic feature operations")
392 "BEDOPS is a suite of tools to address common questions raised in genomic
393 studies---mostly with regard to overlap and proximity relationships between
394 data sets. It aims to be scalable and flexible, facilitating the efficient
395 and accurate analysis and management of large-scale genomic data.
397 BEDOPS provides tools that perform highly efficient and scalable Boolean and
398 other set operations, statistical calculations, archiving, conversion and
399 other management of genomic data of arbitrary scale. Tasks can be easily
400 split by chromosome for distributing whole-genome analyses across a
401 computational cluster.")
402 (license license:gpl2+)))
404 (define-public bedtools
410 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
411 "download/v" version "/"
412 "bedtools-" version ".tar.gz"))
415 "1ndg5yknrxl4djx8ddzgk12rrbiidfpmkkg5z3f95jzryfxarhn8"))))
416 (build-system gnu-build-system)
418 '(#:test-target "test"
420 (list (string-append "prefix=" (assoc-ref %outputs "out")))
422 (modify-phases %standard-phases
423 (delete 'configure))))
424 (native-inputs `(("python" ,python-2)))
426 `(("samtools" ,samtools)
428 (home-page "https://github.com/arq5x/bedtools2")
429 (synopsis "Tools for genome analysis and arithmetic")
431 "Collectively, the bedtools utilities are a swiss-army knife of tools for
432 a wide-range of genomics analysis tasks. The most widely-used tools enable
433 genome arithmetic: that is, set theory on the genome. For example, bedtools
434 allows one to intersect, merge, count, complement, and shuffle genomic
435 intervals from multiple files in widely-used genomic file formats such as BAM,
437 (license license:gpl2)))
439 ;; Later releases of bedtools produce files with more columns than
440 ;; what Ribotaper expects.
441 (define-public bedtools-2.18
442 (package (inherit bedtools)
447 (uri (string-append "https://github.com/arq5x/bedtools2/"
448 "releases/download/v" version
449 "/bedtools-" version ".tar.gz"))
452 "11rvca19ncg03kxd0wzlfx5ws7r3nisd0z8s9j9n182d8ksp2pxz"))))
454 '(#:test-target "test"
456 (modify-phases %standard-phases
459 (lambda* (#:key outputs #:allow-other-keys)
460 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
461 (for-each (lambda (file)
462 (install-file file bin))
463 (find-files "bin" ".*")))
466 ;; Needed for pybedtools.
467 (define-public bedtools-2.26
468 (package (inherit bedtools)
473 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
474 "download/v" version "/"
475 "bedtools-" version ".tar.gz"))
478 "0jhavwifnf7lmkb11h9y7dynr8d699h0rd2l52j1pfgircr2zwv5"))))))
480 (define-public ribotaper
486 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
487 "files/RiboTaper/RiboTaper_Version_"
491 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
492 (build-system gnu-build-system)
495 (modify-phases %standard-phases
496 (add-after 'install 'wrap-executables
497 (lambda* (#:key inputs outputs #:allow-other-keys)
498 (let* ((out (assoc-ref outputs "out")))
501 (wrap-program (string-append out "/bin/" script)
502 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
503 '("create_annotations_files.bash"
504 "create_metaplots.bash"
505 "Ribotaper_ORF_find.sh"
509 `(("bedtools" ,bedtools-2.18)
510 ("samtools" ,samtools-0.1)
511 ("r-minimal" ,r-minimal)
512 ("r-foreach" ,r-foreach)
513 ("r-xnomial" ,r-xnomial)
515 ("r-multitaper" ,r-multitaper)
516 ("r-seqinr" ,r-seqinr)))
517 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
518 (synopsis "Define translated ORFs using ribosome profiling data")
520 "Ribotaper is a method for defining translated @dfn{open reading
521 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
522 provides the Ribotaper pipeline.")
523 (license license:gpl3+)))
525 (define-public ribodiff
533 (url "https://github.com/ratschlab/RiboDiff.git")
534 (commit (string-append "v" version))))
535 (file-name (git-file-name name version))
538 "0x75nlp7qnmm64jasbi6l21f2cy99r2cjyl6b4hr8zf2bq22drnz"))))
539 (build-system python-build-system)
543 (modify-phases %standard-phases
544 ;; Generate an installable executable script wrapper.
545 (add-after 'unpack 'patch-setup.py
547 (substitute* "setup.py"
548 (("^(.*)packages=.*" line prefix)
549 (string-append line "\n"
550 prefix "scripts=['scripts/TE.py'],\n")))
553 `(("python-numpy" ,python2-numpy)
554 ("python-matplotlib" ,python2-matplotlib)
555 ("python-scipy" ,python2-scipy)
556 ("python-statsmodels" ,python2-statsmodels)))
558 `(("python-mock" ,python2-mock)
559 ("python-nose" ,python2-nose)))
560 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
561 (synopsis "Detect translation efficiency changes from ribosome footprints")
562 (description "RiboDiff is a statistical tool that detects the protein
563 translational efficiency change from Ribo-Seq (ribosome footprinting) and
564 RNA-Seq data. It uses a generalized linear model to detect genes showing
565 difference in translational profile taking mRNA abundance into account. It
566 facilitates us to decipher the translational regulation that behave
567 independently with transcriptional regulation.")
568 (license license:gpl3+)))
570 (define-public bioawk
577 (url "https://github.com/lh3/bioawk.git")
578 (commit (string-append "v" version))))
579 (file-name (git-file-name name version))
582 "1pxc3zdnirxbf9a0az698hd8xdik7qkhypm7v6hn922x8y9qmspm"))))
583 (build-system gnu-build-system)
589 `(#:tests? #f ; There are no tests to run.
590 ;; Bison must generate files, before other targets can build.
593 (modify-phases %standard-phases
594 (delete 'configure) ; There is no configure phase.
596 (lambda* (#:key outputs #:allow-other-keys)
597 (let* ((out (assoc-ref outputs "out"))
598 (bin (string-append out "/bin"))
599 (man (string-append out "/share/man/man1")))
601 (copy-file "awk.1" (string-append man "/bioawk.1"))
602 (install-file "bioawk" bin))
604 (home-page "https://github.com/lh3/bioawk")
605 (synopsis "AWK with bioinformatics extensions")
606 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
607 support of several common biological data formats, including optionally gzip'ed
608 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
609 also adds a few built-in functions and a command line option to use TAB as the
610 input/output delimiter. When the new functionality is not used, bioawk is
611 intended to behave exactly the same as the original BWK awk.")
612 (license license:x11)))
614 (define-public python-pybedtools
616 (name "python-pybedtools")
620 (uri (pypi-uri "pybedtools" version))
623 "1xl454ijvd4dzfvqgfahad49b49j7qy710fq9xh1rvk42z6x5ssf"))))
624 (build-system python-build-system)
626 `(#:modules ((ice-9 ftw)
630 (guix build python-build-system))
631 ;; See https://github.com/daler/pybedtools/issues/192
633 (modify-phases %standard-phases
634 ;; See https://github.com/daler/pybedtools/issues/261
635 (add-after 'unpack 'disable-broken-tests
637 ;; This test (pybedtools.test.test_scripts.test_venn_mpl) needs a
638 ;; graphical environment.
639 (substitute* "pybedtools/test/test_scripts.py"
640 (("def test_venn_mpl")
641 "def _do_not_test_venn_mpl"))
642 (substitute* "pybedtools/test/test_helpers.py"
643 ;; Requires internet access.
644 (("def test_chromsizes")
645 "def _do_not_test_chromsizes")
646 ;; Broken as a result of the workaround used in the check phase
647 ;; (see: https://github.com/daler/pybedtools/issues/192).
648 (("def test_getting_example_beds")
649 "def _do_not_test_getting_example_beds"))
651 ;; TODO: Remove phase after it's part of PYTHON-BUILD-SYSTEM.
653 ;; Force the Cythonization of C++ files to guard against compilation
655 (add-after 'unpack 'remove-cython-generated-files
657 (let ((cython-sources (map (cut string-drop-right <> 4)
658 (find-files "." "\\.pyx$")))
659 (c/c++-files (find-files "." "\\.(c|cpp|cxx)$")))
660 (define (strip-extension filename)
661 (string-take filename (string-index-right filename #\.)))
662 (define (cythonized? c/c++-file)
663 (member (strip-extension c/c++-file) cython-sources))
664 (for-each delete-file (filter cythonized? c/c++-files))
666 (add-after 'remove-cython-generated-files 'generate-cython-extensions
668 (invoke "python" "setup.py" "cythonize")))
671 (let* ((cwd (getcwd))
672 (build-root-directory (string-append cwd "/build/"))
673 (build (string-append
675 (find (cut string-prefix? "lib" <>)
676 (scandir (string-append
677 build-root-directory)))))
678 (scripts (string-append
680 (find (cut string-prefix? "scripts" <>)
681 (scandir build-root-directory)))))
683 (string-append build ":" (getenv "PYTHONPATH")))
684 ;; Executable scripts such as 'intron_exon_reads.py' must be
685 ;; available in the PATH.
687 (string-append scripts ":" (getenv "PATH"))))
688 ;; The tests need to be run from elsewhere...
689 (mkdir-p "/tmp/test")
690 (copy-recursively "pybedtools/test" "/tmp/test")
691 (with-directory-excursion "/tmp/test"
692 (invoke "pytest")))))))
694 `(("bedtools" ,bedtools)
695 ("samtools" ,samtools)
696 ("python-matplotlib" ,python-matplotlib)
697 ("python-pysam" ,python-pysam)
698 ("python-pyyaml" ,python-pyyaml)))
700 `(("python-numpy" ,python-numpy)
701 ("python-pandas" ,python-pandas)
702 ("python-cython" ,python-cython)
703 ("kentutils" ,kentutils) ; for bedGraphToBigWig
704 ("python-six" ,python-six)
705 ;; For the test suite.
706 ("python-pytest" ,python-pytest)
707 ("python-psutil" ,python-psutil)))
708 (home-page "https://pythonhosted.org/pybedtools/")
709 (synopsis "Python wrapper for BEDtools programs")
711 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
712 which are widely used for genomic interval manipulation or \"genome algebra\".
713 pybedtools extends BEDTools by offering feature-level manipulations from with
715 (license license:gpl2+)))
717 (define-public python2-pybedtools
718 (package-with-python2 python-pybedtools))
720 (define-public python-biom-format
722 (name "python-biom-format")
727 ;; Use GitHub as source because PyPI distribution does not contain
728 ;; test data: https://github.com/biocore/biom-format/issues/693
730 (url "https://github.com/biocore/biom-format.git")
732 (file-name (git-file-name name version))
735 "1rna16lyk5aqhnv0dp77wwaplias93f1vw28ad3jmyw6hwkai05v"))))
736 (build-system python-build-system)
739 (modify-phases %standard-phases
740 (add-after 'unpack 'use-cython
741 (lambda _ (setenv "USE_CYTHON" "1") #t))
742 (add-after 'unpack 'disable-broken-test
744 (substitute* "biom/tests/test_cli/test_validate_table.py"
745 (("^(.+)def test_invalid_hdf5" m indent)
746 (string-append indent
747 "@npt.dec.skipif(True, msg='Guix')\n"
750 (add-before 'reset-gzip-timestamps 'make-files-writable
751 (lambda* (#:key outputs #:allow-other-keys)
752 (let ((out (assoc-ref outputs "out")))
753 (for-each (lambda (file) (chmod file #o644))
754 (find-files out "\\.gz"))
757 `(("python-numpy" ,python-numpy)
758 ("python-scipy" ,python-scipy)
759 ("python-flake8" ,python-flake8)
760 ("python-future" ,python-future)
761 ("python-click" ,python-click)
762 ("python-h5py" ,python-h5py)
763 ("python-pandas" ,python-pandas)))
765 `(("python-cython" ,python-cython)
766 ("python-pytest" ,python-pytest)
767 ("python-pytest-cov" ,python-pytest-cov)
768 ("python-nose" ,python-nose)))
769 (home-page "http://www.biom-format.org")
770 (synopsis "Biological Observation Matrix (BIOM) format utilities")
772 "The BIOM file format is designed to be a general-use format for
773 representing counts of observations e.g. operational taxonomic units, KEGG
774 orthology groups or lipid types, in one or more biological samples
775 e.g. microbiome samples, genomes, metagenomes.")
776 (license license:bsd-3)
777 (properties `((python2-variant . ,(delay python2-biom-format))))))
779 (define-public python2-biom-format
780 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
784 (substitute-keyword-arguments (package-arguments base)
786 `(modify-phases ,phases
787 ;; Do not require the unmaintained pyqi library.
788 (add-after 'unpack 'remove-pyqi
790 (substitute* "setup.py"
791 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
794 (define-public bioperl-minimal
795 (let* ((inputs `(("perl-module-build" ,perl-module-build)
796 ("perl-data-stag" ,perl-data-stag)
797 ("perl-libwww" ,perl-libwww)
798 ("perl-uri" ,perl-uri)))
800 (map (compose package-name cadr)
803 (map (compose package-transitive-target-inputs cadr) inputs))))))
805 (name "bioperl-minimal")
810 (uri (string-append "https://github.com/bioperl/bioperl-live/"
812 (string-map (lambda (c)
818 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
819 (build-system perl-build-system)
822 (modify-phases %standard-phases
824 'install 'wrap-programs
825 (lambda* (#:key outputs #:allow-other-keys)
826 ;; Make sure all executables in "bin" find the required Perl
827 ;; modules at runtime. As the PERL5LIB variable contains also
828 ;; the paths of native inputs, we pick the transitive target
829 ;; inputs from %build-inputs.
830 (let* ((out (assoc-ref outputs "out"))
831 (bin (string-append out "/bin/"))
833 (cons (string-append out "/lib/perl5/site_perl")
835 (assoc-ref %build-inputs name))
836 ',transitive-inputs))
838 (for-each (lambda (file)
840 `("PERL5LIB" ":" prefix (,path))))
841 (find-files bin "\\.pl$"))
845 `(("perl-test-most" ,perl-test-most)))
846 (home-page "https://metacpan.org/release/BioPerl")
847 (synopsis "Bioinformatics toolkit")
849 "BioPerl is the product of a community effort to produce Perl code which
850 is useful in biology. Examples include Sequence objects, Alignment objects
851 and database searching objects. These objects not only do what they are
852 advertised to do in the documentation, but they also interact - Alignment
853 objects are made from the Sequence objects, Sequence objects have access to
854 Annotation and SeqFeature objects and databases, Blast objects can be
855 converted to Alignment objects, and so on. This means that the objects
856 provide a coordinated and extensible framework to do computational biology.")
857 (license license:perl-license))))
859 (define-public python-biopython
861 (name "python-biopython")
865 ;; use PyPi rather than biopython.org to ease updating
866 (uri (pypi-uri "biopython" version))
869 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
870 (build-system python-build-system)
873 (modify-phases %standard-phases
874 (add-before 'check 'set-home
875 ;; Some tests require a home directory to be set.
876 (lambda _ (setenv "HOME" "/tmp") #t)))))
878 `(("python-numpy" ,python-numpy)))
879 (home-page "http://biopython.org/")
880 (synopsis "Tools for biological computation in Python")
882 "Biopython is a set of tools for biological computation including parsers
883 for bioinformatics files into Python data structures; interfaces to common
884 bioinformatics programs; a standard sequence class and tools for performing
885 common operations on them; code to perform data classification; code for
886 dealing with alignments; code making it easy to split up parallelizable tasks
887 into separate processes; and more.")
888 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
890 (define-public python2-biopython
891 (package-with-python2 python-biopython))
893 (define-public python-fastalite
895 (name "python-fastalite")
900 (uri (pypi-uri "fastalite" version))
903 "1qli6pxp77i9xn2wfciq2zaxhl82bdxb33cpzqzj1z25yd036wqj"))))
904 (build-system python-build-system)
906 `(#:tests? #f)) ; Test data is not distributed.
907 (home-page "https://github.com/nhoffman/fastalite")
908 (synopsis "Simplest possible FASTA parser")
909 (description "This library implements a FASTA and a FASTQ parser without
910 relying on a complex dependency tree.")
911 (license license:expat)))
913 (define-public python2-fastalite
914 (package-with-python2 python-fastalite))
916 (define-public bpp-core
917 ;; The last release was in 2014 and the recommended way to install from source
918 ;; is to clone the git repository, so we do this.
919 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
920 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
923 (version (string-append "2.2.0-1." (string-take commit 7)))
927 (url "http://biopp.univ-montp2.fr/git/bpp-core")
929 (file-name (string-append name "-" version "-checkout"))
932 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
933 (build-system cmake-build-system)
935 `(#:parallel-build? #f))
937 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
938 ; compile all of the bpp packages with GCC 5.
939 (home-page "http://biopp.univ-montp2.fr")
940 (synopsis "C++ libraries for Bioinformatics")
942 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
943 analysis, phylogenetics, molecular evolution and population genetics. It is
944 Object Oriented and is designed to be both easy to use and computer efficient.
945 Bio++ intends to help programmers to write computer expensive programs, by
946 providing them a set of re-usable tools.")
947 (license license:cecill-c))))
949 (define-public bpp-phyl
950 ;; The last release was in 2014 and the recommended way to install from source
951 ;; is to clone the git repository, so we do this.
952 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
953 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
956 (version (string-append "2.2.0-1." (string-take commit 7)))
960 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
962 (file-name (string-append name "-" version "-checkout"))
965 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
966 (build-system cmake-build-system)
968 `(#:parallel-build? #f
969 ;; If out-of-source, test data is not copied into the build directory
970 ;; so the tests fail.
971 #:out-of-source? #f))
973 `(("bpp-core" ,bpp-core)
975 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
978 (home-page "http://biopp.univ-montp2.fr")
979 (synopsis "Bio++ phylogenetic Library")
981 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
982 analysis, phylogenetics, molecular evolution and population genetics. This
983 library provides phylogenetics-related modules.")
984 (license license:cecill-c))))
986 (define-public bpp-popgen
987 ;; The last release was in 2014 and the recommended way to install from source
988 ;; is to clone the git repository, so we do this.
989 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
990 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
993 (version (string-append "2.2.0-1." (string-take commit 7)))
997 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
999 (file-name (string-append name "-" version "-checkout"))
1002 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
1003 (build-system cmake-build-system)
1005 `(#:parallel-build? #f
1006 #:tests? #f)) ; There are no tests.
1008 `(("bpp-core" ,bpp-core)
1009 ("bpp-seq" ,bpp-seq)
1011 (home-page "http://biopp.univ-montp2.fr")
1012 (synopsis "Bio++ population genetics library")
1014 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1015 analysis, phylogenetics, molecular evolution and population genetics. This
1016 library provides population genetics-related modules.")
1017 (license license:cecill-c))))
1019 (define-public bpp-seq
1020 ;; The last release was in 2014 and the recommended way to install from source
1021 ;; is to clone the git repository, so we do this.
1022 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1023 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
1026 (version (string-append "2.2.0-1." (string-take commit 7)))
1030 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
1032 (file-name (string-append name "-" version "-checkout"))
1035 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
1036 (build-system cmake-build-system)
1038 `(#:parallel-build? #f
1039 ;; If out-of-source, test data is not copied into the build directory
1040 ;; so the tests fail.
1041 #:out-of-source? #f))
1043 `(("bpp-core" ,bpp-core)
1044 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
1045 (home-page "http://biopp.univ-montp2.fr")
1046 (synopsis "Bio++ sequence library")
1048 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1049 analysis, phylogenetics, molecular evolution and population genetics. This
1050 library provides sequence-related modules.")
1051 (license license:cecill-c))))
1053 (define-public bppsuite
1054 ;; The last release was in 2014 and the recommended way to install from source
1055 ;; is to clone the git repository, so we do this.
1056 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1057 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
1060 (version (string-append "2.2.0-1." (string-take commit 7)))
1064 (url "http://biopp.univ-montp2.fr/git/bppsuite")
1066 (file-name (string-append name "-" version "-checkout"))
1069 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
1070 (build-system cmake-build-system)
1072 `(#:parallel-build? #f
1073 #:tests? #f)) ; There are no tests.
1077 ("texinfo" ,texinfo)))
1079 `(("bpp-core" ,bpp-core)
1080 ("bpp-seq" ,bpp-seq)
1081 ("bpp-phyl" ,bpp-phyl)
1082 ("bpp-phyl" ,bpp-popgen)
1084 (home-page "http://biopp.univ-montp2.fr")
1085 (synopsis "Bioinformatics tools written with the Bio++ libraries")
1087 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1088 analysis, phylogenetics, molecular evolution and population genetics. This
1089 package provides command line tools using the Bio++ library.")
1090 (license license:cecill-c))))
1092 (define-public blast+
1099 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
1100 version "/ncbi-blast-" version "+-src.tar.gz"))
1103 "15n937pw5aqmyfjb6l387d18grqbb96l63d5xj4l7yyh0zbf2405"))
1104 (patches (search-patches "blast+-fix-makefile.patch"))
1105 (modules '((guix build utils)))
1108 ;; Remove bundled bzip2, zlib and pcre.
1109 (delete-file-recursively "c++/src/util/compress/bzip2")
1110 (delete-file-recursively "c++/src/util/compress/zlib")
1111 (delete-file-recursively "c++/src/util/regexp")
1112 (substitute* "c++/src/util/compress/Makefile.in"
1113 (("bzip2 zlib api") "api"))
1114 ;; Remove useless msbuild directory
1115 (delete-file-recursively
1116 "c++/src/build-system/project_tree_builder/msbuild")
1118 (build-system gnu-build-system)
1120 `(;; There are two(!) tests for this massive library, and both fail with
1121 ;; "unparsable timing stats".
1122 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
1123 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
1126 #:parallel-build? #f ; not supported
1128 (modify-phases %standard-phases
1129 (add-before 'configure 'set-HOME
1130 ;; $HOME needs to be set at some point during the configure phase
1131 (lambda _ (setenv "HOME" "/tmp") #t))
1132 (add-after 'unpack 'enter-dir
1133 (lambda _ (chdir "c++") #t))
1134 (add-after 'enter-dir 'fix-build-system
1136 (define (which* cmd)
1137 (cond ((string=? cmd "date")
1138 ;; make call to "date" deterministic
1143 (format (current-error-port)
1144 "WARNING: Unable to find absolute path for ~s~%"
1148 ;; Rewrite hardcoded paths to various tools
1149 (substitute* (append '("src/build-system/configure.ac"
1150 "src/build-system/configure"
1151 "src/build-system/helpers/run_with_lock.c"
1152 "scripts/common/impl/if_diff.sh"
1153 "scripts/common/impl/run_with_lock.sh"
1154 "src/build-system/Makefile.configurables.real"
1155 "src/build-system/Makefile.in.top"
1156 "src/build-system/Makefile.meta.gmake=no"
1157 "src/build-system/Makefile.meta.in"
1158 "src/build-system/Makefile.meta_l"
1159 "src/build-system/Makefile.meta_p"
1160 "src/build-system/Makefile.meta_r"
1161 "src/build-system/Makefile.mk.in"
1162 "src/build-system/Makefile.requirements"
1163 "src/build-system/Makefile.rules_with_autodep.in")
1164 (find-files "scripts/common/check" "\\.sh$"))
1165 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1166 (or (which* cmd) all)))
1168 (substitute* (find-files "src/build-system" "^config.*")
1169 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1172 ;; rewrite "/var/tmp" in check script
1173 (substitute* "scripts/common/check/check_make_unix.sh"
1174 (("/var/tmp") "/tmp"))
1176 ;; do not reset PATH
1177 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1179 (("action=/bin/") "action=")
1180 (("export PATH") ":"))
1183 (lambda* (#:key inputs outputs #:allow-other-keys)
1184 (let ((out (assoc-ref outputs "out"))
1185 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1186 (include (string-append (assoc-ref outputs "include")
1187 "/include/ncbi-tools++")))
1188 ;; The 'configure' script doesn't recognize things like
1189 ;; '--enable-fast-install'.
1190 (invoke "./configure.orig"
1191 (string-append "--with-build-root=" (getcwd) "/build")
1192 (string-append "--prefix=" out)
1193 (string-append "--libdir=" lib)
1194 (string-append "--includedir=" include)
1195 (string-append "--with-bz2="
1196 (assoc-ref inputs "bzip2"))
1197 (string-append "--with-z="
1198 (assoc-ref inputs "zlib"))
1199 (string-append "--with-pcre="
1200 (assoc-ref inputs "pcre"))
1201 ;; Each library is built twice by default, once
1202 ;; with "-static" in its name, and again
1207 (outputs '("out" ; 21 MB
1215 ("python" ,python-wrapper)))
1218 (home-page "http://blast.ncbi.nlm.nih.gov")
1219 (synopsis "Basic local alignment search tool")
1221 "BLAST is a popular method of performing a DNA or protein sequence
1222 similarity search, using heuristics to produce results quickly. It also
1223 calculates an “expect value” that estimates how many matches would have
1224 occurred at a given score by chance, which can aid a user in judging how much
1225 confidence to have in an alignment.")
1226 ;; Most of the sources are in the public domain, with the following
1229 ;; * ./c++/include/util/bitset/
1230 ;; * ./c++/src/html/ncbi_menu*.js
1232 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1234 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1236 ;; * ./c++/src/corelib/teamcity_*
1237 (license (list license:public-domain
1243 (define-public bless
1249 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1253 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1254 (modules '((guix build utils)))
1257 ;; Remove bundled boost, pigz, zlib, and .git directory
1258 ;; FIXME: also remove bundled sources for murmurhash3 and
1259 ;; kmc once packaged.
1260 (delete-file-recursively "boost")
1261 (delete-file-recursively "pigz")
1262 (delete-file-recursively "google-sparsehash")
1263 (delete-file-recursively "zlib")
1264 (delete-file-recursively ".git")
1266 (build-system gnu-build-system)
1268 '(#:tests? #f ;no "check" target
1270 (list (string-append "ZLIB="
1271 (assoc-ref %build-inputs "zlib:static")
1273 (string-append "LDFLAGS="
1274 (string-join '("-lboost_filesystem"
1281 (modify-phases %standard-phases
1282 (add-after 'unpack 'do-not-build-bundled-pigz
1283 (lambda* (#:key inputs outputs #:allow-other-keys)
1284 (substitute* "Makefile"
1285 (("cd pigz/pigz-2.3.3; make") ""))
1287 (add-after 'unpack 'patch-paths-to-executables
1288 (lambda* (#:key inputs outputs #:allow-other-keys)
1289 (substitute* "parse_args.cpp"
1290 (("kmc_binary = .*")
1291 (string-append "kmc_binary = \""
1292 (assoc-ref outputs "out")
1294 (("pigz_binary = .*")
1295 (string-append "pigz_binary = \""
1296 (assoc-ref inputs "pigz")
1300 (lambda* (#:key outputs #:allow-other-keys)
1301 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1302 (for-each (lambda (file)
1303 (install-file file bin))
1304 '("bless" "kmc/bin/kmc"))
1306 (delete 'configure))))
1310 `(("openmpi" ,openmpi)
1312 ("sparsehash" ,sparsehash)
1314 ("zlib:static" ,zlib "static")
1316 (supported-systems '("x86_64-linux"))
1317 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1318 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1320 "@dfn{Bloom-filter-based error correction solution for high-throughput
1321 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1322 correction tool for genomic reads produced by @dfn{Next-generation
1323 sequencing} (NGS). BLESS produces accurate correction results with much less
1324 memory compared with previous solutions and is also able to tolerate a higher
1325 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1326 errors at the end of reads.")
1327 (license license:gpl3+)))
1329 (define-public bowtie
1336 (url "https://github.com/BenLangmead/bowtie2.git")
1337 (commit (string-append "v" version))))
1338 (file-name (git-file-name name version))
1341 "1zl3cf327y2p7p03cavymbh7b00djc7lncfaqih33n96iy9q8ibp"))
1342 (modules '((guix build utils)))
1345 (substitute* "Makefile"
1346 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1347 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1348 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
1350 (build-system gnu-build-system)
1355 (string-append "prefix=" (assoc-ref %outputs "out")))
1357 (modify-phases %standard-phases
1362 "scripts/test/simple_tests.pl"
1363 "--bowtie2=./bowtie2"
1364 "--bowtie2-build=./bowtie2-build")
1369 ("python" ,python-wrapper)))
1372 ("perl-clone" ,perl-clone)
1373 ("perl-test-deep" ,perl-test-deep)
1374 ("perl-test-simple" ,perl-test-simple)))
1375 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1376 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1378 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1379 reads to long reference sequences. It is particularly good at aligning reads
1380 of about 50 up to 100s or 1,000s of characters, and particularly good at
1381 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1382 genome with an FM Index to keep its memory footprint small: for the human
1383 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1384 gapped, local, and paired-end alignment modes.")
1385 (supported-systems '("x86_64-linux"))
1386 (license license:gpl3+)))
1388 (define-public bowtie1
1394 (uri (string-append "mirror://sourceforge/bowtie-bio/bowtie/"
1395 version "/bowtie-" version "-src.zip"))
1398 "1jl2cj9bz8lwz8dwnxbycn8yp8g4kky62fkcxifyf1ri0y6n2vc0"))
1399 (modules '((guix build utils)))
1401 '(substitute* "Makefile"
1402 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1403 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1404 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1405 (build-system gnu-build-system)
1407 '(#:tests? #f ; no "check" target
1410 (string-append "prefix=" (assoc-ref %outputs "out")))
1412 (modify-phases %standard-phases
1413 (delete 'configure))))
1417 (supported-systems '("x86_64-linux"))
1418 (home-page "http://bowtie-bio.sourceforge.net/index.shtml")
1419 (synopsis "Fast aligner for short nucleotide sequence reads")
1421 "Bowtie is a fast, memory-efficient short read aligner. It aligns short
1422 DNA sequences (reads) to the human genome at a rate of over 25 million 35-bp
1423 reads per hour. Bowtie indexes the genome with a Burrows-Wheeler index to
1424 keep its memory footprint small: typically about 2.2 GB for the human
1425 genome (2.9 GB for paired-end).")
1426 (license license:artistic2.0)))
1428 (define-public tophat
1435 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1439 "19add02kv2xhd6ihd779dr7x35ggym3jqr0m5c4315i1yfb0p11p"))
1440 (modules '((guix build utils)))
1443 ;; Remove bundled SeqAn and samtools
1444 (delete-file-recursively "src/SeqAn-1.4.2")
1445 (delete-file-recursively "src/samtools-0.1.18")
1447 (build-system gnu-build-system)
1449 '(#:parallel-build? #f ; not supported
1451 (modify-phases %standard-phases
1452 (add-after 'unpack 'use-system-samtools
1453 (lambda* (#:key inputs #:allow-other-keys)
1454 (substitute* "src/Makefile.in"
1455 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1456 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1457 (("SAMPROG = samtools_0\\.1\\.18") "")
1458 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1459 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1460 (substitute* '("src/common.cpp"
1462 (("samtools_0.1.18") (which "samtools")))
1463 (substitute* '("src/common.h"
1464 "src/bam2fastx.cpp")
1465 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1466 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1467 (substitute* '("src/bwt_map.h"
1469 "src/align_status.h")
1470 (("#include <bam.h>") "#include <samtools/bam.h>")
1471 (("#include <sam.h>") "#include <samtools/sam.h>"))
1476 ("samtools" ,samtools-0.1)
1477 ("ncurses" ,ncurses)
1478 ("python" ,python-2)
1481 ("seqan" ,seqan-1)))
1482 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1483 (synopsis "Spliced read mapper for RNA-Seq data")
1485 "TopHat is a fast splice junction mapper for nucleotide sequence
1486 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1487 mammalian-sized genomes using the ultra high-throughput short read
1488 aligner Bowtie, and then analyzes the mapping results to identify
1489 splice junctions between exons.")
1490 ;; TopHat is released under the Boost Software License, Version 1.0
1491 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1492 (license license:boost1.0)))
1501 "https://github.com/lh3/bwa/releases/download/v"
1502 version "/bwa-" version ".tar.bz2"))
1505 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1506 (build-system gnu-build-system)
1508 '(#:tests? #f ;no "check" target
1510 (modify-phases %standard-phases
1512 (lambda* (#:key outputs #:allow-other-keys)
1513 (let ((bin (string-append
1514 (assoc-ref outputs "out") "/bin"))
1516 (assoc-ref outputs "out") "/share/doc/bwa"))
1518 (assoc-ref outputs "out") "/share/man/man1")))
1519 (install-file "bwa" bin)
1520 (install-file "README.md" doc)
1521 (install-file "bwa.1" man))
1523 ;; no "configure" script
1524 (delete 'configure))))
1525 (inputs `(("zlib" ,zlib)))
1526 ;; Non-portable SSE instructions are used so building fails on platforms
1527 ;; other than x86_64.
1528 (supported-systems '("x86_64-linux"))
1529 (home-page "http://bio-bwa.sourceforge.net/")
1530 (synopsis "Burrows-Wheeler sequence aligner")
1532 "BWA is a software package for mapping low-divergent sequences against a
1533 large reference genome, such as the human genome. It consists of three
1534 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1535 designed for Illumina sequence reads up to 100bp, while the rest two for
1536 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1537 features such as long-read support and split alignment, but BWA-MEM, which is
1538 the latest, is generally recommended for high-quality queries as it is faster
1539 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1540 70-100bp Illumina reads.")
1541 (license license:gpl3+)))
1543 (define-public bwa-pssm
1544 (package (inherit bwa)
1550 (url "https://github.com/pkerpedjiev/bwa-pssm.git")
1552 (file-name (git-file-name name version))
1555 "076c4q0cdqz8jgylb067y9zmvxglppnzi3qiscn0xiypgc6lgb5r"))))
1556 (build-system gnu-build-system)
1561 (home-page "http://bwa-pssm.binf.ku.dk/")
1562 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1564 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1565 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1566 existing aligners it is fast and sensitive. Unlike most other aligners,
1567 however, it is also adaptible in the sense that one can direct the alignment
1568 based on known biases within the data set. It is coded as a modification of
1569 the original BWA alignment program and shares the genome index structure as
1570 well as many of the command line options.")
1571 (license license:gpl3+)))
1573 (define-public python-bx-python
1575 (name "python-bx-python")
1579 (uri (pypi-uri "bx-python" version))
1582 "11kksg2rbzihpmcid823xvg42xi88m7sz58rzk29abybkxy0rszs"))))
1583 (build-system python-build-system)
1584 ;; Tests fail because test data are not included
1585 (arguments '(#:tests? #f))
1587 `(("python-numpy" ,python-numpy)
1588 ("python-six" ,python-six)))
1592 `(("python-lzo" ,python-lzo)
1593 ("python-nose" ,python-nose)
1594 ("python-cython" ,python-cython)))
1595 (home-page "https://github.com/bxlab/bx-python")
1596 (synopsis "Tools for manipulating biological data")
1598 "bx-python provides tools for manipulating biological data, particularly
1599 multiple sequence alignments.")
1600 (license license:expat)))
1602 (define-public python2-bx-python
1603 (package-with-python2 python-bx-python))
1605 (define-public python-pysam
1607 (name "python-pysam")
1611 ;; Test data is missing on PyPi.
1613 (url "https://github.com/pysam-developers/pysam.git")
1614 (commit (string-append "v" version))))
1615 (file-name (git-file-name name version))
1618 "1vj367w6xbn9bpmksm162l1aipf7cj97h1q83y7jcpm33ihwpf7x"))
1619 (modules '((guix build utils)))
1621 ;; Drop bundled htslib. TODO: Also remove samtools
1623 (delete-file-recursively "htslib")
1625 (build-system python-build-system)
1627 `(#:modules ((ice-9 ftw)
1629 (guix build python-build-system)
1632 (modify-phases %standard-phases
1633 (add-before 'build 'set-flags
1634 (lambda* (#:key inputs #:allow-other-keys)
1635 (setenv "HTSLIB_MODE" "external")
1636 (setenv "HTSLIB_LIBRARY_DIR"
1637 (string-append (assoc-ref inputs "htslib") "/lib"))
1638 (setenv "HTSLIB_INCLUDE_DIR"
1639 (string-append (assoc-ref inputs "htslib") "/include"))
1640 (setenv "LDFLAGS" "-lncurses")
1641 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1644 (lambda* (#:key inputs outputs #:allow-other-keys)
1645 ;; This file contains tests that require a connection to the
1647 (delete-file "tests/tabix_test.py")
1648 ;; FIXME: This test fails
1649 (delete-file "tests/AlignmentFile_test.py")
1650 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1651 (setenv "PYTHONPATH"
1653 (getenv "PYTHONPATH")
1654 ":" (getcwd) "/build/"
1655 (car (scandir "build"
1656 (negate (cut string-prefix? "." <>))))))
1657 ;; Step out of source dir so python does not import from CWD.
1658 (with-directory-excursion "tests"
1659 (setenv "HOME" "/tmp")
1660 (invoke "make" "-C" "pysam_data")
1661 (invoke "make" "-C" "cbcf_data")
1662 ;; Running nosetests without explicitly asking for a single
1663 ;; process leads to a crash. Running with multiple processes
1664 ;; fails because the tests are not designed to run in parallel.
1666 ;; FIXME: tests keep timing out on some systems.
1667 (invoke "nosetests" "-v" "--processes" "1")))))))
1669 `(("htslib" ,htslib))) ; Included from installed header files.
1671 `(("ncurses" ,ncurses)
1675 `(("python-cython" ,python-cython)
1676 ;; Dependencies below are are for tests only.
1677 ("samtools" ,samtools)
1678 ("bcftools" ,bcftools)
1679 ("python-nose" ,python-nose)))
1680 (home-page "https://github.com/pysam-developers/pysam")
1681 (synopsis "Python bindings to the SAMtools C API")
1683 "Pysam is a Python module for reading and manipulating files in the
1684 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1685 also includes an interface for tabix.")
1686 (license license:expat)))
1688 (define-public python2-pysam
1689 (package-with-python2 python-pysam))
1691 (define-public python-twobitreader
1693 (name "python-twobitreader")
1698 (url "https://github.com/benjschiller/twobitreader")
1700 (file-name (git-file-name name version))
1703 "1qbxvv1h58cismbk1anpjrkpghsaiy64a11ir3lhy6qch6xf8n62"))))
1704 (build-system python-build-system)
1705 ;; Tests are not included
1706 (arguments '(#:tests? #f))
1708 `(("python-sphinx" ,python-sphinx)))
1709 (home-page "https://github.com/benjschiller/twobitreader")
1710 (synopsis "Python library for reading .2bit files")
1712 "twobitreader is a Python library for reading .2bit files as used by the
1713 UCSC genome browser.")
1714 (license license:artistic2.0)))
1716 (define-public python2-twobitreader
1717 (package-with-python2 python-twobitreader))
1719 (define-public python-plastid
1721 (name "python-plastid")
1725 (uri (pypi-uri "plastid" version))
1728 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1729 (build-system python-build-system)
1731 ;; Some test files are not included.
1734 `(("python-numpy" ,python-numpy)
1735 ("python-scipy" ,python-scipy)
1736 ("python-pandas" ,python-pandas)
1737 ("python-pysam" ,python-pysam)
1738 ("python-matplotlib" ,python-matplotlib)
1739 ("python-biopython" ,python-biopython)
1740 ("python-twobitreader" ,python-twobitreader)
1741 ("python-termcolor" ,python-termcolor)))
1743 `(("python-cython" ,python-cython)
1744 ("python-nose" ,python-nose)))
1745 (home-page "https://github.com/joshuagryphon/plastid")
1746 (synopsis "Python library for genomic analysis")
1748 "plastid is a Python library for genomic analysis – in particular,
1749 high-throughput sequencing data – with an emphasis on simplicity.")
1750 (license license:bsd-3)))
1752 (define-public python2-plastid
1753 (package-with-python2 python-plastid))
1755 (define-public cd-hit
1761 (uri (string-append "https://github.com/weizhongli/cdhit"
1762 "/releases/download/V" version
1764 "-2017-0621-source.tar.gz"))
1767 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
1768 (build-system gnu-build-system)
1770 `(#:tests? #f ; there are no tests
1772 ;; Executables are copied directly to the PREFIX.
1773 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin")
1774 ;; Support longer sequences (e.g. Pacbio sequences)
1777 (modify-phases %standard-phases
1778 ;; No "configure" script
1780 ;; Remove sources of non-determinism
1781 (add-after 'unpack 'be-timeless
1783 (substitute* "cdhit-utility.c++"
1784 ((" \\(built on \" __DATE__ \"\\)") ""))
1785 (substitute* "cdhit-common.c++"
1786 (("__DATE__") "\"0\"")
1787 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1789 ;; The "install" target does not create the target directory.
1790 (add-before 'install 'create-target-dir
1791 (lambda* (#:key outputs #:allow-other-keys)
1792 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1796 (home-page "http://weizhongli-lab.org/cd-hit/")
1797 (synopsis "Cluster and compare protein or nucleotide sequences")
1799 "CD-HIT is a program for clustering and comparing protein or nucleotide
1800 sequences. CD-HIT is designed to be fast and handle extremely large
1802 ;; The manual says: "It can be copied under the GNU General Public License
1803 ;; version 2 (GPLv2)."
1804 (license license:gpl2)))
1806 (define-public clipper
1813 (url "https://github.com/YeoLab/clipper.git")
1815 (file-name (git-file-name name version))
1818 "0fja1rj84wp9vpj8rxpj3n8zqzcqq454m904yp9as1w4phccirjb"))
1819 (modules '((guix build utils)))
1822 ;; remove unnecessary setup dependency
1823 (substitute* "setup.py"
1824 (("setup_requires = .*") ""))
1826 (build-system python-build-system)
1828 `(#:python ,python-2 ; only Python 2 is supported
1830 (modify-phases %standard-phases
1831 ;; This is fixed in upstream commit
1832 ;; f6c2990198f906bf97730d95695b4bd5a6d01ddb.
1833 (add-after 'unpack 'fix-typo
1835 (substitute* "clipper/src/readsToWiggle.pyx"
1839 `(("htseq" ,python2-htseq)
1840 ("python-pybedtools" ,python2-pybedtools)
1841 ("python-cython" ,python2-cython)
1842 ("python-scikit-learn" ,python2-scikit-learn)
1843 ("python-matplotlib" ,python2-matplotlib)
1844 ("python-pandas" ,python2-pandas)
1845 ("python-pysam" ,python2-pysam)
1846 ("python-numpy" ,python2-numpy)
1847 ("python-scipy" ,python2-scipy)))
1849 `(("python-mock" ,python2-mock) ; for tests
1850 ("python-nose" ,python2-nose) ; for tests
1851 ("python-pytz" ,python2-pytz))) ; for tests
1852 (home-page "https://github.com/YeoLab/clipper")
1853 (synopsis "CLIP peak enrichment recognition")
1855 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1856 (license license:gpl2)))
1858 (define-public codingquarry
1860 (name "codingquarry")
1865 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1869 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1870 (build-system gnu-build-system)
1872 '(#:tests? #f ; no "check" target
1874 (modify-phases %standard-phases
1877 (lambda* (#:key outputs #:allow-other-keys)
1878 (let* ((out (assoc-ref outputs "out"))
1879 (bin (string-append out "/bin"))
1880 (doc (string-append out "/share/doc/codingquarry")))
1881 (install-file "INSTRUCTIONS.pdf" doc)
1882 (copy-recursively "QuarryFiles"
1883 (string-append out "/QuarryFiles"))
1884 (install-file "CodingQuarry" bin)
1885 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin))
1887 (inputs `(("openmpi" ,openmpi)))
1888 (native-search-paths
1889 (list (search-path-specification
1890 (variable "QUARRY_PATH")
1891 (files '("QuarryFiles")))))
1892 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1893 (synopsis "Fungal gene predictor")
1894 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1895 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1896 (home-page "https://sourceforge.net/projects/codingquarry/")
1897 (license license:gpl3+)))
1899 (define-public couger
1906 "http://couger.oit.duke.edu/static/assets/COUGER"
1910 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1911 (build-system gnu-build-system)
1915 (modify-phases %standard-phases
1920 (lambda* (#:key outputs #:allow-other-keys)
1921 (let* ((out (assoc-ref outputs "out"))
1922 (bin (string-append out "/bin")))
1923 (copy-recursively "src" (string-append out "/src"))
1925 ;; Add "src" directory to module lookup path.
1926 (substitute* "couger"
1928 (string-append "import sys\nsys.path.append(\""
1929 out "\")\nfrom argparse")))
1930 (install-file "couger" bin))
1933 'install 'wrap-program
1934 (lambda* (#:key inputs outputs #:allow-other-keys)
1935 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1936 (let* ((out (assoc-ref outputs "out"))
1937 (path (getenv "PYTHONPATH")))
1938 (wrap-program (string-append out "/bin/couger")
1939 `("PYTHONPATH" ":" prefix (,path))))
1942 `(("python" ,python-2)
1943 ("python2-pillow" ,python2-pillow)
1944 ("python2-numpy" ,python2-numpy)
1945 ("python2-scipy" ,python2-scipy)
1946 ("python2-matplotlib" ,python2-matplotlib)))
1948 `(("r-minimal" ,r-minimal)
1950 ("randomjungle" ,randomjungle)))
1952 `(("unzip" ,unzip)))
1953 (home-page "http://couger.oit.duke.edu")
1954 (synopsis "Identify co-factors in sets of genomic regions")
1956 "COUGER can be applied to any two sets of genomic regions bound by
1957 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1958 putative co-factors that provide specificity to each TF. The framework
1959 determines the genomic targets uniquely-bound by each TF, and identifies a
1960 small set of co-factors that best explain the in vivo binding differences
1961 between the two TFs.
1963 COUGER uses classification algorithms (support vector machines and random
1964 forests) with features that reflect the DNA binding specificities of putative
1965 co-factors. The features are generated either from high-throughput TF-DNA
1966 binding data (from protein binding microarray experiments), or from large
1967 collections of DNA motifs.")
1968 (license license:gpl3+)))
1970 (define-public clustal-omega
1972 (name "clustal-omega")
1976 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
1980 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
1981 (build-system gnu-build-system)
1983 `(("argtable" ,argtable)))
1984 (home-page "http://www.clustal.org/omega/")
1985 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1987 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1988 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1989 of handling data-sets of hundreds of thousands of sequences in reasonable
1991 (license license:gpl2+)))
1993 (define-public crossmap
1999 (uri (pypi-uri "CrossMap" version))
2002 "1byhclrqnqpvc1rqkfh4jwj6yhn0x9y7jk47i0qcjlhk0pjkw92p"))))
2003 (build-system python-build-system)
2004 (arguments `(#:python ,python-2))
2006 `(("python-bx-python" ,python2-bx-python)
2007 ("python-numpy" ,python2-numpy)
2008 ("python-pysam" ,python2-pysam)
2011 `(("python-cython" ,python2-cython)
2012 ("python-nose" ,python2-nose)))
2013 (home-page "http://crossmap.sourceforge.net/")
2014 (synopsis "Convert genome coordinates between assemblies")
2016 "CrossMap is a program for conversion of genome coordinates or annotation
2017 files between different genome assemblies. It supports most commonly used
2018 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
2019 (license license:gpl2+)))
2021 (define-public python-dnaio
2023 (name "python-dnaio")
2028 (uri (pypi-uri "dnaio" version))
2031 "0f16m7hdlm0fz1n7y5asy0v9ghyrq17ni1p9iybq22ddzyd49r27"))))
2032 (build-system python-build-system)
2034 `(("python-cython" ,python-cython)
2035 ("python-pytest" ,python-pytest)
2036 ("python-xopen" ,python-xopen)))
2037 (home-page "https://github.com/marcelm/dnaio/")
2038 (synopsis "Read FASTA and FASTQ files efficiently")
2040 "dnaio is a Python library for fast parsing of FASTQ and also FASTA
2041 files. The code was previously part of the cutadapt tool.")
2042 (license license:expat)))
2044 (define-public cutadapt
2051 (url "https://github.com/marcelm/cutadapt.git")
2052 (commit (string-append "v" version))))
2053 (file-name (git-file-name name version))
2056 "08bbfwyc0kvcd95jf2s95xiv9s3cbsxm39ydl0qck3fw3cviwxpg"))))
2057 (build-system python-build-system)
2059 `(("python-dnaio" ,python-dnaio)
2060 ("python-xopen" ,python-xopen)))
2062 `(("python-cython" ,python-cython)
2063 ("python-pytest" ,python-pytest)))
2064 (home-page "https://cutadapt.readthedocs.io/en/stable/")
2065 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
2067 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
2068 other types of unwanted sequence from high-throughput sequencing reads.")
2069 (license license:expat)))
2071 (define-public libbigwig
2078 (url "https://github.com/dpryan79/libBigWig.git")
2080 (file-name (string-append name "-" version "-checkout"))
2083 "0h2smg24v5srdcqzrmz2g23cmlp4va465mgx8r2z571sfz8pv454"))))
2084 (build-system gnu-build-system)
2086 `(#:test-target "test"
2087 #:tests? #f ; tests require access to the web
2090 (string-append "prefix=" (assoc-ref %outputs "out")))
2092 (modify-phases %standard-phases
2093 (delete 'configure))))
2098 `(("doxygen" ,doxygen)
2100 ("python" ,python-2)))
2101 (home-page "https://github.com/dpryan79/libBigWig")
2102 (synopsis "C library for handling bigWig files")
2104 "This package provides a C library for parsing local and remote BigWig
2106 (license license:expat)))
2108 (define-public python-pybigwig
2110 (name "python-pybigwig")
2114 (uri (pypi-uri "pyBigWig" version))
2117 "00w4kfnm2c5l7wdwr2nj1z5djv8kzgf7h1zhsgv6njff1rwr26g0"))
2118 (modules '((guix build utils)))
2121 ;; Delete bundled libBigWig sources
2122 (delete-file-recursively "libBigWig")
2124 (build-system python-build-system)
2127 (modify-phases %standard-phases
2128 (add-after 'unpack 'link-with-libBigWig
2129 (lambda* (#:key inputs #:allow-other-keys)
2130 (substitute* "setup.py"
2131 (("libs=\\[") "libs=[\"BigWig\", "))
2134 `(("python-numpy" ,python-numpy)))
2136 `(("libbigwig" ,libbigwig)
2139 (home-page "https://github.com/dpryan79/pyBigWig")
2140 (synopsis "Access bigWig files in Python using libBigWig")
2142 "This package provides Python bindings to the libBigWig library for
2143 accessing bigWig files.")
2144 (license license:expat)))
2146 (define-public python2-pybigwig
2147 (package-with-python2 python-pybigwig))
2149 (define-public python-dendropy
2151 (name "python-dendropy")
2156 ;; Source from GitHub so that tests are included.
2158 (url "https://github.com/jeetsukumaran/DendroPy.git")
2159 (commit (string-append "v" version))))
2160 (file-name (git-file-name name version))
2163 "097hfyv2kaf4x92i4rjx0paw2cncxap48qivv8zxng4z7nhid0x9"))))
2164 (build-system python-build-system)
2165 (home-page "http://packages.python.org/DendroPy/")
2166 (synopsis "Library for phylogenetics and phylogenetic computing")
2168 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
2169 writing, simulation, processing and manipulation of phylogenetic
2170 trees (phylogenies) and characters.")
2171 (license license:bsd-3)))
2173 (define-public python2-dendropy
2174 (let ((base (package-with-python2 python-dendropy)))
2179 (modify-phases %standard-phases
2180 (add-after 'unpack 'remove-failing-test
2182 ;; This test fails when the full test suite is run, as documented
2183 ;; at https://github.com/jeetsukumaran/DendroPy/issues/74
2184 (substitute* "tests/test_dataio_nexml_reader_tree_list.py"
2185 (("test_collection_comments_and_annotations")
2186 "do_not_test_collection_comments_and_annotations"))
2188 ,@(package-arguments base))))))
2190 (define-public python-py2bit
2192 (name "python-py2bit")
2197 (uri (pypi-uri "py2bit" version))
2200 "1vw2nvw1yrl7ikkqsqs1pg239yr5nspvd969r1x9arms1k25a1a5"))))
2201 (build-system python-build-system)
2202 (home-page "https://github.com/dpryan79/py2bit")
2203 (synopsis "Access 2bit files using lib2bit")
2205 "This package provides Python bindings for lib2bit to access 2bit files
2207 (license license:expat)))
2209 (define-public deeptools
2216 (url "https://github.com/deeptools/deepTools.git")
2218 (file-name (git-file-name name version))
2221 "1vggnf52g6q2vifdl4cyi7s2fnfqq0ky2zrkj5zv2qfzsc3p3siw"))))
2222 (build-system python-build-system)
2225 (modify-phases %standard-phases
2226 ;; This phase fails, but it's not needed.
2227 (delete 'reset-gzip-timestamps))))
2229 `(("python-plotly" ,python-plotly)
2230 ("python-scipy" ,python-scipy)
2231 ("python-numpy" ,python-numpy)
2232 ("python-numpydoc" ,python-numpydoc)
2233 ("python-matplotlib" ,python-matplotlib)
2234 ("python-pysam" ,python-pysam)
2235 ("python-py2bit" ,python-py2bit)
2236 ("python-pybigwig" ,python-pybigwig)))
2238 `(("python-mock" ,python-mock) ;for tests
2239 ("python-nose" ,python-nose) ;for tests
2240 ("python-pytz" ,python-pytz))) ;for tests
2241 (home-page "https://github.com/deeptools/deepTools")
2242 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2244 "DeepTools addresses the challenge of handling the large amounts of data
2245 that are now routinely generated from DNA sequencing centers. To do so,
2246 deepTools contains useful modules to process the mapped reads data to create
2247 coverage files in standard bedGraph and bigWig file formats. By doing so,
2248 deepTools allows the creation of normalized coverage files or the comparison
2249 between two files (for example, treatment and control). Finally, using such
2250 normalized and standardized files, multiple visualizations can be created to
2251 identify enrichments with functional annotations of the genome.")
2252 (license license:gpl3+)))
2254 (define-public delly
2261 (url "https://github.com/dellytools/delly.git")
2262 (commit (string-append "v" version))))
2263 (file-name (git-file-name name version))
2265 (base32 "034jqsxswy9gqdh2zkgc1js99qkv75ks4xvzgmh0284sraagv61z"))
2266 (modules '((guix build utils)))
2269 (delete-file-recursively "src/htslib")
2271 (build-system gnu-build-system)
2273 `(#:tests? #f ; There are no tests to run.
2275 (list "PARALLEL=1" ; Allow parallel execution at run-time.
2276 (string-append "prefix=" (assoc-ref %outputs "out")))
2278 (modify-phases %standard-phases
2279 (delete 'configure) ; There is no configure phase.
2280 (add-after 'install 'install-templates
2281 (lambda* (#:key outputs #:allow-other-keys)
2282 (let ((templates (string-append (assoc-ref outputs "out")
2283 "/share/delly/templates")))
2285 (copy-recursively "excludeTemplates" templates)
2292 (home-page "https://github.com/dellytools/delly")
2293 (synopsis "Integrated structural variant prediction method")
2294 (description "Delly is an integrated structural variant prediction method
2295 that can discover and genotype deletions, tandem duplications, inversions and
2296 translocations at single-nucleotide resolution in short-read massively parallel
2297 sequencing data. It uses paired-ends and split-reads to sensitively and
2298 accurately delineate genomic rearrangements throughout the genome.")
2299 (license license:gpl3+)))
2301 (define-public diamond
2308 (url "https://github.com/bbuchfink/diamond.git")
2309 (commit (string-append "v" version))))
2310 (file-name (git-file-name name version))
2313 "0bky78v79g3wmdpsd706cscckgw1v09fg8vdd0z8z0d5b97aj9zl"))))
2314 (build-system cmake-build-system)
2316 '(#:tests? #f ; no "check" target
2318 (modify-phases %standard-phases
2319 (add-after 'unpack 'remove-native-compilation
2321 (substitute* "CMakeLists.txt" (("-march=native") ""))
2325 (home-page "https://github.com/bbuchfink/diamond")
2326 (synopsis "Accelerated BLAST compatible local sequence aligner")
2328 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2329 translated DNA query sequences against a protein reference database (BLASTP
2330 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2331 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2332 data and settings.")
2333 (license license:agpl3+)))
2335 (define-public discrover
2343 (url "https://github.com/maaskola/discrover.git")
2345 (file-name (git-file-name name version))
2348 "173fwi2vb6a5kp406hm3jj6j7v4whww796f2qcygp4rpvamh307y"))))
2349 (build-system cmake-build-system)
2351 `(#:tests? #f ; there are no tests
2353 (modify-phases %standard-phases
2354 (add-after 'unpack 'fix-latex-errors
2356 (with-fluids ((%default-port-encoding #f))
2357 (substitute* "doc/references.bib"
2358 (("\\{S\\}illanp[^,]+,")
2359 "{S}illanp{\\\"a}{\\\"a},")))
2360 ;; XXX: I just can't get pdflatex to not complain about these
2361 ;; characters. They end up in the manual via the generated
2362 ;; discrover-cli-help.txt.
2363 (substitute* "src/hmm/cli.cpp"
2367 ;; This seems to be a syntax error.
2368 (substitute* "doc/discrover-manual.tex"
2369 (("theverbbox\\[t\\]") "theverbbox"))
2371 (add-after 'unpack 'add-missing-includes
2373 (substitute* "src/executioninformation.hpp"
2374 (("#define EXECUTIONINFORMATION_HPP" line)
2375 (string-append line "\n#include <random>")))
2376 (substitute* "src/plasma/fasta.hpp"
2377 (("#define FASTA_HPP" line)
2378 (string-append line "\n#include <random>")))
2380 ;; FIXME: this is needed because we're using texlive-union, which
2381 ;; doesn't handle fonts correctly. It expects to be able to generate
2382 ;; fonts in the home directory.
2383 (add-before 'build 'setenv-HOME
2384 (lambda _ (setenv "HOME" "/tmp") #t)))))
2388 ("rmath-standalone" ,rmath-standalone)))
2390 `(("texlive" ,(texlive-union (list texlive-fonts-cm
2391 texlive-fonts-amsfonts
2394 texlive-latex-examplep
2395 texlive-latex-hyperref
2397 texlive-latex-natbib
2398 texlive-bibtex ; style files used by natbib
2399 texlive-latex-pgf ; tikz
2400 texlive-latex-verbatimbox)))
2401 ("imagemagick" ,imagemagick)))
2402 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2403 (synopsis "Discover discriminative nucleotide sequence motifs")
2404 (description "Discrover is a motif discovery method to find binding sites
2405 of nucleic acid binding proteins.")
2406 (license license:gpl3+)))
2408 (define-public eigensoft
2416 (url "https://github.com/DReichLab/EIG.git")
2417 (commit (string-append "v" version))))
2418 (file-name (git-file-name name version))
2421 "1c141fqvhnzibmnf22sv23vbmzm20kjjyrib44cfh75wyndp2d9k"))
2422 (modules '((guix build utils)))
2423 ;; Remove pre-built binaries.
2425 (delete-file-recursively "bin")
2428 (build-system gnu-build-system)
2430 `(#:tests? #f ; There are no tests.
2431 #:make-flags '("CC=gcc")
2433 (modify-phases %standard-phases
2434 ;; There is no configure phase, but the Makefile is in a
2437 (lambda _ (chdir "src") #t))
2438 ;; The provided install target only copies executables to
2439 ;; the "bin" directory in the build root.
2440 (add-after 'install 'actually-install
2441 (lambda* (#:key outputs #:allow-other-keys)
2442 (let* ((out (assoc-ref outputs "out"))
2443 (bin (string-append out "/bin")))
2444 (for-each (lambda (file)
2445 (install-file file bin))
2446 (find-files "../bin" ".*"))
2451 ("openblas" ,openblas)
2453 ("gfortran" ,gfortran "lib")))
2454 (home-page "https://github.com/DReichLab/EIG")
2455 (synopsis "Tools for population genetics")
2456 (description "The EIGENSOFT package provides tools for population
2457 genetics and stratification correction. EIGENSOFT implements methods commonly
2458 used in population genetics analyses such as PCA, computation of Tracy-Widom
2459 statistics, and finding related individuals in structured populations. It
2460 comes with a built-in plotting script and supports multiple file formats and
2461 quantitative phenotypes.")
2462 ;; The license of the eigensoft tools is Expat, but since it's
2463 ;; linking with the GNU Scientific Library (GSL) the effective
2464 ;; license is the GPL.
2465 (license license:gpl3+)))
2467 (define-public edirect
2470 (version "10.2.20181018")
2473 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect"
2474 "/versions/" version
2475 "/edirect-" version ".tar.gz"))
2478 "091f4aigzpbqih6h82nq566gkp3y07i72yqndmqskfgar1vwgci7"))))
2479 (build-system perl-build-system)
2482 (modify-phases %standard-phases
2485 (delete 'check) ; simple check after install
2487 (lambda* (#:key outputs #:allow-other-keys)
2488 (install-file "edirect.pl"
2489 (string-append (assoc-ref outputs "out") "/bin"))
2491 (add-after 'install 'wrap-program
2492 (lambda* (#:key outputs #:allow-other-keys)
2493 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2494 (let* ((out (assoc-ref outputs "out"))
2495 (path (getenv "PERL5LIB")))
2496 (wrap-program (string-append out "/bin/edirect.pl")
2497 `("PERL5LIB" ":" prefix (,path))))
2499 (add-after 'wrap-program 'check
2500 (lambda* (#:key outputs #:allow-other-keys)
2501 (invoke (string-append (assoc-ref outputs "out")
2506 `(("perl-html-parser" ,perl-html-parser)
2507 ("perl-encode-locale" ,perl-encode-locale)
2508 ("perl-file-listing" ,perl-file-listing)
2509 ("perl-html-tagset" ,perl-html-tagset)
2510 ("perl-html-tree" ,perl-html-tree)
2511 ("perl-http-cookies" ,perl-http-cookies)
2512 ("perl-http-date" ,perl-http-date)
2513 ("perl-http-message" ,perl-http-message)
2514 ("perl-http-negotiate" ,perl-http-negotiate)
2515 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2516 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2517 ("perl-net-http" ,perl-net-http)
2518 ("perl-uri" ,perl-uri)
2519 ("perl-www-robotrules" ,perl-www-robotrules)
2520 ("perl-xml-simple" ,perl-xml-simple)
2522 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2523 (synopsis "Tools for accessing the NCBI's set of databases")
2525 "Entrez Direct (EDirect) is a method for accessing the National Center
2526 for Biotechnology Information's (NCBI) set of interconnected
2527 databases (publication, sequence, structure, gene, variation, expression,
2528 etc.) from a terminal. Functions take search terms from command-line
2529 arguments. Individual operations are combined to build multi-step queries.
2530 Record retrieval and formatting normally complete the process.
2532 EDirect also provides an argument-driven function that simplifies the
2533 extraction of data from document summaries or other results that are returned
2534 in structured XML format. This can eliminate the need for writing custom
2535 software to answer ad hoc questions.")
2536 (license license:public-domain)))
2538 (define-public exonerate
2547 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2548 "exonerate-" version ".tar.gz"))
2551 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2552 (build-system gnu-build-system)
2554 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2556 `(("pkg-config" ,pkg-config)))
2560 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2561 (synopsis "Generic tool for biological sequence alignment")
2563 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2564 the alignment of sequences using a many alignment models, either exhaustive
2565 dynamic programming or a variety of heuristics.")
2566 (license license:gpl3)))
2568 (define-public express
2576 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2577 version "/express-" version "-src.tgz"))
2580 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2581 (build-system cmake-build-system)
2583 `(#:tests? #f ;no "check" target
2585 (modify-phases %standard-phases
2586 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2587 (lambda* (#:key inputs #:allow-other-keys)
2588 (substitute* "CMakeLists.txt"
2589 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2590 "set(Boost_USE_STATIC_LIBS OFF)")
2591 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2592 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2593 (substitute* "src/CMakeLists.txt"
2594 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2595 (string-append (assoc-ref inputs "bamtools") "/lib"))
2596 (("libprotobuf.a") "libprotobuf.so"))
2600 ("bamtools" ,bamtools)
2601 ("protobuf" ,protobuf)
2603 (home-page "http://bio.math.berkeley.edu/eXpress")
2604 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2606 "eXpress is a streaming tool for quantifying the abundances of a set of
2607 target sequences from sampled subsequences. Example applications include
2608 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2609 analysis (from RNA-Seq), transcription factor binding quantification in
2610 ChIP-Seq, and analysis of metagenomic data.")
2611 (license license:artistic2.0)))
2613 (define-public express-beta-diversity
2615 (name "express-beta-diversity")
2620 (url "https://github.com/dparks1134/ExpressBetaDiversity.git")
2621 (commit (string-append "v" version))))
2622 (file-name (git-file-name name version))
2625 "0s0yzg5c21349rh7x4w9266jsvnp7j1hp9cf8sk32hz8nvrj745x"))))
2626 (build-system gnu-build-system)
2629 (modify-phases %standard-phases
2631 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2633 (lambda _ (invoke "../bin/ExpressBetaDiversity" "-u") #t))
2635 (lambda* (#:key outputs #:allow-other-keys)
2636 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
2637 (install-file "../scripts/convertToEBD.py" bin)
2638 (install-file "../bin/ExpressBetaDiversity" bin)
2641 `(("python" ,python-2)))
2642 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2643 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2645 "Express Beta Diversity (EBD) calculates ecological beta diversity
2646 (dissimilarity) measures between biological communities. EBD implements a
2647 variety of diversity measures including those that make use of phylogenetic
2648 similarity of community members.")
2649 (license license:gpl3+)))
2651 (define-public fasttree
2658 "http://www.microbesonline.org/fasttree/FastTree-"
2662 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2663 (build-system gnu-build-system)
2665 `(#:tests? #f ; no "check" target
2667 (modify-phases %standard-phases
2671 (lambda* (#:key source #:allow-other-keys)
2674 "-finline-functions"
2685 "-finline-functions"
2694 (lambda* (#:key outputs #:allow-other-keys)
2695 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
2696 (install-file "FastTree" bin)
2697 (install-file "FastTreeMP" bin)
2699 (home-page "http://www.microbesonline.org/fasttree")
2700 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2702 "FastTree can handle alignments with up to a million of sequences in a
2703 reasonable amount of time and memory. For large alignments, FastTree is
2704 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2705 (license license:gpl2+)))
2707 (define-public fastx-toolkit
2709 (name "fastx-toolkit")
2715 "https://github.com/agordon/fastx_toolkit/releases/download/"
2716 version "/fastx_toolkit-" version ".tar.bz2"))
2719 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2720 (build-system gnu-build-system)
2722 `(("libgtextutils" ,libgtextutils)))
2724 `(("pkg-config" ,pkg-config)))
2725 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2726 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2728 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2729 FASTA/FASTQ files preprocessing.
2731 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2732 containing multiple short-reads sequences. The main processing of such
2733 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2734 is sometimes more productive to preprocess the files before mapping the
2735 sequences to the genome---manipulating the sequences to produce better mapping
2736 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2737 (license license:agpl3+)))
2739 (define-public flexbar
2746 (url "https://github.com/seqan/flexbar.git")
2747 (commit (string-append "v" version))))
2748 (file-name (git-file-name name version))
2751 "1pq9sxvdnldl14libk234m72dqhwgzs3acgl943wchwdqlcsi5r2"))))
2752 (build-system cmake-build-system)
2755 (modify-phases %standard-phases
2756 (add-after 'unpack 'do-not-tune-to-CPU
2758 (substitute* "src/CMakeLists.txt"
2759 ((" -march=native") ""))
2762 (lambda* (#:key outputs #:allow-other-keys)
2763 (setenv "PATH" (string-append (getcwd) ":" (getenv "PATH")))
2764 (with-directory-excursion "../source/test"
2765 (invoke "bash" "flexbar_test.sh"))
2768 (lambda* (#:key outputs #:allow-other-keys)
2769 (let* ((out (string-append (assoc-ref outputs "out")))
2770 (bin (string-append out "/bin/")))
2771 (install-file "flexbar" bin))
2777 `(("pkg-config" ,pkg-config)
2779 (home-page "https://github.com/seqan/flexbar")
2780 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2782 "Flexbar preprocesses high-throughput nucleotide sequencing data
2783 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2784 Moreover, trimming and filtering features are provided. Flexbar increases
2785 read mapping rates and improves genome and transcriptome assemblies. It
2786 supports next-generation sequencing data in fasta/q and csfasta/q format from
2787 Illumina, Roche 454, and the SOLiD platform.")
2788 (license license:bsd-3)))
2790 (define-public fraggenescan
2792 (name "fraggenescan")
2798 (string-append "mirror://sourceforge/fraggenescan/"
2799 "FragGeneScan" version ".tar.gz"))
2801 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
2802 (build-system gnu-build-system)
2805 (modify-phases %standard-phases
2807 (add-before 'build 'patch-paths
2808 (lambda* (#:key outputs #:allow-other-keys)
2809 (let* ((out (string-append (assoc-ref outputs "out")))
2810 (share (string-append out "/share/fraggenescan/")))
2811 (substitute* "run_FragGeneScan.pl"
2813 (string-append "system(\"" (which "rm")))
2815 (string-append "system(\"" (which "mv")))
2816 (("\\\"awk") (string-append "\"" (which "awk")))
2817 ;; This script and other programs expect the training files
2818 ;; to be in the non-standard location bin/train/XXX. Change
2819 ;; this to be share/fraggenescan/train/XXX instead.
2820 (("^\\$train.file = \\$dir.*")
2821 (string-append "$train_file = \""
2823 "train/\".$FGS_train_file;")))
2824 (substitute* "run_hmm.c"
2825 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2826 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
2830 (invoke "make" "clean")
2831 (invoke "make" "fgs")
2834 (lambda* (#:key outputs #:allow-other-keys)
2835 (let* ((out (string-append (assoc-ref outputs "out")))
2836 (bin (string-append out "/bin/"))
2837 (share (string-append out "/share/fraggenescan/train")))
2838 (install-file "run_FragGeneScan.pl" bin)
2839 (install-file "FragGeneScan" bin)
2840 (copy-recursively "train" share))
2843 (add-after 'install 'post-install-check
2844 ;; In lieu of 'make check', run one of the examples and check the
2845 ;; output files gets created.
2846 (lambda* (#:key outputs #:allow-other-keys)
2847 (let* ((out (string-append (assoc-ref outputs "out")))
2848 (bin (string-append out "/bin/"))
2849 (frag (string-append bin "run_FragGeneScan.pl")))
2850 ;; Test complete genome.
2852 "-genome=./example/NC_000913.fna"
2856 (unless (and (file-exists? "test2.faa")
2857 (file-exists? "test2.ffn")
2858 (file-exists? "test2.gff")
2859 (file-exists? "test2.out"))
2860 (error "Expected files do not exist."))
2861 ;; Test incomplete sequences.
2863 "-genome=./example/NC_000913-fgs.ffn"
2870 ("python" ,python-2))) ;not compatible with python 3.
2871 (home-page "https://sourceforge.net/projects/fraggenescan/")
2872 (synopsis "Finds potentially fragmented genes in short reads")
2874 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2875 short and error-prone DNA sequencing reads. It can also be applied to predict
2876 genes in incomplete assemblies or complete genomes.")
2877 ;; GPL3+ according to private correspondense with the authors.
2878 (license license:gpl3+)))
2880 (define-public fxtract
2881 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2889 (url "https://github.com/ctSkennerton/fxtract.git")
2891 (file-name (git-file-name name version))
2894 "0hab3gpwf4w9s87qlbswq6ws1qqybh4dcqk79q1ahyldzai5fgp5"))))
2895 (build-system gnu-build-system)
2897 `(#:make-flags (list
2898 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2900 #:test-target "fxtract_test"
2902 (modify-phases %standard-phases
2904 (add-before 'build 'copy-util
2905 (lambda* (#:key inputs #:allow-other-keys)
2907 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2909 ;; Do not use make install as this requires additional dependencies.
2911 (lambda* (#:key outputs #:allow-other-keys)
2912 (let* ((out (assoc-ref outputs "out"))
2913 (bin (string-append out"/bin")))
2914 (install-file "fxtract" bin)
2920 ;; ctskennerton-util is licensed under GPL2.
2921 `(("ctskennerton-util"
2925 (url "https://github.com/ctSkennerton/util.git")
2926 (commit util-commit)))
2927 (file-name (string-append
2928 "ctstennerton-util-" util-commit "-checkout"))
2931 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2932 (home-page "https://github.com/ctSkennerton/fxtract")
2933 (synopsis "Extract sequences from FASTA and FASTQ files")
2935 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2936 or FASTQ) file given a subsequence. It uses a simple substring search for
2937 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2938 lookups or multi-pattern searching as required. By default fxtract looks in
2939 the sequence of each record but can also be told to look in the header,
2940 comment or quality sections.")
2941 ;; 'util' requires SSE instructions.
2942 (supported-systems '("x86_64-linux"))
2943 (license license:expat))))
2945 (define-public gemma
2952 (url "https://github.com/xiangzhou/GEMMA.git")
2953 (commit (string-append "v" version))))
2954 (file-name (git-file-name name version))
2957 "1s3ncnbn45r2hh1cvrqky1kbqq6546biypr4f5mkw1kqlrgyh0yg"))))
2960 ("gfortran" ,gfortran "lib")
2963 ("openblas" ,openblas)
2965 (build-system gnu-build-system)
2968 '(,@(match (%current-system)
2970 '("FORCE_DYNAMIC=1"))
2972 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
2974 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
2976 (modify-phases %standard-phases
2978 (add-after 'unpack 'find-eigen
2979 (lambda* (#:key inputs #:allow-other-keys)
2980 ;; Ensure that Eigen headers can be found
2981 (setenv "CPLUS_INCLUDE_PATH"
2982 (string-append (getenv "CPLUS_INCLUDE_PATH")
2984 (assoc-ref inputs "eigen")
2987 (add-before 'build 'bin-mkdir
2992 (lambda* (#:key outputs #:allow-other-keys)
2993 (let ((out (assoc-ref outputs "out")))
2994 (install-file "bin/gemma"
2998 #:tests? #f)) ; no tests included yet
2999 (home-page "https://github.com/xiangzhou/GEMMA")
3000 (synopsis "Tool for genome-wide efficient mixed model association")
3002 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
3003 standard linear mixed model resolver with application in genome-wide
3004 association studies (GWAS).")
3005 (license license:gpl3)))
3014 (url "https://github.com/nboley/grit.git")
3016 (file-name (git-file-name name version))
3019 "1l5v8vfvfbrpmgnrvbrbv40d0arhxcnmxgv2f1mlcqfa3q6bkqm9"))))
3020 (build-system python-build-system)
3022 `(#:python ,python-2
3024 (modify-phases %standard-phases
3025 (add-after 'unpack 'generate-from-cython-sources
3026 (lambda* (#:key inputs outputs #:allow-other-keys)
3027 ;; Delete these C files to force fresh generation from pyx sources.
3028 (delete-file "grit/sparsify_support_fns.c")
3029 (delete-file "grit/call_peaks_support_fns.c")
3030 (substitute* "setup.py"
3031 (("Cython.Setup") "Cython.Build"))
3034 `(("python-scipy" ,python2-scipy)
3035 ("python-numpy" ,python2-numpy)
3036 ("python-pysam" ,python2-pysam)
3037 ("python-networkx" ,python2-networkx)))
3039 `(("python-cython" ,python2-cython)))
3040 (home-page "http://grit-bio.org")
3041 (synopsis "Tool for integrative analysis of RNA-seq type assays")
3043 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
3044 full length transcript models. When none of these data sources are available,
3045 GRIT can be run by providing a candidate set of TES or TSS sites. In
3046 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
3047 also be run in quantification mode, where it uses a provided GTF file and just
3048 estimates transcript expression.")
3049 (license license:gpl3+)))
3051 (define-public hisat
3058 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
3059 version "-beta-source.zip"))
3062 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
3063 (build-system gnu-build-system)
3065 `(#:tests? #f ;no check target
3066 #:make-flags '("allall"
3067 ;; Disable unsupported `popcnt' instructions on
3068 ;; architectures other than x86_64
3069 ,@(if (string-prefix? "x86_64"
3070 (or (%current-target-system)
3073 '("POPCNT_CAPABILITY=0")))
3075 (modify-phases %standard-phases
3076 (add-after 'unpack 'patch-sources
3078 ;; XXX Cannot use snippet because zip files are not supported
3079 (substitute* "Makefile"
3080 (("^CC = .*$") "CC = gcc")
3081 (("^CPP = .*$") "CPP = g++")
3082 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
3083 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
3084 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
3085 (substitute* '("hisat-build" "hisat-inspect")
3086 (("/usr/bin/env") (which "env")))
3089 (lambda* (#:key outputs #:allow-other-keys)
3090 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
3091 (for-each (lambda (file)
3092 (install-file file bin))
3095 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
3097 (delete 'configure))))
3099 `(("unzip" ,unzip)))
3104 ;; Non-portable SSE instructions are used so building fails on platforms
3105 ;; other than x86_64.
3106 (supported-systems '("x86_64-linux"))
3107 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
3108 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
3110 "HISAT is a fast and sensitive spliced alignment program for mapping
3111 RNA-seq reads. In addition to one global FM index that represents a whole
3112 genome, HISAT uses a large set of small FM indexes that collectively cover the
3113 whole genome. These small indexes (called local indexes) combined with
3114 several alignment strategies enable effective alignment of RNA-seq reads, in
3115 particular, reads spanning multiple exons.")
3116 (license license:gpl3+)))
3118 (define-public hisat2
3125 (uri (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
3126 "/downloads/hisat2-" version "-source.zip"))
3129 "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"))))
3130 (build-system gnu-build-system)
3132 `(#:tests? #f ; no check target
3133 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
3134 #:modules ((guix build gnu-build-system)
3138 (modify-phases %standard-phases
3139 (add-after 'unpack 'make-deterministic
3141 (substitute* "Makefile"
3146 (lambda* (#:key outputs #:allow-other-keys)
3147 (let* ((out (assoc-ref outputs "out"))
3148 (bin (string-append out "/bin/"))
3149 (doc (string-append out "/share/doc/hisat2/")))
3151 (cut install-file <> bin)
3153 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
3155 (install-file "doc/manual.inc.html" doc))
3158 `(("unzip" ,unzip) ; needed for archive from ftp
3160 ("pandoc" ,ghc-pandoc))) ; for documentation
3161 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
3162 (synopsis "Graph-based alignment of genomic sequencing reads")
3163 (description "HISAT2 is a fast and sensitive alignment program for mapping
3164 next-generation sequencing reads (both DNA and RNA) to a population of human
3165 genomes (as well as to a single reference genome). In addition to using one
3166 global @dfn{graph FM} (GFM) index that represents a population of human
3167 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
3168 the whole genome. These small indexes, combined with several alignment
3169 strategies, enable rapid and accurate alignment of sequencing reads. This new
3170 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
3171 ;; HISAT2 contains files from Bowtie2, which is released under
3172 ;; GPLv2 or later. The HISAT2 source files are released under
3174 (license license:gpl3+)))
3176 (define-public hmmer
3184 "http://eddylab.org/software/hmmer/hmmer-" version ".tar.gz"))
3187 "171bivy6xhgjsz5nv53n81pc3frnwz29ylblawk2bv46szwjjqd5"))))
3188 (build-system gnu-build-system)
3189 (native-inputs `(("perl" ,perl)))
3190 (home-page "http://hmmer.org/")
3191 (synopsis "Biosequence analysis using profile hidden Markov models")
3193 "HMMER is used for searching sequence databases for homologs of protein
3194 sequences, and for making protein sequence alignments. It implements methods
3195 using probabilistic models called profile hidden Markov models (profile
3197 ;; hmmer uses non-portable SSE intrinsics so building fails on other
3199 (supported-systems '("x86_64-linux" "i686-linux"))
3200 (license license:bsd-3)))
3202 (define-public htseq
3208 (uri (pypi-uri "HTSeq" version))
3211 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
3212 (build-system python-build-system)
3214 `(("python-cython" ,python-cython)))
3215 ;; Numpy needs to be propagated when htseq is used as a Python library.
3217 `(("python-numpy" ,python-numpy)))
3219 `(("python-pysam" ,python-pysam)
3220 ("python-matplotlib" ,python-matplotlib)))
3221 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
3222 (synopsis "Analysing high-throughput sequencing data with Python")
3224 "HTSeq is a Python package that provides infrastructure to process data
3225 from high-throughput sequencing assays.")
3226 (license license:gpl3+)))
3228 (define-public python2-htseq
3229 (package-with-python2 htseq))
3231 (define-public java-htsjdk
3233 (name "java-htsjdk")
3234 (version "2.3.0") ; last version without build dependency on gradle
3238 (url "https://github.com/samtools/htsjdk.git")
3240 (file-name (git-file-name name version))
3243 "1b178ixcabanm834ydjl3jiakpyxdmki32hqfv2abrzn3rcwa28i"))
3244 (modules '((guix build utils)))
3246 ;; Delete pre-built binaries
3248 (delete-file-recursively "lib")
3251 (build-system ant-build-system)
3253 `(#:tests? #f ; test require Internet access
3256 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3257 "/share/java/htsjdk/"))
3258 #:build-target "all"
3260 (modify-phases %standard-phases
3261 ;; The build phase also installs the jars
3262 (delete 'install))))
3264 `(("java-ngs" ,java-ngs)
3265 ("java-snappy-1" ,java-snappy-1)
3266 ("java-commons-compress" ,java-commons-compress)
3267 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3268 ("java-commons-jexl-2" ,java-commons-jexl-2)
3269 ("java-xz" ,java-xz)))
3271 `(("java-testng" ,java-testng)))
3272 (home-page "http://samtools.github.io/htsjdk/")
3273 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3275 "HTSJDK is an implementation of a unified Java library for accessing
3276 common file formats, such as SAM and VCF, used for high-throughput
3277 sequencing (HTS) data. There are also an number of useful utilities for
3278 manipulating HTS data.")
3279 (license license:expat)))
3281 (define-public java-htsjdk-latest
3283 (name "java-htsjdk")
3288 (url "https://github.com/samtools/htsjdk.git")
3290 (file-name (string-append name "-" version "-checkout"))
3293 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
3294 (build-system ant-build-system)
3296 `(#:tests? #f ; test require Scala
3298 #:jar-name "htsjdk.jar"
3300 (modify-phases %standard-phases
3301 (add-after 'unpack 'remove-useless-build.xml
3302 (lambda _ (delete-file "build.xml") #t))
3303 ;; The tests require the scalatest package.
3304 (add-after 'unpack 'remove-tests
3305 (lambda _ (delete-file-recursively "src/test") #t)))))
3307 `(("java-ngs" ,java-ngs)
3308 ("java-snappy-1" ,java-snappy-1)
3309 ("java-commons-compress" ,java-commons-compress)
3310 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3311 ("java-commons-jexl-2" ,java-commons-jexl-2)
3312 ("java-xz" ,java-xz)))
3314 `(("java-junit" ,java-junit)))
3315 (home-page "http://samtools.github.io/htsjdk/")
3316 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3318 "HTSJDK is an implementation of a unified Java library for accessing
3319 common file formats, such as SAM and VCF, used for high-throughput
3320 sequencing (HTS) data. There are also an number of useful utilities for
3321 manipulating HTS data.")
3322 (license license:expat)))
3324 ;; This is needed for picard 2.10.3
3325 (define-public java-htsjdk-2.10.1
3326 (package (inherit java-htsjdk-latest)
3327 (name "java-htsjdk")
3332 (url "https://github.com/samtools/htsjdk.git")
3334 (file-name (string-append name "-" version "-checkout"))
3337 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
3338 (build-system ant-build-system)
3340 `(#:tests? #f ; tests require Scala
3342 #:jar-name "htsjdk.jar"
3344 (modify-phases %standard-phases
3345 (add-after 'unpack 'remove-useless-build.xml
3346 (lambda _ (delete-file "build.xml") #t))
3347 ;; The tests require the scalatest package.
3348 (add-after 'unpack 'remove-tests
3349 (lambda _ (delete-file-recursively "src/test") #t)))))))
3351 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3352 ;; recent version of java-htsjdk, which depends on gradle.
3353 (define-public java-picard
3355 (name "java-picard")
3360 (url "https://github.com/broadinstitute/picard.git")
3362 (file-name (string-append "java-picard-" version "-checkout"))
3365 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3366 (modules '((guix build utils)))
3369 ;; Delete pre-built binaries.
3370 (delete-file-recursively "lib")
3372 (substitute* "build.xml"
3373 ;; Remove build-time dependency on git.
3374 (("failifexecutionfails=\"true\"")
3375 "failifexecutionfails=\"false\"")
3377 (("depends=\"compile-htsjdk, ")
3379 (("depends=\"compile-htsjdk-tests, ")
3381 ;; Build picard-lib.jar before building picard.jar
3382 (("name=\"picard-jar\" depends=\"" line)
3383 (string-append line "picard-lib-jar, ")))
3385 (build-system ant-build-system)
3387 `(#:build-target "picard-jar"
3388 #:test-target "test"
3389 ;; Tests require jacoco:coverage.
3392 (list (string-append "-Dhtsjdk_lib_dir="
3393 (assoc-ref %build-inputs "java-htsjdk")
3394 "/share/java/htsjdk/")
3395 "-Dhtsjdk-classes=dist/tmp"
3396 (string-append "-Dhtsjdk-version="
3397 ,(package-version java-htsjdk)))
3400 (modify-phases %standard-phases
3401 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3402 (delete 'generate-jar-indices)
3403 (add-after 'unpack 'use-our-htsjdk
3404 (lambda* (#:key inputs #:allow-other-keys)
3405 (substitute* "build.xml"
3406 (("\\$\\{htsjdk\\}/lib")
3407 (string-append (assoc-ref inputs "java-htsjdk")
3408 "/share/java/htsjdk/")))
3410 (add-after 'unpack 'make-test-target-independent
3411 (lambda* (#:key inputs #:allow-other-keys)
3412 (substitute* "build.xml"
3413 (("name=\"test\" depends=\"compile, ")
3414 "name=\"test\" depends=\""))
3416 (replace 'install (install-jars "dist")))))
3418 `(("java-htsjdk" ,java-htsjdk)
3419 ("java-guava" ,java-guava)))
3421 `(("java-testng" ,java-testng)))
3422 (home-page "http://broadinstitute.github.io/picard/")
3423 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3424 (description "Picard is a set of Java command line tools for manipulating
3425 high-throughput sequencing (HTS) data and formats. Picard is implemented
3426 using the HTSJDK Java library to support accessing file formats that are
3427 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3429 (license license:expat)))
3431 ;; This is needed for dropseq-tools
3432 (define-public java-picard-2.10.3
3434 (name "java-picard")
3439 (url "https://github.com/broadinstitute/picard.git")
3441 (file-name (string-append "java-picard-" version "-checkout"))
3444 "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi"))))
3445 (build-system ant-build-system)
3447 `(#:jar-name "picard.jar"
3448 ;; Tests require jacoco:coverage.
3451 #:main-class "picard.cmdline.PicardCommandLine"
3452 #:modules ((guix build ant-build-system)
3454 (guix build java-utils)
3459 (modify-phases %standard-phases
3460 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3461 (delete 'generate-jar-indices)
3462 (add-after 'unpack 'remove-useless-build.xml
3463 (lambda _ (delete-file "build.xml") #t))
3464 ;; This is necessary to ensure that htsjdk is found when using
3465 ;; picard.jar as an executable.
3466 (add-before 'build 'edit-classpath-in-manifest
3467 (lambda* (#:key inputs #:allow-other-keys)
3468 (chmod "build.xml" #o664)
3469 (call-with-output-file "build.xml.new"
3473 (with-input-from-file "build.xml"
3474 (lambda _ (xml->sxml #:trim-whitespace? #t)))
3475 `((target . ,(lambda (tag . kids)
3476 (let ((name ((sxpath '(name *text*))
3478 ;; FIXME: We're breaking the line
3479 ;; early with a dummy path to
3480 ;; ensure that the store reference
3481 ;; isn't broken apart and can still
3482 ;; be found by the reference
3487 ~a/share/java/htsjdk.jar${line.separator}${line.separator}"
3488 ;; maximum line length is 70
3489 (string-tabulate (const #\b) 57)
3490 (assoc-ref inputs "java-htsjdk"))))
3491 (if (member "manifest" name)
3494 (@ (file "${manifest.file}")
3495 (match "\\r\\n\\r\\n")
3496 (replace "${line.separator}")))
3499 (file "${manifest.file}")
3502 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
3503 (*text* . ,(lambda (_ txt) txt))))
3505 (rename-file "build.xml.new" "build.xml")
3508 `(("java-htsjdk" ,java-htsjdk-2.10.1)))
3510 `(("java-testng" ,java-testng)
3511 ("java-guava" ,java-guava)))
3512 (home-page "http://broadinstitute.github.io/picard/")
3513 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3514 (description "Picard is a set of Java command line tools for manipulating
3515 high-throughput sequencing (HTS) data and formats. Picard is implemented
3516 using the HTSJDK Java library to support accessing file formats that are
3517 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3519 (license license:expat)))
3521 ;; This is the last version of Picard to provide net.sf.samtools
3522 (define-public java-picard-1.113
3523 (package (inherit java-picard)
3524 (name "java-picard")
3529 (url "https://github.com/broadinstitute/picard.git")
3531 (file-name (string-append "java-picard-" version "-checkout"))
3534 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
3535 (modules '((guix build utils)))
3538 ;; Delete pre-built binaries.
3539 (delete-file-recursively "lib")
3542 (build-system ant-build-system)
3544 `(#:build-target "picard-jar"
3545 #:test-target "test"
3546 ;; FIXME: the class path at test time is wrong.
3547 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
3548 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
3551 ;; This is only used for tests.
3553 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
3555 (modify-phases %standard-phases
3556 ;; FIXME: This phase fails.
3557 (delete 'generate-jar-indices)
3558 ;; Do not use bundled ant bzip2.
3559 (add-after 'unpack 'use-ant-bzip
3560 (lambda* (#:key inputs #:allow-other-keys)
3561 (substitute* "build.xml"
3562 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
3563 (string-append (assoc-ref inputs "ant")
3566 (add-after 'unpack 'make-test-target-independent
3567 (lambda* (#:key inputs #:allow-other-keys)
3568 (substitute* "build.xml"
3569 (("name=\"test\" depends=\"compile, ")
3570 "name=\"test\" depends=\"compile-tests, ")
3571 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
3572 "name=\"compile\" depends=\"compile-src\""))
3574 (add-after 'unpack 'fix-deflater-path
3575 (lambda* (#:key outputs #:allow-other-keys)
3576 (substitute* "src/java/net/sf/samtools/Defaults.java"
3577 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
3578 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
3579 (assoc-ref outputs "out")
3580 "/lib/jni/libIntelDeflater.so"
3583 ;; Build the deflater library, because we've previously deleted the
3584 ;; pre-built one. This can only be built with access to the JDK
3586 (add-after 'build 'build-jni
3587 (lambda* (#:key inputs #:allow-other-keys)
3590 (invoke "tar" "--strip-components=1" "-C" "jdk-src"
3591 "-xf" (assoc-ref inputs "jdk-src"))
3592 (invoke "javah" "-jni"
3593 "-classpath" "classes"
3595 "net.sf.samtools.util.zip.IntelDeflater")
3596 (with-directory-excursion "src/c/inteldeflater"
3597 (invoke "gcc" "-I../../../lib" "-I."
3598 (string-append "-I" (assoc-ref inputs "jdk")
3600 "-I../../../jdk-src/src/share/native/common/"
3601 "-I../../../jdk-src/src/solaris/native/common/"
3602 "-c" "-O3" "-fPIC" "IntelDeflater.c")
3603 (invoke "gcc" "-shared"
3604 "-o" "../../../lib/jni/libIntelDeflater.so"
3605 "IntelDeflater.o" "-lz" "-lstdc++"))
3607 ;; We can only build everything else after building the JNI library.
3608 (add-after 'build-jni 'build-rest
3609 (lambda* (#:key make-flags #:allow-other-keys)
3610 (apply invoke `("ant" "all" ,@make-flags))
3612 (add-before 'build 'set-JAVA6_HOME
3614 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
3616 (replace 'install (install-jars "dist"))
3617 (add-after 'install 'install-jni-lib
3618 (lambda* (#:key outputs #:allow-other-keys)
3619 (let ((jni (string-append (assoc-ref outputs "out")
3622 (install-file "lib/jni/libIntelDeflater.so" jni)
3625 `(("java-snappy-1" ,java-snappy-1)
3626 ("java-commons-jexl-2" ,java-commons-jexl-2)
3627 ("java-cofoja" ,java-cofoja)
3628 ("ant" ,ant) ; for bzip2 support at runtime
3631 `(("ant-apache-bcel" ,ant-apache-bcel)
3632 ("ant-junit" ,ant-junit)
3633 ("java-testng" ,java-testng)
3634 ("java-commons-bcel" ,java-commons-bcel)
3635 ("java-jcommander" ,java-jcommander)
3636 ("jdk" ,icedtea-8 "jdk")
3637 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
3639 (define-public fastqc
3646 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
3647 "projects/fastqc/fastqc_v"
3648 version "_source.zip"))
3651 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
3652 (build-system ant-build-system)
3654 `(#:tests? #f ; there are no tests
3655 #:build-target "build"
3657 (modify-phases %standard-phases
3658 (add-after 'unpack 'fix-dependencies
3659 (lambda* (#:key inputs #:allow-other-keys)
3660 (substitute* "build.xml"
3662 (string-append (assoc-ref inputs "java-jbzip2")
3663 "/share/java/jbzip2.jar"))
3665 (string-append (assoc-ref inputs "java-picard-1.113")
3666 "/share/java/sam-1.112.jar"))
3668 (string-append (assoc-ref inputs "java-cisd-jhdf5")
3669 "/share/java/sis-jhdf5.jar")))
3671 ;; There is no installation target
3673 (lambda* (#:key inputs outputs #:allow-other-keys)
3674 (let* ((out (assoc-ref outputs "out"))
3675 (bin (string-append out "/bin"))
3676 (share (string-append out "/share/fastqc/"))
3677 (exe (string-append share "/fastqc")))
3678 (for-each mkdir-p (list bin share))
3679 (copy-recursively "bin" share)
3681 (("my \\$java_bin = 'java';")
3682 (string-append "my $java_bin = '"
3683 (assoc-ref inputs "java")
3686 (symlink exe (string-append bin "/fastqc"))
3690 ("perl" ,perl) ; needed for the wrapper script
3691 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
3692 ("java-picard-1.113" ,java-picard-1.113)
3693 ("java-jbzip2" ,java-jbzip2)))
3695 `(("unzip" ,unzip)))
3696 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
3697 (synopsis "Quality control tool for high throughput sequence data")
3699 "FastQC aims to provide a simple way to do some quality control
3700 checks on raw sequence data coming from high throughput sequencing
3701 pipelines. It provides a modular set of analyses which you can use to
3702 give a quick impression of whether your data has any problems of which
3703 you should be aware before doing any further analysis.
3705 The main functions of FastQC are:
3708 @item Import of data from BAM, SAM or FastQ files (any variant);
3709 @item Providing a quick overview to tell you in which areas there may
3711 @item Summary graphs and tables to quickly assess your data;
3712 @item Export of results to an HTML based permanent report;
3713 @item Offline operation to allow automated generation of reports
3714 without running the interactive application.
3716 (license license:gpl3+)))
3718 (define-public fastp
3726 (url "https://github.com/OpenGene/fastp.git")
3727 (commit (string-append "v" version))))
3728 (file-name (git-file-name name version))
3731 "1r6ms5zbf5rps4rgp4z73nczadl00b5rqylw8f684isfz27dp0xh"))))
3732 (build-system gnu-build-system)
3734 `(#:tests? #f ; there are none
3736 (list (string-append "BINDIR=" (assoc-ref %outputs "out") "/bin"))
3738 (modify-phases %standard-phases
3740 (add-before 'install 'create-target-dir
3741 (lambda* (#:key outputs #:allow-other-keys)
3742 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
3746 (home-page "https://github.com/OpenGene/fastp/")
3747 (synopsis "All-in-one FastQ preprocessor")
3749 "Fastp is a tool designed to provide fast all-in-one preprocessing for
3750 FastQ files. This tool has multi-threading support to afford high
3752 (license license:expat)))
3754 (define-public htslib
3761 "https://github.com/samtools/htslib/releases/download/"
3762 version "/htslib-" version ".tar.bz2"))
3765 "16ljv43sc3fxmv63w7b2ff8m1s7h89xhazwmbm1bicz8axq8fjz0"))))
3766 (build-system gnu-build-system)
3768 `(("openssl" ,openssl)
3773 (home-page "http://www.htslib.org")
3774 (synopsis "C library for reading/writing high-throughput sequencing data")
3776 "HTSlib is a C library for reading/writing high-throughput sequencing
3777 data. It also provides the @command{bgzip}, @command{htsfile}, and
3778 @command{tabix} utilities.")
3779 ;; Files under cram/ are released under the modified BSD license;
3780 ;; the rest is released under the Expat license
3781 (license (list license:expat license:bsd-3))))
3783 ;; This package should be removed once no packages rely upon it.
3791 "https://github.com/samtools/htslib/releases/download/"
3792 version "/htslib-" version ".tar.bz2"))
3795 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
3804 (url "https://github.com/nboley/idr.git")
3806 (file-name (git-file-name name version))
3809 "04j876h6z444v2q79drxx283d3k5snd72kj895wbalnl42206x9g"))
3810 ;; Delete generated C code.
3812 '(begin (delete-file "idr/inv_cdf.c") #t))))
3813 (build-system python-build-system)
3814 ;; There is only one test ("test_inv_cdf.py") and it tests features that
3815 ;; are no longer part of this package. It also asserts False, which
3816 ;; causes the tests to always fail.
3817 (arguments `(#:tests? #f))
3819 `(("python-scipy" ,python-scipy)
3820 ("python-sympy" ,python-sympy)
3821 ("python-numpy" ,python-numpy)
3822 ("python-matplotlib" ,python-matplotlib)))
3824 `(("python-cython" ,python-cython)))
3825 (home-page "https://github.com/nboley/idr")
3826 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3828 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3829 to measure the reproducibility of findings identified from replicate
3830 experiments and provide highly stable thresholds based on reproducibility.")
3831 (license license:gpl2+)))
3833 (define-public jellyfish
3839 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3840 "releases/download/v" version
3841 "/jellyfish-" version ".tar.gz"))
3844 "1k4pc3fvv6w1km2yph4m5sd78fbxp21d6xyzgmy0gjihzc6mb249"))))
3845 (build-system gnu-build-system)
3846 (outputs '("out" ;for library
3847 "ruby" ;for Ruby bindings
3848 "python")) ;for Python bindings
3851 (list (string-append "--enable-ruby-binding="
3852 (assoc-ref %outputs "ruby"))
3853 (string-append "--enable-python-binding="
3854 (assoc-ref %outputs "python")))
3856 (modify-phases %standard-phases
3857 (add-before 'check 'set-SHELL-variable
3859 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3861 (setenv "SHELL" (which "bash"))
3867 ("python" ,python-2)
3868 ("pkg-config" ,pkg-config)))
3870 `(("htslib" ,htslib)))
3871 (synopsis "Tool for fast counting of k-mers in DNA")
3873 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3874 DNA. A k-mer is a substring of length k, and counting the occurrences of all
3875 such substrings is a central step in many analyses of DNA sequence. Jellyfish
3876 is a command-line program that reads FASTA and multi-FASTA files containing
3877 DNA sequences. It outputs its k-mer counts in a binary format, which can be
3878 translated into a human-readable text format using the @code{jellyfish dump}
3879 command, or queried for specific k-mers with @code{jellyfish query}.")
3880 (home-page "http://www.genome.umd.edu/jellyfish.html")
3881 ;; JELLYFISH seems to be 64-bit only.
3882 (supported-systems '("x86_64-linux" "aarch64-linux" "mips64el-linux"))
3883 ;; The combined work is published under the GPLv3 or later. Individual
3884 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3885 (license (list license:gpl3+ license:expat))))
3887 (define-public khmer
3895 (url "https://github.com/dib-lab/khmer.git")
3896 (commit (string-append "v" version))))
3897 (file-name (git-file-name name version))
3900 "02x38d9jw2r58y8dmnj4hffy9wxv1yc1jwbvdbhby9dxndv94r9m"))
3901 (patches (search-patches "khmer-use-libraries.patch"))
3902 (modules '((guix build utils)))
3905 ;; Delete bundled libraries. We do not replace the bundled seqan
3906 ;; as it is a modified subset of the old version 1.4.1.
3908 ;; We do not replace the bundled MurmurHash as the canonical
3909 ;; repository for this code 'SMHasher' is unsuitable for providing
3911 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3912 (delete-file-recursively "third-party/zlib")
3913 (delete-file-recursively "third-party/bzip2")
3915 (build-system python-build-system)
3918 (modify-phases %standard-phases
3919 (add-after 'unpack 'set-cc
3920 (lambda _ (setenv "CC" "gcc") #t))
3921 ;; FIXME: This fails with "permission denied".
3922 (delete 'reset-gzip-timestamps))))
3924 `(("python-cython" ,python-cython)
3925 ("python-pytest" ,python-pytest)
3926 ("python-pytest-runner" ,python-pytest-runner)))
3930 ("python-screed" ,python-screed)
3931 ("python-bz2file" ,python-bz2file)))
3932 (home-page "https://khmer.readthedocs.org/")
3933 (synopsis "K-mer counting, filtering and graph traversal library")
3934 (description "The khmer software is a set of command-line tools for
3935 working with DNA shotgun sequencing data from genomes, transcriptomes,
3936 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3937 sometimes better. Khmer can also identify and fix problems with shotgun
3939 ;; When building on i686, armhf and mips64el, we get the following error:
3940 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3941 (supported-systems '("x86_64-linux" "aarch64-linux"))
3942 (license license:bsd-3)))
3944 (define-public kaiju
3951 (url "https://github.com/bioinformatics-centre/kaiju")
3952 (commit (string-append "v" version))))
3953 (file-name (git-file-name name version))
3956 "119pzi0ddzv9mjg4wwa6han0cwr3k3ssn7kirvsjfcq05mi5ka0x"))))
3957 (build-system gnu-build-system)
3959 `(#:tests? #f ; There are no tests.
3961 (modify-phases %standard-phases
3963 (add-before 'build 'move-to-src-dir
3964 (lambda _ (chdir "src") #t))
3966 (lambda* (#:key inputs outputs #:allow-other-keys)
3967 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3970 (copy-recursively "bin" bin))
3975 (home-page "http://kaiju.binf.ku.dk/")
3976 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
3977 (description "Kaiju is a program for sensitive taxonomic classification
3978 of high-throughput sequencing reads from metagenomic whole genome sequencing
3980 (license license:gpl3+)))
3985 (version "2.1.1.20160309")
3988 (uri (pypi-uri "MACS2" version))
3991 "09ixspd1vcqmz1c81ih70xs4m7qml2iy5vyx1y74zww3iy1vl210"))))
3992 (build-system python-build-system)
3994 `(#:python ,python-2 ; only compatible with Python 2.7
3995 #:tests? #f)) ; no test target
3997 `(("python-numpy" ,python2-numpy)))
3998 (home-page "https://github.com/taoliu/MACS/")
3999 (synopsis "Model based analysis for ChIP-Seq data")
4001 "MACS is an implementation of a ChIP-Seq analysis algorithm for
4002 identifying transcript factor binding sites named Model-based Analysis of
4003 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
4004 the significance of enriched ChIP regions and it improves the spatial
4005 resolution of binding sites through combining the information of both
4006 sequencing tag position and orientation.")
4007 (license license:bsd-3)))
4009 (define-public mafft
4016 "https://mafft.cbrc.jp/alignment/software/mafft-" version
4017 "-without-extensions-src.tgz"))
4018 (file-name (string-append name "-" version ".tgz"))
4021 "0bacjkxfg944p5khhyh5rd4y7wkjc9qk4v2jjj442sqlq0f8ar7b"))))
4022 (build-system gnu-build-system)
4024 `(#:tests? #f ; no automated tests, though there are tests in the read me
4025 #:make-flags (let ((out (assoc-ref %outputs "out")))
4026 (list (string-append "PREFIX=" out)
4027 (string-append "BINDIR="
4028 (string-append out "/bin"))))
4030 (modify-phases %standard-phases
4031 (add-after 'unpack 'enter-dir
4032 (lambda _ (chdir "core") #t))
4033 (add-after 'enter-dir 'patch-makefile
4035 ;; on advice from the MAFFT authors, there is no need to
4036 ;; distribute mafft-profile, mafft-distance, or
4037 ;; mafft-homologs.rb as they are too "specialised".
4038 (substitute* "Makefile"
4039 ;; remove mafft-homologs.rb from SCRIPTS
4040 (("^SCRIPTS = mafft mafft-homologs.rb")
4042 ;; remove mafft-homologs from MANPAGES
4043 (("^MANPAGES = mafft.1 mafft-homologs.1")
4044 "MANPAGES = mafft.1")
4045 ;; remove mafft-distance from PROGS
4046 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
4047 "PROGS = dvtditr dndfast7 dndblast sextet5")
4048 ;; remove mafft-profile from PROGS
4049 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
4050 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
4051 (("^rm -f mafft-profile mafft-profile.exe") "#")
4052 (("^rm -f mafft-distance mafft-distance.exe") ")#")
4053 ;; do not install MAN pages in libexec folder
4054 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
4055 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
4057 (add-after 'enter-dir 'patch-paths
4058 (lambda* (#:key inputs #:allow-other-keys)
4059 (substitute* '("pairash.c"
4061 (("perl") (which "perl"))
4062 (("([\"`| ])awk" _ prefix)
4063 (string-append prefix (which "awk")))
4064 (("grep") (which "grep")))
4067 (add-after 'install 'wrap-programs
4068 (lambda* (#:key outputs #:allow-other-keys)
4069 (let* ((out (assoc-ref outputs "out"))
4070 (bin (string-append out "/bin"))
4071 (path (string-append
4072 (assoc-ref %build-inputs "coreutils") "/bin:")))
4073 (for-each (lambda (file)
4075 `("PATH" ":" prefix (,path))))
4083 ("coreutils" ,coreutils)))
4084 (home-page "http://mafft.cbrc.jp/alignment/software/")
4085 (synopsis "Multiple sequence alignment program")
4087 "MAFFT offers a range of multiple alignment methods for nucleotide and
4088 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
4089 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
4091 (license (license:non-copyleft
4092 "http://mafft.cbrc.jp/alignment/software/license.txt"
4093 "BSD-3 with different formatting"))))
4102 (url "https://github.com/marbl/mash.git")
4103 (commit (string-append "v" version))))
4104 (file-name (git-file-name name version))
4107 "049hwcc059p2fd9vwndn63laifvvsi0wmv84i6y1fr79k15dxwy6"))
4108 (modules '((guix build utils)))
4111 ;; Delete bundled kseq.
4112 ;; TODO: Also delete bundled murmurhash and open bloom filter.
4113 (delete-file "src/mash/kseq.h")
4115 (build-system gnu-build-system)
4117 `(#:tests? #f ; No tests.
4120 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
4121 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
4122 #:make-flags (list "CC=gcc")
4124 (modify-phases %standard-phases
4125 (add-after 'unpack 'fix-includes
4127 (substitute* '("src/mash/Sketch.cpp"
4128 "src/mash/CommandFind.cpp"
4129 "src/mash/CommandScreen.cpp")
4130 (("^#include \"kseq\\.h\"")
4131 "#include \"htslib/kseq.h\""))
4133 (add-after 'fix-includes 'use-c++14
4135 ;; capnproto 0.7 requires c++14 to build
4136 (substitute* "configure.ac"
4137 (("c\\+\\+11") "c++14"))
4138 (substitute* "Makefile.in"
4139 (("c\\+\\+11") "c++14"))
4142 `(("autoconf" ,autoconf)
4143 ;; Capnproto and htslib are statically embedded in the final
4144 ;; application. Therefore we also list their licenses, below.
4145 ("capnproto" ,capnproto)
4146 ("htslib" ,htslib)))
4150 (supported-systems '("x86_64-linux"))
4151 (home-page "https://mash.readthedocs.io")
4152 (synopsis "Fast genome and metagenome distance estimation using MinHash")
4153 (description "Mash is a fast sequence distance estimator that uses the
4154 MinHash algorithm and is designed to work with genomes and metagenomes in the
4155 form of assemblies or reads.")
4156 (license (list license:bsd-3 ; Mash
4157 license:expat ; HTSlib and capnproto
4158 license:public-domain ; MurmurHash 3
4159 license:cpl1.0)))) ; Open Bloom Filter
4161 (define-public metabat
4169 (url "https://bitbucket.org/berkeleylab/metabat.git")
4170 (commit (string-append "v" version))))
4171 (file-name (git-file-name name version))
4174 "0hyg2smw1nz69mfvjpk45xyyychmda92c80a0cv7baji84ri4iyn"))
4175 (patches (search-patches "metabat-fix-compilation.patch"))))
4176 (build-system scons-build-system)
4178 `(#:scons ,scons-python2
4180 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
4181 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
4182 #:tests? #f ;; Tests are run during the build phase.
4184 (modify-phases %standard-phases
4185 (add-after 'unpack 'fix-includes
4187 (substitute* "src/BamUtils.h"
4188 (("^#include \"bam/bam\\.h\"")
4189 "#include \"samtools/bam.h\"")
4190 (("^#include \"bam/sam\\.h\"")
4191 "#include \"samtools/sam.h\""))
4192 (substitute* "src/KseqReader.h"
4193 (("^#include \"bam/kseq\\.h\"")
4194 "#include \"htslib/kseq.h\""))
4196 (add-after 'unpack 'fix-scons
4197 (lambda* (#:key inputs #:allow-other-keys)
4198 (substitute* "SConstruct"
4199 (("^htslib_dir += 'samtools'")
4200 (string-append "htslib_dir = '"
4201 (assoc-ref inputs "htslib")
4203 (("^samtools_dir = 'samtools'")
4204 (string-append "samtools_dir = '"
4205 (assoc-ref inputs "samtools")
4207 (("^findStaticOrShared\\('bam', hts_lib")
4208 (string-append "findStaticOrShared('bam', '"
4209 (assoc-ref inputs "samtools")
4211 ;; Do not distribute README.
4212 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
4217 ("samtools" ,samtools)
4220 (home-page "https://bitbucket.org/berkeleylab/metabat")
4222 "Reconstruction of single genomes from complex microbial communities")
4224 "Grouping large genomic fragments assembled from shotgun metagenomic
4225 sequences to deconvolute complex microbial communities, or metagenome binning,
4226 enables the study of individual organisms and their interactions. MetaBAT is
4227 an automated metagenome binning software, which integrates empirical
4228 probabilistic distances of genome abundance and tetranucleotide frequency.")
4229 ;; The source code contains inline assembly.
4230 (supported-systems '("x86_64-linux" "i686-linux"))
4231 (license (license:non-copyleft "file://license.txt"
4232 "See license.txt in the distribution."))))
4234 (define-public minced
4241 (url "https://github.com/ctSkennerton/minced.git")
4243 (file-name (git-file-name name version))
4246 "1f5h9him0gd355cnx7p6pnxpknhckd4g0v62mg8zyhfbx9as25fv"))))
4247 (build-system gnu-build-system)
4249 `(#:test-target "test"
4251 (modify-phases %standard-phases
4253 (add-before 'check 'fix-test
4255 ;; Fix test for latest version.
4256 (substitute* "t/Aquifex_aeolicus_VF5.expected"
4257 (("minced:0.1.6") "minced:0.2.0"))
4259 (replace 'install ; No install target.
4260 (lambda* (#:key inputs outputs #:allow-other-keys)
4261 (let* ((out (assoc-ref outputs "out"))
4262 (bin (string-append out "/bin"))
4263 (wrapper (string-append bin "/minced")))
4264 ;; Minced comes with a wrapper script that tries to figure out where
4265 ;; it is located before running the JAR. Since these paths are known
4266 ;; to us, we build our own wrapper to avoid coreutils dependency.
4267 (install-file "minced.jar" bin)
4268 (with-output-to-file wrapper
4272 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
4273 (assoc-ref inputs "jre") "/bin/java -jar "
4274 bin "/minced.jar \"$@\"\n"))))
4275 (chmod wrapper #o555))
4278 `(("jdk" ,icedtea "jdk")))
4281 ("jre" ,icedtea "out")))
4282 (home-page "https://github.com/ctSkennerton/minced")
4283 (synopsis "Mining CRISPRs in Environmental Datasets")
4285 "MinCED is a program to find Clustered Regularly Interspaced Short
4286 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
4287 unassembled metagenomic reads, but is mainly designed for full genomes and
4288 assembled metagenomic sequence.")
4289 (license license:gpl3+)))
4297 (uri (pypi-uri "misopy" version))
4300 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
4301 (modules '((guix build utils)))
4303 (substitute* "setup.py"
4304 ;; Use setuptools, or else the executables are not
4306 (("distutils.core") "setuptools")
4307 ;; use "gcc" instead of "cc" for compilation
4309 "cc.set_executables(
4313 linker_so='gcc -shared'); defines"))
4315 (build-system python-build-system)
4317 `(#:python ,python-2 ; only Python 2 is supported
4318 #:tests? #f)) ; no "test" target
4320 `(("samtools" ,samtools)
4321 ("python-numpy" ,python2-numpy)
4322 ("python-pysam" ,python2-pysam)
4323 ("python-scipy" ,python2-scipy)
4324 ("python-matplotlib" ,python2-matplotlib)))
4326 `(("python-mock" ,python2-mock) ;for tests
4327 ("python-pytz" ,python2-pytz))) ;for tests
4328 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
4329 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
4331 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
4332 the expression level of alternatively spliced genes from RNA-Seq data, and
4333 identifies differentially regulated isoforms or exons across samples. By
4334 modeling the generative process by which reads are produced from isoforms in
4335 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
4336 that a read originated from a particular isoform.")
4337 (license license:gpl2)))
4339 (define-public muscle
4342 (version "3.8.1551")
4344 (method url-fetch/tarbomb)
4346 "http://www.drive5.com/muscle/muscle_src_"
4350 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
4351 (build-system gnu-build-system)
4353 `(#:make-flags (list "LDLIBS = -lm")
4355 (modify-phases %standard-phases
4358 ;; There are no tests, so just test if it runs.
4359 (lambda _ (invoke "./muscle" "-version") #t))
4361 (lambda* (#:key outputs #:allow-other-keys)
4362 (let* ((out (assoc-ref outputs "out"))
4363 (bin (string-append out "/bin")))
4364 (install-file "muscle" bin)
4366 (home-page "http://www.drive5.com/muscle")
4367 (synopsis "Multiple sequence alignment program")
4369 "MUSCLE aims to be a fast and accurate multiple sequence alignment
4370 program for nucleotide and protein sequences.")
4371 ;; License information found in 'muscle -h' and usage.cpp.
4372 (license license:public-domain)))
4374 (define-public newick-utils
4375 ;; There are no recent releases so we package from git.
4376 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
4378 (name "newick-utils")
4379 (version (string-append "1.6-1." (string-take commit 8)))
4383 (url "https://github.com/tjunier/newick_utils.git")
4385 (file-name (string-append name "-" version "-checkout"))
4388 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4389 (build-system gnu-build-system)
4391 ;; XXX: TODO: Enable Lua and Guile bindings.
4392 ;; https://github.com/tjunier/newick_utils/issues/13
4393 `(("libxml2" ,libxml2)
4397 `(("autoconf" ,autoconf)
4398 ("automake" ,automake)
4399 ("libtool" ,libtool)))
4400 (synopsis "Programs for working with newick format phylogenetic trees")
4402 "Newick-utils is a suite of utilities for processing phylogenetic trees
4403 in Newick format. Functions include re-rooting, extracting subtrees,
4404 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4405 (home-page "https://github.com/tjunier/newick_utils")
4406 (license license:bsd-3))))
4415 "https://github.com/wwood/OrfM/releases/download/v"
4416 version "/orfm-" version ".tar.gz"))
4419 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4420 (build-system gnu-build-system)
4421 (inputs `(("zlib" ,zlib)))
4423 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4424 ("ruby-rspec" ,ruby-rspec)
4426 (synopsis "Simple and not slow open reading frame (ORF) caller")
4428 "An ORF caller finds stretches of DNA that, when translated, are not
4429 interrupted by stop codons. OrfM finds and prints these ORFs.")
4430 (home-page "https://github.com/wwood/OrfM")
4431 (license license:lgpl3+)))
4433 (define-public python2-pbcore
4435 (name "python2-pbcore")
4439 (uri (pypi-uri "pbcore" version))
4442 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4443 (build-system python-build-system)
4444 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
4446 `(("python-cython" ,python2-cython)
4447 ("python-numpy" ,python2-numpy)
4448 ("python-pysam" ,python2-pysam)
4449 ("python-h5py" ,python2-h5py)))
4451 `(("python-nose" ,python2-nose)
4452 ("python-sphinx" ,python2-sphinx)
4453 ("python-pyxb" ,python2-pyxb)))
4454 (home-page "http://pacificbiosciences.github.io/pbcore/")
4455 (synopsis "Library for reading and writing PacBio data files")
4457 "The pbcore package provides Python APIs for interacting with PacBio data
4458 files and writing bioinformatics applications.")
4459 (license license:bsd-3)))
4461 (define-public python2-warpedlmm
4463 (name "python2-warpedlmm")
4468 (uri (pypi-uri "WarpedLMM" version ".zip"))
4471 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4472 (build-system python-build-system)
4474 `(#:python ,python-2)) ; requires Python 2.7
4476 `(("python-scipy" ,python2-scipy)
4477 ("python-numpy" ,python2-numpy)
4478 ("python-matplotlib" ,python2-matplotlib)
4479 ("python-fastlmm" ,python2-fastlmm)
4480 ("python-pandas" ,python2-pandas)
4481 ("python-pysnptools" ,python2-pysnptools)))
4483 `(("python-mock" ,python2-mock)
4484 ("python-nose" ,python2-nose)
4486 (home-page "https://github.com/PMBio/warpedLMM")
4487 (synopsis "Implementation of warped linear mixed models")
4489 "WarpedLMM is a Python implementation of the warped linear mixed model,
4490 which automatically learns an optimal warping function (or transformation) for
4491 the phenotype as it models the data.")
4492 (license license:asl2.0)))
4494 (define-public pbtranscript-tofu
4495 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
4497 (name "pbtranscript-tofu")
4498 (version (string-append "2.2.3." (string-take commit 7)))
4502 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
4504 (file-name (string-append name "-" version "-checkout"))
4507 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
4508 (modules '((guix build utils)))
4511 ;; remove bundled Cython sources
4512 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
4514 (build-system python-build-system)
4516 `(#:python ,python-2
4517 ;; FIXME: Tests fail with "No such file or directory:
4518 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
4521 (modify-phases %standard-phases
4522 (add-after 'unpack 'enter-directory
4524 (chdir "pbtranscript-tofu/pbtranscript/")
4526 ;; With setuptools version 18.0 and later this setup.py hack causes
4527 ;; a build error, so we disable it.
4528 (add-after 'enter-directory 'patch-setuppy
4530 (substitute* "setup.py"
4531 (("if 'setuptools.extension' in sys.modules:")
4535 `(("python-numpy" ,python2-numpy)
4536 ("python-bx-python" ,python2-bx-python)
4537 ("python-networkx" ,python2-networkx)
4538 ("python-scipy" ,python2-scipy)
4539 ("python-pbcore" ,python2-pbcore)
4540 ("python-h5py" ,python2-h5py)))
4542 `(("python-cython" ,python2-cython)
4543 ("python-nose" ,python2-nose)))
4544 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4545 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4547 "pbtranscript-tofu contains scripts to analyze transcriptome data
4548 generated using the PacBio Iso-Seq protocol.")
4549 (license license:bsd-3))))
4551 (define-public prank
4558 "http://wasabiapp.org/download/prank/prank.source."
4562 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
4563 (build-system gnu-build-system)
4566 (modify-phases %standard-phases
4567 (add-after 'unpack 'enter-src-dir
4571 (add-after 'unpack 'remove-m64-flag
4572 ;; Prank will build with the correct 'bit-ness' without this flag
4573 ;; and this allows building on 32-bit machines.
4574 (lambda _ (substitute* "src/Makefile"
4579 (lambda* (#:key outputs #:allow-other-keys)
4580 (let* ((out (assoc-ref outputs "out"))
4581 (bin (string-append out "/bin"))
4582 (man (string-append out "/share/man/man1"))
4583 (path (string-append
4584 (assoc-ref %build-inputs "mafft") "/bin:"
4585 (assoc-ref %build-inputs "exonerate") "/bin:"
4586 (assoc-ref %build-inputs "bppsuite") "/bin")))
4587 (install-file "prank" bin)
4588 (wrap-program (string-append bin "/prank")
4589 `("PATH" ":" prefix (,path)))
4590 (install-file "prank.1" man))
4594 ("exonerate" ,exonerate)
4595 ("bppsuite" ,bppsuite)))
4596 (home-page "http://wasabiapp.org/software/prank/")
4597 (synopsis "Probabilistic multiple sequence alignment program")
4599 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4600 codon and amino-acid sequences. It is based on a novel algorithm that treats
4601 insertions correctly and avoids over-estimation of the number of deletion
4602 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4603 in phylogenetics and correctly takes into account the evolutionary distances
4604 between sequences. Lastly, PRANK allows for defining a potential structure
4605 for sequences to be aligned and then, simultaneously with the alignment,
4606 predicts the locations of structural units in the sequences.")
4607 (license license:gpl2+)))
4609 (define-public proteinortho
4611 (name "proteinortho")
4618 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4619 version "_src.tar.gz"))
4622 "1wl0dawpssqwfjvr651r4wlww8hhjin8nba6xh71ks7sbypx886j"))))
4623 (build-system gnu-build-system)
4625 `(#:test-target "test"
4627 (modify-phases %standard-phases
4629 ;; There is no configure script, so we modify the Makefile directly.
4630 (lambda* (#:key outputs #:allow-other-keys)
4631 (substitute* "Makefile"
4634 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4636 (add-before 'install 'make-install-directory
4637 ;; The install directory is not created during 'make install'.
4638 (lambda* (#:key outputs #:allow-other-keys)
4639 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4641 (add-after 'install 'wrap-programs
4642 (lambda* (#:key inputs outputs #:allow-other-keys)
4643 (let* ((path (getenv "PATH"))
4644 (out (assoc-ref outputs "out"))
4645 (binary (string-append out "/bin/proteinortho5.pl")))
4646 (wrap-program binary `("PATH" ":" prefix (,path))))
4650 ("python" ,python-2)
4651 ("blast+" ,blast+)))
4652 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4653 (synopsis "Detect orthologous genes across species")
4655 "Proteinortho is a tool to detect orthologous genes across different
4656 species. For doing so, it compares similarities of given gene sequences and
4657 clusters them to find significant groups. The algorithm was designed to handle
4658 large-scale data and can be applied to hundreds of species at once.")
4659 (license license:gpl2+)))
4661 (define-public pyicoteo
4669 (url "https://bitbucket.org/regulatorygenomicsupf/pyicoteo.git")
4670 (commit (string-append "v" version))))
4671 (file-name (git-file-name name version))
4674 "0hz5g8d25lbjy1wpscr490l0lmyvaix893hhax4fxnh1h9w34w8p"))))
4675 (build-system python-build-system)
4677 `(#:python ,python-2 ; does not work with Python 3
4678 #:tests? #f)) ; there are no tests
4680 `(("python2-matplotlib" ,python2-matplotlib)))
4681 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4682 (synopsis "Analyze high-throughput genetic sequencing data")
4684 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4685 sequencing data. It works with genomic coordinates. There are currently six
4686 different command-line tools:
4689 @item pyicoregion: for generating exploratory regions automatically;
4690 @item pyicoenrich: for differential enrichment between two conditions;
4691 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4692 @item pyicos: for genomic coordinates manipulation;
4693 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4694 @item pyicount: to count how many reads from N experiment files overlap in a
4696 @item pyicotrocol: to combine operations from pyicoteo.
4698 (license license:gpl3+)))
4700 (define-public prodigal
4707 (url "https://github.com/hyattpd/Prodigal.git")
4708 (commit (string-append "v" version))))
4709 (file-name (git-file-name name version))
4712 "1fs1hqk83qjbjhrvhw6ni75zakx5ki1ayy3v6wwkn3xvahc9hi5s"))))
4713 (build-system gnu-build-system)
4715 `(#:tests? #f ;no check target
4716 #:make-flags (list (string-append "INSTALLDIR="
4717 (assoc-ref %outputs "out")
4720 (modify-phases %standard-phases
4721 (delete 'configure))))
4722 (home-page "http://prodigal.ornl.gov")
4723 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
4725 "Prodigal runs smoothly on finished genomes, draft genomes, and
4726 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
4727 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
4728 partial genes, and identifies translation initiation sites.")
4729 (license license:gpl3+)))
4731 (define-public roary
4739 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
4743 "0qxrds9wx7cfhlkihrp6697kx0flhhxymap9fwan0b3rbdhcnmff"))))
4744 (build-system perl-build-system)
4747 (modify-phases %standard-phases
4752 ;; The tests are not run by default, so we run each test file
4754 (setenv "PATH" (string-append (getcwd) "/bin" ":"
4756 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
4757 (getenv "PERL5LIB")))
4758 (for-each (lambda (file)
4759 (display file)(display "\n")
4760 (invoke "perl" file))
4761 (find-files "t" ".*\\.t$"))
4764 ;; There is no 'install' target in the Makefile.
4765 (lambda* (#:key outputs #:allow-other-keys)
4766 (let* ((out (assoc-ref outputs "out"))
4767 (bin (string-append out "/bin"))
4768 (perl (string-append out "/lib/perl5/site_perl"))
4769 (roary-plots "contrib/roary_plots"))
4772 (copy-recursively "bin" bin)
4773 (copy-recursively "lib" perl)
4775 (add-after 'install 'wrap-programs
4776 (lambda* (#:key inputs outputs #:allow-other-keys)
4777 (let* ((out (assoc-ref outputs "out"))
4778 (perl5lib (getenv "PERL5LIB"))
4779 (path (getenv "PATH")))
4780 (for-each (lambda (prog)
4781 (let ((binary (string-append out "/" prog)))
4782 (wrap-program binary
4783 `("PERL5LIB" ":" prefix
4784 (,(string-append perl5lib ":" out
4785 "/lib/perl5/site_perl"))))
4786 (wrap-program binary
4788 (,(string-append path ":" out "/bin"))))))
4789 (find-files "bin" ".*[^R]$"))
4791 (string-append out "/bin/roary-create_pan_genome_plots.R"))
4792 (r-site-lib (getenv "R_LIBS_SITE"))
4794 (string-append (assoc-ref inputs "coreutils") "/bin")))
4796 `("R_LIBS_SITE" ":" prefix
4797 (,(string-append r-site-lib ":" out "/site-library/"))))
4800 (,(string-append coreutils-path ":" out "/bin"))))))
4803 `(("perl-env-path" ,perl-env-path)
4804 ("perl-test-files" ,perl-test-files)
4805 ("perl-test-most" ,perl-test-most)
4806 ("perl-test-output" ,perl-test-output)))
4808 `(("perl-array-utils" ,perl-array-utils)
4809 ("bioperl" ,bioperl-minimal)
4810 ("perl-digest-md5-file" ,perl-digest-md5-file)
4811 ("perl-exception-class" ,perl-exception-class)
4812 ("perl-file-find-rule" ,perl-file-find-rule)
4813 ("perl-file-grep" ,perl-file-grep)
4814 ("perl-file-slurper" ,perl-file-slurper)
4815 ("perl-file-which" ,perl-file-which)
4816 ("perl-graph" ,perl-graph)
4817 ("perl-graph-readwrite" ,perl-graph-readwrite)
4818 ("perl-log-log4perl" ,perl-log-log4perl)
4819 ("perl-moose" ,perl-moose)
4820 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
4821 ("perl-text-csv" ,perl-text-csv)
4822 ("bedtools" ,bedtools)
4826 ("parallel" ,parallel)
4829 ("fasttree" ,fasttree)
4833 ("r-minimal" ,r-minimal)
4834 ("r-ggplot2" ,r-ggplot2)
4835 ("coreutils" ,coreutils)))
4836 (home-page "http://sanger-pathogens.github.io/Roary")
4837 (synopsis "High speed stand-alone pan genome pipeline")
4839 "Roary is a high speed stand alone pan genome pipeline, which takes
4840 annotated assemblies in GFF3 format (produced by the Prokka program) and
4841 calculates the pan genome. Using a standard desktop PC, it can analyse
4842 datasets with thousands of samples, without compromising the quality of the
4843 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4844 single processor. Roary is not intended for metagenomics or for comparing
4845 extremely diverse sets of genomes.")
4846 (license license:gpl3)))
4848 (define-public raxml
4856 (url "https://github.com/stamatak/standard-RAxML.git")
4857 (commit (string-append "v" version))))
4858 (file-name (git-file-name name version))
4861 "1jqjzhch0rips0vp04prvb8vmc20c5pdmsqn8knadcf91yy859fh"))))
4862 (build-system gnu-build-system)
4864 `(#:tests? #f ; There are no tests.
4865 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4866 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4868 (modify-phases %standard-phases
4871 (lambda* (#:key outputs #:allow-other-keys)
4872 (let* ((out (assoc-ref outputs "out"))
4873 (bin (string-append out "/bin"))
4874 (executable "raxmlHPC-HYBRID"))
4875 (install-file executable bin)
4876 (symlink (string-append bin "/" executable) "raxml"))
4879 `(("openmpi" ,openmpi)))
4880 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4881 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4883 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4885 ;; The source includes x86 specific code
4886 (supported-systems '("x86_64-linux" "i686-linux"))
4887 (license license:gpl2+)))
4897 (url "https://github.com/deweylab/RSEM.git")
4898 (commit (string-append "v" version))))
4900 (base32 "1jlq11d1p8qp64w75yj8cnbbd1a93viq10pzsbwal7vdn8fg13j1"))
4901 (file-name (git-file-name name version))
4902 (modules '((guix build utils)))
4905 ;; remove bundled copy of boost and samtools
4906 (delete-file-recursively "boost")
4907 (delete-file-recursively "samtools-1.3")
4909 (build-system gnu-build-system)
4911 `(#:tests? #f ;no "check" target
4913 (list (string-append "BOOST="
4914 (assoc-ref %build-inputs "boost")
4916 (string-append "SAMHEADERS="
4917 (assoc-ref %build-inputs "htslib")
4918 "/include/htslib/sam.h")
4919 (string-append "SAMLIBS="
4920 (assoc-ref %build-inputs "htslib")
4923 (modify-phases %standard-phases
4924 ;; No "configure" script.
4925 ;; Do not build bundled samtools library.
4928 (substitute* "Makefile"
4929 (("^all : \\$\\(PROGRAMS\\).*") "all: $(PROGRAMS)\n")
4930 (("^\\$\\(SAMLIBS\\).*") ""))
4933 (lambda* (#:key outputs #:allow-other-keys)
4934 (let* ((out (string-append (assoc-ref outputs "out")))
4935 (bin (string-append out "/bin/"))
4936 (perl (string-append out "/lib/perl5/site_perl")))
4939 (for-each (lambda (file)
4940 (install-file file bin))
4941 (find-files "." "rsem-.*"))
4942 (install-file "rsem_perl_utils.pm" perl))
4944 (add-after 'install 'wrap-program
4945 (lambda* (#:key outputs #:allow-other-keys)
4946 (let ((out (assoc-ref outputs "out")))
4947 (for-each (lambda (prog)
4948 (wrap-program (string-append out "/bin/" prog)
4949 `("PERL5LIB" ":" prefix
4950 (,(string-append out "/lib/perl5/site_perl")))))
4951 '("rsem-calculate-expression"
4953 "rsem-generate-data-matrix"
4954 "rsem-generate-ngvector"
4955 "rsem-plot-transcript-wiggles"
4956 "rsem-prepare-reference"
4958 "rsem-run-prsem-testing-procedure")))
4962 ("r-minimal" ,r-minimal)
4964 ("htslib" ,htslib-1.3)
4966 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
4967 (synopsis "Estimate gene expression levels from RNA-Seq data")
4969 "RSEM is a software package for estimating gene and isoform expression
4970 levels from RNA-Seq data. The RSEM package provides a user-friendly
4971 interface, supports threads for parallel computation of the EM algorithm,
4972 single-end and paired-end read data, quality scores, variable-length reads and
4973 RSPD estimation. In addition, it provides posterior mean and 95% credibility
4974 interval estimates for expression levels. For visualization, it can generate
4975 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
4976 (license license:gpl3+)))
4978 (define-public rseqc
4986 (string-append "mirror://sourceforge/rseqc/"
4987 "RSeQC-" version ".tar.gz"))
4989 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
4990 (modules '((guix build utils)))
4993 ;; remove bundled copy of pysam
4994 (delete-file-recursively "lib/pysam")
4995 (substitute* "setup.py"
4996 ;; remove dependency on outdated "distribute" module
4997 (("^from distribute_setup import use_setuptools") "")
4998 (("^use_setuptools\\(\\)") "")
4999 ;; do not use bundled copy of pysam
5000 (("^have_pysam = False") "have_pysam = True"))
5002 (build-system python-build-system)
5003 (arguments `(#:python ,python-2))
5005 `(("python-cython" ,python2-cython)
5006 ("python-pysam" ,python2-pysam)
5007 ("python-numpy" ,python2-numpy)
5010 `(("python-nose" ,python2-nose)))
5011 (home-page "http://rseqc.sourceforge.net/")
5012 (synopsis "RNA-seq quality control package")
5014 "RSeQC provides a number of modules that can comprehensively evaluate
5015 high throughput sequence data, especially RNA-seq data. Some basic modules
5016 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
5017 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
5018 distribution, coverage uniformity, strand specificity, etc.")
5019 (license license:gpl3+)))
5022 ;; There are no release tarballs. According to the installation
5023 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
5024 ;; stable release is identified by this changeset ID.
5025 (let ((changeset "2329130")
5029 (version (string-append "0-" revision "." changeset))
5033 (url "https://bitbucket.org/libsleipnir/sleipnir")
5034 (changeset changeset)))
5035 (file-name (string-append name "-" version "-checkout"))
5038 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
5039 (build-system gnu-build-system)
5041 `(#:modules ((srfi srfi-1)
5042 (guix build gnu-build-system)
5045 (let ((dirs '("SeekMiner"
5051 (modify-phases %standard-phases
5054 (substitute* "gen_tools_am"
5055 (("/usr/bin/env.*") (which "perl")))
5056 (invoke "bash" "gen_auto")
5058 (add-after 'build 'build-additional-tools
5059 (lambda* (#:key make-flags #:allow-other-keys)
5060 (for-each (lambda (dir)
5061 (with-directory-excursion (string-append "tools/" dir)
5062 (apply invoke "make" make-flags)))
5065 (add-after 'install 'install-additional-tools
5066 (lambda* (#:key make-flags #:allow-other-keys)
5067 (for-each (lambda (dir)
5068 (with-directory-excursion (string-append "tools/" dir)
5069 (apply invoke `("make" ,@make-flags "install"))))
5076 ("readline" ,readline)
5077 ("gengetopt" ,gengetopt)
5078 ("log4cpp" ,log4cpp)))
5080 `(("autoconf" ,autoconf)
5081 ("automake" ,automake)
5083 (home-page "http://seek.princeton.edu")
5084 (synopsis "Gene co-expression search engine")
5086 "SEEK is a computational gene co-expression search engine. SEEK provides
5087 biologists with a way to navigate the massive human expression compendium that
5088 now contains thousands of expression datasets. SEEK returns a robust ranking
5089 of co-expressed genes in the biological area of interest defined by the user's
5090 query genes. It also prioritizes thousands of expression datasets according
5091 to the user's query of interest.")
5092 (license license:cc-by3.0))))
5094 (define-public samtools
5102 (string-append "mirror://sourceforge/samtools/samtools/"
5103 version "/samtools-" version ".tar.bz2"))
5106 "10ilqbmm7ri8z431sn90lvbjwizd0hhkf9rcqw8j823hf26nhgq8"))
5107 (modules '((guix build utils)))
5109 ;; Delete bundled htslib.
5110 (delete-file-recursively "htslib-1.9")
5112 (build-system gnu-build-system)
5114 `(#:modules ((ice-9 ftw)
5116 (guix build gnu-build-system)
5118 #:configure-flags (list "--with-ncurses")
5120 (modify-phases %standard-phases
5121 (add-after 'unpack 'patch-tests
5123 (substitute* "test/test.pl"
5124 ;; The test script calls out to /bin/bash
5125 (("/bin/bash") (which "bash")))
5127 (add-after 'install 'install-library
5128 (lambda* (#:key outputs #:allow-other-keys)
5129 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
5130 (install-file "libbam.a" lib)
5132 (add-after 'install 'install-headers
5133 (lambda* (#:key outputs #:allow-other-keys)
5134 (let ((include (string-append (assoc-ref outputs "out")
5135 "/include/samtools/")))
5136 (for-each (lambda (file)
5137 (install-file file include))
5138 (scandir "." (lambda (name) (string-match "\\.h$" name))))
5140 (native-inputs `(("pkg-config" ,pkg-config)))
5142 `(("htslib" ,htslib)
5143 ("ncurses" ,ncurses)
5147 (home-page "http://samtools.sourceforge.net")
5148 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
5150 "Samtools implements various utilities for post-processing nucleotide
5151 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
5152 variant calling (in conjunction with bcftools), and a simple alignment
5154 (license license:expat)))
5156 (define-public samtools-0.1
5157 ;; This is the most recent version of the 0.1 line of samtools. The input
5158 ;; and output formats differ greatly from that used and produced by samtools
5159 ;; 1.x and is still used in many bioinformatics pipelines.
5160 (package (inherit samtools)
5166 (string-append "mirror://sourceforge/samtools/samtools/"
5167 version "/samtools-" version ".tar.bz2"))
5169 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
5171 `(#:tests? #f ;no "check" target
5173 (list "LIBCURSES=-lncurses")
5174 ,@(substitute-keyword-arguments (package-arguments samtools)
5176 `(modify-phases ,phases
5178 (lambda* (#:key outputs #:allow-other-keys)
5179 (let ((bin (string-append
5180 (assoc-ref outputs "out") "/bin")))
5182 (install-file "samtools" bin)
5184 (delete 'patch-tests)
5185 (delete 'configure))))))))
5187 (define-public mosaik
5188 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
5193 ;; There are no release tarballs nor tags.
5196 (url "https://github.com/wanpinglee/MOSAIK.git")
5198 (file-name (string-append name "-" version))
5201 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
5202 (build-system gnu-build-system)
5204 `(#:tests? #f ; no tests
5205 #:make-flags (list "CC=gcc")
5207 (modify-phases %standard-phases
5209 (lambda _ (chdir "src") #t))
5211 (lambda* (#:key outputs #:allow-other-keys)
5212 (let ((bin (string-append (assoc-ref outputs "out")
5215 (copy-recursively "../bin" bin)
5219 ("zlib:static" ,zlib "static")
5221 (supported-systems '("x86_64-linux"))
5222 (home-page "https://github.com/wanpinglee/MOSAIK")
5223 (synopsis "Map nucleotide sequence reads to reference genomes")
5225 "MOSAIK is a program for mapping second and third-generation sequencing
5226 reads to a reference genome. MOSAIK can align reads generated by all the
5227 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
5228 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
5229 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
5230 ;; code released into the public domain:
5231 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
5232 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
5233 (license (list license:gpl2+ license:public-domain)))))
5235 (define-public ngs-sdk
5242 (url "https://github.com/ncbi/ngs.git")
5244 (file-name (git-file-name name version))
5247 "17c0v1nah3g3d2ib5bbi0vhma1ghd6vb9xycavqsh64lhp840rk3"))))
5248 (build-system gnu-build-system)
5250 `(#:parallel-build? #f ; not supported
5251 #:tests? #f ; no "check" target
5253 (modify-phases %standard-phases
5255 (lambda* (#:key outputs #:allow-other-keys)
5256 (let ((out (assoc-ref outputs "out")))
5257 ;; Allow 'konfigure.perl' to find 'package.prl'.
5259 (string-append ".:" (getenv "PERL5LIB")))
5261 ;; The 'configure' script doesn't recognize things like
5262 ;; '--enable-fast-install'.
5263 (invoke "./configure"
5264 (string-append "--build-prefix=" (getcwd) "/build")
5265 (string-append "--prefix=" out))
5267 (add-after 'unpack 'enter-dir
5268 (lambda _ (chdir "ngs-sdk") #t)))))
5269 (native-inputs `(("perl" ,perl)))
5270 ;; According to the test
5271 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
5272 ;; in ngs-sdk/setup/konfigure.perl
5273 (supported-systems '("i686-linux" "x86_64-linux"))
5274 (home-page "https://github.com/ncbi/ngs")
5275 (synopsis "API for accessing Next Generation Sequencing data")
5277 "NGS is a domain-specific API for accessing reads, alignments and pileups
5278 produced from Next Generation Sequencing. The API itself is independent from
5279 any particular back-end implementation, and supports use of multiple back-ends
5281 (license license:public-domain)))
5283 (define-public java-ngs
5284 (package (inherit ngs-sdk)
5287 `(,@(substitute-keyword-arguments
5288 `(#:modules ((guix build gnu-build-system)
5292 ,@(package-arguments ngs-sdk))
5294 `(modify-phases ,phases
5295 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5297 `(("jdk" ,icedtea "jdk")
5298 ("ngs-sdk" ,ngs-sdk)))
5299 (synopsis "Java bindings for NGS SDK")))
5301 (define-public ncbi-vdb
5308 (url "https://github.com/ncbi/ncbi-vdb.git")
5310 (file-name (git-file-name name version))
5313 "1l4ny67nxwv1lagk9wwjbrgm7ln7adci6dnpc7k1yaln6shj0qpm"))))
5314 (build-system gnu-build-system)
5316 `(#:parallel-build? #f ; not supported
5317 #:tests? #f ; no "check" target
5319 (modify-phases %standard-phases
5320 (add-after 'unpack 'make-files-writable
5321 (lambda _ (for-each make-file-writable (find-files "." ".*")) #t))
5322 (add-before 'configure 'set-perl-search-path
5324 ;; Work around "dotless @INC" build failure.
5326 (string-append (getcwd) "/setup:"
5327 (getenv "PERL5LIB")))
5330 (lambda* (#:key inputs outputs #:allow-other-keys)
5331 (let ((out (assoc-ref outputs "out")))
5332 ;; Override include path for libmagic
5333 (substitute* "setup/package.prl"
5334 (("name => 'magic', Include => '/usr/include'")
5335 (string-append "name=> 'magic', Include => '"
5336 (assoc-ref inputs "libmagic")
5339 ;; Install kdf5 library (needed by sra-tools)
5340 (substitute* "build/Makefile.install"
5341 (("LIBRARIES_TO_INSTALL =")
5342 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5344 (substitute* "build/Makefile.env"
5345 (("CFLAGS =" prefix)
5346 (string-append prefix "-msse2 ")))
5348 ;; Override search path for ngs-java
5349 (substitute* "setup/package.prl"
5350 (("/usr/local/ngs/ngs-java")
5351 (assoc-ref inputs "java-ngs")))
5353 ;; The 'configure' script doesn't recognize things like
5354 ;; '--enable-fast-install'.
5355 (invoke "./configure"
5356 (string-append "--build-prefix=" (getcwd) "/build")
5357 (string-append "--prefix=" (assoc-ref outputs "out"))
5358 (string-append "--debug")
5359 (string-append "--with-xml2-prefix="
5360 (assoc-ref inputs "libxml2"))
5361 (string-append "--with-ngs-sdk-prefix="
5362 (assoc-ref inputs "ngs-sdk"))
5363 (string-append "--with-hdf5-prefix="
5364 (assoc-ref inputs "hdf5")))
5366 (add-after 'install 'install-interfaces
5367 (lambda* (#:key outputs #:allow-other-keys)
5368 ;; Install interface libraries. On i686 the interface libraries
5369 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5370 ;; architecture name ("i386") instead of the target system prefix
5372 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5373 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5374 ,(system->linux-architecture
5375 (or (%current-target-system)
5378 (string-append (assoc-ref outputs "out")
5380 ;; Install interface headers
5381 (copy-recursively "interfaces"
5382 (string-append (assoc-ref outputs "out")
5385 ;; These files are needed by sra-tools.
5386 (add-after 'install 'install-configuration-files
5387 (lambda* (#:key outputs #:allow-other-keys)
5388 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5390 (install-file "libs/kfg/default.kfg" target)
5391 (install-file "libs/kfg/certs.kfg" target))
5394 `(("libxml2" ,libxml2)
5395 ("ngs-sdk" ,ngs-sdk)
5396 ("java-ngs" ,java-ngs)
5399 (native-inputs `(("perl" ,perl)))
5400 ;; NCBI-VDB requires SSE capability.
5401 (supported-systems '("i686-linux" "x86_64-linux"))
5402 (home-page "https://github.com/ncbi/ncbi-vdb")
5403 (synopsis "Database engine for genetic information")
5405 "The NCBI-VDB library implements a highly compressed columnar data
5406 warehousing engine that is most often used to store genetic information.
5407 Databases are stored in a portable image within the file system, and can be
5408 accessed/downloaded on demand across HTTP.")
5409 (license license:public-domain)))
5411 (define-public plink
5419 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5420 version "-src.zip"))
5422 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5423 (patches (search-patches "plink-1.07-unclobber-i.patch"
5424 "plink-endian-detection.patch"))))
5425 (build-system gnu-build-system)
5427 '(#:tests? #f ;no "check" target
5428 #:make-flags (list (string-append "LIB_LAPACK="
5429 (assoc-ref %build-inputs "lapack")
5430 "/lib/liblapack.so")
5433 ;; disable phoning home
5436 (modify-phases %standard-phases
5437 ;; no "configure" script
5440 (lambda* (#:key outputs #:allow-other-keys)
5441 (let ((bin (string-append (assoc-ref outputs "out")
5443 (install-file "plink" bin)
5447 ("lapack" ,lapack)))
5449 `(("unzip" ,unzip)))
5450 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5451 (synopsis "Whole genome association analysis toolset")
5453 "PLINK is a whole genome association analysis toolset, designed to
5454 perform a range of basic, large-scale analyses in a computationally efficient
5455 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5456 so there is no support for steps prior to this (e.g. study design and
5457 planning, generating genotype or CNV calls from raw data). Through
5458 integration with gPLINK and Haploview, there is some support for the
5459 subsequent visualization, annotation and storage of results.")
5460 ;; Code is released under GPLv2, except for fisher.h, which is under
5462 (license (list license:gpl2 license:lgpl2.1+))))
5464 (define-public plink-ng
5465 (package (inherit plink)
5472 (url "https://github.com/chrchang/plink-ng.git")
5473 (commit (string-append "v" version))))
5474 (file-name (git-file-name name version))
5476 (base32 "02npdwgkpfkdnhw819rhj5kw02a5k5m90b14zq9zzya4hyg929c0"))))
5477 (build-system gnu-build-system)
5479 '(#:tests? #f ;no "check" target
5480 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5481 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5483 "-f" "Makefile.std")
5485 (modify-phases %standard-phases
5486 (add-after 'unpack 'chdir
5487 (lambda _ (chdir "1.9") #t))
5488 (delete 'configure) ; no "configure" script
5490 (lambda* (#:key outputs #:allow-other-keys)
5491 (let ((bin (string-append (assoc-ref outputs "out")
5493 (install-file "plink" bin)
5498 ("openblas" ,openblas)))
5499 (home-page "https://www.cog-genomics.org/plink/")
5500 (license license:gpl3+)))
5502 (define-public smithlab-cpp
5503 (let ((revision "1")
5504 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
5506 (name "smithlab-cpp")
5507 (version (string-append "0." revision "." (string-take commit 7)))
5511 (url "https://github.com/smithlabcode/smithlab_cpp.git")
5513 (file-name (string-append name "-" version "-checkout"))
5516 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
5517 (build-system gnu-build-system)
5519 `(#:modules ((guix build gnu-build-system)
5522 #:tests? #f ;no "check" target
5524 (modify-phases %standard-phases
5525 (add-after 'unpack 'use-samtools-headers
5527 (substitute* '("SAM.cpp"
5529 (("sam.h") "samtools/sam.h"))
5532 (lambda* (#:key outputs #:allow-other-keys)
5533 (let* ((out (assoc-ref outputs "out"))
5534 (lib (string-append out "/lib"))
5535 (include (string-append out "/include/smithlab-cpp")))
5538 (for-each (cut install-file <> lib)
5539 (find-files "." "\\.o$"))
5540 (for-each (cut install-file <> include)
5541 (find-files "." "\\.hpp$")))
5543 (delete 'configure))))
5545 `(("samtools" ,samtools-0.1)
5547 (home-page "https://github.com/smithlabcode/smithlab_cpp")
5548 (synopsis "C++ helper library for functions used in Smith lab projects")
5550 "Smithlab CPP is a C++ library that includes functions used in many of
5551 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
5552 structures, classes for genomic regions, mapped sequencing reads, etc.")
5553 (license license:gpl3+))))
5555 (define-public preseq
5561 (uri (string-append "https://github.com/smithlabcode/preseq/"
5562 "releases/download/v" version
5563 "/preseq_v" version ".tar.bz2"))
5565 (base32 "149x9xmk1wy1gff85325yfzqc0qk4sgp1w6gbyj9cnji4x1dszbl"))
5566 (modules '((guix build utils)))
5568 ;; Remove bundled samtools.
5569 (delete-file-recursively "samtools")
5571 (build-system gnu-build-system)
5573 `(#:tests? #f ;no "check" target
5575 (modify-phases %standard-phases
5576 (delete 'configure))
5578 (list (string-append "PREFIX="
5579 (assoc-ref %outputs "out"))
5580 (string-append "LIBBAM="
5581 (assoc-ref %build-inputs "samtools")
5583 (string-append "SMITHLAB_CPP="
5584 (assoc-ref %build-inputs "smithlab-cpp")
5587 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
5590 ("samtools" ,samtools-0.1)
5591 ("smithlab-cpp" ,smithlab-cpp)
5593 (home-page "http://smithlabresearch.org/software/preseq/")
5594 (synopsis "Program for analyzing library complexity")
5596 "The preseq package is aimed at predicting and estimating the complexity
5597 of a genomic sequencing library, equivalent to predicting and estimating the
5598 number of redundant reads from a given sequencing depth and how many will be
5599 expected from additional sequencing using an initial sequencing experiment.
5600 The estimates can then be used to examine the utility of further sequencing,
5601 optimize the sequencing depth, or to screen multiple libraries to avoid low
5602 complexity samples.")
5603 (license license:gpl3+)))
5605 (define-public python-screed
5607 (name "python-screed")
5612 (uri (pypi-uri "screed" version))
5615 "148vcb7w2wr6a4w6vs2bsxanbqibxfk490zbcbg4m61s8669zdjx"))))
5616 (build-system python-build-system)
5619 (modify-phases %standard-phases
5620 ;; Tests must be run after installation, as the "screed" command does
5621 ;; not exist right after building.
5623 (add-after 'install 'check
5624 (lambda* (#:key inputs outputs #:allow-other-keys)
5625 (let ((out (assoc-ref outputs "out")))
5626 (setenv "PYTHONPATH"
5627 (string-append out "/lib/python"
5628 (string-take (string-take-right
5629 (assoc-ref inputs "python")
5632 (getenv "PYTHONPATH")))
5633 (setenv "PATH" (string-append out "/bin:" (getenv "PATH"))))
5634 (invoke "python" "setup.py" "test")
5637 `(("python-pytest" ,python-pytest)
5638 ("python-pytest-cov" ,python-pytest-cov)
5639 ("python-pytest-runner" ,python-pytest-runner)))
5641 `(("python-bz2file" ,python-bz2file)))
5642 (home-page "https://github.com/dib-lab/screed/")
5643 (synopsis "Short read sequence database utilities")
5644 (description "Screed parses FASTA and FASTQ files and generates databases.
5645 Values such as sequence name, sequence description, sequence quality and the
5646 sequence itself can be retrieved from these databases.")
5647 (license license:bsd-3)))
5649 (define-public python2-screed
5650 (package-with-python2 python-screed))
5652 (define-public sra-tools
5660 (url "https://github.com/ncbi/sra-tools.git")
5662 (file-name (git-file-name name version))
5665 "0663gcdxkziwsmlznjxysb00621rllpbz6jwsfifq7z3dj3lwm8b"))))
5666 (build-system gnu-build-system)
5668 `(#:parallel-build? #f ; not supported
5669 #:tests? #f ; no "check" target
5671 (list (string-append "DEFAULT_CRT="
5672 (assoc-ref %build-inputs "ncbi-vdb")
5674 (string-append "DEFAULT_KFG="
5675 (assoc-ref %build-inputs "ncbi-vdb")
5677 (string-append "VDB_LIBDIR="
5678 (assoc-ref %build-inputs "ncbi-vdb")
5679 ,(if (string-prefix? "x86_64"
5680 (or (%current-target-system)
5685 (modify-phases %standard-phases
5686 (add-before 'configure 'set-perl-search-path
5688 ;; Work around "dotless @INC" build failure.
5690 (string-append (getcwd) "/setup:"
5691 (getenv "PERL5LIB")))
5694 (lambda* (#:key inputs outputs #:allow-other-keys)
5695 ;; The build system expects a directory containing the sources and
5696 ;; raw build output of ncbi-vdb, including files that are not
5697 ;; installed. Since we are building against an installed version of
5698 ;; ncbi-vdb, the following modifications are needed.
5699 (substitute* "setup/konfigure.perl"
5700 ;; Make the configure script look for the "ilib" directory of
5701 ;; "ncbi-vdb" without first checking for the existence of a
5702 ;; matching library in its "lib" directory.
5703 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5704 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5705 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5706 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5707 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
5710 (substitute* "tools/copycat/Makefile"
5711 (("smagic-static") "lmagic"))
5713 ;; The 'configure' script doesn't recognize things like
5714 ;; '--enable-fast-install'.
5715 (invoke "./configure"
5716 (string-append "--build-prefix=" (getcwd) "/build")
5717 (string-append "--prefix=" (assoc-ref outputs "out"))
5718 (string-append "--debug")
5719 (string-append "--with-fuse-prefix="
5720 (assoc-ref inputs "fuse"))
5721 (string-append "--with-magic-prefix="
5722 (assoc-ref inputs "libmagic"))
5723 ;; TODO: building with libxml2 fails with linker errors
5724 ;; (string-append "--with-xml2-prefix="
5725 ;; (assoc-ref inputs "libxml2"))
5726 (string-append "--with-ncbi-vdb-sources="
5727 (assoc-ref inputs "ncbi-vdb"))
5728 (string-append "--with-ncbi-vdb-build="
5729 (assoc-ref inputs "ncbi-vdb"))
5730 (string-append "--with-ngs-sdk-prefix="
5731 (assoc-ref inputs "ngs-sdk"))
5732 (string-append "--with-hdf5-prefix="
5733 (assoc-ref inputs "hdf5")))
5735 (native-inputs `(("perl" ,perl)))
5737 `(("ngs-sdk" ,ngs-sdk)
5738 ("ncbi-vdb" ,ncbi-vdb)
5743 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
5744 (synopsis "Tools and libraries for reading and writing sequencing data")
5746 "The SRA Toolkit from NCBI is a collection of tools and libraries for
5747 reading of sequencing files from the Sequence Read Archive (SRA) database and
5748 writing files into the .sra format.")
5749 (license license:public-domain)))
5751 (define-public seqan
5757 (uri (string-append "https://github.com/seqan/seqan/releases/"
5758 "download/seqan-v" version
5759 "/seqan-library-" version ".tar.xz"))
5762 "19a1rlxx03qy1i1iriicly68w64yjxbv24g9gdywnfmq998v35yx"))))
5763 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5764 ;; makes sense to split the outputs.
5765 (outputs '("out" "doc"))
5766 (build-system trivial-build-system)
5768 `(#:modules ((guix build utils))
5771 (use-modules (guix build utils))
5772 (let ((tar (assoc-ref %build-inputs "tar"))
5773 (xz (assoc-ref %build-inputs "xz"))
5774 (out (assoc-ref %outputs "out"))
5775 (doc (assoc-ref %outputs "doc")))
5776 (setenv "PATH" (string-append tar "/bin:" xz "/bin"))
5777 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
5778 (chdir (string-append "seqan-library-" ,version))
5779 (copy-recursively "include" (string-append out "/include"))
5780 (copy-recursively "share" (string-append doc "/share"))
5783 `(("source" ,source)
5786 (home-page "http://www.seqan.de")
5787 (synopsis "Library for nucleotide sequence analysis")
5789 "SeqAn is a C++ library of efficient algorithms and data structures for
5790 the analysis of sequences with the focus on biological data. It contains
5791 algorithms and data structures for string representation and their
5792 manipulation, online and indexed string search, efficient I/O of
5793 bioinformatics file formats, sequence alignment, and more.")
5794 (license license:bsd-3)))
5796 (define-public seqan-1
5797 (package (inherit seqan)
5802 (uri (string-append "http://packages.seqan.de/seqan-library/"
5803 "seqan-library-" version ".tar.bz2"))
5806 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
5807 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5808 ;; makes sense to split the outputs.
5809 (outputs '("out" "doc"))
5810 (build-system trivial-build-system)
5812 `(#:modules ((guix build utils))
5815 (use-modules (guix build utils))
5816 (let ((tar (assoc-ref %build-inputs "tar"))
5817 (bzip (assoc-ref %build-inputs "bzip2"))
5818 (out (assoc-ref %outputs "out"))
5819 (doc (assoc-ref %outputs "doc")))
5820 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
5821 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
5822 (chdir (string-append "seqan-library-" ,version))
5823 (copy-recursively "include" (string-append out "/include"))
5824 (copy-recursively "share" (string-append doc "/share"))
5827 `(("source" ,source)
5829 ("bzip2" ,bzip2)))))
5831 (define-public seqmagick
5838 (uri (pypi-uri "seqmagick" version))
5841 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
5842 (build-system python-build-system)
5844 `(("python-biopython" ,python-biopython)))
5846 `(("python-nose" ,python-nose)))
5847 (home-page "https://github.com/fhcrc/seqmagick")
5848 (synopsis "Tools for converting and modifying sequence files")
5850 "Bioinformaticians often have to convert sequence files between formats
5851 and do little manipulations on them, and it's not worth writing scripts for
5852 that. Seqmagick is a utility to expose the file format conversion in
5853 BioPython in a convenient way. Instead of having a big mess of scripts, there
5854 is one that takes arguments.")
5855 (license license:gpl3)))
5857 (define-public seqtk
5864 (url "https://github.com/lh3/seqtk.git")
5865 (commit (string-append "v" version))))
5866 (file-name (git-file-name name version))
5869 "1bfzlqa84b5s1qi22blmmw2s8xdyp9h9ydcq22pfjhh5gab3yz6l"))))
5870 (build-system gnu-build-system)
5873 (modify-phases %standard-phases
5876 ;; There are no tests, so we just run a sanity check.
5877 (lambda _ (invoke "./seqtk" "seq") #t))
5879 (lambda* (#:key outputs #:allow-other-keys)
5880 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5881 (install-file "seqtk" bin)
5885 (home-page "https://github.com/lh3/seqtk")
5886 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
5888 "Seqtk is a fast and lightweight tool for processing sequences in the
5889 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
5890 optionally compressed by gzip.")
5891 (license license:expat)))
5893 (define-public snap-aligner
5895 (name "snap-aligner")
5896 (version "1.0beta.18")
5900 (url "https://github.com/amplab/snap.git")
5901 (commit (string-append "v" version))))
5902 (file-name (git-file-name name version))
5905 "01w3qq4wm07z73vky0cfwlmrbf50n3w722cxrlzxfi99mnb808d8"))))
5906 (build-system gnu-build-system)
5909 (modify-phases %standard-phases
5911 (replace 'check (lambda _ (invoke "./unit_tests") #t))
5913 (lambda* (#:key outputs #:allow-other-keys)
5914 (let* ((out (assoc-ref outputs "out"))
5915 (bin (string-append out "/bin")))
5916 (install-file "snap-aligner" bin)
5917 (install-file "SNAPCommand" bin)
5921 (home-page "http://snap.cs.berkeley.edu/")
5922 (synopsis "Short read DNA sequence aligner")
5924 "SNAP is a fast and accurate aligner for short DNA reads. It is
5925 optimized for modern read lengths of 100 bases or higher, and takes advantage
5926 of these reads to align data quickly through a hash-based indexing scheme.")
5927 ;; 32-bit systems are not supported by the unpatched code.
5928 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
5929 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
5930 ;; systems without a lot of memory cannot make good use of this program.
5931 (supported-systems '("x86_64-linux"))
5932 (license license:asl2.0)))
5934 (define-public sortmerna
5942 (url "https://github.com/biocore/sortmerna.git")
5944 (file-name (git-file-name name version))
5947 "0j3mbz4n25738yijmjbr5r4fyvkgm8v5vn3sshyfvmyqf5q9byqf"))))
5948 (build-system gnu-build-system)
5949 (outputs '("out" ;for binaries
5950 "db")) ;for sequence databases
5953 (modify-phases %standard-phases
5955 (lambda* (#:key outputs #:allow-other-keys)
5956 (let* ((out (assoc-ref outputs "out"))
5957 (bin (string-append out "/bin"))
5958 (db (assoc-ref outputs "db"))
5960 (string-append db "/share/sortmerna/rRNA_databases")))
5961 (install-file "sortmerna" bin)
5962 (install-file "indexdb_rna" bin)
5963 (for-each (lambda (file)
5964 (install-file file share))
5965 (find-files "rRNA_databases" ".*fasta"))
5969 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
5970 (synopsis "Biological sequence analysis tool for NGS reads")
5972 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
5973 and operational taxonomic unit (OTU) picking of next generation
5974 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
5975 allows for fast and sensitive analyses of nucleotide sequences. The main
5976 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
5977 ;; The source includes x86 specific code
5978 (supported-systems '("x86_64-linux" "i686-linux"))
5979 (license license:lgpl3)))
5988 (url "https://github.com/alexdobin/STAR.git")
5990 (file-name (string-append name "-" version "-checkout"))
5993 "1lih6cbpvnvhyvvswdhy06mwyzvwax96m723378v4z6psqzsh11d"))
5994 (modules '((guix build utils)))
5997 (substitute* "source/Makefile"
5999 ;; Remove pre-built binaries and bundled htslib sources.
6000 (delete-file-recursively "bin/MacOSX_x86_64")
6001 (delete-file-recursively "bin/Linux_x86_64")
6002 (delete-file-recursively "bin/Linux_x86_64_static")
6003 (delete-file-recursively "source/htslib")
6005 (build-system gnu-build-system)
6007 '(#:tests? #f ;no check target
6008 #:make-flags '("STAR")
6010 (modify-phases %standard-phases
6011 (add-after 'unpack 'enter-source-dir
6012 (lambda _ (chdir "source") #t))
6013 (add-after 'enter-source-dir 'make-reproducible
6015 (substitute* "Makefile"
6016 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
6017 (string-append pre "Built with Guix" post)))
6019 ;; See https://github.com/alexdobin/STAR/pull/562
6020 (add-after 'enter-source-dir 'add-missing-header
6022 (substitute* "SoloReadFeature_inputRecords.cpp"
6023 (("#include \"binarySearch2.h\"" h)
6024 (string-append h "\n#include <math.h>")))
6026 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
6028 (substitute* "Makefile"
6029 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
6031 (substitute* '("BAMfunctions.cpp"
6036 "bamRemoveDuplicates.cpp")
6037 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
6038 (string-append "#include <" header ">")))
6039 (substitute* "IncludeDefine.h"
6040 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
6041 (string-append "<" header ">")))
6044 (lambda* (#:key outputs #:allow-other-keys)
6045 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6046 (install-file "STAR" bin))
6048 (delete 'configure))))
6052 `(("htslib" ,htslib)
6054 (home-page "https://github.com/alexdobin/STAR")
6055 (synopsis "Universal RNA-seq aligner")
6057 "The Spliced Transcripts Alignment to a Reference (STAR) software is
6058 based on a previously undescribed RNA-seq alignment algorithm that uses
6059 sequential maximum mappable seed search in uncompressed suffix arrays followed
6060 by seed clustering and stitching procedure. In addition to unbiased de novo
6061 detection of canonical junctions, STAR can discover non-canonical splices and
6062 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
6064 ;; Only 64-bit systems are supported according to the README.
6065 (supported-systems '("x86_64-linux" "mips64el-linux"))
6066 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
6067 (license license:gpl3+)))
6069 (define-public subread
6075 (uri (string-append "mirror://sourceforge/subread/subread-"
6076 version "/subread-" version "-source.tar.gz"))
6079 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
6080 (build-system gnu-build-system)
6082 `(#:tests? #f ;no "check" target
6083 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
6084 ;; optimizations by default, so we override these flags such that x86_64
6085 ;; flags are only added when the build target is an x86_64 system.
6087 (list (let ((system ,(or (%current-target-system)
6089 (flags '("-ggdb" "-fomit-frame-pointer"
6090 "-ffast-math" "-funroll-loops"
6091 "-fmessage-length=0"
6092 "-O9" "-Wall" "-DMAKE_FOR_EXON"
6094 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
6095 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
6096 (if (string-prefix? "x86_64" system)
6097 (string-append "CCFLAGS=" (string-join (append flags flags64)))
6098 (string-append "CCFLAGS=" (string-join flags))))
6099 "-f" "Makefile.Linux"
6100 "CC=gcc ${CCFLAGS}")
6102 (modify-phases %standard-phases
6103 (add-after 'unpack 'enter-dir
6104 (lambda _ (chdir "src") #t))
6106 (lambda* (#:key outputs #:allow-other-keys)
6107 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6109 (copy-recursively "../bin" bin))
6111 ;; no "configure" script
6112 (delete 'configure))))
6113 (inputs `(("zlib" ,zlib)))
6114 (home-page "http://bioinf.wehi.edu.au/subread-package/")
6115 (synopsis "Tool kit for processing next-gen sequencing data")
6117 "The subread package contains the following tools: subread aligner, a
6118 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
6119 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
6120 features; exactSNP: a SNP caller that discovers SNPs by testing signals
6121 against local background noises.")
6122 (license license:gpl3+)))
6124 (define-public stringtie
6130 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
6131 "stringtie-" version ".tar.gz"))
6134 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
6135 (modules '((guix build utils)))
6138 (delete-file-recursively "samtools-0.1.18")
6140 (build-system gnu-build-system)
6142 `(#:tests? #f ;no test suite
6144 (modify-phases %standard-phases
6145 ;; no configure script
6147 (add-before 'build 'use-system-samtools
6149 (substitute* "Makefile"
6150 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
6152 (substitute* '("gclib/GBam.h"
6154 (("#include \"(bam|sam|kstring).h\"" _ header)
6155 (string-append "#include <samtools/" header ".h>")))
6157 (add-after 'unpack 'remove-duplicate-typedef
6159 ;; This typedef conflicts with the typedef in
6160 ;; glibc-2.25/include/bits/types.h
6161 (substitute* "gclib/GThreads.h"
6162 (("typedef long long __intmax_t;") ""))
6165 (lambda* (#:key outputs #:allow-other-keys)
6166 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6167 (install-file "stringtie" bin)
6170 `(("samtools" ,samtools-0.1)
6172 (home-page "http://ccb.jhu.edu/software/stringtie/")
6173 (synopsis "Transcript assembly and quantification for RNA-Seq data")
6175 "StringTie is a fast and efficient assembler of RNA-Seq sequence
6176 alignments into potential transcripts. It uses a novel network flow algorithm
6177 as well as an optional de novo assembly step to assemble and quantitate
6178 full-length transcripts representing multiple splice variants for each gene
6179 locus. Its input can include not only the alignments of raw reads used by
6180 other transcript assemblers, but also alignments of longer sequences that have
6181 been assembled from those reads. To identify differentially expressed genes
6182 between experiments, StringTie's output can be processed either by the
6183 Cuffdiff or Ballgown programs.")
6184 (license license:artistic2.0)))
6186 (define-public taxtastic
6192 (uri (pypi-uri "taxtastic" version))
6195 "03pysw79lsrvz4lwzis88j15067ffqbi4cid5pqhrlxmd6bh8rrk"))))
6196 (build-system python-build-system)
6198 `(#:python ,python-2
6200 (modify-phases %standard-phases
6202 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t)))))
6204 `(("python-sqlalchemy" ,python2-sqlalchemy)
6205 ("python-decorator" ,python2-decorator)
6206 ("python-biopython" ,python2-biopython)
6207 ("python-pandas" ,python2-pandas)
6208 ("python-psycopg2" ,python2-psycopg2)
6209 ("python-fastalite" ,python2-fastalite)
6210 ("python-pyyaml" ,python2-pyyaml)
6211 ("python-six" ,python2-six)
6212 ("python-jinja2" ,python2-jinja2)
6213 ("python-dendropy" ,python2-dendropy)))
6214 (home-page "https://github.com/fhcrc/taxtastic")
6215 (synopsis "Tools for taxonomic naming and annotation")
6217 "Taxtastic is software written in python used to build and maintain
6218 reference packages i.e. collections of reference trees, reference alignments,
6219 profiles, and associated taxonomic information.")
6220 (license license:gpl3+)))
6222 (define-public vcftools
6229 "https://github.com/vcftools/vcftools/releases/download/v"
6230 version "/vcftools-" version ".tar.gz"))
6233 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
6234 (build-system gnu-build-system)
6236 `(#:tests? #f ; no "check" target
6238 "CFLAGS=-O2" ; override "-m64" flag
6239 (string-append "PREFIX=" (assoc-ref %outputs "out"))
6240 (string-append "MANDIR=" (assoc-ref %outputs "out")
6241 "/share/man/man1"))))
6243 `(("pkg-config" ,pkg-config)))
6247 (home-page "https://vcftools.github.io/")
6248 (synopsis "Tools for working with VCF files")
6250 "VCFtools is a program package designed for working with VCF files, such
6251 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
6252 provide easily accessible methods for working with complex genetic variation
6253 data in the form of VCF files.")
6254 ;; The license is declared as LGPLv3 in the README and
6255 ;; at https://vcftools.github.io/license.html
6256 (license license:lgpl3)))
6258 (define-public infernal
6264 (uri (string-append "http://eddylab.org/software/infernal/"
6265 "infernal-" version ".tar.gz"))
6268 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
6269 (build-system gnu-build-system)
6271 `(("perl" ,perl))) ; for tests
6272 (home-page "http://eddylab.org/infernal/")
6273 (synopsis "Inference of RNA alignments")
6274 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
6275 searching DNA sequence databases for RNA structure and sequence similarities.
6276 It is an implementation of a special case of profile stochastic context-free
6277 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
6278 profile, but it scores a combination of sequence consensus and RNA secondary
6279 structure consensus, so in many cases, it is more capable of identifying RNA
6280 homologs that conserve their secondary structure more than their primary
6282 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
6283 (supported-systems '("i686-linux" "x86_64-linux"))
6284 (license license:bsd-3)))
6286 (define-public r-scde
6293 (url "https://github.com/hms-dbmi/scde.git")
6295 (file-name (git-file-name name version))
6298 "10na2gyka24mszdxf92wz9h2c13hdf1ww30c68gfsw53lvvhhhxb"))))
6299 (build-system r-build-system)
6301 `(("r-rcpp" ,r-rcpp)
6302 ("r-rcpparmadillo" ,r-rcpparmadillo)
6305 ("r-rjson" ,r-rjson)
6306 ("r-cairo" ,r-cairo)
6307 ("r-rcolorbrewer" ,r-rcolorbrewer)
6308 ("r-edger" ,r-edger)
6309 ("r-quantreg" ,r-quantreg)
6311 ("r-rmtstat" ,r-rmtstat)
6312 ("r-extremes" ,r-extremes)
6313 ("r-pcamethods" ,r-pcamethods)
6314 ("r-biocparallel" ,r-biocparallel)
6315 ("r-flexmix" ,r-flexmix)))
6316 (home-page "https://hms-dbmi.github.io/scde/")
6317 (synopsis "R package for analyzing single-cell RNA-seq data")
6318 (description "The SCDE package implements a set of statistical methods for
6319 analyzing single-cell RNA-seq data. SCDE fits individual error models for
6320 single-cell RNA-seq measurements. These models can then be used for
6321 assessment of differential expression between groups of cells, as well as
6322 other types of analysis. The SCDE package also contains the pagoda framework
6323 which applies pathway and gene set overdispersion analysis to identify aspects
6324 of transcriptional heterogeneity among single cells.")
6325 ;; See https://github.com/hms-dbmi/scde/issues/38
6326 (license license:gpl2)))
6328 (define-public r-centipede
6330 (name "r-centipede")
6334 (uri (string-append "http://download.r-forge.r-project.org/"
6335 "src/contrib/CENTIPEDE_" version ".tar.gz"))
6338 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
6339 (build-system r-build-system)
6340 (home-page "http://centipede.uchicago.edu/")
6341 (synopsis "Predict transcription factor binding sites")
6343 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
6344 of the genome that are bound by particular transcription factors. It starts
6345 by identifying a set of candidate binding sites, and then aims to classify the
6346 sites according to whether each site is bound or not bound by a transcription
6347 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
6348 between two different types of motif instances using as much relevant
6349 information as possible.")
6350 (license (list license:gpl2+ license:gpl3+))))
6352 (define-public r-genefilter
6354 (name "r-genefilter")
6359 (uri (bioconductor-uri "genefilter" version))
6362 "0p64s1n1627yafnp25wjr4b22p34lqw574fx2qg4s1m0lffh1z6i"))))
6363 (build-system r-build-system)
6365 `(("gfortran" ,gfortran)))
6367 `(("r-annotate" ,r-annotate)
6368 ("r-annotationdbi" ,r-annotationdbi)
6369 ("r-biobase" ,r-biobase)
6370 ("r-s4vectors" ,r-s4vectors)
6371 ("r-survival" ,r-survival)))
6372 (home-page "https://bioconductor.org/packages/genefilter")
6373 (synopsis "Filter genes from high-throughput experiments")
6375 "This package provides basic functions for filtering genes from
6376 high-throughput sequencing experiments.")
6377 (license license:artistic2.0)))
6379 (define-public r-deseq2
6386 (uri (bioconductor-uri "DESeq2" version))
6389 "0n5ah84mxn87p45drzy0wh2yknmzj1q5i6gv0v9vgg1lj7awb91r"))))
6390 (properties `((upstream-name . "DESeq2")))
6391 (build-system r-build-system)
6393 `(("r-biobase" ,r-biobase)
6394 ("r-biocgenerics" ,r-biocgenerics)
6395 ("r-biocparallel" ,r-biocparallel)
6396 ("r-genefilter" ,r-genefilter)
6397 ("r-geneplotter" ,r-geneplotter)
6398 ("r-genomicranges" ,r-genomicranges)
6399 ("r-ggplot2" ,r-ggplot2)
6400 ("r-hmisc" ,r-hmisc)
6401 ("r-iranges" ,r-iranges)
6402 ("r-locfit" ,r-locfit)
6404 ("r-rcpparmadillo" ,r-rcpparmadillo)
6405 ("r-s4vectors" ,r-s4vectors)
6406 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6407 (home-page "https://bioconductor.org/packages/DESeq2")
6408 (synopsis "Differential gene expression analysis")
6410 "This package provides functions to estimate variance-mean dependence in
6411 count data from high-throughput nucleotide sequencing assays and test for
6412 differential expression based on a model using the negative binomial
6414 (license license:lgpl3+)))
6416 (define-public r-dexseq
6423 (uri (bioconductor-uri "DEXSeq" version))
6426 "134znafy7hn38rp4nia4pglz56fz6nbkxrf7z2k1sajfsgxa1hs6"))))
6427 (properties `((upstream-name . "DEXSeq")))
6428 (build-system r-build-system)
6430 `(("r-annotationdbi" ,r-annotationdbi)
6431 ("r-biobase" ,r-biobase)
6432 ("r-biocgenerics" ,r-biocgenerics)
6433 ("r-biocparallel" ,r-biocparallel)
6434 ("r-biomart" ,r-biomart)
6435 ("r-deseq2" ,r-deseq2)
6436 ("r-genefilter" ,r-genefilter)
6437 ("r-geneplotter" ,r-geneplotter)
6438 ("r-genomicranges" ,r-genomicranges)
6439 ("r-hwriter" ,r-hwriter)
6440 ("r-iranges" ,r-iranges)
6441 ("r-rcolorbrewer" ,r-rcolorbrewer)
6442 ("r-rsamtools" ,r-rsamtools)
6443 ("r-s4vectors" ,r-s4vectors)
6444 ("r-statmod" ,r-statmod)
6445 ("r-stringr" ,r-stringr)
6446 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6447 (home-page "https://bioconductor.org/packages/DEXSeq")
6448 (synopsis "Inference of differential exon usage in RNA-Seq")
6450 "This package is focused on finding differential exon usage using RNA-seq
6451 exon counts between samples with different experimental designs. It provides
6452 functions that allows the user to make the necessary statistical tests based
6453 on a model that uses the negative binomial distribution to estimate the
6454 variance between biological replicates and generalized linear models for
6455 testing. The package also provides functions for the visualization and
6456 exploration of the results.")
6457 (license license:gpl3+)))
6459 (define-public r-annotationforge
6461 (name "r-annotationforge")
6466 (uri (bioconductor-uri "AnnotationForge" version))
6469 "13yvhf3yskmvhs8szs6rkw93h81h5xqa3h19h91pp6nprhc8s3ll"))))
6471 `((upstream-name . "AnnotationForge")))
6472 (build-system r-build-system)
6474 `(("r-annotationdbi" ,r-annotationdbi)
6475 ("r-biobase" ,r-biobase)
6476 ("r-biocgenerics" ,r-biocgenerics)
6478 ("r-rcurl" ,r-rcurl)
6479 ("r-rsqlite" ,r-rsqlite)
6480 ("r-s4vectors" ,r-s4vectors)
6482 (home-page "https://bioconductor.org/packages/AnnotationForge")
6483 (synopsis "Code for building annotation database packages")
6485 "This package provides code for generating Annotation packages and their
6486 databases. Packages produced are intended to be used with AnnotationDbi.")
6487 (license license:artistic2.0)))
6489 (define-public r-rbgl
6496 (uri (bioconductor-uri "RBGL" version))
6499 "1l5x2icv9di1lr3gqfi0vjnyd9xc3l77yc42ippqd4cadj3d1pzf"))))
6500 (properties `((upstream-name . "RBGL")))
6501 (build-system r-build-system)
6502 (propagated-inputs `(("r-graph" ,r-graph)))
6503 (home-page "https://www.bioconductor.org/packages/RBGL")
6504 (synopsis "Interface to the Boost graph library")
6506 "This package provides a fairly extensive and comprehensive interface to
6507 the graph algorithms contained in the Boost library.")
6508 (license license:artistic2.0)))
6510 (define-public r-gseabase
6517 (uri (bioconductor-uri "GSEABase" version))
6520 "110al7x0ig8plzrprvhwc7xshi1jzpj2n8llhhg2fh6v6k0k6awr"))))
6521 (properties `((upstream-name . "GSEABase")))
6522 (build-system r-build-system)
6524 `(("r-annotate" ,r-annotate)
6525 ("r-annotationdbi" ,r-annotationdbi)
6526 ("r-biobase" ,r-biobase)
6527 ("r-biocgenerics" ,r-biocgenerics)
6528 ("r-graph" ,r-graph)
6530 (home-page "https://bioconductor.org/packages/GSEABase")
6531 (synopsis "Gene set enrichment data structures and methods")
6533 "This package provides classes and methods to support @dfn{Gene Set
6534 Enrichment Analysis} (GSEA).")
6535 (license license:artistic2.0)))
6537 (define-public r-category
6544 (uri (bioconductor-uri "Category" version))
6547 "1jdm83bwdfhpfm1y6hwgvxzj6l83h1bdkqv23799kzywnwm016kv"))))
6548 (properties `((upstream-name . "Category")))
6549 (build-system r-build-system)
6551 `(("r-annotate" ,r-annotate)
6552 ("r-annotationdbi" ,r-annotationdbi)
6553 ("r-biobase" ,r-biobase)
6554 ("r-biocgenerics" ,r-biocgenerics)
6555 ("r-genefilter" ,r-genefilter)
6556 ("r-graph" ,r-graph)
6557 ("r-gseabase" ,r-gseabase)
6558 ("r-matrix" ,r-matrix)
6561 (home-page "https://bioconductor.org/packages/Category")
6562 (synopsis "Category analysis")
6564 "This package provides a collection of tools for performing category
6566 (license license:artistic2.0)))
6568 (define-public r-gostats
6575 (uri (bioconductor-uri "GOstats" version))
6578 "0wlqqgfynwqnqhckhsfjwg9zkj6hkmzwd5y76dhqz720vy21rcln"))))
6579 (properties `((upstream-name . "GOstats")))
6580 (build-system r-build-system)
6582 `(("r-annotate" ,r-annotate)
6583 ("r-annotationdbi" ,r-annotationdbi)
6584 ("r-annotationforge" ,r-annotationforge)
6585 ("r-biobase" ,r-biobase)
6586 ("r-category" ,r-category)
6587 ("r-go-db" ,r-go-db)
6588 ("r-graph" ,r-graph)
6589 ("r-rgraphviz" ,r-rgraphviz)
6590 ("r-rbgl" ,r-rbgl)))
6591 (home-page "https://bioconductor.org/packages/GOstats")
6592 (synopsis "Tools for manipulating GO and microarrays")
6594 "This package provides a set of tools for interacting with GO and
6595 microarray data. A variety of basic manipulation tools for graphs, hypothesis
6596 testing and other simple calculations.")
6597 (license license:artistic2.0)))
6599 (define-public r-shortread
6601 (name "r-shortread")
6606 (uri (bioconductor-uri "ShortRead" version))
6609 "0iks123i1adkb9i2q4wvfqdmmj9dy867jvngj9757y8gj6xbcpy1"))))
6610 (properties `((upstream-name . "ShortRead")))
6611 (build-system r-build-system)
6615 `(("r-biobase" ,r-biobase)
6616 ("r-biocgenerics" ,r-biocgenerics)
6617 ("r-biocparallel" ,r-biocparallel)
6618 ("r-biostrings" ,r-biostrings)
6619 ("r-genomeinfodb" ,r-genomeinfodb)
6620 ("r-genomicalignments" ,r-genomicalignments)
6621 ("r-genomicranges" ,r-genomicranges)
6622 ("r-hwriter" ,r-hwriter)
6623 ("r-iranges" ,r-iranges)
6624 ("r-lattice" ,r-lattice)
6625 ("r-latticeextra" ,r-latticeextra)
6626 ("r-rsamtools" ,r-rsamtools)
6627 ("r-s4vectors" ,r-s4vectors)
6628 ("r-xvector" ,r-xvector)
6629 ("r-zlibbioc" ,r-zlibbioc)))
6630 (home-page "https://bioconductor.org/packages/ShortRead")
6631 (synopsis "FASTQ input and manipulation tools")
6633 "This package implements sampling, iteration, and input of FASTQ files.
6634 It includes functions for filtering and trimming reads, and for generating a
6635 quality assessment report. Data are represented as
6636 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6637 purposes. The package also contains legacy support for early single-end,
6638 ungapped alignment formats.")
6639 (license license:artistic2.0)))
6641 (define-public r-systempiper
6643 (name "r-systempiper")
6648 (uri (bioconductor-uri "systemPipeR" version))
6651 "0qzydz87rld2nhwzbfgrw5jfgh8maa9y54mjx9c4285m11qj2shq"))))
6652 (properties `((upstream-name . "systemPipeR")))
6653 (build-system r-build-system)
6655 `(("r-annotate" ,r-annotate)
6656 ("r-batchjobs" ,r-batchjobs)
6657 ("r-biocgenerics" ,r-biocgenerics)
6658 ("r-biostrings" ,r-biostrings)
6659 ("r-deseq2" ,r-deseq2)
6660 ("r-edger" ,r-edger)
6661 ("r-genomicfeatures" ,r-genomicfeatures)
6662 ("r-genomicranges" ,r-genomicranges)
6663 ("r-ggplot2" ,r-ggplot2)
6664 ("r-go-db" ,r-go-db)
6665 ("r-gostats" ,r-gostats)
6666 ("r-limma" ,r-limma)
6667 ("r-pheatmap" ,r-pheatmap)
6668 ("r-rjson" ,r-rjson)
6669 ("r-rsamtools" ,r-rsamtools)
6670 ("r-shortread" ,r-shortread)
6671 ("r-summarizedexperiment" ,r-summarizedexperiment)
6672 ("r-variantannotation" ,r-variantannotation)))
6673 (home-page "https://github.com/tgirke/systemPipeR")
6674 (synopsis "Next generation sequencing workflow and reporting environment")
6676 "This R package provides tools for building and running automated
6677 end-to-end analysis workflows for a wide range of @dfn{next generation
6678 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6679 Important features include a uniform workflow interface across different NGS
6680 applications, automated report generation, and support for running both R and
6681 command-line software, such as NGS aligners or peak/variant callers, on local
6682 computers or compute clusters. Efficient handling of complex sample sets and
6683 experimental designs is facilitated by a consistently implemented sample
6684 annotation infrastructure.")
6685 (license license:artistic2.0)))
6687 (define-public r-grohmm
6694 (uri (bioconductor-uri "groHMM" version))
6697 "1ph92fv44b90v7mk4b1mjvv0dlrhl8ba01klxbnd0vs4qn9zxplh"))))
6698 (properties `((upstream-name . "groHMM")))
6699 (build-system r-build-system)
6701 `(("r-genomeinfodb" ,r-genomeinfodb)
6702 ("r-genomicalignments" ,r-genomicalignments)
6703 ("r-genomicranges" ,r-genomicranges)
6704 ("r-iranges" ,r-iranges)
6706 ("r-rtracklayer" ,r-rtracklayer)
6707 ("r-s4vectors" ,r-s4vectors)))
6708 (home-page "https://github.com/Kraus-Lab/groHMM")
6709 (synopsis "GRO-seq analysis pipeline")
6711 "This package provides a pipeline for the analysis of GRO-seq data.")
6712 (license license:gpl3+)))
6714 (define-public r-sparql
6720 (uri (cran-uri "SPARQL" version))
6723 "0gak1q06yyhdmcxb2n3v0h9gr1vqd0viqji52wpw211qp6r6dcrc"))))
6724 (properties `((upstream-name . "SPARQL")))
6725 (build-system r-build-system)
6727 `(("r-rcurl" ,r-rcurl)
6729 (home-page "https://cran.r-project.org/web/packages/SPARQL")
6730 (synopsis "SPARQL client for R")
6731 (description "This package provides an interface to use SPARQL to pose
6732 SELECT or UPDATE queries to an end-point.")
6733 ;; The only license indication is found in the DESCRIPTION file,
6734 ;; which states GPL-3. So we cannot assume GPLv3+.
6735 (license license:gpl3)))
6737 (define-public vsearch
6745 (url "https://github.com/torognes/vsearch.git")
6746 (commit (string-append "v" version))))
6747 (file-name (git-file-name name version))
6750 "0vhrpjfdf75ba04b24xknp41790cvcgwl0vgpy7qbzj5xh2521ss"))
6751 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
6754 ;; Remove bundled cityhash sources. The vsearch source is adjusted
6755 ;; for this in the patch.
6756 (delete-file "src/city.h")
6757 (delete-file "src/citycrc.h")
6758 (delete-file "src/city.cc")
6760 (build-system gnu-build-system)
6764 ("cityhash" ,cityhash)))
6766 `(("autoconf" ,autoconf)
6767 ("automake" ,automake)))
6768 (synopsis "Sequence search tools for metagenomics")
6770 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
6771 dereplication, pairwise alignment, shuffling, subsampling, sorting and
6772 masking. The tool takes advantage of parallelism in the form of SIMD
6773 vectorization as well as multiple threads to perform accurate alignments at
6774 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
6775 Needleman-Wunsch).")
6776 (home-page "https://github.com/torognes/vsearch")
6777 ;; vsearch uses non-portable SSE intrinsics so building fails on other
6779 (supported-systems '("x86_64-linux"))
6780 ;; Dual licensed; also includes public domain source.
6781 (license (list license:gpl3 license:bsd-2))))
6783 (define-public pardre
6786 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
6791 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
6795 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
6796 (build-system gnu-build-system)
6798 `(#:tests? #f ; no tests included
6800 (modify-phases %standard-phases
6803 (lambda* (#:key outputs #:allow-other-keys)
6804 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
6805 (install-file "ParDRe" bin)
6808 `(("openmpi" ,openmpi)
6810 (synopsis "Parallel tool to remove duplicate DNA reads")
6812 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
6813 Duplicate reads can be seen as identical or nearly identical sequences with
6814 some mismatches. This tool lets users avoid the analysis of unnecessary
6815 reads, reducing the time of subsequent procedures with the
6816 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
6817 in order to exploit the parallel capabilities of multicore clusters. It is
6818 faster than multithreaded counterparts (end of 2015) for the same number of
6819 cores and, thanks to the message-passing technology, it can be executed on
6821 (home-page "https://sourceforge.net/projects/pardre/")
6822 (license license:gpl3+)))
6824 (define-public ruby-bio-kseq
6826 (name "ruby-bio-kseq")
6831 (uri (rubygems-uri "bio-kseq" version))
6834 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
6835 (build-system ruby-build-system)
6837 `(#:test-target "spec"))
6839 `(("bundler" ,bundler)
6840 ("ruby-rspec" ,ruby-rspec)
6841 ("ruby-rake-compiler" ,ruby-rake-compiler)))
6844 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
6846 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
6847 FASTQ parsing code. It provides a fast iterator over sequences and their
6849 (home-page "https://github.com/gusevfe/bio-kseq")
6850 (license license:expat)))
6852 (define-public bio-locus
6859 (uri (rubygems-uri "bio-locus" version))
6862 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
6863 (build-system ruby-build-system)
6865 `(("ruby-rspec" ,ruby-rspec)))
6866 (synopsis "Tool for fast querying of genome locations")
6868 "Bio-locus is a tabix-like tool for fast querying of genome
6869 locations. Many file formats in bioinformatics contain records that
6870 start with a chromosome name and a position for a SNP, or a start-end
6871 position for indels. Bio-locus allows users to store this chr+pos or
6872 chr+pos+alt information in a database.")
6873 (home-page "https://github.com/pjotrp/bio-locus")
6874 (license license:expat)))
6876 (define-public bio-blastxmlparser
6878 (name "bio-blastxmlparser")
6882 (uri (rubygems-uri "bio-blastxmlparser" version))
6885 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
6886 (build-system ruby-build-system)
6888 `(("ruby-bio-logger" ,ruby-bio-logger)
6889 ("ruby-nokogiri" ,ruby-nokogiri)))
6891 `(("ruby-rspec" ,ruby-rspec)))
6892 (synopsis "Fast big data BLAST XML parser and library")
6894 "Very fast parallel big-data BLAST XML file parser which can be used as
6895 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
6896 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
6897 (home-page "https://github.com/pjotrp/blastxmlparser")
6898 (license license:expat)))
6900 (define-public bioruby
6907 (uri (rubygems-uri "bio" version))
6910 "1d56amdsjv1mag7m6gv2w0xij8hqx1v5xbdjsix8sp3yp36m7938"))))
6911 (build-system ruby-build-system)
6913 `(("ruby-libxml" ,ruby-libxml)))
6915 `(("which" ,which))) ; required for test phase
6918 (modify-phases %standard-phases
6919 (add-before 'build 'patch-test-command
6921 (substitute* '("test/functional/bio/test_command.rb")
6922 (("/bin/sh") (which "sh")))
6923 (substitute* '("test/functional/bio/test_command.rb")
6924 (("/bin/ls") (which "ls")))
6925 (substitute* '("test/functional/bio/test_command.rb")
6926 (("which") (which "which")))
6927 (substitute* '("test/functional/bio/test_command.rb",
6928 "test/data/command/echoarg2.sh")
6929 (("/bin/echo") (which "echo")))
6931 (synopsis "Ruby library, shell and utilities for bioinformatics")
6932 (description "BioRuby comes with a comprehensive set of Ruby development
6933 tools and libraries for bioinformatics and molecular biology. BioRuby has
6934 components for sequence analysis, pathway analysis, protein modelling and
6935 phylogenetic analysis; it supports many widely used data formats and provides
6936 easy access to databases, external programs and public web services, including
6937 BLAST, KEGG, GenBank, MEDLINE and GO.")
6938 (home-page "http://bioruby.org/")
6939 ;; Code is released under Ruby license, except for setup
6940 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
6941 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
6943 (define-public r-acsnminer
6945 (name "r-acsnminer")
6946 (version "0.16.8.25")
6949 (uri (cran-uri "ACSNMineR" version))
6952 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
6953 (properties `((upstream-name . "ACSNMineR")))
6954 (build-system r-build-system)
6956 `(("r-ggplot2" ,r-ggplot2)
6957 ("r-gridextra" ,r-gridextra)))
6958 (home-page "https://cran.r-project.org/web/packages/ACSNMineR")
6959 (synopsis "Gene enrichment analysis")
6961 "This package provides tools to compute and represent gene set enrichment
6962 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
6963 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
6964 enrichment can be run with hypergeometric test or Fisher exact test, and can
6965 use multiple corrections. Visualization of data can be done either by
6966 barplots or heatmaps.")
6967 (license license:gpl2+)))
6969 (define-public r-biocinstaller
6971 (name "r-biocinstaller")
6975 (uri (bioconductor-uri "BiocInstaller" version))
6978 "1s1f9qhyf3mc73ir25x2zlgi9hf45a37lg4z8fbva4i21hqisgsl"))))
6980 `((upstream-name . "BiocInstaller")))
6981 (build-system r-build-system)
6982 (home-page "https://bioconductor.org/packages/BiocInstaller")
6983 (synopsis "Install Bioconductor packages")
6984 (description "This package is used to install and update R packages from
6985 Bioconductor, CRAN, and Github.")
6986 (license license:artistic2.0)))
6988 (define-public r-biocviews
6990 (name "r-biocviews")
6994 (uri (bioconductor-uri "biocViews" version))
6997 "06ms82pyc5rxbd9crfvqjxcwpafv0c627i83v80d12925mrc51h8"))))
6999 `((upstream-name . "biocViews")))
7000 (build-system r-build-system)
7002 `(("r-biobase" ,r-biobase)
7003 ("r-graph" ,r-graph)
7005 ("r-rcurl" ,r-rcurl)
7007 ("r-runit" ,r-runit)))
7008 (home-page "https://bioconductor.org/packages/biocViews")
7009 (synopsis "Bioconductor package categorization helper")
7010 (description "The purpose of biocViews is to create HTML pages that
7011 categorize packages in a Bioconductor package repository according to keywords,
7012 also known as views, in a controlled vocabulary.")
7013 (license license:artistic2.0)))
7015 (define-public r-bookdown
7021 (uri (cran-uri "bookdown" version))
7024 "0vg1s1w0l9pm95asqb21yf39mfk1nc9rdhmlys9xwr7p7i7rsz32"))))
7025 (build-system r-build-system)
7027 `(("r-htmltools" ,r-htmltools)
7028 ("r-knitr" ,r-knitr)
7029 ("r-rmarkdown" ,r-rmarkdown)
7030 ("r-tinytex" ,r-tinytex)
7032 ("r-xfun" ,r-xfun)))
7033 (home-page "https://github.com/rstudio/bookdown")
7034 (synopsis "Authoring books and technical documents with R markdown")
7035 (description "This package provides output formats and utilities for
7036 authoring books and technical documents with R Markdown.")
7037 (license license:gpl3)))
7039 (define-public r-biocstyle
7041 (name "r-biocstyle")
7045 (uri (bioconductor-uri "BiocStyle" version))
7048 "01lm8xljilj666fcl3wnw82dxkcxnlr294lddr553rm8xr5nwg31"))))
7050 `((upstream-name . "BiocStyle")))
7051 (build-system r-build-system)
7053 `(("r-biocmanager" ,r-biocmanager)
7054 ("r-bookdown" ,r-bookdown)
7055 ("r-knitr" ,r-knitr)
7056 ("r-rmarkdown" ,r-rmarkdown)
7057 ("r-yaml" ,r-yaml)))
7058 (home-page "https://bioconductor.org/packages/BiocStyle")
7059 (synopsis "Bioconductor formatting styles")
7060 (description "This package provides standard formatting styles for
7061 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
7063 (license license:artistic2.0)))
7065 (define-public r-bioccheck
7067 (name "r-bioccheck")
7071 (uri (bioconductor-uri "BiocCheck" version))
7074 "0zamvs5jar38293ff27imvwy0ra25y64ls9z8w3q1y4jcp8p8pg7"))))
7076 `((upstream-name . "BiocCheck")))
7077 (build-system r-build-system)
7080 (modify-phases %standard-phases
7081 ;; This package can be used by calling BiocCheck(<package>) from
7082 ;; within R, or by running R CMD BiocCheck <package>. This phase
7083 ;; makes sure the latter works. For this to work, the BiocCheck
7084 ;; script must be somewhere on the PATH (not the R bin directory).
7085 (add-after 'install 'install-bioccheck-subcommand
7086 (lambda* (#:key outputs #:allow-other-keys)
7087 (let* ((out (assoc-ref outputs "out"))
7088 (dest-dir (string-append out "/bin"))
7090 (string-append out "/site-library/BiocCheck/script/")))
7092 (symlink (string-append script-dir "/checkBadDeps.R")
7093 (string-append dest-dir "/checkBadDeps.R"))
7094 (symlink (string-append script-dir "/BiocCheck")
7095 (string-append dest-dir "/BiocCheck")))
7098 `(("r-codetools" ,r-codetools)
7099 ("r-graph" ,r-graph)
7101 ("r-knitr" ,r-knitr)
7102 ("r-optparse" ,r-optparse)
7103 ("r-biocmanager" ,r-biocmanager)
7104 ("r-biocviews" ,r-biocviews)
7105 ("r-stringdist" ,r-stringdist)))
7106 (home-page "https://bioconductor.org/packages/BiocCheck")
7107 (synopsis "Executes Bioconductor-specific package checks")
7108 (description "This package contains tools to perform additional quality
7109 checks on R packages that are to be submitted to the Bioconductor repository.")
7110 (license license:artistic2.0)))
7112 (define-public r-optparse
7119 (uri (cran-uri "optparse" version))
7122 "04vyb6dhcga30mvghsg1p052jmf69xqxkvh3hzqz7dscyppy76w1"))))
7123 (build-system r-build-system)
7125 `(("r-getopt" ,r-getopt)))
7127 "https://github.com/trevorld/optparse")
7128 (synopsis "Command line option parser")
7130 "This package provides a command line parser inspired by Python's
7131 @code{optparse} library to be used with Rscript to write shebang scripts
7132 that accept short and long options.")
7133 (license license:gpl2+)))
7135 (define-public r-s4vectors
7137 (name "r-s4vectors")
7141 (uri (bioconductor-uri "S4Vectors" version))
7144 "18whrw67nxn82xshckl2pjy7d14sa3c27h3n9naqyqwz88lr6dzg"))))
7146 `((upstream-name . "S4Vectors")))
7147 (build-system r-build-system)
7149 `(("r-biocgenerics" ,r-biocgenerics)))
7150 (home-page "https://bioconductor.org/packages/S4Vectors")
7151 (synopsis "S4 implementation of vectors and lists")
7153 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7154 classes and a set of generic functions that extend the semantic of ordinary
7155 vectors and lists in R. Package developers can easily implement vector-like
7156 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7157 In addition, a few low-level concrete subclasses of general interest (e.g.
7158 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7159 S4Vectors package itself.")
7160 (license license:artistic2.0)))
7162 (define-public r-seqinr
7169 (uri (cran-uri "seqinr" version))
7172 "17zv0n5cji17izwmwg0jcbxbjl3w5rls91w15svcnlpxjms38ahn"))))
7173 (build-system r-build-system)
7175 `(("r-ade4" ,r-ade4)
7176 ("r-segmented" ,r-segmented)))
7179 (home-page "http://seqinr.r-forge.r-project.org/")
7180 (synopsis "Biological sequences retrieval and analysis")
7182 "This package provides tools for exploratory data analysis and data
7183 visualization of biological sequence (DNA and protein) data. It also includes
7184 utilities for sequence data management under the ACNUC system.")
7185 (license license:gpl2+)))
7187 (define-public r-iranges
7193 (uri (bioconductor-uri "IRanges" version))
7196 "0ljppsk611xi72gc8mbdx1311b63b1ijd401jz5xmxk5frla1nc1"))))
7198 `((upstream-name . "IRanges")))
7199 (build-system r-build-system)
7201 `(("r-biocgenerics" ,r-biocgenerics)
7202 ("r-s4vectors" ,r-s4vectors)))
7203 (home-page "https://bioconductor.org/packages/IRanges")
7204 (synopsis "Infrastructure for manipulating intervals on sequences")
7206 "This package provides efficient low-level and highly reusable S4 classes
7207 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7208 generally, data that can be organized sequentially (formally defined as
7209 @code{Vector} objects), as well as views on these @code{Vector} objects.
7210 Efficient list-like classes are also provided for storing big collections of
7211 instances of the basic classes. All classes in the package use consistent
7212 naming and share the same rich and consistent \"Vector API\" as much as
7214 (license license:artistic2.0)))
7216 (define-public r-genomeinfodbdata
7218 (name "r-genomeinfodbdata")
7222 ;; We cannot use bioconductor-uri here because this tarball is
7223 ;; located under "data/annotation/" instead of "bioc/".
7224 (uri (string-append "https://bioconductor.org/packages/release/"
7225 "data/annotation/src/contrib/GenomeInfoDbData_"
7229 "0di6nlqpsyqf693k2na65ayqldih563x3zfrczpqc5q2hl5kg35c"))))
7231 `((upstream-name . "GenomeInfoDbData")))
7232 (build-system r-build-system)
7233 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7234 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7235 (description "This package contains data for mapping between NCBI taxonomy
7236 ID and species. It is used by functions in the GenomeInfoDb package.")
7237 (license license:artistic2.0)))
7239 (define-public r-genomeinfodb
7241 (name "r-genomeinfodb")
7245 (uri (bioconductor-uri "GenomeInfoDb" version))
7248 "07bm35jcczpyxap0b3gky4b28z38z423sngzsm19d9krjxr76b5p"))))
7250 `((upstream-name . "GenomeInfoDb")))
7251 (build-system r-build-system)
7253 `(("r-biocgenerics" ,r-biocgenerics)
7254 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7255 ("r-iranges" ,r-iranges)
7256 ("r-rcurl" ,r-rcurl)
7257 ("r-s4vectors" ,r-s4vectors)))
7258 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7259 (synopsis "Utilities for manipulating chromosome identifiers")
7261 "This package contains data and functions that define and allow
7262 translation between different chromosome sequence naming conventions (e.g.,
7263 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7264 names in their natural, rather than lexicographic, order.")
7265 (license license:artistic2.0)))
7267 (define-public r-edger
7273 (uri (bioconductor-uri "edgeR" version))
7276 "15yimsbsxmxhlsfmgw5j7fd8qn08zz4xqxrir1c6n2dc103y22xg"))))
7277 (properties `((upstream-name . "edgeR")))
7278 (build-system r-build-system)
7280 `(("r-limma" ,r-limma)
7281 ("r-locfit" ,r-locfit)
7283 ("r-statmod" ,r-statmod))) ;for estimateDisp
7284 (home-page "http://bioinf.wehi.edu.au/edgeR")
7285 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7286 (description "This package can do differential expression analysis of
7287 RNA-seq expression profiles with biological replication. It implements a range
7288 of statistical methodology based on the negative binomial distributions,
7289 including empirical Bayes estimation, exact tests, generalized linear models
7290 and quasi-likelihood tests. It be applied to differential signal analysis of
7291 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7293 (license license:gpl2+)))
7295 (define-public r-variantannotation
7297 (name "r-variantannotation")
7301 (uri (bioconductor-uri "VariantAnnotation" version))
7304 "19bxi5b9fzqdjadb8bfm8xsgi6nvrwbgn1xcpk59bnmv9vzjkwrh"))))
7306 `((upstream-name . "VariantAnnotation")))
7310 `(("r-annotationdbi" ,r-annotationdbi)
7311 ("r-biobase" ,r-biobase)
7312 ("r-biocgenerics" ,r-biocgenerics)
7313 ("r-biostrings" ,r-biostrings)
7314 ("r-bsgenome" ,r-bsgenome)
7316 ("r-genomeinfodb" ,r-genomeinfodb)
7317 ("r-genomicfeatures" ,r-genomicfeatures)
7318 ("r-genomicranges" ,r-genomicranges)
7319 ("r-iranges" ,r-iranges)
7320 ("r-summarizedexperiment" ,r-summarizedexperiment)
7321 ("r-rsamtools" ,r-rsamtools)
7322 ("r-rtracklayer" ,r-rtracklayer)
7323 ("r-s4vectors" ,r-s4vectors)
7324 ("r-xvector" ,r-xvector)
7325 ("r-zlibbioc" ,r-zlibbioc)))
7326 (build-system r-build-system)
7327 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7328 (synopsis "Package for annotation of genetic variants")
7329 (description "This R package can annotate variants, compute amino acid
7330 coding changes and predict coding outcomes.")
7331 (license license:artistic2.0)))
7333 (define-public r-limma
7339 (uri (bioconductor-uri "limma" version))
7342 "08va8jggmv61wym955mnb1n31mgikrmjys7dl1kp5hp3yia8jg7l"))))
7343 (build-system r-build-system)
7344 (home-page "http://bioinf.wehi.edu.au/limma")
7345 (synopsis "Package for linear models for microarray and RNA-seq data")
7346 (description "This package can be used for the analysis of gene expression
7347 studies, especially the use of linear models for analysing designed experiments
7348 and the assessment of differential expression. The analysis methods apply to
7349 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7350 (license license:gpl2+)))
7352 (define-public r-xvector
7358 (uri (bioconductor-uri "XVector" version))
7361 "01fph1ydd6g0rl5mcw54spx22glq2kqv7wyw8bqw0plmabzcwwdm"))))
7363 `((upstream-name . "XVector")))
7364 (build-system r-build-system)
7367 (modify-phases %standard-phases
7368 (add-after 'unpack 'use-system-zlib
7370 (substitute* "DESCRIPTION"
7371 (("zlibbioc, ") ""))
7372 (substitute* "NAMESPACE"
7373 (("import\\(zlibbioc\\)") ""))
7378 `(("r-biocgenerics" ,r-biocgenerics)
7379 ("r-iranges" ,r-iranges)
7380 ("r-s4vectors" ,r-s4vectors)))
7381 (home-page "https://bioconductor.org/packages/XVector")
7382 (synopsis "Representation and manpulation of external sequences")
7384 "This package provides memory efficient S4 classes for storing sequences
7385 \"externally\" (behind an R external pointer, or on disk).")
7386 (license license:artistic2.0)))
7388 (define-public r-genomicranges
7390 (name "r-genomicranges")
7394 (uri (bioconductor-uri "GenomicRanges" version))
7397 "0bgh14d15dpf2iy36qinw45r6n45rqkf0ghazrdl3jfva6vbrb29"))))
7399 `((upstream-name . "GenomicRanges")))
7400 (build-system r-build-system)
7402 `(("r-biocgenerics" ,r-biocgenerics)
7403 ("r-genomeinfodb" ,r-genomeinfodb)
7404 ("r-iranges" ,r-iranges)
7405 ("r-s4vectors" ,r-s4vectors)
7406 ("r-xvector" ,r-xvector)))
7407 (home-page "https://bioconductor.org/packages/GenomicRanges")
7408 (synopsis "Representation and manipulation of genomic intervals")
7410 "This package provides tools to efficiently represent and manipulate
7411 genomic annotations and alignments is playing a central role when it comes to
7412 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7413 GenomicRanges package defines general purpose containers for storing and
7414 manipulating genomic intervals and variables defined along a genome.")
7415 (license license:artistic2.0)))
7417 (define-public r-biobase
7423 (uri (bioconductor-uri "Biobase" version))
7426 "10nr6nrkj5vlq8hsgbhbhv669z0dbpz4m3vz9k32rx1czbrrqwin"))))
7428 `((upstream-name . "Biobase")))
7429 (build-system r-build-system)
7431 `(("r-biocgenerics" ,r-biocgenerics)))
7432 (home-page "https://bioconductor.org/packages/Biobase")
7433 (synopsis "Base functions for Bioconductor")
7435 "This package provides functions that are needed by many other packages
7436 on Bioconductor or which replace R functions.")
7437 (license license:artistic2.0)))
7439 (define-public r-annotationdbi
7441 (name "r-annotationdbi")
7445 (uri (bioconductor-uri "AnnotationDbi" version))
7448 "1954vimkx5yb9irppq8vssq0f3yjkg36w38b9r0rqmijx1ps7x5d"))))
7450 `((upstream-name . "AnnotationDbi")))
7451 (build-system r-build-system)
7453 `(("r-biobase" ,r-biobase)
7454 ("r-biocgenerics" ,r-biocgenerics)
7456 ("r-iranges" ,r-iranges)
7457 ("r-rsqlite" ,r-rsqlite)
7458 ("r-s4vectors" ,r-s4vectors)))
7459 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7460 (synopsis "Annotation database interface")
7462 "This package provides user interface and database connection code for
7463 annotation data packages using SQLite data storage.")
7464 (license license:artistic2.0)))
7466 (define-public r-biomart
7472 (uri (bioconductor-uri "biomaRt" version))
7475 "1lshkknp7dmr3p6dd2zbv86cc71h53ggh9ji83jcjym8sgbbspl2"))))
7477 `((upstream-name . "biomaRt")))
7478 (build-system r-build-system)
7480 `(("r-annotationdbi" ,r-annotationdbi)
7482 ("r-progress" ,r-progress)
7483 ("r-rcurl" ,r-rcurl)
7484 ("r-stringr" ,r-stringr)
7486 (home-page "https://bioconductor.org/packages/biomaRt")
7487 (synopsis "Interface to BioMart databases")
7489 "biomaRt provides an interface to a growing collection of databases
7490 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7491 package enables retrieval of large amounts of data in a uniform way without
7492 the need to know the underlying database schemas or write complex SQL queries.
7493 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7494 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7495 users direct access to a diverse set of data and enable a wide range of
7496 powerful online queries from gene annotation to database mining.")
7497 (license license:artistic2.0)))
7499 (define-public r-biocparallel
7501 (name "r-biocparallel")
7505 (uri (bioconductor-uri "BiocParallel" version))
7508 "1iv2xzm6lz371z0llhcxl8hmc5jfw0hjwnf1qc8d7jk9djgcaks2"))))
7510 `((upstream-name . "BiocParallel")))
7511 (build-system r-build-system)
7513 `(("r-futile-logger" ,r-futile-logger)
7516 (home-page "https://bioconductor.org/packages/BiocParallel")
7517 (synopsis "Bioconductor facilities for parallel evaluation")
7519 "This package provides modified versions and novel implementation of
7520 functions for parallel evaluation, tailored to use with Bioconductor
7522 (license (list license:gpl2+ license:gpl3+))))
7524 (define-public r-biostrings
7526 (name "r-biostrings")
7530 (uri (bioconductor-uri "Biostrings" version))
7533 "16cqqc8i6gb0jcz0lizfqqxsq7g0yb0ll2s9qzmb45brp07dg8f7"))))
7535 `((upstream-name . "Biostrings")))
7536 (build-system r-build-system)
7538 `(("r-biocgenerics" ,r-biocgenerics)
7539 ("r-iranges" ,r-iranges)
7540 ("r-s4vectors" ,r-s4vectors)
7541 ("r-xvector" ,r-xvector)))
7542 (home-page "https://bioconductor.org/packages/Biostrings")
7543 (synopsis "String objects and algorithms for biological sequences")
7545 "This package provides memory efficient string containers, string
7546 matching algorithms, and other utilities, for fast manipulation of large
7547 biological sequences or sets of sequences.")
7548 (license license:artistic2.0)))
7550 (define-public r-rsamtools
7552 (name "r-rsamtools")
7556 (uri (bioconductor-uri "Rsamtools" version))
7559 "02paq7klabdkaf1b8pmmbpmyqsj3yncnfsz62rgka6r4dpsilwk9"))))
7561 `((upstream-name . "Rsamtools")))
7562 (build-system r-build-system)
7565 (modify-phases %standard-phases
7566 (add-after 'unpack 'use-system-zlib
7568 (substitute* "DESCRIPTION"
7569 (("zlibbioc, ") ""))
7570 (substitute* "NAMESPACE"
7571 (("import\\(zlibbioc\\)") ""))
7576 `(("r-biocgenerics" ,r-biocgenerics)
7577 ("r-biocparallel" ,r-biocparallel)
7578 ("r-biostrings" ,r-biostrings)
7579 ("r-bitops" ,r-bitops)
7580 ("r-genomeinfodb" ,r-genomeinfodb)
7581 ("r-genomicranges" ,r-genomicranges)
7582 ("r-iranges" ,r-iranges)
7583 ("r-s4vectors" ,r-s4vectors)
7584 ("r-xvector" ,r-xvector)))
7585 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7586 (synopsis "Interface to samtools, bcftools, and tabix")
7588 "This package provides an interface to the 'samtools', 'bcftools', and
7589 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
7590 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
7592 (license license:expat)))
7594 (define-public r-delayedarray
7596 (name "r-delayedarray")
7600 (uri (bioconductor-uri "DelayedArray" version))
7603 "0cl5anqkjwvqx19snjhz0zj8cp8ibckiifl28h821h50g62nvb2f"))))
7605 `((upstream-name . "DelayedArray")))
7606 (build-system r-build-system)
7608 `(("r-biocgenerics" ,r-biocgenerics)
7609 ("r-biocparallel" ,r-biocparallel)
7610 ("r-s4vectors" ,r-s4vectors)
7611 ("r-iranges" ,r-iranges)
7612 ("r-matrixstats" ,r-matrixstats)))
7613 (home-page "https://bioconductor.org/packages/DelayedArray")
7614 (synopsis "Delayed operations on array-like objects")
7616 "Wrapping an array-like object (typically an on-disk object) in a
7617 @code{DelayedArray} object allows one to perform common array operations on it
7618 without loading the object in memory. In order to reduce memory usage and
7619 optimize performance, operations on the object are either delayed or executed
7620 using a block processing mechanism. Note that this also works on in-memory
7621 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7622 @code{Matrix} objects, and ordinary arrays and data frames.")
7623 (license license:artistic2.0)))
7625 (define-public r-summarizedexperiment
7627 (name "r-summarizedexperiment")
7631 (uri (bioconductor-uri "SummarizedExperiment" version))
7634 "07805572xhpj5mfwq6kw1ha21wgalqvhh4ydvafyl1bnf3r20vps"))))
7636 `((upstream-name . "SummarizedExperiment")))
7637 (build-system r-build-system)
7639 `(("r-biobase" ,r-biobase)
7640 ("r-biocgenerics" ,r-biocgenerics)
7641 ("r-delayedarray" ,r-delayedarray)
7642 ("r-genomeinfodb" ,r-genomeinfodb)
7643 ("r-genomicranges" ,r-genomicranges)
7644 ("r-iranges" ,r-iranges)
7645 ("r-matrix" ,r-matrix)
7646 ("r-s4vectors" ,r-s4vectors)))
7647 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
7648 (synopsis "Container for representing genomic ranges by sample")
7650 "The SummarizedExperiment container contains one or more assays, each
7651 represented by a matrix-like object of numeric or other mode. The rows
7652 typically represent genomic ranges of interest and the columns represent
7654 (license license:artistic2.0)))
7656 (define-public r-genomicalignments
7658 (name "r-genomicalignments")
7662 (uri (bioconductor-uri "GenomicAlignments" version))
7665 "1maslav2r34wjyzh2nlwa862in1ir7i5xk57nw2nlfh5gqy112jd"))))
7667 `((upstream-name . "GenomicAlignments")))
7668 (build-system r-build-system)
7670 `(("r-biocgenerics" ,r-biocgenerics)
7671 ("r-biocparallel" ,r-biocparallel)
7672 ("r-biostrings" ,r-biostrings)
7673 ("r-genomeinfodb" ,r-genomeinfodb)
7674 ("r-genomicranges" ,r-genomicranges)
7675 ("r-iranges" ,r-iranges)
7676 ("r-rsamtools" ,r-rsamtools)
7677 ("r-s4vectors" ,r-s4vectors)
7678 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7679 (home-page "https://bioconductor.org/packages/GenomicAlignments")
7680 (synopsis "Representation and manipulation of short genomic alignments")
7682 "This package provides efficient containers for storing and manipulating
7683 short genomic alignments (typically obtained by aligning short reads to a
7684 reference genome). This includes read counting, computing the coverage,
7685 junction detection, and working with the nucleotide content of the
7687 (license license:artistic2.0)))
7689 (define-public r-rtracklayer
7691 (name "r-rtracklayer")
7695 (uri (bioconductor-uri "rtracklayer" version))
7698 "1c76g6h9lx2nm7dvb2zp9dmrpk3vanx3zaz6q9clggpj7yj5lmjd"))))
7699 (build-system r-build-system)
7702 (modify-phases %standard-phases
7703 (add-after 'unpack 'use-system-zlib
7705 (substitute* "DESCRIPTION"
7706 ((" zlibbioc,") ""))
7707 (substitute* "NAMESPACE"
7708 (("import\\(zlibbioc\\)") ""))
7711 `(("pkg-config" ,pkg-config)))
7715 `(("r-biocgenerics" ,r-biocgenerics)
7716 ("r-biostrings" ,r-biostrings)
7717 ("r-genomeinfodb" ,r-genomeinfodb)
7718 ("r-genomicalignments" ,r-genomicalignments)
7719 ("r-genomicranges" ,r-genomicranges)
7720 ("r-iranges" ,r-iranges)
7721 ("r-rcurl" ,r-rcurl)
7722 ("r-rsamtools" ,r-rsamtools)
7723 ("r-s4vectors" ,r-s4vectors)
7725 ("r-xvector" ,r-xvector)))
7726 (home-page "https://bioconductor.org/packages/rtracklayer")
7727 (synopsis "R interface to genome browsers and their annotation tracks")
7729 "rtracklayer is an extensible framework for interacting with multiple
7730 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7731 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7732 built-in). The user may export/import tracks to/from the supported browsers,
7733 as well as query and modify the browser state, such as the current viewport.")
7734 (license license:artistic2.0)))
7736 (define-public r-genomicfeatures
7738 (name "r-genomicfeatures")
7742 (uri (bioconductor-uri "GenomicFeatures" version))
7745 "09gc1vbqszrr3ixv4hsfan2l18fcf3gg58783mrfwjv6ci9c4w0d"))))
7747 `((upstream-name . "GenomicFeatures")))
7748 (build-system r-build-system)
7750 `(("r-annotationdbi" ,r-annotationdbi)
7751 ("r-biobase" ,r-biobase)
7752 ("r-biocgenerics" ,r-biocgenerics)
7753 ("r-biomart" ,r-biomart)
7754 ("r-biostrings" ,r-biostrings)
7756 ("r-genomeinfodb" ,r-genomeinfodb)
7757 ("r-genomicranges" ,r-genomicranges)
7758 ("r-iranges" ,r-iranges)
7759 ("r-rcurl" ,r-rcurl)
7760 ("r-rsqlite" ,r-rsqlite)
7761 ("r-rtracklayer" ,r-rtracklayer)
7762 ("r-s4vectors" ,r-s4vectors)
7763 ("r-xvector" ,r-xvector)))
7764 (home-page "https://bioconductor.org/packages/GenomicFeatures")
7765 (synopsis "Tools for working with transcript centric annotations")
7767 "This package provides a set of tools and methods for making and
7768 manipulating transcript centric annotations. With these tools the user can
7769 easily download the genomic locations of the transcripts, exons and cds of a
7770 given organism, from either the UCSC Genome Browser or a BioMart
7771 database (more sources will be supported in the future). This information is
7772 then stored in a local database that keeps track of the relationship between
7773 transcripts, exons, cds and genes. Flexible methods are provided for
7774 extracting the desired features in a convenient format.")
7775 (license license:artistic2.0)))
7777 (define-public r-go-db
7783 (uri (string-append "https://www.bioconductor.org/packages/"
7784 "release/data/annotation/src/contrib/GO.db_"
7788 "0i3wcf5h3n0dawzc1hy0kv74f06j80c47n4p3g3fmrcxlhi3jpa5"))))
7790 `((upstream-name . "GO.db")))
7791 (build-system r-build-system)
7793 `(("r-annotationdbi" ,r-annotationdbi)))
7794 (home-page "https://bioconductor.org/packages/GO.db")
7795 (synopsis "Annotation maps describing the entire Gene Ontology")
7797 "The purpose of this GO.db annotation package is to provide detailed
7798 information about the latest version of the Gene Ontologies.")
7799 (license license:artistic2.0)))
7801 (define-public r-topgo
7807 (uri (bioconductor-uri "topGO" version))
7810 "1j1jcd16j564kr6qz28140fzmnh9xasi84v1c1fi98sqv30zq9bh"))))
7812 `((upstream-name . "topGO")))
7813 (build-system r-build-system)
7815 `(("r-annotationdbi" ,r-annotationdbi)
7817 ("r-biobase" ,r-biobase)
7818 ("r-biocgenerics" ,r-biocgenerics)
7819 ("r-go-db" ,r-go-db)
7820 ("r-graph" ,r-graph)
7821 ("r-lattice" ,r-lattice)
7822 ("r-matrixstats" ,r-matrixstats)
7823 ("r-sparsem" ,r-sparsem)))
7824 (home-page "https://bioconductor.org/packages/topGO")
7825 (synopsis "Enrichment analysis for gene ontology")
7827 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
7828 terms while accounting for the topology of the GO graph. Different test
7829 statistics and different methods for eliminating local similarities and
7830 dependencies between GO terms can be implemented and applied.")
7831 ;; Any version of the LGPL applies.
7832 (license license:lgpl2.1+)))
7834 (define-public r-bsgenome
7840 (uri (bioconductor-uri "BSgenome" version))
7843 "07z4zxx0khrc86qqvc7vxww8df9fh6pyks9ajxkc9gdqr5nn79j7"))))
7845 `((upstream-name . "BSgenome")))
7846 (build-system r-build-system)
7848 `(("r-biocgenerics" ,r-biocgenerics)
7849 ("r-biostrings" ,r-biostrings)
7850 ("r-genomeinfodb" ,r-genomeinfodb)
7851 ("r-genomicranges" ,r-genomicranges)
7852 ("r-iranges" ,r-iranges)
7853 ("r-rsamtools" ,r-rsamtools)
7854 ("r-rtracklayer" ,r-rtracklayer)
7855 ("r-s4vectors" ,r-s4vectors)
7856 ("r-xvector" ,r-xvector)))
7857 (home-page "https://bioconductor.org/packages/BSgenome")
7858 (synopsis "Infrastructure for Biostrings-based genome data packages")
7860 "This package provides infrastructure shared by all Biostrings-based
7861 genome data packages and support for efficient SNP representation.")
7862 (license license:artistic2.0)))
7864 (define-public r-impute
7870 (uri (bioconductor-uri "impute" version))
7873 "08z0pj1dz5iq967nwj67qyka7ir7m5an2ggv7bsrlz3apzfsla33"))))
7875 `(("gfortran" ,gfortran)))
7876 (build-system r-build-system)
7877 (home-page "https://bioconductor.org/packages/impute")
7878 (synopsis "Imputation for microarray data")
7880 "This package provides a function to impute missing gene expression
7881 microarray data, using nearest neighbor averaging.")
7882 (license license:gpl2+)))
7884 (define-public r-seqpattern
7886 (name "r-seqpattern")
7890 (uri (bioconductor-uri "seqPattern" version))
7893 "0di83qi83mrlw7i12khsq55d03hlazcywaa9m9pki1sfhafpq733"))))
7895 `((upstream-name . "seqPattern")))
7896 (build-system r-build-system)
7898 `(("r-biostrings" ,r-biostrings)
7899 ("r-genomicranges" ,r-genomicranges)
7900 ("r-iranges" ,r-iranges)
7901 ("r-kernsmooth" ,r-kernsmooth)
7902 ("r-plotrix" ,r-plotrix)))
7903 (home-page "https://bioconductor.org/packages/seqPattern")
7904 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
7906 "This package provides tools to visualize oligonucleotide patterns and
7907 sequence motif occurrences across a large set of sequences centred at a common
7908 reference point and sorted by a user defined feature.")
7909 (license license:gpl3+)))
7911 (define-public r-genomation
7913 (name "r-genomation")
7917 (uri (bioconductor-uri "genomation" version))
7920 "0g0v4alfpqlinqinjnyzl3mrjnpbdx9ri34mcaiqbvbvg8ic8wvg"))))
7921 (build-system r-build-system)
7923 `(("r-biostrings" ,r-biostrings)
7924 ("r-bsgenome" ,r-bsgenome)
7925 ("r-data-table" ,r-data-table)
7926 ("r-genomeinfodb" ,r-genomeinfodb)
7927 ("r-genomicalignments" ,r-genomicalignments)
7928 ("r-genomicranges" ,r-genomicranges)
7929 ("r-ggplot2" ,r-ggplot2)
7930 ("r-gridbase" ,r-gridbase)
7931 ("r-impute" ,r-impute)
7932 ("r-iranges" ,r-iranges)
7933 ("r-matrixstats" ,r-matrixstats)
7934 ("r-plotrix" ,r-plotrix)
7937 ("r-readr" ,r-readr)
7938 ("r-reshape2" ,r-reshape2)
7939 ("r-rsamtools" ,r-rsamtools)
7940 ("r-rtracklayer" ,r-rtracklayer)
7941 ("r-runit" ,r-runit)
7942 ("r-s4vectors" ,r-s4vectors)
7943 ("r-seqpattern" ,r-seqpattern)))
7944 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7945 (synopsis "Summary, annotation and visualization of genomic data")
7947 "This package provides a package for summary and annotation of genomic
7948 intervals. Users can visualize and quantify genomic intervals over
7949 pre-defined functional regions, such as promoters, exons, introns, etc. The
7950 genomic intervals represent regions with a defined chromosome position, which
7951 may be associated with a score, such as aligned reads from HT-seq experiments,
7952 TF binding sites, methylation scores, etc. The package can use any tabular
7953 genomic feature data as long as it has minimal information on the locations of
7954 genomic intervals. In addition, it can use BAM or BigWig files as input.")
7955 (license license:artistic2.0)))
7957 (define-public r-genomationdata
7959 (name "r-genomationdata")
7963 ;; We cannot use bioconductor-uri here because this tarball is
7964 ;; located under "data/annotation/" instead of "bioc/".
7965 (uri (string-append "https://bioconductor.org/packages/"
7966 "release/data/experiment/src/contrib/"
7967 "genomationData_" version ".tar.gz"))
7970 "10xyb8akjrhmak2i0mnv1agny2ipy364q9nlibyplpzc7vdb6bw7"))))
7971 (build-system r-build-system)
7972 ;; As this package provides little more than large data files, it doesn't
7973 ;; make sense to build substitutes.
7974 (arguments `(#:substitutable? #f))
7976 `(("r-knitr" ,r-knitr)))
7977 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7978 (synopsis "Experimental data for use with the genomation package")
7980 "This package contains experimental genetic data for use with the
7981 genomation package. Included are Chip Seq, Methylation and Cage data,
7982 downloaded from Encode.")
7983 (license license:gpl3+)))
7985 (define-public r-seqlogo
7992 (uri (bioconductor-uri "seqLogo" version))
7995 "022vr9ydwcivs7rw7kwj73gfk5gc7ckwa1q66vhd4kw9ylh70v68"))))
7996 (properties `((upstream-name . "seqLogo")))
7997 (build-system r-build-system)
7998 (home-page "https://bioconductor.org/packages/seqLogo")
7999 (synopsis "Sequence logos for DNA sequence alignments")
8001 "seqLogo takes the position weight matrix of a DNA sequence motif and
8002 plots the corresponding sequence logo as introduced by Schneider and
8004 (license license:lgpl2.0+)))
8006 (define-public r-motifrg
8013 (uri (bioconductor-uri "motifRG" version))
8016 "1wxww6i0jgyapqclcwy0zzf9kqjvrvylr89z7yhg1izi7jnw2fka"))))
8017 (properties `((upstream-name . "motifRG")))
8018 (build-system r-build-system)
8020 `(("r-biostrings" ,r-biostrings)
8021 ("r-bsgenome" ,r-bsgenome)
8022 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8023 ("r-iranges" ,r-iranges)
8024 ("r-seqlogo" ,r-seqlogo)
8025 ("r-xvector" ,r-xvector)))
8026 (home-page "https://bioconductor.org/packages/motifRG")
8027 (synopsis "Discover motifs in high throughput sequencing data")
8029 "This package provides tools for discriminative motif discovery in high
8030 throughput genetic sequencing data sets using regression methods.")
8031 (license license:artistic2.0)))
8033 (define-public r-qtl
8040 (uri (string-append "mirror://cran/src/contrib/qtl_"
8044 "03lmvydln8b7666b6w46qbryhf83vsd11d4y2v95rfgvqgq66l1i"))))
8045 (build-system r-build-system)
8046 (home-page "http://rqtl.org/")
8047 (synopsis "R package for analyzing QTL experiments in genetics")
8048 (description "R/qtl is an extension library for the R statistics
8049 system. It is used to analyze experimental crosses for identifying
8050 genes contributing to variation in quantitative traits (so-called
8051 quantitative trait loci, QTLs).
8053 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
8054 identify genotyping errors, and to perform single-QTL and two-QTL,
8055 two-dimensional genome scans.")
8056 (license license:gpl3)))
8058 (define-public r-zlibbioc
8064 (uri (bioconductor-uri "zlibbioc" version))
8067 "0bjvzy24kab7ank02cc1qk2ikcz4dllgf66wpsdl0d3zp4gn3l2h"))))
8069 `((upstream-name . "zlibbioc")))
8070 (build-system r-build-system)
8071 (home-page "https://bioconductor.org/packages/zlibbioc")
8072 (synopsis "Provider for zlib-1.2.5 to R packages")
8073 (description "This package uses the source code of zlib-1.2.5 to create
8074 libraries for systems that do not have these available via other means.")
8075 (license license:artistic2.0)))
8077 (define-public r-r4rna
8084 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8088 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8089 (build-system r-build-system)
8091 `(("r-optparse" ,r-optparse)
8092 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8093 (home-page "http://www.e-rna.org/r-chie/index.cgi")
8094 (synopsis "Analysis framework for RNA secondary structure")
8096 "The R4RNA package aims to be a general framework for the analysis of RNA
8097 secondary structure and comparative analysis in R.")
8098 (license license:gpl3+)))
8100 (define-public r-rhtslib
8107 (uri (bioconductor-uri "Rhtslib" version))
8110 "13fv78sk5g0gqfl3ks3rps3zc1k66a4lzxvgn36r7ix43yxk7hnr"))))
8111 (properties `((upstream-name . "Rhtslib")))
8112 (build-system r-build-system)
8114 `(("r-zlibbioc" ,r-zlibbioc)))
8118 `(("pkg-config" ,pkg-config)))
8119 (home-page "https://github.com/nhayden/Rhtslib")
8120 (synopsis "High-throughput sequencing library as an R package")
8122 "This package provides the HTSlib C library for high-throughput
8123 nucleotide sequence analysis. The package is primarily useful to developers
8124 of other R packages who wish to make use of HTSlib.")
8125 (license license:lgpl2.0+)))
8127 (define-public r-bamsignals
8129 (name "r-bamsignals")
8134 (uri (bioconductor-uri "bamsignals" version))
8137 "19irfx1y1izf903vq59wxsdbf88g143zy9l89gxqawh7jfxds8w8"))))
8138 (build-system r-build-system)
8140 `(("r-biocgenerics" ,r-biocgenerics)
8141 ("r-genomicranges" ,r-genomicranges)
8142 ("r-iranges" ,r-iranges)
8144 ("r-rhtslib" ,r-rhtslib)
8145 ("r-zlibbioc" ,r-zlibbioc)))
8148 (home-page "https://bioconductor.org/packages/bamsignals")
8149 (synopsis "Extract read count signals from bam files")
8151 "This package allows to efficiently obtain count vectors from indexed bam
8152 files. It counts the number of nucleotide sequence reads in given genomic
8153 ranges and it computes reads profiles and coverage profiles. It also handles
8155 (license license:gpl2+)))
8157 (define-public r-rcas
8163 (uri (bioconductor-uri "RCAS" version))
8166 "0ss5hcg2m7gjji6dd23zxa5bd5a7knwcnada4qs5q2l4clgk39ad"))))
8167 (build-system r-build-system)
8169 `(("r-annotationdbi" ,r-annotationdbi)
8170 ("r-biocgenerics" ,r-biocgenerics)
8171 ("r-biomart" ,r-biomart)
8172 ("r-biostrings" ,r-biostrings)
8173 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8174 ("r-cowplot" ,r-cowplot)
8175 ("r-data-table" ,r-data-table)
8178 ("r-genomation" ,r-genomation)
8179 ("r-genomeinfodb" ,r-genomeinfodb)
8180 ("r-genomicfeatures" ,r-genomicfeatures)
8181 ("r-genomicranges" ,r-genomicranges)
8182 ("r-ggplot2" ,r-ggplot2)
8183 ("r-ggseqlogo" ,r-ggseqlogo)
8184 ("r-knitr" ,r-knitr)
8185 ("r-motifrg" ,r-motifrg)
8186 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8187 ("r-pbapply" ,r-pbapply)
8188 ("r-pheatmap" ,r-pheatmap)
8189 ("r-plotly" ,r-plotly)
8190 ("r-plotrix" ,r-plotrix)
8191 ("r-proxy" ,r-proxy)
8192 ("r-rsqlite" ,r-rsqlite)
8193 ("r-rtracklayer" ,r-rtracklayer)
8194 ("r-rmarkdown" ,r-rmarkdown)
8195 ("r-s4vectors" ,r-s4vectors)
8196 ("r-topgo" ,r-topgo)))
8197 (synopsis "RNA-centric annotation system")
8199 "RCAS aims to be a standalone RNA-centric annotation system that provides
8200 intuitive reports and publication-ready graphics. This package provides the R
8201 library implementing most of the pipeline's features.")
8202 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8203 (license license:artistic2.0)))
8205 (define-public rcas-web
8212 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8213 "releases/download/v" version
8214 "/rcas-web-" version ".tar.gz"))
8217 "0wq951aj45gqki1bickg876i993lmawkp8x24agg264br5x716db"))))
8218 (build-system gnu-build-system)
8221 (modify-phases %standard-phases
8222 (add-after 'install 'wrap-executable
8223 (lambda* (#:key inputs outputs #:allow-other-keys)
8224 (let* ((out (assoc-ref outputs "out"))
8225 (json (assoc-ref inputs "guile-json"))
8226 (redis (assoc-ref inputs "guile-redis"))
8227 (path (string-append
8228 json "/share/guile/site/2.2:"
8229 redis "/share/guile/site/2.2")))
8230 (wrap-program (string-append out "/bin/rcas-web")
8231 `("GUILE_LOAD_PATH" ":" = (,path))
8232 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8233 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8236 `(("r-minimal" ,r-minimal)
8238 ("guile-next" ,guile-2.2)
8239 ("guile-json" ,guile-json)
8240 ("guile-redis" ,guile-redis)))
8242 `(("pkg-config" ,pkg-config)))
8243 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8244 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8245 (description "This package provides a simple web interface for the
8246 @dfn{RNA-centric annotation system} (RCAS).")
8247 (license license:agpl3+)))
8249 (define-public r-mutationalpatterns
8251 (name "r-mutationalpatterns")
8256 (uri (bioconductor-uri "MutationalPatterns" version))
8259 "0w9lg1zs106h6rqvy8mhikq6q6q9syw6c1prcxr38ssh85rcih12"))))
8260 (build-system r-build-system)
8262 `(("r-biocgenerics" ,r-biocgenerics)
8263 ("r-biostrings" ,r-biostrings)
8264 ;; These two packages are suggested packages
8265 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8266 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8267 ("r-genomicranges" ,r-genomicranges)
8268 ("r-genomeinfodb" ,r-genomeinfodb)
8269 ("r-ggplot2" ,r-ggplot2)
8270 ("r-iranges" ,r-iranges)
8273 ("r-pracma" ,r-pracma)
8274 ("r-reshape2" ,r-reshape2)
8275 ("r-cowplot" ,r-cowplot)
8276 ("r-ggdendro" ,r-ggdendro)
8277 ("r-s4vectors" ,r-s4vectors)
8278 ("r-summarizedexperiment" ,r-summarizedexperiment)
8279 ("r-variantannotation" ,r-variantannotation)))
8280 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8281 (synopsis "Extract and visualize mutational patterns in genomic data")
8282 (description "This package provides an extensive toolset for the
8283 characterization and visualization of a wide range of mutational patterns
8284 in SNV base substitution data.")
8285 (license license:expat)))
8287 (define-public r-wgcna
8294 (uri (cran-uri "WGCNA" version))
8297 "0rhnyhzfn93yp24jz9v6dzrmyizwzdw070a7idm0k33w1cm8sjqv"))))
8298 (properties `((upstream-name . "WGCNA")))
8299 (build-system r-build-system)
8301 `(("r-annotationdbi" ,r-annotationdbi)
8302 ("r-doparallel" ,r-doparallel)
8303 ("r-dynamictreecut" ,r-dynamictreecut)
8304 ("r-fastcluster" ,r-fastcluster)
8305 ("r-foreach" ,r-foreach)
8306 ("r-go-db" ,r-go-db)
8307 ("r-hmisc" ,r-hmisc)
8308 ("r-impute" ,r-impute)
8310 ("r-robust" ,r-robust)
8311 ("r-survival" ,r-survival)
8312 ("r-matrixstats" ,r-matrixstats)
8313 ("r-preprocesscore" ,r-preprocesscore)))
8315 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8316 (synopsis "Weighted correlation network analysis")
8318 "This package provides functions necessary to perform Weighted
8319 Correlation Network Analysis on high-dimensional data. It includes functions
8320 for rudimentary data cleaning, construction and summarization of correlation
8321 networks, module identification and functions for relating both variables and
8322 modules to sample traits. It also includes a number of utility functions for
8323 data manipulation and visualization.")
8324 (license license:gpl2+)))
8326 (define-public r-chipkernels
8327 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8330 (name "r-chipkernels")
8331 (version (string-append "1.1-" revision "." (string-take commit 9)))
8336 (url "https://github.com/ManuSetty/ChIPKernels.git")
8338 (file-name (string-append name "-" version))
8341 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8342 (build-system r-build-system)
8344 `(("r-iranges" ,r-iranges)
8345 ("r-xvector" ,r-xvector)
8346 ("r-biostrings" ,r-biostrings)
8347 ("r-bsgenome" ,r-bsgenome)
8348 ("r-gtools" ,r-gtools)
8349 ("r-genomicranges" ,r-genomicranges)
8350 ("r-sfsmisc" ,r-sfsmisc)
8351 ("r-kernlab" ,r-kernlab)
8352 ("r-s4vectors" ,r-s4vectors)
8353 ("r-biocgenerics" ,r-biocgenerics)))
8354 (home-page "https://github.com/ManuSetty/ChIPKernels")
8355 (synopsis "Build string kernels for DNA Sequence analysis")
8356 (description "ChIPKernels is an R package for building different string
8357 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8358 must be built and this dictionary can be used for determining kernels for DNA
8360 (license license:gpl2+))))
8362 (define-public r-seqgl
8370 (url "https://github.com/ManuSetty/SeqGL.git")
8372 (file-name (git-file-name name version))
8375 "1r6ywvhxl3ffv48lgj7sbd582mcc6dha3ksgc2qjlvjrnkbj3799"))))
8376 (build-system r-build-system)
8378 `(("r-biostrings" ,r-biostrings)
8379 ("r-chipkernels" ,r-chipkernels)
8380 ("r-genomicranges" ,r-genomicranges)
8381 ("r-spams" ,r-spams)
8382 ("r-wgcna" ,r-wgcna)
8383 ("r-fastcluster" ,r-fastcluster)))
8384 (home-page "https://github.com/ManuSetty/SeqGL")
8385 (synopsis "Group lasso for Dnase/ChIP-seq data")
8386 (description "SeqGL is a group lasso based algorithm to extract
8387 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8388 This package presents a method which uses group lasso to discriminate between
8389 bound and non bound genomic regions to accurately identify transcription
8390 factors bound at the specific regions.")
8391 (license license:gpl2+)))
8393 (define-public r-gkmsvm
8400 (uri (cran-uri "gkmSVM" version))
8403 "04dakbgfvfalz4rm4fvvybp506dn5fbj5g86ybfhrc6wywjllsz3"))))
8404 (properties `((upstream-name . "gkmSVM")))
8405 (build-system r-build-system)
8407 `(("r-biocgenerics" ,r-biocgenerics)
8408 ("r-biostrings" ,r-biostrings)
8409 ("r-genomeinfodb" ,r-genomeinfodb)
8410 ("r-genomicranges" ,r-genomicranges)
8411 ("r-iranges" ,r-iranges)
8412 ("r-kernlab" ,r-kernlab)
8415 ("r-rtracklayer" ,r-rtracklayer)
8416 ("r-s4vectors" ,r-s4vectors)
8417 ("r-seqinr" ,r-seqinr)))
8418 (home-page "https://cran.r-project.org/web/packages/gkmSVM")
8419 (synopsis "Gapped-kmer support vector machine")
8421 "This R package provides tools for training gapped-kmer SVM classifiers
8422 for DNA and protein sequences. This package supports several sequence
8423 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8424 (license license:gpl2+)))
8426 (define-public r-tximport
8432 (uri (bioconductor-uri "tximport" version))
8435 "16wp09dm0cpb4mc00nmglfb8ica7qb4a55vm8ajgzyagbpfdd44l"))))
8436 (build-system r-build-system)
8437 (home-page "https://bioconductor.org/packages/tximport")
8438 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8440 "This package provides tools to import transcript-level abundance,
8441 estimated counts and transcript lengths, and to summarize them into matrices
8442 for use with downstream gene-level analysis packages. Average transcript
8443 length, weighted by sample-specific transcript abundance estimates, is
8444 provided as a matrix which can be used as an offset for different expression
8445 of gene-level counts.")
8446 (license license:gpl2+)))
8448 (define-public r-rhdf5
8454 (uri (bioconductor-uri "rhdf5" version))
8457 "10zkw3k13wmvyif417gplyf6rwp2gpkjasw97lhwv2f9i32rry9l"))))
8458 (build-system r-build-system)
8460 `(("r-rhdf5lib" ,r-rhdf5lib)))
8463 (home-page "https://bioconductor.org/packages/rhdf5")
8464 (synopsis "HDF5 interface to R")
8466 "This R/Bioconductor package provides an interface between HDF5 and R.
8467 HDF5's main features are the ability to store and access very large and/or
8468 complex datasets and a wide variety of metadata on mass storage (disk) through
8469 a completely portable file format. The rhdf5 package is thus suited for the
8470 exchange of large and/or complex datasets between R and other software
8471 package, and for letting R applications work on datasets that are larger than
8472 the available RAM.")
8473 (license license:artistic2.0)))
8475 (define-public r-annotationfilter
8477 (name "r-annotationfilter")
8481 (uri (bioconductor-uri "AnnotationFilter" version))
8484 "0wrr10cxjzmxx46vjzq2nsf6xlqz1sqwx4xm0sk3d77ff8wmph4x"))))
8486 `((upstream-name . "AnnotationFilter")))
8487 (build-system r-build-system)
8489 `(("r-genomicranges" ,r-genomicranges)
8490 ("r-lazyeval" ,r-lazyeval)))
8491 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8492 (synopsis "Facilities for filtering Bioconductor annotation resources")
8494 "This package provides classes and other infrastructure to implement
8495 filters for manipulating Bioconductor annotation resources. The filters are
8496 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8497 (license license:artistic2.0)))
8499 (define-public emboss
8505 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8506 (version-major+minor version) ".0/"
8507 "EMBOSS-" version ".tar.gz"))
8510 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8511 (build-system gnu-build-system)
8514 (list (string-append "--with-hpdf="
8515 (assoc-ref %build-inputs "libharu")))
8517 (modify-phases %standard-phases
8518 (add-after 'unpack 'fix-checks
8520 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8521 ;; and zlib, but assume that they are all found at the same
8523 (substitute* "configure.in"
8524 (("CHECK_PNGDRIVER")
8525 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8526 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8527 AM_CONDITIONAL(AMPNG, true)"))
8529 (add-after 'fix-checks 'disable-update-check
8531 ;; At build time there is no connection to the Internet, so
8532 ;; looking for updates will not work.
8533 (substitute* "Makefile.am"
8534 (("\\$\\(bindir\\)/embossupdate") ""))
8536 (add-after 'disable-update-check 'autogen
8537 (lambda _ (invoke "autoreconf" "-vif") #t)))))
8543 ("libharu" ,libharu)
8546 `(("autoconf" ,autoconf)
8547 ("automake" ,automake)
8548 ("libtool" ,libtool)
8549 ("pkg-config" ,pkg-config)))
8550 (home-page "http://emboss.sourceforge.net")
8551 (synopsis "Molecular biology analysis suite")
8552 (description "EMBOSS is the \"European Molecular Biology Open Software
8553 Suite\". EMBOSS is an analysis package specially developed for the needs of
8554 the molecular biology (e.g. EMBnet) user community. The software
8555 automatically copes with data in a variety of formats and even allows
8556 transparent retrieval of sequence data from the web. It also provides a
8557 number of libraries for the development of software in the field of molecular
8558 biology. EMBOSS also integrates a range of currently available packages and
8559 tools for sequence analysis into a seamless whole.")
8560 (license license:gpl2+)))
8563 (let ((revision "1")
8564 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8567 ;; The version is 2.13.0 even though no release archives have been
8568 ;; published as yet.
8569 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8573 (url "https://github.com/arq5x/bits.git")
8575 (file-name (string-append name "-" version "-checkout"))
8578 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8579 (build-system gnu-build-system)
8581 `(#:tests? #f ;no tests included
8583 (modify-phases %standard-phases
8585 (add-after 'unpack 'remove-cuda
8587 (substitute* "Makefile"
8589 (("(bits_test_intersections) \\\\" _ match) match))
8592 (lambda* (#:key outputs #:allow-other-keys)
8594 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8599 (home-page "https://github.com/arq5x/bits")
8600 (synopsis "Implementation of binary interval search algorithm")
8601 (description "This package provides an implementation of the
8602 BITS (Binary Interval Search) algorithm, an approach to interval set
8603 intersection. It is especially suited for the comparison of diverse genomic
8604 datasets and the exploration of large datasets of genome
8605 intervals (e.g. genes, sequence alignments).")
8606 (license license:gpl2))))
8608 (define-public piranha
8609 ;; There is no release tarball for the latest version. The latest commit is
8610 ;; older than one year at the time of this writing.
8611 (let ((revision "1")
8612 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8615 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8619 (url "https://github.com/smithlabcode/piranha.git")
8621 (file-name (git-file-name name version))
8624 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
8625 (build-system gnu-build-system)
8627 `(#:test-target "test"
8629 (modify-phases %standard-phases
8630 (add-after 'unpack 'copy-smithlab-cpp
8631 (lambda* (#:key inputs #:allow-other-keys)
8632 (for-each (lambda (file)
8633 (install-file file "./src/smithlab_cpp/"))
8634 (find-files (assoc-ref inputs "smithlab-cpp")))
8636 (add-after 'install 'install-to-store
8637 (lambda* (#:key outputs #:allow-other-keys)
8638 (let* ((out (assoc-ref outputs "out"))
8639 (bin (string-append out "/bin")))
8640 (for-each (lambda (file)
8641 (install-file file bin))
8642 (find-files "bin" ".*")))
8645 (list (string-append "--with-bam_tools_headers="
8646 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
8647 (string-append "--with-bam_tools_library="
8648 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
8650 `(("bamtools" ,bamtools)
8651 ("samtools" ,samtools-0.1)
8654 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8658 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8660 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8663 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8665 `(("python" ,python-2)))
8666 (home-page "https://github.com/smithlabcode/piranha")
8667 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
8669 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
8670 RIP-seq experiments. It takes input in BED or BAM format and identifies
8671 regions of statistically significant read enrichment. Additional covariates
8672 may optionally be provided to further inform the peak-calling process.")
8673 (license license:gpl3+))))
8681 (uri (pypi-uri "PePr" version))
8684 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
8685 (build-system python-build-system)
8687 `(#:python ,python-2 ; python2 only
8688 #:tests? #f)) ; no tests included
8690 `(("python2-numpy" ,python2-numpy)
8691 ("python2-scipy" ,python2-scipy)
8692 ("python2-pysam" ,python2-pysam)))
8693 (home-page "https://github.com/shawnzhangyx/PePr")
8694 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
8696 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
8697 that is primarily designed for data with biological replicates. It uses a
8698 negative binomial distribution to model the read counts among the samples in
8699 the same group, and look for consistent differences between ChIP and control
8700 group or two ChIP groups run under different conditions.")
8701 (license license:gpl3+)))
8703 (define-public filevercmp
8704 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
8707 (version (string-append "0-1." (string-take commit 7)))
8711 (url "https://github.com/ekg/filevercmp.git")
8713 (file-name (git-file-name name commit))
8716 "1j9vxsy0y050v59h0q1d6501fcw1kjvj0d18l1xk2zyg0jzj247c"))))
8717 (build-system gnu-build-system)
8719 `(#:tests? #f ; There are no tests to run.
8721 (modify-phases %standard-phases
8722 (delete 'configure) ; There is no configure phase.
8724 (lambda* (#:key outputs #:allow-other-keys)
8725 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
8726 (install-file "filevercmp" bin)
8728 (home-page "https://github.com/ekg/filevercmp")
8729 (synopsis "This program compares version strings")
8730 (description "This program compares version strings. It intends to be a
8731 replacement for strverscmp.")
8732 (license license:gpl3+))))
8734 (define-public multiqc
8741 (uri (pypi-uri "multiqc" version))
8744 "02iihfl0w0hpnr4pa0sbd1y9qxrg3ycyhjp5lidkcrqh1lmzs3zy"))))
8745 (build-system python-build-system)
8747 `(("python-jinja2" ,python-jinja2)
8748 ("python-simplejson" ,python-simplejson)
8749 ("python-pyyaml" ,python-pyyaml)
8750 ("python-click" ,python-click)
8751 ("python-spectra" ,python-spectra)
8752 ("python-requests" ,python-requests)
8753 ("python-markdown" ,python-markdown)
8754 ("python-lzstring" ,python-lzstring)
8755 ("python-matplotlib" ,python-matplotlib)
8756 ("python-numpy" ,python-numpy)
8757 ;; MultQC checks for the presence of nose at runtime.
8758 ("python-nose" ,python-nose)))
8761 (modify-phases %standard-phases
8762 (add-after 'unpack 'relax-requirements
8764 (substitute* "setup.py"
8765 ;; MultiQC 1.5 ‘requires’ a version of python-matplotlib older
8766 ;; than the one in Guix, but should work fine with 2.2.2.
8767 ;; See <https://github.com/ewels/MultiQC/issues/725> and
8768 ;; <https://github.com/ewels/MultiQC/issues/732> for details.
8769 (("['\"]matplotlib.*?['\"]")
8772 (home-page "http://multiqc.info")
8773 (synopsis "Aggregate bioinformatics analysis reports")
8775 "MultiQC is a tool to aggregate bioinformatics results across many
8776 samples into a single report. It contains modules for a large number of
8777 common bioinformatics tools.")
8778 (license license:gpl3+)))
8780 (define-public r-chipseq
8787 (uri (bioconductor-uri "chipseq" version))
8790 "1pp1rm5fs3hlar5x4dl3a3b4gara7qwf81dbvka6r1n78hrf9x1b"))))
8791 (build-system r-build-system)
8793 `(("r-biocgenerics" ,r-biocgenerics)
8794 ("r-genomicranges" ,r-genomicranges)
8795 ("r-iranges" ,r-iranges)
8796 ("r-lattice" ,r-lattice)
8797 ("r-s4vectors" ,r-s4vectors)
8798 ("r-shortread" ,r-shortread)))
8799 (home-page "https://bioconductor.org/packages/chipseq")
8800 (synopsis "Package for analyzing ChIPseq data")
8802 "This package provides tools for processing short read data from ChIPseq
8804 (license license:artistic2.0)))
8806 (define-public r-copyhelper
8808 (name "r-copyhelper")
8813 (uri (string-append "https://bioconductor.org/packages/release/"
8814 "data/experiment/src/contrib/CopyhelpeR_"
8818 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
8819 (properties `((upstream-name . "CopyhelpeR")))
8820 (build-system r-build-system)
8821 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
8822 (synopsis "Helper files for CopywriteR")
8824 "This package contains the helper files that are required to run the
8825 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
8826 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
8827 mm10. In addition, it contains a blacklist filter to remove regions that
8828 display copy number variation. Files are stored as GRanges objects from the
8829 GenomicRanges Bioconductor package.")
8830 (license license:gpl2)))
8832 (define-public r-copywriter
8834 (name "r-copywriter")
8839 (uri (bioconductor-uri "CopywriteR" version))
8842 "1hbiw0m9hmx4na9v502pxf8y5wvxzr68r4d3fqr2755gxx86qck6"))))
8843 (properties `((upstream-name . "CopywriteR")))
8844 (build-system r-build-system)
8846 `(("r-biocparallel" ,r-biocparallel)
8847 ("r-chipseq" ,r-chipseq)
8848 ("r-copyhelper" ,r-copyhelper)
8849 ("r-data-table" ,r-data-table)
8850 ("r-dnacopy" ,r-dnacopy)
8851 ("r-futile-logger" ,r-futile-logger)
8852 ("r-genomeinfodb" ,r-genomeinfodb)
8853 ("r-genomicalignments" ,r-genomicalignments)
8854 ("r-genomicranges" ,r-genomicranges)
8855 ("r-gtools" ,r-gtools)
8856 ("r-iranges" ,r-iranges)
8857 ("r-matrixstats" ,r-matrixstats)
8858 ("r-rsamtools" ,r-rsamtools)
8859 ("r-s4vectors" ,r-s4vectors)))
8860 (home-page "https://github.com/PeeperLab/CopywriteR")
8861 (synopsis "Copy number information from targeted sequencing")
8863 "CopywriteR extracts DNA copy number information from targeted sequencing
8864 by utilizing off-target reads. It allows for extracting uniformly distributed
8865 copy number information, can be used without reference, and can be applied to
8866 sequencing data obtained from various techniques including chromatin
8867 immunoprecipitation and target enrichment on small gene panels. Thereby,
8868 CopywriteR constitutes a widely applicable alternative to available copy
8869 number detection tools.")
8870 (license license:gpl2)))
8872 (define-public r-methylkit
8874 (name "r-methylkit")
8878 (uri (bioconductor-uri "methylKit" version))
8881 "1zcfwy7i10aqgnf7r0c41hakb5aai3s3n9y8pc6a98vimz51ly2z"))))
8882 (properties `((upstream-name . "methylKit")))
8883 (build-system r-build-system)
8885 `(("r-data-table" ,r-data-table)
8886 ("r-emdbook" ,r-emdbook)
8887 ("r-fastseg" ,r-fastseg)
8888 ("r-genomeinfodb" ,r-genomeinfodb)
8889 ("r-genomicranges" ,r-genomicranges)
8890 ("r-gtools" ,r-gtools)
8891 ("r-iranges" ,r-iranges)
8892 ("r-kernsmooth" ,r-kernsmooth)
8893 ("r-limma" ,r-limma)
8894 ("r-mclust" ,r-mclust)
8895 ("r-qvalue" ,r-qvalue)
8896 ("r-r-utils" ,r-r-utils)
8898 ("r-rhtslib" ,r-rhtslib)
8899 ("r-rsamtools" ,r-rsamtools)
8900 ("r-rtracklayer" ,r-rtracklayer)
8901 ("r-s4vectors" ,r-s4vectors)
8902 ("r-zlibbioc" ,r-zlibbioc)))
8905 (home-page "https://github.com/al2na/methylKit")
8907 "DNA methylation analysis from high-throughput bisulfite sequencing results")
8909 "MethylKit is an R package for DNA methylation analysis and annotation
8910 from high-throughput bisulfite sequencing. The package is designed to deal
8911 with sequencing data from @dfn{Reduced representation bisulfite
8912 sequencing} (RRBS) and its variants, but also target-capture methods and whole
8913 genome bisulfite sequencing. It also has functions to analyze base-pair
8914 resolution 5hmC data from experimental protocols such as oxBS-Seq and
8916 (license license:artistic2.0)))
8918 (define-public r-sva
8925 (uri (bioconductor-uri "sva" version))
8928 "0czja4c5jxa0g3fspi90nyajqmvzb29my4ykv2wi66h43f5dlwhq"))))
8929 (build-system r-build-system)
8931 `(("r-genefilter" ,r-genefilter)
8933 ("r-biocparallel" ,r-biocparallel)
8934 ("r-matrixstats" ,r-matrixstats)
8935 ("r-limma" ,r-limma)))
8936 (home-page "https://bioconductor.org/packages/sva")
8937 (synopsis "Surrogate variable analysis")
8939 "This package contains functions for removing batch effects and other
8940 unwanted variation in high-throughput experiment. It also contains functions
8941 for identifying and building surrogate variables for high-dimensional data
8942 sets. Surrogate variables are covariates constructed directly from
8943 high-dimensional data like gene expression/RNA sequencing/methylation/brain
8944 imaging data that can be used in subsequent analyses to adjust for unknown,
8945 unmodeled, or latent sources of noise.")
8946 (license license:artistic2.0)))
8948 (define-public r-seqminer
8955 (uri (cran-uri "seqminer" version))
8958 "1jydcpkw4rwfp983j83kipvsvr10as9pb49zzn3c2v09k1gh3ymy"))))
8959 (build-system r-build-system)
8962 (home-page "http://seqminer.genomic.codes")
8963 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
8965 "This package provides tools to integrate nucleotide sequencing
8966 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
8967 ;; Any version of the GPL is acceptable
8968 (license (list license:gpl2+ license:gpl3+))))
8970 (define-public r-raremetals2
8972 (name "r-raremetals2")
8977 (uri (string-append "http://genome.sph.umich.edu/w/images/"
8978 "b/b7/RareMETALS2_" version ".tar.gz"))
8981 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
8982 (properties `((upstream-name . "RareMETALS2")))
8983 (build-system r-build-system)
8985 `(("r-seqminer" ,r-seqminer)
8986 ("r-mvtnorm" ,r-mvtnorm)
8988 ("r-compquadform" ,r-compquadform)
8989 ("r-getopt" ,r-getopt)))
8990 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
8991 (synopsis "Analyze gene-level association tests for binary trait")
8993 "The R package rareMETALS2 is an extension of the R package rareMETALS.
8994 It was designed to meta-analyze gene-level association tests for binary trait.
8995 While rareMETALS offers a near-complete solution for meta-analysis of
8996 gene-level tests for quantitative trait, it does not offer the optimal
8997 solution for binary trait. The package rareMETALS2 offers improved features
8998 for analyzing gene-level association tests in meta-analyses for binary
9000 (license license:gpl3)))
9002 (define-public r-maldiquant
9004 (name "r-maldiquant")
9009 (uri (cran-uri "MALDIquant" version))
9012 "18nl214xjsxkcpbg79jkmw0yznwm5szyh2qb84n7ip46mm779ha6"))))
9013 (properties `((upstream-name . "MALDIquant")))
9014 (build-system r-build-system)
9015 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9016 (synopsis "Quantitative analysis of mass spectrometry data")
9018 "This package provides a complete analysis pipeline for matrix-assisted
9019 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9020 two-dimensional mass spectrometry data. In addition to commonly used plotting
9021 and processing methods it includes distinctive features, namely baseline
9022 subtraction methods such as morphological filters (TopHat) or the
9023 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9024 alignment using warping functions, handling of replicated measurements as well
9025 as allowing spectra with different resolutions.")
9026 (license license:gpl3+)))
9028 (define-public r-protgenerics
9030 (name "r-protgenerics")
9035 (uri (bioconductor-uri "ProtGenerics" version))
9038 "053mmxhzncqgigl2iqjlq56qzimlw2zzw31wpzw19rf7rld1vi3b"))))
9039 (properties `((upstream-name . "ProtGenerics")))
9040 (build-system r-build-system)
9041 (home-page "https://github.com/lgatto/ProtGenerics")
9042 (synopsis "S4 generic functions for proteomics infrastructure")
9044 "This package provides S4 generic functions needed by Bioconductor
9045 proteomics packages.")
9046 (license license:artistic2.0)))
9048 (define-public r-mzr
9055 (uri (bioconductor-uri "mzR" version))
9058 "0mlwg646k49klxrznckzfv54a9mz6irj42fqpaaa0xjm6cw2lwaa"))
9059 (modules '((guix build utils)))
9062 (delete-file-recursively "src/boost")
9064 (properties `((upstream-name . "mzR")))
9065 (build-system r-build-system)
9068 (modify-phases %standard-phases
9069 (add-after 'unpack 'use-system-boost
9071 (substitute* "src/Makevars"
9072 (("\\./boost/libs.*") "")
9073 (("ARCH_OBJS=" line)
9075 "\nARCH_LIBS=-lboost_system -lboost_regex \
9076 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9079 `(("boost" ,boost) ; use this instead of the bundled boost sources
9082 `(("r-biobase" ,r-biobase)
9083 ("r-biocgenerics" ,r-biocgenerics)
9084 ("r-ncdf4" ,r-ncdf4)
9085 ("r-protgenerics" ,r-protgenerics)
9087 ("r-rhdf5lib" ,r-rhdf5lib)
9088 ("r-zlibbioc" ,r-zlibbioc)))
9089 (home-page "https://github.com/sneumann/mzR/")
9090 (synopsis "Parser for mass spectrometry data files")
9092 "The mzR package provides a unified API to the common file formats and
9093 parsers available for mass spectrometry data. It comes with a wrapper for the
9094 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9095 The package contains the original code written by the ISB, and a subset of the
9096 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9097 previously been used in XCMS.")
9098 (license license:artistic2.0)))
9100 (define-public r-affyio
9107 (uri (bioconductor-uri "affyio" version))
9110 "1s4zp1211vf0krxzch9v3q3r6vs8hihqppq18i2fpvwlknfja7c1"))))
9111 (build-system r-build-system)
9113 `(("r-zlibbioc" ,r-zlibbioc)))
9116 (home-page "https://github.com/bmbolstad/affyio")
9117 (synopsis "Tools for parsing Affymetrix data files")
9119 "This package provides routines for parsing Affymetrix data files based
9120 upon file format information. The primary focus is on accessing the CEL and
9122 (license license:lgpl2.0+)))
9124 (define-public r-affy
9131 (uri (bioconductor-uri "affy" version))
9134 "0x8h4fk2igv7vykqfvf6v9whmx3344v5rf3gyfajd431xkjldz6k"))))
9135 (build-system r-build-system)
9137 `(("r-affyio" ,r-affyio)
9138 ("r-biobase" ,r-biobase)
9139 ("r-biocgenerics" ,r-biocgenerics)
9140 ("r-biocmanager" ,r-biocmanager)
9141 ("r-preprocesscore" ,r-preprocesscore)
9142 ("r-zlibbioc" ,r-zlibbioc)))
9145 (home-page "https://bioconductor.org/packages/affy")
9146 (synopsis "Methods for affymetrix oligonucleotide arrays")
9148 "This package contains functions for exploratory oligonucleotide array
9150 (license license:lgpl2.0+)))
9152 (define-public r-vsn
9159 (uri (bioconductor-uri "vsn" version))
9162 "1g6qkpykw99jm2wv2i61dg2ffwk0n8fm4s5pm2q4c024vw5c9b69"))))
9163 (build-system r-build-system)
9165 `(("r-affy" ,r-affy)
9166 ("r-biobase" ,r-biobase)
9167 ("r-ggplot2" ,r-ggplot2)
9168 ("r-lattice" ,r-lattice)
9169 ("r-limma" ,r-limma)))
9170 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9171 (synopsis "Variance stabilization and calibration for microarray data")
9173 "The package implements a method for normalising microarray intensities,
9174 and works for single- and multiple-color arrays. It can also be used for data
9175 from other technologies, as long as they have similar format. The method uses
9176 a robust variant of the maximum-likelihood estimator for an
9177 additive-multiplicative error model and affine calibration. The model
9178 incorporates data calibration step (a.k.a. normalization), a model for the
9179 dependence of the variance on the mean intensity and a variance stabilizing
9180 data transformation. Differences between transformed intensities are
9181 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9182 their variance is independent of the mean, and they are usually more sensitive
9183 and specific in detecting differential transcription.")
9184 (license license:artistic2.0)))
9186 (define-public r-mzid
9193 (uri (bioconductor-uri "mzID" version))
9196 "15yd4bdxprw3kg7zj2k652y3yr3si781iw28jqvnkm0gsc23rd0c"))))
9197 (properties `((upstream-name . "mzID")))
9198 (build-system r-build-system)
9200 `(("r-doparallel" ,r-doparallel)
9201 ("r-foreach" ,r-foreach)
9202 ("r-iterators" ,r-iterators)
9204 ("r-protgenerics" ,r-protgenerics)
9207 (home-page "https://bioconductor.org/packages/mzID")
9208 (synopsis "Parser for mzIdentML files")
9210 "This package provides a parser for mzIdentML files implemented using the
9211 XML package. The parser tries to be general and able to handle all types of
9212 mzIdentML files with the drawback of having less pretty output than a vendor
9214 (license license:gpl2+)))
9216 (define-public r-pcamethods
9218 (name "r-pcamethods")
9223 (uri (bioconductor-uri "pcaMethods" version))
9226 "0ik82s9bsdj4a1mmv0a3k6yisa92mxx7maf3dvip1r8gqlm3dyng"))))
9227 (properties `((upstream-name . "pcaMethods")))
9228 (build-system r-build-system)
9230 `(("r-biobase" ,r-biobase)
9231 ("r-biocgenerics" ,r-biocgenerics)
9233 ("r-rcpp" ,r-rcpp)))
9234 (home-page "https://github.com/hredestig/pcamethods")
9235 (synopsis "Collection of PCA methods")
9237 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9238 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9239 for missing value estimation is included for comparison. BPCA, PPCA and
9240 NipalsPCA may be used to perform PCA on incomplete data as well as for
9241 accurate missing value estimation. A set of methods for printing and plotting
9242 the results is also provided. All PCA methods make use of the same data
9243 structure (pcaRes) to provide a common interface to the PCA results.")
9244 (license license:gpl3+)))
9246 (define-public r-msnbase
9253 (uri (bioconductor-uri "MSnbase" version))
9256 "1kl1d7byphnfpmbl5fzbgs68dxskhpsdyx7ka51bpfn0nv3pp492"))))
9257 (properties `((upstream-name . "MSnbase")))
9258 (build-system r-build-system)
9260 `(("r-affy" ,r-affy)
9261 ("r-biobase" ,r-biobase)
9262 ("r-biocgenerics" ,r-biocgenerics)
9263 ("r-biocparallel" ,r-biocparallel)
9264 ("r-digest" ,r-digest)
9265 ("r-ggplot2" ,r-ggplot2)
9266 ("r-impute" ,r-impute)
9267 ("r-iranges" ,r-iranges)
9268 ("r-lattice" ,r-lattice)
9269 ("r-maldiquant" ,r-maldiquant)
9273 ("r-pcamethods" ,r-pcamethods)
9275 ("r-preprocesscore" ,r-preprocesscore)
9276 ("r-protgenerics" ,r-protgenerics)
9278 ("r-s4vectors" ,r-s4vectors)
9279 ("r-scales" ,r-scales)
9282 (home-page "https://github.com/lgatto/MSnbase")
9283 (synopsis "Base functions and classes for MS-based proteomics")
9285 "This package provides basic plotting, data manipulation and processing
9286 of mass spectrometry based proteomics data.")
9287 (license license:artistic2.0)))
9289 (define-public r-msnid
9296 (uri (bioconductor-uri "MSnID" version))
9299 "077n6ljcnnl7q4w0qj8v46vm4sjk9vzzfqf7wsc6lz0wmyzqdng3"))))
9300 (properties `((upstream-name . "MSnID")))
9301 (build-system r-build-system)
9303 `(("r-biobase" ,r-biobase)
9304 ("r-data-table" ,r-data-table)
9305 ("r-doparallel" ,r-doparallel)
9306 ("r-dplyr" ,r-dplyr)
9307 ("r-foreach" ,r-foreach)
9308 ("r-iterators" ,r-iterators)
9309 ("r-msnbase" ,r-msnbase)
9312 ("r-protgenerics" ,r-protgenerics)
9313 ("r-r-cache" ,r-r-cache)
9315 ("r-reshape2" ,r-reshape2)))
9316 (home-page "https://bioconductor.org/packages/MSnID")
9317 (synopsis "Utilities for LC-MSn proteomics identifications")
9319 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9320 from mzIdentML (leveraging the mzID package) or text files. After collating
9321 the search results from multiple datasets it assesses their identification
9322 quality and optimize filtering criteria to achieve the maximum number of
9323 identifications while not exceeding a specified false discovery rate. It also
9324 contains a number of utilities to explore the MS/MS results and assess missed
9325 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9326 (license license:artistic2.0)))
9328 (define-public r-seurat
9334 (uri (cran-uri "Seurat" version))
9337 "0l8bv4i9nzz26mirnva10mq6pimibj24vk7vpvfypgn7xk4942hd"))))
9338 (properties `((upstream-name . "Seurat")))
9339 (build-system r-build-system)
9342 ("r-cluster" ,r-cluster)
9343 ("r-cowplot" ,r-cowplot)
9344 ("r-dosnow" ,r-dosnow)
9345 ("r-dplyr" ,r-dplyr)
9347 ("r-fitdistrplus" ,r-fitdistrplus)
9348 ("r-foreach" ,r-foreach)
9350 ("r-ggplot2" ,r-ggplot2)
9351 ("r-ggridges" ,r-ggridges)
9352 ("r-gplots" ,r-gplots)
9353 ("r-hdf5r" ,r-hdf5r)
9354 ("r-hmisc" ,r-hmisc)
9357 ("r-igraph" ,r-igraph)
9358 ("r-irlba" ,r-irlba)
9360 ("r-lmtest" ,r-lmtest)
9362 ("r-matrix" ,r-matrix)
9363 ("r-metap" ,r-metap)
9364 ("r-mixtools" ,r-mixtools)
9365 ("r-pbapply" ,r-pbapply)
9366 ("r-plotly" ,r-plotly)
9369 ("r-rcolorbrewer" ,r-rcolorbrewer)
9371 ("r-rcppeigen" ,r-rcppeigen)
9372 ("r-rcppprogress" ,r-rcppprogress)
9373 ("r-reshape2" ,r-reshape2)
9374 ("r-reticulate" ,r-reticulate)
9376 ("r-rtsne" ,r-rtsne)
9377 ("r-sdmtools" ,r-sdmtools)
9378 ("r-tidyr" ,r-tidyr)
9379 ("r-tsne" ,r-tsne)))
9380 (home-page "http://www.satijalab.org/seurat")
9381 (synopsis "Seurat is an R toolkit for single cell genomics")
9383 "This package is an R package designed for QC, analysis, and
9384 exploration of single cell RNA-seq data. It easily enables widely-used
9385 analytical techniques, including the identification of highly variable genes,
9386 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9387 algorithms; density clustering, hierarchical clustering, k-means, and the
9388 discovery of differentially expressed genes and markers.")
9389 (license license:gpl3)))
9391 (define-public r-aroma-light
9393 (name "r-aroma-light")
9398 (uri (bioconductor-uri "aroma.light" version))
9401 "0vfifgpqxjjncbiv6gvlk9jmj14j90r9f30bqk3ks9v1csjnjhrb"))))
9402 (properties `((upstream-name . "aroma.light")))
9403 (build-system r-build-system)
9405 `(("r-matrixstats" ,r-matrixstats)
9406 ("r-r-methodss3" ,r-r-methodss3)
9408 ("r-r-utils" ,r-r-utils)))
9409 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9410 (synopsis "Methods for normalization and visualization of microarray data")
9412 "This package provides methods for microarray analysis that take basic
9413 data types such as matrices and lists of vectors. These methods can be used
9414 standalone, be utilized in other packages, or be wrapped up in higher-level
9416 (license license:gpl2+)))
9418 (define-public r-deseq
9425 (uri (bioconductor-uri "DESeq" version))
9428 "0bpiixczbhlyaiinpbl6xrpmv72k2bq76bxnw06gl35m4pgs94p2"))))
9429 (properties `((upstream-name . "DESeq")))
9430 (build-system r-build-system)
9432 `(("r-biobase" ,r-biobase)
9433 ("r-biocgenerics" ,r-biocgenerics)
9434 ("r-genefilter" ,r-genefilter)
9435 ("r-geneplotter" ,r-geneplotter)
9436 ("r-lattice" ,r-lattice)
9437 ("r-locfit" ,r-locfit)
9439 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9440 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9441 (synopsis "Differential gene expression analysis")
9443 "This package provides tools for estimating variance-mean dependence in
9444 count data from high-throughput genetic sequencing assays and for testing for
9445 differential expression based on a model using the negative binomial
9447 (license license:gpl3+)))
9449 (define-public r-edaseq
9456 (uri (bioconductor-uri "EDASeq" version))
9459 "0559ph606ps2g9bwbl0a2knkcs5w581n9igngpjxvk5p56k24gb5"))))
9460 (properties `((upstream-name . "EDASeq")))
9461 (build-system r-build-system)
9463 `(("r-annotationdbi" ,r-annotationdbi)
9464 ("r-aroma-light" ,r-aroma-light)
9465 ("r-biobase" ,r-biobase)
9466 ("r-biocgenerics" ,r-biocgenerics)
9467 ("r-biocmanager" ,r-biocmanager)
9468 ("r-biomart" ,r-biomart)
9469 ("r-biostrings" ,r-biostrings)
9470 ("r-deseq" ,r-deseq)
9471 ("r-genomicfeatures" ,r-genomicfeatures)
9472 ("r-genomicranges" ,r-genomicranges)
9473 ("r-iranges" ,r-iranges)
9474 ("r-rsamtools" ,r-rsamtools)
9475 ("r-shortread" ,r-shortread)))
9476 (home-page "https://github.com/drisso/EDASeq")
9477 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9479 "This package provides support for numerical and graphical summaries of
9480 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9481 adjust for GC-content effect (or other gene-level effects) on read counts:
9482 loess robust local regression, global-scaling, and full-quantile
9483 normalization. Between-lane normalization procedures to adjust for
9484 distributional differences between lanes (e.g., sequencing depth):
9485 global-scaling and full-quantile normalization.")
9486 (license license:artistic2.0)))
9488 (define-public r-interactivedisplaybase
9490 (name "r-interactivedisplaybase")
9495 (uri (bioconductor-uri "interactiveDisplayBase" version))
9498 "04xz3dkwan2s5ic1mwkdfnggm0l41mgqfagx160bcsrpkw6z7ark"))))
9500 `((upstream-name . "interactiveDisplayBase")))
9501 (build-system r-build-system)
9503 `(("r-biocgenerics" ,r-biocgenerics)
9504 ("r-shiny" ,r-shiny)))
9505 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9506 (synopsis "Base package for web displays of Bioconductor objects")
9508 "This package contains the basic methods needed to generate interactive
9509 Shiny-based display methods for Bioconductor objects.")
9510 (license license:artistic2.0)))
9512 (define-public r-annotationhub
9514 (name "r-annotationhub")
9519 (uri (bioconductor-uri "AnnotationHub" version))
9522 "17fgrvcnbii9siv5rq5j09bxhqffx47f6jf10418qvr7hh61ic1g"))))
9523 (properties `((upstream-name . "AnnotationHub")))
9524 (build-system r-build-system)
9526 `(("r-annotationdbi" ,r-annotationdbi)
9527 ("r-biocgenerics" ,r-biocgenerics)
9528 ("r-biocmanager" ,r-biocmanager)
9531 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9532 ("r-rsqlite" ,r-rsqlite)
9533 ("r-s4vectors" ,r-s4vectors)
9534 ("r-yaml" ,r-yaml)))
9535 (home-page "https://bioconductor.org/packages/AnnotationHub")
9536 (synopsis "Client to access AnnotationHub resources")
9538 "This package provides a client for the Bioconductor AnnotationHub web
9539 resource. The AnnotationHub web resource provides a central location where
9540 genomic files (e.g. VCF, bed, wig) and other resources from standard
9541 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9542 metadata about each resource, e.g., a textual description, tags, and date of
9543 modification. The client creates and manages a local cache of files retrieved
9544 by the user, helping with quick and reproducible access.")
9545 (license license:artistic2.0)))
9547 (define-public r-fastseg
9554 (uri (bioconductor-uri "fastseg" version))
9557 "1l8mdjpfpgwqdss2ywjkb8b4h55wf8v6kmyxdlvy04ds2hj16sb1"))))
9558 (build-system r-build-system)
9560 `(("r-biobase" ,r-biobase)
9561 ("r-biocgenerics" ,r-biocgenerics)
9562 ("r-genomicranges" ,r-genomicranges)
9563 ("r-iranges" ,r-iranges)
9564 ("r-s4vectors" ,r-s4vectors)))
9565 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
9566 (synopsis "Fast segmentation algorithm for genetic sequencing data")
9568 "Fastseg implements a very fast and efficient segmentation algorithm.
9569 It can segment data from DNA microarrays and data from next generation
9570 sequencing for example to detect copy number segments. Further it can segment
9571 data from RNA microarrays like tiling arrays to identify transcripts. Most
9572 generally, it can segment data given as a matrix or as a vector. Various data
9573 formats can be used as input to fastseg like expression set objects for
9574 microarrays or GRanges for sequencing data.")
9575 (license license:lgpl2.0+)))
9577 (define-public r-keggrest
9584 (uri (bioconductor-uri "KEGGREST" version))
9587 "0blpd5a7whd2sswfhqd17h58hg06ymaf80gapdr9ja43hnnlj309"))))
9588 (properties `((upstream-name . "KEGGREST")))
9589 (build-system r-build-system)
9591 `(("r-biostrings" ,r-biostrings)
9594 (home-page "https://bioconductor.org/packages/KEGGREST")
9595 (synopsis "Client-side REST access to KEGG")
9597 "This package provides a package that provides a client interface to the
9598 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
9599 (license license:artistic2.0)))
9601 (define-public r-gage
9608 (uri (bioconductor-uri "gage" version))
9611 "02g796sb1800ff0f1mq9f2m5wwzpf8pnfzajs49i68dhq2hm01a8"))))
9612 (build-system r-build-system)
9614 `(("r-annotationdbi" ,r-annotationdbi)
9615 ("r-graph" ,r-graph)
9616 ("r-keggrest" ,r-keggrest)))
9617 (home-page "http://www.biomedcentral.com/1471-2105/10/161")
9618 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
9620 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
9621 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
9622 data attributes including sample sizes, experimental designs, assay platforms,
9623 and other types of heterogeneity. The gage package provides functions for
9624 basic GAGE analysis, result processing and presentation. In addition, it
9625 provides demo microarray data and commonly used gene set data based on KEGG
9626 pathways and GO terms. These funtions and data are also useful for gene set
9627 analysis using other methods.")
9628 (license license:gpl2+)))
9630 (define-public r-genomicfiles
9632 (name "r-genomicfiles")
9637 (uri (bioconductor-uri "GenomicFiles" version))
9640 "0qf2yj4lfnnk64fk125n8sqms01shfqiik04nasx2z3k129ykpxp"))))
9641 (properties `((upstream-name . "GenomicFiles")))
9642 (build-system r-build-system)
9644 `(("r-biocgenerics" ,r-biocgenerics)
9645 ("r-biocparallel" ,r-biocparallel)
9646 ("r-genomeinfodb" ,r-genomeinfodb)
9647 ("r-genomicalignments" ,r-genomicalignments)
9648 ("r-genomicranges" ,r-genomicranges)
9649 ("r-iranges" ,r-iranges)
9650 ("r-rsamtools" ,r-rsamtools)
9651 ("r-rtracklayer" ,r-rtracklayer)
9652 ("r-s4vectors" ,r-s4vectors)
9653 ("r-summarizedexperiment" ,r-summarizedexperiment)
9654 ("r-variantannotation" ,r-variantannotation)))
9655 (home-page "https://bioconductor.org/packages/GenomicFiles")
9656 (synopsis "Distributed computing by file or by range")
9658 "This package provides infrastructure for parallel computations
9659 distributed by file or by range. User defined mapper and reducer functions
9660 provide added flexibility for data combination and manipulation.")
9661 (license license:artistic2.0)))
9663 (define-public r-complexheatmap
9665 (name "r-complexheatmap")
9670 (uri (bioconductor-uri "ComplexHeatmap" version))
9673 "0s01dzcfj1lmpqfpsbqw7r4858krfzy499lz4cwx4fq3mbyvy2aj"))))
9675 `((upstream-name . "ComplexHeatmap")))
9676 (build-system r-build-system)
9678 `(("r-circlize" ,r-circlize)
9679 ("r-colorspace" ,r-colorspace)
9680 ("r-getoptlong" ,r-getoptlong)
9681 ("r-globaloptions" ,r-globaloptions)
9682 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9684 "https://github.com/jokergoo/ComplexHeatmap")
9685 (synopsis "Making Complex Heatmaps")
9687 "Complex heatmaps are efficient to visualize associations between
9688 different sources of data sets and reveal potential structures. This package
9689 provides a highly flexible way to arrange multiple heatmaps and supports
9690 self-defined annotation graphics.")
9691 (license license:gpl2+)))
9693 (define-public r-dirichletmultinomial
9695 (name "r-dirichletmultinomial")
9700 (uri (bioconductor-uri "DirichletMultinomial" version))
9703 "0vazfjzqy78p5g7dnv30lbqbj4bhq4zafd2wh6gdwy2il1fd78xa"))))
9705 `((upstream-name . "DirichletMultinomial")))
9706 (build-system r-build-system)
9710 `(("r-biocgenerics" ,r-biocgenerics)
9711 ("r-iranges" ,r-iranges)
9712 ("r-s4vectors" ,r-s4vectors)))
9713 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
9714 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
9716 "Dirichlet-multinomial mixture models can be used to describe variability
9717 in microbial metagenomic data. This package is an interface to code
9718 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
9720 (license license:lgpl3)))
9722 (define-public r-ensembldb
9724 (name "r-ensembldb")
9729 (uri (bioconductor-uri "ensembldb" version))
9732 "0kzdsfk6mdwlp57sw4j2cf7lx5nc67v5j0xr3iag9kzmgikaq1lb"))))
9733 (build-system r-build-system)
9735 `(("r-annotationdbi" ,r-annotationdbi)
9736 ("r-annotationfilter" ,r-annotationfilter)
9737 ("r-biobase" ,r-biobase)
9738 ("r-biocgenerics" ,r-biocgenerics)
9739 ("r-biostrings" ,r-biostrings)
9742 ("r-genomeinfodb" ,r-genomeinfodb)
9743 ("r-genomicfeatures" ,r-genomicfeatures)
9744 ("r-genomicranges" ,r-genomicranges)
9745 ("r-iranges" ,r-iranges)
9746 ("r-protgenerics" ,r-protgenerics)
9747 ("r-rsamtools" ,r-rsamtools)
9748 ("r-rsqlite" ,r-rsqlite)
9749 ("r-rtracklayer" ,r-rtracklayer)
9750 ("r-s4vectors" ,r-s4vectors)))
9751 (home-page "https://github.com/jotsetung/ensembldb")
9752 (synopsis "Utilities to create and use Ensembl-based annotation databases")
9754 "The package provides functions to create and use transcript-centric
9755 annotation databases/packages. The annotation for the databases are directly
9756 fetched from Ensembl using their Perl API. The functionality and data is
9757 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
9758 but, in addition to retrieve all gene/transcript models and annotations from
9759 the database, the @code{ensembldb} package also provides a filter framework
9760 allowing to retrieve annotations for specific entries like genes encoded on a
9761 chromosome region or transcript models of lincRNA genes.")
9762 ;; No version specified
9763 (license license:lgpl3+)))
9765 (define-public r-organismdbi
9767 (name "r-organismdbi")
9772 (uri (bioconductor-uri "OrganismDbi" version))
9775 "11pyv56cy4iy095h40k6k0mpjdlh6gsb4ld3s57nfa9nd4ypx3yi"))))
9776 (properties `((upstream-name . "OrganismDbi")))
9777 (build-system r-build-system)
9779 `(("r-annotationdbi" ,r-annotationdbi)
9780 ("r-biobase" ,r-biobase)
9781 ("r-biocgenerics" ,r-biocgenerics)
9782 ("r-biocmanager" ,r-biocmanager)
9784 ("r-genomicfeatures" ,r-genomicfeatures)
9785 ("r-genomicranges" ,r-genomicranges)
9786 ("r-graph" ,r-graph)
9787 ("r-iranges" ,r-iranges)
9789 ("r-s4vectors" ,r-s4vectors)))
9790 (home-page "https://bioconductor.org/packages/OrganismDbi")
9791 (synopsis "Software to enable the smooth interfacing of database packages")
9792 (description "The package enables a simple unified interface to several
9793 annotation packages each of which has its own schema by taking advantage of
9794 the fact that each of these packages implements a select methods.")
9795 (license license:artistic2.0)))
9797 (define-public r-biovizbase
9799 (name "r-biovizbase")
9804 (uri (bioconductor-uri "biovizBase" version))
9807 "0v5gvcx180qn5487i1dph9abadw3ggqwp5yzy41jswzbdc8q6sbm"))))
9808 (properties `((upstream-name . "biovizBase")))
9809 (build-system r-build-system)
9811 `(("r-annotationdbi" ,r-annotationdbi)
9812 ("r-annotationfilter" ,r-annotationfilter)
9813 ("r-biocgenerics" ,r-biocgenerics)
9814 ("r-biostrings" ,r-biostrings)
9815 ("r-dichromat" ,r-dichromat)
9816 ("r-ensembldb" ,r-ensembldb)
9817 ("r-genomeinfodb" ,r-genomeinfodb)
9818 ("r-genomicalignments" ,r-genomicalignments)
9819 ("r-genomicfeatures" ,r-genomicfeatures)
9820 ("r-genomicranges" ,r-genomicranges)
9821 ("r-hmisc" ,r-hmisc)
9822 ("r-iranges" ,r-iranges)
9823 ("r-rcolorbrewer" ,r-rcolorbrewer)
9824 ("r-rlang" ,r-rlang)
9825 ("r-rsamtools" ,r-rsamtools)
9826 ("r-s4vectors" ,r-s4vectors)
9827 ("r-scales" ,r-scales)
9828 ("r-summarizedexperiment" ,r-summarizedexperiment)
9829 ("r-variantannotation" ,r-variantannotation)))
9830 (home-page "https://bioconductor.org/packages/biovizBase")
9831 (synopsis "Basic graphic utilities for visualization of genomic data")
9833 "The biovizBase package is designed to provide a set of utilities, color
9834 schemes and conventions for genomic data. It serves as the base for various
9835 high-level packages for biological data visualization. This saves development
9836 effort and encourages consistency.")
9837 (license license:artistic2.0)))
9839 (define-public r-ggbio
9846 (uri (bioconductor-uri "ggbio" version))
9849 "0wq49qqzkcn8s19xgaxf2s1j1a563d7pbhhvris6fhxfdjsz4934"))))
9850 (build-system r-build-system)
9852 `(("r-annotationdbi" ,r-annotationdbi)
9853 ("r-annotationfilter" ,r-annotationfilter)
9854 ("r-biobase" ,r-biobase)
9855 ("r-biocgenerics" ,r-biocgenerics)
9856 ("r-biostrings" ,r-biostrings)
9857 ("r-biovizbase" ,r-biovizbase)
9858 ("r-bsgenome" ,r-bsgenome)
9859 ("r-ensembldb" ,r-ensembldb)
9860 ("r-genomeinfodb" ,r-genomeinfodb)
9861 ("r-genomicalignments" ,r-genomicalignments)
9862 ("r-genomicfeatures" ,r-genomicfeatures)
9863 ("r-genomicranges" ,r-genomicranges)
9864 ("r-ggally" ,r-ggally)
9865 ("r-ggplot2" ,r-ggplot2)
9866 ("r-gridextra" ,r-gridextra)
9867 ("r-gtable" ,r-gtable)
9868 ("r-hmisc" ,r-hmisc)
9869 ("r-iranges" ,r-iranges)
9870 ("r-organismdbi" ,r-organismdbi)
9871 ("r-reshape2" ,r-reshape2)
9872 ("r-rlang" ,r-rlang)
9873 ("r-rsamtools" ,r-rsamtools)
9874 ("r-rtracklayer" ,r-rtracklayer)
9875 ("r-s4vectors" ,r-s4vectors)
9876 ("r-scales" ,r-scales)
9877 ("r-summarizedexperiment" ,r-summarizedexperiment)
9878 ("r-variantannotation" ,r-variantannotation)))
9879 (home-page "http://www.tengfei.name/ggbio/")
9880 (synopsis "Visualization tools for genomic data")
9882 "The ggbio package extends and specializes the grammar of graphics for
9883 biological data. The graphics are designed to answer common scientific
9884 questions, in particular those often asked of high throughput genomics data.
9885 All core Bioconductor data structures are supported, where appropriate. The
9886 package supports detailed views of particular genomic regions, as well as
9887 genome-wide overviews. Supported overviews include ideograms and grand linear
9888 views. High-level plots include sequence fragment length, edge-linked
9889 interval to data view, mismatch pileup, and several splicing summaries.")
9890 (license license:artistic2.0)))
9892 (define-public r-gprofiler
9894 (name "r-gprofiler")
9899 (uri (cran-uri "gProfileR" version))
9902 "12nwidbnqmnfy5dnqga26byslvdnkrpz2fi19qfcby6xx0wbndk7"))))
9903 (properties `((upstream-name . "gProfileR")))
9904 (build-system r-build-system)
9906 `(("r-plyr" ,r-plyr)
9907 ("r-rcurl" ,r-rcurl)))
9908 (home-page "https://cran.r-project.org/web/packages/gProfileR/")
9909 (synopsis "Interface to the g:Profiler toolkit")
9911 "This package provides tools for functional enrichment analysis,
9912 gene identifier conversion and mapping homologous genes across related
9913 organisms via the @code{g:Profiler} toolkit.")
9914 (license license:gpl2+)))
9916 (define-public r-gqtlbase
9923 (uri (bioconductor-uri "gQTLBase" version))
9926 "1lbk1m1mkvbk30flk5pf3pcrnm2s0sj5r48kbjgad39dsvd8zgqx"))))
9927 (properties `((upstream-name . "gQTLBase")))
9928 (build-system r-build-system)
9930 `(("r-batchjobs" ,r-batchjobs)
9931 ("r-bbmisc" ,r-bbmisc)
9932 ("r-biocgenerics" ,r-biocgenerics)
9934 ("r-doparallel" ,r-doparallel)
9936 ("r-ffbase" ,r-ffbase)
9937 ("r-foreach" ,r-foreach)
9938 ("r-genomicfiles" ,r-genomicfiles)
9939 ("r-genomicranges" ,r-genomicranges)
9940 ("r-rtracklayer" ,r-rtracklayer)
9941 ("r-s4vectors" ,r-s4vectors)
9942 ("r-summarizedexperiment" ,r-summarizedexperiment)))
9943 (home-page "https://bioconductor.org/packages/gQTLBase")
9944 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
9946 "The purpose of this package is to simplify the storage and interrogation
9947 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
9949 (license license:artistic2.0)))
9951 (define-public r-snpstats
9958 (uri (bioconductor-uri "snpStats" version))
9961 "1pplx4pf9bqi7v5v1l74yknc1s61carvbqkf327ky7vbvp0bck33"))))
9962 (properties `((upstream-name . "snpStats")))
9963 (build-system r-build-system)
9964 (inputs `(("zlib" ,zlib)))
9966 `(("r-biocgenerics" ,r-biocgenerics)
9967 ("r-matrix" ,r-matrix)
9968 ("r-survival" ,r-survival)
9969 ("r-zlibbioc" ,r-zlibbioc)))
9970 (home-page "https://bioconductor.org/packages/snpStats")
9971 (synopsis "Methods for SNP association studies")
9973 "This package provides classes and statistical methods for large
9974 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
9975 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
9976 (license license:gpl3)))
9978 (define-public r-homo-sapiens
9980 (name "r-homo-sapiens")
9984 ;; We cannot use bioconductor-uri here because this tarball is
9985 ;; located under "data/annotation/" instead of "bioc/".
9986 (uri (string-append "http://www.bioconductor.org/packages/"
9987 "release/data/annotation/src/contrib/"
9992 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
9994 `((upstream-name . "Homo.sapiens")))
9995 (build-system r-build-system)
9997 `(("r-genomicfeatures" ,r-genomicfeatures)
9998 ("r-go-db" ,r-go-db)
9999 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10000 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10001 ("r-organismdbi" ,r-organismdbi)
10002 ("r-annotationdbi" ,r-annotationdbi)))
10003 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10004 (synopsis "Annotation package for the Homo.sapiens object")
10006 "This package contains the Homo.sapiens object to access data from
10007 several related annotation packages.")
10008 (license license:artistic2.0)))
10010 (define-public r-erma
10017 (uri (bioconductor-uri "erma" version))
10020 "0hj9iz904rr1y66442lkxjywkw1ydyxxlhmjirawbf09ic5ad4g9"))))
10021 (build-system r-build-system)
10023 `(("r-annotationdbi" ,r-annotationdbi)
10024 ("r-biobase" ,r-biobase)
10025 ("r-biocgenerics" ,r-biocgenerics)
10026 ("r-biocparallel" ,r-biocparallel)
10027 ("r-genomeinfodb" ,r-genomeinfodb)
10028 ("r-genomicfiles" ,r-genomicfiles)
10029 ("r-genomicranges" ,r-genomicranges)
10030 ("r-ggplot2" ,r-ggplot2)
10031 ("r-homo-sapiens" ,r-homo-sapiens)
10032 ("r-iranges" ,r-iranges)
10033 ("r-rtracklayer" ,r-rtracklayer)
10034 ("r-s4vectors" ,r-s4vectors)
10035 ("r-shiny" ,r-shiny)
10036 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10037 (home-page "https://bioconductor.org/packages/erma")
10038 (synopsis "Epigenomic road map adventures")
10040 "The epigenomics road map describes locations of epigenetic marks in DNA
10041 from a variety of cell types. Of interest are locations of histone
10042 modifications, sites of DNA methylation, and regions of accessible chromatin.
10043 This package presents a selection of elements of the road map including
10044 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10045 by Ernst and Kellis.")
10046 (license license:artistic2.0)))
10048 (define-public r-ldblock
10055 (uri (bioconductor-uri "ldblock" version))
10058 "0xbf4pmhrk5fnd1iz5wzjvdr75v114bwpznhcig4wiqmxc27sips"))))
10059 (build-system r-build-system)
10061 `(("r-biocgenerics" ,r-biocgenerics)
10063 ("r-genomeinfodb" ,r-genomeinfodb)
10064 ("r-genomicfiles" ,r-genomicfiles)
10065 ("r-go-db" ,r-go-db)
10066 ("r-homo-sapiens" ,r-homo-sapiens)
10067 ("r-matrix" ,r-matrix)
10068 ("r-rsamtools" ,r-rsamtools)
10069 ("r-snpstats" ,r-snpstats)
10070 ("r-variantannotation" ,r-variantannotation)))
10071 (home-page "https://bioconductor.org/packages/ldblock")
10072 (synopsis "Data structures for linkage disequilibrium measures in populations")
10074 "This package defines data structures for @dfn{linkage
10075 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10076 handling of existing population-level data for the purpose of flexibly
10077 defining LD blocks.")
10078 (license license:artistic2.0)))
10080 (define-public r-gqtlstats
10082 (name "r-gqtlstats")
10087 (uri (bioconductor-uri "gQTLstats" version))
10090 "1sg9kw59dlayj7qxql9pd93d4hmml504sa3kkfpzfh3xri7m5pxf"))))
10091 (properties `((upstream-name . "gQTLstats")))
10092 (build-system r-build-system)
10094 `(("r-annotationdbi" ,r-annotationdbi)
10095 ("r-batchjobs" ,r-batchjobs)
10096 ("r-bbmisc" ,r-bbmisc)
10097 ("r-beeswarm" ,r-beeswarm)
10098 ("r-biobase" ,r-biobase)
10099 ("r-biocgenerics" ,r-biocgenerics)
10100 ("r-doparallel" ,r-doparallel)
10101 ("r-dplyr" ,r-dplyr)
10103 ("r-ffbase" ,r-ffbase)
10104 ("r-foreach" ,r-foreach)
10105 ("r-genomeinfodb" ,r-genomeinfodb)
10106 ("r-genomicfeatures" ,r-genomicfeatures)
10107 ("r-genomicfiles" ,r-genomicfiles)
10108 ("r-genomicranges" ,r-genomicranges)
10109 ("r-ggbeeswarm" ,r-ggbeeswarm)
10110 ("r-ggplot2" ,r-ggplot2)
10111 ("r-gqtlbase" ,r-gqtlbase)
10112 ("r-hardyweinberg" ,r-hardyweinberg)
10113 ("r-homo-sapiens" ,r-homo-sapiens)
10114 ("r-iranges" ,r-iranges)
10115 ("r-limma" ,r-limma)
10117 ("r-plotly" ,r-plotly)
10118 ("r-reshape2" ,r-reshape2)
10119 ("r-s4vectors" ,r-s4vectors)
10120 ("r-shiny" ,r-shiny)
10121 ("r-snpstats" ,r-snpstats)
10122 ("r-summarizedexperiment" ,r-summarizedexperiment)
10123 ("r-variantannotation" ,r-variantannotation)))
10124 (home-page "https://bioconductor.org/packages/gQTLstats")
10125 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10127 "This package provides tools for the computationally efficient analysis
10128 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10129 The software in this package aims to support refinements and functional
10130 interpretation of members of a collection of association statistics on a
10131 family of feature/genome hypotheses.")
10132 (license license:artistic2.0)))
10134 (define-public r-gviz
10141 (uri (bioconductor-uri "Gviz" version))
10144 "0jvcivgw0ahv2rjadxmrww76xambhf7silczmh38nn4yn4qw6w9y"))))
10145 (properties `((upstream-name . "Gviz")))
10146 (build-system r-build-system)
10148 `(("r-annotationdbi" ,r-annotationdbi)
10149 ("r-biobase" ,r-biobase)
10150 ("r-biocgenerics" ,r-biocgenerics)
10151 ("r-biomart" ,r-biomart)
10152 ("r-biostrings" ,r-biostrings)
10153 ("r-biovizbase" ,r-biovizbase)
10154 ("r-bsgenome" ,r-bsgenome)
10155 ("r-digest" ,r-digest)
10156 ("r-genomeinfodb" ,r-genomeinfodb)
10157 ("r-genomicalignments" ,r-genomicalignments)
10158 ("r-genomicfeatures" ,r-genomicfeatures)
10159 ("r-genomicranges" ,r-genomicranges)
10160 ("r-iranges" ,r-iranges)
10161 ("r-lattice" ,r-lattice)
10162 ("r-latticeextra" ,r-latticeextra)
10163 ("r-matrixstats" ,r-matrixstats)
10164 ("r-rcolorbrewer" ,r-rcolorbrewer)
10165 ("r-rsamtools" ,r-rsamtools)
10166 ("r-rtracklayer" ,r-rtracklayer)
10167 ("r-s4vectors" ,r-s4vectors)
10168 ("r-xvector" ,r-xvector)))
10169 (home-page "https://bioconductor.org/packages/Gviz")
10170 (synopsis "Plotting data and annotation information along genomic coordinates")
10172 "Genomic data analyses requires integrated visualization of known genomic
10173 information and new experimental data. Gviz uses the biomaRt and the
10174 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10175 and translates this to e.g. gene/transcript structures in viewports of the
10176 grid graphics package. This results in genomic information plotted together
10178 (license license:artistic2.0)))
10180 (define-public r-gwascat
10187 (uri (bioconductor-uri "gwascat" version))
10190 "1fnyjydhicq4ayrv0lqjv48h9bd72h40s6l82g1h2ng0icwz38g0"))))
10191 (build-system r-build-system)
10193 `(("r-annotationdbi" ,r-annotationdbi)
10194 ("r-annotationhub" ,r-annotationhub)
10195 ("r-biocgenerics" ,r-biocgenerics)
10196 ("r-biostrings" ,r-biostrings)
10197 ("r-genomeinfodb" ,r-genomeinfodb)
10198 ("r-genomicfeatures" ,r-genomicfeatures)
10199 ("r-genomicranges" ,r-genomicranges)
10200 ("r-ggbio" ,r-ggbio)
10201 ("r-ggplot2" ,r-ggplot2)
10202 ("r-gqtlstats" ,r-gqtlstats)
10203 ("r-graph" ,r-graph)
10205 ("r-homo-sapiens" ,r-homo-sapiens)
10206 ("r-iranges" ,r-iranges)
10207 ("r-rsamtools" ,r-rsamtools)
10208 ("r-rtracklayer" ,r-rtracklayer)
10209 ("r-s4vectors" ,r-s4vectors)
10210 ("r-snpstats" ,r-snpstats)
10211 ("r-summarizedexperiment" ,r-summarizedexperiment)
10212 ("r-variantannotation" ,r-variantannotation)))
10213 (home-page "https://bioconductor.org/packages/gwascat")
10214 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10216 "This package provides tools for representing and modeling data in the
10217 EMBL-EBI GWAS catalog.")
10218 (license license:artistic2.0)))
10220 (define-public r-sushi
10226 (uri (bioconductor-uri "Sushi" version))
10229 "0dv5di0hgbvk9cxnqhyf18mdjl50k6bk00a89r6zgp83rbxwr1r8"))))
10230 (properties `((upstream-name . "Sushi")))
10231 (build-system r-build-system)
10233 `(("r-biomart" ,r-biomart)
10235 (home-page "https://bioconductor.org/packages/Sushi")
10236 (synopsis "Tools for visualizing genomics data")
10238 "This package provides flexible, quantitative, and integrative genomic
10239 visualizations for publication-quality multi-panel figures.")
10240 (license license:gpl2+)))
10242 (define-public r-fithic
10248 (uri (bioconductor-uri "FitHiC" version))
10251 "15xd8mz7660q4zr9p74mq1pqps4iz7pxp8f9ifn21gwg94aq1avn"))))
10252 (properties `((upstream-name . "FitHiC")))
10253 (build-system r-build-system)
10255 `(("r-data-table" ,r-data-table)
10256 ("r-fdrtool" ,r-fdrtool)
10257 ("r-rcpp" ,r-rcpp)))
10258 (home-page "https://bioconductor.org/packages/FitHiC")
10259 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10261 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10262 intra-chromosomal contact maps produced by genome-wide genome architecture
10263 assays such as Hi-C.")
10264 (license license:gpl2+)))
10266 (define-public r-hitc
10272 (uri (bioconductor-uri "HiTC" version))
10275 "11f96k1707g6milpjgnrjf3b5r42hsrxhb5d8znkcr3y3mrskdbj"))))
10276 (properties `((upstream-name . "HiTC")))
10277 (build-system r-build-system)
10279 `(("r-biostrings" ,r-biostrings)
10280 ("r-genomeinfodb" ,r-genomeinfodb)
10281 ("r-genomicranges" ,r-genomicranges)
10282 ("r-iranges" ,r-iranges)
10283 ("r-matrix" ,r-matrix)
10284 ("r-rcolorbrewer" ,r-rcolorbrewer)
10285 ("r-rtracklayer" ,r-rtracklayer)))
10286 (home-page "https://bioconductor.org/packages/HiTC")
10287 (synopsis "High throughput chromosome conformation capture analysis")
10289 "The HiTC package was developed to explore high-throughput \"C\" data
10290 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10291 quality controls, normalization, visualization, and further analysis are also
10293 (license license:artistic2.0)))
10295 (define-public r-qvalue
10302 (uri (bioconductor-uri "qvalue" version))
10305 "0kxavzm1j2mk26qicmjm90nxx4w5h3dxighzks7wzihay3k8cysc"))))
10306 (build-system r-build-system)
10308 `(("r-ggplot2" ,r-ggplot2)
10309 ("r-reshape2" ,r-reshape2)))
10310 (home-page "http://github.com/jdstorey/qvalue")
10311 (synopsis "Q-value estimation for false discovery rate control")
10313 "This package takes a list of p-values resulting from the simultaneous
10314 testing of many hypotheses and estimates their q-values and local @dfn{false
10315 discovery rate} (FDR) values. The q-value of a test measures the proportion
10316 of false positives incurred when that particular test is called significant.
10317 The local FDR measures the posterior probability the null hypothesis is true
10318 given the test's p-value. Various plots are automatically generated, allowing
10319 one to make sensible significance cut-offs. The software can be applied to
10320 problems in genomics, brain imaging, astrophysics, and data mining.")
10321 ;; Any version of the LGPL.
10322 (license license:lgpl3+)))
10324 (define-public r-hdf5array
10326 (name "r-hdf5array")
10331 (uri (bioconductor-uri "HDF5Array" version))
10334 "1qwdsygcadl58qj598hfyvs8hp0hqcl9ghnhknahrlhmb7k2bd2d"))))
10335 (properties `((upstream-name . "HDF5Array")))
10336 (build-system r-build-system)
10338 `(("r-biocgenerics" ,r-biocgenerics)
10339 ("r-delayedarray" ,r-delayedarray)
10340 ("r-iranges" ,r-iranges)
10341 ("r-rhdf5" ,r-rhdf5)
10342 ("r-s4vectors" ,r-s4vectors)))
10343 (home-page "https://bioconductor.org/packages/HDF5Array")
10344 (synopsis "HDF5 back end for DelayedArray objects")
10345 (description "This package provides an array-like container for convenient
10346 access and manipulation of HDF5 datasets. It supports delayed operations and
10347 block processing.")
10348 (license license:artistic2.0)))
10350 (define-public r-rhdf5lib
10352 (name "r-rhdf5lib")
10357 (uri (bioconductor-uri "Rhdf5lib" version))
10360 "06bxd3wz8lrvh2hzvmjpdv4lvzj5lz9353bw5b3zb98cb8w9r2j5"))
10361 (modules '((guix build utils)))
10364 ;; Delete bundled binaries
10365 (delete-file-recursively "src/winlib/")
10367 (properties `((upstream-name . "Rhdf5lib")))
10368 (build-system r-build-system)
10371 (modify-phases %standard-phases
10372 (add-after 'unpack 'do-not-use-bundled-hdf5
10373 (lambda* (#:key inputs #:allow-other-keys)
10374 (for-each delete-file '("configure" "configure.ac"))
10375 ;; Do not make other packages link with the proprietary libsz.
10376 (substitute* "R/zzz.R"
10377 (("'%s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a -lz'")
10378 "'%s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a -lz'")
10379 (("'%s/libhdf5.a %s/libsz.a -lz'")
10380 "'%s/libhdf5.a %s/libhdf5.a -lz'"))
10381 (with-directory-excursion "src"
10382 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10383 (rename-file (string-append "hdf5-" ,(package-version hdf5-1.10))
10385 ;; Remove timestamp and host system information to make
10386 ;; the build reproducible.
10387 (substitute* "hdf5/src/libhdf5.settings.in"
10388 (("Configured on: @CONFIG_DATE@")
10389 "Configured on: Guix")
10390 (("Uname information:.*")
10391 "Uname information: Linux\n")
10392 ;; Remove unnecessary store reference.
10394 "C Compiler: GCC\n"))
10395 (rename-file "Makevars.in" "Makevars")
10396 (substitute* "Makevars"
10397 (("HDF5_CXX_LIB=.*")
10398 (string-append "HDF5_CXX_LIB="
10399 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10401 (string-append "HDF5_LIB="
10402 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10403 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10404 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10405 ;; szip is non-free software
10406 (("cp \\$\\{SZIP_LIB\\}.*") "")
10407 (("\\$\\{USER_LIB_DIR\\}libsz.a") "")))
10412 `(("hdf5" ,hdf5-1.10)))
10414 `(("hdf5-source" ,(package-source hdf5-1.10))))
10415 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10416 (synopsis "HDF5 library as an R package")
10417 (description "This package provides C and C++ HDF5 libraries for use in R
10419 (license license:artistic2.0)))
10421 (define-public r-beachmat
10423 (name "r-beachmat")
10428 (uri (bioconductor-uri "beachmat" version))
10431 "07zgmms0qg8gw7x0js46965bbhpfj2aa1h5ixdz9r332bxv9cdmr"))))
10432 (build-system r-build-system)
10437 `(("r-biocgenerics" ,r-biocgenerics)
10438 ("r-delayedarray" ,r-delayedarray)
10439 ("r-hdf5array" ,r-hdf5array)
10441 ("r-rhdf5" ,r-rhdf5)
10442 ("r-rhdf5lib" ,r-rhdf5lib)))
10443 (home-page "https://bioconductor.org/packages/beachmat")
10444 (synopsis "Compiling Bioconductor to handle each matrix type")
10445 (description "This package provides a consistent C++ class interface for a
10446 variety of commonly used matrix types, including sparse and HDF5-backed
10448 (license license:gpl3)))
10450 (define-public r-singlecellexperiment
10452 (name "r-singlecellexperiment")
10457 (uri (bioconductor-uri "SingleCellExperiment" version))
10460 "12139kk9cqgzpm6f3cwdsq31gj5lxamz2q939dy9fa0fa54gdaq4"))))
10462 `((upstream-name . "SingleCellExperiment")))
10463 (build-system r-build-system)
10465 `(("r-biocgenerics" ,r-biocgenerics)
10466 ("r-s4vectors" ,r-s4vectors)
10467 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10468 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10469 (synopsis "S4 classes for single cell data")
10470 (description "This package defines an S4 class for storing data from
10471 single-cell experiments. This includes specialized methods to store and
10472 retrieve spike-in information, dimensionality reduction coordinates and size
10473 factors for each cell, along with the usual metadata for genes and
10475 (license license:gpl3)))
10477 (define-public r-scater
10483 (uri (bioconductor-uri "scater" version))
10486 "0rijhy7g5qmcn927y1wyd63la1fhyar9fv1hccsqd23jd98yc55a"))))
10487 (build-system r-build-system)
10489 `(("r-beachmat" ,r-beachmat)
10490 ("r-biocgenerics" ,r-biocgenerics)
10491 ("r-biocparallel" ,r-biocparallel)
10492 ("r-delayedarray" ,r-delayedarray)
10493 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10494 ("r-dplyr" ,r-dplyr)
10495 ("r-ggbeeswarm" ,r-ggbeeswarm)
10496 ("r-ggplot2" ,r-ggplot2)
10497 ("r-matrix" ,r-matrix)
10500 ("r-reshape2" ,r-reshape2)
10501 ("r-rhdf5lib" ,r-rhdf5lib)
10502 ("r-s4vectors" ,r-s4vectors)
10503 ("r-singlecellexperiment" ,r-singlecellexperiment)
10504 ("r-summarizedexperiment" ,r-summarizedexperiment)
10505 ("r-viridis" ,r-viridis)))
10506 (home-page "https://github.com/davismcc/scater")
10507 (synopsis "Single-cell analysis toolkit for gene expression data in R")
10508 (description "This package provides a collection of tools for doing
10509 various analyses of single-cell RNA-seq gene expression data, with a focus on
10511 (license license:gpl2+)))
10513 (define-public r-scran
10520 (uri (bioconductor-uri "scran" version))
10523 "07mgilr3gq3lnrm1fjm9zhz4w7970bjhsykln1drqy9gkzj5sn7g"))))
10524 (build-system r-build-system)
10526 `(("r-beachmat" ,r-beachmat)
10527 ("r-biocgenerics" ,r-biocgenerics)
10528 ("r-biocneighbors" ,r-biocneighbors)
10529 ("r-biocparallel" ,r-biocparallel)
10530 ("r-delayedarray" ,r-delayedarray)
10531 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10532 ("r-dynamictreecut" ,r-dynamictreecut)
10533 ("r-edger" ,r-edger)
10534 ("r-igraph" ,r-igraph)
10535 ("r-limma" ,r-limma)
10536 ("r-matrix" ,r-matrix)
10538 ("r-rhdf5lib" ,r-rhdf5lib)
10539 ("r-s4vectors" ,r-s4vectors)
10540 ("r-scater" ,r-scater)
10541 ("r-singlecellexperiment" ,r-singlecellexperiment)
10542 ("r-statmod" ,r-statmod)
10543 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10544 (home-page "https://bioconductor.org/packages/scran")
10545 (synopsis "Methods for single-cell RNA-Seq data analysis")
10546 (description "This package implements a variety of low-level analyses of
10547 single-cell RNA-seq data. Methods are provided for normalization of
10548 cell-specific biases, assignment of cell cycle phase, and detection of highly
10549 variable and significantly correlated genes.")
10550 (license license:gpl3)))
10552 (define-public r-delayedmatrixstats
10554 (name "r-delayedmatrixstats")
10559 (uri (bioconductor-uri "DelayedMatrixStats" version))
10562 "03fk2avl1vyjv2wslczkc82qr0zmp1ra8iimd47pbmnnm839ly4w"))))
10564 `((upstream-name . "DelayedMatrixStats")))
10565 (build-system r-build-system)
10567 `(("r-biocparallel" ,r-biocparallel)
10568 ("r-delayedarray" ,r-delayedarray)
10569 ("r-hdf5array" ,r-hdf5array)
10570 ("r-iranges" ,r-iranges)
10571 ("r-matrix" ,r-matrix)
10572 ("r-matrixstats" ,r-matrixstats)
10573 ("r-s4vectors" ,r-s4vectors)))
10574 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
10575 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
10577 "This package provides a port of the @code{matrixStats} API for use with
10578 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
10579 contains high-performing functions operating on rows and columns of
10580 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
10581 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
10582 are optimized per data type and for subsetted calculations such that both
10583 memory usage and processing time is minimized.")
10584 (license license:expat)))
10586 (define-public r-phangorn
10588 (name "r-phangorn")
10593 (uri (cran-uri "phangorn" version))
10596 "0xc8k552nxczy19jr0xjjagrzc8x6lafasgk2c099ls8bc1yml1i"))))
10597 (build-system r-build-system)
10600 ("r-fastmatch" ,r-fastmatch)
10601 ("r-igraph" ,r-igraph)
10602 ("r-magrittr" ,r-magrittr)
10603 ("r-matrix" ,r-matrix)
10604 ("r-quadprog" ,r-quadprog)
10605 ("r-rcpp" ,r-rcpp)))
10606 (home-page "https://github.com/KlausVigo/phangorn")
10607 (synopsis "Phylogenetic analysis in R")
10609 "Phangorn is a package for phylogenetic analysis in R. It supports
10610 estimation of phylogenetic trees and networks using Maximum Likelihood,
10611 Maximum Parsimony, distance methods and Hadamard conjugation.")
10612 (license license:gpl2+)))
10614 (define-public r-dropbead
10615 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
10618 (name "r-dropbead")
10619 (version (string-append "0-" revision "." (string-take commit 7)))
10623 (uri (git-reference
10624 (url "https://github.com/rajewsky-lab/dropbead.git")
10626 (file-name (git-file-name name version))
10629 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
10630 (build-system r-build-system)
10632 `(("r-ggplot2" ,r-ggplot2)
10633 ("r-rcolorbrewer" ,r-rcolorbrewer)
10634 ("r-gridextra" ,r-gridextra)
10635 ("r-gplots" ,r-gplots)
10636 ("r-plyr" ,r-plyr)))
10637 (home-page "https://github.com/rajewsky-lab/dropbead")
10638 (synopsis "Basic exploration and analysis of Drop-seq data")
10639 (description "This package offers a quick and straight-forward way to
10640 explore and perform basic analysis of single cell sequencing data coming from
10641 droplet sequencing. It has been particularly tailored for Drop-seq.")
10642 (license license:gpl3))))
10644 (define htslib-for-sambamba
10645 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
10648 (name "htslib-for-sambamba")
10649 (version (string-append "1.3.1-1." (string-take commit 9)))
10653 (uri (git-reference
10654 (url "https://github.com/lomereiter/htslib.git")
10656 (file-name (string-append "htslib-" version "-checkout"))
10659 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
10661 `(("autoconf" ,autoconf)
10662 ("automake" ,automake)
10663 ,@(package-native-inputs htslib))))))
10665 (define-public sambamba
10672 (uri (git-reference
10673 (url "https://github.com/lomereiter/sambamba.git")
10674 (commit (string-append "v" version))))
10675 (file-name (string-append name "-" version "-checkout"))
10678 "0k0cz3qcv98p6cq09zlbgnjsggxcqbcmzxg5zikgcgbr2nfq4lry"))))
10679 (build-system gnu-build-system)
10681 `(#:tests? #f ; there is no test target
10682 #:parallel-build? #f ; not supported
10684 (modify-phases %standard-phases
10685 (delete 'configure)
10686 (add-after 'unpack 'fix-ldc-version
10688 (substitute* "gen_ldc_version_info.py"
10689 (("/usr/bin/env.*") (which "python3")))
10690 (substitute* "Makefile"
10691 ;; We use ldc2 instead of ldmd2 to compile sambamba.
10692 (("\\$\\(shell which ldmd2\\)") (which "ldc2")))
10694 (add-after 'unpack 'place-biod-and-undead
10695 (lambda* (#:key inputs #:allow-other-keys)
10696 (copy-recursively (assoc-ref inputs "biod") "BioD")
10697 (copy-recursively (assoc-ref inputs "undead") "undeaD")
10699 (add-after 'unpack 'unbundle-prerequisites
10701 (substitute* "Makefile"
10702 (("htslib/libhts.a lz4/lib/liblz4.a")
10704 ((" lz4-static htslib-static") ""))
10707 (lambda* (#:key outputs #:allow-other-keys)
10708 (let* ((out (assoc-ref outputs "out"))
10709 (bin (string-append out "/bin")))
10711 (install-file "bin/sambamba" bin)
10718 ,(let ((commit "4f1a7d2fb7ef3dfe962aa357d672f354ebfbe42e"))
10721 (uri (git-reference
10722 (url "https://github.com/biod/BioD.git")
10724 (file-name (string-append "biod-"
10725 (string-take commit 9)
10729 "1k5pdjv1qvi0a3rwd1sfq6zbj37l86i7bf710m4c0y6737lxj426")))))
10731 ,(let ((commit "9be93876982b5f14fcca60832563b3cd767dd84d"))
10734 (uri (git-reference
10735 (url "https://github.com/biod/undeaD.git")
10737 (file-name (string-append "undead-"
10738 (string-take commit 9)
10742 "1xfarj0nqlmi5jd1vmcmm7pabzaf9hxyvk6hp0d6jslb5k9r8r3d")))))))
10745 ("htslib" ,htslib-for-sambamba)))
10746 (home-page "http://lomereiter.github.io/sambamba")
10747 (synopsis "Tools for working with SAM/BAM data")
10748 (description "Sambamba is a high performance modern robust and
10749 fast tool (and library), written in the D programming language, for
10750 working with SAM and BAM files. Current parallelised functionality is
10751 an important subset of samtools functionality, including view, index,
10752 sort, markdup, and depth.")
10753 (license license:gpl2+)))
10755 (define-public ritornello
10757 (name "ritornello")
10761 (uri (git-reference
10762 (url "https://github.com/KlugerLab/Ritornello.git")
10763 (commit (string-append "v" version))))
10764 (file-name (git-file-name name version))
10767 "1xahvq215qld7x1w8vpa5zbrsj6p9crb9shqa2x89sb0aaxa02jk"))))
10768 (build-system gnu-build-system)
10770 `(#:tests? #f ; there are no tests
10772 (modify-phases %standard-phases
10773 (add-after 'unpack 'patch-samtools-references
10774 (lambda* (#:key inputs #:allow-other-keys)
10775 (substitute* '("src/SamStream.h"
10777 (("<sam.h>") "<samtools/sam.h>"))
10779 (delete 'configure)
10781 (lambda* (#:key inputs outputs #:allow-other-keys)
10782 (let* ((out (assoc-ref outputs "out"))
10783 (bin (string-append out "/bin/")))
10785 (install-file "bin/Ritornello" bin)
10788 `(("samtools" ,samtools-0.1)
10792 (home-page "https://github.com/KlugerLab/Ritornello")
10793 (synopsis "Control-free peak caller for ChIP-seq data")
10794 (description "Ritornello is a ChIP-seq peak calling algorithm based on
10795 signal processing that can accurately call binding events without the need to
10796 do a pair total DNA input or IgG control sample. It has been tested for use
10797 with narrow binding events such as transcription factor ChIP-seq.")
10798 (license license:gpl3+)))
10800 (define-public trim-galore
10802 (name "trim-galore")
10807 (uri (git-reference
10808 (url "https://github.com/FelixKrueger/TrimGalore.git")
10810 (file-name (string-append name "-" version "-checkout"))
10813 "0x5892l48c816pf00wmnz5vq0zq6170d3xc8zrxncd4jcz7h1p71"))))
10814 (build-system gnu-build-system)
10816 `(#:tests? #f ; no tests
10818 (modify-phases %standard-phases
10819 (delete 'configure)
10821 (add-after 'unpack 'hardcode-tool-references
10822 (lambda* (#:key inputs #:allow-other-keys)
10823 (substitute* "trim_galore"
10824 (("\\$path_to_cutadapt = 'cutadapt'")
10825 (string-append "$path_to_cutadapt = '"
10826 (assoc-ref inputs "cutadapt")
10829 (string-append "| "
10830 (assoc-ref inputs "gzip")
10833 (string-append "\""
10834 (assoc-ref inputs "gzip")
10838 (lambda* (#:key outputs #:allow-other-keys)
10839 (let ((bin (string-append (assoc-ref outputs "out")
10842 (install-file "trim_galore" bin)
10847 ("cutadapt" ,cutadapt)))
10849 `(("unzip" ,unzip)))
10850 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
10851 (synopsis "Wrapper around Cutadapt and FastQC")
10852 (description "Trim Galore! is a wrapper script to automate quality and
10853 adapter trimming as well as quality control, with some added functionality to
10854 remove biased methylation positions for RRBS sequence files.")
10855 (license license:gpl3+)))
10857 (define-public gess
10863 (uri (string-append "http://compbio.uthscsa.edu/"
10865 "gess-" version ".src.tar.gz"))
10868 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
10869 (build-system gnu-build-system)
10871 `(#:tests? #f ; no tests
10873 (modify-phases %standard-phases
10874 (delete 'configure)
10877 (lambda* (#:key inputs outputs #:allow-other-keys)
10878 (let* ((python (assoc-ref inputs "python"))
10879 (out (assoc-ref outputs "out"))
10880 (bin (string-append out "/bin/"))
10881 (target (string-append
10883 ,(version-major+minor
10884 (package-version python))
10885 "/site-packages/gess/")))
10887 (copy-recursively "." target)
10888 ;; Make GESS.py executable
10889 (chmod (string-append target "GESS.py") #o555)
10890 ;; Add Python shebang to the top and make Matplotlib
10892 (substitute* (string-append target "GESS.py")
10893 (("\"\"\"Description:" line)
10894 (string-append "#!" (which "python") "
10896 matplotlib.use('Agg')
10898 ;; Make sure GESS has all modules in its path
10899 (wrap-program (string-append target "GESS.py")
10900 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
10902 (symlink (string-append target "GESS.py")
10903 (string-append bin "GESS.py"))
10906 `(("python" ,python-2)
10907 ("python2-pysam" ,python2-pysam)
10908 ("python2-scipy" ,python2-scipy)
10909 ("python2-numpy" ,python2-numpy)
10910 ("python2-networkx" ,python2-networkx)
10911 ("python2-biopython" ,python2-biopython)))
10912 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
10913 (synopsis "Detect exon-skipping events from raw RNA-seq data")
10915 "GESS is an implementation of a novel computational method to detect de
10916 novo exon-skipping events directly from raw RNA-seq data without the prior
10917 knowledge of gene annotation information. GESS stands for the graph-based
10918 exon-skipping scanner detection scheme.")
10919 (license license:bsd-3)))
10921 (define-public phylip
10928 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
10929 "download/phylip-" version ".tar.gz"))
10932 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
10933 (build-system gnu-build-system)
10935 `(#:tests? #f ; no check target
10936 #:make-flags (list "-f" "Makefile.unx" "install")
10937 #:parallel-build? #f ; not supported
10939 (modify-phases %standard-phases
10940 (add-after 'unpack 'enter-dir
10941 (lambda _ (chdir "src") #t))
10942 (delete 'configure)
10944 (lambda* (#:key inputs outputs #:allow-other-keys)
10945 (let ((target (string-append (assoc-ref outputs "out")
10948 (for-each (lambda (file)
10949 (install-file file target))
10950 (find-files "../exe" ".*")))
10952 (home-page "http://evolution.genetics.washington.edu/phylip/")
10953 (synopsis "Tools for inferring phylogenies")
10954 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
10955 programs for inferring phylogenies (evolutionary trees).")
10956 (license license:bsd-2)))
10965 (uri (string-append "https://integrativemodeling.org/"
10966 version "/download/imp-" version ".tar.gz"))
10969 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
10970 (build-system cmake-build-system)
10972 `(;; FIXME: Some tests fail because they produce warnings, others fail
10973 ;; because the PYTHONPATH does not include the modeller's directory.
10981 ("python" ,python-2)))
10983 `(("python2-numpy" ,python2-numpy)
10984 ("python2-scipy" ,python2-scipy)
10985 ("python2-pandas" ,python2-pandas)
10986 ("python2-scikit-learn" ,python2-scikit-learn)
10987 ("python2-networkx" ,python2-networkx)))
10988 (home-page "https://integrativemodeling.org")
10989 (synopsis "Integrative modeling platform")
10990 (description "IMP's broad goal is to contribute to a comprehensive
10991 structural characterization of biomolecules ranging in size and complexity
10992 from small peptides to large macromolecular assemblies, by integrating data
10993 from diverse biochemical and biophysical experiments. IMP provides a C++ and
10994 Python toolbox for solving complex modeling problems, and a number of
10995 applications for tackling some common problems in a user-friendly way.")
10996 ;; IMP is largely available under the GNU Lesser GPL; see the file
10997 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
10998 ;; available under the GNU GPL (see the file COPYING.GPL).
10999 (license (list license:lgpl2.1+
11002 (define-public tadbit
11008 (uri (git-reference
11009 (url "https://github.com/3DGenomes/TADbit.git")
11010 (commit (string-append "v" version))))
11011 (file-name (git-file-name name version))
11014 "07g3aj648prmsvxp9caz5yl41k0y0647vxh0f5p3w8376mfiljd0"))))
11015 (build-system python-build-system)
11017 `(;; Tests are included and must be run after installation, but
11018 ;; they are incomplete and thus cannot be run.
11022 (modify-phases %standard-phases
11023 (add-after 'unpack 'fix-problems-with-setup.py
11024 (lambda* (#:key outputs #:allow-other-keys)
11025 ;; setup.py opens these files for writing
11026 (chmod "_pytadbit/_version.py" #o664)
11027 (chmod "README.rst" #o664)
11029 ;; Don't attempt to install the bash completions to
11030 ;; the home directory.
11031 (rename-file "extras/.bash_completion"
11033 (substitute* "setup.py"
11034 (("\\(path.expanduser\\('~'\\)")
11035 (string-append "(\""
11036 (assoc-ref outputs "out")
11037 "/etc/bash_completion.d\""))
11038 (("extras/\\.bash_completion")
11042 ;; TODO: add Chimera for visualization
11045 ("python2-scipy" ,python2-scipy)
11046 ("python2-numpy" ,python2-numpy)
11047 ("python2-matplotlib" ,python2-matplotlib)
11048 ("python2-pysam" ,python2-pysam)))
11049 (home-page "https://3dgenomes.github.io/TADbit/")
11050 (synopsis "Analyze, model, and explore 3C-based data")
11052 "TADbit is a complete Python library to deal with all steps to analyze,
11053 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11054 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11055 correct interaction matrices, identify and compare the so-called
11056 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11057 interaction matrices, and finally, extract structural properties from the
11058 models. TADbit is complemented by TADkit for visualizing 3D models.")
11059 (license license:gpl3+)))
11061 (define-public kentutils
11064 ;; 302.1.0 is out, but the only difference is the inclusion of
11065 ;; pre-built binaries.
11066 (version "302.0.0")
11070 (uri (git-reference
11071 (url "https://github.com/ENCODE-DCC/kentUtils.git")
11072 (commit (string-append "v" version))))
11073 (file-name (git-file-name name version))
11076 "0n1wbyjpzii2b9qhyp9r1q76j623cggpg3y8fmw78ld3z4y7ivha"))
11077 (modules '((guix build utils)
11082 ;; Only the contents of the specified directories are free
11083 ;; for all uses, so we remove the rest. "hg/autoSql" and
11084 ;; "hg/autoXml" are nominally free, but they depend on a
11085 ;; library that is built from the sources in "hg/lib",
11086 ;; which is nonfree.
11087 (let ((free (list "." ".."
11088 "utils" "lib" "inc" "tagStorm"
11089 "parasol" "htslib"))
11090 (directory? (lambda (file)
11091 (eq? 'directory (stat:type (stat file))))))
11092 (for-each (lambda (file)
11093 (and (directory? file)
11094 (delete-file-recursively file)))
11095 (map (cut string-append "src/" <>)
11098 (not (member file free)))))))
11099 ;; Only make the utils target, not the userApps target,
11100 ;; because that requires libraries we won't build.
11101 (substitute* "Makefile"
11102 ((" userApps") " utils"))
11103 ;; Only build libraries that are free.
11104 (substitute* "src/makefile"
11105 (("DIRS =.*") "DIRS =\n")
11106 (("cd jkOwnLib.*") "")
11109 (substitute* "src/utils/makefile"
11110 ;; These tools depend on "jkhgap.a", which is part of the
11111 ;; nonfree "src/hg/lib" directory.
11112 (("raSqlQuery") "")
11113 (("pslLiftSubrangeBlat") "")
11115 ;; Do not build UCSC tools, which may require nonfree
11117 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11119 (build-system gnu-build-system)
11121 `( ;; There is no global test target and the test target for
11122 ;; individual tools depends on input files that are not
11126 (modify-phases %standard-phases
11127 (add-after 'unpack 'fix-permissions
11128 (lambda _ (make-file-writable "src/inc/localEnvironment.mk") #t))
11129 (add-after 'unpack 'fix-paths
11131 (substitute* "Makefile"
11132 (("/bin/echo") (which "echo")))
11134 (add-after 'unpack 'prepare-samtabix
11135 (lambda* (#:key inputs #:allow-other-keys)
11136 (copy-recursively (assoc-ref inputs "samtabix")
11139 (delete 'configure)
11141 (lambda* (#:key outputs #:allow-other-keys)
11142 (let ((bin (string-append (assoc-ref outputs "out")
11144 (copy-recursively "bin" bin))
11150 (uri (git-reference
11151 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11152 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11155 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11161 ("mariadb" ,mariadb)
11162 ("openssl" ,openssl)))
11163 (home-page "http://genome.cse.ucsc.edu/index.html")
11164 (synopsis "Assorted bioinformatics utilities")
11165 (description "This package provides the kentUtils, a selection of
11166 bioinformatics utilities used in combination with the UCSC genome
11168 ;; Only a subset of the sources are released under a non-copyleft
11169 ;; free software license. All other sources are removed in a
11170 ;; snippet. See this bug report for an explanation of how the
11171 ;; license statements apply:
11172 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11173 (license (license:non-copyleft
11174 "http://genome.ucsc.edu/license/"
11175 "The contents of this package are free for all uses."))))
11177 (define-public f-seq
11178 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11182 (version (string-append "1.1-" revision "." (string-take commit 7)))
11185 (uri (git-reference
11186 (url "https://github.com/aboyle/F-seq.git")
11188 (file-name (string-append name "-" version))
11191 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11192 (modules '((guix build utils)))
11193 ;; Remove bundled Java library archives.
11196 (for-each delete-file (find-files "lib" ".*"))
11198 (build-system ant-build-system)
11200 `(#:tests? #f ; no tests included
11202 (modify-phases %standard-phases
11204 (lambda* (#:key inputs outputs #:allow-other-keys)
11205 (let* ((target (assoc-ref outputs "out"))
11206 (bin (string-append target "/bin"))
11207 (doc (string-append target "/share/doc/f-seq"))
11208 (lib (string-append target "/lib")))
11211 (substitute* "bin/linux/fseq"
11212 (("java") (which "java"))
11213 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11214 (string-append (assoc-ref inputs "java-commons-cli")
11215 "/share/java/commons-cli.jar"))
11217 (string-append "REALDIR=" bin "\n")))
11218 (install-file "README.txt" doc)
11219 (install-file "bin/linux/fseq" bin)
11220 (install-file "build~/fseq.jar" lib)
11221 (copy-recursively "lib" lib)
11225 ("java-commons-cli" ,java-commons-cli)))
11226 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11227 (synopsis "Feature density estimator for high-throughput sequence tags")
11229 "F-Seq is a software package that generates a continuous tag sequence
11230 density estimation allowing identification of biologically meaningful sites
11231 such as transcription factor binding sites (ChIP-seq) or regions of open
11232 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11234 (license license:gpl3+))))
11236 (define-public bismark
11243 (uri (git-reference
11244 (url "https://github.com/FelixKrueger/Bismark.git")
11246 (file-name (string-append name "-" version "-checkout"))
11249 "0xchm3rgilj6vfjnyzfzzymfd7djr64sbrmrvs3njbwi66jqbzw9"))))
11250 (build-system perl-build-system)
11252 `(#:tests? #f ; there are no tests
11253 #:modules ((guix build utils)
11256 (guix build perl-build-system))
11258 (modify-phases %standard-phases
11259 ;; The bundled plotly.js is minified.
11260 (add-after 'unpack 'replace-plotly.js
11261 (lambda* (#:key inputs #:allow-other-keys)
11262 (let* ((file (assoc-ref inputs "plotly.js"))
11263 (installed "plotly/plotly.js"))
11264 (let ((minified (open-pipe* OPEN_READ "uglify-js" file)))
11265 (call-with-output-file installed
11266 (cut dump-port minified <>))))
11268 (delete 'configure)
11271 (lambda* (#:key inputs outputs #:allow-other-keys)
11272 (let* ((out (assoc-ref outputs "out"))
11273 (bin (string-append out "/bin"))
11274 (share (string-append out "/share/bismark"))
11275 (docdir (string-append out "/share/doc/bismark"))
11276 (docs '("Docs/Bismark_User_Guide.html"))
11277 (scripts '("bismark"
11278 "bismark_genome_preparation"
11279 "bismark_methylation_extractor"
11282 "coverage2cytosine"
11283 "deduplicate_bismark"
11284 "filter_non_conversion"
11287 "NOMe_filtering")))
11288 (substitute* "bismark2report"
11289 (("\\$RealBin/plotly")
11290 (string-append share "/plotly")))
11294 (for-each (lambda (file) (install-file file bin))
11296 (for-each (lambda (file) (install-file file docdir))
11298 (copy-recursively "Docs/Images" (string-append docdir "/Images"))
11299 (copy-recursively "plotly"
11300 (string-append share "/plotly"))
11302 ;; Fix references to gunzip
11303 (substitute* (map (lambda (file)
11304 (string-append bin "/" file))
11307 (string-append "\"" (assoc-ref inputs "gzip")
11308 "/bin/gunzip -c")))
11312 ("perl-carp" ,perl-carp)
11313 ("perl-getopt-long" ,perl-getopt-long)))
11318 (uri (string-append "https://raw.githubusercontent.com/plotly/plotly.js/"
11319 "v1.39.4/dist/plotly.js"))
11321 (base32 "138mwsr4nf5qif4mrxx286mpnagxd1xwl6k8aidrjgknaqg88zyr"))))
11322 ("uglify-js" ,uglify-js)))
11323 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11324 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11325 (description "Bismark is a program to map bisulfite treated sequencing
11326 reads to a genome of interest and perform methylation calls in a single step.
11327 The output can be easily imported into a genome viewer, such as SeqMonk, and
11328 enables a researcher to analyse the methylation levels of their samples
11329 straight away. Its main features are:
11332 @item Bisulfite mapping and methylation calling in one single step
11333 @item Supports single-end and paired-end read alignments
11334 @item Supports ungapped and gapped alignments
11335 @item Alignment seed length, number of mismatches etc are adjustable
11336 @item Output discriminates between cytosine methylation in CpG, CHG
11339 (license license:gpl3+)))
11341 (define-public paml
11347 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11348 "paml" version ".tgz"))
11351 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11352 (modules '((guix build utils)))
11353 ;; Remove Windows binaries
11356 (for-each delete-file (find-files "." "\\.exe$"))
11358 (build-system gnu-build-system)
11360 `(#:tests? #f ; there are no tests
11361 #:make-flags '("CC=gcc")
11363 (modify-phases %standard-phases
11364 (replace 'configure
11366 (substitute* "src/BFdriver.c"
11367 (("/bin/bash") (which "bash")))
11371 (lambda* (#:key outputs #:allow-other-keys)
11372 (let ((tools '("baseml" "basemlg" "codeml"
11373 "pamp" "evolver" "yn00" "chi2"))
11374 (bin (string-append (assoc-ref outputs "out") "/bin"))
11375 (docdir (string-append (assoc-ref outputs "out")
11376 "/share/doc/paml")))
11378 (for-each (lambda (file) (install-file file bin)) tools)
11379 (copy-recursively "../doc" docdir)
11381 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11382 (synopsis "Phylogentic analysis by maximum likelihood")
11383 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11384 contains a few programs for model fitting and phylogenetic tree reconstruction
11385 using nucleotide or amino-acid sequence data.")
11387 (license license:gpl3)))
11389 (define-public kallisto
11395 (uri (git-reference
11396 (url "https://github.com/pachterlab/kallisto.git")
11397 (commit (string-append "v" version))))
11398 (file-name (git-file-name name version))
11401 "0nj382jiywqnpgvyhichajpkkh5r0bapn43f4dx40zdaq5v4m40m"))))
11402 (build-system cmake-build-system)
11404 `(#:tests? #f ; no "check" target
11406 (modify-phases %standard-phases
11407 (add-after 'unpack 'do-not-use-bundled-htslib
11409 (substitute* "CMakeLists.txt"
11410 (("^ExternalProject_Add" m)
11411 (string-append "if (NEVER)\n" m))
11413 (string-append ")\nendif(NEVER)"))
11414 (("include_directories\\(\\$\\{htslib_PREFIX.*" m)
11415 (string-append "# " m)))
11416 (substitute* "src/CMakeLists.txt"
11417 (("target_link_libraries\\(kallisto kallisto_core pthread \
11418 \\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/../ext/htslib/libhts.a\\)")
11419 "target_link_libraries(kallisto kallisto_core pthread hts)")
11420 (("include_directories\\(\\.\\./ext/htslib\\)") ""))
11426 (home-page "http://pachterlab.github.io/kallisto/")
11427 (synopsis "Near-optimal RNA-Seq quantification")
11429 "Kallisto is a program for quantifying abundances of transcripts from
11430 RNA-Seq data, or more generally of target sequences using high-throughput
11431 sequencing reads. It is based on the novel idea of pseudoalignment for
11432 rapidly determining the compatibility of reads with targets, without the need
11433 for alignment. Pseudoalignment of reads preserves the key information needed
11434 for quantification, and kallisto is therefore not only fast, but also as
11435 accurate as existing quantification tools.")
11436 (license license:bsd-2)))
11438 (define-public libgff
11444 (uri (git-reference
11445 (url "https://github.com/Kingsford-Group/libgff.git")
11446 (commit (string-append "v" version))))
11447 (file-name (git-file-name name version))
11450 "0n6vfjnq7a2mianipscbshrvbncss8z4zkgkbjw754p9043nfkps"))))
11451 (build-system cmake-build-system)
11452 (arguments `(#:tests? #f)) ; no tests included
11453 (home-page "https://github.com/Kingsford-Group/libgff")
11454 (synopsis "Parser library for reading/writing GFF files")
11455 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11456 code that is used in the Cufflinks codebase. The goal of this library is to
11457 provide this functionality without the necessity of drawing in a heavy-weight
11458 dependency like SeqAn.")
11459 (license (license:x11-style "https://www.boost.org/LICENSE_1_0.txt"))))
11461 (define-public libdivsufsort
11463 (name "libdivsufsort")
11467 (uri (git-reference
11468 (url "https://github.com/y-256/libdivsufsort.git")
11470 (file-name (git-file-name name version))
11473 "0fgdz9fzihlvjjrxy01md1bv9vh12rkgkwbm90b1hj5xpbaqp7z2"))))
11474 (build-system cmake-build-system)
11476 '(#:tests? #f ; there are no tests
11478 ;; Needed for rapmap and sailfish.
11479 '("-DBUILD_DIVSUFSORT64=ON")))
11480 (home-page "https://github.com/y-256/libdivsufsort")
11481 (synopsis "Lightweight suffix-sorting library")
11482 (description "libdivsufsort is a software library that implements a
11483 lightweight suffix array construction algorithm. This library provides a
11484 simple and an efficient C API to construct a suffix array and a
11485 Burrows-Wheeler transformed string from a given string over a constant-size
11486 alphabet. The algorithm runs in O(n log n) worst-case time using only 5n+O(1)
11487 bytes of memory space, where n is the length of the string.")
11488 (license license:expat)))
11490 (define-public sailfish
11496 (uri (git-reference
11497 (url "https://github.com/kingsfordgroup/sailfish.git")
11498 (commit (string-append "v" version))))
11499 (file-name (git-file-name name version))
11502 "1amcc5hqvsl42hg4x19bi9vy47cl874s0lw1fmi0hwsdk9i8c03v"))
11503 (modules '((guix build utils)))
11506 ;; Delete bundled headers for eigen3.
11507 (delete-file-recursively "include/eigen3/")
11509 (build-system cmake-build-system)
11511 `(#:configure-flags
11512 (list (string-append "-DBOOST_INCLUDEDIR="
11513 (assoc-ref %build-inputs "boost")
11515 (string-append "-DBOOST_LIBRARYDIR="
11516 (assoc-ref %build-inputs "boost")
11518 (string-append "-DBoost_LIBRARIES="
11519 "-lboost_iostreams "
11520 "-lboost_filesystem "
11525 "-lboost_program_options")
11526 "-DBoost_FOUND=TRUE"
11527 ;; Don't download RapMap---we already have it!
11528 "-DFETCHED_RAPMAP=1")
11529 ;; Tests must be run after installation and the location of the test
11530 ;; data file must be overridden. But the tests fail. It looks like
11531 ;; they are not really meant to be run.
11534 (modify-phases %standard-phases
11535 ;; Boost cannot be found, even though it's right there.
11536 (add-after 'unpack 'do-not-look-for-boost
11537 (lambda* (#:key inputs #:allow-other-keys)
11538 (substitute* "CMakeLists.txt"
11539 (("find_package\\(Boost 1\\.53\\.0") "#"))
11541 (add-after 'unpack 'do-not-assign-to-macro
11543 (substitute* "include/spdlog/details/format.cc"
11544 (("const unsigned CHAR_WIDTH = 1;") ""))
11546 (add-after 'unpack 'prepare-rapmap
11547 (lambda* (#:key inputs #:allow-other-keys)
11548 (let ((src "external/install/src/rapmap/")
11549 (include "external/install/include/rapmap/")
11550 (rapmap (assoc-ref inputs "rapmap")))
11551 (mkdir-p "/tmp/rapmap")
11553 (assoc-ref inputs "rapmap")
11555 "--strip-components=1")
11558 (for-each (lambda (file)
11559 (install-file file src))
11560 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
11561 (copy-recursively "/tmp/rapmap/include" include))
11563 (add-after 'unpack 'use-system-libraries
11564 (lambda* (#:key inputs #:allow-other-keys)
11565 (substitute* '("src/SailfishIndexer.cpp"
11566 "src/SailfishUtils.cpp"
11567 "src/SailfishQuantify.cpp"
11568 "src/FASTAParser.cpp"
11570 "include/SailfishUtils.hpp"
11571 "include/SailfishIndex.hpp"
11572 "include/CollapsedEMOptimizer.hpp"
11573 "src/CollapsedEMOptimizer.cpp")
11574 (("#include \"jellyfish/config.h\"") ""))
11575 (substitute* "src/CMakeLists.txt"
11576 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11577 (string-append (assoc-ref inputs "jellyfish")
11578 "/include/jellyfish-" ,(package-version jellyfish)))
11579 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11580 (string-append (assoc-ref inputs "jellyfish")
11581 "/lib/libjellyfish-2.0.a"))
11582 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11583 (string-append (assoc-ref inputs "libdivsufsort")
11584 "/lib/libdivsufsort.so"))
11585 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11586 (string-append (assoc-ref inputs "libdivsufsort")
11587 "/lib/libdivsufsort64.so")))
11588 (substitute* "CMakeLists.txt"
11589 ;; Don't prefer static libs
11590 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11591 (("find_package\\(Jellyfish.*") "")
11592 (("ExternalProject_Add\\(libjellyfish") "message(")
11593 (("ExternalProject_Add\\(libgff") "message(")
11594 (("ExternalProject_Add\\(libsparsehash") "message(")
11595 (("ExternalProject_Add\\(libdivsufsort") "message("))
11597 ;; Ensure that Eigen headers can be found
11598 (setenv "CPLUS_INCLUDE_PATH"
11599 (string-append (getenv "CPLUS_INCLUDE_PATH")
11601 (assoc-ref inputs "eigen")
11602 "/include/eigen3"))
11607 ("jemalloc" ,jemalloc)
11608 ("jellyfish" ,jellyfish)
11609 ("sparsehash" ,sparsehash)
11612 (uri (git-reference
11613 (url "https://github.com/COMBINE-lab/RapMap.git")
11614 (commit (string-append "sf-v" version))))
11615 (file-name (string-append "rapmap-sf-v" version "-checkout"))
11618 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
11619 (modules '((guix build utils)))
11620 ;; These files are expected to be excluded.
11622 '(begin (delete-file-recursively "include/spdlog")
11623 (for-each delete-file '("include/xxhash.h"
11626 ("libdivsufsort" ,libdivsufsort)
11631 `(("pkg-config" ,pkg-config)))
11632 (home-page "http://www.cs.cmu.edu/~ckingsf/software/sailfish")
11633 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
11634 (description "Sailfish is a tool for genomic transcript quantification
11635 from RNA-seq data. It requires a set of target transcripts (either from a
11636 reference or de-novo assembly) to quantify. All you need to run sailfish is a
11637 fasta file containing your reference transcripts and a (set of) fasta/fastq
11638 file(s) containing your reads.")
11639 (license license:gpl3+)))
11641 (define libstadenio-for-salmon
11643 (name "libstadenio")
11647 (uri (git-reference
11648 (url "https://github.com/COMBINE-lab/staden-io_lib.git")
11649 (commit (string-append "v" version))))
11650 (file-name (string-append name "-" version "-checkout"))
11653 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
11654 (build-system gnu-build-system)
11655 (arguments '(#:parallel-tests? #f)) ; not supported
11659 `(("perl" ,perl))) ; for tests
11660 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
11661 (synopsis "General purpose trace and experiment file library")
11662 (description "This package provides a library of file reading and writing
11663 code to provide a general purpose Trace file (and Experiment File) reading
11666 The following file formats are supported:
11669 @item SCF trace files
11670 @item ABI trace files
11671 @item ALF trace files
11672 @item ZTR trace files
11673 @item SFF trace archives
11674 @item SRF trace archives
11675 @item Experiment files
11676 @item Plain text files
11677 @item SAM/BAM sequence files
11678 @item CRAM sequence files
11680 (license license:bsd-3)))
11682 (define spdlog-for-salmon
11688 (uri (git-reference
11689 (url "https://github.com/COMBINE-lab/spdlog.git")
11690 (commit (string-append "v" version))))
11691 (file-name (string-append name "-" version "-checkout"))
11694 "13730429gwlabi432ilpnja3sfvy0nn2719vnhhmii34xcdyc57q"))))
11695 (build-system cmake-build-system)
11696 (home-page "https://github.com/COMBINE-lab/spdlog")
11697 (synopsis "Very fast C++ logging library")
11698 (description "Spdlog is a very fast header-only C++ logging library with
11699 performance as its primary goal.")
11700 (license license:expat)))
11702 ;; This is a modified variant of bwa for use with Salmon. It installs a
11703 ;; library to avoid having to build this as part of Salmon.
11704 (define bwa-for-salmon
11705 (package (inherit bwa)
11707 (version "0.7.12.5")
11710 (uri (git-reference
11711 (url "https://github.com/COMBINE-lab/bwa.git")
11712 (commit (string-append "v" version))))
11713 (file-name (string-append "bwa-for-salmon-" version "-checkout"))
11716 "1z2qa64y0c5hky10510x137mnzlhz6k8qf27csw4w9j6qihq95gb"))))
11717 (build-system gnu-build-system)
11719 '(#:tests? #f ;no "check" target
11721 (modify-phases %standard-phases
11723 (lambda* (#:key outputs #:allow-other-keys)
11724 (let* ((out (assoc-ref outputs "out"))
11725 (bin (string-append out "/bin"))
11726 (lib (string-append out "/lib"))
11727 (doc (string-append out "/share/doc/bwa"))
11728 (man (string-append out "/share/man/man1"))
11729 (inc (string-append out "/include/bwa")))
11730 (install-file "bwa" bin)
11731 (install-file "README.md" doc)
11732 (install-file "bwa.1" man)
11733 (install-file "libbwa.a" lib)
11736 (for-each (lambda (file)
11737 (install-file file inc))
11738 (find-files "." "\\.h$")))
11740 ;; no "configure" script
11741 (delete 'configure))))))
11743 (define-public salmon
11749 (uri (git-reference
11750 (url "https://github.com/COMBINE-lab/salmon.git")
11751 (commit (string-append "v" version))))
11752 (file-name (string-append name "-" version "-checkout"))
11755 "1zi1ff4i7y2ykk0vdzysgwzzzv166vg2x77pj1mf4baclavxj87a"))
11756 (modules '((guix build utils)))
11759 ;; Delete bundled headers for eigen3.
11760 (delete-file-recursively "include/eigen3/")
11762 (build-system cmake-build-system)
11764 `(#:configure-flags
11765 (list (string-append "-DBOOST_INCLUDEDIR="
11766 (assoc-ref %build-inputs "boost")
11768 (string-append "-DBOOST_LIBRARYDIR="
11769 (assoc-ref %build-inputs "boost")
11771 (string-append "-DBoost_LIBRARIES="
11772 "-lboost_iostreams "
11773 "-lboost_filesystem "
11778 "-lboost_program_options")
11779 "-DBoost_FOUND=TRUE"
11780 "-DTBB_LIBRARIES=tbb tbbmalloc"
11781 ;; Don't download RapMap---we already have it!
11782 "-DFETCHED_RAPMAP=1")
11784 (modify-phases %standard-phases
11785 ;; Boost cannot be found, even though it's right there.
11786 (add-after 'unpack 'do-not-look-for-boost
11787 (lambda* (#:key inputs #:allow-other-keys)
11788 (substitute* "CMakeLists.txt"
11789 (("find_package\\(Boost 1\\.53\\.0") "#"))
11791 (add-after 'unpack 'do-not-phone-home
11793 (substitute* "src/Salmon.cpp"
11794 (("getVersionMessage\\(\\)") "\"\""))
11796 (add-after 'unpack 'prepare-rapmap
11797 (lambda* (#:key inputs #:allow-other-keys)
11798 (let ((src "external/install/src/rapmap/")
11799 (include "external/install/include/rapmap/")
11800 (rapmap (assoc-ref inputs "rapmap")))
11803 (for-each (lambda (file)
11804 (install-file file src))
11805 (find-files (string-append rapmap "/src") "\\.(c|cpp)"))
11806 (copy-recursively (string-append rapmap "/include") include)
11807 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
11808 "external/install/include/rapmap/FastxParser.hpp"
11809 "external/install/include/rapmap/concurrentqueue.h"
11810 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
11811 "external/install/src/rapmap/FastxParser.cpp"
11812 "external/install/src/rapmap/xxhash.c")))
11814 (add-after 'unpack 'use-system-libraries
11815 (lambda* (#:key inputs #:allow-other-keys)
11816 (substitute* "src/CMakeLists.txt"
11817 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11818 (string-append (assoc-ref inputs "jellyfish")
11819 "/include/jellyfish-" ,(package-version jellyfish)))
11820 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11821 (string-append (assoc-ref inputs "jellyfish")
11822 "/lib/libjellyfish-2.0.a"))
11823 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11824 (string-append (assoc-ref inputs "libdivsufsort")
11825 "/lib/libdivsufsort.so"))
11826 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
11827 (string-append (assoc-ref inputs "libstadenio-for-salmon")
11828 "/lib/libstaden-read.a"))
11829 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libbwa.a")
11830 (string-append (assoc-ref inputs "bwa") "/lib/libbwa.a"))
11831 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11832 (string-append (assoc-ref inputs "libdivsufsort")
11833 "/lib/libdivsufsort64.so")))
11834 (substitute* "CMakeLists.txt"
11835 ;; Don't prefer static libs
11836 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11837 (("set\\(TBB_LIBRARIES") "message(")
11838 (("find_package\\(Jellyfish.*") "")
11839 (("ExternalProject_Add\\(libcereal") "message(")
11840 (("ExternalProject_Add\\(libbwa") "message(")
11841 (("ExternalProject_Add\\(libjellyfish") "message(")
11842 (("ExternalProject_Add\\(libgff") "message(")
11843 (("ExternalProject_Add\\(libtbb") "message(")
11844 (("ExternalProject_Add\\(libspdlog") "message(")
11845 (("ExternalProject_Add\\(libdivsufsort") "message(")
11846 (("ExternalProject_Add\\(libstadenio") "message(")
11847 (("ExternalProject_Add_Step\\(") "message("))
11849 ;; Ensure that all headers can be found
11850 (setenv "CPLUS_INCLUDE_PATH"
11851 (string-append (getenv "CPLUS_INCLUDE_PATH")
11853 (assoc-ref inputs "bwa")
11856 (assoc-ref inputs "eigen")
11857 "/include/eigen3"))
11859 (string-append (assoc-ref inputs "bwa")
11862 (assoc-ref inputs "eigen")
11863 "/include/eigen3"))
11865 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
11866 ;; run. It only exists after the install phase.
11867 (add-after 'unpack 'fix-tests
11869 (substitute* "src/CMakeLists.txt"
11870 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
11871 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
11875 ("bwa" ,bwa-for-salmon)
11881 (uri (git-reference
11882 (url "https://github.com/COMBINE-lab/RapMap.git")
11883 (commit (string-append "salmon-v" version))))
11884 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
11887 "1yc12yqsz6f0r8sg1qnk57xg34aqwc9jbqq6gd5ys28xw3plj98p"))))
11888 ("jemalloc" ,jemalloc)
11889 ("jellyfish" ,jellyfish)
11892 ("libdivsufsort" ,libdivsufsort)
11893 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
11894 ("spdlog-for-salmon" ,spdlog-for-salmon)
11897 (home-page "https://github.com/COMBINE-lab/salmon")
11898 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
11899 (description "Salmon is a program to produce highly-accurate,
11900 transcript-level quantification estimates from RNA-seq data. Salmon achieves
11901 its accuracy and speed via a number of different innovations, including the
11902 use of lightweight alignments (accurate but fast-to-compute proxies for
11903 traditional read alignments) and massively-parallel stochastic collapsed
11904 variational inference.")
11905 (license license:gpl3+)))
11907 (define-public python-loompy
11909 (name "python-loompy")
11914 (uri (pypi-uri "loompy" version))
11917 "1drgv8j1hxqzzpnfg272x9djb6j8qr798w1pc2x8ikmfgyd9gh51"))))
11918 (build-system python-build-system)
11919 ;; There are no tests
11920 (arguments '(#:tests? #f))
11922 `(("python-h5py" ,python-h5py)
11923 ("python-numpy" ,python-numpy)
11924 ("python-scipy" ,python-scipy)))
11925 (home-page "https://github.com/linnarsson-lab/loompy")
11926 (synopsis "Work with .loom files for single-cell RNA-seq data")
11927 (description "The loom file format is an efficient format for very large
11928 omics datasets, consisting of a main matrix, optional additional layers, a
11929 variable number of row and column annotations. Loom also supports sparse
11930 graphs. This library makes it easy to work with @file{.loom} files for
11931 single-cell RNA-seq data.")
11932 (license license:bsd-3)))
11934 ;; We cannot use the latest commit because it requires Java 9.
11935 (define-public java-forester
11936 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
11939 (name "java-forester")
11940 (version (string-append "0-" revision "." (string-take commit 7)))
11943 (uri (git-reference
11944 (url "https://github.com/cmzmasek/forester.git")
11946 (file-name (string-append name "-" version "-checkout"))
11949 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
11950 (modules '((guix build utils)))
11953 ;; Delete bundled jars and pre-built classes
11954 (delete-file-recursively "forester/java/resources")
11955 (delete-file-recursively "forester/java/classes")
11956 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
11957 ;; Delete bundled applications
11958 (delete-file-recursively "forester_applications")
11960 (build-system ant-build-system)
11962 `(#:tests? #f ; there are none
11964 #:modules ((guix build ant-build-system)
11966 (guix build java-utils)
11970 (modify-phases %standard-phases
11971 (add-after 'unpack 'chdir
11972 (lambda _ (chdir "forester/java") #t))
11973 (add-after 'chdir 'fix-dependencies
11975 (chmod "build.xml" #o664)
11976 (call-with-output-file "build.xml.new"
11980 (with-input-from-file "build.xml"
11981 (lambda _ (xml->sxml #:trim-whitespace? #t)))
11982 `(;; Remove all unjar tags to avoid repacking classes.
11983 (unjar . ,(lambda _ '()))
11984 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
11985 (*text* . ,(lambda (_ txt) txt))))
11987 (rename-file "build.xml.new" "build.xml")
11989 ;; FIXME: itext is difficult to package as it depends on a few
11990 ;; unpackaged libraries.
11991 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
11993 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
11994 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
11995 (("pdf_written_to = PdfExporter.*")
11996 "throw new IOException(\"PDF export is not available.\");"))
11998 ;; There is no install target
11999 (replace 'install (install-jars ".")))))
12001 `(("java-commons-codec" ,java-commons-codec)
12002 ("java-openchart2" ,java-openchart2)))
12003 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12004 (synopsis "Phylogenomics libraries for Java")
12005 (description "Forester is a collection of Java libraries for
12006 phylogenomics and evolutionary biology research. It includes support for
12007 reading, writing, and exporting phylogenetic trees.")
12008 (license license:lgpl2.1+))))
12010 (define-public java-forester-1.005
12012 (name "java-forester")
12016 (uri (string-append "http://search.maven.org/remotecontent?"
12017 "filepath=org/biojava/thirdparty/forester/"
12018 version "/forester-" version "-sources.jar"))
12019 (file-name (string-append name "-" version ".jar"))
12022 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12023 (build-system ant-build-system)
12025 `(#:tests? #f ; there are none
12027 #:modules ((guix build ant-build-system)
12029 (guix build java-utils)
12033 (modify-phases %standard-phases
12034 (add-after 'unpack 'fix-dependencies
12035 (lambda* (#:key inputs #:allow-other-keys)
12036 (call-with-output-file "build.xml"
12040 (with-input-from-file "src/build.xml"
12041 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12042 `(;; Remove all unjar tags to avoid repacking classes.
12043 (unjar . ,(lambda _ '()))
12044 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12045 (*text* . ,(lambda (_ txt) txt))))
12047 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12048 "synth_look_and_feel_1.xml")
12049 (copy-file (assoc-ref inputs "phyloxml.xsd")
12051 (substitute* "build.xml"
12052 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12053 "synth_look_and_feel_1.xml")
12054 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12057 ;; FIXME: itext is difficult to package as it depends on a few
12058 ;; unpackaged libraries.
12059 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12061 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12062 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12063 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12064 (("pdf_written_to = PdfExporter.*")
12065 "throw new IOException(\"PDF export is not available.\"); /*")
12066 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12067 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12069 (add-after 'unpack 'delete-pre-built-classes
12070 (lambda _ (delete-file-recursively "src/classes") #t))
12071 ;; There is no install target
12072 (replace 'install (install-jars ".")))))
12074 `(("java-commons-codec" ,java-commons-codec)
12075 ("java-openchart2" ,java-openchart2)))
12076 ;; The source archive does not contain the resources.
12081 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12082 "b61cc2dcede0bede317db362472333115756b8c6/"
12083 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12084 (file-name (string-append name "-phyloxml-" version ".xsd"))
12087 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12088 ("synth_look_and_feel_1.xml"
12091 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12092 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12093 "forester/java/classes/resources/synth_look_and_feel_1.xml"))
12094 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12097 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12098 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12099 (synopsis "Phylogenomics libraries for Java")
12100 (description "Forester is a collection of Java libraries for
12101 phylogenomics and evolutionary biology research. It includes support for
12102 reading, writing, and exporting phylogenetic trees.")
12103 (license license:lgpl2.1+)))
12105 (define-public java-biojava-core
12107 (name "java-biojava-core")
12111 (uri (git-reference
12112 (url "https://github.com/biojava/biojava")
12113 (commit (string-append "biojava-" version))))
12114 (file-name (string-append name "-" version "-checkout"))
12117 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12118 (build-system ant-build-system)
12121 #:jar-name "biojava-core.jar"
12122 #:source-dir "biojava-core/src/main/java/"
12123 #:test-dir "biojava-core/src/test"
12124 ;; These tests seem to require internet access.
12125 #:test-exclude (list "**/SearchIOTest.java"
12126 "**/BlastXMLParserTest.java"
12127 "**/GenbankCookbookTest.java"
12128 "**/GenbankProxySequenceReaderTest.java")
12130 (modify-phases %standard-phases
12131 (add-before 'build 'copy-resources
12133 (copy-recursively "biojava-core/src/main/resources"
12136 (add-before 'check 'copy-test-resources
12138 (copy-recursively "biojava-core/src/test/resources"
12139 "build/test-classes")
12142 `(("java-log4j-api" ,java-log4j-api)
12143 ("java-log4j-core" ,java-log4j-core)
12144 ("java-slf4j-api" ,java-slf4j-api)
12145 ("java-slf4j-simple" ,java-slf4j-simple)))
12147 `(("java-junit" ,java-junit)
12148 ("java-hamcrest-core" ,java-hamcrest-core)))
12149 (home-page "http://biojava.org")
12150 (synopsis "Core libraries of Java framework for processing biological data")
12151 (description "BioJava is a project dedicated to providing a Java framework
12152 for processing biological data. It provides analytical and statistical
12153 routines, parsers for common file formats, reference implementations of
12154 popular algorithms, and allows the manipulation of sequences and 3D
12155 structures. The goal of the biojava project is to facilitate rapid
12156 application development for bioinformatics.
12158 This package provides the core libraries.")
12159 (license license:lgpl2.1+)))
12161 (define-public java-biojava-phylo
12162 (package (inherit java-biojava-core)
12163 (name "java-biojava-phylo")
12164 (build-system ant-build-system)
12167 #:jar-name "biojava-phylo.jar"
12168 #:source-dir "biojava-phylo/src/main/java/"
12169 #:test-dir "biojava-phylo/src/test"
12171 (modify-phases %standard-phases
12172 (add-before 'build 'copy-resources
12174 (copy-recursively "biojava-phylo/src/main/resources"
12177 (add-before 'check 'copy-test-resources
12179 (copy-recursively "biojava-phylo/src/test/resources"
12180 "build/test-classes")
12183 `(("java-log4j-api" ,java-log4j-api)
12184 ("java-log4j-core" ,java-log4j-core)
12185 ("java-slf4j-api" ,java-slf4j-api)
12186 ("java-slf4j-simple" ,java-slf4j-simple)
12187 ("java-biojava-core" ,java-biojava-core)
12188 ("java-forester" ,java-forester)))
12190 `(("java-junit" ,java-junit)
12191 ("java-hamcrest-core" ,java-hamcrest-core)))
12192 (home-page "http://biojava.org")
12193 (synopsis "Biojava interface to the forester phylogenomics library")
12194 (description "The phylo module provides a biojava interface layer to the
12195 forester phylogenomics library for constructing phylogenetic trees.")))
12197 (define-public java-biojava-alignment
12198 (package (inherit java-biojava-core)
12199 (name "java-biojava-alignment")
12200 (build-system ant-build-system)
12203 #:jar-name "biojava-alignment.jar"
12204 #:source-dir "biojava-alignment/src/main/java/"
12205 #:test-dir "biojava-alignment/src/test"
12207 (modify-phases %standard-phases
12208 (add-before 'build 'copy-resources
12210 (copy-recursively "biojava-alignment/src/main/resources"
12213 (add-before 'check 'copy-test-resources
12215 (copy-recursively "biojava-alignment/src/test/resources"
12216 "build/test-classes")
12219 `(("java-log4j-api" ,java-log4j-api)
12220 ("java-log4j-core" ,java-log4j-core)
12221 ("java-slf4j-api" ,java-slf4j-api)
12222 ("java-slf4j-simple" ,java-slf4j-simple)
12223 ("java-biojava-core" ,java-biojava-core)
12224 ("java-biojava-phylo" ,java-biojava-phylo)
12225 ("java-forester" ,java-forester)))
12227 `(("java-junit" ,java-junit)
12228 ("java-hamcrest-core" ,java-hamcrest-core)))
12229 (home-page "http://biojava.org")
12230 (synopsis "Biojava API for genetic sequence alignment")
12231 (description "The alignment module of BioJava provides an API that
12235 @item implementations of dynamic programming algorithms for sequence
12237 @item reading and writing of popular alignment file formats;
12238 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12241 (define-public java-biojava-core-4.0
12242 (package (inherit java-biojava-core)
12243 (name "java-biojava-core")
12247 (uri (git-reference
12248 (url "https://github.com/biojava/biojava")
12249 (commit (string-append "biojava-" version))))
12250 (file-name (string-append name "-" version "-checkout"))
12253 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12255 (define-public java-biojava-phylo-4.0
12256 (package (inherit java-biojava-core-4.0)
12257 (name "java-biojava-phylo")
12258 (build-system ant-build-system)
12261 #:jar-name "biojava-phylo.jar"
12262 #:source-dir "biojava-phylo/src/main/java/"
12263 #:test-dir "biojava-phylo/src/test"
12265 (modify-phases %standard-phases
12266 (add-before 'build 'copy-resources
12268 (copy-recursively "biojava-phylo/src/main/resources"
12271 (add-before 'check 'copy-test-resources
12273 (copy-recursively "biojava-phylo/src/test/resources"
12274 "build/test-classes")
12277 `(("java-log4j-api" ,java-log4j-api)
12278 ("java-log4j-core" ,java-log4j-core)
12279 ("java-slf4j-api" ,java-slf4j-api)
12280 ("java-slf4j-simple" ,java-slf4j-simple)
12281 ("java-biojava-core" ,java-biojava-core-4.0)
12282 ("java-forester" ,java-forester-1.005)))
12284 `(("java-junit" ,java-junit)
12285 ("java-hamcrest-core" ,java-hamcrest-core)))
12286 (home-page "http://biojava.org")
12287 (synopsis "Biojava interface to the forester phylogenomics library")
12288 (description "The phylo module provides a biojava interface layer to the
12289 forester phylogenomics library for constructing phylogenetic trees.")))
12291 (define-public java-biojava-alignment-4.0
12292 (package (inherit java-biojava-core-4.0)
12293 (name "java-biojava-alignment")
12294 (build-system ant-build-system)
12297 #:jar-name "biojava-alignment.jar"
12298 #:source-dir "biojava-alignment/src/main/java/"
12299 #:test-dir "biojava-alignment/src/test"
12301 (modify-phases %standard-phases
12302 (add-before 'build 'copy-resources
12304 (copy-recursively "biojava-alignment/src/main/resources"
12307 (add-before 'check 'copy-test-resources
12309 (copy-recursively "biojava-alignment/src/test/resources"
12310 "build/test-classes")
12313 `(("java-log4j-api" ,java-log4j-api)
12314 ("java-log4j-core" ,java-log4j-core)
12315 ("java-slf4j-api" ,java-slf4j-api)
12316 ("java-slf4j-simple" ,java-slf4j-simple)
12317 ("java-biojava-core" ,java-biojava-core-4.0)
12318 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12319 ("java-forester" ,java-forester-1.005)))
12321 `(("java-junit" ,java-junit)
12322 ("java-hamcrest-core" ,java-hamcrest-core)))
12323 (home-page "http://biojava.org")
12324 (synopsis "Biojava API for genetic sequence alignment")
12325 (description "The alignment module of BioJava provides an API that
12329 @item implementations of dynamic programming algorithms for sequence
12331 @item reading and writing of popular alignment file formats;
12332 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12335 (define-public dropseq-tools
12337 (name "dropseq-tools")
12342 (uri "http://mccarrolllab.com/download/1276/")
12343 (file-name (string-append "dropseq-tools-" version ".zip"))
12346 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12347 ;; Delete bundled libraries
12348 (modules '((guix build utils)))
12351 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12352 (delete-file-recursively "3rdParty")
12354 (build-system ant-build-system)
12356 `(#:tests? #f ; test data are not included
12357 #:test-target "test"
12358 #:build-target "all"
12359 #:source-dir "public/src/"
12362 (list (string-append "-Dpicard.executable.dir="
12363 (assoc-ref %build-inputs "java-picard")
12365 #:modules ((ice-9 match)
12368 (guix build java-utils)
12369 (guix build ant-build-system))
12371 (modify-phases %standard-phases
12372 ;; FIXME: fails with "java.io.FileNotFoundException:
12373 ;; /gnu/store/…-dropseq-tools-1.13/share/java/lib/biojava-alignment.jar"
12374 (delete 'generate-jar-indices)
12375 ;; All dependencies must be linked to "lib", because that's where
12376 ;; they will be searched for when the Class-Path property of the
12377 ;; manifest is computed.
12378 (add-after 'unpack 'record-references
12379 (lambda* (#:key inputs #:allow-other-keys)
12380 (mkdir-p "jar/lib")
12381 (let ((dirs (filter-map (match-lambda
12383 (if (and (string-prefix? "java-" name)
12384 (not (string=? name "java-testng")))
12387 (for-each (lambda (jar)
12388 (symlink jar (string-append "jar/lib/" (basename jar))))
12389 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12392 ;; There is no installation target
12394 (lambda* (#:key inputs outputs #:allow-other-keys)
12395 (let* ((out (assoc-ref outputs "out"))
12396 (bin (string-append out "/bin"))
12397 (share (string-append out "/share/java/"))
12398 (lib (string-append share "/lib/"))
12399 (scripts (list "BAMTagHistogram"
12400 "BAMTagofTagCounts"
12401 "BaseDistributionAtReadPosition"
12402 "CollapseBarcodesInPlace"
12403 "CollapseTagWithContext"
12405 "CreateIntervalsFiles"
12406 "DetectBeadSynthesisErrors"
12407 "DigitalExpression"
12408 "Drop-seq_alignment.sh"
12411 "GatherGeneGCLength"
12412 "GatherMolecularBarcodeDistributionByGene"
12413 "GatherReadQualityMetrics"
12416 "SelectCellsByNumTranscripts"
12417 "SingleCellRnaSeqMetricsCollector"
12418 "TagBamWithReadSequenceExtended"
12419 "TagReadWithGeneExon"
12420 "TagReadWithInterval"
12421 "TrimStartingSequence"
12422 "ValidateReference")))
12423 (for-each mkdir-p (list bin share lib))
12424 (install-file "dist/dropseq.jar" share)
12425 (for-each (lambda (script)
12426 (chmod script #o555)
12427 (install-file script bin))
12429 (substitute* (map (lambda (script)
12430 (string-append bin "/" script))
12432 (("^java") (which "java"))
12433 (("jar_deploy_dir=.*")
12434 (string-append "jar_deploy_dir=" share "\n"))))
12436 ;; FIXME: We do this after stripping jars because we don't want it to
12437 ;; copy all these jars and strip them. We only want to install
12438 ;; links. Arguably, this is a problem with the ant-build-system.
12439 (add-after 'strip-jar-timestamps 'install-links
12440 (lambda* (#:key outputs #:allow-other-keys)
12441 (let* ((out (assoc-ref outputs "out"))
12442 (share (string-append out "/share/java/"))
12443 (lib (string-append share "/lib/")))
12444 (for-each (lambda (jar)
12445 (symlink (readlink jar)
12446 (string-append lib (basename jar))))
12447 (find-files "jar/lib" "\\.jar$")))
12450 `(("jdk" ,icedtea-8)
12451 ("java-picard" ,java-picard-2.10.3)
12452 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12453 ("java-commons-math3" ,java-commons-math3)
12454 ("java-commons-jexl2" ,java-commons-jexl-2)
12455 ("java-commons-collections4" ,java-commons-collections4)
12456 ("java-commons-lang2" ,java-commons-lang)
12457 ("java-commons-io" ,java-commons-io)
12458 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12459 ("java-guava" ,java-guava)
12460 ("java-la4j" ,java-la4j)
12461 ("java-biojava-core" ,java-biojava-core-4.0)
12462 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12463 ("java-jdistlib" ,java-jdistlib)
12464 ("java-simple-xml" ,java-simple-xml)
12465 ("java-snakeyaml" ,java-snakeyaml)))
12468 ("java-testng" ,java-testng)))
12469 (home-page "http://mccarrolllab.com/dropseq/")
12470 (synopsis "Tools for Drop-seq analyses")
12471 (description "Drop-seq is a technology to enable biologists to
12472 analyze RNA expression genome-wide in thousands of individual cells at
12473 once. This package provides tools to perform Drop-seq analyses.")
12474 (license license:expat)))
12476 (define-public pigx-rnaseq
12478 (name "pigx-rnaseq")
12482 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12483 "releases/download/v" version
12484 "/pigx_rnaseq-" version ".tar.gz"))
12487 "05gn658zpj9xki5dbs728z9zxq1mcm25hkwr5vzwqxsfi15l5f2l"))))
12488 (build-system gnu-build-system)
12490 `(#:parallel-tests? #f ; not supported
12492 (modify-phases %standard-phases
12493 ;; "test.sh" runs STAR, which requires excessive amounts of memory.
12494 (add-after 'unpack 'disable-resource-intensive-test
12496 (substitute* "Makefile.in"
12497 (("(^ tests/test_trim_galore/test.sh).*" _ m) m)
12498 (("^ tests/test_multiqc/test.sh") "")
12499 (("^ test.sh") ""))
12503 ("snakemake" ,snakemake)
12505 ("multiqc" ,multiqc)
12507 ("trim-galore" ,trim-galore)
12509 ("samtools" ,samtools)
12510 ("bedtools" ,bedtools)
12511 ("r-minimal" ,r-minimal)
12512 ("r-rmarkdown" ,r-rmarkdown)
12513 ("r-ggplot2" ,r-ggplot2)
12514 ("r-ggrepel" ,r-ggrepel)
12515 ("r-gprofiler" ,r-gprofiler)
12516 ("r-deseq2" ,r-deseq2)
12518 ("r-knitr" ,r-knitr)
12519 ("r-pheatmap" ,r-pheatmap)
12520 ("r-corrplot" ,r-corrplot)
12521 ("r-reshape2" ,r-reshape2)
12522 ("r-plotly" ,r-plotly)
12523 ("r-scales" ,r-scales)
12524 ("r-summarizedexperiment" ,r-summarizedexperiment)
12525 ("r-crosstalk" ,r-crosstalk)
12526 ("r-tximport" ,r-tximport)
12527 ("r-rtracklayer" ,r-rtracklayer)
12528 ("r-rjson" ,r-rjson)
12530 ("ghc-pandoc" ,ghc-pandoc)
12531 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12532 ("python-wrapper" ,python-wrapper)
12533 ("python-pyyaml" ,python-pyyaml)))
12534 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12535 (synopsis "Analysis pipeline for RNA sequencing experiments")
12536 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
12537 reporting for RNA sequencing experiments. It is easy to use and produces high
12538 quality reports. The inputs are reads files from the sequencing experiment,
12539 and a configuration file which describes the experiment. In addition to
12540 quality control of the experiment, the pipeline produces a differential
12541 expression report comparing samples in an easily configurable manner.")
12542 (license license:gpl3+)))
12544 (define-public pigx-chipseq
12546 (name "pigx-chipseq")
12550 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
12551 "releases/download/v" version
12552 "/pigx_chipseq-" version ".tar.gz"))
12555 "0l3vd9xwqzap3mmyj8xwqp84kj7scbq308diqnwg2albphl75xqs"))))
12556 (build-system gnu-build-system)
12557 ;; parts of the tests rely on access to the network
12558 (arguments '(#:tests? #f))
12561 ("coreutils" ,coreutils)
12562 ("r-minimal" ,r-minimal)
12563 ("r-argparser" ,r-argparser)
12564 ("r-biocparallel" ,r-biocparallel)
12565 ("r-biostrings" ,r-biostrings)
12566 ("r-chipseq" ,r-chipseq)
12567 ("r-data-table" ,r-data-table)
12568 ("r-dplyr" ,r-dplyr)
12569 ("r-genomation" ,r-genomation)
12570 ("r-genomicalignments" ,r-genomicalignments)
12571 ("r-genomicranges" ,r-genomicranges)
12572 ("r-rsamtools" ,r-rsamtools)
12573 ("r-rtracklayer" ,r-rtracklayer)
12574 ("r-s4vectors" ,r-s4vectors)
12575 ("r-stringr" ,r-stringr)
12576 ("r-tibble" ,r-tibble)
12577 ("r-tidyr" ,r-tidyr)
12578 ("r-jsonlite" ,r-jsonlite)
12579 ("r-heatmaply" ,r-heatmaply)
12580 ("r-htmlwidgets" ,r-htmlwidgets)
12581 ("r-ggplot2" ,r-ggplot2)
12582 ("r-plotly" ,r-plotly)
12583 ("r-rmarkdown" ,r-rmarkdown)
12584 ("python-wrapper" ,python-wrapper)
12585 ("python-pyyaml" ,python-pyyaml)
12586 ("python-magic" ,python-magic)
12587 ("python-xlrd" ,python-xlrd)
12588 ("trim-galore" ,trim-galore)
12590 ("multiqc" ,multiqc)
12592 ("ghc-pandoc" ,ghc-pandoc)
12593 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12597 ("snakemake" ,snakemake)
12598 ("samtools" ,samtools)
12599 ("bedtools" ,bedtools)
12600 ("kentutils" ,kentutils)))
12602 `(("python-pytest" ,python-pytest)))
12603 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12604 (synopsis "Analysis pipeline for ChIP sequencing experiments")
12605 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
12606 calling and reporting for ChIP sequencing experiments. It is easy to use and
12607 produces high quality reports. The inputs are reads files from the sequencing
12608 experiment, and a configuration file which describes the experiment. In
12609 addition to quality control of the experiment, the pipeline enables to set up
12610 multiple peak calling analysis and allows the generation of a UCSC track hub
12611 in an easily configurable manner.")
12612 (license license:gpl3+)))
12614 (define-public pigx-bsseq
12616 (name "pigx-bsseq")
12620 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
12621 "releases/download/v" version
12622 "/pigx_bsseq-" version ".tar.gz"))
12625 "0l97wvkq4diq8lcarraj33bby1zzf0w804jwi8mlc5qddp8idwhy"))))
12626 (build-system gnu-build-system)
12629 (modify-phases %standard-phases
12630 (add-before 'check 'set-timezone
12631 ;; The readr package is picky about timezones.
12632 (lambda* (#:key inputs #:allow-other-keys)
12633 (setenv "TZ" "UTC+1")
12635 (string-append (assoc-ref inputs "tzdata")
12636 "/share/zoneinfo"))
12639 `(("tzdata" ,tzdata)))
12641 `(("coreutils" ,coreutils)
12644 ("r-minimal" ,r-minimal)
12645 ("r-annotationhub" ,r-annotationhub)
12647 ("r-genomation" ,r-genomation)
12648 ("r-methylkit" ,r-methylkit)
12649 ("r-rtracklayer" ,r-rtracklayer)
12650 ("r-rmarkdown" ,r-rmarkdown)
12651 ("r-bookdown" ,r-bookdown)
12652 ("r-ggplot2" ,r-ggplot2)
12653 ("r-ggbio" ,r-ggbio)
12654 ("ghc-pandoc" ,ghc-pandoc)
12655 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12656 ("python-wrapper" ,python-wrapper)
12657 ("python-pyyaml" ,python-pyyaml)
12658 ("snakemake" ,snakemake)
12659 ("bismark" ,bismark)
12662 ("trim-galore" ,trim-galore)
12663 ("cutadapt" ,cutadapt)
12664 ("samtools" ,samtools)))
12665 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12666 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
12667 (description "PiGx BSseq is a data processing pipeline for raw fastq read
12668 data of bisulfite experiments; it produces reports on aggregate methylation
12669 and coverage and can be used to produce information on differential
12670 methylation and segmentation.")
12671 (license license:gpl3+)))
12673 (define-public pigx-scrnaseq
12675 (name "pigx-scrnaseq")
12679 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/"
12680 "releases/download/v" version
12681 "/pigx_scrnaseq-" version ".tar.gz"))
12684 "131zarirv16w8653m0d66jgjnwqfsxqc0hix0rypssz4d83bl51j"))))
12685 (build-system gnu-build-system)
12687 `(#:configure-flags
12688 (list (string-append "PICARDJAR=" (assoc-ref %build-inputs "java-picard")
12689 "/share/java/picard.jar")
12690 (string-append "DROPSEQJAR=" (assoc-ref %build-inputs "dropseq-tools")
12691 "/share/java/dropseq.jar"))))
12693 `(("coreutils" ,coreutils)
12695 ("dropseq-tools" ,dropseq-tools)
12697 ("java-picard" ,java-picard-2.10.3) ; same as for dropseq
12698 ("java" ,icedtea-8)
12699 ("python-wrapper" ,python-wrapper)
12700 ("python-pyyaml" ,python-pyyaml)
12701 ("python-pandas" ,python-pandas)
12702 ("python-magic" ,python-magic)
12703 ("python-numpy" ,python-numpy)
12704 ("python-loompy" ,python-loompy)
12705 ("ghc-pandoc" ,ghc-pandoc)
12706 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12707 ("samtools" ,samtools)
12708 ("snakemake" ,snakemake)
12710 ("r-minimal" ,r-minimal)
12711 ("r-argparser" ,r-argparser)
12712 ("r-cowplot" ,r-cowplot)
12713 ("r-data-table" ,r-data-table)
12714 ("r-delayedarray" ,r-delayedarray)
12715 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
12716 ("r-dplyr" ,r-dplyr)
12717 ("r-dropbead" ,r-dropbead)
12719 ("r-genomicalignments" ,r-genomicalignments)
12720 ("r-genomicfiles" ,r-genomicfiles)
12721 ("r-genomicranges" ,r-genomicranges)
12722 ("r-ggplot2" ,r-ggplot2)
12723 ("r-hdf5array" ,r-hdf5array)
12724 ("r-pheatmap" ,r-pheatmap)
12725 ("r-rmarkdown" ,r-rmarkdown)
12726 ("r-rsamtools" ,r-rsamtools)
12727 ("r-rtracklayer" ,r-rtracklayer)
12728 ("r-rtsne" ,r-rtsne)
12729 ("r-scater" ,r-scater)
12730 ("r-scran" ,r-scran)
12731 ("r-singlecellexperiment" ,r-singlecellexperiment)
12732 ("r-stringr" ,r-stringr)
12733 ("r-yaml" ,r-yaml)))
12734 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12735 (synopsis "Analysis pipeline for single-cell RNA sequencing experiments")
12736 (description "PiGX scRNAseq is an analysis pipeline for preprocessing and
12737 quality control for single cell RNA sequencing experiments. The inputs are
12738 read files from the sequencing experiment, and a configuration file which
12739 describes the experiment. It produces processed files for downstream analysis
12740 and interactive quality reports. The pipeline is designed to work with UMI
12742 (license license:gpl3+)))
12744 (define-public pigx
12750 (uri (string-append "https://github.com/BIMSBbioinfo/pigx/"
12751 "releases/download/v" version
12752 "/pigx-" version ".tar.gz"))
12755 "1i5njdy1clj5ncw45d16p7mwmqvb1ilikl9n797pxklc3f4s7mq7"))))
12756 (build-system gnu-build-system)
12758 `(("python" ,python)
12759 ("pigx-bsseq" ,pigx-bsseq)
12760 ("pigx-chipseq" ,pigx-chipseq)
12761 ("pigx-rnaseq" ,pigx-rnaseq)
12762 ("pigx-scrnaseq" ,pigx-scrnaseq)))
12763 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12764 (synopsis "Analysis pipelines for genomics")
12765 (description "PiGx is a collection of genomics pipelines. It includes the
12766 following pipelines:
12769 @item PiGx BSseq for raw fastq read data of bisulfite experiments
12770 @item PiGx RNAseq for RNAseq samples
12771 @item PiGx scRNAseq for single cell dropseq analysis
12772 @item PiGx ChIPseq for reads from ChIPseq experiments
12775 All pipelines are easily configured with a simple sample sheet and a
12776 descriptive settings file. The result is a set of comprehensive, interactive
12777 HTML reports with interesting findings about your samples.")
12778 (license license:gpl3+)))
12780 (define-public genrich
12786 (uri (git-reference
12787 (url "https://github.com/jsh58/Genrich.git")
12788 (commit (string-append "v" version))))
12791 "0x0q6z0208n3cxzqjla4rgjqpyqgwpmz27852lcvzkzaigymq4zp"))))
12792 (build-system gnu-build-system)
12794 `(#:tests? #f ; there are none
12796 (modify-phases %standard-phases
12797 (delete 'configure)
12799 (lambda* (#:key outputs #:allow-other-keys)
12800 (install-file "Genrich" (string-append (assoc-ref outputs "out") "/bin"))
12804 (home-page "https://github.com/jsh58/Genrich")
12805 (synopsis "Detecting sites of genomic enrichment")
12806 (description "Genrich is a peak-caller for genomic enrichment
12807 assays (e.g. ChIP-seq, ATAC-seq). It analyzes alignment files generated
12808 following the assay and produces a file detailing peaks of significant
12810 (license license:expat)))
12812 (define-public mantis
12813 (let ((commit "4ffd171632c2cb0056a86d709dfd2bf21bc69b84")
12817 (version (git-version "0" revision commit))
12820 (uri (git-reference
12821 (url "https://github.com/splatlab/mantis.git")
12823 (file-name (git-file-name name version))
12826 "0iqbr0dhmlc8mzpirmm2s4pkzkwdgrcx50yx6cv3wlr2qi064p55"))))
12827 (build-system cmake-build-system)
12828 (arguments '(#:tests? #f)) ; there are none
12830 `(("sdsl-lite" ,sdsl-lite)
12831 ("openssl" ,openssl)
12833 (home-page "https://github.com/splatlab/mantis")
12834 (synopsis "Large-scale sequence-search index data structure")
12835 (description "Mantis is a space-efficient data structure that can be
12836 used to index thousands of raw-read genomics experiments and facilitate
12837 large-scale sequence searches on those experiments. Mantis uses counting
12838 quotient filters instead of Bloom filters, enabling rapid index builds and
12839 queries, small indexes, and exact results, i.e., no false positives or
12840 negatives. Furthermore, Mantis is also a colored de Bruijn graph
12841 representation, so it supports fast graph traversal and other topological
12842 analyses in addition to large-scale sequence-level searches.")
12843 ;; uses __uint128_t and inline assembly
12844 (supported-systems '("x86_64-linux"))
12845 (license license:bsd-3))))
12847 (define-public r-diversitree
12849 (name "r-diversitree")
12854 (uri (cran-uri "diversitree" version))
12857 "0gh4rcrp0an3jh8915i1fsxlgyfk7njywgbd5ln5r2jhr085kpz7"))))
12858 (build-system r-build-system)
12860 `(("gfortran" ,gfortran)))
12861 (inputs `(("fftw" ,fftw) ("gsl" ,gsl)))
12864 ("r-desolve" ,r-desolve)
12866 ("r-suplex" ,r-subplex)))
12867 (home-page "https://www.zoology.ubc.ca/prog/diversitree")
12868 (synopsis "Comparative 'phylogenetic' analyses of diversification")
12869 (description "This package contains a number of comparative \"phylogenetic\"
12870 methods, mostly focusing on analysing diversification and character evolution.
12871 Contains implementations of \"BiSSE\" (Binary State Speciation and Extinction)
12872 and its unresolved tree extensions, \"MuSSE\" (Multiple State Speciation and
12873 Extinction), \"QuaSSE\", \"GeoSSE\", and \"BiSSE-ness\" Other included methods
12874 include Markov models of discrete and continuous trait evolution and constant
12875 rate speciation and extinction.")
12876 (license license:gpl2+)))
12878 (define-public sjcount
12879 ;; There is no tag for version 3.2, nor is there a release archive.
12880 (let ((commit "292d3917cadb3f6834c81e509c30e61cd7ead6e5")
12884 (version (git-version "3.2" revision commit))
12887 (uri (git-reference
12888 (url "https://github.com/pervouchine/sjcount-full.git")
12890 (file-name (string-append name "-" version "-checkout"))
12893 "0gdgj35j249f04rqgq8ymcc1xg1vi9kzbajnjqpaq2wpbh8bl234"))))
12894 (build-system gnu-build-system)
12896 `(#:tests? #f ; requires a 1.4G test file
12898 (list (string-append "SAMTOOLS_DIR="
12899 (assoc-ref %build-inputs "samtools")
12902 (modify-phases %standard-phases
12903 (replace 'configure
12904 (lambda* (#:key inputs #:allow-other-keys)
12905 (substitute* "makefile"
12906 (("-I \\$\\{SAMTOOLS_DIR\\}")
12907 (string-append "-I" (assoc-ref inputs "samtools")
12908 "/include/samtools"))
12909 (("-lz ") "-lz -lpthread "))
12912 (lambda* (#:key outputs #:allow-other-keys)
12913 (for-each (lambda (tool)
12915 (string-append (assoc-ref outputs "out")
12917 '("j_count" "b_count" "sjcount"))
12920 `(("samtools" ,samtools-0.1)
12922 (home-page "https://github.com/pervouchine/sjcount-full/")
12923 (synopsis "Annotation-agnostic splice junction counting pipeline")
12924 (description "Sjcount is a utility for fast quantification of splice
12925 junctions in RNA-seq data. It is annotation-agnostic and offset-aware. This
12926 version does count multisplits.")
12927 (license license:gpl3+))))
12929 (define-public minimap2
12936 (uri (string-append "https://github.com/lh3/minimap2/"
12937 "releases/download/v" version "/"
12938 "minimap2-" version ".tar.bz2"))
12941 "080w9066irkbhbyr4nmf19pzkdd2s4v31hpzlajgq2y0drr6zcsj"))))
12942 (build-system gnu-build-system)
12944 `(#:tests? #f ; there are none
12947 (let ((system ,(or (%current-target-system)
12948 (%current-system))))
12950 ((string-prefix? "x86_64" system)
12952 ((or (string-prefix? "armhf" system)
12953 (string-prefix? "aarch64" system))
12955 (_ "sse2only=1"))))
12957 (modify-phases %standard-phases
12958 (delete 'configure)
12960 (lambda* (#:key outputs #:allow-other-keys)
12961 (let* ((out (assoc-ref outputs "out"))
12962 (bin (string-append out "/bin"))
12963 (man (string-append out "/share/man/man1")))
12964 (install-file "minimap2" bin)
12966 (install-file "minimap2.1" man))
12970 (home-page "https://lh3.github.io/minimap2/")
12971 (synopsis "Pairwise aligner for genomic and spliced nucleotide sequences")
12972 (description "Minimap2 is a versatile sequence alignment program that
12973 aligns DNA or mRNA sequences against a large reference database. Typical use
12977 @item mapping PacBio or Oxford Nanopore genomic reads to the human genome;
12978 @item finding overlaps between long reads with error rate up to ~15%;
12979 @item splice-aware alignment of PacBio Iso-Seq or Nanopore cDNA or Direct RNA
12980 reads against a reference genome;
12981 @item aligning Illumina single- or paired-end reads;
12982 @item assembly-to-assembly alignment;
12983 @item full-genome alignment between two closely related species with
12984 divergence below ~15%.
12986 (license license:expat)))
12988 (define-public r-circus
12995 (uri (git-reference
12996 (url "https://github.com/BIMSBbioinfo/ciRcus.git")
12997 (commit (string-append "v" version))))
12998 (file-name (git-file-name name version))
13001 "0jhjn3ilb057hbf6yzrihj13ifxxs32y7nkby8l3lkm28dg4p97h"))))
13002 (build-system r-build-system)
13004 `(("r-annotationdbi" ,r-annotationdbi)
13005 ("r-annotationhub" ,r-annotationhub)
13006 ("r-biomart" ,r-biomart)
13007 ("r-data-table" ,r-data-table)
13009 ("r-genomicfeatures" ,r-genomicfeatures)
13010 ("r-genomicranges" ,r-genomicranges)
13011 ("r-ggplot2" ,r-ggplot2)
13013 ("r-iranges" ,r-iranges)
13014 ("r-rcolorbrewer" ,r-rcolorbrewer)
13015 ("r-rmysql" ,r-rmysql)
13016 ("r-s4vectors" ,r-s4vectors)
13017 ("r-stringr" ,r-stringr)
13018 ("r-summarizedexperiment" ,r-summarizedexperiment)))
13020 `(("r-knitr" ,r-knitr)))
13021 (home-page "https://github.com/BIMSBbioinfo/ciRcus")
13022 (synopsis "Annotation, analysis and visualization of circRNA data")
13023 (description "Circus is an R package for annotation, analysis and
13024 visualization of circRNA data. Users can annotate their circRNA candidates
13025 with host genes, gene featrues they are spliced from, and discriminate between
13026 known and yet unknown splice junctions. Circular-to-linear ratios of circRNAs
13027 can be calculated, and a number of descriptive plots easily generated.")
13028 (license license:artistic2.0)))
13030 (define-public r-loomr
13031 (let ((commit "df0144bd2bbceca6fadef9edc1bbc5ca672d4739")
13035 (version (git-version "0.2.0" revision commit))
13039 (uri (git-reference
13040 (url "https://github.com/mojaveazure/loomR.git")
13042 (file-name (git-file-name name version))
13045 "1b1g4dlmfdyhn56bz1mkh9ymirri43wiz7rjhs7py3y7bdw1s3yr"))))
13046 (build-system r-build-system)
13049 ("r-hdf5r" ,r-hdf5r)
13050 ("r-iterators" ,r-iterators)
13051 ("r-itertools" ,r-itertools)
13052 ("r-matrix" ,r-matrix)))
13053 (home-page "https://github.com/mojaveazure/loomR")
13054 (synopsis "R interface for loom files")
13055 (description "This package provides an R interface to access, create,
13056 and modify loom files. loomR aims to be completely compatible with loompy.")
13057 (license license:gpl3))))
13059 (define-public gffread
13060 ;; We cannot use the tagged release because it is not in sync with gclib.
13061 ;; See https://github.com/gpertea/gffread/issues/26
13062 (let ((commit "ba7535fcb3cea55a6e5a491d916e93b454e87fd0")
13066 (version (git-version "0.9.12" revision commit))
13070 (uri (git-reference
13071 (url "https://github.com/gpertea/gffread.git")
13073 (file-name (git-file-name name version))
13076 "1dl2nbcg96lxpd0drg48ssa8343nf7pw9s9mkrc4mjjmfwsin3ki"))))
13077 (build-system gnu-build-system)
13079 `(#:tests? #f ; no check target
13081 (list "GCLDIR=gclib")
13083 (modify-phases %standard-phases
13084 (delete 'configure)
13085 (add-after 'unpack 'copy-gclib-source
13086 (lambda* (#:key inputs #:allow-other-keys)
13088 (copy-recursively (assoc-ref inputs "gclib-source") "gclib")
13090 ;; There is no install target
13092 (lambda* (#:key outputs #:allow-other-keys)
13093 (let* ((out (assoc-ref outputs "out"))
13094 (bin (string-append out "/bin")))
13095 (install-file "gffread" bin))
13099 ,(let ((version "0.10.3")
13100 (commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13104 (uri (git-reference
13105 (url "https://github.com/gpertea/gclib.git")
13107 (file-name (git-file-name "gclib" version))
13110 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13111 (home-page "https://github.com/gpertea/gffread/")
13112 (synopsis "Parse and convert GFF/GTF files")
13114 "This package provides a GFF/GTF file parsing utility providing format
13115 conversions, region filtering, FASTA sequence extraction and more.")
13116 ;; gffread is under Expat, but gclib is under Artistic 2.0
13117 (license (list license:expat
13118 license:artistic2.0)))))
13120 (define-public find-circ
13121 ;; The last release was in 2015. The license was clarified in 2017, so we
13122 ;; take the latest commit.
13123 (let ((commit "8655dca54970fcf7e92e22fbf57e1188724dda7d")
13127 (version (git-version "1.2" revision commit))
13131 (uri (git-reference
13132 (url "https://github.com/marvin-jens/find_circ.git")
13134 (file-name (git-file-name name version))
13137 "0p77pbqbclqr4srms34y1b9b4njybfpjiknc11ki84f3p8skb3cg"))))
13138 (build-system gnu-build-system)
13140 `(#:tests? #f ; there are none
13142 ;; There is no actual build system.
13143 (modify-phases %standard-phases
13144 (delete 'configure)
13147 (lambda* (#:key outputs #:allow-other-keys)
13148 (let* ((out (assoc-ref outputs "out"))
13149 (bin (string-append out "/bin"))
13150 (path (getenv "PYTHONPATH")))
13151 (for-each (lambda (script)
13152 (install-file script bin)
13153 (wrap-program (string-append bin "/" script)
13154 `("PYTHONPATH" ":" prefix (,path))))
13159 "unmapped2anchors.py")))
13162 `(("python2" ,python-2)
13163 ("python2-pysam" ,python2-pysam)
13164 ("python2-numpy" ,python2-numpy)))
13165 (home-page "https://github.com/marvin-jens/find_circ")
13166 (synopsis "circRNA detection from RNA-seq reads")
13167 (description "This package provides tools to detect head-to-tail
13168 spliced (back-spliced) sequencing reads, indicative of circular RNA (circRNA)
13170 (license license:gpl3))))
13172 (define-public python-scanpy
13174 (name "python-scanpy")
13179 (uri (pypi-uri "scanpy" version))
13182 "1ak7bxms5a0yvf65prppq2g38clkv7c7jnjbnfpkh3xxv7q512jz"))))
13183 (build-system python-build-system)
13185 `(("python-anndata" ,python-anndata)
13186 ("python-igraph" ,python-igraph)
13187 ("python-numba" ,python-numba)
13188 ("python-joblib" ,python-joblib)
13189 ("python-natsort" ,python-natsort)
13190 ("python-networkx" ,python-networkx)
13191 ("python-statsmodels" ,python-statsmodels)
13192 ("python-scikit-learn" ,python-scikit-learn)
13193 ("python-matplotlib" ,python-matplotlib)
13194 ("python-pandas" ,python-pandas)
13195 ("python-scipy" ,python-scipy)
13196 ("python-seaborn" ,python-seaborn)
13197 ("python-h5py" ,python-h5py)
13198 ("python-tables" ,python-tables)))
13199 (home-page "http://github.com/theislab/scanpy")
13200 (synopsis "Single-Cell Analysis in Python.")
13201 (description "Scanpy is a scalable toolkit for analyzing single-cell gene
13202 expression data. It includes preprocessing, visualization, clustering,
13203 pseudotime and trajectory inference and differential expression testing. The
13204 Python-based implementation efficiently deals with datasets of more than one
13206 (license license:bsd-3)))
13208 (define-public gffcompare
13209 (let ((commit "be56ef4349ea3966c12c6397f85e49e047361c41")
13212 (name "gffcompare")
13213 (version (git-version "0.10.15" revision commit))
13217 (uri (git-reference
13218 (url "https://github.com/gpertea/gffcompare/")
13220 (file-name (git-file-name name version))
13222 (base32 "0cp5qpxdhw4mxpya5dld8wi3jk00zyklm6rcri426wydinrnfmkg"))))
13223 (build-system gnu-build-system)
13225 `(#:tests? #f ; no check target
13227 (modify-phases %standard-phases
13228 (delete 'configure)
13229 (add-before 'build 'copy-gclib-source
13230 (lambda* (#:key inputs #:allow-other-keys)
13233 (assoc-ref inputs "gclib-source") "../gclib")
13236 (lambda* (#:key outputs #:allow-other-keys)
13237 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
13238 (install-file "gffcompare" bin)
13241 `(("gclib-source" ; see 'README.md' of gffcompare
13242 ,(let ((commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13245 (version (git-version "0.10.3" revision commit)))
13248 (uri (git-reference
13249 (url "https://github.com/gpertea/gclib/")
13251 (file-name (git-file-name name version))
13253 (base32 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13254 (home-page "https://github.com/gpertea/gffcompare/")
13255 (synopsis "Tool for comparing or classifing transcripts of RNA-Seq")
13257 "@code{gffcompare} is a tool that can:
13259 @item compare and evaluate the accuracy of RNA-Seq transcript assemblers
13260 (Cufflinks, Stringtie);
13261 @item collapse (merge) duplicate transcripts from multiple GTF/GFF3 files (e.g.
13262 resulted from assembly of different samples);
13263 @item classify transcripts from one or multiple GTF/GFF3 files as they relate to
13264 reference transcripts provided in a annotation file (also in GTF/GFF3 format).
13268 license:expat ;license for gffcompare
13269 license:artistic2.0))))) ;license for gclib
13271 (define-public python-intervaltree
13273 (name "python-intervaltree")
13278 (uri (pypi-uri "intervaltree" version))
13281 "02w191m9zxkcjqr1kv2slxvhymwhj3jnsyy3a28b837pi15q19dc"))))
13282 (build-system python-build-system)
13283 ;; FIXME: error when collecting tests
13284 (arguments '(#:tests? #f))
13286 `(("python-sortedcontainers" ,python-sortedcontainers)))
13288 `(("python-pytest" ,python-pytest)))
13289 (home-page "https://github.com/chaimleib/intervaltree")
13290 (synopsis "Editable interval tree data structure")
13292 "This package provides a mutable, self-balancing interval tree
13293 implementation for Python. Queries may be by point, by range overlap, or by
13294 range envelopment. This library was designed to allow tagging text and time
13295 intervals, where the intervals include the lower bound but not the upper
13297 (license license:asl2.0)))
13299 (define-public python-pypairix
13301 (name "python-pypairix")
13306 (uri (pypi-uri "pypairix" version))
13309 "0zs92b74s5v4xy2h16s15f3z6l4nnbw8x8zyif7xx5xpafjn0xss"))))
13310 (build-system python-build-system)
13311 ;; FIXME: the tests fail because test.support cannot be loaded:
13312 ;; ImportError: cannot import name 'support'
13313 (arguments '(#:tests? #f))
13316 (home-page "https://github.com/4dn-dcic/pairix")
13317 (synopsis "Support for querying pairix-indexed bgzipped text files")
13319 "Pypairix is a Python module for fast querying on a pairix-indexed
13320 bgzipped text file that contains a pair of genomic coordinates per line.")
13321 (license license:expat)))
13323 (define-public python-pyfaidx
13325 (name "python-pyfaidx")
13326 (version "0.5.4.2")
13330 (uri (pypi-uri "pyfaidx" version))
13333 "0y5zyjksj1rdglj601xd2bbni5abhdh622y3ck76chyzxz9z4rx8"))))
13334 (build-system python-build-system)
13336 `(("python-setuptools" ,python-setuptools)
13337 ("python-six" ,python-six)))
13338 (home-page "http://mattshirley.com")
13339 (synopsis "Random access to fasta subsequences")
13341 "This package provides procedures for efficient pythonic random access to
13342 fasta subsequences.")
13343 (license license:bsd-3)))
13345 (define-public python-cooler
13347 (name "python-cooler")
13352 (uri (pypi-uri "cooler" version))
13355 "08k5nxnxa6qsbk15z5z0q01n28042k87wi4905hh95rzqib15mhx"))))
13356 (build-system python-build-system)
13358 `(("python-biopython" ,python-biopython)
13359 ("python-click" ,python-click)
13360 ("python-cytoolz" ,python-cytoolz)
13361 ("python-dask" ,python-dask)
13362 ("python-h5py" ,python-h5py)
13363 ("python-multiprocess" ,python-multiprocess)
13364 ("python-pandas" ,python-pandas)
13365 ("python-pyfaidx" ,python-pyfaidx)
13366 ("python-pypairix" ,python-pypairix)
13367 ("python-pysam" ,python-pysam)
13368 ("python-scipy" ,python-scipy)))
13370 `(("python-mock" ,python-mock)
13371 ("python-nose" ,python-nose)
13372 ("python-numpydoc" ,python-numpydoc)
13373 ("python-sphinx" ,python-sphinx)))
13374 (home-page "https://github.com/mirnylab/cooler")
13375 (synopsis "Sparse binary format for genomic interaction matrices")
13377 "Cooler is a support library for a sparse, compressed, binary persistent
13378 storage format, called @code{cool}, used to store genomic interaction data,
13379 such as Hi-C contact matrices.")
13380 (license license:bsd-3)))
13382 (define-public python-hicexplorer
13384 (name "python-hicexplorer")
13388 ;; The latest version is not available on Pypi.
13390 (uri (git-reference
13391 (url "https://github.com/deeptools/HiCExplorer.git")
13393 (file-name (git-file-name name version))
13396 "0q5gpbzmrkvygqgw524q36b4nrivcmyi5v194vsx0qw7b3gcmq08"))))
13397 (build-system python-build-system)
13400 (modify-phases %standard-phases
13401 (add-after 'unpack 'loosen-up-requirements
13403 (substitute* "setup.py"
13407 `(("python-biopython" ,python-biopython)
13408 ("python-configparser" ,python-configparser)
13409 ("python-cooler" ,python-cooler)
13410 ("python-future" ,python-future)
13411 ("python-intervaltree" ,python-intervaltree)
13412 ("python-jinja2" ,python-jinja2)
13413 ("python-matplotlib" ,python-matplotlib)
13414 ("python-numpy" ,python-numpy)
13415 ("python-pandas" ,python-pandas)
13416 ("python-pybigwig" ,python-pybigwig)
13417 ("python-pysam" ,python-pysam)
13418 ("python-scipy" ,python-scipy)
13419 ("python-six" ,python-six)
13420 ("python-tables" ,python-tables)
13421 ("python-unidecode" ,python-unidecode)))
13422 (home-page "http://hicexplorer.readthedocs.io")
13423 (synopsis "Process, analyze and visualize Hi-C data")
13425 "HiCExplorer is a powerful and easy to use set of tools to process,
13426 normalize and visualize Hi-C data. HiCExplorer facilitates the creation of
13427 contact matrices, correction of contacts, TAD detection, A/B compartments,
13428 merging, reordering or chromosomes, conversion from different formats
13429 including cooler and detection of long-range contacts. Moreover, it allows
13430 the visualization of multiple contact matrices along with other types of data
13431 like genes, compartments, ChIP-seq coverage tracks (and in general any type of
13432 genomic scores), long range contacts and the visualization of viewpoints.")
13433 (license license:gpl3)))
13435 (define-public python-pygenometracks
13437 (name "python-pygenometracks")
13442 (uri (pypi-uri "pyGenomeTracks" version))
13445 "1fws6bqsyy9kj3qiabhkqx4wd4i775gsxnhszqd3zg7w67sc1ic5"))))
13446 (build-system python-build-system)
13448 `(("python-configparser" ,python-configparser)
13449 ("python-future" ,python-future)
13450 ("python-hicexplorer" ,python-hicexplorer)
13451 ("python-intervaltree" ,python-intervaltree)
13452 ("python-matplotlib" ,python-matplotlib)
13453 ("python-numpy" ,python-numpy)
13454 ("python-pybigwig" ,python-pybigwig)))
13456 `(("python-pytest" ,python-pytest)))
13457 (home-page "https://pygenometracks.readthedocs.io")
13458 (synopsis "Program and library to plot beautiful genome browser tracks")
13460 "This package aims to produce high-quality genome browser tracks that
13461 are highly customizable. Currently, it is possible to plot: bigwig, bed (many
13462 options), bedgraph, links (represented as arcs), and Hi-C matrices.
13463 pyGenomeTracks can make plots with or without Hi-C data.")
13464 (license license:gpl3+)))
13466 (define-public python-hic2cool
13468 (name "python-hic2cool")
13473 (uri (pypi-uri "hic2cool" version))
13476 "0xy6mhfns2lzib1kcr6419jjp6pmh0qx8z8na55lmiwn0ds8q9cl"))))
13477 (build-system python-build-system)
13478 (arguments '(#:tests? #f)) ; no tests included
13480 `(("python-cooler" ,python-cooler)))
13481 (home-page "https://github.com/4dn-dcic/hic2cool")
13482 (synopsis "Converter for .hic and .cool files")
13484 "This package provides a converter between @code{.hic} files (from
13485 juicer) and single-resolution or multi-resolution @code{.cool} files (for
13486 cooler). Both @code{hic} and @code{cool} files describe Hi-C contact
13488 (license license:expat)))
13490 (define-public r-pore
13498 (string-append "mirror://sourceforge/rpore/" version
13499 "/poRe_" version ".tar.gz"))
13501 (base32 "0pih9nljbv8g4x8rkk29i7aqq681b782r5s5ynp4nw9yzqnmmksv"))))
13502 (properties `((upstream-name . "poRe")))
13503 (build-system r-build-system)
13505 `(("r-bit64" ,r-bit64)
13506 ("r-data-table" ,r-data-table)
13507 ("r-rhdf5" ,r-rhdf5)
13508 ("r-shiny" ,r-shiny)
13509 ("r-svdialogs" ,r-svdialogs)))
13510 (home-page "https://sourceforge.net/projects/rpore/")
13511 (synopsis "Visualize Nanopore sequencing data")
13513 "This package provides graphical user interfaces to organize and visualize Nanopore
13515 ;; This is free software but the license variant is unclear:
13516 ;; <https://github.com/mw55309/poRe_docs/issues/10>.
13517 (license license:bsd-3)))
13519 (define-public r-xbioc
13520 (let ((revision "1")
13521 (commit "f798c187e376fd1ba27abd559f47bbae7e3e466b"))
13524 (version (git-version "0.1.15" revision commit))
13527 (uri (git-reference
13528 (url "https://github.com/renozao/xbioc.git")
13530 (file-name (git-file-name name version))
13533 "03hffh2f6z71y6l6dqpa5cql3hdaw7zigdi8sm2dzgx379k9rgrr"))))
13534 (build-system r-build-system)
13536 `(("r-annotationdbi" ,r-annotationdbi)
13537 ("r-assertthat" ,r-assertthat)
13538 ("r-biobase" ,r-biobase)
13539 ("r-biocinstaller" ,r-biocinstaller)
13540 ("r-digest" ,r-digest)
13541 ("r-pkgmaker" ,r-pkgmaker)
13543 ("r-reshape2" ,r-reshape2)
13544 ("r-stringr" ,r-stringr)))
13545 (home-page "https://github.com/renozao/xbioc/")
13546 (synopsis "Extra base functions for Bioconductor")
13547 (description "This package provides extra utility functions to perform
13548 common tasks in the analysis of omics data, leveraging and enhancing features
13549 provided by Bioconductor packages.")
13550 (license license:gpl3+))))
13552 (define-public r-cssam
13553 (let ((revision "1")
13554 (commit "9ec58c982fa551af0d80b1a266890d92954833f2"))
13557 (version (git-version "1.4" revision commit))
13560 (uri (git-reference
13561 (url "https://github.com/shenorrLab/csSAM.git")
13563 (file-name (git-file-name name version))
13566 "128syf9v39gk0z3ip000qpsjbg6l1siyq6c8b0hz41dzg5achyb3"))))
13567 (build-system r-build-system)
13569 `(("r-formula" ,r-formula)
13570 ("r-ggplot2" ,r-ggplot2)
13571 ("r-pkgmaker" ,r-pkgmaker)
13573 ("r-rngtools" ,r-rngtools)
13574 ("r-scales" ,r-scales)))
13575 (home-page "https://github.com/shenorrLab/csSAM/")
13576 (synopsis "Cell type-specific statistical analysis of microarray")
13577 (description "This package implements the method csSAM that computes
13578 cell-specific differential expression from measured cell proportions using
13581 (license license:lgpl2.1+))))
13583 (define-public r-bseqsc
13584 (let ((revision "1")
13585 (commit "fef3f3e38dcf3df37103348b5780937982b43b98"))
13588 (version (git-version "1.0" revision commit))
13591 (uri (git-reference
13592 (url "https://github.com/shenorrLab/bseqsc.git")
13594 (file-name (git-file-name name version))
13597 "1prw13wa20f7wlc3gkkls66n1kxz8d28qrb8icfqdwdnnv8w5qg8"))))
13598 (build-system r-build-system)
13600 `(("r-abind" ,r-abind)
13601 ("r-annotationdbi" ,r-annotationdbi)
13602 ("r-biobase" ,r-biobase)
13603 ("r-cssam" ,r-cssam)
13604 ("r-dplyr" ,r-dplyr)
13605 ("r-e1071" ,r-e1071)
13606 ("r-edger" ,r-edger)
13607 ("r-ggplot2" ,r-ggplot2)
13609 ("r-openxlsx" ,r-openxlsx)
13610 ("r-pkgmaker" ,r-pkgmaker)
13612 ("r-preprocesscore" ,r-preprocesscore)
13613 ("r-rngtools" ,r-rngtools)
13614 ("r-scales" ,r-scales)
13615 ("r-stringr" ,r-stringr)
13616 ("r-xbioc" ,r-xbioc)))
13617 (home-page "https://github.com/shenorrLab/bseqsc")
13618 (synopsis "Deconvolution of bulk sequencing experiments using single cell data")
13619 (description "BSeq-sc is a bioinformatics analysis pipeline that
13620 leverages single-cell sequencing data to estimate cell type proportion and
13621 cell type-specific gene expression differences from RNA-seq data from bulk
13622 tissue samples. This is a companion package to the publication \"A
13623 single-cell transcriptomic map of the human and mouse pancreas reveals inter-
13624 and intra-cell population structure.\" Baron et al. Cell Systems (2016)
13625 @url{https://www.ncbi.nlm.nih.gov/pubmed/27667365}.")
13626 (license license:gpl2+))))
13628 (define-public porechop
13629 ;; The recommended way to install is to clone the git repository
13630 ;; https://github.com/rrwick/Porechop#installation
13631 (let ((commit "289d5dca4a5fc327f97b3f8cecb68ecaf1014861")
13635 (version (git-version "0.2.3" revision commit))
13639 (uri (git-reference
13640 (url "https://github.com/rrwick/Porechop.git")
13642 (file-name (git-file-name name version))
13644 (base32 "05ps43gig0d3ia9x5lj84lb00hbsl6ba9n7y7jz927npxbr2ym23"))))
13645 (build-system python-build-system)
13646 (home-page "https://github.com/rrwick/porechop")
13647 (synopsis "Finding, trimming or splitting adapters, in Oxford Nanopore reads")
13649 "The porechop package is a tool for finding and removing adapters from Oxford
13650 Nanopore reads. Adapters on the ends of reads are trimmed off, and when a read
13651 has an adapter in its middle, it is treated as chimeric and chopped into
13652 separate reads. Porechop performs thorough alignments to effectively find
13653 adapters, even at low sequence identity. Porechop also supports demultiplexing
13654 of Nanopore reads that were barcoded with the Native Barcoding Kit, PCR
13655 Barcoding Kit or Rapid Barcoding Kit.")
13656 (license license:gpl3+))))
13658 (define-public poretools
13659 ;; The latest release was in 2016 and the latest commit is from 2017
13660 ;; the recommended way to install is to clone the git repository
13661 ;; https://poretools.readthedocs.io/en/latest/content/installation.html
13662 (let ((commit "e426b1f09e86ac259a00c261c79df91510777407")
13666 (version (git-version "0.6.0" revision commit))
13670 (uri (git-reference
13671 (url "https://github.com/arq5x/poretools.git")
13673 (file-name (git-file-name name version))
13675 (base32 "0bglj833wxpp3cq430p1d3xp085ls221js2y90w7ir2x5ay8l7am"))))
13676 (build-system python-build-system)
13677 ;; requires python >=2.7, <3.0, and the same for python dependencies
13678 (arguments `(#:python ,python-2))
13682 `(("python-dateutil" ,python2-dateutil)
13683 ("python-h5py" ,python2-h5py)
13684 ("python-matplotlib" ,python2-matplotlib)
13685 ("python-pandas" ,python2-pandas)
13686 ("python-seaborn" ,python2-seaborn)))
13687 (home-page "https://poretools.readthedocs.io")
13688 (synopsis "Toolkit for working with nanopore sequencing data")
13690 "The MinION from Oxford Nanopore Technologies is a nanopore sequencer.
13691 This @code{poretools} package is a flexible toolkit for exploring datasets
13692 generated by nanopore sequencing devices for the purposes of quality control and
13693 downstream analysis. Poretools operates directly on the native FAST5, a variant
13694 of the Hierarchical Data Format (HDF5) standard.")
13695 (license license:expat))))
13697 (define-public r-absfiltergsea
13699 (name "r-absfiltergsea")
13704 (uri (cran-uri "AbsFilterGSEA" version))
13706 (base32 "15srxkxsvn38kd5frdrwfdf0ad8gskrd0h01wmdf9hglq8fjrp7w"))))
13707 (properties `((upstream-name . "AbsFilterGSEA")))
13708 (build-system r-build-system)
13710 `(("r-biobase" ,r-biobase)
13711 ("r-deseq" ,r-deseq)
13712 ("r-limma" ,r-limma)
13714 ("r-rcpparmadillo" ,r-rcpparmadillo)))
13715 (home-page "https://cran.r-project.org/web/packages/AbsFilterGSEA/")
13716 (synopsis "Improved false positive control of gene-permuting with absolute filtering")
13718 "This package provides a function that performs gene-permuting of a gene-set
13719 enrichment analysis (GSEA) calculation with or without the absolute filtering.
13720 Without filtering, users can perform (original) two-tailed or one-tailed
13722 (license license:gpl2)))
13724 (define-public jamm
13727 (version "1.0.7.5")
13731 (uri (git-reference
13732 (url "https://github.com/mahmoudibrahim/JAMM.git")
13733 (commit (string-append "JAMMv" version))))
13734 (file-name (git-file-name name version))
13737 "0ls889jcma1ch9h21jjhnkadgszgqj41842hhcjh6cg88f85qf3i"))))
13738 (build-system gnu-build-system)
13740 `(#:tests? #f ; there are none
13742 (modify-phases %standard-phases
13743 (delete 'configure)
13746 (lambda* (#:key inputs outputs #:allow-other-keys)
13747 (let* ((out (assoc-ref outputs "out"))
13748 (libexec (string-append out "/libexec/jamm"))
13749 (bin (string-append out "/bin")))
13750 (substitute* '("JAMM.sh"
13751 "SignalGenerator.sh")
13753 (string-append "sPath=\"" libexec "\"\n")))
13754 (for-each (lambda (file)
13755 (install-file file libexec))
13756 (list "bincalculator.r"
13768 (chmod script #o555)
13769 (install-file script bin)
13770 (wrap-program (string-append bin "/" script)
13771 `("PATH" ":" prefix
13772 (,(string-append (assoc-ref inputs "coreutils") "/bin")
13773 ,(string-append (assoc-ref inputs "gawk") "/bin")
13774 ,(string-append (assoc-ref inputs "perl") "/bin")
13775 ,(string-append (assoc-ref inputs "r-minimal") "/bin")))
13776 `("PERL5LIB" ":" prefix (,(getenv "PERL5LIB")))
13777 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
13778 (list "JAMM.sh" "SignalGenerator.sh")))
13782 ("coreutils" ,coreutils)
13785 ("r-minimal" ,r-minimal)
13786 ;;("r-parallel" ,r-parallel)
13787 ("r-signal" ,r-signal)
13788 ("r-mclust" ,r-mclust)))
13789 (home-page "https://github.com/mahmoudibrahim/JAMM")
13790 (synopsis "Peak finder for NGS datasets")
13792 "JAMM is a peak finder for next generation sequencing datasets (ChIP-Seq,
13793 ATAC-Seq, DNase-Seq, etc.) that can integrate replicates and assign peak
13794 boundaries accurately. JAMM is applicable to both broad and narrow
13796 (license license:gpl3+)))
13798 (define-public ngless
13805 (uri (git-reference
13806 (url "https://gitlab.com/ngless/ngless.git")
13807 (commit (string-append "v" version))))
13808 (file-name (git-file-name name version))
13811 "0mc2gi7h4lx74zylvyp76mvc0w6706j858ii9vlgzqsw6acpr117"))))
13812 (build-system haskell-build-system)
13814 `(#:haddock? #f ; The haddock phase fails with: NGLess/CmdArgs.hs:20:1:
13815 ; error: parse error on input import
13816 ; import Options.Applicative
13818 (modify-phases %standard-phases
13819 (add-after 'unpack 'create-cabal-file
13820 (lambda _ (invoke "hpack") #t))
13821 ;; These tools are expected to be installed alongside ngless.
13822 (add-after 'install 'link-tools
13823 (lambda* (#:key inputs outputs #:allow-other-keys)
13824 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
13825 (symlink (string-append (assoc-ref inputs "prodigal")
13827 (string-append bin "ngless-" ,version "-prodigal"))
13828 (symlink (string-append (assoc-ref inputs "minimap2")
13830 (string-append bin "ngless-" ,version "-minimap2"))
13831 (symlink (string-append (assoc-ref inputs "samtools")
13833 (string-append bin "ngless-" ,version "-samtools"))
13834 (symlink (string-append (assoc-ref inputs "bwa")
13836 (string-append bin "ngless-" ,version "-bwa"))
13839 `(("prodigal" ,prodigal)
13841 ("samtools" ,samtools)
13842 ("minimap2" ,minimap2)
13843 ("ghc-aeson" ,ghc-aeson)
13844 ("ghc-ansi-terminal" ,ghc-ansi-terminal)
13845 ("ghc-async" ,ghc-async)
13846 ("ghc-atomic-write" ,ghc-atomic-write)
13847 ("ghc-bytestring-lexing" ,ghc-bytestring-lexing)
13848 ("ghc-chart" ,ghc-chart)
13849 ("ghc-chart-cairo" ,ghc-chart-cairo)
13850 ("ghc-conduit" ,ghc-conduit)
13851 ("ghc-conduit-algorithms" ,ghc-conduit-algorithms)
13852 ("ghc-conduit-combinators" ,ghc-conduit-combinators)
13853 ("ghc-conduit-extra" ,ghc-conduit-extra)
13854 ("ghc-configurator" ,ghc-configurator)
13855 ("ghc-convertible" ,ghc-convertible)
13856 ("ghc-data-default" ,ghc-data-default)
13857 ("ghc-double-conversion" ,ghc-double-conversion)
13858 ("ghc-edit-distance" ,ghc-edit-distance)
13859 ("ghc-either" ,ghc-either)
13860 ("ghc-errors" ,ghc-errors)
13861 ("ghc-extra" ,ghc-extra)
13862 ("ghc-filemanip" ,ghc-filemanip)
13863 ("ghc-file-embed" ,ghc-file-embed)
13864 ("ghc-gitrev" ,ghc-gitrev)
13865 ("ghc-hashtables" ,ghc-hashtables)
13866 ("ghc-http-conduit" ,ghc-http-conduit)
13867 ("ghc-inline-c" ,ghc-inline-c)
13868 ("ghc-inline-c-cpp" ,ghc-inline-c-cpp)
13869 ("ghc-intervalmap" ,ghc-intervalmap)
13870 ("ghc-missingh" ,ghc-missingh)
13871 ("ghc-optparse-applicative" ,ghc-optparse-applicative)
13872 ("ghc-parsec" ,ghc-parsec)
13873 ("ghc-regex" ,ghc-regex)
13874 ("ghc-safe" ,ghc-safe)
13875 ("ghc-safeio" ,ghc-safeio)
13876 ("ghc-strict" ,ghc-strict)
13877 ("ghc-tar" ,ghc-tar)
13878 ("ghc-text" ,ghc-text)
13879 ("ghc-unliftio" ,ghc-unliftio)
13880 ("ghc-unliftio-core" ,ghc-unliftio-core)
13881 ("ghc-vector" ,ghc-vector)
13882 ("ghc-yaml" ,ghc-yaml)
13883 ("ghc-zlib" ,ghc-zlib)))
13886 ("r-hdf5r" ,r-hdf5r)
13887 ("r-iterators" ,r-iterators)
13888 ("r-itertools" ,r-itertools)
13889 ("r-matrix" ,r-matrix)))
13891 `(("ghc-hpack" ,ghc-hpack)
13892 ("ghc-quickcheck" ,ghc-quickcheck)
13893 ("ghc-test-framework" ,ghc-test-framework)
13894 ("ghc-test-framework-hunit",ghc-test-framework-hunit)
13895 ("ghc-test-framework-quickcheck2" ,ghc-test-framework-quickcheck2)
13896 ("ghc-test-framework-th" ,ghc-test-framework-th)))
13897 (home-page "https://gitlab.com/ngless/ngless")
13898 (synopsis "DSL for processing next-generation sequencing data")
13899 (description "Ngless is a domain-specific language for
13900 @dfn{next-generation sequencing} (NGS) data processing.")
13901 (license license:expat)))
13903 (define-public filtlong
13904 ;; The recommended way to install is to clone the git repository
13905 ;; https://github.com/rrwick/Filtlong#installation
13906 ;; and the lastest release is more than nine months old
13907 (let ((commit "d1bb46dfe8bc7efe6257b5ce222c04bfe8aedaab")
13911 (version (git-version "0.2.0" revision commit))
13915 (uri (git-reference
13916 (url "https://github.com/rrwick/Filtlong.git")
13918 (file-name (git-file-name name version))
13920 (base32 "1xr92r820x8qlkcr3b57iw223yq8vjgyi42jr79w2xgw47qzr575"))))
13921 (build-system gnu-build-system)
13923 `(#:tests? #f ; no check target
13925 (modify-phases %standard-phases
13926 (delete 'configure)
13928 (lambda* (#:key outputs #:allow-other-keys)
13929 (let* ((out (assoc-ref outputs "out"))
13930 (bin (string-append out "/bin"))
13931 (scripts (string-append out "/share/filtlong/scripts")))
13932 (install-file "bin/filtlong" bin)
13933 (install-file "scripts/histogram.py" scripts)
13934 (install-file "scripts/read_info_histograms.sh" scripts))
13936 (add-after 'install 'wrap-program
13937 (lambda* (#:key inputs outputs #:allow-other-keys)
13938 (let* ((out (assoc-ref outputs "out"))
13939 (path (getenv "PYTHONPATH")))
13940 (wrap-program (string-append out
13941 "/share/filtlong/scripts/histogram.py")
13942 `("PYTHONPATH" ":" prefix (,path))))
13944 (add-before 'check 'patch-tests
13946 (substitute* "scripts/read_info_histograms.sh"
13947 (("awk") (which "gawk")))
13950 `(("gawk" ,gawk) ;for read_info_histograms.sh
13951 ("python" ,python-2) ;required for histogram.py
13953 (home-page "https://github.com/rrwick/Filtlong/")
13954 (synopsis "Tool for quality filtering of Nanopore and PacBio data")
13956 "The Filtlong package is a tool for filtering long reads by quality.
13957 It can take a set of long reads and produce a smaller, better subset. It uses
13958 both read length (longer is better) and read identity (higher is better) when
13959 choosing which reads pass the filter.")
13960 (license (list license:gpl3 ;filtlong
13961 license:asl2.0))))) ;histogram.py
13963 (define-public nanopolish
13964 ;; The recommended way to install is to clone the git repository
13965 ;; <https://github.com/jts/nanopolish#installing-a-particular-release>.
13966 ;; Also, the differences between release and current version seem to be
13968 (let ((commit "50e8b5cc62f9b46f5445f5c5e8c5ab7263ea6d9d")
13971 (name "nanopolish")
13972 (version (git-version "0.10.2" revision commit))
13976 (uri (git-reference
13977 (url "https://github.com/jts/nanopolish.git")
13980 (file-name (git-file-name name version))
13982 (base32 "09j5gz57yr9i34a27vbl72i4g8syv2zzgmsfyjq02yshmnrvkjs6"))))
13983 (build-system gnu-build-system)
13986 `("HDF5=noinstall" "EIGEN=noinstall" "HTS=noinstall" "CC=gcc")
13987 #:tests? #f ; no check target
13989 (modify-phases %standard-phases
13990 (add-after 'unpack 'find-eigen
13991 (lambda* (#:key inputs #:allow-other-keys)
13993 (string-append (assoc-ref inputs "eigen")
13994 "/include/eigen3"))
13996 (delete 'configure)
13998 (lambda* (#:key outputs #:allow-other-keys)
13999 (let* ((out (assoc-ref outputs "out"))
14000 (bin (string-append out "/bin"))
14001 (scripts (string-append out "/share/nanopolish/scripts")))
14003 (install-file "nanopolish" bin)
14004 (for-each (lambda (file) (install-file file scripts))
14005 (find-files "scripts" ".*"))
14007 (add-after 'install 'wrap-programs
14008 (lambda* (#:key outputs #:allow-other-keys)
14009 (for-each (lambda (file)
14010 (wrap-program file `("PYTHONPATH" ":" prefix (,path))))
14011 (find-files "/share/nanopolish/scripts" "\\.py"))
14012 (for-each (lambda (file)
14013 (wrap-program file `("PERL5LIB" ":" prefix (,path))))
14014 (find-files "/share/nanopolish/scripts" "\\.pl"))
14022 ("python-biopython" ,python-biopython)
14023 ("python-numpy" ,python-numpy)
14024 ("python-pysam" ,python-pysam)
14025 ("python-scikit-learn" , python-scikit-learn)
14026 ("python-scipy" ,python-scipy)
14028 (home-page "https://github.com/jts/nanopolish")
14029 (synopsis "Signal-level analysis of Oxford Nanopore sequencing data")
14031 "This package analyses the Oxford Nanopore sequencing data at signal-level.
14032 Nanopolish can calculate an improved consensus sequence for a draft genome
14033 assembly, detect base modifications, call SNPs (Single nucleotide
14034 polymorphisms) and indels with respect to a reference genome and more.")
14035 (license license:expat))))
14037 (define-public cnvkit
14044 (uri (git-reference
14045 (url "https://github.com/etal/cnvkit.git")
14046 (commit (string-append "v" version))))
14047 (file-name (git-file-name name version))
14049 (base32 "0g2f78k68yglmj4fsfmgs8idqv3di9aj53fg0ld0hqljg8chhh82"))))
14050 (build-system python-build-system)
14052 `(("python-biopython" ,python-biopython)
14053 ("python-future" ,python-future)
14054 ("python-matplotlib" ,python-matplotlib)
14055 ("python-numpy" ,python-numpy)
14056 ("python-reportlab" ,python-reportlab)
14057 ("python-pandas" ,python-pandas)
14058 ("python-pysam" ,python-pysam)
14059 ("python-pyfaidx" ,python-pyfaidx)
14060 ("python-scipy" ,python-scipy)
14062 ("r-dnacopy" ,r-dnacopy)))
14063 (home-page "https://cnvkit.readthedocs.org/")
14064 (synopsis "Copy number variant detection from targeted DNA sequencing")
14066 "CNVkit is a Python library and command-line software toolkit to infer
14067 and visualize copy number from high-throughput DNA sequencing data. It is
14068 designed for use with hybrid capture, including both whole-exome and custom
14069 target panels, and short-read sequencing platforms such as Illumina and Ion
14071 (license license:asl2.0)))
14073 (define-public python-pyfit-sne
14075 (name "python-pyfit-sne")
14080 (uri (git-reference
14081 (url "https://github.com/KlugerLab/pyFIt-SNE.git")
14083 (file-name (git-file-name name version))
14085 (base32 "13wh3qkzs56azmmgnxib6xfr29g7xh09sxylzjpni5j0pp0rc5qw"))))
14086 (build-system python-build-system)
14088 `(("python-numpy" ,python-numpy)))
14092 `(("python-cython" ,python-cython)))
14093 (home-page "https://github.com/KlugerLab/pyFIt-SNE")
14094 (synopsis "FFT-accelerated Interpolation-based t-SNE")
14096 "t-Stochastic Neighborhood Embedding (t-SNE) is a highly successful
14097 method for dimensionality reduction and visualization of high dimensional
14098 datasets. A popular implementation of t-SNE uses the Barnes-Hut algorithm to
14099 approximate the gradient at each iteration of gradient descent. This package
14100 is a Cython wrapper for FIt-SNE.")
14101 (license license:bsd-4)))
14103 (define-public velvet
14109 (uri (string-append "https://www.ebi.ac.uk/~zerbino/velvet/"
14110 "velvet_" version ".tgz"))
14113 "0h3njwy66p6bx14r3ar1byb0ccaxmxka4c65rn4iybyiqa4d8kc8"))
14114 ;; Delete bundled libraries
14115 (modules '((guix build utils)))
14118 (delete-file "Manual.pdf")
14119 (delete-file-recursively "third-party")
14121 (build-system gnu-build-system)
14123 `(#:make-flags '("OPENMP=t")
14124 #:test-target "test"
14126 (modify-phases %standard-phases
14127 (delete 'configure)
14128 (add-after 'unpack 'fix-zlib-include
14130 (substitute* "src/binarySequences.c"
14131 (("../third-party/zlib-1.2.3/zlib.h") "zlib.h"))
14134 (lambda* (#:key outputs #:allow-other-keys)
14135 (let* ((out (assoc-ref outputs "out"))
14136 (bin (string-append out "/bin"))
14137 (doc (string-append out "/share/doc/velvet")))
14140 (install-file "velveth" bin)
14141 (install-file "velvetg" bin)
14142 (install-file "Manual.pdf" doc)
14143 (install-file "Columbus_manual.pdf" doc)
14146 `(("openmpi" ,openmpi)
14149 `(("texlive" ,(texlive-union (list texlive-latex-graphics
14150 texlive-latex-hyperref)))))
14151 (home-page "https://www.ebi.ac.uk/~zerbino/velvet/")
14152 (synopsis "Nucleic acid sequence assembler for very short reads")
14154 "Velvet is a de novo genomic assembler specially designed for short read
14155 sequencing technologies, such as Solexa or 454. Velvet currently takes in
14156 short read sequences, removes errors then produces high quality unique
14157 contigs. It then uses paired read information, if available, to retrieve the
14158 repeated areas between contigs.")
14159 (license license:gpl2+)))