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"))
1775 (modify-phases %standard-phases
1776 ;; No "configure" script
1778 ;; Remove sources of non-determinism
1779 (add-after 'unpack 'be-timeless
1781 (substitute* "cdhit-utility.c++"
1782 ((" \\(built on \" __DATE__ \"\\)") ""))
1783 (substitute* "cdhit-common.c++"
1784 (("__DATE__") "\"0\"")
1785 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
1787 ;; The "install" target does not create the target directory.
1788 (add-before 'install 'create-target-dir
1789 (lambda* (#:key outputs #:allow-other-keys)
1790 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
1794 (home-page "http://weizhongli-lab.org/cd-hit/")
1795 (synopsis "Cluster and compare protein or nucleotide sequences")
1797 "CD-HIT is a program for clustering and comparing protein or nucleotide
1798 sequences. CD-HIT is designed to be fast and handle extremely large
1800 ;; The manual says: "It can be copied under the GNU General Public License
1801 ;; version 2 (GPLv2)."
1802 (license license:gpl2)))
1804 (define-public clipper
1811 (url "https://github.com/YeoLab/clipper.git")
1813 (file-name (git-file-name name version))
1816 "0fja1rj84wp9vpj8rxpj3n8zqzcqq454m904yp9as1w4phccirjb"))
1817 (modules '((guix build utils)))
1820 ;; remove unnecessary setup dependency
1821 (substitute* "setup.py"
1822 (("setup_requires = .*") ""))
1824 (build-system python-build-system)
1826 `(#:python ,python-2 ; only Python 2 is supported
1828 (modify-phases %standard-phases
1829 ;; This is fixed in upstream commit
1830 ;; f6c2990198f906bf97730d95695b4bd5a6d01ddb.
1831 (add-after 'unpack 'fix-typo
1833 (substitute* "clipper/src/readsToWiggle.pyx"
1837 `(("htseq" ,python2-htseq)
1838 ("python-pybedtools" ,python2-pybedtools)
1839 ("python-cython" ,python2-cython)
1840 ("python-scikit-learn" ,python2-scikit-learn)
1841 ("python-matplotlib" ,python2-matplotlib)
1842 ("python-pandas" ,python2-pandas)
1843 ("python-pysam" ,python2-pysam)
1844 ("python-numpy" ,python2-numpy)
1845 ("python-scipy" ,python2-scipy)))
1847 `(("python-mock" ,python2-mock) ; for tests
1848 ("python-nose" ,python2-nose) ; for tests
1849 ("python-pytz" ,python2-pytz))) ; for tests
1850 (home-page "https://github.com/YeoLab/clipper")
1851 (synopsis "CLIP peak enrichment recognition")
1853 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
1854 (license license:gpl2)))
1856 (define-public codingquarry
1858 (name "codingquarry")
1863 "mirror://sourceforge/codingquarry/CodingQuarry_v"
1867 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
1868 (build-system gnu-build-system)
1870 '(#:tests? #f ; no "check" target
1872 (modify-phases %standard-phases
1875 (lambda* (#:key outputs #:allow-other-keys)
1876 (let* ((out (assoc-ref outputs "out"))
1877 (bin (string-append out "/bin"))
1878 (doc (string-append out "/share/doc/codingquarry")))
1879 (install-file "INSTRUCTIONS.pdf" doc)
1880 (copy-recursively "QuarryFiles"
1881 (string-append out "/QuarryFiles"))
1882 (install-file "CodingQuarry" bin)
1883 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin))
1885 (inputs `(("openmpi" ,openmpi)))
1886 (native-search-paths
1887 (list (search-path-specification
1888 (variable "QUARRY_PATH")
1889 (files '("QuarryFiles")))))
1890 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
1891 (synopsis "Fungal gene predictor")
1892 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
1893 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
1894 (home-page "https://sourceforge.net/projects/codingquarry/")
1895 (license license:gpl3+)))
1897 (define-public couger
1904 "http://couger.oit.duke.edu/static/assets/COUGER"
1908 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
1909 (build-system gnu-build-system)
1913 (modify-phases %standard-phases
1918 (lambda* (#:key outputs #:allow-other-keys)
1919 (let* ((out (assoc-ref outputs "out"))
1920 (bin (string-append out "/bin")))
1921 (copy-recursively "src" (string-append out "/src"))
1923 ;; Add "src" directory to module lookup path.
1924 (substitute* "couger"
1926 (string-append "import sys\nsys.path.append(\""
1927 out "\")\nfrom argparse")))
1928 (install-file "couger" bin))
1931 'install 'wrap-program
1932 (lambda* (#:key inputs outputs #:allow-other-keys)
1933 ;; Make sure 'couger' runs with the correct PYTHONPATH.
1934 (let* ((out (assoc-ref outputs "out"))
1935 (path (getenv "PYTHONPATH")))
1936 (wrap-program (string-append out "/bin/couger")
1937 `("PYTHONPATH" ":" prefix (,path))))
1940 `(("python" ,python-2)
1941 ("python2-pillow" ,python2-pillow)
1942 ("python2-numpy" ,python2-numpy)
1943 ("python2-scipy" ,python2-scipy)
1944 ("python2-matplotlib" ,python2-matplotlib)))
1946 `(("r-minimal" ,r-minimal)
1948 ("randomjungle" ,randomjungle)))
1950 `(("unzip" ,unzip)))
1951 (home-page "http://couger.oit.duke.edu")
1952 (synopsis "Identify co-factors in sets of genomic regions")
1954 "COUGER can be applied to any two sets of genomic regions bound by
1955 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
1956 putative co-factors that provide specificity to each TF. The framework
1957 determines the genomic targets uniquely-bound by each TF, and identifies a
1958 small set of co-factors that best explain the in vivo binding differences
1959 between the two TFs.
1961 COUGER uses classification algorithms (support vector machines and random
1962 forests) with features that reflect the DNA binding specificities of putative
1963 co-factors. The features are generated either from high-throughput TF-DNA
1964 binding data (from protein binding microarray experiments), or from large
1965 collections of DNA motifs.")
1966 (license license:gpl3+)))
1968 (define-public clustal-omega
1970 (name "clustal-omega")
1974 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
1978 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
1979 (build-system gnu-build-system)
1981 `(("argtable" ,argtable)))
1982 (home-page "http://www.clustal.org/omega/")
1983 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
1985 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
1986 program for protein and DNA/RNA. It produces high quality MSAs and is capable
1987 of handling data-sets of hundreds of thousands of sequences in reasonable
1989 (license license:gpl2+)))
1991 (define-public crossmap
1997 (uri (pypi-uri "CrossMap" version))
2000 "1byhclrqnqpvc1rqkfh4jwj6yhn0x9y7jk47i0qcjlhk0pjkw92p"))))
2001 (build-system python-build-system)
2002 (arguments `(#:python ,python-2))
2004 `(("python-bx-python" ,python2-bx-python)
2005 ("python-numpy" ,python2-numpy)
2006 ("python-pysam" ,python2-pysam)
2009 `(("python-cython" ,python2-cython)
2010 ("python-nose" ,python2-nose)))
2011 (home-page "http://crossmap.sourceforge.net/")
2012 (synopsis "Convert genome coordinates between assemblies")
2014 "CrossMap is a program for conversion of genome coordinates or annotation
2015 files between different genome assemblies. It supports most commonly used
2016 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
2017 (license license:gpl2+)))
2019 (define-public python-dnaio
2021 (name "python-dnaio")
2026 (uri (pypi-uri "dnaio" version))
2029 "0f16m7hdlm0fz1n7y5asy0v9ghyrq17ni1p9iybq22ddzyd49r27"))))
2030 (build-system python-build-system)
2032 `(("python-cython" ,python-cython)
2033 ("python-pytest" ,python-pytest)
2034 ("python-xopen" ,python-xopen)))
2035 (home-page "https://github.com/marcelm/dnaio/")
2036 (synopsis "Read FASTA and FASTQ files efficiently")
2038 "dnaio is a Python library for fast parsing of FASTQ and also FASTA
2039 files. The code was previously part of the cutadapt tool.")
2040 (license license:expat)))
2042 (define-public cutadapt
2049 (url "https://github.com/marcelm/cutadapt.git")
2050 (commit (string-append "v" version))))
2051 (file-name (git-file-name name version))
2054 "08bbfwyc0kvcd95jf2s95xiv9s3cbsxm39ydl0qck3fw3cviwxpg"))))
2055 (build-system python-build-system)
2057 `(("python-dnaio" ,python-dnaio)
2058 ("python-xopen" ,python-xopen)))
2060 `(("python-cython" ,python-cython)
2061 ("python-pytest" ,python-pytest)))
2062 (home-page "https://cutadapt.readthedocs.io/en/stable/")
2063 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
2065 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
2066 other types of unwanted sequence from high-throughput sequencing reads.")
2067 (license license:expat)))
2069 (define-public libbigwig
2076 (url "https://github.com/dpryan79/libBigWig.git")
2078 (file-name (string-append name "-" version "-checkout"))
2081 "0h2smg24v5srdcqzrmz2g23cmlp4va465mgx8r2z571sfz8pv454"))))
2082 (build-system gnu-build-system)
2084 `(#:test-target "test"
2085 #:tests? #f ; tests require access to the web
2088 (string-append "prefix=" (assoc-ref %outputs "out")))
2090 (modify-phases %standard-phases
2091 (delete 'configure))))
2096 `(("doxygen" ,doxygen)
2098 ("python" ,python-2)))
2099 (home-page "https://github.com/dpryan79/libBigWig")
2100 (synopsis "C library for handling bigWig files")
2102 "This package provides a C library for parsing local and remote BigWig
2104 (license license:expat)))
2106 (define-public python-pybigwig
2108 (name "python-pybigwig")
2112 (uri (pypi-uri "pyBigWig" version))
2115 "00w4kfnm2c5l7wdwr2nj1z5djv8kzgf7h1zhsgv6njff1rwr26g0"))
2116 (modules '((guix build utils)))
2119 ;; Delete bundled libBigWig sources
2120 (delete-file-recursively "libBigWig")
2122 (build-system python-build-system)
2125 (modify-phases %standard-phases
2126 (add-after 'unpack 'link-with-libBigWig
2127 (lambda* (#:key inputs #:allow-other-keys)
2128 (substitute* "setup.py"
2129 (("libs=\\[") "libs=[\"BigWig\", "))
2132 `(("python-numpy" ,python-numpy)))
2134 `(("libbigwig" ,libbigwig)
2137 (home-page "https://github.com/dpryan79/pyBigWig")
2138 (synopsis "Access bigWig files in Python using libBigWig")
2140 "This package provides Python bindings to the libBigWig library for
2141 accessing bigWig files.")
2142 (license license:expat)))
2144 (define-public python2-pybigwig
2145 (package-with-python2 python-pybigwig))
2147 (define-public python-dendropy
2149 (name "python-dendropy")
2154 ;; Source from GitHub so that tests are included.
2156 (url "https://github.com/jeetsukumaran/DendroPy.git")
2157 (commit (string-append "v" version))))
2158 (file-name (git-file-name name version))
2161 "097hfyv2kaf4x92i4rjx0paw2cncxap48qivv8zxng4z7nhid0x9"))))
2162 (build-system python-build-system)
2163 (home-page "http://packages.python.org/DendroPy/")
2164 (synopsis "Library for phylogenetics and phylogenetic computing")
2166 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
2167 writing, simulation, processing and manipulation of phylogenetic
2168 trees (phylogenies) and characters.")
2169 (license license:bsd-3)))
2171 (define-public python2-dendropy
2172 (let ((base (package-with-python2 python-dendropy)))
2177 (modify-phases %standard-phases
2178 (add-after 'unpack 'remove-failing-test
2180 ;; This test fails when the full test suite is run, as documented
2181 ;; at https://github.com/jeetsukumaran/DendroPy/issues/74
2182 (substitute* "tests/test_dataio_nexml_reader_tree_list.py"
2183 (("test_collection_comments_and_annotations")
2184 "do_not_test_collection_comments_and_annotations"))
2186 ,@(package-arguments base))))))
2188 (define-public python-py2bit
2190 (name "python-py2bit")
2195 (uri (pypi-uri "py2bit" version))
2198 "1vw2nvw1yrl7ikkqsqs1pg239yr5nspvd969r1x9arms1k25a1a5"))))
2199 (build-system python-build-system)
2200 (home-page "https://github.com/dpryan79/py2bit")
2201 (synopsis "Access 2bit files using lib2bit")
2203 "This package provides Python bindings for lib2bit to access 2bit files
2205 (license license:expat)))
2207 (define-public deeptools
2214 (url "https://github.com/deeptools/deepTools.git")
2216 (file-name (git-file-name name version))
2219 "1vggnf52g6q2vifdl4cyi7s2fnfqq0ky2zrkj5zv2qfzsc3p3siw"))))
2220 (build-system python-build-system)
2223 (modify-phases %standard-phases
2224 ;; This phase fails, but it's not needed.
2225 (delete 'reset-gzip-timestamps))))
2227 `(("python-plotly" ,python-plotly)
2228 ("python-scipy" ,python-scipy)
2229 ("python-numpy" ,python-numpy)
2230 ("python-numpydoc" ,python-numpydoc)
2231 ("python-matplotlib" ,python-matplotlib)
2232 ("python-pysam" ,python-pysam)
2233 ("python-py2bit" ,python-py2bit)
2234 ("python-pybigwig" ,python-pybigwig)))
2236 `(("python-mock" ,python-mock) ;for tests
2237 ("python-nose" ,python-nose) ;for tests
2238 ("python-pytz" ,python-pytz))) ;for tests
2239 (home-page "https://github.com/deeptools/deepTools")
2240 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2242 "DeepTools addresses the challenge of handling the large amounts of data
2243 that are now routinely generated from DNA sequencing centers. To do so,
2244 deepTools contains useful modules to process the mapped reads data to create
2245 coverage files in standard bedGraph and bigWig file formats. By doing so,
2246 deepTools allows the creation of normalized coverage files or the comparison
2247 between two files (for example, treatment and control). Finally, using such
2248 normalized and standardized files, multiple visualizations can be created to
2249 identify enrichments with functional annotations of the genome.")
2250 (license license:gpl3+)))
2252 (define-public delly
2259 (url "https://github.com/dellytools/delly.git")
2260 (commit (string-append "v" version))))
2261 (file-name (git-file-name name version))
2263 (base32 "034jqsxswy9gqdh2zkgc1js99qkv75ks4xvzgmh0284sraagv61z"))
2264 (modules '((guix build utils)))
2267 (delete-file-recursively "src/htslib")
2269 (build-system gnu-build-system)
2271 `(#:tests? #f ; There are no tests to run.
2273 (list "PARALLEL=1" ; Allow parallel execution at run-time.
2274 (string-append "prefix=" (assoc-ref %outputs "out")))
2276 (modify-phases %standard-phases
2277 (delete 'configure) ; There is no configure phase.
2278 (add-after 'install 'install-templates
2279 (lambda* (#:key outputs #:allow-other-keys)
2280 (let ((templates (string-append (assoc-ref outputs "out")
2281 "/share/delly/templates")))
2283 (copy-recursively "excludeTemplates" templates)
2290 (home-page "https://github.com/dellytools/delly")
2291 (synopsis "Integrated structural variant prediction method")
2292 (description "Delly is an integrated structural variant prediction method
2293 that can discover and genotype deletions, tandem duplications, inversions and
2294 translocations at single-nucleotide resolution in short-read massively parallel
2295 sequencing data. It uses paired-ends and split-reads to sensitively and
2296 accurately delineate genomic rearrangements throughout the genome.")
2297 (license license:gpl3+)))
2299 (define-public diamond
2306 (url "https://github.com/bbuchfink/diamond.git")
2307 (commit (string-append "v" version))))
2308 (file-name (git-file-name name version))
2311 "0bky78v79g3wmdpsd706cscckgw1v09fg8vdd0z8z0d5b97aj9zl"))))
2312 (build-system cmake-build-system)
2314 '(#:tests? #f ; no "check" target
2316 (modify-phases %standard-phases
2317 (add-after 'unpack 'remove-native-compilation
2319 (substitute* "CMakeLists.txt" (("-march=native") ""))
2323 (home-page "https://github.com/bbuchfink/diamond")
2324 (synopsis "Accelerated BLAST compatible local sequence aligner")
2326 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2327 translated DNA query sequences against a protein reference database (BLASTP
2328 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2329 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2330 data and settings.")
2331 (license license:agpl3+)))
2333 (define-public discrover
2341 (url "https://github.com/maaskola/discrover.git")
2343 (file-name (git-file-name name version))
2346 "173fwi2vb6a5kp406hm3jj6j7v4whww796f2qcygp4rpvamh307y"))))
2347 (build-system cmake-build-system)
2349 `(#:tests? #f ; there are no tests
2351 (modify-phases %standard-phases
2352 (add-after 'unpack 'fix-latex-errors
2354 (with-fluids ((%default-port-encoding #f))
2355 (substitute* "doc/references.bib"
2356 (("\\{S\\}illanp[^,]+,")
2357 "{S}illanp{\\\"a}{\\\"a},")))
2358 ;; XXX: I just can't get pdflatex to not complain about these
2359 ;; characters. They end up in the manual via the generated
2360 ;; discrover-cli-help.txt.
2361 (substitute* "src/hmm/cli.cpp"
2365 ;; This seems to be a syntax error.
2366 (substitute* "doc/discrover-manual.tex"
2367 (("theverbbox\\[t\\]") "theverbbox"))
2369 (add-after 'unpack 'add-missing-includes
2371 (substitute* "src/executioninformation.hpp"
2372 (("#define EXECUTIONINFORMATION_HPP" line)
2373 (string-append line "\n#include <random>")))
2374 (substitute* "src/plasma/fasta.hpp"
2375 (("#define FASTA_HPP" line)
2376 (string-append line "\n#include <random>")))
2378 ;; FIXME: this is needed because we're using texlive-union, which
2379 ;; doesn't handle fonts correctly. It expects to be able to generate
2380 ;; fonts in the home directory.
2381 (add-before 'build 'setenv-HOME
2382 (lambda _ (setenv "HOME" "/tmp") #t)))))
2386 ("rmath-standalone" ,rmath-standalone)))
2388 `(("texlive" ,(texlive-union (list texlive-fonts-cm
2389 texlive-fonts-amsfonts
2392 texlive-latex-examplep
2393 texlive-latex-hyperref
2395 texlive-latex-natbib
2396 texlive-bibtex ; style files used by natbib
2397 texlive-latex-pgf ; tikz
2398 texlive-latex-verbatimbox)))
2399 ("imagemagick" ,imagemagick)))
2400 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2401 (synopsis "Discover discriminative nucleotide sequence motifs")
2402 (description "Discrover is a motif discovery method to find binding sites
2403 of nucleic acid binding proteins.")
2404 (license license:gpl3+)))
2406 (define-public eigensoft
2414 (url "https://github.com/DReichLab/EIG.git")
2415 (commit (string-append "v" version))))
2416 (file-name (git-file-name name version))
2419 "1c141fqvhnzibmnf22sv23vbmzm20kjjyrib44cfh75wyndp2d9k"))
2420 (modules '((guix build utils)))
2421 ;; Remove pre-built binaries.
2423 (delete-file-recursively "bin")
2426 (build-system gnu-build-system)
2428 `(#:tests? #f ; There are no tests.
2429 #:make-flags '("CC=gcc")
2431 (modify-phases %standard-phases
2432 ;; There is no configure phase, but the Makefile is in a
2435 (lambda _ (chdir "src") #t))
2436 ;; The provided install target only copies executables to
2437 ;; the "bin" directory in the build root.
2438 (add-after 'install 'actually-install
2439 (lambda* (#:key outputs #:allow-other-keys)
2440 (let* ((out (assoc-ref outputs "out"))
2441 (bin (string-append out "/bin")))
2442 (for-each (lambda (file)
2443 (install-file file bin))
2444 (find-files "../bin" ".*"))
2449 ("openblas" ,openblas)
2451 ("gfortran" ,gfortran "lib")))
2452 (home-page "https://github.com/DReichLab/EIG")
2453 (synopsis "Tools for population genetics")
2454 (description "The EIGENSOFT package provides tools for population
2455 genetics and stratification correction. EIGENSOFT implements methods commonly
2456 used in population genetics analyses such as PCA, computation of Tracy-Widom
2457 statistics, and finding related individuals in structured populations. It
2458 comes with a built-in plotting script and supports multiple file formats and
2459 quantitative phenotypes.")
2460 ;; The license of the eigensoft tools is Expat, but since it's
2461 ;; linking with the GNU Scientific Library (GSL) the effective
2462 ;; license is the GPL.
2463 (license license:gpl3+)))
2465 (define-public edirect
2468 (version "10.2.20181018")
2471 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect"
2472 "/versions/" version
2473 "/edirect-" version ".tar.gz"))
2476 "091f4aigzpbqih6h82nq566gkp3y07i72yqndmqskfgar1vwgci7"))))
2477 (build-system perl-build-system)
2480 (modify-phases %standard-phases
2483 (delete 'check) ; simple check after install
2485 (lambda* (#:key outputs #:allow-other-keys)
2486 (install-file "edirect.pl"
2487 (string-append (assoc-ref outputs "out") "/bin"))
2489 (add-after 'install 'wrap-program
2490 (lambda* (#:key outputs #:allow-other-keys)
2491 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2492 (let* ((out (assoc-ref outputs "out"))
2493 (path (getenv "PERL5LIB")))
2494 (wrap-program (string-append out "/bin/edirect.pl")
2495 `("PERL5LIB" ":" prefix (,path))))
2497 (add-after 'wrap-program 'check
2498 (lambda* (#:key outputs #:allow-other-keys)
2499 (invoke (string-append (assoc-ref outputs "out")
2504 `(("perl-html-parser" ,perl-html-parser)
2505 ("perl-encode-locale" ,perl-encode-locale)
2506 ("perl-file-listing" ,perl-file-listing)
2507 ("perl-html-tagset" ,perl-html-tagset)
2508 ("perl-html-tree" ,perl-html-tree)
2509 ("perl-http-cookies" ,perl-http-cookies)
2510 ("perl-http-date" ,perl-http-date)
2511 ("perl-http-message" ,perl-http-message)
2512 ("perl-http-negotiate" ,perl-http-negotiate)
2513 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2514 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2515 ("perl-net-http" ,perl-net-http)
2516 ("perl-uri" ,perl-uri)
2517 ("perl-www-robotrules" ,perl-www-robotrules)
2518 ("perl-xml-simple" ,perl-xml-simple)
2520 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2521 (synopsis "Tools for accessing the NCBI's set of databases")
2523 "Entrez Direct (EDirect) is a method for accessing the National Center
2524 for Biotechnology Information's (NCBI) set of interconnected
2525 databases (publication, sequence, structure, gene, variation, expression,
2526 etc.) from a terminal. Functions take search terms from command-line
2527 arguments. Individual operations are combined to build multi-step queries.
2528 Record retrieval and formatting normally complete the process.
2530 EDirect also provides an argument-driven function that simplifies the
2531 extraction of data from document summaries or other results that are returned
2532 in structured XML format. This can eliminate the need for writing custom
2533 software to answer ad hoc questions.")
2534 (license license:public-domain)))
2536 (define-public exonerate
2545 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2546 "exonerate-" version ".tar.gz"))
2549 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2550 (build-system gnu-build-system)
2552 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2554 `(("pkg-config" ,pkg-config)))
2558 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2559 (synopsis "Generic tool for biological sequence alignment")
2561 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2562 the alignment of sequences using a many alignment models, either exhaustive
2563 dynamic programming or a variety of heuristics.")
2564 (license license:gpl3)))
2566 (define-public express
2574 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2575 version "/express-" version "-src.tgz"))
2578 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2579 (build-system cmake-build-system)
2581 `(#:tests? #f ;no "check" target
2583 (modify-phases %standard-phases
2584 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2585 (lambda* (#:key inputs #:allow-other-keys)
2586 (substitute* "CMakeLists.txt"
2587 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2588 "set(Boost_USE_STATIC_LIBS OFF)")
2589 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2590 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2591 (substitute* "src/CMakeLists.txt"
2592 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2593 (string-append (assoc-ref inputs "bamtools") "/lib"))
2594 (("libprotobuf.a") "libprotobuf.so"))
2598 ("bamtools" ,bamtools)
2599 ("protobuf" ,protobuf)
2601 (home-page "http://bio.math.berkeley.edu/eXpress")
2602 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2604 "eXpress is a streaming tool for quantifying the abundances of a set of
2605 target sequences from sampled subsequences. Example applications include
2606 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2607 analysis (from RNA-Seq), transcription factor binding quantification in
2608 ChIP-Seq, and analysis of metagenomic data.")
2609 (license license:artistic2.0)))
2611 (define-public express-beta-diversity
2613 (name "express-beta-diversity")
2618 (url "https://github.com/dparks1134/ExpressBetaDiversity.git")
2619 (commit (string-append "v" version))))
2620 (file-name (git-file-name name version))
2623 "0s0yzg5c21349rh7x4w9266jsvnp7j1hp9cf8sk32hz8nvrj745x"))))
2624 (build-system gnu-build-system)
2627 (modify-phases %standard-phases
2629 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2631 (lambda _ (invoke "../bin/ExpressBetaDiversity" "-u") #t))
2633 (lambda* (#:key outputs #:allow-other-keys)
2634 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
2635 (install-file "../scripts/convertToEBD.py" bin)
2636 (install-file "../bin/ExpressBetaDiversity" bin)
2639 `(("python" ,python-2)))
2640 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2641 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2643 "Express Beta Diversity (EBD) calculates ecological beta diversity
2644 (dissimilarity) measures between biological communities. EBD implements a
2645 variety of diversity measures including those that make use of phylogenetic
2646 similarity of community members.")
2647 (license license:gpl3+)))
2649 (define-public fasttree
2656 "http://www.microbesonline.org/fasttree/FastTree-"
2660 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2661 (build-system gnu-build-system)
2663 `(#:tests? #f ; no "check" target
2665 (modify-phases %standard-phases
2669 (lambda* (#:key source #:allow-other-keys)
2672 "-finline-functions"
2683 "-finline-functions"
2692 (lambda* (#:key outputs #:allow-other-keys)
2693 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
2694 (install-file "FastTree" bin)
2695 (install-file "FastTreeMP" bin)
2697 (home-page "http://www.microbesonline.org/fasttree")
2698 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2700 "FastTree can handle alignments with up to a million of sequences in a
2701 reasonable amount of time and memory. For large alignments, FastTree is
2702 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2703 (license license:gpl2+)))
2705 (define-public fastx-toolkit
2707 (name "fastx-toolkit")
2713 "https://github.com/agordon/fastx_toolkit/releases/download/"
2714 version "/fastx_toolkit-" version ".tar.bz2"))
2717 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2718 (build-system gnu-build-system)
2720 `(("libgtextutils" ,libgtextutils)))
2722 `(("pkg-config" ,pkg-config)))
2723 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2724 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2726 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
2727 FASTA/FASTQ files preprocessing.
2729 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
2730 containing multiple short-reads sequences. The main processing of such
2731 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
2732 is sometimes more productive to preprocess the files before mapping the
2733 sequences to the genome---manipulating the sequences to produce better mapping
2734 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
2735 (license license:agpl3+)))
2737 (define-public flexbar
2744 (url "https://github.com/seqan/flexbar.git")
2745 (commit (string-append "v" version))))
2746 (file-name (git-file-name name version))
2749 "1pq9sxvdnldl14libk234m72dqhwgzs3acgl943wchwdqlcsi5r2"))))
2750 (build-system cmake-build-system)
2753 (modify-phases %standard-phases
2754 (add-after 'unpack 'do-not-tune-to-CPU
2756 (substitute* "src/CMakeLists.txt"
2757 ((" -march=native") ""))
2760 (lambda* (#:key outputs #:allow-other-keys)
2761 (setenv "PATH" (string-append (getcwd) ":" (getenv "PATH")))
2762 (with-directory-excursion "../source/test"
2763 (invoke "bash" "flexbar_test.sh"))
2766 (lambda* (#:key outputs #:allow-other-keys)
2767 (let* ((out (string-append (assoc-ref outputs "out")))
2768 (bin (string-append out "/bin/")))
2769 (install-file "flexbar" bin))
2775 `(("pkg-config" ,pkg-config)
2777 (home-page "https://github.com/seqan/flexbar")
2778 (synopsis "Barcode and adapter removal tool for sequencing platforms")
2780 "Flexbar preprocesses high-throughput nucleotide sequencing data
2781 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
2782 Moreover, trimming and filtering features are provided. Flexbar increases
2783 read mapping rates and improves genome and transcriptome assemblies. It
2784 supports next-generation sequencing data in fasta/q and csfasta/q format from
2785 Illumina, Roche 454, and the SOLiD platform.")
2786 (license license:bsd-3)))
2788 (define-public fraggenescan
2790 (name "fraggenescan")
2796 (string-append "mirror://sourceforge/fraggenescan/"
2797 "FragGeneScan" version ".tar.gz"))
2799 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
2800 (build-system gnu-build-system)
2803 (modify-phases %standard-phases
2805 (add-before 'build 'patch-paths
2806 (lambda* (#:key outputs #:allow-other-keys)
2807 (let* ((out (string-append (assoc-ref outputs "out")))
2808 (share (string-append out "/share/fraggenescan/")))
2809 (substitute* "run_FragGeneScan.pl"
2811 (string-append "system(\"" (which "rm")))
2813 (string-append "system(\"" (which "mv")))
2814 (("\\\"awk") (string-append "\"" (which "awk")))
2815 ;; This script and other programs expect the training files
2816 ;; to be in the non-standard location bin/train/XXX. Change
2817 ;; this to be share/fraggenescan/train/XXX instead.
2818 (("^\\$train.file = \\$dir.*")
2819 (string-append "$train_file = \""
2821 "train/\".$FGS_train_file;")))
2822 (substitute* "run_hmm.c"
2823 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
2824 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
2828 (invoke "make" "clean")
2829 (invoke "make" "fgs")
2832 (lambda* (#:key outputs #:allow-other-keys)
2833 (let* ((out (string-append (assoc-ref outputs "out")))
2834 (bin (string-append out "/bin/"))
2835 (share (string-append out "/share/fraggenescan/train")))
2836 (install-file "run_FragGeneScan.pl" bin)
2837 (install-file "FragGeneScan" bin)
2838 (copy-recursively "train" share))
2841 (add-after 'install 'post-install-check
2842 ;; In lieu of 'make check', run one of the examples and check the
2843 ;; output files gets created.
2844 (lambda* (#:key outputs #:allow-other-keys)
2845 (let* ((out (string-append (assoc-ref outputs "out")))
2846 (bin (string-append out "/bin/"))
2847 (frag (string-append bin "run_FragGeneScan.pl")))
2848 ;; Test complete genome.
2850 "-genome=./example/NC_000913.fna"
2854 (unless (and (file-exists? "test2.faa")
2855 (file-exists? "test2.ffn")
2856 (file-exists? "test2.gff")
2857 (file-exists? "test2.out"))
2858 (error "Expected files do not exist."))
2859 ;; Test incomplete sequences.
2861 "-genome=./example/NC_000913-fgs.ffn"
2868 ("python" ,python-2))) ;not compatible with python 3.
2869 (home-page "https://sourceforge.net/projects/fraggenescan/")
2870 (synopsis "Finds potentially fragmented genes in short reads")
2872 "FragGeneScan is a program for predicting bacterial and archaeal genes in
2873 short and error-prone DNA sequencing reads. It can also be applied to predict
2874 genes in incomplete assemblies or complete genomes.")
2875 ;; GPL3+ according to private correspondense with the authors.
2876 (license license:gpl3+)))
2878 (define-public fxtract
2879 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
2887 (url "https://github.com/ctSkennerton/fxtract.git")
2889 (file-name (git-file-name name version))
2892 "0hab3gpwf4w9s87qlbswq6ws1qqybh4dcqk79q1ahyldzai5fgp5"))))
2893 (build-system gnu-build-system)
2895 `(#:make-flags (list
2896 (string-append "PREFIX=" (assoc-ref %outputs "out"))
2898 #:test-target "fxtract_test"
2900 (modify-phases %standard-phases
2902 (add-before 'build 'copy-util
2903 (lambda* (#:key inputs #:allow-other-keys)
2905 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
2907 ;; Do not use make install as this requires additional dependencies.
2909 (lambda* (#:key outputs #:allow-other-keys)
2910 (let* ((out (assoc-ref outputs "out"))
2911 (bin (string-append out"/bin")))
2912 (install-file "fxtract" bin)
2918 ;; ctskennerton-util is licensed under GPL2.
2919 `(("ctskennerton-util"
2923 (url "https://github.com/ctSkennerton/util.git")
2924 (commit util-commit)))
2925 (file-name (string-append
2926 "ctstennerton-util-" util-commit "-checkout"))
2929 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
2930 (home-page "https://github.com/ctSkennerton/fxtract")
2931 (synopsis "Extract sequences from FASTA and FASTQ files")
2933 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
2934 or FASTQ) file given a subsequence. It uses a simple substring search for
2935 basic tasks but can change to using POSIX regular expressions, PCRE, hash
2936 lookups or multi-pattern searching as required. By default fxtract looks in
2937 the sequence of each record but can also be told to look in the header,
2938 comment or quality sections.")
2939 ;; 'util' requires SSE instructions.
2940 (supported-systems '("x86_64-linux"))
2941 (license license:expat))))
2943 (define-public gemma
2950 (url "https://github.com/xiangzhou/GEMMA.git")
2951 (commit (string-append "v" version))))
2952 (file-name (git-file-name name version))
2955 "1s3ncnbn45r2hh1cvrqky1kbqq6546biypr4f5mkw1kqlrgyh0yg"))))
2958 ("gfortran" ,gfortran "lib")
2961 ("openblas" ,openblas)
2963 (build-system gnu-build-system)
2966 '(,@(match (%current-system)
2968 '("FORCE_DYNAMIC=1"))
2970 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
2972 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
2974 (modify-phases %standard-phases
2976 (add-after 'unpack 'find-eigen
2977 (lambda* (#:key inputs #:allow-other-keys)
2978 ;; Ensure that Eigen headers can be found
2979 (setenv "CPLUS_INCLUDE_PATH"
2980 (string-append (getenv "CPLUS_INCLUDE_PATH")
2982 (assoc-ref inputs "eigen")
2985 (add-before 'build 'bin-mkdir
2990 (lambda* (#:key outputs #:allow-other-keys)
2991 (let ((out (assoc-ref outputs "out")))
2992 (install-file "bin/gemma"
2996 #:tests? #f)) ; no tests included yet
2997 (home-page "https://github.com/xiangzhou/GEMMA")
2998 (synopsis "Tool for genome-wide efficient mixed model association")
3000 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
3001 standard linear mixed model resolver with application in genome-wide
3002 association studies (GWAS).")
3003 (license license:gpl3)))
3012 (url "https://github.com/nboley/grit.git")
3014 (file-name (git-file-name name version))
3017 "1l5v8vfvfbrpmgnrvbrbv40d0arhxcnmxgv2f1mlcqfa3q6bkqm9"))))
3018 (build-system python-build-system)
3020 `(#:python ,python-2
3022 (modify-phases %standard-phases
3023 (add-after 'unpack 'generate-from-cython-sources
3024 (lambda* (#:key inputs outputs #:allow-other-keys)
3025 ;; Delete these C files to force fresh generation from pyx sources.
3026 (delete-file "grit/sparsify_support_fns.c")
3027 (delete-file "grit/call_peaks_support_fns.c")
3028 (substitute* "setup.py"
3029 (("Cython.Setup") "Cython.Build"))
3032 `(("python-scipy" ,python2-scipy)
3033 ("python-numpy" ,python2-numpy)
3034 ("python-pysam" ,python2-pysam)
3035 ("python-networkx" ,python2-networkx)))
3037 `(("python-cython" ,python2-cython)))
3038 (home-page "http://grit-bio.org")
3039 (synopsis "Tool for integrative analysis of RNA-seq type assays")
3041 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
3042 full length transcript models. When none of these data sources are available,
3043 GRIT can be run by providing a candidate set of TES or TSS sites. In
3044 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
3045 also be run in quantification mode, where it uses a provided GTF file and just
3046 estimates transcript expression.")
3047 (license license:gpl3+)))
3049 (define-public hisat
3056 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
3057 version "-beta-source.zip"))
3060 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
3061 (build-system gnu-build-system)
3063 `(#:tests? #f ;no check target
3064 #:make-flags '("allall"
3065 ;; Disable unsupported `popcnt' instructions on
3066 ;; architectures other than x86_64
3067 ,@(if (string-prefix? "x86_64"
3068 (or (%current-target-system)
3071 '("POPCNT_CAPABILITY=0")))
3073 (modify-phases %standard-phases
3074 (add-after 'unpack 'patch-sources
3076 ;; XXX Cannot use snippet because zip files are not supported
3077 (substitute* "Makefile"
3078 (("^CC = .*$") "CC = gcc")
3079 (("^CPP = .*$") "CPP = g++")
3080 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
3081 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
3082 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
3083 (substitute* '("hisat-build" "hisat-inspect")
3084 (("/usr/bin/env") (which "env")))
3087 (lambda* (#:key outputs #:allow-other-keys)
3088 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
3089 (for-each (lambda (file)
3090 (install-file file bin))
3093 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
3095 (delete 'configure))))
3097 `(("unzip" ,unzip)))
3102 ;; Non-portable SSE instructions are used so building fails on platforms
3103 ;; other than x86_64.
3104 (supported-systems '("x86_64-linux"))
3105 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
3106 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
3108 "HISAT is a fast and sensitive spliced alignment program for mapping
3109 RNA-seq reads. In addition to one global FM index that represents a whole
3110 genome, HISAT uses a large set of small FM indexes that collectively cover the
3111 whole genome. These small indexes (called local indexes) combined with
3112 several alignment strategies enable effective alignment of RNA-seq reads, in
3113 particular, reads spanning multiple exons.")
3114 (license license:gpl3+)))
3116 (define-public hisat2
3123 (uri (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
3124 "/downloads/hisat2-" version "-source.zip"))
3127 "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"))))
3128 (build-system gnu-build-system)
3130 `(#:tests? #f ; no check target
3131 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
3132 #:modules ((guix build gnu-build-system)
3136 (modify-phases %standard-phases
3137 (add-after 'unpack 'make-deterministic
3139 (substitute* "Makefile"
3144 (lambda* (#:key outputs #:allow-other-keys)
3145 (let* ((out (assoc-ref outputs "out"))
3146 (bin (string-append out "/bin/"))
3147 (doc (string-append out "/share/doc/hisat2/")))
3149 (cut install-file <> bin)
3151 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
3153 (install-file "doc/manual.inc.html" doc))
3156 `(("unzip" ,unzip) ; needed for archive from ftp
3158 ("pandoc" ,ghc-pandoc))) ; for documentation
3159 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
3160 (synopsis "Graph-based alignment of genomic sequencing reads")
3161 (description "HISAT2 is a fast and sensitive alignment program for mapping
3162 next-generation sequencing reads (both DNA and RNA) to a population of human
3163 genomes (as well as to a single reference genome). In addition to using one
3164 global @dfn{graph FM} (GFM) index that represents a population of human
3165 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
3166 the whole genome. These small indexes, combined with several alignment
3167 strategies, enable rapid and accurate alignment of sequencing reads. This new
3168 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
3169 ;; HISAT2 contains files from Bowtie2, which is released under
3170 ;; GPLv2 or later. The HISAT2 source files are released under
3172 (license license:gpl3+)))
3174 (define-public hmmer
3182 "http://eddylab.org/software/hmmer/hmmer-" version ".tar.gz"))
3185 "171bivy6xhgjsz5nv53n81pc3frnwz29ylblawk2bv46szwjjqd5"))))
3186 (build-system gnu-build-system)
3187 (native-inputs `(("perl" ,perl)))
3188 (home-page "http://hmmer.org/")
3189 (synopsis "Biosequence analysis using profile hidden Markov models")
3191 "HMMER is used for searching sequence databases for homologs of protein
3192 sequences, and for making protein sequence alignments. It implements methods
3193 using probabilistic models called profile hidden Markov models (profile
3195 ;; hmmer uses non-portable SSE intrinsics so building fails on other
3197 (supported-systems '("x86_64-linux" "i686-linux"))
3198 (license license:bsd-3)))
3200 (define-public htseq
3206 (uri (pypi-uri "HTSeq" version))
3209 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
3210 (build-system python-build-system)
3212 `(("python-cython" ,python-cython)))
3213 ;; Numpy needs to be propagated when htseq is used as a Python library.
3215 `(("python-numpy" ,python-numpy)))
3217 `(("python-pysam" ,python-pysam)
3218 ("python-matplotlib" ,python-matplotlib)))
3219 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
3220 (synopsis "Analysing high-throughput sequencing data with Python")
3222 "HTSeq is a Python package that provides infrastructure to process data
3223 from high-throughput sequencing assays.")
3224 (license license:gpl3+)))
3226 (define-public python2-htseq
3227 (package-with-python2 htseq))
3229 (define-public java-htsjdk
3231 (name "java-htsjdk")
3232 (version "2.3.0") ; last version without build dependency on gradle
3236 (url "https://github.com/samtools/htsjdk.git")
3238 (file-name (git-file-name name version))
3241 "1b178ixcabanm834ydjl3jiakpyxdmki32hqfv2abrzn3rcwa28i"))
3242 (modules '((guix build utils)))
3244 ;; Delete pre-built binaries
3246 (delete-file-recursively "lib")
3249 (build-system ant-build-system)
3251 `(#:tests? #f ; test require Internet access
3254 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3255 "/share/java/htsjdk/"))
3256 #:build-target "all"
3258 (modify-phases %standard-phases
3259 ;; The build phase also installs the jars
3260 (delete 'install))))
3262 `(("java-ngs" ,java-ngs)
3263 ("java-snappy-1" ,java-snappy-1)
3264 ("java-commons-compress" ,java-commons-compress)
3265 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3266 ("java-commons-jexl-2" ,java-commons-jexl-2)
3267 ("java-xz" ,java-xz)))
3269 `(("java-testng" ,java-testng)))
3270 (home-page "http://samtools.github.io/htsjdk/")
3271 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3273 "HTSJDK is an implementation of a unified Java library for accessing
3274 common file formats, such as SAM and VCF, used for high-throughput
3275 sequencing (HTS) data. There are also an number of useful utilities for
3276 manipulating HTS data.")
3277 (license license:expat)))
3279 (define-public java-htsjdk-latest
3281 (name "java-htsjdk")
3286 (url "https://github.com/samtools/htsjdk.git")
3288 (file-name (string-append name "-" version "-checkout"))
3291 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
3292 (build-system ant-build-system)
3294 `(#:tests? #f ; test require Scala
3296 #:jar-name "htsjdk.jar"
3298 (modify-phases %standard-phases
3299 (add-after 'unpack 'remove-useless-build.xml
3300 (lambda _ (delete-file "build.xml") #t))
3301 ;; The tests require the scalatest package.
3302 (add-after 'unpack 'remove-tests
3303 (lambda _ (delete-file-recursively "src/test") #t)))))
3305 `(("java-ngs" ,java-ngs)
3306 ("java-snappy-1" ,java-snappy-1)
3307 ("java-commons-compress" ,java-commons-compress)
3308 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3309 ("java-commons-jexl-2" ,java-commons-jexl-2)
3310 ("java-xz" ,java-xz)))
3312 `(("java-junit" ,java-junit)))
3313 (home-page "http://samtools.github.io/htsjdk/")
3314 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3316 "HTSJDK is an implementation of a unified Java library for accessing
3317 common file formats, such as SAM and VCF, used for high-throughput
3318 sequencing (HTS) data. There are also an number of useful utilities for
3319 manipulating HTS data.")
3320 (license license:expat)))
3322 ;; This is needed for picard 2.10.3
3323 (define-public java-htsjdk-2.10.1
3324 (package (inherit java-htsjdk-latest)
3325 (name "java-htsjdk")
3330 (url "https://github.com/samtools/htsjdk.git")
3332 (file-name (string-append name "-" version "-checkout"))
3335 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
3336 (build-system ant-build-system)
3338 `(#:tests? #f ; tests require Scala
3340 #:jar-name "htsjdk.jar"
3342 (modify-phases %standard-phases
3343 (add-after 'unpack 'remove-useless-build.xml
3344 (lambda _ (delete-file "build.xml") #t))
3345 ;; The tests require the scalatest package.
3346 (add-after 'unpack 'remove-tests
3347 (lambda _ (delete-file-recursively "src/test") #t)))))))
3349 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3350 ;; recent version of java-htsjdk, which depends on gradle.
3351 (define-public java-picard
3353 (name "java-picard")
3358 (url "https://github.com/broadinstitute/picard.git")
3360 (file-name (string-append "java-picard-" version "-checkout"))
3363 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3364 (modules '((guix build utils)))
3367 ;; Delete pre-built binaries.
3368 (delete-file-recursively "lib")
3370 (substitute* "build.xml"
3371 ;; Remove build-time dependency on git.
3372 (("failifexecutionfails=\"true\"")
3373 "failifexecutionfails=\"false\"")
3375 (("depends=\"compile-htsjdk, ")
3377 (("depends=\"compile-htsjdk-tests, ")
3379 ;; Build picard-lib.jar before building picard.jar
3380 (("name=\"picard-jar\" depends=\"" line)
3381 (string-append line "picard-lib-jar, ")))
3383 (build-system ant-build-system)
3385 `(#:build-target "picard-jar"
3386 #:test-target "test"
3387 ;; Tests require jacoco:coverage.
3390 (list (string-append "-Dhtsjdk_lib_dir="
3391 (assoc-ref %build-inputs "java-htsjdk")
3392 "/share/java/htsjdk/")
3393 "-Dhtsjdk-classes=dist/tmp"
3394 (string-append "-Dhtsjdk-version="
3395 ,(package-version java-htsjdk)))
3398 (modify-phases %standard-phases
3399 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3400 (delete 'generate-jar-indices)
3401 (add-after 'unpack 'use-our-htsjdk
3402 (lambda* (#:key inputs #:allow-other-keys)
3403 (substitute* "build.xml"
3404 (("\\$\\{htsjdk\\}/lib")
3405 (string-append (assoc-ref inputs "java-htsjdk")
3406 "/share/java/htsjdk/")))
3408 (add-after 'unpack 'make-test-target-independent
3409 (lambda* (#:key inputs #:allow-other-keys)
3410 (substitute* "build.xml"
3411 (("name=\"test\" depends=\"compile, ")
3412 "name=\"test\" depends=\""))
3414 (replace 'install (install-jars "dist")))))
3416 `(("java-htsjdk" ,java-htsjdk)
3417 ("java-guava" ,java-guava)))
3419 `(("java-testng" ,java-testng)))
3420 (home-page "http://broadinstitute.github.io/picard/")
3421 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3422 (description "Picard is a set of Java command line tools for manipulating
3423 high-throughput sequencing (HTS) data and formats. Picard is implemented
3424 using the HTSJDK Java library to support accessing file formats that are
3425 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3427 (license license:expat)))
3429 ;; This is needed for dropseq-tools
3430 (define-public java-picard-2.10.3
3432 (name "java-picard")
3437 (url "https://github.com/broadinstitute/picard.git")
3439 (file-name (string-append "java-picard-" version "-checkout"))
3442 "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi"))))
3443 (build-system ant-build-system)
3445 `(#:jar-name "picard.jar"
3446 ;; Tests require jacoco:coverage.
3449 #:main-class "picard.cmdline.PicardCommandLine"
3450 #:modules ((guix build ant-build-system)
3452 (guix build java-utils)
3457 (modify-phases %standard-phases
3458 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3459 (delete 'generate-jar-indices)
3460 (add-after 'unpack 'remove-useless-build.xml
3461 (lambda _ (delete-file "build.xml") #t))
3462 ;; This is necessary to ensure that htsjdk is found when using
3463 ;; picard.jar as an executable.
3464 (add-before 'build 'edit-classpath-in-manifest
3465 (lambda* (#:key inputs #:allow-other-keys)
3466 (chmod "build.xml" #o664)
3467 (call-with-output-file "build.xml.new"
3471 (with-input-from-file "build.xml"
3472 (lambda _ (xml->sxml #:trim-whitespace? #t)))
3473 `((target . ,(lambda (tag . kids)
3474 (let ((name ((sxpath '(name *text*))
3476 ;; FIXME: We're breaking the line
3477 ;; early with a dummy path to
3478 ;; ensure that the store reference
3479 ;; isn't broken apart and can still
3480 ;; be found by the reference
3485 ~a/share/java/htsjdk.jar${line.separator}${line.separator}"
3486 ;; maximum line length is 70
3487 (string-tabulate (const #\b) 57)
3488 (assoc-ref inputs "java-htsjdk"))))
3489 (if (member "manifest" name)
3492 (@ (file "${manifest.file}")
3493 (match "\\r\\n\\r\\n")
3494 (replace "${line.separator}")))
3497 (file "${manifest.file}")
3500 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
3501 (*text* . ,(lambda (_ txt) txt))))
3503 (rename-file "build.xml.new" "build.xml")
3506 `(("java-htsjdk" ,java-htsjdk-2.10.1)))
3508 `(("java-testng" ,java-testng)
3509 ("java-guava" ,java-guava)))
3510 (home-page "http://broadinstitute.github.io/picard/")
3511 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3512 (description "Picard is a set of Java command line tools for manipulating
3513 high-throughput sequencing (HTS) data and formats. Picard is implemented
3514 using the HTSJDK Java library to support accessing file formats that are
3515 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3517 (license license:expat)))
3519 ;; This is the last version of Picard to provide net.sf.samtools
3520 (define-public java-picard-1.113
3521 (package (inherit java-picard)
3522 (name "java-picard")
3527 (url "https://github.com/broadinstitute/picard.git")
3529 (file-name (string-append "java-picard-" version "-checkout"))
3532 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
3533 (modules '((guix build utils)))
3536 ;; Delete pre-built binaries.
3537 (delete-file-recursively "lib")
3540 (build-system ant-build-system)
3542 `(#:build-target "picard-jar"
3543 #:test-target "test"
3544 ;; FIXME: the class path at test time is wrong.
3545 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
3546 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
3549 ;; This is only used for tests.
3551 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
3553 (modify-phases %standard-phases
3554 ;; FIXME: This phase fails.
3555 (delete 'generate-jar-indices)
3556 ;; Do not use bundled ant bzip2.
3557 (add-after 'unpack 'use-ant-bzip
3558 (lambda* (#:key inputs #:allow-other-keys)
3559 (substitute* "build.xml"
3560 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
3561 (string-append (assoc-ref inputs "ant")
3564 (add-after 'unpack 'make-test-target-independent
3565 (lambda* (#:key inputs #:allow-other-keys)
3566 (substitute* "build.xml"
3567 (("name=\"test\" depends=\"compile, ")
3568 "name=\"test\" depends=\"compile-tests, ")
3569 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
3570 "name=\"compile\" depends=\"compile-src\""))
3572 (add-after 'unpack 'fix-deflater-path
3573 (lambda* (#:key outputs #:allow-other-keys)
3574 (substitute* "src/java/net/sf/samtools/Defaults.java"
3575 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
3576 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
3577 (assoc-ref outputs "out")
3578 "/lib/jni/libIntelDeflater.so"
3581 ;; Build the deflater library, because we've previously deleted the
3582 ;; pre-built one. This can only be built with access to the JDK
3584 (add-after 'build 'build-jni
3585 (lambda* (#:key inputs #:allow-other-keys)
3588 (invoke "tar" "--strip-components=1" "-C" "jdk-src"
3589 "-xf" (assoc-ref inputs "jdk-src"))
3590 (invoke "javah" "-jni"
3591 "-classpath" "classes"
3593 "net.sf.samtools.util.zip.IntelDeflater")
3594 (with-directory-excursion "src/c/inteldeflater"
3595 (invoke "gcc" "-I../../../lib" "-I."
3596 (string-append "-I" (assoc-ref inputs "jdk")
3598 "-I../../../jdk-src/src/share/native/common/"
3599 "-I../../../jdk-src/src/solaris/native/common/"
3600 "-c" "-O3" "-fPIC" "IntelDeflater.c")
3601 (invoke "gcc" "-shared"
3602 "-o" "../../../lib/jni/libIntelDeflater.so"
3603 "IntelDeflater.o" "-lz" "-lstdc++"))
3605 ;; We can only build everything else after building the JNI library.
3606 (add-after 'build-jni 'build-rest
3607 (lambda* (#:key make-flags #:allow-other-keys)
3608 (apply invoke `("ant" "all" ,@make-flags))
3610 (add-before 'build 'set-JAVA6_HOME
3612 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
3614 (replace 'install (install-jars "dist"))
3615 (add-after 'install 'install-jni-lib
3616 (lambda* (#:key outputs #:allow-other-keys)
3617 (let ((jni (string-append (assoc-ref outputs "out")
3620 (install-file "lib/jni/libIntelDeflater.so" jni)
3623 `(("java-snappy-1" ,java-snappy-1)
3624 ("java-commons-jexl-2" ,java-commons-jexl-2)
3625 ("java-cofoja" ,java-cofoja)
3626 ("ant" ,ant) ; for bzip2 support at runtime
3629 `(("ant-apache-bcel" ,ant-apache-bcel)
3630 ("ant-junit" ,ant-junit)
3631 ("java-testng" ,java-testng)
3632 ("java-commons-bcel" ,java-commons-bcel)
3633 ("java-jcommander" ,java-jcommander)
3634 ("jdk" ,icedtea-8 "jdk")
3635 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
3637 (define-public fastqc
3644 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
3645 "projects/fastqc/fastqc_v"
3646 version "_source.zip"))
3649 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
3650 (build-system ant-build-system)
3652 `(#:tests? #f ; there are no tests
3653 #:build-target "build"
3655 (modify-phases %standard-phases
3656 (add-after 'unpack 'fix-dependencies
3657 (lambda* (#:key inputs #:allow-other-keys)
3658 (substitute* "build.xml"
3660 (string-append (assoc-ref inputs "java-jbzip2")
3661 "/share/java/jbzip2.jar"))
3663 (string-append (assoc-ref inputs "java-picard-1.113")
3664 "/share/java/sam-1.112.jar"))
3666 (string-append (assoc-ref inputs "java-cisd-jhdf5")
3667 "/share/java/sis-jhdf5.jar")))
3669 ;; There is no installation target
3671 (lambda* (#:key inputs outputs #:allow-other-keys)
3672 (let* ((out (assoc-ref outputs "out"))
3673 (bin (string-append out "/bin"))
3674 (share (string-append out "/share/fastqc/"))
3675 (exe (string-append share "/fastqc")))
3676 (for-each mkdir-p (list bin share))
3677 (copy-recursively "bin" share)
3679 (("my \\$java_bin = 'java';")
3680 (string-append "my $java_bin = '"
3681 (assoc-ref inputs "java")
3684 (symlink exe (string-append bin "/fastqc"))
3688 ("perl" ,perl) ; needed for the wrapper script
3689 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
3690 ("java-picard-1.113" ,java-picard-1.113)
3691 ("java-jbzip2" ,java-jbzip2)))
3693 `(("unzip" ,unzip)))
3694 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
3695 (synopsis "Quality control tool for high throughput sequence data")
3697 "FastQC aims to provide a simple way to do some quality control
3698 checks on raw sequence data coming from high throughput sequencing
3699 pipelines. It provides a modular set of analyses which you can use to
3700 give a quick impression of whether your data has any problems of which
3701 you should be aware before doing any further analysis.
3703 The main functions of FastQC are:
3706 @item Import of data from BAM, SAM or FastQ files (any variant);
3707 @item Providing a quick overview to tell you in which areas there may
3709 @item Summary graphs and tables to quickly assess your data;
3710 @item Export of results to an HTML based permanent report;
3711 @item Offline operation to allow automated generation of reports
3712 without running the interactive application.
3714 (license license:gpl3+)))
3716 (define-public fastp
3724 (url "https://github.com/OpenGene/fastp.git")
3725 (commit (string-append "v" version))))
3726 (file-name (git-file-name name version))
3729 "1r6ms5zbf5rps4rgp4z73nczadl00b5rqylw8f684isfz27dp0xh"))))
3730 (build-system gnu-build-system)
3732 `(#:tests? #f ; there are none
3734 (list (string-append "BINDIR=" (assoc-ref %outputs "out") "/bin"))
3736 (modify-phases %standard-phases
3738 (add-before 'install 'create-target-dir
3739 (lambda* (#:key outputs #:allow-other-keys)
3740 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
3744 (home-page "https://github.com/OpenGene/fastp/")
3745 (synopsis "All-in-one FastQ preprocessor")
3747 "Fastp is a tool designed to provide fast all-in-one preprocessing for
3748 FastQ files. This tool has multi-threading support to afford high
3750 (license license:expat)))
3752 (define-public htslib
3759 "https://github.com/samtools/htslib/releases/download/"
3760 version "/htslib-" version ".tar.bz2"))
3763 "16ljv43sc3fxmv63w7b2ff8m1s7h89xhazwmbm1bicz8axq8fjz0"))))
3764 (build-system gnu-build-system)
3766 `(("openssl" ,openssl)
3771 (home-page "http://www.htslib.org")
3772 (synopsis "C library for reading/writing high-throughput sequencing data")
3774 "HTSlib is a C library for reading/writing high-throughput sequencing
3775 data. It also provides the @command{bgzip}, @command{htsfile}, and
3776 @command{tabix} utilities.")
3777 ;; Files under cram/ are released under the modified BSD license;
3778 ;; the rest is released under the Expat license
3779 (license (list license:expat license:bsd-3))))
3781 ;; This package should be removed once no packages rely upon it.
3789 "https://github.com/samtools/htslib/releases/download/"
3790 version "/htslib-" version ".tar.bz2"))
3793 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
3802 (url "https://github.com/nboley/idr.git")
3804 (file-name (git-file-name name version))
3807 "04j876h6z444v2q79drxx283d3k5snd72kj895wbalnl42206x9g"))
3808 ;; Delete generated C code.
3810 '(begin (delete-file "idr/inv_cdf.c") #t))))
3811 (build-system python-build-system)
3812 ;; There is only one test ("test_inv_cdf.py") and it tests features that
3813 ;; are no longer part of this package. It also asserts False, which
3814 ;; causes the tests to always fail.
3815 (arguments `(#:tests? #f))
3817 `(("python-scipy" ,python-scipy)
3818 ("python-sympy" ,python-sympy)
3819 ("python-numpy" ,python-numpy)
3820 ("python-matplotlib" ,python-matplotlib)))
3822 `(("python-cython" ,python-cython)))
3823 (home-page "https://github.com/nboley/idr")
3824 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
3826 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
3827 to measure the reproducibility of findings identified from replicate
3828 experiments and provide highly stable thresholds based on reproducibility.")
3829 (license license:gpl2+)))
3831 (define-public jellyfish
3837 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
3838 "releases/download/v" version
3839 "/jellyfish-" version ".tar.gz"))
3842 "1k4pc3fvv6w1km2yph4m5sd78fbxp21d6xyzgmy0gjihzc6mb249"))))
3843 (build-system gnu-build-system)
3844 (outputs '("out" ;for library
3845 "ruby" ;for Ruby bindings
3846 "python")) ;for Python bindings
3849 (list (string-append "--enable-ruby-binding="
3850 (assoc-ref %outputs "ruby"))
3851 (string-append "--enable-python-binding="
3852 (assoc-ref %outputs "python")))
3854 (modify-phases %standard-phases
3855 (add-before 'check 'set-SHELL-variable
3857 ;; generator_manager.hpp either uses /bin/sh or $SHELL
3859 (setenv "SHELL" (which "bash"))
3865 ("python" ,python-2)
3866 ("pkg-config" ,pkg-config)))
3868 `(("htslib" ,htslib)))
3869 (synopsis "Tool for fast counting of k-mers in DNA")
3871 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
3872 DNA. A k-mer is a substring of length k, and counting the occurrences of all
3873 such substrings is a central step in many analyses of DNA sequence. Jellyfish
3874 is a command-line program that reads FASTA and multi-FASTA files containing
3875 DNA sequences. It outputs its k-mer counts in a binary format, which can be
3876 translated into a human-readable text format using the @code{jellyfish dump}
3877 command, or queried for specific k-mers with @code{jellyfish query}.")
3878 (home-page "http://www.genome.umd.edu/jellyfish.html")
3879 ;; JELLYFISH seems to be 64-bit only.
3880 (supported-systems '("x86_64-linux" "aarch64-linux" "mips64el-linux"))
3881 ;; The combined work is published under the GPLv3 or later. Individual
3882 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
3883 (license (list license:gpl3+ license:expat))))
3885 (define-public khmer
3893 (url "https://github.com/dib-lab/khmer.git")
3894 (commit (string-append "v" version))))
3895 (file-name (git-file-name name version))
3898 "02x38d9jw2r58y8dmnj4hffy9wxv1yc1jwbvdbhby9dxndv94r9m"))
3899 (patches (search-patches "khmer-use-libraries.patch"))
3900 (modules '((guix build utils)))
3903 ;; Delete bundled libraries. We do not replace the bundled seqan
3904 ;; as it is a modified subset of the old version 1.4.1.
3906 ;; We do not replace the bundled MurmurHash as the canonical
3907 ;; repository for this code 'SMHasher' is unsuitable for providing
3909 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
3910 (delete-file-recursively "third-party/zlib")
3911 (delete-file-recursively "third-party/bzip2")
3913 (build-system python-build-system)
3916 (modify-phases %standard-phases
3917 (add-after 'unpack 'set-cc
3918 (lambda _ (setenv "CC" "gcc") #t))
3919 ;; FIXME: This fails with "permission denied".
3920 (delete 'reset-gzip-timestamps))))
3922 `(("python-cython" ,python-cython)
3923 ("python-pytest" ,python-pytest)
3924 ("python-pytest-runner" ,python-pytest-runner)))
3928 ("python-screed" ,python-screed)
3929 ("python-bz2file" ,python-bz2file)))
3930 (home-page "https://khmer.readthedocs.org/")
3931 (synopsis "K-mer counting, filtering and graph traversal library")
3932 (description "The khmer software is a set of command-line tools for
3933 working with DNA shotgun sequencing data from genomes, transcriptomes,
3934 metagenomes and single cells. Khmer can make de novo assemblies faster, and
3935 sometimes better. Khmer can also identify and fix problems with shotgun
3937 ;; When building on i686, armhf and mips64el, we get the following error:
3938 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
3939 (supported-systems '("x86_64-linux" "aarch64-linux"))
3940 (license license:bsd-3)))
3942 (define-public kaiju
3949 (url "https://github.com/bioinformatics-centre/kaiju")
3950 (commit (string-append "v" version))))
3951 (file-name (git-file-name name version))
3954 "119pzi0ddzv9mjg4wwa6han0cwr3k3ssn7kirvsjfcq05mi5ka0x"))))
3955 (build-system gnu-build-system)
3957 `(#:tests? #f ; There are no tests.
3959 (modify-phases %standard-phases
3961 (add-before 'build 'move-to-src-dir
3962 (lambda _ (chdir "src") #t))
3964 (lambda* (#:key inputs outputs #:allow-other-keys)
3965 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3968 (copy-recursively "bin" bin))
3973 (home-page "http://kaiju.binf.ku.dk/")
3974 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
3975 (description "Kaiju is a program for sensitive taxonomic classification
3976 of high-throughput sequencing reads from metagenomic whole genome sequencing
3978 (license license:gpl3+)))
3983 (version "2.1.1.20160309")
3986 (uri (pypi-uri "MACS2" version))
3989 "09ixspd1vcqmz1c81ih70xs4m7qml2iy5vyx1y74zww3iy1vl210"))))
3990 (build-system python-build-system)
3992 `(#:python ,python-2 ; only compatible with Python 2.7
3993 #:tests? #f)) ; no test target
3995 `(("python-numpy" ,python2-numpy)))
3996 (home-page "https://github.com/taoliu/MACS/")
3997 (synopsis "Model based analysis for ChIP-Seq data")
3999 "MACS is an implementation of a ChIP-Seq analysis algorithm for
4000 identifying transcript factor binding sites named Model-based Analysis of
4001 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
4002 the significance of enriched ChIP regions and it improves the spatial
4003 resolution of binding sites through combining the information of both
4004 sequencing tag position and orientation.")
4005 (license license:bsd-3)))
4007 (define-public mafft
4014 "https://mafft.cbrc.jp/alignment/software/mafft-" version
4015 "-without-extensions-src.tgz"))
4016 (file-name (string-append name "-" version ".tgz"))
4019 "0bacjkxfg944p5khhyh5rd4y7wkjc9qk4v2jjj442sqlq0f8ar7b"))))
4020 (build-system gnu-build-system)
4022 `(#:tests? #f ; no automated tests, though there are tests in the read me
4023 #:make-flags (let ((out (assoc-ref %outputs "out")))
4024 (list (string-append "PREFIX=" out)
4025 (string-append "BINDIR="
4026 (string-append out "/bin"))))
4028 (modify-phases %standard-phases
4029 (add-after 'unpack 'enter-dir
4030 (lambda _ (chdir "core") #t))
4031 (add-after 'enter-dir 'patch-makefile
4033 ;; on advice from the MAFFT authors, there is no need to
4034 ;; distribute mafft-profile, mafft-distance, or
4035 ;; mafft-homologs.rb as they are too "specialised".
4036 (substitute* "Makefile"
4037 ;; remove mafft-homologs.rb from SCRIPTS
4038 (("^SCRIPTS = mafft mafft-homologs.rb")
4040 ;; remove mafft-homologs from MANPAGES
4041 (("^MANPAGES = mafft.1 mafft-homologs.1")
4042 "MANPAGES = mafft.1")
4043 ;; remove mafft-distance from PROGS
4044 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
4045 "PROGS = dvtditr dndfast7 dndblast sextet5")
4046 ;; remove mafft-profile from PROGS
4047 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
4048 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
4049 (("^rm -f mafft-profile mafft-profile.exe") "#")
4050 (("^rm -f mafft-distance mafft-distance.exe") ")#")
4051 ;; do not install MAN pages in libexec folder
4052 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
4053 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
4055 (add-after 'enter-dir 'patch-paths
4056 (lambda* (#:key inputs #:allow-other-keys)
4057 (substitute* '("pairash.c"
4059 (("perl") (which "perl"))
4060 (("([\"`| ])awk" _ prefix)
4061 (string-append prefix (which "awk")))
4062 (("grep") (which "grep")))
4065 (add-after 'install 'wrap-programs
4066 (lambda* (#:key outputs #:allow-other-keys)
4067 (let* ((out (assoc-ref outputs "out"))
4068 (bin (string-append out "/bin"))
4069 (path (string-append
4070 (assoc-ref %build-inputs "coreutils") "/bin:")))
4071 (for-each (lambda (file)
4073 `("PATH" ":" prefix (,path))))
4081 ("coreutils" ,coreutils)))
4082 (home-page "http://mafft.cbrc.jp/alignment/software/")
4083 (synopsis "Multiple sequence alignment program")
4085 "MAFFT offers a range of multiple alignment methods for nucleotide and
4086 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
4087 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
4089 (license (license:non-copyleft
4090 "http://mafft.cbrc.jp/alignment/software/license.txt"
4091 "BSD-3 with different formatting"))))
4100 (url "https://github.com/marbl/mash.git")
4101 (commit (string-append "v" version))))
4102 (file-name (git-file-name name version))
4105 "049hwcc059p2fd9vwndn63laifvvsi0wmv84i6y1fr79k15dxwy6"))
4106 (modules '((guix build utils)))
4109 ;; Delete bundled kseq.
4110 ;; TODO: Also delete bundled murmurhash and open bloom filter.
4111 (delete-file "src/mash/kseq.h")
4113 (build-system gnu-build-system)
4115 `(#:tests? #f ; No tests.
4118 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
4119 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
4120 #:make-flags (list "CC=gcc")
4122 (modify-phases %standard-phases
4123 (add-after 'unpack 'fix-includes
4125 (substitute* '("src/mash/Sketch.cpp"
4126 "src/mash/CommandFind.cpp"
4127 "src/mash/CommandScreen.cpp")
4128 (("^#include \"kseq\\.h\"")
4129 "#include \"htslib/kseq.h\""))
4131 (add-after 'fix-includes 'use-c++14
4133 ;; capnproto 0.7 requires c++14 to build
4134 (substitute* "configure.ac"
4135 (("c\\+\\+11") "c++14"))
4136 (substitute* "Makefile.in"
4137 (("c\\+\\+11") "c++14"))
4140 `(("autoconf" ,autoconf)
4141 ;; Capnproto and htslib are statically embedded in the final
4142 ;; application. Therefore we also list their licenses, below.
4143 ("capnproto" ,capnproto)
4144 ("htslib" ,htslib)))
4148 (supported-systems '("x86_64-linux"))
4149 (home-page "https://mash.readthedocs.io")
4150 (synopsis "Fast genome and metagenome distance estimation using MinHash")
4151 (description "Mash is a fast sequence distance estimator that uses the
4152 MinHash algorithm and is designed to work with genomes and metagenomes in the
4153 form of assemblies or reads.")
4154 (license (list license:bsd-3 ; Mash
4155 license:expat ; HTSlib and capnproto
4156 license:public-domain ; MurmurHash 3
4157 license:cpl1.0)))) ; Open Bloom Filter
4159 (define-public metabat
4167 (url "https://bitbucket.org/berkeleylab/metabat.git")
4168 (commit (string-append "v" version))))
4169 (file-name (git-file-name name version))
4172 "0hyg2smw1nz69mfvjpk45xyyychmda92c80a0cv7baji84ri4iyn"))
4173 (patches (search-patches "metabat-fix-compilation.patch"))))
4174 (build-system scons-build-system)
4176 `(#:scons ,scons-python2
4178 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
4179 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
4180 #:tests? #f ;; Tests are run during the build phase.
4182 (modify-phases %standard-phases
4183 (add-after 'unpack 'fix-includes
4185 (substitute* "src/BamUtils.h"
4186 (("^#include \"bam/bam\\.h\"")
4187 "#include \"samtools/bam.h\"")
4188 (("^#include \"bam/sam\\.h\"")
4189 "#include \"samtools/sam.h\""))
4190 (substitute* "src/KseqReader.h"
4191 (("^#include \"bam/kseq\\.h\"")
4192 "#include \"htslib/kseq.h\""))
4194 (add-after 'unpack 'fix-scons
4195 (lambda* (#:key inputs #:allow-other-keys)
4196 (substitute* "SConstruct"
4197 (("^htslib_dir += 'samtools'")
4198 (string-append "htslib_dir = '"
4199 (assoc-ref inputs "htslib")
4201 (("^samtools_dir = 'samtools'")
4202 (string-append "samtools_dir = '"
4203 (assoc-ref inputs "samtools")
4205 (("^findStaticOrShared\\('bam', hts_lib")
4206 (string-append "findStaticOrShared('bam', '"
4207 (assoc-ref inputs "samtools")
4209 ;; Do not distribute README.
4210 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
4215 ("samtools" ,samtools)
4218 (home-page "https://bitbucket.org/berkeleylab/metabat")
4220 "Reconstruction of single genomes from complex microbial communities")
4222 "Grouping large genomic fragments assembled from shotgun metagenomic
4223 sequences to deconvolute complex microbial communities, or metagenome binning,
4224 enables the study of individual organisms and their interactions. MetaBAT is
4225 an automated metagenome binning software, which integrates empirical
4226 probabilistic distances of genome abundance and tetranucleotide frequency.")
4227 ;; The source code contains inline assembly.
4228 (supported-systems '("x86_64-linux" "i686-linux"))
4229 (license (license:non-copyleft "file://license.txt"
4230 "See license.txt in the distribution."))))
4232 (define-public minced
4239 (url "https://github.com/ctSkennerton/minced.git")
4241 (file-name (git-file-name name version))
4244 "1f5h9him0gd355cnx7p6pnxpknhckd4g0v62mg8zyhfbx9as25fv"))))
4245 (build-system gnu-build-system)
4247 `(#:test-target "test"
4249 (modify-phases %standard-phases
4251 (add-before 'check 'fix-test
4253 ;; Fix test for latest version.
4254 (substitute* "t/Aquifex_aeolicus_VF5.expected"
4255 (("minced:0.1.6") "minced:0.2.0"))
4257 (replace 'install ; No install target.
4258 (lambda* (#:key inputs outputs #:allow-other-keys)
4259 (let* ((out (assoc-ref outputs "out"))
4260 (bin (string-append out "/bin"))
4261 (wrapper (string-append bin "/minced")))
4262 ;; Minced comes with a wrapper script that tries to figure out where
4263 ;; it is located before running the JAR. Since these paths are known
4264 ;; to us, we build our own wrapper to avoid coreutils dependency.
4265 (install-file "minced.jar" bin)
4266 (with-output-to-file wrapper
4270 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
4271 (assoc-ref inputs "jre") "/bin/java -jar "
4272 bin "/minced.jar \"$@\"\n"))))
4273 (chmod wrapper #o555))
4276 `(("jdk" ,icedtea "jdk")))
4279 ("jre" ,icedtea "out")))
4280 (home-page "https://github.com/ctSkennerton/minced")
4281 (synopsis "Mining CRISPRs in Environmental Datasets")
4283 "MinCED is a program to find Clustered Regularly Interspaced Short
4284 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
4285 unassembled metagenomic reads, but is mainly designed for full genomes and
4286 assembled metagenomic sequence.")
4287 (license license:gpl3+)))
4295 (uri (pypi-uri "misopy" version))
4298 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
4299 (modules '((guix build utils)))
4301 (substitute* "setup.py"
4302 ;; Use setuptools, or else the executables are not
4304 (("distutils.core") "setuptools")
4305 ;; use "gcc" instead of "cc" for compilation
4307 "cc.set_executables(
4311 linker_so='gcc -shared'); defines"))
4313 (build-system python-build-system)
4315 `(#:python ,python-2 ; only Python 2 is supported
4316 #:tests? #f)) ; no "test" target
4318 `(("samtools" ,samtools)
4319 ("python-numpy" ,python2-numpy)
4320 ("python-pysam" ,python2-pysam)
4321 ("python-scipy" ,python2-scipy)
4322 ("python-matplotlib" ,python2-matplotlib)))
4324 `(("python-mock" ,python2-mock) ;for tests
4325 ("python-pytz" ,python2-pytz))) ;for tests
4326 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
4327 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
4329 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
4330 the expression level of alternatively spliced genes from RNA-Seq data, and
4331 identifies differentially regulated isoforms or exons across samples. By
4332 modeling the generative process by which reads are produced from isoforms in
4333 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
4334 that a read originated from a particular isoform.")
4335 (license license:gpl2)))
4337 (define-public muscle
4340 (version "3.8.1551")
4342 (method url-fetch/tarbomb)
4344 "http://www.drive5.com/muscle/muscle_src_"
4348 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
4349 (build-system gnu-build-system)
4351 `(#:make-flags (list "LDLIBS = -lm")
4353 (modify-phases %standard-phases
4356 ;; There are no tests, so just test if it runs.
4357 (lambda _ (invoke "./muscle" "-version") #t))
4359 (lambda* (#:key outputs #:allow-other-keys)
4360 (let* ((out (assoc-ref outputs "out"))
4361 (bin (string-append out "/bin")))
4362 (install-file "muscle" bin)
4364 (home-page "http://www.drive5.com/muscle")
4365 (synopsis "Multiple sequence alignment program")
4367 "MUSCLE aims to be a fast and accurate multiple sequence alignment
4368 program for nucleotide and protein sequences.")
4369 ;; License information found in 'muscle -h' and usage.cpp.
4370 (license license:public-domain)))
4372 (define-public newick-utils
4373 ;; There are no recent releases so we package from git.
4374 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
4376 (name "newick-utils")
4377 (version (string-append "1.6-1." (string-take commit 8)))
4381 (url "https://github.com/tjunier/newick_utils.git")
4383 (file-name (string-append name "-" version "-checkout"))
4386 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4387 (build-system gnu-build-system)
4389 ;; XXX: TODO: Enable Lua and Guile bindings.
4390 ;; https://github.com/tjunier/newick_utils/issues/13
4391 `(("libxml2" ,libxml2)
4395 `(("autoconf" ,autoconf)
4396 ("automake" ,automake)
4397 ("libtool" ,libtool)))
4398 (synopsis "Programs for working with newick format phylogenetic trees")
4400 "Newick-utils is a suite of utilities for processing phylogenetic trees
4401 in Newick format. Functions include re-rooting, extracting subtrees,
4402 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4403 (home-page "https://github.com/tjunier/newick_utils")
4404 (license license:bsd-3))))
4413 "https://github.com/wwood/OrfM/releases/download/v"
4414 version "/orfm-" version ".tar.gz"))
4417 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4418 (build-system gnu-build-system)
4419 (inputs `(("zlib" ,zlib)))
4421 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4422 ("ruby-rspec" ,ruby-rspec)
4424 (synopsis "Simple and not slow open reading frame (ORF) caller")
4426 "An ORF caller finds stretches of DNA that, when translated, are not
4427 interrupted by stop codons. OrfM finds and prints these ORFs.")
4428 (home-page "https://github.com/wwood/OrfM")
4429 (license license:lgpl3+)))
4431 (define-public python2-pbcore
4433 (name "python2-pbcore")
4437 (uri (pypi-uri "pbcore" version))
4440 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4441 (build-system python-build-system)
4442 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
4444 `(("python-cython" ,python2-cython)
4445 ("python-numpy" ,python2-numpy)
4446 ("python-pysam" ,python2-pysam)
4447 ("python-h5py" ,python2-h5py)))
4449 `(("python-nose" ,python2-nose)
4450 ("python-sphinx" ,python2-sphinx)
4451 ("python-pyxb" ,python2-pyxb)))
4452 (home-page "http://pacificbiosciences.github.io/pbcore/")
4453 (synopsis "Library for reading and writing PacBio data files")
4455 "The pbcore package provides Python APIs for interacting with PacBio data
4456 files and writing bioinformatics applications.")
4457 (license license:bsd-3)))
4459 (define-public python2-warpedlmm
4461 (name "python2-warpedlmm")
4466 (uri (pypi-uri "WarpedLMM" version ".zip"))
4469 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4470 (build-system python-build-system)
4472 `(#:python ,python-2)) ; requires Python 2.7
4474 `(("python-scipy" ,python2-scipy)
4475 ("python-numpy" ,python2-numpy)
4476 ("python-matplotlib" ,python2-matplotlib)
4477 ("python-fastlmm" ,python2-fastlmm)
4478 ("python-pandas" ,python2-pandas)
4479 ("python-pysnptools" ,python2-pysnptools)))
4481 `(("python-mock" ,python2-mock)
4482 ("python-nose" ,python2-nose)
4484 (home-page "https://github.com/PMBio/warpedLMM")
4485 (synopsis "Implementation of warped linear mixed models")
4487 "WarpedLMM is a Python implementation of the warped linear mixed model,
4488 which automatically learns an optimal warping function (or transformation) for
4489 the phenotype as it models the data.")
4490 (license license:asl2.0)))
4492 (define-public pbtranscript-tofu
4493 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
4495 (name "pbtranscript-tofu")
4496 (version (string-append "2.2.3." (string-take commit 7)))
4500 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
4502 (file-name (string-append name "-" version "-checkout"))
4505 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
4506 (modules '((guix build utils)))
4509 ;; remove bundled Cython sources
4510 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
4512 (build-system python-build-system)
4514 `(#:python ,python-2
4515 ;; FIXME: Tests fail with "No such file or directory:
4516 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
4519 (modify-phases %standard-phases
4520 (add-after 'unpack 'enter-directory
4522 (chdir "pbtranscript-tofu/pbtranscript/")
4524 ;; With setuptools version 18.0 and later this setup.py hack causes
4525 ;; a build error, so we disable it.
4526 (add-after 'enter-directory 'patch-setuppy
4528 (substitute* "setup.py"
4529 (("if 'setuptools.extension' in sys.modules:")
4533 `(("python-numpy" ,python2-numpy)
4534 ("python-bx-python" ,python2-bx-python)
4535 ("python-networkx" ,python2-networkx)
4536 ("python-scipy" ,python2-scipy)
4537 ("python-pbcore" ,python2-pbcore)
4538 ("python-h5py" ,python2-h5py)))
4540 `(("python-cython" ,python2-cython)
4541 ("python-nose" ,python2-nose)))
4542 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4543 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4545 "pbtranscript-tofu contains scripts to analyze transcriptome data
4546 generated using the PacBio Iso-Seq protocol.")
4547 (license license:bsd-3))))
4549 (define-public prank
4556 "http://wasabiapp.org/download/prank/prank.source."
4560 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
4561 (build-system gnu-build-system)
4564 (modify-phases %standard-phases
4565 (add-after 'unpack 'enter-src-dir
4569 (add-after 'unpack 'remove-m64-flag
4570 ;; Prank will build with the correct 'bit-ness' without this flag
4571 ;; and this allows building on 32-bit machines.
4572 (lambda _ (substitute* "src/Makefile"
4577 (lambda* (#:key outputs #:allow-other-keys)
4578 (let* ((out (assoc-ref outputs "out"))
4579 (bin (string-append out "/bin"))
4580 (man (string-append out "/share/man/man1"))
4581 (path (string-append
4582 (assoc-ref %build-inputs "mafft") "/bin:"
4583 (assoc-ref %build-inputs "exonerate") "/bin:"
4584 (assoc-ref %build-inputs "bppsuite") "/bin")))
4585 (install-file "prank" bin)
4586 (wrap-program (string-append bin "/prank")
4587 `("PATH" ":" prefix (,path)))
4588 (install-file "prank.1" man))
4592 ("exonerate" ,exonerate)
4593 ("bppsuite" ,bppsuite)))
4594 (home-page "http://wasabiapp.org/software/prank/")
4595 (synopsis "Probabilistic multiple sequence alignment program")
4597 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4598 codon and amino-acid sequences. It is based on a novel algorithm that treats
4599 insertions correctly and avoids over-estimation of the number of deletion
4600 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4601 in phylogenetics and correctly takes into account the evolutionary distances
4602 between sequences. Lastly, PRANK allows for defining a potential structure
4603 for sequences to be aligned and then, simultaneously with the alignment,
4604 predicts the locations of structural units in the sequences.")
4605 (license license:gpl2+)))
4607 (define-public proteinortho
4609 (name "proteinortho")
4616 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4617 version "_src.tar.gz"))
4620 "1wl0dawpssqwfjvr651r4wlww8hhjin8nba6xh71ks7sbypx886j"))))
4621 (build-system gnu-build-system)
4623 `(#:test-target "test"
4625 (modify-phases %standard-phases
4627 ;; There is no configure script, so we modify the Makefile directly.
4628 (lambda* (#:key outputs #:allow-other-keys)
4629 (substitute* "Makefile"
4632 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4634 (add-before 'install 'make-install-directory
4635 ;; The install directory is not created during 'make install'.
4636 (lambda* (#:key outputs #:allow-other-keys)
4637 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4639 (add-after 'install 'wrap-programs
4640 (lambda* (#:key inputs outputs #:allow-other-keys)
4641 (let* ((path (getenv "PATH"))
4642 (out (assoc-ref outputs "out"))
4643 (binary (string-append out "/bin/proteinortho5.pl")))
4644 (wrap-program binary `("PATH" ":" prefix (,path))))
4648 ("python" ,python-2)
4649 ("blast+" ,blast+)))
4650 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4651 (synopsis "Detect orthologous genes across species")
4653 "Proteinortho is a tool to detect orthologous genes across different
4654 species. For doing so, it compares similarities of given gene sequences and
4655 clusters them to find significant groups. The algorithm was designed to handle
4656 large-scale data and can be applied to hundreds of species at once.")
4657 (license license:gpl2+)))
4659 (define-public pyicoteo
4667 (url "https://bitbucket.org/regulatorygenomicsupf/pyicoteo.git")
4668 (commit (string-append "v" version))))
4669 (file-name (git-file-name name version))
4672 "0hz5g8d25lbjy1wpscr490l0lmyvaix893hhax4fxnh1h9w34w8p"))))
4673 (build-system python-build-system)
4675 `(#:python ,python-2 ; does not work with Python 3
4676 #:tests? #f)) ; there are no tests
4678 `(("python2-matplotlib" ,python2-matplotlib)))
4679 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4680 (synopsis "Analyze high-throughput genetic sequencing data")
4682 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4683 sequencing data. It works with genomic coordinates. There are currently six
4684 different command-line tools:
4687 @item pyicoregion: for generating exploratory regions automatically;
4688 @item pyicoenrich: for differential enrichment between two conditions;
4689 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4690 @item pyicos: for genomic coordinates manipulation;
4691 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4692 @item pyicount: to count how many reads from N experiment files overlap in a
4694 @item pyicotrocol: to combine operations from pyicoteo.
4696 (license license:gpl3+)))
4698 (define-public prodigal
4705 (url "https://github.com/hyattpd/Prodigal.git")
4706 (commit (string-append "v" version))))
4707 (file-name (git-file-name name version))
4710 "1fs1hqk83qjbjhrvhw6ni75zakx5ki1ayy3v6wwkn3xvahc9hi5s"))))
4711 (build-system gnu-build-system)
4713 `(#:tests? #f ;no check target
4714 #:make-flags (list (string-append "INSTALLDIR="
4715 (assoc-ref %outputs "out")
4718 (modify-phases %standard-phases
4719 (delete 'configure))))
4720 (home-page "http://prodigal.ornl.gov")
4721 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
4723 "Prodigal runs smoothly on finished genomes, draft genomes, and
4724 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
4725 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
4726 partial genes, and identifies translation initiation sites.")
4727 (license license:gpl3+)))
4729 (define-public roary
4737 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
4741 "0qxrds9wx7cfhlkihrp6697kx0flhhxymap9fwan0b3rbdhcnmff"))))
4742 (build-system perl-build-system)
4745 (modify-phases %standard-phases
4750 ;; The tests are not run by default, so we run each test file
4752 (setenv "PATH" (string-append (getcwd) "/bin" ":"
4754 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
4755 (getenv "PERL5LIB")))
4756 (for-each (lambda (file)
4757 (display file)(display "\n")
4758 (invoke "perl" file))
4759 (find-files "t" ".*\\.t$"))
4762 ;; There is no 'install' target in the Makefile.
4763 (lambda* (#:key outputs #:allow-other-keys)
4764 (let* ((out (assoc-ref outputs "out"))
4765 (bin (string-append out "/bin"))
4766 (perl (string-append out "/lib/perl5/site_perl"))
4767 (roary-plots "contrib/roary_plots"))
4770 (copy-recursively "bin" bin)
4771 (copy-recursively "lib" perl)
4773 (add-after 'install 'wrap-programs
4774 (lambda* (#:key inputs outputs #:allow-other-keys)
4775 (let* ((out (assoc-ref outputs "out"))
4776 (perl5lib (getenv "PERL5LIB"))
4777 (path (getenv "PATH")))
4778 (for-each (lambda (prog)
4779 (let ((binary (string-append out "/" prog)))
4780 (wrap-program binary
4781 `("PERL5LIB" ":" prefix
4782 (,(string-append perl5lib ":" out
4783 "/lib/perl5/site_perl"))))
4784 (wrap-program binary
4786 (,(string-append path ":" out "/bin"))))))
4787 (find-files "bin" ".*[^R]$"))
4789 (string-append out "/bin/roary-create_pan_genome_plots.R"))
4790 (r-site-lib (getenv "R_LIBS_SITE"))
4792 (string-append (assoc-ref inputs "coreutils") "/bin")))
4794 `("R_LIBS_SITE" ":" prefix
4795 (,(string-append r-site-lib ":" out "/site-library/"))))
4798 (,(string-append coreutils-path ":" out "/bin"))))))
4801 `(("perl-env-path" ,perl-env-path)
4802 ("perl-test-files" ,perl-test-files)
4803 ("perl-test-most" ,perl-test-most)
4804 ("perl-test-output" ,perl-test-output)))
4806 `(("perl-array-utils" ,perl-array-utils)
4807 ("bioperl" ,bioperl-minimal)
4808 ("perl-digest-md5-file" ,perl-digest-md5-file)
4809 ("perl-exception-class" ,perl-exception-class)
4810 ("perl-file-find-rule" ,perl-file-find-rule)
4811 ("perl-file-grep" ,perl-file-grep)
4812 ("perl-file-slurper" ,perl-file-slurper)
4813 ("perl-file-which" ,perl-file-which)
4814 ("perl-graph" ,perl-graph)
4815 ("perl-graph-readwrite" ,perl-graph-readwrite)
4816 ("perl-log-log4perl" ,perl-log-log4perl)
4817 ("perl-moose" ,perl-moose)
4818 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
4819 ("perl-text-csv" ,perl-text-csv)
4820 ("bedtools" ,bedtools)
4824 ("parallel" ,parallel)
4827 ("fasttree" ,fasttree)
4831 ("r-minimal" ,r-minimal)
4832 ("r-ggplot2" ,r-ggplot2)
4833 ("coreutils" ,coreutils)))
4834 (home-page "http://sanger-pathogens.github.io/Roary")
4835 (synopsis "High speed stand-alone pan genome pipeline")
4837 "Roary is a high speed stand alone pan genome pipeline, which takes
4838 annotated assemblies in GFF3 format (produced by the Prokka program) and
4839 calculates the pan genome. Using a standard desktop PC, it can analyse
4840 datasets with thousands of samples, without compromising the quality of the
4841 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
4842 single processor. Roary is not intended for metagenomics or for comparing
4843 extremely diverse sets of genomes.")
4844 (license license:gpl3)))
4846 (define-public raxml
4854 (url "https://github.com/stamatak/standard-RAxML.git")
4855 (commit (string-append "v" version))))
4856 (file-name (git-file-name name version))
4859 "1jqjzhch0rips0vp04prvb8vmc20c5pdmsqn8knadcf91yy859fh"))))
4860 (build-system gnu-build-system)
4862 `(#:tests? #f ; There are no tests.
4863 ;; Use 'standard' Makefile rather than SSE or AVX ones.
4864 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
4866 (modify-phases %standard-phases
4869 (lambda* (#:key outputs #:allow-other-keys)
4870 (let* ((out (assoc-ref outputs "out"))
4871 (bin (string-append out "/bin"))
4872 (executable "raxmlHPC-HYBRID"))
4873 (install-file executable bin)
4874 (symlink (string-append bin "/" executable) "raxml"))
4877 `(("openmpi" ,openmpi)))
4878 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
4879 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
4881 "RAxML is a tool for phylogenetic analysis and post-analysis of large
4883 ;; The source includes x86 specific code
4884 (supported-systems '("x86_64-linux" "i686-linux"))
4885 (license license:gpl2+)))
4895 (url "https://github.com/deweylab/RSEM.git")
4896 (commit (string-append "v" version))))
4898 (base32 "1jlq11d1p8qp64w75yj8cnbbd1a93viq10pzsbwal7vdn8fg13j1"))
4899 (file-name (git-file-name name version))
4900 (modules '((guix build utils)))
4903 ;; remove bundled copy of boost and samtools
4904 (delete-file-recursively "boost")
4905 (delete-file-recursively "samtools-1.3")
4907 (build-system gnu-build-system)
4909 `(#:tests? #f ;no "check" target
4911 (list (string-append "BOOST="
4912 (assoc-ref %build-inputs "boost")
4914 (string-append "SAMHEADERS="
4915 (assoc-ref %build-inputs "htslib")
4916 "/include/htslib/sam.h")
4917 (string-append "SAMLIBS="
4918 (assoc-ref %build-inputs "htslib")
4921 (modify-phases %standard-phases
4922 ;; No "configure" script.
4923 ;; Do not build bundled samtools library.
4926 (substitute* "Makefile"
4927 (("^all : \\$\\(PROGRAMS\\).*") "all: $(PROGRAMS)\n")
4928 (("^\\$\\(SAMLIBS\\).*") ""))
4931 (lambda* (#:key outputs #:allow-other-keys)
4932 (let* ((out (string-append (assoc-ref outputs "out")))
4933 (bin (string-append out "/bin/"))
4934 (perl (string-append out "/lib/perl5/site_perl")))
4937 (for-each (lambda (file)
4938 (install-file file bin))
4939 (find-files "." "rsem-.*"))
4940 (install-file "rsem_perl_utils.pm" perl))
4942 (add-after 'install 'wrap-program
4943 (lambda* (#:key outputs #:allow-other-keys)
4944 (let ((out (assoc-ref outputs "out")))
4945 (for-each (lambda (prog)
4946 (wrap-program (string-append out "/bin/" prog)
4947 `("PERL5LIB" ":" prefix
4948 (,(string-append out "/lib/perl5/site_perl")))))
4949 '("rsem-calculate-expression"
4951 "rsem-generate-data-matrix"
4952 "rsem-generate-ngvector"
4953 "rsem-plot-transcript-wiggles"
4954 "rsem-prepare-reference"
4956 "rsem-run-prsem-testing-procedure")))
4960 ("r-minimal" ,r-minimal)
4962 ("htslib" ,htslib-1.3)
4964 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
4965 (synopsis "Estimate gene expression levels from RNA-Seq data")
4967 "RSEM is a software package for estimating gene and isoform expression
4968 levels from RNA-Seq data. The RSEM package provides a user-friendly
4969 interface, supports threads for parallel computation of the EM algorithm,
4970 single-end and paired-end read data, quality scores, variable-length reads and
4971 RSPD estimation. In addition, it provides posterior mean and 95% credibility
4972 interval estimates for expression levels. For visualization, it can generate
4973 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
4974 (license license:gpl3+)))
4976 (define-public rseqc
4984 (string-append "mirror://sourceforge/rseqc/"
4985 "RSeQC-" version ".tar.gz"))
4987 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
4988 (modules '((guix build utils)))
4991 ;; remove bundled copy of pysam
4992 (delete-file-recursively "lib/pysam")
4993 (substitute* "setup.py"
4994 ;; remove dependency on outdated "distribute" module
4995 (("^from distribute_setup import use_setuptools") "")
4996 (("^use_setuptools\\(\\)") "")
4997 ;; do not use bundled copy of pysam
4998 (("^have_pysam = False") "have_pysam = True"))
5000 (build-system python-build-system)
5001 (arguments `(#:python ,python-2))
5003 `(("python-cython" ,python2-cython)
5004 ("python-pysam" ,python2-pysam)
5005 ("python-numpy" ,python2-numpy)
5008 `(("python-nose" ,python2-nose)))
5009 (home-page "http://rseqc.sourceforge.net/")
5010 (synopsis "RNA-seq quality control package")
5012 "RSeQC provides a number of modules that can comprehensively evaluate
5013 high throughput sequence data, especially RNA-seq data. Some basic modules
5014 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
5015 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
5016 distribution, coverage uniformity, strand specificity, etc.")
5017 (license license:gpl3+)))
5020 ;; There are no release tarballs. According to the installation
5021 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
5022 ;; stable release is identified by this changeset ID.
5023 (let ((changeset "2329130")
5027 (version (string-append "0-" revision "." changeset))
5031 (url "https://bitbucket.org/libsleipnir/sleipnir")
5032 (changeset changeset)))
5033 (file-name (string-append name "-" version "-checkout"))
5036 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
5037 (build-system gnu-build-system)
5039 `(#:modules ((srfi srfi-1)
5040 (guix build gnu-build-system)
5043 (let ((dirs '("SeekMiner"
5049 (modify-phases %standard-phases
5052 (substitute* "gen_tools_am"
5053 (("/usr/bin/env.*") (which "perl")))
5054 (invoke "bash" "gen_auto")
5056 (add-after 'build 'build-additional-tools
5057 (lambda* (#:key make-flags #:allow-other-keys)
5058 (for-each (lambda (dir)
5059 (with-directory-excursion (string-append "tools/" dir)
5060 (apply invoke "make" make-flags)))
5063 (add-after 'install 'install-additional-tools
5064 (lambda* (#:key make-flags #:allow-other-keys)
5065 (for-each (lambda (dir)
5066 (with-directory-excursion (string-append "tools/" dir)
5067 (apply invoke `("make" ,@make-flags "install"))))
5074 ("readline" ,readline)
5075 ("gengetopt" ,gengetopt)
5076 ("log4cpp" ,log4cpp)))
5078 `(("autoconf" ,autoconf)
5079 ("automake" ,automake)
5081 (home-page "http://seek.princeton.edu")
5082 (synopsis "Gene co-expression search engine")
5084 "SEEK is a computational gene co-expression search engine. SEEK provides
5085 biologists with a way to navigate the massive human expression compendium that
5086 now contains thousands of expression datasets. SEEK returns a robust ranking
5087 of co-expressed genes in the biological area of interest defined by the user's
5088 query genes. It also prioritizes thousands of expression datasets according
5089 to the user's query of interest.")
5090 (license license:cc-by3.0))))
5092 (define-public samtools
5100 (string-append "mirror://sourceforge/samtools/samtools/"
5101 version "/samtools-" version ".tar.bz2"))
5104 "10ilqbmm7ri8z431sn90lvbjwizd0hhkf9rcqw8j823hf26nhgq8"))
5105 (modules '((guix build utils)))
5107 ;; Delete bundled htslib.
5108 (delete-file-recursively "htslib-1.9")
5110 (build-system gnu-build-system)
5112 `(#:modules ((ice-9 ftw)
5114 (guix build gnu-build-system)
5116 #:configure-flags (list "--with-ncurses")
5118 (modify-phases %standard-phases
5119 (add-after 'unpack 'patch-tests
5121 (substitute* "test/test.pl"
5122 ;; The test script calls out to /bin/bash
5123 (("/bin/bash") (which "bash")))
5125 (add-after 'install 'install-library
5126 (lambda* (#:key outputs #:allow-other-keys)
5127 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
5128 (install-file "libbam.a" lib)
5130 (add-after 'install 'install-headers
5131 (lambda* (#:key outputs #:allow-other-keys)
5132 (let ((include (string-append (assoc-ref outputs "out")
5133 "/include/samtools/")))
5134 (for-each (lambda (file)
5135 (install-file file include))
5136 (scandir "." (lambda (name) (string-match "\\.h$" name))))
5138 (native-inputs `(("pkg-config" ,pkg-config)))
5140 `(("htslib" ,htslib)
5141 ("ncurses" ,ncurses)
5145 (home-page "http://samtools.sourceforge.net")
5146 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
5148 "Samtools implements various utilities for post-processing nucleotide
5149 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
5150 variant calling (in conjunction with bcftools), and a simple alignment
5152 (license license:expat)))
5154 (define-public samtools-0.1
5155 ;; This is the most recent version of the 0.1 line of samtools. The input
5156 ;; and output formats differ greatly from that used and produced by samtools
5157 ;; 1.x and is still used in many bioinformatics pipelines.
5158 (package (inherit samtools)
5164 (string-append "mirror://sourceforge/samtools/samtools/"
5165 version "/samtools-" version ".tar.bz2"))
5167 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
5169 `(#:tests? #f ;no "check" target
5171 (list "LIBCURSES=-lncurses")
5172 ,@(substitute-keyword-arguments (package-arguments samtools)
5174 `(modify-phases ,phases
5176 (lambda* (#:key outputs #:allow-other-keys)
5177 (let ((bin (string-append
5178 (assoc-ref outputs "out") "/bin")))
5180 (install-file "samtools" bin)
5182 (delete 'patch-tests)
5183 (delete 'configure))))))))
5185 (define-public mosaik
5186 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
5191 ;; There are no release tarballs nor tags.
5194 (url "https://github.com/wanpinglee/MOSAIK.git")
5196 (file-name (string-append name "-" version))
5199 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
5200 (build-system gnu-build-system)
5202 `(#:tests? #f ; no tests
5203 #:make-flags (list "CC=gcc")
5205 (modify-phases %standard-phases
5207 (lambda _ (chdir "src") #t))
5209 (lambda* (#:key outputs #:allow-other-keys)
5210 (let ((bin (string-append (assoc-ref outputs "out")
5213 (copy-recursively "../bin" bin)
5217 ("zlib:static" ,zlib "static")
5219 (supported-systems '("x86_64-linux"))
5220 (home-page "https://github.com/wanpinglee/MOSAIK")
5221 (synopsis "Map nucleotide sequence reads to reference genomes")
5223 "MOSAIK is a program for mapping second and third-generation sequencing
5224 reads to a reference genome. MOSAIK can align reads generated by all the
5225 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
5226 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
5227 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
5228 ;; code released into the public domain:
5229 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
5230 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
5231 (license (list license:gpl2+ license:public-domain)))))
5233 (define-public ngs-sdk
5240 (url "https://github.com/ncbi/ngs.git")
5242 (file-name (git-file-name name version))
5245 "17c0v1nah3g3d2ib5bbi0vhma1ghd6vb9xycavqsh64lhp840rk3"))))
5246 (build-system gnu-build-system)
5248 `(#:parallel-build? #f ; not supported
5249 #:tests? #f ; no "check" target
5251 (modify-phases %standard-phases
5253 (lambda* (#:key outputs #:allow-other-keys)
5254 (let ((out (assoc-ref outputs "out")))
5255 ;; Allow 'konfigure.perl' to find 'package.prl'.
5257 (string-append ".:" (getenv "PERL5LIB")))
5259 ;; The 'configure' script doesn't recognize things like
5260 ;; '--enable-fast-install'.
5261 (invoke "./configure"
5262 (string-append "--build-prefix=" (getcwd) "/build")
5263 (string-append "--prefix=" out))
5265 (add-after 'unpack 'enter-dir
5266 (lambda _ (chdir "ngs-sdk") #t)))))
5267 (native-inputs `(("perl" ,perl)))
5268 ;; According to the test
5269 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
5270 ;; in ngs-sdk/setup/konfigure.perl
5271 (supported-systems '("i686-linux" "x86_64-linux"))
5272 (home-page "https://github.com/ncbi/ngs")
5273 (synopsis "API for accessing Next Generation Sequencing data")
5275 "NGS is a domain-specific API for accessing reads, alignments and pileups
5276 produced from Next Generation Sequencing. The API itself is independent from
5277 any particular back-end implementation, and supports use of multiple back-ends
5279 (license license:public-domain)))
5281 (define-public java-ngs
5282 (package (inherit ngs-sdk)
5285 `(,@(substitute-keyword-arguments
5286 `(#:modules ((guix build gnu-build-system)
5290 ,@(package-arguments ngs-sdk))
5292 `(modify-phases ,phases
5293 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5295 `(("jdk" ,icedtea "jdk")
5296 ("ngs-sdk" ,ngs-sdk)))
5297 (synopsis "Java bindings for NGS SDK")))
5299 (define-public ncbi-vdb
5306 (url "https://github.com/ncbi/ncbi-vdb.git")
5308 (file-name (git-file-name name version))
5311 "1l4ny67nxwv1lagk9wwjbrgm7ln7adci6dnpc7k1yaln6shj0qpm"))))
5312 (build-system gnu-build-system)
5314 `(#:parallel-build? #f ; not supported
5315 #:tests? #f ; no "check" target
5317 (modify-phases %standard-phases
5318 (add-after 'unpack 'make-files-writable
5319 (lambda _ (for-each make-file-writable (find-files "." ".*")) #t))
5320 (add-before 'configure 'set-perl-search-path
5322 ;; Work around "dotless @INC" build failure.
5324 (string-append (getcwd) "/setup:"
5325 (getenv "PERL5LIB")))
5328 (lambda* (#:key inputs outputs #:allow-other-keys)
5329 (let ((out (assoc-ref outputs "out")))
5330 ;; Override include path for libmagic
5331 (substitute* "setup/package.prl"
5332 (("name => 'magic', Include => '/usr/include'")
5333 (string-append "name=> 'magic', Include => '"
5334 (assoc-ref inputs "libmagic")
5337 ;; Install kdf5 library (needed by sra-tools)
5338 (substitute* "build/Makefile.install"
5339 (("LIBRARIES_TO_INSTALL =")
5340 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5342 (substitute* "build/Makefile.env"
5343 (("CFLAGS =" prefix)
5344 (string-append prefix "-msse2 ")))
5346 ;; Override search path for ngs-java
5347 (substitute* "setup/package.prl"
5348 (("/usr/local/ngs/ngs-java")
5349 (assoc-ref inputs "java-ngs")))
5351 ;; The 'configure' script doesn't recognize things like
5352 ;; '--enable-fast-install'.
5353 (invoke "./configure"
5354 (string-append "--build-prefix=" (getcwd) "/build")
5355 (string-append "--prefix=" (assoc-ref outputs "out"))
5356 (string-append "--debug")
5357 (string-append "--with-xml2-prefix="
5358 (assoc-ref inputs "libxml2"))
5359 (string-append "--with-ngs-sdk-prefix="
5360 (assoc-ref inputs "ngs-sdk"))
5361 (string-append "--with-hdf5-prefix="
5362 (assoc-ref inputs "hdf5")))
5364 (add-after 'install 'install-interfaces
5365 (lambda* (#:key outputs #:allow-other-keys)
5366 ;; Install interface libraries. On i686 the interface libraries
5367 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5368 ;; architecture name ("i386") instead of the target system prefix
5370 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5371 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5372 ,(system->linux-architecture
5373 (or (%current-target-system)
5376 (string-append (assoc-ref outputs "out")
5378 ;; Install interface headers
5379 (copy-recursively "interfaces"
5380 (string-append (assoc-ref outputs "out")
5383 ;; These files are needed by sra-tools.
5384 (add-after 'install 'install-configuration-files
5385 (lambda* (#:key outputs #:allow-other-keys)
5386 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5388 (install-file "libs/kfg/default.kfg" target)
5389 (install-file "libs/kfg/certs.kfg" target))
5392 `(("libxml2" ,libxml2)
5393 ("ngs-sdk" ,ngs-sdk)
5394 ("java-ngs" ,java-ngs)
5397 (native-inputs `(("perl" ,perl)))
5398 ;; NCBI-VDB requires SSE capability.
5399 (supported-systems '("i686-linux" "x86_64-linux"))
5400 (home-page "https://github.com/ncbi/ncbi-vdb")
5401 (synopsis "Database engine for genetic information")
5403 "The NCBI-VDB library implements a highly compressed columnar data
5404 warehousing engine that is most often used to store genetic information.
5405 Databases are stored in a portable image within the file system, and can be
5406 accessed/downloaded on demand across HTTP.")
5407 (license license:public-domain)))
5409 (define-public plink
5417 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5418 version "-src.zip"))
5420 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5421 (patches (search-patches "plink-1.07-unclobber-i.patch"
5422 "plink-endian-detection.patch"))))
5423 (build-system gnu-build-system)
5425 '(#:tests? #f ;no "check" target
5426 #:make-flags (list (string-append "LIB_LAPACK="
5427 (assoc-ref %build-inputs "lapack")
5428 "/lib/liblapack.so")
5431 ;; disable phoning home
5434 (modify-phases %standard-phases
5435 ;; no "configure" script
5438 (lambda* (#:key outputs #:allow-other-keys)
5439 (let ((bin (string-append (assoc-ref outputs "out")
5441 (install-file "plink" bin)
5445 ("lapack" ,lapack)))
5447 `(("unzip" ,unzip)))
5448 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5449 (synopsis "Whole genome association analysis toolset")
5451 "PLINK is a whole genome association analysis toolset, designed to
5452 perform a range of basic, large-scale analyses in a computationally efficient
5453 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5454 so there is no support for steps prior to this (e.g. study design and
5455 planning, generating genotype or CNV calls from raw data). Through
5456 integration with gPLINK and Haploview, there is some support for the
5457 subsequent visualization, annotation and storage of results.")
5458 ;; Code is released under GPLv2, except for fisher.h, which is under
5460 (license (list license:gpl2 license:lgpl2.1+))))
5462 (define-public plink-ng
5463 (package (inherit plink)
5470 (url "https://github.com/chrchang/plink-ng.git")
5471 (commit (string-append "v" version))))
5472 (file-name (git-file-name name version))
5474 (base32 "02npdwgkpfkdnhw819rhj5kw02a5k5m90b14zq9zzya4hyg929c0"))))
5475 (build-system gnu-build-system)
5477 '(#:tests? #f ;no "check" target
5478 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5479 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5481 "-f" "Makefile.std")
5483 (modify-phases %standard-phases
5484 (add-after 'unpack 'chdir
5485 (lambda _ (chdir "1.9") #t))
5486 (delete 'configure) ; no "configure" script
5488 (lambda* (#:key outputs #:allow-other-keys)
5489 (let ((bin (string-append (assoc-ref outputs "out")
5491 (install-file "plink" bin)
5496 ("openblas" ,openblas)))
5497 (home-page "https://www.cog-genomics.org/plink/")
5498 (license license:gpl3+)))
5500 (define-public smithlab-cpp
5501 (let ((revision "1")
5502 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
5504 (name "smithlab-cpp")
5505 (version (string-append "0." revision "." (string-take commit 7)))
5509 (url "https://github.com/smithlabcode/smithlab_cpp.git")
5511 (file-name (string-append name "-" version "-checkout"))
5514 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
5515 (build-system gnu-build-system)
5517 `(#:modules ((guix build gnu-build-system)
5520 #:tests? #f ;no "check" target
5522 (modify-phases %standard-phases
5523 (add-after 'unpack 'use-samtools-headers
5525 (substitute* '("SAM.cpp"
5527 (("sam.h") "samtools/sam.h"))
5530 (lambda* (#:key outputs #:allow-other-keys)
5531 (let* ((out (assoc-ref outputs "out"))
5532 (lib (string-append out "/lib"))
5533 (include (string-append out "/include/smithlab-cpp")))
5536 (for-each (cut install-file <> lib)
5537 (find-files "." "\\.o$"))
5538 (for-each (cut install-file <> include)
5539 (find-files "." "\\.hpp$")))
5541 (delete 'configure))))
5543 `(("samtools" ,samtools-0.1)
5545 (home-page "https://github.com/smithlabcode/smithlab_cpp")
5546 (synopsis "C++ helper library for functions used in Smith lab projects")
5548 "Smithlab CPP is a C++ library that includes functions used in many of
5549 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
5550 structures, classes for genomic regions, mapped sequencing reads, etc.")
5551 (license license:gpl3+))))
5553 (define-public preseq
5559 (uri (string-append "https://github.com/smithlabcode/preseq/"
5560 "releases/download/v" version
5561 "/preseq_v" version ".tar.bz2"))
5563 (base32 "149x9xmk1wy1gff85325yfzqc0qk4sgp1w6gbyj9cnji4x1dszbl"))
5564 (modules '((guix build utils)))
5566 ;; Remove bundled samtools.
5567 (delete-file-recursively "samtools")
5569 (build-system gnu-build-system)
5571 `(#:tests? #f ;no "check" target
5573 (modify-phases %standard-phases
5574 (delete 'configure))
5576 (list (string-append "PREFIX="
5577 (assoc-ref %outputs "out"))
5578 (string-append "LIBBAM="
5579 (assoc-ref %build-inputs "samtools")
5581 (string-append "SMITHLAB_CPP="
5582 (assoc-ref %build-inputs "smithlab-cpp")
5585 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
5588 ("samtools" ,samtools-0.1)
5589 ("smithlab-cpp" ,smithlab-cpp)
5591 (home-page "http://smithlabresearch.org/software/preseq/")
5592 (synopsis "Program for analyzing library complexity")
5594 "The preseq package is aimed at predicting and estimating the complexity
5595 of a genomic sequencing library, equivalent to predicting and estimating the
5596 number of redundant reads from a given sequencing depth and how many will be
5597 expected from additional sequencing using an initial sequencing experiment.
5598 The estimates can then be used to examine the utility of further sequencing,
5599 optimize the sequencing depth, or to screen multiple libraries to avoid low
5600 complexity samples.")
5601 (license license:gpl3+)))
5603 (define-public python-screed
5605 (name "python-screed")
5610 (uri (pypi-uri "screed" version))
5613 "148vcb7w2wr6a4w6vs2bsxanbqibxfk490zbcbg4m61s8669zdjx"))))
5614 (build-system python-build-system)
5617 (modify-phases %standard-phases
5618 ;; Tests must be run after installation, as the "screed" command does
5619 ;; not exist right after building.
5621 (add-after 'install 'check
5622 (lambda* (#:key inputs outputs #:allow-other-keys)
5623 (let ((out (assoc-ref outputs "out")))
5624 (setenv "PYTHONPATH"
5625 (string-append out "/lib/python"
5626 (string-take (string-take-right
5627 (assoc-ref inputs "python")
5630 (getenv "PYTHONPATH")))
5631 (setenv "PATH" (string-append out "/bin:" (getenv "PATH"))))
5632 (invoke "python" "setup.py" "test")
5635 `(("python-pytest" ,python-pytest)
5636 ("python-pytest-cov" ,python-pytest-cov)
5637 ("python-pytest-runner" ,python-pytest-runner)))
5639 `(("python-bz2file" ,python-bz2file)))
5640 (home-page "https://github.com/dib-lab/screed/")
5641 (synopsis "Short read sequence database utilities")
5642 (description "Screed parses FASTA and FASTQ files and generates databases.
5643 Values such as sequence name, sequence description, sequence quality and the
5644 sequence itself can be retrieved from these databases.")
5645 (license license:bsd-3)))
5647 (define-public python2-screed
5648 (package-with-python2 python-screed))
5650 (define-public sra-tools
5658 (url "https://github.com/ncbi/sra-tools.git")
5660 (file-name (git-file-name name version))
5663 "0663gcdxkziwsmlznjxysb00621rllpbz6jwsfifq7z3dj3lwm8b"))))
5664 (build-system gnu-build-system)
5666 `(#:parallel-build? #f ; not supported
5667 #:tests? #f ; no "check" target
5669 (list (string-append "DEFAULT_CRT="
5670 (assoc-ref %build-inputs "ncbi-vdb")
5672 (string-append "DEFAULT_KFG="
5673 (assoc-ref %build-inputs "ncbi-vdb")
5675 (string-append "VDB_LIBDIR="
5676 (assoc-ref %build-inputs "ncbi-vdb")
5677 ,(if (string-prefix? "x86_64"
5678 (or (%current-target-system)
5683 (modify-phases %standard-phases
5684 (add-before 'configure 'set-perl-search-path
5686 ;; Work around "dotless @INC" build failure.
5688 (string-append (getcwd) "/setup:"
5689 (getenv "PERL5LIB")))
5692 (lambda* (#:key inputs outputs #:allow-other-keys)
5693 ;; The build system expects a directory containing the sources and
5694 ;; raw build output of ncbi-vdb, including files that are not
5695 ;; installed. Since we are building against an installed version of
5696 ;; ncbi-vdb, the following modifications are needed.
5697 (substitute* "setup/konfigure.perl"
5698 ;; Make the configure script look for the "ilib" directory of
5699 ;; "ncbi-vdb" without first checking for the existence of a
5700 ;; matching library in its "lib" directory.
5701 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5702 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5703 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5704 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5705 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
5708 (substitute* "tools/copycat/Makefile"
5709 (("smagic-static") "lmagic"))
5711 ;; The 'configure' script doesn't recognize things like
5712 ;; '--enable-fast-install'.
5713 (invoke "./configure"
5714 (string-append "--build-prefix=" (getcwd) "/build")
5715 (string-append "--prefix=" (assoc-ref outputs "out"))
5716 (string-append "--debug")
5717 (string-append "--with-fuse-prefix="
5718 (assoc-ref inputs "fuse"))
5719 (string-append "--with-magic-prefix="
5720 (assoc-ref inputs "libmagic"))
5721 ;; TODO: building with libxml2 fails with linker errors
5722 ;; (string-append "--with-xml2-prefix="
5723 ;; (assoc-ref inputs "libxml2"))
5724 (string-append "--with-ncbi-vdb-sources="
5725 (assoc-ref inputs "ncbi-vdb"))
5726 (string-append "--with-ncbi-vdb-build="
5727 (assoc-ref inputs "ncbi-vdb"))
5728 (string-append "--with-ngs-sdk-prefix="
5729 (assoc-ref inputs "ngs-sdk"))
5730 (string-append "--with-hdf5-prefix="
5731 (assoc-ref inputs "hdf5")))
5733 (native-inputs `(("perl" ,perl)))
5735 `(("ngs-sdk" ,ngs-sdk)
5736 ("ncbi-vdb" ,ncbi-vdb)
5741 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
5742 (synopsis "Tools and libraries for reading and writing sequencing data")
5744 "The SRA Toolkit from NCBI is a collection of tools and libraries for
5745 reading of sequencing files from the Sequence Read Archive (SRA) database and
5746 writing files into the .sra format.")
5747 (license license:public-domain)))
5749 (define-public seqan
5755 (uri (string-append "https://github.com/seqan/seqan/releases/"
5756 "download/seqan-v" version
5757 "/seqan-library-" version ".tar.xz"))
5760 "19a1rlxx03qy1i1iriicly68w64yjxbv24g9gdywnfmq998v35yx"))))
5761 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5762 ;; makes sense to split the outputs.
5763 (outputs '("out" "doc"))
5764 (build-system trivial-build-system)
5766 `(#:modules ((guix build utils))
5769 (use-modules (guix build utils))
5770 (let ((tar (assoc-ref %build-inputs "tar"))
5771 (xz (assoc-ref %build-inputs "xz"))
5772 (out (assoc-ref %outputs "out"))
5773 (doc (assoc-ref %outputs "doc")))
5774 (setenv "PATH" (string-append tar "/bin:" xz "/bin"))
5775 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
5776 (chdir (string-append "seqan-library-" ,version))
5777 (copy-recursively "include" (string-append out "/include"))
5778 (copy-recursively "share" (string-append doc "/share"))
5781 `(("source" ,source)
5784 (home-page "http://www.seqan.de")
5785 (synopsis "Library for nucleotide sequence analysis")
5787 "SeqAn is a C++ library of efficient algorithms and data structures for
5788 the analysis of sequences with the focus on biological data. It contains
5789 algorithms and data structures for string representation and their
5790 manipulation, online and indexed string search, efficient I/O of
5791 bioinformatics file formats, sequence alignment, and more.")
5792 (license license:bsd-3)))
5794 (define-public seqan-1
5795 (package (inherit seqan)
5800 (uri (string-append "http://packages.seqan.de/seqan-library/"
5801 "seqan-library-" version ".tar.bz2"))
5804 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
5805 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
5806 ;; makes sense to split the outputs.
5807 (outputs '("out" "doc"))
5808 (build-system trivial-build-system)
5810 `(#:modules ((guix build utils))
5813 (use-modules (guix build utils))
5814 (let ((tar (assoc-ref %build-inputs "tar"))
5815 (bzip (assoc-ref %build-inputs "bzip2"))
5816 (out (assoc-ref %outputs "out"))
5817 (doc (assoc-ref %outputs "doc")))
5818 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
5819 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
5820 (chdir (string-append "seqan-library-" ,version))
5821 (copy-recursively "include" (string-append out "/include"))
5822 (copy-recursively "share" (string-append doc "/share"))
5825 `(("source" ,source)
5827 ("bzip2" ,bzip2)))))
5829 (define-public seqmagick
5836 (uri (pypi-uri "seqmagick" version))
5839 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
5840 (build-system python-build-system)
5842 `(("python-biopython" ,python-biopython)))
5844 `(("python-nose" ,python-nose)))
5845 (home-page "https://github.com/fhcrc/seqmagick")
5846 (synopsis "Tools for converting and modifying sequence files")
5848 "Bioinformaticians often have to convert sequence files between formats
5849 and do little manipulations on them, and it's not worth writing scripts for
5850 that. Seqmagick is a utility to expose the file format conversion in
5851 BioPython in a convenient way. Instead of having a big mess of scripts, there
5852 is one that takes arguments.")
5853 (license license:gpl3)))
5855 (define-public seqtk
5862 (url "https://github.com/lh3/seqtk.git")
5863 (commit (string-append "v" version))))
5864 (file-name (git-file-name name version))
5867 "1bfzlqa84b5s1qi22blmmw2s8xdyp9h9ydcq22pfjhh5gab3yz6l"))))
5868 (build-system gnu-build-system)
5871 (modify-phases %standard-phases
5874 ;; There are no tests, so we just run a sanity check.
5875 (lambda _ (invoke "./seqtk" "seq") #t))
5877 (lambda* (#:key outputs #:allow-other-keys)
5878 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
5879 (install-file "seqtk" bin)
5883 (home-page "https://github.com/lh3/seqtk")
5884 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
5886 "Seqtk is a fast and lightweight tool for processing sequences in the
5887 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
5888 optionally compressed by gzip.")
5889 (license license:expat)))
5891 (define-public snap-aligner
5893 (name "snap-aligner")
5894 (version "1.0beta.18")
5898 (url "https://github.com/amplab/snap.git")
5899 (commit (string-append "v" version))))
5900 (file-name (git-file-name name version))
5903 "01w3qq4wm07z73vky0cfwlmrbf50n3w722cxrlzxfi99mnb808d8"))))
5904 (build-system gnu-build-system)
5907 (modify-phases %standard-phases
5909 (replace 'check (lambda _ (invoke "./unit_tests") #t))
5911 (lambda* (#:key outputs #:allow-other-keys)
5912 (let* ((out (assoc-ref outputs "out"))
5913 (bin (string-append out "/bin")))
5914 (install-file "snap-aligner" bin)
5915 (install-file "SNAPCommand" bin)
5919 (home-page "http://snap.cs.berkeley.edu/")
5920 (synopsis "Short read DNA sequence aligner")
5922 "SNAP is a fast and accurate aligner for short DNA reads. It is
5923 optimized for modern read lengths of 100 bases or higher, and takes advantage
5924 of these reads to align data quickly through a hash-based indexing scheme.")
5925 ;; 32-bit systems are not supported by the unpatched code.
5926 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
5927 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
5928 ;; systems without a lot of memory cannot make good use of this program.
5929 (supported-systems '("x86_64-linux"))
5930 (license license:asl2.0)))
5932 (define-public sortmerna
5940 (url "https://github.com/biocore/sortmerna.git")
5942 (file-name (git-file-name name version))
5945 "0j3mbz4n25738yijmjbr5r4fyvkgm8v5vn3sshyfvmyqf5q9byqf"))))
5946 (build-system gnu-build-system)
5947 (outputs '("out" ;for binaries
5948 "db")) ;for sequence databases
5951 (modify-phases %standard-phases
5953 (lambda* (#:key outputs #:allow-other-keys)
5954 (let* ((out (assoc-ref outputs "out"))
5955 (bin (string-append out "/bin"))
5956 (db (assoc-ref outputs "db"))
5958 (string-append db "/share/sortmerna/rRNA_databases")))
5959 (install-file "sortmerna" bin)
5960 (install-file "indexdb_rna" bin)
5961 (for-each (lambda (file)
5962 (install-file file share))
5963 (find-files "rRNA_databases" ".*fasta"))
5967 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
5968 (synopsis "Biological sequence analysis tool for NGS reads")
5970 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
5971 and operational taxonomic unit (OTU) picking of next generation
5972 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
5973 allows for fast and sensitive analyses of nucleotide sequences. The main
5974 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
5975 ;; The source includes x86 specific code
5976 (supported-systems '("x86_64-linux" "i686-linux"))
5977 (license license:lgpl3)))
5986 (url "https://github.com/alexdobin/STAR.git")
5988 (file-name (string-append name "-" version "-checkout"))
5991 "1lih6cbpvnvhyvvswdhy06mwyzvwax96m723378v4z6psqzsh11d"))
5992 (modules '((guix build utils)))
5995 (substitute* "source/Makefile"
5997 ;; Remove pre-built binaries and bundled htslib sources.
5998 (delete-file-recursively "bin/MacOSX_x86_64")
5999 (delete-file-recursively "bin/Linux_x86_64")
6000 (delete-file-recursively "bin/Linux_x86_64_static")
6001 (delete-file-recursively "source/htslib")
6003 (build-system gnu-build-system)
6005 '(#:tests? #f ;no check target
6006 #:make-flags '("STAR")
6008 (modify-phases %standard-phases
6009 (add-after 'unpack 'enter-source-dir
6010 (lambda _ (chdir "source") #t))
6011 (add-after 'enter-source-dir 'make-reproducible
6013 (substitute* "Makefile"
6014 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
6015 (string-append pre "Built with Guix" post)))
6017 ;; See https://github.com/alexdobin/STAR/pull/562
6018 (add-after 'enter-source-dir 'add-missing-header
6020 (substitute* "SoloReadFeature_inputRecords.cpp"
6021 (("#include \"binarySearch2.h\"" h)
6022 (string-append h "\n#include <math.h>")))
6024 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
6026 (substitute* "Makefile"
6027 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
6029 (substitute* '("BAMfunctions.cpp"
6034 "bamRemoveDuplicates.cpp")
6035 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
6036 (string-append "#include <" header ">")))
6037 (substitute* "IncludeDefine.h"
6038 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
6039 (string-append "<" header ">")))
6042 (lambda* (#:key outputs #:allow-other-keys)
6043 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6044 (install-file "STAR" bin))
6046 (delete 'configure))))
6050 `(("htslib" ,htslib)
6052 (home-page "https://github.com/alexdobin/STAR")
6053 (synopsis "Universal RNA-seq aligner")
6055 "The Spliced Transcripts Alignment to a Reference (STAR) software is
6056 based on a previously undescribed RNA-seq alignment algorithm that uses
6057 sequential maximum mappable seed search in uncompressed suffix arrays followed
6058 by seed clustering and stitching procedure. In addition to unbiased de novo
6059 detection of canonical junctions, STAR can discover non-canonical splices and
6060 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
6062 ;; Only 64-bit systems are supported according to the README.
6063 (supported-systems '("x86_64-linux" "mips64el-linux"))
6064 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
6065 (license license:gpl3+)))
6067 (define-public subread
6073 (uri (string-append "mirror://sourceforge/subread/subread-"
6074 version "/subread-" version "-source.tar.gz"))
6077 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
6078 (build-system gnu-build-system)
6080 `(#:tests? #f ;no "check" target
6081 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
6082 ;; optimizations by default, so we override these flags such that x86_64
6083 ;; flags are only added when the build target is an x86_64 system.
6085 (list (let ((system ,(or (%current-target-system)
6087 (flags '("-ggdb" "-fomit-frame-pointer"
6088 "-ffast-math" "-funroll-loops"
6089 "-fmessage-length=0"
6090 "-O9" "-Wall" "-DMAKE_FOR_EXON"
6092 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
6093 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
6094 (if (string-prefix? "x86_64" system)
6095 (string-append "CCFLAGS=" (string-join (append flags flags64)))
6096 (string-append "CCFLAGS=" (string-join flags))))
6097 "-f" "Makefile.Linux"
6098 "CC=gcc ${CCFLAGS}")
6100 (modify-phases %standard-phases
6101 (add-after 'unpack 'enter-dir
6102 (lambda _ (chdir "src") #t))
6104 (lambda* (#:key outputs #:allow-other-keys)
6105 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6107 (copy-recursively "../bin" bin))
6109 ;; no "configure" script
6110 (delete 'configure))))
6111 (inputs `(("zlib" ,zlib)))
6112 (home-page "http://bioinf.wehi.edu.au/subread-package/")
6113 (synopsis "Tool kit for processing next-gen sequencing data")
6115 "The subread package contains the following tools: subread aligner, a
6116 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
6117 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
6118 features; exactSNP: a SNP caller that discovers SNPs by testing signals
6119 against local background noises.")
6120 (license license:gpl3+)))
6122 (define-public stringtie
6128 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
6129 "stringtie-" version ".tar.gz"))
6132 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
6133 (modules '((guix build utils)))
6136 (delete-file-recursively "samtools-0.1.18")
6138 (build-system gnu-build-system)
6140 `(#:tests? #f ;no test suite
6142 (modify-phases %standard-phases
6143 ;; no configure script
6145 (add-before 'build 'use-system-samtools
6147 (substitute* "Makefile"
6148 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
6150 (substitute* '("gclib/GBam.h"
6152 (("#include \"(bam|sam|kstring).h\"" _ header)
6153 (string-append "#include <samtools/" header ".h>")))
6155 (add-after 'unpack 'remove-duplicate-typedef
6157 ;; This typedef conflicts with the typedef in
6158 ;; glibc-2.25/include/bits/types.h
6159 (substitute* "gclib/GThreads.h"
6160 (("typedef long long __intmax_t;") ""))
6163 (lambda* (#:key outputs #:allow-other-keys)
6164 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6165 (install-file "stringtie" bin)
6168 `(("samtools" ,samtools-0.1)
6170 (home-page "http://ccb.jhu.edu/software/stringtie/")
6171 (synopsis "Transcript assembly and quantification for RNA-Seq data")
6173 "StringTie is a fast and efficient assembler of RNA-Seq sequence
6174 alignments into potential transcripts. It uses a novel network flow algorithm
6175 as well as an optional de novo assembly step to assemble and quantitate
6176 full-length transcripts representing multiple splice variants for each gene
6177 locus. Its input can include not only the alignments of raw reads used by
6178 other transcript assemblers, but also alignments of longer sequences that have
6179 been assembled from those reads. To identify differentially expressed genes
6180 between experiments, StringTie's output can be processed either by the
6181 Cuffdiff or Ballgown programs.")
6182 (license license:artistic2.0)))
6184 (define-public taxtastic
6190 (uri (pypi-uri "taxtastic" version))
6193 "03pysw79lsrvz4lwzis88j15067ffqbi4cid5pqhrlxmd6bh8rrk"))))
6194 (build-system python-build-system)
6196 `(#:python ,python-2
6198 (modify-phases %standard-phases
6200 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t)))))
6202 `(("python-sqlalchemy" ,python2-sqlalchemy)
6203 ("python-decorator" ,python2-decorator)
6204 ("python-biopython" ,python2-biopython)
6205 ("python-pandas" ,python2-pandas)
6206 ("python-psycopg2" ,python2-psycopg2)
6207 ("python-fastalite" ,python2-fastalite)
6208 ("python-pyyaml" ,python2-pyyaml)
6209 ("python-six" ,python2-six)
6210 ("python-jinja2" ,python2-jinja2)
6211 ("python-dendropy" ,python2-dendropy)))
6212 (home-page "https://github.com/fhcrc/taxtastic")
6213 (synopsis "Tools for taxonomic naming and annotation")
6215 "Taxtastic is software written in python used to build and maintain
6216 reference packages i.e. collections of reference trees, reference alignments,
6217 profiles, and associated taxonomic information.")
6218 (license license:gpl3+)))
6220 (define-public vcftools
6227 "https://github.com/vcftools/vcftools/releases/download/v"
6228 version "/vcftools-" version ".tar.gz"))
6231 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
6232 (build-system gnu-build-system)
6234 `(#:tests? #f ; no "check" target
6236 "CFLAGS=-O2" ; override "-m64" flag
6237 (string-append "PREFIX=" (assoc-ref %outputs "out"))
6238 (string-append "MANDIR=" (assoc-ref %outputs "out")
6239 "/share/man/man1"))))
6241 `(("pkg-config" ,pkg-config)))
6245 (home-page "https://vcftools.github.io/")
6246 (synopsis "Tools for working with VCF files")
6248 "VCFtools is a program package designed for working with VCF files, such
6249 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
6250 provide easily accessible methods for working with complex genetic variation
6251 data in the form of VCF files.")
6252 ;; The license is declared as LGPLv3 in the README and
6253 ;; at https://vcftools.github.io/license.html
6254 (license license:lgpl3)))
6256 (define-public infernal
6262 (uri (string-append "http://eddylab.org/software/infernal/"
6263 "infernal-" version ".tar.gz"))
6266 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
6267 (build-system gnu-build-system)
6269 `(("perl" ,perl))) ; for tests
6270 (home-page "http://eddylab.org/infernal/")
6271 (synopsis "Inference of RNA alignments")
6272 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
6273 searching DNA sequence databases for RNA structure and sequence similarities.
6274 It is an implementation of a special case of profile stochastic context-free
6275 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
6276 profile, but it scores a combination of sequence consensus and RNA secondary
6277 structure consensus, so in many cases, it is more capable of identifying RNA
6278 homologs that conserve their secondary structure more than their primary
6280 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
6281 (supported-systems '("i686-linux" "x86_64-linux"))
6282 (license license:bsd-3)))
6284 (define-public r-scde
6291 (url "https://github.com/hms-dbmi/scde.git")
6293 (file-name (git-file-name name version))
6296 "10na2gyka24mszdxf92wz9h2c13hdf1ww30c68gfsw53lvvhhhxb"))))
6297 (build-system r-build-system)
6299 `(("r-rcpp" ,r-rcpp)
6300 ("r-rcpparmadillo" ,r-rcpparmadillo)
6303 ("r-rjson" ,r-rjson)
6304 ("r-cairo" ,r-cairo)
6305 ("r-rcolorbrewer" ,r-rcolorbrewer)
6306 ("r-edger" ,r-edger)
6307 ("r-quantreg" ,r-quantreg)
6309 ("r-rmtstat" ,r-rmtstat)
6310 ("r-extremes" ,r-extremes)
6311 ("r-pcamethods" ,r-pcamethods)
6312 ("r-biocparallel" ,r-biocparallel)
6313 ("r-flexmix" ,r-flexmix)))
6314 (home-page "https://hms-dbmi.github.io/scde/")
6315 (synopsis "R package for analyzing single-cell RNA-seq data")
6316 (description "The SCDE package implements a set of statistical methods for
6317 analyzing single-cell RNA-seq data. SCDE fits individual error models for
6318 single-cell RNA-seq measurements. These models can then be used for
6319 assessment of differential expression between groups of cells, as well as
6320 other types of analysis. The SCDE package also contains the pagoda framework
6321 which applies pathway and gene set overdispersion analysis to identify aspects
6322 of transcriptional heterogeneity among single cells.")
6323 ;; See https://github.com/hms-dbmi/scde/issues/38
6324 (license license:gpl2)))
6326 (define-public r-centipede
6328 (name "r-centipede")
6332 (uri (string-append "http://download.r-forge.r-project.org/"
6333 "src/contrib/CENTIPEDE_" version ".tar.gz"))
6336 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
6337 (build-system r-build-system)
6338 (home-page "http://centipede.uchicago.edu/")
6339 (synopsis "Predict transcription factor binding sites")
6341 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
6342 of the genome that are bound by particular transcription factors. It starts
6343 by identifying a set of candidate binding sites, and then aims to classify the
6344 sites according to whether each site is bound or not bound by a transcription
6345 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
6346 between two different types of motif instances using as much relevant
6347 information as possible.")
6348 (license (list license:gpl2+ license:gpl3+))))
6350 (define-public r-genefilter
6352 (name "r-genefilter")
6357 (uri (bioconductor-uri "genefilter" version))
6360 "0p64s1n1627yafnp25wjr4b22p34lqw574fx2qg4s1m0lffh1z6i"))))
6361 (build-system r-build-system)
6363 `(("gfortran" ,gfortran)))
6365 `(("r-annotate" ,r-annotate)
6366 ("r-annotationdbi" ,r-annotationdbi)
6367 ("r-biobase" ,r-biobase)
6368 ("r-s4vectors" ,r-s4vectors)
6369 ("r-survival" ,r-survival)))
6370 (home-page "https://bioconductor.org/packages/genefilter")
6371 (synopsis "Filter genes from high-throughput experiments")
6373 "This package provides basic functions for filtering genes from
6374 high-throughput sequencing experiments.")
6375 (license license:artistic2.0)))
6377 (define-public r-deseq2
6384 (uri (bioconductor-uri "DESeq2" version))
6387 "0n5ah84mxn87p45drzy0wh2yknmzj1q5i6gv0v9vgg1lj7awb91r"))))
6388 (properties `((upstream-name . "DESeq2")))
6389 (build-system r-build-system)
6391 `(("r-biobase" ,r-biobase)
6392 ("r-biocgenerics" ,r-biocgenerics)
6393 ("r-biocparallel" ,r-biocparallel)
6394 ("r-genefilter" ,r-genefilter)
6395 ("r-geneplotter" ,r-geneplotter)
6396 ("r-genomicranges" ,r-genomicranges)
6397 ("r-ggplot2" ,r-ggplot2)
6398 ("r-hmisc" ,r-hmisc)
6399 ("r-iranges" ,r-iranges)
6400 ("r-locfit" ,r-locfit)
6402 ("r-rcpparmadillo" ,r-rcpparmadillo)
6403 ("r-s4vectors" ,r-s4vectors)
6404 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6405 (home-page "https://bioconductor.org/packages/DESeq2")
6406 (synopsis "Differential gene expression analysis")
6408 "This package provides functions to estimate variance-mean dependence in
6409 count data from high-throughput nucleotide sequencing assays and test for
6410 differential expression based on a model using the negative binomial
6412 (license license:lgpl3+)))
6414 (define-public r-dexseq
6421 (uri (bioconductor-uri "DEXSeq" version))
6424 "0g5w9bn2nb3m670hkcsnhfvvkza2318z9irlhhwhb3n8rdzlsdym"))))
6425 (properties `((upstream-name . "DEXSeq")))
6426 (build-system r-build-system)
6428 `(("r-annotationdbi" ,r-annotationdbi)
6429 ("r-biobase" ,r-biobase)
6430 ("r-biocgenerics" ,r-biocgenerics)
6431 ("r-biocparallel" ,r-biocparallel)
6432 ("r-biomart" ,r-biomart)
6433 ("r-deseq2" ,r-deseq2)
6434 ("r-genefilter" ,r-genefilter)
6435 ("r-geneplotter" ,r-geneplotter)
6436 ("r-genomicranges" ,r-genomicranges)
6437 ("r-hwriter" ,r-hwriter)
6438 ("r-iranges" ,r-iranges)
6439 ("r-rcolorbrewer" ,r-rcolorbrewer)
6440 ("r-rsamtools" ,r-rsamtools)
6441 ("r-s4vectors" ,r-s4vectors)
6442 ("r-statmod" ,r-statmod)
6443 ("r-stringr" ,r-stringr)
6444 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6445 (home-page "https://bioconductor.org/packages/DEXSeq")
6446 (synopsis "Inference of differential exon usage in RNA-Seq")
6448 "This package is focused on finding differential exon usage using RNA-seq
6449 exon counts between samples with different experimental designs. It provides
6450 functions that allows the user to make the necessary statistical tests based
6451 on a model that uses the negative binomial distribution to estimate the
6452 variance between biological replicates and generalized linear models for
6453 testing. The package also provides functions for the visualization and
6454 exploration of the results.")
6455 (license license:gpl3+)))
6457 (define-public r-annotationforge
6459 (name "r-annotationforge")
6464 (uri (bioconductor-uri "AnnotationForge" version))
6467 "13yvhf3yskmvhs8szs6rkw93h81h5xqa3h19h91pp6nprhc8s3ll"))))
6469 `((upstream-name . "AnnotationForge")))
6470 (build-system r-build-system)
6472 `(("r-annotationdbi" ,r-annotationdbi)
6473 ("r-biobase" ,r-biobase)
6474 ("r-biocgenerics" ,r-biocgenerics)
6476 ("r-rcurl" ,r-rcurl)
6477 ("r-rsqlite" ,r-rsqlite)
6478 ("r-s4vectors" ,r-s4vectors)
6480 (home-page "https://bioconductor.org/packages/AnnotationForge")
6481 (synopsis "Code for building annotation database packages")
6483 "This package provides code for generating Annotation packages and their
6484 databases. Packages produced are intended to be used with AnnotationDbi.")
6485 (license license:artistic2.0)))
6487 (define-public r-rbgl
6494 (uri (bioconductor-uri "RBGL" version))
6497 "1l5x2icv9di1lr3gqfi0vjnyd9xc3l77yc42ippqd4cadj3d1pzf"))))
6498 (properties `((upstream-name . "RBGL")))
6499 (build-system r-build-system)
6500 (propagated-inputs `(("r-graph" ,r-graph)))
6501 (home-page "https://www.bioconductor.org/packages/RBGL")
6502 (synopsis "Interface to the Boost graph library")
6504 "This package provides a fairly extensive and comprehensive interface to
6505 the graph algorithms contained in the Boost library.")
6506 (license license:artistic2.0)))
6508 (define-public r-gseabase
6515 (uri (bioconductor-uri "GSEABase" version))
6518 "110al7x0ig8plzrprvhwc7xshi1jzpj2n8llhhg2fh6v6k0k6awr"))))
6519 (properties `((upstream-name . "GSEABase")))
6520 (build-system r-build-system)
6522 `(("r-annotate" ,r-annotate)
6523 ("r-annotationdbi" ,r-annotationdbi)
6524 ("r-biobase" ,r-biobase)
6525 ("r-biocgenerics" ,r-biocgenerics)
6526 ("r-graph" ,r-graph)
6528 (home-page "https://bioconductor.org/packages/GSEABase")
6529 (synopsis "Gene set enrichment data structures and methods")
6531 "This package provides classes and methods to support @dfn{Gene Set
6532 Enrichment Analysis} (GSEA).")
6533 (license license:artistic2.0)))
6535 (define-public r-category
6542 (uri (bioconductor-uri "Category" version))
6545 "1jdm83bwdfhpfm1y6hwgvxzj6l83h1bdkqv23799kzywnwm016kv"))))
6546 (properties `((upstream-name . "Category")))
6547 (build-system r-build-system)
6549 `(("r-annotate" ,r-annotate)
6550 ("r-annotationdbi" ,r-annotationdbi)
6551 ("r-biobase" ,r-biobase)
6552 ("r-biocgenerics" ,r-biocgenerics)
6553 ("r-genefilter" ,r-genefilter)
6554 ("r-graph" ,r-graph)
6555 ("r-gseabase" ,r-gseabase)
6556 ("r-matrix" ,r-matrix)
6559 (home-page "https://bioconductor.org/packages/Category")
6560 (synopsis "Category analysis")
6562 "This package provides a collection of tools for performing category
6564 (license license:artistic2.0)))
6566 (define-public r-gostats
6573 (uri (bioconductor-uri "GOstats" version))
6576 "0wlqqgfynwqnqhckhsfjwg9zkj6hkmzwd5y76dhqz720vy21rcln"))))
6577 (properties `((upstream-name . "GOstats")))
6578 (build-system r-build-system)
6580 `(("r-annotate" ,r-annotate)
6581 ("r-annotationdbi" ,r-annotationdbi)
6582 ("r-annotationforge" ,r-annotationforge)
6583 ("r-biobase" ,r-biobase)
6584 ("r-category" ,r-category)
6585 ("r-go-db" ,r-go-db)
6586 ("r-graph" ,r-graph)
6587 ("r-rgraphviz" ,r-rgraphviz)
6588 ("r-rbgl" ,r-rbgl)))
6589 (home-page "https://bioconductor.org/packages/GOstats")
6590 (synopsis "Tools for manipulating GO and microarrays")
6592 "This package provides a set of tools for interacting with GO and
6593 microarray data. A variety of basic manipulation tools for graphs, hypothesis
6594 testing and other simple calculations.")
6595 (license license:artistic2.0)))
6597 (define-public r-shortread
6599 (name "r-shortread")
6604 (uri (bioconductor-uri "ShortRead" version))
6607 "0iks123i1adkb9i2q4wvfqdmmj9dy867jvngj9757y8gj6xbcpy1"))))
6608 (properties `((upstream-name . "ShortRead")))
6609 (build-system r-build-system)
6613 `(("r-biobase" ,r-biobase)
6614 ("r-biocgenerics" ,r-biocgenerics)
6615 ("r-biocparallel" ,r-biocparallel)
6616 ("r-biostrings" ,r-biostrings)
6617 ("r-genomeinfodb" ,r-genomeinfodb)
6618 ("r-genomicalignments" ,r-genomicalignments)
6619 ("r-genomicranges" ,r-genomicranges)
6620 ("r-hwriter" ,r-hwriter)
6621 ("r-iranges" ,r-iranges)
6622 ("r-lattice" ,r-lattice)
6623 ("r-latticeextra" ,r-latticeextra)
6624 ("r-rsamtools" ,r-rsamtools)
6625 ("r-s4vectors" ,r-s4vectors)
6626 ("r-xvector" ,r-xvector)
6627 ("r-zlibbioc" ,r-zlibbioc)))
6628 (home-page "https://bioconductor.org/packages/ShortRead")
6629 (synopsis "FASTQ input and manipulation tools")
6631 "This package implements sampling, iteration, and input of FASTQ files.
6632 It includes functions for filtering and trimming reads, and for generating a
6633 quality assessment report. Data are represented as
6634 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6635 purposes. The package also contains legacy support for early single-end,
6636 ungapped alignment formats.")
6637 (license license:artistic2.0)))
6639 (define-public r-systempiper
6641 (name "r-systempiper")
6646 (uri (bioconductor-uri "systemPipeR" version))
6649 "0qzydz87rld2nhwzbfgrw5jfgh8maa9y54mjx9c4285m11qj2shq"))))
6650 (properties `((upstream-name . "systemPipeR")))
6651 (build-system r-build-system)
6653 `(("r-annotate" ,r-annotate)
6654 ("r-batchjobs" ,r-batchjobs)
6655 ("r-biocgenerics" ,r-biocgenerics)
6656 ("r-biostrings" ,r-biostrings)
6657 ("r-deseq2" ,r-deseq2)
6658 ("r-edger" ,r-edger)
6659 ("r-genomicfeatures" ,r-genomicfeatures)
6660 ("r-genomicranges" ,r-genomicranges)
6661 ("r-ggplot2" ,r-ggplot2)
6662 ("r-go-db" ,r-go-db)
6663 ("r-gostats" ,r-gostats)
6664 ("r-limma" ,r-limma)
6665 ("r-pheatmap" ,r-pheatmap)
6666 ("r-rjson" ,r-rjson)
6667 ("r-rsamtools" ,r-rsamtools)
6668 ("r-shortread" ,r-shortread)
6669 ("r-summarizedexperiment" ,r-summarizedexperiment)
6670 ("r-variantannotation" ,r-variantannotation)))
6671 (home-page "https://github.com/tgirke/systemPipeR")
6672 (synopsis "Next generation sequencing workflow and reporting environment")
6674 "This R package provides tools for building and running automated
6675 end-to-end analysis workflows for a wide range of @dfn{next generation
6676 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6677 Important features include a uniform workflow interface across different NGS
6678 applications, automated report generation, and support for running both R and
6679 command-line software, such as NGS aligners or peak/variant callers, on local
6680 computers or compute clusters. Efficient handling of complex sample sets and
6681 experimental designs is facilitated by a consistently implemented sample
6682 annotation infrastructure.")
6683 (license license:artistic2.0)))
6685 (define-public r-grohmm
6692 (uri (bioconductor-uri "groHMM" version))
6695 "1ph92fv44b90v7mk4b1mjvv0dlrhl8ba01klxbnd0vs4qn9zxplh"))))
6696 (properties `((upstream-name . "groHMM")))
6697 (build-system r-build-system)
6699 `(("r-genomeinfodb" ,r-genomeinfodb)
6700 ("r-genomicalignments" ,r-genomicalignments)
6701 ("r-genomicranges" ,r-genomicranges)
6702 ("r-iranges" ,r-iranges)
6704 ("r-rtracklayer" ,r-rtracklayer)
6705 ("r-s4vectors" ,r-s4vectors)))
6706 (home-page "https://github.com/Kraus-Lab/groHMM")
6707 (synopsis "GRO-seq analysis pipeline")
6709 "This package provides a pipeline for the analysis of GRO-seq data.")
6710 (license license:gpl3+)))
6712 (define-public r-sparql
6718 (uri (cran-uri "SPARQL" version))
6721 "0gak1q06yyhdmcxb2n3v0h9gr1vqd0viqji52wpw211qp6r6dcrc"))))
6722 (properties `((upstream-name . "SPARQL")))
6723 (build-system r-build-system)
6725 `(("r-rcurl" ,r-rcurl)
6727 (home-page "https://cran.r-project.org/web/packages/SPARQL")
6728 (synopsis "SPARQL client for R")
6729 (description "This package provides an interface to use SPARQL to pose
6730 SELECT or UPDATE queries to an end-point.")
6731 ;; The only license indication is found in the DESCRIPTION file,
6732 ;; which states GPL-3. So we cannot assume GPLv3+.
6733 (license license:gpl3)))
6735 (define-public vsearch
6743 (url "https://github.com/torognes/vsearch.git")
6744 (commit (string-append "v" version))))
6745 (file-name (git-file-name name version))
6748 "0vhrpjfdf75ba04b24xknp41790cvcgwl0vgpy7qbzj5xh2521ss"))
6749 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
6752 ;; Remove bundled cityhash sources. The vsearch source is adjusted
6753 ;; for this in the patch.
6754 (delete-file "src/city.h")
6755 (delete-file "src/citycrc.h")
6756 (delete-file "src/city.cc")
6758 (build-system gnu-build-system)
6762 ("cityhash" ,cityhash)))
6764 `(("autoconf" ,autoconf)
6765 ("automake" ,automake)))
6766 (synopsis "Sequence search tools for metagenomics")
6768 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
6769 dereplication, pairwise alignment, shuffling, subsampling, sorting and
6770 masking. The tool takes advantage of parallelism in the form of SIMD
6771 vectorization as well as multiple threads to perform accurate alignments at
6772 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
6773 Needleman-Wunsch).")
6774 (home-page "https://github.com/torognes/vsearch")
6775 ;; vsearch uses non-portable SSE intrinsics so building fails on other
6777 (supported-systems '("x86_64-linux"))
6778 ;; Dual licensed; also includes public domain source.
6779 (license (list license:gpl3 license:bsd-2))))
6781 (define-public pardre
6784 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
6789 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
6793 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
6794 (build-system gnu-build-system)
6796 `(#:tests? #f ; no tests included
6798 (modify-phases %standard-phases
6801 (lambda* (#:key outputs #:allow-other-keys)
6802 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
6803 (install-file "ParDRe" bin)
6806 `(("openmpi" ,openmpi)
6808 (synopsis "Parallel tool to remove duplicate DNA reads")
6810 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
6811 Duplicate reads can be seen as identical or nearly identical sequences with
6812 some mismatches. This tool lets users avoid the analysis of unnecessary
6813 reads, reducing the time of subsequent procedures with the
6814 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
6815 in order to exploit the parallel capabilities of multicore clusters. It is
6816 faster than multithreaded counterparts (end of 2015) for the same number of
6817 cores and, thanks to the message-passing technology, it can be executed on
6819 (home-page "https://sourceforge.net/projects/pardre/")
6820 (license license:gpl3+)))
6822 (define-public ruby-bio-kseq
6824 (name "ruby-bio-kseq")
6829 (uri (rubygems-uri "bio-kseq" version))
6832 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
6833 (build-system ruby-build-system)
6835 `(#:test-target "spec"))
6837 `(("bundler" ,bundler)
6838 ("ruby-rspec" ,ruby-rspec)
6839 ("ruby-rake-compiler" ,ruby-rake-compiler)))
6842 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
6844 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
6845 FASTQ parsing code. It provides a fast iterator over sequences and their
6847 (home-page "https://github.com/gusevfe/bio-kseq")
6848 (license license:expat)))
6850 (define-public bio-locus
6857 (uri (rubygems-uri "bio-locus" version))
6860 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
6861 (build-system ruby-build-system)
6863 `(("ruby-rspec" ,ruby-rspec)))
6864 (synopsis "Tool for fast querying of genome locations")
6866 "Bio-locus is a tabix-like tool for fast querying of genome
6867 locations. Many file formats in bioinformatics contain records that
6868 start with a chromosome name and a position for a SNP, or a start-end
6869 position for indels. Bio-locus allows users to store this chr+pos or
6870 chr+pos+alt information in a database.")
6871 (home-page "https://github.com/pjotrp/bio-locus")
6872 (license license:expat)))
6874 (define-public bio-blastxmlparser
6876 (name "bio-blastxmlparser")
6880 (uri (rubygems-uri "bio-blastxmlparser" version))
6883 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
6884 (build-system ruby-build-system)
6886 `(("ruby-bio-logger" ,ruby-bio-logger)
6887 ("ruby-nokogiri" ,ruby-nokogiri)))
6889 `(("ruby-rspec" ,ruby-rspec)))
6890 (synopsis "Fast big data BLAST XML parser and library")
6892 "Very fast parallel big-data BLAST XML file parser which can be used as
6893 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
6894 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
6895 (home-page "https://github.com/pjotrp/blastxmlparser")
6896 (license license:expat)))
6898 (define-public bioruby
6905 (uri (rubygems-uri "bio" version))
6908 "1d56amdsjv1mag7m6gv2w0xij8hqx1v5xbdjsix8sp3yp36m7938"))))
6909 (build-system ruby-build-system)
6911 `(("ruby-libxml" ,ruby-libxml)))
6913 `(("which" ,which))) ; required for test phase
6916 (modify-phases %standard-phases
6917 (add-before 'build 'patch-test-command
6919 (substitute* '("test/functional/bio/test_command.rb")
6920 (("/bin/sh") (which "sh")))
6921 (substitute* '("test/functional/bio/test_command.rb")
6922 (("/bin/ls") (which "ls")))
6923 (substitute* '("test/functional/bio/test_command.rb")
6924 (("which") (which "which")))
6925 (substitute* '("test/functional/bio/test_command.rb",
6926 "test/data/command/echoarg2.sh")
6927 (("/bin/echo") (which "echo")))
6929 (synopsis "Ruby library, shell and utilities for bioinformatics")
6930 (description "BioRuby comes with a comprehensive set of Ruby development
6931 tools and libraries for bioinformatics and molecular biology. BioRuby has
6932 components for sequence analysis, pathway analysis, protein modelling and
6933 phylogenetic analysis; it supports many widely used data formats and provides
6934 easy access to databases, external programs and public web services, including
6935 BLAST, KEGG, GenBank, MEDLINE and GO.")
6936 (home-page "http://bioruby.org/")
6937 ;; Code is released under Ruby license, except for setup
6938 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
6939 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
6941 (define-public r-acsnminer
6943 (name "r-acsnminer")
6944 (version "0.16.8.25")
6947 (uri (cran-uri "ACSNMineR" version))
6950 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
6951 (properties `((upstream-name . "ACSNMineR")))
6952 (build-system r-build-system)
6954 `(("r-ggplot2" ,r-ggplot2)
6955 ("r-gridextra" ,r-gridextra)))
6956 (home-page "https://cran.r-project.org/web/packages/ACSNMineR")
6957 (synopsis "Gene enrichment analysis")
6959 "This package provides tools to compute and represent gene set enrichment
6960 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
6961 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
6962 enrichment can be run with hypergeometric test or Fisher exact test, and can
6963 use multiple corrections. Visualization of data can be done either by
6964 barplots or heatmaps.")
6965 (license license:gpl2+)))
6967 (define-public r-biocinstaller
6969 (name "r-biocinstaller")
6973 (uri (bioconductor-uri "BiocInstaller" version))
6976 "1s1f9qhyf3mc73ir25x2zlgi9hf45a37lg4z8fbva4i21hqisgsl"))))
6978 `((upstream-name . "BiocInstaller")))
6979 (build-system r-build-system)
6980 (home-page "https://bioconductor.org/packages/BiocInstaller")
6981 (synopsis "Install Bioconductor packages")
6982 (description "This package is used to install and update R packages from
6983 Bioconductor, CRAN, and Github.")
6984 (license license:artistic2.0)))
6986 (define-public r-biocviews
6988 (name "r-biocviews")
6992 (uri (bioconductor-uri "biocViews" version))
6995 "06ms82pyc5rxbd9crfvqjxcwpafv0c627i83v80d12925mrc51h8"))))
6997 `((upstream-name . "biocViews")))
6998 (build-system r-build-system)
7000 `(("r-biobase" ,r-biobase)
7001 ("r-graph" ,r-graph)
7003 ("r-rcurl" ,r-rcurl)
7005 ("r-runit" ,r-runit)))
7006 (home-page "https://bioconductor.org/packages/biocViews")
7007 (synopsis "Bioconductor package categorization helper")
7008 (description "The purpose of biocViews is to create HTML pages that
7009 categorize packages in a Bioconductor package repository according to keywords,
7010 also known as views, in a controlled vocabulary.")
7011 (license license:artistic2.0)))
7013 (define-public r-bookdown
7019 (uri (cran-uri "bookdown" version))
7022 "0vg1s1w0l9pm95asqb21yf39mfk1nc9rdhmlys9xwr7p7i7rsz32"))))
7023 (build-system r-build-system)
7025 `(("r-htmltools" ,r-htmltools)
7026 ("r-knitr" ,r-knitr)
7027 ("r-rmarkdown" ,r-rmarkdown)
7028 ("r-tinytex" ,r-tinytex)
7030 ("r-xfun" ,r-xfun)))
7031 (home-page "https://github.com/rstudio/bookdown")
7032 (synopsis "Authoring books and technical documents with R markdown")
7033 (description "This package provides output formats and utilities for
7034 authoring books and technical documents with R Markdown.")
7035 (license license:gpl3)))
7037 (define-public r-biocstyle
7039 (name "r-biocstyle")
7043 (uri (bioconductor-uri "BiocStyle" version))
7046 "01lm8xljilj666fcl3wnw82dxkcxnlr294lddr553rm8xr5nwg31"))))
7048 `((upstream-name . "BiocStyle")))
7049 (build-system r-build-system)
7051 `(("r-biocmanager" ,r-biocmanager)
7052 ("r-bookdown" ,r-bookdown)
7053 ("r-knitr" ,r-knitr)
7054 ("r-rmarkdown" ,r-rmarkdown)
7055 ("r-yaml" ,r-yaml)))
7056 (home-page "https://bioconductor.org/packages/BiocStyle")
7057 (synopsis "Bioconductor formatting styles")
7058 (description "This package provides standard formatting styles for
7059 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
7061 (license license:artistic2.0)))
7063 (define-public r-bioccheck
7065 (name "r-bioccheck")
7069 (uri (bioconductor-uri "BiocCheck" version))
7072 "0zamvs5jar38293ff27imvwy0ra25y64ls9z8w3q1y4jcp8p8pg7"))))
7074 `((upstream-name . "BiocCheck")))
7075 (build-system r-build-system)
7078 (modify-phases %standard-phases
7079 ;; This package can be used by calling BiocCheck(<package>) from
7080 ;; within R, or by running R CMD BiocCheck <package>. This phase
7081 ;; makes sure the latter works. For this to work, the BiocCheck
7082 ;; script must be somewhere on the PATH (not the R bin directory).
7083 (add-after 'install 'install-bioccheck-subcommand
7084 (lambda* (#:key outputs #:allow-other-keys)
7085 (let* ((out (assoc-ref outputs "out"))
7086 (dest-dir (string-append out "/bin"))
7088 (string-append out "/site-library/BiocCheck/script/")))
7090 (symlink (string-append script-dir "/checkBadDeps.R")
7091 (string-append dest-dir "/checkBadDeps.R"))
7092 (symlink (string-append script-dir "/BiocCheck")
7093 (string-append dest-dir "/BiocCheck")))
7096 `(("r-codetools" ,r-codetools)
7097 ("r-graph" ,r-graph)
7099 ("r-knitr" ,r-knitr)
7100 ("r-optparse" ,r-optparse)
7101 ("r-biocmanager" ,r-biocmanager)
7102 ("r-biocviews" ,r-biocviews)
7103 ("r-stringdist" ,r-stringdist)))
7104 (home-page "https://bioconductor.org/packages/BiocCheck")
7105 (synopsis "Executes Bioconductor-specific package checks")
7106 (description "This package contains tools to perform additional quality
7107 checks on R packages that are to be submitted to the Bioconductor repository.")
7108 (license license:artistic2.0)))
7110 (define-public r-optparse
7117 (uri (cran-uri "optparse" version))
7120 "04vyb6dhcga30mvghsg1p052jmf69xqxkvh3hzqz7dscyppy76w1"))))
7121 (build-system r-build-system)
7123 `(("r-getopt" ,r-getopt)))
7125 "https://github.com/trevorld/optparse")
7126 (synopsis "Command line option parser")
7128 "This package provides a command line parser inspired by Python's
7129 @code{optparse} library to be used with Rscript to write shebang scripts
7130 that accept short and long options.")
7131 (license license:gpl2+)))
7133 (define-public r-s4vectors
7135 (name "r-s4vectors")
7139 (uri (bioconductor-uri "S4Vectors" version))
7142 "18whrw67nxn82xshckl2pjy7d14sa3c27h3n9naqyqwz88lr6dzg"))))
7144 `((upstream-name . "S4Vectors")))
7145 (build-system r-build-system)
7147 `(("r-biocgenerics" ,r-biocgenerics)))
7148 (home-page "https://bioconductor.org/packages/S4Vectors")
7149 (synopsis "S4 implementation of vectors and lists")
7151 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7152 classes and a set of generic functions that extend the semantic of ordinary
7153 vectors and lists in R. Package developers can easily implement vector-like
7154 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7155 In addition, a few low-level concrete subclasses of general interest (e.g.
7156 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7157 S4Vectors package itself.")
7158 (license license:artistic2.0)))
7160 (define-public r-seqinr
7167 (uri (cran-uri "seqinr" version))
7170 "17zv0n5cji17izwmwg0jcbxbjl3w5rls91w15svcnlpxjms38ahn"))))
7171 (build-system r-build-system)
7173 `(("r-ade4" ,r-ade4)
7174 ("r-segmented" ,r-segmented)))
7177 (home-page "http://seqinr.r-forge.r-project.org/")
7178 (synopsis "Biological sequences retrieval and analysis")
7180 "This package provides tools for exploratory data analysis and data
7181 visualization of biological sequence (DNA and protein) data. It also includes
7182 utilities for sequence data management under the ACNUC system.")
7183 (license license:gpl2+)))
7185 (define-public r-iranges
7191 (uri (bioconductor-uri "IRanges" version))
7194 "0ljppsk611xi72gc8mbdx1311b63b1ijd401jz5xmxk5frla1nc1"))))
7196 `((upstream-name . "IRanges")))
7197 (build-system r-build-system)
7199 `(("r-biocgenerics" ,r-biocgenerics)
7200 ("r-s4vectors" ,r-s4vectors)))
7201 (home-page "https://bioconductor.org/packages/IRanges")
7202 (synopsis "Infrastructure for manipulating intervals on sequences")
7204 "This package provides efficient low-level and highly reusable S4 classes
7205 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7206 generally, data that can be organized sequentially (formally defined as
7207 @code{Vector} objects), as well as views on these @code{Vector} objects.
7208 Efficient list-like classes are also provided for storing big collections of
7209 instances of the basic classes. All classes in the package use consistent
7210 naming and share the same rich and consistent \"Vector API\" as much as
7212 (license license:artistic2.0)))
7214 (define-public r-genomeinfodbdata
7216 (name "r-genomeinfodbdata")
7220 ;; We cannot use bioconductor-uri here because this tarball is
7221 ;; located under "data/annotation/" instead of "bioc/".
7222 (uri (string-append "https://bioconductor.org/packages/release/"
7223 "data/annotation/src/contrib/GenomeInfoDbData_"
7227 "0di6nlqpsyqf693k2na65ayqldih563x3zfrczpqc5q2hl5kg35c"))))
7229 `((upstream-name . "GenomeInfoDbData")))
7230 (build-system r-build-system)
7231 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7232 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7233 (description "This package contains data for mapping between NCBI taxonomy
7234 ID and species. It is used by functions in the GenomeInfoDb package.")
7235 (license license:artistic2.0)))
7237 (define-public r-genomeinfodb
7239 (name "r-genomeinfodb")
7243 (uri (bioconductor-uri "GenomeInfoDb" version))
7246 "049pyzr8iszv3g7wdqf3pz7vg7bzd450c20ln6fgw4g5xnkkr10s"))))
7248 `((upstream-name . "GenomeInfoDb")))
7249 (build-system r-build-system)
7251 `(("r-biocgenerics" ,r-biocgenerics)
7252 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7253 ("r-iranges" ,r-iranges)
7254 ("r-rcurl" ,r-rcurl)
7255 ("r-s4vectors" ,r-s4vectors)))
7256 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7257 (synopsis "Utilities for manipulating chromosome identifiers")
7259 "This package contains data and functions that define and allow
7260 translation between different chromosome sequence naming conventions (e.g.,
7261 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7262 names in their natural, rather than lexicographic, order.")
7263 (license license:artistic2.0)))
7265 (define-public r-edger
7271 (uri (bioconductor-uri "edgeR" version))
7274 "15yimsbsxmxhlsfmgw5j7fd8qn08zz4xqxrir1c6n2dc103y22xg"))))
7275 (properties `((upstream-name . "edgeR")))
7276 (build-system r-build-system)
7278 `(("r-limma" ,r-limma)
7279 ("r-locfit" ,r-locfit)
7281 ("r-statmod" ,r-statmod))) ;for estimateDisp
7282 (home-page "http://bioinf.wehi.edu.au/edgeR")
7283 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7284 (description "This package can do differential expression analysis of
7285 RNA-seq expression profiles with biological replication. It implements a range
7286 of statistical methodology based on the negative binomial distributions,
7287 including empirical Bayes estimation, exact tests, generalized linear models
7288 and quasi-likelihood tests. It be applied to differential signal analysis of
7289 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7291 (license license:gpl2+)))
7293 (define-public r-variantannotation
7295 (name "r-variantannotation")
7299 (uri (bioconductor-uri "VariantAnnotation" version))
7302 "0kxf583cgkdz1shi85r0mpnfxmzi7s5f6srd1czbdl2iibvrm8jn"))))
7304 `((upstream-name . "VariantAnnotation")))
7308 `(("r-annotationdbi" ,r-annotationdbi)
7309 ("r-biobase" ,r-biobase)
7310 ("r-biocgenerics" ,r-biocgenerics)
7311 ("r-biostrings" ,r-biostrings)
7312 ("r-bsgenome" ,r-bsgenome)
7314 ("r-genomeinfodb" ,r-genomeinfodb)
7315 ("r-genomicfeatures" ,r-genomicfeatures)
7316 ("r-genomicranges" ,r-genomicranges)
7317 ("r-iranges" ,r-iranges)
7318 ("r-summarizedexperiment" ,r-summarizedexperiment)
7319 ("r-rsamtools" ,r-rsamtools)
7320 ("r-rtracklayer" ,r-rtracklayer)
7321 ("r-s4vectors" ,r-s4vectors)
7322 ("r-xvector" ,r-xvector)
7323 ("r-zlibbioc" ,r-zlibbioc)))
7324 (build-system r-build-system)
7325 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7326 (synopsis "Package for annotation of genetic variants")
7327 (description "This R package can annotate variants, compute amino acid
7328 coding changes and predict coding outcomes.")
7329 (license license:artistic2.0)))
7331 (define-public r-limma
7337 (uri (bioconductor-uri "limma" version))
7340 "08va8jggmv61wym955mnb1n31mgikrmjys7dl1kp5hp3yia8jg7l"))))
7341 (build-system r-build-system)
7342 (home-page "http://bioinf.wehi.edu.au/limma")
7343 (synopsis "Package for linear models for microarray and RNA-seq data")
7344 (description "This package can be used for the analysis of gene expression
7345 studies, especially the use of linear models for analysing designed experiments
7346 and the assessment of differential expression. The analysis methods apply to
7347 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7348 (license license:gpl2+)))
7350 (define-public r-xvector
7356 (uri (bioconductor-uri "XVector" version))
7359 "01fph1ydd6g0rl5mcw54spx22glq2kqv7wyw8bqw0plmabzcwwdm"))))
7361 `((upstream-name . "XVector")))
7362 (build-system r-build-system)
7365 (modify-phases %standard-phases
7366 (add-after 'unpack 'use-system-zlib
7368 (substitute* "DESCRIPTION"
7369 (("zlibbioc, ") ""))
7370 (substitute* "NAMESPACE"
7371 (("import\\(zlibbioc\\)") ""))
7376 `(("r-biocgenerics" ,r-biocgenerics)
7377 ("r-iranges" ,r-iranges)
7378 ("r-s4vectors" ,r-s4vectors)))
7379 (home-page "https://bioconductor.org/packages/XVector")
7380 (synopsis "Representation and manpulation of external sequences")
7382 "This package provides memory efficient S4 classes for storing sequences
7383 \"externally\" (behind an R external pointer, or on disk).")
7384 (license license:artistic2.0)))
7386 (define-public r-genomicranges
7388 (name "r-genomicranges")
7392 (uri (bioconductor-uri "GenomicRanges" version))
7395 "0bgh14d15dpf2iy36qinw45r6n45rqkf0ghazrdl3jfva6vbrb29"))))
7397 `((upstream-name . "GenomicRanges")))
7398 (build-system r-build-system)
7400 `(("r-biocgenerics" ,r-biocgenerics)
7401 ("r-genomeinfodb" ,r-genomeinfodb)
7402 ("r-iranges" ,r-iranges)
7403 ("r-s4vectors" ,r-s4vectors)
7404 ("r-xvector" ,r-xvector)))
7405 (home-page "https://bioconductor.org/packages/GenomicRanges")
7406 (synopsis "Representation and manipulation of genomic intervals")
7408 "This package provides tools to efficiently represent and manipulate
7409 genomic annotations and alignments is playing a central role when it comes to
7410 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7411 GenomicRanges package defines general purpose containers for storing and
7412 manipulating genomic intervals and variables defined along a genome.")
7413 (license license:artistic2.0)))
7415 (define-public r-biobase
7421 (uri (bioconductor-uri "Biobase" version))
7424 "10nr6nrkj5vlq8hsgbhbhv669z0dbpz4m3vz9k32rx1czbrrqwin"))))
7426 `((upstream-name . "Biobase")))
7427 (build-system r-build-system)
7429 `(("r-biocgenerics" ,r-biocgenerics)))
7430 (home-page "https://bioconductor.org/packages/Biobase")
7431 (synopsis "Base functions for Bioconductor")
7433 "This package provides functions that are needed by many other packages
7434 on Bioconductor or which replace R functions.")
7435 (license license:artistic2.0)))
7437 (define-public r-annotationdbi
7439 (name "r-annotationdbi")
7443 (uri (bioconductor-uri "AnnotationDbi" version))
7446 "1954vimkx5yb9irppq8vssq0f3yjkg36w38b9r0rqmijx1ps7x5d"))))
7448 `((upstream-name . "AnnotationDbi")))
7449 (build-system r-build-system)
7451 `(("r-biobase" ,r-biobase)
7452 ("r-biocgenerics" ,r-biocgenerics)
7454 ("r-iranges" ,r-iranges)
7455 ("r-rsqlite" ,r-rsqlite)
7456 ("r-s4vectors" ,r-s4vectors)))
7457 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7458 (synopsis "Annotation database interface")
7460 "This package provides user interface and database connection code for
7461 annotation data packages using SQLite data storage.")
7462 (license license:artistic2.0)))
7464 (define-public r-biomart
7470 (uri (bioconductor-uri "biomaRt" version))
7473 "1lshkknp7dmr3p6dd2zbv86cc71h53ggh9ji83jcjym8sgbbspl2"))))
7475 `((upstream-name . "biomaRt")))
7476 (build-system r-build-system)
7478 `(("r-annotationdbi" ,r-annotationdbi)
7480 ("r-progress" ,r-progress)
7481 ("r-rcurl" ,r-rcurl)
7482 ("r-stringr" ,r-stringr)
7484 (home-page "https://bioconductor.org/packages/biomaRt")
7485 (synopsis "Interface to BioMart databases")
7487 "biomaRt provides an interface to a growing collection of databases
7488 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7489 package enables retrieval of large amounts of data in a uniform way without
7490 the need to know the underlying database schemas or write complex SQL queries.
7491 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7492 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7493 users direct access to a diverse set of data and enable a wide range of
7494 powerful online queries from gene annotation to database mining.")
7495 (license license:artistic2.0)))
7497 (define-public r-biocparallel
7499 (name "r-biocparallel")
7503 (uri (bioconductor-uri "BiocParallel" version))
7506 "1164dk0fajb2vrkfpcjs11055qf1cs4vvbnq0aqdaaf2p4lyx41l"))))
7508 `((upstream-name . "BiocParallel")))
7509 (build-system r-build-system)
7511 `(("r-futile-logger" ,r-futile-logger)
7514 (home-page "https://bioconductor.org/packages/BiocParallel")
7515 (synopsis "Bioconductor facilities for parallel evaluation")
7517 "This package provides modified versions and novel implementation of
7518 functions for parallel evaluation, tailored to use with Bioconductor
7520 (license (list license:gpl2+ license:gpl3+))))
7522 (define-public r-biostrings
7524 (name "r-biostrings")
7528 (uri (bioconductor-uri "Biostrings" version))
7531 "16cqqc8i6gb0jcz0lizfqqxsq7g0yb0ll2s9qzmb45brp07dg8f7"))))
7533 `((upstream-name . "Biostrings")))
7534 (build-system r-build-system)
7536 `(("r-biocgenerics" ,r-biocgenerics)
7537 ("r-iranges" ,r-iranges)
7538 ("r-s4vectors" ,r-s4vectors)
7539 ("r-xvector" ,r-xvector)))
7540 (home-page "https://bioconductor.org/packages/Biostrings")
7541 (synopsis "String objects and algorithms for biological sequences")
7543 "This package provides memory efficient string containers, string
7544 matching algorithms, and other utilities, for fast manipulation of large
7545 biological sequences or sets of sequences.")
7546 (license license:artistic2.0)))
7548 (define-public r-rsamtools
7550 (name "r-rsamtools")
7554 (uri (bioconductor-uri "Rsamtools" version))
7557 "01v4bjhj2i126pwyk0v9lvmfp2ih495xsq903k3xa2z24bjxphbi"))))
7559 `((upstream-name . "Rsamtools")))
7560 (build-system r-build-system)
7563 (modify-phases %standard-phases
7564 (add-after 'unpack 'use-system-zlib
7566 (substitute* "DESCRIPTION"
7567 (("zlibbioc, ") ""))
7568 (substitute* "NAMESPACE"
7569 (("import\\(zlibbioc\\)") ""))
7574 `(("r-biocgenerics" ,r-biocgenerics)
7575 ("r-biocparallel" ,r-biocparallel)
7576 ("r-biostrings" ,r-biostrings)
7577 ("r-bitops" ,r-bitops)
7578 ("r-genomeinfodb" ,r-genomeinfodb)
7579 ("r-genomicranges" ,r-genomicranges)
7580 ("r-iranges" ,r-iranges)
7581 ("r-s4vectors" ,r-s4vectors)
7582 ("r-xvector" ,r-xvector)))
7583 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7584 (synopsis "Interface to samtools, bcftools, and tabix")
7586 "This package provides an interface to the 'samtools', 'bcftools', and
7587 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
7588 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
7590 (license license:expat)))
7592 (define-public r-delayedarray
7594 (name "r-delayedarray")
7598 (uri (bioconductor-uri "DelayedArray" version))
7601 "0cl5anqkjwvqx19snjhz0zj8cp8ibckiifl28h821h50g62nvb2f"))))
7603 `((upstream-name . "DelayedArray")))
7604 (build-system r-build-system)
7606 `(("r-biocgenerics" ,r-biocgenerics)
7607 ("r-biocparallel" ,r-biocparallel)
7608 ("r-s4vectors" ,r-s4vectors)
7609 ("r-iranges" ,r-iranges)
7610 ("r-matrixstats" ,r-matrixstats)))
7611 (home-page "https://bioconductor.org/packages/DelayedArray")
7612 (synopsis "Delayed operations on array-like objects")
7614 "Wrapping an array-like object (typically an on-disk object) in a
7615 @code{DelayedArray} object allows one to perform common array operations on it
7616 without loading the object in memory. In order to reduce memory usage and
7617 optimize performance, operations on the object are either delayed or executed
7618 using a block processing mechanism. Note that this also works on in-memory
7619 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7620 @code{Matrix} objects, and ordinary arrays and data frames.")
7621 (license license:artistic2.0)))
7623 (define-public r-summarizedexperiment
7625 (name "r-summarizedexperiment")
7629 (uri (bioconductor-uri "SummarizedExperiment" version))
7632 "07805572xhpj5mfwq6kw1ha21wgalqvhh4ydvafyl1bnf3r20vps"))))
7634 `((upstream-name . "SummarizedExperiment")))
7635 (build-system r-build-system)
7637 `(("r-biobase" ,r-biobase)
7638 ("r-biocgenerics" ,r-biocgenerics)
7639 ("r-delayedarray" ,r-delayedarray)
7640 ("r-genomeinfodb" ,r-genomeinfodb)
7641 ("r-genomicranges" ,r-genomicranges)
7642 ("r-iranges" ,r-iranges)
7643 ("r-matrix" ,r-matrix)
7644 ("r-s4vectors" ,r-s4vectors)))
7645 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
7646 (synopsis "Container for representing genomic ranges by sample")
7648 "The SummarizedExperiment container contains one or more assays, each
7649 represented by a matrix-like object of numeric or other mode. The rows
7650 typically represent genomic ranges of interest and the columns represent
7652 (license license:artistic2.0)))
7654 (define-public r-genomicalignments
7656 (name "r-genomicalignments")
7660 (uri (bioconductor-uri "GenomicAlignments" version))
7663 "1maslav2r34wjyzh2nlwa862in1ir7i5xk57nw2nlfh5gqy112jd"))))
7665 `((upstream-name . "GenomicAlignments")))
7666 (build-system r-build-system)
7668 `(("r-biocgenerics" ,r-biocgenerics)
7669 ("r-biocparallel" ,r-biocparallel)
7670 ("r-biostrings" ,r-biostrings)
7671 ("r-genomeinfodb" ,r-genomeinfodb)
7672 ("r-genomicranges" ,r-genomicranges)
7673 ("r-iranges" ,r-iranges)
7674 ("r-rsamtools" ,r-rsamtools)
7675 ("r-s4vectors" ,r-s4vectors)
7676 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7677 (home-page "https://bioconductor.org/packages/GenomicAlignments")
7678 (synopsis "Representation and manipulation of short genomic alignments")
7680 "This package provides efficient containers for storing and manipulating
7681 short genomic alignments (typically obtained by aligning short reads to a
7682 reference genome). This includes read counting, computing the coverage,
7683 junction detection, and working with the nucleotide content of the
7685 (license license:artistic2.0)))
7687 (define-public r-rtracklayer
7689 (name "r-rtracklayer")
7693 (uri (bioconductor-uri "rtracklayer" version))
7696 "1ycmcxvgvszvjv75hlmg0i6pq8i7r8720vgmfayb905s9l6j82x6"))))
7697 (build-system r-build-system)
7700 (modify-phases %standard-phases
7701 (add-after 'unpack 'use-system-zlib
7703 (substitute* "DESCRIPTION"
7704 ((" zlibbioc,") ""))
7705 (substitute* "NAMESPACE"
7706 (("import\\(zlibbioc\\)") ""))
7709 `(("pkg-config" ,pkg-config)))
7713 `(("r-biocgenerics" ,r-biocgenerics)
7714 ("r-biostrings" ,r-biostrings)
7715 ("r-genomeinfodb" ,r-genomeinfodb)
7716 ("r-genomicalignments" ,r-genomicalignments)
7717 ("r-genomicranges" ,r-genomicranges)
7718 ("r-iranges" ,r-iranges)
7719 ("r-rcurl" ,r-rcurl)
7720 ("r-rsamtools" ,r-rsamtools)
7721 ("r-s4vectors" ,r-s4vectors)
7723 ("r-xvector" ,r-xvector)))
7724 (home-page "https://bioconductor.org/packages/rtracklayer")
7725 (synopsis "R interface to genome browsers and their annotation tracks")
7727 "rtracklayer is an extensible framework for interacting with multiple
7728 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7729 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7730 built-in). The user may export/import tracks to/from the supported browsers,
7731 as well as query and modify the browser state, such as the current viewport.")
7732 (license license:artistic2.0)))
7734 (define-public r-genomicfeatures
7736 (name "r-genomicfeatures")
7740 (uri (bioconductor-uri "GenomicFeatures" version))
7743 "0qs94b0ywrjyc9m1jykrbch3lb07576m508dikvx18vwn304mban"))))
7745 `((upstream-name . "GenomicFeatures")))
7746 (build-system r-build-system)
7748 `(("r-annotationdbi" ,r-annotationdbi)
7749 ("r-biobase" ,r-biobase)
7750 ("r-biocgenerics" ,r-biocgenerics)
7751 ("r-biomart" ,r-biomart)
7752 ("r-biostrings" ,r-biostrings)
7754 ("r-genomeinfodb" ,r-genomeinfodb)
7755 ("r-genomicranges" ,r-genomicranges)
7756 ("r-iranges" ,r-iranges)
7757 ("r-rcurl" ,r-rcurl)
7758 ("r-rsqlite" ,r-rsqlite)
7759 ("r-rtracklayer" ,r-rtracklayer)
7760 ("r-s4vectors" ,r-s4vectors)
7761 ("r-xvector" ,r-xvector)))
7762 (home-page "https://bioconductor.org/packages/GenomicFeatures")
7763 (synopsis "Tools for working with transcript centric annotations")
7765 "This package provides a set of tools and methods for making and
7766 manipulating transcript centric annotations. With these tools the user can
7767 easily download the genomic locations of the transcripts, exons and cds of a
7768 given organism, from either the UCSC Genome Browser or a BioMart
7769 database (more sources will be supported in the future). This information is
7770 then stored in a local database that keeps track of the relationship between
7771 transcripts, exons, cds and genes. Flexible methods are provided for
7772 extracting the desired features in a convenient format.")
7773 (license license:artistic2.0)))
7775 (define-public r-go-db
7781 (uri (string-append "https://www.bioconductor.org/packages/"
7782 "release/data/annotation/src/contrib/GO.db_"
7786 "0i3wcf5h3n0dawzc1hy0kv74f06j80c47n4p3g3fmrcxlhi3jpa5"))))
7788 `((upstream-name . "GO.db")))
7789 (build-system r-build-system)
7791 `(("r-annotationdbi" ,r-annotationdbi)))
7792 (home-page "https://bioconductor.org/packages/GO.db")
7793 (synopsis "Annotation maps describing the entire Gene Ontology")
7795 "The purpose of this GO.db annotation package is to provide detailed
7796 information about the latest version of the Gene Ontologies.")
7797 (license license:artistic2.0)))
7799 (define-public r-topgo
7805 (uri (bioconductor-uri "topGO" version))
7808 "1j1jcd16j564kr6qz28140fzmnh9xasi84v1c1fi98sqv30zq9bh"))))
7810 `((upstream-name . "topGO")))
7811 (build-system r-build-system)
7813 `(("r-annotationdbi" ,r-annotationdbi)
7815 ("r-biobase" ,r-biobase)
7816 ("r-biocgenerics" ,r-biocgenerics)
7817 ("r-go-db" ,r-go-db)
7818 ("r-graph" ,r-graph)
7819 ("r-lattice" ,r-lattice)
7820 ("r-matrixstats" ,r-matrixstats)
7821 ("r-sparsem" ,r-sparsem)))
7822 (home-page "https://bioconductor.org/packages/topGO")
7823 (synopsis "Enrichment analysis for gene ontology")
7825 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
7826 terms while accounting for the topology of the GO graph. Different test
7827 statistics and different methods for eliminating local similarities and
7828 dependencies between GO terms can be implemented and applied.")
7829 ;; Any version of the LGPL applies.
7830 (license license:lgpl2.1+)))
7832 (define-public r-bsgenome
7838 (uri (bioconductor-uri "BSgenome" version))
7841 "07z4zxx0khrc86qqvc7vxww8df9fh6pyks9ajxkc9gdqr5nn79j7"))))
7843 `((upstream-name . "BSgenome")))
7844 (build-system r-build-system)
7846 `(("r-biocgenerics" ,r-biocgenerics)
7847 ("r-biostrings" ,r-biostrings)
7848 ("r-genomeinfodb" ,r-genomeinfodb)
7849 ("r-genomicranges" ,r-genomicranges)
7850 ("r-iranges" ,r-iranges)
7851 ("r-rsamtools" ,r-rsamtools)
7852 ("r-rtracklayer" ,r-rtracklayer)
7853 ("r-s4vectors" ,r-s4vectors)
7854 ("r-xvector" ,r-xvector)))
7855 (home-page "https://bioconductor.org/packages/BSgenome")
7856 (synopsis "Infrastructure for Biostrings-based genome data packages")
7858 "This package provides infrastructure shared by all Biostrings-based
7859 genome data packages and support for efficient SNP representation.")
7860 (license license:artistic2.0)))
7862 (define-public r-impute
7868 (uri (bioconductor-uri "impute" version))
7871 "08z0pj1dz5iq967nwj67qyka7ir7m5an2ggv7bsrlz3apzfsla33"))))
7873 `(("gfortran" ,gfortran)))
7874 (build-system r-build-system)
7875 (home-page "https://bioconductor.org/packages/impute")
7876 (synopsis "Imputation for microarray data")
7878 "This package provides a function to impute missing gene expression
7879 microarray data, using nearest neighbor averaging.")
7880 (license license:gpl2+)))
7882 (define-public r-seqpattern
7884 (name "r-seqpattern")
7888 (uri (bioconductor-uri "seqPattern" version))
7891 "0di83qi83mrlw7i12khsq55d03hlazcywaa9m9pki1sfhafpq733"))))
7893 `((upstream-name . "seqPattern")))
7894 (build-system r-build-system)
7896 `(("r-biostrings" ,r-biostrings)
7897 ("r-genomicranges" ,r-genomicranges)
7898 ("r-iranges" ,r-iranges)
7899 ("r-kernsmooth" ,r-kernsmooth)
7900 ("r-plotrix" ,r-plotrix)))
7901 (home-page "https://bioconductor.org/packages/seqPattern")
7902 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
7904 "This package provides tools to visualize oligonucleotide patterns and
7905 sequence motif occurrences across a large set of sequences centred at a common
7906 reference point and sorted by a user defined feature.")
7907 (license license:gpl3+)))
7909 (define-public r-genomation
7911 (name "r-genomation")
7915 (uri (bioconductor-uri "genomation" version))
7918 "0g0v4alfpqlinqinjnyzl3mrjnpbdx9ri34mcaiqbvbvg8ic8wvg"))))
7919 (build-system r-build-system)
7921 `(("r-biostrings" ,r-biostrings)
7922 ("r-bsgenome" ,r-bsgenome)
7923 ("r-data-table" ,r-data-table)
7924 ("r-genomeinfodb" ,r-genomeinfodb)
7925 ("r-genomicalignments" ,r-genomicalignments)
7926 ("r-genomicranges" ,r-genomicranges)
7927 ("r-ggplot2" ,r-ggplot2)
7928 ("r-gridbase" ,r-gridbase)
7929 ("r-impute" ,r-impute)
7930 ("r-iranges" ,r-iranges)
7931 ("r-matrixstats" ,r-matrixstats)
7932 ("r-plotrix" ,r-plotrix)
7935 ("r-readr" ,r-readr)
7936 ("r-reshape2" ,r-reshape2)
7937 ("r-rsamtools" ,r-rsamtools)
7938 ("r-rtracklayer" ,r-rtracklayer)
7939 ("r-runit" ,r-runit)
7940 ("r-s4vectors" ,r-s4vectors)
7941 ("r-seqpattern" ,r-seqpattern)))
7942 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7943 (synopsis "Summary, annotation and visualization of genomic data")
7945 "This package provides a package for summary and annotation of genomic
7946 intervals. Users can visualize and quantify genomic intervals over
7947 pre-defined functional regions, such as promoters, exons, introns, etc. The
7948 genomic intervals represent regions with a defined chromosome position, which
7949 may be associated with a score, such as aligned reads from HT-seq experiments,
7950 TF binding sites, methylation scores, etc. The package can use any tabular
7951 genomic feature data as long as it has minimal information on the locations of
7952 genomic intervals. In addition, it can use BAM or BigWig files as input.")
7953 (license license:artistic2.0)))
7955 (define-public r-genomationdata
7957 (name "r-genomationdata")
7961 ;; We cannot use bioconductor-uri here because this tarball is
7962 ;; located under "data/annotation/" instead of "bioc/".
7963 (uri (string-append "https://bioconductor.org/packages/"
7964 "release/data/experiment/src/contrib/"
7965 "genomationData_" version ".tar.gz"))
7968 "10xyb8akjrhmak2i0mnv1agny2ipy364q9nlibyplpzc7vdb6bw7"))))
7969 (build-system r-build-system)
7970 ;; As this package provides little more than large data files, it doesn't
7971 ;; make sense to build substitutes.
7972 (arguments `(#:substitutable? #f))
7974 `(("r-knitr" ,r-knitr)))
7975 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
7976 (synopsis "Experimental data for use with the genomation package")
7978 "This package contains experimental genetic data for use with the
7979 genomation package. Included are Chip Seq, Methylation and Cage data,
7980 downloaded from Encode.")
7981 (license license:gpl3+)))
7983 (define-public r-org-hs-eg-db
7985 (name "r-org-hs-eg-db")
7989 ;; We cannot use bioconductor-uri here because this tarball is
7990 ;; located under "data/annotation/" instead of "bioc/".
7991 (uri (string-append "https://www.bioconductor.org/packages/"
7992 "release/data/annotation/src/contrib/"
7993 "org.Hs.eg.db_" version ".tar.gz"))
7996 "1qxz9l80yg3qdqszs6dsscp7lrpfi1bgd0pxh9j7q34vprzwhdim"))))
7998 `((upstream-name . "org.Hs.eg.db")))
7999 (build-system r-build-system)
8001 `(("r-annotationdbi" ,r-annotationdbi)))
8002 (home-page "https://www.bioconductor.org/packages/org.Hs.eg.db/")
8003 (synopsis "Genome wide annotation for Human")
8005 "This package contains genome-wide annotations for Human, primarily based
8006 on mapping using Entrez Gene identifiers.")
8007 (license license:artistic2.0)))
8009 (define-public r-org-ce-eg-db
8011 (name "r-org-ce-eg-db")
8015 ;; We cannot use bioconductor-uri here because this tarball is
8016 ;; located under "data/annotation/" instead of "bioc/".
8017 (uri (string-append "https://www.bioconductor.org/packages/"
8018 "release/data/annotation/src/contrib/"
8019 "org.Ce.eg.db_" version ".tar.gz"))
8022 "1w5br1ss4ha8wv4v2saj7cmbjc2jw0dyj2f2y269l078z31wcnaz"))))
8024 `((upstream-name . "org.Ce.eg.db")))
8025 (build-system r-build-system)
8027 `(("r-annotationdbi" ,r-annotationdbi)))
8028 (home-page "https://www.bioconductor.org/packages/org.Ce.eg.db/")
8029 (synopsis "Genome wide annotation for Worm")
8031 "This package provides mappings from Entrez gene identifiers to various
8032 annotations for the genome of the model worm Caenorhabditis elegans.")
8033 (license license:artistic2.0)))
8035 (define-public r-org-dm-eg-db
8037 (name "r-org-dm-eg-db")
8041 ;; We cannot use bioconductor-uri here because this tarball is
8042 ;; located under "data/annotation/" instead of "bioc/".
8043 (uri (string-append "https://www.bioconductor.org/packages/"
8044 "release/data/annotation/src/contrib/"
8045 "org.Dm.eg.db_" version ".tar.gz"))
8048 "1pqjrzlyg72bjpy8zsxvaglc7jsv176bnyi87xdajmkvsgxpm7b3"))))
8050 `((upstream-name . "org.Dm.eg.db")))
8051 (build-system r-build-system)
8053 `(("r-annotationdbi" ,r-annotationdbi)))
8054 (home-page "https://www.bioconductor.org/packages/org.Dm.eg.db/")
8055 (synopsis "Genome wide annotation for Fly")
8057 "This package provides mappings from Entrez gene identifiers to various
8058 annotations for the genome of the model fruit fly Drosophila melanogaster.")
8059 (license license:artistic2.0)))
8061 (define-public r-org-mm-eg-db
8063 (name "r-org-mm-eg-db")
8067 ;; We cannot use bioconductor-uri here because this tarball is
8068 ;; located under "data/annotation/" instead of "bioc/".
8069 (uri (string-append "https://www.bioconductor.org/packages/"
8070 "release/data/annotation/src/contrib/"
8071 "org.Mm.eg.db_" version ".tar.gz"))
8074 "1i3nvrd3wjigf1rmgxq1p5xxc3p8v02h5gwi62s30rkrsyjjfjxx"))))
8076 `((upstream-name . "org.Mm.eg.db")))
8077 (build-system r-build-system)
8079 `(("r-annotationdbi" ,r-annotationdbi)))
8080 (home-page "https://www.bioconductor.org/packages/org.Mm.eg.db/")
8081 (synopsis "Genome wide annotation for Mouse")
8083 "This package provides mappings from Entrez gene identifiers to various
8084 annotations for the genome of the model mouse Mus musculus.")
8085 (license license:artistic2.0)))
8087 (define-public r-seqlogo
8094 (uri (bioconductor-uri "seqLogo" version))
8097 "022vr9ydwcivs7rw7kwj73gfk5gc7ckwa1q66vhd4kw9ylh70v68"))))
8098 (properties `((upstream-name . "seqLogo")))
8099 (build-system r-build-system)
8100 (home-page "https://bioconductor.org/packages/seqLogo")
8101 (synopsis "Sequence logos for DNA sequence alignments")
8103 "seqLogo takes the position weight matrix of a DNA sequence motif and
8104 plots the corresponding sequence logo as introduced by Schneider and
8106 (license license:lgpl2.0+)))
8108 (define-public r-bsgenome-mmusculus-ucsc-mm10
8110 (name "r-bsgenome-mmusculus-ucsc-mm10")
8114 ;; We cannot use bioconductor-uri here because this tarball is
8115 ;; located under "data/annotation/" instead of "bioc/".
8116 (uri (string-append "https://www.bioconductor.org/packages/"
8117 "release/data/annotation/src/contrib/"
8118 "BSgenome.Mmusculus.UCSC.mm10_"
8122 "12s0nm2na9brjad4rn9l7d3db2aj8qa1xvz0y1k7gk08wayb6bkf"))))
8124 `((upstream-name . "BSgenome.Mmusculus.UCSC.mm10")))
8125 (build-system r-build-system)
8126 ;; As this package provides little more than a very large data file it
8127 ;; doesn't make sense to build substitutes.
8128 (arguments `(#:substitutable? #f))
8130 `(("r-bsgenome" ,r-bsgenome)))
8132 "https://www.bioconductor.org/packages/BSgenome.Mmusculus.UCSC.mm10/")
8133 (synopsis "Full genome sequences for Mouse")
8135 "This package provides full genome sequences for Mus
8136 musculus (Mouse) as provided by UCSC (mm10, December 2011) and stored
8137 in Biostrings objects.")
8138 (license license:artistic2.0)))
8140 (define-public r-txdb-mmusculus-ucsc-mm10-knowngene
8142 (name "r-txdb-mmusculus-ucsc-mm10-knowngene")
8146 ;; We cannot use bioconductor-uri here because this tarball is
8147 ;; located under "data/annotation/" instead of "bioc/".
8148 (uri (string-append "https://www.bioconductor.org/packages/"
8149 "release/data/annotation/src/contrib/"
8150 "TxDb.Mmusculus.UCSC.mm10.knownGene_"
8154 "01lgxc1fx5nhlpbwjd5zqghkkbmh6axd98ikx4b0spv0jdg6gf39"))))
8156 `((upstream-name . "TxDb.Mmusculus.UCSC.mm10.knownGene")))
8157 (build-system r-build-system)
8158 ;; As this package provides little more than a very large data file it
8159 ;; doesn't make sense to build substitutes.
8160 (arguments `(#:substitutable? #f))
8162 `(("r-bsgenome" ,r-bsgenome)
8163 ("r-genomicfeatures" ,r-genomicfeatures)
8164 ("r-annotationdbi" ,r-annotationdbi)))
8166 "https://bioconductor.org/packages/TxDb.Mmusculus.UCSC.mm10.knownGene/")
8167 (synopsis "Annotation package for TxDb knownGene object(s) for Mouse")
8169 "This package loads a TxDb object, which is an R interface to
8170 prefabricated databases contained in this package. This package provides
8171 the TxDb object of Mouse data as provided by UCSC (mm10, December 2011)
8172 based on the knownGene track.")
8173 (license license:artistic2.0)))
8175 (define-public r-bsgenome-celegans-ucsc-ce6
8177 (name "r-bsgenome-celegans-ucsc-ce6")
8181 ;; We cannot use bioconductor-uri here because this tarball is
8182 ;; located under "data/annotation/" instead of "bioc/".
8183 (uri (string-append "https://www.bioconductor.org/packages/"
8184 "release/data/annotation/src/contrib/"
8185 "BSgenome.Celegans.UCSC.ce6_"
8189 "0mqzb353xv2c3m3vkb315dkmnxkgczp7ndnknyhpgjlybyf715v9"))))
8191 `((upstream-name . "BSgenome.Celegans.UCSC.ce6")))
8192 (build-system r-build-system)
8193 ;; As this package provides little more than a very large data file it
8194 ;; doesn't make sense to build substitutes.
8195 (arguments `(#:substitutable? #f))
8197 `(("r-bsgenome" ,r-bsgenome)))
8199 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce6/")
8200 (synopsis "Full genome sequences for Worm")
8202 "This package provides full genome sequences for Caenorhabditis
8203 elegans (Worm) as provided by UCSC (ce6, May 2008) and stored in Biostrings
8205 (license license:artistic2.0)))
8207 (define-public r-bsgenome-celegans-ucsc-ce10
8209 (name "r-bsgenome-celegans-ucsc-ce10")
8213 ;; We cannot use bioconductor-uri here because this tarball is
8214 ;; located under "data/annotation/" instead of "bioc/".
8215 (uri (string-append "https://www.bioconductor.org/packages/"
8216 "release/data/annotation/src/contrib/"
8217 "BSgenome.Celegans.UCSC.ce10_"
8221 "1zaym97jk4npxk14ifvwz2rvhm4zx9xgs33r9vvx9rlynp0gydrk"))))
8223 `((upstream-name . "BSgenome.Celegans.UCSC.ce10")))
8224 (build-system r-build-system)
8225 ;; As this package provides little more than a very large data file it
8226 ;; doesn't make sense to build substitutes.
8227 (arguments `(#:substitutable? #f))
8229 `(("r-bsgenome" ,r-bsgenome)))
8231 "https://www.bioconductor.org/packages/BSgenome.Celegans.UCSC.ce10/")
8232 (synopsis "Full genome sequences for Worm")
8234 "This package provides full genome sequences for Caenorhabditis
8235 elegans (Worm) as provided by UCSC (ce10, Oct 2010) and stored in Biostrings
8237 (license license:artistic2.0)))
8239 (define-public r-bsgenome-dmelanogaster-ucsc-dm3
8241 (name "r-bsgenome-dmelanogaster-ucsc-dm3")
8245 ;; We cannot use bioconductor-uri here because this tarball is
8246 ;; located under "data/annotation/" instead of "bioc/".
8247 (uri (string-append "https://www.bioconductor.org/packages/"
8248 "release/data/annotation/src/contrib/"
8249 "BSgenome.Dmelanogaster.UCSC.dm3_"
8253 "19bm3lkhhkag3gnwp419211fh0cnr0x6fa0r1lr0ycwrikxdxsv8"))))
8255 `((upstream-name . "BSgenome.Dmelanogaster.UCSC.dm3")))
8256 (build-system r-build-system)
8257 ;; As this package provides little more than a very large data file it
8258 ;; doesn't make sense to build substitutes.
8259 (arguments `(#:substitutable? #f))
8261 `(("r-bsgenome" ,r-bsgenome)))
8263 "https://www.bioconductor.org/packages/BSgenome.Dmelanogaster.UCSC.dm3/")
8264 (synopsis "Full genome sequences for Fly")
8266 "This package provides full genome sequences for Drosophila
8267 melanogaster (Fly) as provided by UCSC (dm3, April 2006) and stored in
8268 Biostrings objects.")
8269 (license license:artistic2.0)))
8271 (define-public r-motifrg
8278 (uri (bioconductor-uri "motifRG" version))
8281 "1wxww6i0jgyapqclcwy0zzf9kqjvrvylr89z7yhg1izi7jnw2fka"))))
8282 (properties `((upstream-name . "motifRG")))
8283 (build-system r-build-system)
8285 `(("r-biostrings" ,r-biostrings)
8286 ("r-bsgenome" ,r-bsgenome)
8287 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8288 ("r-iranges" ,r-iranges)
8289 ("r-seqlogo" ,r-seqlogo)
8290 ("r-xvector" ,r-xvector)))
8291 (home-page "https://bioconductor.org/packages/motifRG")
8292 (synopsis "Discover motifs in high throughput sequencing data")
8294 "This package provides tools for discriminative motif discovery in high
8295 throughput genetic sequencing data sets using regression methods.")
8296 (license license:artistic2.0)))
8298 (define-public r-qtl
8305 (uri (string-append "mirror://cran/src/contrib/qtl_"
8309 "03lmvydln8b7666b6w46qbryhf83vsd11d4y2v95rfgvqgq66l1i"))))
8310 (build-system r-build-system)
8311 (home-page "http://rqtl.org/")
8312 (synopsis "R package for analyzing QTL experiments in genetics")
8313 (description "R/qtl is an extension library for the R statistics
8314 system. It is used to analyze experimental crosses for identifying
8315 genes contributing to variation in quantitative traits (so-called
8316 quantitative trait loci, QTLs).
8318 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
8319 identify genotyping errors, and to perform single-QTL and two-QTL,
8320 two-dimensional genome scans.")
8321 (license license:gpl3)))
8323 (define-public r-zlibbioc
8329 (uri (bioconductor-uri "zlibbioc" version))
8332 "0bjvzy24kab7ank02cc1qk2ikcz4dllgf66wpsdl0d3zp4gn3l2h"))))
8334 `((upstream-name . "zlibbioc")))
8335 (build-system r-build-system)
8336 (home-page "https://bioconductor.org/packages/zlibbioc")
8337 (synopsis "Provider for zlib-1.2.5 to R packages")
8338 (description "This package uses the source code of zlib-1.2.5 to create
8339 libraries for systems that do not have these available via other means.")
8340 (license license:artistic2.0)))
8342 (define-public r-r4rna
8349 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8353 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8354 (build-system r-build-system)
8356 `(("r-optparse" ,r-optparse)
8357 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8358 (home-page "http://www.e-rna.org/r-chie/index.cgi")
8359 (synopsis "Analysis framework for RNA secondary structure")
8361 "The R4RNA package aims to be a general framework for the analysis of RNA
8362 secondary structure and comparative analysis in R.")
8363 (license license:gpl3+)))
8365 (define-public r-rhtslib
8372 (uri (bioconductor-uri "Rhtslib" version))
8375 "1h4q54f8za3aaxgy186zf2165sar5c3cgxkk44lq5hzx5pxkl5wn"))))
8376 (properties `((upstream-name . "Rhtslib")))
8377 (build-system r-build-system)
8379 `(("r-zlibbioc" ,r-zlibbioc)))
8383 `(("pkg-config" ,pkg-config)))
8384 (home-page "https://github.com/nhayden/Rhtslib")
8385 (synopsis "High-throughput sequencing library as an R package")
8387 "This package provides the HTSlib C library for high-throughput
8388 nucleotide sequence analysis. The package is primarily useful to developers
8389 of other R packages who wish to make use of HTSlib.")
8390 (license license:lgpl2.0+)))
8392 (define-public r-bamsignals
8394 (name "r-bamsignals")
8399 (uri (bioconductor-uri "bamsignals" version))
8402 "19irfx1y1izf903vq59wxsdbf88g143zy9l89gxqawh7jfxds8w8"))))
8403 (build-system r-build-system)
8405 `(("r-biocgenerics" ,r-biocgenerics)
8406 ("r-genomicranges" ,r-genomicranges)
8407 ("r-iranges" ,r-iranges)
8409 ("r-rhtslib" ,r-rhtslib)
8410 ("r-zlibbioc" ,r-zlibbioc)))
8413 (home-page "https://bioconductor.org/packages/bamsignals")
8414 (synopsis "Extract read count signals from bam files")
8416 "This package allows to efficiently obtain count vectors from indexed bam
8417 files. It counts the number of nucleotide sequence reads in given genomic
8418 ranges and it computes reads profiles and coverage profiles. It also handles
8420 (license license:gpl2+)))
8422 (define-public r-rcas
8428 (uri (bioconductor-uri "RCAS" version))
8431 "0ss5hcg2m7gjji6dd23zxa5bd5a7knwcnada4qs5q2l4clgk39ad"))))
8432 (build-system r-build-system)
8434 `(("r-annotationdbi" ,r-annotationdbi)
8435 ("r-biocgenerics" ,r-biocgenerics)
8436 ("r-biomart" ,r-biomart)
8437 ("r-biostrings" ,r-biostrings)
8438 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8439 ("r-cowplot" ,r-cowplot)
8440 ("r-data-table" ,r-data-table)
8443 ("r-genomation" ,r-genomation)
8444 ("r-genomeinfodb" ,r-genomeinfodb)
8445 ("r-genomicfeatures" ,r-genomicfeatures)
8446 ("r-genomicranges" ,r-genomicranges)
8447 ("r-ggplot2" ,r-ggplot2)
8448 ("r-ggseqlogo" ,r-ggseqlogo)
8449 ("r-knitr" ,r-knitr)
8450 ("r-motifrg" ,r-motifrg)
8451 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8452 ("r-pbapply" ,r-pbapply)
8453 ("r-pheatmap" ,r-pheatmap)
8454 ("r-plotly" ,r-plotly)
8455 ("r-plotrix" ,r-plotrix)
8456 ("r-proxy" ,r-proxy)
8457 ("r-rsqlite" ,r-rsqlite)
8458 ("r-rtracklayer" ,r-rtracklayer)
8459 ("r-rmarkdown" ,r-rmarkdown)
8460 ("r-s4vectors" ,r-s4vectors)
8461 ("r-topgo" ,r-topgo)))
8462 (synopsis "RNA-centric annotation system")
8464 "RCAS aims to be a standalone RNA-centric annotation system that provides
8465 intuitive reports and publication-ready graphics. This package provides the R
8466 library implementing most of the pipeline's features.")
8467 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8468 (license license:artistic2.0)))
8470 (define-public rcas-web
8477 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8478 "releases/download/v" version
8479 "/rcas-web-" version ".tar.gz"))
8482 "0wq951aj45gqki1bickg876i993lmawkp8x24agg264br5x716db"))))
8483 (build-system gnu-build-system)
8486 (modify-phases %standard-phases
8487 (add-after 'install 'wrap-executable
8488 (lambda* (#:key inputs outputs #:allow-other-keys)
8489 (let* ((out (assoc-ref outputs "out"))
8490 (json (assoc-ref inputs "guile-json"))
8491 (redis (assoc-ref inputs "guile-redis"))
8492 (path (string-append
8493 json "/share/guile/site/2.2:"
8494 redis "/share/guile/site/2.2")))
8495 (wrap-program (string-append out "/bin/rcas-web")
8496 `("GUILE_LOAD_PATH" ":" = (,path))
8497 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8498 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8501 `(("r-minimal" ,r-minimal)
8503 ("guile-next" ,guile-2.2)
8504 ("guile-json" ,guile-json)
8505 ("guile-redis" ,guile-redis)))
8507 `(("pkg-config" ,pkg-config)))
8508 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8509 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8510 (description "This package provides a simple web interface for the
8511 @dfn{RNA-centric annotation system} (RCAS).")
8512 (license license:agpl3+)))
8514 (define-public r-mutationalpatterns
8516 (name "r-mutationalpatterns")
8521 (uri (bioconductor-uri "MutationalPatterns" version))
8524 "0w9lg1zs106h6rqvy8mhikq6q6q9syw6c1prcxr38ssh85rcih12"))))
8525 (build-system r-build-system)
8527 `(("r-biocgenerics" ,r-biocgenerics)
8528 ("r-biostrings" ,r-biostrings)
8529 ;; These two packages are suggested packages
8530 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8531 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8532 ("r-genomicranges" ,r-genomicranges)
8533 ("r-genomeinfodb" ,r-genomeinfodb)
8534 ("r-ggplot2" ,r-ggplot2)
8535 ("r-iranges" ,r-iranges)
8538 ("r-pracma" ,r-pracma)
8539 ("r-reshape2" ,r-reshape2)
8540 ("r-cowplot" ,r-cowplot)
8541 ("r-ggdendro" ,r-ggdendro)
8542 ("r-s4vectors" ,r-s4vectors)
8543 ("r-summarizedexperiment" ,r-summarizedexperiment)
8544 ("r-variantannotation" ,r-variantannotation)))
8545 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8546 (synopsis "Extract and visualize mutational patterns in genomic data")
8547 (description "This package provides an extensive toolset for the
8548 characterization and visualization of a wide range of mutational patterns
8549 in SNV base substitution data.")
8550 (license license:expat)))
8552 (define-public r-wgcna
8559 (uri (cran-uri "WGCNA" version))
8562 "0rhnyhzfn93yp24jz9v6dzrmyizwzdw070a7idm0k33w1cm8sjqv"))))
8563 (properties `((upstream-name . "WGCNA")))
8564 (build-system r-build-system)
8566 `(("r-annotationdbi" ,r-annotationdbi)
8567 ("r-doparallel" ,r-doparallel)
8568 ("r-dynamictreecut" ,r-dynamictreecut)
8569 ("r-fastcluster" ,r-fastcluster)
8570 ("r-foreach" ,r-foreach)
8571 ("r-go-db" ,r-go-db)
8572 ("r-hmisc" ,r-hmisc)
8573 ("r-impute" ,r-impute)
8575 ("r-robust" ,r-robust)
8576 ("r-survival" ,r-survival)
8577 ("r-matrixstats" ,r-matrixstats)
8578 ("r-preprocesscore" ,r-preprocesscore)))
8580 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8581 (synopsis "Weighted correlation network analysis")
8583 "This package provides functions necessary to perform Weighted
8584 Correlation Network Analysis on high-dimensional data. It includes functions
8585 for rudimentary data cleaning, construction and summarization of correlation
8586 networks, module identification and functions for relating both variables and
8587 modules to sample traits. It also includes a number of utility functions for
8588 data manipulation and visualization.")
8589 (license license:gpl2+)))
8591 (define-public r-chipkernels
8592 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8595 (name "r-chipkernels")
8596 (version (string-append "1.1-" revision "." (string-take commit 9)))
8601 (url "https://github.com/ManuSetty/ChIPKernels.git")
8603 (file-name (string-append name "-" version))
8606 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8607 (build-system r-build-system)
8609 `(("r-iranges" ,r-iranges)
8610 ("r-xvector" ,r-xvector)
8611 ("r-biostrings" ,r-biostrings)
8612 ("r-bsgenome" ,r-bsgenome)
8613 ("r-gtools" ,r-gtools)
8614 ("r-genomicranges" ,r-genomicranges)
8615 ("r-sfsmisc" ,r-sfsmisc)
8616 ("r-kernlab" ,r-kernlab)
8617 ("r-s4vectors" ,r-s4vectors)
8618 ("r-biocgenerics" ,r-biocgenerics)))
8619 (home-page "https://github.com/ManuSetty/ChIPKernels")
8620 (synopsis "Build string kernels for DNA Sequence analysis")
8621 (description "ChIPKernels is an R package for building different string
8622 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8623 must be built and this dictionary can be used for determining kernels for DNA
8625 (license license:gpl2+))))
8627 (define-public r-seqgl
8635 (url "https://github.com/ManuSetty/SeqGL.git")
8637 (file-name (git-file-name name version))
8640 "1r6ywvhxl3ffv48lgj7sbd582mcc6dha3ksgc2qjlvjrnkbj3799"))))
8641 (build-system r-build-system)
8643 `(("r-biostrings" ,r-biostrings)
8644 ("r-chipkernels" ,r-chipkernels)
8645 ("r-genomicranges" ,r-genomicranges)
8646 ("r-spams" ,r-spams)
8647 ("r-wgcna" ,r-wgcna)
8648 ("r-fastcluster" ,r-fastcluster)))
8649 (home-page "https://github.com/ManuSetty/SeqGL")
8650 (synopsis "Group lasso for Dnase/ChIP-seq data")
8651 (description "SeqGL is a group lasso based algorithm to extract
8652 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8653 This package presents a method which uses group lasso to discriminate between
8654 bound and non bound genomic regions to accurately identify transcription
8655 factors bound at the specific regions.")
8656 (license license:gpl2+)))
8658 (define-public r-gkmsvm
8665 (uri (cran-uri "gkmSVM" version))
8668 "04dakbgfvfalz4rm4fvvybp506dn5fbj5g86ybfhrc6wywjllsz3"))))
8669 (properties `((upstream-name . "gkmSVM")))
8670 (build-system r-build-system)
8672 `(("r-biocgenerics" ,r-biocgenerics)
8673 ("r-biostrings" ,r-biostrings)
8674 ("r-genomeinfodb" ,r-genomeinfodb)
8675 ("r-genomicranges" ,r-genomicranges)
8676 ("r-iranges" ,r-iranges)
8677 ("r-kernlab" ,r-kernlab)
8680 ("r-rtracklayer" ,r-rtracklayer)
8681 ("r-s4vectors" ,r-s4vectors)
8682 ("r-seqinr" ,r-seqinr)))
8683 (home-page "https://cran.r-project.org/web/packages/gkmSVM")
8684 (synopsis "Gapped-kmer support vector machine")
8686 "This R package provides tools for training gapped-kmer SVM classifiers
8687 for DNA and protein sequences. This package supports several sequence
8688 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8689 (license license:gpl2+)))
8691 (define-public r-tximport
8697 (uri (bioconductor-uri "tximport" version))
8700 "16wp09dm0cpb4mc00nmglfb8ica7qb4a55vm8ajgzyagbpfdd44l"))))
8701 (build-system r-build-system)
8702 (home-page "https://bioconductor.org/packages/tximport")
8703 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8705 "This package provides tools to import transcript-level abundance,
8706 estimated counts and transcript lengths, and to summarize them into matrices
8707 for use with downstream gene-level analysis packages. Average transcript
8708 length, weighted by sample-specific transcript abundance estimates, is
8709 provided as a matrix which can be used as an offset for different expression
8710 of gene-level counts.")
8711 (license license:gpl2+)))
8713 (define-public r-rhdf5
8719 (uri (bioconductor-uri "rhdf5" version))
8722 "10zkw3k13wmvyif417gplyf6rwp2gpkjasw97lhwv2f9i32rry9l"))))
8723 (build-system r-build-system)
8725 `(("r-rhdf5lib" ,r-rhdf5lib)))
8728 (home-page "https://bioconductor.org/packages/rhdf5")
8729 (synopsis "HDF5 interface to R")
8731 "This R/Bioconductor package provides an interface between HDF5 and R.
8732 HDF5's main features are the ability to store and access very large and/or
8733 complex datasets and a wide variety of metadata on mass storage (disk) through
8734 a completely portable file format. The rhdf5 package is thus suited for the
8735 exchange of large and/or complex datasets between R and other software
8736 package, and for letting R applications work on datasets that are larger than
8737 the available RAM.")
8738 (license license:artistic2.0)))
8740 (define-public r-annotationfilter
8742 (name "r-annotationfilter")
8746 (uri (bioconductor-uri "AnnotationFilter" version))
8749 "0wrr10cxjzmxx46vjzq2nsf6xlqz1sqwx4xm0sk3d77ff8wmph4x"))))
8751 `((upstream-name . "AnnotationFilter")))
8752 (build-system r-build-system)
8754 `(("r-genomicranges" ,r-genomicranges)
8755 ("r-lazyeval" ,r-lazyeval)))
8756 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8757 (synopsis "Facilities for filtering Bioconductor annotation resources")
8759 "This package provides classes and other infrastructure to implement
8760 filters for manipulating Bioconductor annotation resources. The filters are
8761 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8762 (license license:artistic2.0)))
8764 (define-public emboss
8770 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8771 (version-major+minor version) ".0/"
8772 "EMBOSS-" version ".tar.gz"))
8775 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8776 (build-system gnu-build-system)
8779 (list (string-append "--with-hpdf="
8780 (assoc-ref %build-inputs "libharu")))
8782 (modify-phases %standard-phases
8783 (add-after 'unpack 'fix-checks
8785 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8786 ;; and zlib, but assume that they are all found at the same
8788 (substitute* "configure.in"
8789 (("CHECK_PNGDRIVER")
8790 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8791 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8792 AM_CONDITIONAL(AMPNG, true)"))
8794 (add-after 'fix-checks 'disable-update-check
8796 ;; At build time there is no connection to the Internet, so
8797 ;; looking for updates will not work.
8798 (substitute* "Makefile.am"
8799 (("\\$\\(bindir\\)/embossupdate") ""))
8801 (add-after 'disable-update-check 'autogen
8802 (lambda _ (invoke "autoreconf" "-vif") #t)))))
8808 ("libharu" ,libharu)
8811 `(("autoconf" ,autoconf)
8812 ("automake" ,automake)
8813 ("libtool" ,libtool)
8814 ("pkg-config" ,pkg-config)))
8815 (home-page "http://emboss.sourceforge.net")
8816 (synopsis "Molecular biology analysis suite")
8817 (description "EMBOSS is the \"European Molecular Biology Open Software
8818 Suite\". EMBOSS is an analysis package specially developed for the needs of
8819 the molecular biology (e.g. EMBnet) user community. The software
8820 automatically copes with data in a variety of formats and even allows
8821 transparent retrieval of sequence data from the web. It also provides a
8822 number of libraries for the development of software in the field of molecular
8823 biology. EMBOSS also integrates a range of currently available packages and
8824 tools for sequence analysis into a seamless whole.")
8825 (license license:gpl2+)))
8828 (let ((revision "1")
8829 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8832 ;; The version is 2.13.0 even though no release archives have been
8833 ;; published as yet.
8834 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8838 (url "https://github.com/arq5x/bits.git")
8840 (file-name (string-append name "-" version "-checkout"))
8843 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8844 (build-system gnu-build-system)
8846 `(#:tests? #f ;no tests included
8848 (modify-phases %standard-phases
8850 (add-after 'unpack 'remove-cuda
8852 (substitute* "Makefile"
8854 (("(bits_test_intersections) \\\\" _ match) match))
8857 (lambda* (#:key outputs #:allow-other-keys)
8859 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8864 (home-page "https://github.com/arq5x/bits")
8865 (synopsis "Implementation of binary interval search algorithm")
8866 (description "This package provides an implementation of the
8867 BITS (Binary Interval Search) algorithm, an approach to interval set
8868 intersection. It is especially suited for the comparison of diverse genomic
8869 datasets and the exploration of large datasets of genome
8870 intervals (e.g. genes, sequence alignments).")
8871 (license license:gpl2))))
8873 (define-public piranha
8874 ;; There is no release tarball for the latest version. The latest commit is
8875 ;; older than one year at the time of this writing.
8876 (let ((revision "1")
8877 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8880 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8884 (url "https://github.com/smithlabcode/piranha.git")
8886 (file-name (git-file-name name version))
8889 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
8890 (build-system gnu-build-system)
8892 `(#:test-target "test"
8894 (modify-phases %standard-phases
8895 (add-after 'unpack 'copy-smithlab-cpp
8896 (lambda* (#:key inputs #:allow-other-keys)
8897 (for-each (lambda (file)
8898 (install-file file "./src/smithlab_cpp/"))
8899 (find-files (assoc-ref inputs "smithlab-cpp")))
8901 (add-after 'install 'install-to-store
8902 (lambda* (#:key outputs #:allow-other-keys)
8903 (let* ((out (assoc-ref outputs "out"))
8904 (bin (string-append out "/bin")))
8905 (for-each (lambda (file)
8906 (install-file file bin))
8907 (find-files "bin" ".*")))
8910 (list (string-append "--with-bam_tools_headers="
8911 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
8912 (string-append "--with-bam_tools_library="
8913 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
8915 `(("bamtools" ,bamtools)
8916 ("samtools" ,samtools-0.1)
8919 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8923 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8925 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8928 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8930 `(("python" ,python-2)))
8931 (home-page "https://github.com/smithlabcode/piranha")
8932 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
8934 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
8935 RIP-seq experiments. It takes input in BED or BAM format and identifies
8936 regions of statistically significant read enrichment. Additional covariates
8937 may optionally be provided to further inform the peak-calling process.")
8938 (license license:gpl3+))))
8946 (uri (pypi-uri "PePr" version))
8949 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
8950 (build-system python-build-system)
8952 `(#:python ,python-2 ; python2 only
8953 #:tests? #f)) ; no tests included
8955 `(("python2-numpy" ,python2-numpy)
8956 ("python2-scipy" ,python2-scipy)
8957 ("python2-pysam" ,python2-pysam)))
8958 (home-page "https://github.com/shawnzhangyx/PePr")
8959 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
8961 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
8962 that is primarily designed for data with biological replicates. It uses a
8963 negative binomial distribution to model the read counts among the samples in
8964 the same group, and look for consistent differences between ChIP and control
8965 group or two ChIP groups run under different conditions.")
8966 (license license:gpl3+)))
8968 (define-public filevercmp
8969 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
8972 (version (string-append "0-1." (string-take commit 7)))
8976 (url "https://github.com/ekg/filevercmp.git")
8978 (file-name (git-file-name name commit))
8981 "1j9vxsy0y050v59h0q1d6501fcw1kjvj0d18l1xk2zyg0jzj247c"))))
8982 (build-system gnu-build-system)
8984 `(#:tests? #f ; There are no tests to run.
8986 (modify-phases %standard-phases
8987 (delete 'configure) ; There is no configure phase.
8989 (lambda* (#:key outputs #:allow-other-keys)
8990 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
8991 (install-file "filevercmp" bin)
8993 (home-page "https://github.com/ekg/filevercmp")
8994 (synopsis "This program compares version strings")
8995 (description "This program compares version strings. It intends to be a
8996 replacement for strverscmp.")
8997 (license license:gpl3+))))
8999 (define-public multiqc
9006 (uri (pypi-uri "multiqc" version))
9009 "02iihfl0w0hpnr4pa0sbd1y9qxrg3ycyhjp5lidkcrqh1lmzs3zy"))))
9010 (build-system python-build-system)
9012 `(("python-jinja2" ,python-jinja2)
9013 ("python-simplejson" ,python-simplejson)
9014 ("python-pyyaml" ,python-pyyaml)
9015 ("python-click" ,python-click)
9016 ("python-spectra" ,python-spectra)
9017 ("python-requests" ,python-requests)
9018 ("python-markdown" ,python-markdown)
9019 ("python-lzstring" ,python-lzstring)
9020 ("python-matplotlib" ,python-matplotlib)
9021 ("python-numpy" ,python-numpy)
9022 ;; MultQC checks for the presence of nose at runtime.
9023 ("python-nose" ,python-nose)))
9026 (modify-phases %standard-phases
9027 (add-after 'unpack 'relax-requirements
9029 (substitute* "setup.py"
9030 ;; MultiQC 1.5 ‘requires’ a version of python-matplotlib older
9031 ;; than the one in Guix, but should work fine with 2.2.2.
9032 ;; See <https://github.com/ewels/MultiQC/issues/725> and
9033 ;; <https://github.com/ewels/MultiQC/issues/732> for details.
9034 (("['\"]matplotlib.*?['\"]")
9037 (home-page "http://multiqc.info")
9038 (synopsis "Aggregate bioinformatics analysis reports")
9040 "MultiQC is a tool to aggregate bioinformatics results across many
9041 samples into a single report. It contains modules for a large number of
9042 common bioinformatics tools.")
9043 (license license:gpl3+)))
9045 (define-public r-chipseq
9052 (uri (bioconductor-uri "chipseq" version))
9055 "1pp1rm5fs3hlar5x4dl3a3b4gara7qwf81dbvka6r1n78hrf9x1b"))))
9056 (build-system r-build-system)
9058 `(("r-biocgenerics" ,r-biocgenerics)
9059 ("r-genomicranges" ,r-genomicranges)
9060 ("r-iranges" ,r-iranges)
9061 ("r-lattice" ,r-lattice)
9062 ("r-s4vectors" ,r-s4vectors)
9063 ("r-shortread" ,r-shortread)))
9064 (home-page "https://bioconductor.org/packages/chipseq")
9065 (synopsis "Package for analyzing ChIPseq data")
9067 "This package provides tools for processing short read data from ChIPseq
9069 (license license:artistic2.0)))
9071 (define-public r-copyhelper
9073 (name "r-copyhelper")
9078 (uri (string-append "https://bioconductor.org/packages/release/"
9079 "data/experiment/src/contrib/CopyhelpeR_"
9083 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
9084 (properties `((upstream-name . "CopyhelpeR")))
9085 (build-system r-build-system)
9086 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
9087 (synopsis "Helper files for CopywriteR")
9089 "This package contains the helper files that are required to run the
9090 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
9091 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
9092 mm10. In addition, it contains a blacklist filter to remove regions that
9093 display copy number variation. Files are stored as GRanges objects from the
9094 GenomicRanges Bioconductor package.")
9095 (license license:gpl2)))
9097 (define-public r-copywriter
9099 (name "r-copywriter")
9104 (uri (bioconductor-uri "CopywriteR" version))
9107 "1hbiw0m9hmx4na9v502pxf8y5wvxzr68r4d3fqr2755gxx86qck6"))))
9108 (properties `((upstream-name . "CopywriteR")))
9109 (build-system r-build-system)
9111 `(("r-biocparallel" ,r-biocparallel)
9112 ("r-chipseq" ,r-chipseq)
9113 ("r-copyhelper" ,r-copyhelper)
9114 ("r-data-table" ,r-data-table)
9115 ("r-dnacopy" ,r-dnacopy)
9116 ("r-futile-logger" ,r-futile-logger)
9117 ("r-genomeinfodb" ,r-genomeinfodb)
9118 ("r-genomicalignments" ,r-genomicalignments)
9119 ("r-genomicranges" ,r-genomicranges)
9120 ("r-gtools" ,r-gtools)
9121 ("r-iranges" ,r-iranges)
9122 ("r-matrixstats" ,r-matrixstats)
9123 ("r-rsamtools" ,r-rsamtools)
9124 ("r-s4vectors" ,r-s4vectors)))
9125 (home-page "https://github.com/PeeperLab/CopywriteR")
9126 (synopsis "Copy number information from targeted sequencing")
9128 "CopywriteR extracts DNA copy number information from targeted sequencing
9129 by utilizing off-target reads. It allows for extracting uniformly distributed
9130 copy number information, can be used without reference, and can be applied to
9131 sequencing data obtained from various techniques including chromatin
9132 immunoprecipitation and target enrichment on small gene panels. Thereby,
9133 CopywriteR constitutes a widely applicable alternative to available copy
9134 number detection tools.")
9135 (license license:gpl2)))
9137 (define-public r-methylkit
9139 (name "r-methylkit")
9143 (uri (bioconductor-uri "methylKit" version))
9146 "1zcfwy7i10aqgnf7r0c41hakb5aai3s3n9y8pc6a98vimz51ly2z"))))
9147 (properties `((upstream-name . "methylKit")))
9148 (build-system r-build-system)
9150 `(("r-data-table" ,r-data-table)
9151 ("r-emdbook" ,r-emdbook)
9152 ("r-fastseg" ,r-fastseg)
9153 ("r-genomeinfodb" ,r-genomeinfodb)
9154 ("r-genomicranges" ,r-genomicranges)
9155 ("r-gtools" ,r-gtools)
9156 ("r-iranges" ,r-iranges)
9157 ("r-kernsmooth" ,r-kernsmooth)
9158 ("r-limma" ,r-limma)
9159 ("r-mclust" ,r-mclust)
9160 ("r-qvalue" ,r-qvalue)
9161 ("r-r-utils" ,r-r-utils)
9163 ("r-rhtslib" ,r-rhtslib)
9164 ("r-rsamtools" ,r-rsamtools)
9165 ("r-rtracklayer" ,r-rtracklayer)
9166 ("r-s4vectors" ,r-s4vectors)
9167 ("r-zlibbioc" ,r-zlibbioc)))
9170 (home-page "https://github.com/al2na/methylKit")
9172 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9174 "MethylKit is an R package for DNA methylation analysis and annotation
9175 from high-throughput bisulfite sequencing. The package is designed to deal
9176 with sequencing data from @dfn{Reduced representation bisulfite
9177 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9178 genome bisulfite sequencing. It also has functions to analyze base-pair
9179 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9181 (license license:artistic2.0)))
9183 (define-public r-sva
9190 (uri (bioconductor-uri "sva" version))
9193 "0czja4c5jxa0g3fspi90nyajqmvzb29my4ykv2wi66h43f5dlwhq"))))
9194 (build-system r-build-system)
9196 `(("r-genefilter" ,r-genefilter)
9198 ("r-biocparallel" ,r-biocparallel)
9199 ("r-matrixstats" ,r-matrixstats)
9200 ("r-limma" ,r-limma)))
9201 (home-page "https://bioconductor.org/packages/sva")
9202 (synopsis "Surrogate variable analysis")
9204 "This package contains functions for removing batch effects and other
9205 unwanted variation in high-throughput experiment. It also contains functions
9206 for identifying and building surrogate variables for high-dimensional data
9207 sets. Surrogate variables are covariates constructed directly from
9208 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9209 imaging data that can be used in subsequent analyses to adjust for unknown,
9210 unmodeled, or latent sources of noise.")
9211 (license license:artistic2.0)))
9213 (define-public r-seqminer
9220 (uri (cran-uri "seqminer" version))
9223 "1jydcpkw4rwfp983j83kipvsvr10as9pb49zzn3c2v09k1gh3ymy"))))
9224 (build-system r-build-system)
9227 (home-page "http://seqminer.genomic.codes")
9228 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9230 "This package provides tools to integrate nucleotide sequencing
9231 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9232 ;; Any version of the GPL is acceptable
9233 (license (list license:gpl2+ license:gpl3+))))
9235 (define-public r-raremetals2
9237 (name "r-raremetals2")
9242 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9243 "b/b7/RareMETALS2_" version ".tar.gz"))
9246 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9247 (properties `((upstream-name . "RareMETALS2")))
9248 (build-system r-build-system)
9250 `(("r-seqminer" ,r-seqminer)
9251 ("r-mvtnorm" ,r-mvtnorm)
9253 ("r-compquadform" ,r-compquadform)
9254 ("r-getopt" ,r-getopt)))
9255 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9256 (synopsis "Analyze gene-level association tests for binary trait")
9258 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9259 It was designed to meta-analyze gene-level association tests for binary trait.
9260 While rareMETALS offers a near-complete solution for meta-analysis of
9261 gene-level tests for quantitative trait, it does not offer the optimal
9262 solution for binary trait. The package rareMETALS2 offers improved features
9263 for analyzing gene-level association tests in meta-analyses for binary
9265 (license license:gpl3)))
9267 (define-public r-maldiquant
9269 (name "r-maldiquant")
9274 (uri (cran-uri "MALDIquant" version))
9277 "18nl214xjsxkcpbg79jkmw0yznwm5szyh2qb84n7ip46mm779ha6"))))
9278 (properties `((upstream-name . "MALDIquant")))
9279 (build-system r-build-system)
9280 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9281 (synopsis "Quantitative analysis of mass spectrometry data")
9283 "This package provides a complete analysis pipeline for matrix-assisted
9284 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9285 two-dimensional mass spectrometry data. In addition to commonly used plotting
9286 and processing methods it includes distinctive features, namely baseline
9287 subtraction methods such as morphological filters (TopHat) or the
9288 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9289 alignment using warping functions, handling of replicated measurements as well
9290 as allowing spectra with different resolutions.")
9291 (license license:gpl3+)))
9293 (define-public r-protgenerics
9295 (name "r-protgenerics")
9300 (uri (bioconductor-uri "ProtGenerics" version))
9303 "053mmxhzncqgigl2iqjlq56qzimlw2zzw31wpzw19rf7rld1vi3b"))))
9304 (properties `((upstream-name . "ProtGenerics")))
9305 (build-system r-build-system)
9306 (home-page "https://github.com/lgatto/ProtGenerics")
9307 (synopsis "S4 generic functions for proteomics infrastructure")
9309 "This package provides S4 generic functions needed by Bioconductor
9310 proteomics packages.")
9311 (license license:artistic2.0)))
9313 (define-public r-mzr
9320 (uri (bioconductor-uri "mzR" version))
9323 "0mlwg646k49klxrznckzfv54a9mz6irj42fqpaaa0xjm6cw2lwaa"))
9324 (modules '((guix build utils)))
9327 (delete-file-recursively "src/boost")
9329 (properties `((upstream-name . "mzR")))
9330 (build-system r-build-system)
9333 (modify-phases %standard-phases
9334 (add-after 'unpack 'use-system-boost
9336 (substitute* "src/Makevars"
9337 (("\\./boost/libs.*") "")
9338 (("ARCH_OBJS=" line)
9340 "\nARCH_LIBS=-lboost_system -lboost_regex \
9341 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9344 `(("boost" ,boost) ; use this instead of the bundled boost sources
9347 `(("r-biobase" ,r-biobase)
9348 ("r-biocgenerics" ,r-biocgenerics)
9349 ("r-ncdf4" ,r-ncdf4)
9350 ("r-protgenerics" ,r-protgenerics)
9352 ("r-rhdf5lib" ,r-rhdf5lib)
9353 ("r-zlibbioc" ,r-zlibbioc)))
9354 (home-page "https://github.com/sneumann/mzR/")
9355 (synopsis "Parser for mass spectrometry data files")
9357 "The mzR package provides a unified API to the common file formats and
9358 parsers available for mass spectrometry data. It comes with a wrapper for the
9359 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9360 The package contains the original code written by the ISB, and a subset of the
9361 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9362 previously been used in XCMS.")
9363 (license license:artistic2.0)))
9365 (define-public r-affyio
9372 (uri (bioconductor-uri "affyio" version))
9375 "1s4zp1211vf0krxzch9v3q3r6vs8hihqppq18i2fpvwlknfja7c1"))))
9376 (build-system r-build-system)
9378 `(("r-zlibbioc" ,r-zlibbioc)))
9381 (home-page "https://github.com/bmbolstad/affyio")
9382 (synopsis "Tools for parsing Affymetrix data files")
9384 "This package provides routines for parsing Affymetrix data files based
9385 upon file format information. The primary focus is on accessing the CEL and
9387 (license license:lgpl2.0+)))
9389 (define-public r-affy
9396 (uri (bioconductor-uri "affy" version))
9399 "0x8h4fk2igv7vykqfvf6v9whmx3344v5rf3gyfajd431xkjldz6k"))))
9400 (build-system r-build-system)
9402 `(("r-affyio" ,r-affyio)
9403 ("r-biobase" ,r-biobase)
9404 ("r-biocgenerics" ,r-biocgenerics)
9405 ("r-biocmanager" ,r-biocmanager)
9406 ("r-preprocesscore" ,r-preprocesscore)
9407 ("r-zlibbioc" ,r-zlibbioc)))
9410 (home-page "https://bioconductor.org/packages/affy")
9411 (synopsis "Methods for affymetrix oligonucleotide arrays")
9413 "This package contains functions for exploratory oligonucleotide array
9415 (license license:lgpl2.0+)))
9417 (define-public r-vsn
9424 (uri (bioconductor-uri "vsn" version))
9427 "1g6qkpykw99jm2wv2i61dg2ffwk0n8fm4s5pm2q4c024vw5c9b69"))))
9428 (build-system r-build-system)
9430 `(("r-affy" ,r-affy)
9431 ("r-biobase" ,r-biobase)
9432 ("r-ggplot2" ,r-ggplot2)
9433 ("r-lattice" ,r-lattice)
9434 ("r-limma" ,r-limma)))
9435 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9436 (synopsis "Variance stabilization and calibration for microarray data")
9438 "The package implements a method for normalising microarray intensities,
9439 and works for single- and multiple-color arrays. It can also be used for data
9440 from other technologies, as long as they have similar format. The method uses
9441 a robust variant of the maximum-likelihood estimator for an
9442 additive-multiplicative error model and affine calibration. The model
9443 incorporates data calibration step (a.k.a. normalization), a model for the
9444 dependence of the variance on the mean intensity and a variance stabilizing
9445 data transformation. Differences between transformed intensities are
9446 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9447 their variance is independent of the mean, and they are usually more sensitive
9448 and specific in detecting differential transcription.")
9449 (license license:artistic2.0)))
9451 (define-public r-mzid
9458 (uri (bioconductor-uri "mzID" version))
9461 "15yd4bdxprw3kg7zj2k652y3yr3si781iw28jqvnkm0gsc23rd0c"))))
9462 (properties `((upstream-name . "mzID")))
9463 (build-system r-build-system)
9465 `(("r-doparallel" ,r-doparallel)
9466 ("r-foreach" ,r-foreach)
9467 ("r-iterators" ,r-iterators)
9469 ("r-protgenerics" ,r-protgenerics)
9472 (home-page "https://bioconductor.org/packages/mzID")
9473 (synopsis "Parser for mzIdentML files")
9475 "This package provides a parser for mzIdentML files implemented using the
9476 XML package. The parser tries to be general and able to handle all types of
9477 mzIdentML files with the drawback of having less pretty output than a vendor
9479 (license license:gpl2+)))
9481 (define-public r-pcamethods
9483 (name "r-pcamethods")
9488 (uri (bioconductor-uri "pcaMethods" version))
9491 "0ik82s9bsdj4a1mmv0a3k6yisa92mxx7maf3dvip1r8gqlm3dyng"))))
9492 (properties `((upstream-name . "pcaMethods")))
9493 (build-system r-build-system)
9495 `(("r-biobase" ,r-biobase)
9496 ("r-biocgenerics" ,r-biocgenerics)
9498 ("r-rcpp" ,r-rcpp)))
9499 (home-page "https://github.com/hredestig/pcamethods")
9500 (synopsis "Collection of PCA methods")
9502 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9503 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9504 for missing value estimation is included for comparison. BPCA, PPCA and
9505 NipalsPCA may be used to perform PCA on incomplete data as well as for
9506 accurate missing value estimation. A set of methods for printing and plotting
9507 the results is also provided. All PCA methods make use of the same data
9508 structure (pcaRes) to provide a common interface to the PCA results.")
9509 (license license:gpl3+)))
9511 (define-public r-msnbase
9518 (uri (bioconductor-uri "MSnbase" version))
9521 "1kl1d7byphnfpmbl5fzbgs68dxskhpsdyx7ka51bpfn0nv3pp492"))))
9522 (properties `((upstream-name . "MSnbase")))
9523 (build-system r-build-system)
9525 `(("r-affy" ,r-affy)
9526 ("r-biobase" ,r-biobase)
9527 ("r-biocgenerics" ,r-biocgenerics)
9528 ("r-biocparallel" ,r-biocparallel)
9529 ("r-digest" ,r-digest)
9530 ("r-ggplot2" ,r-ggplot2)
9531 ("r-impute" ,r-impute)
9532 ("r-iranges" ,r-iranges)
9533 ("r-lattice" ,r-lattice)
9534 ("r-maldiquant" ,r-maldiquant)
9538 ("r-pcamethods" ,r-pcamethods)
9540 ("r-preprocesscore" ,r-preprocesscore)
9541 ("r-protgenerics" ,r-protgenerics)
9543 ("r-s4vectors" ,r-s4vectors)
9544 ("r-scales" ,r-scales)
9547 (home-page "https://github.com/lgatto/MSnbase")
9548 (synopsis "Base functions and classes for MS-based proteomics")
9550 "This package provides basic plotting, data manipulation and processing
9551 of mass spectrometry based proteomics data.")
9552 (license license:artistic2.0)))
9554 (define-public r-msnid
9561 (uri (bioconductor-uri "MSnID" version))
9564 "077n6ljcnnl7q4w0qj8v46vm4sjk9vzzfqf7wsc6lz0wmyzqdng3"))))
9565 (properties `((upstream-name . "MSnID")))
9566 (build-system r-build-system)
9568 `(("r-biobase" ,r-biobase)
9569 ("r-data-table" ,r-data-table)
9570 ("r-doparallel" ,r-doparallel)
9571 ("r-dplyr" ,r-dplyr)
9572 ("r-foreach" ,r-foreach)
9573 ("r-iterators" ,r-iterators)
9574 ("r-msnbase" ,r-msnbase)
9577 ("r-protgenerics" ,r-protgenerics)
9578 ("r-r-cache" ,r-r-cache)
9580 ("r-reshape2" ,r-reshape2)))
9581 (home-page "https://bioconductor.org/packages/MSnID")
9582 (synopsis "Utilities for LC-MSn proteomics identifications")
9584 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9585 from mzIdentML (leveraging the mzID package) or text files. After collating
9586 the search results from multiple datasets it assesses their identification
9587 quality and optimize filtering criteria to achieve the maximum number of
9588 identifications while not exceeding a specified false discovery rate. It also
9589 contains a number of utilities to explore the MS/MS results and assess missed
9590 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9591 (license license:artistic2.0)))
9593 (define-public r-seurat
9599 (uri (cran-uri "Seurat" version))
9602 "0l8bv4i9nzz26mirnva10mq6pimibj24vk7vpvfypgn7xk4942hd"))))
9603 (properties `((upstream-name . "Seurat")))
9604 (build-system r-build-system)
9607 ("r-cluster" ,r-cluster)
9608 ("r-cowplot" ,r-cowplot)
9609 ("r-dosnow" ,r-dosnow)
9610 ("r-dplyr" ,r-dplyr)
9612 ("r-fitdistrplus" ,r-fitdistrplus)
9613 ("r-foreach" ,r-foreach)
9615 ("r-ggplot2" ,r-ggplot2)
9616 ("r-ggridges" ,r-ggridges)
9617 ("r-gplots" ,r-gplots)
9618 ("r-hdf5r" ,r-hdf5r)
9619 ("r-hmisc" ,r-hmisc)
9622 ("r-igraph" ,r-igraph)
9623 ("r-irlba" ,r-irlba)
9625 ("r-lmtest" ,r-lmtest)
9627 ("r-matrix" ,r-matrix)
9628 ("r-metap" ,r-metap)
9629 ("r-mixtools" ,r-mixtools)
9630 ("r-pbapply" ,r-pbapply)
9631 ("r-plotly" ,r-plotly)
9634 ("r-rcolorbrewer" ,r-rcolorbrewer)
9636 ("r-rcppeigen" ,r-rcppeigen)
9637 ("r-rcppprogress" ,r-rcppprogress)
9638 ("r-reshape2" ,r-reshape2)
9639 ("r-reticulate" ,r-reticulate)
9641 ("r-rtsne" ,r-rtsne)
9642 ("r-sdmtools" ,r-sdmtools)
9643 ("r-tidyr" ,r-tidyr)
9644 ("r-tsne" ,r-tsne)))
9645 (home-page "http://www.satijalab.org/seurat")
9646 (synopsis "Seurat is an R toolkit for single cell genomics")
9648 "This package is an R package designed for QC, analysis, and
9649 exploration of single cell RNA-seq data. It easily enables widely-used
9650 analytical techniques, including the identification of highly variable genes,
9651 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9652 algorithms; density clustering, hierarchical clustering, k-means, and the
9653 discovery of differentially expressed genes and markers.")
9654 (license license:gpl3)))
9656 (define-public r-aroma-light
9658 (name "r-aroma-light")
9663 (uri (bioconductor-uri "aroma.light" version))
9666 "0vfifgpqxjjncbiv6gvlk9jmj14j90r9f30bqk3ks9v1csjnjhrb"))))
9667 (properties `((upstream-name . "aroma.light")))
9668 (build-system r-build-system)
9670 `(("r-matrixstats" ,r-matrixstats)
9671 ("r-r-methodss3" ,r-r-methodss3)
9673 ("r-r-utils" ,r-r-utils)))
9674 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9675 (synopsis "Methods for normalization and visualization of microarray data")
9677 "This package provides methods for microarray analysis that take basic
9678 data types such as matrices and lists of vectors. These methods can be used
9679 standalone, be utilized in other packages, or be wrapped up in higher-level
9681 (license license:gpl2+)))
9683 (define-public r-deseq
9690 (uri (bioconductor-uri "DESeq" version))
9693 "0bpiixczbhlyaiinpbl6xrpmv72k2bq76bxnw06gl35m4pgs94p2"))))
9694 (properties `((upstream-name . "DESeq")))
9695 (build-system r-build-system)
9697 `(("r-biobase" ,r-biobase)
9698 ("r-biocgenerics" ,r-biocgenerics)
9699 ("r-genefilter" ,r-genefilter)
9700 ("r-geneplotter" ,r-geneplotter)
9701 ("r-lattice" ,r-lattice)
9702 ("r-locfit" ,r-locfit)
9704 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9705 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9706 (synopsis "Differential gene expression analysis")
9708 "This package provides tools for estimating variance-mean dependence in
9709 count data from high-throughput genetic sequencing assays and for testing for
9710 differential expression based on a model using the negative binomial
9712 (license license:gpl3+)))
9714 (define-public r-edaseq
9721 (uri (bioconductor-uri "EDASeq" version))
9724 "0559ph606ps2g9bwbl0a2knkcs5w581n9igngpjxvk5p56k24gb5"))))
9725 (properties `((upstream-name . "EDASeq")))
9726 (build-system r-build-system)
9728 `(("r-annotationdbi" ,r-annotationdbi)
9729 ("r-aroma-light" ,r-aroma-light)
9730 ("r-biobase" ,r-biobase)
9731 ("r-biocgenerics" ,r-biocgenerics)
9732 ("r-biocmanager" ,r-biocmanager)
9733 ("r-biomart" ,r-biomart)
9734 ("r-biostrings" ,r-biostrings)
9735 ("r-deseq" ,r-deseq)
9736 ("r-genomicfeatures" ,r-genomicfeatures)
9737 ("r-genomicranges" ,r-genomicranges)
9738 ("r-iranges" ,r-iranges)
9739 ("r-rsamtools" ,r-rsamtools)
9740 ("r-shortread" ,r-shortread)))
9741 (home-page "https://github.com/drisso/EDASeq")
9742 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9744 "This package provides support for numerical and graphical summaries of
9745 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9746 adjust for GC-content effect (or other gene-level effects) on read counts:
9747 loess robust local regression, global-scaling, and full-quantile
9748 normalization. Between-lane normalization procedures to adjust for
9749 distributional differences between lanes (e.g., sequencing depth):
9750 global-scaling and full-quantile normalization.")
9751 (license license:artistic2.0)))
9753 (define-public r-interactivedisplaybase
9755 (name "r-interactivedisplaybase")
9760 (uri (bioconductor-uri "interactiveDisplayBase" version))
9763 "04xz3dkwan2s5ic1mwkdfnggm0l41mgqfagx160bcsrpkw6z7ark"))))
9765 `((upstream-name . "interactiveDisplayBase")))
9766 (build-system r-build-system)
9768 `(("r-biocgenerics" ,r-biocgenerics)
9769 ("r-shiny" ,r-shiny)))
9770 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9771 (synopsis "Base package for web displays of Bioconductor objects")
9773 "This package contains the basic methods needed to generate interactive
9774 Shiny-based display methods for Bioconductor objects.")
9775 (license license:artistic2.0)))
9777 (define-public r-annotationhub
9779 (name "r-annotationhub")
9784 (uri (bioconductor-uri "AnnotationHub" version))
9787 "17fgrvcnbii9siv5rq5j09bxhqffx47f6jf10418qvr7hh61ic1g"))))
9788 (properties `((upstream-name . "AnnotationHub")))
9789 (build-system r-build-system)
9791 `(("r-annotationdbi" ,r-annotationdbi)
9792 ("r-biocgenerics" ,r-biocgenerics)
9793 ("r-biocmanager" ,r-biocmanager)
9796 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9797 ("r-rsqlite" ,r-rsqlite)
9798 ("r-s4vectors" ,r-s4vectors)
9799 ("r-yaml" ,r-yaml)))
9800 (home-page "https://bioconductor.org/packages/AnnotationHub")
9801 (synopsis "Client to access AnnotationHub resources")
9803 "This package provides a client for the Bioconductor AnnotationHub web
9804 resource. The AnnotationHub web resource provides a central location where
9805 genomic files (e.g. VCF, bed, wig) and other resources from standard
9806 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9807 metadata about each resource, e.g., a textual description, tags, and date of
9808 modification. The client creates and manages a local cache of files retrieved
9809 by the user, helping with quick and reproducible access.")
9810 (license license:artistic2.0)))
9812 (define-public r-fastseg
9819 (uri (bioconductor-uri "fastseg" version))
9822 "1l8mdjpfpgwqdss2ywjkb8b4h55wf8v6kmyxdlvy04ds2hj16sb1"))))
9823 (build-system r-build-system)
9825 `(("r-biobase" ,r-biobase)
9826 ("r-biocgenerics" ,r-biocgenerics)
9827 ("r-genomicranges" ,r-genomicranges)
9828 ("r-iranges" ,r-iranges)
9829 ("r-s4vectors" ,r-s4vectors)))
9830 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
9831 (synopsis "Fast segmentation algorithm for genetic sequencing data")
9833 "Fastseg implements a very fast and efficient segmentation algorithm.
9834 It can segment data from DNA microarrays and data from next generation
9835 sequencing for example to detect copy number segments. Further it can segment
9836 data from RNA microarrays like tiling arrays to identify transcripts. Most
9837 generally, it can segment data given as a matrix or as a vector. Various data
9838 formats can be used as input to fastseg like expression set objects for
9839 microarrays or GRanges for sequencing data.")
9840 (license license:lgpl2.0+)))
9842 (define-public r-keggrest
9849 (uri (bioconductor-uri "KEGGREST" version))
9852 "0blpd5a7whd2sswfhqd17h58hg06ymaf80gapdr9ja43hnnlj309"))))
9853 (properties `((upstream-name . "KEGGREST")))
9854 (build-system r-build-system)
9856 `(("r-biostrings" ,r-biostrings)
9859 (home-page "https://bioconductor.org/packages/KEGGREST")
9860 (synopsis "Client-side REST access to KEGG")
9862 "This package provides a package that provides a client interface to the
9863 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
9864 (license license:artistic2.0)))
9866 (define-public r-gage
9873 (uri (bioconductor-uri "gage" version))
9876 "02g796sb1800ff0f1mq9f2m5wwzpf8pnfzajs49i68dhq2hm01a8"))))
9877 (build-system r-build-system)
9879 `(("r-annotationdbi" ,r-annotationdbi)
9880 ("r-graph" ,r-graph)
9881 ("r-keggrest" ,r-keggrest)))
9882 (home-page "http://www.biomedcentral.com/1471-2105/10/161")
9883 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
9885 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
9886 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
9887 data attributes including sample sizes, experimental designs, assay platforms,
9888 and other types of heterogeneity. The gage package provides functions for
9889 basic GAGE analysis, result processing and presentation. In addition, it
9890 provides demo microarray data and commonly used gene set data based on KEGG
9891 pathways and GO terms. These funtions and data are also useful for gene set
9892 analysis using other methods.")
9893 (license license:gpl2+)))
9895 (define-public r-genomicfiles
9897 (name "r-genomicfiles")
9902 (uri (bioconductor-uri "GenomicFiles" version))
9905 "0qf2yj4lfnnk64fk125n8sqms01shfqiik04nasx2z3k129ykpxp"))))
9906 (properties `((upstream-name . "GenomicFiles")))
9907 (build-system r-build-system)
9909 `(("r-biocgenerics" ,r-biocgenerics)
9910 ("r-biocparallel" ,r-biocparallel)
9911 ("r-genomeinfodb" ,r-genomeinfodb)
9912 ("r-genomicalignments" ,r-genomicalignments)
9913 ("r-genomicranges" ,r-genomicranges)
9914 ("r-iranges" ,r-iranges)
9915 ("r-rsamtools" ,r-rsamtools)
9916 ("r-rtracklayer" ,r-rtracklayer)
9917 ("r-s4vectors" ,r-s4vectors)
9918 ("r-summarizedexperiment" ,r-summarizedexperiment)
9919 ("r-variantannotation" ,r-variantannotation)))
9920 (home-page "https://bioconductor.org/packages/GenomicFiles")
9921 (synopsis "Distributed computing by file or by range")
9923 "This package provides infrastructure for parallel computations
9924 distributed by file or by range. User defined mapper and reducer functions
9925 provide added flexibility for data combination and manipulation.")
9926 (license license:artistic2.0)))
9928 (define-public r-complexheatmap
9930 (name "r-complexheatmap")
9935 (uri (bioconductor-uri "ComplexHeatmap" version))
9938 "0s01dzcfj1lmpqfpsbqw7r4858krfzy499lz4cwx4fq3mbyvy2aj"))))
9940 `((upstream-name . "ComplexHeatmap")))
9941 (build-system r-build-system)
9943 `(("r-circlize" ,r-circlize)
9944 ("r-colorspace" ,r-colorspace)
9945 ("r-getoptlong" ,r-getoptlong)
9946 ("r-globaloptions" ,r-globaloptions)
9947 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9949 "https://github.com/jokergoo/ComplexHeatmap")
9950 (synopsis "Making Complex Heatmaps")
9952 "Complex heatmaps are efficient to visualize associations between
9953 different sources of data sets and reveal potential structures. This package
9954 provides a highly flexible way to arrange multiple heatmaps and supports
9955 self-defined annotation graphics.")
9956 (license license:gpl2+)))
9958 (define-public r-dirichletmultinomial
9960 (name "r-dirichletmultinomial")
9965 (uri (bioconductor-uri "DirichletMultinomial" version))
9968 "0vazfjzqy78p5g7dnv30lbqbj4bhq4zafd2wh6gdwy2il1fd78xa"))))
9970 `((upstream-name . "DirichletMultinomial")))
9971 (build-system r-build-system)
9975 `(("r-biocgenerics" ,r-biocgenerics)
9976 ("r-iranges" ,r-iranges)
9977 ("r-s4vectors" ,r-s4vectors)))
9978 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
9979 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
9981 "Dirichlet-multinomial mixture models can be used to describe variability
9982 in microbial metagenomic data. This package is an interface to code
9983 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
9985 (license license:lgpl3)))
9987 (define-public r-ensembldb
9989 (name "r-ensembldb")
9994 (uri (bioconductor-uri "ensembldb" version))
9997 "0kzdsfk6mdwlp57sw4j2cf7lx5nc67v5j0xr3iag9kzmgikaq1lb"))))
9998 (build-system r-build-system)
10000 `(("r-annotationdbi" ,r-annotationdbi)
10001 ("r-annotationfilter" ,r-annotationfilter)
10002 ("r-biobase" ,r-biobase)
10003 ("r-biocgenerics" ,r-biocgenerics)
10004 ("r-biostrings" ,r-biostrings)
10007 ("r-genomeinfodb" ,r-genomeinfodb)
10008 ("r-genomicfeatures" ,r-genomicfeatures)
10009 ("r-genomicranges" ,r-genomicranges)
10010 ("r-iranges" ,r-iranges)
10011 ("r-protgenerics" ,r-protgenerics)
10012 ("r-rsamtools" ,r-rsamtools)
10013 ("r-rsqlite" ,r-rsqlite)
10014 ("r-rtracklayer" ,r-rtracklayer)
10015 ("r-s4vectors" ,r-s4vectors)))
10016 (home-page "https://github.com/jotsetung/ensembldb")
10017 (synopsis "Utilities to create and use Ensembl-based annotation databases")
10019 "The package provides functions to create and use transcript-centric
10020 annotation databases/packages. The annotation for the databases are directly
10021 fetched from Ensembl using their Perl API. The functionality and data is
10022 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
10023 but, in addition to retrieve all gene/transcript models and annotations from
10024 the database, the @code{ensembldb} package also provides a filter framework
10025 allowing to retrieve annotations for specific entries like genes encoded on a
10026 chromosome region or transcript models of lincRNA genes.")
10027 ;; No version specified
10028 (license license:lgpl3+)))
10030 (define-public r-organismdbi
10032 (name "r-organismdbi")
10037 (uri (bioconductor-uri "OrganismDbi" version))
10040 "11pyv56cy4iy095h40k6k0mpjdlh6gsb4ld3s57nfa9nd4ypx3yi"))))
10041 (properties `((upstream-name . "OrganismDbi")))
10042 (build-system r-build-system)
10044 `(("r-annotationdbi" ,r-annotationdbi)
10045 ("r-biobase" ,r-biobase)
10046 ("r-biocgenerics" ,r-biocgenerics)
10047 ("r-biocmanager" ,r-biocmanager)
10049 ("r-genomicfeatures" ,r-genomicfeatures)
10050 ("r-genomicranges" ,r-genomicranges)
10051 ("r-graph" ,r-graph)
10052 ("r-iranges" ,r-iranges)
10054 ("r-s4vectors" ,r-s4vectors)))
10055 (home-page "https://bioconductor.org/packages/OrganismDbi")
10056 (synopsis "Software to enable the smooth interfacing of database packages")
10057 (description "The package enables a simple unified interface to several
10058 annotation packages each of which has its own schema by taking advantage of
10059 the fact that each of these packages implements a select methods.")
10060 (license license:artistic2.0)))
10062 (define-public r-biovizbase
10064 (name "r-biovizbase")
10069 (uri (bioconductor-uri "biovizBase" version))
10072 "0v5gvcx180qn5487i1dph9abadw3ggqwp5yzy41jswzbdc8q6sbm"))))
10073 (properties `((upstream-name . "biovizBase")))
10074 (build-system r-build-system)
10076 `(("r-annotationdbi" ,r-annotationdbi)
10077 ("r-annotationfilter" ,r-annotationfilter)
10078 ("r-biocgenerics" ,r-biocgenerics)
10079 ("r-biostrings" ,r-biostrings)
10080 ("r-dichromat" ,r-dichromat)
10081 ("r-ensembldb" ,r-ensembldb)
10082 ("r-genomeinfodb" ,r-genomeinfodb)
10083 ("r-genomicalignments" ,r-genomicalignments)
10084 ("r-genomicfeatures" ,r-genomicfeatures)
10085 ("r-genomicranges" ,r-genomicranges)
10086 ("r-hmisc" ,r-hmisc)
10087 ("r-iranges" ,r-iranges)
10088 ("r-rcolorbrewer" ,r-rcolorbrewer)
10089 ("r-rlang" ,r-rlang)
10090 ("r-rsamtools" ,r-rsamtools)
10091 ("r-s4vectors" ,r-s4vectors)
10092 ("r-scales" ,r-scales)
10093 ("r-summarizedexperiment" ,r-summarizedexperiment)
10094 ("r-variantannotation" ,r-variantannotation)))
10095 (home-page "https://bioconductor.org/packages/biovizBase")
10096 (synopsis "Basic graphic utilities for visualization of genomic data")
10098 "The biovizBase package is designed to provide a set of utilities, color
10099 schemes and conventions for genomic data. It serves as the base for various
10100 high-level packages for biological data visualization. This saves development
10101 effort and encourages consistency.")
10102 (license license:artistic2.0)))
10104 (define-public r-ggbio
10111 (uri (bioconductor-uri "ggbio" version))
10114 "0wq49qqzkcn8s19xgaxf2s1j1a563d7pbhhvris6fhxfdjsz4934"))))
10115 (build-system r-build-system)
10117 `(("r-annotationdbi" ,r-annotationdbi)
10118 ("r-annotationfilter" ,r-annotationfilter)
10119 ("r-biobase" ,r-biobase)
10120 ("r-biocgenerics" ,r-biocgenerics)
10121 ("r-biostrings" ,r-biostrings)
10122 ("r-biovizbase" ,r-biovizbase)
10123 ("r-bsgenome" ,r-bsgenome)
10124 ("r-ensembldb" ,r-ensembldb)
10125 ("r-genomeinfodb" ,r-genomeinfodb)
10126 ("r-genomicalignments" ,r-genomicalignments)
10127 ("r-genomicfeatures" ,r-genomicfeatures)
10128 ("r-genomicranges" ,r-genomicranges)
10129 ("r-ggally" ,r-ggally)
10130 ("r-ggplot2" ,r-ggplot2)
10131 ("r-gridextra" ,r-gridextra)
10132 ("r-gtable" ,r-gtable)
10133 ("r-hmisc" ,r-hmisc)
10134 ("r-iranges" ,r-iranges)
10135 ("r-organismdbi" ,r-organismdbi)
10136 ("r-reshape2" ,r-reshape2)
10137 ("r-rlang" ,r-rlang)
10138 ("r-rsamtools" ,r-rsamtools)
10139 ("r-rtracklayer" ,r-rtracklayer)
10140 ("r-s4vectors" ,r-s4vectors)
10141 ("r-scales" ,r-scales)
10142 ("r-summarizedexperiment" ,r-summarizedexperiment)
10143 ("r-variantannotation" ,r-variantannotation)))
10144 (home-page "http://www.tengfei.name/ggbio/")
10145 (synopsis "Visualization tools for genomic data")
10147 "The ggbio package extends and specializes the grammar of graphics for
10148 biological data. The graphics are designed to answer common scientific
10149 questions, in particular those often asked of high throughput genomics data.
10150 All core Bioconductor data structures are supported, where appropriate. The
10151 package supports detailed views of particular genomic regions, as well as
10152 genome-wide overviews. Supported overviews include ideograms and grand linear
10153 views. High-level plots include sequence fragment length, edge-linked
10154 interval to data view, mismatch pileup, and several splicing summaries.")
10155 (license license:artistic2.0)))
10157 (define-public r-gprofiler
10159 (name "r-gprofiler")
10164 (uri (cran-uri "gProfileR" version))
10167 "12nwidbnqmnfy5dnqga26byslvdnkrpz2fi19qfcby6xx0wbndk7"))))
10168 (properties `((upstream-name . "gProfileR")))
10169 (build-system r-build-system)
10171 `(("r-plyr" ,r-plyr)
10172 ("r-rcurl" ,r-rcurl)))
10173 (home-page "https://cran.r-project.org/web/packages/gProfileR/")
10174 (synopsis "Interface to the g:Profiler toolkit")
10176 "This package provides tools for functional enrichment analysis,
10177 gene identifier conversion and mapping homologous genes across related
10178 organisms via the @code{g:Profiler} toolkit.")
10179 (license license:gpl2+)))
10181 (define-public r-gqtlbase
10183 (name "r-gqtlbase")
10188 (uri (bioconductor-uri "gQTLBase" version))
10191 "1lbk1m1mkvbk30flk5pf3pcrnm2s0sj5r48kbjgad39dsvd8zgqx"))))
10192 (properties `((upstream-name . "gQTLBase")))
10193 (build-system r-build-system)
10195 `(("r-batchjobs" ,r-batchjobs)
10196 ("r-bbmisc" ,r-bbmisc)
10197 ("r-biocgenerics" ,r-biocgenerics)
10199 ("r-doparallel" ,r-doparallel)
10201 ("r-ffbase" ,r-ffbase)
10202 ("r-foreach" ,r-foreach)
10203 ("r-genomicfiles" ,r-genomicfiles)
10204 ("r-genomicranges" ,r-genomicranges)
10205 ("r-rtracklayer" ,r-rtracklayer)
10206 ("r-s4vectors" ,r-s4vectors)
10207 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10208 (home-page "https://bioconductor.org/packages/gQTLBase")
10209 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10211 "The purpose of this package is to simplify the storage and interrogation
10212 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10214 (license license:artistic2.0)))
10216 (define-public r-snpstats
10218 (name "r-snpstats")
10223 (uri (bioconductor-uri "snpStats" version))
10226 "1pplx4pf9bqi7v5v1l74yknc1s61carvbqkf327ky7vbvp0bck33"))))
10227 (properties `((upstream-name . "snpStats")))
10228 (build-system r-build-system)
10229 (inputs `(("zlib" ,zlib)))
10231 `(("r-biocgenerics" ,r-biocgenerics)
10232 ("r-matrix" ,r-matrix)
10233 ("r-survival" ,r-survival)
10234 ("r-zlibbioc" ,r-zlibbioc)))
10235 (home-page "https://bioconductor.org/packages/snpStats")
10236 (synopsis "Methods for SNP association studies")
10238 "This package provides classes and statistical methods for large
10239 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10240 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10241 (license license:gpl3)))
10243 (define-public r-homo-sapiens
10245 (name "r-homo-sapiens")
10249 ;; We cannot use bioconductor-uri here because this tarball is
10250 ;; located under "data/annotation/" instead of "bioc/".
10251 (uri (string-append "http://www.bioconductor.org/packages/"
10252 "release/data/annotation/src/contrib/"
10254 version ".tar.gz"))
10257 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10259 `((upstream-name . "Homo.sapiens")))
10260 (build-system r-build-system)
10262 `(("r-genomicfeatures" ,r-genomicfeatures)
10263 ("r-go-db" ,r-go-db)
10264 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10265 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10266 ("r-organismdbi" ,r-organismdbi)
10267 ("r-annotationdbi" ,r-annotationdbi)))
10268 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10269 (synopsis "Annotation package for the Homo.sapiens object")
10271 "This package contains the Homo.sapiens object to access data from
10272 several related annotation packages.")
10273 (license license:artistic2.0)))
10275 (define-public r-erma
10282 (uri (bioconductor-uri "erma" version))
10285 "0hj9iz904rr1y66442lkxjywkw1ydyxxlhmjirawbf09ic5ad4g9"))))
10286 (build-system r-build-system)
10288 `(("r-annotationdbi" ,r-annotationdbi)
10289 ("r-biobase" ,r-biobase)
10290 ("r-biocgenerics" ,r-biocgenerics)
10291 ("r-biocparallel" ,r-biocparallel)
10292 ("r-genomeinfodb" ,r-genomeinfodb)
10293 ("r-genomicfiles" ,r-genomicfiles)
10294 ("r-genomicranges" ,r-genomicranges)
10295 ("r-ggplot2" ,r-ggplot2)
10296 ("r-homo-sapiens" ,r-homo-sapiens)
10297 ("r-iranges" ,r-iranges)
10298 ("r-rtracklayer" ,r-rtracklayer)
10299 ("r-s4vectors" ,r-s4vectors)
10300 ("r-shiny" ,r-shiny)
10301 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10302 (home-page "https://bioconductor.org/packages/erma")
10303 (synopsis "Epigenomic road map adventures")
10305 "The epigenomics road map describes locations of epigenetic marks in DNA
10306 from a variety of cell types. Of interest are locations of histone
10307 modifications, sites of DNA methylation, and regions of accessible chromatin.
10308 This package presents a selection of elements of the road map including
10309 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10310 by Ernst and Kellis.")
10311 (license license:artistic2.0)))
10313 (define-public r-ldblock
10320 (uri (bioconductor-uri "ldblock" version))
10323 "0xbf4pmhrk5fnd1iz5wzjvdr75v114bwpznhcig4wiqmxc27sips"))))
10324 (build-system r-build-system)
10326 `(("r-biocgenerics" ,r-biocgenerics)
10328 ("r-genomeinfodb" ,r-genomeinfodb)
10329 ("r-genomicfiles" ,r-genomicfiles)
10330 ("r-go-db" ,r-go-db)
10331 ("r-homo-sapiens" ,r-homo-sapiens)
10332 ("r-matrix" ,r-matrix)
10333 ("r-rsamtools" ,r-rsamtools)
10334 ("r-snpstats" ,r-snpstats)
10335 ("r-variantannotation" ,r-variantannotation)))
10336 (home-page "https://bioconductor.org/packages/ldblock")
10337 (synopsis "Data structures for linkage disequilibrium measures in populations")
10339 "This package defines data structures for @dfn{linkage
10340 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10341 handling of existing population-level data for the purpose of flexibly
10342 defining LD blocks.")
10343 (license license:artistic2.0)))
10345 (define-public r-gqtlstats
10347 (name "r-gqtlstats")
10352 (uri (bioconductor-uri "gQTLstats" version))
10355 "1sg9kw59dlayj7qxql9pd93d4hmml504sa3kkfpzfh3xri7m5pxf"))))
10356 (properties `((upstream-name . "gQTLstats")))
10357 (build-system r-build-system)
10359 `(("r-annotationdbi" ,r-annotationdbi)
10360 ("r-batchjobs" ,r-batchjobs)
10361 ("r-bbmisc" ,r-bbmisc)
10362 ("r-beeswarm" ,r-beeswarm)
10363 ("r-biobase" ,r-biobase)
10364 ("r-biocgenerics" ,r-biocgenerics)
10365 ("r-doparallel" ,r-doparallel)
10366 ("r-dplyr" ,r-dplyr)
10368 ("r-ffbase" ,r-ffbase)
10369 ("r-foreach" ,r-foreach)
10370 ("r-genomeinfodb" ,r-genomeinfodb)
10371 ("r-genomicfeatures" ,r-genomicfeatures)
10372 ("r-genomicfiles" ,r-genomicfiles)
10373 ("r-genomicranges" ,r-genomicranges)
10374 ("r-ggbeeswarm" ,r-ggbeeswarm)
10375 ("r-ggplot2" ,r-ggplot2)
10376 ("r-gqtlbase" ,r-gqtlbase)
10377 ("r-hardyweinberg" ,r-hardyweinberg)
10378 ("r-homo-sapiens" ,r-homo-sapiens)
10379 ("r-iranges" ,r-iranges)
10380 ("r-limma" ,r-limma)
10382 ("r-plotly" ,r-plotly)
10383 ("r-reshape2" ,r-reshape2)
10384 ("r-s4vectors" ,r-s4vectors)
10385 ("r-shiny" ,r-shiny)
10386 ("r-snpstats" ,r-snpstats)
10387 ("r-summarizedexperiment" ,r-summarizedexperiment)
10388 ("r-variantannotation" ,r-variantannotation)))
10389 (home-page "https://bioconductor.org/packages/gQTLstats")
10390 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10392 "This package provides tools for the computationally efficient analysis
10393 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10394 The software in this package aims to support refinements and functional
10395 interpretation of members of a collection of association statistics on a
10396 family of feature/genome hypotheses.")
10397 (license license:artistic2.0)))
10399 (define-public r-gviz
10406 (uri (bioconductor-uri "Gviz" version))
10409 "0jvcivgw0ahv2rjadxmrww76xambhf7silczmh38nn4yn4qw6w9y"))))
10410 (properties `((upstream-name . "Gviz")))
10411 (build-system r-build-system)
10413 `(("r-annotationdbi" ,r-annotationdbi)
10414 ("r-biobase" ,r-biobase)
10415 ("r-biocgenerics" ,r-biocgenerics)
10416 ("r-biomart" ,r-biomart)
10417 ("r-biostrings" ,r-biostrings)
10418 ("r-biovizbase" ,r-biovizbase)
10419 ("r-bsgenome" ,r-bsgenome)
10420 ("r-digest" ,r-digest)
10421 ("r-genomeinfodb" ,r-genomeinfodb)
10422 ("r-genomicalignments" ,r-genomicalignments)
10423 ("r-genomicfeatures" ,r-genomicfeatures)
10424 ("r-genomicranges" ,r-genomicranges)
10425 ("r-iranges" ,r-iranges)
10426 ("r-lattice" ,r-lattice)
10427 ("r-latticeextra" ,r-latticeextra)
10428 ("r-matrixstats" ,r-matrixstats)
10429 ("r-rcolorbrewer" ,r-rcolorbrewer)
10430 ("r-rsamtools" ,r-rsamtools)
10431 ("r-rtracklayer" ,r-rtracklayer)
10432 ("r-s4vectors" ,r-s4vectors)
10433 ("r-xvector" ,r-xvector)))
10434 (home-page "https://bioconductor.org/packages/Gviz")
10435 (synopsis "Plotting data and annotation information along genomic coordinates")
10437 "Genomic data analyses requires integrated visualization of known genomic
10438 information and new experimental data. Gviz uses the biomaRt and the
10439 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10440 and translates this to e.g. gene/transcript structures in viewports of the
10441 grid graphics package. This results in genomic information plotted together
10443 (license license:artistic2.0)))
10445 (define-public r-gwascat
10452 (uri (bioconductor-uri "gwascat" version))
10455 "1fnyjydhicq4ayrv0lqjv48h9bd72h40s6l82g1h2ng0icwz38g0"))))
10456 (build-system r-build-system)
10458 `(("r-annotationdbi" ,r-annotationdbi)
10459 ("r-annotationhub" ,r-annotationhub)
10460 ("r-biocgenerics" ,r-biocgenerics)
10461 ("r-biostrings" ,r-biostrings)
10462 ("r-genomeinfodb" ,r-genomeinfodb)
10463 ("r-genomicfeatures" ,r-genomicfeatures)
10464 ("r-genomicranges" ,r-genomicranges)
10465 ("r-ggbio" ,r-ggbio)
10466 ("r-ggplot2" ,r-ggplot2)
10467 ("r-gqtlstats" ,r-gqtlstats)
10468 ("r-graph" ,r-graph)
10470 ("r-homo-sapiens" ,r-homo-sapiens)
10471 ("r-iranges" ,r-iranges)
10472 ("r-rsamtools" ,r-rsamtools)
10473 ("r-rtracklayer" ,r-rtracklayer)
10474 ("r-s4vectors" ,r-s4vectors)
10475 ("r-snpstats" ,r-snpstats)
10476 ("r-summarizedexperiment" ,r-summarizedexperiment)
10477 ("r-variantannotation" ,r-variantannotation)))
10478 (home-page "https://bioconductor.org/packages/gwascat")
10479 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10481 "This package provides tools for representing and modeling data in the
10482 EMBL-EBI GWAS catalog.")
10483 (license license:artistic2.0)))
10485 (define-public r-sushi
10491 (uri (bioconductor-uri "Sushi" version))
10494 "0dv5di0hgbvk9cxnqhyf18mdjl50k6bk00a89r6zgp83rbxwr1r8"))))
10495 (properties `((upstream-name . "Sushi")))
10496 (build-system r-build-system)
10498 `(("r-biomart" ,r-biomart)
10500 (home-page "https://bioconductor.org/packages/Sushi")
10501 (synopsis "Tools for visualizing genomics data")
10503 "This package provides flexible, quantitative, and integrative genomic
10504 visualizations for publication-quality multi-panel figures.")
10505 (license license:gpl2+)))
10507 (define-public r-fithic
10513 (uri (bioconductor-uri "FitHiC" version))
10516 "15xd8mz7660q4zr9p74mq1pqps4iz7pxp8f9ifn21gwg94aq1avn"))))
10517 (properties `((upstream-name . "FitHiC")))
10518 (build-system r-build-system)
10520 `(("r-data-table" ,r-data-table)
10521 ("r-fdrtool" ,r-fdrtool)
10522 ("r-rcpp" ,r-rcpp)))
10523 (home-page "https://bioconductor.org/packages/FitHiC")
10524 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10526 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10527 intra-chromosomal contact maps produced by genome-wide genome architecture
10528 assays such as Hi-C.")
10529 (license license:gpl2+)))
10531 (define-public r-hitc
10537 (uri (bioconductor-uri "HiTC" version))
10540 "11f96k1707g6milpjgnrjf3b5r42hsrxhb5d8znkcr3y3mrskdbj"))))
10541 (properties `((upstream-name . "HiTC")))
10542 (build-system r-build-system)
10544 `(("r-biostrings" ,r-biostrings)
10545 ("r-genomeinfodb" ,r-genomeinfodb)
10546 ("r-genomicranges" ,r-genomicranges)
10547 ("r-iranges" ,r-iranges)
10548 ("r-matrix" ,r-matrix)
10549 ("r-rcolorbrewer" ,r-rcolorbrewer)
10550 ("r-rtracklayer" ,r-rtracklayer)))
10551 (home-page "https://bioconductor.org/packages/HiTC")
10552 (synopsis "High throughput chromosome conformation capture analysis")
10554 "The HiTC package was developed to explore high-throughput \"C\" data
10555 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10556 quality controls, normalization, visualization, and further analysis are also
10558 (license license:artistic2.0)))
10560 (define-public r-qvalue
10567 (uri (bioconductor-uri "qvalue" version))
10570 "0kxavzm1j2mk26qicmjm90nxx4w5h3dxighzks7wzihay3k8cysc"))))
10571 (build-system r-build-system)
10573 `(("r-ggplot2" ,r-ggplot2)
10574 ("r-reshape2" ,r-reshape2)))
10575 (home-page "http://github.com/jdstorey/qvalue")
10576 (synopsis "Q-value estimation for false discovery rate control")
10578 "This package takes a list of p-values resulting from the simultaneous
10579 testing of many hypotheses and estimates their q-values and local @dfn{false
10580 discovery rate} (FDR) values. The q-value of a test measures the proportion
10581 of false positives incurred when that particular test is called significant.
10582 The local FDR measures the posterior probability the null hypothesis is true
10583 given the test's p-value. Various plots are automatically generated, allowing
10584 one to make sensible significance cut-offs. The software can be applied to
10585 problems in genomics, brain imaging, astrophysics, and data mining.")
10586 ;; Any version of the LGPL.
10587 (license license:lgpl3+)))
10589 (define-public r-hdf5array
10591 (name "r-hdf5array")
10596 (uri (bioconductor-uri "HDF5Array" version))
10599 "1qwdsygcadl58qj598hfyvs8hp0hqcl9ghnhknahrlhmb7k2bd2d"))))
10600 (properties `((upstream-name . "HDF5Array")))
10601 (build-system r-build-system)
10603 `(("r-biocgenerics" ,r-biocgenerics)
10604 ("r-delayedarray" ,r-delayedarray)
10605 ("r-iranges" ,r-iranges)
10606 ("r-rhdf5" ,r-rhdf5)
10607 ("r-s4vectors" ,r-s4vectors)))
10608 (home-page "https://bioconductor.org/packages/HDF5Array")
10609 (synopsis "HDF5 back end for DelayedArray objects")
10610 (description "This package provides an array-like container for convenient
10611 access and manipulation of HDF5 datasets. It supports delayed operations and
10612 block processing.")
10613 (license license:artistic2.0)))
10615 (define-public r-rhdf5lib
10617 (name "r-rhdf5lib")
10622 (uri (bioconductor-uri "Rhdf5lib" version))
10625 "06bxd3wz8lrvh2hzvmjpdv4lvzj5lz9353bw5b3zb98cb8w9r2j5"))
10626 (modules '((guix build utils)))
10629 ;; Delete bundled binaries
10630 (delete-file-recursively "src/winlib/")
10632 (properties `((upstream-name . "Rhdf5lib")))
10633 (build-system r-build-system)
10636 (modify-phases %standard-phases
10637 (add-after 'unpack 'do-not-use-bundled-hdf5
10638 (lambda* (#:key inputs #:allow-other-keys)
10639 (for-each delete-file '("configure" "configure.ac"))
10640 ;; Do not make other packages link with the proprietary libsz.
10641 (substitute* "R/zzz.R"
10642 (("'%s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a -lz'")
10643 "'%s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a -lz'")
10644 (("'%s/libhdf5.a %s/libsz.a -lz'")
10645 "'%s/libhdf5.a %s/libhdf5.a -lz'"))
10646 (with-directory-excursion "src"
10647 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10648 (rename-file (string-append "hdf5-" ,(package-version hdf5-1.10))
10650 ;; Remove timestamp and host system information to make
10651 ;; the build reproducible.
10652 (substitute* "hdf5/src/libhdf5.settings.in"
10653 (("Configured on: @CONFIG_DATE@")
10654 "Configured on: Guix")
10655 (("Uname information:.*")
10656 "Uname information: Linux\n")
10657 ;; Remove unnecessary store reference.
10659 "C Compiler: GCC\n"))
10660 (rename-file "Makevars.in" "Makevars")
10661 (substitute* "Makevars"
10662 (("HDF5_CXX_LIB=.*")
10663 (string-append "HDF5_CXX_LIB="
10664 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10666 (string-append "HDF5_LIB="
10667 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10668 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10669 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10670 ;; szip is non-free software
10671 (("cp \\$\\{SZIP_LIB\\}.*") "")
10672 (("\\$\\{USER_LIB_DIR\\}libsz.a") "")))
10677 `(("hdf5" ,hdf5-1.10)))
10679 `(("hdf5-source" ,(package-source hdf5-1.10))))
10680 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10681 (synopsis "HDF5 library as an R package")
10682 (description "This package provides C and C++ HDF5 libraries for use in R
10684 (license license:artistic2.0)))
10686 (define-public r-beachmat
10688 (name "r-beachmat")
10693 (uri (bioconductor-uri "beachmat" version))
10696 "07zgmms0qg8gw7x0js46965bbhpfj2aa1h5ixdz9r332bxv9cdmr"))))
10697 (build-system r-build-system)
10702 `(("r-biocgenerics" ,r-biocgenerics)
10703 ("r-delayedarray" ,r-delayedarray)
10704 ("r-hdf5array" ,r-hdf5array)
10706 ("r-rhdf5" ,r-rhdf5)
10707 ("r-rhdf5lib" ,r-rhdf5lib)))
10708 (home-page "https://bioconductor.org/packages/beachmat")
10709 (synopsis "Compiling Bioconductor to handle each matrix type")
10710 (description "This package provides a consistent C++ class interface for a
10711 variety of commonly used matrix types, including sparse and HDF5-backed
10713 (license license:gpl3)))
10715 (define-public r-singlecellexperiment
10717 (name "r-singlecellexperiment")
10722 (uri (bioconductor-uri "SingleCellExperiment" version))
10725 "12139kk9cqgzpm6f3cwdsq31gj5lxamz2q939dy9fa0fa54gdaq4"))))
10727 `((upstream-name . "SingleCellExperiment")))
10728 (build-system r-build-system)
10730 `(("r-biocgenerics" ,r-biocgenerics)
10731 ("r-s4vectors" ,r-s4vectors)
10732 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10733 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10734 (synopsis "S4 classes for single cell data")
10735 (description "This package defines an S4 class for storing data from
10736 single-cell experiments. This includes specialized methods to store and
10737 retrieve spike-in information, dimensionality reduction coordinates and size
10738 factors for each cell, along with the usual metadata for genes and
10740 (license license:gpl3)))
10742 (define-public r-scater
10748 (uri (bioconductor-uri "scater" version))
10751 "0rijhy7g5qmcn927y1wyd63la1fhyar9fv1hccsqd23jd98yc55a"))))
10752 (build-system r-build-system)
10754 `(("r-beachmat" ,r-beachmat)
10755 ("r-biocgenerics" ,r-biocgenerics)
10756 ("r-biocparallel" ,r-biocparallel)
10757 ("r-delayedarray" ,r-delayedarray)
10758 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10759 ("r-dplyr" ,r-dplyr)
10760 ("r-ggbeeswarm" ,r-ggbeeswarm)
10761 ("r-ggplot2" ,r-ggplot2)
10762 ("r-matrix" ,r-matrix)
10765 ("r-reshape2" ,r-reshape2)
10766 ("r-rhdf5lib" ,r-rhdf5lib)
10767 ("r-s4vectors" ,r-s4vectors)
10768 ("r-singlecellexperiment" ,r-singlecellexperiment)
10769 ("r-summarizedexperiment" ,r-summarizedexperiment)
10770 ("r-viridis" ,r-viridis)))
10771 (home-page "https://github.com/davismcc/scater")
10772 (synopsis "Single-cell analysis toolkit for gene expression data in R")
10773 (description "This package provides a collection of tools for doing
10774 various analyses of single-cell RNA-seq gene expression data, with a focus on
10776 (license license:gpl2+)))
10778 (define-public r-scran
10785 (uri (bioconductor-uri "scran" version))
10788 "07mgilr3gq3lnrm1fjm9zhz4w7970bjhsykln1drqy9gkzj5sn7g"))))
10789 (build-system r-build-system)
10791 `(("r-beachmat" ,r-beachmat)
10792 ("r-biocgenerics" ,r-biocgenerics)
10793 ("r-biocneighbors" ,r-biocneighbors)
10794 ("r-biocparallel" ,r-biocparallel)
10795 ("r-delayedarray" ,r-delayedarray)
10796 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10797 ("r-dynamictreecut" ,r-dynamictreecut)
10798 ("r-edger" ,r-edger)
10799 ("r-igraph" ,r-igraph)
10800 ("r-limma" ,r-limma)
10801 ("r-matrix" ,r-matrix)
10803 ("r-rhdf5lib" ,r-rhdf5lib)
10804 ("r-s4vectors" ,r-s4vectors)
10805 ("r-scater" ,r-scater)
10806 ("r-singlecellexperiment" ,r-singlecellexperiment)
10807 ("r-statmod" ,r-statmod)
10808 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10809 (home-page "https://bioconductor.org/packages/scran")
10810 (synopsis "Methods for single-cell RNA-Seq data analysis")
10811 (description "This package implements a variety of low-level analyses of
10812 single-cell RNA-seq data. Methods are provided for normalization of
10813 cell-specific biases, assignment of cell cycle phase, and detection of highly
10814 variable and significantly correlated genes.")
10815 (license license:gpl3)))
10817 (define-public r-delayedmatrixstats
10819 (name "r-delayedmatrixstats")
10824 (uri (bioconductor-uri "DelayedMatrixStats" version))
10827 "03fk2avl1vyjv2wslczkc82qr0zmp1ra8iimd47pbmnnm839ly4w"))))
10829 `((upstream-name . "DelayedMatrixStats")))
10830 (build-system r-build-system)
10832 `(("r-biocparallel" ,r-biocparallel)
10833 ("r-delayedarray" ,r-delayedarray)
10834 ("r-hdf5array" ,r-hdf5array)
10835 ("r-iranges" ,r-iranges)
10836 ("r-matrix" ,r-matrix)
10837 ("r-matrixstats" ,r-matrixstats)
10838 ("r-s4vectors" ,r-s4vectors)))
10839 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
10840 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
10842 "This package provides a port of the @code{matrixStats} API for use with
10843 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
10844 contains high-performing functions operating on rows and columns of
10845 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
10846 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
10847 are optimized per data type and for subsetted calculations such that both
10848 memory usage and processing time is minimized.")
10849 (license license:expat)))
10851 (define-public r-phangorn
10853 (name "r-phangorn")
10858 (uri (cran-uri "phangorn" version))
10861 "0xc8k552nxczy19jr0xjjagrzc8x6lafasgk2c099ls8bc1yml1i"))))
10862 (build-system r-build-system)
10865 ("r-fastmatch" ,r-fastmatch)
10866 ("r-igraph" ,r-igraph)
10867 ("r-magrittr" ,r-magrittr)
10868 ("r-matrix" ,r-matrix)
10869 ("r-quadprog" ,r-quadprog)
10870 ("r-rcpp" ,r-rcpp)))
10871 (home-page "https://github.com/KlausVigo/phangorn")
10872 (synopsis "Phylogenetic analysis in R")
10874 "Phangorn is a package for phylogenetic analysis in R. It supports
10875 estimation of phylogenetic trees and networks using Maximum Likelihood,
10876 Maximum Parsimony, distance methods and Hadamard conjugation.")
10877 (license license:gpl2+)))
10879 (define-public r-dropbead
10880 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
10883 (name "r-dropbead")
10884 (version (string-append "0-" revision "." (string-take commit 7)))
10888 (uri (git-reference
10889 (url "https://github.com/rajewsky-lab/dropbead.git")
10891 (file-name (git-file-name name version))
10894 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
10895 (build-system r-build-system)
10897 `(("r-ggplot2" ,r-ggplot2)
10898 ("r-rcolorbrewer" ,r-rcolorbrewer)
10899 ("r-gridextra" ,r-gridextra)
10900 ("r-gplots" ,r-gplots)
10901 ("r-plyr" ,r-plyr)))
10902 (home-page "https://github.com/rajewsky-lab/dropbead")
10903 (synopsis "Basic exploration and analysis of Drop-seq data")
10904 (description "This package offers a quick and straight-forward way to
10905 explore and perform basic analysis of single cell sequencing data coming from
10906 droplet sequencing. It has been particularly tailored for Drop-seq.")
10907 (license license:gpl3))))
10909 (define htslib-for-sambamba
10910 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
10913 (name "htslib-for-sambamba")
10914 (version (string-append "1.3.1-1." (string-take commit 9)))
10918 (uri (git-reference
10919 (url "https://github.com/lomereiter/htslib.git")
10921 (file-name (string-append "htslib-" version "-checkout"))
10924 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
10926 `(("autoconf" ,autoconf)
10927 ("automake" ,automake)
10928 ,@(package-native-inputs htslib))))))
10930 (define-public sambamba
10937 (uri (git-reference
10938 (url "https://github.com/lomereiter/sambamba.git")
10939 (commit (string-append "v" version))))
10940 (file-name (string-append name "-" version "-checkout"))
10943 "0k0cz3qcv98p6cq09zlbgnjsggxcqbcmzxg5zikgcgbr2nfq4lry"))))
10944 (build-system gnu-build-system)
10946 `(#:tests? #f ; there is no test target
10947 #:parallel-build? #f ; not supported
10949 (modify-phases %standard-phases
10950 (delete 'configure)
10951 (add-after 'unpack 'fix-ldc-version
10953 (substitute* "gen_ldc_version_info.py"
10954 (("/usr/bin/env.*") (which "python3")))
10955 (substitute* "Makefile"
10956 ;; We use ldc2 instead of ldmd2 to compile sambamba.
10957 (("\\$\\(shell which ldmd2\\)") (which "ldc2")))
10959 (add-after 'unpack 'place-biod-and-undead
10960 (lambda* (#:key inputs #:allow-other-keys)
10961 (copy-recursively (assoc-ref inputs "biod") "BioD")
10962 (copy-recursively (assoc-ref inputs "undead") "undeaD")
10964 (add-after 'unpack 'unbundle-prerequisites
10966 (substitute* "Makefile"
10967 (("htslib/libhts.a lz4/lib/liblz4.a")
10969 ((" lz4-static htslib-static") ""))
10972 (lambda* (#:key outputs #:allow-other-keys)
10973 (let* ((out (assoc-ref outputs "out"))
10974 (bin (string-append out "/bin")))
10976 (install-file "bin/sambamba" bin)
10983 ,(let ((commit "4f1a7d2fb7ef3dfe962aa357d672f354ebfbe42e"))
10986 (uri (git-reference
10987 (url "https://github.com/biod/BioD.git")
10989 (file-name (string-append "biod-"
10990 (string-take commit 9)
10994 "1k5pdjv1qvi0a3rwd1sfq6zbj37l86i7bf710m4c0y6737lxj426")))))
10996 ,(let ((commit "9be93876982b5f14fcca60832563b3cd767dd84d"))
10999 (uri (git-reference
11000 (url "https://github.com/biod/undeaD.git")
11002 (file-name (string-append "undead-"
11003 (string-take commit 9)
11007 "1xfarj0nqlmi5jd1vmcmm7pabzaf9hxyvk6hp0d6jslb5k9r8r3d")))))))
11010 ("htslib" ,htslib-for-sambamba)))
11011 (home-page "http://lomereiter.github.io/sambamba")
11012 (synopsis "Tools for working with SAM/BAM data")
11013 (description "Sambamba is a high performance modern robust and
11014 fast tool (and library), written in the D programming language, for
11015 working with SAM and BAM files. Current parallelised functionality is
11016 an important subset of samtools functionality, including view, index,
11017 sort, markdup, and depth.")
11018 (license license:gpl2+)))
11020 (define-public ritornello
11022 (name "ritornello")
11026 (uri (git-reference
11027 (url "https://github.com/KlugerLab/Ritornello.git")
11028 (commit (string-append "v" version))))
11029 (file-name (git-file-name name version))
11032 "1xahvq215qld7x1w8vpa5zbrsj6p9crb9shqa2x89sb0aaxa02jk"))))
11033 (build-system gnu-build-system)
11035 `(#:tests? #f ; there are no tests
11037 (modify-phases %standard-phases
11038 (add-after 'unpack 'patch-samtools-references
11039 (lambda* (#:key inputs #:allow-other-keys)
11040 (substitute* '("src/SamStream.h"
11042 (("<sam.h>") "<samtools/sam.h>"))
11044 (delete 'configure)
11046 (lambda* (#:key inputs outputs #:allow-other-keys)
11047 (let* ((out (assoc-ref outputs "out"))
11048 (bin (string-append out "/bin/")))
11050 (install-file "bin/Ritornello" bin)
11053 `(("samtools" ,samtools-0.1)
11057 (home-page "https://github.com/KlugerLab/Ritornello")
11058 (synopsis "Control-free peak caller for ChIP-seq data")
11059 (description "Ritornello is a ChIP-seq peak calling algorithm based on
11060 signal processing that can accurately call binding events without the need to
11061 do a pair total DNA input or IgG control sample. It has been tested for use
11062 with narrow binding events such as transcription factor ChIP-seq.")
11063 (license license:gpl3+)))
11065 (define-public trim-galore
11067 (name "trim-galore")
11072 (uri (git-reference
11073 (url "https://github.com/FelixKrueger/TrimGalore.git")
11075 (file-name (string-append name "-" version "-checkout"))
11078 "0x5892l48c816pf00wmnz5vq0zq6170d3xc8zrxncd4jcz7h1p71"))))
11079 (build-system gnu-build-system)
11081 `(#:tests? #f ; no tests
11083 (modify-phases %standard-phases
11084 (delete 'configure)
11086 (add-after 'unpack 'hardcode-tool-references
11087 (lambda* (#:key inputs #:allow-other-keys)
11088 (substitute* "trim_galore"
11089 (("\\$path_to_cutadapt = 'cutadapt'")
11090 (string-append "$path_to_cutadapt = '"
11091 (assoc-ref inputs "cutadapt")
11094 (string-append "| "
11095 (assoc-ref inputs "gzip")
11098 (string-append "\""
11099 (assoc-ref inputs "gzip")
11103 (lambda* (#:key outputs #:allow-other-keys)
11104 (let ((bin (string-append (assoc-ref outputs "out")
11107 (install-file "trim_galore" bin)
11112 ("cutadapt" ,cutadapt)))
11114 `(("unzip" ,unzip)))
11115 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
11116 (synopsis "Wrapper around Cutadapt and FastQC")
11117 (description "Trim Galore! is a wrapper script to automate quality and
11118 adapter trimming as well as quality control, with some added functionality to
11119 remove biased methylation positions for RRBS sequence files.")
11120 (license license:gpl3+)))
11122 (define-public gess
11128 (uri (string-append "http://compbio.uthscsa.edu/"
11130 "gess-" version ".src.tar.gz"))
11133 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
11134 (build-system gnu-build-system)
11136 `(#:tests? #f ; no tests
11138 (modify-phases %standard-phases
11139 (delete 'configure)
11142 (lambda* (#:key inputs outputs #:allow-other-keys)
11143 (let* ((python (assoc-ref inputs "python"))
11144 (out (assoc-ref outputs "out"))
11145 (bin (string-append out "/bin/"))
11146 (target (string-append
11148 ,(version-major+minor
11149 (package-version python))
11150 "/site-packages/gess/")))
11152 (copy-recursively "." target)
11153 ;; Make GESS.py executable
11154 (chmod (string-append target "GESS.py") #o555)
11155 ;; Add Python shebang to the top and make Matplotlib
11157 (substitute* (string-append target "GESS.py")
11158 (("\"\"\"Description:" line)
11159 (string-append "#!" (which "python") "
11161 matplotlib.use('Agg')
11163 ;; Make sure GESS has all modules in its path
11164 (wrap-program (string-append target "GESS.py")
11165 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
11167 (symlink (string-append target "GESS.py")
11168 (string-append bin "GESS.py"))
11171 `(("python" ,python-2)
11172 ("python2-pysam" ,python2-pysam)
11173 ("python2-scipy" ,python2-scipy)
11174 ("python2-numpy" ,python2-numpy)
11175 ("python2-networkx" ,python2-networkx)
11176 ("python2-biopython" ,python2-biopython)))
11177 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
11178 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11180 "GESS is an implementation of a novel computational method to detect de
11181 novo exon-skipping events directly from raw RNA-seq data without the prior
11182 knowledge of gene annotation information. GESS stands for the graph-based
11183 exon-skipping scanner detection scheme.")
11184 (license license:bsd-3)))
11186 (define-public phylip
11193 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11194 "download/phylip-" version ".tar.gz"))
11197 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11198 (build-system gnu-build-system)
11200 `(#:tests? #f ; no check target
11201 #:make-flags (list "-f" "Makefile.unx" "install")
11202 #:parallel-build? #f ; not supported
11204 (modify-phases %standard-phases
11205 (add-after 'unpack 'enter-dir
11206 (lambda _ (chdir "src") #t))
11207 (delete 'configure)
11209 (lambda* (#:key inputs outputs #:allow-other-keys)
11210 (let ((target (string-append (assoc-ref outputs "out")
11213 (for-each (lambda (file)
11214 (install-file file target))
11215 (find-files "../exe" ".*")))
11217 (home-page "http://evolution.genetics.washington.edu/phylip/")
11218 (synopsis "Tools for inferring phylogenies")
11219 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11220 programs for inferring phylogenies (evolutionary trees).")
11221 (license license:bsd-2)))
11230 (uri (string-append "https://integrativemodeling.org/"
11231 version "/download/imp-" version ".tar.gz"))
11234 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
11235 (build-system cmake-build-system)
11237 `(;; FIXME: Some tests fail because they produce warnings, others fail
11238 ;; because the PYTHONPATH does not include the modeller's directory.
11246 ("python" ,python-2)))
11248 `(("python2-numpy" ,python2-numpy)
11249 ("python2-scipy" ,python2-scipy)
11250 ("python2-pandas" ,python2-pandas)
11251 ("python2-scikit-learn" ,python2-scikit-learn)
11252 ("python2-networkx" ,python2-networkx)))
11253 (home-page "https://integrativemodeling.org")
11254 (synopsis "Integrative modeling platform")
11255 (description "IMP's broad goal is to contribute to a comprehensive
11256 structural characterization of biomolecules ranging in size and complexity
11257 from small peptides to large macromolecular assemblies, by integrating data
11258 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11259 Python toolbox for solving complex modeling problems, and a number of
11260 applications for tackling some common problems in a user-friendly way.")
11261 ;; IMP is largely available under the GNU Lesser GPL; see the file
11262 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11263 ;; available under the GNU GPL (see the file COPYING.GPL).
11264 (license (list license:lgpl2.1+
11267 (define-public tadbit
11273 (uri (git-reference
11274 (url "https://github.com/3DGenomes/TADbit.git")
11275 (commit (string-append "v" version))))
11276 (file-name (git-file-name name version))
11279 "07g3aj648prmsvxp9caz5yl41k0y0647vxh0f5p3w8376mfiljd0"))))
11280 (build-system python-build-system)
11282 `(;; Tests are included and must be run after installation, but
11283 ;; they are incomplete and thus cannot be run.
11287 (modify-phases %standard-phases
11288 (add-after 'unpack 'fix-problems-with-setup.py
11289 (lambda* (#:key outputs #:allow-other-keys)
11290 ;; setup.py opens these files for writing
11291 (chmod "_pytadbit/_version.py" #o664)
11292 (chmod "README.rst" #o664)
11294 ;; Don't attempt to install the bash completions to
11295 ;; the home directory.
11296 (rename-file "extras/.bash_completion"
11298 (substitute* "setup.py"
11299 (("\\(path.expanduser\\('~'\\)")
11300 (string-append "(\""
11301 (assoc-ref outputs "out")
11302 "/etc/bash_completion.d\""))
11303 (("extras/\\.bash_completion")
11307 ;; TODO: add Chimera for visualization
11310 ("python2-scipy" ,python2-scipy)
11311 ("python2-numpy" ,python2-numpy)
11312 ("python2-matplotlib" ,python2-matplotlib)
11313 ("python2-pysam" ,python2-pysam)))
11314 (home-page "https://3dgenomes.github.io/TADbit/")
11315 (synopsis "Analyze, model, and explore 3C-based data")
11317 "TADbit is a complete Python library to deal with all steps to analyze,
11318 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11319 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11320 correct interaction matrices, identify and compare the so-called
11321 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11322 interaction matrices, and finally, extract structural properties from the
11323 models. TADbit is complemented by TADkit for visualizing 3D models.")
11324 (license license:gpl3+)))
11326 (define-public kentutils
11329 ;; 302.1.0 is out, but the only difference is the inclusion of
11330 ;; pre-built binaries.
11331 (version "302.0.0")
11335 (uri (git-reference
11336 (url "https://github.com/ENCODE-DCC/kentUtils.git")
11337 (commit (string-append "v" version))))
11338 (file-name (git-file-name name version))
11341 "0n1wbyjpzii2b9qhyp9r1q76j623cggpg3y8fmw78ld3z4y7ivha"))
11342 (modules '((guix build utils)
11347 ;; Only the contents of the specified directories are free
11348 ;; for all uses, so we remove the rest. "hg/autoSql" and
11349 ;; "hg/autoXml" are nominally free, but they depend on a
11350 ;; library that is built from the sources in "hg/lib",
11351 ;; which is nonfree.
11352 (let ((free (list "." ".."
11353 "utils" "lib" "inc" "tagStorm"
11354 "parasol" "htslib"))
11355 (directory? (lambda (file)
11356 (eq? 'directory (stat:type (stat file))))))
11357 (for-each (lambda (file)
11358 (and (directory? file)
11359 (delete-file-recursively file)))
11360 (map (cut string-append "src/" <>)
11363 (not (member file free)))))))
11364 ;; Only make the utils target, not the userApps target,
11365 ;; because that requires libraries we won't build.
11366 (substitute* "Makefile"
11367 ((" userApps") " utils"))
11368 ;; Only build libraries that are free.
11369 (substitute* "src/makefile"
11370 (("DIRS =.*") "DIRS =\n")
11371 (("cd jkOwnLib.*") "")
11374 (substitute* "src/utils/makefile"
11375 ;; These tools depend on "jkhgap.a", which is part of the
11376 ;; nonfree "src/hg/lib" directory.
11377 (("raSqlQuery") "")
11378 (("pslLiftSubrangeBlat") "")
11380 ;; Do not build UCSC tools, which may require nonfree
11382 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11384 (build-system gnu-build-system)
11386 `( ;; There is no global test target and the test target for
11387 ;; individual tools depends on input files that are not
11391 (modify-phases %standard-phases
11392 (add-after 'unpack 'fix-permissions
11393 (lambda _ (make-file-writable "src/inc/localEnvironment.mk") #t))
11394 (add-after 'unpack 'fix-paths
11396 (substitute* "Makefile"
11397 (("/bin/echo") (which "echo")))
11399 (add-after 'unpack 'prepare-samtabix
11400 (lambda* (#:key inputs #:allow-other-keys)
11401 (copy-recursively (assoc-ref inputs "samtabix")
11404 (delete 'configure)
11406 (lambda* (#:key outputs #:allow-other-keys)
11407 (let ((bin (string-append (assoc-ref outputs "out")
11409 (copy-recursively "bin" bin))
11415 (uri (git-reference
11416 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11417 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11420 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11426 ("mariadb" ,mariadb)
11427 ("openssl" ,openssl)))
11428 (home-page "http://genome.cse.ucsc.edu/index.html")
11429 (synopsis "Assorted bioinformatics utilities")
11430 (description "This package provides the kentUtils, a selection of
11431 bioinformatics utilities used in combination with the UCSC genome
11433 ;; Only a subset of the sources are released under a non-copyleft
11434 ;; free software license. All other sources are removed in a
11435 ;; snippet. See this bug report for an explanation of how the
11436 ;; license statements apply:
11437 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11438 (license (license:non-copyleft
11439 "http://genome.ucsc.edu/license/"
11440 "The contents of this package are free for all uses."))))
11442 (define-public f-seq
11443 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11447 (version (string-append "1.1-" revision "." (string-take commit 7)))
11450 (uri (git-reference
11451 (url "https://github.com/aboyle/F-seq.git")
11453 (file-name (string-append name "-" version))
11456 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11457 (modules '((guix build utils)))
11458 ;; Remove bundled Java library archives.
11461 (for-each delete-file (find-files "lib" ".*"))
11463 (build-system ant-build-system)
11465 `(#:tests? #f ; no tests included
11467 (modify-phases %standard-phases
11469 (lambda* (#:key inputs outputs #:allow-other-keys)
11470 (let* ((target (assoc-ref outputs "out"))
11471 (bin (string-append target "/bin"))
11472 (doc (string-append target "/share/doc/f-seq"))
11473 (lib (string-append target "/lib")))
11476 (substitute* "bin/linux/fseq"
11477 (("java") (which "java"))
11478 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11479 (string-append (assoc-ref inputs "java-commons-cli")
11480 "/share/java/commons-cli.jar"))
11482 (string-append "REALDIR=" bin "\n")))
11483 (install-file "README.txt" doc)
11484 (install-file "bin/linux/fseq" bin)
11485 (install-file "build~/fseq.jar" lib)
11486 (copy-recursively "lib" lib)
11490 ("java-commons-cli" ,java-commons-cli)))
11491 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11492 (synopsis "Feature density estimator for high-throughput sequence tags")
11494 "F-Seq is a software package that generates a continuous tag sequence
11495 density estimation allowing identification of biologically meaningful sites
11496 such as transcription factor binding sites (ChIP-seq) or regions of open
11497 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11499 (license license:gpl3+))))
11501 (define-public bismark
11508 (uri (git-reference
11509 (url "https://github.com/FelixKrueger/Bismark.git")
11511 (file-name (string-append name "-" version "-checkout"))
11514 "0xchm3rgilj6vfjnyzfzzymfd7djr64sbrmrvs3njbwi66jqbzw9"))))
11515 (build-system perl-build-system)
11517 `(#:tests? #f ; there are no tests
11518 #:modules ((guix build utils)
11521 (guix build perl-build-system))
11523 (modify-phases %standard-phases
11524 ;; The bundled plotly.js is minified.
11525 (add-after 'unpack 'replace-plotly.js
11526 (lambda* (#:key inputs #:allow-other-keys)
11527 (let* ((file (assoc-ref inputs "plotly.js"))
11528 (installed "plotly/plotly.js"))
11529 (let ((minified (open-pipe* OPEN_READ "uglify-js" file)))
11530 (call-with-output-file installed
11531 (cut dump-port minified <>))))
11533 (delete 'configure)
11536 (lambda* (#:key inputs outputs #:allow-other-keys)
11537 (let* ((out (assoc-ref outputs "out"))
11538 (bin (string-append out "/bin"))
11539 (share (string-append out "/share/bismark"))
11540 (docdir (string-append out "/share/doc/bismark"))
11541 (docs '("Docs/Bismark_User_Guide.html"))
11542 (scripts '("bismark"
11543 "bismark_genome_preparation"
11544 "bismark_methylation_extractor"
11547 "coverage2cytosine"
11548 "deduplicate_bismark"
11549 "filter_non_conversion"
11552 "NOMe_filtering")))
11553 (substitute* "bismark2report"
11554 (("\\$RealBin/plotly")
11555 (string-append share "/plotly")))
11559 (for-each (lambda (file) (install-file file bin))
11561 (for-each (lambda (file) (install-file file docdir))
11563 (copy-recursively "Docs/Images" (string-append docdir "/Images"))
11564 (copy-recursively "plotly"
11565 (string-append share "/plotly"))
11567 ;; Fix references to gunzip
11568 (substitute* (map (lambda (file)
11569 (string-append bin "/" file))
11572 (string-append "\"" (assoc-ref inputs "gzip")
11573 "/bin/gunzip -c")))
11577 ("perl-carp" ,perl-carp)
11578 ("perl-getopt-long" ,perl-getopt-long)))
11583 (uri (string-append "https://raw.githubusercontent.com/plotly/plotly.js/"
11584 "v1.39.4/dist/plotly.js"))
11586 (base32 "138mwsr4nf5qif4mrxx286mpnagxd1xwl6k8aidrjgknaqg88zyr"))))
11587 ("uglify-js" ,uglify-js)))
11588 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11589 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11590 (description "Bismark is a program to map bisulfite treated sequencing
11591 reads to a genome of interest and perform methylation calls in a single step.
11592 The output can be easily imported into a genome viewer, such as SeqMonk, and
11593 enables a researcher to analyse the methylation levels of their samples
11594 straight away. Its main features are:
11597 @item Bisulfite mapping and methylation calling in one single step
11598 @item Supports single-end and paired-end read alignments
11599 @item Supports ungapped and gapped alignments
11600 @item Alignment seed length, number of mismatches etc are adjustable
11601 @item Output discriminates between cytosine methylation in CpG, CHG
11604 (license license:gpl3+)))
11606 (define-public paml
11612 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11613 "paml" version ".tgz"))
11616 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11617 (modules '((guix build utils)))
11618 ;; Remove Windows binaries
11621 (for-each delete-file (find-files "." "\\.exe$"))
11623 (build-system gnu-build-system)
11625 `(#:tests? #f ; there are no tests
11626 #:make-flags '("CC=gcc")
11628 (modify-phases %standard-phases
11629 (replace 'configure
11631 (substitute* "src/BFdriver.c"
11632 (("/bin/bash") (which "bash")))
11636 (lambda* (#:key outputs #:allow-other-keys)
11637 (let ((tools '("baseml" "basemlg" "codeml"
11638 "pamp" "evolver" "yn00" "chi2"))
11639 (bin (string-append (assoc-ref outputs "out") "/bin"))
11640 (docdir (string-append (assoc-ref outputs "out")
11641 "/share/doc/paml")))
11643 (for-each (lambda (file) (install-file file bin)) tools)
11644 (copy-recursively "../doc" docdir)
11646 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11647 (synopsis "Phylogentic analysis by maximum likelihood")
11648 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11649 contains a few programs for model fitting and phylogenetic tree reconstruction
11650 using nucleotide or amino-acid sequence data.")
11652 (license license:gpl3)))
11654 (define-public kallisto
11660 (uri (git-reference
11661 (url "https://github.com/pachterlab/kallisto.git")
11662 (commit (string-append "v" version))))
11663 (file-name (git-file-name name version))
11666 "0nj382jiywqnpgvyhichajpkkh5r0bapn43f4dx40zdaq5v4m40m"))))
11667 (build-system cmake-build-system)
11669 `(#:tests? #f ; no "check" target
11671 (modify-phases %standard-phases
11672 (add-after 'unpack 'do-not-use-bundled-htslib
11674 (substitute* "CMakeLists.txt"
11675 (("^ExternalProject_Add" m)
11676 (string-append "if (NEVER)\n" m))
11678 (string-append ")\nendif(NEVER)"))
11679 (("include_directories\\(\\$\\{htslib_PREFIX.*" m)
11680 (string-append "# " m)))
11681 (substitute* "src/CMakeLists.txt"
11682 (("target_link_libraries\\(kallisto kallisto_core pthread \
11683 \\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/../ext/htslib/libhts.a\\)")
11684 "target_link_libraries(kallisto kallisto_core pthread hts)")
11685 (("include_directories\\(\\.\\./ext/htslib\\)") ""))
11691 (home-page "http://pachterlab.github.io/kallisto/")
11692 (synopsis "Near-optimal RNA-Seq quantification")
11694 "Kallisto is a program for quantifying abundances of transcripts from
11695 RNA-Seq data, or more generally of target sequences using high-throughput
11696 sequencing reads. It is based on the novel idea of pseudoalignment for
11697 rapidly determining the compatibility of reads with targets, without the need
11698 for alignment. Pseudoalignment of reads preserves the key information needed
11699 for quantification, and kallisto is therefore not only fast, but also as
11700 accurate as existing quantification tools.")
11701 (license license:bsd-2)))
11703 (define-public libgff
11709 (uri (git-reference
11710 (url "https://github.com/Kingsford-Group/libgff.git")
11711 (commit (string-append "v" version))))
11712 (file-name (git-file-name name version))
11715 "0n6vfjnq7a2mianipscbshrvbncss8z4zkgkbjw754p9043nfkps"))))
11716 (build-system cmake-build-system)
11717 (arguments `(#:tests? #f)) ; no tests included
11718 (home-page "https://github.com/Kingsford-Group/libgff")
11719 (synopsis "Parser library for reading/writing GFF files")
11720 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11721 code that is used in the Cufflinks codebase. The goal of this library is to
11722 provide this functionality without the necessity of drawing in a heavy-weight
11723 dependency like SeqAn.")
11724 (license (license:x11-style "https://www.boost.org/LICENSE_1_0.txt"))))
11726 (define-public libdivsufsort
11728 (name "libdivsufsort")
11732 (uri (git-reference
11733 (url "https://github.com/y-256/libdivsufsort.git")
11735 (file-name (git-file-name name version))
11738 "0fgdz9fzihlvjjrxy01md1bv9vh12rkgkwbm90b1hj5xpbaqp7z2"))))
11739 (build-system cmake-build-system)
11741 '(#:tests? #f ; there are no tests
11743 ;; Needed for rapmap and sailfish.
11744 '("-DBUILD_DIVSUFSORT64=ON")))
11745 (home-page "https://github.com/y-256/libdivsufsort")
11746 (synopsis "Lightweight suffix-sorting library")
11747 (description "libdivsufsort is a software library that implements a
11748 lightweight suffix array construction algorithm. This library provides a
11749 simple and an efficient C API to construct a suffix array and a
11750 Burrows-Wheeler transformed string from a given string over a constant-size
11751 alphabet. The algorithm runs in O(n log n) worst-case time using only 5n+O(1)
11752 bytes of memory space, where n is the length of the string.")
11753 (license license:expat)))
11755 (define-public sailfish
11761 (uri (git-reference
11762 (url "https://github.com/kingsfordgroup/sailfish.git")
11763 (commit (string-append "v" version))))
11764 (file-name (git-file-name name version))
11767 "1amcc5hqvsl42hg4x19bi9vy47cl874s0lw1fmi0hwsdk9i8c03v"))
11768 (modules '((guix build utils)))
11771 ;; Delete bundled headers for eigen3.
11772 (delete-file-recursively "include/eigen3/")
11774 (build-system cmake-build-system)
11776 `(#:configure-flags
11777 (list (string-append "-DBOOST_INCLUDEDIR="
11778 (assoc-ref %build-inputs "boost")
11780 (string-append "-DBOOST_LIBRARYDIR="
11781 (assoc-ref %build-inputs "boost")
11783 (string-append "-DBoost_LIBRARIES="
11784 "-lboost_iostreams "
11785 "-lboost_filesystem "
11790 "-lboost_program_options")
11791 "-DBoost_FOUND=TRUE"
11792 ;; Don't download RapMap---we already have it!
11793 "-DFETCHED_RAPMAP=1")
11794 ;; Tests must be run after installation and the location of the test
11795 ;; data file must be overridden. But the tests fail. It looks like
11796 ;; they are not really meant to be run.
11799 (modify-phases %standard-phases
11800 ;; Boost cannot be found, even though it's right there.
11801 (add-after 'unpack 'do-not-look-for-boost
11802 (lambda* (#:key inputs #:allow-other-keys)
11803 (substitute* "CMakeLists.txt"
11804 (("find_package\\(Boost 1\\.53\\.0") "#"))
11806 (add-after 'unpack 'do-not-assign-to-macro
11808 (substitute* "include/spdlog/details/format.cc"
11809 (("const unsigned CHAR_WIDTH = 1;") ""))
11811 (add-after 'unpack 'prepare-rapmap
11812 (lambda* (#:key inputs #:allow-other-keys)
11813 (let ((src "external/install/src/rapmap/")
11814 (include "external/install/include/rapmap/")
11815 (rapmap (assoc-ref inputs "rapmap")))
11816 (mkdir-p "/tmp/rapmap")
11818 (assoc-ref inputs "rapmap")
11820 "--strip-components=1")
11823 (for-each (lambda (file)
11824 (install-file file src))
11825 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
11826 (copy-recursively "/tmp/rapmap/include" include))
11828 (add-after 'unpack 'use-system-libraries
11829 (lambda* (#:key inputs #:allow-other-keys)
11830 (substitute* '("src/SailfishIndexer.cpp"
11831 "src/SailfishUtils.cpp"
11832 "src/SailfishQuantify.cpp"
11833 "src/FASTAParser.cpp"
11835 "include/SailfishUtils.hpp"
11836 "include/SailfishIndex.hpp"
11837 "include/CollapsedEMOptimizer.hpp"
11838 "src/CollapsedEMOptimizer.cpp")
11839 (("#include \"jellyfish/config.h\"") ""))
11840 (substitute* "src/CMakeLists.txt"
11841 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11842 (string-append (assoc-ref inputs "jellyfish")
11843 "/include/jellyfish-" ,(package-version jellyfish)))
11844 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11845 (string-append (assoc-ref inputs "jellyfish")
11846 "/lib/libjellyfish-2.0.a"))
11847 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11848 (string-append (assoc-ref inputs "libdivsufsort")
11849 "/lib/libdivsufsort.so"))
11850 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11851 (string-append (assoc-ref inputs "libdivsufsort")
11852 "/lib/libdivsufsort64.so")))
11853 (substitute* "CMakeLists.txt"
11854 ;; Don't prefer static libs
11855 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11856 (("find_package\\(Jellyfish.*") "")
11857 (("ExternalProject_Add\\(libjellyfish") "message(")
11858 (("ExternalProject_Add\\(libgff") "message(")
11859 (("ExternalProject_Add\\(libsparsehash") "message(")
11860 (("ExternalProject_Add\\(libdivsufsort") "message("))
11862 ;; Ensure that Eigen headers can be found
11863 (setenv "CPLUS_INCLUDE_PATH"
11864 (string-append (getenv "CPLUS_INCLUDE_PATH")
11866 (assoc-ref inputs "eigen")
11867 "/include/eigen3"))
11872 ("jemalloc" ,jemalloc)
11873 ("jellyfish" ,jellyfish)
11874 ("sparsehash" ,sparsehash)
11877 (uri (git-reference
11878 (url "https://github.com/COMBINE-lab/RapMap.git")
11879 (commit (string-append "sf-v" version))))
11880 (file-name (string-append "rapmap-sf-v" version "-checkout"))
11883 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
11884 (modules '((guix build utils)))
11885 ;; These files are expected to be excluded.
11887 '(begin (delete-file-recursively "include/spdlog")
11888 (for-each delete-file '("include/xxhash.h"
11891 ("libdivsufsort" ,libdivsufsort)
11896 `(("pkg-config" ,pkg-config)))
11897 (home-page "http://www.cs.cmu.edu/~ckingsf/software/sailfish")
11898 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
11899 (description "Sailfish is a tool for genomic transcript quantification
11900 from RNA-seq data. It requires a set of target transcripts (either from a
11901 reference or de-novo assembly) to quantify. All you need to run sailfish is a
11902 fasta file containing your reference transcripts and a (set of) fasta/fastq
11903 file(s) containing your reads.")
11904 (license license:gpl3+)))
11906 (define libstadenio-for-salmon
11908 (name "libstadenio")
11912 (uri (git-reference
11913 (url "https://github.com/COMBINE-lab/staden-io_lib.git")
11914 (commit (string-append "v" version))))
11915 (file-name (string-append name "-" version "-checkout"))
11918 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
11919 (build-system gnu-build-system)
11920 (arguments '(#:parallel-tests? #f)) ; not supported
11924 `(("perl" ,perl))) ; for tests
11925 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
11926 (synopsis "General purpose trace and experiment file library")
11927 (description "This package provides a library of file reading and writing
11928 code to provide a general purpose Trace file (and Experiment File) reading
11931 The following file formats are supported:
11934 @item SCF trace files
11935 @item ABI trace files
11936 @item ALF trace files
11937 @item ZTR trace files
11938 @item SFF trace archives
11939 @item SRF trace archives
11940 @item Experiment files
11941 @item Plain text files
11942 @item SAM/BAM sequence files
11943 @item CRAM sequence files
11945 (license license:bsd-3)))
11947 (define spdlog-for-salmon
11953 (uri (git-reference
11954 (url "https://github.com/COMBINE-lab/spdlog.git")
11955 (commit (string-append "v" version))))
11956 (file-name (string-append name "-" version "-checkout"))
11959 "13730429gwlabi432ilpnja3sfvy0nn2719vnhhmii34xcdyc57q"))))
11960 (build-system cmake-build-system)
11961 (home-page "https://github.com/COMBINE-lab/spdlog")
11962 (synopsis "Very fast C++ logging library")
11963 (description "Spdlog is a very fast header-only C++ logging library with
11964 performance as its primary goal.")
11965 (license license:expat)))
11967 ;; This is a modified variant of bwa for use with Salmon. It installs a
11968 ;; library to avoid having to build this as part of Salmon.
11969 (define bwa-for-salmon
11970 (package (inherit bwa)
11972 (version "0.7.12.5")
11975 (uri (git-reference
11976 (url "https://github.com/COMBINE-lab/bwa.git")
11977 (commit (string-append "v" version))))
11978 (file-name (string-append "bwa-for-salmon-" version "-checkout"))
11981 "1z2qa64y0c5hky10510x137mnzlhz6k8qf27csw4w9j6qihq95gb"))))
11982 (build-system gnu-build-system)
11984 '(#:tests? #f ;no "check" target
11986 (modify-phases %standard-phases
11988 (lambda* (#:key outputs #:allow-other-keys)
11989 (let* ((out (assoc-ref outputs "out"))
11990 (bin (string-append out "/bin"))
11991 (lib (string-append out "/lib"))
11992 (doc (string-append out "/share/doc/bwa"))
11993 (man (string-append out "/share/man/man1"))
11994 (inc (string-append out "/include/bwa")))
11995 (install-file "bwa" bin)
11996 (install-file "README.md" doc)
11997 (install-file "bwa.1" man)
11998 (install-file "libbwa.a" lib)
12001 (for-each (lambda (file)
12002 (install-file file inc))
12003 (find-files "." "\\.h$")))
12005 ;; no "configure" script
12006 (delete 'configure))))))
12008 (define-public salmon
12014 (uri (git-reference
12015 (url "https://github.com/COMBINE-lab/salmon.git")
12016 (commit (string-append "v" version))))
12017 (file-name (string-append name "-" version "-checkout"))
12020 "1zi1ff4i7y2ykk0vdzysgwzzzv166vg2x77pj1mf4baclavxj87a"))
12021 (modules '((guix build utils)))
12024 ;; Delete bundled headers for eigen3.
12025 (delete-file-recursively "include/eigen3/")
12027 (build-system cmake-build-system)
12029 `(#:configure-flags
12030 (list (string-append "-DBOOST_INCLUDEDIR="
12031 (assoc-ref %build-inputs "boost")
12033 (string-append "-DBOOST_LIBRARYDIR="
12034 (assoc-ref %build-inputs "boost")
12036 (string-append "-DBoost_LIBRARIES="
12037 "-lboost_iostreams "
12038 "-lboost_filesystem "
12043 "-lboost_program_options")
12044 "-DBoost_FOUND=TRUE"
12045 "-DTBB_LIBRARIES=tbb tbbmalloc"
12046 ;; Don't download RapMap---we already have it!
12047 "-DFETCHED_RAPMAP=1")
12049 (modify-phases %standard-phases
12050 ;; Boost cannot be found, even though it's right there.
12051 (add-after 'unpack 'do-not-look-for-boost
12052 (lambda* (#:key inputs #:allow-other-keys)
12053 (substitute* "CMakeLists.txt"
12054 (("find_package\\(Boost 1\\.53\\.0") "#"))
12056 (add-after 'unpack 'do-not-phone-home
12058 (substitute* "src/Salmon.cpp"
12059 (("getVersionMessage\\(\\)") "\"\""))
12061 (add-after 'unpack 'prepare-rapmap
12062 (lambda* (#:key inputs #:allow-other-keys)
12063 (let ((src "external/install/src/rapmap/")
12064 (include "external/install/include/rapmap/")
12065 (rapmap (assoc-ref inputs "rapmap")))
12068 (for-each (lambda (file)
12069 (install-file file src))
12070 (find-files (string-append rapmap "/src") "\\.(c|cpp)"))
12071 (copy-recursively (string-append rapmap "/include") include)
12072 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
12073 "external/install/include/rapmap/FastxParser.hpp"
12074 "external/install/include/rapmap/concurrentqueue.h"
12075 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
12076 "external/install/src/rapmap/FastxParser.cpp"
12077 "external/install/src/rapmap/xxhash.c")))
12079 (add-after 'unpack 'use-system-libraries
12080 (lambda* (#:key inputs #:allow-other-keys)
12081 (substitute* "src/CMakeLists.txt"
12082 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
12083 (string-append (assoc-ref inputs "jellyfish")
12084 "/include/jellyfish-" ,(package-version jellyfish)))
12085 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
12086 (string-append (assoc-ref inputs "jellyfish")
12087 "/lib/libjellyfish-2.0.a"))
12088 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12089 (string-append (assoc-ref inputs "libdivsufsort")
12090 "/lib/libdivsufsort.so"))
12091 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
12092 (string-append (assoc-ref inputs "libstadenio-for-salmon")
12093 "/lib/libstaden-read.a"))
12094 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libbwa.a")
12095 (string-append (assoc-ref inputs "bwa") "/lib/libbwa.a"))
12096 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12097 (string-append (assoc-ref inputs "libdivsufsort")
12098 "/lib/libdivsufsort64.so")))
12099 (substitute* "CMakeLists.txt"
12100 ;; Don't prefer static libs
12101 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12102 (("set\\(TBB_LIBRARIES") "message(")
12103 (("find_package\\(Jellyfish.*") "")
12104 (("ExternalProject_Add\\(libcereal") "message(")
12105 (("ExternalProject_Add\\(libbwa") "message(")
12106 (("ExternalProject_Add\\(libjellyfish") "message(")
12107 (("ExternalProject_Add\\(libgff") "message(")
12108 (("ExternalProject_Add\\(libtbb") "message(")
12109 (("ExternalProject_Add\\(libspdlog") "message(")
12110 (("ExternalProject_Add\\(libdivsufsort") "message(")
12111 (("ExternalProject_Add\\(libstadenio") "message(")
12112 (("ExternalProject_Add_Step\\(") "message("))
12114 ;; Ensure that all headers can be found
12115 (setenv "CPLUS_INCLUDE_PATH"
12116 (string-append (getenv "CPLUS_INCLUDE_PATH")
12118 (assoc-ref inputs "bwa")
12121 (assoc-ref inputs "eigen")
12122 "/include/eigen3"))
12124 (string-append (assoc-ref inputs "bwa")
12127 (assoc-ref inputs "eigen")
12128 "/include/eigen3"))
12130 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
12131 ;; run. It only exists after the install phase.
12132 (add-after 'unpack 'fix-tests
12134 (substitute* "src/CMakeLists.txt"
12135 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
12136 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
12140 ("bwa" ,bwa-for-salmon)
12146 (uri (git-reference
12147 (url "https://github.com/COMBINE-lab/RapMap.git")
12148 (commit (string-append "salmon-v" version))))
12149 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
12152 "1yc12yqsz6f0r8sg1qnk57xg34aqwc9jbqq6gd5ys28xw3plj98p"))))
12153 ("jemalloc" ,jemalloc)
12154 ("jellyfish" ,jellyfish)
12157 ("libdivsufsort" ,libdivsufsort)
12158 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
12159 ("spdlog-for-salmon" ,spdlog-for-salmon)
12162 (home-page "https://github.com/COMBINE-lab/salmon")
12163 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
12164 (description "Salmon is a program to produce highly-accurate,
12165 transcript-level quantification estimates from RNA-seq data. Salmon achieves
12166 its accuracy and speed via a number of different innovations, including the
12167 use of lightweight alignments (accurate but fast-to-compute proxies for
12168 traditional read alignments) and massively-parallel stochastic collapsed
12169 variational inference.")
12170 (license license:gpl3+)))
12172 (define-public python-loompy
12174 (name "python-loompy")
12179 (uri (pypi-uri "loompy" version))
12182 "1drgv8j1hxqzzpnfg272x9djb6j8qr798w1pc2x8ikmfgyd9gh51"))))
12183 (build-system python-build-system)
12184 ;; There are no tests
12185 (arguments '(#:tests? #f))
12187 `(("python-h5py" ,python-h5py)
12188 ("python-numpy" ,python-numpy)
12189 ("python-scipy" ,python-scipy)))
12190 (home-page "https://github.com/linnarsson-lab/loompy")
12191 (synopsis "Work with .loom files for single-cell RNA-seq data")
12192 (description "The loom file format is an efficient format for very large
12193 omics datasets, consisting of a main matrix, optional additional layers, a
12194 variable number of row and column annotations. Loom also supports sparse
12195 graphs. This library makes it easy to work with @file{.loom} files for
12196 single-cell RNA-seq data.")
12197 (license license:bsd-3)))
12199 ;; We cannot use the latest commit because it requires Java 9.
12200 (define-public java-forester
12201 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
12204 (name "java-forester")
12205 (version (string-append "0-" revision "." (string-take commit 7)))
12208 (uri (git-reference
12209 (url "https://github.com/cmzmasek/forester.git")
12211 (file-name (string-append name "-" version "-checkout"))
12214 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12215 (modules '((guix build utils)))
12218 ;; Delete bundled jars and pre-built classes
12219 (delete-file-recursively "forester/java/resources")
12220 (delete-file-recursively "forester/java/classes")
12221 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12222 ;; Delete bundled applications
12223 (delete-file-recursively "forester_applications")
12225 (build-system ant-build-system)
12227 `(#:tests? #f ; there are none
12229 #:modules ((guix build ant-build-system)
12231 (guix build java-utils)
12235 (modify-phases %standard-phases
12236 (add-after 'unpack 'chdir
12237 (lambda _ (chdir "forester/java") #t))
12238 (add-after 'chdir 'fix-dependencies
12240 (chmod "build.xml" #o664)
12241 (call-with-output-file "build.xml.new"
12245 (with-input-from-file "build.xml"
12246 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12247 `(;; Remove all unjar tags to avoid repacking classes.
12248 (unjar . ,(lambda _ '()))
12249 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12250 (*text* . ,(lambda (_ txt) txt))))
12252 (rename-file "build.xml.new" "build.xml")
12254 ;; FIXME: itext is difficult to package as it depends on a few
12255 ;; unpackaged libraries.
12256 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12258 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12259 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12260 (("pdf_written_to = PdfExporter.*")
12261 "throw new IOException(\"PDF export is not available.\");"))
12263 ;; There is no install target
12264 (replace 'install (install-jars ".")))))
12266 `(("java-commons-codec" ,java-commons-codec)
12267 ("java-openchart2" ,java-openchart2)))
12268 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12269 (synopsis "Phylogenomics libraries for Java")
12270 (description "Forester is a collection of Java libraries for
12271 phylogenomics and evolutionary biology research. It includes support for
12272 reading, writing, and exporting phylogenetic trees.")
12273 (license license:lgpl2.1+))))
12275 (define-public java-forester-1.005
12277 (name "java-forester")
12281 (uri (string-append "http://search.maven.org/remotecontent?"
12282 "filepath=org/biojava/thirdparty/forester/"
12283 version "/forester-" version "-sources.jar"))
12284 (file-name (string-append name "-" version ".jar"))
12287 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12288 (build-system ant-build-system)
12290 `(#:tests? #f ; there are none
12292 #:modules ((guix build ant-build-system)
12294 (guix build java-utils)
12298 (modify-phases %standard-phases
12299 (add-after 'unpack 'fix-dependencies
12300 (lambda* (#:key inputs #:allow-other-keys)
12301 (call-with-output-file "build.xml"
12305 (with-input-from-file "src/build.xml"
12306 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12307 `(;; Remove all unjar tags to avoid repacking classes.
12308 (unjar . ,(lambda _ '()))
12309 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12310 (*text* . ,(lambda (_ txt) txt))))
12312 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12313 "synth_look_and_feel_1.xml")
12314 (copy-file (assoc-ref inputs "phyloxml.xsd")
12316 (substitute* "build.xml"
12317 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12318 "synth_look_and_feel_1.xml")
12319 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12322 ;; FIXME: itext is difficult to package as it depends on a few
12323 ;; unpackaged libraries.
12324 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12326 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12327 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12328 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12329 (("pdf_written_to = PdfExporter.*")
12330 "throw new IOException(\"PDF export is not available.\"); /*")
12331 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12332 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12334 (add-after 'unpack 'delete-pre-built-classes
12335 (lambda _ (delete-file-recursively "src/classes") #t))
12336 ;; There is no install target
12337 (replace 'install (install-jars ".")))))
12339 `(("java-commons-codec" ,java-commons-codec)
12340 ("java-openchart2" ,java-openchart2)))
12341 ;; The source archive does not contain the resources.
12346 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12347 "b61cc2dcede0bede317db362472333115756b8c6/"
12348 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12349 (file-name (string-append name "-phyloxml-" version ".xsd"))
12352 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12353 ("synth_look_and_feel_1.xml"
12356 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12357 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12358 "forester/java/classes/resources/synth_look_and_feel_1.xml"))
12359 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12362 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12363 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12364 (synopsis "Phylogenomics libraries for Java")
12365 (description "Forester is a collection of Java libraries for
12366 phylogenomics and evolutionary biology research. It includes support for
12367 reading, writing, and exporting phylogenetic trees.")
12368 (license license:lgpl2.1+)))
12370 (define-public java-biojava-core
12372 (name "java-biojava-core")
12376 (uri (git-reference
12377 (url "https://github.com/biojava/biojava")
12378 (commit (string-append "biojava-" version))))
12379 (file-name (string-append name "-" version "-checkout"))
12382 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12383 (build-system ant-build-system)
12386 #:jar-name "biojava-core.jar"
12387 #:source-dir "biojava-core/src/main/java/"
12388 #:test-dir "biojava-core/src/test"
12389 ;; These tests seem to require internet access.
12390 #:test-exclude (list "**/SearchIOTest.java"
12391 "**/BlastXMLParserTest.java"
12392 "**/GenbankCookbookTest.java"
12393 "**/GenbankProxySequenceReaderTest.java")
12395 (modify-phases %standard-phases
12396 (add-before 'build 'copy-resources
12398 (copy-recursively "biojava-core/src/main/resources"
12401 (add-before 'check 'copy-test-resources
12403 (copy-recursively "biojava-core/src/test/resources"
12404 "build/test-classes")
12407 `(("java-log4j-api" ,java-log4j-api)
12408 ("java-log4j-core" ,java-log4j-core)
12409 ("java-slf4j-api" ,java-slf4j-api)
12410 ("java-slf4j-simple" ,java-slf4j-simple)))
12412 `(("java-junit" ,java-junit)
12413 ("java-hamcrest-core" ,java-hamcrest-core)))
12414 (home-page "http://biojava.org")
12415 (synopsis "Core libraries of Java framework for processing biological data")
12416 (description "BioJava is a project dedicated to providing a Java framework
12417 for processing biological data. It provides analytical and statistical
12418 routines, parsers for common file formats, reference implementations of
12419 popular algorithms, and allows the manipulation of sequences and 3D
12420 structures. The goal of the biojava project is to facilitate rapid
12421 application development for bioinformatics.
12423 This package provides the core libraries.")
12424 (license license:lgpl2.1+)))
12426 (define-public java-biojava-phylo
12427 (package (inherit java-biojava-core)
12428 (name "java-biojava-phylo")
12429 (build-system ant-build-system)
12432 #:jar-name "biojava-phylo.jar"
12433 #:source-dir "biojava-phylo/src/main/java/"
12434 #:test-dir "biojava-phylo/src/test"
12436 (modify-phases %standard-phases
12437 (add-before 'build 'copy-resources
12439 (copy-recursively "biojava-phylo/src/main/resources"
12442 (add-before 'check 'copy-test-resources
12444 (copy-recursively "biojava-phylo/src/test/resources"
12445 "build/test-classes")
12448 `(("java-log4j-api" ,java-log4j-api)
12449 ("java-log4j-core" ,java-log4j-core)
12450 ("java-slf4j-api" ,java-slf4j-api)
12451 ("java-slf4j-simple" ,java-slf4j-simple)
12452 ("java-biojava-core" ,java-biojava-core)
12453 ("java-forester" ,java-forester)))
12455 `(("java-junit" ,java-junit)
12456 ("java-hamcrest-core" ,java-hamcrest-core)))
12457 (home-page "http://biojava.org")
12458 (synopsis "Biojava interface to the forester phylogenomics library")
12459 (description "The phylo module provides a biojava interface layer to the
12460 forester phylogenomics library for constructing phylogenetic trees.")))
12462 (define-public java-biojava-alignment
12463 (package (inherit java-biojava-core)
12464 (name "java-biojava-alignment")
12465 (build-system ant-build-system)
12468 #:jar-name "biojava-alignment.jar"
12469 #:source-dir "biojava-alignment/src/main/java/"
12470 #:test-dir "biojava-alignment/src/test"
12472 (modify-phases %standard-phases
12473 (add-before 'build 'copy-resources
12475 (copy-recursively "biojava-alignment/src/main/resources"
12478 (add-before 'check 'copy-test-resources
12480 (copy-recursively "biojava-alignment/src/test/resources"
12481 "build/test-classes")
12484 `(("java-log4j-api" ,java-log4j-api)
12485 ("java-log4j-core" ,java-log4j-core)
12486 ("java-slf4j-api" ,java-slf4j-api)
12487 ("java-slf4j-simple" ,java-slf4j-simple)
12488 ("java-biojava-core" ,java-biojava-core)
12489 ("java-biojava-phylo" ,java-biojava-phylo)
12490 ("java-forester" ,java-forester)))
12492 `(("java-junit" ,java-junit)
12493 ("java-hamcrest-core" ,java-hamcrest-core)))
12494 (home-page "http://biojava.org")
12495 (synopsis "Biojava API for genetic sequence alignment")
12496 (description "The alignment module of BioJava provides an API that
12500 @item implementations of dynamic programming algorithms for sequence
12502 @item reading and writing of popular alignment file formats;
12503 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12506 (define-public java-biojava-core-4.0
12507 (package (inherit java-biojava-core)
12508 (name "java-biojava-core")
12512 (uri (git-reference
12513 (url "https://github.com/biojava/biojava")
12514 (commit (string-append "biojava-" version))))
12515 (file-name (string-append name "-" version "-checkout"))
12518 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12520 (define-public java-biojava-phylo-4.0
12521 (package (inherit java-biojava-core-4.0)
12522 (name "java-biojava-phylo")
12523 (build-system ant-build-system)
12526 #:jar-name "biojava-phylo.jar"
12527 #:source-dir "biojava-phylo/src/main/java/"
12528 #:test-dir "biojava-phylo/src/test"
12530 (modify-phases %standard-phases
12531 (add-before 'build 'copy-resources
12533 (copy-recursively "biojava-phylo/src/main/resources"
12536 (add-before 'check 'copy-test-resources
12538 (copy-recursively "biojava-phylo/src/test/resources"
12539 "build/test-classes")
12542 `(("java-log4j-api" ,java-log4j-api)
12543 ("java-log4j-core" ,java-log4j-core)
12544 ("java-slf4j-api" ,java-slf4j-api)
12545 ("java-slf4j-simple" ,java-slf4j-simple)
12546 ("java-biojava-core" ,java-biojava-core-4.0)
12547 ("java-forester" ,java-forester-1.005)))
12549 `(("java-junit" ,java-junit)
12550 ("java-hamcrest-core" ,java-hamcrest-core)))
12551 (home-page "http://biojava.org")
12552 (synopsis "Biojava interface to the forester phylogenomics library")
12553 (description "The phylo module provides a biojava interface layer to the
12554 forester phylogenomics library for constructing phylogenetic trees.")))
12556 (define-public java-biojava-alignment-4.0
12557 (package (inherit java-biojava-core-4.0)
12558 (name "java-biojava-alignment")
12559 (build-system ant-build-system)
12562 #:jar-name "biojava-alignment.jar"
12563 #:source-dir "biojava-alignment/src/main/java/"
12564 #:test-dir "biojava-alignment/src/test"
12566 (modify-phases %standard-phases
12567 (add-before 'build 'copy-resources
12569 (copy-recursively "biojava-alignment/src/main/resources"
12572 (add-before 'check 'copy-test-resources
12574 (copy-recursively "biojava-alignment/src/test/resources"
12575 "build/test-classes")
12578 `(("java-log4j-api" ,java-log4j-api)
12579 ("java-log4j-core" ,java-log4j-core)
12580 ("java-slf4j-api" ,java-slf4j-api)
12581 ("java-slf4j-simple" ,java-slf4j-simple)
12582 ("java-biojava-core" ,java-biojava-core-4.0)
12583 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12584 ("java-forester" ,java-forester-1.005)))
12586 `(("java-junit" ,java-junit)
12587 ("java-hamcrest-core" ,java-hamcrest-core)))
12588 (home-page "http://biojava.org")
12589 (synopsis "Biojava API for genetic sequence alignment")
12590 (description "The alignment module of BioJava provides an API that
12594 @item implementations of dynamic programming algorithms for sequence
12596 @item reading and writing of popular alignment file formats;
12597 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12600 (define-public dropseq-tools
12602 (name "dropseq-tools")
12607 (uri "http://mccarrolllab.com/download/1276/")
12608 (file-name (string-append "dropseq-tools-" version ".zip"))
12611 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12612 ;; Delete bundled libraries
12613 (modules '((guix build utils)))
12616 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12617 (delete-file-recursively "3rdParty")
12619 (build-system ant-build-system)
12621 `(#:tests? #f ; test data are not included
12622 #:test-target "test"
12623 #:build-target "all"
12624 #:source-dir "public/src/"
12627 (list (string-append "-Dpicard.executable.dir="
12628 (assoc-ref %build-inputs "java-picard")
12630 #:modules ((ice-9 match)
12633 (guix build java-utils)
12634 (guix build ant-build-system))
12636 (modify-phases %standard-phases
12637 ;; FIXME: fails with "java.io.FileNotFoundException:
12638 ;; /gnu/store/…-dropseq-tools-1.13/share/java/lib/biojava-alignment.jar"
12639 (delete 'generate-jar-indices)
12640 ;; All dependencies must be linked to "lib", because that's where
12641 ;; they will be searched for when the Class-Path property of the
12642 ;; manifest is computed.
12643 (add-after 'unpack 'record-references
12644 (lambda* (#:key inputs #:allow-other-keys)
12645 (mkdir-p "jar/lib")
12646 (let ((dirs (filter-map (match-lambda
12648 (if (and (string-prefix? "java-" name)
12649 (not (string=? name "java-testng")))
12652 (for-each (lambda (jar)
12653 (symlink jar (string-append "jar/lib/" (basename jar))))
12654 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12657 ;; There is no installation target
12659 (lambda* (#:key inputs outputs #:allow-other-keys)
12660 (let* ((out (assoc-ref outputs "out"))
12661 (bin (string-append out "/bin"))
12662 (share (string-append out "/share/java/"))
12663 (lib (string-append share "/lib/"))
12664 (scripts (list "BAMTagHistogram"
12665 "BAMTagofTagCounts"
12666 "BaseDistributionAtReadPosition"
12667 "CollapseBarcodesInPlace"
12668 "CollapseTagWithContext"
12670 "CreateIntervalsFiles"
12671 "DetectBeadSynthesisErrors"
12672 "DigitalExpression"
12673 "Drop-seq_alignment.sh"
12676 "GatherGeneGCLength"
12677 "GatherMolecularBarcodeDistributionByGene"
12678 "GatherReadQualityMetrics"
12681 "SelectCellsByNumTranscripts"
12682 "SingleCellRnaSeqMetricsCollector"
12683 "TagBamWithReadSequenceExtended"
12684 "TagReadWithGeneExon"
12685 "TagReadWithInterval"
12686 "TrimStartingSequence"
12687 "ValidateReference")))
12688 (for-each mkdir-p (list bin share lib))
12689 (install-file "dist/dropseq.jar" share)
12690 (for-each (lambda (script)
12691 (chmod script #o555)
12692 (install-file script bin))
12694 (substitute* (map (lambda (script)
12695 (string-append bin "/" script))
12697 (("^java") (which "java"))
12698 (("jar_deploy_dir=.*")
12699 (string-append "jar_deploy_dir=" share "\n"))))
12701 ;; FIXME: We do this after stripping jars because we don't want it to
12702 ;; copy all these jars and strip them. We only want to install
12703 ;; links. Arguably, this is a problem with the ant-build-system.
12704 (add-after 'strip-jar-timestamps 'install-links
12705 (lambda* (#:key outputs #:allow-other-keys)
12706 (let* ((out (assoc-ref outputs "out"))
12707 (share (string-append out "/share/java/"))
12708 (lib (string-append share "/lib/")))
12709 (for-each (lambda (jar)
12710 (symlink (readlink jar)
12711 (string-append lib (basename jar))))
12712 (find-files "jar/lib" "\\.jar$")))
12715 `(("jdk" ,icedtea-8)
12716 ("java-picard" ,java-picard-2.10.3)
12717 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12718 ("java-commons-math3" ,java-commons-math3)
12719 ("java-commons-jexl2" ,java-commons-jexl-2)
12720 ("java-commons-collections4" ,java-commons-collections4)
12721 ("java-commons-lang2" ,java-commons-lang)
12722 ("java-commons-io" ,java-commons-io)
12723 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12724 ("java-guava" ,java-guava)
12725 ("java-la4j" ,java-la4j)
12726 ("java-biojava-core" ,java-biojava-core-4.0)
12727 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12728 ("java-jdistlib" ,java-jdistlib)
12729 ("java-simple-xml" ,java-simple-xml)
12730 ("java-snakeyaml" ,java-snakeyaml)))
12733 ("java-testng" ,java-testng)))
12734 (home-page "http://mccarrolllab.com/dropseq/")
12735 (synopsis "Tools for Drop-seq analyses")
12736 (description "Drop-seq is a technology to enable biologists to
12737 analyze RNA expression genome-wide in thousands of individual cells at
12738 once. This package provides tools to perform Drop-seq analyses.")
12739 (license license:expat)))
12741 (define-public pigx-rnaseq
12743 (name "pigx-rnaseq")
12747 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12748 "releases/download/v" version
12749 "/pigx_rnaseq-" version ".tar.gz"))
12752 "05gn658zpj9xki5dbs728z9zxq1mcm25hkwr5vzwqxsfi15l5f2l"))))
12753 (build-system gnu-build-system)
12755 `(#:parallel-tests? #f ; not supported
12757 (modify-phases %standard-phases
12758 ;; "test.sh" runs STAR, which requires excessive amounts of memory.
12759 (add-after 'unpack 'disable-resource-intensive-test
12761 (substitute* "Makefile.in"
12762 (("(^ tests/test_trim_galore/test.sh).*" _ m) m)
12763 (("^ tests/test_multiqc/test.sh") "")
12764 (("^ test.sh") ""))
12768 ("snakemake" ,snakemake)
12770 ("multiqc" ,multiqc)
12772 ("trim-galore" ,trim-galore)
12774 ("samtools" ,samtools)
12775 ("bedtools" ,bedtools)
12776 ("r-minimal" ,r-minimal)
12777 ("r-rmarkdown" ,r-rmarkdown)
12778 ("r-ggplot2" ,r-ggplot2)
12779 ("r-ggrepel" ,r-ggrepel)
12780 ("r-gprofiler" ,r-gprofiler)
12781 ("r-deseq2" ,r-deseq2)
12783 ("r-knitr" ,r-knitr)
12784 ("r-pheatmap" ,r-pheatmap)
12785 ("r-corrplot" ,r-corrplot)
12786 ("r-reshape2" ,r-reshape2)
12787 ("r-plotly" ,r-plotly)
12788 ("r-scales" ,r-scales)
12789 ("r-summarizedexperiment" ,r-summarizedexperiment)
12790 ("r-crosstalk" ,r-crosstalk)
12791 ("r-tximport" ,r-tximport)
12792 ("r-rtracklayer" ,r-rtracklayer)
12793 ("r-rjson" ,r-rjson)
12795 ("ghc-pandoc" ,ghc-pandoc)
12796 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12797 ("python-wrapper" ,python-wrapper)
12798 ("python-pyyaml" ,python-pyyaml)))
12799 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12800 (synopsis "Analysis pipeline for RNA sequencing experiments")
12801 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
12802 reporting for RNA sequencing experiments. It is easy to use and produces high
12803 quality reports. The inputs are reads files from the sequencing experiment,
12804 and a configuration file which describes the experiment. In addition to
12805 quality control of the experiment, the pipeline produces a differential
12806 expression report comparing samples in an easily configurable manner.")
12807 (license license:gpl3+)))
12809 (define-public pigx-chipseq
12811 (name "pigx-chipseq")
12815 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
12816 "releases/download/v" version
12817 "/pigx_chipseq-" version ".tar.gz"))
12820 "0l3vd9xwqzap3mmyj8xwqp84kj7scbq308diqnwg2albphl75xqs"))))
12821 (build-system gnu-build-system)
12822 ;; parts of the tests rely on access to the network
12823 (arguments '(#:tests? #f))
12826 ("coreutils" ,coreutils)
12827 ("r-minimal" ,r-minimal)
12828 ("r-argparser" ,r-argparser)
12829 ("r-biocparallel" ,r-biocparallel)
12830 ("r-biostrings" ,r-biostrings)
12831 ("r-chipseq" ,r-chipseq)
12832 ("r-data-table" ,r-data-table)
12833 ("r-dplyr" ,r-dplyr)
12834 ("r-genomation" ,r-genomation)
12835 ("r-genomicalignments" ,r-genomicalignments)
12836 ("r-genomicranges" ,r-genomicranges)
12837 ("r-rsamtools" ,r-rsamtools)
12838 ("r-rtracklayer" ,r-rtracklayer)
12839 ("r-s4vectors" ,r-s4vectors)
12840 ("r-stringr" ,r-stringr)
12841 ("r-tibble" ,r-tibble)
12842 ("r-tidyr" ,r-tidyr)
12843 ("r-jsonlite" ,r-jsonlite)
12844 ("r-heatmaply" ,r-heatmaply)
12845 ("r-htmlwidgets" ,r-htmlwidgets)
12846 ("r-ggplot2" ,r-ggplot2)
12847 ("r-plotly" ,r-plotly)
12848 ("r-rmarkdown" ,r-rmarkdown)
12849 ("python-wrapper" ,python-wrapper)
12850 ("python-pyyaml" ,python-pyyaml)
12851 ("python-magic" ,python-magic)
12852 ("python-xlrd" ,python-xlrd)
12853 ("trim-galore" ,trim-galore)
12855 ("multiqc" ,multiqc)
12857 ("ghc-pandoc" ,ghc-pandoc)
12858 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12862 ("snakemake" ,snakemake)
12863 ("samtools" ,samtools)
12864 ("bedtools" ,bedtools)
12865 ("kentutils" ,kentutils)))
12867 `(("python-pytest" ,python-pytest)))
12868 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12869 (synopsis "Analysis pipeline for ChIP sequencing experiments")
12870 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
12871 calling and reporting for ChIP sequencing experiments. It is easy to use and
12872 produces high quality reports. The inputs are reads files from the sequencing
12873 experiment, and a configuration file which describes the experiment. In
12874 addition to quality control of the experiment, the pipeline enables to set up
12875 multiple peak calling analysis and allows the generation of a UCSC track hub
12876 in an easily configurable manner.")
12877 (license license:gpl3+)))
12879 (define-public pigx-bsseq
12881 (name "pigx-bsseq")
12885 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
12886 "releases/download/v" version
12887 "/pigx_bsseq-" version ".tar.gz"))
12890 "0l97wvkq4diq8lcarraj33bby1zzf0w804jwi8mlc5qddp8idwhy"))))
12891 (build-system gnu-build-system)
12894 (modify-phases %standard-phases
12895 (add-before 'check 'set-timezone
12896 ;; The readr package is picky about timezones.
12897 (lambda* (#:key inputs #:allow-other-keys)
12898 (setenv "TZ" "UTC+1")
12900 (string-append (assoc-ref inputs "tzdata")
12901 "/share/zoneinfo"))
12904 `(("tzdata" ,tzdata)))
12906 `(("coreutils" ,coreutils)
12909 ("r-minimal" ,r-minimal)
12910 ("r-annotationhub" ,r-annotationhub)
12912 ("r-genomation" ,r-genomation)
12913 ("r-methylkit" ,r-methylkit)
12914 ("r-rtracklayer" ,r-rtracklayer)
12915 ("r-rmarkdown" ,r-rmarkdown)
12916 ("r-bookdown" ,r-bookdown)
12917 ("r-ggplot2" ,r-ggplot2)
12918 ("r-ggbio" ,r-ggbio)
12919 ("ghc-pandoc" ,ghc-pandoc)
12920 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12921 ("python-wrapper" ,python-wrapper)
12922 ("python-pyyaml" ,python-pyyaml)
12923 ("snakemake" ,snakemake)
12924 ("bismark" ,bismark)
12927 ("trim-galore" ,trim-galore)
12928 ("cutadapt" ,cutadapt)
12929 ("samtools" ,samtools)))
12930 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12931 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
12932 (description "PiGx BSseq is a data processing pipeline for raw fastq read
12933 data of bisulfite experiments; it produces reports on aggregate methylation
12934 and coverage and can be used to produce information on differential
12935 methylation and segmentation.")
12936 (license license:gpl3+)))
12938 (define-public pigx-scrnaseq
12940 (name "pigx-scrnaseq")
12944 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/"
12945 "releases/download/v" version
12946 "/pigx_scrnaseq-" version ".tar.gz"))
12949 "131zarirv16w8653m0d66jgjnwqfsxqc0hix0rypssz4d83bl51j"))))
12950 (build-system gnu-build-system)
12952 `(#:configure-flags
12953 (list (string-append "PICARDJAR=" (assoc-ref %build-inputs "java-picard")
12954 "/share/java/picard.jar")
12955 (string-append "DROPSEQJAR=" (assoc-ref %build-inputs "dropseq-tools")
12956 "/share/java/dropseq.jar"))))
12958 `(("coreutils" ,coreutils)
12960 ("dropseq-tools" ,dropseq-tools)
12962 ("java-picard" ,java-picard-2.10.3) ; same as for dropseq
12963 ("java" ,icedtea-8)
12964 ("python-wrapper" ,python-wrapper)
12965 ("python-pyyaml" ,python-pyyaml)
12966 ("python-pandas" ,python-pandas)
12967 ("python-magic" ,python-magic)
12968 ("python-numpy" ,python-numpy)
12969 ("python-loompy" ,python-loompy)
12970 ("ghc-pandoc" ,ghc-pandoc)
12971 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12972 ("samtools" ,samtools)
12973 ("snakemake" ,snakemake)
12975 ("r-minimal" ,r-minimal)
12976 ("r-argparser" ,r-argparser)
12977 ("r-cowplot" ,r-cowplot)
12978 ("r-data-table" ,r-data-table)
12979 ("r-delayedarray" ,r-delayedarray)
12980 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
12981 ("r-dplyr" ,r-dplyr)
12982 ("r-dropbead" ,r-dropbead)
12984 ("r-genomicalignments" ,r-genomicalignments)
12985 ("r-genomicfiles" ,r-genomicfiles)
12986 ("r-genomicranges" ,r-genomicranges)
12987 ("r-ggplot2" ,r-ggplot2)
12988 ("r-hdf5array" ,r-hdf5array)
12989 ("r-pheatmap" ,r-pheatmap)
12990 ("r-rmarkdown" ,r-rmarkdown)
12991 ("r-rsamtools" ,r-rsamtools)
12992 ("r-rtracklayer" ,r-rtracklayer)
12993 ("r-rtsne" ,r-rtsne)
12994 ("r-scater" ,r-scater)
12995 ("r-scran" ,r-scran)
12996 ("r-singlecellexperiment" ,r-singlecellexperiment)
12997 ("r-stringr" ,r-stringr)
12998 ("r-yaml" ,r-yaml)))
12999 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13000 (synopsis "Analysis pipeline for single-cell RNA sequencing experiments")
13001 (description "PiGX scRNAseq is an analysis pipeline for preprocessing and
13002 quality control for single cell RNA sequencing experiments. The inputs are
13003 read files from the sequencing experiment, and a configuration file which
13004 describes the experiment. It produces processed files for downstream analysis
13005 and interactive quality reports. The pipeline is designed to work with UMI
13007 (license license:gpl3+)))
13009 (define-public pigx
13015 (uri (string-append "https://github.com/BIMSBbioinfo/pigx/"
13016 "releases/download/v" version
13017 "/pigx-" version ".tar.gz"))
13020 "1i5njdy1clj5ncw45d16p7mwmqvb1ilikl9n797pxklc3f4s7mq7"))))
13021 (build-system gnu-build-system)
13023 `(("python" ,python)
13024 ("pigx-bsseq" ,pigx-bsseq)
13025 ("pigx-chipseq" ,pigx-chipseq)
13026 ("pigx-rnaseq" ,pigx-rnaseq)
13027 ("pigx-scrnaseq" ,pigx-scrnaseq)))
13028 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13029 (synopsis "Analysis pipelines for genomics")
13030 (description "PiGx is a collection of genomics pipelines. It includes the
13031 following pipelines:
13034 @item PiGx BSseq for raw fastq read data of bisulfite experiments
13035 @item PiGx RNAseq for RNAseq samples
13036 @item PiGx scRNAseq for single cell dropseq analysis
13037 @item PiGx ChIPseq for reads from ChIPseq experiments
13040 All pipelines are easily configured with a simple sample sheet and a
13041 descriptive settings file. The result is a set of comprehensive, interactive
13042 HTML reports with interesting findings about your samples.")
13043 (license license:gpl3+)))
13045 (define-public genrich
13051 (uri (git-reference
13052 (url "https://github.com/jsh58/Genrich.git")
13053 (commit (string-append "v" version))))
13056 "0x0q6z0208n3cxzqjla4rgjqpyqgwpmz27852lcvzkzaigymq4zp"))))
13057 (build-system gnu-build-system)
13059 `(#:tests? #f ; there are none
13061 (modify-phases %standard-phases
13062 (delete 'configure)
13064 (lambda* (#:key outputs #:allow-other-keys)
13065 (install-file "Genrich" (string-append (assoc-ref outputs "out") "/bin"))
13069 (home-page "https://github.com/jsh58/Genrich")
13070 (synopsis "Detecting sites of genomic enrichment")
13071 (description "Genrich is a peak-caller for genomic enrichment
13072 assays (e.g. ChIP-seq, ATAC-seq). It analyzes alignment files generated
13073 following the assay and produces a file detailing peaks of significant
13075 (license license:expat)))
13077 (define-public mantis
13078 (let ((commit "4ffd171632c2cb0056a86d709dfd2bf21bc69b84")
13082 (version (git-version "0" revision commit))
13085 (uri (git-reference
13086 (url "https://github.com/splatlab/mantis.git")
13088 (file-name (git-file-name name version))
13091 "0iqbr0dhmlc8mzpirmm2s4pkzkwdgrcx50yx6cv3wlr2qi064p55"))))
13092 (build-system cmake-build-system)
13093 (arguments '(#:tests? #f)) ; there are none
13095 `(("sdsl-lite" ,sdsl-lite)
13096 ("openssl" ,openssl)
13098 (home-page "https://github.com/splatlab/mantis")
13099 (synopsis "Large-scale sequence-search index data structure")
13100 (description "Mantis is a space-efficient data structure that can be
13101 used to index thousands of raw-read genomics experiments and facilitate
13102 large-scale sequence searches on those experiments. Mantis uses counting
13103 quotient filters instead of Bloom filters, enabling rapid index builds and
13104 queries, small indexes, and exact results, i.e., no false positives or
13105 negatives. Furthermore, Mantis is also a colored de Bruijn graph
13106 representation, so it supports fast graph traversal and other topological
13107 analyses in addition to large-scale sequence-level searches.")
13108 ;; uses __uint128_t and inline assembly
13109 (supported-systems '("x86_64-linux"))
13110 (license license:bsd-3))))
13112 (define-public r-diversitree
13114 (name "r-diversitree")
13119 (uri (cran-uri "diversitree" version))
13122 "0gh4rcrp0an3jh8915i1fsxlgyfk7njywgbd5ln5r2jhr085kpz7"))))
13123 (build-system r-build-system)
13125 `(("gfortran" ,gfortran)))
13126 (inputs `(("fftw" ,fftw) ("gsl" ,gsl)))
13129 ("r-desolve" ,r-desolve)
13131 ("r-suplex" ,r-subplex)))
13132 (home-page "https://www.zoology.ubc.ca/prog/diversitree")
13133 (synopsis "Comparative 'phylogenetic' analyses of diversification")
13134 (description "This package contains a number of comparative \"phylogenetic\"
13135 methods, mostly focusing on analysing diversification and character evolution.
13136 Contains implementations of \"BiSSE\" (Binary State Speciation and Extinction)
13137 and its unresolved tree extensions, \"MuSSE\" (Multiple State Speciation and
13138 Extinction), \"QuaSSE\", \"GeoSSE\", and \"BiSSE-ness\" Other included methods
13139 include Markov models of discrete and continuous trait evolution and constant
13140 rate speciation and extinction.")
13141 (license license:gpl2+)))
13143 (define-public sjcount
13144 ;; There is no tag for version 3.2, nor is there a release archive.
13145 (let ((commit "292d3917cadb3f6834c81e509c30e61cd7ead6e5")
13149 (version (git-version "3.2" revision commit))
13152 (uri (git-reference
13153 (url "https://github.com/pervouchine/sjcount-full.git")
13155 (file-name (string-append name "-" version "-checkout"))
13158 "0gdgj35j249f04rqgq8ymcc1xg1vi9kzbajnjqpaq2wpbh8bl234"))))
13159 (build-system gnu-build-system)
13161 `(#:tests? #f ; requires a 1.4G test file
13163 (list (string-append "SAMTOOLS_DIR="
13164 (assoc-ref %build-inputs "samtools")
13167 (modify-phases %standard-phases
13168 (replace 'configure
13169 (lambda* (#:key inputs #:allow-other-keys)
13170 (substitute* "makefile"
13171 (("-I \\$\\{SAMTOOLS_DIR\\}")
13172 (string-append "-I" (assoc-ref inputs "samtools")
13173 "/include/samtools"))
13174 (("-lz ") "-lz -lpthread "))
13177 (lambda* (#:key outputs #:allow-other-keys)
13178 (for-each (lambda (tool)
13180 (string-append (assoc-ref outputs "out")
13182 '("j_count" "b_count" "sjcount"))
13185 `(("samtools" ,samtools-0.1)
13187 (home-page "https://github.com/pervouchine/sjcount-full/")
13188 (synopsis "Annotation-agnostic splice junction counting pipeline")
13189 (description "Sjcount is a utility for fast quantification of splice
13190 junctions in RNA-seq data. It is annotation-agnostic and offset-aware. This
13191 version does count multisplits.")
13192 (license license:gpl3+))))
13194 (define-public minimap2
13201 (uri (string-append "https://github.com/lh3/minimap2/"
13202 "releases/download/v" version "/"
13203 "minimap2-" version ".tar.bz2"))
13206 "080w9066irkbhbyr4nmf19pzkdd2s4v31hpzlajgq2y0drr6zcsj"))))
13207 (build-system gnu-build-system)
13209 `(#:tests? #f ; there are none
13212 (let ((system ,(or (%current-target-system)
13213 (%current-system))))
13215 ((string-prefix? "x86_64" system)
13217 ((or (string-prefix? "armhf" system)
13218 (string-prefix? "aarch64" system))
13220 (_ "sse2only=1"))))
13222 (modify-phases %standard-phases
13223 (delete 'configure)
13225 (lambda* (#:key outputs #:allow-other-keys)
13226 (let* ((out (assoc-ref outputs "out"))
13227 (bin (string-append out "/bin"))
13228 (man (string-append out "/share/man/man1")))
13229 (install-file "minimap2" bin)
13231 (install-file "minimap2.1" man))
13235 (home-page "https://lh3.github.io/minimap2/")
13236 (synopsis "Pairwise aligner for genomic and spliced nucleotide sequences")
13237 (description "Minimap2 is a versatile sequence alignment program that
13238 aligns DNA or mRNA sequences against a large reference database. Typical use
13242 @item mapping PacBio or Oxford Nanopore genomic reads to the human genome;
13243 @item finding overlaps between long reads with error rate up to ~15%;
13244 @item splice-aware alignment of PacBio Iso-Seq or Nanopore cDNA or Direct RNA
13245 reads against a reference genome;
13246 @item aligning Illumina single- or paired-end reads;
13247 @item assembly-to-assembly alignment;
13248 @item full-genome alignment between two closely related species with
13249 divergence below ~15%.
13251 (license license:expat)))
13253 (define-public r-circus
13260 (uri (git-reference
13261 (url "https://github.com/BIMSBbioinfo/ciRcus.git")
13262 (commit (string-append "v" version))))
13263 (file-name (git-file-name name version))
13266 "0jhjn3ilb057hbf6yzrihj13ifxxs32y7nkby8l3lkm28dg4p97h"))))
13267 (build-system r-build-system)
13269 `(("r-annotationdbi" ,r-annotationdbi)
13270 ("r-annotationhub" ,r-annotationhub)
13271 ("r-biomart" ,r-biomart)
13272 ("r-data-table" ,r-data-table)
13274 ("r-genomicfeatures" ,r-genomicfeatures)
13275 ("r-genomicranges" ,r-genomicranges)
13276 ("r-ggplot2" ,r-ggplot2)
13278 ("r-iranges" ,r-iranges)
13279 ("r-rcolorbrewer" ,r-rcolorbrewer)
13280 ("r-rmysql" ,r-rmysql)
13281 ("r-s4vectors" ,r-s4vectors)
13282 ("r-stringr" ,r-stringr)
13283 ("r-summarizedexperiment" ,r-summarizedexperiment)))
13285 `(("r-knitr" ,r-knitr)))
13286 (home-page "https://github.com/BIMSBbioinfo/ciRcus")
13287 (synopsis "Annotation, analysis and visualization of circRNA data")
13288 (description "Circus is an R package for annotation, analysis and
13289 visualization of circRNA data. Users can annotate their circRNA candidates
13290 with host genes, gene featrues they are spliced from, and discriminate between
13291 known and yet unknown splice junctions. Circular-to-linear ratios of circRNAs
13292 can be calculated, and a number of descriptive plots easily generated.")
13293 (license license:artistic2.0)))
13295 (define-public r-loomr
13296 (let ((commit "df0144bd2bbceca6fadef9edc1bbc5ca672d4739")
13300 (version (git-version "0.2.0" revision commit))
13304 (uri (git-reference
13305 (url "https://github.com/mojaveazure/loomR.git")
13307 (file-name (git-file-name name version))
13310 "1b1g4dlmfdyhn56bz1mkh9ymirri43wiz7rjhs7py3y7bdw1s3yr"))))
13311 (build-system r-build-system)
13314 ("r-hdf5r" ,r-hdf5r)
13315 ("r-iterators" ,r-iterators)
13316 ("r-itertools" ,r-itertools)
13317 ("r-matrix" ,r-matrix)))
13318 (home-page "https://github.com/mojaveazure/loomR")
13319 (synopsis "R interface for loom files")
13320 (description "This package provides an R interface to access, create,
13321 and modify loom files. loomR aims to be completely compatible with loompy.")
13322 (license license:gpl3))))
13324 (define-public gffread
13325 ;; We cannot use the tagged release because it is not in sync with gclib.
13326 ;; See https://github.com/gpertea/gffread/issues/26
13327 (let ((commit "ba7535fcb3cea55a6e5a491d916e93b454e87fd0")
13331 (version (git-version "0.9.12" revision commit))
13335 (uri (git-reference
13336 (url "https://github.com/gpertea/gffread.git")
13338 (file-name (git-file-name name version))
13341 "1dl2nbcg96lxpd0drg48ssa8343nf7pw9s9mkrc4mjjmfwsin3ki"))))
13342 (build-system gnu-build-system)
13344 `(#:tests? #f ; no check target
13346 (list "GCLDIR=gclib")
13348 (modify-phases %standard-phases
13349 (delete 'configure)
13350 (add-after 'unpack 'copy-gclib-source
13351 (lambda* (#:key inputs #:allow-other-keys)
13353 (copy-recursively (assoc-ref inputs "gclib-source") "gclib")
13355 ;; There is no install target
13357 (lambda* (#:key outputs #:allow-other-keys)
13358 (let* ((out (assoc-ref outputs "out"))
13359 (bin (string-append out "/bin")))
13360 (install-file "gffread" bin))
13364 ,(let ((version "0.10.3")
13365 (commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13369 (uri (git-reference
13370 (url "https://github.com/gpertea/gclib.git")
13372 (file-name (git-file-name "gclib" version))
13375 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13376 (home-page "https://github.com/gpertea/gffread/")
13377 (synopsis "Parse and convert GFF/GTF files")
13379 "This package provides a GFF/GTF file parsing utility providing format
13380 conversions, region filtering, FASTA sequence extraction and more.")
13381 ;; gffread is under Expat, but gclib is under Artistic 2.0
13382 (license (list license:expat
13383 license:artistic2.0)))))
13385 (define-public find-circ
13386 ;; The last release was in 2015. The license was clarified in 2017, so we
13387 ;; take the latest commit.
13388 (let ((commit "8655dca54970fcf7e92e22fbf57e1188724dda7d")
13392 (version (git-version "1.2" revision commit))
13396 (uri (git-reference
13397 (url "https://github.com/marvin-jens/find_circ.git")
13399 (file-name (git-file-name name version))
13402 "0p77pbqbclqr4srms34y1b9b4njybfpjiknc11ki84f3p8skb3cg"))))
13403 (build-system gnu-build-system)
13405 `(#:tests? #f ; there are none
13407 ;; There is no actual build system.
13408 (modify-phases %standard-phases
13409 (delete 'configure)
13412 (lambda* (#:key outputs #:allow-other-keys)
13413 (let* ((out (assoc-ref outputs "out"))
13414 (bin (string-append out "/bin"))
13415 (path (getenv "PYTHONPATH")))
13416 (for-each (lambda (script)
13417 (install-file script bin)
13418 (wrap-program (string-append bin "/" script)
13419 `("PYTHONPATH" ":" prefix (,path))))
13424 "unmapped2anchors.py")))
13427 `(("python2" ,python-2)
13428 ("python2-pysam" ,python2-pysam)
13429 ("python2-numpy" ,python2-numpy)))
13430 (home-page "https://github.com/marvin-jens/find_circ")
13431 (synopsis "circRNA detection from RNA-seq reads")
13432 (description "This package provides tools to detect head-to-tail
13433 spliced (back-spliced) sequencing reads, indicative of circular RNA (circRNA)
13435 (license license:gpl3))))
13437 (define-public python-scanpy
13439 (name "python-scanpy")
13444 (uri (pypi-uri "scanpy" version))
13447 "1ak7bxms5a0yvf65prppq2g38clkv7c7jnjbnfpkh3xxv7q512jz"))))
13448 (build-system python-build-system)
13450 `(("python-anndata" ,python-anndata)
13451 ("python-igraph" ,python-igraph)
13452 ("python-numba" ,python-numba)
13453 ("python-joblib" ,python-joblib)
13454 ("python-natsort" ,python-natsort)
13455 ("python-networkx" ,python-networkx)
13456 ("python-statsmodels" ,python-statsmodels)
13457 ("python-scikit-learn" ,python-scikit-learn)
13458 ("python-matplotlib" ,python-matplotlib)
13459 ("python-pandas" ,python-pandas)
13460 ("python-scipy" ,python-scipy)
13461 ("python-seaborn" ,python-seaborn)
13462 ("python-h5py" ,python-h5py)
13463 ("python-tables" ,python-tables)))
13464 (home-page "http://github.com/theislab/scanpy")
13465 (synopsis "Single-Cell Analysis in Python.")
13466 (description "Scanpy is a scalable toolkit for analyzing single-cell gene
13467 expression data. It includes preprocessing, visualization, clustering,
13468 pseudotime and trajectory inference and differential expression testing. The
13469 Python-based implementation efficiently deals with datasets of more than one
13471 (license license:bsd-3)))
13473 (define-public gffcompare
13474 (let ((commit "be56ef4349ea3966c12c6397f85e49e047361c41")
13477 (name "gffcompare")
13478 (version (git-version "0.10.15" revision commit))
13482 (uri (git-reference
13483 (url "https://github.com/gpertea/gffcompare/")
13485 (file-name (git-file-name name version))
13487 (base32 "0cp5qpxdhw4mxpya5dld8wi3jk00zyklm6rcri426wydinrnfmkg"))))
13488 (build-system gnu-build-system)
13490 `(#:tests? #f ; no check target
13492 (modify-phases %standard-phases
13493 (delete 'configure)
13494 (add-before 'build 'copy-gclib-source
13495 (lambda* (#:key inputs #:allow-other-keys)
13498 (assoc-ref inputs "gclib-source") "../gclib")
13501 (lambda* (#:key outputs #:allow-other-keys)
13502 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
13503 (install-file "gffcompare" bin)
13506 `(("gclib-source" ; see 'README.md' of gffcompare
13507 ,(let ((commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13510 (version (git-version "0.10.3" revision commit)))
13513 (uri (git-reference
13514 (url "https://github.com/gpertea/gclib/")
13516 (file-name (git-file-name name version))
13518 (base32 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13519 (home-page "https://github.com/gpertea/gffcompare/")
13520 (synopsis "Tool for comparing or classifing transcripts of RNA-Seq")
13522 "@code{gffcompare} is a tool that can:
13524 @item compare and evaluate the accuracy of RNA-Seq transcript assemblers
13525 (Cufflinks, Stringtie);
13526 @item collapse (merge) duplicate transcripts from multiple GTF/GFF3 files (e.g.
13527 resulted from assembly of different samples);
13528 @item classify transcripts from one or multiple GTF/GFF3 files as they relate to
13529 reference transcripts provided in a annotation file (also in GTF/GFF3 format).
13533 license:expat ;license for gffcompare
13534 license:artistic2.0))))) ;license for gclib
13536 (define-public python-intervaltree
13538 (name "python-intervaltree")
13543 (uri (pypi-uri "intervaltree" version))
13546 "02w191m9zxkcjqr1kv2slxvhymwhj3jnsyy3a28b837pi15q19dc"))))
13547 (build-system python-build-system)
13548 ;; FIXME: error when collecting tests
13549 (arguments '(#:tests? #f))
13551 `(("python-sortedcontainers" ,python-sortedcontainers)))
13553 `(("python-pytest" ,python-pytest)))
13554 (home-page "https://github.com/chaimleib/intervaltree")
13555 (synopsis "Editable interval tree data structure")
13557 "This package provides a mutable, self-balancing interval tree
13558 implementation for Python. Queries may be by point, by range overlap, or by
13559 range envelopment. This library was designed to allow tagging text and time
13560 intervals, where the intervals include the lower bound but not the upper
13562 (license license:asl2.0)))
13564 (define-public python-pypairix
13566 (name "python-pypairix")
13571 (uri (pypi-uri "pypairix" version))
13574 "0zs92b74s5v4xy2h16s15f3z6l4nnbw8x8zyif7xx5xpafjn0xss"))))
13575 (build-system python-build-system)
13576 ;; FIXME: the tests fail because test.support cannot be loaded:
13577 ;; ImportError: cannot import name 'support'
13578 (arguments '(#:tests? #f))
13581 (home-page "https://github.com/4dn-dcic/pairix")
13582 (synopsis "Support for querying pairix-indexed bgzipped text files")
13584 "Pypairix is a Python module for fast querying on a pairix-indexed
13585 bgzipped text file that contains a pair of genomic coordinates per line.")
13586 (license license:expat)))
13588 (define-public python-pyfaidx
13590 (name "python-pyfaidx")
13591 (version "0.5.4.2")
13595 (uri (pypi-uri "pyfaidx" version))
13598 "0y5zyjksj1rdglj601xd2bbni5abhdh622y3ck76chyzxz9z4rx8"))))
13599 (build-system python-build-system)
13601 `(("python-setuptools" ,python-setuptools)
13602 ("python-six" ,python-six)))
13603 (home-page "http://mattshirley.com")
13604 (synopsis "Random access to fasta subsequences")
13606 "This package provides procedures for efficient pythonic random access to
13607 fasta subsequences.")
13608 (license license:bsd-3)))
13610 (define-public python-cooler
13612 (name "python-cooler")
13617 (uri (pypi-uri "cooler" version))
13620 "08k5nxnxa6qsbk15z5z0q01n28042k87wi4905hh95rzqib15mhx"))))
13621 (build-system python-build-system)
13623 `(("python-biopython" ,python-biopython)
13624 ("python-click" ,python-click)
13625 ("python-cytoolz" ,python-cytoolz)
13626 ("python-dask" ,python-dask)
13627 ("python-h5py" ,python-h5py)
13628 ("python-multiprocess" ,python-multiprocess)
13629 ("python-pandas" ,python-pandas)
13630 ("python-pyfaidx" ,python-pyfaidx)
13631 ("python-pypairix" ,python-pypairix)
13632 ("python-pysam" ,python-pysam)
13633 ("python-scipy" ,python-scipy)))
13635 `(("python-mock" ,python-mock)
13636 ("python-nose" ,python-nose)
13637 ("python-numpydoc" ,python-numpydoc)
13638 ("python-sphinx" ,python-sphinx)))
13639 (home-page "https://github.com/mirnylab/cooler")
13640 (synopsis "Sparse binary format for genomic interaction matrices")
13642 "Cooler is a support library for a sparse, compressed, binary persistent
13643 storage format, called @code{cool}, used to store genomic interaction data,
13644 such as Hi-C contact matrices.")
13645 (license license:bsd-3)))
13647 (define-public python-hicexplorer
13649 (name "python-hicexplorer")
13653 ;; The latest version is not available on Pypi.
13655 (uri (git-reference
13656 (url "https://github.com/deeptools/HiCExplorer.git")
13658 (file-name (git-file-name name version))
13661 "0q5gpbzmrkvygqgw524q36b4nrivcmyi5v194vsx0qw7b3gcmq08"))))
13662 (build-system python-build-system)
13665 (modify-phases %standard-phases
13666 (add-after 'unpack 'loosen-up-requirements
13668 (substitute* "setup.py"
13672 `(("python-biopython" ,python-biopython)
13673 ("python-configparser" ,python-configparser)
13674 ("python-cooler" ,python-cooler)
13675 ("python-future" ,python-future)
13676 ("python-intervaltree" ,python-intervaltree)
13677 ("python-jinja2" ,python-jinja2)
13678 ("python-matplotlib" ,python-matplotlib)
13679 ("python-numpy" ,python-numpy)
13680 ("python-pandas" ,python-pandas)
13681 ("python-pybigwig" ,python-pybigwig)
13682 ("python-pysam" ,python-pysam)
13683 ("python-scipy" ,python-scipy)
13684 ("python-six" ,python-six)
13685 ("python-tables" ,python-tables)
13686 ("python-unidecode" ,python-unidecode)))
13687 (home-page "http://hicexplorer.readthedocs.io")
13688 (synopsis "Process, analyze and visualize Hi-C data")
13690 "HiCExplorer is a powerful and easy to use set of tools to process,
13691 normalize and visualize Hi-C data. HiCExplorer facilitates the creation of
13692 contact matrices, correction of contacts, TAD detection, A/B compartments,
13693 merging, reordering or chromosomes, conversion from different formats
13694 including cooler and detection of long-range contacts. Moreover, it allows
13695 the visualization of multiple contact matrices along with other types of data
13696 like genes, compartments, ChIP-seq coverage tracks (and in general any type of
13697 genomic scores), long range contacts and the visualization of viewpoints.")
13698 (license license:gpl3)))
13700 (define-public python-pygenometracks
13702 (name "python-pygenometracks")
13707 (uri (pypi-uri "pyGenomeTracks" version))
13710 "1fws6bqsyy9kj3qiabhkqx4wd4i775gsxnhszqd3zg7w67sc1ic5"))))
13711 (build-system python-build-system)
13713 `(("python-configparser" ,python-configparser)
13714 ("python-future" ,python-future)
13715 ("python-hicexplorer" ,python-hicexplorer)
13716 ("python-intervaltree" ,python-intervaltree)
13717 ("python-matplotlib" ,python-matplotlib)
13718 ("python-numpy" ,python-numpy)
13719 ("python-pybigwig" ,python-pybigwig)))
13721 `(("python-pytest" ,python-pytest)))
13722 (home-page "https://pygenometracks.readthedocs.io")
13723 (synopsis "Program and library to plot beautiful genome browser tracks")
13725 "This package aims to produce high-quality genome browser tracks that
13726 are highly customizable. Currently, it is possible to plot: bigwig, bed (many
13727 options), bedgraph, links (represented as arcs), and Hi-C matrices.
13728 pyGenomeTracks can make plots with or without Hi-C data.")
13729 (license license:gpl3+)))
13731 (define-public python-hic2cool
13733 (name "python-hic2cool")
13738 (uri (pypi-uri "hic2cool" version))
13741 "0xy6mhfns2lzib1kcr6419jjp6pmh0qx8z8na55lmiwn0ds8q9cl"))))
13742 (build-system python-build-system)
13743 (arguments '(#:tests? #f)) ; no tests included
13745 `(("python-cooler" ,python-cooler)))
13746 (home-page "https://github.com/4dn-dcic/hic2cool")
13747 (synopsis "Converter for .hic and .cool files")
13749 "This package provides a converter between @code{.hic} files (from
13750 juicer) and single-resolution or multi-resolution @code{.cool} files (for
13751 cooler). Both @code{hic} and @code{cool} files describe Hi-C contact
13753 (license license:expat)))
13755 (define-public r-pore
13763 (string-append "mirror://sourceforge/rpore/" version
13764 "/poRe_" version ".tar.gz"))
13766 (base32 "0pih9nljbv8g4x8rkk29i7aqq681b782r5s5ynp4nw9yzqnmmksv"))))
13767 (properties `((upstream-name . "poRe")))
13768 (build-system r-build-system)
13770 `(("r-bit64" ,r-bit64)
13771 ("r-data-table" ,r-data-table)
13772 ("r-rhdf5" ,r-rhdf5)
13773 ("r-shiny" ,r-shiny)
13774 ("r-svdialogs" ,r-svdialogs)))
13775 (home-page "https://sourceforge.net/projects/rpore/")
13776 (synopsis "Visualize Nanopore sequencing data")
13778 "This package provides graphical user interfaces to organize and visualize Nanopore
13780 ;; This is free software but the license variant is unclear:
13781 ;; <https://github.com/mw55309/poRe_docs/issues/10>.
13782 (license license:bsd-3)))
13784 (define-public r-xbioc
13785 (let ((revision "1")
13786 (commit "f798c187e376fd1ba27abd559f47bbae7e3e466b"))
13789 (version (git-version "0.1.15" revision commit))
13792 (uri (git-reference
13793 (url "https://github.com/renozao/xbioc.git")
13795 (file-name (git-file-name name version))
13798 "03hffh2f6z71y6l6dqpa5cql3hdaw7zigdi8sm2dzgx379k9rgrr"))))
13799 (build-system r-build-system)
13801 `(("r-annotationdbi" ,r-annotationdbi)
13802 ("r-assertthat" ,r-assertthat)
13803 ("r-biobase" ,r-biobase)
13804 ("r-biocinstaller" ,r-biocinstaller)
13805 ("r-digest" ,r-digest)
13806 ("r-pkgmaker" ,r-pkgmaker)
13808 ("r-reshape2" ,r-reshape2)
13809 ("r-stringr" ,r-stringr)))
13810 (home-page "https://github.com/renozao/xbioc/")
13811 (synopsis "Extra base functions for Bioconductor")
13812 (description "This package provides extra utility functions to perform
13813 common tasks in the analysis of omics data, leveraging and enhancing features
13814 provided by Bioconductor packages.")
13815 (license license:gpl3+))))
13817 (define-public r-cssam
13818 (let ((revision "1")
13819 (commit "9ec58c982fa551af0d80b1a266890d92954833f2"))
13822 (version (git-version "1.4" revision commit))
13825 (uri (git-reference
13826 (url "https://github.com/shenorrLab/csSAM.git")
13828 (file-name (git-file-name name version))
13831 "128syf9v39gk0z3ip000qpsjbg6l1siyq6c8b0hz41dzg5achyb3"))))
13832 (build-system r-build-system)
13834 `(("r-formula" ,r-formula)
13835 ("r-ggplot2" ,r-ggplot2)
13836 ("r-pkgmaker" ,r-pkgmaker)
13838 ("r-rngtools" ,r-rngtools)
13839 ("r-scales" ,r-scales)))
13840 (home-page "https://github.com/shenorrLab/csSAM/")
13841 (synopsis "Cell type-specific statistical analysis of microarray")
13842 (description "This package implements the method csSAM that computes
13843 cell-specific differential expression from measured cell proportions using
13846 (license license:lgpl2.1+))))
13848 (define-public r-bseqsc
13849 (let ((revision "1")
13850 (commit "fef3f3e38dcf3df37103348b5780937982b43b98"))
13853 (version (git-version "1.0" revision commit))
13856 (uri (git-reference
13857 (url "https://github.com/shenorrLab/bseqsc.git")
13859 (file-name (git-file-name name version))
13862 "1prw13wa20f7wlc3gkkls66n1kxz8d28qrb8icfqdwdnnv8w5qg8"))))
13863 (build-system r-build-system)
13865 `(("r-abind" ,r-abind)
13866 ("r-annotationdbi" ,r-annotationdbi)
13867 ("r-biobase" ,r-biobase)
13868 ("r-cssam" ,r-cssam)
13869 ("r-dplyr" ,r-dplyr)
13870 ("r-e1071" ,r-e1071)
13871 ("r-edger" ,r-edger)
13872 ("r-ggplot2" ,r-ggplot2)
13874 ("r-openxlsx" ,r-openxlsx)
13875 ("r-pkgmaker" ,r-pkgmaker)
13877 ("r-preprocesscore" ,r-preprocesscore)
13878 ("r-rngtools" ,r-rngtools)
13879 ("r-scales" ,r-scales)
13880 ("r-stringr" ,r-stringr)
13881 ("r-xbioc" ,r-xbioc)))
13882 (home-page "https://github.com/shenorrLab/bseqsc")
13883 (synopsis "Deconvolution of bulk sequencing experiments using single cell data")
13884 (description "BSeq-sc is a bioinformatics analysis pipeline that
13885 leverages single-cell sequencing data to estimate cell type proportion and
13886 cell type-specific gene expression differences from RNA-seq data from bulk
13887 tissue samples. This is a companion package to the publication \"A
13888 single-cell transcriptomic map of the human and mouse pancreas reveals inter-
13889 and intra-cell population structure.\" Baron et al. Cell Systems (2016)
13890 @url{https://www.ncbi.nlm.nih.gov/pubmed/27667365}.")
13891 (license license:gpl2+))))
13893 (define-public porechop
13894 ;; The recommended way to install is to clone the git repository
13895 ;; https://github.com/rrwick/Porechop#installation
13896 (let ((commit "289d5dca4a5fc327f97b3f8cecb68ecaf1014861")
13900 (version (git-version "0.2.3" revision commit))
13904 (uri (git-reference
13905 (url "https://github.com/rrwick/Porechop.git")
13907 (file-name (git-file-name name version))
13909 (base32 "05ps43gig0d3ia9x5lj84lb00hbsl6ba9n7y7jz927npxbr2ym23"))))
13910 (build-system python-build-system)
13911 (home-page "https://github.com/rrwick/porechop")
13912 (synopsis "Finding, trimming or splitting adapters, in Oxford Nanopore reads")
13914 "The porechop package is a tool for finding and removing adapters from Oxford
13915 Nanopore reads. Adapters on the ends of reads are trimmed off, and when a read
13916 has an adapter in its middle, it is treated as chimeric and chopped into
13917 separate reads. Porechop performs thorough alignments to effectively find
13918 adapters, even at low sequence identity. Porechop also supports demultiplexing
13919 of Nanopore reads that were barcoded with the Native Barcoding Kit, PCR
13920 Barcoding Kit or Rapid Barcoding Kit.")
13921 (license license:gpl3+))))
13923 (define-public poretools
13924 ;; The latest release was in 2016 and the latest commit is from 2017
13925 ;; the recommended way to install is to clone the git repository
13926 ;; https://poretools.readthedocs.io/en/latest/content/installation.html
13927 (let ((commit "e426b1f09e86ac259a00c261c79df91510777407")
13931 (version (git-version "0.6.0" revision commit))
13935 (uri (git-reference
13936 (url "https://github.com/arq5x/poretools.git")
13938 (file-name (git-file-name name version))
13940 (base32 "0bglj833wxpp3cq430p1d3xp085ls221js2y90w7ir2x5ay8l7am"))))
13941 (build-system python-build-system)
13942 ;; requires python >=2.7, <3.0, and the same for python dependencies
13943 (arguments `(#:python ,python-2))
13947 `(("python-dateutil" ,python2-dateutil)
13948 ("python-h5py" ,python2-h5py)
13949 ("python-matplotlib" ,python2-matplotlib)
13950 ("python-pandas" ,python2-pandas)
13951 ("python-seaborn" ,python2-seaborn)))
13952 (home-page "https://poretools.readthedocs.io")
13953 (synopsis "Toolkit for working with nanopore sequencing data")
13955 "The MinION from Oxford Nanopore Technologies is a nanopore sequencer.
13956 This @code{poretools} package is a flexible toolkit for exploring datasets
13957 generated by nanopore sequencing devices for the purposes of quality control and
13958 downstream analysis. Poretools operates directly on the native FAST5, a variant
13959 of the Hierarchical Data Format (HDF5) standard.")
13960 (license license:expat))))
13962 (define-public r-absfiltergsea
13964 (name "r-absfiltergsea")
13969 (uri (cran-uri "AbsFilterGSEA" version))
13971 (base32 "15srxkxsvn38kd5frdrwfdf0ad8gskrd0h01wmdf9hglq8fjrp7w"))))
13972 (properties `((upstream-name . "AbsFilterGSEA")))
13973 (build-system r-build-system)
13975 `(("r-biobase" ,r-biobase)
13976 ("r-deseq" ,r-deseq)
13977 ("r-limma" ,r-limma)
13979 ("r-rcpparmadillo" ,r-rcpparmadillo)))
13980 (home-page "https://cran.r-project.org/web/packages/AbsFilterGSEA/")
13981 (synopsis "Improved false positive control of gene-permuting with absolute filtering")
13983 "This package provides a function that performs gene-permuting of a gene-set
13984 enrichment analysis (GSEA) calculation with or without the absolute filtering.
13985 Without filtering, users can perform (original) two-tailed or one-tailed
13987 (license license:gpl2)))
13989 (define-public jamm
13992 (version "1.0.7.5")
13996 (uri (git-reference
13997 (url "https://github.com/mahmoudibrahim/JAMM.git")
13998 (commit (string-append "JAMMv" version))))
13999 (file-name (git-file-name name version))
14002 "0ls889jcma1ch9h21jjhnkadgszgqj41842hhcjh6cg88f85qf3i"))))
14003 (build-system gnu-build-system)
14005 `(#:tests? #f ; there are none
14007 (modify-phases %standard-phases
14008 (delete 'configure)
14011 (lambda* (#:key inputs outputs #:allow-other-keys)
14012 (let* ((out (assoc-ref outputs "out"))
14013 (libexec (string-append out "/libexec/jamm"))
14014 (bin (string-append out "/bin")))
14015 (substitute* '("JAMM.sh"
14016 "SignalGenerator.sh")
14018 (string-append "sPath=\"" libexec "\"\n")))
14019 (for-each (lambda (file)
14020 (install-file file libexec))
14021 (list "bincalculator.r"
14033 (chmod script #o555)
14034 (install-file script bin)
14035 (wrap-program (string-append bin "/" script)
14036 `("PATH" ":" prefix
14037 (,(string-append (assoc-ref inputs "coreutils") "/bin")
14038 ,(string-append (assoc-ref inputs "gawk") "/bin")
14039 ,(string-append (assoc-ref inputs "perl") "/bin")
14040 ,(string-append (assoc-ref inputs "r-minimal") "/bin")))
14041 `("PERL5LIB" ":" prefix (,(getenv "PERL5LIB")))
14042 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
14043 (list "JAMM.sh" "SignalGenerator.sh")))
14047 ("coreutils" ,coreutils)
14050 ("r-minimal" ,r-minimal)
14051 ;;("r-parallel" ,r-parallel)
14052 ("r-signal" ,r-signal)
14053 ("r-mclust" ,r-mclust)))
14054 (home-page "https://github.com/mahmoudibrahim/JAMM")
14055 (synopsis "Peak finder for NGS datasets")
14057 "JAMM is a peak finder for next generation sequencing datasets (ChIP-Seq,
14058 ATAC-Seq, DNase-Seq, etc.) that can integrate replicates and assign peak
14059 boundaries accurately. JAMM is applicable to both broad and narrow
14061 (license license:gpl3+)))
14063 (define-public ngless
14070 (uri (git-reference
14071 (url "https://gitlab.com/ngless/ngless.git")
14072 (commit (string-append "v" version))))
14073 (file-name (git-file-name name version))
14076 "0mc2gi7h4lx74zylvyp76mvc0w6706j858ii9vlgzqsw6acpr117"))))
14077 (build-system haskell-build-system)
14079 `(#:haddock? #f ; The haddock phase fails with: NGLess/CmdArgs.hs:20:1:
14080 ; error: parse error on input import
14081 ; import Options.Applicative
14083 (modify-phases %standard-phases
14084 (add-after 'unpack 'create-cabal-file
14085 (lambda _ (invoke "hpack") #t))
14086 ;; These tools are expected to be installed alongside ngless.
14087 (add-after 'install 'link-tools
14088 (lambda* (#:key inputs outputs #:allow-other-keys)
14089 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
14090 (symlink (string-append (assoc-ref inputs "prodigal")
14092 (string-append bin "ngless-" ,version "-prodigal"))
14093 (symlink (string-append (assoc-ref inputs "minimap2")
14095 (string-append bin "ngless-" ,version "-minimap2"))
14096 (symlink (string-append (assoc-ref inputs "samtools")
14098 (string-append bin "ngless-" ,version "-samtools"))
14099 (symlink (string-append (assoc-ref inputs "bwa")
14101 (string-append bin "ngless-" ,version "-bwa"))
14104 `(("prodigal" ,prodigal)
14106 ("samtools" ,samtools)
14107 ("minimap2" ,minimap2)
14108 ("ghc-aeson" ,ghc-aeson)
14109 ("ghc-ansi-terminal" ,ghc-ansi-terminal)
14110 ("ghc-async" ,ghc-async)
14111 ("ghc-atomic-write" ,ghc-atomic-write)
14112 ("ghc-bytestring-lexing" ,ghc-bytestring-lexing)
14113 ("ghc-chart" ,ghc-chart)
14114 ("ghc-chart-cairo" ,ghc-chart-cairo)
14115 ("ghc-conduit" ,ghc-conduit)
14116 ("ghc-conduit-algorithms" ,ghc-conduit-algorithms)
14117 ("ghc-conduit-combinators" ,ghc-conduit-combinators)
14118 ("ghc-conduit-extra" ,ghc-conduit-extra)
14119 ("ghc-configurator" ,ghc-configurator)
14120 ("ghc-convertible" ,ghc-convertible)
14121 ("ghc-data-default" ,ghc-data-default)
14122 ("ghc-double-conversion" ,ghc-double-conversion)
14123 ("ghc-edit-distance" ,ghc-edit-distance)
14124 ("ghc-either" ,ghc-either)
14125 ("ghc-errors" ,ghc-errors)
14126 ("ghc-extra" ,ghc-extra)
14127 ("ghc-filemanip" ,ghc-filemanip)
14128 ("ghc-file-embed" ,ghc-file-embed)
14129 ("ghc-gitrev" ,ghc-gitrev)
14130 ("ghc-hashtables" ,ghc-hashtables)
14131 ("ghc-http-conduit" ,ghc-http-conduit)
14132 ("ghc-inline-c" ,ghc-inline-c)
14133 ("ghc-inline-c-cpp" ,ghc-inline-c-cpp)
14134 ("ghc-intervalmap" ,ghc-intervalmap)
14135 ("ghc-missingh" ,ghc-missingh)
14136 ("ghc-optparse-applicative" ,ghc-optparse-applicative)
14137 ("ghc-parsec" ,ghc-parsec)
14138 ("ghc-regex" ,ghc-regex)
14139 ("ghc-safe" ,ghc-safe)
14140 ("ghc-safeio" ,ghc-safeio)
14141 ("ghc-strict" ,ghc-strict)
14142 ("ghc-tar" ,ghc-tar)
14143 ("ghc-text" ,ghc-text)
14144 ("ghc-unliftio" ,ghc-unliftio)
14145 ("ghc-unliftio-core" ,ghc-unliftio-core)
14146 ("ghc-vector" ,ghc-vector)
14147 ("ghc-yaml" ,ghc-yaml)
14148 ("ghc-zlib" ,ghc-zlib)))
14151 ("r-hdf5r" ,r-hdf5r)
14152 ("r-iterators" ,r-iterators)
14153 ("r-itertools" ,r-itertools)
14154 ("r-matrix" ,r-matrix)))
14156 `(("ghc-hpack" ,ghc-hpack)
14157 ("ghc-quickcheck" ,ghc-quickcheck)
14158 ("ghc-test-framework" ,ghc-test-framework)
14159 ("ghc-test-framework-hunit",ghc-test-framework-hunit)
14160 ("ghc-test-framework-quickcheck2" ,ghc-test-framework-quickcheck2)
14161 ("ghc-test-framework-th" ,ghc-test-framework-th)))
14162 (home-page "https://gitlab.com/ngless/ngless")
14163 (synopsis "DSL for processing next-generation sequencing data")
14164 (description "Ngless is a domain-specific language for
14165 @dfn{next-generation sequencing} (NGS) data processing.")
14166 (license license:expat)))
14168 (define-public filtlong
14169 ;; The recommended way to install is to clone the git repository
14170 ;; https://github.com/rrwick/Filtlong#installation
14171 ;; and the lastest release is more than nine months old
14172 (let ((commit "d1bb46dfe8bc7efe6257b5ce222c04bfe8aedaab")
14176 (version (git-version "0.2.0" revision commit))
14180 (uri (git-reference
14181 (url "https://github.com/rrwick/Filtlong.git")
14183 (file-name (git-file-name name version))
14185 (base32 "1xr92r820x8qlkcr3b57iw223yq8vjgyi42jr79w2xgw47qzr575"))))
14186 (build-system gnu-build-system)
14188 `(#:tests? #f ; no check target
14190 (modify-phases %standard-phases
14191 (delete 'configure)
14193 (lambda* (#:key outputs #:allow-other-keys)
14194 (let* ((out (assoc-ref outputs "out"))
14195 (bin (string-append out "/bin"))
14196 (scripts (string-append out "/share/filtlong/scripts")))
14197 (install-file "bin/filtlong" bin)
14198 (install-file "scripts/histogram.py" scripts)
14199 (install-file "scripts/read_info_histograms.sh" scripts))
14201 (add-after 'install 'wrap-program
14202 (lambda* (#:key inputs outputs #:allow-other-keys)
14203 (let* ((out (assoc-ref outputs "out"))
14204 (path (getenv "PYTHONPATH")))
14205 (wrap-program (string-append out
14206 "/share/filtlong/scripts/histogram.py")
14207 `("PYTHONPATH" ":" prefix (,path))))
14209 (add-before 'check 'patch-tests
14211 (substitute* "scripts/read_info_histograms.sh"
14212 (("awk") (which "gawk")))
14215 `(("gawk" ,gawk) ;for read_info_histograms.sh
14216 ("python" ,python-2) ;required for histogram.py
14218 (home-page "https://github.com/rrwick/Filtlong/")
14219 (synopsis "Tool for quality filtering of Nanopore and PacBio data")
14221 "The Filtlong package is a tool for filtering long reads by quality.
14222 It can take a set of long reads and produce a smaller, better subset. It uses
14223 both read length (longer is better) and read identity (higher is better) when
14224 choosing which reads pass the filter.")
14225 (license (list license:gpl3 ;filtlong
14226 license:asl2.0))))) ;histogram.py
14228 (define-public nanopolish
14229 ;; The recommended way to install is to clone the git repository
14230 ;; <https://github.com/jts/nanopolish#installing-a-particular-release>.
14231 ;; Also, the differences between release and current version seem to be
14233 (let ((commit "50e8b5cc62f9b46f5445f5c5e8c5ab7263ea6d9d")
14236 (name "nanopolish")
14237 (version (git-version "0.10.2" revision commit))
14241 (uri (git-reference
14242 (url "https://github.com/jts/nanopolish.git")
14245 (file-name (git-file-name name version))
14247 (base32 "09j5gz57yr9i34a27vbl72i4g8syv2zzgmsfyjq02yshmnrvkjs6"))))
14248 (build-system gnu-build-system)
14251 `("HDF5=noinstall" "EIGEN=noinstall" "HTS=noinstall" "CC=gcc")
14252 #:tests? #f ; no check target
14254 (modify-phases %standard-phases
14255 (add-after 'unpack 'find-eigen
14256 (lambda* (#:key inputs #:allow-other-keys)
14258 (string-append (assoc-ref inputs "eigen")
14259 "/include/eigen3"))
14261 (delete 'configure)
14263 (lambda* (#:key outputs #:allow-other-keys)
14264 (let* ((out (assoc-ref outputs "out"))
14265 (bin (string-append out "/bin"))
14266 (scripts (string-append out "/share/nanopolish/scripts")))
14268 (install-file "nanopolish" bin)
14269 (for-each (lambda (file) (install-file file scripts))
14270 (find-files "scripts" ".*"))
14272 (add-after 'install 'wrap-programs
14273 (lambda* (#:key outputs #:allow-other-keys)
14274 (for-each (lambda (file)
14275 (wrap-program file `("PYTHONPATH" ":" prefix (,path))))
14276 (find-files "/share/nanopolish/scripts" "\\.py"))
14277 (for-each (lambda (file)
14278 (wrap-program file `("PERL5LIB" ":" prefix (,path))))
14279 (find-files "/share/nanopolish/scripts" "\\.pl"))
14287 ("python-biopython" ,python-biopython)
14288 ("python-numpy" ,python-numpy)
14289 ("python-pysam" ,python-pysam)
14290 ("python-scikit-learn" , python-scikit-learn)
14291 ("python-scipy" ,python-scipy)
14293 (home-page "https://github.com/jts/nanopolish")
14294 (synopsis "Signal-level analysis of Oxford Nanopore sequencing data")
14296 "This package analyses the Oxford Nanopore sequencing data at signal-level.
14297 Nanopolish can calculate an improved consensus sequence for a draft genome
14298 assembly, detect base modifications, call SNPs (Single nucleotide
14299 polymorphisms) and indels with respect to a reference genome and more.")
14300 (license license:expat))))
14302 (define-public cnvkit
14309 (uri (git-reference
14310 (url "https://github.com/etal/cnvkit.git")
14311 (commit (string-append "v" version))))
14312 (file-name (git-file-name name version))
14314 (base32 "0g2f78k68yglmj4fsfmgs8idqv3di9aj53fg0ld0hqljg8chhh82"))))
14315 (build-system python-build-system)
14317 `(("python-biopython" ,python-biopython)
14318 ("python-future" ,python-future)
14319 ("python-matplotlib" ,python-matplotlib)
14320 ("python-numpy" ,python-numpy)
14321 ("python-reportlab" ,python-reportlab)
14322 ("python-pandas" ,python-pandas)
14323 ("python-pysam" ,python-pysam)
14324 ("python-pyfaidx" ,python-pyfaidx)
14325 ("python-scipy" ,python-scipy)
14327 ("r-dnacopy" ,r-dnacopy)))
14328 (home-page "https://cnvkit.readthedocs.org/")
14329 (synopsis "Copy number variant detection from targeted DNA sequencing")
14331 "CNVkit is a Python library and command-line software toolkit to infer
14332 and visualize copy number from high-throughput DNA sequencing data. It is
14333 designed for use with hybrid capture, including both whole-exome and custom
14334 target panels, and short-read sequencing platforms such as Illumina and Ion
14336 (license license:asl2.0)))
14338 (define-public python-pyfit-sne
14340 (name "python-pyfit-sne")
14345 (uri (git-reference
14346 (url "https://github.com/KlugerLab/pyFIt-SNE.git")
14348 (file-name (git-file-name name version))
14350 (base32 "13wh3qkzs56azmmgnxib6xfr29g7xh09sxylzjpni5j0pp0rc5qw"))))
14351 (build-system python-build-system)
14353 `(("python-numpy" ,python-numpy)))
14357 `(("python-cython" ,python-cython)))
14358 (home-page "https://github.com/KlugerLab/pyFIt-SNE")
14359 (synopsis "FFT-accelerated Interpolation-based t-SNE")
14361 "t-Stochastic Neighborhood Embedding (t-SNE) is a highly successful
14362 method for dimensionality reduction and visualization of high dimensional
14363 datasets. A popular implementation of t-SNE uses the Barnes-Hut algorithm to
14364 approximate the gradient at each iteration of gradient descent. This package
14365 is a Cython wrapper for FIt-SNE.")
14366 (license license:bsd-4)))
14368 (define-public velvet
14374 (uri (string-append "https://www.ebi.ac.uk/~zerbino/velvet/"
14375 "velvet_" version ".tgz"))
14378 "0h3njwy66p6bx14r3ar1byb0ccaxmxka4c65rn4iybyiqa4d8kc8"))
14379 ;; Delete bundled libraries
14380 (modules '((guix build utils)))
14383 (delete-file "Manual.pdf")
14384 (delete-file-recursively "third-party")
14386 (build-system gnu-build-system)
14388 `(#:make-flags '("OPENMP=t")
14389 #:test-target "test"
14391 (modify-phases %standard-phases
14392 (delete 'configure)
14393 (add-after 'unpack 'fix-zlib-include
14395 (substitute* "src/binarySequences.c"
14396 (("../third-party/zlib-1.2.3/zlib.h") "zlib.h"))
14399 (lambda* (#:key outputs #:allow-other-keys)
14400 (let* ((out (assoc-ref outputs "out"))
14401 (bin (string-append out "/bin"))
14402 (doc (string-append out "/share/doc/velvet")))
14405 (install-file "velveth" bin)
14406 (install-file "velvetg" bin)
14407 (install-file "Manual.pdf" doc)
14408 (install-file "Columbus_manual.pdf" doc)
14411 `(("openmpi" ,openmpi)
14414 `(("texlive" ,(texlive-union (list texlive-latex-graphics
14415 texlive-latex-hyperref)))))
14416 (home-page "https://www.ebi.ac.uk/~zerbino/velvet/")
14417 (synopsis "Nucleic acid sequence assembler for very short reads")
14419 "Velvet is a de novo genomic assembler specially designed for short read
14420 sequencing technologies, such as Solexa or 454. Velvet currently takes in
14421 short read sequences, removes errors then produces high quality unique
14422 contigs. It then uses paired read information, if available, to retrieve the
14423 repeated areas between contigs.")
14424 (license license:gpl2+)))