1 ;;; GNU Guix --- Functional package management for GNU
2 ;;; Copyright © 2014, 2015, 2016, 2017, 2018, 2019, 2020 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, 2020 Roel Janssen <roel@gnu.org>
7 ;;; Copyright © 2016, 2017, 2018, 2019, 2020 Efraim Flashner <efraim@flashner.co.il>
8 ;;; Copyright © 2016, 2020 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, 2019, 2020 Mădălin Ionel Patrașcu <madalinionel.patrascu@mdc-berlin.de>
15 ;;; Copyright © 2019 Maxim Cournoyer <maxim.cournoyer@gmail.com>
16 ;;; Copyright © 2019 Brian Leung <bkleung89@gmail.com>
17 ;;; Copyright © 2019 Brett Gilio <brettg@gnu.org>
18 ;;; Copyright © 2020 Björn Höfling <bjoern.hoefling@bjoernhoefling.de>
19 ;;; Copyright © 2020 Jakub Kądziołka <kuba@kadziolka.net>
20 ;;; Copyright © 2020 Pierre Langlois <pierre.langlois@gmx.com>
22 ;;; This file is part of GNU Guix.
24 ;;; GNU Guix is free software; you can redistribute it and/or modify it
25 ;;; under the terms of the GNU General Public License as published by
26 ;;; the Free Software Foundation; either version 3 of the License, or (at
27 ;;; your option) any later version.
29 ;;; GNU Guix is distributed in the hope that it will be useful, but
30 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
31 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
32 ;;; GNU General Public License for more details.
34 ;;; You should have received a copy of the GNU General Public License
35 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
37 (define-module (gnu packages bioinformatics)
38 #:use-module ((guix licenses) #:prefix license:)
39 #:use-module (guix packages)
40 #:use-module (guix utils)
41 #:use-module (guix download)
42 #:use-module (guix git-download)
43 #:use-module (guix hg-download)
44 #:use-module (guix build-system ant)
45 #:use-module (guix build-system gnu)
46 #:use-module (guix build-system cmake)
47 #:use-module (guix build-system go)
48 #:use-module (guix build-system haskell)
49 #:use-module (guix build-system meson)
50 #:use-module (guix build-system ocaml)
51 #:use-module (guix build-system perl)
52 #:use-module (guix build-system python)
53 #:use-module (guix build-system r)
54 #:use-module (guix build-system ruby)
55 #:use-module (guix build-system scons)
56 #:use-module (guix build-system trivial)
57 #:use-module (guix deprecation)
58 #:use-module (gnu packages)
59 #:use-module (gnu packages autotools)
60 #:use-module (gnu packages algebra)
61 #:use-module (gnu packages base)
62 #:use-module (gnu packages bash)
63 #:use-module (gnu packages bison)
64 #:use-module (gnu packages bioconductor)
65 #:use-module (gnu packages boost)
66 #:use-module (gnu packages check)
67 #:use-module (gnu packages code)
68 #:use-module (gnu packages compression)
69 #:use-module (gnu packages cpio)
70 #:use-module (gnu packages cran)
71 #:use-module (gnu packages curl)
72 #:use-module (gnu packages documentation)
73 #:use-module (gnu packages databases)
74 #:use-module (gnu packages datastructures)
75 #:use-module (gnu packages dlang)
76 #:use-module (gnu packages file)
77 #:use-module (gnu packages flex)
78 #:use-module (gnu packages gawk)
79 #:use-module (gnu packages gcc)
80 #:use-module (gnu packages gd)
81 #:use-module (gnu packages golang)
82 #:use-module (gnu packages glib)
83 #:use-module (gnu packages graph)
84 #:use-module (gnu packages graphviz)
85 #:use-module (gnu packages groff)
86 #:use-module (gnu packages gtk)
87 #:use-module (gnu packages guile)
88 #:use-module (gnu packages guile-xyz)
89 #:use-module (gnu packages haskell-check)
90 #:use-module (gnu packages haskell-web)
91 #:use-module (gnu packages haskell-xyz)
92 #:use-module (gnu packages image)
93 #:use-module (gnu packages imagemagick)
94 #:use-module (gnu packages java)
95 #:use-module (gnu packages java-compression)
96 #:use-module (gnu packages jemalloc)
97 #:use-module (gnu packages linux)
98 #:use-module (gnu packages lisp-xyz)
99 #:use-module (gnu packages logging)
100 #:use-module (gnu packages machine-learning)
101 #:use-module (gnu packages man)
102 #:use-module (gnu packages maths)
103 #:use-module (gnu packages mpi)
104 #:use-module (gnu packages ncurses)
105 #:use-module (gnu packages ocaml)
106 #:use-module (gnu packages pcre)
107 #:use-module (gnu packages parallel)
108 #:use-module (gnu packages pdf)
109 #:use-module (gnu packages perl)
110 #:use-module (gnu packages perl-check)
111 #:use-module (gnu packages pkg-config)
112 #:use-module (gnu packages popt)
113 #:use-module (gnu packages protobuf)
114 #:use-module (gnu packages python)
115 #:use-module (gnu packages python-compression)
116 #:use-module (gnu packages python-science)
117 #:use-module (gnu packages python-web)
118 #:use-module (gnu packages python-xyz)
119 #:use-module (gnu packages readline)
120 #:use-module (gnu packages ruby)
121 #:use-module (gnu packages serialization)
122 #:use-module (gnu packages shells)
123 #:use-module (gnu packages sphinx)
124 #:use-module (gnu packages statistics)
125 #:use-module (gnu packages swig)
126 #:use-module (gnu packages tbb)
127 #:use-module (gnu packages tex)
128 #:use-module (gnu packages texinfo)
129 #:use-module (gnu packages textutils)
130 #:use-module (gnu packages time)
131 #:use-module (gnu packages tls)
132 #:use-module (gnu packages vim)
133 #:use-module (gnu packages web)
134 #:use-module (gnu packages xml)
135 #:use-module (gnu packages xorg)
136 #:use-module (srfi srfi-1)
137 #:use-module (ice-9 match))
139 (define-public aragorn
146 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
150 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
151 (build-system gnu-build-system)
153 `(#:tests? #f ; there are no tests
155 (modify-phases %standard-phases
165 (string-append "aragorn" ,version ".c"))
168 (lambda* (#:key outputs #:allow-other-keys)
169 (let* ((out (assoc-ref outputs "out"))
170 (bin (string-append out "/bin"))
171 (man (string-append out "/share/man/man1")))
172 (install-file "aragorn" bin)
173 (install-file "aragorn.1" man))
175 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
176 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
178 "Aragorn identifies transfer RNA, mitochondrial RNA and
179 transfer-messenger RNA from nucleotide sequences, based on homology to known
180 tRNA consensus sequences and RNA structure. It also outputs the secondary
181 structure of the predicted RNA.")
182 (license license:gpl2)))
190 ;; BamM is not available on pypi.
192 (url "https://github.com/Ecogenomics/BamM")
195 (file-name (git-file-name name version))
198 "1p83ahi984ipslxlg4yqy1gdnya9rkn1v71z8djgxkm9d2chw4c5"))
199 (modules '((guix build utils)))
202 ;; Delete bundled htslib.
203 (delete-file-recursively "c/htslib-1.3.1")
205 (build-system python-build-system)
207 `(#:python ,python-2 ; BamM is Python 2 only.
208 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
209 ;; been modified from its original form.
211 (let ((htslib (assoc-ref %build-inputs "htslib")))
212 (list "--with-libhts-lib" (string-append htslib "/lib")
213 "--with-libhts-inc" (string-append htslib "/include/htslib")))
215 (modify-phases %standard-phases
216 (add-after 'unpack 'autogen
218 (with-directory-excursion "c"
219 (let ((sh (which "sh")))
220 (for-each make-file-writable (find-files "." ".*"))
221 ;; Use autogen so that 'configure' works.
222 (substitute* "autogen.sh" (("/bin/sh") sh))
223 (setenv "CONFIG_SHELL" sh)
224 (invoke "./autogen.sh")))
227 ;; Run tests after installation so compilation only happens once.
229 (add-after 'install 'wrap-executable
230 (lambda* (#:key outputs #:allow-other-keys)
231 (let* ((out (assoc-ref outputs "out"))
232 (path (getenv "PATH")))
233 (wrap-program (string-append out "/bin/bamm")
234 `("PATH" ":" prefix (,path))))
236 (add-after 'wrap-executable 'post-install-check
237 (lambda* (#:key inputs outputs #:allow-other-keys)
239 (string-append (assoc-ref outputs "out")
244 (assoc-ref outputs "out")
246 (string-take (string-take-right
247 (assoc-ref inputs "python") 5) 3)
249 (getenv "PYTHONPATH")))
250 ;; There are 2 errors printed, but they are safe to ignore:
251 ;; 1) [E::hts_open_format] fail to open file ...
252 ;; 2) samtools view: failed to open ...
256 `(("autoconf" ,autoconf)
257 ("automake" ,automake)
260 ("python-nose" ,python2-nose)
261 ("python-pysam" ,python2-pysam)))
263 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
264 ("samtools" ,samtools)
268 ("coreutils" ,coreutils)))
270 `(("python-numpy" ,python2-numpy)))
271 (home-page "https://ecogenomics.github.io/BamM/")
272 (synopsis "Metagenomics-focused BAM file manipulator")
274 "BamM is a C library, wrapped in python, to efficiently generate and
275 parse BAM files, specifically for the analysis of metagenomic data. For
276 instance, it implements several methods to assess contig-wise read coverage.")
277 (license license:lgpl3+)))
279 (define-public bamtools
286 (url "https://github.com/pezmaster31/bamtools")
287 (commit (string-append "v" version))))
288 (file-name (git-file-name name version))
291 "0nfb2ypcx9959xnbz6wxh6py3xfizgmg8nrknxl95c507m9hmq8b"))))
292 (build-system cmake-build-system)
294 `(#:tests? #f ;no "check" target
296 (modify-phases %standard-phases
298 'configure 'set-ldflags
299 (lambda* (#:key outputs #:allow-other-keys)
303 (assoc-ref outputs "out") "/lib/bamtools"))
305 (inputs `(("zlib" ,zlib)))
306 (home-page "https://github.com/pezmaster31/bamtools")
307 (synopsis "C++ API and command-line toolkit for working with BAM data")
309 "BamTools provides both a C++ API and a command-line toolkit for handling
311 (license license:expat)))
313 (define-public bcftools
319 (uri (string-append "https://github.com/samtools/bcftools/"
321 version "/bcftools-" version ".tar.bz2"))
324 "0r508mp15pqzf8r1269kb4v5naw9zsvbwd3cz8s1yj7carsf9viw"))
325 (modules '((guix build utils)))
327 ;; Delete bundled htslib.
328 (delete-file-recursively "htslib-1.11")
330 (build-system gnu-build-system)
333 (list "--enable-libgsl")
336 (modify-phases %standard-phases
337 (add-before 'check 'patch-tests
339 (substitute* "test/test.pl"
340 (("/bin/bash") (which "bash")))
348 (home-page "https://samtools.github.io/bcftools/")
349 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
351 "BCFtools is a set of utilities that manipulate variant calls in the
352 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
353 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
354 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
355 (license (list license:gpl3+ license:expat))))
357 (define-public bcftools-1.9
358 (package (inherit bcftools)
363 (uri (string-append "https://github.com/samtools/bcftools/"
365 version "/bcftools-" version ".tar.bz2"))
368 "1j3h638i8kgihzyrlnpj82xg1b23sijibys9hvwari3fy7kd0dkg"))
369 (modules '((guix build utils)))
371 ;; Delete bundled htslib.
372 (delete-file-recursively "htslib-1.9")
374 (build-system gnu-build-system)
376 `(("htslib" ,htslib-1.9)
379 (define-public bedops
386 (url "https://github.com/bedops/bedops")
387 (commit (string-append "v" version))))
388 (file-name (git-file-name name version))
391 "0mmgsgwz5r9w76hzgxkxc9s9lkdhhaf7vr6i02b09vbswvs1fyqx"))))
392 (build-system gnu-build-system)
395 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
397 (modify-phases %standard-phases
398 (add-after 'unpack 'unpack-tarballs
400 ;; FIXME: Bedops includes tarballs of minimally patched upstream
401 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
402 ;; libraries because at least one of the libraries (zlib) is
403 ;; patched to add a C++ function definition (deflateInit2cpp).
404 ;; Until the Bedops developers offer a way to link against system
405 ;; libraries we have to build the in-tree copies of these three
408 ;; See upstream discussion:
409 ;; https://github.com/bedops/bedops/issues/124
411 ;; Unpack the tarballs to benefit from shebang patching.
412 (with-directory-excursion "third-party"
413 (invoke "tar" "xvf" "jansson-2.6.tar.bz2")
414 (invoke "tar" "xvf" "zlib-1.2.7.tar.bz2")
415 (invoke "tar" "xvf" "bzip2-1.0.6.tar.bz2"))
416 ;; Disable unpacking of tarballs in Makefile.
417 (substitute* "system.mk/Makefile.linux"
418 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
419 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
420 (substitute* "third-party/zlib-1.2.7/Makefile.in"
421 (("^SHELL=.*$") "SHELL=bash\n"))
423 (delete 'configure))))
424 (home-page "https://github.com/bedops/bedops")
425 (synopsis "Tools for high-performance genomic feature operations")
427 "BEDOPS is a suite of tools to address common questions raised in genomic
428 studies---mostly with regard to overlap and proximity relationships between
429 data sets. It aims to be scalable and flexible, facilitating the efficient
430 and accurate analysis and management of large-scale genomic data.
432 BEDOPS provides tools that perform highly efficient and scalable Boolean and
433 other set operations, statistical calculations, archiving, conversion and
434 other management of genomic data of arbitrary scale. Tasks can be easily
435 split by chromosome for distributing whole-genome analyses across a
436 computational cluster.")
437 (license license:gpl2+)))
439 (define-public bedtools
445 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
446 "download/v" version "/"
447 "bedtools-" version ".tar.gz"))
450 "0m3hk6548846w83a9s5drsczvy67n2azx41kj71n03klb2gbzwg3"))))
451 (build-system gnu-build-system)
453 '(#:test-target "test"
455 (list (string-append "prefix=" (assoc-ref %outputs "out")))
457 (modify-phases %standard-phases
458 (delete 'configure))))
460 `(("python" ,python-wrapper)))
462 `(("samtools" ,samtools-1.9)
464 (home-page "https://github.com/arq5x/bedtools2")
465 (synopsis "Tools for genome analysis and arithmetic")
467 "Collectively, the bedtools utilities are a swiss-army knife of tools for
468 a wide-range of genomics analysis tasks. The most widely-used tools enable
469 genome arithmetic: that is, set theory on the genome. For example, bedtools
470 allows one to intersect, merge, count, complement, and shuffle genomic
471 intervals from multiple files in widely-used genomic file formats such as BAM,
473 (license license:expat)))
475 ;; Later releases of bedtools produce files with more columns than
476 ;; what Ribotaper expects.
477 (define-public bedtools-2.18
478 (package (inherit bedtools)
483 (uri (string-append "https://github.com/arq5x/bedtools2/"
484 "releases/download/v" version
485 "/bedtools-" version ".tar.gz"))
488 "11rvca19ncg03kxd0wzlfx5ws7r3nisd0z8s9j9n182d8ksp2pxz"))))
490 '(#:test-target "test"
492 (modify-phases %standard-phases
495 (lambda* (#:key outputs #:allow-other-keys)
496 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
497 (for-each (lambda (file)
498 (install-file file bin))
499 (find-files "bin" ".*")))
509 (url "https://github.com/PacificBiosciences/pbbam")
511 (file-name (git-file-name name version))
514 "0h9gkrpf2lrxklxp72xfl5bi3h5zcm5hprrya9gf0hr3xwlbpp0x"))))
515 (build-system meson-build-system)
518 (modify-phases %standard-phases
519 (add-after 'unpack 'find-googletest
520 (lambda* (#:key inputs #:allow-other-keys)
521 ;; It doesn't find gtest_main because there's no pkg-config file
522 ;; for it. Find it another way.
523 (substitute* "tests/meson.build"
524 (("pbbam_gtest_dep = dependency\\('gtest_main'.*")
525 (format #f "cpp = meson.get_compiler('cpp')
526 pbbam_gtest_dep = cpp.find_library('gtest_main', dirs : '~a')\n"
527 (assoc-ref inputs "googletest"))))
529 ;; TODO: tests/pbbam_test cannot be linked
530 ;; ld: tests/59830eb@@pbbam_test@exe/src_test_Accuracy.cpp.o:
531 ;; undefined reference to symbol '_ZTIN7testing4TestE'
532 ;; ld: /gnu/store/...-googletest-1.8.0/lib/libgtest.so:
533 ;; error adding symbols: DSO missing from command line
535 #:configure-flags '("-Dtests=false")))
536 ;; These libraries are listed as "Required" in the pkg-config file.
542 ("samtools" ,samtools)))
544 `(("googletest" ,googletest)
545 ("pkg-config" ,pkg-config)
546 ("python" ,python-wrapper))) ; for tests
547 (home-page "https://github.com/PacificBiosciences/pbbam")
548 (synopsis "Work with PacBio BAM files")
550 "The pbbam software package provides components to create, query, and
551 edit PacBio BAM files and associated indices. These components include a core
552 C++ library, bindings for additional languages, and command-line utilities.
553 This library is not intended to be used as a general-purpose BAM utility - all
554 input and output BAMs must adhere to the PacBio BAM format specification.
555 Non-PacBio BAMs will cause exceptions to be thrown.")
556 (license license:bsd-3)))
558 (define-public blasr-libcpp
560 (name "blasr-libcpp")
565 (url "https://github.com/PacificBiosciences/blasr_libcpp")
567 (file-name (git-file-name name version))
570 "0cn5l42zyq67sj0g2imqkhayz2iqvv0a1pgpbmlq0qynjmsrbfd2"))))
571 (build-system meson-build-system)
574 (modify-phases %standard-phases
575 (add-after 'unpack 'link-with-hdf5
576 (lambda* (#:key inputs #:allow-other-keys)
577 (let ((hdf5 (assoc-ref inputs "hdf5")))
578 (substitute* "meson.build"
579 (("libblasr_deps = \\[" m)
582 (format #f "cpp.find_library('hdf5', dirs : '~a'), \
583 cpp.find_library('hdf5_cpp', dirs : '~a'), "
586 (add-after 'unpack 'find-googletest
587 (lambda* (#:key inputs #:allow-other-keys)
588 ;; It doesn't find gtest_main because there's no pkg-config file
589 ;; for it. Find it another way.
590 (substitute* "unittest/meson.build"
591 (("libblasr_gtest_dep = dependency\\('gtest_main'.*")
592 (format #f "cpp = meson.get_compiler('cpp')
593 libblasr_gtest_dep = cpp.find_library('gtest_main', dirs : '~a')\n"
594 (assoc-ref inputs "googletest"))))
596 ;; TODO: unittest/libblasr_unittest cannot be linked
597 ;; ld: ;; unittest/df08227@@libblasr_unittest@exe/alignment_utils_FileUtils_gtest.cpp.o:
598 ;; undefined reference to symbol
599 ;; '_ZN7testing8internal9DeathTest6CreateEPKcPKNS0_2REES3_iPPS1_'
600 ;; ld: /gnu/store/...-googletest-1.8.0/lib/libgtest.so:
601 ;; error adding symbols: DSO missing from command line
603 #:configure-flags '("-Dtests=false")))
610 `(("googletest" ,googletest)
611 ("pkg-config" ,pkg-config)))
612 (home-page "https://github.com/PacificBiosciences/blasr_libcpp")
613 (synopsis "Library for analyzing PacBio genomic sequences")
615 "This package provides three libraries used by applications for analyzing
616 PacBio genomic sequences. This library contains three sub-libraries: pbdata,
618 (license license:bsd-3)))
627 (url "https://github.com/PacificBiosciences/blasr")
629 (file-name (git-file-name name version))
632 "1skgy2mvz8gsgfh1gc2nfgwvpyzb1hpmp2cf2773h5wsj8nw22kl"))))
633 (build-system meson-build-system)
636 (modify-phases %standard-phases
637 (add-after 'unpack 'link-with-hdf5
638 (lambda* (#:key inputs #:allow-other-keys)
639 (let ((hdf5 (assoc-ref inputs "hdf5")))
640 (substitute* "meson.build"
641 (("blasr_deps = \\[" m)
644 (format #f "cpp.find_library('hdf5', dirs : '~a'), \
645 cpp.find_library('hdf5_cpp', dirs : '~a'), "
648 ;; Tests require "cram" executable, which is not packaged.
650 #:configure-flags '("-Dtests=false")))
653 ("blasr-libcpp" ,blasr-libcpp)
658 `(("pkg-config" ,pkg-config)))
659 (home-page "https://github.com/PacificBiosciences/blasr")
660 (synopsis "PacBio long read aligner")
662 "Blasr is a genomic sequence aligner for processing PacBio long reads.")
663 (license license:bsd-3)))
665 (define-public ribotaper
671 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
672 "files/RiboTaper/RiboTaper_Version_"
676 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
677 (build-system gnu-build-system)
680 (modify-phases %standard-phases
681 (add-after 'install 'wrap-executables
682 (lambda* (#:key inputs outputs #:allow-other-keys)
683 (let* ((out (assoc-ref outputs "out")))
686 (wrap-program (string-append out "/bin/" script)
687 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
688 '("create_annotations_files.bash"
689 "create_metaplots.bash"
690 "Ribotaper_ORF_find.sh"
694 `(("bedtools" ,bedtools-2.18)
695 ("samtools" ,samtools-0.1)
696 ("r-minimal" ,r-minimal)
697 ("r-foreach" ,r-foreach)
698 ("r-xnomial" ,r-xnomial)
700 ("r-multitaper" ,r-multitaper)
701 ("r-seqinr" ,r-seqinr)))
702 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
703 (synopsis "Define translated ORFs using ribosome profiling data")
705 "Ribotaper is a method for defining translated @dfn{open reading
706 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
707 provides the Ribotaper pipeline.")
708 (license license:gpl3+)))
710 (define-public ribodiff
718 (url "https://github.com/ratschlab/RiboDiff")
719 (commit (string-append "v" version))))
720 (file-name (git-file-name name version))
723 "0x75nlp7qnmm64jasbi6l21f2cy99r2cjyl6b4hr8zf2bq22drnz"))))
724 (build-system python-build-system)
728 (modify-phases %standard-phases
729 ;; Generate an installable executable script wrapper.
730 (add-after 'unpack 'patch-setup.py
732 (substitute* "setup.py"
733 (("^(.*)packages=.*" line prefix)
734 (string-append line "\n"
735 prefix "scripts=['scripts/TE.py'],\n")))
738 `(("python-numpy" ,python2-numpy)
739 ("python-matplotlib" ,python2-matplotlib)
740 ("python-scipy" ,python2-scipy)
741 ("python-statsmodels" ,python2-statsmodels)))
743 `(("python-mock" ,python2-mock)
744 ("python-nose" ,python2-nose)))
745 (home-page "https://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
746 (synopsis "Detect translation efficiency changes from ribosome footprints")
747 (description "RiboDiff is a statistical tool that detects the protein
748 translational efficiency change from Ribo-Seq (ribosome footprinting) and
749 RNA-Seq data. It uses a generalized linear model to detect genes showing
750 difference in translational profile taking mRNA abundance into account. It
751 facilitates us to decipher the translational regulation that behave
752 independently with transcriptional regulation.")
753 (license license:gpl3+)))
755 (define-public bioawk
762 (url "https://github.com/lh3/bioawk")
763 (commit (string-append "v" version))))
764 (file-name (git-file-name name version))
767 "1pxc3zdnirxbf9a0az698hd8xdik7qkhypm7v6hn922x8y9qmspm"))))
768 (build-system gnu-build-system)
774 `(#:tests? #f ; There are no tests to run.
775 ;; Bison must generate files, before other targets can build.
778 (modify-phases %standard-phases
779 (delete 'configure) ; There is no configure phase.
781 (lambda* (#:key outputs #:allow-other-keys)
782 (let* ((out (assoc-ref outputs "out"))
783 (bin (string-append out "/bin"))
784 (man (string-append out "/share/man/man1")))
786 (copy-file "awk.1" (string-append man "/bioawk.1"))
787 (install-file "bioawk" bin))
789 (home-page "https://github.com/lh3/bioawk")
790 (synopsis "AWK with bioinformatics extensions")
791 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
792 support of several common biological data formats, including optionally gzip'ed
793 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
794 also adds a few built-in functions and a command line option to use TAB as the
795 input/output delimiter. When the new functionality is not used, bioawk is
796 intended to behave exactly the same as the original BWK awk.")
797 (license license:x11)))
799 (define-public python-pybedtools
801 (name "python-pybedtools")
805 (uri (pypi-uri "pybedtools" version))
808 "14w5i40gi25clrr7h4wa2pcpnyipya8hrqi7nq77553zc5wf0df0"))))
809 (build-system python-build-system)
811 `(#:modules ((ice-9 ftw)
815 (guix build python-build-system))
816 ;; See https://github.com/daler/pybedtools/issues/192
818 (modify-phases %standard-phases
819 (add-after 'unpack 'disable-broken-tests
821 (substitute* "pybedtools/test/test_scripts.py"
822 ;; This test freezes.
823 (("def test_intron_exon_reads")
824 "def _do_not_test_intron_exon_reads")
825 ;; This test fails in the Python 2 build.
826 (("def test_venn_mpl")
827 "def _do_not_test_venn_mpl"))
828 (substitute* "pybedtools/test/test_helpers.py"
829 ;; Requires internet access.
830 (("def test_chromsizes")
831 "def _do_not_test_chromsizes")
832 ;; Broken as a result of the workaround used in the check phase
833 ;; (see: https://github.com/daler/pybedtools/issues/192).
834 (("def test_getting_example_beds")
835 "def _do_not_test_getting_example_beds"))
836 ;; This issue still occurs on python2
837 (substitute* "pybedtools/test/test_issues.py"
838 (("def test_issue_303")
839 "def _test_issue_303"))
841 ;; TODO: Remove phase after it's part of PYTHON-BUILD-SYSTEM.
843 ;; Force the Cythonization of C++ files to guard against compilation
845 (add-after 'unpack 'remove-cython-generated-files
847 (let ((cython-sources (map (cut string-drop-right <> 4)
848 (find-files "." "\\.pyx$")))
849 (c/c++-files (find-files "." "\\.(c|cpp|cxx)$")))
850 (define (strip-extension filename)
851 (string-take filename (string-index-right filename #\.)))
852 (define (cythonized? c/c++-file)
853 (member (strip-extension c/c++-file) cython-sources))
854 (for-each delete-file (filter cythonized? c/c++-files))
856 (add-after 'remove-cython-generated-files 'generate-cython-extensions
858 (invoke "python" "setup.py" "cythonize")))
861 (let* ((cwd (getcwd))
862 (build-root-directory (string-append cwd "/build/"))
863 (build (string-append
865 (find (cut string-prefix? "lib" <>)
866 (scandir (string-append
867 build-root-directory)))))
868 (scripts (string-append
870 (find (cut string-prefix? "scripts" <>)
871 (scandir build-root-directory)))))
873 (string-append build ":" (getenv "PYTHONPATH")))
874 ;; Executable scripts such as 'intron_exon_reads.py' must be
875 ;; available in the PATH.
877 (string-append scripts ":" (getenv "PATH"))))
878 ;; The tests need to be run from elsewhere...
879 (mkdir-p "/tmp/test")
880 (copy-recursively "pybedtools/test" "/tmp/test")
881 (with-directory-excursion "/tmp/test"
882 (invoke "pytest" "-v" "--doctest-modules")))))))
884 `(("bedtools" ,bedtools)
885 ("samtools" ,samtools)
886 ("python-matplotlib" ,python-matplotlib)
887 ("python-pysam" ,python-pysam)
888 ("python-pyyaml" ,python-pyyaml)))
890 `(("python-numpy" ,python-numpy)
891 ("python-pandas" ,python-pandas)
892 ("python-cython" ,python-cython)
893 ("kentutils" ,kentutils) ; for bedGraphToBigWig
894 ("python-six" ,python-six)
895 ;; For the test suite.
896 ("python-pytest" ,python-pytest)
897 ("python-psutil" ,python-psutil)))
898 (home-page "https://pythonhosted.org/pybedtools/")
899 (synopsis "Python wrapper for BEDtools programs")
901 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
902 which are widely used for genomic interval manipulation or \"genome algebra\".
903 pybedtools extends BEDTools by offering feature-level manipulations from with
905 (license license:gpl2+)))
907 (define-public python2-pybedtools
908 (let ((pybedtools (package-with-python2 python-pybedtools)))
912 `(("python2-pathlib" ,python2-pathlib)
913 ,@(package-native-inputs pybedtools))))))
915 (define-public python-biom-format
917 (name "python-biom-format")
922 ;; Use GitHub as source because PyPI distribution does not contain
923 ;; test data: https://github.com/biocore/biom-format/issues/693
925 (url "https://github.com/biocore/biom-format")
927 (file-name (git-file-name name version))
930 "1rna16lyk5aqhnv0dp77wwaplias93f1vw28ad3jmyw6hwkai05v"))
931 (modules '((guix build utils)))
933 ;; Delete generated C files.
934 (for-each delete-file (find-files "." "\\.c"))
936 (build-system python-build-system)
939 (modify-phases %standard-phases
940 (add-after 'unpack 'use-cython
941 (lambda _ (setenv "USE_CYTHON" "1") #t))
942 (add-after 'unpack 'disable-broken-tests
944 (substitute* "biom/tests/test_cli/test_validate_table.py"
945 (("^(.+)def test_invalid_hdf5" m indent)
946 (string-append indent
947 "@npt.dec.skipif(True, msg='Guix')\n"
949 (substitute* "biom/tests/test_table.py"
950 (("^(.+)def test_from_hdf5_issue_731" m indent)
951 (string-append indent
952 "@npt.dec.skipif(True, msg='Guix')\n"
955 (add-before 'reset-gzip-timestamps 'make-files-writable
956 (lambda* (#:key outputs #:allow-other-keys)
957 (let ((out (assoc-ref outputs "out")))
958 (for-each (lambda (file) (chmod file #o644))
959 (find-files out "\\.gz"))
962 `(("python-numpy" ,python-numpy)
963 ("python-scipy" ,python-scipy)
964 ("python-flake8" ,python-flake8)
965 ("python-future" ,python-future)
966 ("python-click" ,python-click)
967 ("python-h5py" ,python-h5py)
968 ;; FIXME: Upgrade to pandas 1.0 when
969 ;; https://github.com/biocore/biom-format/issues/837 is resolved.
970 ("python-pandas" ,python-pandas-0.25)))
972 `(("python-cython" ,python-cython)
973 ("python-pytest" ,python-pytest)
974 ("python-pytest-cov" ,python-pytest-cov)
975 ("python-nose" ,python-nose)))
976 (home-page "http://www.biom-format.org")
977 (synopsis "Biological Observation Matrix (BIOM) format utilities")
979 "The BIOM file format is designed to be a general-use format for
980 representing counts of observations e.g. operational taxonomic units, KEGG
981 orthology groups or lipid types, in one or more biological samples
982 e.g. microbiome samples, genomes, metagenomes.")
983 (license license:bsd-3)
984 (properties `((python2-variant . ,(delay python2-biom-format))))))
986 (define-public python2-biom-format
987 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
991 (substitute-keyword-arguments (package-arguments base)
993 `(modify-phases ,phases
994 ;; Do not require the unmaintained pyqi library.
995 (add-after 'unpack 'remove-pyqi
997 (substitute* "setup.py"
998 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
1001 (define-public python-pairtools
1003 (name "python-pairtools")
1008 (url "https://github.com/mirnylab/pairtools")
1009 (commit (string-append "v" version))))
1010 (file-name (git-file-name name version))
1013 "0gr8y13q7sd6yai6df4aavl2470n1f9s3cib6r473z4hr8hcbwmc"))))
1014 (build-system python-build-system)
1017 (modify-phases %standard-phases
1018 (add-after 'unpack 'fix-references
1020 (substitute* '("pairtools/pairtools_merge.py"
1021 "pairtools/pairtools_sort.py")
1022 (("/bin/bash") (which "bash")))
1025 (lambda* (#:key inputs outputs #:allow-other-keys)
1026 (add-installed-pythonpath inputs outputs)
1027 (with-directory-excursion "/tmp"
1028 (invoke "pytest" "-v")))))))
1030 `(("python-cython" ,python-cython)
1031 ("python-nose" ,python-nose)
1032 ("python-pytest" ,python-pytest)))
1034 `(("python" ,python-wrapper)))
1036 `(("htslib" ,htslib) ; for bgzip, looked up in PATH
1037 ("samtools" ,samtools) ; looked up in PATH
1038 ("lz4" ,lz4) ; for lz4c
1039 ("python-click" ,python-click)
1040 ("python-numpy" ,python-numpy)))
1041 (home-page "https://github.com/mirnylab/pairtools")
1042 (synopsis "Process mapped Hi-C data")
1043 (description "Pairtools is a simple and fast command-line framework to
1044 process sequencing data from a Hi-C experiment. Process pair-end sequence
1045 alignments and perform the following operations:
1048 @item detect ligation junctions (a.k.a. Hi-C pairs) in aligned paired-end
1049 sequences of Hi-C DNA molecules
1050 @item sort @code{.pairs} files for downstream analyses
1051 @item detect, tag and remove PCR/optical duplicates
1052 @item generate extensive statistics of Hi-C datasets
1053 @item select Hi-C pairs given flexibly defined criteria
1054 @item restore @code{.sam} alignments from Hi-C pairs.
1057 (license license:expat)))
1059 (define-public bioperl-minimal
1060 (let* ((inputs `(("perl-module-build" ,perl-module-build)
1061 ("perl-data-stag" ,perl-data-stag)
1062 ("perl-libwww" ,perl-libwww)
1063 ("perl-uri" ,perl-uri)))
1065 (map (compose package-name cadr)
1068 (map (compose package-transitive-target-inputs cadr) inputs))))))
1070 (name "bioperl-minimal")
1076 (url "https://github.com/bioperl/bioperl-live")
1077 (commit (string-append "release-"
1078 (string-map (lambda (c)
1080 #\- c)) version)))))
1081 (file-name (git-file-name name version))
1084 "0wl8yvzcls59pwwk6m8ahy87pwg6nnibzy5cldbvmcwg2x2w7783"))))
1085 (build-system perl-build-system)
1088 (modify-phases %standard-phases
1090 'install 'wrap-programs
1091 (lambda* (#:key outputs #:allow-other-keys)
1092 ;; Make sure all executables in "bin" find the required Perl
1093 ;; modules at runtime. As the PERL5LIB variable contains also
1094 ;; the paths of native inputs, we pick the transitive target
1095 ;; inputs from %build-inputs.
1096 (let* ((out (assoc-ref outputs "out"))
1097 (bin (string-append out "/bin/"))
1099 (cons (string-append out "/lib/perl5/site_perl")
1101 (assoc-ref %build-inputs name))
1102 ',transitive-inputs))
1104 (for-each (lambda (file)
1106 `("PERL5LIB" ":" prefix (,path))))
1107 (find-files bin "\\.pl$"))
1111 `(("perl-test-most" ,perl-test-most)))
1112 (home-page "https://metacpan.org/release/BioPerl")
1113 (synopsis "Bioinformatics toolkit")
1115 "BioPerl is the product of a community effort to produce Perl code which
1116 is useful in biology. Examples include Sequence objects, Alignment objects
1117 and database searching objects. These objects not only do what they are
1118 advertised to do in the documentation, but they also interact - Alignment
1119 objects are made from the Sequence objects, Sequence objects have access to
1120 Annotation and SeqFeature objects and databases, Blast objects can be
1121 converted to Alignment objects, and so on. This means that the objects
1122 provide a coordinated and extensible framework to do computational biology.")
1123 (license license:perl-license))))
1125 (define-public python-biopython
1127 (name "python-biopython")
1131 ;; use PyPi rather than biopython.org to ease updating
1132 (uri (pypi-uri "biopython" version))
1135 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
1136 (build-system python-build-system)
1139 (modify-phases %standard-phases
1140 (add-before 'check 'set-home
1141 ;; Some tests require a home directory to be set.
1142 (lambda _ (setenv "HOME" "/tmp") #t)))))
1144 `(("python-numpy" ,python-numpy)))
1145 (home-page "https://biopython.org/")
1146 (synopsis "Tools for biological computation in Python")
1148 "Biopython is a set of tools for biological computation including parsers
1149 for bioinformatics files into Python data structures; interfaces to common
1150 bioinformatics programs; a standard sequence class and tools for performing
1151 common operations on them; code to perform data classification; code for
1152 dealing with alignments; code making it easy to split up parallelizable tasks
1153 into separate processes; and more.")
1154 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
1156 (define-public python2-biopython
1157 (package-with-python2 python-biopython))
1159 (define-public python-fastalite
1161 (name "python-fastalite")
1166 (uri (pypi-uri "fastalite" version))
1169 "1qli6pxp77i9xn2wfciq2zaxhl82bdxb33cpzqzj1z25yd036wqj"))))
1170 (build-system python-build-system)
1172 `(#:tests? #f)) ; Test data is not distributed.
1173 (home-page "https://github.com/nhoffman/fastalite")
1174 (synopsis "Simplest possible FASTA parser")
1175 (description "This library implements a FASTA and a FASTQ parser without
1176 relying on a complex dependency tree.")
1177 (license license:expat)))
1179 (define-public python2-fastalite
1180 (package-with-python2 python-fastalite))
1182 (define-public bpp-core
1183 ;; The last release was in 2014 and the recommended way to install from source
1184 ;; is to clone the git repository, so we do this.
1185 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1186 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
1189 (version (string-append "2.2.0-1." (string-take commit 7)))
1193 (url "http://biopp.univ-montp2.fr/git/bpp-core")
1195 (file-name (string-append name "-" version "-checkout"))
1198 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
1199 (build-system cmake-build-system)
1201 `(#:parallel-build? #f))
1202 (home-page "http://biopp.univ-montp2.fr")
1203 (synopsis "C++ libraries for Bioinformatics")
1205 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1206 analysis, phylogenetics, molecular evolution and population genetics. It is
1207 Object Oriented and is designed to be both easy to use and computer efficient.
1208 Bio++ intends to help programmers to write computer expensive programs, by
1209 providing them a set of re-usable tools.")
1210 (license license:cecill-c))))
1212 (define-public bpp-phyl
1213 ;; The last release was in 2014 and the recommended way to install from source
1214 ;; is to clone the git repository, so we do this.
1215 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1216 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
1219 (version (string-append "2.2.0-1." (string-take commit 7)))
1223 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
1225 (file-name (string-append name "-" version "-checkout"))
1228 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
1229 (build-system cmake-build-system)
1231 `(#:parallel-build? #f
1232 ;; If out-of-source, test data is not copied into the build directory
1233 ;; so the tests fail.
1234 #:out-of-source? #f))
1236 `(("bpp-core" ,bpp-core)
1237 ("bpp-seq" ,bpp-seq)))
1238 (home-page "http://biopp.univ-montp2.fr")
1239 (synopsis "Bio++ phylogenetic Library")
1241 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1242 analysis, phylogenetics, molecular evolution and population genetics. This
1243 library provides phylogenetics-related modules.")
1244 (license license:cecill-c))))
1246 (define-public bpp-popgen
1247 ;; The last release was in 2014 and the recommended way to install from source
1248 ;; is to clone the git repository, so we do this.
1249 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1250 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
1253 (version (string-append "2.2.0-1." (string-take commit 7)))
1257 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
1259 (file-name (string-append name "-" version "-checkout"))
1262 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
1263 (build-system cmake-build-system)
1265 `(#:parallel-build? #f
1266 #:tests? #f)) ; There are no tests.
1268 `(("bpp-core" ,bpp-core)
1269 ("bpp-seq" ,bpp-seq)))
1270 (home-page "http://biopp.univ-montp2.fr")
1271 (synopsis "Bio++ population genetics library")
1273 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1274 analysis, phylogenetics, molecular evolution and population genetics. This
1275 library provides population genetics-related modules.")
1276 (license license:cecill-c))))
1278 (define-public bpp-seq
1279 ;; The last release was in 2014 and the recommended way to install from source
1280 ;; is to clone the git repository, so we do this.
1281 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1282 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
1285 (version (string-append "2.2.0-1." (string-take commit 7)))
1289 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
1291 (file-name (string-append name "-" version "-checkout"))
1294 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
1295 (build-system cmake-build-system)
1297 `(#:parallel-build? #f
1298 ;; If out-of-source, test data is not copied into the build directory
1299 ;; so the tests fail.
1300 #:out-of-source? #f))
1302 `(("bpp-core" ,bpp-core)))
1303 (home-page "http://biopp.univ-montp2.fr")
1304 (synopsis "Bio++ sequence library")
1306 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1307 analysis, phylogenetics, molecular evolution and population genetics. This
1308 library provides sequence-related modules.")
1309 (license license:cecill-c))))
1311 (define-public bppsuite
1312 ;; The last release was in 2014 and the recommended way to install from source
1313 ;; is to clone the git repository, so we do this.
1314 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1315 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
1318 (version (string-append "2.2.0-1." (string-take commit 7)))
1322 (url "http://biopp.univ-montp2.fr/git/bppsuite")
1324 (file-name (string-append name "-" version "-checkout"))
1327 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
1328 (build-system cmake-build-system)
1330 `(#:parallel-build? #f
1331 #:tests? #f)) ; There are no tests.
1335 ("texinfo" ,texinfo)))
1337 `(("bpp-core" ,bpp-core)
1338 ("bpp-seq" ,bpp-seq)
1339 ("bpp-phyl" ,bpp-phyl)
1340 ("bpp-phyl" ,bpp-popgen)))
1341 (home-page "http://biopp.univ-montp2.fr")
1342 (synopsis "Bioinformatics tools written with the Bio++ libraries")
1344 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1345 analysis, phylogenetics, molecular evolution and population genetics. This
1346 package provides command line tools using the Bio++ library.")
1347 (license license:cecill-c))))
1349 (define-public blast+
1356 "https://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
1357 version "/ncbi-blast-" version "+-src.tar.gz"))
1360 "11kvrrl0mcwww6530r55hccpg3x3msmhr3051fwnjbq8rzg2j1qi"))
1361 (modules '((guix build utils)))
1364 ;; Remove bundled bzip2, zlib and pcre.
1365 (delete-file-recursively "c++/src/util/compress/bzip2")
1366 (delete-file-recursively "c++/src/util/compress/zlib")
1367 (delete-file-recursively "c++/src/util/regexp")
1368 (substitute* "c++/src/util/compress/Makefile.in"
1369 (("bzip2 zlib api") "api"))
1370 ;; Remove useless msbuild directory
1371 (delete-file-recursively
1372 "c++/src/build-system/project_tree_builder/msbuild")
1374 (build-system gnu-build-system)
1376 `(;; There are two(!) tests for this massive library, and both fail with
1377 ;; "unparsable timing stats".
1378 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
1379 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
1382 #:parallel-build? #f ; not supported
1384 (modify-phases %standard-phases
1385 (add-before 'configure 'set-HOME
1386 ;; $HOME needs to be set at some point during the configure phase
1387 (lambda _ (setenv "HOME" "/tmp") #t))
1388 (add-after 'unpack 'enter-dir
1389 (lambda _ (chdir "c++") #t))
1390 (add-after 'enter-dir 'fix-build-system
1392 (define (which* cmd)
1393 (cond ((string=? cmd "date")
1394 ;; make call to "date" deterministic
1399 (format (current-error-port)
1400 "WARNING: Unable to find absolute path for ~s~%"
1404 ;; Rewrite hardcoded paths to various tools
1405 (substitute* (append '("src/build-system/configure.ac"
1406 "src/build-system/configure"
1407 "src/build-system/helpers/run_with_lock.c"
1408 "scripts/common/impl/if_diff.sh"
1409 "scripts/common/impl/run_with_lock.sh"
1410 "src/build-system/Makefile.configurables.real"
1411 "src/build-system/Makefile.in.top"
1412 "src/build-system/Makefile.meta.gmake=no"
1413 "src/build-system/Makefile.meta.in"
1414 "src/build-system/Makefile.meta_l"
1415 "src/build-system/Makefile.meta_p"
1416 "src/build-system/Makefile.meta_r"
1417 "src/build-system/Makefile.mk.in"
1418 "src/build-system/Makefile.requirements"
1419 "src/build-system/Makefile.rules_with_autodep.in")
1420 (find-files "scripts/common/check" "\\.sh$"))
1421 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1422 (or (which* cmd) all)))
1424 (substitute* (find-files "src/build-system" "^config.*")
1425 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1428 ;; rewrite "/var/tmp" in check script
1429 (substitute* "scripts/common/check/check_make_unix.sh"
1430 (("/var/tmp") "/tmp"))
1432 ;; do not reset PATH
1433 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1435 (("action=/bin/") "action=")
1436 (("export PATH") ":"))
1439 (lambda* (#:key inputs outputs #:allow-other-keys)
1440 (let ((out (assoc-ref outputs "out"))
1441 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1442 (include (string-append (assoc-ref outputs "include")
1443 "/include/ncbi-tools++")))
1444 ;; The 'configure' script doesn't recognize things like
1445 ;; '--enable-fast-install'.
1446 (invoke "./configure.orig"
1447 (string-append "--with-build-root=" (getcwd) "/build")
1448 (string-append "--prefix=" out)
1449 (string-append "--libdir=" lib)
1450 (string-append "--includedir=" include)
1451 (string-append "--with-bz2="
1452 (assoc-ref inputs "bzip2"))
1453 (string-append "--with-z="
1454 (assoc-ref inputs "zlib"))
1455 (string-append "--with-pcre="
1456 (assoc-ref inputs "pcre"))
1457 ;; Each library is built twice by default, once
1458 ;; with "-static" in its name, and again
1463 (outputs '("out" ; 21 MB
1472 ("python" ,python-wrapper)))
1475 (home-page "https://blast.ncbi.nlm.nih.gov")
1476 (synopsis "Basic local alignment search tool")
1478 "BLAST is a popular method of performing a DNA or protein sequence
1479 similarity search, using heuristics to produce results quickly. It also
1480 calculates an “expect value” that estimates how many matches would have
1481 occurred at a given score by chance, which can aid a user in judging how much
1482 confidence to have in an alignment.")
1483 ;; Most of the sources are in the public domain, with the following
1486 ;; * ./c++/include/util/bitset/
1487 ;; * ./c++/src/html/ncbi_menu*.js
1489 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1491 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1493 ;; * ./c++/src/corelib/teamcity_*
1494 (license (list license:public-domain
1500 (define-public bless
1506 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1510 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1511 (modules '((guix build utils)))
1514 ;; Remove bundled boost, pigz, zlib, and .git directory
1515 ;; FIXME: also remove bundled sources for murmurhash3 and
1516 ;; kmc once packaged.
1517 (delete-file-recursively "boost")
1518 (delete-file-recursively "pigz")
1519 (delete-file-recursively "google-sparsehash")
1520 (delete-file-recursively "zlib")
1521 (delete-file-recursively ".git")
1523 (build-system gnu-build-system)
1525 '(#:tests? #f ;no "check" target
1527 (list (string-append "ZLIB="
1528 (assoc-ref %build-inputs "zlib:static")
1530 (string-append "LDFLAGS="
1531 (string-join '("-lboost_filesystem"
1537 (modify-phases %standard-phases
1538 (add-after 'unpack 'do-not-build-bundled-pigz
1539 (lambda* (#:key inputs outputs #:allow-other-keys)
1540 (substitute* "Makefile"
1541 (("cd pigz/pigz-2.3.3; make") ""))
1543 (add-after 'unpack 'patch-paths-to-executables
1544 (lambda* (#:key inputs outputs #:allow-other-keys)
1545 (substitute* "parse_args.cpp"
1546 (("kmc_binary = .*")
1547 (string-append "kmc_binary = \""
1548 (assoc-ref outputs "out")
1550 (("pigz_binary = .*")
1551 (string-append "pigz_binary = \""
1552 (assoc-ref inputs "pigz")
1556 (lambda* (#:key outputs #:allow-other-keys)
1557 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1558 (for-each (lambda (file)
1559 (install-file file bin))
1560 '("bless" "kmc/bin/kmc"))
1562 (delete 'configure))))
1566 `(("openmpi" ,openmpi)
1568 ("sparsehash" ,sparsehash)
1570 ("zlib:static" ,zlib "static")
1572 (supported-systems '("x86_64-linux"))
1573 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1574 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1576 "@dfn{Bloom-filter-based error correction solution for high-throughput
1577 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1578 correction tool for genomic reads produced by @dfn{Next-generation
1579 sequencing} (NGS). BLESS produces accurate correction results with much less
1580 memory compared with previous solutions and is also able to tolerate a higher
1581 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1582 errors at the end of reads.")
1583 (license license:gpl3+)))
1585 (define-public bowtie
1592 (url "https://github.com/BenLangmead/bowtie2")
1593 (commit (string-append "v" version))))
1594 (file-name (git-file-name name version))
1597 "1zl3cf327y2p7p03cavymbh7b00djc7lncfaqih33n96iy9q8ibp"))
1598 (modules '((guix build utils)))
1601 (substitute* "Makefile"
1602 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1603 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1604 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
1606 (build-system gnu-build-system)
1611 (string-append "prefix=" (assoc-ref %outputs "out")))
1613 (modify-phases %standard-phases
1618 "scripts/test/simple_tests.pl"
1619 "--bowtie2=./bowtie2"
1620 "--bowtie2-build=./bowtie2-build")
1625 ("python" ,python-wrapper)))
1628 ("perl-clone" ,perl-clone)
1629 ("perl-test-deep" ,perl-test-deep)
1630 ("perl-test-simple" ,perl-test-simple)))
1631 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1632 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1634 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1635 reads to long reference sequences. It is particularly good at aligning reads
1636 of about 50 up to 100s or 1,000s of characters, and particularly good at
1637 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1638 genome with an FM Index to keep its memory footprint small: for the human
1639 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1640 gapped, local, and paired-end alignment modes.")
1641 (supported-systems '("x86_64-linux"))
1642 (license license:gpl3+)))
1644 (define-public bowtie1
1650 (uri (string-append "mirror://sourceforge/bowtie-bio/bowtie/"
1651 version "/bowtie-src-x86_64.zip"))
1654 "0vmiqdhc9dzyfy9sh6vgi7k9xy2hiw8g87vbamnc6cgpm179zsa4"))
1655 (modules '((guix build utils)))
1657 '(substitute* "Makefile"
1658 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1659 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1660 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1661 (build-system gnu-build-system)
1663 '(#:tests? #f ; no "check" target
1666 (string-append "prefix=" (assoc-ref %outputs "out")))
1668 (modify-phases %standard-phases
1669 (delete 'configure))))
1671 `(("python-wrapper" ,python-wrapper)
1674 (supported-systems '("x86_64-linux"))
1675 (home-page "http://bowtie-bio.sourceforge.net/index.shtml")
1676 (synopsis "Fast aligner for short nucleotide sequence reads")
1678 "Bowtie is a fast, memory-efficient short read aligner. It aligns short
1679 DNA sequences (reads) to the human genome at a rate of over 25 million 35-bp
1680 reads per hour. Bowtie indexes the genome with a Burrows-Wheeler index to
1681 keep its memory footprint small: typically about 2.2 GB for the human
1682 genome (2.9 GB for paired-end).")
1683 (license license:artistic2.0)))
1685 (define-public tophat
1692 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1696 "19add02kv2xhd6ihd779dr7x35ggym3jqr0m5c4315i1yfb0p11p"))
1697 (modules '((guix build utils)))
1700 ;; Remove bundled SeqAn and samtools
1701 (delete-file-recursively "src/SeqAn-1.4.2")
1702 (delete-file-recursively "src/samtools-0.1.18")
1704 (build-system gnu-build-system)
1706 '(#:parallel-build? #f ; not supported
1708 (modify-phases %standard-phases
1709 (add-after 'set-paths 'hide-default-gcc
1710 (lambda* (#:key inputs #:allow-other-keys)
1711 (let ((gcc (assoc-ref inputs "gcc")))
1712 ;; Remove the default GCC from CPLUS_INCLUDE_PATH to prevent
1713 ;; conflicts with the GCC 5 input.
1714 (setenv "CPLUS_INCLUDE_PATH"
1716 (delete (string-append gcc "/include/c++")
1717 (string-split (getenv "CPLUS_INCLUDE_PATH") #\:))
1720 (add-after 'unpack 'use-system-samtools
1721 (lambda* (#:key inputs #:allow-other-keys)
1722 (substitute* "src/Makefile.in"
1723 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1724 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1725 (("SAMPROG = samtools_0\\.1\\.18") "")
1726 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1727 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1728 (substitute* '("src/common.cpp"
1730 (("samtools_0.1.18") (which "samtools")))
1731 (substitute* '("src/common.h"
1732 "src/bam2fastx.cpp")
1733 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1734 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1735 (substitute* '("src/bwt_map.h"
1737 "src/align_status.h")
1738 (("#include <bam.h>") "#include <samtools/bam.h>")
1739 (("#include <sam.h>") "#include <samtools/sam.h>"))
1742 `(("gcc@5" ,gcc-5))) ;; doesn't build with later versions
1746 ("ncurses" ,ncurses)
1748 ("python" ,python-2)
1749 ("samtools" ,samtools-0.1)
1752 (home-page "https://ccb.jhu.edu/software/tophat/index.shtml")
1753 (synopsis "Spliced read mapper for RNA-Seq data")
1755 "TopHat is a fast splice junction mapper for nucleotide sequence
1756 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1757 mammalian-sized genomes using the ultra high-throughput short read
1758 aligner Bowtie, and then analyzes the mapping results to identify
1759 splice junctions between exons.")
1760 ;; TopHat is released under the Boost Software License, Version 1.0
1761 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1762 (license license:boost1.0)))
1771 "https://github.com/lh3/bwa/releases/download/v"
1772 version "/bwa-" version ".tar.bz2"))
1775 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1776 (build-system gnu-build-system)
1778 '(#:tests? #f ;no "check" target
1780 (modify-phases %standard-phases
1782 (lambda* (#:key outputs #:allow-other-keys)
1783 (let* ((out (assoc-ref outputs "out"))
1784 (bin (string-append out "/bin"))
1785 (lib (string-append out "/lib"))
1786 (doc (string-append out "/share/doc/bwa"))
1787 (man (string-append out "/share/man/man1")))
1788 (install-file "bwa" bin)
1789 (install-file "libbwa.a" lib)
1790 (install-file "README.md" doc)
1791 (install-file "bwa.1" man))
1793 ;; no "configure" script
1794 (delete 'configure))))
1795 (inputs `(("zlib" ,zlib)))
1796 ;; Non-portable SSE instructions are used so building fails on platforms
1797 ;; other than x86_64.
1798 (supported-systems '("x86_64-linux"))
1799 (home-page "http://bio-bwa.sourceforge.net/")
1800 (synopsis "Burrows-Wheeler sequence aligner")
1802 "BWA is a software package for mapping low-divergent sequences against a
1803 large reference genome, such as the human genome. It consists of three
1804 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1805 designed for Illumina sequence reads up to 100bp, while the rest two for
1806 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1807 features such as long-read support and split alignment, but BWA-MEM, which is
1808 the latest, is generally recommended for high-quality queries as it is faster
1809 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1810 70-100bp Illumina reads.")
1811 (license license:gpl3+)))
1813 (define-public bwa-pssm
1814 (package (inherit bwa)
1820 (url "https://github.com/pkerpedjiev/bwa-pssm")
1822 (file-name (git-file-name name version))
1825 "076c4q0cdqz8jgylb067y9zmvxglppnzi3qiscn0xiypgc6lgb5r"))))
1826 (build-system gnu-build-system)
1831 (home-page "http://bwa-pssm.binf.ku.dk/")
1832 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1834 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1835 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1836 existing aligners it is fast and sensitive. Unlike most other aligners,
1837 however, it is also adaptible in the sense that one can direct the alignment
1838 based on known biases within the data set. It is coded as a modification of
1839 the original BWA alignment program and shares the genome index structure as
1840 well as many of the command line options.")
1841 (license license:gpl3+)))
1843 (define-public bwa-meth
1850 (url "https://github.com/brentp/bwa-meth")
1851 (commit (string-append "v" version))))
1852 (file-name (git-file-name name version))
1855 "17j31i7zws5j7mhsq9x3qgkxly6mlmrgwhfq0qbflgxrmx04yaiz"))))
1856 (build-system python-build-system)
1859 (modify-phases %standard-phases
1860 (add-after 'unpack 'keep-references-to-bwa
1861 (lambda* (#:key inputs #:allow-other-keys)
1862 (substitute* "bwameth.py"
1863 (("bwa (mem|index)" _ command)
1864 (string-append (which "bwa") " " command))
1865 ;; There's an ill-advised check for "samtools" on PATH.
1871 `(("python-toolshed" ,python-toolshed)))
1872 (home-page "https://github.com/brentp/bwa-meth")
1873 (synopsis "Fast and accurante alignment of BS-Seq reads")
1875 "BWA-Meth works for single-end reads and for paired-end reads from the
1876 directional protocol (most common). It uses the method employed by
1877 methylcoder and Bismark of in silico conversion of all C's to T's in both
1878 reference and reads. It recovers the original read (needed to tabulate
1879 methylation) by attaching it as a comment which BWA appends as a tag to the
1880 read. It performs favorably to existing aligners gauged by number of on and
1881 off-target reads for a capture method that targets CpG-rich region.")
1882 (license license:expat)))
1884 (define-public python-bx-python
1886 (name "python-bx-python")
1890 (uri (pypi-uri "bx-python" version))
1893 "11kksg2rbzihpmcid823xvg42xi88m7sz58rzk29abybkxy0rszs"))))
1894 (build-system python-build-system)
1895 ;; Tests fail because test data are not included
1896 (arguments '(#:tests? #f))
1898 `(("python-numpy" ,python-numpy)
1899 ("python-six" ,python-six)))
1903 `(("python-lzo" ,python-lzo)
1904 ("python-nose" ,python-nose)
1905 ("python-cython" ,python-cython)))
1906 (home-page "https://github.com/bxlab/bx-python")
1907 (synopsis "Tools for manipulating biological data")
1909 "bx-python provides tools for manipulating biological data, particularly
1910 multiple sequence alignments.")
1911 (license license:expat)))
1913 (define-public python2-bx-python
1914 (package-with-python2 python-bx-python))
1916 (define-public python-pysam
1918 (name "python-pysam")
1922 ;; Test data is missing on PyPi.
1924 (url "https://github.com/pysam-developers/pysam")
1925 (commit (string-append "v" version))))
1926 (file-name (git-file-name name version))
1929 "1vj367w6xbn9bpmksm162l1aipf7cj97h1q83y7jcpm33ihwpf7x"))
1930 (modules '((guix build utils)))
1932 ;; Drop bundled htslib. TODO: Also remove samtools
1934 (delete-file-recursively "htslib")
1936 (build-system python-build-system)
1938 `(#:modules ((ice-9 ftw)
1940 (guix build python-build-system)
1943 (modify-phases %standard-phases
1944 (add-before 'build 'set-flags
1945 (lambda* (#:key inputs #:allow-other-keys)
1946 (setenv "HTSLIB_MODE" "external")
1947 (setenv "HTSLIB_LIBRARY_DIR"
1948 (string-append (assoc-ref inputs "htslib") "/lib"))
1949 (setenv "HTSLIB_INCLUDE_DIR"
1950 (string-append (assoc-ref inputs "htslib") "/include"))
1951 (setenv "LDFLAGS" "-lncurses")
1952 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1955 (lambda* (#:key inputs outputs #:allow-other-keys)
1956 ;; This file contains tests that require a connection to the
1958 (delete-file "tests/tabix_test.py")
1959 ;; FIXME: This test fails
1960 (delete-file "tests/AlignmentFile_test.py")
1961 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1962 (setenv "PYTHONPATH"
1964 (getenv "PYTHONPATH")
1965 ":" (getcwd) "/build/"
1966 (car (scandir "build"
1967 (negate (cut string-prefix? "." <>))))))
1968 ;; Step out of source dir so python does not import from CWD.
1969 (with-directory-excursion "tests"
1970 (setenv "HOME" "/tmp")
1971 (invoke "make" "-C" "pysam_data")
1972 (invoke "make" "-C" "cbcf_data")
1973 ;; Running nosetests without explicitly asking for a single
1974 ;; process leads to a crash. Running with multiple processes
1975 ;; fails because the tests are not designed to run in parallel.
1977 ;; FIXME: tests keep timing out on some systems.
1978 (invoke "nosetests" "-v" "--processes" "1")))))))
1980 `(("htslib" ,htslib-1.9))) ; Included from installed header files.
1982 `(("ncurses" ,ncurses)
1986 `(("python-cython" ,python-cython)
1987 ;; Dependencies below are are for tests only.
1988 ("samtools" ,samtools-1.9)
1989 ("bcftools" ,bcftools-1.9)
1990 ("python-nose" ,python-nose)))
1991 (home-page "https://github.com/pysam-developers/pysam")
1992 (synopsis "Python bindings to the SAMtools C API")
1994 "Pysam is a Python module for reading and manipulating files in the
1995 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1996 also includes an interface for tabix.")
1997 (license license:expat)))
1999 (define-public python2-pysam
2000 (package-with-python2 python-pysam))
2002 (define-public python-twobitreader
2004 (name "python-twobitreader")
2009 (url "https://github.com/benjschiller/twobitreader")
2011 (file-name (git-file-name name version))
2014 "1qbxvv1h58cismbk1anpjrkpghsaiy64a11ir3lhy6qch6xf8n62"))))
2015 (build-system python-build-system)
2016 ;; Tests are not included
2017 (arguments '(#:tests? #f))
2019 `(("python-sphinx" ,python-sphinx)))
2020 (home-page "https://github.com/benjschiller/twobitreader")
2021 (synopsis "Python library for reading .2bit files")
2023 "twobitreader is a Python library for reading .2bit files as used by the
2024 UCSC genome browser.")
2025 (license license:artistic2.0)))
2027 (define-public python2-twobitreader
2028 (package-with-python2 python-twobitreader))
2030 (define-public python-plastid
2032 (name "python-plastid")
2036 (uri (pypi-uri "plastid" version))
2039 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
2040 (build-system python-build-system)
2042 ;; Some test files are not included.
2045 `(("python-numpy" ,python-numpy)
2046 ("python-scipy" ,python-scipy)
2047 ("python-pandas" ,python-pandas)
2048 ("python-pysam" ,python-pysam)
2049 ("python-matplotlib" ,python-matplotlib)
2050 ("python-biopython" ,python-biopython)
2051 ("python-twobitreader" ,python-twobitreader)
2052 ("python-termcolor" ,python-termcolor)))
2054 `(("python-cython" ,python-cython)
2055 ("python-nose" ,python-nose)))
2056 (home-page "https://github.com/joshuagryphon/plastid")
2057 (synopsis "Python library for genomic analysis")
2059 "plastid is a Python library for genomic analysis – in particular,
2060 high-throughput sequencing data – with an emphasis on simplicity.")
2061 (license license:bsd-3)))
2063 (define-public python2-plastid
2064 (package-with-python2 python-plastid))
2066 (define-public tetoolkit
2073 (url "https://github.com/mhammell-laboratory/tetoolkit")
2075 (file-name (git-file-name name version))
2078 "1yzi0kfpzip8zpjb82x1ik6h22yzfyjiz2dv85v6as2awwqvk807"))))
2079 (build-system python-build-system)
2081 `(#:python ,python-2 ; not guaranteed to work with Python 3
2083 (modify-phases %standard-phases
2084 (add-after 'unpack 'make-writable
2086 (for-each make-file-writable (find-files "."))
2088 (add-after 'unpack 'patch-invocations
2089 (lambda* (#:key inputs #:allow-other-keys)
2090 (substitute* '("bin/TEtranscripts"
2093 (string-append "'" (which "sort") " "))
2095 (string-append "'" (which "rm") " -f "))
2096 (("'Rscript'") (string-append "'" (which "Rscript") "'")))
2097 (substitute* "TEToolkit/IO/ReadInputs.py"
2098 (("BamToBED") (which "bamToBed")))
2099 (substitute* "TEToolkit/Normalization.py"
2101 (string-append "\"" (which "Rscript") "\"")))
2103 (add-after 'install 'wrap-program
2104 (lambda* (#:key outputs #:allow-other-keys)
2105 ;; Make sure the executables find R packages.
2106 (let ((out (assoc-ref outputs "out")))
2109 (wrap-program (string-append out "/bin/" script)
2110 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
2115 `(("coreutils" ,coreutils)
2116 ("bedtools" ,bedtools)
2117 ("python-argparse" ,python2-argparse)
2118 ("python-pysam" ,python2-pysam)
2119 ("r-minimal" ,r-minimal)
2120 ("r-deseq2" ,r-deseq2)))
2121 (home-page "https://github.com/mhammell-laboratory/tetoolkit")
2122 (synopsis "Transposable elements in differential enrichment analysis")
2124 "This is package for including transposable elements in differential
2125 enrichment analysis of sequencing datasets. TEtranscripts and TEcount take
2126 RNA-seq (and similar data) and annotates reads to both genes and transposable
2127 elements. TEtranscripts then performs differential analysis using DESeq2.
2128 Note that TEtranscripts and TEcount rely on specially curated GTF files, which
2129 are not included due to their size.")
2130 (license license:gpl3+)))
2132 (define-public cd-hit
2138 (uri (string-append "https://github.com/weizhongli/cdhit"
2139 "/releases/download/V" version
2141 "-2017-0621-source.tar.gz"))
2144 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
2145 (build-system gnu-build-system)
2147 `(#:tests? #f ; there are no tests
2149 ;; Executables are copied directly to the PREFIX.
2150 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin")
2151 ;; Support longer sequences (e.g. Pacbio sequences)
2154 (modify-phases %standard-phases
2155 ;; No "configure" script
2157 ;; Remove sources of non-determinism
2158 (add-after 'unpack 'be-timeless
2160 (substitute* "cdhit-utility.c++"
2161 ((" \\(built on \" __DATE__ \"\\)") ""))
2162 (substitute* "cdhit-common.c++"
2163 (("__DATE__") "\"0\"")
2164 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
2166 ;; The "install" target does not create the target directory.
2167 (add-before 'install 'create-target-dir
2168 (lambda* (#:key outputs #:allow-other-keys)
2169 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
2173 (home-page "http://weizhongli-lab.org/cd-hit/")
2174 (synopsis "Cluster and compare protein or nucleotide sequences")
2176 "CD-HIT is a program for clustering and comparing protein or nucleotide
2177 sequences. CD-HIT is designed to be fast and handle extremely large
2179 ;; The manual says: "It can be copied under the GNU General Public License
2180 ;; version 2 (GPLv2)."
2181 (license license:gpl2)))
2183 (define-public clipper
2190 (url "https://github.com/YeoLab/clipper")
2192 (file-name (git-file-name name version))
2195 "1bcag4lb5bkzsj2vg7lrq24aw6yfgq275ifrbhd82l7kqgbbjbkv"))))
2196 (build-system python-build-system)
2199 (modify-phases %standard-phases
2200 (add-before 'reset-gzip-timestamps 'make-files-writable
2201 (lambda* (#:key outputs #:allow-other-keys)
2202 ;; Make sure .gz files are writable so that the
2203 ;; 'reset-gzip-timestamps' phase can do its work.
2204 (let ((out (assoc-ref outputs "out")))
2205 (for-each make-file-writable
2206 (find-files out "\\.gz$"))
2210 ("python-pybedtools" ,python-pybedtools)
2211 ("python-cython" ,python-cython)
2212 ("python-scikit-learn" ,python-scikit-learn)
2213 ("python-matplotlib" ,python-matplotlib)
2214 ("python-pandas" ,python-pandas)
2215 ("python-pysam" ,python-pysam)
2216 ("python-numpy" ,python-numpy)
2217 ("python-scipy" ,python-scipy)))
2219 `(("python-setuptools-git" ,python-setuptools-git)
2220 ("python-mock" ,python-mock) ; for tests
2221 ("python-nose" ,python-nose) ; for tests
2222 ("python-pytz" ,python-pytz))) ; for tests
2223 (home-page "https://github.com/YeoLab/clipper")
2224 (synopsis "CLIP peak enrichment recognition")
2226 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
2227 (license license:gpl2)))
2229 (define-public codingquarry
2231 (name "codingquarry")
2236 "mirror://sourceforge/codingquarry/CodingQuarry_v"
2240 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
2241 (build-system gnu-build-system)
2243 '(#:tests? #f ; no "check" target
2245 (modify-phases %standard-phases
2248 (lambda* (#:key outputs #:allow-other-keys)
2249 (let* ((out (assoc-ref outputs "out"))
2250 (bin (string-append out "/bin"))
2251 (doc (string-append out "/share/doc/codingquarry")))
2252 (install-file "INSTRUCTIONS.pdf" doc)
2253 (copy-recursively "QuarryFiles"
2254 (string-append out "/QuarryFiles"))
2255 (install-file "CodingQuarry" bin)
2256 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin))
2258 (inputs `(("openmpi" ,openmpi)))
2259 (native-search-paths
2260 (list (search-path-specification
2261 (variable "QUARRY_PATH")
2262 (files '("QuarryFiles")))))
2263 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
2264 (synopsis "Fungal gene predictor")
2265 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
2266 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
2267 (home-page "https://sourceforge.net/projects/codingquarry/")
2268 (license license:gpl3+)))
2270 (define-public couger
2277 "http://couger.oit.duke.edu/static/assets/COUGER"
2281 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
2282 (build-system gnu-build-system)
2286 (modify-phases %standard-phases
2291 (lambda* (#:key outputs #:allow-other-keys)
2292 (let* ((out (assoc-ref outputs "out"))
2293 (bin (string-append out "/bin")))
2294 (copy-recursively "src" (string-append out "/src"))
2296 ;; Add "src" directory to module lookup path.
2297 (substitute* "couger"
2299 (string-append "import sys\nsys.path.append(\""
2300 out "\")\nfrom argparse")))
2301 (install-file "couger" bin))
2304 'install 'wrap-program
2305 (lambda* (#:key inputs outputs #:allow-other-keys)
2306 ;; Make sure 'couger' runs with the correct PYTHONPATH.
2307 (let* ((out (assoc-ref outputs "out"))
2308 (path (getenv "PYTHONPATH")))
2309 (wrap-program (string-append out "/bin/couger")
2310 `("PYTHONPATH" ":" prefix (,path))))
2313 `(("python" ,python-2)
2314 ("python2-pillow" ,python2-pillow)
2315 ("python2-numpy" ,python2-numpy)
2316 ("python2-scipy" ,python2-scipy)
2317 ("python2-matplotlib" ,python2-matplotlib)))
2319 `(("r-minimal" ,r-minimal)
2321 ("randomjungle" ,randomjungle)))
2323 `(("unzip" ,unzip)))
2324 (home-page "http://couger.oit.duke.edu")
2325 (synopsis "Identify co-factors in sets of genomic regions")
2327 "COUGER can be applied to any two sets of genomic regions bound by
2328 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
2329 putative co-factors that provide specificity to each TF. The framework
2330 determines the genomic targets uniquely-bound by each TF, and identifies a
2331 small set of co-factors that best explain the in vivo binding differences
2332 between the two TFs.
2334 COUGER uses classification algorithms (support vector machines and random
2335 forests) with features that reflect the DNA binding specificities of putative
2336 co-factors. The features are generated either from high-throughput TF-DNA
2337 binding data (from protein binding microarray experiments), or from large
2338 collections of DNA motifs.")
2339 (license license:gpl3+)))
2341 (define-public clustal-omega
2343 (name "clustal-omega")
2347 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
2351 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
2352 (build-system gnu-build-system)
2354 `(("argtable" ,argtable)))
2355 (home-page "http://www.clustal.org/omega/")
2356 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
2358 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
2359 program for protein and DNA/RNA. It produces high quality MSAs and is capable
2360 of handling data-sets of hundreds of thousands of sequences in reasonable
2362 (license license:gpl2+)))
2364 (define-public crossmap
2370 (uri (pypi-uri "CrossMap" version))
2373 "1sb2f2qbxya4fzw3yjl09vbrs8vfmw22zrygrvz004sf9gb1vkan"))))
2374 (build-system python-build-system)
2376 `(("python-bx-python" ,python-bx-python)
2377 ("python-numpy" ,python-numpy)
2378 ("python-pybigwig" ,python-pybigwig)
2379 ("python-pysam" ,python-pysam)
2382 `(("python-cython" ,python-cython)
2383 ("python-nose" ,python-nose)))
2384 (home-page "http://crossmap.sourceforge.net/")
2385 (synopsis "Convert genome coordinates between assemblies")
2387 "CrossMap is a program for conversion of genome coordinates or annotation
2388 files between different genome assemblies. It supports most commonly used
2389 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
2390 (license license:gpl2+)))
2392 (define-public python-dnaio
2394 (name "python-dnaio")
2399 (uri (pypi-uri "dnaio" version))
2402 "0f16m7hdlm0fz1n7y5asy0v9ghyrq17ni1p9iybq22ddzyd49r27"))))
2403 (build-system python-build-system)
2405 `(("python-cython" ,python-cython)
2406 ("python-pytest" ,python-pytest)
2407 ("python-xopen" ,python-xopen)))
2408 (home-page "https://github.com/marcelm/dnaio/")
2409 (synopsis "Read FASTA and FASTQ files efficiently")
2411 "dnaio is a Python library for fast parsing of FASTQ and also FASTA
2412 files. The code was previously part of the cutadapt tool.")
2413 (license license:expat)))
2415 (define-public python-deeptoolsintervals
2417 (name "python-deeptoolsintervals")
2421 (uri (pypi-uri "deeptoolsintervals" version))
2424 "1xnl80nblysj6dylj4683wgrfa425rkx4dp5k65hvwdns9pw753x"))))
2425 (build-system python-build-system)
2428 (home-page "https://github.com/deeptools/deeptools_intervals")
2429 (synopsis "Create GTF-based interval trees with associated meta-data")
2431 "This package provides a Python module creating/accessing GTF-based
2432 interval trees with associated meta-data. It is primarily used by the
2433 @code{deeptools} package.")
2434 (license license:expat)))
2436 (define-public python-deeptools
2438 (name "python-deeptools")
2443 (url "https://github.com/deeptools/deepTools")
2445 (file-name (git-file-name name version))
2448 "0l09vyynz6s6w7fnyd94rpys4a6aja6kp4gli64pngdxdz3md1nl"))))
2449 (build-system python-build-system)
2451 `(("python-mock" ,python-mock)
2452 ("python-nose" ,python-nose)))
2454 `(("python-matplotlib" ,python-matplotlib)
2455 ("python-numpy" ,python-numpy)
2456 ("python-numpydoc" ,python-numpydoc)
2457 ("python-py2bit" ,python-py2bit)
2458 ("python-pybigwig" ,python-pybigwig)
2459 ("python-pysam" ,python-pysam)
2460 ("python-scipy" ,python-scipy)
2461 ("python-deeptoolsintervals" ,python-deeptoolsintervals)
2462 ("python-plotly" ,python-plotly-2.4.1)))
2463 (home-page "https://pypi.org/project/deepTools/")
2464 (synopsis "Useful tools for exploring deep sequencing data")
2465 (description "This package addresses the challenge of handling large amounts
2466 of data that are now routinely generated from DNA sequencing centers.
2467 @code{deepTools} contains useful modules to process the mapped reads data for
2468 multiple quality checks, creating normalized coverage files in standard bedGraph
2469 and bigWig file formats, that allow comparison between different files. Finally,
2470 using such normalized and standardized files, deepTools can create many
2471 publication-ready visualizations to identify enrichments and for functional
2472 annotations of the genome.")
2473 ;; The file deeptools/cm.py is licensed under the BSD license. The
2474 ;; remainder of the code is licensed under the MIT license.
2475 (license (list license:bsd-3 license:expat))))
2477 (define-deprecated deeptools python-deeptools)
2479 (define-public cutadapt
2485 (uri (pypi-uri "cutadapt" version))
2488 "1vqmsfkm6llxzmsz9wcfcvzx9a9f8iabvwik2rbyn7nc4wm25z89"))))
2489 (build-system python-build-system)
2491 `(("python-dnaio" ,python-dnaio)
2492 ("python-xopen" ,python-xopen)))
2494 `(("python-cython" ,python-cython)
2495 ("python-pytest" ,python-pytest)
2496 ("python-setuptools-scm" ,python-setuptools-scm)))
2497 (home-page "https://cutadapt.readthedocs.io/en/stable/")
2498 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
2500 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
2501 other types of unwanted sequence from high-throughput sequencing reads.")
2502 (license license:expat)))
2504 (define-public libbigwig
2511 (url "https://github.com/dpryan79/libBigWig")
2513 (file-name (git-file-name name version))
2516 "09693dmf1scdac5pyq6qyn8b4mcipvnmc370k9a5z41z81m3dcsj"))))
2517 (build-system gnu-build-system)
2519 `(#:test-target "test"
2520 #:tests? #f ; tests require access to the web
2523 (string-append "prefix=" (assoc-ref %outputs "out")))
2525 (modify-phases %standard-phases
2526 (delete 'configure))))
2531 `(("doxygen" ,doxygen)
2533 ("python" ,python-2)))
2534 (home-page "https://github.com/dpryan79/libBigWig")
2535 (synopsis "C library for handling bigWig files")
2537 "This package provides a C library for parsing local and remote BigWig
2539 (license license:expat)))
2541 (define-public python-pybigwig
2543 (name "python-pybigwig")
2547 (uri (pypi-uri "pyBigWig" version))
2550 "157x6v48y299zm382krf1dw08fdxg95im8lnabhp5vc94s04zxj1"))
2551 (modules '((guix build utils)))
2554 ;; Delete bundled libBigWig sources
2555 (delete-file-recursively "libBigWig")
2557 (build-system python-build-system)
2560 (modify-phases %standard-phases
2561 (add-after 'unpack 'link-with-libBigWig
2562 (lambda* (#:key inputs #:allow-other-keys)
2563 (substitute* "setup.py"
2564 (("libs=\\[") "libs=[\"BigWig\", "))
2567 `(("python-numpy" ,python-numpy)))
2569 `(("libbigwig" ,libbigwig)
2572 (home-page "https://github.com/dpryan79/pyBigWig")
2573 (synopsis "Access bigWig files in Python using libBigWig")
2575 "This package provides Python bindings to the libBigWig library for
2576 accessing bigWig files.")
2577 (license license:expat)))
2579 (define-public python2-pybigwig
2580 (package-with-python2 python-pybigwig))
2582 (define-public python-dendropy
2584 (name "python-dendropy")
2589 ;; Source from GitHub so that tests are included.
2591 (url "https://github.com/jeetsukumaran/DendroPy")
2592 (commit (string-append "v" version))))
2593 (file-name (git-file-name name version))
2596 "097hfyv2kaf4x92i4rjx0paw2cncxap48qivv8zxng4z7nhid0x9"))))
2597 (build-system python-build-system)
2598 (home-page "https://dendropy.org/")
2599 (synopsis "Library for phylogenetics and phylogenetic computing")
2601 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
2602 writing, simulation, processing and manipulation of phylogenetic
2603 trees (phylogenies) and characters.")
2604 (license license:bsd-3)))
2606 (define-public python2-dendropy
2607 (let ((base (package-with-python2 python-dendropy)))
2612 (modify-phases %standard-phases
2613 (add-after 'unpack 'remove-failing-test
2615 ;; This test fails when the full test suite is run, as documented
2616 ;; at https://github.com/jeetsukumaran/DendroPy/issues/74
2617 (substitute* "tests/test_dataio_nexml_reader_tree_list.py"
2618 (("test_collection_comments_and_annotations")
2619 "do_not_test_collection_comments_and_annotations"))
2621 ,@(package-arguments base))))))
2623 (define-public python-py2bit
2625 (name "python-py2bit")
2630 (uri (pypi-uri "py2bit" version))
2633 "1vw2nvw1yrl7ikkqsqs1pg239yr5nspvd969r1x9arms1k25a1a5"))))
2634 (build-system python-build-system)
2635 (home-page "https://github.com/dpryan79/py2bit")
2636 (synopsis "Access 2bit files using lib2bit")
2638 "This package provides Python bindings for lib2bit to access 2bit files
2640 (license license:expat)))
2642 (define-public delly
2649 (url "https://github.com/dellytools/delly")
2650 (commit (string-append "v" version))))
2651 (file-name (git-file-name name version))
2653 (base32 "1ibnplgfzj96w8glkx17v7sld3pm402fr5ybmf3h0rlcryabxrqy"))
2654 (modules '((guix build utils)))
2657 (delete-file-recursively "src/htslib")
2659 (build-system gnu-build-system)
2661 `(#:tests? #f ; There are no tests to run.
2663 (list "PARALLEL=1" ; Allow parallel execution at run-time.
2664 (string-append "prefix=" (assoc-ref %outputs "out")))
2666 (modify-phases %standard-phases
2667 (delete 'configure) ; There is no configure phase.
2668 (add-after 'install 'install-templates
2669 (lambda* (#:key outputs #:allow-other-keys)
2670 (let ((templates (string-append (assoc-ref outputs "out")
2671 "/share/delly/templates")))
2673 (copy-recursively "excludeTemplates" templates)
2680 (home-page "https://github.com/dellytools/delly")
2681 (synopsis "Integrated structural variant prediction method")
2682 (description "Delly is an integrated structural variant prediction method
2683 that can discover and genotype deletions, tandem duplications, inversions and
2684 translocations at single-nucleotide resolution in short-read massively parallel
2685 sequencing data. It uses paired-ends and split-reads to sensitively and
2686 accurately delineate genomic rearrangements throughout the genome.")
2687 (license license:gpl3+)))
2689 (define-public diamond
2696 (url "https://github.com/bbuchfink/diamond")
2697 (commit (string-append "v" version))))
2698 (file-name (git-file-name name version))
2701 "0k6f3kb6cniw11xw6763kkbs1sl0yack7xsy7q5fl5v170ssphq4"))))
2702 (build-system cmake-build-system)
2704 '(#:tests? #f ; no "check" target
2706 (modify-phases %standard-phases
2707 (add-after 'unpack 'remove-native-compilation
2709 (substitute* "CMakeLists.txt" (("-march=native") ""))
2713 (home-page "https://github.com/bbuchfink/diamond")
2714 (synopsis "Accelerated BLAST compatible local sequence aligner")
2716 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2717 translated DNA query sequences against a protein reference database (BLASTP
2718 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2719 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2720 data and settings.")
2721 (license license:agpl3+)))
2723 (define-public discrover
2731 (url "https://github.com/maaskola/discrover")
2733 (file-name (git-file-name name version))
2736 "173fwi2vb6a5kp406hm3jj6j7v4whww796f2qcygp4rpvamh307y"))))
2737 (build-system cmake-build-system)
2739 `(#:tests? #f ; there are no tests
2741 (modify-phases %standard-phases
2742 (add-after 'unpack 'fix-latex-errors
2744 (with-fluids ((%default-port-encoding #f))
2745 (substitute* "doc/references.bib"
2746 (("\\{S\\}illanp[^,]+,")
2747 "{S}illanp{\\\"a}{\\\"a},")))
2748 ;; XXX: I just can't get pdflatex to not complain about these
2749 ;; characters. They end up in the manual via the generated
2750 ;; discrover-cli-help.txt.
2751 (substitute* "src/hmm/cli.cpp"
2755 ;; This seems to be a syntax error.
2756 (substitute* "doc/discrover-manual.tex"
2757 (("theverbbox\\[t\\]") "theverbbox"))
2759 (add-after 'unpack 'add-missing-includes
2761 (substitute* "src/executioninformation.hpp"
2762 (("#define EXECUTIONINFORMATION_HPP" line)
2763 (string-append line "\n#include <random>")))
2764 (substitute* "src/plasma/fasta.hpp"
2765 (("#define FASTA_HPP" line)
2766 (string-append line "\n#include <random>")))
2768 ;; FIXME: this is needed because we're using texlive-union, which
2769 ;; doesn't handle fonts correctly. It expects to be able to generate
2770 ;; fonts in the home directory.
2771 (add-before 'build 'setenv-HOME
2772 (lambda _ (setenv "HOME" "/tmp") #t)))))
2776 ("rmath-standalone" ,rmath-standalone)))
2778 `(("texlive" ,(texlive-union (list texlive-fonts-cm
2779 texlive-fonts-amsfonts
2782 texlive-latex-examplep
2783 texlive-latex-hyperref
2785 texlive-latex-natbib
2786 texlive-bibtex ; style files used by natbib
2787 texlive-latex-pgf ; tikz
2788 texlive-latex-verbatimbox)))
2789 ("imagemagick" ,imagemagick)))
2790 (home-page "https://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2791 (synopsis "Discover discriminative nucleotide sequence motifs")
2792 (description "Discrover is a motif discovery method to find binding sites
2793 of nucleic acid binding proteins.")
2794 (license license:gpl3+)))
2796 (define-public eigensoft
2804 (url "https://github.com/DReichLab/EIG")
2805 (commit (string-append "v" version))))
2806 (file-name (git-file-name name version))
2809 "1c141fqvhnzibmnf22sv23vbmzm20kjjyrib44cfh75wyndp2d9k"))
2810 (modules '((guix build utils)))
2811 ;; Remove pre-built binaries.
2813 (delete-file-recursively "bin")
2816 (build-system gnu-build-system)
2818 `(#:tests? #f ; There are no tests.
2819 #:make-flags '("CC=gcc")
2821 (modify-phases %standard-phases
2822 ;; There is no configure phase, but the Makefile is in a
2825 (lambda _ (chdir "src") #t))
2826 ;; The provided install target only copies executables to
2827 ;; the "bin" directory in the build root.
2828 (add-after 'install 'actually-install
2829 (lambda* (#:key outputs #:allow-other-keys)
2830 (let* ((out (assoc-ref outputs "out"))
2831 (bin (string-append out "/bin")))
2832 (for-each (lambda (file)
2833 (install-file file bin))
2834 (find-files "../bin" ".*"))
2839 ("openblas" ,openblas)
2841 ("gfortran" ,gfortran "lib")))
2842 (home-page "https://github.com/DReichLab/EIG")
2843 (synopsis "Tools for population genetics")
2844 (description "The EIGENSOFT package provides tools for population
2845 genetics and stratification correction. EIGENSOFT implements methods commonly
2846 used in population genetics analyses such as PCA, computation of Tracy-Widom
2847 statistics, and finding related individuals in structured populations. It
2848 comes with a built-in plotting script and supports multiple file formats and
2849 quantitative phenotypes.")
2850 ;; The license of the eigensoft tools is Expat, but since it's
2851 ;; linking with the GNU Scientific Library (GSL) the effective
2852 ;; license is the GPL.
2853 (license license:gpl3+)))
2855 (define-public edirect
2858 (version "13.3.20200128")
2861 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect"
2862 "/versions/" version
2863 "/edirect-" version ".tar.gz"))
2866 "093zp7klv81ph0y8mm8d78a9hnpfxbv2kdym70gzdf3vz176rw33"))
2867 (modules '((guix build utils)))
2869 '(begin (delete-file "Mozilla-CA.tar.gz")
2870 (substitute* "rchive.go"
2871 ;; This go library does not have any license.
2872 (("github.com/fiam/gounidecode/unidecode")
2873 "golang.org/rainycape/unidecode"))
2875 (build-system perl-build-system)
2878 (modify-phases %standard-phases
2881 (delete 'check) ; simple check after install
2882 (add-after 'unpack 'patch-programs
2883 (lambda* (#:key inputs #:allow-other-keys)
2884 ;; Ignore errors about missing xtract.Linux and rchive.Linux.
2885 (substitute* "pm-refresh"
2886 (("cat \\\"\\$target")
2887 "grep ^[[:digit:]] \"$target"))
2890 (lambda* (#:key inputs outputs #:allow-other-keys)
2891 (let ((bin (string-append (assoc-ref outputs "out") "/bin"))
2892 (edirect-go (assoc-ref inputs "edirect-go-programs")))
2895 (install-file file bin))
2896 '("archive-pubmed" "asp-cp" "asp-ls" "download-ncbi-data"
2897 "download-pubmed" "edirect.pl" "efetch" "epost" "esearch"
2898 "fetch-pubmed" "ftp-cp" "ftp-ls" "has-asp" "index-pubmed"
2899 "pm-prepare" "pm-refresh" "pm-stash" "pm-collect"
2900 "pm-index" "pm-invert" "pm-merge" "pm-promote"))
2901 (symlink (string-append edirect-go "/bin/xtract.Linux")
2902 (string-append bin "/xtract"))
2903 (symlink (string-append edirect-go "/bin/rchive.Linux")
2904 (string-append bin "/rchive")))
2906 (add-after 'install 'wrap-program
2907 (lambda* (#:key outputs #:allow-other-keys)
2908 ;; Make sure everything can run in a pure environment.
2909 (let ((out (assoc-ref outputs "out"))
2910 (path (getenv "PERL5LIB")))
2914 `("PERL5LIB" ":" prefix (,path)))
2916 `("PATH" ":" prefix (,(string-append out "/bin")
2917 ,(dirname (which "sed"))
2918 ,(dirname (which "gzip"))
2919 ,(dirname (which "grep"))
2920 ,(dirname (which "perl"))
2921 ,(dirname (which "uname"))))))
2922 (find-files out ".")))
2924 (add-after 'wrap-program 'check
2925 (lambda* (#:key outputs #:allow-other-keys)
2926 (invoke (string-append (assoc-ref outputs "out")
2931 `(("edirect-go-programs" ,edirect-go-programs)
2932 ("perl-html-parser" ,perl-html-parser)
2933 ("perl-encode-locale" ,perl-encode-locale)
2934 ("perl-file-listing" ,perl-file-listing)
2935 ("perl-html-tagset" ,perl-html-tagset)
2936 ("perl-html-tree" ,perl-html-tree)
2937 ("perl-http-cookies" ,perl-http-cookies)
2938 ("perl-http-date" ,perl-http-date)
2939 ("perl-http-message" ,perl-http-message)
2940 ("perl-http-negotiate" ,perl-http-negotiate)
2941 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2942 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2943 ("perl-net-http" ,perl-net-http)
2944 ("perl-uri" ,perl-uri)
2945 ("perl-www-robotrules" ,perl-www-robotrules)
2946 ("perl-xml-simple" ,perl-xml-simple)
2948 (home-page "https://www.ncbi.nlm.nih.gov/books/NBK179288/")
2949 (synopsis "Tools for accessing the NCBI's set of databases")
2951 "Entrez Direct (EDirect) is a method for accessing the National Center
2952 for Biotechnology Information's (NCBI) set of interconnected
2953 databases (publication, sequence, structure, gene, variation, expression,
2954 etc.) from a terminal. Functions take search terms from command-line
2955 arguments. Individual operations are combined to build multi-step queries.
2956 Record retrieval and formatting normally complete the process.
2958 EDirect also provides an argument-driven function that simplifies the
2959 extraction of data from document summaries or other results that are returned
2960 in structured XML format. This can eliminate the need for writing custom
2961 software to answer ad hoc questions.")
2962 (native-search-paths
2963 ;; Ideally this should be set for LWP somewhere.
2964 (list (search-path-specification
2965 (variable "PERL_LWP_SSL_CA_FILE")
2966 (file-type 'regular)
2968 (files '("/etc/ssl/certs/ca-certificates.crt")))))
2969 (license license:public-domain)))
2971 (define-public edirect-go-programs
2974 (name "edirect-go-programs")
2975 (build-system go-build-system)
2977 `(#:install-source? #f
2978 #:tests? #f ; No tests.
2979 #:import-path "ncbi.nlm.nih.gov/entrez/edirect"
2981 (modify-phases %standard-phases
2983 (lambda* (#:key import-path #:allow-other-keys)
2984 (with-directory-excursion (string-append "src/" import-path)
2985 (invoke "go" "build" "-v" "-x" "j2x.go")
2986 (invoke "go" "build" "-v" "-x" "t2x.go")
2987 (invoke "go" "build" "-v" "-x" "-o"
2988 "xtract.Linux" "xtract.go" "common.go")
2989 (invoke "go" "build" "-v" "-x" "-o"
2990 "rchive.Linux" "rchive.go" "common.go")
2991 (invoke "go" "build" "-v" "-x" "-o" "symbols.Linux" "s2p.go"))))
2993 (lambda* (#:key outputs import-path #:allow-other-keys)
2994 (let ((dest (string-append (assoc-ref outputs "out") "/bin"))
2995 (source (string-append "src/" import-path "/")))
2996 (for-each (lambda (file)
2997 (format #t "installing ~a~%" file)
2998 (install-file (string-append source file) dest))
2999 '("j2x" "t2x" "symbols.Linux" "xtract.Linux" "rchive.Linux"))
3002 (propagated-inputs '())
3004 `(("go-github-com-fatih-color" ,go-github-com-fatih-color)
3005 ("go-github-com-fogleman-gg" ,go-github-com-fogleman-gg)
3006 ("go-github-com-gedex-inflector" ,go-github-com-gedex-inflector)
3007 ("go-github-com-golang-freetype" ,go-github-com-golang-freetype)
3008 ("go-github-com-klauspost-cpuid" ,go-github-com-klauspost-cpuid)
3009 ("go-github-com-pbnjay-memory" ,go-github-com-pbnjay-memory)
3010 ("go-github-com-surgebase-porter2" ,go-github-com-surgebase-porter2)
3011 ("go-golang-org-rainycape-unidecode" ,go-golang-org-rainycape-unidecode)
3012 ("go-golang-org-x-image" ,go-golang-org-x-image)
3013 ("go-golang-org-x-text" ,go-golang-org-x-text)))))
3015 (define-public exonerate
3024 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
3025 "exonerate-" version ".tar.gz"))
3028 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
3029 (build-system gnu-build-system)
3031 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
3033 `(("pkg-config" ,pkg-config)))
3037 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
3038 (synopsis "Generic tool for biological sequence alignment")
3040 "Exonerate is a generic tool for pairwise sequence comparison. It allows
3041 the alignment of sequences using a many alignment models, either exhaustive
3042 dynamic programming or a variety of heuristics.")
3043 (license license:gpl3)))
3045 (define-public express
3052 (url "https://github.com/adarob/eXpress")
3054 (file-name (git-file-name name version))
3057 "18nb22n7x820fzjngf4qgyb3mspqkw7xyk7v7s5ps6wfrd8qwscb"))))
3058 (build-system cmake-build-system)
3060 `(#:tests? #f ;no "check" target
3062 (modify-phases %standard-phases
3063 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
3064 (lambda* (#:key inputs #:allow-other-keys)
3065 (substitute* "CMakeLists.txt"
3066 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
3067 "set(Boost_USE_STATIC_LIBS OFF)")
3068 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
3069 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
3070 (substitute* "src/CMakeLists.txt"
3071 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
3072 (string-append (assoc-ref inputs "bamtools") "/lib"))
3073 (("libprotobuf.a") "libprotobuf.so"))
3075 (add-after 'unpack 'remove-update-check
3077 (substitute* "src/main.cpp"
3078 (("#include \"update_check.h\"") "")
3079 (("check_version\\(PACKAGE_VERSION\\);") ""))
3083 ("bamtools" ,bamtools)
3084 ("protobuf" ,protobuf)
3086 (home-page "http://bio.math.berkeley.edu/eXpress")
3087 (synopsis "Streaming quantification for high-throughput genomic sequencing")
3089 "eXpress is a streaming tool for quantifying the abundances of a set of
3090 target sequences from sampled subsequences. Example applications include
3091 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
3092 analysis (from RNA-Seq), transcription factor binding quantification in
3093 ChIP-Seq, and analysis of metagenomic data.")
3094 (license license:artistic2.0)))
3096 (define-public express-beta-diversity
3098 (name "express-beta-diversity")
3103 (url "https://github.com/dparks1134/ExpressBetaDiversity")
3104 (commit (string-append "v" version))))
3105 (file-name (git-file-name name version))
3108 "0s0yzg5c21349rh7x4w9266jsvnp7j1hp9cf8sk32hz8nvrj745x"))))
3109 (build-system gnu-build-system)
3112 (modify-phases %standard-phases
3114 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
3116 (lambda _ (invoke "../bin/ExpressBetaDiversity" "-u") #t))
3118 (lambda* (#:key outputs #:allow-other-keys)
3119 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3120 (install-file "../scripts/convertToEBD.py" bin)
3121 (install-file "../bin/ExpressBetaDiversity" bin)
3124 `(("python" ,python-2)))
3125 (home-page "https://github.com/dparks1134/ExpressBetaDiversity")
3126 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
3128 "Express Beta Diversity (EBD) calculates ecological beta diversity
3129 (dissimilarity) measures between biological communities. EBD implements a
3130 variety of diversity measures including those that make use of phylogenetic
3131 similarity of community members.")
3132 (license license:gpl3+)))
3134 (define-public fasttree
3141 "http://www.microbesonline.org/fasttree/FastTree-"
3145 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
3146 (build-system gnu-build-system)
3148 `(#:tests? #f ; no "check" target
3150 (modify-phases %standard-phases
3154 (lambda* (#:key source #:allow-other-keys)
3157 "-finline-functions"
3168 "-finline-functions"
3177 (lambda* (#:key outputs #:allow-other-keys)
3178 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3179 (install-file "FastTree" bin)
3180 (install-file "FastTreeMP" bin)
3182 (home-page "http://www.microbesonline.org/fasttree")
3183 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
3185 "FastTree can handle alignments with up to a million of sequences in a
3186 reasonable amount of time and memory. For large alignments, FastTree is
3187 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
3188 (license license:gpl2+)))
3190 (define-public fastx-toolkit
3192 (name "fastx-toolkit")
3198 "https://github.com/agordon/fastx_toolkit/releases/download/"
3199 version "/fastx_toolkit-" version ".tar.bz2"))
3202 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
3203 (build-system gnu-build-system)
3205 `(("libgtextutils" ,libgtextutils)))
3207 `(("gcc" ,gcc-6) ;; doesn't build with later versions
3208 ("pkg-config" ,pkg-config)))
3209 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
3210 (synopsis "Tools for FASTA/FASTQ file preprocessing")
3212 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
3213 FASTA/FASTQ files preprocessing.
3215 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
3216 containing multiple short-reads sequences. The main processing of such
3217 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
3218 is sometimes more productive to preprocess the files before mapping the
3219 sequences to the genome---manipulating the sequences to produce better mapping
3220 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
3221 (license license:agpl3+)))
3223 (define-public flexbar
3230 (url "https://github.com/seqan/flexbar")
3231 (commit (string-append "v" version))))
3232 (file-name (git-file-name name version))
3235 "1pq9sxvdnldl14libk234m72dqhwgzs3acgl943wchwdqlcsi5r2"))))
3236 (build-system cmake-build-system)
3239 (modify-phases %standard-phases
3240 (add-after 'unpack 'do-not-tune-to-CPU
3242 (substitute* "src/CMakeLists.txt"
3243 ((" -march=native") ""))
3246 (lambda* (#:key outputs #:allow-other-keys)
3247 (setenv "PATH" (string-append (getcwd) ":" (getenv "PATH")))
3248 (with-directory-excursion "../source/test"
3249 (invoke "bash" "flexbar_test.sh"))
3252 (lambda* (#:key outputs #:allow-other-keys)
3253 (let* ((out (string-append (assoc-ref outputs "out")))
3254 (bin (string-append out "/bin/")))
3255 (install-file "flexbar" bin))
3261 `(("pkg-config" ,pkg-config)
3263 (home-page "https://github.com/seqan/flexbar")
3264 (synopsis "Barcode and adapter removal tool for sequencing platforms")
3266 "Flexbar preprocesses high-throughput nucleotide sequencing data
3267 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
3268 Moreover, trimming and filtering features are provided. Flexbar increases
3269 read mapping rates and improves genome and transcriptome assemblies. It
3270 supports next-generation sequencing data in fasta/q and csfasta/q format from
3271 Illumina, Roche 454, and the SOLiD platform.")
3272 (license license:bsd-3)))
3274 (define-public fraggenescan
3276 (name "fraggenescan")
3282 (string-append "mirror://sourceforge/fraggenescan/"
3283 "FragGeneScan" version ".tar.gz"))
3285 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
3286 (build-system gnu-build-system)
3289 (modify-phases %standard-phases
3291 (add-before 'build 'patch-paths
3292 (lambda* (#:key outputs #:allow-other-keys)
3293 (let* ((out (string-append (assoc-ref outputs "out")))
3294 (share (string-append out "/share/fraggenescan/")))
3295 (substitute* "run_FragGeneScan.pl"
3297 (string-append "system(\"" (which "rm")))
3299 (string-append "system(\"" (which "mv")))
3300 (("\\\"awk") (string-append "\"" (which "awk")))
3301 ;; This script and other programs expect the training files
3302 ;; to be in the non-standard location bin/train/XXX. Change
3303 ;; this to be share/fraggenescan/train/XXX instead.
3304 (("^\\$train.file = \\$dir.*")
3305 (string-append "$train_file = \""
3307 "train/\".$FGS_train_file;")))
3308 (substitute* "run_hmm.c"
3309 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
3310 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
3314 (invoke "make" "clean")
3315 (invoke "make" "fgs")
3318 (lambda* (#:key outputs #:allow-other-keys)
3319 (let* ((out (string-append (assoc-ref outputs "out")))
3320 (bin (string-append out "/bin/"))
3321 (share (string-append out "/share/fraggenescan/train")))
3322 (install-file "run_FragGeneScan.pl" bin)
3323 (install-file "FragGeneScan" bin)
3324 (copy-recursively "train" share))
3327 (add-after 'install 'post-install-check
3328 ;; In lieu of 'make check', run one of the examples and check the
3329 ;; output files gets created.
3330 (lambda* (#:key outputs #:allow-other-keys)
3331 (let* ((out (string-append (assoc-ref outputs "out")))
3332 (bin (string-append out "/bin/"))
3333 (frag (string-append bin "run_FragGeneScan.pl")))
3334 ;; Test complete genome.
3336 "-genome=./example/NC_000913.fna"
3340 (unless (and (file-exists? "test2.faa")
3341 (file-exists? "test2.ffn")
3342 (file-exists? "test2.gff")
3343 (file-exists? "test2.out"))
3344 (error "Expected files do not exist."))
3345 ;; Test incomplete sequences.
3347 "-genome=./example/NC_000913-fgs.ffn"
3354 ("python" ,python-2))) ;not compatible with python 3.
3355 (home-page "https://sourceforge.net/projects/fraggenescan/")
3356 (synopsis "Finds potentially fragmented genes in short reads")
3358 "FragGeneScan is a program for predicting bacterial and archaeal genes in
3359 short and error-prone DNA sequencing reads. It can also be applied to predict
3360 genes in incomplete assemblies or complete genomes.")
3361 ;; GPL3+ according to private correspondense with the authors.
3362 (license license:gpl3+)))
3364 (define-public fxtract
3365 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
3373 (url "https://github.com/ctSkennerton/fxtract")
3375 (file-name (git-file-name name version))
3378 "0hab3gpwf4w9s87qlbswq6ws1qqybh4dcqk79q1ahyldzai5fgp5"))))
3379 (build-system gnu-build-system)
3381 `(#:make-flags (list
3382 (string-append "PREFIX=" (assoc-ref %outputs "out"))
3384 #:test-target "fxtract_test"
3386 (modify-phases %standard-phases
3388 (add-before 'build 'copy-util
3389 (lambda* (#:key inputs #:allow-other-keys)
3391 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
3393 ;; Do not use make install as this requires additional dependencies.
3395 (lambda* (#:key outputs #:allow-other-keys)
3396 (let* ((out (assoc-ref outputs "out"))
3397 (bin (string-append out"/bin")))
3398 (install-file "fxtract" bin)
3404 ;; ctskennerton-util is licensed under GPL2.
3405 `(("ctskennerton-util"
3409 (url "https://github.com/ctSkennerton/util")
3410 (commit util-commit)))
3411 (file-name (string-append
3412 "ctstennerton-util-" util-commit "-checkout"))
3415 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
3416 (home-page "https://github.com/ctSkennerton/fxtract")
3417 (synopsis "Extract sequences from FASTA and FASTQ files")
3419 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
3420 or FASTQ) file given a subsequence. It uses a simple substring search for
3421 basic tasks but can change to using POSIX regular expressions, PCRE, hash
3422 lookups or multi-pattern searching as required. By default fxtract looks in
3423 the sequence of each record but can also be told to look in the header,
3424 comment or quality sections.")
3425 ;; 'util' requires SSE instructions.
3426 (supported-systems '("x86_64-linux"))
3427 (license license:expat))))
3429 (define-public gemma
3436 (url "https://github.com/xiangzhou/GEMMA")
3437 (commit (string-append "v" version))))
3438 (file-name (git-file-name name version))
3441 "1s3ncnbn45r2hh1cvrqky1kbqq6546biypr4f5mkw1kqlrgyh0yg"))))
3444 ("gfortran" ,gfortran "lib")
3447 ("openblas" ,openblas)
3449 (build-system gnu-build-system)
3452 '(,@(match (%current-system)
3454 '("FORCE_DYNAMIC=1"))
3456 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
3458 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
3460 (modify-phases %standard-phases
3462 (add-after 'unpack 'find-eigen
3463 (lambda* (#:key inputs #:allow-other-keys)
3464 ;; Ensure that Eigen headers can be found
3465 (setenv "CPLUS_INCLUDE_PATH"
3466 (string-append (assoc-ref inputs "eigen")
3469 (add-before 'build 'bin-mkdir
3474 (lambda* (#:key outputs #:allow-other-keys)
3475 (let ((out (assoc-ref outputs "out")))
3476 (install-file "bin/gemma"
3480 #:tests? #f)) ; no tests included yet
3481 (home-page "https://github.com/xiangzhou/GEMMA")
3482 (synopsis "Tool for genome-wide efficient mixed model association")
3484 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
3485 standard linear mixed model resolver with application in genome-wide
3486 association studies (GWAS).")
3487 (license license:gpl3)))
3496 (url "https://github.com/nboley/grit")
3498 (file-name (git-file-name name version))
3501 "1l5v8vfvfbrpmgnrvbrbv40d0arhxcnmxgv2f1mlcqfa3q6bkqm9"))))
3502 (build-system python-build-system)
3504 `(#:python ,python-2
3506 (modify-phases %standard-phases
3507 (add-after 'unpack 'generate-from-cython-sources
3508 (lambda* (#:key inputs outputs #:allow-other-keys)
3509 ;; Delete these C files to force fresh generation from pyx sources.
3510 (delete-file "grit/sparsify_support_fns.c")
3511 (delete-file "grit/call_peaks_support_fns.c")
3512 (substitute* "setup.py"
3513 (("Cython.Setup") "Cython.Build"))
3516 `(("python-scipy" ,python2-scipy)
3517 ("python-numpy" ,python2-numpy)
3518 ("python-pysam" ,python2-pysam)
3519 ("python-networkx" ,python2-networkx)))
3521 `(("python-cython" ,python2-cython)))
3522 ;; The canonical <http://grit-bio.org> home page times out as of 2020-01-21.
3523 (home-page "https://github.com/nboley/grit")
3524 (synopsis "Tool for integrative analysis of RNA-seq type assays")
3526 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
3527 full length transcript models. When none of these data sources are available,
3528 GRIT can be run by providing a candidate set of TES or TSS sites. In
3529 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
3530 also be run in quantification mode, where it uses a provided GTF file and just
3531 estimates transcript expression.")
3532 (license license:gpl3+)))
3534 (define-public hisat
3541 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
3542 version "-beta-source.zip"))
3545 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
3546 (build-system gnu-build-system)
3548 `(#:tests? #f ;no check target
3549 #:make-flags '("allall"
3550 ;; Disable unsupported `popcnt' instructions on
3551 ;; architectures other than x86_64
3552 ,@(if (string-prefix? "x86_64"
3553 (or (%current-target-system)
3556 '("POPCNT_CAPABILITY=0")))
3558 (modify-phases %standard-phases
3559 (add-after 'unpack 'patch-sources
3561 ;; XXX Cannot use snippet because zip files are not supported
3562 (substitute* "Makefile"
3563 (("^CC = .*$") "CC = gcc")
3564 (("^CPP = .*$") "CPP = g++")
3565 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
3566 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
3567 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
3568 (substitute* '("hisat-build" "hisat-inspect")
3569 (("/usr/bin/env") (which "env")))
3572 (lambda* (#:key outputs #:allow-other-keys)
3573 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
3574 (for-each (lambda (file)
3575 (install-file file bin))
3578 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
3580 (delete 'configure))))
3582 `(("unzip" ,unzip)))
3587 ;; Non-portable SSE instructions are used so building fails on platforms
3588 ;; other than x86_64.
3589 (supported-systems '("x86_64-linux"))
3590 (home-page "https://ccb.jhu.edu/software/hisat/index.shtml")
3591 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
3593 "HISAT is a fast and sensitive spliced alignment program for mapping
3594 RNA-seq reads. In addition to one global FM index that represents a whole
3595 genome, HISAT uses a large set of small FM indexes that collectively cover the
3596 whole genome. These small indexes (called local indexes) combined with
3597 several alignment strategies enable effective alignment of RNA-seq reads, in
3598 particular, reads spanning multiple exons.")
3599 (license license:gpl3+)))
3601 (define-public hisat2
3608 (uri (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
3609 "/downloads/hisat2-" version "-source.zip"))
3612 "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"))))
3613 (build-system gnu-build-system)
3615 `(#:tests? #f ; no check target
3616 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
3617 #:modules ((guix build gnu-build-system)
3621 (modify-phases %standard-phases
3622 (add-after 'unpack 'make-deterministic
3624 (substitute* "Makefile"
3629 (lambda* (#:key outputs #:allow-other-keys)
3630 (let* ((out (assoc-ref outputs "out"))
3631 (bin (string-append out "/bin/"))
3632 (doc (string-append out "/share/doc/hisat2/")))
3634 (cut install-file <> bin)
3636 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
3638 (install-file "doc/manual.inc.html" doc))
3641 `(("unzip" ,unzip) ; needed for archive from ftp
3643 ("pandoc" ,pandoc))) ; for documentation
3644 (home-page "https://ccb.jhu.edu/software/hisat2/index.shtml")
3645 (synopsis "Graph-based alignment of genomic sequencing reads")
3646 (description "HISAT2 is a fast and sensitive alignment program for mapping
3647 next-generation sequencing reads (both DNA and RNA) to a population of human
3648 genomes (as well as to a single reference genome). In addition to using one
3649 global @dfn{graph FM} (GFM) index that represents a population of human
3650 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
3651 the whole genome. These small indexes, combined with several alignment
3652 strategies, enable rapid and accurate alignment of sequencing reads. This new
3653 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
3654 ;; HISAT2 contains files from Bowtie2, which is released under
3655 ;; GPLv2 or later. The HISAT2 source files are released under
3657 (license license:gpl3+)))
3659 (define-public hmmer
3667 "http://eddylab.org/software/hmmer/hmmer-" version ".tar.gz"))
3670 "171bivy6xhgjsz5nv53n81pc3frnwz29ylblawk2bv46szwjjqd5"))))
3671 (build-system gnu-build-system)
3672 (native-inputs `(("perl" ,perl)))
3673 (home-page "http://hmmer.org/")
3674 (synopsis "Biosequence analysis using profile hidden Markov models")
3676 "HMMER is used for searching sequence databases for homologs of protein
3677 sequences, and for making protein sequence alignments. It implements methods
3678 using probabilistic models called profile hidden Markov models (profile
3680 ;; hmmer uses non-portable SSE intrinsics so building fails on other
3682 (supported-systems '("x86_64-linux" "i686-linux"))
3683 (license license:bsd-3)))
3685 (define-public htseq
3691 (uri (pypi-uri "HTSeq" version))
3694 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
3695 (build-system python-build-system)
3697 `(("python-cython" ,python-cython)))
3698 ;; Numpy needs to be propagated when htseq is used as a Python library.
3700 `(("python-numpy" ,python-numpy)))
3702 `(("python-pysam" ,python-pysam)
3703 ("python-matplotlib" ,python-matplotlib)))
3704 (home-page "https://htseq.readthedocs.io/")
3705 (synopsis "Analysing high-throughput sequencing data with Python")
3707 "HTSeq is a Python package that provides infrastructure to process data
3708 from high-throughput sequencing assays.")
3709 (license license:gpl3+)))
3711 (define-public python2-htseq
3712 (package-with-python2 htseq))
3714 (define-public java-htsjdk
3716 (name "java-htsjdk")
3717 (version "2.3.0") ; last version without build dependency on gradle
3721 (url "https://github.com/samtools/htsjdk")
3723 (file-name (git-file-name name version))
3726 "1b178ixcabanm834ydjl3jiakpyxdmki32hqfv2abrzn3rcwa28i"))
3727 (modules '((guix build utils)))
3729 ;; Delete pre-built binaries
3731 (delete-file-recursively "lib")
3734 (build-system ant-build-system)
3736 `(#:tests? #f ; test require Internet access
3739 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3740 "/share/java/htsjdk/"))
3741 #:build-target "all"
3743 (modify-phases %standard-phases
3744 ;; The build phase also installs the jars
3745 (delete 'install))))
3747 `(("java-ngs" ,java-ngs)
3748 ("java-snappy-1" ,java-snappy-1)
3749 ("java-commons-compress" ,java-commons-compress)
3750 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3751 ("java-commons-jexl-2" ,java-commons-jexl-2)
3752 ("java-xz" ,java-xz)))
3754 `(("java-testng" ,java-testng)))
3755 (home-page "http://samtools.github.io/htsjdk/")
3756 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3758 "HTSJDK is an implementation of a unified Java library for accessing
3759 common file formats, such as SAM and VCF, used for high-throughput
3760 sequencing (HTS) data. There are also an number of useful utilities for
3761 manipulating HTS data.")
3762 (license license:expat)))
3764 (define-public java-htsjdk-latest
3766 (name "java-htsjdk")
3771 (url "https://github.com/samtools/htsjdk")
3773 (file-name (string-append name "-" version "-checkout"))
3776 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
3777 (build-system ant-build-system)
3779 `(#:tests? #f ; test require Scala
3781 #:jar-name "htsjdk.jar"
3783 (modify-phases %standard-phases
3784 (add-after 'unpack 'remove-useless-build.xml
3785 (lambda _ (delete-file "build.xml") #t))
3786 ;; The tests require the scalatest package.
3787 (add-after 'unpack 'remove-tests
3788 (lambda _ (delete-file-recursively "src/test") #t)))))
3790 `(("java-ngs" ,java-ngs)
3791 ("java-snappy-1" ,java-snappy-1)
3792 ("java-commons-compress" ,java-commons-compress)
3793 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3794 ("java-commons-jexl-2" ,java-commons-jexl-2)
3795 ("java-xz" ,java-xz)))
3797 `(("java-junit" ,java-junit)))
3798 (home-page "http://samtools.github.io/htsjdk/")
3799 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3801 "HTSJDK is an implementation of a unified Java library for accessing
3802 common file formats, such as SAM and VCF, used for high-throughput
3803 sequencing (HTS) data. There are also an number of useful utilities for
3804 manipulating HTS data.")
3805 (license license:expat)))
3807 ;; This is needed for picard 2.10.3
3808 (define-public java-htsjdk-2.10.1
3809 (package (inherit java-htsjdk-latest)
3810 (name "java-htsjdk")
3815 (url "https://github.com/samtools/htsjdk")
3817 (file-name (string-append name "-" version "-checkout"))
3820 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
3821 (build-system ant-build-system)
3823 `(#:tests? #f ; tests require Scala
3825 #:jar-name "htsjdk.jar"
3827 (modify-phases %standard-phases
3828 (add-after 'unpack 'remove-useless-build.xml
3829 (lambda _ (delete-file "build.xml") #t))
3830 ;; The tests require the scalatest package.
3831 (add-after 'unpack 'remove-tests
3832 (lambda _ (delete-file-recursively "src/test") #t)))))))
3834 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3835 ;; recent version of java-htsjdk, which depends on gradle.
3836 (define-public java-picard
3838 (name "java-picard")
3843 (url "https://github.com/broadinstitute/picard")
3845 (file-name (string-append "java-picard-" version "-checkout"))
3848 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3849 (modules '((guix build utils)))
3852 ;; Delete pre-built binaries.
3853 (delete-file-recursively "lib")
3855 (substitute* "build.xml"
3856 ;; Remove build-time dependency on git.
3857 (("failifexecutionfails=\"true\"")
3858 "failifexecutionfails=\"false\"")
3860 (("depends=\"compile-htsjdk, ")
3862 (("depends=\"compile-htsjdk-tests, ")
3864 ;; Build picard-lib.jar before building picard.jar
3865 (("name=\"picard-jar\" depends=\"" line)
3866 (string-append line "picard-lib-jar, ")))
3868 (build-system ant-build-system)
3870 `(#:build-target "picard-jar"
3871 #:test-target "test"
3872 ;; Tests require jacoco:coverage.
3875 (list (string-append "-Dhtsjdk_lib_dir="
3876 (assoc-ref %build-inputs "java-htsjdk")
3877 "/share/java/htsjdk/")
3878 "-Dhtsjdk-classes=dist/tmp"
3879 (string-append "-Dhtsjdk-version="
3880 ,(package-version java-htsjdk)))
3883 (modify-phases %standard-phases
3884 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3885 (delete 'generate-jar-indices)
3886 (add-after 'unpack 'use-our-htsjdk
3887 (lambda* (#:key inputs #:allow-other-keys)
3888 (substitute* "build.xml"
3889 (("\\$\\{htsjdk\\}/lib")
3890 (string-append (assoc-ref inputs "java-htsjdk")
3891 "/share/java/htsjdk/")))
3893 (add-after 'unpack 'make-test-target-independent
3894 (lambda* (#:key inputs #:allow-other-keys)
3895 (substitute* "build.xml"
3896 (("name=\"test\" depends=\"compile, ")
3897 "name=\"test\" depends=\""))
3899 (replace 'install (install-jars "dist")))))
3901 `(("java-htsjdk" ,java-htsjdk)
3902 ("java-guava" ,java-guava)))
3904 `(("java-testng" ,java-testng)))
3905 (home-page "http://broadinstitute.github.io/picard/")
3906 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3907 (description "Picard is a set of Java command line tools for manipulating
3908 high-throughput sequencing (HTS) data and formats. Picard is implemented
3909 using the HTSJDK Java library to support accessing file formats that are
3910 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3912 (license license:expat)))
3914 ;; This is needed for dropseq-tools
3915 (define-public java-picard-2.10.3
3917 (name "java-picard")
3922 (url "https://github.com/broadinstitute/picard")
3924 (file-name (string-append "java-picard-" version "-checkout"))
3927 "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi"))))
3928 (build-system ant-build-system)
3930 `(#:jar-name "picard.jar"
3931 ;; Tests require jacoco:coverage.
3934 #:main-class "picard.cmdline.PicardCommandLine"
3935 #:modules ((guix build ant-build-system)
3937 (guix build java-utils)
3942 (modify-phases %standard-phases
3943 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3944 (delete 'generate-jar-indices)
3945 (add-after 'unpack 'remove-useless-build.xml
3946 (lambda _ (delete-file "build.xml") #t))
3947 ;; This is necessary to ensure that htsjdk is found when using
3948 ;; picard.jar as an executable.
3949 (add-before 'build 'edit-classpath-in-manifest
3950 (lambda* (#:key inputs #:allow-other-keys)
3951 (chmod "build.xml" #o664)
3952 (call-with-output-file "build.xml.new"
3956 (with-input-from-file "build.xml"
3957 (lambda _ (xml->sxml #:trim-whitespace? #t)))
3958 `((target . ,(lambda (tag . kids)
3959 (let ((name ((sxpath '(name *text*))
3961 ;; FIXME: We're breaking the line
3962 ;; early with a dummy path to
3963 ;; ensure that the store reference
3964 ;; isn't broken apart and can still
3965 ;; be found by the reference
3970 ~a/share/java/htsjdk.jar${line.separator}${line.separator}"
3971 ;; maximum line length is 70
3972 (string-tabulate (const #\b) 57)
3973 (assoc-ref inputs "java-htsjdk"))))
3974 (if (member "manifest" name)
3977 (@ (file "${manifest.file}")
3978 (match "\\r\\n\\r\\n")
3979 (replace "${line.separator}")))
3982 (file "${manifest.file}")
3985 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
3986 (*text* . ,(lambda (_ txt) txt))))
3988 (rename-file "build.xml.new" "build.xml")
3991 `(("java-htsjdk" ,java-htsjdk-2.10.1)))
3993 `(("java-testng" ,java-testng)
3994 ("java-guava" ,java-guava)))
3995 (home-page "http://broadinstitute.github.io/picard/")
3996 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3997 (description "Picard is a set of Java command line tools for manipulating
3998 high-throughput sequencing (HTS) data and formats. Picard is implemented
3999 using the HTSJDK Java library to support accessing file formats that are
4000 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
4002 (license license:expat)))
4004 ;; This is the last version of Picard to provide net.sf.samtools
4005 (define-public java-picard-1.113
4006 (package (inherit java-picard)
4007 (name "java-picard")
4012 (url "https://github.com/broadinstitute/picard")
4014 (file-name (string-append "java-picard-" version "-checkout"))
4017 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
4018 (modules '((guix build utils)))
4021 ;; Delete pre-built binaries.
4022 (delete-file-recursively "lib")
4025 (build-system ant-build-system)
4027 `(#:build-target "picard-jar"
4028 #:test-target "test"
4029 ;; FIXME: the class path at test time is wrong.
4030 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
4031 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
4034 ;; This is only used for tests.
4036 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
4038 (modify-phases %standard-phases
4039 ;; FIXME: This phase fails.
4040 (delete 'generate-jar-indices)
4041 ;; Do not use bundled ant bzip2.
4042 (add-after 'unpack 'use-ant-bzip
4043 (lambda* (#:key inputs #:allow-other-keys)
4044 (substitute* "build.xml"
4045 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
4046 (string-append (assoc-ref inputs "ant")
4049 (add-after 'unpack 'make-test-target-independent
4050 (lambda* (#:key inputs #:allow-other-keys)
4051 (substitute* "build.xml"
4052 (("name=\"test\" depends=\"compile, ")
4053 "name=\"test\" depends=\"compile-tests, ")
4054 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
4055 "name=\"compile\" depends=\"compile-src\""))
4057 (add-after 'unpack 'fix-deflater-path
4058 (lambda* (#:key outputs #:allow-other-keys)
4059 (substitute* "src/java/net/sf/samtools/Defaults.java"
4060 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
4061 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
4062 (assoc-ref outputs "out")
4063 "/lib/jni/libIntelDeflater.so"
4066 ;; Build the deflater library, because we've previously deleted the
4067 ;; pre-built one. This can only be built with access to the JDK
4069 (add-after 'build 'build-jni
4070 (lambda* (#:key inputs #:allow-other-keys)
4073 (invoke "tar" "--strip-components=1" "-C" "jdk-src"
4074 "-xf" (assoc-ref inputs "jdk-src"))
4075 (invoke "javah" "-jni"
4076 "-classpath" "classes"
4078 "net.sf.samtools.util.zip.IntelDeflater")
4079 (with-directory-excursion "src/c/inteldeflater"
4080 (invoke "gcc" "-I../../../lib" "-I."
4081 (string-append "-I" (assoc-ref inputs "jdk")
4083 "-I../../../jdk-src/src/share/native/common/"
4084 "-I../../../jdk-src/src/solaris/native/common/"
4085 "-c" "-O3" "-fPIC" "IntelDeflater.c")
4086 (invoke "gcc" "-shared"
4087 "-o" "../../../lib/jni/libIntelDeflater.so"
4088 "IntelDeflater.o" "-lz" "-lstdc++"))
4090 ;; We can only build everything else after building the JNI library.
4091 (add-after 'build-jni 'build-rest
4092 (lambda* (#:key make-flags #:allow-other-keys)
4093 (apply invoke `("ant" "all" ,@make-flags))
4095 (add-before 'build 'set-JAVA6_HOME
4097 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
4099 (replace 'install (install-jars "dist"))
4100 (add-after 'install 'install-jni-lib
4101 (lambda* (#:key outputs #:allow-other-keys)
4102 (let ((jni (string-append (assoc-ref outputs "out")
4105 (install-file "lib/jni/libIntelDeflater.so" jni)
4108 `(("java-snappy-1" ,java-snappy-1)
4109 ("java-commons-jexl-2" ,java-commons-jexl-2)
4110 ("java-cofoja" ,java-cofoja)
4111 ("ant" ,ant) ; for bzip2 support at runtime
4114 `(("ant-apache-bcel" ,ant-apache-bcel)
4115 ("ant-junit" ,ant-junit)
4116 ("java-testng" ,java-testng)
4117 ("java-commons-bcel" ,java-commons-bcel)
4118 ("java-jcommander" ,java-jcommander)
4119 ("jdk" ,icedtea-8 "jdk")
4120 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
4122 (define-public fastqc
4129 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
4130 "projects/fastqc/fastqc_v"
4131 version "_source.zip"))
4134 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
4135 (build-system ant-build-system)
4137 `(#:tests? #f ; there are no tests
4138 #:build-target "build"
4140 (modify-phases %standard-phases
4141 (add-after 'unpack 'fix-dependencies
4142 (lambda* (#:key inputs #:allow-other-keys)
4143 (substitute* "build.xml"
4145 (string-append (assoc-ref inputs "java-jbzip2")
4146 "/share/java/jbzip2.jar"))
4148 (string-append (assoc-ref inputs "java-picard-1.113")
4149 "/share/java/sam-1.112.jar"))
4151 (string-append (assoc-ref inputs "java-cisd-jhdf5")
4152 "/share/java/sis-jhdf5.jar")))
4154 ;; There is no installation target
4156 (lambda* (#:key inputs outputs #:allow-other-keys)
4157 (let* ((out (assoc-ref outputs "out"))
4158 (bin (string-append out "/bin"))
4159 (share (string-append out "/share/fastqc/"))
4160 (exe (string-append share "/fastqc")))
4161 (for-each mkdir-p (list bin share))
4162 (copy-recursively "bin" share)
4164 (("my \\$java_bin = 'java';")
4165 (string-append "my $java_bin = '"
4166 (assoc-ref inputs "java")
4169 (symlink exe (string-append bin "/fastqc"))
4173 ("perl" ,perl) ; needed for the wrapper script
4174 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
4175 ("java-picard-1.113" ,java-picard-1.113)
4176 ("java-jbzip2" ,java-jbzip2)))
4178 `(("unzip" ,unzip)))
4179 (home-page "https://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
4180 (synopsis "Quality control tool for high throughput sequence data")
4182 "FastQC aims to provide a simple way to do some quality control
4183 checks on raw sequence data coming from high throughput sequencing
4184 pipelines. It provides a modular set of analyses which you can use to
4185 give a quick impression of whether your data has any problems of which
4186 you should be aware before doing any further analysis.
4188 The main functions of FastQC are:
4191 @item Import of data from BAM, SAM or FastQ files (any variant);
4192 @item Providing a quick overview to tell you in which areas there may
4194 @item Summary graphs and tables to quickly assess your data;
4195 @item Export of results to an HTML based permanent report;
4196 @item Offline operation to allow automated generation of reports
4197 without running the interactive application.
4199 (license license:gpl3+)))
4201 (define-public fastp
4209 (url "https://github.com/OpenGene/fastp")
4210 (commit (string-append "v" version))))
4211 (file-name (git-file-name name version))
4214 "1r6ms5zbf5rps4rgp4z73nczadl00b5rqylw8f684isfz27dp0xh"))))
4215 (build-system gnu-build-system)
4217 `(#:tests? #f ; there are none
4219 (list (string-append "BINDIR=" (assoc-ref %outputs "out") "/bin"))
4221 (modify-phases %standard-phases
4223 (add-before 'install 'create-target-dir
4224 (lambda* (#:key outputs #:allow-other-keys)
4225 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4229 (home-page "https://github.com/OpenGene/fastp/")
4230 (synopsis "All-in-one FastQ preprocessor")
4232 "Fastp is a tool designed to provide fast all-in-one preprocessing for
4233 FastQ files. This tool has multi-threading support to afford high
4235 (license license:expat)))
4237 (define-public htslib
4244 "https://github.com/samtools/htslib/releases/download/"
4245 version "/htslib-" version ".tar.bz2"))
4248 "1mrq4mihzx37yqhj3sfz6da6mw49niia808bzsw2gkkgmadxvyng"))))
4249 (build-system gnu-build-system)
4250 ;; Let htslib translate "gs://" and "s3://" to regular https links with
4251 ;; "--enable-gcs" and "--enable-s3". For these options to work, we also
4252 ;; need to set "--enable-libcurl".
4254 `(#:configure-flags '("--enable-gcs"
4259 ("openssl" ,openssl)))
4260 ;; This is referred to in the pkg-config file as a required library.
4265 (home-page "https://www.htslib.org")
4266 (synopsis "C library for reading/writing high-throughput sequencing data")
4268 "HTSlib is a C library for reading/writing high-throughput sequencing
4269 data. It also provides the @command{bgzip}, @command{htsfile}, and
4270 @command{tabix} utilities.")
4271 ;; Files under cram/ are released under the modified BSD license;
4272 ;; the rest is released under the Expat license
4273 (license (list license:expat license:bsd-3))))
4275 (define-public htslib-1.9
4276 (package (inherit htslib)
4282 "https://github.com/samtools/htslib/releases/download/"
4283 version "/htslib-" version ".tar.bz2"))
4286 "16ljv43sc3fxmv63w7b2ff8m1s7h89xhazwmbm1bicz8axq8fjz0"))))))
4288 ;; This package should be removed once no packages rely upon it.
4296 "https://github.com/samtools/htslib/releases/download/"
4297 version "/htslib-" version ".tar.bz2"))
4300 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
4309 (url "https://github.com/nboley/idr")
4311 (file-name (git-file-name name version))
4314 "04j876h6z444v2q79drxx283d3k5snd72kj895wbalnl42206x9g"))
4315 ;; Delete generated C code.
4317 '(begin (delete-file "idr/inv_cdf.c") #t))))
4318 (build-system python-build-system)
4319 ;; There is only one test ("test_inv_cdf.py") and it tests features that
4320 ;; are no longer part of this package. It also asserts False, which
4321 ;; causes the tests to always fail.
4322 (arguments `(#:tests? #f))
4324 `(("python-scipy" ,python-scipy)
4325 ("python-sympy" ,python-sympy)
4326 ("python-numpy" ,python-numpy)
4327 ("python-matplotlib" ,python-matplotlib)))
4329 `(("python-cython" ,python-cython)))
4330 (home-page "https://github.com/nboley/idr")
4331 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
4333 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
4334 to measure the reproducibility of findings identified from replicate
4335 experiments and provide highly stable thresholds based on reproducibility.")
4336 (license license:gpl2+)))
4338 (define-public jellyfish
4344 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
4345 "releases/download/v" version
4346 "/jellyfish-" version ".tar.gz"))
4349 "1k4pc3fvv6w1km2yph4m5sd78fbxp21d6xyzgmy0gjihzc6mb249"))))
4350 (build-system gnu-build-system)
4351 (outputs '("out" ;for library
4352 "ruby" ;for Ruby bindings
4353 "python")) ;for Python bindings
4356 (list (string-append "--enable-ruby-binding="
4357 (assoc-ref %outputs "ruby"))
4358 (string-append "--enable-python-binding="
4359 (assoc-ref %outputs "python")))
4361 (modify-phases %standard-phases
4362 (add-before 'check 'set-SHELL-variable
4364 ;; generator_manager.hpp either uses /bin/sh or $SHELL
4366 (setenv "SHELL" (which "bash"))
4372 ("python" ,python-2)
4373 ("pkg-config" ,pkg-config)))
4375 `(("htslib" ,htslib)))
4376 (synopsis "Tool for fast counting of k-mers in DNA")
4378 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
4379 DNA. A k-mer is a substring of length k, and counting the occurrences of all
4380 such substrings is a central step in many analyses of DNA sequence. Jellyfish
4381 is a command-line program that reads FASTA and multi-FASTA files containing
4382 DNA sequences. It outputs its k-mer counts in a binary format, which can be
4383 translated into a human-readable text format using the @code{jellyfish dump}
4384 command, or queried for specific k-mers with @code{jellyfish query}.")
4385 (home-page "http://www.genome.umd.edu/jellyfish.html")
4386 ;; JELLYFISH seems to be 64-bit only.
4387 (supported-systems '("x86_64-linux" "aarch64-linux" "mips64el-linux"))
4388 ;; The combined work is published under the GPLv3 or later. Individual
4389 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
4390 (license (list license:gpl3+ license:expat))))
4392 (define-public khmer
4400 (url "https://github.com/dib-lab/khmer")
4401 (commit (string-append "v" version))))
4402 (file-name (git-file-name name version))
4405 "01l4jczglkl7yfhgvzx8j0df7k54bk1r8sli9ll16i1mis0d8f37"))
4406 (modules '((guix build utils)))
4409 ;; Delete bundled libraries. We do not replace the bundled seqan
4410 ;; as it is a modified subset of the old version 1.4.1.
4412 ;; We do not replace the bundled MurmurHash as the canonical
4413 ;; repository for this code 'SMHasher' is unsuitable for providing
4415 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
4416 (delete-file-recursively "third-party/zlib")
4417 (delete-file-recursively "third-party/bzip2")
4418 (delete-file-recursively "third-party/seqan")
4419 (substitute* "setup.cfg"
4420 (("# libraries = z,bz2")
4421 "libraries = z,bz2")
4422 (("include:third-party/zlib:third-party/bzip2")
4425 (build-system python-build-system)
4428 (modify-phases %standard-phases
4429 (add-after 'unpack 'set-cc
4430 (lambda _ (setenv "CC" "gcc") #t))
4432 (add-before 'reset-gzip-timestamps 'make-files-writable
4433 (lambda* (#:key outputs #:allow-other-keys)
4434 ;; Make sure .gz files are writable so that the
4435 ;; 'reset-gzip-timestamps' phase can do its work.
4436 (let ((out (assoc-ref outputs "out")))
4437 (for-each make-file-writable
4438 (find-files out "\\.gz$"))
4441 `(("python-cython" ,python-cython)
4442 ("python-pytest" ,python-pytest)
4443 ("python-pytest-runner" ,python-pytest-runner)))
4448 ("python-screed" ,python-screed)
4449 ("python-bz2file" ,python-bz2file)))
4450 (home-page "https://khmer.readthedocs.org/")
4451 (synopsis "K-mer counting, filtering and graph traversal library")
4452 (description "The khmer software is a set of command-line tools for
4453 working with DNA shotgun sequencing data from genomes, transcriptomes,
4454 metagenomes and single cells. Khmer can make de novo assemblies faster, and
4455 sometimes better. Khmer can also identify and fix problems with shotgun
4457 ;; When building on i686, armhf and mips64el, we get the following error:
4458 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
4459 (supported-systems '("x86_64-linux" "aarch64-linux"))
4460 (license license:bsd-3)))
4462 (define-public kaiju
4469 (url "https://github.com/bioinformatics-centre/kaiju")
4470 (commit (string-append "v" version))))
4471 (file-name (git-file-name name version))
4474 "119pzi0ddzv9mjg4wwa6han0cwr3k3ssn7kirvsjfcq05mi5ka0x"))))
4475 (build-system gnu-build-system)
4477 `(#:tests? #f ; There are no tests.
4479 (modify-phases %standard-phases
4481 (add-before 'build 'move-to-src-dir
4482 (lambda _ (chdir "src") #t))
4484 (lambda* (#:key inputs outputs #:allow-other-keys)
4485 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
4488 (copy-recursively "bin" bin))
4493 (home-page "http://kaiju.binf.ku.dk/")
4494 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
4495 (description "Kaiju is a program for sensitive taxonomic classification
4496 of high-throughput sequencing reads from metagenomic whole genome sequencing
4498 (license license:gpl3+)))
4505 ;; The PyPi tarball does not contain tests.
4508 (url "https://github.com/macs3-project/MACS")
4509 (commit (string-append "v" version))))
4510 (file-name (git-file-name name version))
4513 "1c5gxr0mk6hkd4vclf0k00wvyvzw2vrmk52c85338p7aqjwg6n15"))
4514 (modules '((guix build utils)))
4515 ;; Remove files generated by Cython
4518 (for-each (lambda (file)
4519 (let ((generated-file
4520 (string-append (string-drop-right file 3) "c")))
4521 (when (file-exists? generated-file)
4522 (delete-file generated-file))))
4523 (find-files "." "\\.pyx$"))
4524 (delete-file "MACS2/IO/CallPeakUnitPrecompiled.c")
4526 (build-system python-build-system)
4529 (modify-phases %standard-phases
4531 (lambda* (#:key tests? inputs outputs #:allow-other-keys)
4533 (add-installed-pythonpath inputs outputs)
4534 (invoke "pytest" "-v"))
4537 `(("python-numpy" ,python-numpy)))
4539 `(("python-cython" ,python-cython)
4540 ("python-pytest" ,python-pytest)))
4541 (home-page "https://github.com/macs3-project/MACS")
4542 (synopsis "Model based analysis for ChIP-Seq data")
4544 "MACS is an implementation of a ChIP-Seq analysis algorithm for
4545 identifying transcript factor binding sites named Model-based Analysis of
4546 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
4547 the significance of enriched ChIP regions and it improves the spatial
4548 resolution of binding sites through combining the information of both
4549 sequencing tag position and orientation.")
4550 (license license:bsd-3)))
4552 (define-public mafft
4559 "https://mafft.cbrc.jp/alignment/software/mafft-" version
4560 "-without-extensions-src.tgz"))
4561 (file-name (string-append name "-" version ".tgz"))
4564 "0r1973fx2scq4712zdqfy67wkzqj0c0bhrdy4jxhvq40mdxyry30"))))
4565 (build-system gnu-build-system)
4567 `(#:tests? #f ; no automated tests, though there are tests in the read me
4568 #:make-flags (let ((out (assoc-ref %outputs "out")))
4569 (list (string-append "PREFIX=" out)
4570 (string-append "BINDIR="
4571 (string-append out "/bin"))))
4573 (modify-phases %standard-phases
4574 (add-after 'unpack 'enter-dir
4575 (lambda _ (chdir "core") #t))
4576 (add-after 'enter-dir 'patch-makefile
4578 ;; on advice from the MAFFT authors, there is no need to
4579 ;; distribute mafft-profile, mafft-distance, or
4580 ;; mafft-homologs.rb as they are too "specialised".
4581 (substitute* "Makefile"
4582 ;; remove mafft-homologs.rb from SCRIPTS
4583 (("^SCRIPTS = mafft mafft-homologs.rb")
4585 ;; remove mafft-homologs from MANPAGES
4586 (("^MANPAGES = mafft.1 mafft-homologs.1")
4587 "MANPAGES = mafft.1")
4588 ;; remove mafft-distance from PROGS
4589 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
4590 "PROGS = dvtditr dndfast7 dndblast sextet5")
4591 ;; remove mafft-profile from PROGS
4592 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
4593 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
4594 (("^rm -f mafft-profile mafft-profile.exe") "#")
4595 (("^rm -f mafft-distance mafft-distance.exe") ")#")
4596 ;; do not install MAN pages in libexec folder
4597 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
4598 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
4600 (add-after 'enter-dir 'patch-paths
4601 (lambda* (#:key inputs #:allow-other-keys)
4602 (substitute* '("pairash.c"
4604 (("perl") (which "perl"))
4605 (("([\"`| ])awk" _ prefix)
4606 (string-append prefix (which "awk")))
4607 (("grep") (which "grep")))
4610 (add-after 'install 'wrap-programs
4611 (lambda* (#:key outputs #:allow-other-keys)
4612 (let* ((out (assoc-ref outputs "out"))
4613 (bin (string-append out "/bin"))
4614 (path (string-append
4615 (assoc-ref %build-inputs "coreutils") "/bin:")))
4616 (for-each (lambda (file)
4618 `("PATH" ":" prefix (,path))))
4626 ("coreutils" ,coreutils)))
4627 (home-page "https://mafft.cbrc.jp/alignment/software/")
4628 (synopsis "Multiple sequence alignment program")
4630 "MAFFT offers a range of multiple alignment methods for nucleotide and
4631 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
4632 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
4634 (license (license:non-copyleft
4635 "https://mafft.cbrc.jp/alignment/software/license.txt"
4636 "BSD-3 with different formatting"))))
4645 (url "https://github.com/marbl/mash")
4646 (commit (string-append "v" version))))
4647 (file-name (git-file-name name version))
4650 "049hwcc059p2fd9vwndn63laifvvsi0wmv84i6y1fr79k15dxwy6"))
4651 (modules '((guix build utils)))
4654 ;; Delete bundled kseq.
4655 ;; TODO: Also delete bundled murmurhash and open bloom filter.
4656 (delete-file "src/mash/kseq.h")
4658 (build-system gnu-build-system)
4660 `(#:tests? #f ; No tests.
4663 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
4664 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
4665 #:make-flags (list "CC=gcc")
4667 (modify-phases %standard-phases
4668 (add-after 'unpack 'fix-includes
4670 (substitute* '("src/mash/Sketch.cpp"
4671 "src/mash/CommandFind.cpp"
4672 "src/mash/CommandScreen.cpp")
4673 (("^#include \"kseq\\.h\"")
4674 "#include \"htslib/kseq.h\""))
4676 (add-after 'fix-includes 'use-c++14
4678 ;; capnproto 0.7 requires c++14 to build
4679 (substitute* "configure.ac"
4680 (("c\\+\\+11") "c++14"))
4681 (substitute* "Makefile.in"
4682 (("c\\+\\+11") "c++14"))
4685 `(("autoconf" ,autoconf)
4686 ;; Capnproto and htslib are statically embedded in the final
4687 ;; application. Therefore we also list their licenses, below.
4688 ("capnproto" ,capnproto)
4689 ("htslib" ,htslib)))
4693 (supported-systems '("x86_64-linux"))
4694 (home-page "https://mash.readthedocs.io")
4695 (synopsis "Fast genome and metagenome distance estimation using MinHash")
4696 (description "Mash is a fast sequence distance estimator that uses the
4697 MinHash algorithm and is designed to work with genomes and metagenomes in the
4698 form of assemblies or reads.")
4699 (license (list license:bsd-3 ; Mash
4700 license:expat ; HTSlib and capnproto
4701 license:public-domain ; MurmurHash 3
4702 license:cpl1.0)))) ; Open Bloom Filter
4704 (define-public metabat
4712 (url "https://bitbucket.org/berkeleylab/metabat.git")
4713 (commit (string-append "v" version))))
4714 (file-name (git-file-name name version))
4717 "0hyg2smw1nz69mfvjpk45xyyychmda92c80a0cv7baji84ri4iyn"))
4718 (patches (search-patches "metabat-fix-compilation.patch"))))
4719 (build-system scons-build-system)
4721 `(#:scons ,scons-python2
4723 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
4724 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
4725 #:tests? #f ;; Tests are run during the build phase.
4727 (modify-phases %standard-phases
4728 (add-after 'unpack 'fix-includes
4730 (substitute* "src/BamUtils.h"
4731 (("^#include \"bam/bam\\.h\"")
4732 "#include \"samtools/bam.h\"")
4733 (("^#include \"bam/sam\\.h\"")
4734 "#include \"samtools/sam.h\""))
4735 (substitute* "src/KseqReader.h"
4736 (("^#include \"bam/kseq\\.h\"")
4737 "#include \"htslib/kseq.h\""))
4739 (add-after 'unpack 'fix-scons
4740 (lambda* (#:key inputs #:allow-other-keys)
4741 (substitute* "SConstruct"
4742 (("^htslib_dir += 'samtools'")
4743 (string-append "htslib_dir = '"
4744 (assoc-ref inputs "htslib")
4746 (("^samtools_dir = 'samtools'")
4747 (string-append "samtools_dir = '"
4748 (assoc-ref inputs "samtools")
4750 (("^findStaticOrShared\\('bam', hts_lib")
4751 (string-append "findStaticOrShared('bam', '"
4752 (assoc-ref inputs "samtools")
4754 ;; Do not distribute README.
4755 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
4760 ("samtools" ,samtools)
4763 (home-page "https://bitbucket.org/berkeleylab/metabat")
4765 "Reconstruction of single genomes from complex microbial communities")
4767 "Grouping large genomic fragments assembled from shotgun metagenomic
4768 sequences to deconvolute complex microbial communities, or metagenome binning,
4769 enables the study of individual organisms and their interactions. MetaBAT is
4770 an automated metagenome binning software, which integrates empirical
4771 probabilistic distances of genome abundance and tetranucleotide frequency.")
4772 ;; The source code contains inline assembly.
4773 (supported-systems '("x86_64-linux" "i686-linux"))
4774 (license (license:non-copyleft "file://license.txt"
4775 "See license.txt in the distribution."))))
4777 (define-public minced
4784 (url "https://github.com/ctSkennerton/minced")
4786 (file-name (git-file-name name version))
4789 "1f5h9him0gd355cnx7p6pnxpknhckd4g0v62mg8zyhfbx9as25fv"))))
4790 (build-system gnu-build-system)
4792 `(#:test-target "test"
4794 (modify-phases %standard-phases
4796 (add-before 'check 'fix-test
4798 ;; Fix test for latest version.
4799 (substitute* "t/Aquifex_aeolicus_VF5.expected"
4800 (("minced:0.1.6") "minced:0.2.0"))
4802 (replace 'install ; No install target.
4803 (lambda* (#:key inputs outputs #:allow-other-keys)
4804 (let* ((out (assoc-ref outputs "out"))
4805 (bin (string-append out "/bin"))
4806 (wrapper (string-append bin "/minced")))
4807 ;; Minced comes with a wrapper script that tries to figure out where
4808 ;; it is located before running the JAR. Since these paths are known
4809 ;; to us, we build our own wrapper to avoid coreutils dependency.
4810 (install-file "minced.jar" bin)
4811 (with-output-to-file wrapper
4815 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
4816 (assoc-ref inputs "jre") "/bin/java -jar "
4817 bin "/minced.jar \"$@\"\n"))))
4818 (chmod wrapper #o555))
4821 `(("jdk" ,icedtea "jdk")))
4824 ("jre" ,icedtea "out")))
4825 (home-page "https://github.com/ctSkennerton/minced")
4826 (synopsis "Mining CRISPRs in Environmental Datasets")
4828 "MinCED is a program to find Clustered Regularly Interspaced Short
4829 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
4830 unassembled metagenomic reads, but is mainly designed for full genomes and
4831 assembled metagenomic sequence.")
4832 (license license:gpl3+)))
4840 (uri (pypi-uri "misopy" version))
4843 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
4844 (modules '((guix build utils)))
4846 (substitute* "setup.py"
4847 ;; Use setuptools, or else the executables are not
4849 (("distutils.core") "setuptools")
4850 ;; Use "gcc" instead of "cc" for compilation.
4852 "cc.set_executables(
4856 linker_so='gcc -shared'); defines"))
4858 (build-system python-build-system)
4860 `(#:python ,python-2 ; only Python 2 is supported
4861 #:tests? #f)) ; no "test" target
4863 `(("samtools" ,samtools)
4864 ("python-numpy" ,python2-numpy)
4865 ("python-pysam" ,python2-pysam)
4866 ("python-scipy" ,python2-scipy)
4867 ("python-matplotlib" ,python2-matplotlib)))
4869 `(("python-mock" ,python2-mock) ; for tests
4870 ("python-pytz" ,python2-pytz))) ; for tests
4871 (home-page "https://www.genes.mit.edu/burgelab/miso/index.html")
4872 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
4874 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
4875 the expression level of alternatively spliced genes from RNA-Seq data, and
4876 identifies differentially regulated isoforms or exons across samples. By
4877 modeling the generative process by which reads are produced from isoforms in
4878 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
4879 that a read originated from a particular isoform.")
4880 (license license:gpl2)))
4882 (define-public muscle
4885 (version "3.8.1551")
4887 (method url-fetch/tarbomb)
4889 "http://www.drive5.com/muscle/muscle_src_"
4893 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
4894 (build-system gnu-build-system)
4896 `(#:make-flags (list "LDLIBS = -lm")
4898 (modify-phases %standard-phases
4901 ;; There are no tests, so just test if it runs.
4902 (lambda _ (invoke "./muscle" "-version") #t))
4904 (lambda* (#:key outputs #:allow-other-keys)
4905 (let* ((out (assoc-ref outputs "out"))
4906 (bin (string-append out "/bin")))
4907 (install-file "muscle" bin)
4909 (home-page "http://www.drive5.com/muscle")
4910 (synopsis "Multiple sequence alignment program")
4912 "MUSCLE aims to be a fast and accurate multiple sequence alignment
4913 program for nucleotide and protein sequences.")
4914 ;; License information found in 'muscle -h' and usage.cpp.
4915 (license license:public-domain)))
4917 (define-public newick-utils
4918 ;; There are no recent releases so we package from git.
4919 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
4921 (name "newick-utils")
4922 (version (string-append "1.6-1." (string-take commit 8)))
4926 (url "https://github.com/tjunier/newick_utils")
4928 (file-name (string-append name "-" version "-checkout"))
4931 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4932 (build-system gnu-build-system)
4934 ;; XXX: TODO: Enable Lua and Guile bindings.
4935 ;; https://github.com/tjunier/newick_utils/issues/13
4936 `(("libxml2" ,libxml2)
4940 `(("autoconf" ,autoconf)
4941 ("automake" ,automake)
4942 ("libtool" ,libtool)))
4943 (synopsis "Programs for working with newick format phylogenetic trees")
4945 "Newick-utils is a suite of utilities for processing phylogenetic trees
4946 in Newick format. Functions include re-rooting, extracting subtrees,
4947 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4948 (home-page "https://github.com/tjunier/newick_utils")
4949 (license license:bsd-3))))
4958 "https://github.com/wwood/OrfM/releases/download/v"
4959 version "/orfm-" version ".tar.gz"))
4962 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4963 (build-system gnu-build-system)
4964 (inputs `(("zlib" ,zlib)))
4966 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4967 ("ruby-rspec" ,ruby-rspec)
4969 (synopsis "Simple and not slow open reading frame (ORF) caller")
4971 "An ORF caller finds stretches of DNA that, when translated, are not
4972 interrupted by stop codons. OrfM finds and prints these ORFs.")
4973 (home-page "https://github.com/wwood/OrfM")
4974 (license license:lgpl3+)))
4976 (define-public python2-pbcore
4978 (name "python2-pbcore")
4982 (uri (pypi-uri "pbcore" version))
4985 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4986 (build-system python-build-system)
4988 `(#:python ,python-2 ;pbcore < 2.0 requires Python 2.7
4989 #:phases (modify-phases %standard-phases
4990 (add-after 'unpack 'remove-sphinx-dependency
4992 ;; Sphinx is only required for documentation tests, which
4993 ;; we do not run; furthermore it depends on python2-sphinx
4994 ;; which is no longer maintained.
4995 (substitute* "requirements-dev.txt"
4999 `(("python-cython" ,python2-cython)
5000 ("python-numpy" ,python2-numpy)
5001 ("python-pysam" ,python2-pysam)
5002 ("python-h5py" ,python2-h5py)))
5004 `(("python-nose" ,python2-nose)
5005 ("python-pyxb" ,python2-pyxb)))
5006 (home-page "https://pacificbiosciences.github.io/pbcore/")
5007 (synopsis "Library for reading and writing PacBio data files")
5009 "The pbcore package provides Python APIs for interacting with PacBio data
5010 files and writing bioinformatics applications.")
5011 (license license:bsd-3)))
5013 (define-public python2-warpedlmm
5015 (name "python2-warpedlmm")
5020 (uri (pypi-uri "WarpedLMM" version ".zip"))
5023 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
5024 (build-system python-build-system)
5026 `(#:python ,python-2 ; requires Python 2.7
5027 #:tests? #f ; test data are not included
5029 (modify-phases %standard-phases
5030 (add-after 'unpack 'use-weave
5032 (substitute* "warpedlmm/util/linalg.py"
5033 (("from scipy import linalg, weave")
5034 "from scipy import linalg\nimport weave"))
5037 `(("python-scipy" ,python2-scipy)
5038 ("python-numpy" ,python2-numpy)
5039 ("python-matplotlib" ,python2-matplotlib)
5040 ("python-fastlmm" ,python2-fastlmm)
5041 ("python-pandas" ,python2-pandas)
5042 ("python-pysnptools" ,python2-pysnptools)
5043 ("python-weave" ,python2-weave)))
5045 `(("python-mock" ,python2-mock)
5046 ("python-nose" ,python2-nose)
5048 (home-page "https://github.com/PMBio/warpedLMM")
5049 (synopsis "Implementation of warped linear mixed models")
5051 "WarpedLMM is a Python implementation of the warped linear mixed model,
5052 which automatically learns an optimal warping function (or transformation) for
5053 the phenotype as it models the data.")
5054 (license license:asl2.0)))
5056 (define-public pbtranscript-tofu
5057 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
5059 (name "pbtranscript-tofu")
5060 (version (string-append "2.2.3." (string-take commit 7)))
5064 (url "https://github.com/PacificBiosciences/cDNA_primer")
5066 (file-name (string-append name "-" version "-checkout"))
5069 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
5070 (modules '((guix build utils)))
5073 ;; remove bundled Cython sources
5074 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
5076 (build-system python-build-system)
5078 `(#:python ,python-2
5079 ;; FIXME: Tests fail with "No such file or directory:
5080 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
5083 (modify-phases %standard-phases
5084 (add-after 'unpack 'enter-directory
5086 (chdir "pbtranscript-tofu/pbtranscript/")
5088 ;; With setuptools version 18.0 and later this setup.py hack causes
5089 ;; a build error, so we disable it.
5090 (add-after 'enter-directory 'patch-setuppy
5092 (substitute* "setup.py"
5093 (("if 'setuptools.extension' in sys.modules:")
5097 `(("python-numpy" ,python2-numpy)
5098 ("python-bx-python" ,python2-bx-python)
5099 ("python-networkx" ,python2-networkx)
5100 ("python-scipy" ,python2-scipy)
5101 ("python-pbcore" ,python2-pbcore)
5102 ("python-h5py" ,python2-h5py)))
5104 `(("python-cython" ,python2-cython)
5105 ("python-nose" ,python2-nose)))
5106 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
5107 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
5109 "pbtranscript-tofu contains scripts to analyze transcriptome data
5110 generated using the PacBio Iso-Seq protocol.")
5111 (license license:bsd-3))))
5113 (define-public prank
5120 "http://wasabiapp.org/download/prank/prank.source."
5124 "0nc8g9c5rkdxcir46s0in9ci1sxwzbjibxrvkksf22ybnplvagk2"))))
5125 (build-system gnu-build-system)
5128 (modify-phases %standard-phases
5129 (add-after 'unpack 'enter-src-dir
5133 (add-after 'unpack 'remove-m64-flag
5134 ;; Prank will build with the correct 'bit-ness' without this flag
5135 ;; and this allows building on 32-bit machines.
5136 (lambda _ (substitute* "src/Makefile"
5141 (lambda* (#:key outputs #:allow-other-keys)
5142 (let* ((out (assoc-ref outputs "out"))
5143 (bin (string-append out "/bin"))
5144 (man (string-append out "/share/man/man1"))
5145 (path (string-append
5146 (assoc-ref %build-inputs "mafft") "/bin:"
5147 (assoc-ref %build-inputs "exonerate") "/bin:"
5148 (assoc-ref %build-inputs "bppsuite") "/bin")))
5149 (install-file "prank" bin)
5150 (wrap-program (string-append bin "/prank")
5151 `("PATH" ":" prefix (,path)))
5152 (install-file "prank.1" man))
5156 ("exonerate" ,exonerate)
5157 ("bppsuite" ,bppsuite)))
5158 (home-page "http://wasabiapp.org/software/prank/")
5159 (synopsis "Probabilistic multiple sequence alignment program")
5161 "PRANK is a probabilistic multiple sequence alignment program for DNA,
5162 codon and amino-acid sequences. It is based on a novel algorithm that treats
5163 insertions correctly and avoids over-estimation of the number of deletion
5164 events. In addition, PRANK borrows ideas from maximum likelihood methods used
5165 in phylogenetics and correctly takes into account the evolutionary distances
5166 between sequences. Lastly, PRANK allows for defining a potential structure
5167 for sequences to be aligned and then, simultaneously with the alignment,
5168 predicts the locations of structural units in the sequences.")
5169 (license license:gpl2+)))
5171 (define-public proteinortho
5173 (name "proteinortho")
5178 (url "https://gitlab.com/paulklemm_PHD/proteinortho.git")
5179 (commit (string-append "v" version))))
5180 (file-name (git-file-name name version))
5183 "0pmy617zy2z2w6hjqxjhf3rzikf5n3mpia80ysq8233vfr7wrzff"))
5184 (modules '((guix build utils)))
5187 ;; remove pre-built scripts
5188 (delete-file-recursively "src/BUILD/")
5190 (build-system gnu-build-system)
5192 `(#:test-target "test"
5193 #:make-flags '("CC=gcc")
5195 (modify-phases %standard-phases
5197 ;; There is no configure script, so we modify the Makefile directly.
5198 (lambda* (#:key outputs #:allow-other-keys)
5199 (substitute* "Makefile"
5202 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
5204 (add-before 'install 'make-install-directory
5205 ;; The install directory is not created during 'make install'.
5206 (lambda* (#:key outputs #:allow-other-keys)
5207 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
5209 (add-after 'install 'wrap-programs
5210 (lambda* (#:key inputs outputs #:allow-other-keys)
5211 (let ((path (getenv "PATH"))
5212 (out (assoc-ref outputs "out")))
5213 (for-each (lambda (script)
5214 (wrap-script script `("PATH" ":" prefix (,path))))
5215 (cons (string-append out "/bin/proteinortho")
5216 (find-files out "\\.(pl|py)$"))))
5219 `(("guile" ,guile-3.0) ; for wrap-script
5220 ("diamond" ,diamond)
5222 ("python" ,python-wrapper)
5225 ("openblas" ,openblas)))
5227 `(("which" ,which)))
5228 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
5229 (synopsis "Detect orthologous genes across species")
5231 "Proteinortho is a tool to detect orthologous genes across different
5232 species. For doing so, it compares similarities of given gene sequences and
5233 clusters them to find significant groups. The algorithm was designed to handle
5234 large-scale data and can be applied to hundreds of species at once.")
5235 (license license:gpl3+)))
5237 (define-public pyicoteo
5245 (url "https://bitbucket.org/regulatorygenomicsupf/pyicoteo.git")
5246 (commit (string-append "v" version))))
5247 (file-name (git-file-name name version))
5250 "0hz5g8d25lbjy1wpscr490l0lmyvaix893hhax4fxnh1h9w34w8p"))))
5251 (build-system python-build-system)
5253 `(#:python ,python-2 ; does not work with Python 3
5254 #:tests? #f)) ; there are no tests
5256 `(("python2-matplotlib" ,python2-matplotlib)))
5257 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
5258 (synopsis "Analyze high-throughput genetic sequencing data")
5260 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
5261 sequencing data. It works with genomic coordinates. There are currently six
5262 different command-line tools:
5265 @item pyicoregion: for generating exploratory regions automatically;
5266 @item pyicoenrich: for differential enrichment between two conditions;
5267 @item pyicoclip: for calling CLIP-Seq peaks without a control;
5268 @item pyicos: for genomic coordinates manipulation;
5269 @item pyicoller: for peak calling on punctuated ChIP-Seq;
5270 @item pyicount: to count how many reads from N experiment files overlap in a
5272 @item pyicotrocol: to combine operations from pyicoteo.
5274 (license license:gpl3+)))
5276 (define-public prodigal
5279 ;; Check for a new home page when updating this package:
5280 ;; https://github.com/hyattpd/Prodigal/issues/36#issuecomment-536617588
5285 (url "https://github.com/hyattpd/Prodigal")
5286 (commit (string-append "v" version))))
5287 (file-name (git-file-name name version))
5290 "1fs1hqk83qjbjhrvhw6ni75zakx5ki1ayy3v6wwkn3xvahc9hi5s"))))
5291 (build-system gnu-build-system)
5293 `(#:tests? #f ; no check target
5294 #:make-flags (list (string-append "INSTALLDIR="
5295 (assoc-ref %outputs "out")
5298 (modify-phases %standard-phases
5299 (delete 'configure))))
5300 (home-page "https://github.com/hyattpd/Prodigal")
5301 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
5303 "Prodigal runs smoothly on finished genomes, draft genomes, and
5304 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
5305 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
5306 partial genes, and identifies translation initiation sites.")
5307 (license license:gpl3+)))
5309 (define-public roary
5317 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
5321 "0qxrds9wx7cfhlkihrp6697kx0flhhxymap9fwan0b3rbdhcnmff"))))
5322 (build-system perl-build-system)
5325 (modify-phases %standard-phases
5330 ;; The tests are not run by default, so we run each test file
5332 (setenv "PATH" (string-append (getcwd) "/bin" ":"
5334 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
5335 (getenv "PERL5LIB")))
5336 (for-each (lambda (file)
5337 (display file)(display "\n")
5338 (invoke "perl" file))
5339 (find-files "t" ".*\\.t$"))
5342 ;; There is no 'install' target in the Makefile.
5343 (lambda* (#:key outputs #:allow-other-keys)
5344 (let* ((out (assoc-ref outputs "out"))
5345 (bin (string-append out "/bin"))
5346 (perl (string-append out "/lib/perl5/site_perl"))
5347 (roary-plots "contrib/roary_plots"))
5350 (copy-recursively "bin" bin)
5351 (copy-recursively "lib" perl)
5353 (add-after 'install 'wrap-programs
5354 (lambda* (#:key inputs outputs #:allow-other-keys)
5355 (let* ((out (assoc-ref outputs "out"))
5356 (perl5lib (getenv "PERL5LIB"))
5357 (path (getenv "PATH")))
5358 (for-each (lambda (prog)
5359 (let ((binary (string-append out "/" prog)))
5360 (wrap-program binary
5361 `("PERL5LIB" ":" prefix
5362 (,(string-append perl5lib ":" out
5363 "/lib/perl5/site_perl"))))
5364 (wrap-program binary
5366 (,(string-append path ":" out "/bin"))))))
5367 (find-files "bin" ".*[^R]$"))
5369 (string-append out "/bin/roary-create_pan_genome_plots.R"))
5370 (r-site-lib (getenv "R_LIBS_SITE"))
5372 (string-append (assoc-ref inputs "coreutils") "/bin")))
5374 `("R_LIBS_SITE" ":" prefix
5375 (,(string-append r-site-lib ":" out "/site-library/"))))
5378 (,(string-append coreutils-path ":" out "/bin"))))))
5381 `(("perl-env-path" ,perl-env-path)
5382 ("perl-test-files" ,perl-test-files)
5383 ("perl-test-most" ,perl-test-most)
5384 ("perl-test-output" ,perl-test-output)))
5386 `(("perl-array-utils" ,perl-array-utils)
5387 ("bioperl" ,bioperl-minimal)
5388 ("perl-digest-md5-file" ,perl-digest-md5-file)
5389 ("perl-exception-class" ,perl-exception-class)
5390 ("perl-file-find-rule" ,perl-file-find-rule)
5391 ("perl-file-grep" ,perl-file-grep)
5392 ("perl-file-slurper" ,perl-file-slurper)
5393 ("perl-file-which" ,perl-file-which)
5394 ("perl-graph" ,perl-graph)
5395 ("perl-graph-readwrite" ,perl-graph-readwrite)
5396 ("perl-log-log4perl" ,perl-log-log4perl)
5397 ("perl-moose" ,perl-moose)
5398 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
5399 ("perl-text-csv" ,perl-text-csv)
5400 ("bedtools" ,bedtools)
5404 ("parallel" ,parallel)
5407 ("fasttree" ,fasttree)
5411 ("r-minimal" ,r-minimal)
5412 ("r-ggplot2" ,r-ggplot2)
5413 ("coreutils" ,coreutils)))
5414 (home-page "https://sanger-pathogens.github.io/Roary/")
5415 (synopsis "High speed stand-alone pan genome pipeline")
5417 "Roary is a high speed stand alone pan genome pipeline, which takes
5418 annotated assemblies in GFF3 format (produced by the Prokka program) and
5419 calculates the pan genome. Using a standard desktop PC, it can analyse
5420 datasets with thousands of samples, without compromising the quality of the
5421 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
5422 single processor. Roary is not intended for metagenomics or for comparing
5423 extremely diverse sets of genomes.")
5424 (license license:gpl3)))
5426 (define-public raxml
5434 (url "https://github.com/stamatak/standard-RAxML")
5435 (commit (string-append "v" version))))
5436 (file-name (git-file-name name version))
5439 "1jqjzhch0rips0vp04prvb8vmc20c5pdmsqn8knadcf91yy859fh"))))
5440 (build-system gnu-build-system)
5442 `(#:tests? #f ; There are no tests.
5443 ;; Use 'standard' Makefile rather than SSE or AVX ones.
5444 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
5446 (modify-phases %standard-phases
5449 (lambda* (#:key outputs #:allow-other-keys)
5450 (let* ((out (assoc-ref outputs "out"))
5451 (bin (string-append out "/bin"))
5452 (executable "raxmlHPC-HYBRID"))
5453 (install-file executable bin)
5454 (symlink (string-append bin "/" executable) "raxml"))
5457 `(("openmpi" ,openmpi)))
5458 (home-page "https://cme.h-its.org/exelixis/web/software/raxml/index.html")
5459 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
5461 "RAxML is a tool for phylogenetic analysis and post-analysis of large
5463 ;; The source includes x86 specific code
5464 (supported-systems '("x86_64-linux" "i686-linux"))
5465 (license license:gpl2+)))
5475 (url "https://github.com/deweylab/RSEM")
5476 (commit (string-append "v" version))))
5478 (base32 "1jlq11d1p8qp64w75yj8cnbbd1a93viq10pzsbwal7vdn8fg13j1"))
5479 (file-name (git-file-name name version))
5480 (modules '((guix build utils)))
5483 ;; remove bundled copy of boost and samtools
5484 (delete-file-recursively "boost")
5485 (delete-file-recursively "samtools-1.3")
5487 (build-system gnu-build-system)
5489 `(#:tests? #f ;no "check" target
5491 (list (string-append "BOOST="
5492 (assoc-ref %build-inputs "boost")
5494 (string-append "SAMHEADERS="
5495 (assoc-ref %build-inputs "htslib")
5496 "/include/htslib/sam.h")
5497 (string-append "SAMLIBS="
5498 (assoc-ref %build-inputs "htslib")
5501 (modify-phases %standard-phases
5502 ;; No "configure" script.
5503 ;; Do not build bundled samtools library.
5506 (substitute* "Makefile"
5507 (("^all : \\$\\(PROGRAMS\\).*") "all: $(PROGRAMS)\n")
5508 (("^\\$\\(SAMLIBS\\).*") ""))
5511 (lambda* (#:key outputs #:allow-other-keys)
5512 (let* ((out (string-append (assoc-ref outputs "out")))
5513 (bin (string-append out "/bin/"))
5514 (perl (string-append out "/lib/perl5/site_perl")))
5517 (for-each (lambda (file)
5518 (install-file file bin))
5519 (find-files "." "rsem-.*"))
5520 (install-file "rsem_perl_utils.pm" perl))
5522 (add-after 'install 'wrap-program
5523 (lambda* (#:key outputs #:allow-other-keys)
5524 (let ((out (assoc-ref outputs "out")))
5525 (for-each (lambda (prog)
5526 (wrap-program (string-append out "/bin/" prog)
5527 `("PERL5LIB" ":" prefix
5528 (,(string-append out "/lib/perl5/site_perl")))))
5529 '("rsem-calculate-expression"
5531 "rsem-generate-data-matrix"
5532 "rsem-generate-ngvector"
5533 "rsem-plot-transcript-wiggles"
5534 "rsem-prepare-reference"
5536 "rsem-run-prsem-testing-procedure")))
5540 ("r-minimal" ,r-minimal)
5542 ("htslib" ,htslib-1.3)
5544 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
5545 (synopsis "Estimate gene expression levels from RNA-Seq data")
5547 "RSEM is a software package for estimating gene and isoform expression
5548 levels from RNA-Seq data. The RSEM package provides a user-friendly
5549 interface, supports threads for parallel computation of the EM algorithm,
5550 single-end and paired-end read data, quality scores, variable-length reads and
5551 RSPD estimation. In addition, it provides posterior mean and 95% credibility
5552 interval estimates for expression levels. For visualization, it can generate
5553 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
5554 (license license:gpl3+)))
5556 (define-public rseqc
5564 (string-append "mirror://sourceforge/rseqc/"
5565 "RSeQC-" version ".tar.gz"))
5568 "0gbb9iyb7swiv5455fm5rg98r7l6qn27v564yllqjd574hncpx6m"))))
5569 (build-system python-build-system)
5571 `(("python-cython" ,python-cython)
5572 ("python-bx-python" ,python-bx-python)
5573 ("python-pybigwig" ,python-pybigwig)
5574 ("python-pysam" ,python-pysam)
5575 ("python-numpy" ,python-numpy)
5578 `(("python-nose" ,python-nose)))
5579 (home-page "http://rseqc.sourceforge.net/")
5580 (synopsis "RNA-seq quality control package")
5582 "RSeQC provides a number of modules that can comprehensively evaluate
5583 high throughput sequence data, especially RNA-seq data. Some basic modules
5584 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
5585 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
5586 distribution, coverage uniformity, strand specificity, etc.")
5587 (license license:gpl3+)))
5590 ;; There are no release tarballs. According to the installation
5591 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
5592 ;; stable release is identified by this changeset ID.
5593 (let ((changeset "2329130")
5597 (version (string-append "0-" revision "." changeset))
5601 (url "https://bitbucket.org/libsleipnir/sleipnir")
5602 (changeset changeset)))
5603 (file-name (string-append name "-" version "-checkout"))
5606 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
5607 (build-system gnu-build-system)
5609 `(#:modules ((srfi srfi-1)
5610 (guix build gnu-build-system)
5613 (let ((dirs '("SeekMiner"
5619 (modify-phases %standard-phases
5622 (substitute* "gen_tools_am"
5623 (("/usr/bin/env.*") (which "perl")))
5624 (invoke "bash" "gen_auto")
5626 (add-after 'build 'build-additional-tools
5627 (lambda* (#:key make-flags #:allow-other-keys)
5628 (for-each (lambda (dir)
5629 (with-directory-excursion (string-append "tools/" dir)
5630 (apply invoke "make" make-flags)))
5633 (add-after 'install 'install-additional-tools
5634 (lambda* (#:key make-flags #:allow-other-keys)
5635 (for-each (lambda (dir)
5636 (with-directory-excursion (string-append "tools/" dir)
5637 (apply invoke `("make" ,@make-flags "install"))))
5644 ("readline" ,readline)
5645 ("gengetopt" ,gengetopt)
5646 ("log4cpp" ,log4cpp)))
5648 `(("autoconf" ,autoconf)
5649 ("automake" ,automake)
5651 (home-page "http://seek.princeton.edu")
5652 (synopsis "Gene co-expression search engine")
5654 "SEEK is a computational gene co-expression search engine. SEEK provides
5655 biologists with a way to navigate the massive human expression compendium that
5656 now contains thousands of expression datasets. SEEK returns a robust ranking
5657 of co-expressed genes in the biological area of interest defined by the user's
5658 query genes. It also prioritizes thousands of expression datasets according
5659 to the user's query of interest.")
5660 (license license:cc-by3.0))))
5662 (define-public samtools
5670 (string-append "mirror://sourceforge/samtools/samtools/"
5671 version "/samtools-" version ".tar.bz2"))
5674 "1dp5wknak4arnw5ghhif9mmljlfnw5bgm91wib7z0j8wdjywx0z2"))
5675 (modules '((guix build utils)))
5677 ;; Delete bundled htslib.
5678 (delete-file-recursively "htslib-1.11")
5680 (build-system gnu-build-system)
5682 `(#:modules ((ice-9 ftw)
5684 (guix build gnu-build-system)
5686 #:configure-flags (list "--with-ncurses")
5688 (modify-phases %standard-phases
5689 (add-after 'unpack 'patch-tests
5691 (substitute* "test/test.pl"
5692 ;; The test script calls out to /bin/bash
5693 (("/bin/bash") (which "bash")))
5695 (add-after 'install 'install-library
5696 (lambda* (#:key outputs #:allow-other-keys)
5697 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
5698 (install-file "libbam.a" lib)
5700 (add-after 'install 'install-headers
5701 (lambda* (#:key outputs #:allow-other-keys)
5702 (let ((include (string-append (assoc-ref outputs "out")
5703 "/include/samtools/")))
5704 (for-each (lambda (file)
5705 (install-file file include))
5706 (scandir "." (lambda (name) (string-match "\\.h$" name))))
5708 (native-inputs `(("pkg-config" ,pkg-config)))
5710 `(("htslib" ,htslib)
5711 ("ncurses" ,ncurses)
5715 (home-page "http://samtools.sourceforge.net")
5716 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
5718 "Samtools implements various utilities for post-processing nucleotide
5719 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
5720 variant calling (in conjunction with bcftools), and a simple alignment
5722 (license license:expat)))
5724 (define-public samtools-1.9
5725 (package (inherit samtools)
5732 (string-append "mirror://sourceforge/samtools/samtools/"
5733 version "/samtools-" version ".tar.bz2"))
5736 "10ilqbmm7ri8z431sn90lvbjwizd0hhkf9rcqw8j823hf26nhgq8"))
5737 (modules '((guix build utils)))
5739 ;; Delete bundled htslib.
5740 (delete-file-recursively "htslib-1.9")
5743 `(("htslib" ,htslib-1.9)
5744 ("ncurses" ,ncurses)
5749 (define-public samtools-0.1
5750 ;; This is the most recent version of the 0.1 line of samtools. The input
5751 ;; and output formats differ greatly from that used and produced by samtools
5752 ;; 1.x and is still used in many bioinformatics pipelines.
5753 (package (inherit samtools)
5759 (string-append "mirror://sourceforge/samtools/samtools/"
5760 version "/samtools-" version ".tar.bz2"))
5762 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
5764 `(#:tests? #f ;no "check" target
5766 (list "LIBCURSES=-lncurses")
5767 ,@(substitute-keyword-arguments (package-arguments samtools)
5769 `(modify-phases ,phases
5771 (lambda* (#:key outputs #:allow-other-keys)
5772 (let ((bin (string-append
5773 (assoc-ref outputs "out") "/bin")))
5775 (install-file "samtools" bin)
5777 (delete 'patch-tests)
5778 (delete 'configure))))))))
5780 (define-public mosaik
5781 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
5786 ;; There are no release tarballs nor tags.
5789 (url "https://github.com/wanpinglee/MOSAIK")
5791 (file-name (string-append name "-" version))
5794 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
5795 (build-system gnu-build-system)
5797 `(#:tests? #f ; no tests
5798 #:make-flags (list "CC=gcc")
5800 (modify-phases %standard-phases
5802 (lambda _ (chdir "src") #t))
5804 (lambda* (#:key outputs #:allow-other-keys)
5805 (let ((bin (string-append (assoc-ref outputs "out")
5808 (copy-recursively "../bin" bin)
5812 ("zlib:static" ,zlib "static")
5814 (supported-systems '("x86_64-linux"))
5815 (home-page "https://github.com/wanpinglee/MOSAIK")
5816 (synopsis "Map nucleotide sequence reads to reference genomes")
5818 "MOSAIK is a program for mapping second and third-generation sequencing
5819 reads to a reference genome. MOSAIK can align reads generated by all the
5820 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
5821 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
5822 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
5823 ;; code released into the public domain:
5824 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
5825 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
5826 (license (list license:gpl2+ license:public-domain)))))
5828 (define-public ngs-sdk
5835 (url "https://github.com/ncbi/ngs")
5837 (file-name (git-file-name name version))
5840 "1ix51c25hjn57w93qmwzw80xh2i34wx8j2hn7szh8p6w8i3az5qa"))))
5841 (build-system gnu-build-system)
5843 `(#:parallel-build? #f ; not supported
5844 #:tests? #f ; no "check" target
5846 (modify-phases %standard-phases
5848 (lambda* (#:key outputs #:allow-other-keys)
5849 (let ((out (assoc-ref outputs "out")))
5850 ;; Allow 'konfigure.perl' to find 'package.prl'.
5852 (string-append ".:" (getenv "PERL5LIB")))
5854 ;; The 'configure' script doesn't recognize things like
5855 ;; '--enable-fast-install'.
5856 (invoke "./configure"
5857 (string-append "--build-prefix=" (getcwd) "/build")
5858 (string-append "--prefix=" out))
5860 (add-after 'unpack 'enter-dir
5861 (lambda _ (chdir "ngs-sdk") #t)))))
5862 (native-inputs `(("perl" ,perl)))
5863 ;; According to the test
5864 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
5865 ;; in ngs-sdk/setup/konfigure.perl
5866 (supported-systems '("i686-linux" "x86_64-linux"))
5867 (home-page "https://github.com/ncbi/ngs")
5868 (synopsis "API for accessing Next Generation Sequencing data")
5870 "NGS is a domain-specific API for accessing reads, alignments and pileups
5871 produced from Next Generation Sequencing. The API itself is independent from
5872 any particular back-end implementation, and supports use of multiple back-ends
5874 (license license:public-domain)))
5876 (define-public java-ngs
5877 (package (inherit ngs-sdk)
5880 `(,@(substitute-keyword-arguments
5881 `(#:modules ((guix build gnu-build-system)
5885 ,@(package-arguments ngs-sdk))
5887 `(modify-phases ,phases
5888 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5890 `(("jdk" ,icedtea "jdk")
5891 ("ngs-sdk" ,ngs-sdk)))
5892 (synopsis "Java bindings for NGS SDK")))
5894 (define-public ncbi-vdb
5901 (url "https://github.com/ncbi/ncbi-vdb")
5903 (file-name (git-file-name name version))
5906 "0m8hlxscidsfqm9x9fyi62q6lpf1dv5115kgjjgnrkl49q9c27m6"))))
5907 (build-system gnu-build-system)
5909 `(#:parallel-build? #f ; not supported
5910 #:tests? #f ; no "check" target
5911 #:make-flags '("HAVE_HDF5=1")
5913 (modify-phases %standard-phases
5914 (add-after 'unpack 'make-files-writable
5915 (lambda _ (for-each make-file-writable (find-files "." ".*")) #t))
5916 (add-before 'configure 'set-perl-search-path
5918 ;; Work around "dotless @INC" build failure.
5920 (string-append (getcwd) "/setup:"
5921 (getenv "PERL5LIB")))
5923 ;; See https://github.com/ncbi/ncbi-vdb/issues/14
5924 (add-after 'unpack 'patch-krypto-flags
5926 (substitute* "libs/krypto/Makefile"
5927 (("-Wa,-march=generic64\\+aes") "")
5928 (("-Wa,-march=generic64\\+sse4") ""))
5931 (lambda* (#:key inputs outputs #:allow-other-keys)
5932 (let ((out (assoc-ref outputs "out")))
5933 ;; Override include path for libmagic
5934 (substitute* "setup/package.prl"
5935 (("name => 'magic', Include => '/usr/include'")
5936 (string-append "name=> 'magic', Include => '"
5937 (assoc-ref inputs "libmagic")
5940 ;; Install kdf5 library (needed by sra-tools)
5941 (substitute* "build/Makefile.install"
5942 (("LIBRARIES_TO_INSTALL =")
5943 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5945 (substitute* "build/Makefile.env"
5946 (("CFLAGS =" prefix)
5947 (string-append prefix "-msse2 ")))
5949 ;; Override search path for ngs-java
5950 (substitute* "setup/package.prl"
5951 (("/usr/local/ngs/ngs-java")
5952 (assoc-ref inputs "java-ngs")))
5954 ;; The 'configure' script doesn't recognize things like
5955 ;; '--enable-fast-install'.
5956 (invoke "./configure"
5957 (string-append "--build-prefix=" (getcwd) "/build")
5958 (string-append "--prefix=" (assoc-ref outputs "out"))
5959 (string-append "--debug")
5960 (string-append "--with-xml2-prefix="
5961 (assoc-ref inputs "libxml2"))
5962 (string-append "--with-ngs-sdk-prefix="
5963 (assoc-ref inputs "ngs-sdk"))
5964 (string-append "--with-hdf5-prefix="
5965 (assoc-ref inputs "hdf5")))
5967 (add-after 'install 'install-interfaces
5968 (lambda* (#:key outputs #:allow-other-keys)
5969 ;; Install interface libraries. On i686 the interface libraries
5970 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5971 ;; architecture name ("i386") instead of the target system prefix
5973 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5974 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5975 ,(system->linux-architecture
5976 (or (%current-target-system)
5979 (string-append (assoc-ref outputs "out")
5981 ;; Install interface headers
5982 (copy-recursively "interfaces"
5983 (string-append (assoc-ref outputs "out")
5986 ;; These files are needed by sra-tools.
5987 (add-after 'install 'install-configuration-files
5988 (lambda* (#:key outputs #:allow-other-keys)
5989 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5991 (install-file "libs/kfg/default.kfg" target)
5992 (install-file "libs/kfg/certs.kfg" target))
5995 `(("libxml2" ,libxml2)
5996 ("ngs-sdk" ,ngs-sdk)
5997 ("java-ngs" ,java-ngs)
6000 (native-inputs `(("perl" ,perl)))
6001 ;; NCBI-VDB requires SSE capability.
6002 (supported-systems '("i686-linux" "x86_64-linux"))
6003 (home-page "https://github.com/ncbi/ncbi-vdb")
6004 (synopsis "Database engine for genetic information")
6006 "The NCBI-VDB library implements a highly compressed columnar data
6007 warehousing engine that is most often used to store genetic information.
6008 Databases are stored in a portable image within the file system, and can be
6009 accessed/downloaded on demand across HTTP.")
6010 (license license:public-domain)))
6012 (define-public plink
6020 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
6021 version "-src.zip"))
6023 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
6024 (patches (search-patches "plink-1.07-unclobber-i.patch"
6025 "plink-endian-detection.patch"))))
6026 (build-system gnu-build-system)
6028 '(#:tests? #f ;no "check" target
6029 #:make-flags (list (string-append "LIB_LAPACK="
6030 (assoc-ref %build-inputs "lapack")
6031 "/lib/liblapack.so")
6034 ;; disable phoning home
6037 (modify-phases %standard-phases
6038 ;; no "configure" script
6041 (lambda* (#:key outputs #:allow-other-keys)
6042 (let ((bin (string-append (assoc-ref outputs "out")
6044 (install-file "plink" bin)
6048 ("lapack" ,lapack)))
6050 `(("unzip" ,unzip)))
6051 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
6052 (synopsis "Whole genome association analysis toolset")
6054 "PLINK is a whole genome association analysis toolset, designed to
6055 perform a range of basic, large-scale analyses in a computationally efficient
6056 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
6057 so there is no support for steps prior to this (e.g. study design and
6058 planning, generating genotype or CNV calls from raw data). Through
6059 integration with gPLINK and Haploview, there is some support for the
6060 subsequent visualization, annotation and storage of results.")
6061 ;; Code is released under GPLv2, except for fisher.h, which is under
6063 (license (list license:gpl2 license:lgpl2.1+))))
6065 (define-public plink-ng
6066 (package (inherit plink)
6073 (url "https://github.com/chrchang/plink-ng")
6074 (commit (string-append "v" version))))
6075 (file-name (git-file-name name version))
6077 (base32 "02npdwgkpfkdnhw819rhj5kw02a5k5m90b14zq9zzya4hyg929c0"))))
6078 (build-system gnu-build-system)
6080 '(#:tests? #f ;no "check" target
6081 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
6082 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
6084 "-f" "Makefile.std")
6086 (modify-phases %standard-phases
6087 (add-after 'unpack 'chdir
6088 (lambda _ (chdir "1.9") #t))
6089 (delete 'configure) ; no "configure" script
6091 (lambda* (#:key outputs #:allow-other-keys)
6092 (let ((bin (string-append (assoc-ref outputs "out")
6094 (install-file "plink" bin)
6099 ("openblas" ,openblas)))
6100 (home-page "https://www.cog-genomics.org/plink/")
6101 (license license:gpl3+)))
6103 (define-public smithlab-cpp
6104 (let ((revision "1")
6105 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
6107 (name "smithlab-cpp")
6108 (version (string-append "0." revision "." (string-take commit 7)))
6112 (url "https://github.com/smithlabcode/smithlab_cpp")
6114 (file-name (string-append name "-" version "-checkout"))
6117 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
6118 (build-system gnu-build-system)
6120 `(#:modules ((guix build gnu-build-system)
6123 #:tests? #f ;no "check" target
6125 (modify-phases %standard-phases
6126 (add-after 'unpack 'use-samtools-headers
6128 (substitute* '("SAM.cpp"
6130 (("sam.h") "samtools/sam.h"))
6133 (lambda* (#:key outputs #:allow-other-keys)
6134 (let* ((out (assoc-ref outputs "out"))
6135 (lib (string-append out "/lib"))
6136 (include (string-append out "/include/smithlab-cpp")))
6139 (for-each (cut install-file <> lib)
6140 (find-files "." "\\.o$"))
6141 (for-each (cut install-file <> include)
6142 (find-files "." "\\.hpp$")))
6144 (delete 'configure))))
6146 `(("samtools" ,samtools-0.1)
6148 (home-page "https://github.com/smithlabcode/smithlab_cpp")
6149 (synopsis "C++ helper library for functions used in Smith lab projects")
6151 "Smithlab CPP is a C++ library that includes functions used in many of
6152 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
6153 structures, classes for genomic regions, mapped sequencing reads, etc.")
6154 (license license:gpl3+))))
6156 (define-public preseq
6162 (uri (string-append "https://github.com/smithlabcode/preseq/"
6163 "releases/download/v" version
6164 "/preseq_v" version ".tar.bz2"))
6166 (base32 "149x9xmk1wy1gff85325yfzqc0qk4sgp1w6gbyj9cnji4x1dszbl"))
6167 (modules '((guix build utils)))
6169 ;; Remove bundled samtools.
6170 (delete-file-recursively "samtools")
6172 (build-system gnu-build-system)
6174 `(#:tests? #f ;no "check" target
6176 (modify-phases %standard-phases
6177 (delete 'configure))
6179 (list (string-append "PREFIX="
6180 (assoc-ref %outputs "out"))
6181 (string-append "LIBBAM="
6182 (assoc-ref %build-inputs "samtools")
6184 (string-append "SMITHLAB_CPP="
6185 (assoc-ref %build-inputs "smithlab-cpp")
6188 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
6191 ("samtools" ,samtools-0.1)
6192 ("smithlab-cpp" ,smithlab-cpp)
6194 (home-page "http://smithlabresearch.org/software/preseq/")
6195 (synopsis "Program for analyzing library complexity")
6197 "The preseq package is aimed at predicting and estimating the complexity
6198 of a genomic sequencing library, equivalent to predicting and estimating the
6199 number of redundant reads from a given sequencing depth and how many will be
6200 expected from additional sequencing using an initial sequencing experiment.
6201 The estimates can then be used to examine the utility of further sequencing,
6202 optimize the sequencing depth, or to screen multiple libraries to avoid low
6203 complexity samples.")
6204 (license license:gpl3+)))
6206 (define-public python-screed
6208 (name "python-screed")
6213 (uri (pypi-uri "screed" version))
6216 "148vcb7w2wr6a4w6vs2bsxanbqibxfk490zbcbg4m61s8669zdjx"))))
6217 (build-system python-build-system)
6220 (modify-phases %standard-phases
6221 ;; Tests must be run after installation, as the "screed" command does
6222 ;; not exist right after building.
6224 (add-after 'install 'check
6225 (lambda* (#:key inputs outputs #:allow-other-keys)
6226 (let ((out (assoc-ref outputs "out")))
6227 (setenv "PYTHONPATH"
6228 (string-append out "/lib/python"
6229 (string-take (string-take-right
6230 (assoc-ref inputs "python")
6233 (getenv "PYTHONPATH")))
6234 (setenv "PATH" (string-append out "/bin:" (getenv "PATH"))))
6235 (invoke "python" "setup.py" "test")
6238 `(("python-pytest" ,python-pytest)
6239 ("python-pytest-cov" ,python-pytest-cov)
6240 ("python-pytest-runner" ,python-pytest-runner)))
6242 `(("python-bz2file" ,python-bz2file)))
6243 (home-page "https://github.com/dib-lab/screed/")
6244 (synopsis "Short read sequence database utilities")
6245 (description "Screed parses FASTA and FASTQ files and generates databases.
6246 Values such as sequence name, sequence description, sequence quality and the
6247 sequence itself can be retrieved from these databases.")
6248 (license license:bsd-3)))
6250 (define-public python2-screed
6251 (package-with-python2 python-screed))
6253 (define-public sra-tools
6261 (url "https://github.com/ncbi/sra-tools")
6263 (file-name (git-file-name name version))
6266 "1cr2mijkfs5sm35ffjs6861qsd1qkgnhnbavdv65zg5d655abbjf"))))
6267 (build-system gnu-build-system)
6269 `(#:parallel-build? #f ; not supported
6270 #:tests? #f ; no "check" target
6272 (list (string-append "DEFAULT_CRT="
6273 (assoc-ref %build-inputs "ncbi-vdb")
6275 (string-append "DEFAULT_KFG="
6276 (assoc-ref %build-inputs "ncbi-vdb")
6278 (string-append "VDB_LIBDIR="
6279 (assoc-ref %build-inputs "ncbi-vdb")
6280 ,(if (string-prefix? "x86_64"
6281 (or (%current-target-system)
6286 (modify-phases %standard-phases
6287 (add-before 'configure 'set-perl-search-path
6289 ;; Work around "dotless @INC" build failure.
6291 (string-append (getcwd) "/setup:"
6292 (getenv "PERL5LIB")))
6295 (lambda* (#:key inputs outputs #:allow-other-keys)
6296 ;; The build system expects a directory containing the sources and
6297 ;; raw build output of ncbi-vdb, including files that are not
6298 ;; installed. Since we are building against an installed version of
6299 ;; ncbi-vdb, the following modifications are needed.
6300 (substitute* "setup/konfigure.perl"
6301 ;; Make the configure script look for the "ilib" directory of
6302 ;; "ncbi-vdb" without first checking for the existence of a
6303 ;; matching library in its "lib" directory.
6304 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
6305 "my $f = File::Spec->catdir($ilibdir, $ilib);")
6306 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
6307 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
6308 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
6311 (substitute* "tools/copycat/Makefile"
6312 (("smagic-static") "lmagic"))
6313 (substitute* "tools/driver-tool/utf8proc/Makefile"
6314 (("CC\\?=gcc") "myCC=gcc")
6315 (("\\(CC\\)") "(myCC)"))
6317 ;; The 'configure' script doesn't recognize things like
6318 ;; '--enable-fast-install'.
6319 (invoke "./configure"
6320 (string-append "--build-prefix=" (getcwd) "/build")
6321 (string-append "--prefix=" (assoc-ref outputs "out"))
6322 (string-append "--debug")
6323 (string-append "--with-fuse-prefix="
6324 (assoc-ref inputs "fuse"))
6325 (string-append "--with-magic-prefix="
6326 (assoc-ref inputs "libmagic"))
6327 ;; TODO: building with libxml2 fails with linker errors
6329 (string-append "--with-xml2-prefix="
6330 (assoc-ref inputs "libxml2"))
6331 (string-append "--with-ncbi-vdb-sources="
6332 (assoc-ref inputs "ncbi-vdb"))
6333 (string-append "--with-ncbi-vdb-build="
6334 (assoc-ref inputs "ncbi-vdb"))
6335 (string-append "--with-ngs-sdk-prefix="
6336 (assoc-ref inputs "ngs-sdk"))
6337 (string-append "--with-hdf5-prefix="
6338 (assoc-ref inputs "hdf5")))
6340 (native-inputs `(("perl" ,perl)))
6342 `(("ngs-sdk" ,ngs-sdk)
6343 ("ncbi-vdb" ,ncbi-vdb)
6348 ("python" ,python-wrapper)))
6350 "https://trace.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
6351 (synopsis "Tools and libraries for reading and writing sequencing data")
6353 "The SRA Toolkit from NCBI is a collection of tools and libraries for
6354 reading of sequencing files from the Sequence Read Archive (SRA) database and
6355 writing files into the .sra format.")
6356 (license license:public-domain)))
6358 (define-public seqan
6364 (uri (string-append "https://github.com/seqan/seqan/releases/"
6365 "download/seqan-v" version
6366 "/seqan-library-" version ".tar.xz"))
6369 "19a1rlxx03qy1i1iriicly68w64yjxbv24g9gdywnfmq998v35yx"))))
6370 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6371 ;; makes sense to split the outputs.
6372 (outputs '("out" "doc"))
6373 (build-system trivial-build-system)
6375 `(#:modules ((guix build utils))
6378 (use-modules (guix build utils))
6379 (let ((tar (assoc-ref %build-inputs "tar"))
6380 (xz (assoc-ref %build-inputs "xz"))
6381 (out (assoc-ref %outputs "out"))
6382 (doc (assoc-ref %outputs "doc")))
6383 (setenv "PATH" (string-append tar "/bin:" xz "/bin"))
6384 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6385 (chdir (string-append "seqan-library-" ,version))
6386 (copy-recursively "include" (string-append out "/include"))
6387 (copy-recursively "share" (string-append doc "/share"))
6390 `(("source" ,source)
6393 (home-page "http://www.seqan.de")
6394 (synopsis "Library for nucleotide sequence analysis")
6396 "SeqAn is a C++ library of efficient algorithms and data structures for
6397 the analysis of sequences with the focus on biological data. It contains
6398 algorithms and data structures for string representation and their
6399 manipulation, online and indexed string search, efficient I/O of
6400 bioinformatics file formats, sequence alignment, and more.")
6401 (license license:bsd-3)))
6403 (define-public seqan-1
6404 (package (inherit seqan)
6409 (uri (string-append "http://packages.seqan.de/seqan-library/"
6410 "seqan-library-" version ".tar.bz2"))
6413 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
6414 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6415 ;; makes sense to split the outputs.
6416 (outputs '("out" "doc"))
6417 (build-system trivial-build-system)
6419 `(#:modules ((guix build utils))
6422 (use-modules (guix build utils))
6423 (let ((tar (assoc-ref %build-inputs "tar"))
6424 (bzip (assoc-ref %build-inputs "bzip2"))
6425 (out (assoc-ref %outputs "out"))
6426 (doc (assoc-ref %outputs "doc")))
6427 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
6428 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6429 (chdir (string-append "seqan-library-" ,version))
6430 (copy-recursively "include" (string-append out "/include"))
6431 (copy-recursively "share" (string-append doc "/share"))
6434 `(("source" ,source)
6436 ("bzip2" ,bzip2)))))
6438 (define-public seqmagick
6445 (uri (pypi-uri "seqmagick" version))
6448 "0pf98da7i59q47gwrbx0wjk6xlvbybiwphw80w7h4ydjj0579a2b"))))
6449 (build-system python-build-system)
6451 `(("python-biopython" ,python-biopython)))
6453 `(("python-nose" ,python-nose)))
6454 (home-page "https://github.com/fhcrc/seqmagick")
6455 (synopsis "Tools for converting and modifying sequence files")
6457 "Bioinformaticians often have to convert sequence files between formats
6458 and do little manipulations on them, and it's not worth writing scripts for
6459 that. Seqmagick is a utility to expose the file format conversion in
6460 BioPython in a convenient way. Instead of having a big mess of scripts, there
6461 is one that takes arguments.")
6462 (license license:gpl3)))
6464 (define-public seqtk
6471 (url "https://github.com/lh3/seqtk")
6472 (commit (string-append "v" version))))
6473 (file-name (git-file-name name version))
6476 "1bfzlqa84b5s1qi22blmmw2s8xdyp9h9ydcq22pfjhh5gab3yz6l"))))
6477 (build-system gnu-build-system)
6480 (modify-phases %standard-phases
6483 ;; There are no tests, so we just run a sanity check.
6484 (lambda _ (invoke "./seqtk" "seq") #t))
6486 (lambda* (#:key outputs #:allow-other-keys)
6487 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6488 (install-file "seqtk" bin)
6492 (home-page "https://github.com/lh3/seqtk")
6493 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
6495 "Seqtk is a fast and lightweight tool for processing sequences in the
6496 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
6497 optionally compressed by gzip.")
6498 (license license:expat)))
6500 (define-public snap-aligner
6502 (name "snap-aligner")
6503 (version "1.0beta.18")
6507 (url "https://github.com/amplab/snap")
6508 (commit (string-append "v" version))))
6509 (file-name (git-file-name name version))
6512 "01w3qq4wm07z73vky0cfwlmrbf50n3w722cxrlzxfi99mnb808d8"))))
6513 (build-system gnu-build-system)
6516 (modify-phases %standard-phases
6518 (replace 'check (lambda _ (invoke "./unit_tests") #t))
6520 (lambda* (#:key outputs #:allow-other-keys)
6521 (let* ((out (assoc-ref outputs "out"))
6522 (bin (string-append out "/bin")))
6523 (install-file "snap-aligner" bin)
6524 (install-file "SNAPCommand" bin)
6528 (home-page "http://snap.cs.berkeley.edu/")
6529 (synopsis "Short read DNA sequence aligner")
6531 "SNAP is a fast and accurate aligner for short DNA reads. It is
6532 optimized for modern read lengths of 100 bases or higher, and takes advantage
6533 of these reads to align data quickly through a hash-based indexing scheme.")
6534 ;; 32-bit systems are not supported by the unpatched code.
6535 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
6536 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
6537 ;; systems without a lot of memory cannot make good use of this program.
6538 (supported-systems '("x86_64-linux"))
6539 (license license:asl2.0)))
6541 (define-public sortmerna
6549 (url "https://github.com/biocore/sortmerna")
6551 (file-name (git-file-name name version))
6554 "0j3mbz4n25738yijmjbr5r4fyvkgm8v5vn3sshyfvmyqf5q9byqf"))))
6555 (build-system gnu-build-system)
6556 (outputs '("out" ;for binaries
6557 "db")) ;for sequence databases
6560 (modify-phases %standard-phases
6562 (lambda* (#:key outputs #:allow-other-keys)
6563 (let* ((out (assoc-ref outputs "out"))
6564 (bin (string-append out "/bin"))
6565 (db (assoc-ref outputs "db"))
6567 (string-append db "/share/sortmerna/rRNA_databases")))
6568 (install-file "sortmerna" bin)
6569 (install-file "indexdb_rna" bin)
6570 (for-each (lambda (file)
6571 (install-file file share))
6572 (find-files "rRNA_databases" ".*fasta"))
6576 (home-page "https://bioinfo.lifl.fr/RNA/sortmerna/")
6577 (synopsis "Biological sequence analysis tool for NGS reads")
6579 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
6580 and operational taxonomic unit (OTU) picking of next generation
6581 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
6582 allows for fast and sensitive analyses of nucleotide sequences. The main
6583 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
6584 ;; The source includes x86 specific code
6585 (supported-systems '("x86_64-linux" "i686-linux"))
6586 (license license:lgpl3)))
6595 (url "https://github.com/alexdobin/STAR")
6597 (file-name (git-file-name name version))
6600 "1hgiqw5qhs0pc1xazzihcfd92na02xyq2kb469z04y1v51kpvvjq"))
6601 (modules '((guix build utils)))
6604 (substitute* "source/Makefile"
6606 ;; Remove pre-built binaries and bundled htslib sources.
6607 (delete-file-recursively "bin/MacOSX_x86_64")
6608 (delete-file-recursively "bin/Linux_x86_64")
6609 (delete-file-recursively "bin/Linux_x86_64_static")
6610 (delete-file-recursively "source/htslib")
6612 (build-system gnu-build-system)
6614 '(#:tests? #f ;no check target
6615 #:make-flags '("STAR")
6617 (modify-phases %standard-phases
6618 (add-after 'unpack 'enter-source-dir
6619 (lambda _ (chdir "source") #t))
6620 (add-after 'enter-source-dir 'make-reproducible
6622 (substitute* "Makefile"
6623 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
6624 (string-append pre "Built with Guix" post)))
6626 ;; See https://github.com/alexdobin/STAR/pull/562
6627 (add-after 'enter-source-dir 'add-missing-header
6629 (substitute* "SoloReadFeature_inputRecords.cpp"
6630 (("#include \"binarySearch2.h\"" h)
6631 (string-append h "\n#include <math.h>")))
6633 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
6635 (substitute* "Makefile"
6636 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
6638 (substitute* '("BAMfunctions.cpp"
6643 "bamRemoveDuplicates.cpp")
6644 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
6645 (string-append "#include <" header ">")))
6646 (substitute* "IncludeDefine.h"
6647 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
6648 (string-append "<" header ">")))
6651 (lambda* (#:key outputs #:allow-other-keys)
6652 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6653 (install-file "STAR" bin))
6655 (delete 'configure))))
6659 `(("htslib" ,htslib)
6661 (home-page "https://github.com/alexdobin/STAR")
6662 (synopsis "Universal RNA-seq aligner")
6664 "The Spliced Transcripts Alignment to a Reference (STAR) software is
6665 based on a previously undescribed RNA-seq alignment algorithm that uses
6666 sequential maximum mappable seed search in uncompressed suffix arrays followed
6667 by seed clustering and stitching procedure. In addition to unbiased de novo
6668 detection of canonical junctions, STAR can discover non-canonical splices and
6669 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
6671 ;; Only 64-bit systems are supported according to the README.
6672 (supported-systems '("x86_64-linux" "mips64el-linux"))
6673 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
6674 (license license:gpl3+)))
6676 (define-public starlong
6677 (package (inherit star)
6680 (substitute-keyword-arguments (package-arguments star)
6681 ((#:make-flags flags)
6684 `(modify-phases ,phases
6685 ;; Allow extra long sequence reads.
6686 (add-after 'unpack 'make-extra-long
6688 (substitute* "source/IncludeDefine.h"
6689 (("(#define DEF_readNameLengthMax ).*" _ match)
6690 (string-append match "900000\n")))
6693 (lambda* (#:key outputs #:allow-other-keys)
6694 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6695 (install-file "STARlong" bin))
6698 (define-public subread
6704 (uri (string-append "mirror://sourceforge/subread/subread-"
6705 version "/subread-" version "-source.tar.gz"))
6708 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
6709 (build-system gnu-build-system)
6711 `(#:tests? #f ;no "check" target
6712 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
6713 ;; optimizations by default, so we override these flags such that x86_64
6714 ;; flags are only added when the build target is an x86_64 system.
6716 (list (let ((system ,(or (%current-target-system)
6718 (flags '("-ggdb" "-fomit-frame-pointer"
6719 "-ffast-math" "-funroll-loops"
6720 "-fmessage-length=0"
6721 "-O9" "-Wall" "-DMAKE_FOR_EXON"
6723 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
6724 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
6725 (if (string-prefix? "x86_64" system)
6726 (string-append "CCFLAGS=" (string-join (append flags flags64)))
6727 (string-append "CCFLAGS=" (string-join flags))))
6728 "-f" "Makefile.Linux"
6729 "CC=gcc ${CCFLAGS}")
6731 (modify-phases %standard-phases
6732 (add-after 'unpack 'enter-dir
6733 (lambda _ (chdir "src") #t))
6735 (lambda* (#:key outputs #:allow-other-keys)
6736 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6738 (copy-recursively "../bin" bin))
6740 ;; no "configure" script
6741 (delete 'configure))))
6742 (inputs `(("zlib" ,zlib)))
6743 (home-page "http://bioinf.wehi.edu.au/subread-package/")
6744 (synopsis "Tool kit for processing next-gen sequencing data")
6746 "The subread package contains the following tools: subread aligner, a
6747 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
6748 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
6749 features; exactSNP: a SNP caller that discovers SNPs by testing signals
6750 against local background noises.")
6751 (license license:gpl3+)))
6753 (define-public stringtie
6759 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
6760 "stringtie-" version ".tar.gz"))
6763 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
6764 (modules '((guix build utils)))
6767 (delete-file-recursively "samtools-0.1.18")
6769 (build-system gnu-build-system)
6771 `(#:tests? #f ;no test suite
6773 (modify-phases %standard-phases
6774 ;; no configure script
6776 (add-before 'build 'use-system-samtools
6778 (substitute* "Makefile"
6779 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
6781 (substitute* '("gclib/GBam.h"
6783 (("#include \"(bam|sam|kstring).h\"" _ header)
6784 (string-append "#include <samtools/" header ".h>")))
6786 (add-after 'unpack 'remove-duplicate-typedef
6788 ;; This typedef conflicts with the typedef in
6789 ;; glibc-2.25/include/bits/types.h
6790 (substitute* "gclib/GThreads.h"
6791 (("typedef long long __intmax_t;") ""))
6794 (lambda* (#:key outputs #:allow-other-keys)
6795 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6796 (install-file "stringtie" bin)
6799 `(("samtools" ,samtools-0.1)
6801 (home-page "http://ccb.jhu.edu/software/stringtie/")
6802 (synopsis "Transcript assembly and quantification for RNA-Seq data")
6804 "StringTie is a fast and efficient assembler of RNA-Seq sequence
6805 alignments into potential transcripts. It uses a novel network flow algorithm
6806 as well as an optional de novo assembly step to assemble and quantitate
6807 full-length transcripts representing multiple splice variants for each gene
6808 locus. Its input can include not only the alignments of raw reads used by
6809 other transcript assemblers, but also alignments of longer sequences that have
6810 been assembled from those reads. To identify differentially expressed genes
6811 between experiments, StringTie's output can be processed either by the
6812 Cuffdiff or Ballgown programs.")
6813 (license license:artistic2.0)))
6815 (define-public taxtastic
6820 ;; The Pypi version does not include tests.
6823 (url "https://github.com/fhcrc/taxtastic")
6824 (commit (string-append "v" version))))
6825 (file-name (git-file-name name version))
6828 "1sv8mkg64jn7zdwf1jj71c16686yrwxk0apb1l8sjszy9p166g0p"))))
6829 (build-system python-build-system)
6832 (modify-phases %standard-phases
6833 (add-after 'unpack 'prepare-directory
6835 ;; The git checkout must be writable for tests.
6836 (for-each make-file-writable (find-files "."))
6837 ;; This test fails, but the error is not caught by the test
6838 ;; framework, so the tests fail...
6839 (substitute* "tests/test_taxit.py"
6840 (("self.cmd_fails\\(''\\)")
6841 "self.cmd_fails('nothing')"))
6842 ;; This version file is expected to be created with git describe.
6843 (mkdir-p "taxtastic/data")
6844 (with-output-to-file "taxtastic/data/ver"
6845 (lambda () (display ,version)))
6847 (add-after 'unpack 'python37-compatibility
6849 (substitute* "taxtastic/utils.py"
6850 (("import csv") "import csv, errno")
6851 (("os.errno") "errno"))
6854 ;; Note, this fails to run with "-v" as it tries to write to a
6855 ;; closed output stream.
6856 (lambda _ (invoke "python" "-m" "unittest") #t)))))
6858 `(("python-sqlalchemy" ,python-sqlalchemy)
6859 ("python-decorator" ,python-decorator)
6860 ("python-biopython" ,python-biopython)
6861 ("python-pandas" ,python-pandas)
6862 ("python-psycopg2" ,python-psycopg2)
6863 ("python-fastalite" ,python-fastalite)
6864 ("python-pyyaml" ,python-pyyaml)
6865 ("python-six" ,python-six)
6866 ("python-jinja2" ,python-jinja2)
6867 ("python-dendropy" ,python-dendropy)))
6868 (home-page "https://github.com/fhcrc/taxtastic")
6869 (synopsis "Tools for taxonomic naming and annotation")
6871 "Taxtastic is software written in python used to build and maintain
6872 reference packages i.e. collections of reference trees, reference alignments,
6873 profiles, and associated taxonomic information.")
6874 (license license:gpl3+)))
6876 (define-public vcftools
6883 "https://github.com/vcftools/vcftools/releases/download/v"
6884 version "/vcftools-" version ".tar.gz"))
6887 "1qqlx7flfv7axrjwkaz6njkscsl1d0jw98ns8d8bh1n1hd1pgz6v"))))
6888 (build-system gnu-build-system)
6890 `(#:tests? #f ; no "check" target
6892 "CFLAGS=-O2" ; override "-m64" flag
6893 (string-append "PREFIX=" (assoc-ref %outputs "out"))
6894 (string-append "MANDIR=" (assoc-ref %outputs "out")
6895 "/share/man/man1"))))
6897 `(("pkg-config" ,pkg-config)))
6901 (home-page "https://vcftools.github.io/")
6902 (synopsis "Tools for working with VCF files")
6904 "VCFtools is a program package designed for working with VCF files, such
6905 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
6906 provide easily accessible methods for working with complex genetic variation
6907 data in the form of VCF files.")
6908 ;; The license is declared as LGPLv3 in the README and
6909 ;; at https://vcftools.github.io/license.html
6910 (license license:lgpl3)))
6912 (define-public infernal
6918 (uri (string-append "http://eddylab.org/software/infernal/"
6919 "infernal-" version ".tar.gz"))
6922 "0pm8bm3s6nfa0av4x6m6h27lsg12b3lz3jm0fyh1mc77l2isd61v"))))
6923 (build-system gnu-build-system)
6926 ("python" ,python))) ; for tests
6927 (home-page "http://eddylab.org/infernal/")
6928 (synopsis "Inference of RNA alignments")
6929 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
6930 searching DNA sequence databases for RNA structure and sequence similarities.
6931 It is an implementation of a special case of profile stochastic context-free
6932 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
6933 profile, but it scores a combination of sequence consensus and RNA secondary
6934 structure consensus, so in many cases, it is more capable of identifying RNA
6935 homologs that conserve their secondary structure more than their primary
6937 ;; Infernal 1.1.3 requires VMX or SSE capability for parallel instructions.
6938 (supported-systems '("i686-linux" "x86_64-linux"))
6939 (license license:bsd-3)))
6941 (define-public r-scde
6948 (url "https://github.com/hms-dbmi/scde")
6950 (file-name (git-file-name name version))
6953 "10na2gyka24mszdxf92wz9h2c13hdf1ww30c68gfsw53lvvhhhxb"))))
6954 (build-system r-build-system)
6956 `(("r-rcpp" ,r-rcpp)
6957 ("r-rcpparmadillo" ,r-rcpparmadillo)
6960 ("r-rjson" ,r-rjson)
6961 ("r-cairo" ,r-cairo)
6962 ("r-rcolorbrewer" ,r-rcolorbrewer)
6963 ("r-edger" ,r-edger)
6964 ("r-quantreg" ,r-quantreg)
6966 ("r-rmtstat" ,r-rmtstat)
6967 ("r-extremes" ,r-extremes)
6968 ("r-pcamethods" ,r-pcamethods)
6969 ("r-biocparallel" ,r-biocparallel)
6970 ("r-flexmix" ,r-flexmix)))
6971 (home-page "https://hms-dbmi.github.io/scde/")
6972 (synopsis "R package for analyzing single-cell RNA-seq data")
6973 (description "The SCDE package implements a set of statistical methods for
6974 analyzing single-cell RNA-seq data. SCDE fits individual error models for
6975 single-cell RNA-seq measurements. These models can then be used for
6976 assessment of differential expression between groups of cells, as well as
6977 other types of analysis. The SCDE package also contains the pagoda framework
6978 which applies pathway and gene set overdispersion analysis to identify aspects
6979 of transcriptional heterogeneity among single cells.")
6980 ;; See https://github.com/hms-dbmi/scde/issues/38
6981 (license license:gpl2)))
6983 (define-public r-centipede
6985 (name "r-centipede")
6989 (uri (string-append "http://download.r-forge.r-project.org/"
6990 "src/contrib/CENTIPEDE_" version ".tar.gz"))
6993 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
6994 (build-system r-build-system)
6995 (home-page "http://centipede.uchicago.edu/")
6996 (synopsis "Predict transcription factor binding sites")
6998 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
6999 of the genome that are bound by particular transcription factors. It starts
7000 by identifying a set of candidate binding sites, and then aims to classify the
7001 sites according to whether each site is bound or not bound by a transcription
7002 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
7003 between two different types of motif instances using as much relevant
7004 information as possible.")
7005 (license (list license:gpl2+ license:gpl3+))))
7007 (define-public r-genefilter
7009 (name "r-genefilter")
7014 (uri (bioconductor-uri "genefilter" version))
7017 "1sbbrnq6p90fri0ik6aq2zw26kasw63nyiy7xkzrj6vgyq7x258g"))))
7018 (build-system r-build-system)
7020 `(("gfortran" ,gfortran)
7021 ("r-knitr" ,r-knitr)))
7023 `(("r-annotate" ,r-annotate)
7024 ("r-annotationdbi" ,r-annotationdbi)
7025 ("r-biobase" ,r-biobase)
7026 ("r-biocgenerics" ,r-biocgenerics)
7027 ("r-survival" ,r-survival)))
7028 (home-page "https://bioconductor.org/packages/genefilter")
7029 (synopsis "Filter genes from high-throughput experiments")
7031 "This package provides basic functions for filtering genes from
7032 high-throughput sequencing experiments.")
7033 (license license:artistic2.0)))
7035 (define-public r-deseq2
7042 (uri (bioconductor-uri "DESeq2" version))
7045 "0xh12c2skr0bbv893p05gvbismkcnqw8zwh7yz4wmycgajfzg2pp"))))
7046 (properties `((upstream-name . "DESeq2")))
7047 (build-system r-build-system)
7049 `(("r-biobase" ,r-biobase)
7050 ("r-biocgenerics" ,r-biocgenerics)
7051 ("r-biocparallel" ,r-biocparallel)
7052 ("r-genefilter" ,r-genefilter)
7053 ("r-geneplotter" ,r-geneplotter)
7054 ("r-genomicranges" ,r-genomicranges)
7055 ("r-ggplot2" ,r-ggplot2)
7056 ("r-iranges" ,r-iranges)
7057 ("r-locfit" ,r-locfit)
7059 ("r-rcpparmadillo" ,r-rcpparmadillo)
7060 ("r-s4vectors" ,r-s4vectors)
7061 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7063 `(("r-knitr" ,r-knitr)))
7064 (home-page "https://bioconductor.org/packages/DESeq2")
7065 (synopsis "Differential gene expression analysis")
7067 "This package provides functions to estimate variance-mean dependence in
7068 count data from high-throughput nucleotide sequencing assays and test for
7069 differential expression based on a model using the negative binomial
7071 (license license:lgpl3+)))
7073 (define-public r-dexseq
7080 (uri (bioconductor-uri "DEXSeq" version))
7083 "1m03awaw06mfv5gszq23k5apsqqzjqa5rcwp20y4xbpl7bywpsyl"))))
7084 (properties `((upstream-name . "DEXSeq")))
7085 (build-system r-build-system)
7087 `(("r-annotationdbi" ,r-annotationdbi)
7088 ("r-biobase" ,r-biobase)
7089 ("r-biocgenerics" ,r-biocgenerics)
7090 ("r-biocparallel" ,r-biocparallel)
7091 ("r-biomart" ,r-biomart)
7092 ("r-deseq2" ,r-deseq2)
7093 ("r-genefilter" ,r-genefilter)
7094 ("r-geneplotter" ,r-geneplotter)
7095 ("r-genomicranges" ,r-genomicranges)
7096 ("r-hwriter" ,r-hwriter)
7097 ("r-iranges" ,r-iranges)
7098 ("r-rcolorbrewer" ,r-rcolorbrewer)
7099 ("r-rsamtools" ,r-rsamtools)
7100 ("r-s4vectors" ,r-s4vectors)
7101 ("r-statmod" ,r-statmod)
7102 ("r-stringr" ,r-stringr)
7103 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7105 `(("r-knitr" ,r-knitr)))
7106 (home-page "https://bioconductor.org/packages/DEXSeq")
7107 (synopsis "Inference of differential exon usage in RNA-Seq")
7109 "This package is focused on finding differential exon usage using RNA-seq
7110 exon counts between samples with different experimental designs. It provides
7111 functions that allows the user to make the necessary statistical tests based
7112 on a model that uses the negative binomial distribution to estimate the
7113 variance between biological replicates and generalized linear models for
7114 testing. The package also provides functions for the visualization and
7115 exploration of the results.")
7116 (license license:gpl3+)))
7118 (define-public r-annotationforge
7120 (name "r-annotationforge")
7125 (uri (bioconductor-uri "AnnotationForge" version))
7128 "1a2155jxbwc6qr3dcyvp850grhdr7czc7bs3s87ff4sgdl0jp3jw"))))
7130 `((upstream-name . "AnnotationForge")))
7131 (build-system r-build-system)
7133 `(("r-annotationdbi" ,r-annotationdbi)
7134 ("r-biobase" ,r-biobase)
7135 ("r-biocgenerics" ,r-biocgenerics)
7137 ("r-rcurl" ,r-rcurl)
7138 ("r-rsqlite" ,r-rsqlite)
7139 ("r-s4vectors" ,r-s4vectors)
7142 `(("r-knitr" ,r-knitr)))
7143 (home-page "https://bioconductor.org/packages/AnnotationForge")
7144 (synopsis "Code for building annotation database packages")
7146 "This package provides code for generating Annotation packages and their
7147 databases. Packages produced are intended to be used with AnnotationDbi.")
7148 (license license:artistic2.0)))
7150 (define-public r-rbgl
7157 (uri (bioconductor-uri "RBGL" version))
7160 "079599a6xn2i7snfn2vgshkw0c00rrfhj44pvi03ap8id29bkayy"))))
7161 (properties `((upstream-name . "RBGL")))
7162 (build-system r-build-system)
7165 ("r-graph" ,r-graph)))
7166 (home-page "https://www.bioconductor.org/packages/RBGL")
7167 (synopsis "Interface to the Boost graph library")
7169 "This package provides a fairly extensive and comprehensive interface to
7170 the graph algorithms contained in the Boost library.")
7171 (license license:artistic2.0)))
7173 (define-public r-gseabase
7180 (uri (bioconductor-uri "GSEABase" version))
7183 "1k4faj53cwvqijad8cf7fcghzxcv9shlbpl8n73bsncc8k192y2j"))))
7184 (properties `((upstream-name . "GSEABase")))
7185 (build-system r-build-system)
7187 `(("r-annotate" ,r-annotate)
7188 ("r-annotationdbi" ,r-annotationdbi)
7189 ("r-biobase" ,r-biobase)
7190 ("r-biocgenerics" ,r-biocgenerics)
7191 ("r-graph" ,r-graph)
7194 `(("r-knitr" ,r-knitr)))
7195 (home-page "https://bioconductor.org/packages/GSEABase")
7196 (synopsis "Gene set enrichment data structures and methods")
7198 "This package provides classes and methods to support @dfn{Gene Set
7199 Enrichment Analysis} (GSEA).")
7200 (license license:artistic2.0)))
7202 (define-public r-category
7209 (uri (bioconductor-uri "Category" version))
7212 "1grspdzk5a4vidnxwcd1jmy1vcn494aydsp3vydx235yv7iqac1b"))))
7213 (properties `((upstream-name . "Category")))
7214 (build-system r-build-system)
7216 `(("r-annotate" ,r-annotate)
7217 ("r-annotationdbi" ,r-annotationdbi)
7218 ("r-biobase" ,r-biobase)
7219 ("r-biocgenerics" ,r-biocgenerics)
7220 ("r-genefilter" ,r-genefilter)
7221 ("r-graph" ,r-graph)
7222 ("r-gseabase" ,r-gseabase)
7223 ("r-matrix" ,r-matrix)
7226 (home-page "https://bioconductor.org/packages/Category")
7227 (synopsis "Category analysis")
7229 "This package provides a collection of tools for performing category
7231 (license license:artistic2.0)))
7233 (define-public r-gostats
7240 (uri (bioconductor-uri "GOstats" version))
7243 "00q39cyv4l28r6s9gjnd0qhl7h80vmwp4lpmchisqzj44xzyics9"))))
7244 (properties `((upstream-name . "GOstats")))
7245 (build-system r-build-system)
7247 `(("r-annotate" ,r-annotate)
7248 ("r-annotationdbi" ,r-annotationdbi)
7249 ("r-annotationforge" ,r-annotationforge)
7250 ("r-biobase" ,r-biobase)
7251 ("r-category" ,r-category)
7252 ("r-go-db" ,r-go-db)
7253 ("r-graph" ,r-graph)
7254 ("r-rgraphviz" ,r-rgraphviz)
7255 ("r-rbgl" ,r-rbgl)))
7256 (home-page "https://bioconductor.org/packages/GOstats")
7257 (synopsis "Tools for manipulating GO and microarrays")
7259 "This package provides a set of tools for interacting with GO and
7260 microarray data. A variety of basic manipulation tools for graphs, hypothesis
7261 testing and other simple calculations.")
7262 (license license:artistic2.0)))
7264 (define-public r-shortread
7266 (name "r-shortread")
7271 (uri (bioconductor-uri "ShortRead" version))
7274 "0l4kdln69y6yhln0xiv2jmpxg05fjcglln406p43a2bqvk2lr03d"))))
7275 (properties `((upstream-name . "ShortRead")))
7276 (build-system r-build-system)
7280 `(("r-biobase" ,r-biobase)
7281 ("r-biocgenerics" ,r-biocgenerics)
7282 ("r-biocparallel" ,r-biocparallel)
7283 ("r-biostrings" ,r-biostrings)
7284 ("r-genomeinfodb" ,r-genomeinfodb)
7285 ("r-genomicalignments" ,r-genomicalignments)
7286 ("r-genomicranges" ,r-genomicranges)
7287 ("r-hwriter" ,r-hwriter)
7288 ("r-iranges" ,r-iranges)
7289 ("r-lattice" ,r-lattice)
7290 ("r-latticeextra" ,r-latticeextra)
7291 ("r-rsamtools" ,r-rsamtools)
7292 ("r-s4vectors" ,r-s4vectors)
7293 ("r-xvector" ,r-xvector)
7294 ("r-zlibbioc" ,r-zlibbioc)))
7295 (home-page "https://bioconductor.org/packages/ShortRead")
7296 (synopsis "FASTQ input and manipulation tools")
7298 "This package implements sampling, iteration, and input of FASTQ files.
7299 It includes functions for filtering and trimming reads, and for generating a
7300 quality assessment report. Data are represented as
7301 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
7302 purposes. The package also contains legacy support for early single-end,
7303 ungapped alignment formats.")
7304 (license license:artistic2.0)))
7306 (define-public r-systempiper
7308 (name "r-systempiper")
7313 (uri (bioconductor-uri "systemPipeR" version))
7316 "01ilhlrvy28jfdyxjria4024yryj5zgympgqznw17g3y3az78kk2"))))
7317 (properties `((upstream-name . "systemPipeR")))
7318 (build-system r-build-system)
7320 `(("r-annotate" ,r-annotate)
7321 ("r-assertthat" ,r-assertthat)
7322 ("r-batchtools" ,r-batchtools)
7323 ("r-biostrings" ,r-biostrings)
7324 ("r-deseq2" ,r-deseq2)
7326 ("r-edger" ,r-edger)
7327 ("r-genomicfeatures" ,r-genomicfeatures)
7328 ("r-genomicranges" ,r-genomicranges)
7329 ("r-ggplot2" ,r-ggplot2)
7330 ("r-go-db" ,r-go-db)
7331 ("r-gostats" ,r-gostats)
7332 ("r-limma" ,r-limma)
7333 ("r-magrittr" ,r-magrittr)
7334 ("r-pheatmap" ,r-pheatmap)
7335 ("r-rjson" ,r-rjson)
7336 ("r-rsamtools" ,r-rsamtools)
7338 ("r-shortread" ,r-shortread)
7339 ("r-stringr" ,r-stringr)
7340 ("r-summarizedexperiment" ,r-summarizedexperiment)
7342 ("r-variantannotation" ,r-variantannotation)))
7344 `(("r-knitr" ,r-knitr)))
7345 (home-page "https://github.com/tgirke/systemPipeR")
7346 (synopsis "Next generation sequencing workflow and reporting environment")
7348 "This R package provides tools for building and running automated
7349 end-to-end analysis workflows for a wide range of @dfn{next generation
7350 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
7351 Important features include a uniform workflow interface across different NGS
7352 applications, automated report generation, and support for running both R and
7353 command-line software, such as NGS aligners or peak/variant callers, on local
7354 computers or compute clusters. Efficient handling of complex sample sets and
7355 experimental designs is facilitated by a consistently implemented sample
7356 annotation infrastructure.")
7357 (license license:artistic2.0)))
7359 (define-public r-grohmm
7366 (uri (bioconductor-uri "groHMM" version))
7369 "04z9qq1xwdsaxbqhyld37w0ybvzly9pc1hcyrnwdbyjwd7n1fncb"))))
7370 (properties `((upstream-name . "groHMM")))
7371 (build-system r-build-system)
7373 `(("r-genomeinfodb" ,r-genomeinfodb)
7374 ("r-genomicalignments" ,r-genomicalignments)
7375 ("r-genomicranges" ,r-genomicranges)
7376 ("r-iranges" ,r-iranges)
7378 ("r-rtracklayer" ,r-rtracklayer)
7379 ("r-s4vectors" ,r-s4vectors)))
7380 (home-page "https://github.com/Kraus-Lab/groHMM")
7381 (synopsis "GRO-seq analysis pipeline")
7383 "This package provides a pipeline for the analysis of GRO-seq data.")
7384 (license license:gpl3+)))
7386 (define-public vsearch
7394 (url "https://github.com/torognes/vsearch")
7395 (commit (string-append "v" version))))
7396 (file-name (git-file-name name version))
7399 "0vhrpjfdf75ba04b24xknp41790cvcgwl0vgpy7qbzj5xh2521ss"))
7400 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
7403 ;; Remove bundled cityhash sources. The vsearch source is adjusted
7404 ;; for this in the patch.
7405 (delete-file "src/city.h")
7406 (delete-file "src/citycrc.h")
7407 (delete-file "src/city.cc")
7409 (build-system gnu-build-system)
7413 ("cityhash" ,cityhash)))
7415 `(("autoconf" ,autoconf)
7416 ("automake" ,automake)))
7417 (synopsis "Sequence search tools for metagenomics")
7419 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
7420 dereplication, pairwise alignment, shuffling, subsampling, sorting and
7421 masking. The tool takes advantage of parallelism in the form of SIMD
7422 vectorization as well as multiple threads to perform accurate alignments at
7423 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
7424 Needleman-Wunsch).")
7425 (home-page "https://github.com/torognes/vsearch")
7426 ;; vsearch uses non-portable SSE intrinsics so building fails on other
7428 (supported-systems '("x86_64-linux"))
7429 ;; Dual licensed; also includes public domain source.
7430 (license (list license:gpl3 license:bsd-2))))
7432 (define-public pardre
7435 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
7440 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
7444 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
7445 (build-system gnu-build-system)
7447 `(#:tests? #f ; no tests included
7449 (modify-phases %standard-phases
7452 (lambda* (#:key outputs #:allow-other-keys)
7453 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
7454 (install-file "ParDRe" bin)
7457 `(("openmpi" ,openmpi)
7459 (synopsis "Parallel tool to remove duplicate DNA reads")
7461 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
7462 Duplicate reads can be seen as identical or nearly identical sequences with
7463 some mismatches. This tool lets users avoid the analysis of unnecessary
7464 reads, reducing the time of subsequent procedures with the
7465 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
7466 in order to exploit the parallel capabilities of multicore clusters. It is
7467 faster than multithreaded counterparts (end of 2015) for the same number of
7468 cores and, thanks to the message-passing technology, it can be executed on
7470 (home-page "https://sourceforge.net/projects/pardre/")
7471 (license license:gpl3+)))
7473 (define-public ruby-bio-kseq
7475 (name "ruby-bio-kseq")
7480 (uri (rubygems-uri "bio-kseq" version))
7483 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
7484 (build-system ruby-build-system)
7486 `(#:test-target "spec"))
7488 `(("bundler" ,bundler)
7489 ("ruby-rspec" ,ruby-rspec)
7490 ("ruby-rake-compiler" ,ruby-rake-compiler)))
7493 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
7495 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
7496 FASTQ parsing code. It provides a fast iterator over sequences and their
7498 (home-page "https://github.com/gusevfe/bio-kseq")
7499 (license license:expat)))
7501 (define-public bio-locus
7508 (uri (rubygems-uri "bio-locus" version))
7511 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
7512 (build-system ruby-build-system)
7514 `(("ruby-rspec" ,ruby-rspec)))
7515 (synopsis "Tool for fast querying of genome locations")
7517 "Bio-locus is a tabix-like tool for fast querying of genome
7518 locations. Many file formats in bioinformatics contain records that
7519 start with a chromosome name and a position for a SNP, or a start-end
7520 position for indels. Bio-locus allows users to store this chr+pos or
7521 chr+pos+alt information in a database.")
7522 (home-page "https://github.com/pjotrp/bio-locus")
7523 (license license:expat)))
7525 (define-public bio-blastxmlparser
7527 (name "bio-blastxmlparser")
7531 (uri (rubygems-uri "bio-blastxmlparser" version))
7534 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
7535 (build-system ruby-build-system)
7537 `(("ruby-bio-logger" ,ruby-bio-logger)
7538 ("ruby-nokogiri" ,ruby-nokogiri)))
7540 `(("ruby-rspec" ,ruby-rspec)))
7541 (synopsis "Fast big data BLAST XML parser and library")
7543 "Very fast parallel big-data BLAST XML file parser which can be used as
7544 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
7545 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
7546 (home-page "https://github.com/pjotrp/blastxmlparser")
7547 (license license:expat)))
7549 (define-public bioruby
7556 (uri (rubygems-uri "bio" version))
7559 "1d56amdsjv1mag7m6gv2w0xij8hqx1v5xbdjsix8sp3yp36m7938"))))
7560 (build-system ruby-build-system)
7562 `(("ruby-libxml" ,ruby-libxml)))
7564 `(("which" ,which))) ; required for test phase
7567 (modify-phases %standard-phases
7568 (add-before 'build 'patch-test-command
7570 (substitute* '("test/functional/bio/test_command.rb")
7571 (("/bin/sh") (which "sh")))
7572 (substitute* '("test/functional/bio/test_command.rb")
7573 (("/bin/ls") (which "ls")))
7574 (substitute* '("test/functional/bio/test_command.rb")
7575 (("which") (which "which")))
7576 (substitute* '("test/functional/bio/test_command.rb",
7577 "test/data/command/echoarg2.sh")
7578 (("/bin/echo") (which "echo")))
7580 (synopsis "Ruby library, shell and utilities for bioinformatics")
7581 (description "BioRuby comes with a comprehensive set of Ruby development
7582 tools and libraries for bioinformatics and molecular biology. BioRuby has
7583 components for sequence analysis, pathway analysis, protein modelling and
7584 phylogenetic analysis; it supports many widely used data formats and provides
7585 easy access to databases, external programs and public web services, including
7586 BLAST, KEGG, GenBank, MEDLINE and GO.")
7587 (home-page "http://bioruby.org/")
7588 ;; Code is released under Ruby license, except for setup
7589 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
7590 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
7592 (define-public r-biocviews
7594 (name "r-biocviews")
7598 (uri (bioconductor-uri "biocViews" version))
7601 "0kw0qfm1fw5yv2rbz6x23431rh0fnzj66f2bls7j285biyjmmx7w"))))
7603 `((upstream-name . "biocViews")))
7604 (build-system r-build-system)
7606 `(("r-biobase" ,r-biobase)
7607 ("r-biocmanager" ,r-biocmanager)
7608 ("r-graph" ,r-graph)
7610 ("r-rcurl" ,r-rcurl)
7612 ("r-runit" ,r-runit)))
7613 (home-page "https://bioconductor.org/packages/biocViews")
7614 (synopsis "Bioconductor package categorization helper")
7615 (description "The purpose of biocViews is to create HTML pages that
7616 categorize packages in a Bioconductor package repository according to keywords,
7617 also known as views, in a controlled vocabulary.")
7618 (license license:artistic2.0)))
7620 (define-public r-biocstyle
7622 (name "r-biocstyle")
7626 (uri (bioconductor-uri "BiocStyle" version))
7629 "09sz2bnbfbj8wz16k0q8xrvag9fldxqyp5vbg9pvd9skh28hv7c7"))))
7631 `((upstream-name . "BiocStyle")))
7632 (build-system r-build-system)
7634 `(("r-biocmanager" ,r-biocmanager)
7635 ("r-bookdown" ,r-bookdown)
7636 ("r-knitr" ,r-knitr)
7637 ("r-rmarkdown" ,r-rmarkdown)
7638 ("r-yaml" ,r-yaml)))
7640 `(("r-knitr" ,r-knitr)))
7641 (home-page "https://bioconductor.org/packages/BiocStyle")
7642 (synopsis "Bioconductor formatting styles")
7643 (description "This package provides standard formatting styles for
7644 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
7646 (license license:artistic2.0)))
7648 (define-public r-bioccheck
7650 (name "r-bioccheck")
7654 (uri (bioconductor-uri "BiocCheck" version))
7657 "1p9ys18sn1crxw1iac2jdgqvwpb5hjd9nfxx0qn0ncrv0b550mny"))))
7659 `((upstream-name . "BiocCheck")))
7660 (build-system r-build-system)
7663 (modify-phases %standard-phases
7664 ;; This package can be used by calling BiocCheck(<package>) from
7665 ;; within R, or by running R CMD BiocCheck <package>. This phase
7666 ;; makes sure the latter works. For this to work, the BiocCheck
7667 ;; script must be somewhere on the PATH (not the R bin directory).
7668 (add-after 'install 'install-bioccheck-subcommand
7669 (lambda* (#:key outputs #:allow-other-keys)
7670 (let* ((out (assoc-ref outputs "out"))
7671 (dest-dir (string-append out "/bin"))
7673 (string-append out "/site-library/BiocCheck/script/")))
7675 (symlink (string-append script-dir "/checkBadDeps.R")
7676 (string-append dest-dir "/checkBadDeps.R"))
7677 (symlink (string-append script-dir "/BiocCheck")
7678 (string-append dest-dir "/BiocCheck")))
7681 `(("r-codetools" ,r-codetools)
7682 ("r-graph" ,r-graph)
7684 ("r-knitr" ,r-knitr)
7685 ("r-optparse" ,r-optparse)
7686 ("r-biocmanager" ,r-biocmanager)
7687 ("r-biocviews" ,r-biocviews)
7688 ("r-stringdist" ,r-stringdist)))
7690 `(("r-knitr" ,r-knitr)))
7691 (home-page "https://bioconductor.org/packages/BiocCheck")
7692 (synopsis "Executes Bioconductor-specific package checks")
7693 (description "This package contains tools to perform additional quality
7694 checks on R packages that are to be submitted to the Bioconductor repository.")
7695 (license license:artistic2.0)))
7697 (define-public r-s4vectors
7699 (name "r-s4vectors")
7703 (uri (bioconductor-uri "S4Vectors" version))
7706 "1ddr3ngyczx332zw9ai1a6h7442lgrbfcj8vrhvbkdkzqwj14xmb"))))
7708 `((upstream-name . "S4Vectors")))
7709 (build-system r-build-system)
7711 `(("r-biocgenerics" ,r-biocgenerics)))
7712 (home-page "https://bioconductor.org/packages/S4Vectors")
7713 (synopsis "S4 implementation of vectors and lists")
7715 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7716 classes and a set of generic functions that extend the semantic of ordinary
7717 vectors and lists in R. Package developers can easily implement vector-like
7718 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7719 In addition, a few low-level concrete subclasses of general interest (e.g.
7720 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7721 S4Vectors package itself.")
7722 (license license:artistic2.0)))
7724 (define-public r-iranges
7730 (uri (bioconductor-uri "IRanges" version))
7733 "1y24jw62806wp2afiyj1x6n00gj7d3323klqdypra9q43pg1w49d"))))
7735 `((upstream-name . "IRanges")))
7736 (build-system r-build-system)
7738 `(("r-biocgenerics" ,r-biocgenerics)
7739 ("r-s4vectors" ,r-s4vectors)))
7740 (home-page "https://bioconductor.org/packages/IRanges")
7741 (synopsis "Infrastructure for manipulating intervals on sequences")
7743 "This package provides efficient low-level and highly reusable S4 classes
7744 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7745 generally, data that can be organized sequentially (formally defined as
7746 @code{Vector} objects), as well as views on these @code{Vector} objects.
7747 Efficient list-like classes are also provided for storing big collections of
7748 instances of the basic classes. All classes in the package use consistent
7749 naming and share the same rich and consistent \"Vector API\" as much as
7751 (license license:artistic2.0)))
7753 (define-public r-genomeinfodbdata
7755 (name "r-genomeinfodbdata")
7759 ;; We cannot use bioconductor-uri here because this tarball is
7760 ;; located under "data/annotation/" instead of "bioc/".
7761 (uri (string-append "https://bioconductor.org/packages/release/"
7762 "data/annotation/src/contrib/GenomeInfoDbData_"
7766 "0di6nlqpsyqf693k2na65ayqldih563x3zfrczpqc5q2hl5kg35c"))))
7768 `((upstream-name . "GenomeInfoDbData")))
7769 (build-system r-build-system)
7770 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7771 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7772 (description "This package contains data for mapping between NCBI taxonomy
7773 ID and species. It is used by functions in the GenomeInfoDb package.")
7774 (license license:artistic2.0)))
7776 (define-public r-genomeinfodb
7778 (name "r-genomeinfodb")
7782 (uri (bioconductor-uri "GenomeInfoDb" version))
7785 "1cqs53p4m5q1dr59war72bccphy01ilw4xra24fmngrv4x32rznd"))))
7787 `((upstream-name . "GenomeInfoDb")))
7788 (build-system r-build-system)
7790 `(("r-biocgenerics" ,r-biocgenerics)
7791 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7792 ("r-iranges" ,r-iranges)
7793 ("r-rcurl" ,r-rcurl)
7794 ("r-s4vectors" ,r-s4vectors)))
7796 `(("r-knitr" ,r-knitr)))
7797 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7798 (synopsis "Utilities for manipulating chromosome identifiers")
7800 "This package contains data and functions that define and allow
7801 translation between different chromosome sequence naming conventions (e.g.,
7802 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7803 names in their natural, rather than lexicographic, order.")
7804 (license license:artistic2.0)))
7806 (define-public r-edger
7812 (uri (bioconductor-uri "edgeR" version))
7815 "1z9bkg08rgqn3jm2s4ndbj641w33wl8jd3j6m5if6h2nnw6011ic"))))
7816 (properties `((upstream-name . "edgeR")))
7817 (build-system r-build-system)
7819 `(("r-limma" ,r-limma)
7820 ("r-locfit" ,r-locfit)
7822 ("r-statmod" ,r-statmod))) ;for estimateDisp
7823 (home-page "http://bioinf.wehi.edu.au/edgeR")
7824 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7825 (description "This package can do differential expression analysis of
7826 RNA-seq expression profiles with biological replication. It implements a range
7827 of statistical methodology based on the negative binomial distributions,
7828 including empirical Bayes estimation, exact tests, generalized linear models
7829 and quasi-likelihood tests. It be applied to differential signal analysis of
7830 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7832 (license license:gpl2+)))
7834 (define-public r-variantannotation
7836 (name "r-variantannotation")
7840 (uri (bioconductor-uri "VariantAnnotation" version))
7843 "09y6ymwky839nb0y7y93w810hk9mvwqn7595q1276c28dkddiqvw"))))
7845 `((upstream-name . "VariantAnnotation")))
7849 `(("r-annotationdbi" ,r-annotationdbi)
7850 ("r-biobase" ,r-biobase)
7851 ("r-biocgenerics" ,r-biocgenerics)
7852 ("r-biostrings" ,r-biostrings)
7853 ("r-bsgenome" ,r-bsgenome)
7855 ("r-genomeinfodb" ,r-genomeinfodb)
7856 ("r-genomicfeatures" ,r-genomicfeatures)
7857 ("r-genomicranges" ,r-genomicranges)
7858 ("r-iranges" ,r-iranges)
7859 ("r-summarizedexperiment" ,r-summarizedexperiment)
7860 ("r-rhtslib" ,r-rhtslib)
7861 ("r-rsamtools" ,r-rsamtools)
7862 ("r-rtracklayer" ,r-rtracklayer)
7863 ("r-s4vectors" ,r-s4vectors)
7864 ("r-xvector" ,r-xvector)
7865 ("r-zlibbioc" ,r-zlibbioc)))
7866 (build-system r-build-system)
7867 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7868 (synopsis "Package for annotation of genetic variants")
7869 (description "This R package can annotate variants, compute amino acid
7870 coding changes and predict coding outcomes.")
7871 (license license:artistic2.0)))
7873 (define-public r-limma
7879 (uri (bioconductor-uri "limma" version))
7882 "09fnqxx4rzq5n447aqg2l6y0idfwgz2jxz99sifxsr2q8afzbcj6"))))
7883 (build-system r-build-system)
7884 (home-page "http://bioinf.wehi.edu.au/limma")
7885 (synopsis "Package for linear models for microarray and RNA-seq data")
7886 (description "This package can be used for the analysis of gene expression
7887 studies, especially the use of linear models for analysing designed experiments
7888 and the assessment of differential expression. The analysis methods apply to
7889 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7890 (license license:gpl2+)))
7892 (define-public r-xvector
7898 (uri (bioconductor-uri "XVector" version))
7901 "11h1hszv4798q1gbx8r6zf8vlaqx4v9ql0lbh2xaxybp66a03pvc"))))
7903 `((upstream-name . "XVector")))
7904 (build-system r-build-system)
7907 (modify-phases %standard-phases
7908 (add-after 'unpack 'use-system-zlib
7910 (substitute* "DESCRIPTION"
7911 (("zlibbioc, ") ""))
7912 (substitute* "NAMESPACE"
7913 (("import\\(zlibbioc\\)") ""))
7918 `(("r-biocgenerics" ,r-biocgenerics)
7919 ("r-iranges" ,r-iranges)
7920 ("r-s4vectors" ,r-s4vectors)))
7921 (home-page "https://bioconductor.org/packages/XVector")
7922 (synopsis "Representation and manpulation of external sequences")
7924 "This package provides memory efficient S4 classes for storing sequences
7925 \"externally\" (behind an R external pointer, or on disk).")
7926 (license license:artistic2.0)))
7928 (define-public r-genomicranges
7930 (name "r-genomicranges")
7934 (uri (bioconductor-uri "GenomicRanges" version))
7937 "0wn1zr2qq0rpv9z2wialgizn6xzdlcjg1w2kif67n53svz6vk2x1"))))
7939 `((upstream-name . "GenomicRanges")))
7940 (build-system r-build-system)
7942 `(("r-biocgenerics" ,r-biocgenerics)
7943 ("r-genomeinfodb" ,r-genomeinfodb)
7944 ("r-iranges" ,r-iranges)
7945 ("r-s4vectors" ,r-s4vectors)
7946 ("r-xvector" ,r-xvector)))
7948 `(("r-knitr" ,r-knitr)))
7949 (home-page "https://bioconductor.org/packages/GenomicRanges")
7950 (synopsis "Representation and manipulation of genomic intervals")
7952 "This package provides tools to efficiently represent and manipulate
7953 genomic annotations and alignments is playing a central role when it comes to
7954 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7955 GenomicRanges package defines general purpose containers for storing and
7956 manipulating genomic intervals and variables defined along a genome.")
7957 (license license:artistic2.0)))
7959 (define-public r-biobase
7965 (uri (bioconductor-uri "Biobase" version))
7968 "13p3kgnxm7hbn8cy289kbhaiyfa6rxx7l1pbvajwqzbay3cxznqp"))))
7970 `((upstream-name . "Biobase")))
7971 (build-system r-build-system)
7973 `(("r-biocgenerics" ,r-biocgenerics)))
7974 (home-page "https://bioconductor.org/packages/Biobase")
7975 (synopsis "Base functions for Bioconductor")
7977 "This package provides functions that are needed by many other packages
7978 on Bioconductor or which replace R functions.")
7979 (license license:artistic2.0)))
7981 (define-public r-annotationdbi
7983 (name "r-annotationdbi")
7987 (uri (bioconductor-uri "AnnotationDbi" version))
7990 "0qcxfn4pvaksna0nvxr74ysn2wzaxn732pkhd6ffrj8pwhkhy5p3"))))
7992 `((upstream-name . "AnnotationDbi")))
7993 (build-system r-build-system)
7995 `(("r-biobase" ,r-biobase)
7996 ("r-biocgenerics" ,r-biocgenerics)
7998 ("r-iranges" ,r-iranges)
7999 ("r-rsqlite" ,r-rsqlite)
8000 ("r-s4vectors" ,r-s4vectors)))
8002 `(("r-knitr" ,r-knitr)))
8003 (home-page "https://bioconductor.org/packages/AnnotationDbi")
8004 (synopsis "Annotation database interface")
8006 "This package provides user interface and database connection code for
8007 annotation data packages using SQLite data storage.")
8008 (license license:artistic2.0)))
8010 (define-public r-biomart
8016 (uri (bioconductor-uri "biomaRt" version))
8019 "0np4nh3gj60mgb6312z7x0z9fg5bhrhw872sp3dzgmqc8q8b84iz"))))
8021 `((upstream-name . "biomaRt")))
8022 (build-system r-build-system)
8024 `(("r-annotationdbi" ,r-annotationdbi)
8025 ("r-biocfilecache" ,r-biocfilecache)
8027 ("r-openssl" ,r-openssl)
8028 ("r-progress" ,r-progress)
8029 ("r-rappdirs" ,r-rappdirs)
8030 ("r-stringr" ,r-stringr)
8033 `(("r-knitr" ,r-knitr)))
8034 (home-page "https://bioconductor.org/packages/biomaRt")
8035 (synopsis "Interface to BioMart databases")
8037 "biomaRt provides an interface to a growing collection of databases
8038 implementing the @url{BioMart software suite, http://www.biomart.org}. The
8039 package enables retrieval of large amounts of data in a uniform way without
8040 the need to know the underlying database schemas or write complex SQL queries.
8041 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
8042 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
8043 users direct access to a diverse set of data and enable a wide range of
8044 powerful online queries from gene annotation to database mining.")
8045 (license license:artistic2.0)))
8047 (define-public r-biocparallel
8049 (name "r-biocparallel")
8053 (uri (bioconductor-uri "BiocParallel" version))
8056 "1lsg5xm5j3ly5k60fidzhkgqc9jgscyfkqngjvd9qp6yfzvsb82g"))))
8058 `((upstream-name . "BiocParallel")))
8059 (build-system r-build-system)
8061 `(("r-futile-logger" ,r-futile-logger)
8065 `(("r-knitr" ,r-knitr)))
8066 (home-page "https://bioconductor.org/packages/BiocParallel")
8067 (synopsis "Bioconductor facilities for parallel evaluation")
8069 "This package provides modified versions and novel implementation of
8070 functions for parallel evaluation, tailored to use with Bioconductor
8072 (license (list license:gpl2+ license:gpl3+))))
8074 (define-public r-biostrings
8076 (name "r-biostrings")
8080 (uri (bioconductor-uri "Biostrings" version))
8083 "0imhfz7dg8b3l5qzipjranqqshdsg2x6zc49drlhn8sc7j40cvi8"))))
8085 `((upstream-name . "Biostrings")))
8086 (build-system r-build-system)
8088 `(("r-biocgenerics" ,r-biocgenerics)
8089 ("r-crayon" ,r-crayon)
8090 ("r-iranges" ,r-iranges)
8091 ("r-s4vectors" ,r-s4vectors)
8092 ("r-xvector" ,r-xvector)))
8093 (home-page "https://bioconductor.org/packages/Biostrings")
8094 (synopsis "String objects and algorithms for biological sequences")
8096 "This package provides memory efficient string containers, string
8097 matching algorithms, and other utilities, for fast manipulation of large
8098 biological sequences or sets of sequences.")
8099 (license license:artistic2.0)))
8101 (define-public r-rsamtools
8103 (name "r-rsamtools")
8107 (uri (bioconductor-uri "Rsamtools" version))
8110 "0z01z0s71f941k7sns46nyabps28c69d6jxx6sppjpc6h4vrw0vq"))))
8112 `((upstream-name . "Rsamtools")))
8113 (build-system r-build-system)
8116 (modify-phases %standard-phases
8117 (add-after 'unpack 'use-system-zlib
8119 (substitute* "DESCRIPTION"
8120 (("zlibbioc, ") ""))
8121 (substitute* "NAMESPACE"
8122 (("import\\(zlibbioc\\)") ""))
8127 `(("r-biocgenerics" ,r-biocgenerics)
8128 ("r-biocparallel" ,r-biocparallel)
8129 ("r-biostrings" ,r-biostrings)
8130 ("r-bitops" ,r-bitops)
8131 ("r-genomeinfodb" ,r-genomeinfodb)
8132 ("r-genomicranges" ,r-genomicranges)
8133 ("r-iranges" ,r-iranges)
8134 ("r-rhtslib" ,r-rhtslib)
8135 ("r-s4vectors" ,r-s4vectors)
8136 ("r-xvector" ,r-xvector)))
8137 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
8138 (synopsis "Interface to samtools, bcftools, and tabix")
8140 "This package provides an interface to the @code{samtools},
8141 @code{bcftools}, and @code{tabix} utilities for manipulating SAM (Sequence
8142 Alignment / Map), FASTA, binary variant call (BCF) and compressed indexed
8143 tab-delimited (tabix) files.")
8144 (license license:expat)))
8146 (define-public r-delayedarray
8148 (name "r-delayedarray")
8152 (uri (bioconductor-uri "DelayedArray" version))
8155 "0xi0i621hrl7k9rsc8x8nc3ib74sk8hxhbyr2lxqclw45pk95s7v"))))
8157 `((upstream-name . "DelayedArray")))
8158 (build-system r-build-system)
8160 `(("r-biocgenerics" ,r-biocgenerics)
8161 ("r-s4vectors" ,r-s4vectors)
8162 ("r-iranges" ,r-iranges)
8163 ("r-matrix" ,r-matrix)
8164 ("r-matrixstats" ,r-matrixstats)))
8166 `(("r-knitr" ,r-knitr)))
8167 (home-page "https://bioconductor.org/packages/DelayedArray")
8168 (synopsis "Delayed operations on array-like objects")
8170 "Wrapping an array-like object (typically an on-disk object) in a
8171 @code{DelayedArray} object allows one to perform common array operations on it
8172 without loading the object in memory. In order to reduce memory usage and
8173 optimize performance, operations on the object are either delayed or executed
8174 using a block processing mechanism. Note that this also works on in-memory
8175 array-like objects like @code{DataFrame} objects (typically with Rle columns),
8176 @code{Matrix} objects, and ordinary arrays and data frames.")
8177 (license license:artistic2.0)))
8179 (define-public r-summarizedexperiment
8181 (name "r-summarizedexperiment")
8185 (uri (bioconductor-uri "SummarizedExperiment" version))
8188 "1raw5ycigr6gjgzn3kx3jls5hzww10fhnwd8c17c20hmhirf13rw"))))
8190 `((upstream-name . "SummarizedExperiment")))
8191 (build-system r-build-system)
8193 `(("r-biobase" ,r-biobase)
8194 ("r-biocgenerics" ,r-biocgenerics)
8195 ("r-delayedarray" ,r-delayedarray)
8196 ("r-genomeinfodb" ,r-genomeinfodb)
8197 ("r-genomicranges" ,r-genomicranges)
8198 ("r-iranges" ,r-iranges)
8199 ("r-matrix" ,r-matrix)
8200 ("r-s4vectors" ,r-s4vectors)))
8202 `(("r-knitr" ,r-knitr)))
8203 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
8204 (synopsis "Container for representing genomic ranges by sample")
8206 "The SummarizedExperiment container contains one or more assays, each
8207 represented by a matrix-like object of numeric or other mode. The rows
8208 typically represent genomic ranges of interest and the columns represent
8210 (license license:artistic2.0)))
8212 (define-public r-genomicalignments
8214 (name "r-genomicalignments")
8218 (uri (bioconductor-uri "GenomicAlignments" version))
8221 "0v8k6d7frm5p48cmk4zik78cw9abz4inx0zhl4zrmmx31ifyvk8d"))))
8223 `((upstream-name . "GenomicAlignments")))
8224 (build-system r-build-system)
8226 `(("r-biocgenerics" ,r-biocgenerics)
8227 ("r-biocparallel" ,r-biocparallel)
8228 ("r-biostrings" ,r-biostrings)
8229 ("r-genomeinfodb" ,r-genomeinfodb)
8230 ("r-genomicranges" ,r-genomicranges)
8231 ("r-iranges" ,r-iranges)
8232 ("r-rsamtools" ,r-rsamtools)
8233 ("r-s4vectors" ,r-s4vectors)
8234 ("r-summarizedexperiment" ,r-summarizedexperiment)))
8235 (home-page "https://bioconductor.org/packages/GenomicAlignments")
8236 (synopsis "Representation and manipulation of short genomic alignments")
8238 "This package provides efficient containers for storing and manipulating
8239 short genomic alignments (typically obtained by aligning short reads to a
8240 reference genome). This includes read counting, computing the coverage,
8241 junction detection, and working with the nucleotide content of the
8243 (license license:artistic2.0)))
8245 (define-public r-rtracklayer
8247 (name "r-rtracklayer")
8251 (uri (bioconductor-uri "rtracklayer" version))
8254 "1zcgk92sidhy4y7ws9ms4nkkh2hnccfhfh53qgna0kma9jy4v5xf"))))
8255 (build-system r-build-system)
8258 (modify-phases %standard-phases
8259 (add-after 'unpack 'use-system-zlib
8261 (substitute* "DESCRIPTION"
8262 ((" zlibbioc,") ""))
8263 (substitute* "NAMESPACE"
8264 (("import\\(zlibbioc\\)") ""))
8267 `(("pkg-config" ,pkg-config)))
8271 `(("r-biocgenerics" ,r-biocgenerics)
8272 ("r-biostrings" ,r-biostrings)
8273 ("r-genomeinfodb" ,r-genomeinfodb)
8274 ("r-genomicalignments" ,r-genomicalignments)
8275 ("r-genomicranges" ,r-genomicranges)
8276 ("r-iranges" ,r-iranges)
8277 ("r-rcurl" ,r-rcurl)
8278 ("r-rsamtools" ,r-rsamtools)
8279 ("r-s4vectors" ,r-s4vectors)
8281 ("r-xvector" ,r-xvector)))
8282 (home-page "https://bioconductor.org/packages/rtracklayer")
8283 (synopsis "R interface to genome browsers and their annotation tracks")
8285 "rtracklayer is an extensible framework for interacting with multiple
8286 genome browsers (currently UCSC built-in) and manipulating annotation tracks
8287 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
8288 built-in). The user may export/import tracks to/from the supported browsers,
8289 as well as query and modify the browser state, such as the current viewport.")
8290 (license license:artistic2.0)))
8292 (define-public r-genomicfeatures
8294 (name "r-genomicfeatures")
8298 (uri (bioconductor-uri "GenomicFeatures" version))
8301 "0zm7q957g952qyfqmvf27sldsnq6sqd0wlgnqzvmxayg9pxh0l0z"))))
8303 `((upstream-name . "GenomicFeatures")))
8304 (build-system r-build-system)
8306 `(("r-annotationdbi" ,r-annotationdbi)
8307 ("r-biobase" ,r-biobase)
8308 ("r-biocgenerics" ,r-biocgenerics)
8309 ("r-biomart" ,r-biomart)
8310 ("r-biostrings" ,r-biostrings)
8312 ("r-genomeinfodb" ,r-genomeinfodb)
8313 ("r-genomicranges" ,r-genomicranges)
8314 ("r-iranges" ,r-iranges)
8315 ("r-rcurl" ,r-rcurl)
8316 ("r-rsqlite" ,r-rsqlite)
8317 ("r-rtracklayer" ,r-rtracklayer)
8318 ("r-s4vectors" ,r-s4vectors)
8319 ("r-xvector" ,r-xvector)))
8321 `(("r-knitr" ,r-knitr)))
8322 (home-page "https://bioconductor.org/packages/GenomicFeatures")
8323 (synopsis "Tools for working with transcript centric annotations")
8325 "This package provides a set of tools and methods for making and
8326 manipulating transcript centric annotations. With these tools the user can
8327 easily download the genomic locations of the transcripts, exons and cds of a
8328 given organism, from either the UCSC Genome Browser or a BioMart
8329 database (more sources will be supported in the future). This information is
8330 then stored in a local database that keeps track of the relationship between
8331 transcripts, exons, cds and genes. Flexible methods are provided for
8332 extracting the desired features in a convenient format.")
8333 (license license:artistic2.0)))
8335 (define-public r-go-db
8341 (uri (string-append "https://www.bioconductor.org/packages/"
8342 "release/data/annotation/src/contrib/GO.db_"
8346 "0i3wcf5h3n0dawzc1hy0kv74f06j80c47n4p3g3fmrcxlhi3jpa5"))))
8348 `((upstream-name . "GO.db")))
8349 (build-system r-build-system)
8351 `(("r-annotationdbi" ,r-annotationdbi)))
8352 (home-page "https://bioconductor.org/packages/GO.db")
8353 (synopsis "Annotation maps describing the entire Gene Ontology")
8355 "The purpose of this GO.db annotation package is to provide detailed
8356 information about the latest version of the Gene Ontologies.")
8357 (license license:artistic2.0)))
8359 (define-public r-topgo
8365 (uri (bioconductor-uri "topGO" version))
8368 "13rhbvn27sj75fklf1cnjaazacx8yyjlhqlnbp5zk157q6y5cwdr"))))
8370 `((upstream-name . "topGO")))
8371 (build-system r-build-system)
8373 `(("r-annotationdbi" ,r-annotationdbi)
8375 ("r-biobase" ,r-biobase)
8376 ("r-biocgenerics" ,r-biocgenerics)
8377 ("r-go-db" ,r-go-db)
8378 ("r-graph" ,r-graph)
8379 ("r-lattice" ,r-lattice)
8380 ("r-matrixstats" ,r-matrixstats)
8381 ("r-sparsem" ,r-sparsem)))
8382 (home-page "https://bioconductor.org/packages/topGO")
8383 (synopsis "Enrichment analysis for gene ontology")
8385 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
8386 terms while accounting for the topology of the GO graph. Different test
8387 statistics and different methods for eliminating local similarities and
8388 dependencies between GO terms can be implemented and applied.")
8389 ;; Any version of the LGPL applies.
8390 (license license:lgpl2.1+)))
8392 (define-public r-bsgenome
8398 (uri (bioconductor-uri "BSgenome" version))
8401 "1jw8r1qm9fpg2s1cw2y4np243jjxm65j2xdy2785h8fc1b02msf6"))))
8403 `((upstream-name . "BSgenome")))
8404 (build-system r-build-system)
8406 `(("r-biocgenerics" ,r-biocgenerics)
8407 ("r-biostrings" ,r-biostrings)
8408 ("r-genomeinfodb" ,r-genomeinfodb)
8409 ("r-genomicranges" ,r-genomicranges)
8410 ("r-iranges" ,r-iranges)
8411 ("r-matrixstats" ,r-matrixstats)
8412 ("r-rsamtools" ,r-rsamtools)
8413 ("r-rtracklayer" ,r-rtracklayer)
8414 ("r-s4vectors" ,r-s4vectors)
8415 ("r-xvector" ,r-xvector)))
8416 (home-page "https://bioconductor.org/packages/BSgenome")
8417 (synopsis "Infrastructure for Biostrings-based genome data packages")
8419 "This package provides infrastructure shared by all Biostrings-based
8420 genome data packages and support for efficient SNP representation.")
8421 (license license:artistic2.0)))
8423 (define-public r-impute
8429 (uri (bioconductor-uri "impute" version))
8432 "161p6l1cp3wwdynkxwvg0yhrh6yv20brdlplw5w5mavn4hf1nm0h"))))
8434 `(("gfortran" ,gfortran)))
8435 (build-system r-build-system)
8436 (home-page "https://bioconductor.org/packages/impute")
8437 (synopsis "Imputation for microarray data")
8439 "This package provides a function to impute missing gene expression
8440 microarray data, using nearest neighbor averaging.")
8441 (license license:gpl2+)))
8443 (define-public r-seqpattern
8445 (name "r-seqpattern")
8449 (uri (bioconductor-uri "seqPattern" version))
8452 "0f1yvx2ri1557rzjx08q5bgml1cvkm8hjl8xn1qi4rjs64sy6mci"))))
8454 `((upstream-name . "seqPattern")))
8455 (build-system r-build-system)
8457 `(("r-biostrings" ,r-biostrings)
8458 ("r-genomicranges" ,r-genomicranges)
8459 ("r-iranges" ,r-iranges)
8460 ("r-kernsmooth" ,r-kernsmooth)
8461 ("r-plotrix" ,r-plotrix)))
8462 (home-page "https://bioconductor.org/packages/seqPattern")
8463 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
8465 "This package provides tools to visualize oligonucleotide patterns and
8466 sequence motif occurrences across a large set of sequences centred at a common
8467 reference point and sorted by a user defined feature.")
8468 (license license:gpl3+)))
8470 (define-public r-genomation
8472 (name "r-genomation")
8476 (uri (bioconductor-uri "genomation" version))
8479 "1cy8kqwddiha5jy6nda1al956i4wncbgjkrxwijdb08cmka2sfwh"))))
8480 (build-system r-build-system)
8482 `(("r-biostrings" ,r-biostrings)
8483 ("r-bsgenome" ,r-bsgenome)
8484 ("r-data-table" ,r-data-table)
8485 ("r-genomeinfodb" ,r-genomeinfodb)
8486 ("r-genomicalignments" ,r-genomicalignments)
8487 ("r-genomicranges" ,r-genomicranges)
8488 ("r-ggplot2" ,r-ggplot2)
8489 ("r-gridbase" ,r-gridbase)
8490 ("r-impute" ,r-impute)
8491 ("r-iranges" ,r-iranges)
8492 ("r-matrixstats" ,r-matrixstats)
8493 ("r-plotrix" ,r-plotrix)
8496 ("r-readr" ,r-readr)
8497 ("r-reshape2" ,r-reshape2)
8498 ("r-rsamtools" ,r-rsamtools)
8499 ("r-rtracklayer" ,r-rtracklayer)
8500 ("r-runit" ,r-runit)
8501 ("r-s4vectors" ,r-s4vectors)
8502 ("r-seqpattern" ,r-seqpattern)))
8504 `(("r-knitr" ,r-knitr)))
8505 (home-page "https://bioinformatics.mdc-berlin.de/genomation/")
8506 (synopsis "Summary, annotation and visualization of genomic data")
8508 "This package provides a package for summary and annotation of genomic
8509 intervals. Users can visualize and quantify genomic intervals over
8510 pre-defined functional regions, such as promoters, exons, introns, etc. The
8511 genomic intervals represent regions with a defined chromosome position, which
8512 may be associated with a score, such as aligned reads from HT-seq experiments,
8513 TF binding sites, methylation scores, etc. The package can use any tabular
8514 genomic feature data as long as it has minimal information on the locations of
8515 genomic intervals. In addition, it can use BAM or BigWig files as input.")
8516 (license license:artistic2.0)))
8518 (define-public r-genomationdata
8520 (name "r-genomationdata")
8524 ;; We cannot use bioconductor-uri here because this tarball is
8525 ;; located under "data/annotation/" instead of "bioc/".
8526 (uri (string-append "https://bioconductor.org/packages/"
8527 "release/data/experiment/src/contrib/"
8528 "genomationData_" version ".tar.gz"))
8531 "10xyb8akjrhmak2i0mnv1agny2ipy364q9nlibyplpzc7vdb6bw7"))))
8532 (build-system r-build-system)
8533 ;; As this package provides little more than large data files, it doesn't
8534 ;; make sense to build substitutes.
8535 (arguments `(#:substitutable? #f))
8537 `(("r-knitr" ,r-knitr)))
8538 (home-page "https://bioinformatics.mdc-berlin.de/genomation/")
8539 (synopsis "Experimental data for use with the genomation package")
8541 "This package contains experimental genetic data for use with the
8542 genomation package. Included are Chip Seq, Methylation and Cage data,
8543 downloaded from Encode.")
8544 (license license:gpl3+)))
8546 (define-public r-seqlogo
8553 (uri (bioconductor-uri "seqLogo" version))
8556 "09kkxir305fv8z2yyihvspkrzclxbw1cx5mvhfkrhl10rap6662j"))))
8557 (properties `((upstream-name . "seqLogo")))
8558 (build-system r-build-system)
8559 (home-page "https://bioconductor.org/packages/seqLogo")
8560 (synopsis "Sequence logos for DNA sequence alignments")
8562 "seqLogo takes the position weight matrix of a DNA sequence motif and
8563 plots the corresponding sequence logo as introduced by Schneider and
8565 (license license:lgpl2.0+)))
8567 (define-public r-motifrg
8574 (uri (bioconductor-uri "motifRG" version))
8577 "1ml6zyzlk8yjbnfhga2qnw8nl43rankvka0kc1yljxr2b66aqbhn"))))
8578 (properties `((upstream-name . "motifRG")))
8579 (build-system r-build-system)
8581 `(("r-biostrings" ,r-biostrings)
8582 ("r-bsgenome" ,r-bsgenome)
8583 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8584 ("r-iranges" ,r-iranges)
8585 ("r-seqlogo" ,r-seqlogo)
8586 ("r-xvector" ,r-xvector)))
8587 (home-page "https://bioconductor.org/packages/motifRG")
8588 (synopsis "Discover motifs in high throughput sequencing data")
8590 "This package provides tools for discriminative motif discovery in high
8591 throughput genetic sequencing data sets using regression methods.")
8592 (license license:artistic2.0)))
8594 (define-public r-zlibbioc
8600 (uri (bioconductor-uri "zlibbioc" version))
8603 "0j1l052jb2cwc1nifxzwknc9csagf4f2d092zs0i95dz0rma89l0"))))
8605 `((upstream-name . "zlibbioc")))
8606 (build-system r-build-system)
8607 (home-page "https://bioconductor.org/packages/zlibbioc")
8608 (synopsis "Provider for zlib-1.2.5 to R packages")
8609 (description "This package uses the source code of zlib-1.2.5 to create
8610 libraries for systems that do not have these available via other means.")
8611 (license license:artistic2.0)))
8613 (define-public r-r4rna
8620 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8624 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8625 (build-system r-build-system)
8627 `(("r-optparse" ,r-optparse)
8628 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8629 (home-page "https://www.e-rna.org/r-chie/index.cgi")
8630 (synopsis "Analysis framework for RNA secondary structure")
8632 "The R4RNA package aims to be a general framework for the analysis of RNA
8633 secondary structure and comparative analysis in R.")
8634 (license license:gpl3+)))
8636 (define-public r-rhtslib
8643 (uri (bioconductor-uri "Rhtslib" version))
8646 "186r7icrkzrni1c4n33ip7dlsfgys7hnqf0simvxrpl3yhh3ygdi"))))
8647 (properties `((upstream-name . "Rhtslib")))
8648 (build-system r-build-system)
8649 ;; Without this a temporary directory ends up in the Rhtslib.so binary,
8650 ;; which makes R abort the build.
8651 (arguments '(#:configure-flags '("--no-staged-install")))
8654 ("r-zlibbioc" ,r-zlibbioc)))
8658 `(("pkg-config" ,pkg-config)
8659 ("r-knitr" ,r-knitr)))
8660 (home-page "https://github.com/nhayden/Rhtslib")
8661 (synopsis "High-throughput sequencing library as an R package")
8663 "This package provides the HTSlib C library for high-throughput
8664 nucleotide sequence analysis. The package is primarily useful to developers
8665 of other R packages who wish to make use of HTSlib.")
8666 (license license:lgpl2.0+)))
8668 (define-public r-bamsignals
8670 (name "r-bamsignals")
8675 (uri (bioconductor-uri "bamsignals" version))
8678 "0p858xxfv79yc8b3lq58zl9f00irvbn3czsd8wdi5040xg42m402"))))
8679 (build-system r-build-system)
8681 `(("r-biocgenerics" ,r-biocgenerics)
8682 ("r-genomicranges" ,r-genomicranges)
8683 ("r-iranges" ,r-iranges)
8685 ("r-rhtslib" ,r-rhtslib)
8686 ("r-zlibbioc" ,r-zlibbioc)))
8690 `(("r-knitr" ,r-knitr)))
8691 (home-page "https://bioconductor.org/packages/bamsignals")
8692 (synopsis "Extract read count signals from bam files")
8694 "This package efficiently obtains count vectors from indexed bam
8695 files. It counts the number of nucleotide sequence reads in given genomic
8696 ranges and it computes reads profiles and coverage profiles. It also handles
8698 (license license:gpl2+)))
8700 (define-public r-rcas
8706 (uri (bioconductor-uri "RCAS" version))
8709 "0f812pgv3ys1zv4n9sqkgm01hj4cdd0i0h85dqbhkwd94zl6cavl"))))
8710 (properties `((upstream-name . "RCAS")))
8711 (build-system r-build-system)
8713 `(("r-biocgenerics" ,r-biocgenerics)
8714 ("r-biostrings" ,r-biostrings)
8715 ("r-bsgenome" ,r-bsgenome)
8716 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8717 ("r-cowplot" ,r-cowplot)
8718 ("r-data-table" ,r-data-table)
8720 ("r-genomation" ,r-genomation)
8721 ("r-genomeinfodb" ,r-genomeinfodb)
8722 ("r-genomicfeatures" ,r-genomicfeatures)
8723 ("r-genomicranges" ,r-genomicranges)
8724 ("r-ggplot2" ,r-ggplot2)
8725 ("r-ggseqlogo" ,r-ggseqlogo)
8726 ("r-gprofiler2" ,r-gprofiler2)
8727 ("r-iranges" ,r-iranges)
8728 ("r-pbapply" ,r-pbapply)
8729 ("r-pheatmap" ,r-pheatmap)
8730 ("r-plotly" ,r-plotly)
8731 ("r-plotrix" ,r-plotrix)
8732 ("r-proxy" ,r-proxy)
8733 ("r-ranger" ,r-ranger)
8734 ("r-rsqlite" ,r-rsqlite)
8735 ("r-rtracklayer" ,r-rtracklayer)
8736 ("r-rmarkdown" ,r-rmarkdown)
8737 ("r-s4vectors" ,r-s4vectors)
8738 ("pandoc" ,pandoc)))
8740 `(("r-knitr" ,r-knitr)))
8741 (synopsis "RNA-centric annotation system")
8743 "RCAS aims to be a standalone RNA-centric annotation system that provides
8744 intuitive reports and publication-ready graphics. This package provides the R
8745 library implementing most of the pipeline's features.")
8746 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8747 (license license:artistic2.0)))
8749 (define-public rcas-web
8756 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8757 "releases/download/v" version
8758 "/rcas-web-" version ".tar.gz"))
8761 "0wq951aj45gqki1bickg876i993lmawkp8x24agg264br5x716db"))))
8762 (build-system gnu-build-system)
8765 (modify-phases %standard-phases
8766 (add-before 'configure 'find-RCAS
8767 ;; The configure script can't find non-1.3.x versions of RCAS because
8768 ;; its R expression ‘1.10.1 >= 1.3.4’ evaluates to false.
8770 (substitute* "configure"
8771 (("1\\.3\\.4") "0.0.0"))
8773 (add-after 'install 'wrap-executable
8774 (lambda* (#:key inputs outputs #:allow-other-keys)
8775 (let* ((out (assoc-ref outputs "out"))
8776 (json (assoc-ref inputs "guile-json"))
8777 (redis (assoc-ref inputs "guile-redis"))
8778 (path (string-append
8779 json "/share/guile/site/2.2:"
8780 redis "/share/guile/site/2.2")))
8781 (wrap-program (string-append out "/bin/rcas-web")
8782 `("GUILE_LOAD_PATH" ":" = (,path))
8783 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8784 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8787 `(("r-minimal" ,r-minimal)
8789 ("guile" ,guile-2.2)
8790 ("guile-json" ,guile-json-1)
8791 ("guile-redis" ,guile2.2-redis)))
8793 `(("pkg-config" ,pkg-config)))
8794 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8795 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8796 (description "This package provides a simple web interface for the
8797 @dfn{RNA-centric annotation system} (RCAS).")
8798 (license license:agpl3+)))
8800 (define-public r-mutationalpatterns
8802 (name "r-mutationalpatterns")
8807 (uri (bioconductor-uri "MutationalPatterns" version))
8810 "02lyjiabyhmifycksvpcx29a0pb7z9xjw0hgg8n0sd0dy3afqhcm"))))
8811 (build-system r-build-system)
8813 `(("r-biocgenerics" ,r-biocgenerics)
8814 ("r-biostrings" ,r-biostrings)
8815 ;; These two packages are suggested packages
8816 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8817 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8818 ("r-genomicranges" ,r-genomicranges)
8819 ("r-genomeinfodb" ,r-genomeinfodb)
8820 ("r-ggplot2" ,r-ggplot2)
8821 ("r-iranges" ,r-iranges)
8824 ("r-pracma" ,r-pracma)
8825 ("r-reshape2" ,r-reshape2)
8826 ("r-cowplot" ,r-cowplot)
8827 ("r-ggdendro" ,r-ggdendro)
8828 ("r-s4vectors" ,r-s4vectors)
8829 ("r-summarizedexperiment" ,r-summarizedexperiment)
8830 ("r-variantannotation" ,r-variantannotation)))
8831 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8832 (synopsis "Extract and visualize mutational patterns in genomic data")
8833 (description "This package provides an extensive toolset for the
8834 characterization and visualization of a wide range of mutational patterns
8835 in SNV base substitution data.")
8836 (license license:expat)))
8838 (define-public r-chipkernels
8839 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8842 (name "r-chipkernels")
8843 (version (string-append "1.1-" revision "." (string-take commit 9)))
8848 (url "https://github.com/ManuSetty/ChIPKernels")
8850 (file-name (string-append name "-" version))
8853 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8854 (build-system r-build-system)
8856 `(("r-iranges" ,r-iranges)
8857 ("r-xvector" ,r-xvector)
8858 ("r-biostrings" ,r-biostrings)
8859 ("r-bsgenome" ,r-bsgenome)
8860 ("r-gtools" ,r-gtools)
8861 ("r-genomicranges" ,r-genomicranges)
8862 ("r-sfsmisc" ,r-sfsmisc)
8863 ("r-kernlab" ,r-kernlab)
8864 ("r-s4vectors" ,r-s4vectors)
8865 ("r-biocgenerics" ,r-biocgenerics)))
8866 (home-page "https://github.com/ManuSetty/ChIPKernels")
8867 (synopsis "Build string kernels for DNA Sequence analysis")
8868 (description "ChIPKernels is an R package for building different string
8869 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8870 must be built and this dictionary can be used for determining kernels for DNA
8872 (license license:gpl2+))))
8874 (define-public r-seqgl
8882 (url "https://github.com/ManuSetty/SeqGL")
8884 (file-name (git-file-name name version))
8887 "1r6ywvhxl3ffv48lgj7sbd582mcc6dha3ksgc2qjlvjrnkbj3799"))))
8888 (build-system r-build-system)
8890 `(("r-biostrings" ,r-biostrings)
8891 ("r-chipkernels" ,r-chipkernels)
8892 ("r-genomicranges" ,r-genomicranges)
8893 ("r-spams" ,r-spams)
8894 ("r-wgcna" ,r-wgcna)
8895 ("r-fastcluster" ,r-fastcluster)))
8896 (home-page "https://github.com/ManuSetty/SeqGL")
8897 (synopsis "Group lasso for Dnase/ChIP-seq data")
8898 (description "SeqGL is a group lasso based algorithm to extract
8899 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8900 This package presents a method which uses group lasso to discriminate between
8901 bound and non bound genomic regions to accurately identify transcription
8902 factors bound at the specific regions.")
8903 (license license:gpl2+)))
8905 (define-public r-tximport
8911 (uri (bioconductor-uri "tximport" version))
8914 "1x9959lkjl2h869rgd1b30q1idxzjkr1fyqbpndqk3kbi4q2gr40"))))
8915 (build-system r-build-system)
8917 `(("r-knitr" ,r-knitr)))
8918 (home-page "https://bioconductor.org/packages/tximport")
8919 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8921 "This package provides tools to import transcript-level abundance,
8922 estimated counts and transcript lengths, and to summarize them into matrices
8923 for use with downstream gene-level analysis packages. Average transcript
8924 length, weighted by sample-specific transcript abundance estimates, is
8925 provided as a matrix which can be used as an offset for different expression
8926 of gene-level counts.")
8927 (license license:gpl2+)))
8929 (define-public r-rhdf5
8935 (uri (bioconductor-uri "rhdf5" version))
8938 "0fnx60dpf6s2qwq48lg98g18g8k7wgm66pw0kamlbb7l2hnwycvf"))))
8939 (build-system r-build-system)
8941 `(("r-rhdf5lib" ,r-rhdf5lib)))
8945 `(("r-knitr" ,r-knitr)))
8946 (home-page "https://bioconductor.org/packages/rhdf5")
8947 (synopsis "HDF5 interface to R")
8949 "This R/Bioconductor package provides an interface between HDF5 and R.
8950 HDF5's main features are the ability to store and access very large and/or
8951 complex datasets and a wide variety of metadata on mass storage (disk) through
8952 a completely portable file format. The rhdf5 package is thus suited for the
8953 exchange of large and/or complex datasets between R and other software
8954 package, and for letting R applications work on datasets that are larger than
8955 the available RAM.")
8956 (license license:artistic2.0)))
8958 (define-public r-annotationfilter
8960 (name "r-annotationfilter")
8964 (uri (bioconductor-uri "AnnotationFilter" version))
8967 "18kh1xrhpwb48s1qj4f1v8af3jmw49pnbp5afi2myn9894hxg0cs"))))
8969 `((upstream-name . "AnnotationFilter")))
8970 (build-system r-build-system)
8972 `(("r-genomicranges" ,r-genomicranges)
8973 ("r-lazyeval" ,r-lazyeval)))
8975 `(("r-knitr" ,r-knitr)))
8976 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8977 (synopsis "Facilities for filtering Bioconductor annotation resources")
8979 "This package provides classes and other infrastructure to implement
8980 filters for manipulating Bioconductor annotation resources. The filters are
8981 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8982 (license license:artistic2.0)))
8984 (define-public emboss
8990 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8991 (version-major+minor version) ".0/"
8992 "EMBOSS-" version ".tar.gz"))
8995 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8996 (build-system gnu-build-system)
8999 (list (string-append "--with-hpdf="
9000 (assoc-ref %build-inputs "libharu")))
9002 (modify-phases %standard-phases
9003 (add-after 'unpack 'fix-checks
9005 ;; The PNGDRIVER tests check for the presence of libgd, libpng
9006 ;; and zlib, but assume that they are all found at the same
9008 (substitute* "configure.in"
9009 (("CHECK_PNGDRIVER")
9010 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
9011 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
9012 AM_CONDITIONAL(AMPNG, true)"))
9014 (add-after 'fix-checks 'disable-update-check
9016 ;; At build time there is no connection to the Internet, so
9017 ;; looking for updates will not work.
9018 (substitute* "Makefile.am"
9019 (("\\$\\(bindir\\)/embossupdate") ""))
9021 (add-after 'disable-update-check 'autogen
9022 (lambda _ (invoke "autoreconf" "-vif") #t)))))
9028 ("libharu" ,libharu)
9031 `(("autoconf" ,autoconf)
9032 ("automake" ,automake)
9033 ("libtool" ,libtool)
9034 ("pkg-config" ,pkg-config)))
9035 (home-page "http://emboss.sourceforge.net")
9036 (synopsis "Molecular biology analysis suite")
9037 (description "EMBOSS is the \"European Molecular Biology Open Software
9038 Suite\". EMBOSS is an analysis package specially developed for the needs of
9039 the molecular biology (e.g. EMBnet) user community. The software
9040 automatically copes with data in a variety of formats and even allows
9041 transparent retrieval of sequence data from the web. It also provides a
9042 number of libraries for the development of software in the field of molecular
9043 biology. EMBOSS also integrates a range of currently available packages and
9044 tools for sequence analysis into a seamless whole.")
9045 (license license:gpl2+)))
9048 (let ((revision "1")
9049 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
9052 ;; The version is 2.13.0 even though no release archives have been
9053 ;; published as yet.
9054 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
9058 (url "https://github.com/arq5x/bits")
9060 (file-name (string-append name "-" version "-checkout"))
9063 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
9064 (build-system gnu-build-system)
9066 `(#:tests? #f ;no tests included
9068 (modify-phases %standard-phases
9070 (add-after 'unpack 'remove-cuda
9072 (substitute* "Makefile"
9074 (("(bits_test_intersections) \\\\" _ match) match))
9077 (lambda* (#:key outputs #:allow-other-keys)
9079 "bin" (string-append (assoc-ref outputs "out") "/bin"))
9084 (home-page "https://github.com/arq5x/bits")
9085 (synopsis "Implementation of binary interval search algorithm")
9086 (description "This package provides an implementation of the
9087 BITS (Binary Interval Search) algorithm, an approach to interval set
9088 intersection. It is especially suited for the comparison of diverse genomic
9089 datasets and the exploration of large datasets of genome
9090 intervals (e.g. genes, sequence alignments).")
9091 (license license:gpl2))))
9093 (define-public piranha
9094 ;; There is no release tarball for the latest version. The latest commit is
9095 ;; older than one year at the time of this writing.
9096 (let ((revision "1")
9097 (commit "0466d364b71117d01e4471b74c514436cc281233"))
9100 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
9104 (url "https://github.com/smithlabcode/piranha")
9106 (file-name (git-file-name name version))
9109 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
9110 (build-system gnu-build-system)
9112 `(#:test-target "test"
9114 (modify-phases %standard-phases
9115 (add-after 'unpack 'copy-smithlab-cpp
9116 (lambda* (#:key inputs #:allow-other-keys)
9117 (for-each (lambda (file)
9118 (install-file file "./src/smithlab_cpp/"))
9119 (find-files (assoc-ref inputs "smithlab-cpp")))
9121 (add-after 'install 'install-to-store
9122 (lambda* (#:key outputs #:allow-other-keys)
9123 (let* ((out (assoc-ref outputs "out"))
9124 (bin (string-append out "/bin")))
9125 (for-each (lambda (file)
9126 (install-file file bin))
9127 (find-files "bin" ".*")))
9130 (list (string-append "--with-bam_tools_headers="
9131 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
9132 (string-append "--with-bam_tools_library="
9133 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
9135 `(("bamtools" ,bamtools)
9136 ("samtools" ,samtools-0.1)
9139 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
9143 (url "https://github.com/smithlabcode/smithlab_cpp")
9145 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
9148 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
9150 `(("python" ,python-2)))
9151 (home-page "https://github.com/smithlabcode/piranha")
9152 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
9154 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
9155 RIP-seq experiments. It takes input in BED or BAM format and identifies
9156 regions of statistically significant read enrichment. Additional covariates
9157 may optionally be provided to further inform the peak-calling process.")
9158 (license license:gpl3+))))
9166 (uri (pypi-uri "PePr" version))
9169 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
9170 (build-system python-build-system)
9172 `(#:python ,python-2 ; python2 only
9173 #:tests? #f)) ; no tests included
9175 `(("python2-numpy" ,python2-numpy)
9176 ("python2-scipy" ,python2-scipy)
9177 ("python2-pysam" ,python2-pysam)))
9178 (home-page "https://github.com/shawnzhangyx/PePr")
9179 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
9181 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
9182 that is primarily designed for data with biological replicates. It uses a
9183 negative binomial distribution to model the read counts among the samples in
9184 the same group, and look for consistent differences between ChIP and control
9185 group or two ChIP groups run under different conditions.")
9186 (license license:gpl3+)))
9188 (define-public filevercmp
9189 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
9192 (version (string-append "0-1." (string-take commit 7)))
9196 (url "https://github.com/ekg/filevercmp")
9198 (file-name (git-file-name name commit))
9201 "1j9vxsy0y050v59h0q1d6501fcw1kjvj0d18l1xk2zyg0jzj247c"))))
9202 (build-system gnu-build-system)
9204 `(#:tests? #f ; There are no tests to run.
9206 (modify-phases %standard-phases
9207 (delete 'configure) ; There is no configure phase.
9209 (lambda* (#:key outputs #:allow-other-keys)
9210 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
9211 (install-file "filevercmp" bin)
9213 (home-page "https://github.com/ekg/filevercmp")
9214 (synopsis "This program compares version strings")
9215 (description "This program compares version strings. It intends to be a
9216 replacement for strverscmp.")
9217 (license license:gpl3+))))
9219 (define-public multiqc
9226 (uri (pypi-uri "multiqc" version))
9229 "02iihfl0w0hpnr4pa0sbd1y9qxrg3ycyhjp5lidkcrqh1lmzs3zy"))))
9230 (build-system python-build-system)
9232 `(("python-jinja2" ,python-jinja2)
9233 ("python-simplejson" ,python-simplejson)
9234 ("python-pyyaml" ,python-pyyaml)
9235 ("python-click" ,python-click)
9236 ("python-spectra" ,python-spectra)
9237 ("python-requests" ,python-requests)
9238 ("python-markdown" ,python-markdown)
9239 ("python-lzstring" ,python-lzstring)
9240 ("python-matplotlib" ,python-matplotlib)
9241 ("python-numpy" ,python-numpy)
9242 ;; MultQC checks for the presence of nose at runtime.
9243 ("python-nose" ,python-nose)))
9246 (modify-phases %standard-phases
9247 (add-after 'unpack 'relax-requirements
9249 (substitute* "setup.py"
9250 ;; MultiQC 1.5 ‘requires’ a version of python-matplotlib older
9251 ;; than the one in Guix, but should work fine with 2.2.2.
9252 ;; See <https://github.com/ewels/MultiQC/issues/725> and
9253 ;; <https://github.com/ewels/MultiQC/issues/732> for details.
9254 (("['\"]matplotlib.*?['\"]")
9257 (home-page "https://multiqc.info")
9258 (synopsis "Aggregate bioinformatics analysis reports")
9260 "MultiQC is a tool to aggregate bioinformatics results across many
9261 samples into a single report. It contains modules for a large number of
9262 common bioinformatics tools.")
9263 (license license:gpl3+)))
9265 (define-public variant-tools
9267 (name "variant-tools")
9273 (url "https://github.com/vatlab/varianttools")
9274 ;; There is no tag corresponding to version 3.1.2
9275 (commit "813ae4a90d25b69abc8a40f4f70441fe09015249")))
9276 (file-name (git-file-name name version))
9279 "12ibdmksj7icyqhks4xyvd61bygk4pjmxn618kp6vgk1af01y34g"))))
9280 (build-system python-build-system)
9283 ("c-blosc" ,c-blosc)
9286 ("hdf5-blosc" ,hdf5-blosc)
9287 ("python-cython" ,python-cython)
9290 `(("python-numpy" ,python-numpy)
9291 ("python-pycurl" ,python-pycurl)
9292 ("python-pyzmq" ,python-pyzmq)
9293 ("python-scipy" ,python-scipy)
9294 ("python-tables" ,python-tables)))
9295 (home-page "https://vatlab.github.io/vat-docs/")
9296 (synopsis "Analyze genetic variants from Next-Gen sequencing studies")
9298 "Variant tools is a tool for the manipulation, annotation,
9299 selection, simulation, and analysis of variants in the context of next-gen
9300 sequencing analysis. Unlike some other tools used for next-gen sequencing
9301 analysis, variant tools is project based and provides a whole set of tools to
9302 manipulate and analyze genetic variants.")
9303 (license license:gpl3+)))
9305 (define-public r-chipseq
9312 (uri (bioconductor-uri "chipseq" version))
9315 "0lh859s0aq73vac1phcgagf6n000qgq2xsk0bmfr61n5swifml2a"))))
9316 (build-system r-build-system)
9318 `(("r-biocgenerics" ,r-biocgenerics)
9319 ("r-genomicranges" ,r-genomicranges)
9320 ("r-iranges" ,r-iranges)
9321 ("r-lattice" ,r-lattice)
9322 ("r-s4vectors" ,r-s4vectors)
9323 ("r-shortread" ,r-shortread)))
9324 (home-page "https://bioconductor.org/packages/chipseq")
9325 (synopsis "Package for analyzing ChIPseq data")
9327 "This package provides tools for processing short read data from ChIPseq
9329 (license license:artistic2.0)))
9331 (define-public r-copyhelper
9333 (name "r-copyhelper")
9338 (uri (string-append "https://bioconductor.org/packages/release/"
9339 "data/experiment/src/contrib/CopyhelpeR_"
9343 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
9344 (properties `((upstream-name . "CopyhelpeR")))
9345 (build-system r-build-system)
9346 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
9347 (synopsis "Helper files for CopywriteR")
9349 "This package contains the helper files that are required to run the
9350 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
9351 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
9352 mm10. In addition, it contains a blacklist filter to remove regions that
9353 display copy number variation. Files are stored as GRanges objects from the
9354 GenomicRanges Bioconductor package.")
9355 (license license:gpl2)))
9357 (define-public r-copywriter
9359 (name "r-copywriter")
9364 (uri (bioconductor-uri "CopywriteR" version))
9367 "0c36wpv0rygkbqpf3dwh5xmc3lr7p8lrdzsq2fbbpw04skl6i7m2"))))
9368 (properties `((upstream-name . "CopywriteR")))
9369 (build-system r-build-system)
9371 `(("r-biocparallel" ,r-biocparallel)
9372 ("r-chipseq" ,r-chipseq)
9373 ("r-copyhelper" ,r-copyhelper)
9374 ("r-data-table" ,r-data-table)
9375 ("r-dnacopy" ,r-dnacopy)
9376 ("r-futile-logger" ,r-futile-logger)
9377 ("r-genomeinfodb" ,r-genomeinfodb)
9378 ("r-genomicalignments" ,r-genomicalignments)
9379 ("r-genomicranges" ,r-genomicranges)
9380 ("r-gtools" ,r-gtools)
9381 ("r-iranges" ,r-iranges)
9382 ("r-matrixstats" ,r-matrixstats)
9383 ("r-rsamtools" ,r-rsamtools)
9384 ("r-s4vectors" ,r-s4vectors)))
9385 (home-page "https://github.com/PeeperLab/CopywriteR")
9386 (synopsis "Copy number information from targeted sequencing")
9388 "CopywriteR extracts DNA copy number information from targeted sequencing
9389 by utilizing off-target reads. It allows for extracting uniformly distributed
9390 copy number information, can be used without reference, and can be applied to
9391 sequencing data obtained from various techniques including chromatin
9392 immunoprecipitation and target enrichment on small gene panels. Thereby,
9393 CopywriteR constitutes a widely applicable alternative to available copy
9394 number detection tools.")
9395 (license license:gpl2)))
9397 (define-public r-methylkit
9399 (name "r-methylkit")
9403 (uri (bioconductor-uri "methylKit" version))
9406 "1qr13d2712ypbn96ijic2z5adr5dsd61kzscx7shw6vyj360rlm5"))))
9407 (properties `((upstream-name . "methylKit")))
9408 (build-system r-build-system)
9410 `(("r-data-table" ,r-data-table)
9411 ("r-emdbook" ,r-emdbook)
9412 ("r-fastseg" ,r-fastseg)
9413 ("r-genomeinfodb" ,r-genomeinfodb)
9414 ("r-genomicranges" ,r-genomicranges)
9415 ("r-gtools" ,r-gtools)
9416 ("r-iranges" ,r-iranges)
9417 ("r-kernsmooth" ,r-kernsmooth)
9418 ("r-limma" ,r-limma)
9419 ("r-mclust" ,r-mclust)
9421 ("r-qvalue" ,r-qvalue)
9422 ("r-r-utils" ,r-r-utils)
9424 ("r-rhtslib" ,r-rhtslib)
9425 ("r-rsamtools" ,r-rsamtools)
9426 ("r-rtracklayer" ,r-rtracklayer)
9427 ("r-s4vectors" ,r-s4vectors)
9428 ("r-zlibbioc" ,r-zlibbioc)))
9430 `(("r-knitr" ,r-knitr))) ; for vignettes
9433 (home-page "https://github.com/al2na/methylKit")
9435 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9437 "MethylKit is an R package for DNA methylation analysis and annotation
9438 from high-throughput bisulfite sequencing. The package is designed to deal
9439 with sequencing data from @dfn{Reduced representation bisulfite
9440 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9441 genome bisulfite sequencing. It also has functions to analyze base-pair
9442 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9444 (license license:artistic2.0)))
9446 (define-public r-sva
9453 (uri (bioconductor-uri "sva" version))
9456 "0xa1lm0k1a6nig90mab6xh4gln88rbs5l1cdr6ik6agg7jhs7ji4"))))
9457 (build-system r-build-system)
9459 `(("r-edger" ,r-edger)
9460 ("r-genefilter" ,r-genefilter)
9462 ("r-biocparallel" ,r-biocparallel)
9463 ("r-matrixstats" ,r-matrixstats)
9464 ("r-limma" ,r-limma)))
9465 (home-page "https://bioconductor.org/packages/sva")
9466 (synopsis "Surrogate variable analysis")
9468 "This package contains functions for removing batch effects and other
9469 unwanted variation in high-throughput experiment. It also contains functions
9470 for identifying and building surrogate variables for high-dimensional data
9471 sets. Surrogate variables are covariates constructed directly from
9472 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9473 imaging data that can be used in subsequent analyses to adjust for unknown,
9474 unmodeled, or latent sources of noise.")
9475 (license license:artistic2.0)))
9477 (define-public r-raremetals2
9479 (name "r-raremetals2")
9484 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9485 "b/b7/RareMETALS2_" version ".tar.gz"))
9488 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9489 (properties `((upstream-name . "RareMETALS2")))
9490 (build-system r-build-system)
9492 `(("r-seqminer" ,r-seqminer)
9493 ("r-mvtnorm" ,r-mvtnorm)
9495 ("r-compquadform" ,r-compquadform)
9496 ("r-getopt" ,r-getopt)))
9497 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9498 (synopsis "Analyze gene-level association tests for binary trait")
9500 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9501 It was designed to meta-analyze gene-level association tests for binary trait.
9502 While rareMETALS offers a near-complete solution for meta-analysis of
9503 gene-level tests for quantitative trait, it does not offer the optimal
9504 solution for binary trait. The package rareMETALS2 offers improved features
9505 for analyzing gene-level association tests in meta-analyses for binary
9507 (license license:gpl3)))
9509 (define-public r-protgenerics
9511 (name "r-protgenerics")
9516 (uri (bioconductor-uri "ProtGenerics" version))
9519 "14xzdh7vxss8vmrw91hcwrszdn3ikm71mah8875b2lkrkrfzbl73"))))
9520 (properties `((upstream-name . "ProtGenerics")))
9521 (build-system r-build-system)
9522 (home-page "https://github.com/lgatto/ProtGenerics")
9523 (synopsis "S4 generic functions for proteomics infrastructure")
9525 "This package provides S4 generic functions needed by Bioconductor
9526 proteomics packages.")
9527 (license license:artistic2.0)))
9529 (define-public r-mzr
9536 (uri (bioconductor-uri "mzR" version))
9539 "1r8j8yiz5lcan7j4h37sza2kwczl48dxvld3da3ghjjq67cdc2cm"))
9540 (modules '((guix build utils)))
9543 (delete-file-recursively "src/boost")
9545 (properties `((upstream-name . "mzR")))
9546 (build-system r-build-system)
9549 (modify-phases %standard-phases
9550 (add-after 'unpack 'use-system-boost
9552 (substitute* "src/Makevars"
9553 (("\\./boost/libs.*") "")
9554 (("ARCH_OBJS=" line)
9556 "\nARCH_LIBS=-lboost_system -lboost_regex \
9557 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9560 `(;; Our default boost package won't work here, unfortunately, even with
9561 ;; mzR version 2.22.0.
9562 ("boost" ,boost-for-mysql) ; use this instead of the bundled boost sources
9565 `(("r-biobase" ,r-biobase)
9566 ("r-biocgenerics" ,r-biocgenerics)
9567 ("r-ncdf4" ,r-ncdf4)
9568 ("r-protgenerics" ,r-protgenerics)
9570 ("r-rhdf5lib" ,r-rhdf5lib)
9571 ("r-zlibbioc" ,r-zlibbioc)))
9573 `(("r-knitr" ,r-knitr)))
9574 (home-page "https://github.com/sneumann/mzR/")
9575 (synopsis "Parser for mass spectrometry data files")
9577 "The mzR package provides a unified API to the common file formats and
9578 parsers available for mass spectrometry data. It comes with a wrapper for the
9579 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9580 The package contains the original code written by the ISB, and a subset of the
9581 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9582 previously been used in XCMS.")
9583 (license license:artistic2.0)))
9585 (define-public r-affyio
9592 (uri (bioconductor-uri "affyio" version))
9595 "0j1f61409yq6hmkqrpzamfm7dx35rlq33ccs7wb1qcqx3d3nb75q"))))
9596 (build-system r-build-system)
9598 `(("r-zlibbioc" ,r-zlibbioc)))
9601 (home-page "https://github.com/bmbolstad/affyio")
9602 (synopsis "Tools for parsing Affymetrix data files")
9604 "This package provides routines for parsing Affymetrix data files based
9605 upon file format information. The primary focus is on accessing the CEL and
9607 (license license:lgpl2.0+)))
9609 (define-public r-affy
9616 (uri (bioconductor-uri "affy" version))
9619 "0m6hkyjxmsf80n3anhwh9k26csxczv6v92fkb7klnchdski61pyc"))))
9620 (build-system r-build-system)
9622 `(("r-affyio" ,r-affyio)
9623 ("r-biobase" ,r-biobase)
9624 ("r-biocgenerics" ,r-biocgenerics)
9625 ("r-biocmanager" ,r-biocmanager)
9626 ("r-preprocesscore" ,r-preprocesscore)
9627 ("r-zlibbioc" ,r-zlibbioc)))
9630 (home-page "https://bioconductor.org/packages/affy")
9631 (synopsis "Methods for affymetrix oligonucleotide arrays")
9633 "This package contains functions for exploratory oligonucleotide array
9635 (license license:lgpl2.0+)))
9637 (define-public r-vsn
9644 (uri (bioconductor-uri "vsn" version))
9647 "1k82dikrv1gcync5y1131wg7z1kxv2z2jl4nndg20bixc3398h58"))))
9648 (build-system r-build-system)
9650 `(("r-affy" ,r-affy)
9651 ("r-biobase" ,r-biobase)
9652 ("r-ggplot2" ,r-ggplot2)
9653 ("r-lattice" ,r-lattice)
9654 ("r-limma" ,r-limma)))
9656 `(("r-knitr" ,r-knitr))) ; for vignettes
9657 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9658 (synopsis "Variance stabilization and calibration for microarray data")
9660 "The package implements a method for normalising microarray intensities,
9661 and works for single- and multiple-color arrays. It can also be used for data
9662 from other technologies, as long as they have similar format. The method uses
9663 a robust variant of the maximum-likelihood estimator for an
9664 additive-multiplicative error model and affine calibration. The model
9665 incorporates data calibration step (a.k.a. normalization), a model for the
9666 dependence of the variance on the mean intensity and a variance stabilizing
9667 data transformation. Differences between transformed intensities are
9668 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9669 their variance is independent of the mean, and they are usually more sensitive
9670 and specific in detecting differential transcription.")
9671 (license license:artistic2.0)))
9673 (define-public r-mzid
9680 (uri (bioconductor-uri "mzID" version))
9683 "0y50lzkdamkpz67f6r5whp246qsxpbammjil7g8vjprx0c4jk5n5"))))
9684 (properties `((upstream-name . "mzID")))
9685 (build-system r-build-system)
9687 `(("r-doparallel" ,r-doparallel)
9688 ("r-foreach" ,r-foreach)
9689 ("r-iterators" ,r-iterators)
9691 ("r-protgenerics" ,r-protgenerics)
9695 `(("r-knitr" ,r-knitr)))
9696 (home-page "https://bioconductor.org/packages/mzID")
9697 (synopsis "Parser for mzIdentML files")
9699 "This package provides a parser for mzIdentML files implemented using the
9700 XML package. The parser tries to be general and able to handle all types of
9701 mzIdentML files with the drawback of having less pretty output than a vendor
9703 (license license:gpl2+)))
9705 (define-public r-pcamethods
9707 (name "r-pcamethods")
9712 (uri (bioconductor-uri "pcaMethods" version))
9715 "10cww4jxyynkwxbbsx804nwac31j0hh8dgisygld0q663gaxkgni"))))
9716 (properties `((upstream-name . "pcaMethods")))
9717 (build-system r-build-system)
9719 `(("r-biobase" ,r-biobase)
9720 ("r-biocgenerics" ,r-biocgenerics)
9722 ("r-rcpp" ,r-rcpp)))
9723 (home-page "https://github.com/hredestig/pcamethods")
9724 (synopsis "Collection of PCA methods")
9726 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9727 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9728 for missing value estimation is included for comparison. BPCA, PPCA and
9729 NipalsPCA may be used to perform PCA on incomplete data as well as for
9730 accurate missing value estimation. A set of methods for printing and plotting
9731 the results is also provided. All PCA methods make use of the same data
9732 structure (pcaRes) to provide a common interface to the PCA results.")
9733 (license license:gpl3+)))
9735 (define-public r-msnbase
9742 (uri (bioconductor-uri "MSnbase" version))
9745 "17vlv9gh41s1hp043b7j1jfqiw52alh1misjzy1kxl0g90rld00l"))))
9746 (properties `((upstream-name . "MSnbase")))
9747 (build-system r-build-system)
9749 `(("r-affy" ,r-affy)
9750 ("r-biobase" ,r-biobase)
9751 ("r-biocgenerics" ,r-biocgenerics)
9752 ("r-biocparallel" ,r-biocparallel)
9753 ("r-digest" ,r-digest)
9754 ("r-ggplot2" ,r-ggplot2)
9755 ("r-impute" ,r-impute)
9756 ("r-iranges" ,r-iranges)
9757 ("r-lattice" ,r-lattice)
9758 ("r-maldiquant" ,r-maldiquant)
9762 ("r-pcamethods" ,r-pcamethods)
9764 ("r-preprocesscore" ,r-preprocesscore)
9765 ("r-protgenerics" ,r-protgenerics)
9767 ("r-s4vectors" ,r-s4vectors)
9768 ("r-scales" ,r-scales)
9772 `(("r-knitr" ,r-knitr)))
9773 (home-page "https://github.com/lgatto/MSnbase")
9774 (synopsis "Base functions and classes for MS-based proteomics")
9776 "This package provides basic plotting, data manipulation and processing
9777 of mass spectrometry based proteomics data.")
9778 (license license:artistic2.0)))
9780 (define-public r-msnid
9787 (uri (bioconductor-uri "MSnID" version))
9790 "0dwa6j2nqb3223a8g4f453aznjh69wngrpvdi12iy69j1psbbjcc"))))
9791 (properties `((upstream-name . "MSnID")))
9792 (build-system r-build-system)
9794 `(("r-biobase" ,r-biobase)
9795 ("r-data-table" ,r-data-table)
9796 ("r-doparallel" ,r-doparallel)
9797 ("r-dplyr" ,r-dplyr)
9798 ("r-foreach" ,r-foreach)
9799 ("r-iterators" ,r-iterators)
9800 ("r-msnbase" ,r-msnbase)
9803 ("r-protgenerics" ,r-protgenerics)
9804 ("r-r-cache" ,r-r-cache)
9806 ("r-reshape2" ,r-reshape2)))
9807 (home-page "https://bioconductor.org/packages/MSnID")
9808 (synopsis "Utilities for LC-MSn proteomics identifications")
9810 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9811 from mzIdentML (leveraging the mzID package) or text files. After collating
9812 the search results from multiple datasets it assesses their identification
9813 quality and optimize filtering criteria to achieve the maximum number of
9814 identifications while not exceeding a specified false discovery rate. It also
9815 contains a number of utilities to explore the MS/MS results and assess missed
9816 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9817 (license license:artistic2.0)))
9819 (define-public r-aroma-light
9821 (name "r-aroma-light")
9826 (uri (bioconductor-uri "aroma.light" version))
9829 "19y5f2minx2pp73zdh43v1qkwpkaxygkl8cwlnwja15i46s0bcyc"))))
9830 (properties `((upstream-name . "aroma.light")))
9831 (build-system r-build-system)
9833 `(("r-matrixstats" ,r-matrixstats)
9834 ("r-r-methodss3" ,r-r-methodss3)
9836 ("r-r-utils" ,r-r-utils)))
9837 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9838 (synopsis "Methods for normalization and visualization of microarray data")
9840 "This package provides methods for microarray analysis that take basic
9841 data types such as matrices and lists of vectors. These methods can be used
9842 standalone, be utilized in other packages, or be wrapped up in higher-level
9844 (license license:gpl2+)))
9846 (define-public r-deseq
9853 (uri (bioconductor-uri "DESeq" version))
9856 "047hph5aqmjnz1aqprziw0smdn5lf96hmwpnvqrxv1j2yfvcf3h1"))))
9857 (properties `((upstream-name . "DESeq")))
9858 (build-system r-build-system)
9860 `(("r-biobase" ,r-biobase)
9861 ("r-biocgenerics" ,r-biocgenerics)
9862 ("r-genefilter" ,r-genefilter)
9863 ("r-geneplotter" ,r-geneplotter)
9864 ("r-lattice" ,r-lattice)
9865 ("r-locfit" ,r-locfit)
9867 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9868 (home-page "https://www-huber.embl.de/users/anders/DESeq/")
9869 (synopsis "Differential gene expression analysis")
9871 "This package provides tools for estimating variance-mean dependence in
9872 count data from high-throughput genetic sequencing assays and for testing for
9873 differential expression based on a model using the negative binomial
9875 (license license:gpl3+)))
9877 (define-public r-edaseq
9884 (uri (bioconductor-uri "EDASeq" version))
9887 "12gzxjh73qshlwvsf92lbrf4bi199kxg2snrkprh1z4yqf7bjfm4"))))
9888 (properties `((upstream-name . "EDASeq")))
9889 (build-system r-build-system)
9891 `(("r-annotationdbi" ,r-annotationdbi)
9892 ("r-aroma-light" ,r-aroma-light)
9893 ("r-biobase" ,r-biobase)
9894 ("r-biocgenerics" ,r-biocgenerics)
9895 ("r-biocmanager" ,r-biocmanager)
9896 ("r-biomart" ,r-biomart)
9897 ("r-biostrings" ,r-biostrings)
9898 ("r-deseq" ,r-deseq)
9899 ("r-genomicfeatures" ,r-genomicfeatures)
9900 ("r-genomicranges" ,r-genomicranges)
9901 ("r-iranges" ,r-iranges)
9902 ("r-rsamtools" ,r-rsamtools)
9903 ("r-shortread" ,r-shortread)))
9905 `(("r-knitr" ,r-knitr)))
9906 (home-page "https://github.com/drisso/EDASeq")
9907 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9909 "This package provides support for numerical and graphical summaries of
9910 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9911 adjust for GC-content effect (or other gene-level effects) on read counts:
9912 loess robust local regression, global-scaling, and full-quantile
9913 normalization. Between-lane normalization procedures to adjust for
9914 distributional differences between lanes (e.g., sequencing depth):
9915 global-scaling and full-quantile normalization.")
9916 (license license:artistic2.0)))
9918 (define-public r-interactivedisplaybase
9920 (name "r-interactivedisplaybase")
9925 (uri (bioconductor-uri "interactiveDisplayBase" version))
9928 "1x5vipqa4pgwpd62c1c58shnlpv3zyzzpf4wdwr00q1swkdb7wv3"))))
9930 `((upstream-name . "interactiveDisplayBase")))
9931 (build-system r-build-system)
9933 `(("r-biocgenerics" ,r-biocgenerics)
9935 ("r-shiny" ,r-shiny)))
9937 `(("r-knitr" ,r-knitr)))
9938 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9939 (synopsis "Base package for web displays of Bioconductor objects")
9941 "This package contains the basic methods needed to generate interactive
9942 Shiny-based display methods for Bioconductor objects.")
9943 (license license:artistic2.0)))
9945 (define-public r-annotationhub
9947 (name "r-annotationhub")
9952 (uri (bioconductor-uri "AnnotationHub" version))
9955 "04bz91m2wx1zm61rvpr0syyklz232fw74wrl73d965wi3x8fyda5"))))
9956 (properties `((upstream-name . "AnnotationHub")))
9957 (build-system r-build-system)
9959 `(("r-annotationdbi" ,r-annotationdbi)
9960 ("r-biocfilecache" ,r-biocfilecache)
9961 ("r-biocgenerics" ,r-biocgenerics)
9962 ("r-biocmanager" ,r-biocmanager)
9963 ("r-biocversion" ,r-biocversion)
9965 ("r-dplyr" ,r-dplyr)
9967 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9968 ("r-rappdirs" ,r-rappdirs)
9969 ("r-rsqlite" ,r-rsqlite)
9970 ("r-s4vectors" ,r-s4vectors)
9971 ("r-yaml" ,r-yaml)))
9973 `(("r-knitr" ,r-knitr)))
9974 (home-page "https://bioconductor.org/packages/AnnotationHub")
9975 (synopsis "Client to access AnnotationHub resources")
9977 "This package provides a client for the Bioconductor AnnotationHub web
9978 resource. The AnnotationHub web resource provides a central location where
9979 genomic files (e.g. VCF, bed, wig) and other resources from standard
9980 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9981 metadata about each resource, e.g., a textual description, tags, and date of
9982 modification. The client creates and manages a local cache of files retrieved
9983 by the user, helping with quick and reproducible access.")
9984 (license license:artistic2.0)))
9986 (define-public r-fastseg
9993 (uri (bioconductor-uri "fastseg" version))
9996 "1d48n245pzmvcpsz93lxb4frqh222gfhpmlvm0sb74skn16way63"))))
9997 (build-system r-build-system)
9999 `(("r-biobase" ,r-biobase)
10000 ("r-biocgenerics" ,r-biocgenerics)
10001 ("r-genomicranges" ,r-genomicranges)
10002 ("r-iranges" ,r-iranges)
10003 ("r-s4vectors" ,r-s4vectors)))
10004 (home-page "https://www.bioinf.jku.at/software/fastseg/index.html")
10005 (synopsis "Fast segmentation algorithm for genetic sequencing data")
10007 "Fastseg implements a very fast and efficient segmentation algorithm.
10008 It can segment data from DNA microarrays and data from next generation
10009 sequencing for example to detect copy number segments. Further it can segment
10010 data from RNA microarrays like tiling arrays to identify transcripts. Most
10011 generally, it can segment data given as a matrix or as a vector. Various data
10012 formats can be used as input to fastseg like expression set objects for
10013 microarrays or GRanges for sequencing data.")
10014 (license license:lgpl2.0+)))
10016 (define-public r-keggrest
10018 (name "r-keggrest")
10023 (uri (bioconductor-uri "KEGGREST" version))
10026 "0q76w17fya2x0z7mvyhkk5kqh07flldgih13ma44vhcy1bdlm6j1"))))
10027 (properties `((upstream-name . "KEGGREST")))
10028 (build-system r-build-system)
10030 `(("r-biostrings" ,r-biostrings)
10034 `(("r-knitr" ,r-knitr)))
10035 (home-page "https://bioconductor.org/packages/KEGGREST")
10036 (synopsis "Client-side REST access to KEGG")
10038 "This package provides a package that provides a client interface to the
10039 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
10040 (license license:artistic2.0)))
10042 (define-public r-gage
10049 (uri (bioconductor-uri "gage" version))
10052 "1bqmvjiya1df0b3h491lp1jxahiyidvaf9n094z0sk84x5y3xh2p"))))
10053 (build-system r-build-system)
10055 `(("r-annotationdbi" ,r-annotationdbi)
10056 ("r-go-db" ,r-go-db)
10057 ("r-graph" ,r-graph)
10058 ("r-keggrest" ,r-keggrest)))
10059 (home-page (string-append "https://bmcbioinformatics.biomedcentral.com/"
10060 "articles/10.1186/1471-2105-10-161"))
10061 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
10063 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
10064 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
10065 data attributes including sample sizes, experimental designs, assay platforms,
10066 and other types of heterogeneity. The gage package provides functions for
10067 basic GAGE analysis, result processing and presentation. In addition, it
10068 provides demo microarray data and commonly used gene set data based on KEGG
10069 pathways and GO terms. These functions and data are also useful for gene set
10070 analysis using other methods.")
10071 (license license:gpl2+)))
10073 (define-public r-genomicfiles
10075 (name "r-genomicfiles")
10080 (uri (bioconductor-uri "GenomicFiles" version))
10083 "1k3824pzf9fdqvcv6cz2742q3mabpmncrc72hwa21ac8wy1b04n4"))))
10084 (properties `((upstream-name . "GenomicFiles")))
10085 (build-system r-build-system)
10087 `(("r-biocgenerics" ,r-biocgenerics)
10088 ("r-biocparallel" ,r-biocparallel)
10089 ("r-genomeinfodb" ,r-genomeinfodb)
10090 ("r-genomicalignments" ,r-genomicalignments)
10091 ("r-genomicranges" ,r-genomicranges)
10092 ("r-iranges" ,r-iranges)
10093 ("r-rsamtools" ,r-rsamtools)
10094 ("r-rtracklayer" ,r-rtracklayer)
10095 ("r-s4vectors" ,r-s4vectors)
10096 ("r-summarizedexperiment" ,r-summarizedexperiment)
10097 ("r-variantannotation" ,r-variantannotation)))
10098 (home-page "https://bioconductor.org/packages/GenomicFiles")
10099 (synopsis "Distributed computing by file or by range")
10101 "This package provides infrastructure for parallel computations
10102 distributed by file or by range. User defined mapper and reducer functions
10103 provide added flexibility for data combination and manipulation.")
10104 (license license:artistic2.0)))
10106 (define-public r-complexheatmap
10108 (name "r-complexheatmap")
10113 (uri (bioconductor-uri "ComplexHeatmap" version))
10116 "1gx0hzrkla92pgmfkrm2zp0ccnhizq6rs26zgzpi5x8a5lvghh5q"))))
10118 `((upstream-name . "ComplexHeatmap")))
10119 (build-system r-build-system)
10121 `(("r-circlize" ,r-circlize)
10123 ("r-colorspace" ,r-colorspace)
10124 ("r-getoptlong" ,r-getoptlong)
10125 ("r-globaloptions" ,r-globaloptions)
10127 ("r-rcolorbrewer" ,r-rcolorbrewer)))
10129 `(("r-knitr" ,r-knitr)))
10131 "https://github.com/jokergoo/ComplexHeatmap")
10132 (synopsis "Making Complex Heatmaps")
10134 "Complex heatmaps are efficient to visualize associations between
10135 different sources of data sets and reveal potential structures. This package
10136 provides a highly flexible way to arrange multiple heatmaps and supports
10137 self-defined annotation graphics.")
10138 (license license:gpl2+)))
10140 (define-public r-dirichletmultinomial
10142 (name "r-dirichletmultinomial")
10147 (uri (bioconductor-uri "DirichletMultinomial" version))
10150 "1m9dsrddrllb2i88qzik1867iv9mggrgdkn0dlp8sq7gl69vmalb"))))
10152 `((upstream-name . "DirichletMultinomial")))
10153 (build-system r-build-system)
10157 `(("r-biocgenerics" ,r-biocgenerics)
10158 ("r-iranges" ,r-iranges)
10159 ("r-s4vectors" ,r-s4vectors)))
10160 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
10161 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
10163 "Dirichlet-multinomial mixture models can be used to describe variability
10164 in microbial metagenomic data. This package is an interface to code
10165 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
10167 (license license:lgpl3)))
10169 (define-public r-ensembldb
10171 (name "r-ensembldb")
10176 (uri (bioconductor-uri "ensembldb" version))
10179 "1vvchc04nshxc768fp31rxb603aj3hmq8xlh5qabcwf2c3z9719g"))))
10180 (build-system r-build-system)
10182 `(("r-annotationdbi" ,r-annotationdbi)
10183 ("r-annotationfilter" ,r-annotationfilter)
10184 ("r-biobase" ,r-biobase)
10185 ("r-biocgenerics" ,r-biocgenerics)
10186 ("r-biostrings" ,r-biostrings)
10189 ("r-genomeinfodb" ,r-genomeinfodb)
10190 ("r-genomicfeatures" ,r-genomicfeatures)
10191 ("r-genomicranges" ,r-genomicranges)
10192 ("r-iranges" ,r-iranges)
10193 ("r-protgenerics" ,r-protgenerics)
10194 ("r-rsamtools" ,r-rsamtools)
10195 ("r-rsqlite" ,r-rsqlite)
10196 ("r-rtracklayer" ,r-rtracklayer)
10197 ("r-s4vectors" ,r-s4vectors)))
10199 `(("r-knitr" ,r-knitr)))
10200 (home-page "https://github.com/jotsetung/ensembldb")
10201 (synopsis "Utilities to create and use Ensembl-based annotation databases")
10203 "The package provides functions to create and use transcript-centric
10204 annotation databases/packages. The annotation for the databases are directly
10205 fetched from Ensembl using their Perl API. The functionality and data is
10206 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
10207 but, in addition to retrieve all gene/transcript models and annotations from
10208 the database, the @code{ensembldb} package also provides a filter framework
10209 allowing to retrieve annotations for specific entries like genes encoded on a
10210 chromosome region or transcript models of lincRNA genes.")
10211 ;; No version specified
10212 (license license:lgpl3+)))
10214 (define-public r-organismdbi
10216 (name "r-organismdbi")
10221 (uri (bioconductor-uri "OrganismDbi" version))
10224 "194h5576inq44qr666snzq0ygnc77rk5ljkn9bn8zs6x6gb3cwaw"))))
10225 (properties `((upstream-name . "OrganismDbi")))
10226 (build-system r-build-system)
10228 `(("r-annotationdbi" ,r-annotationdbi)
10229 ("r-biobase" ,r-biobase)
10230 ("r-biocgenerics" ,r-biocgenerics)
10231 ("r-biocmanager" ,r-biocmanager)
10233 ("r-genomicfeatures" ,r-genomicfeatures)
10234 ("r-genomicranges" ,r-genomicranges)
10235 ("r-graph" ,r-graph)
10236 ("r-iranges" ,r-iranges)
10238 ("r-s4vectors" ,r-s4vectors)))
10239 (home-page "https://bioconductor.org/packages/OrganismDbi")
10240 (synopsis "Software to enable the smooth interfacing of database packages")
10241 (description "The package enables a simple unified interface to several
10242 annotation packages each of which has its own schema by taking advantage of
10243 the fact that each of these packages implements a select methods.")
10244 (license license:artistic2.0)))
10246 (define-public r-biovizbase
10248 (name "r-biovizbase")
10253 (uri (bioconductor-uri "biovizBase" version))
10256 "1vq2mxa2jkljgw75zqjdkyml0ppi5dspvwj4cznfhi31cq8ds0qh"))))
10257 (properties `((upstream-name . "biovizBase")))
10258 (build-system r-build-system)
10260 `(("r-annotationdbi" ,r-annotationdbi)
10261 ("r-annotationfilter" ,r-annotationfilter)
10262 ("r-biocgenerics" ,r-biocgenerics)
10263 ("r-biostrings" ,r-biostrings)
10264 ("r-dichromat" ,r-dichromat)
10265 ("r-ensembldb" ,r-ensembldb)
10266 ("r-genomeinfodb" ,r-genomeinfodb)
10267 ("r-genomicalignments" ,r-genomicalignments)
10268 ("r-genomicfeatures" ,r-genomicfeatures)
10269 ("r-genomicranges" ,r-genomicranges)
10270 ("r-hmisc" ,r-hmisc)
10271 ("r-iranges" ,r-iranges)
10272 ("r-rcolorbrewer" ,r-rcolorbrewer)
10273 ("r-rlang" ,r-rlang)
10274 ("r-rsamtools" ,r-rsamtools)
10275 ("r-s4vectors" ,r-s4vectors)
10276 ("r-scales" ,r-scales)
10277 ("r-summarizedexperiment" ,r-summarizedexperiment)
10278 ("r-variantannotation" ,r-variantannotation)))
10279 (home-page "https://bioconductor.org/packages/biovizBase")
10280 (synopsis "Basic graphic utilities for visualization of genomic data")
10282 "The biovizBase package is designed to provide a set of utilities, color
10283 schemes and conventions for genomic data. It serves as the base for various
10284 high-level packages for biological data visualization. This saves development
10285 effort and encourages consistency.")
10286 (license license:artistic2.0)))
10288 (define-public r-ggbio
10295 (uri (bioconductor-uri "ggbio" version))
10298 "11ggnqjq42fi2hm9xlvrrlr2xhy4kglvl1a0mycp1s4v67lxw5h5"))))
10299 (build-system r-build-system)
10302 (modify-phases %standard-phases
10303 ;; See https://github.com/tengfei/ggbio/issues/117
10304 ;; This fix will be included in the next release.
10305 (add-after 'unpack 'fix-typo
10307 (substitute* "R/GGbio-class.R"
10308 (("fechable") "fetchable"))
10311 `(("r-annotationdbi" ,r-annotationdbi)
10312 ("r-annotationfilter" ,r-annotationfilter)
10313 ("r-biobase" ,r-biobase)
10314 ("r-biocgenerics" ,r-biocgenerics)
10315 ("r-biostrings" ,r-biostrings)
10316 ("r-biovizbase" ,r-biovizbase)
10317 ("r-bsgenome" ,r-bsgenome)
10318 ("r-ensembldb" ,r-ensembldb)
10319 ("r-genomeinfodb" ,r-genomeinfodb)
10320 ("r-genomicalignments" ,r-genomicalignments)
10321 ("r-genomicfeatures" ,r-genomicfeatures)
10322 ("r-genomicranges" ,r-genomicranges)
10323 ("r-ggally" ,r-ggally)
10324 ("r-ggplot2" ,r-ggplot2)
10325 ("r-gridextra" ,r-gridextra)
10326 ("r-gtable" ,r-gtable)
10327 ("r-hmisc" ,r-hmisc)
10328 ("r-iranges" ,r-iranges)
10329 ("r-organismdbi" ,r-organismdbi)
10330 ("r-reshape2" ,r-reshape2)
10331 ("r-rlang" ,r-rlang)
10332 ("r-rsamtools" ,r-rsamtools)
10333 ("r-rtracklayer" ,r-rtracklayer)
10334 ("r-s4vectors" ,r-s4vectors)
10335 ("r-scales" ,r-scales)
10336 ("r-summarizedexperiment" ,r-summarizedexperiment)
10337 ("r-variantannotation" ,r-variantannotation)))
10339 `(("r-knitr" ,r-knitr)))
10340 (home-page "http://www.tengfei.name/ggbio/")
10341 (synopsis "Visualization tools for genomic data")
10343 "The ggbio package extends and specializes the grammar of graphics for
10344 biological data. The graphics are designed to answer common scientific
10345 questions, in particular those often asked of high throughput genomics data.
10346 All core Bioconductor data structures are supported, where appropriate. The
10347 package supports detailed views of particular genomic regions, as well as
10348 genome-wide overviews. Supported overviews include ideograms and grand linear
10349 views. High-level plots include sequence fragment length, edge-linked
10350 interval to data view, mismatch pileup, and several splicing summaries.")
10351 (license license:artistic2.0)))
10353 (define-public r-gqtlbase
10355 (name "r-gqtlbase")
10360 (uri (bioconductor-uri "gQTLBase" version))
10363 "1ly14vhhqxjpbxjypi6ppd37dycabdhf4ny4nsvp9969k418zv41"))))
10364 (properties `((upstream-name . "gQTLBase")))
10365 (build-system r-build-system)
10367 `(("r-batchjobs" ,r-batchjobs)
10368 ("r-bbmisc" ,r-bbmisc)
10369 ("r-biocgenerics" ,r-biocgenerics)
10371 ("r-doparallel" ,r-doparallel)
10373 ("r-ffbase" ,r-ffbase)
10374 ("r-foreach" ,r-foreach)
10375 ("r-genomicfiles" ,r-genomicfiles)
10376 ("r-genomicranges" ,r-genomicranges)
10377 ("r-rtracklayer" ,r-rtracklayer)
10378 ("r-s4vectors" ,r-s4vectors)
10379 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10381 `(("r-knitr" ,r-knitr)))
10382 (home-page "https://bioconductor.org/packages/gQTLBase")
10383 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10385 "The purpose of this package is to simplify the storage and interrogation
10386 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10388 (license license:artistic2.0)))
10390 (define-public r-snpstats
10392 (name "r-snpstats")
10397 (uri (bioconductor-uri "snpStats" version))
10400 "1qv3nqqr30d3n66mawqd9dbl95dl89r4bcjvkc5iassy1yrwr8wq"))))
10401 (properties `((upstream-name . "snpStats")))
10402 (build-system r-build-system)
10403 (inputs `(("zlib" ,zlib)))
10405 `(("r-biocgenerics" ,r-biocgenerics)
10406 ("r-matrix" ,r-matrix)
10407 ("r-survival" ,r-survival)
10408 ("r-zlibbioc" ,r-zlibbioc)))
10409 (home-page "https://bioconductor.org/packages/snpStats")
10410 (synopsis "Methods for SNP association studies")
10412 "This package provides classes and statistical methods for large
10413 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10414 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10415 (license license:gpl3)))
10417 (define-public r-homo-sapiens
10419 (name "r-homo-sapiens")
10423 ;; We cannot use bioconductor-uri here because this tarball is
10424 ;; located under "data/annotation/" instead of "bioc/".
10425 (uri (string-append "https://www.bioconductor.org/packages/"
10426 "release/data/annotation/src/contrib/"
10428 version ".tar.gz"))
10431 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10433 `((upstream-name . "Homo.sapiens")))
10434 (build-system r-build-system)
10436 `(("r-genomicfeatures" ,r-genomicfeatures)
10437 ("r-go-db" ,r-go-db)
10438 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10439 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10440 ("r-organismdbi" ,r-organismdbi)
10441 ("r-annotationdbi" ,r-annotationdbi)))
10442 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10443 (synopsis "Annotation package for the Homo.sapiens object")
10445 "This package contains the Homo.sapiens object to access data from
10446 several related annotation packages.")
10447 (license license:artistic2.0)))
10449 (define-public r-erma
10456 (uri (bioconductor-uri "erma" version))
10459 "1ccfbq0r48sr3h8050w8zv8402h7nx09adr0xdyqlg7kwp9vd2l3"))))
10460 (build-system r-build-system)
10462 `(("r-annotationdbi" ,r-annotationdbi)
10463 ("r-biobase" ,r-biobase)
10464 ("r-biocgenerics" ,r-biocgenerics)
10465 ("r-biocparallel" ,r-biocparallel)
10466 ("r-genomeinfodb" ,r-genomeinfodb)
10467 ("r-genomicfiles" ,r-genomicfiles)
10468 ("r-genomicranges" ,r-genomicranges)
10469 ("r-ggplot2" ,r-ggplot2)
10470 ("r-homo-sapiens" ,r-homo-sapiens)
10471 ("r-iranges" ,r-iranges)
10472 ("r-rtracklayer" ,r-rtracklayer)
10473 ("r-s4vectors" ,r-s4vectors)
10474 ("r-shiny" ,r-shiny)
10475 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10477 `(("r-knitr" ,r-knitr)))
10478 (home-page "https://bioconductor.org/packages/erma")
10479 (synopsis "Epigenomic road map adventures")
10481 "The epigenomics road map describes locations of epigenetic marks in DNA
10482 from a variety of cell types. Of interest are locations of histone
10483 modifications, sites of DNA methylation, and regions of accessible chromatin.
10484 This package presents a selection of elements of the road map including
10485 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10486 by Ernst and Kellis.")
10487 (license license:artistic2.0)))
10489 (define-public r-ldblock
10496 (uri (bioconductor-uri "ldblock" version))
10499 "0plw00n2zfgh029ab41dnydzgv2yxrapjp770147rx9pff4dngrv"))))
10500 (build-system r-build-system)
10502 `(("r-biocgenerics" ,r-biocgenerics)
10503 ("r-ensdb-hsapiens-v75" ,r-ensdb-hsapiens-v75)
10504 ("r-ensembldb" ,r-ensembldb)
10505 ("r-genomeinfodb" ,r-genomeinfodb)
10506 ("r-genomicfiles" ,r-genomicfiles)
10508 ("r-matrix" ,r-matrix)
10509 ("r-rsamtools" ,r-rsamtools)
10510 ("r-snpstats" ,r-snpstats)
10511 ("r-variantannotation" ,r-variantannotation)))
10513 `(("r-knitr" ,r-knitr)))
10514 (home-page "https://bioconductor.org/packages/ldblock")
10515 (synopsis "Data structures for linkage disequilibrium measures in populations")
10517 "This package defines data structures for @dfn{linkage
10518 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10519 handling of existing population-level data for the purpose of flexibly
10520 defining LD blocks.")
10521 (license license:artistic2.0)))
10523 (define-public r-gqtlstats
10525 (name "r-gqtlstats")
10530 (uri (bioconductor-uri "gQTLstats" version))
10533 "1jjqfpjp93nmxjn757j5mzcax96bzcqdd1gr3rsdxg7ap008l2w7"))))
10534 (properties `((upstream-name . "gQTLstats")))
10535 (build-system r-build-system)
10537 `(("r-annotationdbi" ,r-annotationdbi)
10538 ("r-batchjobs" ,r-batchjobs)
10539 ("r-bbmisc" ,r-bbmisc)
10540 ("r-beeswarm" ,r-beeswarm)
10541 ("r-biobase" ,r-biobase)
10542 ("r-biocgenerics" ,r-biocgenerics)
10543 ("r-doparallel" ,r-doparallel)
10544 ("r-dplyr" ,r-dplyr)
10546 ("r-ffbase" ,r-ffbase)
10547 ("r-foreach" ,r-foreach)
10548 ("r-genomeinfodb" ,r-genomeinfodb)
10549 ("r-genomicfeatures" ,r-genomicfeatures)
10550 ("r-genomicfiles" ,r-genomicfiles)
10551 ("r-genomicranges" ,r-genomicranges)
10552 ("r-ggbeeswarm" ,r-ggbeeswarm)
10553 ("r-ggplot2" ,r-ggplot2)
10554 ("r-gqtlbase" ,r-gqtlbase)
10555 ("r-hardyweinberg" ,r-hardyweinberg)
10556 ("r-homo-sapiens" ,r-homo-sapiens)
10557 ("r-iranges" ,r-iranges)
10558 ("r-limma" ,r-limma)
10560 ("r-plotly" ,r-plotly)
10561 ("r-reshape2" ,r-reshape2)
10562 ("r-s4vectors" ,r-s4vectors)
10563 ("r-shiny" ,r-shiny)
10564 ("r-snpstats" ,r-snpstats)
10565 ("r-summarizedexperiment" ,r-summarizedexperiment)
10566 ("r-variantannotation" ,r-variantannotation)))
10568 `(("r-knitr" ,r-knitr)))
10569 (home-page "https://bioconductor.org/packages/gQTLstats")
10570 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10572 "This package provides tools for the computationally efficient analysis
10573 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10574 The software in this package aims to support refinements and functional
10575 interpretation of members of a collection of association statistics on a
10576 family of feature/genome hypotheses.")
10577 (license license:artistic2.0)))
10579 (define-public r-gviz
10586 (uri (bioconductor-uri "Gviz" version))
10589 "0cgkp0ciyy2qykqgh3vzp5mx9b4vsvacjh2jnsj3wldiapzlz08a"))))
10590 (properties `((upstream-name . "Gviz")))
10591 (build-system r-build-system)
10593 `(("r-annotationdbi" ,r-annotationdbi)
10594 ("r-biobase" ,r-biobase)
10595 ("r-biocgenerics" ,r-biocgenerics)
10596 ("r-biomart" ,r-biomart)
10597 ("r-biostrings" ,r-biostrings)
10598 ("r-biovizbase" ,r-biovizbase)
10599 ("r-bsgenome" ,r-bsgenome)
10600 ("r-digest" ,r-digest)
10601 ("r-ensembldb" ,r-ensembldb)
10602 ("r-genomeinfodb" ,r-genomeinfodb)
10603 ("r-genomicalignments" ,r-genomicalignments)
10604 ("r-genomicfeatures" ,r-genomicfeatures)
10605 ("r-genomicranges" ,r-genomicranges)
10606 ("r-iranges" ,r-iranges)
10607 ("r-lattice" ,r-lattice)
10608 ("r-latticeextra" ,r-latticeextra)
10609 ("r-matrixstats" ,r-matrixstats)
10610 ("r-rcolorbrewer" ,r-rcolorbrewer)
10611 ("r-rsamtools" ,r-rsamtools)
10612 ("r-rtracklayer" ,r-rtracklayer)
10613 ("r-s4vectors" ,r-s4vectors)
10614 ("r-xvector" ,r-xvector)))
10616 `(("r-knitr" ,r-knitr)))
10617 (home-page "https://bioconductor.org/packages/Gviz")
10618 (synopsis "Plotting data and annotation information along genomic coordinates")
10620 "Genomic data analyses requires integrated visualization of known genomic
10621 information and new experimental data. Gviz uses the biomaRt and the
10622 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10623 and translates this to e.g. gene/transcript structures in viewports of the
10624 grid graphics package. This results in genomic information plotted together
10626 (license license:artistic2.0)))
10628 (define-public r-gwascat
10635 (uri (bioconductor-uri "gwascat" version))
10638 "1cq5cmdrf0a0arr841yvkh6d8drc15p7mif1afr215l1s3y2dwd4"))))
10639 (build-system r-build-system)
10641 `(("r-annotationdbi" ,r-annotationdbi)
10642 ("r-biocgenerics" ,r-biocgenerics)
10643 ("r-biostrings" ,r-biostrings)
10644 ("r-genomeinfodb" ,r-genomeinfodb)
10645 ("r-genomicfeatures" ,r-genomicfeatures)
10646 ("r-genomicranges" ,r-genomicranges)
10647 ("r-ggplot2" ,r-ggplot2)
10648 ("r-iranges" ,r-iranges)
10649 ("r-rsamtools" ,r-rsamtools)
10650 ("r-rtracklayer" ,r-rtracklayer)
10651 ("r-s4vectors" ,r-s4vectors)))
10653 `(("r-knitr" ,r-knitr)))
10654 (home-page "https://bioconductor.org/packages/gwascat")
10655 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10657 "This package provides tools for representing and modeling data in the
10658 EMBL-EBI GWAS catalog.")
10659 (license license:artistic2.0)))
10661 (define-public r-sushi
10667 (uri (bioconductor-uri "Sushi" version))
10670 "17j3d5qjq5nbv99by5mq8rwr0jgh2jyyfn2nwxmwgzlmk3lgi1rb"))))
10671 (properties `((upstream-name . "Sushi")))
10672 (build-system r-build-system)
10674 `(("r-biomart" ,r-biomart)
10676 (home-page "https://bioconductor.org/packages/Sushi")
10677 (synopsis "Tools for visualizing genomics data")
10679 "This package provides flexible, quantitative, and integrative genomic
10680 visualizations for publication-quality multi-panel figures.")
10681 (license license:gpl2+)))
10683 (define-public r-dropbead
10684 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
10687 (name "r-dropbead")
10688 (version (string-append "0-" revision "." (string-take commit 7)))
10692 (uri (git-reference
10693 (url "https://github.com/rajewsky-lab/dropbead")
10695 (file-name (git-file-name name version))
10698 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
10699 (build-system r-build-system)
10701 `(("r-ggplot2" ,r-ggplot2)
10702 ("r-rcolorbrewer" ,r-rcolorbrewer)
10703 ("r-gridextra" ,r-gridextra)
10704 ("r-gplots" ,r-gplots)
10705 ("r-plyr" ,r-plyr)))
10706 (home-page "https://github.com/rajewsky-lab/dropbead")
10707 (synopsis "Basic exploration and analysis of Drop-seq data")
10708 (description "This package offers a quick and straight-forward way to
10709 explore and perform basic analysis of single cell sequencing data coming from
10710 droplet sequencing. It has been particularly tailored for Drop-seq.")
10711 (license license:gpl3))))
10713 (define htslib-for-sambamba
10714 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
10717 (name "htslib-for-sambamba")
10718 (version (string-append "1.3.1-1." (string-take commit 9)))
10722 (uri (git-reference
10723 (url "https://github.com/lomereiter/htslib")
10725 (file-name (string-append "htslib-" version "-checkout"))
10728 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
10730 `(("autoconf" ,autoconf)
10731 ("automake" ,automake)
10732 ,@(package-native-inputs htslib))))))
10734 (define-public sambamba
10741 (uri (git-reference
10742 (url "https://github.com/lomereiter/sambamba")
10743 (commit (string-append "v" version))))
10744 (file-name (string-append name "-" version "-checkout"))
10747 "111h05b60pj8dxbidiamy4imc92x2962b3lmb7wgysl6lx064qis"))))
10748 (build-system gnu-build-system)
10750 `(#:tests? #f ; there is no test target
10751 #:parallel-build? #f ; not supported
10753 (modify-phases %standard-phases
10754 (delete 'configure)
10755 (add-after 'unpack 'fix-ldc-version
10757 (substitute* "gen_ldc_version_info.py"
10758 (("/usr/bin/env.*") (which "python3")))
10759 (substitute* "Makefile"
10760 ;; We use ldc2 instead of ldmd2 to compile sambamba.
10761 (("\\$\\(shell which ldmd2\\)") (which "ldc2")))
10763 (add-after 'unpack 'place-biod-and-undead
10764 (lambda* (#:key inputs #:allow-other-keys)
10765 (copy-recursively (assoc-ref inputs "biod") "BioD")
10767 (add-after 'unpack 'unbundle-prerequisites
10769 (substitute* "Makefile"
10770 (("htslib/libhts.a lz4/lib/liblz4.a")
10772 ((" lz4-static htslib-static") ""))
10775 (lambda* (#:key outputs #:allow-other-keys)
10776 (let* ((out (assoc-ref outputs "out"))
10777 (bin (string-append out "/bin")))
10779 (copy-file (string-append "bin/sambamba-" ,version)
10780 (string-append bin "/sambamba"))
10787 ,(let ((commit "7969eb0a847b05874e83ffddead26e193ece8101"))
10790 (uri (git-reference
10791 (url "https://github.com/biod/BioD")
10793 (file-name (string-append "biod-"
10794 (string-take commit 9)
10798 "0mjxsmbmv0jxl3pq21p8j5r829d648if8q58ka50b2956lc6qkpm")))))))
10801 ("htslib" ,htslib-for-sambamba)))
10802 (home-page "https://lomereiter.github.io/sambamba/")
10803 (synopsis "Tools for working with SAM/BAM data")
10804 (description "Sambamba is a high performance modern robust and
10805 fast tool (and library), written in the D programming language, for
10806 working with SAM and BAM files. Current parallelised functionality is
10807 an important subset of samtools functionality, including view, index,
10808 sort, markdup, and depth.")
10809 (license license:gpl2+)))
10811 (define-public ritornello
10813 (name "ritornello")
10817 (uri (git-reference
10818 (url "https://github.com/KlugerLab/Ritornello")
10819 (commit (string-append "v" version))))
10820 (file-name (git-file-name name version))
10823 "1xahvq215qld7x1w8vpa5zbrsj6p9crb9shqa2x89sb0aaxa02jk"))))
10824 (build-system gnu-build-system)
10826 `(#:tests? #f ; there are no tests
10828 (modify-phases %standard-phases
10829 (add-after 'unpack 'patch-samtools-references
10830 (lambda* (#:key inputs #:allow-other-keys)
10831 (substitute* '("src/SamStream.h"
10833 (("<sam.h>") "<samtools/sam.h>"))
10835 (delete 'configure)
10837 (lambda* (#:key inputs outputs #:allow-other-keys)
10838 (let* ((out (assoc-ref outputs "out"))
10839 (bin (string-append out "/bin/")))
10841 (install-file "bin/Ritornello" bin)
10844 `(("samtools" ,samtools-0.1)
10848 (home-page "https://github.com/KlugerLab/Ritornello")
10849 (synopsis "Control-free peak caller for ChIP-seq data")
10850 (description "Ritornello is a ChIP-seq peak calling algorithm based on
10851 signal processing that can accurately call binding events without the need to
10852 do a pair total DNA input or IgG control sample. It has been tested for use
10853 with narrow binding events such as transcription factor ChIP-seq.")
10854 (license license:gpl3+)))
10856 (define-public trim-galore
10858 (name "trim-galore")
10863 (uri (git-reference
10864 (url "https://github.com/FelixKrueger/TrimGalore")
10866 (file-name (git-file-name name version))
10869 "1y31wbxwkm9xqzr5zv1pk5q418whnmlmgmfyxxpnl12h83m2i9iv"))))
10870 (build-system gnu-build-system)
10872 `(#:tests? #f ; no tests
10874 (modify-phases %standard-phases
10875 (replace 'configure
10877 ;; Trim Galore tries to figure out what version of Python
10878 ;; cutadapt is using by looking at the shebang. Of course that
10879 ;; doesn't work, because cutadapt is wrapped in a shell script.
10880 (substitute* "trim_galore"
10881 (("my \\$python_return.*")
10882 "my $python_return = \"Python 3.999\";\n"))
10885 (add-after 'unpack 'hardcode-tool-references
10886 (lambda* (#:key inputs #:allow-other-keys)
10887 (substitute* "trim_galore"
10888 (("\\$path_to_cutadapt = 'cutadapt'")
10889 (string-append "$path_to_cutadapt = '"
10890 (assoc-ref inputs "cutadapt")
10892 (("\\$compression_path = \"gzip\"")
10893 (string-append "$compression_path = \""
10894 (assoc-ref inputs "gzip")
10897 (string-append "\""
10898 (assoc-ref inputs "gzip")
10901 (string-append "\""
10902 (assoc-ref inputs "pigz")
10906 (lambda* (#:key outputs #:allow-other-keys)
10907 (let ((bin (string-append (assoc-ref outputs "out")
10910 (install-file "trim_galore" bin)
10916 ("cutadapt" ,cutadapt)))
10918 `(("unzip" ,unzip)))
10919 (home-page "https://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
10920 (synopsis "Wrapper around Cutadapt and FastQC")
10921 (description "Trim Galore! is a wrapper script to automate quality and
10922 adapter trimming as well as quality control, with some added functionality to
10923 remove biased methylation positions for RRBS sequence files.")
10924 (license license:gpl3+)))
10926 (define-public gess
10932 (uri (string-append "http://compbio.uthscsa.edu/"
10934 "gess-" version ".src.tar.gz"))
10937 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
10938 (build-system gnu-build-system)
10940 `(#:tests? #f ; no tests
10942 (modify-phases %standard-phases
10943 (delete 'configure)
10946 (lambda* (#:key inputs outputs #:allow-other-keys)
10947 (let* ((python (assoc-ref inputs "python"))
10948 (out (assoc-ref outputs "out"))
10949 (bin (string-append out "/bin/"))
10950 (target (string-append
10952 ,(version-major+minor
10953 (package-version python))
10954 "/site-packages/gess/")))
10956 (copy-recursively "." target)
10957 ;; Make GESS.py executable
10958 (chmod (string-append target "GESS.py") #o555)
10959 ;; Add Python shebang to the top and make Matplotlib
10961 (substitute* (string-append target "GESS.py")
10962 (("\"\"\"Description:" line)
10963 (string-append "#!" (which "python") "
10965 matplotlib.use('Agg')
10967 ;; Make sure GESS has all modules in its path
10968 (wrap-script (string-append target "GESS.py")
10969 `("PYTHONPATH" ":" = (,target ,(getenv "PYTHONPATH"))))
10971 (symlink (string-append target "GESS.py")
10972 (string-append bin "GESS.py"))
10975 `(("python" ,python-2)
10976 ("python2-pysam" ,python2-pysam)
10977 ("python2-scipy" ,python2-scipy)
10978 ("python2-numpy" ,python2-numpy)
10979 ("python2-networkx" ,python2-networkx)
10980 ("python2-biopython" ,python2-biopython)
10981 ("guile" ,guile-3.0))) ; for the script wrapper
10982 (home-page "https://compbio.uthscsa.edu/GESS_Web/")
10983 (synopsis "Detect exon-skipping events from raw RNA-seq data")
10985 "GESS is an implementation of a novel computational method to detect de
10986 novo exon-skipping events directly from raw RNA-seq data without the prior
10987 knowledge of gene annotation information. GESS stands for the graph-based
10988 exon-skipping scanner detection scheme.")
10989 (license license:bsd-3)))
10991 (define-public phylip
10998 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
10999 "download/phylip-" version ".tar.gz"))
11002 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11003 (build-system gnu-build-system)
11005 `(#:tests? #f ; no check target
11006 #:make-flags (list "-f" "Makefile.unx" "install")
11007 #:parallel-build? #f ; not supported
11009 (modify-phases %standard-phases
11010 (add-after 'unpack 'enter-dir
11011 (lambda _ (chdir "src") #t))
11012 (delete 'configure)
11014 (lambda* (#:key inputs outputs #:allow-other-keys)
11015 (let ((target (string-append (assoc-ref outputs "out")
11018 (for-each (lambda (file)
11019 (install-file file target))
11020 (find-files "../exe" ".*")))
11022 (home-page "http://evolution.genetics.washington.edu/phylip/")
11023 (synopsis "Tools for inferring phylogenies")
11024 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11025 programs for inferring phylogenies (evolutionary trees).")
11026 (license license:bsd-2)))
11035 (uri (string-append "https://integrativemodeling.org/"
11036 version "/download/imp-" version ".tar.gz"))
11039 "1z1vcpwbylixk0zywngg5iw0jv083jj1bqphi817jpg3fb9fx2jj"))))
11040 (build-system cmake-build-system)
11042 `(;; FIXME: Some tests fail because they produce warnings, others fail
11043 ;; because the PYTHONPATH does not include the modeller's directory.
11052 ("python" ,python-2)))
11054 `(("python2-numpy" ,python2-numpy)
11055 ("python2-scipy" ,python2-scipy)
11056 ("python2-pandas" ,python2-pandas)
11057 ("python2-scikit-learn" ,python2-scikit-learn)
11058 ("python2-networkx" ,python2-networkx)))
11059 (home-page "https://integrativemodeling.org")
11060 (synopsis "Integrative modeling platform")
11061 (description "IMP's broad goal is to contribute to a comprehensive
11062 structural characterization of biomolecules ranging in size and complexity
11063 from small peptides to large macromolecular assemblies, by integrating data
11064 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11065 Python toolbox for solving complex modeling problems, and a number of
11066 applications for tackling some common problems in a user-friendly way.")
11067 ;; IMP is largely available under the GNU Lesser GPL; see the file
11068 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11069 ;; available under the GNU GPL (see the file COPYING.GPL).
11070 (license (list license:lgpl2.1+
11073 (define-public tadbit
11079 (uri (git-reference
11080 (url "https://github.com/3DGenomes/TADbit")
11081 (commit (string-append "v" version))))
11082 (file-name (git-file-name name version))
11085 "07g3aj648prmsvxp9caz5yl41k0y0647vxh0f5p3w8376mfiljd0"))))
11086 (build-system python-build-system)
11088 `(;; Tests are included and must be run after installation, but
11089 ;; they are incomplete and thus cannot be run.
11093 (modify-phases %standard-phases
11094 (add-after 'unpack 'fix-problems-with-setup.py
11095 (lambda* (#:key outputs #:allow-other-keys)
11096 ;; setup.py opens these files for writing
11097 (chmod "_pytadbit/_version.py" #o664)
11098 (chmod "README.rst" #o664)
11100 ;; Don't attempt to install the bash completions to
11101 ;; the home directory.
11102 (rename-file "extras/.bash_completion"
11104 (substitute* "setup.py"
11105 (("\\(path.expanduser\\('~'\\)")
11106 (string-append "(\""
11107 (assoc-ref outputs "out")
11108 "/etc/bash_completion.d\""))
11109 (("extras/\\.bash_completion")
11113 ;; TODO: add Chimera for visualization
11116 ("python2-scipy" ,python2-scipy)
11117 ("python2-numpy" ,python2-numpy)
11118 ("python2-matplotlib" ,python2-matplotlib)
11119 ("python2-pysam" ,python2-pysam)))
11120 (home-page "https://3dgenomes.github.io/TADbit/")
11121 (synopsis "Analyze, model, and explore 3C-based data")
11123 "TADbit is a complete Python library to deal with all steps to analyze,
11124 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11125 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11126 correct interaction matrices, identify and compare the so-called
11127 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11128 interaction matrices, and finally, extract structural properties from the
11129 models. TADbit is complemented by TADkit for visualizing 3D models.")
11130 (license license:gpl3+)))
11132 (define-public kentutils
11135 ;; 302.1.0 is out, but the only difference is the inclusion of
11136 ;; pre-built binaries.
11137 (version "302.0.0")
11141 (uri (git-reference
11142 (url "https://github.com/ENCODE-DCC/kentUtils")
11143 (commit (string-append "v" version))))
11144 (file-name (git-file-name name version))
11147 "0n1wbyjpzii2b9qhyp9r1q76j623cggpg3y8fmw78ld3z4y7ivha"))
11148 (modules '((guix build utils)
11153 ;; Only the contents of the specified directories are free
11154 ;; for all uses, so we remove the rest. "hg/autoSql" and
11155 ;; "hg/autoXml" are nominally free, but they depend on a
11156 ;; library that is built from the sources in "hg/lib",
11157 ;; which is nonfree.
11158 (let ((free (list "." ".."
11159 "utils" "lib" "inc" "tagStorm"
11160 "parasol" "htslib"))
11161 (directory? (lambda (file)
11162 (eq? 'directory (stat:type (stat file))))))
11163 (for-each (lambda (file)
11164 (and (directory? file)
11165 (delete-file-recursively file)))
11166 (map (cut string-append "src/" <>)
11169 (not (member file free)))))))
11170 ;; Only make the utils target, not the userApps target,
11171 ;; because that requires libraries we won't build.
11172 (substitute* "Makefile"
11173 ((" userApps") " utils"))
11174 ;; Only build libraries that are free.
11175 (substitute* "src/makefile"
11176 (("DIRS =.*") "DIRS =\n")
11177 (("cd jkOwnLib.*") "")
11180 (substitute* "src/utils/makefile"
11181 ;; These tools depend on "jkhgap.a", which is part of the
11182 ;; nonfree "src/hg/lib" directory.
11183 (("raSqlQuery") "")
11184 (("pslLiftSubrangeBlat") "")
11186 ;; Do not build UCSC tools, which may require nonfree
11188 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11190 (build-system gnu-build-system)
11192 `( ;; There is no global test target and the test target for
11193 ;; individual tools depends on input files that are not
11197 (modify-phases %standard-phases
11198 (add-after 'unpack 'fix-permissions
11199 (lambda _ (make-file-writable "src/inc/localEnvironment.mk") #t))
11200 (add-after 'unpack 'fix-paths
11202 (substitute* "Makefile"
11203 (("/bin/echo") (which "echo")))
11205 (add-after 'unpack 'prepare-samtabix
11206 (lambda* (#:key inputs #:allow-other-keys)
11207 (copy-recursively (assoc-ref inputs "samtabix")
11210 (delete 'configure)
11212 (lambda* (#:key outputs #:allow-other-keys)
11213 (let ((bin (string-append (assoc-ref outputs "out")
11215 (copy-recursively "bin" bin))
11221 (uri (git-reference
11222 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11223 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11226 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11232 ("mariadb" ,mariadb "lib")
11233 ("mariadb-dev" ,mariadb "dev")
11234 ("openssl" ,openssl-1.0)))
11235 (home-page "https://genome.cse.ucsc.edu/index.html")
11236 (synopsis "Assorted bioinformatics utilities")
11237 (description "This package provides the kentUtils, a selection of
11238 bioinformatics utilities used in combination with the UCSC genome
11240 ;; Only a subset of the sources are released under a non-copyleft
11241 ;; free software license. All other sources are removed in a
11242 ;; snippet. See this bug report for an explanation of how the
11243 ;; license statements apply:
11244 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11245 (license (license:non-copyleft
11246 "http://genome.ucsc.edu/license/"
11247 "The contents of this package are free for all uses."))))
11249 (define-public f-seq
11250 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11254 (version (string-append "1.1-" revision "." (string-take commit 7)))
11257 (uri (git-reference
11258 (url "https://github.com/aboyle/F-seq")
11260 (file-name (string-append name "-" version))
11263 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11264 (modules '((guix build utils)))
11265 ;; Remove bundled Java library archives.
11268 (for-each delete-file (find-files "lib" ".*"))
11270 (build-system ant-build-system)
11272 `(#:tests? #f ; no tests included
11274 (modify-phases %standard-phases
11276 (lambda* (#:key inputs outputs #:allow-other-keys)
11277 (let* ((target (assoc-ref outputs "out"))
11278 (bin (string-append target "/bin"))
11279 (doc (string-append target "/share/doc/f-seq"))
11280 (lib (string-append target "/lib")))
11283 (substitute* "bin/linux/fseq"
11284 (("java") (which "java"))
11285 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11286 (string-append (assoc-ref inputs "java-commons-cli")
11287 "/share/java/commons-cli.jar"))
11289 (string-append "REALDIR=" bin "\n")))
11290 (install-file "README.txt" doc)
11291 (install-file "bin/linux/fseq" bin)
11292 (install-file "build~/fseq.jar" lib)
11293 (copy-recursively "lib" lib)
11297 ("java-commons-cli" ,java-commons-cli)))
11298 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11299 (synopsis "Feature density estimator for high-throughput sequence tags")
11301 "F-Seq is a software package that generates a continuous tag sequence
11302 density estimation allowing identification of biologically meaningful sites
11303 such as transcription factor binding sites (ChIP-seq) or regions of open
11304 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11306 (license license:gpl3+))))
11308 (define-public bismark
11315 (uri (git-reference
11316 (url "https://github.com/FelixKrueger/Bismark")
11318 (file-name (string-append name "-" version "-checkout"))
11321 "0xchm3rgilj6vfjnyzfzzymfd7djr64sbrmrvs3njbwi66jqbzw9"))))
11322 (build-system perl-build-system)
11324 `(#:tests? #f ; there are no tests
11325 #:modules ((guix build utils)
11328 (guix build perl-build-system))
11330 (modify-phases %standard-phases
11331 ;; The bundled plotly.js is minified.
11332 (add-after 'unpack 'replace-plotly.js
11333 (lambda* (#:key inputs #:allow-other-keys)
11334 (let* ((file (assoc-ref inputs "plotly.js"))
11335 (installed "plotly/plotly.js"))
11336 (let ((minified (open-pipe* OPEN_READ "uglify-js" file)))
11337 (call-with-output-file installed
11338 (cut dump-port minified <>))))
11340 (delete 'configure)
11343 (lambda* (#:key inputs outputs #:allow-other-keys)
11344 (let* ((out (assoc-ref outputs "out"))
11345 (bin (string-append out "/bin"))
11346 (share (string-append out "/share/bismark"))
11347 (docdir (string-append out "/share/doc/bismark"))
11348 (docs '("Docs/Bismark_User_Guide.html"))
11349 (scripts '("bismark"
11350 "bismark_genome_preparation"
11351 "bismark_methylation_extractor"
11354 "coverage2cytosine"
11355 "deduplicate_bismark"
11356 "filter_non_conversion"
11359 "NOMe_filtering")))
11360 (substitute* "bismark2report"
11361 (("\\$RealBin/plotly")
11362 (string-append share "/plotly")))
11366 (for-each (lambda (file) (install-file file bin))
11368 (for-each (lambda (file) (install-file file docdir))
11370 (copy-recursively "Docs/Images" (string-append docdir "/Images"))
11371 (copy-recursively "plotly"
11372 (string-append share "/plotly"))
11374 ;; Fix references to gunzip
11375 (substitute* (map (lambda (file)
11376 (string-append bin "/" file))
11379 (string-append "\"" (assoc-ref inputs "gzip")
11380 "/bin/gunzip -c")))
11384 ("perl-carp" ,perl-carp)
11385 ("perl-getopt-long" ,perl-getopt-long)))
11390 (uri (string-append "https://raw.githubusercontent.com/plotly/plotly.js/"
11391 "v1.39.4/dist/plotly.js"))
11393 (base32 "138mwsr4nf5qif4mrxx286mpnagxd1xwl6k8aidrjgknaqg88zyr"))))
11394 ("uglify-js" ,uglify-js)))
11395 (home-page "https://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11396 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11397 (description "Bismark is a program to map bisulfite treated sequencing
11398 reads to a genome of interest and perform methylation calls in a single step.
11399 The output can be easily imported into a genome viewer, such as SeqMonk, and
11400 enables a researcher to analyse the methylation levels of their samples
11401 straight away. Its main features are:
11404 @item Bisulfite mapping and methylation calling in one single step
11405 @item Supports single-end and paired-end read alignments
11406 @item Supports ungapped and gapped alignments
11407 @item Alignment seed length, number of mismatches etc are adjustable
11408 @item Output discriminates between cytosine methylation in CpG, CHG
11411 (license license:gpl3+)))
11413 (define-public paml
11419 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11420 "paml" version ".tgz"))
11423 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11424 (modules '((guix build utils)))
11425 ;; Remove Windows binaries
11428 (for-each delete-file (find-files "." "\\.exe$"))
11429 ;; Some files in the original tarball have restrictive
11430 ;; permissions, which makes repackaging fail
11431 (for-each (lambda (file) (chmod file #o644)) (find-files "."))
11433 (build-system gnu-build-system)
11435 `(#:tests? #f ; there are no tests
11436 #:make-flags '("CC=gcc")
11438 (modify-phases %standard-phases
11439 (replace 'configure
11441 (substitute* "src/BFdriver.c"
11442 (("/bin/bash") (which "bash")))
11446 (lambda* (#:key outputs #:allow-other-keys)
11447 (let ((tools '("baseml" "basemlg" "codeml"
11448 "pamp" "evolver" "yn00" "chi2"))
11449 (bin (string-append (assoc-ref outputs "out") "/bin"))
11450 (docdir (string-append (assoc-ref outputs "out")
11451 "/share/doc/paml")))
11453 (for-each (lambda (file) (install-file file bin)) tools)
11454 (copy-recursively "../doc" docdir)
11456 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11457 (synopsis "Phylogentic analysis by maximum likelihood")
11458 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11459 contains a few programs for model fitting and phylogenetic tree reconstruction
11460 using nucleotide or amino-acid sequence data.")
11462 (license license:gpl3)))
11464 (define-public kallisto
11470 (uri (git-reference
11471 (url "https://github.com/pachterlab/kallisto")
11472 (commit (string-append "v" version))))
11473 (file-name (git-file-name name version))
11476 "0nj382jiywqnpgvyhichajpkkh5r0bapn43f4dx40zdaq5v4m40m"))))
11477 (build-system cmake-build-system)
11479 `(#:tests? #f ; no "check" target
11481 (modify-phases %standard-phases
11482 (add-after 'unpack 'do-not-use-bundled-htslib
11484 (substitute* "CMakeLists.txt"
11485 (("^ExternalProject_Add" m)
11486 (string-append "if (NEVER)\n" m))
11488 (string-append ")\nendif(NEVER)"))
11489 (("include_directories\\(\\$\\{htslib_PREFIX.*" m)
11490 (string-append "# " m)))
11491 (substitute* "src/CMakeLists.txt"
11492 (("target_link_libraries\\(kallisto kallisto_core pthread \
11493 \\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/../ext/htslib/libhts.a\\)")
11494 "target_link_libraries(kallisto kallisto_core pthread hts)")
11495 (("include_directories\\(\\.\\./ext/htslib\\)") ""))
11501 (home-page "https://pachterlab.github.io/kallisto/")
11502 (synopsis "Near-optimal RNA-Seq quantification")
11504 "Kallisto is a program for quantifying abundances of transcripts from
11505 RNA-Seq data, or more generally of target sequences using high-throughput
11506 sequencing reads. It is based on the novel idea of pseudoalignment for
11507 rapidly determining the compatibility of reads with targets, without the need
11508 for alignment. Pseudoalignment of reads preserves the key information needed
11509 for quantification, and kallisto is therefore not only fast, but also as
11510 accurate as existing quantification tools.")
11511 (license license:bsd-2)))
11513 (define-public libgff
11519 (uri (git-reference
11520 (url "https://github.com/Kingsford-Group/libgff")
11521 (commit (string-append "v" version))))
11522 (file-name (git-file-name name version))
11525 "0n6vfjnq7a2mianipscbshrvbncss8z4zkgkbjw754p9043nfkps"))))
11526 (build-system cmake-build-system)
11527 (arguments `(#:tests? #f)) ; no tests included
11528 (home-page "https://github.com/Kingsford-Group/libgff")
11529 (synopsis "Parser library for reading/writing GFF files")
11530 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11531 code that is used in the Cufflinks codebase. The goal of this library is to
11532 provide this functionality without the necessity of drawing in a heavy-weight
11533 dependency like SeqAn.")
11534 (license (license:x11-style "https://www.boost.org/LICENSE_1_0.txt"))))
11536 (define-public sailfish
11542 (uri (git-reference
11543 (url "https://github.com/kingsfordgroup/sailfish")
11544 (commit (string-append "v" version))))
11545 (file-name (git-file-name name version))
11548 "1amcc5hqvsl42hg4x19bi9vy47cl874s0lw1fmi0hwsdk9i8c03v"))
11549 (modules '((guix build utils)))
11552 ;; Delete bundled headers for eigen3.
11553 (delete-file-recursively "include/eigen3/")
11555 (build-system cmake-build-system)
11557 `(#:configure-flags
11558 (list (string-append "-DBOOST_INCLUDEDIR="
11559 (assoc-ref %build-inputs "boost")
11561 (string-append "-DBOOST_LIBRARYDIR="
11562 (assoc-ref %build-inputs "boost")
11564 (string-append "-DBoost_LIBRARIES="
11565 "-lboost_iostreams "
11566 "-lboost_filesystem "
11571 "-lboost_program_options")
11572 "-DBoost_FOUND=TRUE"
11573 ;; Don't download RapMap---we already have it!
11574 "-DFETCHED_RAPMAP=1")
11575 ;; Tests must be run after installation and the location of the test
11576 ;; data file must be overridden. But the tests fail. It looks like
11577 ;; they are not really meant to be run.
11580 (modify-phases %standard-phases
11581 ;; Boost cannot be found, even though it's right there.
11582 (add-after 'unpack 'do-not-look-for-boost
11583 (lambda* (#:key inputs #:allow-other-keys)
11584 (substitute* "CMakeLists.txt"
11585 (("find_package\\(Boost 1\\.53\\.0") "#"))
11587 (add-after 'unpack 'do-not-assign-to-macro
11589 (substitute* "include/spdlog/details/format.cc"
11590 (("const unsigned CHAR_WIDTH = 1;") ""))
11592 (add-after 'unpack 'prepare-rapmap
11593 (lambda* (#:key inputs #:allow-other-keys)
11594 (let ((src "external/install/src/rapmap/")
11595 (include "external/install/include/rapmap/")
11596 (rapmap (assoc-ref inputs "rapmap")))
11597 (mkdir-p "/tmp/rapmap")
11599 (assoc-ref inputs "rapmap")
11601 "--strip-components=1")
11604 (for-each (lambda (file)
11605 (install-file file src))
11606 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
11607 (copy-recursively "/tmp/rapmap/include" include))
11609 (add-after 'unpack 'use-system-libraries
11610 (lambda* (#:key inputs #:allow-other-keys)
11611 (substitute* '("src/SailfishIndexer.cpp"
11612 "src/SailfishUtils.cpp"
11613 "src/SailfishQuantify.cpp"
11614 "src/FASTAParser.cpp"
11616 "include/SailfishUtils.hpp"
11617 "include/SailfishIndex.hpp"
11618 "include/CollapsedEMOptimizer.hpp"
11619 "src/CollapsedEMOptimizer.cpp")
11620 (("#include \"jellyfish/config.h\"") ""))
11621 (substitute* "src/CMakeLists.txt"
11622 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11623 (string-append (assoc-ref inputs "jellyfish")
11624 "/include/jellyfish-" ,(package-version jellyfish)))
11625 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11626 (string-append (assoc-ref inputs "jellyfish")
11627 "/lib/libjellyfish-2.0.a"))
11628 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11629 (string-append (assoc-ref inputs "libdivsufsort")
11630 "/lib/libdivsufsort.so"))
11631 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11632 (string-append (assoc-ref inputs "libdivsufsort")
11633 "/lib/libdivsufsort64.so")))
11634 (substitute* "CMakeLists.txt"
11635 ;; Don't prefer static libs
11636 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11637 (("find_package\\(Jellyfish.*") "")
11638 (("ExternalProject_Add\\(libjellyfish") "message(")
11639 (("ExternalProject_Add\\(libgff") "message(")
11640 (("ExternalProject_Add\\(libsparsehash") "message(")
11641 (("ExternalProject_Add\\(libdivsufsort") "message("))
11643 ;; Ensure that Eigen headers can be found
11644 (setenv "CPLUS_INCLUDE_PATH"
11645 (string-append (assoc-ref inputs "eigen")
11647 (or (getenv "CPLUS_INCLUDE_PATH") "")))
11652 ("jemalloc" ,jemalloc)
11653 ("jellyfish" ,jellyfish)
11654 ("sparsehash" ,sparsehash)
11657 (uri (git-reference
11658 (url "https://github.com/COMBINE-lab/RapMap")
11659 (commit (string-append "sf-v" version))))
11660 (file-name (string-append "rapmap-sf-v" version "-checkout"))
11663 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
11664 (modules '((guix build utils)))
11665 ;; These files are expected to be excluded.
11667 '(begin (delete-file-recursively "include/spdlog")
11668 (for-each delete-file '("include/xxhash.h"
11671 ("libdivsufsort" ,libdivsufsort)
11676 `(("pkg-config" ,pkg-config)))
11677 (home-page "https://www.cs.cmu.edu/~ckingsf/software/sailfish/")
11678 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
11679 (description "Sailfish is a tool for genomic transcript quantification
11680 from RNA-seq data. It requires a set of target transcripts (either from a
11681 reference or de-novo assembly) to quantify. All you need to run sailfish is a
11682 fasta file containing your reference transcripts and a (set of) fasta/fastq
11683 file(s) containing your reads.")
11684 (license license:gpl3+)))
11686 (define libstadenio-for-salmon
11688 (name "libstadenio")
11692 (uri (git-reference
11693 (url "https://github.com/COMBINE-lab/staden-io_lib")
11694 (commit (string-append "v" version))))
11695 (file-name (string-append name "-" version "-checkout"))
11698 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
11699 (build-system gnu-build-system)
11700 (arguments '(#:parallel-tests? #f)) ; not supported
11704 `(("perl" ,perl))) ; for tests
11705 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
11706 (synopsis "General purpose trace and experiment file library")
11707 (description "This package provides a library of file reading and writing
11708 code to provide a general purpose Trace file (and Experiment File) reading
11711 The following file formats are supported:
11714 @item SCF trace files
11715 @item ABI trace files
11716 @item ALF trace files
11717 @item ZTR trace files
11718 @item SFF trace archives
11719 @item SRF trace archives
11720 @item Experiment files
11721 @item Plain text files
11722 @item SAM/BAM sequence files
11723 @item CRAM sequence files
11725 (license license:bsd-3)))
11727 (define-public salmon
11733 (uri (git-reference
11734 (url "https://github.com/COMBINE-lab/salmon")
11735 (commit (string-append "v" version))))
11736 (file-name (git-file-name name version))
11739 "1i2z4aivicmiixdz9bxalp7vmfzi3k92fxa63iqa8kgvfw5a4aq5"))
11740 (modules '((guix build utils)))
11743 ;; Delete bundled headers for eigen3.
11744 (delete-file-recursively "include/eigen3/")
11746 (build-system cmake-build-system)
11748 `(#:configure-flags
11749 (list (string-append "-DBOOST_INCLUDEDIR="
11750 (assoc-ref %build-inputs "boost")
11752 (string-append "-DBOOST_LIBRARYDIR="
11753 (assoc-ref %build-inputs "boost")
11755 (string-append "-DBoost_LIBRARIES="
11756 "-lboost_iostreams "
11757 "-lboost_filesystem "
11762 "-lboost_program_options")
11763 "-DBoost_FOUND=TRUE"
11764 "-DTBB_LIBRARIES=tbb tbbmalloc"
11765 ;; Don't download RapMap---we already have it!
11766 "-DFETCHED_RAPMAP=1")
11768 (modify-phases %standard-phases
11769 ;; Boost cannot be found, even though it's right there.
11770 (add-after 'unpack 'do-not-look-for-boost
11771 (lambda* (#:key inputs #:allow-other-keys)
11772 (substitute* "CMakeLists.txt"
11773 (("find_package\\(Boost 1\\.59\\.0") "#"))
11775 (add-after 'unpack 'do-not-phone-home
11777 (substitute* "src/Salmon.cpp"
11778 (("getVersionMessage\\(\\)") "\"\""))
11780 (add-after 'unpack 'prepare-rapmap
11781 (lambda* (#:key inputs #:allow-other-keys)
11782 (let ((src "external/install/src/rapmap/")
11783 (include "external/install/include/rapmap/")
11784 (rapmap (assoc-ref inputs "rapmap")))
11787 (copy-recursively (string-append rapmap "/src") src)
11788 (copy-recursively (string-append rapmap "/include") include)
11789 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
11790 "external/install/include/rapmap/FastxParser.hpp"
11791 "external/install/include/rapmap/concurrentqueue.h"
11792 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
11793 "external/install/src/rapmap/FastxParser.cpp"
11794 "external/install/src/rapmap/xxhash.c"))
11795 (delete-file-recursively "external/install/include/rapmap/spdlog"))
11797 (add-after 'unpack 'use-system-libraries
11798 (lambda* (#:key inputs #:allow-other-keys)
11799 (substitute* "CMakeLists.txt"
11800 ;; Don't prefer static libs
11801 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11802 (("set\\(TBB_LIBRARIES") "message(")
11803 ;; Don't download anything
11804 (("DOWNLOAD_COMMAND") "DOWNLOAD_COMMAND echo")
11805 (("externalproject_add\\(libcereal") "message(")
11806 (("externalproject_add\\(libgff") "message(")
11807 (("externalproject_add\\(libtbb") "message(")
11808 (("externalproject_add\\(libdivsufsort") "message(")
11809 (("externalproject_add\\(libstadenio") "message(")
11810 (("externalproject_add_step\\(") "message("))
11811 (substitute* "src/CMakeLists.txt"
11812 (("add_dependencies") "#")
11813 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
11814 (string-append (assoc-ref inputs "libstadenio-for-salmon")
11815 "/lib/libstaden-read.so"))
11816 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11817 (string-append (assoc-ref inputs "libdivsufsort")
11818 "/lib/libdivsufsort.so"))
11819 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11820 (string-append (assoc-ref inputs "libdivsufsort")
11821 "/lib/libdivsufsort64.so"))
11822 (("lib/libdivsufsort.a") "/lib/libdivsufsort.so"))
11824 ;; Ensure that all headers can be found
11825 (setenv "CPLUS_INCLUDE_PATH"
11826 (string-append (or (getenv "CPLUS_INCLUDE_PATH") "")
11828 (assoc-ref inputs "eigen")
11829 "/include/eigen3"))
11831 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
11832 ;; run. It only exists after the install phase.
11833 (add-after 'unpack 'fix-tests
11835 (substitute* "src/CMakeLists.txt"
11836 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
11837 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
11846 (uri (git-reference
11847 (url "https://github.com/COMBINE-lab/RapMap")
11848 (commit (string-append "salmon-v" version))))
11849 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
11852 "1biplxf0csc7a8h1wf219b0vmjkvw6wk2zylhdklb577kgmihdms"))))
11853 ("jemalloc" ,jemalloc)
11856 ("libdivsufsort" ,libdivsufsort)
11857 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
11861 `(("pkg-config" ,pkg-config)))
11862 (home-page "https://github.com/COMBINE-lab/salmon")
11863 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
11864 (description "Salmon is a program to produce highly-accurate,
11865 transcript-level quantification estimates from RNA-seq data. Salmon achieves
11866 its accuracy and speed via a number of different innovations, including the
11867 use of lightweight alignments (accurate but fast-to-compute proxies for
11868 traditional read alignments) and massively-parallel stochastic collapsed
11869 variational inference.")
11870 (license license:gpl3+)))
11872 (define-public python-loompy
11874 (name "python-loompy")
11876 ;; The tarball on Pypi does not include the tests.
11879 (uri (git-reference
11880 (url "https://github.com/linnarsson-lab/loompy")
11882 (file-name (git-file-name name version))
11885 "12a5kjgiikapv93wahfw0frszx1lblnppyz3vs5gy8fgmgngra07"))))
11886 (build-system python-build-system)
11889 (modify-phases %standard-phases
11892 (setenv "PYTHONPATH"
11893 (string-append (getcwd) ":"
11894 (getenv "PYTHONPATH")))
11895 (invoke "pytest" "tests")
11898 `(("python-h5py" ,python-h5py)
11899 ("python-numpy" ,python-numpy)
11900 ("python-pandas" ,python-pandas)
11901 ("python-scipy" ,python-scipy)))
11903 `(("python-pytest" ,python-pytest)))
11904 (home-page "https://github.com/linnarsson-lab/loompy")
11905 (synopsis "Work with .loom files for single-cell RNA-seq data")
11906 (description "The loom file format is an efficient format for very large
11907 omics datasets, consisting of a main matrix, optional additional layers, a
11908 variable number of row and column annotations. Loom also supports sparse
11909 graphs. This library makes it easy to work with @file{.loom} files for
11910 single-cell RNA-seq data.")
11911 (license license:bsd-3)))
11913 ;; We cannot use the latest commit because it requires Java 9.
11914 (define-public java-forester
11915 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
11918 (name "java-forester")
11919 (version (string-append "0-" revision "." (string-take commit 7)))
11922 (uri (git-reference
11923 (url "https://github.com/cmzmasek/forester")
11925 (file-name (string-append name "-" version "-checkout"))
11928 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
11929 (modules '((guix build utils)))
11932 ;; Delete bundled jars and pre-built classes
11933 (delete-file-recursively "forester/java/resources")
11934 (delete-file-recursively "forester/java/classes")
11935 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
11936 ;; Delete bundled applications
11937 (delete-file-recursively "forester_applications")
11939 (build-system ant-build-system)
11941 `(#:tests? #f ; there are none
11943 #:modules ((guix build ant-build-system)
11945 (guix build java-utils)
11949 (modify-phases %standard-phases
11950 (add-after 'unpack 'chdir
11951 (lambda _ (chdir "forester/java") #t))
11952 (add-after 'chdir 'fix-dependencies
11954 (chmod "build.xml" #o664)
11955 (call-with-output-file "build.xml.new"
11959 (with-input-from-file "build.xml"
11960 (lambda _ (xml->sxml #:trim-whitespace? #t)))
11961 `(;; Remove all unjar tags to avoid repacking classes.
11962 (unjar . ,(lambda _ '()))
11963 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
11964 (*text* . ,(lambda (_ txt) txt))))
11966 (rename-file "build.xml.new" "build.xml")
11968 ;; FIXME: itext is difficult to package as it depends on a few
11969 ;; unpackaged libraries.
11970 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
11972 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
11973 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
11974 (("pdf_written_to = PdfExporter.*")
11975 "throw new IOException(\"PDF export is not available.\");"))
11977 ;; There is no install target
11978 (replace 'install (install-jars ".")))))
11980 `(("java-commons-codec" ,java-commons-codec)
11981 ("java-openchart2" ,java-openchart2)))
11982 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
11983 (synopsis "Phylogenomics libraries for Java")
11984 (description "Forester is a collection of Java libraries for
11985 phylogenomics and evolutionary biology research. It includes support for
11986 reading, writing, and exporting phylogenetic trees.")
11987 (license license:lgpl2.1+))))
11989 (define-public java-forester-1.005
11991 (name "java-forester")
11995 (uri (string-append "https://repo1.maven.org/maven2/"
11996 "org/biojava/thirdparty/forester/"
11997 version "/forester-" version "-sources.jar"))
11998 (file-name (string-append name "-" version ".jar"))
12001 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12002 (build-system ant-build-system)
12004 `(#:tests? #f ; there are none
12006 #:modules ((guix build ant-build-system)
12008 (guix build java-utils)
12012 (modify-phases %standard-phases
12013 (add-after 'unpack 'fix-dependencies
12014 (lambda* (#:key inputs #:allow-other-keys)
12015 (call-with-output-file "build.xml"
12019 (with-input-from-file "src/build.xml"
12020 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12021 `(;; Remove all unjar tags to avoid repacking classes.
12022 (unjar . ,(lambda _ '()))
12023 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12024 (*text* . ,(lambda (_ txt) txt))))
12026 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12027 "synth_look_and_feel_1.xml")
12028 (copy-file (assoc-ref inputs "phyloxml.xsd")
12030 (substitute* "build.xml"
12031 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12032 "synth_look_and_feel_1.xml")
12033 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12036 ;; FIXME: itext is difficult to package as it depends on a few
12037 ;; unpackaged libraries.
12038 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12040 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12041 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12042 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12043 (("pdf_written_to = PdfExporter.*")
12044 "throw new IOException(\"PDF export is not available.\"); /*")
12045 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12046 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12048 (add-after 'unpack 'delete-pre-built-classes
12049 (lambda _ (delete-file-recursively "src/classes") #t))
12050 ;; There is no install target
12051 (replace 'install (install-jars ".")))))
12053 `(("java-commons-codec" ,java-commons-codec)
12054 ("java-openchart2" ,java-openchart2)))
12055 ;; The source archive does not contain the resources.
12060 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12061 "b61cc2dcede0bede317db362472333115756b8c6/"
12062 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12063 (file-name (string-append name "-phyloxml-" version ".xsd"))
12066 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12067 ("synth_look_and_feel_1.xml"
12070 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12071 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12072 "forester/java/classes/resources/"
12073 "synth_look_and_feel_1.xml"))
12074 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12077 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12078 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12079 (synopsis "Phylogenomics libraries for Java")
12080 (description "Forester is a collection of Java libraries for
12081 phylogenomics and evolutionary biology research. It includes support for
12082 reading, writing, and exporting phylogenetic trees.")
12083 (license license:lgpl2.1+)))
12085 (define-public java-biojava-core
12087 (name "java-biojava-core")
12091 (uri (git-reference
12092 (url "https://github.com/biojava/biojava")
12093 (commit (string-append "biojava-" version))))
12094 (file-name (string-append name "-" version "-checkout"))
12097 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12098 (build-system ant-build-system)
12101 #:jar-name "biojava-core.jar"
12102 #:source-dir "biojava-core/src/main/java/"
12103 #:test-dir "biojava-core/src/test"
12104 ;; These tests seem to require internet access.
12105 #:test-exclude (list "**/SearchIOTest.java"
12106 "**/BlastXMLParserTest.java"
12107 "**/GenbankCookbookTest.java"
12108 "**/GenbankProxySequenceReaderTest.java")
12110 (modify-phases %standard-phases
12111 (add-before 'build 'copy-resources
12113 (copy-recursively "biojava-core/src/main/resources"
12116 (add-before 'check 'copy-test-resources
12118 (copy-recursively "biojava-core/src/test/resources"
12119 "build/test-classes")
12122 `(("java-log4j-api" ,java-log4j-api)
12123 ("java-log4j-core" ,java-log4j-core)
12124 ("java-slf4j-api" ,java-slf4j-api)
12125 ("java-slf4j-simple" ,java-slf4j-simple)))
12127 `(("java-junit" ,java-junit)
12128 ("java-hamcrest-core" ,java-hamcrest-core)))
12129 (home-page "https://biojava.org")
12130 (synopsis "Core libraries of Java framework for processing biological data")
12131 (description "BioJava is a project dedicated to providing a Java framework
12132 for processing biological data. It provides analytical and statistical
12133 routines, parsers for common file formats, reference implementations of
12134 popular algorithms, and allows the manipulation of sequences and 3D
12135 structures. The goal of the biojava project is to facilitate rapid
12136 application development for bioinformatics.
12138 This package provides the core libraries.")
12139 (license license:lgpl2.1+)))
12141 (define-public java-biojava-phylo
12142 (package (inherit java-biojava-core)
12143 (name "java-biojava-phylo")
12144 (build-system ant-build-system)
12147 #:jar-name "biojava-phylo.jar"
12148 #:source-dir "biojava-phylo/src/main/java/"
12149 #:test-dir "biojava-phylo/src/test"
12151 (modify-phases %standard-phases
12152 (add-before 'build 'copy-resources
12154 (copy-recursively "biojava-phylo/src/main/resources"
12157 (add-before 'check 'copy-test-resources
12159 (copy-recursively "biojava-phylo/src/test/resources"
12160 "build/test-classes")
12163 `(("java-log4j-api" ,java-log4j-api)
12164 ("java-log4j-core" ,java-log4j-core)
12165 ("java-slf4j-api" ,java-slf4j-api)
12166 ("java-slf4j-simple" ,java-slf4j-simple)
12167 ("java-biojava-core" ,java-biojava-core)
12168 ("java-forester" ,java-forester)))
12170 `(("java-junit" ,java-junit)
12171 ("java-hamcrest-core" ,java-hamcrest-core)))
12172 (home-page "https://biojava.org")
12173 (synopsis "Biojava interface to the forester phylogenomics library")
12174 (description "The phylo module provides a biojava interface layer to the
12175 forester phylogenomics library for constructing phylogenetic trees.")))
12177 (define-public java-biojava-alignment
12178 (package (inherit java-biojava-core)
12179 (name "java-biojava-alignment")
12180 (build-system ant-build-system)
12183 #:jar-name "biojava-alignment.jar"
12184 #:source-dir "biojava-alignment/src/main/java/"
12185 #:test-dir "biojava-alignment/src/test"
12187 (modify-phases %standard-phases
12188 (add-before 'build 'copy-resources
12190 (copy-recursively "biojava-alignment/src/main/resources"
12193 (add-before 'check 'copy-test-resources
12195 (copy-recursively "biojava-alignment/src/test/resources"
12196 "build/test-classes")
12199 `(("java-log4j-api" ,java-log4j-api)
12200 ("java-log4j-core" ,java-log4j-core)
12201 ("java-slf4j-api" ,java-slf4j-api)
12202 ("java-slf4j-simple" ,java-slf4j-simple)
12203 ("java-biojava-core" ,java-biojava-core)
12204 ("java-biojava-phylo" ,java-biojava-phylo)
12205 ("java-forester" ,java-forester)))
12207 `(("java-junit" ,java-junit)
12208 ("java-hamcrest-core" ,java-hamcrest-core)))
12209 (home-page "https://biojava.org")
12210 (synopsis "Biojava API for genetic sequence alignment")
12211 (description "The alignment module of BioJava provides an API that
12215 @item implementations of dynamic programming algorithms for sequence
12217 @item reading and writing of popular alignment file formats;
12218 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12221 (define-public java-biojava-core-4.0
12222 (package (inherit java-biojava-core)
12223 (name "java-biojava-core")
12227 (uri (git-reference
12228 (url "https://github.com/biojava/biojava")
12229 (commit (string-append "biojava-" version))))
12230 (file-name (string-append name "-" version "-checkout"))
12233 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12235 (define-public java-biojava-phylo-4.0
12236 (package (inherit java-biojava-core-4.0)
12237 (name "java-biojava-phylo")
12238 (build-system ant-build-system)
12241 #:jar-name "biojava-phylo.jar"
12242 #:source-dir "biojava-phylo/src/main/java/"
12243 #:test-dir "biojava-phylo/src/test"
12245 (modify-phases %standard-phases
12246 (add-before 'build 'copy-resources
12248 (copy-recursively "biojava-phylo/src/main/resources"
12251 (add-before 'check 'copy-test-resources
12253 (copy-recursively "biojava-phylo/src/test/resources"
12254 "build/test-classes")
12257 `(("java-log4j-api" ,java-log4j-api)
12258 ("java-log4j-core" ,java-log4j-core)
12259 ("java-slf4j-api" ,java-slf4j-api)
12260 ("java-slf4j-simple" ,java-slf4j-simple)
12261 ("java-biojava-core" ,java-biojava-core-4.0)
12262 ("java-forester" ,java-forester-1.005)))
12264 `(("java-junit" ,java-junit)
12265 ("java-hamcrest-core" ,java-hamcrest-core)))
12266 (home-page "https://biojava.org")
12267 (synopsis "Biojava interface to the forester phylogenomics library")
12268 (description "The phylo module provides a biojava interface layer to the
12269 forester phylogenomics library for constructing phylogenetic trees.")))
12271 (define-public java-biojava-alignment-4.0
12272 (package (inherit java-biojava-core-4.0)
12273 (name "java-biojava-alignment")
12274 (build-system ant-build-system)
12277 #:jar-name "biojava-alignment.jar"
12278 #:source-dir "biojava-alignment/src/main/java/"
12279 #:test-dir "biojava-alignment/src/test"
12281 (modify-phases %standard-phases
12282 (add-before 'build 'copy-resources
12284 (copy-recursively "biojava-alignment/src/main/resources"
12287 (add-before 'check 'copy-test-resources
12289 (copy-recursively "biojava-alignment/src/test/resources"
12290 "build/test-classes")
12293 `(("java-log4j-api" ,java-log4j-api)
12294 ("java-log4j-core" ,java-log4j-core)
12295 ("java-slf4j-api" ,java-slf4j-api)
12296 ("java-slf4j-simple" ,java-slf4j-simple)
12297 ("java-biojava-core" ,java-biojava-core-4.0)
12298 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12299 ("java-forester" ,java-forester-1.005)))
12301 `(("java-junit" ,java-junit)
12302 ("java-hamcrest-core" ,java-hamcrest-core)))
12303 (home-page "https://biojava.org")
12304 (synopsis "Biojava API for genetic sequence alignment")
12305 (description "The alignment module of BioJava provides an API that
12309 @item implementations of dynamic programming algorithms for sequence
12311 @item reading and writing of popular alignment file formats;
12312 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12315 (define-public dropseq-tools
12317 (name "dropseq-tools")
12322 (uri "http://mccarrolllab.com/download/1276/")
12323 (file-name (string-append "dropseq-tools-" version ".zip"))
12326 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12327 ;; Delete bundled libraries
12328 (modules '((guix build utils)))
12331 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12332 (delete-file-recursively "3rdParty")
12334 (build-system ant-build-system)
12336 `(#:tests? #f ; test data are not included
12337 #:test-target "test"
12338 #:build-target "all"
12339 #:source-dir "public/src/"
12342 (list (string-append "-Dpicard.executable.dir="
12343 (assoc-ref %build-inputs "java-picard")
12345 #:modules ((ice-9 match)
12348 (guix build java-utils)
12349 (guix build ant-build-system))
12351 (modify-phases %standard-phases
12352 ;; FIXME: fails with "java.io.FileNotFoundException:
12353 ;; /gnu/store/…-dropseq-tools-1.13/share/java/lib/biojava-alignment.jar"
12354 (delete 'generate-jar-indices)
12355 ;; All dependencies must be linked to "lib", because that's where
12356 ;; they will be searched for when the Class-Path property of the
12357 ;; manifest is computed.
12358 (add-after 'unpack 'record-references
12359 (lambda* (#:key inputs #:allow-other-keys)
12360 (mkdir-p "jar/lib")
12361 (let ((dirs (filter-map (match-lambda
12363 (if (and (string-prefix? "java-" name)
12364 (not (string=? name "java-testng")))
12367 (for-each (lambda (jar)
12368 (symlink jar (string-append "jar/lib/" (basename jar))))
12369 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12372 ;; There is no installation target
12374 (lambda* (#:key inputs outputs #:allow-other-keys)
12375 (let* ((out (assoc-ref outputs "out"))
12376 (bin (string-append out "/bin"))
12377 (share (string-append out "/share/java/"))
12378 (lib (string-append share "/lib/"))
12379 (scripts (list "BAMTagHistogram"
12380 "BAMTagofTagCounts"
12381 "BaseDistributionAtReadPosition"
12382 "CollapseBarcodesInPlace"
12383 "CollapseTagWithContext"
12385 "CreateIntervalsFiles"
12386 "DetectBeadSynthesisErrors"
12387 "DigitalExpression"
12388 "Drop-seq_alignment.sh"
12391 "GatherGeneGCLength"
12392 "GatherMolecularBarcodeDistributionByGene"
12393 "GatherReadQualityMetrics"
12396 "SelectCellsByNumTranscripts"
12397 "SingleCellRnaSeqMetricsCollector"
12398 "TagBamWithReadSequenceExtended"
12399 "TagReadWithGeneExon"
12400 "TagReadWithInterval"
12401 "TrimStartingSequence"
12402 "ValidateReference")))
12403 (for-each mkdir-p (list bin share lib))
12404 (install-file "dist/dropseq.jar" share)
12405 (for-each (lambda (script)
12406 (chmod script #o555)
12407 (install-file script bin))
12409 (substitute* (map (lambda (script)
12410 (string-append bin "/" script))
12412 (("^java") (which "java"))
12413 (("jar_deploy_dir=.*")
12414 (string-append "jar_deploy_dir=" share "\n"))))
12416 ;; FIXME: We do this after stripping jars because we don't want it to
12417 ;; copy all these jars and strip them. We only want to install
12418 ;; links. Arguably, this is a problem with the ant-build-system.
12419 (add-after 'strip-jar-timestamps 'install-links
12420 (lambda* (#:key outputs #:allow-other-keys)
12421 (let* ((out (assoc-ref outputs "out"))
12422 (share (string-append out "/share/java/"))
12423 (lib (string-append share "/lib/")))
12424 (for-each (lambda (jar)
12425 (symlink (readlink jar)
12426 (string-append lib (basename jar))))
12427 (find-files "jar/lib" "\\.jar$")))
12430 `(("jdk" ,icedtea-8)
12431 ("java-picard" ,java-picard-2.10.3)
12432 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12433 ("java-commons-math3" ,java-commons-math3)
12434 ("java-commons-jexl2" ,java-commons-jexl-2)
12435 ("java-commons-collections4" ,java-commons-collections4)
12436 ("java-commons-lang2" ,java-commons-lang)
12437 ("java-commons-io" ,java-commons-io)
12438 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12439 ("java-guava" ,java-guava)
12440 ("java-la4j" ,java-la4j)
12441 ("java-biojava-core" ,java-biojava-core-4.0)
12442 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12443 ("java-jdistlib" ,java-jdistlib)
12444 ("java-simple-xml" ,java-simple-xml)
12445 ("java-snakeyaml" ,java-snakeyaml)))
12448 ("java-testng" ,java-testng)))
12449 (home-page "http://mccarrolllab.com/dropseq/")
12450 (synopsis "Tools for Drop-seq analyses")
12451 (description "Drop-seq is a technology to enable biologists to
12452 analyze RNA expression genome-wide in thousands of individual cells at
12453 once. This package provides tools to perform Drop-seq analyses.")
12454 (license license:expat)))
12456 (define-public pigx-rnaseq
12458 (name "pigx-rnaseq")
12462 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12463 "releases/download/v" version
12464 "/pigx_rnaseq-" version ".tar.gz"))
12467 "0z3hr120wk2vrlmlpz1vp3n9wy3rq4y2mnzh2vf08qgqn2xfdwcw"))))
12468 (build-system gnu-build-system)
12470 `(#:parallel-tests? #f ; not supported
12472 (modify-phases %standard-phases
12473 ;; "test.sh" runs STAR, which requires excessive amounts of memory.
12474 (add-after 'unpack 'disable-resource-intensive-test
12476 (substitute* "Makefile.in"
12477 (("(^ tests/test_trim_galore/test.sh).*" _ m) m)
12478 (("^ tests/test_multiqc/test.sh") "")
12479 (("^ test.sh") ""))
12482 `(("coreutils" ,coreutils)
12485 ("snakemake" ,snakemake)
12487 ("multiqc" ,multiqc)
12489 ("trim-galore" ,trim-galore)
12491 ("samtools" ,samtools)
12492 ("r-minimal" ,r-minimal)
12493 ("r-rmarkdown" ,r-rmarkdown)
12494 ("r-ggplot2" ,r-ggplot2)
12495 ("r-ggrepel" ,r-ggrepel)
12496 ("r-gprofiler" ,r-gprofiler)
12497 ("r-deseq2" ,r-deseq2)
12499 ("r-knitr" ,r-knitr)
12500 ("r-pheatmap" ,r-pheatmap)
12501 ("r-corrplot" ,r-corrplot)
12502 ("r-reshape2" ,r-reshape2)
12503 ("r-plotly" ,r-plotly)
12504 ("r-scales" ,r-scales)
12505 ("r-summarizedexperiment" ,r-summarizedexperiment)
12506 ("r-crosstalk" ,r-crosstalk)
12507 ("r-tximport" ,r-tximport)
12508 ("r-rtracklayer" ,r-rtracklayer)
12509 ("r-rjson" ,r-rjson)
12512 ("pandoc-citeproc" ,pandoc-citeproc)
12513 ("python-wrapper" ,python-wrapper)
12514 ("python-pyyaml" ,python-pyyaml)))
12515 (home-page "https://bioinformatics.mdc-berlin.de/pigx/")
12516 (synopsis "Analysis pipeline for RNA sequencing experiments")
12517 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
12518 reporting for RNA sequencing experiments. It is easy to use and produces high
12519 quality reports. The inputs are reads files from the sequencing experiment,
12520 and a configuration file which describes the experiment. In addition to
12521 quality control of the experiment, the pipeline produces a differential
12522 expression report comparing samples in an easily configurable manner.")
12523 (license license:gpl3+)))
12525 (define-public pigx-chipseq
12527 (name "pigx-chipseq")
12531 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
12532 "releases/download/v" version
12533 "/pigx_chipseq-" version ".tar.gz"))
12536 "0426i31b7mqqkbss5dgrvf5prkj4z1qrd7yrpd27vybs01xhdlks"))))
12537 (build-system gnu-build-system)
12538 ;; parts of the tests rely on access to the network
12539 (arguments '(#:tests? #f))
12542 ("coreutils" ,coreutils)
12543 ("r-minimal" ,r-minimal)
12544 ("r-argparser" ,r-argparser)
12545 ("r-biocparallel" ,r-biocparallel)
12546 ("r-biostrings" ,r-biostrings)
12547 ("r-chipseq" ,r-chipseq)
12548 ("r-data-table" ,r-data-table)
12549 ("r-dplyr" ,r-dplyr)
12550 ("r-genomation" ,r-genomation)
12551 ("r-genomicalignments" ,r-genomicalignments)
12552 ("r-genomicranges" ,r-genomicranges)
12553 ("r-rsamtools" ,r-rsamtools)
12554 ("r-rtracklayer" ,r-rtracklayer)
12555 ("r-s4vectors" ,r-s4vectors)
12556 ("r-stringr" ,r-stringr)
12557 ("r-tibble" ,r-tibble)
12558 ("r-tidyr" ,r-tidyr)
12559 ("r-jsonlite" ,r-jsonlite)
12560 ("r-heatmaply" ,r-heatmaply)
12561 ("r-htmlwidgets" ,r-htmlwidgets)
12562 ("r-ggplot2" ,r-ggplot2)
12563 ("r-plotly" ,r-plotly)
12564 ("r-rmarkdown" ,r-rmarkdown)
12565 ("python-wrapper" ,python-wrapper)
12566 ("python-pyyaml" ,python-pyyaml)
12567 ("python-magic" ,python-magic)
12568 ("python-xlrd" ,python-xlrd)
12569 ("trim-galore" ,trim-galore)
12571 ("multiqc" ,multiqc)
12574 ("pandoc-citeproc" ,pandoc-citeproc)
12578 ("snakemake" ,snakemake)
12579 ("samtools" ,samtools)
12580 ("bedtools" ,bedtools)
12581 ("kentutils" ,kentutils)))
12583 `(("python-pytest" ,python-pytest)))
12584 (home-page "https://bioinformatics.mdc-berlin.de/pigx/")
12585 (synopsis "Analysis pipeline for ChIP sequencing experiments")
12586 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
12587 calling and reporting for ChIP sequencing experiments. It is easy to use and
12588 produces high quality reports. The inputs are reads files from the sequencing
12589 experiment, and a configuration file which describes the experiment. In
12590 addition to quality control of the experiment, the pipeline enables to set up
12591 multiple peak calling analysis and allows the generation of a UCSC track hub
12592 in an easily configurable manner.")
12593 (license license:gpl3+)))
12595 (define-public pigx-bsseq
12597 (name "pigx-bsseq")
12601 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
12602 "releases/download/v" version
12603 "/pigx_bsseq-" version ".tar.gz"))
12606 "0mpzlay2d5cjpmrcp7knff6rg1c2mqszd638n7lw0mc0cycbp9f8"))))
12607 (build-system gnu-build-system)
12609 `(;; TODO: tests currently require 12+GB of RAM. See
12610 ;; https://github.com/BIMSBbioinfo/pigx_bsseq/issues/164
12613 (modify-phases %standard-phases
12614 (add-before 'check 'set-timezone
12615 ;; The readr package is picky about timezones.
12616 (lambda* (#:key inputs #:allow-other-keys)
12617 (setenv "TZ" "UTC+1")
12619 (string-append (assoc-ref inputs "tzdata")
12620 "/share/zoneinfo"))
12623 `(("tzdata" ,tzdata)))
12625 `(("coreutils" ,coreutils)
12628 ("r-minimal" ,r-minimal)
12629 ("r-annotationhub" ,r-annotationhub)
12631 ("r-genomation" ,r-genomation)
12632 ("r-ggrepel" ,r-ggrepel)
12633 ("r-methylkit" ,r-methylkit)
12634 ("r-rtracklayer" ,r-rtracklayer)
12635 ("r-rmarkdown" ,r-rmarkdown)
12636 ("r-bookdown" ,r-bookdown)
12637 ("r-ggplot2" ,r-ggplot2)
12638 ("r-ggbio" ,r-ggbio)
12640 ("pandoc-citeproc" ,pandoc-citeproc)
12641 ("python-wrapper" ,python-wrapper)
12642 ("python-pyyaml" ,python-pyyaml)
12643 ("snakemake" ,snakemake)
12644 ("bismark" ,bismark)
12646 ("bwa-meth" ,bwa-meth)
12648 ("methyldackel" ,methyldackel)
12649 ("multiqc" ,multiqc)
12650 ("trim-galore" ,trim-galore)
12651 ("cutadapt" ,cutadapt)
12652 ("samblaster" ,samblaster)
12653 ("samtools" ,samtools)))
12654 (home-page "https://bioinformatics.mdc-berlin.de/pigx/")
12655 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
12656 (description "PiGx BSseq is a data processing pipeline for raw fastq read
12657 data of bisulfite experiments; it produces reports on aggregate methylation
12658 and coverage and can be used to produce information on differential
12659 methylation and segmentation.")
12660 (license license:gpl3+)))
12662 (define-public pigx-scrnaseq
12664 (name "pigx-scrnaseq")
12668 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/"
12669 "releases/download/v" version
12670 "/pigx_scrnaseq-" version ".tar.gz"))
12673 "1d5l3gywypi67yz9advxq5xkgfhr4733gj0bwnngm723i3hdf5w9"))))
12674 (build-system gnu-build-system)
12676 `(("coreutils" ,coreutils)
12679 ("flexbar" ,flexbar)
12680 ("java" ,icedtea-8)
12681 ("jellyfish" ,jellyfish)
12682 ("python-wrapper" ,python-wrapper)
12683 ("python-pyyaml" ,python-pyyaml)
12684 ("python-pandas" ,python-pandas)
12685 ("python-magic" ,python-magic)
12686 ("python-numpy" ,python-numpy)
12687 ("python-loompy" ,python-loompy)
12689 ("pandoc-citeproc" ,pandoc-citeproc)
12690 ("samtools" ,samtools)
12691 ("snakemake" ,snakemake)
12693 ("r-minimal" ,r-minimal)
12694 ("r-argparser" ,r-argparser)
12695 ("r-cowplot" ,r-cowplot)
12696 ("r-data-table" ,r-data-table)
12697 ("r-delayedarray" ,r-delayedarray)
12698 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
12699 ("r-dplyr" ,r-dplyr)
12700 ("r-dropbead" ,r-dropbead)
12702 ("r-genomicalignments" ,r-genomicalignments)
12703 ("r-genomicfiles" ,r-genomicfiles)
12704 ("r-genomicranges" ,r-genomicranges)
12705 ("r-ggplot2" ,r-ggplot2)
12706 ("r-hdf5array" ,r-hdf5array)
12707 ("r-pheatmap" ,r-pheatmap)
12708 ("r-rmarkdown" ,r-rmarkdown)
12709 ("r-rsamtools" ,r-rsamtools)
12710 ("r-rtracklayer" ,r-rtracklayer)
12711 ("r-rtsne" ,r-rtsne)
12712 ("r-scater" ,r-scater)
12713 ("r-scran" ,r-scran)
12714 ("r-seurat" ,r-seurat)
12715 ("r-singlecellexperiment" ,r-singlecellexperiment)
12716 ("r-stringr" ,r-stringr)
12717 ("r-yaml" ,r-yaml)))
12718 (home-page "https://bioinformatics.mdc-berlin.de/pigx/")
12719 (synopsis "Analysis pipeline for single-cell RNA sequencing experiments")
12720 (description "PiGX scRNAseq is an analysis pipeline for preprocessing and
12721 quality control for single cell RNA sequencing experiments. The inputs are
12722 read files from the sequencing experiment, and a configuration file which
12723 describes the experiment. It produces processed files for downstream analysis
12724 and interactive quality reports. The pipeline is designed to work with UMI
12726 (license license:gpl3+)))
12728 (define-public pigx
12734 (uri (string-append "https://github.com/BIMSBbioinfo/pigx/"
12735 "releases/download/v" version
12736 "/pigx-" version ".tar.gz"))
12739 "1i5njdy1clj5ncw45d16p7mwmqvb1ilikl9n797pxklc3f4s7mq7"))))
12740 (build-system gnu-build-system)
12742 `(("python" ,python)
12743 ("pigx-bsseq" ,pigx-bsseq)
12744 ("pigx-chipseq" ,pigx-chipseq)
12745 ("pigx-rnaseq" ,pigx-rnaseq)
12746 ("pigx-scrnaseq" ,pigx-scrnaseq)))
12747 (home-page "https://bioinformatics.mdc-berlin.de/pigx/")
12748 (synopsis "Analysis pipelines for genomics")
12749 (description "PiGx is a collection of genomics pipelines. It includes the
12750 following pipelines:
12753 @item PiGx BSseq for raw fastq read data of bisulfite experiments
12754 @item PiGx RNAseq for RNAseq samples
12755 @item PiGx scRNAseq for single cell dropseq analysis
12756 @item PiGx ChIPseq for reads from ChIPseq experiments
12759 All pipelines are easily configured with a simple sample sheet and a
12760 descriptive settings file. The result is a set of comprehensive, interactive
12761 HTML reports with interesting findings about your samples.")
12762 (license license:gpl3+)))
12764 (define-public genrich
12770 (uri (git-reference
12771 (url "https://github.com/jsh58/Genrich")
12772 (commit (string-append "v" version))))
12773 (file-name (git-file-name name version))
12776 "0x0q6z0208n3cxzqjla4rgjqpyqgwpmz27852lcvzkzaigymq4zp"))))
12777 (build-system gnu-build-system)
12779 `(#:tests? #f ; there are none
12781 (modify-phases %standard-phases
12782 (delete 'configure)
12784 (lambda* (#:key outputs #:allow-other-keys)
12785 (install-file "Genrich" (string-append (assoc-ref outputs "out") "/bin"))
12789 (home-page "https://github.com/jsh58/Genrich")
12790 (synopsis "Detecting sites of genomic enrichment")
12791 (description "Genrich is a peak-caller for genomic enrichment
12792 assays (e.g. ChIP-seq, ATAC-seq). It analyzes alignment files generated
12793 following the assay and produces a file detailing peaks of significant
12795 (license license:expat)))
12797 (define-public mantis
12798 (let ((commit "4ffd171632c2cb0056a86d709dfd2bf21bc69b84")
12802 (version (git-version "0" revision commit))
12805 (uri (git-reference
12806 (url "https://github.com/splatlab/mantis")
12808 (file-name (git-file-name name version))
12811 "0iqbr0dhmlc8mzpirmm2s4pkzkwdgrcx50yx6cv3wlr2qi064p55"))))
12812 (build-system cmake-build-system)
12813 (arguments '(#:tests? #f)) ; there are none
12815 `(("sdsl-lite" ,sdsl-lite)
12816 ("openssl" ,openssl)
12818 (home-page "https://github.com/splatlab/mantis")
12819 (synopsis "Large-scale sequence-search index data structure")
12820 (description "Mantis is a space-efficient data structure that can be
12821 used to index thousands of raw-read genomics experiments and facilitate
12822 large-scale sequence searches on those experiments. Mantis uses counting
12823 quotient filters instead of Bloom filters, enabling rapid index builds and
12824 queries, small indexes, and exact results, i.e., no false positives or
12825 negatives. Furthermore, Mantis is also a colored de Bruijn graph
12826 representation, so it supports fast graph traversal and other topological
12827 analyses in addition to large-scale sequence-level searches.")
12828 ;; uses __uint128_t and inline assembly
12829 (supported-systems '("x86_64-linux"))
12830 (license license:bsd-3))))
12832 (define-public sjcount
12833 ;; There is no tag for version 3.2, nor is there a release archive.
12834 (let ((commit "292d3917cadb3f6834c81e509c30e61cd7ead6e5")
12838 (version (git-version "3.2" revision commit))
12841 (uri (git-reference
12842 (url "https://github.com/pervouchine/sjcount-full")
12844 (file-name (string-append name "-" version "-checkout"))
12847 "0gdgj35j249f04rqgq8ymcc1xg1vi9kzbajnjqpaq2wpbh8bl234"))))
12848 (build-system gnu-build-system)
12850 `(#:tests? #f ; requires a 1.4G test file
12852 (list (string-append "SAMTOOLS_DIR="
12853 (assoc-ref %build-inputs "samtools")
12856 (modify-phases %standard-phases
12857 (replace 'configure
12858 (lambda* (#:key inputs #:allow-other-keys)
12859 (substitute* "makefile"
12860 (("-I \\$\\{SAMTOOLS_DIR\\}")
12861 (string-append "-I" (assoc-ref inputs "samtools")
12862 "/include/samtools"))
12863 (("-lz ") "-lz -lpthread "))
12866 (lambda* (#:key outputs #:allow-other-keys)
12867 (for-each (lambda (tool)
12869 (string-append (assoc-ref outputs "out")
12871 '("j_count" "b_count" "sjcount"))
12874 `(("samtools" ,samtools-0.1)
12876 (home-page "https://github.com/pervouchine/sjcount-full/")
12877 (synopsis "Annotation-agnostic splice junction counting pipeline")
12878 (description "Sjcount is a utility for fast quantification of splice
12879 junctions in RNA-seq data. It is annotation-agnostic and offset-aware. This
12880 version does count multisplits.")
12881 (license license:gpl3+))))
12883 (define-public minimap2
12890 (uri (string-append "https://github.com/lh3/minimap2/"
12891 "releases/download/v" version "/"
12892 "minimap2-" version ".tar.bz2"))
12895 "0hi7i9pzxhvjj44khzzzj1lrn5gb5837arr4wgln7k1k5n4ci2mn"))))
12896 (build-system gnu-build-system)
12898 `(#:tests? #f ; there are none
12901 (let ((system ,(or (%current-target-system)
12902 (%current-system))))
12904 ((string-prefix? "x86_64" system)
12906 ((or (string-prefix? "armhf" system)
12907 (string-prefix? "aarch64" system))
12909 (else "sse2only=1"))))
12911 (modify-phases %standard-phases
12912 (delete 'configure)
12914 (lambda* (#:key outputs #:allow-other-keys)
12915 (let* ((out (assoc-ref outputs "out"))
12916 (bin (string-append out "/bin"))
12917 (man (string-append out "/share/man/man1")))
12918 (install-file "minimap2" bin)
12920 (install-file "minimap2.1" man))
12924 (home-page "https://lh3.github.io/minimap2/")
12925 (synopsis "Pairwise aligner for genomic and spliced nucleotide sequences")
12926 (description "Minimap2 is a versatile sequence alignment program that
12927 aligns DNA or mRNA sequences against a large reference database. Typical use
12931 @item mapping PacBio or Oxford Nanopore genomic reads to the human genome;
12932 @item finding overlaps between long reads with error rate up to ~15%;
12933 @item splice-aware alignment of PacBio Iso-Seq or Nanopore cDNA or Direct RNA
12934 reads against a reference genome;
12935 @item aligning Illumina single- or paired-end reads;
12936 @item assembly-to-assembly alignment;
12937 @item full-genome alignment between two closely related species with
12938 divergence below ~15%.
12940 (license license:expat)))
12942 (define-public miniasm
12948 (uri (git-reference
12949 (url "https://github.com/lh3/miniasm")
12950 (commit (string-append "v" version))))
12951 (file-name (git-file-name name version))
12954 "04dv5wv8bhsw1imxwyd438bnn9kby7svp44nbcz8lsadzjjci5gs"))))
12955 (build-system gnu-build-system)
12959 `(#:tests? #f ; There are no tests.
12961 (modify-phases %standard-phases
12962 (delete 'configure)
12964 (lambda* (#:key inputs outputs #:allow-other-keys)
12965 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
12966 (install-file "miniasm" bin)
12967 (install-file "minidot" bin)
12969 (home-page "https://github.com/lh3/miniasm")
12970 (synopsis "Ultrafast de novo assembly for long noisy reads")
12971 (description "Miniasm is a very fast OLC-based de novo assembler for noisy
12972 long reads. It takes all-vs-all read self-mappings (typically by minimap) as
12973 input and outputs an assembly graph in the GFA format. Different from
12974 mainstream assemblers, miniasm does not have a consensus step. It simply
12975 concatenates pieces of read sequences to generate the final unitig sequences.
12976 Thus the per-base error rate is similar to the raw input reads.")
12977 (license license:expat)))
12979 (define-public r-circus
12986 (uri (git-reference
12987 (url "https://github.com/BIMSBbioinfo/ciRcus")
12988 (commit (string-append "v" version))))
12989 (file-name (git-file-name name version))
12992 "0jhjn3ilb057hbf6yzrihj13ifxxs32y7nkby8l3lkm28dg4p97h"))))
12993 (build-system r-build-system)
12995 `(("r-annotationdbi" ,r-annotationdbi)
12996 ("r-annotationhub" ,r-annotationhub)
12997 ("r-biomart" ,r-biomart)
12998 ("r-data-table" ,r-data-table)
13000 ("r-genomicfeatures" ,r-genomicfeatures)
13001 ("r-genomicranges" ,r-genomicranges)
13002 ("r-ggplot2" ,r-ggplot2)
13004 ("r-iranges" ,r-iranges)
13005 ("r-rcolorbrewer" ,r-rcolorbrewer)
13006 ("r-rmysql" ,r-rmysql)
13007 ("r-s4vectors" ,r-s4vectors)
13008 ("r-stringr" ,r-stringr)
13009 ("r-summarizedexperiment" ,r-summarizedexperiment)))
13011 `(("r-knitr" ,r-knitr)))
13012 (home-page "https://github.com/BIMSBbioinfo/ciRcus")
13013 (synopsis "Annotation, analysis and visualization of circRNA data")
13014 (description "Circus is an R package for annotation, analysis and
13015 visualization of circRNA data. Users can annotate their circRNA candidates
13016 with host genes, gene featrues they are spliced from, and discriminate between
13017 known and yet unknown splice junctions. Circular-to-linear ratios of circRNAs
13018 can be calculated, and a number of descriptive plots easily generated.")
13019 (license license:artistic2.0)))
13021 (define-public gffread
13022 ;; We cannot use the tagged release because it is not in sync with gclib.
13023 ;; See https://github.com/gpertea/gffread/issues/26
13024 (let ((commit "ba7535fcb3cea55a6e5a491d916e93b454e87fd0")
13028 (version (git-version "0.9.12" revision commit))
13032 (uri (git-reference
13033 (url "https://github.com/gpertea/gffread")
13035 (file-name (git-file-name name version))
13038 "1dl2nbcg96lxpd0drg48ssa8343nf7pw9s9mkrc4mjjmfwsin3ki"))))
13039 (build-system gnu-build-system)
13041 `(#:tests? #f ; no check target
13043 (list "GCLDIR=gclib")
13045 (modify-phases %standard-phases
13046 (delete 'configure)
13047 (add-after 'unpack 'copy-gclib-source
13048 (lambda* (#:key inputs #:allow-other-keys)
13050 (copy-recursively (assoc-ref inputs "gclib-source") "gclib")
13052 ;; There is no install target
13054 (lambda* (#:key outputs #:allow-other-keys)
13055 (let* ((out (assoc-ref outputs "out"))
13056 (bin (string-append out "/bin")))
13057 (install-file "gffread" bin))
13061 ,(let ((version "0.10.3")
13062 (commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13066 (uri (git-reference
13067 (url "https://github.com/gpertea/gclib")
13069 (file-name (git-file-name "gclib" version))
13072 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13073 (home-page "https://github.com/gpertea/gffread/")
13074 (synopsis "Parse and convert GFF/GTF files")
13076 "This package provides a GFF/GTF file parsing utility providing format
13077 conversions, region filtering, FASTA sequence extraction and more.")
13078 ;; gffread is under Expat, but gclib is under Artistic 2.0
13079 (license (list license:expat
13080 license:artistic2.0)))))
13082 (define-public find-circ
13083 ;; The last release was in 2015. The license was clarified in 2017, so we
13084 ;; take the latest commit.
13085 (let ((commit "8655dca54970fcf7e92e22fbf57e1188724dda7d")
13089 (version (git-version "1.2" revision commit))
13093 (uri (git-reference
13094 (url "https://github.com/marvin-jens/find_circ")
13096 (file-name (git-file-name name version))
13099 "0p77pbqbclqr4srms34y1b9b4njybfpjiknc11ki84f3p8skb3cg"))))
13100 (build-system gnu-build-system)
13102 `(#:tests? #f ; there are none
13104 ;; There is no actual build system.
13105 (modify-phases %standard-phases
13106 (delete 'configure)
13109 (lambda* (#:key outputs #:allow-other-keys)
13110 (let* ((out (assoc-ref outputs "out"))
13111 (bin (string-append out "/bin"))
13112 (path (getenv "PYTHONPATH")))
13113 (for-each (lambda (script)
13114 (install-file script bin)
13115 (wrap-program (string-append bin "/" script)
13116 `("PYTHONPATH" ":" prefix (,path))))
13121 "unmapped2anchors.py")))
13124 `(("python2" ,python-2)
13125 ("python2-pysam" ,python2-pysam)
13126 ("python2-numpy" ,python2-numpy)))
13127 (home-page "https://github.com/marvin-jens/find_circ")
13128 (synopsis "circRNA detection from RNA-seq reads")
13129 (description "This package provides tools to detect head-to-tail
13130 spliced (back-spliced) sequencing reads, indicative of circular RNA (circRNA)
13132 (license license:gpl3))))
13134 (define-public python-scanpy
13136 (name "python-scanpy")
13141 (uri (pypi-uri "scanpy" version))
13144 "0s2b6cvaigx4wzw3850qb93sjwwxbzh22kpbp498zklc5rjpbz4l"))))
13145 (build-system python-build-system)
13148 (modify-phases %standard-phases
13150 (lambda* (#:key inputs #:allow-other-keys)
13151 ;; These tests require Internet access.
13152 (delete-file-recursively "scanpy/tests/notebooks")
13153 (delete-file "scanpy/tests/test_clustering.py")
13154 (delete-file "scanpy/tests/test_datasets.py")
13156 ;; TODO: I can't get the plotting tests to work, even with Xvfb.
13157 (delete-file "scanpy/tests/test_plotting.py")
13158 (delete-file "scanpy/tests/test_preprocessing.py")
13159 (delete-file "scanpy/tests/test_read_10x.py")
13161 (setenv "PYTHONPATH"
13162 (string-append (getcwd) ":"
13163 (getenv "PYTHONPATH")))
13167 `(("python-anndata" ,python-anndata)
13168 ("python-h5py" ,python-h5py)
13169 ("python-igraph" ,python-igraph)
13170 ("python-joblib" ,python-joblib)
13171 ("python-legacy-api-wrap" ,python-legacy-api-wrap)
13172 ("python-louvain" ,python-louvain)
13173 ("python-matplotlib" ,python-matplotlib)
13174 ("python-natsort" ,python-natsort)
13175 ("python-networkx" ,python-networkx)
13176 ("python-numba" ,python-numba)
13177 ("python-packaging" ,python-packaging)
13178 ("python-pandas" ,python-pandas)
13179 ("python-patsy" ,python-patsy)
13180 ("python-scikit-learn" ,python-scikit-learn)
13181 ("python-scipy" ,python-scipy)
13182 ("python-seaborn" ,python-seaborn)
13183 ("python-statsmodels" ,python-statsmodels)
13184 ("python-tables" ,python-tables)
13185 ("python-tqdm" ,python-tqdm)
13186 ("python-umap-learn" ,python-umap-learn)))
13188 `(("python-pytest" ,python-pytest)
13189 ("python-setuptools-scm" ,python-setuptools-scm)))
13190 (home-page "https://github.com/theislab/scanpy")
13191 (synopsis "Single-Cell Analysis in Python.")
13192 (description "Scanpy is a scalable toolkit for analyzing single-cell gene
13193 expression data. It includes preprocessing, visualization, clustering,
13194 pseudotime and trajectory inference and differential expression testing. The
13195 Python-based implementation efficiently deals with datasets of more than one
13197 (license license:bsd-3)))
13199 (define-public python-bbknn
13201 (name "python-bbknn")
13206 (uri (pypi-uri "bbknn" version))
13209 "1jbsh01f57zj4bhvjr3jh4532zznqd6nccmgrl3qi9gnhkf7c4y0"))))
13210 (build-system python-build-system)
13212 `(#:tests? #f)) ; TODO: Enable after migration to scikit-learn.
13214 `(("python-annoy" ,python-annoy)
13215 ("python-cython" ,python-cython)
13216 ("python-numpy" ,python-numpy)
13217 ("python-scipy" ,python-scipy)
13218 ("python-umap-learn" ,python-umap-learn)))
13219 (home-page "https://github.com/Teichlab/bbknn")
13220 (synopsis "Batch balanced KNN")
13221 (description "BBKNN is a batch effect removal tool that can be directly
13222 used in the Scanpy workflow. It serves as an alternative to
13223 @code{scanpy.api.pp.neighbors()}, with both functions creating a neighbour
13224 graph for subsequent use in clustering, pseudotime and UMAP visualisation. If
13225 technical artifacts are present in the data, they will make it challenging to
13226 link corresponding cell types across different batches. BBKNN actively
13227 combats this effect by splitting your data into batches and finding a smaller
13228 number of neighbours for each cell within each of the groups. This helps
13229 create connections between analogous cells in different batches without
13230 altering the counts or PCA space.")
13231 (license license:expat)))
13233 (define-public gffcompare
13234 (let ((commit "be56ef4349ea3966c12c6397f85e49e047361c41")
13237 (name "gffcompare")
13238 (version (git-version "0.10.15" revision commit))
13242 (uri (git-reference
13243 (url "https://github.com/gpertea/gffcompare/")
13245 (file-name (git-file-name name version))
13247 (base32 "0cp5qpxdhw4mxpya5dld8wi3jk00zyklm6rcri426wydinrnfmkg"))))
13248 (build-system gnu-build-system)
13250 `(#:tests? #f ; no check target
13252 (modify-phases %standard-phases
13253 (delete 'configure)
13254 (add-before 'build 'copy-gclib-source
13255 (lambda* (#:key inputs #:allow-other-keys)
13258 (assoc-ref inputs "gclib-source") "../gclib")
13261 (lambda* (#:key outputs #:allow-other-keys)
13262 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
13263 (install-file "gffcompare" bin)
13266 `(("gclib-source" ; see 'README.md' of gffcompare
13267 ,(let ((commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13270 (version (git-version "0.10.3" revision commit)))
13273 (uri (git-reference
13274 (url "https://github.com/gpertea/gclib/")
13276 (file-name (git-file-name name version))
13278 (base32 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13279 (home-page "https://github.com/gpertea/gffcompare/")
13280 (synopsis "Tool for comparing or classifing transcripts of RNA-Seq")
13282 "@code{gffcompare} is a tool that can:
13284 @item compare and evaluate the accuracy of RNA-Seq transcript assemblers
13285 (Cufflinks, Stringtie);
13286 @item collapse (merge) duplicate transcripts from multiple GTF/GFF3 files (e.g.
13287 resulted from assembly of different samples);
13288 @item classify transcripts from one or multiple GTF/GFF3 files as they relate to
13289 reference transcripts provided in a annotation file (also in GTF/GFF3 format).
13293 license:expat ;license for gffcompare
13294 license:artistic2.0))))) ;license for gclib
13296 (define-public intervaltree
13297 (let ((commit "b90527f9e6d51cd36ecbb50429e4524d3a418ea5"))
13299 (name "intervaltree")
13300 (version (git-version "0.0.0" "1" commit))
13304 (uri (git-reference
13305 (url "https://github.com/ekg/intervaltree/")
13307 (file-name (git-file-name name version))
13309 (base32 "0rgv6q5fl4x5d74n6p5wvdna6zmbdbqpb4jqqh6vq3670gn08xad"))))
13310 (build-system gnu-build-system)
13312 '(#:tests? #f ; No tests.
13313 #:make-flags (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
13316 (modify-phases %standard-phases
13317 (delete 'configure)))) ; There is no configure phase.
13318 (home-page "https://github.com/ekg/intervaltree")
13319 (synopsis "Minimal C++ interval tree implementation")
13320 (description "An interval tree can be used to efficiently find a set of
13321 numeric intervals overlapping or containing another interval. This library
13322 provides a basic implementation of an interval tree using C++ templates,
13323 allowing the insertion of arbitrary types into the tree.")
13324 (license license:expat))))
13326 (define-public python-intervaltree
13328 (name "python-intervaltree")
13333 (uri (pypi-uri "intervaltree" version))
13336 "0wz234g6irlm4hivs2qzmnywk0ss06ckagwh15nflkyb3p462kyb"))))
13337 (build-system python-build-system)
13340 (modify-phases %standard-phases
13341 ;; pytest seems to have a check to make sure the user is testing
13342 ;; their checked-out code and not an installed, potentially
13343 ;; out-of-date copy. This is harmless here, since we just installed
13344 ;; the package, so we disable the check to avoid skipping tests
13346 (add-before 'check 'import-mismatch-error-workaround
13348 (setenv "PY_IGNORE_IMPORTMISMATCH" "1")
13351 `(("python-sortedcontainers" ,python-sortedcontainers)))
13353 `(("python-pytest" ,python-pytest)))
13354 (home-page "https://github.com/chaimleib/intervaltree")
13355 (synopsis "Editable interval tree data structure")
13357 "This package provides a mutable, self-balancing interval tree
13358 implementation for Python. Queries may be by point, by range overlap, or by
13359 range envelopment. This library was designed to allow tagging text and time
13360 intervals, where the intervals include the lower bound but not the upper
13362 (license license:asl2.0)))
13364 (define-public python-pypairix
13366 (name "python-pypairix")
13368 ;; The tarball on pypi does not include the makefile to build the
13373 (uri (git-reference
13374 (url "https://github.com/4dn-dcic/pairix")
13376 (file-name (git-file-name name version))
13379 "1snr3lrmsld8sy77ng6ba6wcmd33xjccf1l2f3m6pi29xis9nd6p"))))
13380 (build-system python-build-system)
13383 (modify-phases %standard-phases
13384 (add-before 'build 'build-programs
13385 (lambda _ (invoke "make")))
13386 (add-after 'install 'install-programs
13387 (lambda* (#:key outputs #:allow-other-keys)
13388 (copy-recursively "bin" (string-append
13389 (assoc-ref outputs "out")
13394 (home-page "https://github.com/4dn-dcic/pairix")
13395 (synopsis "Support for querying pairix-indexed bgzipped text files")
13397 "Pypairix is a Python module for fast querying on a pairix-indexed
13398 bgzipped text file that contains a pair of genomic coordinates per line.")
13399 (license license:expat)))
13401 (define-public python-pyfaidx
13403 (name "python-pyfaidx")
13408 (uri (pypi-uri "pyfaidx" version))
13411 "038xi3a6zvrxbyyfpp64ka8pcjgsdq4fgw9cl5lpxbvmm1bzzw2q"))))
13412 (build-system python-build-system)
13414 `(("python-six" ,python-six)))
13415 (home-page "http://mattshirley.com")
13416 (synopsis "Random access to fasta subsequences")
13418 "This package provides procedures for efficient pythonic random access to
13419 fasta subsequences.")
13420 (license license:bsd-3)))
13422 (define-public python2-pyfaidx
13423 (package-with-python2 python-pyfaidx))
13425 (define-public python-cooler
13427 (name "python-cooler")
13432 (uri (pypi-uri "cooler" version))
13435 "01g6gqix9ba27sappz6nfyiwabzrlf8i5fn8kwcz8ra356cq9crp"))))
13436 (build-system python-build-system)
13438 `(("python-asciitree" ,python-asciitree)
13439 ("python-biopython" ,python-biopython)
13440 ("python-click" ,python-click)
13441 ("python-cytoolz" ,python-cytoolz)
13442 ("python-dask" ,python-dask)
13443 ("python-h5py" ,python-h5py)
13444 ("python-multiprocess" ,python-multiprocess)
13445 ("python-numpy" ,python-numpy)
13446 ("python-pandas" ,python-pandas)
13447 ("python-pyfaidx" ,python-pyfaidx)
13448 ("python-pypairix" ,python-pypairix)
13449 ("python-pysam" ,python-pysam)
13450 ("python-pyyaml" ,python-pyyaml)
13451 ("python-scipy" ,python-scipy)
13452 ("python-simplejson" ,python-simplejson)))
13454 `(("python-mock" ,python-mock)
13455 ("python-pytest" ,python-pytest)))
13456 (home-page "https://github.com/mirnylab/cooler")
13457 (synopsis "Sparse binary format for genomic interaction matrices")
13459 "Cooler is a support library for a sparse, compressed, binary persistent
13460 storage format, called @code{cool}, used to store genomic interaction data,
13461 such as Hi-C contact matrices.")
13462 (license license:bsd-3)))
13464 (define-public python-hicmatrix
13466 (name "python-hicmatrix")
13470 ;; Version 12 is not available on pypi.
13472 (uri (git-reference
13473 (url "https://github.com/deeptools/HiCMatrix")
13475 (file-name (git-file-name name version))
13478 "1xhdyx16f3brgxgxybixdi64ki8nbbkq5vk4h9ahi11pzpjfn1pj"))))
13479 (build-system python-build-system)
13482 (modify-phases %standard-phases
13483 (add-after 'unpack 'relax-requirements
13485 (substitute* '("requirements.txt"
13487 (("cooler *=+ *0.8.5")
13491 `(("python-cooler" ,python-cooler)
13492 ("python-intervaltree" ,python-intervaltree)
13493 ("python-numpy" ,python-numpy)
13494 ("python-pandas" ,python-pandas)
13495 ("python-scipy" ,python-scipy)
13496 ("python-tables" ,python-tables)))
13497 (home-page "https://github.com/deeptools/HiCMatrix/")
13498 (synopsis "HiCMatrix class for HiCExplorer and pyGenomeTracks")
13500 "This helper package implements the @code{HiCMatrix} class for
13501 the HiCExplorer and pyGenomeTracks packages.")
13502 (license license:gpl3+)))
13504 (define-public python-hicexplorer
13506 (name "python-hicexplorer")
13510 ;; The latest version is not available on Pypi.
13512 (uri (git-reference
13513 (url "https://github.com/deeptools/HiCExplorer")
13515 (file-name (git-file-name name version))
13518 "0q5gpbzmrkvygqgw524q36b4nrivcmyi5v194vsx0qw7b3gcmq08"))))
13519 (build-system python-build-system)
13522 (modify-phases %standard-phases
13523 (add-after 'unpack 'loosen-up-requirements
13525 (substitute* "setup.py"
13529 `(("python-biopython" ,python-biopython)
13530 ("python-configparser" ,python-configparser)
13531 ("python-cooler" ,python-cooler)
13532 ("python-future" ,python-future)
13533 ("python-intervaltree" ,python-intervaltree)
13534 ("python-jinja2" ,python-jinja2)
13535 ("python-matplotlib" ,python-matplotlib)
13536 ("python-numpy" ,python-numpy)
13537 ("python-pandas" ,python-pandas)
13538 ("python-pybigwig" ,python-pybigwig)
13539 ("python-pysam" ,python-pysam)
13540 ("python-scipy" ,python-scipy)
13541 ("python-six" ,python-six)
13542 ("python-tables" ,python-tables)
13543 ("python-unidecode" ,python-unidecode)))
13544 (home-page "https://hicexplorer.readthedocs.io")
13545 (synopsis "Process, analyze and visualize Hi-C data")
13547 "HiCExplorer is a powerful and easy to use set of tools to process,
13548 normalize and visualize Hi-C data. HiCExplorer facilitates the creation of
13549 contact matrices, correction of contacts, TAD detection, A/B compartments,
13550 merging, reordering or chromosomes, conversion from different formats
13551 including cooler and detection of long-range contacts. Moreover, it allows
13552 the visualization of multiple contact matrices along with other types of data
13553 like genes, compartments, ChIP-seq coverage tracks (and in general any type of
13554 genomic scores), long range contacts and the visualization of viewpoints.")
13555 (license license:gpl3)))
13557 (define-public python-pygenometracks
13559 (name "python-pygenometracks")
13564 (uri (pypi-uri "pyGenomeTracks" version))
13567 "16laa0wnf4qn9fb9ych4w1vqhqwjss70v0y0f6wp4gwqfrlgac0f"))))
13568 (build-system python-build-system)
13570 `(#:tests? #f ; there are none
13572 (modify-phases %standard-phases
13573 (add-after 'unpack 'relax-requirements
13575 (substitute* "setup.py"
13576 (("matplotlib ==3.1.1")
13577 "matplotlib >=3.1.1"))
13580 `(("python-future" ,python-future)
13581 ("python-gffutils" ,python-gffutils)
13582 ("python-hicmatrix" ,python-hicmatrix)
13583 ("python-intervaltree" ,python-intervaltree)
13584 ("python-matplotlib" ,python-matplotlib)
13585 ("python-numpy" ,python-numpy)
13586 ("python-pybigwig" ,python-pybigwig)
13587 ("python-pysam" ,python-pysam)
13588 ("python-tqdm" ,python-tqdm)))
13590 `(("python-pytest" ,python-pytest)))
13591 (home-page "https://pygenometracks.readthedocs.io")
13592 (synopsis "Program and library to plot beautiful genome browser tracks")
13594 "This package aims to produce high-quality genome browser tracks that
13595 are highly customizable. Currently, it is possible to plot: bigwig, bed (many
13596 options), bedgraph, links (represented as arcs), and Hi-C matrices.
13597 pyGenomeTracks can make plots with or without Hi-C data.")
13598 (license license:gpl3+)))
13600 (define-public python-hic2cool
13602 (name "python-hic2cool")
13607 (uri (pypi-uri "hic2cool" version))
13610 "0xy6mhfns2lzib1kcr6419jjp6pmh0qx8z8na55lmiwn0ds8q9cl"))))
13611 (build-system python-build-system)
13612 (arguments '(#:tests? #f)) ; no tests included
13614 `(("python-cooler" ,python-cooler)))
13615 (home-page "https://github.com/4dn-dcic/hic2cool")
13616 (synopsis "Converter for .hic and .cool files")
13618 "This package provides a converter between @code{.hic} files (from
13619 juicer) and single-resolution or multi-resolution @code{.cool} files (for
13620 cooler). Both @code{hic} and @code{cool} files describe Hi-C contact
13622 (license license:expat)))
13624 (define-public r-pore
13632 (string-append "mirror://sourceforge/rpore/" version
13633 "/poRe_" version ".tar.gz"))
13635 (base32 "0pih9nljbv8g4x8rkk29i7aqq681b782r5s5ynp4nw9yzqnmmksv"))))
13636 (properties `((upstream-name . "poRe")))
13637 (build-system r-build-system)
13639 `(("r-bit64" ,r-bit64)
13640 ("r-data-table" ,r-data-table)
13641 ("r-rhdf5" ,r-rhdf5)
13642 ("r-shiny" ,r-shiny)
13643 ("r-svdialogs" ,r-svdialogs)))
13644 (home-page "https://sourceforge.net/projects/rpore/")
13645 (synopsis "Visualize Nanopore sequencing data")
13647 "This package provides graphical user interfaces to organize and visualize Nanopore
13649 ;; This is free software but the license variant is unclear:
13650 ;; <https://github.com/mw55309/poRe_docs/issues/10>.
13651 (license license:bsd-3)))
13653 (define-public r-xbioc
13654 (let ((revision "1")
13655 (commit "6ff0670a37ab3036aaf1d94aa4b208310946b0b5"))
13658 (version (git-version "0.1.16" revision commit))
13661 (uri (git-reference
13662 (url "https://github.com/renozao/xbioc")
13664 (file-name (git-file-name name version))
13667 "0w8bsq5myiwkfhh83nm6is5ichiyvwa1axx2szvxnzq39x6knf66"))))
13668 (build-system r-build-system)
13670 `(("r-annotationdbi" ,r-annotationdbi)
13671 ("r-assertthat" ,r-assertthat)
13672 ("r-biobase" ,r-biobase)
13673 ("r-biocmanager" ,r-biocmanager)
13674 ("r-digest" ,r-digest)
13675 ("r-pkgmaker" ,r-pkgmaker)
13677 ("r-reshape2" ,r-reshape2)
13678 ("r-stringr" ,r-stringr)))
13679 (home-page "https://github.com/renozao/xbioc/")
13680 (synopsis "Extra base functions for Bioconductor")
13681 (description "This package provides extra utility functions to perform
13682 common tasks in the analysis of omics data, leveraging and enhancing features
13683 provided by Bioconductor packages.")
13684 (license license:gpl3+))))
13686 (define-public r-cssam
13687 (let ((revision "1")
13688 (commit "9ec58c982fa551af0d80b1a266890d92954833f2"))
13691 (version (git-version "1.4" revision commit))
13694 (uri (git-reference
13695 (url "https://github.com/shenorrLab/csSAM")
13697 (file-name (git-file-name name version))
13700 "128syf9v39gk0z3ip000qpsjbg6l1siyq6c8b0hz41dzg5achyb3"))))
13701 (build-system r-build-system)
13703 `(("r-formula" ,r-formula)
13704 ("r-ggplot2" ,r-ggplot2)
13705 ("r-pkgmaker" ,r-pkgmaker)
13707 ("r-rngtools" ,r-rngtools)
13708 ("r-scales" ,r-scales)))
13709 (home-page "https://github.com/shenorrLab/csSAM/")
13710 (synopsis "Cell type-specific statistical analysis of microarray")
13711 (description "This package implements the method csSAM that computes
13712 cell-specific differential expression from measured cell proportions using
13715 (license license:lgpl2.1+))))
13717 (define-public r-bseqsc
13718 (let ((revision "1")
13719 (commit "fef3f3e38dcf3df37103348b5780937982b43b98"))
13722 (version (git-version "1.0" revision commit))
13725 (uri (git-reference
13726 (url "https://github.com/shenorrLab/bseqsc")
13728 (file-name (git-file-name name version))
13731 "1prw13wa20f7wlc3gkkls66n1kxz8d28qrb8icfqdwdnnv8w5qg8"))))
13732 (build-system r-build-system)
13734 `(("r-abind" ,r-abind)
13735 ("r-annotationdbi" ,r-annotationdbi)
13736 ("r-biobase" ,r-biobase)
13737 ("r-cssam" ,r-cssam)
13738 ("r-dplyr" ,r-dplyr)
13739 ("r-e1071" ,r-e1071)
13740 ("r-edger" ,r-edger)
13741 ("r-ggplot2" ,r-ggplot2)
13743 ("r-openxlsx" ,r-openxlsx)
13744 ("r-pkgmaker" ,r-pkgmaker)
13746 ("r-preprocesscore" ,r-preprocesscore)
13747 ("r-rngtools" ,r-rngtools)
13748 ("r-scales" ,r-scales)
13749 ("r-stringr" ,r-stringr)
13750 ("r-xbioc" ,r-xbioc)))
13751 (home-page "https://github.com/shenorrLab/bseqsc")
13752 (synopsis "Deconvolution of bulk sequencing experiments using single cell data")
13753 (description "BSeq-sc is a bioinformatics analysis pipeline that
13754 leverages single-cell sequencing data to estimate cell type proportion and
13755 cell type-specific gene expression differences from RNA-seq data from bulk
13756 tissue samples. This is a companion package to the publication \"A
13757 single-cell transcriptomic map of the human and mouse pancreas reveals inter-
13758 and intra-cell population structure.\" Baron et al. Cell Systems (2016)
13759 @url{https://www.ncbi.nlm.nih.gov/pubmed/27667365}.")
13760 (license license:gpl2+))))
13762 (define-public porechop
13763 ;; The recommended way to install is to clone the git repository
13764 ;; https://github.com/rrwick/Porechop#installation
13765 (let ((commit "289d5dca4a5fc327f97b3f8cecb68ecaf1014861")
13769 (version (git-version "0.2.3" revision commit))
13773 (uri (git-reference
13774 (url "https://github.com/rrwick/Porechop")
13776 (file-name (git-file-name name version))
13778 (base32 "05ps43gig0d3ia9x5lj84lb00hbsl6ba9n7y7jz927npxbr2ym23"))))
13779 (build-system python-build-system)
13780 (home-page "https://github.com/rrwick/porechop")
13781 (synopsis "Finding, trimming or splitting adapters, in Oxford Nanopore reads")
13783 "The porechop package is a tool for finding and removing adapters from Oxford
13784 Nanopore reads. Adapters on the ends of reads are trimmed off, and when a read
13785 has an adapter in its middle, it is treated as chimeric and chopped into
13786 separate reads. Porechop performs thorough alignments to effectively find
13787 adapters, even at low sequence identity. Porechop also supports demultiplexing
13788 of Nanopore reads that were barcoded with the Native Barcoding Kit, PCR
13789 Barcoding Kit or Rapid Barcoding Kit.")
13790 (license license:gpl3+))))
13792 (define-public poretools
13793 ;; The latest release was in 2016 and the latest commit is from 2017
13794 ;; the recommended way to install is to clone the git repository
13795 ;; https://poretools.readthedocs.io/en/latest/content/installation.html
13796 (let ((commit "e426b1f09e86ac259a00c261c79df91510777407")
13800 (version (git-version "0.6.0" revision commit))
13804 (uri (git-reference
13805 (url "https://github.com/arq5x/poretools")
13807 (file-name (git-file-name name version))
13809 (base32 "0bglj833wxpp3cq430p1d3xp085ls221js2y90w7ir2x5ay8l7am"))))
13810 (build-system python-build-system)
13811 ;; requires python >=2.7, <3.0, and the same for python dependencies
13812 (arguments `(#:python ,python-2))
13816 `(("python-dateutil" ,python2-dateutil)
13817 ("python-h5py" ,python2-h5py)
13818 ("python-matplotlib" ,python2-matplotlib)
13819 ("python-pandas" ,python2-pandas)
13820 ("python-seaborn" ,python2-seaborn)))
13821 (home-page "https://poretools.readthedocs.io")
13822 (synopsis "Toolkit for working with nanopore sequencing data")
13824 "The MinION from Oxford Nanopore Technologies is a nanopore sequencer.
13825 This @code{poretools} package is a flexible toolkit for exploring datasets
13826 generated by nanopore sequencing devices for the purposes of quality control and
13827 downstream analysis. Poretools operates directly on the native FAST5, a variant
13828 of the Hierarchical Data Format (HDF5) standard.")
13829 (license license:expat))))
13831 (define-public jamm
13834 (version "1.0.7.6")
13838 (uri (git-reference
13839 (url "https://github.com/mahmoudibrahim/JAMM")
13840 (commit (string-append "JAMMv" version))))
13841 (file-name (git-file-name name version))
13844 "0bsa5mf9n9q5jz7mmacrra41l7r8rac5vgsn6wv1fb52ya58b970"))))
13845 (build-system gnu-build-system)
13847 `(#:tests? #f ; there are none
13849 (modify-phases %standard-phases
13850 (delete 'configure)
13853 (lambda* (#:key inputs outputs #:allow-other-keys)
13854 (let* ((out (assoc-ref outputs "out"))
13855 (libexec (string-append out "/libexec/jamm"))
13856 (bin (string-append out "/bin")))
13857 (substitute* '("JAMM.sh"
13858 "SignalGenerator.sh")
13860 (string-append "sPath=\"" libexec "\"\n")))
13861 (for-each (lambda (file)
13862 (install-file file libexec))
13863 (list "bincalculator.r"
13875 (chmod script #o555)
13876 (install-file script bin)
13877 (wrap-program (string-append bin "/" script)
13878 `("PATH" ":" prefix
13879 (,(string-append (assoc-ref inputs "coreutils") "/bin")
13880 ,(string-append (assoc-ref inputs "gawk") "/bin")
13881 ,(string-append (assoc-ref inputs "perl") "/bin")
13882 ,(string-append (assoc-ref inputs "r-minimal") "/bin")))
13883 `("PERL5LIB" ":" prefix (,(getenv "PERL5LIB")))
13884 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
13885 (list "JAMM.sh" "SignalGenerator.sh")))
13889 ("coreutils" ,coreutils)
13892 ("r-minimal" ,r-minimal)
13893 ;;("r-parallel" ,r-parallel)
13894 ("r-signal" ,r-signal)
13895 ("r-mclust" ,r-mclust)))
13896 (home-page "https://github.com/mahmoudibrahim/JAMM")
13897 (synopsis "Peak finder for NGS datasets")
13899 "JAMM is a peak finder for next generation sequencing datasets (ChIP-Seq,
13900 ATAC-Seq, DNase-Seq, etc.) that can integrate replicates and assign peak
13901 boundaries accurately. JAMM is applicable to both broad and narrow
13903 (license license:gpl3+)))
13905 (define-public ngless
13912 (uri (git-reference
13913 (url "https://gitlab.com/ngless/ngless.git")
13914 (commit (string-append "v" version))))
13915 (file-name (git-file-name name version))
13918 "1wim8wpqyff080dfcazynrmjwqas38m24m0v350w245mmhrapdma"))))
13919 (build-system haskell-build-system)
13921 `(#:haddock? #f ; The haddock phase fails with: NGLess/CmdArgs.hs:20:1:
13922 ; error: parse error on input import
13923 ; import Options.Applicative
13925 (modify-phases %standard-phases
13926 (add-after 'unpack 'create-Versions.hs
13928 (substitute* "Makefile"
13929 (("BWA_VERSION = .*")
13930 (string-append "BWA_VERSION = "
13931 ,(package-version bwa) "\n"))
13932 (("SAM_VERSION = .*")
13933 (string-append "SAM_VERSION = "
13934 ,(package-version samtools) "\n"))
13935 (("PRODIGAL_VERSION = .*")
13936 (string-append "PRODIGAL_VERSION = "
13937 ,(package-version prodigal) "\n"))
13938 (("MINIMAP2_VERSION = .*")
13939 (string-append "MINIMAP2_VERSION = "
13940 ,(package-version minimap2) "\n")))
13941 (invoke "make" "NGLess/Dependencies/Versions.hs")
13943 (add-after 'create-Versions.hs 'create-cabal-file
13944 (lambda _ (invoke "hpack") #t))
13945 ;; These tools are expected to be installed alongside ngless.
13946 (add-after 'install 'link-tools
13947 (lambda* (#:key inputs outputs #:allow-other-keys)
13948 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
13949 (symlink (string-append (assoc-ref inputs "prodigal")
13951 (string-append bin "ngless-" ,version "-prodigal"))
13952 (symlink (string-append (assoc-ref inputs "minimap2")
13954 (string-append bin "ngless-" ,version "-minimap2"))
13955 (symlink (string-append (assoc-ref inputs "samtools")
13957 (string-append bin "ngless-" ,version "-samtools"))
13958 (symlink (string-append (assoc-ref inputs "bwa")
13960 (string-append bin "ngless-" ,version "-bwa"))
13963 `(("prodigal" ,prodigal)
13965 ("samtools" ,samtools)
13966 ("minimap2" ,minimap2)
13967 ("ghc-aeson" ,ghc-aeson)
13968 ("ghc-ansi-terminal" ,ghc-ansi-terminal)
13969 ("ghc-async" ,ghc-async)
13970 ("ghc-atomic-write" ,ghc-atomic-write)
13971 ("ghc-bytestring-lexing" ,ghc-bytestring-lexing)
13972 ("ghc-conduit" ,ghc-conduit)
13973 ("ghc-conduit-algorithms" ,ghc-conduit-algorithms)
13974 ("ghc-conduit-extra" ,ghc-conduit-extra)
13975 ("ghc-configurator" ,ghc-configurator)
13976 ("ghc-convertible" ,ghc-convertible)
13977 ("ghc-data-default" ,ghc-data-default)
13978 ("ghc-diagrams-core" ,ghc-diagrams-core)
13979 ("ghc-diagrams-lib" ,ghc-diagrams-lib)
13980 ("ghc-diagrams-svg" ,ghc-diagrams-svg)
13981 ("ghc-double-conversion" ,ghc-double-conversion)
13982 ("ghc-edit-distance" ,ghc-edit-distance)
13983 ("ghc-either" ,ghc-either)
13984 ("ghc-errors" ,ghc-errors)
13985 ("ghc-extra" ,ghc-extra)
13986 ("ghc-filemanip" ,ghc-filemanip)
13987 ("ghc-file-embed" ,ghc-file-embed)
13988 ("ghc-gitrev" ,ghc-gitrev)
13989 ("ghc-hashtables" ,ghc-hashtables)
13990 ("ghc-http-conduit" ,ghc-http-conduit)
13991 ("ghc-inline-c" ,ghc-inline-c)
13992 ("ghc-inline-c-cpp" ,ghc-inline-c-cpp)
13993 ("ghc-intervalmap" ,ghc-intervalmap)
13994 ("ghc-missingh" ,ghc-missingh)
13995 ("ghc-optparse-applicative" ,ghc-optparse-applicative)
13996 ("ghc-regex" ,ghc-regex)
13997 ("ghc-safe" ,ghc-safe)
13998 ("ghc-safeio" ,ghc-safeio)
13999 ("ghc-strict" ,ghc-strict)
14000 ("ghc-tar" ,ghc-tar)
14001 ("ghc-tar-conduit" ,ghc-tar-conduit)
14002 ("ghc-unliftio" ,ghc-unliftio)
14003 ("ghc-unliftio-core" ,ghc-unliftio-core)
14004 ("ghc-vector" ,ghc-vector)
14005 ("ghc-yaml" ,ghc-yaml)
14006 ("ghc-zlib" ,ghc-zlib)))
14009 ("r-hdf5r" ,r-hdf5r)
14010 ("r-iterators" ,r-iterators)
14011 ("r-itertools" ,r-itertools)
14012 ("r-matrix" ,r-matrix)))
14014 `(("ghc-hpack" ,ghc-hpack)
14015 ("ghc-quickcheck" ,ghc-quickcheck)
14016 ("ghc-test-framework" ,ghc-test-framework)
14017 ("ghc-test-framework-hunit",ghc-test-framework-hunit)
14018 ("ghc-test-framework-quickcheck2" ,ghc-test-framework-quickcheck2)
14019 ("ghc-test-framework-th" ,ghc-test-framework-th)))
14020 (home-page "https://gitlab.com/ngless/ngless")
14021 (synopsis "DSL for processing next-generation sequencing data")
14022 (description "Ngless is a domain-specific language for
14023 @dfn{next-generation sequencing} (NGS) data processing.")
14024 (license license:expat)))
14026 (define-public filtlong
14027 ;; The recommended way to install is to clone the git repository
14028 ;; https://github.com/rrwick/Filtlong#installation
14029 ;; and the lastest release is more than nine months old
14030 (let ((commit "d1bb46dfe8bc7efe6257b5ce222c04bfe8aedaab")
14034 (version (git-version "0.2.0" revision commit))
14038 (uri (git-reference
14039 (url "https://github.com/rrwick/Filtlong")
14041 (file-name (git-file-name name version))
14043 (base32 "1xr92r820x8qlkcr3b57iw223yq8vjgyi42jr79w2xgw47qzr575"))))
14044 (build-system gnu-build-system)
14046 `(#:tests? #f ; no check target
14048 (modify-phases %standard-phases
14049 (delete 'configure)
14051 (lambda* (#:key outputs #:allow-other-keys)
14052 (let* ((out (assoc-ref outputs "out"))
14053 (bin (string-append out "/bin"))
14054 (scripts (string-append out "/share/filtlong/scripts")))
14055 (install-file "bin/filtlong" bin)
14056 (install-file "scripts/histogram.py" scripts)
14057 (install-file "scripts/read_info_histograms.sh" scripts))
14059 (add-after 'install 'wrap-program
14060 (lambda* (#:key inputs outputs #:allow-other-keys)
14061 (let* ((out (assoc-ref outputs "out"))
14062 (path (getenv "PYTHONPATH")))
14063 (wrap-program (string-append out
14064 "/share/filtlong/scripts/histogram.py")
14065 `("PYTHONPATH" ":" prefix (,path))))
14067 (add-before 'check 'patch-tests
14069 (substitute* "scripts/read_info_histograms.sh"
14070 (("awk") (which "gawk")))
14073 `(("gawk" ,gawk) ;for read_info_histograms.sh
14074 ("python" ,python-2) ;required for histogram.py
14076 (home-page "https://github.com/rrwick/Filtlong/")
14077 (synopsis "Tool for quality filtering of Nanopore and PacBio data")
14079 "The Filtlong package is a tool for filtering long reads by quality.
14080 It can take a set of long reads and produce a smaller, better subset. It uses
14081 both read length (longer is better) and read identity (higher is better) when
14082 choosing which reads pass the filter.")
14083 (license (list license:gpl3 ;filtlong
14084 license:asl2.0))))) ;histogram.py
14086 (define-public nanopolish
14087 ;; The recommended way to install is to clone the git repository
14088 ;; <https://github.com/jts/nanopolish#installing-a-particular-release>.
14089 ;; Also, the differences between release and current version seem to be
14091 (let ((commit "6331dc4f15b9dfabb954ba3fae9d76b6c3ca6377")
14094 (name "nanopolish")
14095 (version (git-version "0.11.1" revision commit))
14099 (uri (git-reference
14100 (url "https://github.com/jts/nanopolish")
14103 (file-name (git-file-name name version))
14105 (base32 "15ikl3d37y49pwd7vx36xksgsqajhf24q7qqsnpl15dqqyy5qgbc"))
14106 (modules '((guix build utils)))
14109 (delete-file-recursively "htslib")
14111 (build-system gnu-build-system)
14114 `("HDF5=noinstall" "EIGEN=noinstall" "HTS=noinstall" "CC=gcc")
14115 #:tests? #f ; no check target
14117 (modify-phases %standard-phases
14118 (add-after 'unpack 'find-eigen
14119 (lambda* (#:key inputs #:allow-other-keys)
14121 (string-append (assoc-ref inputs "eigen")
14123 (or (getenv "CPATH") "")))
14125 (delete 'configure)
14127 (lambda* (#:key outputs #:allow-other-keys)
14128 (let* ((out (assoc-ref outputs "out"))
14129 (bin (string-append out "/bin"))
14130 (scripts (string-append out "/share/nanopolish/scripts")))
14132 (install-file "nanopolish" bin)
14133 (for-each (lambda (file) (install-file file scripts))
14134 (find-files "scripts" ".*"))
14136 (add-after 'install 'wrap-programs
14137 (lambda* (#:key outputs #:allow-other-keys)
14138 (for-each (lambda (file)
14139 (wrap-program file `("PYTHONPATH" ":" prefix (,path))))
14140 (find-files "/share/nanopolish/scripts" "\\.py"))
14141 (for-each (lambda (file)
14142 (wrap-program file `("PERL5LIB" ":" prefix (,path))))
14143 (find-files "/share/nanopolish/scripts" "\\.pl"))
14150 ("python" ,python-wrapper)
14151 ("python-biopython" ,python-biopython)
14152 ("python-numpy" ,python-numpy)
14153 ("python-pysam" ,python-pysam)
14154 ("python-scikit-learn" , python-scikit-learn)
14155 ("python-scipy" ,python-scipy)
14157 (home-page "https://github.com/jts/nanopolish")
14158 (synopsis "Signal-level analysis of Oxford Nanopore sequencing data")
14160 "This package analyses the Oxford Nanopore sequencing data at signal-level.
14161 Nanopolish can calculate an improved consensus sequence for a draft genome
14162 assembly, detect base modifications, call SNPs (Single nucleotide
14163 polymorphisms) and indels with respect to a reference genome and more.")
14164 (license license:expat))))
14166 (define-public cnvkit
14173 (uri (git-reference
14174 (url "https://github.com/etal/cnvkit")
14175 (commit (string-append "v" version))))
14176 (file-name (git-file-name name version))
14178 (base32 "0g2f78k68yglmj4fsfmgs8idqv3di9aj53fg0ld0hqljg8chhh82"))))
14179 (build-system python-build-system)
14181 `(("python-biopython" ,python-biopython)
14182 ("python-future" ,python-future)
14183 ("python-matplotlib" ,python-matplotlib)
14184 ("python-numpy" ,python-numpy)
14185 ("python-reportlab" ,python-reportlab)
14186 ("python-pandas" ,python-pandas)
14187 ("python-pysam" ,python-pysam)
14188 ("python-pyfaidx" ,python-pyfaidx)
14189 ("python-scipy" ,python-scipy)
14191 ("r-dnacopy" ,r-dnacopy)))
14192 (home-page "https://cnvkit.readthedocs.org/")
14193 (synopsis "Copy number variant detection from targeted DNA sequencing")
14195 "CNVkit is a Python library and command-line software toolkit to infer
14196 and visualize copy number from high-throughput DNA sequencing data. It is
14197 designed for use with hybrid capture, including both whole-exome and custom
14198 target panels, and short-read sequencing platforms such as Illumina and Ion
14200 (license license:asl2.0)))
14202 (define-public python-pyfit-sne
14204 (name "python-pyfit-sne")
14209 (uri (git-reference
14210 (url "https://github.com/KlugerLab/pyFIt-SNE")
14212 (file-name (git-file-name name version))
14214 (base32 "13wh3qkzs56azmmgnxib6xfr29g7xh09sxylzjpni5j0pp0rc5qw"))))
14215 (build-system python-build-system)
14217 `(("python-numpy" ,python-numpy)))
14221 `(("python-cython" ,python-cython)))
14222 (home-page "https://github.com/KlugerLab/pyFIt-SNE")
14223 (synopsis "FFT-accelerated Interpolation-based t-SNE")
14225 "t-Stochastic Neighborhood Embedding (t-SNE) is a highly successful
14226 method for dimensionality reduction and visualization of high dimensional
14227 datasets. A popular implementation of t-SNE uses the Barnes-Hut algorithm to
14228 approximate the gradient at each iteration of gradient descent. This package
14229 is a Cython wrapper for FIt-SNE.")
14230 (license license:bsd-4)))
14232 (define-public bbmap
14238 (uri (string-append
14239 "mirror://sourceforge/bbmap/BBMap_" version ".tar.gz"))
14242 "1q4rfhxcb6z3gm8zg2davjz98w22lkf4hm9ikxz9kdl93pil3wkd"))))
14243 (build-system ant-build-system)
14245 `(#:build-target "dist"
14246 #:tests? #f ; there are none
14248 (list (string-append "-Dmpijar="
14249 (assoc-ref %build-inputs "java-openmpi")
14251 #:modules ((guix build ant-build-system)
14253 (guix build java-utils))
14255 (modify-phases %standard-phases
14256 (add-after 'build 'build-jni-library
14258 (with-directory-excursion "jni"
14259 (invoke "make" "-f" "makefile.linux"))))
14260 ;; There is no install target
14261 (replace 'install (install-jars "dist"))
14262 (add-after 'install 'install-scripts-and-documentation
14263 (lambda* (#:key outputs #:allow-other-keys)
14264 (substitute* "calcmem.sh"
14265 (("\\| awk ") (string-append "| " (which "awk") " ")))
14266 (let* ((scripts (find-files "." "\\.sh$"))
14267 (out (assoc-ref outputs "out"))
14268 (bin (string-append out "/bin"))
14269 (doc (string-append out "/share/doc/bbmap"))
14270 (jni (string-append out "/lib/jni")))
14271 (substitute* scripts
14272 (("\\$DIR\"\"docs") doc)
14274 (string-append "CP=" out "/share/java/BBTools.jar\n"))
14275 (("^NATIVELIBDIR.*")
14276 (string-append "NATIVELIBDIR=" jni "\n"))
14278 (string-append "CMD=\"" (which "java"))))
14279 (for-each (lambda (script) (install-file script bin)) scripts)
14281 ;; Install JNI library
14282 (install-file "jni/libbbtoolsjni.so" jni)
14284 ;; Install documentation
14285 (install-file "docs/readme.txt" doc)
14286 (copy-recursively "docs/guides" doc))
14291 ("java-eclipse-jdt-core" ,java-eclipse-jdt-core)
14292 ("java-eclipse-jdt-compiler-apt" ,java-eclipse-jdt-compiler-apt)
14293 ("java-openmpi" ,java-openmpi)))
14294 (home-page "https://sourceforge.net/projects/bbmap/")
14295 (synopsis "Aligner and other tools for short sequencing reads")
14297 "This package provides bioinformatic tools to align, deduplicate,
14298 reformat, filter and normalize DNA and RNA-seq data. It includes the
14299 following tools: BBMap, a short read aligner for DNA and RNA-seq data; BBNorm,
14300 a kmer-based error-correction and normalization tool; Dedupe, a tool to
14301 simplify assemblies by removing duplicate or contained subsequences that share
14302 a target percent identity; Reformat, to convert reads between
14303 fasta/fastq/scarf/fasta+qual/sam, interleaved/paired, and ASCII-33/64, at over
14304 500 MB/s; and BBDuk, a tool to filter, trim, or mask reads with kmer matches
14305 to an artifact/contaminant file.")
14306 (license license:bsd-3)))
14308 (define-public velvet
14314 (uri (string-append "https://www.ebi.ac.uk/~zerbino/velvet/"
14315 "velvet_" version ".tgz"))
14318 "0h3njwy66p6bx14r3ar1byb0ccaxmxka4c65rn4iybyiqa4d8kc8"))
14319 ;; Delete bundled libraries
14320 (modules '((guix build utils)))
14323 (delete-file "Manual.pdf")
14324 (delete-file-recursively "third-party")
14326 (build-system gnu-build-system)
14328 `(#:make-flags '("OPENMP=t")
14329 #:test-target "test"
14331 (modify-phases %standard-phases
14332 (delete 'configure)
14333 (add-after 'unpack 'fix-zlib-include
14335 (substitute* "src/binarySequences.c"
14336 (("../third-party/zlib-1.2.3/zlib.h") "zlib.h"))
14339 (lambda* (#:key outputs #:allow-other-keys)
14340 (let* ((out (assoc-ref outputs "out"))
14341 (bin (string-append out "/bin"))
14342 (doc (string-append out "/share/doc/velvet")))
14345 (install-file "velveth" bin)
14346 (install-file "velvetg" bin)
14347 (install-file "Manual.pdf" doc)
14348 (install-file "Columbus_manual.pdf" doc)
14351 `(("openmpi" ,openmpi)
14354 `(("texlive" ,(texlive-union (list texlive-latex-graphics
14355 texlive-latex-hyperref)))))
14356 (home-page "https://www.ebi.ac.uk/~zerbino/velvet/")
14357 (synopsis "Nucleic acid sequence assembler for very short reads")
14359 "Velvet is a de novo genomic assembler specially designed for short read
14360 sequencing technologies, such as Solexa or 454. Velvet currently takes in
14361 short read sequences, removes errors then produces high quality unique
14362 contigs. It then uses paired read information, if available, to retrieve the
14363 repeated areas between contigs.")
14364 (license license:gpl2+)))
14366 (define-public python-velocyto
14368 (name "python-velocyto")
14369 (version "0.17.17")
14373 (uri (pypi-uri "velocyto" version))
14376 "0fgygyzqgrq32dv6a00biq1p1cwi6kbl5iqblxq1kklj6b2mzmhs"))))
14377 (build-system python-build-system)
14379 `(("python-joblib" ,python-joblib)))
14381 `(("python-click" ,python-click)
14382 ("python-cython" ,python-cython)
14383 ("python-h5py" ,python-h5py)
14384 ("python-loompy" ,python-loompy)
14385 ("python-matplotlib" ,python-matplotlib)
14386 ("python-numba" ,python-numba)
14387 ("python-numpy" ,python-numpy)
14388 ("python-pandas" ,python-pandas)
14389 ("python-pysam" ,python-pysam)
14390 ("python-scikit-learn" ,python-scikit-learn)
14391 ("python-scipy" ,python-scipy)))
14392 (home-page "https://github.com/velocyto-team/velocyto.py")
14393 (synopsis "RNA velocity analysis for single cell RNA-seq data")
14395 "Velocyto is a library for the analysis of RNA velocity. Velocyto
14396 includes a command line tool and an analysis pipeline.")
14397 (license license:bsd-2)))
14399 (define-public arriba
14406 (uri (string-append "https://github.com/suhrig/arriba/releases/"
14407 "download/v" version "/arriba_v" version ".tar.gz"))
14410 "0jx9656ry766vb8z08m1c3im87b0c82qpnjby9wz4kcz8vn87dx2"))))
14411 (build-system gnu-build-system)
14413 `(#:tests? #f ; there are none
14415 (modify-phases %standard-phases
14416 (replace 'configure
14417 (lambda* (#:key inputs #:allow-other-keys)
14418 (let ((htslib (assoc-ref inputs "htslib")))
14419 (substitute* "Makefile"
14420 (("-I\\$\\(HTSLIB\\)/htslib")
14421 (string-append "-I" htslib "/include/htslib"))
14422 ((" \\$\\(HTSLIB\\)/libhts.a")
14423 (string-append " " htslib "/lib/libhts.so"))))
14424 (substitute* "run_arriba.sh"
14425 (("^STAR ") (string-append (which "STAR") " "))
14426 (("samtools --version-only")
14427 (string-append (which "samtools") " --version-only"))
14428 (("samtools index")
14429 (string-append (which "samtools") " index"))
14431 (string-append (which "samtools") " sort")))
14434 (lambda* (#:key outputs #:allow-other-keys)
14435 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
14436 (install-file "arriba" bin)
14437 (install-file "run_arriba.sh" bin)
14438 (install-file "draw_fusions.R" bin)
14439 (wrap-program (string-append bin "/draw_fusions.R")
14440 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
14443 `(("htslib" ,htslib)
14444 ("r-minimal" ,r-minimal)
14445 ("r-circlize" ,r-circlize)
14446 ("r-genomicalignments" ,r-genomicalignments)
14447 ("r-genomicranges" ,r-genomicranges)
14448 ("samtools" ,samtools)
14451 (home-page "https://github.com/suhrig/arriba")
14452 (synopsis "Gene fusion detection from RNA-Seq data ")
14454 "Arriba is a command-line tool for the detection of gene fusions from
14455 RNA-Seq data. It was developed for the use in a clinical research setting.
14456 Therefore, short runtimes and high sensitivity were important design criteria.
14457 It is based on the fast STAR aligner and the post-alignment runtime is
14458 typically just around two minutes. In contrast to many other fusion detection
14459 tools which build on STAR, Arriba does not require to reduce the
14460 @code{alignIntronMax} parameter of STAR to detect small deletions.")
14461 ;; All code is under the Expat license with the exception of
14462 ;; "draw_fusions.R", which is under GPLv3.
14463 (license (list license:expat license:gpl3))))
14465 (define-public adapterremoval
14467 (name "adapterremoval")
14472 (uri (git-reference
14473 (url "https://github.com/MikkelSchubert/adapterremoval")
14474 (commit (string-append "v" version))))
14475 (file-name (git-file-name name version))
14478 "1nf3ki5pfzalhrx2fr1y6pfqfi133yj2m7q4fj9irf5fb94bapwr"))))
14479 (build-system gnu-build-system)
14481 `(#:make-flags (list "COLOR_BUILD=no"
14482 (string-append "PREFIX="
14483 (assoc-ref %outputs "out")))
14484 #:test-target "test"
14486 (modify-phases %standard-phases
14487 (delete 'configure))))
14490 (home-page "https://adapterremoval.readthedocs.io/")
14491 (synopsis "Rapid sequence adapter trimming, identification, and read merging")
14493 "This program searches for and removes remnant adapter sequences from
14494 @dfn{High-Throughput Sequencing} (HTS) data and (optionally) trims low quality
14495 bases from the 3' end of reads following adapter removal. AdapterRemoval can
14496 analyze both single end and paired end data, and can be used to merge
14497 overlapping paired-ended reads into (longer) consensus sequences.
14498 Additionally, the AdapterRemoval may be used to recover a consensus adapter
14499 sequence for paired-ended data, for which this information is not available.")
14500 (license license:gpl3+)))
14502 (define-public pplacer
14503 (let ((commit "807f6f3"))
14506 ;; The commit should be updated with each version change.
14507 (version "1.1.alpha19")
14511 (uri (git-reference
14512 (url "https://github.com/matsen/pplacer")
14513 (commit (string-append "v" version))))
14514 (file-name (git-file-name name version))
14516 (base32 "11ppbbbx20p2g9wj3ff64dhnarb12q79v7qh4rk0gj6lkbz4n7cn"))))
14517 (build-system ocaml-build-system)
14519 `(#:modules ((guix build ocaml-build-system)
14523 (modify-phases %standard-phases
14524 (delete 'configure)
14525 (add-after 'unpack 'fix-build-with-latest-ocaml
14527 (substitute* "myocamlbuild.ml"
14528 (("dep \\[\"c_pam\"\\]" m)
14529 (string-append "flag [\"ocaml\"; \"compile\"] (A \"-unsafe-string\");\n"
14531 (("let run_and_read" m)
14536 let pos = String.index s ch in
14537 x := (String.before s pos)::!x;
14538 go (String.after s (pos + 1))
14541 with Not_found -> !x
14542 let split_nl s = split s '\\n'
14543 let before_space s =
14544 try String.before s (String.index s ' ')
14545 with Not_found -> s
14548 (("run_and_read \"ocamlfind list \\| cut -d' ' -f1\"" m)
14549 (string-append "List.map before_space (split_nl & " m ")"))
14550 ((" blank_sep_strings &") "")
14551 ((" Lexing.from_string &") ""))
14553 (add-after 'unpack 'replace-bundled-cddlib
14554 (lambda* (#:key inputs #:allow-other-keys)
14555 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
14556 (local-dir "cddlib_guix"))
14558 (with-directory-excursion local-dir
14559 (invoke "tar" "xvf" cddlib-src))
14560 (let ((cddlib-src-folder
14561 (string-append local-dir "/"
14562 (list-ref (scandir local-dir) 2)
14564 (for-each make-file-writable (find-files "cdd_src" ".*"))
14568 (string-append "cdd_src/" (basename file))))
14569 (find-files cddlib-src-folder ".*[ch]$")))
14571 (add-after 'unpack 'fix-makefile
14573 ;; Remove system calls to 'git'.
14574 (substitute* "Makefile"
14575 (("^DESCRIPT:=pplacer-.*")
14577 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
14578 (substitute* "myocamlbuild.ml"
14579 (("git describe --tags --long .*\\\" with")
14581 "echo -n v" ,version "-" ,commit "\" with")))
14584 (lambda* (#:key outputs #:allow-other-keys)
14585 (let* ((out (assoc-ref outputs "out"))
14586 (bin (string-append out "/bin")))
14587 (copy-recursively "bin" bin))
14589 #:ocaml ,ocaml-4.07
14590 #:findlib ,ocaml4.07-findlib))
14592 `(("zlib" ,zlib "static")
14594 ("ocaml-ounit" ,(package-with-ocaml4.07 ocaml-ounit))
14595 ("ocaml-batteries" ,(package-with-ocaml4.07 ocaml-batteries))
14596 ("ocaml-camlzip" ,(package-with-ocaml4.07 camlzip))
14597 ("ocaml-csv" ,(package-with-ocaml4.07 ocaml-csv))
14598 ("ocaml-sqlite3" ,ocaml4.07-sqlite3)
14599 ("ocaml-xmlm" ,(package-with-ocaml4.07 ocaml-xmlm))
14600 ("ocaml-mcl" ,(package-with-ocaml4.07 ocaml-mcl))
14601 ("ocaml-gsl" ,ocaml4.07-gsl-1)))
14603 `(("cddlib-src" ,(package-source cddlib))
14604 ("ocamlbuild" ,(package-with-ocaml4.07 ocamlbuild))
14605 ("pkg-config" ,pkg-config)))
14607 `(("pplacer-scripts" ,pplacer-scripts)))
14608 (synopsis "Phylogenetic placement of biological sequences")
14610 "Pplacer places query sequences on a fixed reference phylogenetic tree
14611 to maximize phylogenetic likelihood or posterior probability according to a
14612 reference alignment. Pplacer is designed to be fast, to give useful
14613 information about uncertainty, and to offer advanced visualization and
14614 downstream analysis.")
14615 (home-page "https://matsen.fhcrc.org/pplacer/")
14616 (license license:gpl3))))
14618 ;; This package is installed alongside 'pplacer'. It is a separate package so
14619 ;; that it can use the python-build-system for the scripts that are
14620 ;; distributed alongside the main OCaml binaries.
14621 (define pplacer-scripts
14624 (name "pplacer-scripts")
14625 (build-system python-build-system)
14627 `(#:python ,python-2
14629 (modify-phases %standard-phases
14630 (add-after 'unpack 'enter-scripts-dir
14631 (lambda _ (chdir "scripts") #t))
14633 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t))
14634 (add-after 'install 'wrap-executables
14635 (lambda* (#:key inputs outputs #:allow-other-keys)
14636 (let* ((out (assoc-ref outputs "out"))
14637 (bin (string-append out "/bin")))
14638 (let ((path (string-append
14639 (assoc-ref inputs "hmmer") "/bin:"
14640 (assoc-ref inputs "infernal") "/bin")))
14642 (wrap-program (string-append bin "/refpkg_align.py")
14643 `("PATH" ":" prefix (,path))))
14644 (let ((path (string-append
14645 (assoc-ref inputs "hmmer") "/bin")))
14646 (wrap-program (string-append bin "/hrefpkg_query.py")
14647 `("PATH" ":" prefix (,path)))))
14650 `(("infernal" ,infernal)
14653 `(("python-biopython" ,python2-biopython)
14654 ("taxtastic" ,taxtastic)))
14655 (synopsis "Pplacer Python scripts")))
14657 (define-public python2-checkm-genome
14659 (name "python2-checkm-genome")
14664 (uri (pypi-uri "checkm-genome" version))
14667 "0bm8gpxjmzxsxxl8lzwqhgx8g1dlnmp6znz7wv3hgb0gdjbf9dzz"))))
14668 (build-system python-build-system)
14670 `(#:python ,python-2
14671 #:tests? #f)) ; some tests are interactive
14673 `(("python-dendropy" ,python2-dendropy)
14674 ("python-matplotlib" ,python2-matplotlib)
14675 ("python-numpy" ,python2-numpy)
14676 ("python-pysam" ,python2-pysam)
14677 ("python-scipy" ,python2-scipy)))
14678 (home-page "https://pypi.org/project/Checkm/")
14679 (synopsis "Assess the quality of putative genome bins")
14681 "CheckM provides a set of tools for assessing the quality of genomes
14682 recovered from isolates, single cells, or metagenomes. It provides robust
14683 estimates of genome completeness and contamination by using collocated sets of
14684 genes that are ubiquitous and single-copy within a phylogenetic lineage.
14685 Assessment of genome quality can also be examined using plots depicting key
14686 genomic characteristics (e.g., GC, coding density) which highlight sequences
14687 outside the expected distributions of a typical genome. CheckM also provides
14688 tools for identifying genome bins that are likely candidates for merging based
14689 on marker set compatibility, similarity in genomic characteristics, and
14690 proximity within a reference genome.")
14691 (license license:gpl3+)))
14693 (define-public umi-tools
14700 (uri (pypi-uri "umi_tools" version))
14703 "08y3vz1vcx09whmbsn722lcs6jl9wyrh9i4p3k8j4cb1i32bij4a"))))
14704 (build-system python-build-system)
14706 `(("python-pandas" ,python-pandas)
14707 ("python-future" ,python-future)
14708 ("python-scipy" ,python-scipy)
14709 ("python-matplotlib" ,python-matplotlib)
14710 ("python-regex" ,python-regex)
14711 ("python-pysam" ,python-pysam)))
14713 `(("python-cython" ,python-cython)))
14714 (home-page "https://github.com/CGATOxford/UMI-tools")
14715 (synopsis "Tools for analyzing unique modular identifiers")
14716 (description "This package provides tools for dealing with @dfn{Unique
14717 Molecular Identifiers} (UMIs) and @dfn{Random Molecular Tags} (RMTs) in
14718 genetic sequences. There are six tools: the @code{extract} and
14719 @code{whitelist} commands are used to prepare a fastq containing UMIs @code{+/-}
14720 cell barcodes for alignment. The remaining commands, @code{group},
14721 @code{dedup}, and @{count}/@code{count_tab}, are used to identify PCR
14722 duplicates using the UMIs and perform different levels of analysis depending
14723 on the needs of the user.")
14724 (license license:expat)))
14726 (define-public ataqv
14733 (uri (git-reference
14734 (url "https://github.com/ParkerLab/ataqv")
14736 (file-name (git-file-name name version))
14739 "031xr6jx1aprh26y5b1lv3gzrlmzg4alfl73vvshymx8cq8asrqi"))))
14740 (build-system gnu-build-system)
14743 (list (string-append "prefix=" (assoc-ref %outputs "out"))
14744 (string-append "BOOST_ROOT="
14745 (assoc-ref %build-inputs "boost"))
14746 (string-append "HTSLIB_ROOT="
14747 (assoc-ref %build-inputs "htslib")))
14748 #:test-target "test"
14750 (modify-phases %standard-phases
14751 (delete 'configure))))
14755 ("ncurses" ,ncurses)
14759 (home-page "https://github.com/ParkerLab/ataqv")
14760 (synopsis "Toolkit for quality control and visualization of ATAC-seq data")
14761 (description "This package provides a toolkit for measuring and comparing
14762 ATAC-seq results. It was written to make it easier to spot differences that
14763 might be caused by ATAC-seq library prep or sequencing. The main program,
14764 @code{ataqv}, examines aligned reads and reports some basic metrics.")
14765 (license license:gpl3+)))
14767 (define-public r-psiplot
14774 (uri (git-reference
14775 (url "https://github.com/kcha/psiplot")
14776 (commit (string-append "v" version))))
14777 (file-name (git-file-name name version))
14779 (base32 "08438h16cfry5kqh3y9hs8q1b1a8bxhblsm75knviz5r6q0n1jxh"))))
14780 (build-system r-build-system)
14782 `(("r-mass" ,r-mass)
14783 ("r-dplyr" ,r-dplyr)
14784 ("r-tidyr" ,r-tidyr)
14785 ("r-purrr" ,r-purrr)
14786 ("r-readr" ,r-readr)
14787 ("r-magrittr" ,r-magrittr)
14788 ("r-ggplot2" ,r-ggplot2)))
14789 (home-page "https://github.com/kcha/psiplot")
14790 (synopsis "Plot percent spliced-in values of alternatively-spliced exons")
14792 "PSIplot is an R package for generating plots of @dfn{percent
14793 spliced-in} (PSI) values of alternatively-spliced exons that were computed by
14794 vast-tools, an RNA-Seq pipeline for alternative splicing analysis. The plots
14795 are generated using @code{ggplot2}.")
14796 (license license:expat)))
14798 (define-public python-ont-fast5-api
14800 (name "python-ont-fast5-api")
14805 (uri (git-reference
14806 (url "https://github.com/nanoporetech/ont_fast5_api")
14807 (commit (string-append "release_" version))))
14808 (file-name (git-file-name name version))
14811 "03cbq4zbbwhll8ml2m9k8sa31mirsvcbjkrq1yna0kkzz9fad5fm"))))
14812 (build-system python-build-system)
14814 `(("python-numpy" ,python-numpy)
14815 ("python-six" ,python-six)
14816 ("python-h5py" ,python-h5py)
14817 ("python-progressbar33" ,python-progressbar33)))
14818 (home-page "https://github.com/nanoporetech/ont_fast5_api")
14819 (synopsis "Interface to HDF5 files of the Oxford Nanopore fast5 file format")
14821 "This package provides a concrete implementation of the fast5 file schema
14822 using the generic @code{h5py} library, plain-named methods to interact with
14823 and reflect the fast5 file schema, and tools to convert between
14824 @code{multi_read} and @code{single_read} formats.")
14825 (license license:mpl2.0)))
14827 (define-public tbsp
14828 (let ((commit "ec8fff4410cfb13a677dbbb95cbbc60217e64907")
14832 (version (git-version "1.0.0" revision commit))
14836 (uri (git-reference
14837 (url "https://github.com/phoenixding/tbsp")
14839 (file-name (git-file-name name version))
14842 "025ym14x8gbd6hb55lsinqj6f5qzw36i10klgs7ldzxxd7s39ki1"))))
14843 (build-system python-build-system)
14844 (arguments '(#:tests? #f)) ; no tests included
14846 `(("python-matplotlib" ,python-matplotlib)
14847 ("python-networkx" ,python-networkx)
14848 ("python-numpy" ,python-numpy)
14849 ("python-pybigwig" ,python-pybigwig)
14850 ("python-biopython" ,python-biopython)
14851 ("python-scikit-learn" ,python-scikit-learn)
14852 ("python-scipy" ,python-scipy)))
14853 (home-page "https://github.com/phoenixding/tbsp/")
14854 (synopsis "SNP-based trajectory inference")
14856 "Several studies focus on the inference of developmental and response
14857 trajectories from single cell RNA-Seq (scRNA-Seq) data. A number of
14858 computational methods, often referred to as pseudo-time ordering, have been
14859 developed for this task. CRISPR has also been used to reconstruct lineage
14860 trees by inserting random mutations. The tbsp package implements an
14861 alternative method to detect significant, cell type specific sequence
14862 mutations from scRNA-Seq data.")
14863 (license license:expat))))
14865 (define-public tabixpp
14871 (uri (git-reference
14872 (url "https://github.com/ekg/tabixpp")
14873 (commit (string-append "v" version))))
14874 (file-name (git-file-name name version))
14876 (base32 "1k2a3vbq96ic4lw72iwp5s3mwwc4xhdffjj584yn6l9637q9j1yd"))
14877 (modules '((guix build utils)))
14880 (delete-file-recursively "htslib") #t))))
14881 (build-system gnu-build-system)
14883 `(("htslib" ,htslib)
14886 `(#:tests? #f ; There are no tests to run.
14888 (modify-phases %standard-phases
14889 (delete 'configure) ; There is no configure phase.
14890 ;; The build phase needs overriding the location of htslib.
14892 (lambda* (#:key inputs #:allow-other-keys)
14893 (let ((htslib-ref (assoc-ref inputs "htslib")))
14895 (string-append "HTS_LIB=" htslib-ref "/lib/libhts.a")
14896 (string-append "INCLUDES= -I" htslib-ref "/include/htslib")
14897 "HTS_HEADERS=" ; No need to check for headers here.
14898 (string-append "LIBPATH=-L. -L" htslib-ref "/include"))
14899 (invoke "g++" "-shared" "-o" "libtabixpp.so" "tabix.o" "-lhts")
14900 (invoke "ar" "rcs" "libtabixpp.a" "tabix.o"))))
14902 (lambda* (#:key outputs #:allow-other-keys)
14903 (let* ((out (assoc-ref outputs "out"))
14904 (lib (string-append out "/lib"))
14905 (bin (string-append out "/bin")))
14906 (install-file "tabix++" bin)
14907 (install-file "libtabixpp.so" lib)
14908 (install-file "libtabixpp.a" lib)
14909 (install-file "tabix.hpp" (string-append out "/include"))
14910 (mkdir-p (string-append lib "/pkgconfig"))
14911 (with-output-to-file (string-append lib "/pkgconfig/tabixpp.pc")
14913 (format #t "prefix=~a~@
14914 exec_prefix=${prefix}~@
14915 libdir=${exec_prefix}/lib~@
14916 includedir=${prefix}/include~@
14921 Description: C++ wrapper around tabix project~@
14922 Libs: -L${libdir} -ltabixpp~@
14923 Cflags: -I${includedir}~%"
14926 (home-page "https://github.com/ekg/tabixpp")
14927 (synopsis "C++ wrapper around tabix project")
14928 (description "This is a C++ wrapper around the Tabix project which abstracts
14929 some of the details of opening and jumping in tabix-indexed files.")
14930 (license license:expat)))
14932 (define-public smithwaterman
14933 (let ((commit "2610e259611ae4cde8f03c72499d28f03f6d38a7"))
14935 (name "smithwaterman")
14936 (version (git-version "0.0.0" "2" commit))
14939 (uri (git-reference
14940 (url "https://github.com/ekg/smithwaterman/")
14942 (file-name (git-file-name name version))
14944 (base32 "0i9d8zrxpiracw3mxzd9siybpy62p06rqz9mc2w93arajgbk45bs"))))
14945 (build-system gnu-build-system)
14947 `(#:tests? #f ; There are no tests to run.
14948 #:make-flags '("libsw.a" "all")
14950 (modify-phases %standard-phases
14951 (delete 'configure) ; There is no configure phase.
14952 (add-after 'unpack 'patch-source
14954 (substitute* "Makefile"
14955 (("-c ") "-c -fPIC "))
14957 (add-after 'build 'build-dynamic
14960 "-shared" "-o" "libsmithwaterman.so"
14961 "smithwaterman.o" "SmithWatermanGotoh.o"
14962 "disorder.o" "BandedSmithWaterman.o"
14963 "LeftAlign.o" "Repeats.o" "IndelAllele.o")))
14965 (lambda* (#:key outputs #:allow-other-keys)
14966 (let* ((out (assoc-ref outputs "out"))
14967 (bin (string-append out "/bin"))
14968 (lib (string-append out "/lib")))
14969 (install-file "smithwaterman" bin)
14972 (install-file file (string-append out "/include/smithwaterman")))
14973 (find-files "." "\\.h$"))
14974 (install-file "libsmithwaterman.so" lib)
14975 (install-file "libsw.a" lib)
14976 (mkdir-p (string-append lib "/pkgconfig"))
14977 (with-output-to-file (string-append lib "/pkgconfig/smithwaterman.pc")
14979 (format #t "prefix=~a~@
14980 exec_prefix=${prefix}~@
14981 libdir=${exec_prefix}/lib~@
14982 includedir=${prefix}/include/smithwaterman~@
14985 Name: smithwaterman~@
14987 Description: smith-waterman-gotoh alignment algorithm~@
14988 Libs: -L${libdir} -lsmithwaterman~@
14989 Cflags: -I${includedir}~%"
14992 (home-page "https://github.com/ekg/smithwaterman")
14993 (synopsis "Implementation of the Smith-Waterman algorithm")
14994 (description "Implementation of the Smith-Waterman algorithm.")
14995 ;; The licensing terms are unclear: https://github.com/ekg/smithwaterman/issues/9.
14996 (license (list license:gpl2 license:expat)))))
14998 (define-public multichoose
15000 (name "multichoose")
15004 (uri (git-reference
15005 (url "https://github.com/ekg/multichoose/")
15006 (commit (string-append "v" version))))
15007 (file-name (git-file-name name version))
15009 (base32 "0ci5fqvmpamwgxvmyd79ygj6n3bnbl3vc7b6h1sxz58186sm3pfs"))))
15010 (build-system gnu-build-system)
15012 `(#:tests? #f ; Tests require node.
15014 (modify-phases %standard-phases
15015 (delete 'configure) ; There is no configure phase.
15017 (lambda* (#:key outputs #:allow-other-keys)
15018 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15019 ;; TODO: There are Python modules for these programs too.
15020 (install-file "multichoose" bin)
15021 (install-file "multipermute" bin))
15023 (home-page "https://github.com/ekg/multichoose")
15024 (synopsis "Efficient loopless multiset combination generation algorithm")
15025 (description "This library implements an efficient loopless multiset
15026 combination generation algorithm which is (approximately) described in
15027 \"Loopless algorithms for generating permutations, combinations, and other
15028 combinatorial configurations.\", G. Ehrlich - Journal of the ACM (JACM),
15029 1973. (Algorithm 7.)")
15030 (license license:expat)))
15032 (define-public fsom
15033 (let ((commit "a6ef318fbd347c53189384aef7f670c0e6ce89a3"))
15036 (version (git-version "0.0.0" "1" commit))
15039 (uri (git-reference
15040 (url "https://github.com/ekg/fsom/")
15042 (file-name (git-file-name name version))
15044 (base32 "0gw1lpvr812pywg9y546x0h1hhj261xwls41r6kqhddjlrcjc0pi"))))
15045 (build-system gnu-build-system)
15047 `(#:tests? #f ; There are no tests to run.
15049 (modify-phases %standard-phases
15050 (delete 'configure) ; There is no configure phase.
15052 (lambda* (#:key outputs #:allow-other-keys)
15053 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15054 (install-file "fsom" bin))
15056 (home-page "https://github.com/ekg/fsom")
15057 (synopsis "Manage SOM (Self-Organizing Maps) neural networks")
15058 (description "A tiny C library for managing SOM (Self-Organizing Maps)
15060 (license license:gpl3))))
15062 (define-public fastahack
15068 (uri (git-reference
15069 (url "https://github.com/ekg/fastahack/")
15070 (commit (string-append "v" version))))
15071 (file-name (git-file-name name version))
15073 (base32 "0rp1blskhzxf7vbh253ibpxbgl9wwgyzf1wbkxndi08d3j4vcss9"))))
15074 (build-system gnu-build-system)
15076 `(#:tests? #f ; Unclear how to run tests: https://github.com/ekg/fastahack/issues/15
15078 (modify-phases %standard-phases
15079 (delete 'configure) ; There is no configure phase.
15080 (add-after 'unpack 'patch-source
15082 (substitute* "Makefile"
15083 (("-c ") "-c -fPIC "))
15085 (add-after 'build 'build-dynamic
15088 "-shared" "-o" "libfastahack.so"
15089 "Fasta.o" "FastaHack.o" "split.o" "disorder.o")))
15091 (lambda* (#:key outputs #:allow-other-keys)
15092 (let* ((out (assoc-ref outputs "out"))
15093 (lib (string-append out "/lib"))
15094 (bin (string-append out "/bin")))
15095 (mkdir-p (string-append out "/include/fastahack"))
15098 (install-file file (string-append out "/include/fastahack")))
15099 (find-files "." "\\.h$"))
15100 (install-file "fastahack" bin)
15101 (install-file "libfastahack.so" lib)
15102 (mkdir-p (string-append lib "/pkgconfig"))
15103 (with-output-to-file (string-append lib "/pkgconfig/fastahack.pc")
15105 (format #t "prefix=~a~@
15106 exec_prefix=${prefix}~@
15107 libdir=${exec_prefix}/lib~@
15108 includedir=${prefix}/include/fastahack~@
15113 Description: Indexing and sequence extraction from FASTA files~@
15114 Libs: -L${libdir} -lfastahack~@
15115 Cflags: -I${includedir}~%"
15118 (home-page "https://github.com/ekg/fastahack")
15119 (synopsis "Indexing and sequence extraction from FASTA files")
15120 (description "Fastahack is a small application for indexing and
15121 extracting sequences and subsequences from FASTA files. The included library
15122 provides a FASTA reader and indexer that can be embedded into applications
15123 which would benefit from directly reading subsequences from FASTA files. The
15124 library automatically handles index file generation and use.")
15125 (license (list license:expat license:gpl2))))
15127 (define-public vcflib
15134 (uri (string-append "https://github.com/vcflib/vcflib/releases/"
15135 "download/v" version
15136 "/vcflib-" version "-src.tar.gz"))
15138 (base32 "14zzrg8hg8cq9cvq2wdvp21j7nmxxkjrbagw2apd2yqv2kyx42lm"))
15139 (patches (search-patches "vcflib-use-shared-libraries.patch"))
15140 (modules '((guix build utils)))
15143 (substitute* (find-files "." "\\.(h|c)(pp)?$")
15144 (("\"SmithWatermanGotoh.h\"") "<smithwaterman/SmithWatermanGotoh.h>")
15145 (("\"convert.h\"") "<smithwaterman/convert.h>")
15146 (("\"disorder.h\"") "<smithwaterman/disorder.h>")
15147 (("\"tabix.hpp\"") "<tabix.hpp>")
15148 (("\"Fasta.h\"") "<fastahack/Fasta.h>"))
15149 (for-each delete-file-recursively
15150 '("fastahack" "filevercmp" "fsom" "googletest" "intervaltree"
15151 "libVCFH" "multichoose" "smithwaterman" "tabixpp"))
15153 (build-system gnu-build-system)
15155 `(("htslib" ,htslib)
15156 ("fastahack" ,fastahack)
15159 ("smithwaterman" ,smithwaterman)
15160 ("tabixpp" ,tabixpp)
15164 `(("pkg-config" ,pkg-config)
15166 ;; This package builds against the .o files so we need to extract the source.
15167 ("filevercmp-src" ,(package-source filevercmp))
15168 ("intervaltree-src" ,(package-source intervaltree))
15169 ("multichoose-src" ,(package-source multichoose))))
15171 `(#:tests? #f ; no tests
15173 (modify-phases %standard-phases
15174 (add-after 'unpack 'set-flags
15175 (lambda* (#:key outputs #:allow-other-keys)
15176 (substitute* "Makefile"
15178 (string-append "LDFLAGS = -Wl,-rpath="
15179 (assoc-ref outputs "out") "/lib ")))
15180 (substitute* "filevercmp/Makefile"
15181 (("-c") "-c -fPIC"))
15183 (delete 'configure)
15184 (add-after 'unpack 'unpack-submodule-sources
15185 (lambda* (#:key inputs #:allow-other-keys)
15186 (let ((unpack (lambda (source target)
15188 (with-directory-excursion target
15189 (if (file-is-directory? (assoc-ref inputs source))
15190 (copy-recursively (assoc-ref inputs source) ".")
15191 (invoke "tar" "xvf"
15192 (assoc-ref inputs source)
15193 "--strip-components=1"))))))
15195 (unpack "filevercmp-src" "filevercmp")
15196 (unpack "intervaltree-src" "intervaltree")
15197 (unpack "multichoose-src" "multichoose")))))
15199 (lambda* (#:key outputs #:allow-other-keys)
15200 (let* ((out (assoc-ref outputs "out"))
15201 (bin (string-append out "/bin"))
15202 (lib (string-append out "/lib")))
15203 (for-each (lambda (file)
15204 (install-file file bin))
15205 (find-files "bin" ".*"))
15206 (install-file "libvcflib.so" lib)
15207 (install-file "libvcflib.a" lib)
15210 (install-file file (string-append out "/include")))
15211 (find-files "include" "\\.h(pp)?$"))
15212 (mkdir-p (string-append lib "/pkgconfig"))
15213 (with-output-to-file (string-append lib "/pkgconfig/vcflib.pc")
15215 (format #t "prefix=~a~@
15216 exec_prefix=${prefix}~@
15217 libdir=${exec_prefix}/lib~@
15218 includedir=${prefix}/include~@
15223 Requires: smithwaterman, fastahack~@
15224 Description: C++ library for parsing and manipulating VCF files~@
15225 Libs: -L${libdir} -lvcflib~@
15226 Cflags: -I${includedir}~%"
15229 (home-page "https://github.com/vcflib/vcflib/")
15230 (synopsis "Library for parsing and manipulating VCF files")
15231 (description "Vcflib provides methods to manipulate and interpret
15232 sequence variation as it can be described by VCF. It is both an API for parsing
15233 and operating on records of genomic variation as it can be described by the VCF
15234 format, and a collection of command-line utilities for executing complex
15235 manipulations on VCF files.")
15236 (license license:expat)))
15238 (define-public freebayes
15239 (let ((commit "3ce827d8ebf89bb3bdc097ee0fe7f46f9f30d5fb")
15244 (version (git-version version revision commit))
15247 (uri (git-reference
15248 (url "https://github.com/ekg/freebayes")
15250 (file-name (git-file-name name version))
15252 (base32 "1sbzwmcbn78ybymjnhwk7qc5r912azy5vqz2y7y81616yc3ba2a2"))))
15253 (build-system gnu-build-system)
15255 `(("bamtools" ,bamtools)
15259 `(("bc" ,bc) ; Needed for running tests.
15260 ("samtools" ,samtools) ; Needed for running tests.
15261 ("parallel" ,parallel) ; Needed for running tests.
15262 ("perl" ,perl) ; Needed for running tests.
15263 ("procps" ,procps) ; Needed for running tests.
15264 ("python" ,python-2) ; Needed for running tests.
15265 ("vcflib-src" ,(package-source vcflib))
15266 ;; These are submodules for the vcflib version used in freebayes.
15267 ;; This package builds against the .o files so we need to extract the source.
15268 ("tabixpp-src" ,(package-source tabixpp))
15269 ("smithwaterman-src" ,(package-source smithwaterman))
15270 ("multichoose-src" ,(package-source multichoose))
15271 ("fsom-src" ,(package-source fsom))
15272 ("filevercmp-src" ,(package-source filevercmp))
15273 ("fastahack-src" ,(package-source fastahack))
15274 ("intervaltree-src" ,(package-source intervaltree))
15275 ;; These submodules are needed to run the tests.
15276 ("bash-tap-src" ,(package-source bash-tap))
15277 ("test-simple-bash-src"
15280 (uri (git-reference
15281 (url "https://github.com/ingydotnet/test-simple-bash/")
15282 (commit "124673ff204b01c8e96b7fc9f9b32ee35d898acc")))
15283 (file-name "test-simple-bash-src-checkout")
15285 (base32 "043plp6z0x9yf7mdpky1fw7zcpwn1p47px95w9mh16603zqqqpga"))))))
15289 (string-append "BAMTOOLS_ROOT="
15290 (assoc-ref %build-inputs "bamtools")))
15291 #:test-target "test"
15293 (modify-phases %standard-phases
15294 (delete 'configure)
15295 (add-after 'unpack 'fix-tests
15297 (substitute* "test/t/01_call_variants.t"
15298 (("grep -P \"\\(\\\\t500\\$\\|\\\\t11000\\$\\|\\\\t1000\\$\\)\"")
15299 "grep -E ' (500|11000|1000)$'"))
15301 (add-after 'unpack 'unpack-submodule-sources
15302 (lambda* (#:key inputs #:allow-other-keys)
15303 (let ((unpack (lambda (source target)
15304 (with-directory-excursion target
15305 (if (file-is-directory? (assoc-ref inputs source))
15306 (copy-recursively (assoc-ref inputs source) ".")
15307 (invoke "tar" "xvf"
15308 (assoc-ref inputs source)
15309 "--strip-components=1"))))))
15311 (unpack "vcflib-src" "vcflib")
15312 (unpack "fastahack-src" "vcflib/fastahack")
15313 (unpack "filevercmp-src" "vcflib/filevercmp")
15314 (unpack "fsom-src" "vcflib/fsom")
15315 (unpack "intervaltree-src" "vcflib/intervaltree")
15316 (unpack "multichoose-src" "vcflib/multichoose")
15317 (unpack "smithwaterman-src" "vcflib/smithwaterman")
15318 (unpack "tabixpp-src" "vcflib/tabixpp")
15319 (unpack "test-simple-bash-src" "test/test-simple-bash")
15320 (unpack "bash-tap-src" "test/bash-tap")))))
15321 (add-after 'unpack-submodule-sources 'fix-makefiles
15323 ;; We don't have the .git folder to get the version tag from.
15324 (substitute* "vcflib/Makefile"
15325 (("^GIT_VERSION.*")
15326 (string-append "GIT_VERSION = v" ,version)))
15327 (substitute* "src/Makefile"
15328 (("-I\\$\\(BAMTOOLS_ROOT\\)/src")
15329 "-I$(BAMTOOLS_ROOT)/include/bamtools"))
15331 (add-before 'build 'build-tabixpp-and-vcflib
15332 (lambda* (#:key inputs make-flags #:allow-other-keys)
15333 (with-directory-excursion "vcflib"
15334 (with-directory-excursion "tabixpp"
15335 (apply invoke "make"
15336 (string-append "HTS_LIB="
15337 (assoc-ref inputs "htslib")
15340 (apply invoke "make"
15341 (string-append "CFLAGS=-Itabixpp")
15345 (lambda* (#:key outputs #:allow-other-keys)
15346 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15347 (install-file "bin/freebayes" bin)
15348 (install-file "bin/bamleftalign" bin))
15350 (home-page "https://github.com/ekg/freebayes")
15351 (synopsis "Haplotype-based variant detector")
15352 (description "FreeBayes is a Bayesian genetic variant detector designed to
15353 find small polymorphisms, specifically SNPs (single-nucleotide polymorphisms),
15354 indels (insertions and deletions), MNPs (multi-nucleotide polymorphisms), and
15355 complex events (composite insertion and substitution events) smaller than the
15356 length of a short-read sequencing alignment.")
15357 (license license:expat))))
15359 (define-public samblaster
15361 (name "samblaster")
15365 (uri (git-reference
15366 (url "https://github.com/GregoryFaust/samblaster")
15367 (commit (string-append "v." version))))
15368 (file-name (git-file-name name version))
15371 "0iv2ddfw8363vb2x8gr3p8g88whb6mb9m0pf71i2cqsbv6jghap7"))))
15372 (build-system gnu-build-system)
15374 `(#:tests? #f ; there are none
15376 (modify-phases %standard-phases
15377 (delete 'configure) ; There is no configure phase.
15379 (lambda* (#:key outputs #:allow-other-keys)
15380 (install-file "samblaster"
15381 (string-append (assoc-ref outputs "out") "/bin"))
15383 (home-page "https://github.com/GregoryFaust/samblaster")
15384 (synopsis "Mark duplicates in paired-end SAM files")
15385 (description "Samblaster is a fast and flexible program for marking
15386 duplicates in read-id grouped paired-end SAM files. It can also optionally
15387 output discordant read pairs and/or split read mappings to separate SAM files,
15388 and/or unmapped/clipped reads to a separate FASTQ file. When marking
15389 duplicates, samblaster will require approximately 20MB of memory per 1M read
15391 (license license:expat)))
15393 (define-public r-velocyto
15394 (let ((commit "d7790346cb99f49ab9c2b23ba70dcf9d2c9fc350")
15397 (name "r-velocyto")
15398 (version (git-version "0.6" revision commit))
15402 (uri (git-reference
15403 (url "https://github.com/velocyto-team/velocyto.R")
15405 (file-name (git-file-name name version))
15408 "16wqf70j7rd7pay2q513iyz12i8n9vrpg1bisah4lddbcpx5dz1n"))))
15409 (build-system r-build-system)
15411 `(("boost" ,boost)))
15413 `(("r-hdf5r" ,r-hdf5r)
15416 ("r-pcamethods" ,r-pcamethods)
15418 ("r-rcpparmadillo" ,r-rcpparmadillo)
15419 ;; Suggested packages
15420 ("r-rtsne" ,r-rtsne)
15421 ("r-cluster" ,r-cluster)
15422 ("r-abind" ,r-abind)
15424 ("r-biocgenerics" ,r-biocgenerics)
15425 ("r-genomicalignments" ,r-genomicalignments)
15426 ("r-rsamtools" ,r-rsamtools)
15427 ("r-edger" ,r-edger)
15428 ("r-igraph" ,r-igraph)))
15429 (home-page "https://velocyto.org")
15430 (synopsis "RNA velocity estimation in R")
15432 "This package provides basic routines for estimation of gene-specific
15433 transcriptional derivatives and visualization of the resulting velocity
15435 (license license:gpl3))))
15437 (define-public methyldackel
15439 (name "methyldackel")
15443 (uri (git-reference
15444 (url "https://github.com/dpryan79/MethylDackel")
15446 (file-name (git-file-name name version))
15449 "1sfhf2ap75qxpnmy1ifgmxqs18rq8mah9mcgkby73vc6h0sw99ws"))))
15450 (build-system gnu-build-system)
15452 `(#:test-target "test"
15455 (string-append "prefix="
15456 (assoc-ref %outputs "out") "/bin/"))
15458 (modify-phases %standard-phases
15459 (replace 'configure
15460 (lambda* (#:key outputs #:allow-other-keys)
15461 (substitute* "Makefile"
15462 (("-lhts ") "-lhts -lBigWig ")
15463 (("install MethylDackel \\$\\(prefix\\)" match)
15464 (string-append "install -d $(prefix); " match)))
15467 `(("curl" ,curl) ; XXX: needed by libbigwig
15468 ("htslib" ,htslib-1.9)
15469 ("libbigwig" ,libbigwig)
15471 ;; Needed for tests
15473 `(("python" ,python-wrapper)))
15474 (home-page "https://github.com/dpryan79/MethylDackel")
15475 (synopsis "Universal methylation extractor for BS-seq experiments")
15477 "MethylDackel will process a coordinate-sorted and indexed BAM or CRAM
15478 file containing some form of BS-seq alignments and extract per-base
15479 methylation metrics from them. MethylDackel requires an indexed fasta file
15480 containing the reference genome as well.")
15481 ;; See https://github.com/dpryan79/MethylDackel/issues/85
15482 (license license:expat)))
15484 ;; This package bundles PCRE 8.02 and cannot be built with the current
15486 (define-public phast
15492 (uri (git-reference
15493 (url "https://github.com/CshlSiepelLab/phast")
15494 (commit (string-append "v" version))))
15495 (file-name (git-file-name name version))
15498 "10lpbllvny923jjbbyrpxahhd1m5h7sbj9gx7rd123rg10mlidki"))))
15499 (build-system gnu-build-system)
15503 (string-append "DESTDIR=" (assoc-ref %outputs "out")))
15505 (modify-phases %standard-phases
15506 (replace 'configure
15507 (lambda* (#:key inputs outputs #:allow-other-keys)
15509 (substitute* "test/Makefile"
15511 (substitute* "Makefile"
15512 (("CLAPACKPATH=/usr/lib")
15513 (string-append "CLAPACKPATH="
15514 (assoc-ref inputs "clapack") "/lib")))
15515 ;; Renaming the libraries is not necessary with our version of
15517 (substitute* "src/lib/Makefile"
15518 (("ifdef CLAPACKPATH") "ifdef UNNECESSARY"))
15519 (substitute* "src/make-include.mk"
15520 (("-lblaswr") "-lblas")
15521 (("-ltmg") "-ltmglib")
15522 (("liblapack.a") "liblapack.so")
15523 (("libblas.a") "libblas.so")
15524 (("libf2c.a") "libf2c.so"))
15525 (substitute* "src/Makefile"
15526 (("/opt") "/share")
15532 (string-append (getcwd) "/bin:" (getenv "PATH")))
15533 ;; Disable broken test
15534 (substitute* "test/Makefile"
15535 ((".*if.*hmrc_summary" m) (string-append "#" m)))
15536 ;; Only run the msa_view tests because the others fail for
15537 ;; unknown reasons.
15538 (invoke "make" "-C" "test" "msa_view"))))))
15540 `(("clapack" ,clapack)))
15543 (home-page "http://compgen.cshl.edu/phast/")
15544 (synopsis "Phylogenetic analysis with space/time models")
15546 "Phylogenetic Analysis with Space/Time models (PHAST) is a collection of
15547 command-line programs and supporting libraries for comparative and
15548 evolutionary genomics. Best known as the search engine behind the
15549 Conservation tracks in the University of California, Santa Cruz (UCSC) Genome
15550 Browser, PHAST also includes several tools for phylogenetic modeling,
15551 functional element identification, as well as utilities for manipulating
15552 alignments, trees and genomic annotations.")
15553 (license license:bsd-3)))
15555 (define-public python-gffutils
15556 ;; The latest release is older more than a year than the latest commit
15557 (let ((commit "4034c54600813b1402945e12faa91b3a53162cf1")
15560 (name "python-gffutils")
15561 (version (git-version "0.9" revision commit))
15565 (uri (git-reference
15566 (url "https://github.com/daler/gffutils")
15568 (file-name (git-file-name name version))
15571 "1rwafjdnbir5wnk0ap06ww4lra3p5frhy7mfs03rlldgfnwxymsn"))))
15572 (build-system python-build-system)
15575 (modify-phases %standard-phases
15578 ;; Tests need to access the HOME directory
15579 (setenv "HOME" "/tmp")
15580 (invoke "nosetests" "-a" "!slow")))
15581 (add-after 'unpack 'make-gz-files-writable
15583 (for-each make-file-writable
15584 (find-files "." "\\.gz"))
15587 `(("python-argcomplete" ,python-argcomplete)
15588 ("python-argh" ,python-argh)
15589 ("python-biopython" ,python-biopython)
15590 ("python-pybedtools" ,python-pybedtools)
15591 ("python-pyfaidx" ,python-pyfaidx)
15592 ("python-simplejson" ,python-simplejson)
15593 ("python-six" ,python-six)))
15595 `(("python-nose" , python-nose)))
15596 (home-page "https://github.com/daler/gffutils")
15597 (synopsis "Tool for manipulation of GFF and GTF files")
15599 "python-gffutils is a Python package for working with and manipulating
15600 the GFF and GTF format files typically used for genomic annotations. The
15601 files are loaded into a SQLite database, allowing much more complex
15602 manipulation of hierarchical features (e.g., genes, transcripts, and exons)
15603 than is possible with plain-text methods alone.")
15604 (license license:expat))))
15606 (define-public libsbml
15612 (uri (string-append "mirror://sourceforge/sbml/libsbml/"
15613 version "/stable/libSBML-"
15614 version "-core-src.tar.gz"))
15617 "0slkagrk3nfi2qsksv6b1brj6zhx4bj4bkib2sdycvrcd10ql2lh"))))
15618 (build-system cmake-build-system)
15620 `(#:test-target "test"
15622 (list "-DWITH_CHECK=ON"
15623 (string-append "-DLIBXML_LIBRARY="
15624 (assoc-ref %build-inputs "libxml2")
15626 (string-append "-DLIBXML_INCLUDE_DIR="
15627 (assoc-ref %build-inputs "libxml2")
15628 "/include/libxml2"))))
15630 `(("libxml2" ,libxml2)))
15634 (home-page "http://sbml.org/Software/libSBML")
15635 (synopsis "Process SBML files and data streams")
15636 (description "LibSBML is a library to help you read, write, manipulate,
15637 translate, and validate SBML files and data streams. The @dfn{Systems Biology
15638 Markup Language} (SBML) is an interchange format for computer models of
15639 biological processes. SBML is useful for models of metabolism, cell
15640 signaling, and more. It continues to be evolved and expanded by an
15641 international community.")
15642 (license license:lgpl2.1+)))
15644 (define-public grocsvs
15645 ;; The last release is out of date and new features have been added.
15646 (let ((commit "ecd956a65093a0b2c41849050e4512d46fecea5d")
15650 (version (git-version "0.2.6.1" revision commit))
15653 (uri (git-reference
15654 (url "https://github.com/grocsvs/grocsvs")
15656 (file-name (git-file-name name version))
15658 (base32 "14505725gr7qxc17cxxf0k6lzcwmgi64pija4mwf29aw70qn35cc"))
15659 (patches (search-patches "grocsvs-dont-use-admiral.patch"))))
15660 (build-system python-build-system)
15662 `(#:tests? #f ; No test suite.
15663 #:python ,python-2)) ; Only python-2 supported.
15665 `(("python2-h5py" ,python2-h5py)
15666 ("python2-ipython-cluster-helper" ,python2-ipython-cluster-helper)
15667 ("python2-networkx" ,python2-networkx)
15668 ("python2-psutil" ,python2-psutil)
15669 ("python2-pandas" ,python2-pandas)
15670 ("python2-pybedtools" ,python2-pybedtools)
15671 ("python2-pyfaidx" ,python2-pyfaidx)
15672 ("python2-pygraphviz" ,python2-pygraphviz)
15673 ("python2-pysam" ,python2-pysam)
15674 ("python2-scipy" ,python2-scipy)))
15675 (home-page "https://github.com/grocsvs/grocsvs")
15676 (synopsis "Genome-wide reconstruction of complex structural variants")
15678 "@dfn{Genome-wide Reconstruction of Complex Structural Variants}
15679 (GROC-SVs) is a software pipeline for identifying large-scale structural
15680 variants, performing sequence assembly at the breakpoints, and reconstructing
15681 the complex structural variants using the long-fragment information from the
15682 10x Genomics platform.")
15683 (license license:expat))))