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, 2018, 2019, 2020 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, 2020 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>
21 ;;; Copyright © 2020 Bonface Munyoki Kilyungi <bonfacemunyoki@gmail.com>
23 ;;; This file is part of GNU Guix.
25 ;;; GNU Guix is free software; you can redistribute it and/or modify it
26 ;;; under the terms of the GNU General Public License as published by
27 ;;; the Free Software Foundation; either version 3 of the License, or (at
28 ;;; your option) any later version.
30 ;;; GNU Guix is distributed in the hope that it will be useful, but
31 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
32 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
33 ;;; GNU General Public License for more details.
35 ;;; You should have received a copy of the GNU General Public License
36 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
38 (define-module (gnu packages bioinformatics)
39 #:use-module ((guix licenses) #:prefix license:)
40 #:use-module (guix packages)
41 #:use-module (guix utils)
42 #:use-module (guix download)
43 #:use-module (guix git-download)
44 #:use-module (guix hg-download)
45 #:use-module (guix build-system ant)
46 #:use-module (guix build-system gnu)
47 #:use-module (guix build-system cmake)
48 #:use-module (guix build-system go)
49 #:use-module (guix build-system haskell)
50 #:use-module (guix build-system meson)
51 #:use-module (guix build-system ocaml)
52 #:use-module (guix build-system perl)
53 #:use-module (guix build-system python)
54 #:use-module (guix build-system r)
55 #:use-module (guix build-system ruby)
56 #:use-module (guix build-system scons)
57 #:use-module (guix build-system trivial)
58 #:use-module (guix deprecation)
59 #:use-module (gnu packages)
60 #:use-module (gnu packages autotools)
61 #:use-module (gnu packages algebra)
62 #:use-module (gnu packages base)
63 #:use-module (gnu packages bash)
64 #:use-module (gnu packages bison)
65 #:use-module (gnu packages bioconductor)
66 #:use-module (gnu packages boost)
67 #:use-module (gnu packages check)
68 #:use-module (gnu packages code)
69 #:use-module (gnu packages commencement)
70 #:use-module (gnu packages cmake)
71 #:use-module (gnu packages compression)
72 #:use-module (gnu packages cpio)
73 #:use-module (gnu packages cran)
74 #:use-module (gnu packages curl)
75 #:use-module (gnu packages documentation)
76 #:use-module (gnu packages databases)
77 #:use-module (gnu packages datastructures)
78 #:use-module (gnu packages dlang)
79 #:use-module (gnu packages file)
80 #:use-module (gnu packages flex)
81 #:use-module (gnu packages gawk)
82 #:use-module (gnu packages gcc)
83 #:use-module (gnu packages gd)
84 #:use-module (gnu packages golang)
85 #:use-module (gnu packages glib)
86 #:use-module (gnu packages graph)
87 #:use-module (gnu packages graphics)
88 #:use-module (gnu packages graphviz)
89 #:use-module (gnu packages groff)
90 #:use-module (gnu packages gtk)
91 #:use-module (gnu packages guile)
92 #:use-module (gnu packages guile-xyz)
93 #:use-module (gnu packages haskell-check)
94 #:use-module (gnu packages haskell-web)
95 #:use-module (gnu packages haskell-xyz)
96 #:use-module (gnu packages image)
97 #:use-module (gnu packages image-processing)
98 #:use-module (gnu packages imagemagick)
99 #:use-module (gnu packages java)
100 #:use-module (gnu packages java-compression)
101 #:use-module (gnu packages jemalloc)
102 #:use-module (gnu packages linux)
103 #:use-module (gnu packages lisp-xyz)
104 #:use-module (gnu packages logging)
105 #:use-module (gnu packages machine-learning)
106 #:use-module (gnu packages man)
107 #:use-module (gnu packages maths)
108 #:use-module (gnu packages mpi)
109 #:use-module (gnu packages ncurses)
110 #:use-module (gnu packages node)
111 #:use-module (gnu packages ocaml)
112 #:use-module (gnu packages pcre)
113 #:use-module (gnu packages parallel)
114 #:use-module (gnu packages pdf)
115 #:use-module (gnu packages perl)
116 #:use-module (gnu packages perl-check)
117 #:use-module (gnu packages pkg-config)
118 #:use-module (gnu packages popt)
119 #:use-module (gnu packages protobuf)
120 #:use-module (gnu packages python)
121 #:use-module (gnu packages python-check)
122 #:use-module (gnu packages python-compression)
123 #:use-module (gnu packages python-science)
124 #:use-module (gnu packages python-web)
125 #:use-module (gnu packages python-xyz)
126 #:use-module (gnu packages rdf)
127 #:use-module (gnu packages readline)
128 #:use-module (gnu packages ruby)
129 #:use-module (gnu packages serialization)
130 #:use-module (gnu packages shells)
131 #:use-module (gnu packages sphinx)
132 #:use-module (gnu packages statistics)
133 #:use-module (gnu packages swig)
134 #:use-module (gnu packages tbb)
135 #:use-module (gnu packages tex)
136 #:use-module (gnu packages texinfo)
137 #:use-module (gnu packages textutils)
138 #:use-module (gnu packages time)
139 #:use-module (gnu packages tls)
140 #:use-module (gnu packages vim)
141 #:use-module (gnu packages web)
142 #:use-module (gnu packages xml)
143 #:use-module (gnu packages xorg)
144 #:use-module (srfi srfi-1)
145 #:use-module (ice-9 match))
147 (define-public aragorn
154 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
158 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
159 (build-system gnu-build-system)
161 `(#:tests? #f ; there are no tests
163 (modify-phases %standard-phases
173 (string-append "aragorn" ,version ".c"))
176 (lambda* (#:key outputs #:allow-other-keys)
177 (let* ((out (assoc-ref outputs "out"))
178 (bin (string-append out "/bin"))
179 (man (string-append out "/share/man/man1")))
180 (install-file "aragorn" bin)
181 (install-file "aragorn.1" man))
183 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
184 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
186 "Aragorn identifies transfer RNA, mitochondrial RNA and
187 transfer-messenger RNA from nucleotide sequences, based on homology to known
188 tRNA consensus sequences and RNA structure. It also outputs the secondary
189 structure of the predicted RNA.")
190 (license license:gpl2)))
198 ;; BamM is not available on pypi.
200 (url "https://github.com/Ecogenomics/BamM")
203 (file-name (git-file-name name version))
206 "1p83ahi984ipslxlg4yqy1gdnya9rkn1v71z8djgxkm9d2chw4c5"))
207 (modules '((guix build utils)))
210 ;; Delete bundled htslib.
211 (delete-file-recursively "c/htslib-1.3.1")
213 (build-system python-build-system)
215 `(#:python ,python-2 ; BamM is Python 2 only.
216 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
217 ;; been modified from its original form.
219 (let ((htslib (assoc-ref %build-inputs "htslib")))
220 (list "--with-libhts-lib" (string-append htslib "/lib")
221 "--with-libhts-inc" (string-append htslib "/include/htslib")))
223 (modify-phases %standard-phases
224 (add-after 'unpack 'autogen
226 (with-directory-excursion "c"
227 (let ((sh (which "sh")))
228 (for-each make-file-writable (find-files "." ".*"))
229 ;; Use autogen so that 'configure' works.
230 (substitute* "autogen.sh" (("/bin/sh") sh))
231 (setenv "CONFIG_SHELL" sh)
232 (invoke "./autogen.sh")))
235 ;; Run tests after installation so compilation only happens once.
237 (add-after 'install 'wrap-executable
238 (lambda* (#:key outputs #:allow-other-keys)
239 (let* ((out (assoc-ref outputs "out"))
240 (path (getenv "PATH")))
241 (wrap-program (string-append out "/bin/bamm")
242 `("PATH" ":" prefix (,path))))
244 (add-after 'wrap-executable 'post-install-check
245 (lambda* (#:key inputs outputs #:allow-other-keys)
247 (string-append (assoc-ref outputs "out")
252 (assoc-ref outputs "out")
254 (string-take (string-take-right
255 (assoc-ref inputs "python") 5) 3)
257 (getenv "PYTHONPATH")))
258 ;; There are 2 errors printed, but they are safe to ignore:
259 ;; 1) [E::hts_open_format] fail to open file ...
260 ;; 2) samtools view: failed to open ...
264 `(("autoconf" ,autoconf)
265 ("automake" ,automake)
268 ("python-nose" ,python2-nose)
269 ("python-pysam" ,python2-pysam)))
271 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
272 ("samtools" ,samtools)
276 ("coreutils" ,coreutils)))
278 `(("python-numpy" ,python2-numpy)))
279 (home-page "https://ecogenomics.github.io/BamM/")
280 (synopsis "Metagenomics-focused BAM file manipulator")
282 "BamM is a C library, wrapped in python, to efficiently generate and
283 parse BAM files, specifically for the analysis of metagenomic data. For
284 instance, it implements several methods to assess contig-wise read coverage.")
285 (license license:lgpl3+)))
287 (define-public bamtools
294 (url "https://github.com/pezmaster31/bamtools")
295 (commit (string-append "v" version))))
296 (file-name (git-file-name name version))
299 "0nfb2ypcx9959xnbz6wxh6py3xfizgmg8nrknxl95c507m9hmq8b"))))
300 (build-system cmake-build-system)
302 `(#:tests? #f ;no "check" target
304 (modify-phases %standard-phases
306 'configure 'set-ldflags
307 (lambda* (#:key outputs #:allow-other-keys)
311 (assoc-ref outputs "out") "/lib/bamtools"))
313 (inputs `(("zlib" ,zlib)))
314 (home-page "https://github.com/pezmaster31/bamtools")
315 (synopsis "C++ API and command-line toolkit for working with BAM data")
317 "BamTools provides both a C++ API and a command-line toolkit for handling
319 (license license:expat)))
321 (define-public bcftools
327 (uri (string-append "https://github.com/samtools/bcftools/"
329 version "/bcftools-" version ".tar.bz2"))
332 "0r508mp15pqzf8r1269kb4v5naw9zsvbwd3cz8s1yj7carsf9viw"))
333 (modules '((guix build utils)))
335 ;; Delete bundled htslib.
336 (delete-file-recursively "htslib-1.11")
338 (build-system gnu-build-system)
341 (list "--enable-libgsl")
344 (modify-phases %standard-phases
345 (add-before 'check 'patch-tests
347 (substitute* "test/test.pl"
348 (("/bin/bash") (which "bash")))
356 (home-page "https://samtools.github.io/bcftools/")
357 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
359 "BCFtools is a set of utilities that manipulate variant calls in the
360 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
361 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
362 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
363 (license (list license:gpl3+ license:expat))))
365 (define-public bcftools-1.9
366 (package (inherit bcftools)
371 (uri (string-append "https://github.com/samtools/bcftools/"
373 version "/bcftools-" version ".tar.bz2"))
376 "1j3h638i8kgihzyrlnpj82xg1b23sijibys9hvwari3fy7kd0dkg"))
377 (modules '((guix build utils)))
379 ;; Delete bundled htslib.
380 (delete-file-recursively "htslib-1.9")
382 (build-system gnu-build-system)
384 `(("htslib" ,htslib-1.9)
387 (define-public bedops
394 (url "https://github.com/bedops/bedops")
395 (commit (string-append "v" version))))
396 (file-name (git-file-name name version))
399 "0mmgsgwz5r9w76hzgxkxc9s9lkdhhaf7vr6i02b09vbswvs1fyqx"))))
400 (build-system gnu-build-system)
403 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
405 (modify-phases %standard-phases
406 (add-after 'unpack 'unpack-tarballs
408 ;; FIXME: Bedops includes tarballs of minimally patched upstream
409 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
410 ;; libraries because at least one of the libraries (zlib) is
411 ;; patched to add a C++ function definition (deflateInit2cpp).
412 ;; Until the Bedops developers offer a way to link against system
413 ;; libraries we have to build the in-tree copies of these three
416 ;; See upstream discussion:
417 ;; https://github.com/bedops/bedops/issues/124
419 ;; Unpack the tarballs to benefit from shebang patching.
420 (with-directory-excursion "third-party"
421 (invoke "tar" "xvf" "jansson-2.6.tar.bz2")
422 (invoke "tar" "xvf" "zlib-1.2.7.tar.bz2")
423 (invoke "tar" "xvf" "bzip2-1.0.6.tar.bz2"))
424 ;; Disable unpacking of tarballs in Makefile.
425 (substitute* "system.mk/Makefile.linux"
426 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
427 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
428 (substitute* "third-party/zlib-1.2.7/Makefile.in"
429 (("^SHELL=.*$") "SHELL=bash\n"))
431 (delete 'configure))))
432 (home-page "https://github.com/bedops/bedops")
433 (synopsis "Tools for high-performance genomic feature operations")
435 "BEDOPS is a suite of tools to address common questions raised in genomic
436 studies---mostly with regard to overlap and proximity relationships between
437 data sets. It aims to be scalable and flexible, facilitating the efficient
438 and accurate analysis and management of large-scale genomic data.
440 BEDOPS provides tools that perform highly efficient and scalable Boolean and
441 other set operations, statistical calculations, archiving, conversion and
442 other management of genomic data of arbitrary scale. Tasks can be easily
443 split by chromosome for distributing whole-genome analyses across a
444 computational cluster.")
445 (license license:gpl2+)))
447 (define-public bedtools
453 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
454 "download/v" version "/"
455 "bedtools-" version ".tar.gz"))
458 "0m3hk6548846w83a9s5drsczvy67n2azx41kj71n03klb2gbzwg3"))))
459 (build-system gnu-build-system)
461 '(#:test-target "test"
463 (list (string-append "prefix=" (assoc-ref %outputs "out")))
465 (modify-phases %standard-phases
466 (delete 'configure))))
468 `(("python" ,python-wrapper)))
470 `(("samtools" ,samtools-1.9)
472 (home-page "https://github.com/arq5x/bedtools2")
473 (synopsis "Tools for genome analysis and arithmetic")
475 "Collectively, the bedtools utilities are a swiss-army knife of tools for
476 a wide-range of genomics analysis tasks. The most widely-used tools enable
477 genome arithmetic: that is, set theory on the genome. For example, bedtools
478 allows one to intersect, merge, count, complement, and shuffle genomic
479 intervals from multiple files in widely-used genomic file formats such as BAM,
481 (license license:expat)))
483 ;; Later releases of bedtools produce files with more columns than
484 ;; what Ribotaper expects.
485 (define-public bedtools-2.18
486 (package (inherit bedtools)
491 (uri (string-append "https://github.com/arq5x/bedtools2/"
492 "releases/download/v" version
493 "/bedtools-" version ".tar.gz"))
496 "11rvca19ncg03kxd0wzlfx5ws7r3nisd0z8s9j9n182d8ksp2pxz"))))
498 '(#:test-target "test"
500 (modify-phases %standard-phases
503 (lambda* (#:key outputs #:allow-other-keys)
504 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
505 (for-each (lambda (file)
506 (install-file file bin))
507 (find-files "bin" ".*")))
517 (url "https://github.com/PacificBiosciences/pbbam")
519 (file-name (git-file-name name version))
522 "0h9gkrpf2lrxklxp72xfl5bi3h5zcm5hprrya9gf0hr3xwlbpp0x"))))
523 (build-system meson-build-system)
526 (modify-phases %standard-phases
527 (add-after 'unpack 'find-googletest
528 (lambda* (#:key inputs #:allow-other-keys)
529 ;; It doesn't find gtest_main because there's no pkg-config file
530 ;; for it. Find it another way.
531 (substitute* "tests/meson.build"
532 (("pbbam_gtest_dep = dependency\\('gtest_main'.*")
533 (format #f "cpp = meson.get_compiler('cpp')
534 pbbam_gtest_dep = cpp.find_library('gtest_main', dirs : '~a')\n"
535 (assoc-ref inputs "googletest"))))
537 ;; TODO: tests/pbbam_test cannot be linked
538 ;; ld: tests/59830eb@@pbbam_test@exe/src_test_Accuracy.cpp.o:
539 ;; undefined reference to symbol '_ZTIN7testing4TestE'
540 ;; ld: /gnu/store/...-googletest-1.8.0/lib/libgtest.so:
541 ;; error adding symbols: DSO missing from command line
543 #:configure-flags '("-Dtests=false")))
544 ;; These libraries are listed as "Required" in the pkg-config file.
550 ("samtools" ,samtools)))
552 `(("googletest" ,googletest)
553 ("pkg-config" ,pkg-config)
554 ("python" ,python-wrapper))) ; for tests
555 (home-page "https://github.com/PacificBiosciences/pbbam")
556 (synopsis "Work with PacBio BAM files")
558 "The pbbam software package provides components to create, query, and
559 edit PacBio BAM files and associated indices. These components include a core
560 C++ library, bindings for additional languages, and command-line utilities.
561 This library is not intended to be used as a general-purpose BAM utility - all
562 input and output BAMs must adhere to the PacBio BAM format specification.
563 Non-PacBio BAMs will cause exceptions to be thrown.")
564 (license license:bsd-3)))
566 (define-public blasr-libcpp
568 (name "blasr-libcpp")
573 (url "https://github.com/PacificBiosciences/blasr_libcpp")
575 (file-name (git-file-name name version))
578 "0cn5l42zyq67sj0g2imqkhayz2iqvv0a1pgpbmlq0qynjmsrbfd2"))))
579 (build-system meson-build-system)
582 (modify-phases %standard-phases
583 (add-after 'unpack 'link-with-hdf5
584 (lambda* (#:key inputs #:allow-other-keys)
585 (let ((hdf5 (assoc-ref inputs "hdf5")))
586 (substitute* "meson.build"
587 (("libblasr_deps = \\[" m)
590 (format #f "cpp.find_library('hdf5', dirs : '~a'), \
591 cpp.find_library('hdf5_cpp', dirs : '~a'), "
594 (add-after 'unpack 'find-googletest
595 (lambda* (#:key inputs #:allow-other-keys)
596 ;; It doesn't find gtest_main because there's no pkg-config file
597 ;; for it. Find it another way.
598 (substitute* "unittest/meson.build"
599 (("libblasr_gtest_dep = dependency\\('gtest_main'.*")
600 (format #f "cpp = meson.get_compiler('cpp')
601 libblasr_gtest_dep = cpp.find_library('gtest_main', dirs : '~a')\n"
602 (assoc-ref inputs "googletest"))))
604 ;; TODO: unittest/libblasr_unittest cannot be linked
605 ;; ld: ;; unittest/df08227@@libblasr_unittest@exe/alignment_utils_FileUtils_gtest.cpp.o:
606 ;; undefined reference to symbol
607 ;; '_ZN7testing8internal9DeathTest6CreateEPKcPKNS0_2REES3_iPPS1_'
608 ;; ld: /gnu/store/...-googletest-1.8.0/lib/libgtest.so:
609 ;; error adding symbols: DSO missing from command line
611 #:configure-flags '("-Dtests=false")))
618 `(("googletest" ,googletest)
619 ("pkg-config" ,pkg-config)))
620 (home-page "https://github.com/PacificBiosciences/blasr_libcpp")
621 (synopsis "Library for analyzing PacBio genomic sequences")
623 "This package provides three libraries used by applications for analyzing
624 PacBio genomic sequences. This library contains three sub-libraries: pbdata,
626 (license license:bsd-3)))
635 (url "https://github.com/PacificBiosciences/blasr")
637 (file-name (git-file-name name version))
640 "1skgy2mvz8gsgfh1gc2nfgwvpyzb1hpmp2cf2773h5wsj8nw22kl"))))
641 (build-system meson-build-system)
644 (modify-phases %standard-phases
645 (add-after 'unpack 'link-with-hdf5
646 (lambda* (#:key inputs #:allow-other-keys)
647 (let ((hdf5 (assoc-ref inputs "hdf5")))
648 (substitute* "meson.build"
649 (("blasr_deps = \\[" m)
652 (format #f "cpp.find_library('hdf5', dirs : '~a'), \
653 cpp.find_library('hdf5_cpp', dirs : '~a'), "
656 ;; Tests require "cram" executable, which is not packaged.
658 #:configure-flags '("-Dtests=false")))
661 ("blasr-libcpp" ,blasr-libcpp)
666 `(("pkg-config" ,pkg-config)))
667 (home-page "https://github.com/PacificBiosciences/blasr")
668 (synopsis "PacBio long read aligner")
670 "Blasr is a genomic sequence aligner for processing PacBio long reads.")
671 (license license:bsd-3)))
673 (define-public ribotaper
679 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
680 "files/RiboTaper/RiboTaper_Version_"
684 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
685 (build-system gnu-build-system)
688 (modify-phases %standard-phases
689 (add-after 'install 'wrap-executables
690 (lambda* (#:key inputs outputs #:allow-other-keys)
691 (let* ((out (assoc-ref outputs "out")))
694 (wrap-program (string-append out "/bin/" script)
695 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
696 '("create_annotations_files.bash"
697 "create_metaplots.bash"
698 "Ribotaper_ORF_find.sh"
702 `(("bedtools" ,bedtools-2.18)
703 ("samtools" ,samtools-0.1)
704 ("r-minimal" ,r-minimal)
705 ("r-foreach" ,r-foreach)
706 ("r-xnomial" ,r-xnomial)
708 ("r-multitaper" ,r-multitaper)
709 ("r-seqinr" ,r-seqinr)))
710 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
711 (synopsis "Define translated ORFs using ribosome profiling data")
713 "Ribotaper is a method for defining translated @dfn{open reading
714 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
715 provides the Ribotaper pipeline.")
716 (license license:gpl3+)))
718 (define-public ribodiff
726 (url "https://github.com/ratschlab/RiboDiff")
727 (commit (string-append "v" version))))
728 (file-name (git-file-name name version))
731 "0x75nlp7qnmm64jasbi6l21f2cy99r2cjyl6b4hr8zf2bq22drnz"))))
732 (build-system python-build-system)
736 (modify-phases %standard-phases
737 ;; Generate an installable executable script wrapper.
738 (add-after 'unpack 'patch-setup.py
740 (substitute* "setup.py"
741 (("^(.*)packages=.*" line prefix)
742 (string-append line "\n"
743 prefix "scripts=['scripts/TE.py'],\n")))
746 `(("python-numpy" ,python2-numpy)
747 ("python-matplotlib" ,python2-matplotlib)
748 ("python-scipy" ,python2-scipy)
749 ("python-statsmodels" ,python2-statsmodels)))
751 `(("python-mock" ,python2-mock)
752 ("python-nose" ,python2-nose)))
753 (home-page "https://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
754 (synopsis "Detect translation efficiency changes from ribosome footprints")
755 (description "RiboDiff is a statistical tool that detects the protein
756 translational efficiency change from Ribo-Seq (ribosome footprinting) and
757 RNA-Seq data. It uses a generalized linear model to detect genes showing
758 difference in translational profile taking mRNA abundance into account. It
759 facilitates us to decipher the translational regulation that behave
760 independently with transcriptional regulation.")
761 (license license:gpl3+)))
763 (define-public bioawk
770 (url "https://github.com/lh3/bioawk")
771 (commit (string-append "v" version))))
772 (file-name (git-file-name name version))
775 "1pxc3zdnirxbf9a0az698hd8xdik7qkhypm7v6hn922x8y9qmspm"))))
776 (build-system gnu-build-system)
782 `(#:tests? #f ; There are no tests to run.
783 ;; Bison must generate files, before other targets can build.
786 (modify-phases %standard-phases
787 (delete 'configure) ; There is no configure phase.
789 (lambda* (#:key outputs #:allow-other-keys)
790 (let* ((out (assoc-ref outputs "out"))
791 (bin (string-append out "/bin"))
792 (man (string-append out "/share/man/man1")))
794 (copy-file "awk.1" (string-append man "/bioawk.1"))
795 (install-file "bioawk" bin))
797 (home-page "https://github.com/lh3/bioawk")
798 (synopsis "AWK with bioinformatics extensions")
799 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
800 support of several common biological data formats, including optionally gzip'ed
801 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
802 also adds a few built-in functions and a command line option to use TAB as the
803 input/output delimiter. When the new functionality is not used, bioawk is
804 intended to behave exactly the same as the original BWK awk.")
805 (license license:x11)))
807 (define-public python-pybedtools
809 (name "python-pybedtools")
813 (uri (pypi-uri "pybedtools" version))
816 "14w5i40gi25clrr7h4wa2pcpnyipya8hrqi7nq77553zc5wf0df0"))))
817 (build-system python-build-system)
819 `(#:modules ((ice-9 ftw)
823 (guix build python-build-system))
824 ;; See https://github.com/daler/pybedtools/issues/192
826 (modify-phases %standard-phases
827 (add-after 'unpack 'disable-broken-tests
829 (substitute* "pybedtools/test/test_scripts.py"
830 ;; This test freezes.
831 (("def test_intron_exon_reads")
832 "def _do_not_test_intron_exon_reads")
833 ;; This test fails in the Python 2 build.
834 (("def test_venn_mpl")
835 "def _do_not_test_venn_mpl"))
836 (substitute* "pybedtools/test/test_helpers.py"
837 ;; Requires internet access.
838 (("def test_chromsizes")
839 "def _do_not_test_chromsizes")
840 ;; Broken as a result of the workaround used in the check phase
841 ;; (see: https://github.com/daler/pybedtools/issues/192).
842 (("def test_getting_example_beds")
843 "def _do_not_test_getting_example_beds"))
844 ;; This issue still occurs on python2
845 (substitute* "pybedtools/test/test_issues.py"
846 (("def test_issue_303")
847 "def _test_issue_303"))
849 ;; TODO: Remove phase after it's part of PYTHON-BUILD-SYSTEM.
851 ;; Force the Cythonization of C++ files to guard against compilation
853 (add-after 'unpack 'remove-cython-generated-files
855 (let ((cython-sources (map (cut string-drop-right <> 4)
856 (find-files "." "\\.pyx$")))
857 (c/c++-files (find-files "." "\\.(c|cpp|cxx)$")))
858 (define (strip-extension filename)
859 (string-take filename (string-index-right filename #\.)))
860 (define (cythonized? c/c++-file)
861 (member (strip-extension c/c++-file) cython-sources))
862 (for-each delete-file (filter cythonized? c/c++-files))
864 (add-after 'remove-cython-generated-files 'generate-cython-extensions
866 (invoke "python" "setup.py" "cythonize")))
869 (let* ((cwd (getcwd))
870 (build-root-directory (string-append cwd "/build/"))
871 (build (string-append
873 (find (cut string-prefix? "lib" <>)
874 (scandir (string-append
875 build-root-directory)))))
876 (scripts (string-append
878 (find (cut string-prefix? "scripts" <>)
879 (scandir build-root-directory)))))
881 (string-append build ":" (getenv "PYTHONPATH")))
882 ;; Executable scripts such as 'intron_exon_reads.py' must be
883 ;; available in the PATH.
885 (string-append scripts ":" (getenv "PATH"))))
886 ;; The tests need to be run from elsewhere...
887 (mkdir-p "/tmp/test")
888 (copy-recursively "pybedtools/test" "/tmp/test")
889 (with-directory-excursion "/tmp/test"
890 (invoke "pytest" "-v" "--doctest-modules")))))))
892 `(("bedtools" ,bedtools)
893 ("samtools" ,samtools)
894 ("python-matplotlib" ,python-matplotlib)
895 ("python-pysam" ,python-pysam)
896 ("python-pyyaml" ,python-pyyaml)))
898 `(("python-numpy" ,python-numpy)
899 ("python-pandas" ,python-pandas)
900 ("python-cython" ,python-cython)
901 ("kentutils" ,kentutils) ; for bedGraphToBigWig
902 ("python-six" ,python-six)
903 ;; For the test suite.
904 ("python-pytest" ,python-pytest)
905 ("python-psutil" ,python-psutil)))
906 (home-page "https://pythonhosted.org/pybedtools/")
907 (synopsis "Python wrapper for BEDtools programs")
909 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
910 which are widely used for genomic interval manipulation or \"genome algebra\".
911 pybedtools extends BEDTools by offering feature-level manipulations from with
913 (license license:gpl2+)))
915 (define-public python2-pybedtools
916 (let ((pybedtools (package-with-python2 python-pybedtools)))
920 `(("python2-pathlib" ,python2-pathlib)
921 ,@(package-native-inputs pybedtools))))))
923 (define-public python-biom-format
925 (name "python-biom-format")
930 ;; Use GitHub as source because PyPI distribution does not contain
931 ;; test data: https://github.com/biocore/biom-format/issues/693
933 (url "https://github.com/biocore/biom-format")
935 (file-name (git-file-name name version))
938 "1rna16lyk5aqhnv0dp77wwaplias93f1vw28ad3jmyw6hwkai05v"))
939 (modules '((guix build utils)))
941 ;; Delete generated C files.
942 (for-each delete-file (find-files "." "\\.c"))
944 (build-system python-build-system)
947 (modify-phases %standard-phases
948 (add-after 'unpack 'use-cython
949 (lambda _ (setenv "USE_CYTHON" "1") #t))
950 (add-after 'unpack 'disable-broken-tests
952 (substitute* "biom/tests/test_cli/test_validate_table.py"
953 (("^(.+)def test_invalid_hdf5" m indent)
954 (string-append indent
955 "@npt.dec.skipif(True, msg='Guix')\n"
957 (substitute* "biom/tests/test_table.py"
958 (("^(.+)def test_from_hdf5_issue_731" m indent)
959 (string-append indent
960 "@npt.dec.skipif(True, msg='Guix')\n"
963 (add-before 'reset-gzip-timestamps 'make-files-writable
964 (lambda* (#:key outputs #:allow-other-keys)
965 (let ((out (assoc-ref outputs "out")))
966 (for-each (lambda (file) (chmod file #o644))
967 (find-files out "\\.gz"))
970 `(("python-numpy" ,python-numpy)
971 ("python-scipy" ,python-scipy)
972 ("python-flake8" ,python-flake8)
973 ("python-future" ,python-future)
974 ("python-click" ,python-click)
975 ("python-h5py" ,python-h5py)
976 ;; FIXME: Upgrade to pandas 1.0 when
977 ;; https://github.com/biocore/biom-format/issues/837 is resolved.
978 ("python-pandas" ,python-pandas-0.25)))
980 `(("python-cython" ,python-cython)
981 ("python-pytest" ,python-pytest)
982 ("python-pytest-cov" ,python-pytest-cov)
983 ("python-nose" ,python-nose)))
984 (home-page "http://www.biom-format.org")
985 (synopsis "Biological Observation Matrix (BIOM) format utilities")
987 "The BIOM file format is designed to be a general-use format for
988 representing counts of observations e.g. operational taxonomic units, KEGG
989 orthology groups or lipid types, in one or more biological samples
990 e.g. microbiome samples, genomes, metagenomes.")
991 (license license:bsd-3)
992 (properties `((python2-variant . ,(delay python2-biom-format))))))
994 (define-public python2-biom-format
995 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
999 (substitute-keyword-arguments (package-arguments base)
1001 `(modify-phases ,phases
1002 ;; Do not require the unmaintained pyqi library.
1003 (add-after 'unpack 'remove-pyqi
1005 (substitute* "setup.py"
1006 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
1009 (define-public python-pairtools
1011 (name "python-pairtools")
1016 (url "https://github.com/mirnylab/pairtools")
1017 (commit (string-append "v" version))))
1018 (file-name (git-file-name name version))
1021 "0gr8y13q7sd6yai6df4aavl2470n1f9s3cib6r473z4hr8hcbwmc"))))
1022 (build-system python-build-system)
1025 (modify-phases %standard-phases
1026 (add-after 'unpack 'fix-references
1028 (substitute* '("pairtools/pairtools_merge.py"
1029 "pairtools/pairtools_sort.py")
1030 (("/bin/bash") (which "bash")))
1033 (lambda* (#:key inputs outputs #:allow-other-keys)
1034 (add-installed-pythonpath inputs outputs)
1035 (with-directory-excursion "/tmp"
1036 (invoke "pytest" "-v")))))))
1038 `(("python-cython" ,python-cython)
1039 ("python-nose" ,python-nose)
1040 ("python-pytest" ,python-pytest)))
1042 `(("python" ,python-wrapper)))
1044 `(("htslib" ,htslib) ; for bgzip, looked up in PATH
1045 ("samtools" ,samtools) ; looked up in PATH
1046 ("lz4" ,lz4) ; for lz4c
1047 ("python-click" ,python-click)
1048 ("python-numpy" ,python-numpy)))
1049 (home-page "https://github.com/mirnylab/pairtools")
1050 (synopsis "Process mapped Hi-C data")
1051 (description "Pairtools is a simple and fast command-line framework to
1052 process sequencing data from a Hi-C experiment. Process pair-end sequence
1053 alignments and perform the following operations:
1056 @item detect ligation junctions (a.k.a. Hi-C pairs) in aligned paired-end
1057 sequences of Hi-C DNA molecules
1058 @item sort @code{.pairs} files for downstream analyses
1059 @item detect, tag and remove PCR/optical duplicates
1060 @item generate extensive statistics of Hi-C datasets
1061 @item select Hi-C pairs given flexibly defined criteria
1062 @item restore @code{.sam} alignments from Hi-C pairs.
1065 (license license:expat)))
1067 (define-public bioperl-minimal
1068 (let* ((inputs `(("perl-module-build" ,perl-module-build)
1069 ("perl-data-stag" ,perl-data-stag)
1070 ("perl-libwww" ,perl-libwww)
1071 ("perl-uri" ,perl-uri)))
1073 (map (compose package-name cadr)
1076 (map (compose package-transitive-target-inputs cadr) inputs))))))
1078 (name "bioperl-minimal")
1084 (url "https://github.com/bioperl/bioperl-live")
1085 (commit (string-append "release-"
1086 (string-map (lambda (c)
1088 #\- c)) version)))))
1089 (file-name (git-file-name name version))
1092 "0wl8yvzcls59pwwk6m8ahy87pwg6nnibzy5cldbvmcwg2x2w7783"))))
1093 (build-system perl-build-system)
1096 (modify-phases %standard-phases
1098 'install 'wrap-programs
1099 (lambda* (#:key outputs #:allow-other-keys)
1100 ;; Make sure all executables in "bin" find the required Perl
1101 ;; modules at runtime. As the PERL5LIB variable contains also
1102 ;; the paths of native inputs, we pick the transitive target
1103 ;; inputs from %build-inputs.
1104 (let* ((out (assoc-ref outputs "out"))
1105 (bin (string-append out "/bin/"))
1107 (cons (string-append out "/lib/perl5/site_perl")
1109 (assoc-ref %build-inputs name))
1110 ',transitive-inputs))
1112 (for-each (lambda (file)
1114 `("PERL5LIB" ":" prefix (,path))))
1115 (find-files bin "\\.pl$"))
1119 `(("perl-test-most" ,perl-test-most)))
1120 (home-page "https://metacpan.org/release/BioPerl")
1121 (synopsis "Bioinformatics toolkit")
1123 "BioPerl is the product of a community effort to produce Perl code which
1124 is useful in biology. Examples include Sequence objects, Alignment objects
1125 and database searching objects. These objects not only do what they are
1126 advertised to do in the documentation, but they also interact - Alignment
1127 objects are made from the Sequence objects, Sequence objects have access to
1128 Annotation and SeqFeature objects and databases, Blast objects can be
1129 converted to Alignment objects, and so on. This means that the objects
1130 provide a coordinated and extensible framework to do computational biology.")
1131 (license license:perl-license))))
1133 (define-public python-biopython
1135 (name "python-biopython")
1139 ;; use PyPi rather than biopython.org to ease updating
1140 (uri (pypi-uri "biopython" version))
1143 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
1144 (build-system python-build-system)
1147 (modify-phases %standard-phases
1148 (add-before 'check 'set-home
1149 ;; Some tests require a home directory to be set.
1150 (lambda _ (setenv "HOME" "/tmp") #t)))))
1152 `(("python-numpy" ,python-numpy)))
1153 (home-page "https://biopython.org/")
1154 (synopsis "Tools for biological computation in Python")
1156 "Biopython is a set of tools for biological computation including parsers
1157 for bioinformatics files into Python data structures; interfaces to common
1158 bioinformatics programs; a standard sequence class and tools for performing
1159 common operations on them; code to perform data classification; code for
1160 dealing with alignments; code making it easy to split up parallelizable tasks
1161 into separate processes; and more.")
1162 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
1164 (define-public python2-biopython
1165 (package-with-python2 python-biopython))
1167 (define-public python-fastalite
1169 (name "python-fastalite")
1174 (uri (pypi-uri "fastalite" version))
1177 "1qli6pxp77i9xn2wfciq2zaxhl82bdxb33cpzqzj1z25yd036wqj"))))
1178 (build-system python-build-system)
1180 `(#:tests? #f)) ; Test data is not distributed.
1181 (home-page "https://github.com/nhoffman/fastalite")
1182 (synopsis "Simplest possible FASTA parser")
1183 (description "This library implements a FASTA and a FASTQ parser without
1184 relying on a complex dependency tree.")
1185 (license license:expat)))
1187 (define-public python2-fastalite
1188 (package-with-python2 python-fastalite))
1190 (define-public bpp-core
1191 ;; The last release was in 2014 and the recommended way to install from source
1192 ;; is to clone the git repository, so we do this.
1193 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1194 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
1197 (version (string-append "2.2.0-1." (string-take commit 7)))
1201 (url "http://biopp.univ-montp2.fr/git/bpp-core")
1203 (file-name (string-append name "-" version "-checkout"))
1206 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
1207 (build-system cmake-build-system)
1209 `(#:parallel-build? #f))
1210 (home-page "http://biopp.univ-montp2.fr")
1211 (synopsis "C++ libraries for Bioinformatics")
1213 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1214 analysis, phylogenetics, molecular evolution and population genetics. It is
1215 Object Oriented and is designed to be both easy to use and computer efficient.
1216 Bio++ intends to help programmers to write computer expensive programs, by
1217 providing them a set of re-usable tools.")
1218 (license license:cecill-c))))
1220 (define-public bpp-phyl
1221 ;; The last release was in 2014 and the recommended way to install from source
1222 ;; is to clone the git repository, so we do this.
1223 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1224 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
1227 (version (string-append "2.2.0-1." (string-take commit 7)))
1231 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
1233 (file-name (string-append name "-" version "-checkout"))
1236 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
1237 (build-system cmake-build-system)
1239 `(#:parallel-build? #f
1240 ;; If out-of-source, test data is not copied into the build directory
1241 ;; so the tests fail.
1242 #:out-of-source? #f))
1244 `(("bpp-core" ,bpp-core)
1245 ("bpp-seq" ,bpp-seq)))
1246 (home-page "http://biopp.univ-montp2.fr")
1247 (synopsis "Bio++ phylogenetic Library")
1249 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1250 analysis, phylogenetics, molecular evolution and population genetics. This
1251 library provides phylogenetics-related modules.")
1252 (license license:cecill-c))))
1254 (define-public bpp-popgen
1255 ;; The last release was in 2014 and the recommended way to install from source
1256 ;; is to clone the git repository, so we do this.
1257 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1258 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
1261 (version (string-append "2.2.0-1." (string-take commit 7)))
1265 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
1267 (file-name (string-append name "-" version "-checkout"))
1270 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
1271 (build-system cmake-build-system)
1273 `(#:parallel-build? #f
1274 #:tests? #f)) ; There are no tests.
1276 `(("bpp-core" ,bpp-core)
1277 ("bpp-seq" ,bpp-seq)))
1278 (home-page "http://biopp.univ-montp2.fr")
1279 (synopsis "Bio++ population genetics library")
1281 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1282 analysis, phylogenetics, molecular evolution and population genetics. This
1283 library provides population genetics-related modules.")
1284 (license license:cecill-c))))
1286 (define-public bpp-seq
1287 ;; The last release was in 2014 and the recommended way to install from source
1288 ;; is to clone the git repository, so we do this.
1289 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1290 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
1293 (version (string-append "2.2.0-1." (string-take commit 7)))
1297 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
1299 (file-name (string-append name "-" version "-checkout"))
1302 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
1303 (build-system cmake-build-system)
1305 `(#:parallel-build? #f
1306 ;; If out-of-source, test data is not copied into the build directory
1307 ;; so the tests fail.
1308 #:out-of-source? #f))
1310 `(("bpp-core" ,bpp-core)))
1311 (home-page "http://biopp.univ-montp2.fr")
1312 (synopsis "Bio++ sequence library")
1314 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1315 analysis, phylogenetics, molecular evolution and population genetics. This
1316 library provides sequence-related modules.")
1317 (license license:cecill-c))))
1319 (define-public bppsuite
1320 ;; The last release was in 2014 and the recommended way to install from source
1321 ;; is to clone the git repository, so we do this.
1322 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1323 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
1326 (version (string-append "2.2.0-1." (string-take commit 7)))
1330 (url "http://biopp.univ-montp2.fr/git/bppsuite")
1332 (file-name (string-append name "-" version "-checkout"))
1335 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
1336 (build-system cmake-build-system)
1338 `(#:parallel-build? #f
1339 #:tests? #f)) ; There are no tests.
1343 ("texinfo" ,texinfo)))
1345 `(("bpp-core" ,bpp-core)
1346 ("bpp-seq" ,bpp-seq)
1347 ("bpp-phyl" ,bpp-phyl)
1348 ("bpp-phyl" ,bpp-popgen)))
1349 (home-page "http://biopp.univ-montp2.fr")
1350 (synopsis "Bioinformatics tools written with the Bio++ libraries")
1352 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1353 analysis, phylogenetics, molecular evolution and population genetics. This
1354 package provides command line tools using the Bio++ library.")
1355 (license license:cecill-c))))
1357 (define-public blast+
1364 "https://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
1365 version "/ncbi-blast-" version "+-src.tar.gz"))
1368 "11kvrrl0mcwww6530r55hccpg3x3msmhr3051fwnjbq8rzg2j1qi"))
1369 (modules '((guix build utils)))
1372 ;; Remove bundled bzip2, zlib and pcre.
1373 (delete-file-recursively "c++/src/util/compress/bzip2")
1374 (delete-file-recursively "c++/src/util/compress/zlib")
1375 (delete-file-recursively "c++/src/util/regexp")
1376 (substitute* "c++/src/util/compress/Makefile.in"
1377 (("bzip2 zlib api") "api"))
1378 ;; Remove useless msbuild directory
1379 (delete-file-recursively
1380 "c++/src/build-system/project_tree_builder/msbuild")
1382 (build-system gnu-build-system)
1384 `(;; There are two(!) tests for this massive library, and both fail with
1385 ;; "unparsable timing stats".
1386 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
1387 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
1390 #:parallel-build? #f ; not supported
1392 (modify-phases %standard-phases
1393 (add-before 'configure 'set-HOME
1394 ;; $HOME needs to be set at some point during the configure phase
1395 (lambda _ (setenv "HOME" "/tmp") #t))
1396 (add-after 'unpack 'enter-dir
1397 (lambda _ (chdir "c++") #t))
1398 (add-after 'enter-dir 'fix-build-system
1400 (define (which* cmd)
1401 (cond ((string=? cmd "date")
1402 ;; make call to "date" deterministic
1407 (format (current-error-port)
1408 "WARNING: Unable to find absolute path for ~s~%"
1412 ;; Rewrite hardcoded paths to various tools
1413 (substitute* (append '("src/build-system/configure.ac"
1414 "src/build-system/configure"
1415 "src/build-system/helpers/run_with_lock.c"
1416 "scripts/common/impl/if_diff.sh"
1417 "scripts/common/impl/run_with_lock.sh"
1418 "src/build-system/Makefile.configurables.real"
1419 "src/build-system/Makefile.in.top"
1420 "src/build-system/Makefile.meta.gmake=no"
1421 "src/build-system/Makefile.meta.in"
1422 "src/build-system/Makefile.meta_l"
1423 "src/build-system/Makefile.meta_p"
1424 "src/build-system/Makefile.meta_r"
1425 "src/build-system/Makefile.mk.in"
1426 "src/build-system/Makefile.requirements"
1427 "src/build-system/Makefile.rules_with_autodep.in")
1428 (find-files "scripts/common/check" "\\.sh$"))
1429 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1430 (or (which* cmd) all)))
1432 (substitute* (find-files "src/build-system" "^config.*")
1433 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1436 ;; rewrite "/var/tmp" in check script
1437 (substitute* "scripts/common/check/check_make_unix.sh"
1438 (("/var/tmp") "/tmp"))
1440 ;; do not reset PATH
1441 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1443 (("action=/bin/") "action=")
1444 (("export PATH") ":"))
1447 (lambda* (#:key inputs outputs #:allow-other-keys)
1448 (let ((out (assoc-ref outputs "out"))
1449 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1450 (include (string-append (assoc-ref outputs "include")
1451 "/include/ncbi-tools++")))
1452 ;; The 'configure' script doesn't recognize things like
1453 ;; '--enable-fast-install'.
1454 (invoke "./configure.orig"
1455 (string-append "--with-build-root=" (getcwd) "/build")
1456 (string-append "--prefix=" out)
1457 (string-append "--libdir=" lib)
1458 (string-append "--includedir=" include)
1459 (string-append "--with-bz2="
1460 (assoc-ref inputs "bzip2"))
1461 (string-append "--with-z="
1462 (assoc-ref inputs "zlib"))
1463 (string-append "--with-pcre="
1464 (assoc-ref inputs "pcre"))
1465 ;; Each library is built twice by default, once
1466 ;; with "-static" in its name, and again
1471 (outputs '("out" ; 21 MB
1480 ("python" ,python-wrapper)))
1483 (home-page "https://blast.ncbi.nlm.nih.gov")
1484 (synopsis "Basic local alignment search tool")
1486 "BLAST is a popular method of performing a DNA or protein sequence
1487 similarity search, using heuristics to produce results quickly. It also
1488 calculates an “expect value” that estimates how many matches would have
1489 occurred at a given score by chance, which can aid a user in judging how much
1490 confidence to have in an alignment.")
1491 ;; Most of the sources are in the public domain, with the following
1494 ;; * ./c++/include/util/bitset/
1495 ;; * ./c++/src/html/ncbi_menu*.js
1497 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1499 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1501 ;; * ./c++/src/corelib/teamcity_*
1502 (license (list license:public-domain
1508 (define-public bless
1514 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1518 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1519 (modules '((guix build utils)))
1522 ;; Remove bundled boost, pigz, zlib, and .git directory
1523 ;; FIXME: also remove bundled sources for murmurhash3 and
1524 ;; kmc once packaged.
1525 (delete-file-recursively "boost")
1526 (delete-file-recursively "pigz")
1527 (delete-file-recursively "google-sparsehash")
1528 (delete-file-recursively "zlib")
1529 (delete-file-recursively ".git")
1531 (build-system gnu-build-system)
1533 '(#:tests? #f ;no "check" target
1535 (list (string-append "ZLIB="
1536 (assoc-ref %build-inputs "zlib:static")
1538 (string-append "LDFLAGS="
1539 (string-join '("-lboost_filesystem"
1545 (modify-phases %standard-phases
1546 (add-after 'unpack 'do-not-build-bundled-pigz
1547 (lambda* (#:key inputs outputs #:allow-other-keys)
1548 (substitute* "Makefile"
1549 (("cd pigz/pigz-2.3.3; make") ""))
1551 (add-after 'unpack 'patch-paths-to-executables
1552 (lambda* (#:key inputs outputs #:allow-other-keys)
1553 (substitute* "parse_args.cpp"
1554 (("kmc_binary = .*")
1555 (string-append "kmc_binary = \""
1556 (assoc-ref outputs "out")
1558 (("pigz_binary = .*")
1559 (string-append "pigz_binary = \""
1560 (assoc-ref inputs "pigz")
1564 (lambda* (#:key outputs #:allow-other-keys)
1565 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1566 (for-each (lambda (file)
1567 (install-file file bin))
1568 '("bless" "kmc/bin/kmc"))
1570 (delete 'configure))))
1574 `(("openmpi" ,openmpi)
1576 ("sparsehash" ,sparsehash)
1578 ("zlib:static" ,zlib "static")
1580 (supported-systems '("x86_64-linux"))
1581 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1582 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1584 "@dfn{Bloom-filter-based error correction solution for high-throughput
1585 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1586 correction tool for genomic reads produced by @dfn{Next-generation
1587 sequencing} (NGS). BLESS produces accurate correction results with much less
1588 memory compared with previous solutions and is also able to tolerate a higher
1589 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1590 errors at the end of reads.")
1591 (license license:gpl3+)))
1593 (define-public bowtie
1600 (url "https://github.com/BenLangmead/bowtie2")
1601 (commit (string-append "v" version))))
1602 (file-name (git-file-name name version))
1605 "1zl3cf327y2p7p03cavymbh7b00djc7lncfaqih33n96iy9q8ibp"))
1606 (modules '((guix build utils)))
1609 (substitute* "Makefile"
1610 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1611 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1612 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
1614 (build-system gnu-build-system)
1619 (string-append "prefix=" (assoc-ref %outputs "out")))
1621 (modify-phases %standard-phases
1626 "scripts/test/simple_tests.pl"
1627 "--bowtie2=./bowtie2"
1628 "--bowtie2-build=./bowtie2-build")
1633 ("python" ,python-wrapper)))
1636 ("perl-clone" ,perl-clone)
1637 ("perl-test-deep" ,perl-test-deep)
1638 ("perl-test-simple" ,perl-test-simple)))
1639 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1640 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1642 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1643 reads to long reference sequences. It is particularly good at aligning reads
1644 of about 50 up to 100s or 1,000s of characters, and particularly good at
1645 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1646 genome with an FM Index to keep its memory footprint small: for the human
1647 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1648 gapped, local, and paired-end alignment modes.")
1649 (supported-systems '("x86_64-linux"))
1650 (license license:gpl3+)))
1652 (define-public bowtie1
1658 (uri (string-append "mirror://sourceforge/bowtie-bio/bowtie/"
1659 version "/bowtie-src-x86_64.zip"))
1662 "0vmiqdhc9dzyfy9sh6vgi7k9xy2hiw8g87vbamnc6cgpm179zsa4"))
1663 (modules '((guix build utils)))
1665 '(substitute* "Makefile"
1666 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1667 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1668 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1669 (build-system gnu-build-system)
1671 '(#:tests? #f ; no "check" target
1674 (string-append "prefix=" (assoc-ref %outputs "out")))
1676 (modify-phases %standard-phases
1677 (delete 'configure))))
1679 `(("python-wrapper" ,python-wrapper)
1682 (supported-systems '("x86_64-linux"))
1683 (home-page "http://bowtie-bio.sourceforge.net/index.shtml")
1684 (synopsis "Fast aligner for short nucleotide sequence reads")
1686 "Bowtie is a fast, memory-efficient short read aligner. It aligns short
1687 DNA sequences (reads) to the human genome at a rate of over 25 million 35-bp
1688 reads per hour. Bowtie indexes the genome with a Burrows-Wheeler index to
1689 keep its memory footprint small: typically about 2.2 GB for the human
1690 genome (2.9 GB for paired-end).")
1691 (license license:artistic2.0)))
1693 (define-public tophat
1700 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1704 "19add02kv2xhd6ihd779dr7x35ggym3jqr0m5c4315i1yfb0p11p"))
1705 (modules '((guix build utils)))
1708 ;; Remove bundled SeqAn and samtools
1709 (delete-file-recursively "src/SeqAn-1.4.2")
1710 (delete-file-recursively "src/samtools-0.1.18")
1712 (build-system gnu-build-system)
1714 '(#:parallel-build? #f ; not supported
1716 (modify-phases %standard-phases
1717 (add-after 'set-paths 'hide-default-gcc
1718 (lambda* (#:key inputs #:allow-other-keys)
1719 (let ((gcc (assoc-ref inputs "gcc")))
1720 ;; Remove the default GCC from CPLUS_INCLUDE_PATH to prevent
1721 ;; conflicts with the GCC 5 input.
1722 (setenv "CPLUS_INCLUDE_PATH"
1724 (delete (string-append gcc "/include/c++")
1725 (string-split (getenv "CPLUS_INCLUDE_PATH") #\:))
1728 (add-after 'unpack 'use-system-samtools
1729 (lambda* (#:key inputs #:allow-other-keys)
1730 (substitute* "src/Makefile.in"
1731 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1732 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1733 (("SAMPROG = samtools_0\\.1\\.18") "")
1734 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1735 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1736 (substitute* '("src/common.cpp"
1738 (("samtools_0.1.18") (which "samtools")))
1739 (substitute* '("src/common.h"
1740 "src/bam2fastx.cpp")
1741 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1742 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1743 (substitute* '("src/bwt_map.h"
1745 "src/align_status.h")
1746 (("#include <bam.h>") "#include <samtools/bam.h>")
1747 (("#include <sam.h>") "#include <samtools/sam.h>"))
1750 `(("gcc@5" ,gcc-5))) ;; doesn't build with later versions
1754 ("ncurses" ,ncurses)
1756 ("python" ,python-2)
1757 ("samtools" ,samtools-0.1)
1760 (home-page "https://ccb.jhu.edu/software/tophat/index.shtml")
1761 (synopsis "Spliced read mapper for RNA-Seq data")
1763 "TopHat is a fast splice junction mapper for nucleotide sequence
1764 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1765 mammalian-sized genomes using the ultra high-throughput short read
1766 aligner Bowtie, and then analyzes the mapping results to identify
1767 splice junctions between exons.")
1768 ;; TopHat is released under the Boost Software License, Version 1.0
1769 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1770 (license license:boost1.0)))
1779 "https://github.com/lh3/bwa/releases/download/v"
1780 version "/bwa-" version ".tar.bz2"))
1783 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1784 (build-system gnu-build-system)
1786 '(#:tests? #f ;no "check" target
1788 (modify-phases %standard-phases
1790 (lambda* (#:key outputs #:allow-other-keys)
1791 (let* ((out (assoc-ref outputs "out"))
1792 (bin (string-append out "/bin"))
1793 (lib (string-append out "/lib"))
1794 (doc (string-append out "/share/doc/bwa"))
1795 (man (string-append out "/share/man/man1")))
1796 (install-file "bwa" bin)
1797 (install-file "libbwa.a" lib)
1798 (install-file "README.md" doc)
1799 (install-file "bwa.1" man))
1801 ;; no "configure" script
1802 (delete 'configure))))
1803 (inputs `(("zlib" ,zlib)))
1804 ;; Non-portable SSE instructions are used so building fails on platforms
1805 ;; other than x86_64.
1806 (supported-systems '("x86_64-linux"))
1807 (home-page "http://bio-bwa.sourceforge.net/")
1808 (synopsis "Burrows-Wheeler sequence aligner")
1810 "BWA is a software package for mapping low-divergent sequences against a
1811 large reference genome, such as the human genome. It consists of three
1812 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1813 designed for Illumina sequence reads up to 100bp, while the rest two for
1814 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1815 features such as long-read support and split alignment, but BWA-MEM, which is
1816 the latest, is generally recommended for high-quality queries as it is faster
1817 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1818 70-100bp Illumina reads.")
1819 (license license:gpl3+)))
1821 (define-public bwa-pssm
1822 (package (inherit bwa)
1828 (url "https://github.com/pkerpedjiev/bwa-pssm")
1830 (file-name (git-file-name name version))
1833 "076c4q0cdqz8jgylb067y9zmvxglppnzi3qiscn0xiypgc6lgb5r"))))
1834 (build-system gnu-build-system)
1839 (home-page "http://bwa-pssm.binf.ku.dk/")
1840 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1842 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1843 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1844 existing aligners it is fast and sensitive. Unlike most other aligners,
1845 however, it is also adaptible in the sense that one can direct the alignment
1846 based on known biases within the data set. It is coded as a modification of
1847 the original BWA alignment program and shares the genome index structure as
1848 well as many of the command line options.")
1849 (license license:gpl3+)))
1851 (define-public bwa-meth
1858 (url "https://github.com/brentp/bwa-meth")
1859 (commit (string-append "v" version))))
1860 (file-name (git-file-name name version))
1863 "17j31i7zws5j7mhsq9x3qgkxly6mlmrgwhfq0qbflgxrmx04yaiz"))))
1864 (build-system python-build-system)
1867 (modify-phases %standard-phases
1868 (add-after 'unpack 'keep-references-to-bwa
1869 (lambda* (#:key inputs #:allow-other-keys)
1870 (substitute* "bwameth.py"
1871 (("bwa (mem|index)" _ command)
1872 (string-append (which "bwa") " " command))
1873 ;; There's an ill-advised check for "samtools" on PATH.
1879 `(("python-toolshed" ,python-toolshed)))
1880 (home-page "https://github.com/brentp/bwa-meth")
1881 (synopsis "Fast and accurante alignment of BS-Seq reads")
1883 "BWA-Meth works for single-end reads and for paired-end reads from the
1884 directional protocol (most common). It uses the method employed by
1885 methylcoder and Bismark of in silico conversion of all C's to T's in both
1886 reference and reads. It recovers the original read (needed to tabulate
1887 methylation) by attaching it as a comment which BWA appends as a tag to the
1888 read. It performs favorably to existing aligners gauged by number of on and
1889 off-target reads for a capture method that targets CpG-rich region.")
1890 (license license:expat)))
1892 (define-public python-bx-python
1894 (name "python-bx-python")
1898 (uri (pypi-uri "bx-python" version))
1901 "11kksg2rbzihpmcid823xvg42xi88m7sz58rzk29abybkxy0rszs"))))
1902 (build-system python-build-system)
1903 ;; Tests fail because test data are not included
1904 (arguments '(#:tests? #f))
1906 `(("python-numpy" ,python-numpy)
1907 ("python-six" ,python-six)))
1911 `(("python-lzo" ,python-lzo)
1912 ("python-nose" ,python-nose)
1913 ("python-cython" ,python-cython)))
1914 (home-page "https://github.com/bxlab/bx-python")
1915 (synopsis "Tools for manipulating biological data")
1917 "bx-python provides tools for manipulating biological data, particularly
1918 multiple sequence alignments.")
1919 (license license:expat)))
1921 (define-public python2-bx-python
1922 (package-with-python2 python-bx-python))
1924 (define-public python-pysam
1926 (name "python-pysam")
1930 ;; Test data is missing on PyPi.
1932 (url "https://github.com/pysam-developers/pysam")
1933 (commit (string-append "v" version))))
1934 (file-name (git-file-name name version))
1937 "1vj367w6xbn9bpmksm162l1aipf7cj97h1q83y7jcpm33ihwpf7x"))
1938 (modules '((guix build utils)))
1940 ;; Drop bundled htslib. TODO: Also remove samtools
1942 (delete-file-recursively "htslib")
1944 (build-system python-build-system)
1946 `(#:modules ((ice-9 ftw)
1948 (guix build python-build-system)
1951 (modify-phases %standard-phases
1952 (add-before 'build 'set-flags
1953 (lambda* (#:key inputs #:allow-other-keys)
1954 (setenv "HTSLIB_MODE" "external")
1955 (setenv "HTSLIB_LIBRARY_DIR"
1956 (string-append (assoc-ref inputs "htslib") "/lib"))
1957 (setenv "HTSLIB_INCLUDE_DIR"
1958 (string-append (assoc-ref inputs "htslib") "/include"))
1959 (setenv "LDFLAGS" "-lncurses")
1960 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1963 (lambda* (#:key inputs outputs #:allow-other-keys)
1964 ;; This file contains tests that require a connection to the
1966 (delete-file "tests/tabix_test.py")
1967 ;; FIXME: This test fails
1968 (delete-file "tests/AlignmentFile_test.py")
1969 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1970 (setenv "PYTHONPATH"
1972 (getenv "PYTHONPATH")
1973 ":" (getcwd) "/build/"
1974 (car (scandir "build"
1975 (negate (cut string-prefix? "." <>))))))
1976 ;; Step out of source dir so python does not import from CWD.
1977 (with-directory-excursion "tests"
1978 (setenv "HOME" "/tmp")
1979 (invoke "make" "-C" "pysam_data")
1980 (invoke "make" "-C" "cbcf_data")
1981 ;; Running nosetests without explicitly asking for a single
1982 ;; process leads to a crash. Running with multiple processes
1983 ;; fails because the tests are not designed to run in parallel.
1985 ;; FIXME: tests keep timing out on some systems.
1986 (invoke "nosetests" "-v" "--processes" "1")))))))
1988 `(("htslib" ,htslib-1.9))) ; Included from installed header files.
1990 `(("ncurses" ,ncurses)
1994 `(("python-cython" ,python-cython)
1995 ;; Dependencies below are are for tests only.
1996 ("samtools" ,samtools-1.9)
1997 ("bcftools" ,bcftools-1.9)
1998 ("python-nose" ,python-nose)))
1999 (home-page "https://github.com/pysam-developers/pysam")
2000 (synopsis "Python bindings to the SAMtools C API")
2002 "Pysam is a Python module for reading and manipulating files in the
2003 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
2004 also includes an interface for tabix.")
2005 (license license:expat)))
2007 (define-public python2-pysam
2008 (package-with-python2 python-pysam))
2010 (define-public python-twobitreader
2012 (name "python-twobitreader")
2017 (url "https://github.com/benjschiller/twobitreader")
2019 (file-name (git-file-name name version))
2022 "1qbxvv1h58cismbk1anpjrkpghsaiy64a11ir3lhy6qch6xf8n62"))))
2023 (build-system python-build-system)
2024 ;; Tests are not included
2025 (arguments '(#:tests? #f))
2027 `(("python-sphinx" ,python-sphinx)))
2028 (home-page "https://github.com/benjschiller/twobitreader")
2029 (synopsis "Python library for reading .2bit files")
2031 "twobitreader is a Python library for reading .2bit files as used by the
2032 UCSC genome browser.")
2033 (license license:artistic2.0)))
2035 (define-public python2-twobitreader
2036 (package-with-python2 python-twobitreader))
2038 (define-public python-plastid
2040 (name "python-plastid")
2044 (uri (pypi-uri "plastid" version))
2047 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
2048 (build-system python-build-system)
2050 ;; Some test files are not included.
2053 `(("python-numpy" ,python-numpy)
2054 ("python-scipy" ,python-scipy)
2055 ("python-pandas" ,python-pandas)
2056 ("python-pysam" ,python-pysam)
2057 ("python-matplotlib" ,python-matplotlib)
2058 ("python-biopython" ,python-biopython)
2059 ("python-twobitreader" ,python-twobitreader)
2060 ("python-termcolor" ,python-termcolor)))
2062 `(("python-cython" ,python-cython)
2063 ("python-nose" ,python-nose)))
2064 (home-page "https://github.com/joshuagryphon/plastid")
2065 (synopsis "Python library for genomic analysis")
2067 "plastid is a Python library for genomic analysis – in particular,
2068 high-throughput sequencing data – with an emphasis on simplicity.")
2069 (license license:bsd-3)))
2071 (define-public python2-plastid
2072 (package-with-python2 python-plastid))
2074 (define-public tetoolkit
2081 (url "https://github.com/mhammell-laboratory/tetoolkit")
2083 (file-name (git-file-name name version))
2086 "1yzi0kfpzip8zpjb82x1ik6h22yzfyjiz2dv85v6as2awwqvk807"))))
2087 (build-system python-build-system)
2089 `(#:python ,python-2 ; not guaranteed to work with Python 3
2091 (modify-phases %standard-phases
2092 (add-after 'unpack 'make-writable
2094 (for-each make-file-writable (find-files "."))
2096 (add-after 'unpack 'patch-invocations
2097 (lambda* (#:key inputs #:allow-other-keys)
2098 (substitute* '("bin/TEtranscripts"
2101 (string-append "'" (which "sort") " "))
2103 (string-append "'" (which "rm") " -f "))
2104 (("'Rscript'") (string-append "'" (which "Rscript") "'")))
2105 (substitute* "TEToolkit/IO/ReadInputs.py"
2106 (("BamToBED") (which "bamToBed")))
2107 (substitute* "TEToolkit/Normalization.py"
2109 (string-append "\"" (which "Rscript") "\"")))
2111 (add-after 'install 'wrap-program
2112 (lambda* (#:key outputs #:allow-other-keys)
2113 ;; Make sure the executables find R packages.
2114 (let ((out (assoc-ref outputs "out")))
2117 (wrap-program (string-append out "/bin/" script)
2118 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
2123 `(("coreutils" ,coreutils)
2124 ("bedtools" ,bedtools)
2125 ("python-argparse" ,python2-argparse)
2126 ("python-pysam" ,python2-pysam)
2127 ("r-minimal" ,r-minimal)
2128 ("r-deseq2" ,r-deseq2)))
2129 (home-page "https://github.com/mhammell-laboratory/tetoolkit")
2130 (synopsis "Transposable elements in differential enrichment analysis")
2132 "This is package for including transposable elements in differential
2133 enrichment analysis of sequencing datasets. TEtranscripts and TEcount take
2134 RNA-seq (and similar data) and annotates reads to both genes and transposable
2135 elements. TEtranscripts then performs differential analysis using DESeq2.
2136 Note that TEtranscripts and TEcount rely on specially curated GTF files, which
2137 are not included due to their size.")
2138 (license license:gpl3+)))
2140 (define-public cd-hit
2146 (uri (string-append "https://github.com/weizhongli/cdhit"
2147 "/releases/download/V" version
2149 "-2017-0621-source.tar.gz"))
2152 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
2153 (build-system gnu-build-system)
2155 `(#:tests? #f ; there are no tests
2157 ;; Executables are copied directly to the PREFIX.
2158 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin")
2159 ;; Support longer sequences (e.g. Pacbio sequences)
2162 (modify-phases %standard-phases
2163 ;; No "configure" script
2165 ;; Remove sources of non-determinism
2166 (add-after 'unpack 'be-timeless
2168 (substitute* "cdhit-utility.c++"
2169 ((" \\(built on \" __DATE__ \"\\)") ""))
2170 (substitute* "cdhit-common.c++"
2171 (("__DATE__") "\"0\"")
2172 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
2174 ;; The "install" target does not create the target directory.
2175 (add-before 'install 'create-target-dir
2176 (lambda* (#:key outputs #:allow-other-keys)
2177 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
2181 (home-page "http://weizhongli-lab.org/cd-hit/")
2182 (synopsis "Cluster and compare protein or nucleotide sequences")
2184 "CD-HIT is a program for clustering and comparing protein or nucleotide
2185 sequences. CD-HIT is designed to be fast and handle extremely large
2187 ;; The manual says: "It can be copied under the GNU General Public License
2188 ;; version 2 (GPLv2)."
2189 (license license:gpl2)))
2191 (define-public clipper
2198 (url "https://github.com/YeoLab/clipper")
2200 (file-name (git-file-name name version))
2203 "1bcag4lb5bkzsj2vg7lrq24aw6yfgq275ifrbhd82l7kqgbbjbkv"))))
2204 (build-system python-build-system)
2207 (modify-phases %standard-phases
2208 (add-before 'reset-gzip-timestamps 'make-files-writable
2209 (lambda* (#:key outputs #:allow-other-keys)
2210 ;; Make sure .gz files are writable so that the
2211 ;; 'reset-gzip-timestamps' phase can do its work.
2212 (let ((out (assoc-ref outputs "out")))
2213 (for-each make-file-writable
2214 (find-files out "\\.gz$"))
2218 ("python-pybedtools" ,python-pybedtools)
2219 ("python-cython" ,python-cython)
2220 ("python-scikit-learn" ,python-scikit-learn)
2221 ("python-matplotlib" ,python-matplotlib)
2222 ("python-pandas" ,python-pandas)
2223 ("python-pysam" ,python-pysam)
2224 ("python-numpy" ,python-numpy)
2225 ("python-scipy" ,python-scipy)))
2227 `(("python-setuptools-git" ,python-setuptools-git)
2228 ("python-mock" ,python-mock) ; for tests
2229 ("python-nose" ,python-nose) ; for tests
2230 ("python-pytz" ,python-pytz))) ; for tests
2231 (home-page "https://github.com/YeoLab/clipper")
2232 (synopsis "CLIP peak enrichment recognition")
2234 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
2235 (license license:gpl2)))
2237 (define-public codingquarry
2239 (name "codingquarry")
2244 "mirror://sourceforge/codingquarry/CodingQuarry_v"
2248 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
2249 (build-system gnu-build-system)
2251 '(#:tests? #f ; no "check" target
2253 (modify-phases %standard-phases
2256 (lambda* (#:key outputs #:allow-other-keys)
2257 (let* ((out (assoc-ref outputs "out"))
2258 (bin (string-append out "/bin"))
2259 (doc (string-append out "/share/doc/codingquarry")))
2260 (install-file "INSTRUCTIONS.pdf" doc)
2261 (copy-recursively "QuarryFiles"
2262 (string-append out "/QuarryFiles"))
2263 (install-file "CodingQuarry" bin)
2264 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin))
2266 (inputs `(("openmpi" ,openmpi)))
2267 (native-search-paths
2268 (list (search-path-specification
2269 (variable "QUARRY_PATH")
2270 (files '("QuarryFiles")))))
2271 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
2272 (synopsis "Fungal gene predictor")
2273 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
2274 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
2275 (home-page "https://sourceforge.net/projects/codingquarry/")
2276 (license license:gpl3+)))
2278 (define-public couger
2285 "http://couger.oit.duke.edu/static/assets/COUGER"
2289 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
2290 (build-system gnu-build-system)
2294 (modify-phases %standard-phases
2299 (lambda* (#:key outputs #:allow-other-keys)
2300 (let* ((out (assoc-ref outputs "out"))
2301 (bin (string-append out "/bin")))
2302 (copy-recursively "src" (string-append out "/src"))
2304 ;; Add "src" directory to module lookup path.
2305 (substitute* "couger"
2307 (string-append "import sys\nsys.path.append(\""
2308 out "\")\nfrom argparse")))
2309 (install-file "couger" bin))
2312 'install 'wrap-program
2313 (lambda* (#:key inputs outputs #:allow-other-keys)
2314 ;; Make sure 'couger' runs with the correct PYTHONPATH.
2315 (let* ((out (assoc-ref outputs "out"))
2316 (path (getenv "PYTHONPATH")))
2317 (wrap-program (string-append out "/bin/couger")
2318 `("PYTHONPATH" ":" prefix (,path))))
2321 `(("python" ,python-2)
2322 ("python2-pillow" ,python2-pillow)
2323 ("python2-numpy" ,python2-numpy)
2324 ("python2-scipy" ,python2-scipy)
2325 ("python2-matplotlib" ,python2-matplotlib)))
2327 `(("r-minimal" ,r-minimal)
2329 ("randomjungle" ,randomjungle)))
2331 `(("unzip" ,unzip)))
2332 (home-page "http://couger.oit.duke.edu")
2333 (synopsis "Identify co-factors in sets of genomic regions")
2335 "COUGER can be applied to any two sets of genomic regions bound by
2336 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
2337 putative co-factors that provide specificity to each TF. The framework
2338 determines the genomic targets uniquely-bound by each TF, and identifies a
2339 small set of co-factors that best explain the in vivo binding differences
2340 between the two TFs.
2342 COUGER uses classification algorithms (support vector machines and random
2343 forests) with features that reflect the DNA binding specificities of putative
2344 co-factors. The features are generated either from high-throughput TF-DNA
2345 binding data (from protein binding microarray experiments), or from large
2346 collections of DNA motifs.")
2347 (license license:gpl3+)))
2349 (define-public clustal-omega
2351 (name "clustal-omega")
2355 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
2359 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
2360 (build-system gnu-build-system)
2362 `(("argtable" ,argtable)))
2363 (home-page "http://www.clustal.org/omega/")
2364 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
2366 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
2367 program for protein and DNA/RNA. It produces high quality MSAs and is capable
2368 of handling data-sets of hundreds of thousands of sequences in reasonable
2370 (license license:gpl2+)))
2372 (define-public crossmap
2378 (uri (pypi-uri "CrossMap" version))
2381 "1sb2f2qbxya4fzw3yjl09vbrs8vfmw22zrygrvz004sf9gb1vkan"))))
2382 (build-system python-build-system)
2384 `(("python-bx-python" ,python-bx-python)
2385 ("python-numpy" ,python-numpy)
2386 ("python-pybigwig" ,python-pybigwig)
2387 ("python-pysam" ,python-pysam)
2390 `(("python-cython" ,python-cython)
2391 ("python-nose" ,python-nose)))
2392 (home-page "http://crossmap.sourceforge.net/")
2393 (synopsis "Convert genome coordinates between assemblies")
2395 "CrossMap is a program for conversion of genome coordinates or annotation
2396 files between different genome assemblies. It supports most commonly used
2397 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
2398 (license license:gpl2+)))
2400 (define-public python-dnaio
2402 (name "python-dnaio")
2407 (uri (pypi-uri "dnaio" version))
2410 "0f16m7hdlm0fz1n7y5asy0v9ghyrq17ni1p9iybq22ddzyd49r27"))))
2411 (build-system python-build-system)
2413 `(("python-cython" ,python-cython)
2414 ("python-pytest" ,python-pytest)
2415 ("python-xopen" ,python-xopen)))
2416 (home-page "https://github.com/marcelm/dnaio/")
2417 (synopsis "Read FASTA and FASTQ files efficiently")
2419 "dnaio is a Python library for fast parsing of FASTQ and also FASTA
2420 files. The code was previously part of the cutadapt tool.")
2421 (license license:expat)))
2423 (define-public python-deeptoolsintervals
2425 (name "python-deeptoolsintervals")
2429 (uri (pypi-uri "deeptoolsintervals" version))
2432 "1xnl80nblysj6dylj4683wgrfa425rkx4dp5k65hvwdns9pw753x"))))
2433 (build-system python-build-system)
2436 (home-page "https://github.com/deeptools/deeptools_intervals")
2437 (synopsis "Create GTF-based interval trees with associated meta-data")
2439 "This package provides a Python module creating/accessing GTF-based
2440 interval trees with associated meta-data. It is primarily used by the
2441 @code{deeptools} package.")
2442 (license license:expat)))
2444 (define-public python-deeptools
2446 (name "python-deeptools")
2451 (url "https://github.com/deeptools/deepTools")
2453 (file-name (git-file-name name version))
2456 "0l09vyynz6s6w7fnyd94rpys4a6aja6kp4gli64pngdxdz3md1nl"))))
2457 (build-system python-build-system)
2459 `(("python-mock" ,python-mock)
2460 ("python-nose" ,python-nose)))
2462 `(("python-matplotlib" ,python-matplotlib)
2463 ("python-numpy" ,python-numpy)
2464 ("python-numpydoc" ,python-numpydoc)
2465 ("python-py2bit" ,python-py2bit)
2466 ("python-pybigwig" ,python-pybigwig)
2467 ("python-pysam" ,python-pysam)
2468 ("python-scipy" ,python-scipy)
2469 ("python-deeptoolsintervals" ,python-deeptoolsintervals)
2470 ("python-plotly" ,python-plotly-2.4.1)))
2471 (home-page "https://pypi.org/project/deepTools/")
2472 (synopsis "Useful tools for exploring deep sequencing data")
2473 (description "This package addresses the challenge of handling large amounts
2474 of data that are now routinely generated from DNA sequencing centers.
2475 @code{deepTools} contains useful modules to process the mapped reads data for
2476 multiple quality checks, creating normalized coverage files in standard bedGraph
2477 and bigWig file formats, that allow comparison between different files. Finally,
2478 using such normalized and standardized files, deepTools can create many
2479 publication-ready visualizations to identify enrichments and for functional
2480 annotations of the genome.")
2481 ;; The file deeptools/cm.py is licensed under the BSD license. The
2482 ;; remainder of the code is licensed under the MIT license.
2483 (license (list license:bsd-3 license:expat))))
2485 (define-deprecated deeptools python-deeptools)
2487 (define-public cutadapt
2493 (uri (pypi-uri "cutadapt" version))
2496 "1vqmsfkm6llxzmsz9wcfcvzx9a9f8iabvwik2rbyn7nc4wm25z89"))))
2497 (build-system python-build-system)
2499 `(("python-dnaio" ,python-dnaio)
2500 ("python-xopen" ,python-xopen)))
2502 `(("python-cython" ,python-cython)
2503 ("python-pytest" ,python-pytest)
2504 ("python-setuptools-scm" ,python-setuptools-scm)))
2505 (home-page "https://cutadapt.readthedocs.io/en/stable/")
2506 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
2508 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
2509 other types of unwanted sequence from high-throughput sequencing reads.")
2510 (license license:expat)))
2512 (define-public libbigwig
2519 (url "https://github.com/dpryan79/libBigWig")
2521 (file-name (git-file-name name version))
2524 "09693dmf1scdac5pyq6qyn8b4mcipvnmc370k9a5z41z81m3dcsj"))))
2525 (build-system gnu-build-system)
2527 `(#:test-target "test"
2528 #:tests? #f ; tests require access to the web
2531 (string-append "prefix=" (assoc-ref %outputs "out")))
2533 (modify-phases %standard-phases
2534 (delete 'configure))))
2539 `(("doxygen" ,doxygen)
2541 ("python" ,python-2)))
2542 (home-page "https://github.com/dpryan79/libBigWig")
2543 (synopsis "C library for handling bigWig files")
2545 "This package provides a C library for parsing local and remote BigWig
2547 (license license:expat)))
2549 (define-public python-pybigwig
2551 (name "python-pybigwig")
2555 (uri (pypi-uri "pyBigWig" version))
2558 "157x6v48y299zm382krf1dw08fdxg95im8lnabhp5vc94s04zxj1"))
2559 (modules '((guix build utils)))
2562 ;; Delete bundled libBigWig sources
2563 (delete-file-recursively "libBigWig")
2565 (build-system python-build-system)
2568 (modify-phases %standard-phases
2569 (add-after 'unpack 'link-with-libBigWig
2570 (lambda* (#:key inputs #:allow-other-keys)
2571 (substitute* "setup.py"
2572 (("libs=\\[") "libs=[\"BigWig\", "))
2575 `(("python-numpy" ,python-numpy)))
2577 `(("libbigwig" ,libbigwig)
2580 (home-page "https://github.com/dpryan79/pyBigWig")
2581 (synopsis "Access bigWig files in Python using libBigWig")
2583 "This package provides Python bindings to the libBigWig library for
2584 accessing bigWig files.")
2585 (license license:expat)))
2587 (define-public python2-pybigwig
2588 (package-with-python2 python-pybigwig))
2590 (define-public python-schema-salad
2592 (name "python-schema-salad")
2593 (version "7.0.20200811075006")
2597 (uri (pypi-uri "schema-salad" version))
2600 "0wanbwmqb189x1m0vacnhpivfsr8rwbqknngivzxxs8j46yj80bg"))))
2601 (build-system python-build-system)
2603 `(("python-cachecontrol" ,python-cachecontrol-0.11)
2604 ("python-lockfile" ,python-lockfile)
2605 ("python-mistune" ,python-mistune)
2606 ("python-rdflib" ,python-rdflib)
2607 ("python-rdflib-jsonld" ,python-rdflib-jsonld)
2608 ("python-requests" ,python-requests)
2609 ("python-ruamel.yaml" ,python-ruamel.yaml)
2610 ("python-typing-extensions" ,python-typing-extensions)))
2612 `(("python-pytest" ,python-pytest)
2613 ("python-pytest-runner" ,python-pytest-runner)))
2614 (home-page "https://github.com/common-workflow-language/schema_salad")
2615 (synopsis "Schema Annotations for Linked Avro Data (SALAD)")
2617 "Salad is a schema language for describing JSON or YAML structured linked
2618 data documents. Salad schema describes rules for preprocessing, structural
2619 validation, and hyperlink checking for documents described by a Salad schema.
2620 Salad supports rich data modeling with inheritance, template specialization,
2621 object identifiers, object references, documentation generation, code
2622 generation, and transformation to RDF. Salad provides a bridge between document
2623 and record oriented data modeling and the Semantic Web.")
2624 (license license:asl2.0)))
2626 (define-public cwltool
2629 (version "3.0.20201121085451")
2633 (url "https://github.com/common-workflow-language/cwltool")
2635 (file-name (git-file-name name version))
2638 "1awf99n7aglxc5zszrlrv6jxp355jp45ws7wpsgjlgcdv7advn0w"))))
2639 (build-system python-build-system)
2642 (modify-phases %standard-phases
2643 (add-after 'unpack 'loosen-version-restrictions
2645 (substitute* "setup.py"
2646 (("== 1.5.1") ">=1.5.1") ; prov
2647 ((", < 3.5") "")) ; shellescape
2649 (add-after 'unpack 'dont-use-git
2651 (substitute* "gittaggers.py"
2652 (("self.git_timestamp_tag\\(\\)")
2653 (string-append "time.strftime('.%Y%m%d%H%M%S', time.gmtime(int("
2654 (string-drop ,version 4) ")))")))
2656 (add-after 'unpack 'modify-tests
2658 ;; Tries to connect to the internet.
2659 (delete-file "tests/test_udocker.py")
2660 (delete-file "tests/test_http_input.py")
2661 (substitute* "tests/test_load_tool.py"
2662 (("def test_load_graph_fragment_from_packed")
2663 (string-append "@pytest.mark.skip(reason=\"Disabled by Guix\")\n"
2664 "def test_load_graph_fragment_from_packed")))
2665 (substitute* "tests/test_examples.py"
2666 (("def test_env_filtering")
2667 (string-append "@pytest.mark.skip(reason=\"Disabled by Guix\")\n"
2668 "def test_env_filtering")))
2669 ;; Tries to use cwl-runners.
2670 (substitute* "tests/test_examples.py"
2671 (("def test_v1_0_arg_empty_prefix_separate_false")
2672 (string-append "@pytest.mark.skip(reason=\"Disabled by Guix\")\n"
2673 "def test_v1_0_arg_empty_prefix_separate_false")))
2676 `(("python-argcomplete" ,python-argcomplete)
2677 ("python-bagit" ,python-bagit)
2678 ("python-coloredlogs" ,python-coloredlogs)
2679 ("python-mypy-extensions" ,python-mypy-extensions)
2680 ("python-prov" ,python-prov)
2681 ("python-pydot" ,python-pydot)
2682 ("python-psutil" ,python-psutil)
2683 ("python-rdflib" ,python-rdflib)
2684 ("python-requests" ,python-requests)
2685 ("python-ruamel.yaml" ,python-ruamel.yaml)
2686 ("python-schema-salad" ,python-schema-salad)
2687 ("python-shellescape" ,python-shellescape)
2688 ("python-typing-extensions" ,python-typing-extensions)
2689 ;; Not listed as needed but still necessary:
2692 `(("python-arcp" ,python-arcp)
2693 ("python-humanfriendly" ,python-humanfriendly)
2694 ("python-mock" ,python-mock)
2695 ("python-pytest" ,python-pytest)
2696 ("python-pytest-cov" ,python-pytest-cov)
2697 ("python-pytest-mock" ,python-pytest-mock)
2698 ("python-pytest-runner" ,python-pytest-runner)
2699 ("python-rdflib-jsonld" ,python-rdflib-jsonld)))
2701 "https://github.com/common-workflow-language/common-workflow-language")
2702 (synopsis "Common Workflow Language reference implementation")
2704 "This is the reference implementation of the @acronym{CWL, Common Workflow
2705 Language} standards. The CWL open standards are for describing analysis
2706 workflows and tools in a way that makes them portable and scalable across a
2707 variety of software and hardware environments, from workstations to cluster,
2708 cloud, and high performance computing (HPC) environments. CWL is designed to
2709 meet the needs of data-intensive science, such as Bioinformatics, Medical
2710 Imaging, Astronomy, Physics, and Chemistry. The @acronym{cwltool, CWL reference
2711 implementation} is intended to be feature complete and to provide comprehensive
2712 validation of CWL files as well as provide other tools related to working with
2714 (license license:asl2.0)))
2716 (define-public python-dendropy
2718 (name "python-dendropy")
2723 ;; Source from GitHub so that tests are included.
2725 (url "https://github.com/jeetsukumaran/DendroPy")
2726 (commit (string-append "v" version))))
2727 (file-name (git-file-name name version))
2730 "097hfyv2kaf4x92i4rjx0paw2cncxap48qivv8zxng4z7nhid0x9"))))
2731 (build-system python-build-system)
2732 (home-page "https://dendropy.org/")
2733 (synopsis "Library for phylogenetics and phylogenetic computing")
2735 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
2736 writing, simulation, processing and manipulation of phylogenetic
2737 trees (phylogenies) and characters.")
2738 (license license:bsd-3)))
2740 (define-public python2-dendropy
2741 (let ((base (package-with-python2 python-dendropy)))
2746 (modify-phases %standard-phases
2747 (add-after 'unpack 'remove-failing-test
2749 ;; This test fails when the full test suite is run, as documented
2750 ;; at https://github.com/jeetsukumaran/DendroPy/issues/74
2751 (substitute* "tests/test_dataio_nexml_reader_tree_list.py"
2752 (("test_collection_comments_and_annotations")
2753 "do_not_test_collection_comments_and_annotations"))
2755 ,@(package-arguments base))))))
2757 (define-public python-py2bit
2759 (name "python-py2bit")
2764 (uri (pypi-uri "py2bit" version))
2767 "1vw2nvw1yrl7ikkqsqs1pg239yr5nspvd969r1x9arms1k25a1a5"))))
2768 (build-system python-build-system)
2769 (home-page "https://github.com/dpryan79/py2bit")
2770 (synopsis "Access 2bit files using lib2bit")
2772 "This package provides Python bindings for lib2bit to access 2bit files
2774 (license license:expat)))
2776 (define-public delly
2783 (url "https://github.com/dellytools/delly")
2784 (commit (string-append "v" version))))
2785 (file-name (git-file-name name version))
2787 (base32 "1ibnplgfzj96w8glkx17v7sld3pm402fr5ybmf3h0rlcryabxrqy"))
2788 (modules '((guix build utils)))
2791 (delete-file-recursively "src/htslib")
2793 (build-system gnu-build-system)
2795 `(#:tests? #f ; There are no tests to run.
2797 (list "PARALLEL=1" ; Allow parallel execution at run-time.
2798 (string-append "prefix=" (assoc-ref %outputs "out")))
2800 (modify-phases %standard-phases
2801 (delete 'configure) ; There is no configure phase.
2802 (add-after 'install 'install-templates
2803 (lambda* (#:key outputs #:allow-other-keys)
2804 (let ((templates (string-append (assoc-ref outputs "out")
2805 "/share/delly/templates")))
2807 (copy-recursively "excludeTemplates" templates)
2814 (home-page "https://github.com/dellytools/delly")
2815 (synopsis "Integrated structural variant prediction method")
2816 (description "Delly is an integrated structural variant prediction method
2817 that can discover and genotype deletions, tandem duplications, inversions and
2818 translocations at single-nucleotide resolution in short-read massively parallel
2819 sequencing data. It uses paired-ends and split-reads to sensitively and
2820 accurately delineate genomic rearrangements throughout the genome.")
2821 (license license:gpl3+)))
2823 (define-public diamond
2830 (url "https://github.com/bbuchfink/diamond")
2831 (commit (string-append "v" version))))
2832 (file-name (git-file-name name version))
2835 "0k6f3kb6cniw11xw6763kkbs1sl0yack7xsy7q5fl5v170ssphq4"))))
2836 (build-system cmake-build-system)
2838 '(#:tests? #f ; no "check" target
2840 (modify-phases %standard-phases
2841 (add-after 'unpack 'remove-native-compilation
2843 (substitute* "CMakeLists.txt" (("-march=native") ""))
2847 (home-page "https://github.com/bbuchfink/diamond")
2848 (synopsis "Accelerated BLAST compatible local sequence aligner")
2850 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2851 translated DNA query sequences against a protein reference database (BLASTP
2852 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2853 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2854 data and settings.")
2855 (license license:agpl3+)))
2857 (define-public discrover
2865 (url "https://github.com/maaskola/discrover")
2867 (file-name (git-file-name name version))
2870 "173fwi2vb6a5kp406hm3jj6j7v4whww796f2qcygp4rpvamh307y"))))
2871 (build-system cmake-build-system)
2873 `(#:tests? #f ; there are no tests
2875 (modify-phases %standard-phases
2876 (add-after 'unpack 'fix-latex-errors
2878 (with-fluids ((%default-port-encoding #f))
2879 (substitute* "doc/references.bib"
2880 (("\\{S\\}illanp[^,]+,")
2881 "{S}illanp{\\\"a}{\\\"a},")))
2882 ;; XXX: I just can't get pdflatex to not complain about these
2883 ;; characters. They end up in the manual via the generated
2884 ;; discrover-cli-help.txt.
2885 (substitute* "src/hmm/cli.cpp"
2889 ;; This seems to be a syntax error.
2890 (substitute* "doc/discrover-manual.tex"
2891 (("theverbbox\\[t\\]") "theverbbox"))
2893 (add-after 'unpack 'add-missing-includes
2895 (substitute* "src/executioninformation.hpp"
2896 (("#define EXECUTIONINFORMATION_HPP" line)
2897 (string-append line "\n#include <random>")))
2898 (substitute* "src/plasma/fasta.hpp"
2899 (("#define FASTA_HPP" line)
2900 (string-append line "\n#include <random>")))
2902 ;; FIXME: this is needed because we're using texlive-union, which
2903 ;; doesn't handle fonts correctly. It expects to be able to generate
2904 ;; fonts in the home directory.
2905 (add-before 'build 'setenv-HOME
2906 (lambda _ (setenv "HOME" "/tmp") #t)))))
2910 ("rmath-standalone" ,rmath-standalone)))
2912 `(("texlive" ,(texlive-union (list texlive-fonts-cm
2913 texlive-fonts-amsfonts
2916 texlive-latex-examplep
2917 texlive-latex-hyperref
2919 texlive-latex-natbib
2920 texlive-bibtex ; style files used by natbib
2921 texlive-latex-pgf ; tikz
2922 texlive-latex-verbatimbox)))
2923 ("imagemagick" ,imagemagick)))
2924 (home-page "https://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2925 (synopsis "Discover discriminative nucleotide sequence motifs")
2926 (description "Discrover is a motif discovery method to find binding sites
2927 of nucleic acid binding proteins.")
2928 (license license:gpl3+)))
2930 (define-public eigensoft
2938 (url "https://github.com/DReichLab/EIG")
2939 (commit (string-append "v" version))))
2940 (file-name (git-file-name name version))
2943 "1c141fqvhnzibmnf22sv23vbmzm20kjjyrib44cfh75wyndp2d9k"))
2944 (modules '((guix build utils)))
2945 ;; Remove pre-built binaries.
2947 (delete-file-recursively "bin")
2950 (build-system gnu-build-system)
2952 `(#:tests? #f ; There are no tests.
2953 #:make-flags '("CC=gcc")
2955 (modify-phases %standard-phases
2956 ;; There is no configure phase, but the Makefile is in a
2959 (lambda _ (chdir "src") #t))
2960 ;; The provided install target only copies executables to
2961 ;; the "bin" directory in the build root.
2962 (add-after 'install 'actually-install
2963 (lambda* (#:key outputs #:allow-other-keys)
2964 (let* ((out (assoc-ref outputs "out"))
2965 (bin (string-append out "/bin")))
2966 (for-each (lambda (file)
2967 (install-file file bin))
2968 (find-files "../bin" ".*"))
2973 ("openblas" ,openblas)
2975 ("gfortran" ,gfortran "lib")))
2976 (home-page "https://github.com/DReichLab/EIG")
2977 (synopsis "Tools for population genetics")
2978 (description "The EIGENSOFT package provides tools for population
2979 genetics and stratification correction. EIGENSOFT implements methods commonly
2980 used in population genetics analyses such as PCA, computation of Tracy-Widom
2981 statistics, and finding related individuals in structured populations. It
2982 comes with a built-in plotting script and supports multiple file formats and
2983 quantitative phenotypes.")
2984 ;; The license of the eigensoft tools is Expat, but since it's
2985 ;; linking with the GNU Scientific Library (GSL) the effective
2986 ;; license is the GPL.
2987 (license license:gpl3+)))
2989 (define-public edirect
2992 (version "13.3.20200128")
2995 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect"
2996 "/versions/" version
2997 "/edirect-" version ".tar.gz"))
3000 "093zp7klv81ph0y8mm8d78a9hnpfxbv2kdym70gzdf3vz176rw33"))
3001 (modules '((guix build utils)))
3003 '(begin (delete-file "Mozilla-CA.tar.gz")
3004 (substitute* "rchive.go"
3005 ;; This go library does not have any license.
3006 (("github.com/fiam/gounidecode/unidecode")
3007 "golang.org/rainycape/unidecode"))
3009 (build-system perl-build-system)
3012 (modify-phases %standard-phases
3015 (delete 'check) ; simple check after install
3016 (add-after 'unpack 'patch-programs
3017 (lambda* (#:key inputs #:allow-other-keys)
3018 ;; Ignore errors about missing xtract.Linux and rchive.Linux.
3019 (substitute* "pm-refresh"
3020 (("cat \\\"\\$target")
3021 "grep ^[[:digit:]] \"$target"))
3024 (lambda* (#:key inputs outputs #:allow-other-keys)
3025 (let ((bin (string-append (assoc-ref outputs "out") "/bin"))
3026 (edirect-go (assoc-ref inputs "edirect-go-programs")))
3029 (install-file file bin))
3030 '("archive-pubmed" "asp-cp" "asp-ls" "download-ncbi-data"
3031 "download-pubmed" "edirect.pl" "efetch" "epost" "esearch"
3032 "fetch-pubmed" "ftp-cp" "ftp-ls" "has-asp" "index-pubmed"
3033 "pm-prepare" "pm-refresh" "pm-stash" "pm-collect"
3034 "pm-index" "pm-invert" "pm-merge" "pm-promote"))
3035 (symlink (string-append edirect-go "/bin/xtract.Linux")
3036 (string-append bin "/xtract"))
3037 (symlink (string-append edirect-go "/bin/rchive.Linux")
3038 (string-append bin "/rchive")))
3040 (add-after 'install 'wrap-program
3041 (lambda* (#:key outputs #:allow-other-keys)
3042 ;; Make sure everything can run in a pure environment.
3043 (let ((out (assoc-ref outputs "out"))
3044 (path (getenv "PERL5LIB")))
3048 `("PERL5LIB" ":" prefix (,path)))
3050 `("PATH" ":" prefix (,(string-append out "/bin")
3051 ,(dirname (which "sed"))
3052 ,(dirname (which "gzip"))
3053 ,(dirname (which "grep"))
3054 ,(dirname (which "perl"))
3055 ,(dirname (which "uname"))))))
3056 (find-files out ".")))
3058 (add-after 'wrap-program 'check
3059 (lambda* (#:key outputs #:allow-other-keys)
3060 (invoke (string-append (assoc-ref outputs "out")
3065 `(("edirect-go-programs" ,edirect-go-programs)
3066 ("perl-html-parser" ,perl-html-parser)
3067 ("perl-encode-locale" ,perl-encode-locale)
3068 ("perl-file-listing" ,perl-file-listing)
3069 ("perl-html-tagset" ,perl-html-tagset)
3070 ("perl-html-tree" ,perl-html-tree)
3071 ("perl-http-cookies" ,perl-http-cookies)
3072 ("perl-http-date" ,perl-http-date)
3073 ("perl-http-message" ,perl-http-message)
3074 ("perl-http-negotiate" ,perl-http-negotiate)
3075 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
3076 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
3077 ("perl-net-http" ,perl-net-http)
3078 ("perl-uri" ,perl-uri)
3079 ("perl-www-robotrules" ,perl-www-robotrules)
3080 ("perl-xml-simple" ,perl-xml-simple)
3082 (home-page "https://www.ncbi.nlm.nih.gov/books/NBK179288/")
3083 (synopsis "Tools for accessing the NCBI's set of databases")
3085 "Entrez Direct (EDirect) is a method for accessing the National Center
3086 for Biotechnology Information's (NCBI) set of interconnected
3087 databases (publication, sequence, structure, gene, variation, expression,
3088 etc.) from a terminal. Functions take search terms from command-line
3089 arguments. Individual operations are combined to build multi-step queries.
3090 Record retrieval and formatting normally complete the process.
3092 EDirect also provides an argument-driven function that simplifies the
3093 extraction of data from document summaries or other results that are returned
3094 in structured XML format. This can eliminate the need for writing custom
3095 software to answer ad hoc questions.")
3096 (native-search-paths
3097 ;; Ideally this should be set for LWP somewhere.
3098 (list (search-path-specification
3099 (variable "PERL_LWP_SSL_CA_FILE")
3100 (file-type 'regular)
3102 (files '("/etc/ssl/certs/ca-certificates.crt")))))
3103 (license license:public-domain)))
3105 (define-public edirect-go-programs
3108 (name "edirect-go-programs")
3109 (build-system go-build-system)
3111 `(#:install-source? #f
3112 #:tests? #f ; No tests.
3113 #:import-path "ncbi.nlm.nih.gov/entrez/edirect"
3115 (modify-phases %standard-phases
3117 (lambda* (#:key import-path #:allow-other-keys)
3118 (with-directory-excursion (string-append "src/" import-path)
3119 (invoke "go" "build" "-v" "-x" "j2x.go")
3120 (invoke "go" "build" "-v" "-x" "t2x.go")
3121 (invoke "go" "build" "-v" "-x" "-o"
3122 "xtract.Linux" "xtract.go" "common.go")
3123 (invoke "go" "build" "-v" "-x" "-o"
3124 "rchive.Linux" "rchive.go" "common.go")
3125 (invoke "go" "build" "-v" "-x" "-o" "symbols.Linux" "s2p.go"))))
3127 (lambda* (#:key outputs import-path #:allow-other-keys)
3128 (let ((dest (string-append (assoc-ref outputs "out") "/bin"))
3129 (source (string-append "src/" import-path "/")))
3130 (for-each (lambda (file)
3131 (format #t "installing ~a~%" file)
3132 (install-file (string-append source file) dest))
3133 '("j2x" "t2x" "symbols.Linux" "xtract.Linux" "rchive.Linux"))
3136 (propagated-inputs '())
3138 `(("go-github-com-fatih-color" ,go-github-com-fatih-color)
3139 ("go-github-com-fogleman-gg" ,go-github-com-fogleman-gg)
3140 ("go-github-com-gedex-inflector" ,go-github-com-gedex-inflector)
3141 ("go-github-com-golang-freetype" ,go-github-com-golang-freetype)
3142 ("go-github-com-klauspost-cpuid" ,go-github-com-klauspost-cpuid)
3143 ("go-github-com-pbnjay-memory" ,go-github-com-pbnjay-memory)
3144 ("go-github-com-surgebase-porter2" ,go-github-com-surgebase-porter2)
3145 ("go-golang-org-rainycape-unidecode" ,go-golang-org-rainycape-unidecode)
3146 ("go-golang-org-x-image" ,go-golang-org-x-image)
3147 ("go-golang-org-x-text" ,go-golang-org-x-text)))))
3149 (define-public exonerate
3158 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
3159 "exonerate-" version ".tar.gz"))
3162 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
3163 (build-system gnu-build-system)
3165 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
3167 `(("pkg-config" ,pkg-config)))
3171 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
3172 (synopsis "Generic tool for biological sequence alignment")
3174 "Exonerate is a generic tool for pairwise sequence comparison. It allows
3175 the alignment of sequences using a many alignment models, either exhaustive
3176 dynamic programming or a variety of heuristics.")
3177 (license license:gpl3)))
3179 (define-public express
3186 (url "https://github.com/adarob/eXpress")
3188 (file-name (git-file-name name version))
3191 "18nb22n7x820fzjngf4qgyb3mspqkw7xyk7v7s5ps6wfrd8qwscb"))))
3192 (build-system cmake-build-system)
3194 `(#:tests? #f ;no "check" target
3196 (modify-phases %standard-phases
3197 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
3198 (lambda* (#:key inputs #:allow-other-keys)
3199 (substitute* "CMakeLists.txt"
3200 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
3201 "set(Boost_USE_STATIC_LIBS OFF)")
3202 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
3203 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
3204 (substitute* "src/CMakeLists.txt"
3205 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
3206 (string-append (assoc-ref inputs "bamtools") "/lib"))
3207 (("libprotobuf.a") "libprotobuf.so"))
3209 (add-after 'unpack 'remove-update-check
3211 (substitute* "src/main.cpp"
3212 (("#include \"update_check.h\"") "")
3213 (("check_version\\(PACKAGE_VERSION\\);") ""))
3217 ("bamtools" ,bamtools)
3218 ("protobuf" ,protobuf)
3220 (home-page "http://bio.math.berkeley.edu/eXpress")
3221 (synopsis "Streaming quantification for high-throughput genomic sequencing")
3223 "eXpress is a streaming tool for quantifying the abundances of a set of
3224 target sequences from sampled subsequences. Example applications include
3225 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
3226 analysis (from RNA-Seq), transcription factor binding quantification in
3227 ChIP-Seq, and analysis of metagenomic data.")
3228 (license license:artistic2.0)))
3230 (define-public express-beta-diversity
3232 (name "express-beta-diversity")
3237 (url "https://github.com/dparks1134/ExpressBetaDiversity")
3238 (commit (string-append "v" version))))
3239 (file-name (git-file-name name version))
3242 "0s0yzg5c21349rh7x4w9266jsvnp7j1hp9cf8sk32hz8nvrj745x"))))
3243 (build-system gnu-build-system)
3246 (modify-phases %standard-phases
3248 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
3250 (lambda _ (invoke "../bin/ExpressBetaDiversity" "-u") #t))
3252 (lambda* (#:key outputs #:allow-other-keys)
3253 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3254 (install-file "../scripts/convertToEBD.py" bin)
3255 (install-file "../bin/ExpressBetaDiversity" bin)
3258 `(("python" ,python-2)))
3259 (home-page "https://github.com/dparks1134/ExpressBetaDiversity")
3260 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
3262 "Express Beta Diversity (EBD) calculates ecological beta diversity
3263 (dissimilarity) measures between biological communities. EBD implements a
3264 variety of diversity measures including those that make use of phylogenetic
3265 similarity of community members.")
3266 (license license:gpl3+)))
3268 (define-public fasttree
3275 "http://www.microbesonline.org/fasttree/FastTree-"
3279 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
3280 (build-system gnu-build-system)
3282 `(#:tests? #f ; no "check" target
3284 (modify-phases %standard-phases
3288 (lambda* (#:key source #:allow-other-keys)
3291 "-finline-functions"
3302 "-finline-functions"
3311 (lambda* (#:key outputs #:allow-other-keys)
3312 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3313 (install-file "FastTree" bin)
3314 (install-file "FastTreeMP" bin)
3316 (home-page "http://www.microbesonline.org/fasttree")
3317 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
3319 "FastTree can handle alignments with up to a million of sequences in a
3320 reasonable amount of time and memory. For large alignments, FastTree is
3321 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
3322 (license license:gpl2+)))
3324 (define-public fastx-toolkit
3326 (name "fastx-toolkit")
3332 "https://github.com/agordon/fastx_toolkit/releases/download/"
3333 version "/fastx_toolkit-" version ".tar.bz2"))
3336 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
3337 (build-system gnu-build-system)
3339 `(("libgtextutils" ,libgtextutils)))
3341 `(("gcc" ,gcc-6) ;; doesn't build with later versions
3342 ("pkg-config" ,pkg-config)))
3343 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
3344 (synopsis "Tools for FASTA/FASTQ file preprocessing")
3346 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
3347 FASTA/FASTQ files preprocessing.
3349 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
3350 containing multiple short-reads sequences. The main processing of such
3351 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
3352 is sometimes more productive to preprocess the files before mapping the
3353 sequences to the genome---manipulating the sequences to produce better mapping
3354 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
3355 (license license:agpl3+)))
3357 (define-public flexbar
3364 (url "https://github.com/seqan/flexbar")
3365 (commit (string-append "v" version))))
3366 (file-name (git-file-name name version))
3369 "1pq9sxvdnldl14libk234m72dqhwgzs3acgl943wchwdqlcsi5r2"))))
3370 (build-system cmake-build-system)
3373 (modify-phases %standard-phases
3374 (add-after 'unpack 'do-not-tune-to-CPU
3376 (substitute* "src/CMakeLists.txt"
3377 ((" -march=native") ""))
3380 (lambda* (#:key outputs #:allow-other-keys)
3381 (setenv "PATH" (string-append (getcwd) ":" (getenv "PATH")))
3382 (with-directory-excursion "../source/test"
3383 (invoke "bash" "flexbar_test.sh"))
3386 (lambda* (#:key outputs #:allow-other-keys)
3387 (let* ((out (string-append (assoc-ref outputs "out")))
3388 (bin (string-append out "/bin/")))
3389 (install-file "flexbar" bin))
3395 `(("pkg-config" ,pkg-config)
3397 (home-page "https://github.com/seqan/flexbar")
3398 (synopsis "Barcode and adapter removal tool for sequencing platforms")
3400 "Flexbar preprocesses high-throughput nucleotide sequencing data
3401 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
3402 Moreover, trimming and filtering features are provided. Flexbar increases
3403 read mapping rates and improves genome and transcriptome assemblies. It
3404 supports next-generation sequencing data in fasta/q and csfasta/q format from
3405 Illumina, Roche 454, and the SOLiD platform.")
3406 (license license:bsd-3)))
3408 (define-public fraggenescan
3410 (name "fraggenescan")
3416 (string-append "mirror://sourceforge/fraggenescan/"
3417 "FragGeneScan" version ".tar.gz"))
3419 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
3420 (build-system gnu-build-system)
3423 (modify-phases %standard-phases
3425 (add-before 'build 'patch-paths
3426 (lambda* (#:key outputs #:allow-other-keys)
3427 (let* ((out (string-append (assoc-ref outputs "out")))
3428 (share (string-append out "/share/fraggenescan/")))
3429 (substitute* "run_FragGeneScan.pl"
3431 (string-append "system(\"" (which "rm")))
3433 (string-append "system(\"" (which "mv")))
3434 (("\\\"awk") (string-append "\"" (which "awk")))
3435 ;; This script and other programs expect the training files
3436 ;; to be in the non-standard location bin/train/XXX. Change
3437 ;; this to be share/fraggenescan/train/XXX instead.
3438 (("^\\$train.file = \\$dir.*")
3439 (string-append "$train_file = \""
3441 "train/\".$FGS_train_file;")))
3442 (substitute* "run_hmm.c"
3443 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
3444 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
3448 (invoke "make" "clean")
3449 (invoke "make" "fgs")
3452 (lambda* (#:key outputs #:allow-other-keys)
3453 (let* ((out (string-append (assoc-ref outputs "out")))
3454 (bin (string-append out "/bin/"))
3455 (share (string-append out "/share/fraggenescan/train")))
3456 (install-file "run_FragGeneScan.pl" bin)
3457 (install-file "FragGeneScan" bin)
3458 (copy-recursively "train" share))
3461 (add-after 'install 'post-install-check
3462 ;; In lieu of 'make check', run one of the examples and check the
3463 ;; output files gets created.
3464 (lambda* (#:key outputs #:allow-other-keys)
3465 (let* ((out (string-append (assoc-ref outputs "out")))
3466 (bin (string-append out "/bin/"))
3467 (frag (string-append bin "run_FragGeneScan.pl")))
3468 ;; Test complete genome.
3470 "-genome=./example/NC_000913.fna"
3474 (unless (and (file-exists? "test2.faa")
3475 (file-exists? "test2.ffn")
3476 (file-exists? "test2.gff")
3477 (file-exists? "test2.out"))
3478 (error "Expected files do not exist."))
3479 ;; Test incomplete sequences.
3481 "-genome=./example/NC_000913-fgs.ffn"
3488 ("python" ,python-2))) ;not compatible with python 3.
3489 (home-page "https://sourceforge.net/projects/fraggenescan/")
3490 (synopsis "Finds potentially fragmented genes in short reads")
3492 "FragGeneScan is a program for predicting bacterial and archaeal genes in
3493 short and error-prone DNA sequencing reads. It can also be applied to predict
3494 genes in incomplete assemblies or complete genomes.")
3495 ;; GPL3+ according to private correspondense with the authors.
3496 (license license:gpl3+)))
3498 (define-public fxtract
3499 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
3507 (url "https://github.com/ctSkennerton/fxtract")
3509 (file-name (git-file-name name version))
3512 "0hab3gpwf4w9s87qlbswq6ws1qqybh4dcqk79q1ahyldzai5fgp5"))))
3513 (build-system gnu-build-system)
3515 `(#:make-flags (list
3516 (string-append "PREFIX=" (assoc-ref %outputs "out"))
3518 #:test-target "fxtract_test"
3520 (modify-phases %standard-phases
3522 (add-before 'build 'copy-util
3523 (lambda* (#:key inputs #:allow-other-keys)
3525 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
3527 ;; Do not use make install as this requires additional dependencies.
3529 (lambda* (#:key outputs #:allow-other-keys)
3530 (let* ((out (assoc-ref outputs "out"))
3531 (bin (string-append out"/bin")))
3532 (install-file "fxtract" bin)
3538 ;; ctskennerton-util is licensed under GPL2.
3539 `(("ctskennerton-util"
3543 (url "https://github.com/ctSkennerton/util")
3544 (commit util-commit)))
3545 (file-name (string-append
3546 "ctstennerton-util-" util-commit "-checkout"))
3549 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
3550 (home-page "https://github.com/ctSkennerton/fxtract")
3551 (synopsis "Extract sequences from FASTA and FASTQ files")
3553 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
3554 or FASTQ) file given a subsequence. It uses a simple substring search for
3555 basic tasks but can change to using POSIX regular expressions, PCRE, hash
3556 lookups or multi-pattern searching as required. By default fxtract looks in
3557 the sequence of each record but can also be told to look in the header,
3558 comment or quality sections.")
3559 ;; 'util' requires SSE instructions.
3560 (supported-systems '("x86_64-linux"))
3561 (license license:expat))))
3563 (define-public gemma
3570 (url "https://github.com/xiangzhou/GEMMA")
3571 (commit (string-append "v" version))))
3572 (file-name (git-file-name name version))
3575 "1s3ncnbn45r2hh1cvrqky1kbqq6546biypr4f5mkw1kqlrgyh0yg"))))
3578 ("gfortran" ,gfortran "lib")
3581 ("openblas" ,openblas)
3583 (build-system gnu-build-system)
3586 '(,@(match (%current-system)
3588 '("FORCE_DYNAMIC=1"))
3590 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
3592 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
3594 (modify-phases %standard-phases
3596 (add-after 'unpack 'find-eigen
3597 (lambda* (#:key inputs #:allow-other-keys)
3598 ;; Ensure that Eigen headers can be found
3599 (setenv "CPLUS_INCLUDE_PATH"
3600 (string-append (assoc-ref inputs "eigen")
3603 (add-before 'build 'bin-mkdir
3608 (lambda* (#:key outputs #:allow-other-keys)
3609 (let ((out (assoc-ref outputs "out")))
3610 (install-file "bin/gemma"
3614 #:tests? #f)) ; no tests included yet
3615 (home-page "https://github.com/xiangzhou/GEMMA")
3616 (synopsis "Tool for genome-wide efficient mixed model association")
3618 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
3619 standard linear mixed model resolver with application in genome-wide
3620 association studies (GWAS).")
3621 (license license:gpl3)))
3630 (url "https://github.com/nboley/grit")
3632 (file-name (git-file-name name version))
3635 "1l5v8vfvfbrpmgnrvbrbv40d0arhxcnmxgv2f1mlcqfa3q6bkqm9"))))
3636 (build-system python-build-system)
3638 `(#:python ,python-2
3640 (modify-phases %standard-phases
3641 (add-after 'unpack 'generate-from-cython-sources
3642 (lambda* (#:key inputs outputs #:allow-other-keys)
3643 ;; Delete these C files to force fresh generation from pyx sources.
3644 (delete-file "grit/sparsify_support_fns.c")
3645 (delete-file "grit/call_peaks_support_fns.c")
3646 (substitute* "setup.py"
3647 (("Cython.Setup") "Cython.Build"))
3650 `(("python-scipy" ,python2-scipy)
3651 ("python-numpy" ,python2-numpy)
3652 ("python-pysam" ,python2-pysam)
3653 ("python-networkx" ,python2-networkx)))
3655 `(("python-cython" ,python2-cython)))
3656 ;; The canonical <http://grit-bio.org> home page times out as of 2020-01-21.
3657 (home-page "https://github.com/nboley/grit")
3658 (synopsis "Tool for integrative analysis of RNA-seq type assays")
3660 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
3661 full length transcript models. When none of these data sources are available,
3662 GRIT can be run by providing a candidate set of TES or TSS sites. In
3663 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
3664 also be run in quantification mode, where it uses a provided GTF file and just
3665 estimates transcript expression.")
3666 (license license:gpl3+)))
3668 (define-public hisat
3675 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
3676 version "-beta-source.zip"))
3679 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
3680 (build-system gnu-build-system)
3682 `(#:tests? #f ;no check target
3683 #:make-flags '("allall"
3684 ;; Disable unsupported `popcnt' instructions on
3685 ;; architectures other than x86_64
3686 ,@(if (string-prefix? "x86_64"
3687 (or (%current-target-system)
3690 '("POPCNT_CAPABILITY=0")))
3692 (modify-phases %standard-phases
3693 (add-after 'unpack 'patch-sources
3695 ;; XXX Cannot use snippet because zip files are not supported
3696 (substitute* "Makefile"
3697 (("^CC = .*$") "CC = gcc")
3698 (("^CPP = .*$") "CPP = g++")
3699 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
3700 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
3701 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
3702 (substitute* '("hisat-build" "hisat-inspect")
3703 (("/usr/bin/env") (which "env")))
3706 (lambda* (#:key outputs #:allow-other-keys)
3707 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
3708 (for-each (lambda (file)
3709 (install-file file bin))
3712 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
3714 (delete 'configure))))
3716 `(("unzip" ,unzip)))
3721 ;; Non-portable SSE instructions are used so building fails on platforms
3722 ;; other than x86_64.
3723 (supported-systems '("x86_64-linux"))
3724 (home-page "https://ccb.jhu.edu/software/hisat/index.shtml")
3725 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
3727 "HISAT is a fast and sensitive spliced alignment program for mapping
3728 RNA-seq reads. In addition to one global FM index that represents a whole
3729 genome, HISAT uses a large set of small FM indexes that collectively cover the
3730 whole genome. These small indexes (called local indexes) combined with
3731 several alignment strategies enable effective alignment of RNA-seq reads, in
3732 particular, reads spanning multiple exons.")
3733 (license license:gpl3+)))
3735 (define-public hisat2
3742 (uri (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
3743 "/downloads/hisat2-" version "-source.zip"))
3746 "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"))))
3747 (build-system gnu-build-system)
3749 `(#:tests? #f ; no check target
3750 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
3751 #:modules ((guix build gnu-build-system)
3755 (modify-phases %standard-phases
3756 (add-after 'unpack 'make-deterministic
3758 (substitute* "Makefile"
3763 (lambda* (#:key outputs #:allow-other-keys)
3764 (let* ((out (assoc-ref outputs "out"))
3765 (bin (string-append out "/bin/"))
3766 (doc (string-append out "/share/doc/hisat2/")))
3768 (cut install-file <> bin)
3770 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
3772 (install-file "doc/manual.inc.html" doc))
3775 `(("unzip" ,unzip) ; needed for archive from ftp
3777 ("pandoc" ,pandoc))) ; for documentation
3778 (home-page "https://ccb.jhu.edu/software/hisat2/index.shtml")
3779 (synopsis "Graph-based alignment of genomic sequencing reads")
3780 (description "HISAT2 is a fast and sensitive alignment program for mapping
3781 next-generation sequencing reads (both DNA and RNA) to a population of human
3782 genomes (as well as to a single reference genome). In addition to using one
3783 global @dfn{graph FM} (GFM) index that represents a population of human
3784 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
3785 the whole genome. These small indexes, combined with several alignment
3786 strategies, enable rapid and accurate alignment of sequencing reads. This new
3787 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
3788 ;; HISAT2 contains files from Bowtie2, which is released under
3789 ;; GPLv2 or later. The HISAT2 source files are released under
3791 (license license:gpl3+)))
3793 (define-public hmmer
3801 "http://eddylab.org/software/hmmer/hmmer-" version ".tar.gz"))
3804 "171bivy6xhgjsz5nv53n81pc3frnwz29ylblawk2bv46szwjjqd5"))))
3805 (build-system gnu-build-system)
3806 (native-inputs `(("perl" ,perl)))
3807 (home-page "http://hmmer.org/")
3808 (synopsis "Biosequence analysis using profile hidden Markov models")
3810 "HMMER is used for searching sequence databases for homologs of protein
3811 sequences, and for making protein sequence alignments. It implements methods
3812 using probabilistic models called profile hidden Markov models (profile
3814 ;; hmmer uses non-portable SSE intrinsics so building fails on other
3816 (supported-systems '("x86_64-linux" "i686-linux"))
3817 (license license:bsd-3)))
3819 (define-public htseq
3825 (uri (pypi-uri "HTSeq" version))
3828 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
3829 (build-system python-build-system)
3831 `(("python-cython" ,python-cython)))
3832 ;; Numpy needs to be propagated when htseq is used as a Python library.
3834 `(("python-numpy" ,python-numpy)))
3836 `(("python-pysam" ,python-pysam)
3837 ("python-matplotlib" ,python-matplotlib)))
3838 (home-page "https://htseq.readthedocs.io/")
3839 (synopsis "Analysing high-throughput sequencing data with Python")
3841 "HTSeq is a Python package that provides infrastructure to process data
3842 from high-throughput sequencing assays.")
3843 (license license:gpl3+)))
3845 (define-public python2-htseq
3846 (package-with-python2 htseq))
3848 (define-public java-htsjdk
3850 (name "java-htsjdk")
3851 (version "2.3.0") ; last version without build dependency on gradle
3855 (url "https://github.com/samtools/htsjdk")
3857 (file-name (git-file-name name version))
3860 "1b178ixcabanm834ydjl3jiakpyxdmki32hqfv2abrzn3rcwa28i"))
3861 (modules '((guix build utils)))
3863 ;; Delete pre-built binaries
3865 (delete-file-recursively "lib")
3868 (build-system ant-build-system)
3870 `(#:tests? #f ; test require Internet access
3873 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3874 "/share/java/htsjdk/"))
3875 #:build-target "all"
3877 (modify-phases %standard-phases
3878 ;; The build phase also installs the jars
3879 (delete 'install))))
3881 `(("java-ngs" ,java-ngs)
3882 ("java-snappy-1" ,java-snappy-1)
3883 ("java-commons-compress" ,java-commons-compress)
3884 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3885 ("java-commons-jexl-2" ,java-commons-jexl-2)
3886 ("java-xz" ,java-xz)))
3888 `(("java-testng" ,java-testng)))
3889 (home-page "http://samtools.github.io/htsjdk/")
3890 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3892 "HTSJDK is an implementation of a unified Java library for accessing
3893 common file formats, such as SAM and VCF, used for high-throughput
3894 sequencing (HTS) data. There are also an number of useful utilities for
3895 manipulating HTS data.")
3896 (license license:expat)))
3898 (define-public java-htsjdk-latest
3900 (name "java-htsjdk")
3905 (url "https://github.com/samtools/htsjdk")
3907 (file-name (string-append name "-" version "-checkout"))
3910 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
3911 (build-system ant-build-system)
3913 `(#:tests? #f ; test require Scala
3915 #:jar-name "htsjdk.jar"
3917 (modify-phases %standard-phases
3918 (add-after 'unpack 'remove-useless-build.xml
3919 (lambda _ (delete-file "build.xml") #t))
3920 ;; The tests require the scalatest package.
3921 (add-after 'unpack 'remove-tests
3922 (lambda _ (delete-file-recursively "src/test") #t)))))
3924 `(("java-ngs" ,java-ngs)
3925 ("java-snappy-1" ,java-snappy-1)
3926 ("java-commons-compress" ,java-commons-compress)
3927 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3928 ("java-commons-jexl-2" ,java-commons-jexl-2)
3929 ("java-xz" ,java-xz)))
3931 `(("java-junit" ,java-junit)))
3932 (home-page "http://samtools.github.io/htsjdk/")
3933 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3935 "HTSJDK is an implementation of a unified Java library for accessing
3936 common file formats, such as SAM and VCF, used for high-throughput
3937 sequencing (HTS) data. There are also an number of useful utilities for
3938 manipulating HTS data.")
3939 (license license:expat)))
3941 ;; This is needed for picard 2.10.3
3942 (define-public java-htsjdk-2.10.1
3943 (package (inherit java-htsjdk-latest)
3944 (name "java-htsjdk")
3949 (url "https://github.com/samtools/htsjdk")
3951 (file-name (string-append name "-" version "-checkout"))
3954 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
3955 (build-system ant-build-system)
3957 `(#:tests? #f ; tests require Scala
3959 #:jar-name "htsjdk.jar"
3961 (modify-phases %standard-phases
3962 (add-after 'unpack 'remove-useless-build.xml
3963 (lambda _ (delete-file "build.xml") #t))
3964 ;; The tests require the scalatest package.
3965 (add-after 'unpack 'remove-tests
3966 (lambda _ (delete-file-recursively "src/test") #t)))))))
3968 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3969 ;; recent version of java-htsjdk, which depends on gradle.
3970 (define-public java-picard
3972 (name "java-picard")
3977 (url "https://github.com/broadinstitute/picard")
3979 (file-name (string-append "java-picard-" version "-checkout"))
3982 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3983 (modules '((guix build utils)))
3986 ;; Delete pre-built binaries.
3987 (delete-file-recursively "lib")
3989 (substitute* "build.xml"
3990 ;; Remove build-time dependency on git.
3991 (("failifexecutionfails=\"true\"")
3992 "failifexecutionfails=\"false\"")
3994 (("depends=\"compile-htsjdk, ")
3996 (("depends=\"compile-htsjdk-tests, ")
3998 ;; Build picard-lib.jar before building picard.jar
3999 (("name=\"picard-jar\" depends=\"" line)
4000 (string-append line "picard-lib-jar, ")))
4002 (build-system ant-build-system)
4004 `(#:build-target "picard-jar"
4005 #:test-target "test"
4006 ;; Tests require jacoco:coverage.
4009 (list (string-append "-Dhtsjdk_lib_dir="
4010 (assoc-ref %build-inputs "java-htsjdk")
4011 "/share/java/htsjdk/")
4012 "-Dhtsjdk-classes=dist/tmp"
4013 (string-append "-Dhtsjdk-version="
4014 ,(package-version java-htsjdk)))
4017 (modify-phases %standard-phases
4018 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
4019 (delete 'generate-jar-indices)
4020 (add-after 'unpack 'use-our-htsjdk
4021 (lambda* (#:key inputs #:allow-other-keys)
4022 (substitute* "build.xml"
4023 (("\\$\\{htsjdk\\}/lib")
4024 (string-append (assoc-ref inputs "java-htsjdk")
4025 "/share/java/htsjdk/")))
4027 (add-after 'unpack 'make-test-target-independent
4028 (lambda* (#:key inputs #:allow-other-keys)
4029 (substitute* "build.xml"
4030 (("name=\"test\" depends=\"compile, ")
4031 "name=\"test\" depends=\""))
4033 (replace 'install (install-jars "dist")))))
4035 `(("java-htsjdk" ,java-htsjdk)
4036 ("java-guava" ,java-guava)))
4038 `(("java-testng" ,java-testng)))
4039 (home-page "http://broadinstitute.github.io/picard/")
4040 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
4041 (description "Picard is a set of Java command line tools for manipulating
4042 high-throughput sequencing (HTS) data and formats. Picard is implemented
4043 using the HTSJDK Java library to support accessing file formats that are
4044 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
4046 (license license:expat)))
4048 ;; This is needed for dropseq-tools
4049 (define-public java-picard-2.10.3
4051 (name "java-picard")
4056 (url "https://github.com/broadinstitute/picard")
4058 (file-name (string-append "java-picard-" version "-checkout"))
4061 "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi"))))
4062 (build-system ant-build-system)
4064 `(#:jar-name "picard.jar"
4065 ;; Tests require jacoco:coverage.
4068 #:main-class "picard.cmdline.PicardCommandLine"
4069 #:modules ((guix build ant-build-system)
4071 (guix build java-utils)
4076 (modify-phases %standard-phases
4077 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
4078 (delete 'generate-jar-indices)
4079 (add-after 'unpack 'remove-useless-build.xml
4080 (lambda _ (delete-file "build.xml") #t))
4081 ;; This is necessary to ensure that htsjdk is found when using
4082 ;; picard.jar as an executable.
4083 (add-before 'build 'edit-classpath-in-manifest
4084 (lambda* (#:key inputs #:allow-other-keys)
4085 (chmod "build.xml" #o664)
4086 (call-with-output-file "build.xml.new"
4090 (with-input-from-file "build.xml"
4091 (lambda _ (xml->sxml #:trim-whitespace? #t)))
4092 `((target . ,(lambda (tag . kids)
4093 (let ((name ((sxpath '(name *text*))
4095 ;; FIXME: We're breaking the line
4096 ;; early with a dummy path to
4097 ;; ensure that the store reference
4098 ;; isn't broken apart and can still
4099 ;; be found by the reference
4104 ~a/share/java/htsjdk.jar${line.separator}${line.separator}"
4105 ;; maximum line length is 70
4106 (string-tabulate (const #\b) 57)
4107 (assoc-ref inputs "java-htsjdk"))))
4108 (if (member "manifest" name)
4111 (@ (file "${manifest.file}")
4112 (match "\\r\\n\\r\\n")
4113 (replace "${line.separator}")))
4116 (file "${manifest.file}")
4119 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
4120 (*text* . ,(lambda (_ txt) txt))))
4122 (rename-file "build.xml.new" "build.xml")
4125 `(("java-htsjdk" ,java-htsjdk-2.10.1)))
4127 `(("java-testng" ,java-testng)
4128 ("java-guava" ,java-guava)))
4129 (home-page "http://broadinstitute.github.io/picard/")
4130 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
4131 (description "Picard is a set of Java command line tools for manipulating
4132 high-throughput sequencing (HTS) data and formats. Picard is implemented
4133 using the HTSJDK Java library to support accessing file formats that are
4134 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
4136 (license license:expat)))
4138 ;; This is the last version of Picard to provide net.sf.samtools
4139 (define-public java-picard-1.113
4140 (package (inherit java-picard)
4141 (name "java-picard")
4146 (url "https://github.com/broadinstitute/picard")
4148 (file-name (string-append "java-picard-" version "-checkout"))
4151 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
4152 (modules '((guix build utils)))
4155 ;; Delete pre-built binaries.
4156 (delete-file-recursively "lib")
4159 (build-system ant-build-system)
4161 `(#:build-target "picard-jar"
4162 #:test-target "test"
4163 ;; FIXME: the class path at test time is wrong.
4164 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
4165 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
4169 ;; This is only used for tests.
4171 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
4173 (modify-phases %standard-phases
4174 ;; FIXME: This phase fails.
4175 (delete 'generate-jar-indices)
4176 ;; Do not use bundled ant bzip2.
4177 (add-after 'unpack 'use-ant-bzip
4178 (lambda* (#:key inputs #:allow-other-keys)
4179 (substitute* "build.xml"
4180 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
4181 (string-append (assoc-ref inputs "ant")
4184 (add-after 'unpack 'make-test-target-independent
4185 (lambda* (#:key inputs #:allow-other-keys)
4186 (substitute* "build.xml"
4187 (("name=\"test\" depends=\"compile, ")
4188 "name=\"test\" depends=\"compile-tests, ")
4189 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
4190 "name=\"compile\" depends=\"compile-src\""))
4192 (add-after 'unpack 'fix-deflater-path
4193 (lambda* (#:key outputs #:allow-other-keys)
4194 (substitute* "src/java/net/sf/samtools/Defaults.java"
4195 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
4196 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
4197 (assoc-ref outputs "out")
4198 "/lib/jni/libIntelDeflater.so"
4201 ;; Build the deflater library, because we've previously deleted the
4202 ;; pre-built one. This can only be built with access to the JDK
4204 (add-after 'build 'build-jni
4205 (lambda* (#:key inputs #:allow-other-keys)
4208 (invoke "tar" "--strip-components=1" "-C" "jdk-src"
4209 "-xf" (assoc-ref inputs "jdk-src"))
4210 (invoke "javah" "-jni"
4211 "-classpath" "classes"
4213 "net.sf.samtools.util.zip.IntelDeflater")
4214 (with-directory-excursion "src/c/inteldeflater"
4215 (invoke "gcc" "-I../../../lib" "-I."
4216 (string-append "-I" (assoc-ref inputs "jdk")
4218 "-I../../../jdk-src/src/share/native/common/"
4219 "-I../../../jdk-src/src/solaris/native/common/"
4220 "-c" "-O3" "-fPIC" "IntelDeflater.c")
4221 (invoke "gcc" "-shared"
4222 "-o" "../../../lib/jni/libIntelDeflater.so"
4223 "IntelDeflater.o" "-lz" "-lstdc++"))
4225 ;; We can only build everything else after building the JNI library.
4226 (add-after 'build-jni 'build-rest
4227 (lambda* (#:key make-flags #:allow-other-keys)
4228 (apply invoke `("ant" "all" ,@make-flags))
4230 (add-before 'build 'set-JAVA6_HOME
4232 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
4234 (replace 'install (install-jars "dist"))
4235 (add-after 'install 'install-jni-lib
4236 (lambda* (#:key outputs #:allow-other-keys)
4237 (let ((jni (string-append (assoc-ref outputs "out")
4240 (install-file "lib/jni/libIntelDeflater.so" jni)
4243 `(("java-snappy-1" ,java-snappy-1)
4244 ("java-commons-jexl-2" ,java-commons-jexl-2)
4245 ("java-cofoja" ,java-cofoja)
4246 ("ant" ,ant/java8) ; for bzip2 support at runtime
4249 `(("ant-apache-bcel" ,ant-apache-bcel)
4250 ("ant-junit" ,ant-junit)
4251 ("java-testng" ,java-testng)
4252 ("java-commons-bcel" ,java-commons-bcel)
4253 ("java-jcommander" ,java-jcommander)
4254 ("jdk" ,icedtea-8 "jdk")
4255 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
4257 (define-public fastqc
4264 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
4265 "projects/fastqc/fastqc_v"
4266 version "_source.zip"))
4269 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
4270 (build-system ant-build-system)
4272 `(#:tests? #f ; there are no tests
4273 #:build-target "build"
4275 (modify-phases %standard-phases
4276 (add-after 'unpack 'fix-dependencies
4277 (lambda* (#:key inputs #:allow-other-keys)
4278 (substitute* "build.xml"
4280 (string-append (assoc-ref inputs "java-jbzip2")
4281 "/share/java/jbzip2.jar"))
4283 (string-append (assoc-ref inputs "java-picard-1.113")
4284 "/share/java/sam-1.112.jar"))
4286 (string-append (assoc-ref inputs "java-cisd-jhdf5")
4287 "/share/java/sis-jhdf5.jar")))
4289 ;; There is no installation target
4291 (lambda* (#:key inputs outputs #:allow-other-keys)
4292 (let* ((out (assoc-ref outputs "out"))
4293 (bin (string-append out "/bin"))
4294 (share (string-append out "/share/fastqc/"))
4295 (exe (string-append share "/fastqc")))
4296 (for-each mkdir-p (list bin share))
4297 (copy-recursively "bin" share)
4299 (("my \\$java_bin = 'java';")
4300 (string-append "my $java_bin = '"
4301 (assoc-ref inputs "java")
4304 (symlink exe (string-append bin "/fastqc"))
4308 ("perl" ,perl) ; needed for the wrapper script
4309 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
4310 ("java-picard-1.113" ,java-picard-1.113)
4311 ("java-jbzip2" ,java-jbzip2)))
4313 `(("unzip" ,unzip)))
4314 (home-page "https://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
4315 (synopsis "Quality control tool for high throughput sequence data")
4317 "FastQC aims to provide a simple way to do some quality control
4318 checks on raw sequence data coming from high throughput sequencing
4319 pipelines. It provides a modular set of analyses which you can use to
4320 give a quick impression of whether your data has any problems of which
4321 you should be aware before doing any further analysis.
4323 The main functions of FastQC are:
4326 @item Import of data from BAM, SAM or FastQ files (any variant);
4327 @item Providing a quick overview to tell you in which areas there may
4329 @item Summary graphs and tables to quickly assess your data;
4330 @item Export of results to an HTML based permanent report;
4331 @item Offline operation to allow automated generation of reports
4332 without running the interactive application.
4334 (license license:gpl3+)))
4336 (define-public fastp
4344 (url "https://github.com/OpenGene/fastp")
4345 (commit (string-append "v" version))))
4346 (file-name (git-file-name name version))
4349 "1r6ms5zbf5rps4rgp4z73nczadl00b5rqylw8f684isfz27dp0xh"))))
4350 (build-system gnu-build-system)
4352 `(#:tests? #f ; there are none
4354 (list (string-append "BINDIR=" (assoc-ref %outputs "out") "/bin"))
4356 (modify-phases %standard-phases
4358 (add-before 'install 'create-target-dir
4359 (lambda* (#:key outputs #:allow-other-keys)
4360 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4364 (home-page "https://github.com/OpenGene/fastp/")
4365 (synopsis "All-in-one FastQ preprocessor")
4367 "Fastp is a tool designed to provide fast all-in-one preprocessing for
4368 FastQ files. This tool has multi-threading support to afford high
4370 (license license:expat)))
4372 (define-public htslib
4379 "https://github.com/samtools/htslib/releases/download/"
4380 version "/htslib-" version ".tar.bz2"))
4383 "1mrq4mihzx37yqhj3sfz6da6mw49niia808bzsw2gkkgmadxvyng"))))
4384 (build-system gnu-build-system)
4385 ;; Let htslib translate "gs://" and "s3://" to regular https links with
4386 ;; "--enable-gcs" and "--enable-s3". For these options to work, we also
4387 ;; need to set "--enable-libcurl".
4389 `(#:configure-flags '("--enable-gcs"
4394 ("openssl" ,openssl)))
4395 ;; This is referred to in the pkg-config file as a required library.
4400 (home-page "https://www.htslib.org")
4401 (synopsis "C library for reading/writing high-throughput sequencing data")
4403 "HTSlib is a C library for reading/writing high-throughput sequencing
4404 data. It also provides the @command{bgzip}, @command{htsfile}, and
4405 @command{tabix} utilities.")
4406 ;; Files under cram/ are released under the modified BSD license;
4407 ;; the rest is released under the Expat license
4408 (license (list license:expat license:bsd-3))))
4410 (define-public htslib-1.9
4411 (package (inherit htslib)
4417 "https://github.com/samtools/htslib/releases/download/"
4418 version "/htslib-" version ".tar.bz2"))
4421 "16ljv43sc3fxmv63w7b2ff8m1s7h89xhazwmbm1bicz8axq8fjz0"))))))
4423 ;; This package should be removed once no packages rely upon it.
4431 "https://github.com/samtools/htslib/releases/download/"
4432 version "/htslib-" version ".tar.bz2"))
4435 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
4444 (url "https://github.com/nboley/idr")
4446 (file-name (git-file-name name version))
4449 "04j876h6z444v2q79drxx283d3k5snd72kj895wbalnl42206x9g"))
4450 ;; Delete generated C code.
4452 '(begin (delete-file "idr/inv_cdf.c") #t))))
4453 (build-system python-build-system)
4454 ;; There is only one test ("test_inv_cdf.py") and it tests features that
4455 ;; are no longer part of this package. It also asserts False, which
4456 ;; causes the tests to always fail.
4457 (arguments `(#:tests? #f))
4459 `(("python-scipy" ,python-scipy)
4460 ("python-sympy" ,python-sympy)
4461 ("python-numpy" ,python-numpy)
4462 ("python-matplotlib" ,python-matplotlib)))
4464 `(("python-cython" ,python-cython)))
4465 (home-page "https://github.com/nboley/idr")
4466 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
4468 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
4469 to measure the reproducibility of findings identified from replicate
4470 experiments and provide highly stable thresholds based on reproducibility.")
4471 (license license:gpl2+)))
4473 (define-public jellyfish
4479 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
4480 "releases/download/v" version
4481 "/jellyfish-" version ".tar.gz"))
4484 "1k4pc3fvv6w1km2yph4m5sd78fbxp21d6xyzgmy0gjihzc6mb249"))))
4485 (build-system gnu-build-system)
4486 (outputs '("out" ;for library
4487 "ruby" ;for Ruby bindings
4488 "python")) ;for Python bindings
4491 (list (string-append "--enable-ruby-binding="
4492 (assoc-ref %outputs "ruby"))
4493 (string-append "--enable-python-binding="
4494 (assoc-ref %outputs "python")))
4496 (modify-phases %standard-phases
4497 (add-before 'check 'set-SHELL-variable
4499 ;; generator_manager.hpp either uses /bin/sh or $SHELL
4501 (setenv "SHELL" (which "bash"))
4507 ("python" ,python-2)
4508 ("pkg-config" ,pkg-config)))
4510 `(("htslib" ,htslib)))
4511 (synopsis "Tool for fast counting of k-mers in DNA")
4513 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
4514 DNA. A k-mer is a substring of length k, and counting the occurrences of all
4515 such substrings is a central step in many analyses of DNA sequence. Jellyfish
4516 is a command-line program that reads FASTA and multi-FASTA files containing
4517 DNA sequences. It outputs its k-mer counts in a binary format, which can be
4518 translated into a human-readable text format using the @code{jellyfish dump}
4519 command, or queried for specific k-mers with @code{jellyfish query}.")
4520 (home-page "http://www.genome.umd.edu/jellyfish.html")
4521 ;; JELLYFISH seems to be 64-bit only.
4522 (supported-systems '("x86_64-linux" "aarch64-linux" "mips64el-linux"))
4523 ;; The combined work is published under the GPLv3 or later. Individual
4524 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
4525 (license (list license:gpl3+ license:expat))))
4527 (define-public khmer
4535 (url "https://github.com/dib-lab/khmer")
4536 (commit (string-append "v" version))))
4537 (file-name (git-file-name name version))
4540 "01l4jczglkl7yfhgvzx8j0df7k54bk1r8sli9ll16i1mis0d8f37"))
4541 (modules '((guix build utils)))
4544 ;; Delete bundled libraries. We do not replace the bundled seqan
4545 ;; as it is a modified subset of the old version 1.4.1.
4547 ;; We do not replace the bundled MurmurHash as the canonical
4548 ;; repository for this code 'SMHasher' is unsuitable for providing
4550 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
4551 (delete-file-recursively "third-party/zlib")
4552 (delete-file-recursively "third-party/bzip2")
4553 (delete-file-recursively "third-party/seqan")
4554 (substitute* "setup.cfg"
4555 (("# libraries = z,bz2")
4556 "libraries = z,bz2")
4557 (("include:third-party/zlib:third-party/bzip2")
4560 (build-system python-build-system)
4563 (modify-phases %standard-phases
4564 (add-after 'unpack 'set-cc
4565 (lambda _ (setenv "CC" "gcc") #t))
4567 (add-before 'reset-gzip-timestamps 'make-files-writable
4568 (lambda* (#:key outputs #:allow-other-keys)
4569 ;; Make sure .gz files are writable so that the
4570 ;; 'reset-gzip-timestamps' phase can do its work.
4571 (let ((out (assoc-ref outputs "out")))
4572 (for-each make-file-writable
4573 (find-files out "\\.gz$"))
4576 `(("python-cython" ,python-cython)
4577 ("python-pytest" ,python-pytest)
4578 ("python-pytest-runner" ,python-pytest-runner)))
4583 ("python-screed" ,python-screed)
4584 ("python-bz2file" ,python-bz2file)))
4585 (home-page "https://khmer.readthedocs.org/")
4586 (synopsis "K-mer counting, filtering and graph traversal library")
4587 (description "The khmer software is a set of command-line tools for
4588 working with DNA shotgun sequencing data from genomes, transcriptomes,
4589 metagenomes and single cells. Khmer can make de novo assemblies faster, and
4590 sometimes better. Khmer can also identify and fix problems with shotgun
4592 ;; When building on i686, armhf and mips64el, we get the following error:
4593 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
4594 (supported-systems '("x86_64-linux" "aarch64-linux"))
4595 (license license:bsd-3)))
4597 (define-public kaiju
4604 (url "https://github.com/bioinformatics-centre/kaiju")
4605 (commit (string-append "v" version))))
4606 (file-name (git-file-name name version))
4609 "119pzi0ddzv9mjg4wwa6han0cwr3k3ssn7kirvsjfcq05mi5ka0x"))))
4610 (build-system gnu-build-system)
4612 `(#:tests? #f ; There are no tests.
4614 (modify-phases %standard-phases
4616 (add-before 'build 'move-to-src-dir
4617 (lambda _ (chdir "src") #t))
4619 (lambda* (#:key inputs outputs #:allow-other-keys)
4620 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
4623 (copy-recursively "bin" bin))
4628 (home-page "http://kaiju.binf.ku.dk/")
4629 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
4630 (description "Kaiju is a program for sensitive taxonomic classification
4631 of high-throughput sequencing reads from metagenomic whole genome sequencing
4633 (license license:gpl3+)))
4640 ;; The PyPi tarball does not contain tests.
4643 (url "https://github.com/macs3-project/MACS")
4644 (commit (string-append "v" version))))
4645 (file-name (git-file-name name version))
4648 "1c5gxr0mk6hkd4vclf0k00wvyvzw2vrmk52c85338p7aqjwg6n15"))
4649 (modules '((guix build utils)))
4650 ;; Remove files generated by Cython
4653 (for-each (lambda (file)
4654 (let ((generated-file
4655 (string-append (string-drop-right file 3) "c")))
4656 (when (file-exists? generated-file)
4657 (delete-file generated-file))))
4658 (find-files "." "\\.pyx$"))
4659 (delete-file "MACS2/IO/CallPeakUnitPrecompiled.c")
4661 (build-system python-build-system)
4664 (modify-phases %standard-phases
4666 (lambda* (#:key tests? inputs outputs #:allow-other-keys)
4668 (add-installed-pythonpath inputs outputs)
4669 (invoke "pytest" "-v"))
4672 `(("python-numpy" ,python-numpy)))
4674 `(("python-cython" ,python-cython)
4675 ("python-pytest" ,python-pytest)))
4676 (home-page "https://github.com/macs3-project/MACS")
4677 (synopsis "Model based analysis for ChIP-Seq data")
4679 "MACS is an implementation of a ChIP-Seq analysis algorithm for
4680 identifying transcript factor binding sites named Model-based Analysis of
4681 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
4682 the significance of enriched ChIP regions and it improves the spatial
4683 resolution of binding sites through combining the information of both
4684 sequencing tag position and orientation.")
4685 (license license:bsd-3)))
4687 (define-public mafft
4694 "https://mafft.cbrc.jp/alignment/software/mafft-" version
4695 "-without-extensions-src.tgz"))
4696 (file-name (string-append name "-" version ".tgz"))
4699 "0r1973fx2scq4712zdqfy67wkzqj0c0bhrdy4jxhvq40mdxyry30"))))
4700 (build-system gnu-build-system)
4702 `(#:tests? #f ; no automated tests, though there are tests in the read me
4703 #:make-flags (let ((out (assoc-ref %outputs "out")))
4704 (list (string-append "PREFIX=" out)
4705 (string-append "BINDIR="
4706 (string-append out "/bin"))))
4708 (modify-phases %standard-phases
4709 (add-after 'unpack 'enter-dir
4710 (lambda _ (chdir "core") #t))
4711 (add-after 'enter-dir 'patch-makefile
4713 ;; on advice from the MAFFT authors, there is no need to
4714 ;; distribute mafft-profile, mafft-distance, or
4715 ;; mafft-homologs.rb as they are too "specialised".
4716 (substitute* "Makefile"
4717 ;; remove mafft-homologs.rb from SCRIPTS
4718 (("^SCRIPTS = mafft mafft-homologs.rb")
4720 ;; remove mafft-homologs from MANPAGES
4721 (("^MANPAGES = mafft.1 mafft-homologs.1")
4722 "MANPAGES = mafft.1")
4723 ;; remove mafft-distance from PROGS
4724 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
4725 "PROGS = dvtditr dndfast7 dndblast sextet5")
4726 ;; remove mafft-profile from PROGS
4727 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
4728 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
4729 (("^rm -f mafft-profile mafft-profile.exe") "#")
4730 (("^rm -f mafft-distance mafft-distance.exe") ")#")
4731 ;; do not install MAN pages in libexec folder
4732 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
4733 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
4735 (add-after 'enter-dir 'patch-paths
4736 (lambda* (#:key inputs #:allow-other-keys)
4737 (substitute* '("pairash.c"
4739 (("perl") (which "perl"))
4740 (("([\"`| ])awk" _ prefix)
4741 (string-append prefix (which "awk")))
4742 (("grep") (which "grep")))
4745 (add-after 'install 'wrap-programs
4746 (lambda* (#:key outputs #:allow-other-keys)
4747 (let* ((out (assoc-ref outputs "out"))
4748 (bin (string-append out "/bin"))
4749 (path (string-append
4750 (assoc-ref %build-inputs "coreutils") "/bin:")))
4751 (for-each (lambda (file)
4753 `("PATH" ":" prefix (,path))))
4761 ("coreutils" ,coreutils)))
4762 (home-page "https://mafft.cbrc.jp/alignment/software/")
4763 (synopsis "Multiple sequence alignment program")
4765 "MAFFT offers a range of multiple alignment methods for nucleotide and
4766 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
4767 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
4769 (license (license:non-copyleft
4770 "https://mafft.cbrc.jp/alignment/software/license.txt"
4771 "BSD-3 with different formatting"))))
4780 (url "https://github.com/marbl/mash")
4781 (commit (string-append "v" version))))
4782 (file-name (git-file-name name version))
4785 "049hwcc059p2fd9vwndn63laifvvsi0wmv84i6y1fr79k15dxwy6"))
4786 (modules '((guix build utils)))
4789 ;; Delete bundled kseq.
4790 ;; TODO: Also delete bundled murmurhash and open bloom filter.
4791 (delete-file "src/mash/kseq.h")
4793 (build-system gnu-build-system)
4795 `(#:tests? #f ; No tests.
4798 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
4799 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
4800 #:make-flags (list "CC=gcc")
4802 (modify-phases %standard-phases
4803 (add-after 'unpack 'fix-includes
4805 (substitute* '("src/mash/Sketch.cpp"
4806 "src/mash/CommandFind.cpp"
4807 "src/mash/CommandScreen.cpp")
4808 (("^#include \"kseq\\.h\"")
4809 "#include \"htslib/kseq.h\""))
4811 (add-after 'fix-includes 'use-c++14
4813 ;; capnproto 0.7 requires c++14 to build
4814 (substitute* "configure.ac"
4815 (("c\\+\\+11") "c++14"))
4816 (substitute* "Makefile.in"
4817 (("c\\+\\+11") "c++14"))
4820 `(("autoconf" ,autoconf)
4821 ;; Capnproto and htslib are statically embedded in the final
4822 ;; application. Therefore we also list their licenses, below.
4823 ("capnproto" ,capnproto)
4824 ("htslib" ,htslib)))
4828 (supported-systems '("x86_64-linux"))
4829 (home-page "https://mash.readthedocs.io")
4830 (synopsis "Fast genome and metagenome distance estimation using MinHash")
4831 (description "Mash is a fast sequence distance estimator that uses the
4832 MinHash algorithm and is designed to work with genomes and metagenomes in the
4833 form of assemblies or reads.")
4834 (license (list license:bsd-3 ; Mash
4835 license:expat ; HTSlib and capnproto
4836 license:public-domain ; MurmurHash 3
4837 license:cpl1.0)))) ; Open Bloom Filter
4839 (define-public metabat
4847 (url "https://bitbucket.org/berkeleylab/metabat.git")
4848 (commit (string-append "v" version))))
4849 (file-name (git-file-name name version))
4852 "0hyg2smw1nz69mfvjpk45xyyychmda92c80a0cv7baji84ri4iyn"))
4853 (patches (search-patches "metabat-fix-compilation.patch"))))
4854 (build-system scons-build-system)
4856 `(#:scons ,scons-python2
4858 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
4859 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
4860 #:tests? #f ;; Tests are run during the build phase.
4862 (modify-phases %standard-phases
4863 (add-after 'unpack 'fix-includes
4865 (substitute* "src/BamUtils.h"
4866 (("^#include \"bam/bam\\.h\"")
4867 "#include \"samtools/bam.h\"")
4868 (("^#include \"bam/sam\\.h\"")
4869 "#include \"samtools/sam.h\""))
4870 (substitute* "src/KseqReader.h"
4871 (("^#include \"bam/kseq\\.h\"")
4872 "#include \"htslib/kseq.h\""))
4874 (add-after 'unpack 'fix-scons
4875 (lambda* (#:key inputs #:allow-other-keys)
4876 (substitute* "SConstruct"
4877 (("^htslib_dir += 'samtools'")
4878 (string-append "htslib_dir = '"
4879 (assoc-ref inputs "htslib")
4881 (("^samtools_dir = 'samtools'")
4882 (string-append "samtools_dir = '"
4883 (assoc-ref inputs "samtools")
4885 (("^findStaticOrShared\\('bam', hts_lib")
4886 (string-append "findStaticOrShared('bam', '"
4887 (assoc-ref inputs "samtools")
4889 ;; Do not distribute README.
4890 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
4895 ("samtools" ,samtools)
4898 (home-page "https://bitbucket.org/berkeleylab/metabat")
4900 "Reconstruction of single genomes from complex microbial communities")
4902 "Grouping large genomic fragments assembled from shotgun metagenomic
4903 sequences to deconvolute complex microbial communities, or metagenome binning,
4904 enables the study of individual organisms and their interactions. MetaBAT is
4905 an automated metagenome binning software, which integrates empirical
4906 probabilistic distances of genome abundance and tetranucleotide frequency.")
4907 ;; The source code contains inline assembly.
4908 (supported-systems '("x86_64-linux" "i686-linux"))
4909 (license (license:non-copyleft "file://license.txt"
4910 "See license.txt in the distribution."))))
4912 (define-public minced
4919 (url "https://github.com/ctSkennerton/minced")
4921 (file-name (git-file-name name version))
4924 "1f5h9him0gd355cnx7p6pnxpknhckd4g0v62mg8zyhfbx9as25fv"))))
4925 (build-system gnu-build-system)
4927 `(#:test-target "test"
4929 (modify-phases %standard-phases
4931 (add-before 'check 'fix-test
4933 ;; Fix test for latest version.
4934 (substitute* "t/Aquifex_aeolicus_VF5.expected"
4935 (("minced:0.1.6") "minced:0.2.0"))
4937 (replace 'install ; No install target.
4938 (lambda* (#:key inputs outputs #:allow-other-keys)
4939 (let* ((out (assoc-ref outputs "out"))
4940 (bin (string-append out "/bin"))
4941 (wrapper (string-append bin "/minced")))
4942 ;; Minced comes with a wrapper script that tries to figure out where
4943 ;; it is located before running the JAR. Since these paths are known
4944 ;; to us, we build our own wrapper to avoid coreutils dependency.
4945 (install-file "minced.jar" bin)
4946 (with-output-to-file wrapper
4950 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
4951 (assoc-ref inputs "jre") "/bin/java -jar "
4952 bin "/minced.jar \"$@\"\n"))))
4953 (chmod wrapper #o555))
4956 `(("jdk" ,icedtea "jdk")))
4959 ("jre" ,icedtea "out")))
4960 (home-page "https://github.com/ctSkennerton/minced")
4961 (synopsis "Mining CRISPRs in Environmental Datasets")
4963 "MinCED is a program to find Clustered Regularly Interspaced Short
4964 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
4965 unassembled metagenomic reads, but is mainly designed for full genomes and
4966 assembled metagenomic sequence.")
4967 (license license:gpl3+)))
4975 (uri (pypi-uri "misopy" version))
4978 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
4979 (modules '((guix build utils)))
4981 (substitute* "setup.py"
4982 ;; Use setuptools, or else the executables are not
4984 (("distutils.core") "setuptools")
4985 ;; Use "gcc" instead of "cc" for compilation.
4987 "cc.set_executables(
4991 linker_so='gcc -shared'); defines"))
4993 (build-system python-build-system)
4995 `(#:python ,python-2 ; only Python 2 is supported
4996 #:tests? #f)) ; no "test" target
4998 `(("samtools" ,samtools)
4999 ("python-numpy" ,python2-numpy)
5000 ("python-pysam" ,python2-pysam)
5001 ("python-scipy" ,python2-scipy)
5002 ("python-matplotlib" ,python2-matplotlib)))
5004 `(("python-mock" ,python2-mock) ; for tests
5005 ("python-pytz" ,python2-pytz))) ; for tests
5006 (home-page "https://www.genes.mit.edu/burgelab/miso/index.html")
5007 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
5009 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
5010 the expression level of alternatively spliced genes from RNA-Seq data, and
5011 identifies differentially regulated isoforms or exons across samples. By
5012 modeling the generative process by which reads are produced from isoforms in
5013 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
5014 that a read originated from a particular isoform.")
5015 (license license:gpl2)))
5017 (define-public muscle
5020 (version "3.8.1551")
5022 (method url-fetch/tarbomb)
5024 "http://www.drive5.com/muscle/muscle_src_"
5028 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
5029 (build-system gnu-build-system)
5031 `(#:make-flags (list "LDLIBS = -lm")
5033 (modify-phases %standard-phases
5036 ;; There are no tests, so just test if it runs.
5037 (lambda _ (invoke "./muscle" "-version") #t))
5039 (lambda* (#:key outputs #:allow-other-keys)
5040 (let* ((out (assoc-ref outputs "out"))
5041 (bin (string-append out "/bin")))
5042 (install-file "muscle" bin)
5044 (home-page "http://www.drive5.com/muscle")
5045 (synopsis "Multiple sequence alignment program")
5047 "MUSCLE aims to be a fast and accurate multiple sequence alignment
5048 program for nucleotide and protein sequences.")
5049 ;; License information found in 'muscle -h' and usage.cpp.
5050 (license license:public-domain)))
5052 (define-public newick-utils
5053 ;; There are no recent releases so we package from git.
5054 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
5056 (name "newick-utils")
5057 (version (string-append "1.6-1." (string-take commit 8)))
5061 (url "https://github.com/tjunier/newick_utils")
5063 (file-name (string-append name "-" version "-checkout"))
5066 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
5067 (build-system gnu-build-system)
5069 ;; XXX: TODO: Enable Lua and Guile bindings.
5070 ;; https://github.com/tjunier/newick_utils/issues/13
5071 `(("libxml2" ,libxml2)
5075 `(("autoconf" ,autoconf)
5076 ("automake" ,automake)
5077 ("libtool" ,libtool)))
5078 (synopsis "Programs for working with newick format phylogenetic trees")
5080 "Newick-utils is a suite of utilities for processing phylogenetic trees
5081 in Newick format. Functions include re-rooting, extracting subtrees,
5082 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
5083 (home-page "https://github.com/tjunier/newick_utils")
5084 (license license:bsd-3))))
5093 "https://github.com/wwood/OrfM/releases/download/v"
5094 version "/orfm-" version ".tar.gz"))
5097 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
5098 (build-system gnu-build-system)
5099 (inputs `(("zlib" ,zlib)))
5101 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
5102 ("ruby-rspec" ,ruby-rspec)
5104 (synopsis "Simple and not slow open reading frame (ORF) caller")
5106 "An ORF caller finds stretches of DNA that, when translated, are not
5107 interrupted by stop codons. OrfM finds and prints these ORFs.")
5108 (home-page "https://github.com/wwood/OrfM")
5109 (license license:lgpl3+)))
5111 (define-public python2-pbcore
5113 (name "python2-pbcore")
5117 (uri (pypi-uri "pbcore" version))
5120 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
5121 (build-system python-build-system)
5123 `(#:python ,python-2 ;pbcore < 2.0 requires Python 2.7
5124 #:phases (modify-phases %standard-phases
5125 (add-after 'unpack 'remove-sphinx-dependency
5127 ;; Sphinx is only required for documentation tests, which
5128 ;; we do not run; furthermore it depends on python2-sphinx
5129 ;; which is no longer maintained.
5130 (substitute* "requirements-dev.txt"
5134 `(("python-cython" ,python2-cython)
5135 ("python-numpy" ,python2-numpy)
5136 ("python-pysam" ,python2-pysam)
5137 ("python-h5py" ,python2-h5py)))
5139 `(("python-nose" ,python2-nose)
5140 ("python-pyxb" ,python2-pyxb)))
5141 (home-page "https://pacificbiosciences.github.io/pbcore/")
5142 (synopsis "Library for reading and writing PacBio data files")
5144 "The pbcore package provides Python APIs for interacting with PacBio data
5145 files and writing bioinformatics applications.")
5146 (license license:bsd-3)))
5148 (define-public python2-warpedlmm
5150 (name "python2-warpedlmm")
5155 (uri (pypi-uri "WarpedLMM" version ".zip"))
5158 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
5159 (build-system python-build-system)
5161 `(#:python ,python-2 ; requires Python 2.7
5162 #:tests? #f ; test data are not included
5164 (modify-phases %standard-phases
5165 (add-after 'unpack 'use-weave
5167 (substitute* "warpedlmm/util/linalg.py"
5168 (("from scipy import linalg, weave")
5169 "from scipy import linalg\nimport weave"))
5172 `(("python-scipy" ,python2-scipy)
5173 ("python-numpy" ,python2-numpy)
5174 ("python-matplotlib" ,python2-matplotlib)
5175 ("python-fastlmm" ,python2-fastlmm)
5176 ("python-pandas" ,python2-pandas)
5177 ("python-pysnptools" ,python2-pysnptools)
5178 ("python-weave" ,python2-weave)))
5180 `(("python-mock" ,python2-mock)
5181 ("python-nose" ,python2-nose)
5183 (home-page "https://github.com/PMBio/warpedLMM")
5184 (synopsis "Implementation of warped linear mixed models")
5186 "WarpedLMM is a Python implementation of the warped linear mixed model,
5187 which automatically learns an optimal warping function (or transformation) for
5188 the phenotype as it models the data.")
5189 (license license:asl2.0)))
5191 (define-public pbtranscript-tofu
5192 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
5194 (name "pbtranscript-tofu")
5195 (version (string-append "2.2.3." (string-take commit 7)))
5199 (url "https://github.com/PacificBiosciences/cDNA_primer")
5201 (file-name (string-append name "-" version "-checkout"))
5204 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
5205 (modules '((guix build utils)))
5208 ;; remove bundled Cython sources
5209 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
5211 (build-system python-build-system)
5213 `(#:python ,python-2
5214 ;; FIXME: Tests fail with "No such file or directory:
5215 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
5218 (modify-phases %standard-phases
5219 (add-after 'unpack 'enter-directory
5221 (chdir "pbtranscript-tofu/pbtranscript/")
5223 ;; With setuptools version 18.0 and later this setup.py hack causes
5224 ;; a build error, so we disable it.
5225 (add-after 'enter-directory 'patch-setuppy
5227 (substitute* "setup.py"
5228 (("if 'setuptools.extension' in sys.modules:")
5232 `(("python-numpy" ,python2-numpy)
5233 ("python-bx-python" ,python2-bx-python)
5234 ("python-networkx" ,python2-networkx)
5235 ("python-scipy" ,python2-scipy)
5236 ("python-pbcore" ,python2-pbcore)
5237 ("python-h5py" ,python2-h5py)))
5239 `(("python-cython" ,python2-cython)
5240 ("python-nose" ,python2-nose)))
5241 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
5242 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
5244 "pbtranscript-tofu contains scripts to analyze transcriptome data
5245 generated using the PacBio Iso-Seq protocol.")
5246 (license license:bsd-3))))
5248 (define-public prank
5255 "http://wasabiapp.org/download/prank/prank.source."
5259 "0nc8g9c5rkdxcir46s0in9ci1sxwzbjibxrvkksf22ybnplvagk2"))))
5260 (build-system gnu-build-system)
5263 (modify-phases %standard-phases
5264 (add-after 'unpack 'enter-src-dir
5268 (add-after 'unpack 'remove-m64-flag
5269 ;; Prank will build with the correct 'bit-ness' without this flag
5270 ;; and this allows building on 32-bit machines.
5271 (lambda _ (substitute* "src/Makefile"
5276 (lambda* (#:key outputs #:allow-other-keys)
5277 (let* ((out (assoc-ref outputs "out"))
5278 (bin (string-append out "/bin"))
5279 (man (string-append out "/share/man/man1"))
5280 (path (string-append
5281 (assoc-ref %build-inputs "mafft") "/bin:"
5282 (assoc-ref %build-inputs "exonerate") "/bin:"
5283 (assoc-ref %build-inputs "bppsuite") "/bin")))
5284 (install-file "prank" bin)
5285 (wrap-program (string-append bin "/prank")
5286 `("PATH" ":" prefix (,path)))
5287 (install-file "prank.1" man))
5291 ("exonerate" ,exonerate)
5292 ("bppsuite" ,bppsuite)))
5293 (home-page "http://wasabiapp.org/software/prank/")
5294 (synopsis "Probabilistic multiple sequence alignment program")
5296 "PRANK is a probabilistic multiple sequence alignment program for DNA,
5297 codon and amino-acid sequences. It is based on a novel algorithm that treats
5298 insertions correctly and avoids over-estimation of the number of deletion
5299 events. In addition, PRANK borrows ideas from maximum likelihood methods used
5300 in phylogenetics and correctly takes into account the evolutionary distances
5301 between sequences. Lastly, PRANK allows for defining a potential structure
5302 for sequences to be aligned and then, simultaneously with the alignment,
5303 predicts the locations of structural units in the sequences.")
5304 (license license:gpl2+)))
5306 (define-public proteinortho
5308 (name "proteinortho")
5313 (url "https://gitlab.com/paulklemm_PHD/proteinortho.git")
5314 (commit (string-append "v" version))))
5315 (file-name (git-file-name name version))
5318 "0pmy617zy2z2w6hjqxjhf3rzikf5n3mpia80ysq8233vfr7wrzff"))
5319 (modules '((guix build utils)))
5322 ;; remove pre-built scripts
5323 (delete-file-recursively "src/BUILD/")
5325 (build-system gnu-build-system)
5327 `(#:test-target "test"
5328 #:make-flags '("CC=gcc")
5330 (modify-phases %standard-phases
5332 ;; There is no configure script, so we modify the Makefile directly.
5333 (lambda* (#:key outputs #:allow-other-keys)
5334 (substitute* "Makefile"
5337 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
5339 (add-before 'install 'make-install-directory
5340 ;; The install directory is not created during 'make install'.
5341 (lambda* (#:key outputs #:allow-other-keys)
5342 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
5344 (add-after 'install 'wrap-programs
5345 (lambda* (#:key inputs outputs #:allow-other-keys)
5346 (let ((path (getenv "PATH"))
5347 (out (assoc-ref outputs "out")))
5348 (for-each (lambda (script)
5349 (wrap-script script `("PATH" ":" prefix (,path))))
5350 (cons (string-append out "/bin/proteinortho")
5351 (find-files out "\\.(pl|py)$"))))
5354 `(("guile" ,guile-3.0) ; for wrap-script
5355 ("diamond" ,diamond)
5357 ("python" ,python-wrapper)
5360 ("openblas" ,openblas)))
5362 `(("which" ,which)))
5363 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
5364 (synopsis "Detect orthologous genes across species")
5366 "Proteinortho is a tool to detect orthologous genes across different
5367 species. For doing so, it compares similarities of given gene sequences and
5368 clusters them to find significant groups. The algorithm was designed to handle
5369 large-scale data and can be applied to hundreds of species at once.")
5370 (license license:gpl3+)))
5372 (define-public pyicoteo
5380 (url "https://bitbucket.org/regulatorygenomicsupf/pyicoteo.git")
5381 (commit (string-append "v" version))))
5382 (file-name (git-file-name name version))
5385 "0hz5g8d25lbjy1wpscr490l0lmyvaix893hhax4fxnh1h9w34w8p"))))
5386 (build-system python-build-system)
5388 `(#:python ,python-2 ; does not work with Python 3
5389 #:tests? #f)) ; there are no tests
5391 `(("python2-matplotlib" ,python2-matplotlib)))
5392 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
5393 (synopsis "Analyze high-throughput genetic sequencing data")
5395 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
5396 sequencing data. It works with genomic coordinates. There are currently six
5397 different command-line tools:
5400 @item pyicoregion: for generating exploratory regions automatically;
5401 @item pyicoenrich: for differential enrichment between two conditions;
5402 @item pyicoclip: for calling CLIP-Seq peaks without a control;
5403 @item pyicos: for genomic coordinates manipulation;
5404 @item pyicoller: for peak calling on punctuated ChIP-Seq;
5405 @item pyicount: to count how many reads from N experiment files overlap in a
5407 @item pyicotrocol: to combine operations from pyicoteo.
5409 (license license:gpl3+)))
5411 (define-public prodigal
5414 ;; Check for a new home page when updating this package:
5415 ;; https://github.com/hyattpd/Prodigal/issues/36#issuecomment-536617588
5420 (url "https://github.com/hyattpd/Prodigal")
5421 (commit (string-append "v" version))))
5422 (file-name (git-file-name name version))
5425 "1fs1hqk83qjbjhrvhw6ni75zakx5ki1ayy3v6wwkn3xvahc9hi5s"))))
5426 (build-system gnu-build-system)
5428 `(#:tests? #f ; no check target
5429 #:make-flags (list (string-append "INSTALLDIR="
5430 (assoc-ref %outputs "out")
5433 (modify-phases %standard-phases
5434 (delete 'configure))))
5435 (home-page "https://github.com/hyattpd/Prodigal")
5436 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
5438 "Prodigal runs smoothly on finished genomes, draft genomes, and
5439 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
5440 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
5441 partial genes, and identifies translation initiation sites.")
5442 (license license:gpl3+)))
5444 (define-public roary
5452 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
5456 "0qxrds9wx7cfhlkihrp6697kx0flhhxymap9fwan0b3rbdhcnmff"))))
5457 (build-system perl-build-system)
5460 (modify-phases %standard-phases
5465 ;; The tests are not run by default, so we run each test file
5467 (setenv "PATH" (string-append (getcwd) "/bin" ":"
5469 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
5470 (getenv "PERL5LIB")))
5471 (for-each (lambda (file)
5472 (display file)(display "\n")
5473 (invoke "perl" file))
5474 (find-files "t" ".*\\.t$"))
5477 ;; There is no 'install' target in the Makefile.
5478 (lambda* (#:key outputs #:allow-other-keys)
5479 (let* ((out (assoc-ref outputs "out"))
5480 (bin (string-append out "/bin"))
5481 (perl (string-append out "/lib/perl5/site_perl"))
5482 (roary-plots "contrib/roary_plots"))
5485 (copy-recursively "bin" bin)
5486 (copy-recursively "lib" perl)
5488 (add-after 'install 'wrap-programs
5489 (lambda* (#:key inputs outputs #:allow-other-keys)
5490 (let* ((out (assoc-ref outputs "out"))
5491 (perl5lib (getenv "PERL5LIB"))
5492 (path (getenv "PATH")))
5493 (for-each (lambda (prog)
5494 (let ((binary (string-append out "/" prog)))
5495 (wrap-program binary
5496 `("PERL5LIB" ":" prefix
5497 (,(string-append perl5lib ":" out
5498 "/lib/perl5/site_perl"))))
5499 (wrap-program binary
5501 (,(string-append path ":" out "/bin"))))))
5502 (find-files "bin" ".*[^R]$"))
5504 (string-append out "/bin/roary-create_pan_genome_plots.R"))
5505 (r-site-lib (getenv "R_LIBS_SITE"))
5507 (string-append (assoc-ref inputs "coreutils") "/bin")))
5509 `("R_LIBS_SITE" ":" prefix
5510 (,(string-append r-site-lib ":" out "/site-library/"))))
5513 (,(string-append coreutils-path ":" out "/bin"))))))
5516 `(("perl-env-path" ,perl-env-path)
5517 ("perl-test-files" ,perl-test-files)
5518 ("perl-test-most" ,perl-test-most)
5519 ("perl-test-output" ,perl-test-output)))
5521 `(("perl-array-utils" ,perl-array-utils)
5522 ("bioperl" ,bioperl-minimal)
5523 ("perl-digest-md5-file" ,perl-digest-md5-file)
5524 ("perl-exception-class" ,perl-exception-class)
5525 ("perl-file-find-rule" ,perl-file-find-rule)
5526 ("perl-file-grep" ,perl-file-grep)
5527 ("perl-file-slurper" ,perl-file-slurper)
5528 ("perl-file-which" ,perl-file-which)
5529 ("perl-graph" ,perl-graph)
5530 ("perl-graph-readwrite" ,perl-graph-readwrite)
5531 ("perl-log-log4perl" ,perl-log-log4perl)
5532 ("perl-moose" ,perl-moose)
5533 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
5534 ("perl-text-csv" ,perl-text-csv)
5535 ("bedtools" ,bedtools)
5539 ("parallel" ,parallel)
5542 ("fasttree" ,fasttree)
5546 ("r-minimal" ,r-minimal)
5547 ("r-ggplot2" ,r-ggplot2)
5548 ("coreutils" ,coreutils)))
5549 (home-page "https://sanger-pathogens.github.io/Roary/")
5550 (synopsis "High speed stand-alone pan genome pipeline")
5552 "Roary is a high speed stand alone pan genome pipeline, which takes
5553 annotated assemblies in GFF3 format (produced by the Prokka program) and
5554 calculates the pan genome. Using a standard desktop PC, it can analyse
5555 datasets with thousands of samples, without compromising the quality of the
5556 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
5557 single processor. Roary is not intended for metagenomics or for comparing
5558 extremely diverse sets of genomes.")
5559 (license license:gpl3)))
5561 (define-public raxml
5569 (url "https://github.com/stamatak/standard-RAxML")
5570 (commit (string-append "v" version))))
5571 (file-name (git-file-name name version))
5574 "1jqjzhch0rips0vp04prvb8vmc20c5pdmsqn8knadcf91yy859fh"))))
5575 (build-system gnu-build-system)
5577 `(#:tests? #f ; There are no tests.
5578 ;; Use 'standard' Makefile rather than SSE or AVX ones.
5579 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
5581 (modify-phases %standard-phases
5584 (lambda* (#:key outputs #:allow-other-keys)
5585 (let* ((out (assoc-ref outputs "out"))
5586 (bin (string-append out "/bin"))
5587 (executable "raxmlHPC-HYBRID"))
5588 (install-file executable bin)
5589 (symlink (string-append bin "/" executable) "raxml"))
5592 `(("openmpi" ,openmpi)))
5593 (home-page "https://cme.h-its.org/exelixis/web/software/raxml/index.html")
5594 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
5596 "RAxML is a tool for phylogenetic analysis and post-analysis of large
5598 ;; The source includes x86 specific code
5599 (supported-systems '("x86_64-linux" "i686-linux"))
5600 (license license:gpl2+)))
5610 (url "https://github.com/deweylab/RSEM")
5611 (commit (string-append "v" version))))
5613 (base32 "1jlq11d1p8qp64w75yj8cnbbd1a93viq10pzsbwal7vdn8fg13j1"))
5614 (file-name (git-file-name name version))
5615 (modules '((guix build utils)))
5618 ;; remove bundled copy of boost and samtools
5619 (delete-file-recursively "boost")
5620 (delete-file-recursively "samtools-1.3")
5622 (build-system gnu-build-system)
5624 `(#:tests? #f ;no "check" target
5626 (list (string-append "BOOST="
5627 (assoc-ref %build-inputs "boost")
5629 (string-append "SAMHEADERS="
5630 (assoc-ref %build-inputs "htslib")
5631 "/include/htslib/sam.h")
5632 (string-append "SAMLIBS="
5633 (assoc-ref %build-inputs "htslib")
5636 (modify-phases %standard-phases
5637 ;; No "configure" script.
5638 ;; Do not build bundled samtools library.
5641 (substitute* "Makefile"
5642 (("^all : \\$\\(PROGRAMS\\).*") "all: $(PROGRAMS)\n")
5643 (("^\\$\\(SAMLIBS\\).*") ""))
5646 (lambda* (#:key outputs #:allow-other-keys)
5647 (let* ((out (string-append (assoc-ref outputs "out")))
5648 (bin (string-append out "/bin/"))
5649 (perl (string-append out "/lib/perl5/site_perl")))
5652 (for-each (lambda (file)
5653 (install-file file bin))
5654 (find-files "." "rsem-.*"))
5655 (install-file "rsem_perl_utils.pm" perl))
5657 (add-after 'install 'wrap-program
5658 (lambda* (#:key outputs #:allow-other-keys)
5659 (let ((out (assoc-ref outputs "out")))
5660 (for-each (lambda (prog)
5661 (wrap-program (string-append out "/bin/" prog)
5662 `("PERL5LIB" ":" prefix
5663 (,(string-append out "/lib/perl5/site_perl")))))
5664 '("rsem-calculate-expression"
5666 "rsem-generate-data-matrix"
5667 "rsem-generate-ngvector"
5668 "rsem-plot-transcript-wiggles"
5669 "rsem-prepare-reference"
5671 "rsem-run-prsem-testing-procedure")))
5675 ("r-minimal" ,r-minimal)
5677 ("htslib" ,htslib-1.3)
5679 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
5680 (synopsis "Estimate gene expression levels from RNA-Seq data")
5682 "RSEM is a software package for estimating gene and isoform expression
5683 levels from RNA-Seq data. The RSEM package provides a user-friendly
5684 interface, supports threads for parallel computation of the EM algorithm,
5685 single-end and paired-end read data, quality scores, variable-length reads and
5686 RSPD estimation. In addition, it provides posterior mean and 95% credibility
5687 interval estimates for expression levels. For visualization, it can generate
5688 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
5689 (license license:gpl3+)))
5691 (define-public rseqc
5699 (string-append "mirror://sourceforge/rseqc/"
5700 "RSeQC-" version ".tar.gz"))
5703 "0gbb9iyb7swiv5455fm5rg98r7l6qn27v564yllqjd574hncpx6m"))))
5704 (build-system python-build-system)
5706 `(("python-cython" ,python-cython)
5707 ("python-bx-python" ,python-bx-python)
5708 ("python-pybigwig" ,python-pybigwig)
5709 ("python-pysam" ,python-pysam)
5710 ("python-numpy" ,python-numpy)
5713 `(("python-nose" ,python-nose)))
5714 (home-page "http://rseqc.sourceforge.net/")
5715 (synopsis "RNA-seq quality control package")
5717 "RSeQC provides a number of modules that can comprehensively evaluate
5718 high throughput sequence data, especially RNA-seq data. Some basic modules
5719 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
5720 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
5721 distribution, coverage uniformity, strand specificity, etc.")
5722 (license license:gpl3+)))
5725 ;; There are no release tarballs. According to the installation
5726 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
5727 ;; stable release is identified by this changeset ID.
5728 (let ((changeset "2329130")
5732 (version (string-append "0-" revision "." changeset))
5736 (url "https://bitbucket.org/libsleipnir/sleipnir")
5737 (changeset changeset)))
5738 (file-name (string-append name "-" version "-checkout"))
5741 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
5742 (build-system gnu-build-system)
5744 `(#:modules ((srfi srfi-1)
5745 (guix build gnu-build-system)
5748 (let ((dirs '("SeekMiner"
5754 (modify-phases %standard-phases
5757 (substitute* "gen_tools_am"
5758 (("/usr/bin/env.*") (which "perl")))
5759 (invoke "bash" "gen_auto")
5761 (add-after 'build 'build-additional-tools
5762 (lambda* (#:key make-flags #:allow-other-keys)
5763 (for-each (lambda (dir)
5764 (with-directory-excursion (string-append "tools/" dir)
5765 (apply invoke "make" make-flags)))
5768 (add-after 'install 'install-additional-tools
5769 (lambda* (#:key make-flags #:allow-other-keys)
5770 (for-each (lambda (dir)
5771 (with-directory-excursion (string-append "tools/" dir)
5772 (apply invoke `("make" ,@make-flags "install"))))
5779 ("readline" ,readline)
5780 ("gengetopt" ,gengetopt)
5781 ("log4cpp" ,log4cpp)))
5783 `(("autoconf" ,autoconf)
5784 ("automake" ,automake)
5786 (home-page "http://seek.princeton.edu")
5787 (synopsis "Gene co-expression search engine")
5789 "SEEK is a computational gene co-expression search engine. SEEK provides
5790 biologists with a way to navigate the massive human expression compendium that
5791 now contains thousands of expression datasets. SEEK returns a robust ranking
5792 of co-expressed genes in the biological area of interest defined by the user's
5793 query genes. It also prioritizes thousands of expression datasets according
5794 to the user's query of interest.")
5795 (license license:cc-by3.0))))
5797 (define-public samtools
5805 (string-append "mirror://sourceforge/samtools/samtools/"
5806 version "/samtools-" version ".tar.bz2"))
5809 "1dp5wknak4arnw5ghhif9mmljlfnw5bgm91wib7z0j8wdjywx0z2"))
5810 (modules '((guix build utils)))
5812 ;; Delete bundled htslib.
5813 (delete-file-recursively "htslib-1.11")
5815 (build-system gnu-build-system)
5817 `(#:modules ((ice-9 ftw)
5819 (guix build gnu-build-system)
5821 #:configure-flags (list "--with-ncurses")
5823 (modify-phases %standard-phases
5824 (add-after 'unpack 'patch-tests
5826 (substitute* "test/test.pl"
5827 ;; The test script calls out to /bin/bash
5828 (("/bin/bash") (which "bash")))
5830 (add-after 'install 'install-library
5831 (lambda* (#:key outputs #:allow-other-keys)
5832 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
5833 (install-file "libbam.a" lib)
5835 (add-after 'install 'install-headers
5836 (lambda* (#:key outputs #:allow-other-keys)
5837 (let ((include (string-append (assoc-ref outputs "out")
5838 "/include/samtools/")))
5839 (for-each (lambda (file)
5840 (install-file file include))
5841 (scandir "." (lambda (name) (string-match "\\.h$" name))))
5843 (native-inputs `(("pkg-config" ,pkg-config)))
5845 `(("htslib" ,htslib)
5846 ("ncurses" ,ncurses)
5850 (home-page "http://samtools.sourceforge.net")
5851 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
5853 "Samtools implements various utilities for post-processing nucleotide
5854 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
5855 variant calling (in conjunction with bcftools), and a simple alignment
5857 (license license:expat)))
5859 (define-public samtools-1.9
5860 (package (inherit samtools)
5867 (string-append "mirror://sourceforge/samtools/samtools/"
5868 version "/samtools-" version ".tar.bz2"))
5871 "10ilqbmm7ri8z431sn90lvbjwizd0hhkf9rcqw8j823hf26nhgq8"))
5872 (modules '((guix build utils)))
5874 ;; Delete bundled htslib.
5875 (delete-file-recursively "htslib-1.9")
5878 `(("htslib" ,htslib-1.9)
5879 ("ncurses" ,ncurses)
5884 (define-public samtools-0.1
5885 ;; This is the most recent version of the 0.1 line of samtools. The input
5886 ;; and output formats differ greatly from that used and produced by samtools
5887 ;; 1.x and is still used in many bioinformatics pipelines.
5888 (package (inherit samtools)
5894 (string-append "mirror://sourceforge/samtools/samtools/"
5895 version "/samtools-" version ".tar.bz2"))
5897 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
5899 `(#:tests? #f ;no "check" target
5901 (list "LIBCURSES=-lncurses")
5902 ,@(substitute-keyword-arguments (package-arguments samtools)
5904 `(modify-phases ,phases
5906 (lambda* (#:key outputs #:allow-other-keys)
5907 (let ((bin (string-append
5908 (assoc-ref outputs "out") "/bin")))
5910 (install-file "samtools" bin)
5912 (delete 'patch-tests)
5913 (delete 'configure))))))))
5915 (define-public mosaik
5916 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
5921 ;; There are no release tarballs nor tags.
5924 (url "https://github.com/wanpinglee/MOSAIK")
5926 (file-name (string-append name "-" version))
5929 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
5930 (build-system gnu-build-system)
5932 `(#:tests? #f ; no tests
5933 #:make-flags (list "CC=gcc")
5935 (modify-phases %standard-phases
5937 (lambda _ (chdir "src") #t))
5939 (lambda* (#:key outputs #:allow-other-keys)
5940 (let ((bin (string-append (assoc-ref outputs "out")
5943 (copy-recursively "../bin" bin)
5947 ("zlib:static" ,zlib "static")
5949 (supported-systems '("x86_64-linux"))
5950 (home-page "https://github.com/wanpinglee/MOSAIK")
5951 (synopsis "Map nucleotide sequence reads to reference genomes")
5953 "MOSAIK is a program for mapping second and third-generation sequencing
5954 reads to a reference genome. MOSAIK can align reads generated by all the
5955 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
5956 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
5957 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
5958 ;; code released into the public domain:
5959 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
5960 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
5961 (license (list license:gpl2+ license:public-domain)))))
5963 (define-public ngs-sdk
5970 (url "https://github.com/ncbi/ngs")
5972 (file-name (git-file-name name version))
5975 "1ix51c25hjn57w93qmwzw80xh2i34wx8j2hn7szh8p6w8i3az5qa"))))
5976 (build-system gnu-build-system)
5978 `(#:parallel-build? #f ; not supported
5979 #:tests? #f ; no "check" target
5981 (modify-phases %standard-phases
5983 (lambda* (#:key outputs #:allow-other-keys)
5984 (let ((out (assoc-ref outputs "out")))
5985 ;; Allow 'konfigure.perl' to find 'package.prl'.
5987 (string-append ".:" (getenv "PERL5LIB")))
5989 ;; The 'configure' script doesn't recognize things like
5990 ;; '--enable-fast-install'.
5991 (invoke "./configure"
5992 (string-append "--build-prefix=" (getcwd) "/build")
5993 (string-append "--prefix=" out))
5995 (add-after 'unpack 'enter-dir
5996 (lambda _ (chdir "ngs-sdk") #t)))))
5997 (native-inputs `(("perl" ,perl)))
5998 ;; According to the test
5999 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
6000 ;; in ngs-sdk/setup/konfigure.perl
6001 (supported-systems '("i686-linux" "x86_64-linux"))
6002 (home-page "https://github.com/ncbi/ngs")
6003 (synopsis "API for accessing Next Generation Sequencing data")
6005 "NGS is a domain-specific API for accessing reads, alignments and pileups
6006 produced from Next Generation Sequencing. The API itself is independent from
6007 any particular back-end implementation, and supports use of multiple back-ends
6009 (license license:public-domain)))
6011 (define-public java-ngs
6012 (package (inherit ngs-sdk)
6015 `(,@(substitute-keyword-arguments
6016 `(#:modules ((guix build gnu-build-system)
6020 ,@(package-arguments ngs-sdk))
6022 `(modify-phases ,phases
6023 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
6025 `(("jdk" ,icedtea "jdk")
6026 ("ngs-sdk" ,ngs-sdk)))
6027 (synopsis "Java bindings for NGS SDK")))
6029 (define-public ncbi-vdb
6036 (url "https://github.com/ncbi/ncbi-vdb")
6038 (file-name (git-file-name name version))
6041 "0m8hlxscidsfqm9x9fyi62q6lpf1dv5115kgjjgnrkl49q9c27m6"))))
6042 (build-system gnu-build-system)
6044 `(#:parallel-build? #f ; not supported
6045 #:tests? #f ; no "check" target
6046 #:make-flags '("HAVE_HDF5=1")
6048 (modify-phases %standard-phases
6049 (add-after 'unpack 'make-files-writable
6050 (lambda _ (for-each make-file-writable (find-files "." ".*")) #t))
6051 (add-before 'configure 'set-perl-search-path
6053 ;; Work around "dotless @INC" build failure.
6055 (string-append (getcwd) "/setup:"
6056 (getenv "PERL5LIB")))
6058 ;; See https://github.com/ncbi/ncbi-vdb/issues/14
6059 (add-after 'unpack 'patch-krypto-flags
6061 (substitute* "libs/krypto/Makefile"
6062 (("-Wa,-march=generic64\\+aes") "")
6063 (("-Wa,-march=generic64\\+sse4") ""))
6066 (lambda* (#:key inputs outputs #:allow-other-keys)
6067 (let ((out (assoc-ref outputs "out")))
6068 ;; Override include path for libmagic
6069 (substitute* "setup/package.prl"
6070 (("name => 'magic', Include => '/usr/include'")
6071 (string-append "name=> 'magic', Include => '"
6072 (assoc-ref inputs "libmagic")
6075 ;; Install kdf5 library (needed by sra-tools)
6076 (substitute* "build/Makefile.install"
6077 (("LIBRARIES_TO_INSTALL =")
6078 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
6080 (substitute* "build/Makefile.env"
6081 (("CFLAGS =" prefix)
6082 (string-append prefix "-msse2 ")))
6084 ;; Override search path for ngs-java
6085 (substitute* "setup/package.prl"
6086 (("/usr/local/ngs/ngs-java")
6087 (assoc-ref inputs "java-ngs")))
6089 ;; The 'configure' script doesn't recognize things like
6090 ;; '--enable-fast-install'.
6091 (invoke "./configure"
6092 (string-append "--build-prefix=" (getcwd) "/build")
6093 (string-append "--prefix=" (assoc-ref outputs "out"))
6094 (string-append "--debug")
6095 (string-append "--with-xml2-prefix="
6096 (assoc-ref inputs "libxml2"))
6097 (string-append "--with-ngs-sdk-prefix="
6098 (assoc-ref inputs "ngs-sdk"))
6099 (string-append "--with-hdf5-prefix="
6100 (assoc-ref inputs "hdf5")))
6102 (add-after 'install 'install-interfaces
6103 (lambda* (#:key outputs #:allow-other-keys)
6104 ;; Install interface libraries. On i686 the interface libraries
6105 ;; are installed to "linux/gcc/i386", so we need to use the Linux
6106 ;; architecture name ("i386") instead of the target system prefix
6108 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
6109 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
6110 ,(system->linux-architecture
6111 (or (%current-target-system)
6114 (string-append (assoc-ref outputs "out")
6116 ;; Install interface headers
6117 (copy-recursively "interfaces"
6118 (string-append (assoc-ref outputs "out")
6121 ;; These files are needed by sra-tools.
6122 (add-after 'install 'install-configuration-files
6123 (lambda* (#:key outputs #:allow-other-keys)
6124 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
6126 (install-file "libs/kfg/default.kfg" target)
6127 (install-file "libs/kfg/certs.kfg" target))
6130 `(("libxml2" ,libxml2)
6131 ("ngs-sdk" ,ngs-sdk)
6132 ("java-ngs" ,java-ngs)
6135 (native-inputs `(("perl" ,perl)))
6136 ;; NCBI-VDB requires SSE capability.
6137 (supported-systems '("i686-linux" "x86_64-linux"))
6138 (home-page "https://github.com/ncbi/ncbi-vdb")
6139 (synopsis "Database engine for genetic information")
6141 "The NCBI-VDB library implements a highly compressed columnar data
6142 warehousing engine that is most often used to store genetic information.
6143 Databases are stored in a portable image within the file system, and can be
6144 accessed/downloaded on demand across HTTP.")
6145 (license license:public-domain)))
6147 (define-public plink
6155 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
6156 version "-src.zip"))
6158 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
6159 (patches (search-patches "plink-1.07-unclobber-i.patch"
6160 "plink-endian-detection.patch"))))
6161 (build-system gnu-build-system)
6163 '(#:tests? #f ;no "check" target
6164 #:make-flags (list (string-append "LIB_LAPACK="
6165 (assoc-ref %build-inputs "lapack")
6166 "/lib/liblapack.so")
6169 ;; disable phoning home
6172 (modify-phases %standard-phases
6173 ;; no "configure" script
6176 (lambda* (#:key outputs #:allow-other-keys)
6177 (let ((bin (string-append (assoc-ref outputs "out")
6179 (install-file "plink" bin)
6183 ("lapack" ,lapack)))
6185 `(("unzip" ,unzip)))
6186 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
6187 (synopsis "Whole genome association analysis toolset")
6189 "PLINK is a whole genome association analysis toolset, designed to
6190 perform a range of basic, large-scale analyses in a computationally efficient
6191 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
6192 so there is no support for steps prior to this (e.g. study design and
6193 planning, generating genotype or CNV calls from raw data). Through
6194 integration with gPLINK and Haploview, there is some support for the
6195 subsequent visualization, annotation and storage of results.")
6196 ;; Code is released under GPLv2, except for fisher.h, which is under
6198 (license (list license:gpl2 license:lgpl2.1+))))
6200 (define-public plink-ng
6201 (package (inherit plink)
6208 (url "https://github.com/chrchang/plink-ng")
6209 (commit (string-append "v" version))))
6210 (file-name (git-file-name name version))
6212 (base32 "02npdwgkpfkdnhw819rhj5kw02a5k5m90b14zq9zzya4hyg929c0"))))
6213 (build-system gnu-build-system)
6215 '(#:tests? #f ;no "check" target
6216 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
6217 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
6219 "-f" "Makefile.std")
6221 (modify-phases %standard-phases
6222 (add-after 'unpack 'chdir
6223 (lambda _ (chdir "1.9") #t))
6224 (delete 'configure) ; no "configure" script
6226 (lambda* (#:key outputs #:allow-other-keys)
6227 (let ((bin (string-append (assoc-ref outputs "out")
6229 (install-file "plink" bin)
6234 ("openblas" ,openblas)))
6235 (home-page "https://www.cog-genomics.org/plink/")
6236 (license license:gpl3+)))
6238 (define-public smithlab-cpp
6239 (let ((revision "1")
6240 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
6242 (name "smithlab-cpp")
6243 (version (string-append "0." revision "." (string-take commit 7)))
6247 (url "https://github.com/smithlabcode/smithlab_cpp")
6249 (file-name (string-append name "-" version "-checkout"))
6252 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
6253 (build-system gnu-build-system)
6255 `(#:modules ((guix build gnu-build-system)
6258 #:tests? #f ;no "check" target
6260 (modify-phases %standard-phases
6261 (add-after 'unpack 'use-samtools-headers
6263 (substitute* '("SAM.cpp"
6265 (("sam.h") "samtools/sam.h"))
6268 (lambda* (#:key outputs #:allow-other-keys)
6269 (let* ((out (assoc-ref outputs "out"))
6270 (lib (string-append out "/lib"))
6271 (include (string-append out "/include/smithlab-cpp")))
6274 (for-each (cut install-file <> lib)
6275 (find-files "." "\\.o$"))
6276 (for-each (cut install-file <> include)
6277 (find-files "." "\\.hpp$")))
6279 (delete 'configure))))
6281 `(("samtools" ,samtools-0.1)
6283 (home-page "https://github.com/smithlabcode/smithlab_cpp")
6284 (synopsis "C++ helper library for functions used in Smith lab projects")
6286 "Smithlab CPP is a C++ library that includes functions used in many of
6287 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
6288 structures, classes for genomic regions, mapped sequencing reads, etc.")
6289 (license license:gpl3+))))
6291 (define-public preseq
6297 (uri (string-append "https://github.com/smithlabcode/preseq/"
6298 "releases/download/v" version
6299 "/preseq_v" version ".tar.bz2"))
6301 (base32 "149x9xmk1wy1gff85325yfzqc0qk4sgp1w6gbyj9cnji4x1dszbl"))
6302 (modules '((guix build utils)))
6304 ;; Remove bundled samtools.
6305 (delete-file-recursively "samtools")
6307 (build-system gnu-build-system)
6309 `(#:tests? #f ;no "check" target
6311 (modify-phases %standard-phases
6312 (delete 'configure))
6314 (list (string-append "PREFIX="
6315 (assoc-ref %outputs "out"))
6316 (string-append "LIBBAM="
6317 (assoc-ref %build-inputs "samtools")
6319 (string-append "SMITHLAB_CPP="
6320 (assoc-ref %build-inputs "smithlab-cpp")
6323 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
6326 ("samtools" ,samtools-0.1)
6327 ("smithlab-cpp" ,smithlab-cpp)
6329 (home-page "http://smithlabresearch.org/software/preseq/")
6330 (synopsis "Program for analyzing library complexity")
6332 "The preseq package is aimed at predicting and estimating the complexity
6333 of a genomic sequencing library, equivalent to predicting and estimating the
6334 number of redundant reads from a given sequencing depth and how many will be
6335 expected from additional sequencing using an initial sequencing experiment.
6336 The estimates can then be used to examine the utility of further sequencing,
6337 optimize the sequencing depth, or to screen multiple libraries to avoid low
6338 complexity samples.")
6339 (license license:gpl3+)))
6341 (define-public python-screed
6343 (name "python-screed")
6348 (uri (pypi-uri "screed" version))
6351 "148vcb7w2wr6a4w6vs2bsxanbqibxfk490zbcbg4m61s8669zdjx"))))
6352 (build-system python-build-system)
6355 (modify-phases %standard-phases
6356 ;; Tests must be run after installation, as the "screed" command does
6357 ;; not exist right after building.
6359 (add-after 'install 'check
6360 (lambda* (#:key inputs outputs #:allow-other-keys)
6361 (let ((out (assoc-ref outputs "out")))
6362 (setenv "PYTHONPATH"
6363 (string-append out "/lib/python"
6364 (string-take (string-take-right
6365 (assoc-ref inputs "python")
6368 (getenv "PYTHONPATH")))
6369 (setenv "PATH" (string-append out "/bin:" (getenv "PATH"))))
6370 (invoke "python" "setup.py" "test")
6373 `(("python-pytest" ,python-pytest)
6374 ("python-pytest-cov" ,python-pytest-cov)
6375 ("python-pytest-runner" ,python-pytest-runner)))
6377 `(("python-bz2file" ,python-bz2file)))
6378 (home-page "https://github.com/dib-lab/screed/")
6379 (synopsis "Short read sequence database utilities")
6380 (description "Screed parses FASTA and FASTQ files and generates databases.
6381 Values such as sequence name, sequence description, sequence quality and the
6382 sequence itself can be retrieved from these databases.")
6383 (license license:bsd-3)))
6385 (define-public python2-screed
6386 (package-with-python2 python-screed))
6388 (define-public sra-tools
6396 (url "https://github.com/ncbi/sra-tools")
6398 (file-name (git-file-name name version))
6401 "1cr2mijkfs5sm35ffjs6861qsd1qkgnhnbavdv65zg5d655abbjf"))))
6402 (build-system gnu-build-system)
6404 `(#:parallel-build? #f ; not supported
6405 #:tests? #f ; no "check" target
6407 (list (string-append "DEFAULT_CRT="
6408 (assoc-ref %build-inputs "ncbi-vdb")
6410 (string-append "DEFAULT_KFG="
6411 (assoc-ref %build-inputs "ncbi-vdb")
6413 (string-append "VDB_LIBDIR="
6414 (assoc-ref %build-inputs "ncbi-vdb")
6415 ,(if (string-prefix? "x86_64"
6416 (or (%current-target-system)
6421 (modify-phases %standard-phases
6422 (add-before 'configure 'set-perl-search-path
6424 ;; Work around "dotless @INC" build failure.
6426 (string-append (getcwd) "/setup:"
6427 (getenv "PERL5LIB")))
6430 (lambda* (#:key inputs outputs #:allow-other-keys)
6431 ;; The build system expects a directory containing the sources and
6432 ;; raw build output of ncbi-vdb, including files that are not
6433 ;; installed. Since we are building against an installed version of
6434 ;; ncbi-vdb, the following modifications are needed.
6435 (substitute* "setup/konfigure.perl"
6436 ;; Make the configure script look for the "ilib" directory of
6437 ;; "ncbi-vdb" without first checking for the existence of a
6438 ;; matching library in its "lib" directory.
6439 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
6440 "my $f = File::Spec->catdir($ilibdir, $ilib);")
6441 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
6442 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
6443 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
6446 (substitute* "tools/copycat/Makefile"
6447 (("smagic-static") "lmagic"))
6448 (substitute* "tools/driver-tool/utf8proc/Makefile"
6449 (("CC\\?=gcc") "myCC=gcc")
6450 (("\\(CC\\)") "(myCC)"))
6452 ;; The 'configure' script doesn't recognize things like
6453 ;; '--enable-fast-install'.
6454 (invoke "./configure"
6455 (string-append "--build-prefix=" (getcwd) "/build")
6456 (string-append "--prefix=" (assoc-ref outputs "out"))
6457 (string-append "--debug")
6458 (string-append "--with-fuse-prefix="
6459 (assoc-ref inputs "fuse"))
6460 (string-append "--with-magic-prefix="
6461 (assoc-ref inputs "libmagic"))
6462 ;; TODO: building with libxml2 fails with linker errors
6464 (string-append "--with-xml2-prefix="
6465 (assoc-ref inputs "libxml2"))
6466 (string-append "--with-ncbi-vdb-sources="
6467 (assoc-ref inputs "ncbi-vdb"))
6468 (string-append "--with-ncbi-vdb-build="
6469 (assoc-ref inputs "ncbi-vdb"))
6470 (string-append "--with-ngs-sdk-prefix="
6471 (assoc-ref inputs "ngs-sdk"))
6472 (string-append "--with-hdf5-prefix="
6473 (assoc-ref inputs "hdf5")))
6475 (native-inputs `(("perl" ,perl)))
6477 `(("ngs-sdk" ,ngs-sdk)
6478 ("ncbi-vdb" ,ncbi-vdb)
6483 ("python" ,python-wrapper)))
6485 "https://trace.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
6486 (synopsis "Tools and libraries for reading and writing sequencing data")
6488 "The SRA Toolkit from NCBI is a collection of tools and libraries for
6489 reading of sequencing files from the Sequence Read Archive (SRA) database and
6490 writing files into the .sra format.")
6491 (license license:public-domain)))
6493 (define-public seqan
6499 (uri (string-append "https://github.com/seqan/seqan/releases/"
6500 "download/seqan-v" version
6501 "/seqan-library-" version ".tar.xz"))
6504 "19a1rlxx03qy1i1iriicly68w64yjxbv24g9gdywnfmq998v35yx"))))
6505 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6506 ;; makes sense to split the outputs.
6507 (outputs '("out" "doc"))
6508 (build-system trivial-build-system)
6510 `(#:modules ((guix build utils))
6513 (use-modules (guix build utils))
6514 (let ((tar (assoc-ref %build-inputs "tar"))
6515 (xz (assoc-ref %build-inputs "xz"))
6516 (out (assoc-ref %outputs "out"))
6517 (doc (assoc-ref %outputs "doc")))
6518 (setenv "PATH" (string-append tar "/bin:" xz "/bin"))
6519 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6520 (chdir (string-append "seqan-library-" ,version))
6521 (copy-recursively "include" (string-append out "/include"))
6522 (copy-recursively "share" (string-append doc "/share"))
6525 `(("source" ,source)
6528 (home-page "http://www.seqan.de")
6529 (synopsis "Library for nucleotide sequence analysis")
6531 "SeqAn is a C++ library of efficient algorithms and data structures for
6532 the analysis of sequences with the focus on biological data. It contains
6533 algorithms and data structures for string representation and their
6534 manipulation, online and indexed string search, efficient I/O of
6535 bioinformatics file formats, sequence alignment, and more.")
6536 (license license:bsd-3)))
6538 (define-public seqan-1
6539 (package (inherit seqan)
6544 (uri (string-append "http://packages.seqan.de/seqan-library/"
6545 "seqan-library-" version ".tar.bz2"))
6548 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
6549 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6550 ;; makes sense to split the outputs.
6551 (outputs '("out" "doc"))
6552 (build-system trivial-build-system)
6554 `(#:modules ((guix build utils))
6557 (use-modules (guix build utils))
6558 (let ((tar (assoc-ref %build-inputs "tar"))
6559 (bzip (assoc-ref %build-inputs "bzip2"))
6560 (out (assoc-ref %outputs "out"))
6561 (doc (assoc-ref %outputs "doc")))
6562 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
6563 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6564 (chdir (string-append "seqan-library-" ,version))
6565 (copy-recursively "include" (string-append out "/include"))
6566 (copy-recursively "share" (string-append doc "/share"))
6569 `(("source" ,source)
6571 ("bzip2" ,bzip2)))))
6573 (define-public seqmagick
6580 (uri (pypi-uri "seqmagick" version))
6583 "0pf98da7i59q47gwrbx0wjk6xlvbybiwphw80w7h4ydjj0579a2b"))))
6584 (build-system python-build-system)
6586 `(("python-biopython" ,python-biopython)))
6588 `(("python-nose" ,python-nose)))
6589 (home-page "https://github.com/fhcrc/seqmagick")
6590 (synopsis "Tools for converting and modifying sequence files")
6592 "Bioinformaticians often have to convert sequence files between formats
6593 and do little manipulations on them, and it's not worth writing scripts for
6594 that. Seqmagick is a utility to expose the file format conversion in
6595 BioPython in a convenient way. Instead of having a big mess of scripts, there
6596 is one that takes arguments.")
6597 (license license:gpl3)))
6599 (define-public seqtk
6606 (url "https://github.com/lh3/seqtk")
6607 (commit (string-append "v" version))))
6608 (file-name (git-file-name name version))
6611 "1bfzlqa84b5s1qi22blmmw2s8xdyp9h9ydcq22pfjhh5gab3yz6l"))))
6612 (build-system gnu-build-system)
6615 (modify-phases %standard-phases
6618 ;; There are no tests, so we just run a sanity check.
6619 (lambda _ (invoke "./seqtk" "seq") #t))
6621 (lambda* (#:key outputs #:allow-other-keys)
6622 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6623 (install-file "seqtk" bin)
6627 (home-page "https://github.com/lh3/seqtk")
6628 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
6630 "Seqtk is a fast and lightweight tool for processing sequences in the
6631 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
6632 optionally compressed by gzip.")
6633 (license license:expat)))
6635 (define-public snap-aligner
6637 (name "snap-aligner")
6638 (version "1.0beta.18")
6642 (url "https://github.com/amplab/snap")
6643 (commit (string-append "v" version))))
6644 (file-name (git-file-name name version))
6647 "01w3qq4wm07z73vky0cfwlmrbf50n3w722cxrlzxfi99mnb808d8"))))
6648 (build-system gnu-build-system)
6651 (modify-phases %standard-phases
6653 (replace 'check (lambda _ (invoke "./unit_tests") #t))
6655 (lambda* (#:key outputs #:allow-other-keys)
6656 (let* ((out (assoc-ref outputs "out"))
6657 (bin (string-append out "/bin")))
6658 (install-file "snap-aligner" bin)
6659 (install-file "SNAPCommand" bin)
6663 (home-page "http://snap.cs.berkeley.edu/")
6664 (synopsis "Short read DNA sequence aligner")
6666 "SNAP is a fast and accurate aligner for short DNA reads. It is
6667 optimized for modern read lengths of 100 bases or higher, and takes advantage
6668 of these reads to align data quickly through a hash-based indexing scheme.")
6669 ;; 32-bit systems are not supported by the unpatched code.
6670 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
6671 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
6672 ;; systems without a lot of memory cannot make good use of this program.
6673 (supported-systems '("x86_64-linux"))
6674 (license license:asl2.0)))
6676 (define-public sortmerna
6684 (url "https://github.com/biocore/sortmerna")
6686 (file-name (git-file-name name version))
6689 "0j3mbz4n25738yijmjbr5r4fyvkgm8v5vn3sshyfvmyqf5q9byqf"))))
6690 (build-system gnu-build-system)
6691 (outputs '("out" ;for binaries
6692 "db")) ;for sequence databases
6695 (modify-phases %standard-phases
6697 (lambda* (#:key outputs #:allow-other-keys)
6698 (let* ((out (assoc-ref outputs "out"))
6699 (bin (string-append out "/bin"))
6700 (db (assoc-ref outputs "db"))
6702 (string-append db "/share/sortmerna/rRNA_databases")))
6703 (install-file "sortmerna" bin)
6704 (install-file "indexdb_rna" bin)
6705 (for-each (lambda (file)
6706 (install-file file share))
6707 (find-files "rRNA_databases" ".*fasta"))
6711 (home-page "https://bioinfo.lifl.fr/RNA/sortmerna/")
6712 (synopsis "Biological sequence analysis tool for NGS reads")
6714 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
6715 and operational taxonomic unit (OTU) picking of next generation
6716 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
6717 allows for fast and sensitive analyses of nucleotide sequences. The main
6718 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
6719 ;; The source includes x86 specific code
6720 (supported-systems '("x86_64-linux" "i686-linux"))
6721 (license license:lgpl3)))
6730 (url "https://github.com/alexdobin/STAR")
6732 (file-name (git-file-name name version))
6735 "1hgiqw5qhs0pc1xazzihcfd92na02xyq2kb469z04y1v51kpvvjq"))
6736 (modules '((guix build utils)))
6739 (substitute* "source/Makefile"
6741 ;; Remove pre-built binaries and bundled htslib sources.
6742 (delete-file-recursively "bin/MacOSX_x86_64")
6743 (delete-file-recursively "bin/Linux_x86_64")
6744 (delete-file-recursively "bin/Linux_x86_64_static")
6745 (delete-file-recursively "source/htslib")
6747 (build-system gnu-build-system)
6749 '(#:tests? #f ;no check target
6750 #:make-flags '("STAR")
6752 (modify-phases %standard-phases
6753 (add-after 'unpack 'enter-source-dir
6754 (lambda _ (chdir "source") #t))
6755 (add-after 'enter-source-dir 'make-reproducible
6757 (substitute* "Makefile"
6758 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
6759 (string-append pre "Built with Guix" post)))
6761 ;; See https://github.com/alexdobin/STAR/pull/562
6762 (add-after 'enter-source-dir 'add-missing-header
6764 (substitute* "SoloReadFeature_inputRecords.cpp"
6765 (("#include \"binarySearch2.h\"" h)
6766 (string-append h "\n#include <math.h>")))
6768 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
6770 (substitute* "Makefile"
6771 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
6773 (substitute* '("BAMfunctions.cpp"
6778 "bamRemoveDuplicates.cpp")
6779 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
6780 (string-append "#include <" header ">")))
6781 (substitute* "IncludeDefine.h"
6782 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
6783 (string-append "<" header ">")))
6786 (lambda* (#:key outputs #:allow-other-keys)
6787 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6788 (install-file "STAR" bin))
6790 (delete 'configure))))
6794 `(("htslib" ,htslib)
6796 (home-page "https://github.com/alexdobin/STAR")
6797 (synopsis "Universal RNA-seq aligner")
6799 "The Spliced Transcripts Alignment to a Reference (STAR) software is
6800 based on a previously undescribed RNA-seq alignment algorithm that uses
6801 sequential maximum mappable seed search in uncompressed suffix arrays followed
6802 by seed clustering and stitching procedure. In addition to unbiased de novo
6803 detection of canonical junctions, STAR can discover non-canonical splices and
6804 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
6806 ;; Only 64-bit systems are supported according to the README.
6807 (supported-systems '("x86_64-linux" "mips64el-linux"))
6808 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
6809 (license license:gpl3+)))
6811 (define-public starlong
6812 (package (inherit star)
6815 (substitute-keyword-arguments (package-arguments star)
6816 ((#:make-flags flags)
6819 `(modify-phases ,phases
6820 ;; Allow extra long sequence reads.
6821 (add-after 'unpack 'make-extra-long
6823 (substitute* "source/IncludeDefine.h"
6824 (("(#define DEF_readNameLengthMax ).*" _ match)
6825 (string-append match "900000\n")))
6828 (lambda* (#:key outputs #:allow-other-keys)
6829 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6830 (install-file "STARlong" bin))
6833 (define-public subread
6839 (uri (string-append "mirror://sourceforge/subread/subread-"
6840 version "/subread-" version "-source.tar.gz"))
6843 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
6844 (build-system gnu-build-system)
6846 `(#:tests? #f ;no "check" target
6847 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
6848 ;; optimizations by default, so we override these flags such that x86_64
6849 ;; flags are only added when the build target is an x86_64 system.
6851 (list (let ((system ,(or (%current-target-system)
6853 (flags '("-ggdb" "-fomit-frame-pointer"
6854 "-ffast-math" "-funroll-loops"
6855 "-fmessage-length=0"
6856 "-O9" "-Wall" "-DMAKE_FOR_EXON"
6858 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
6859 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
6860 (if (string-prefix? "x86_64" system)
6861 (string-append "CCFLAGS=" (string-join (append flags flags64)))
6862 (string-append "CCFLAGS=" (string-join flags))))
6863 "-f" "Makefile.Linux"
6864 "CC=gcc ${CCFLAGS}")
6866 (modify-phases %standard-phases
6867 (add-after 'unpack 'enter-dir
6868 (lambda _ (chdir "src") #t))
6870 (lambda* (#:key outputs #:allow-other-keys)
6871 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6873 (copy-recursively "../bin" bin))
6875 ;; no "configure" script
6876 (delete 'configure))))
6877 (inputs `(("zlib" ,zlib)))
6878 (home-page "http://bioinf.wehi.edu.au/subread-package/")
6879 (synopsis "Tool kit for processing next-gen sequencing data")
6881 "The subread package contains the following tools: subread aligner, a
6882 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
6883 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
6884 features; exactSNP: a SNP caller that discovers SNPs by testing signals
6885 against local background noises.")
6886 (license license:gpl3+)))
6888 (define-public stringtie
6894 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
6895 "stringtie-" version ".tar.gz"))
6898 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
6899 (modules '((guix build utils)))
6902 (delete-file-recursively "samtools-0.1.18")
6904 (build-system gnu-build-system)
6906 `(#:tests? #f ;no test suite
6908 (modify-phases %standard-phases
6909 ;; no configure script
6911 (add-before 'build 'use-system-samtools
6913 (substitute* "Makefile"
6914 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
6916 (substitute* '("gclib/GBam.h"
6918 (("#include \"(bam|sam|kstring).h\"" _ header)
6919 (string-append "#include <samtools/" header ".h>")))
6921 (add-after 'unpack 'remove-duplicate-typedef
6923 ;; This typedef conflicts with the typedef in
6924 ;; glibc-2.25/include/bits/types.h
6925 (substitute* "gclib/GThreads.h"
6926 (("typedef long long __intmax_t;") ""))
6929 (lambda* (#:key outputs #:allow-other-keys)
6930 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6931 (install-file "stringtie" bin)
6934 `(("samtools" ,samtools-0.1)
6936 (home-page "http://ccb.jhu.edu/software/stringtie/")
6937 (synopsis "Transcript assembly and quantification for RNA-Seq data")
6939 "StringTie is a fast and efficient assembler of RNA-Seq sequence
6940 alignments into potential transcripts. It uses a novel network flow algorithm
6941 as well as an optional de novo assembly step to assemble and quantitate
6942 full-length transcripts representing multiple splice variants for each gene
6943 locus. Its input can include not only the alignments of raw reads used by
6944 other transcript assemblers, but also alignments of longer sequences that have
6945 been assembled from those reads. To identify differentially expressed genes
6946 between experiments, StringTie's output can be processed either by the
6947 Cuffdiff or Ballgown programs.")
6948 (license license:artistic2.0)))
6950 (define-public taxtastic
6955 ;; The Pypi version does not include tests.
6958 (url "https://github.com/fhcrc/taxtastic")
6959 (commit (string-append "v" version))))
6960 (file-name (git-file-name name version))
6963 "1sv8mkg64jn7zdwf1jj71c16686yrwxk0apb1l8sjszy9p166g0p"))))
6964 (build-system python-build-system)
6967 (modify-phases %standard-phases
6968 (add-after 'unpack 'prepare-directory
6970 ;; The git checkout must be writable for tests.
6971 (for-each make-file-writable (find-files "."))
6972 ;; This test fails, but the error is not caught by the test
6973 ;; framework, so the tests fail...
6974 (substitute* "tests/test_taxit.py"
6975 (("self.cmd_fails\\(''\\)")
6976 "self.cmd_fails('nothing')"))
6977 ;; This version file is expected to be created with git describe.
6978 (mkdir-p "taxtastic/data")
6979 (with-output-to-file "taxtastic/data/ver"
6980 (lambda () (display ,version)))
6982 (add-after 'unpack 'python37-compatibility
6984 (substitute* "taxtastic/utils.py"
6985 (("import csv") "import csv, errno")
6986 (("os.errno") "errno"))
6989 ;; Note, this fails to run with "-v" as it tries to write to a
6990 ;; closed output stream.
6991 (lambda _ (invoke "python" "-m" "unittest") #t)))))
6993 `(("python-sqlalchemy" ,python-sqlalchemy)
6994 ("python-decorator" ,python-decorator)
6995 ("python-biopython" ,python-biopython)
6996 ("python-pandas" ,python-pandas)
6997 ("python-psycopg2" ,python-psycopg2)
6998 ("python-fastalite" ,python-fastalite)
6999 ("python-pyyaml" ,python-pyyaml)
7000 ("python-six" ,python-six)
7001 ("python-jinja2" ,python-jinja2)
7002 ("python-dendropy" ,python-dendropy)))
7003 (home-page "https://github.com/fhcrc/taxtastic")
7004 (synopsis "Tools for taxonomic naming and annotation")
7006 "Taxtastic is software written in python used to build and maintain
7007 reference packages i.e. collections of reference trees, reference alignments,
7008 profiles, and associated taxonomic information.")
7009 (license license:gpl3+)))
7011 (define-public vcftools
7018 "https://github.com/vcftools/vcftools/releases/download/v"
7019 version "/vcftools-" version ".tar.gz"))
7022 "1qqlx7flfv7axrjwkaz6njkscsl1d0jw98ns8d8bh1n1hd1pgz6v"))))
7023 (build-system gnu-build-system)
7025 `(#:tests? #f ; no "check" target
7027 "CFLAGS=-O2" ; override "-m64" flag
7028 (string-append "PREFIX=" (assoc-ref %outputs "out"))
7029 (string-append "MANDIR=" (assoc-ref %outputs "out")
7030 "/share/man/man1"))))
7032 `(("pkg-config" ,pkg-config)))
7036 (home-page "https://vcftools.github.io/")
7037 (synopsis "Tools for working with VCF files")
7039 "VCFtools is a program package designed for working with VCF files, such
7040 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
7041 provide easily accessible methods for working with complex genetic variation
7042 data in the form of VCF files.")
7043 ;; The license is declared as LGPLv3 in the README and
7044 ;; at https://vcftools.github.io/license.html
7045 (license license:lgpl3)))
7047 (define-public infernal
7053 (uri (string-append "http://eddylab.org/software/infernal/"
7054 "infernal-" version ".tar.gz"))
7057 "0pm8bm3s6nfa0av4x6m6h27lsg12b3lz3jm0fyh1mc77l2isd61v"))))
7058 (build-system gnu-build-system)
7061 ("python" ,python))) ; for tests
7062 (home-page "http://eddylab.org/infernal/")
7063 (synopsis "Inference of RNA alignments")
7064 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
7065 searching DNA sequence databases for RNA structure and sequence similarities.
7066 It is an implementation of a special case of profile stochastic context-free
7067 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
7068 profile, but it scores a combination of sequence consensus and RNA secondary
7069 structure consensus, so in many cases, it is more capable of identifying RNA
7070 homologs that conserve their secondary structure more than their primary
7072 ;; Infernal 1.1.3 requires VMX or SSE capability for parallel instructions.
7073 (supported-systems '("i686-linux" "x86_64-linux"))
7074 (license license:bsd-3)))
7076 (define-public r-scde
7083 (url "https://github.com/hms-dbmi/scde")
7085 (file-name (git-file-name name version))
7088 "10na2gyka24mszdxf92wz9h2c13hdf1ww30c68gfsw53lvvhhhxb"))))
7089 (build-system r-build-system)
7091 `(("r-rcpp" ,r-rcpp)
7092 ("r-rcpparmadillo" ,r-rcpparmadillo)
7095 ("r-rjson" ,r-rjson)
7096 ("r-cairo" ,r-cairo)
7097 ("r-rcolorbrewer" ,r-rcolorbrewer)
7098 ("r-edger" ,r-edger)
7099 ("r-quantreg" ,r-quantreg)
7101 ("r-rmtstat" ,r-rmtstat)
7102 ("r-extremes" ,r-extremes)
7103 ("r-pcamethods" ,r-pcamethods)
7104 ("r-biocparallel" ,r-biocparallel)
7105 ("r-flexmix" ,r-flexmix)))
7106 (home-page "https://hms-dbmi.github.io/scde/")
7107 (synopsis "R package for analyzing single-cell RNA-seq data")
7108 (description "The SCDE package implements a set of statistical methods for
7109 analyzing single-cell RNA-seq data. SCDE fits individual error models for
7110 single-cell RNA-seq measurements. These models can then be used for
7111 assessment of differential expression between groups of cells, as well as
7112 other types of analysis. The SCDE package also contains the pagoda framework
7113 which applies pathway and gene set overdispersion analysis to identify aspects
7114 of transcriptional heterogeneity among single cells.")
7115 ;; See https://github.com/hms-dbmi/scde/issues/38
7116 (license license:gpl2)))
7118 (define-public r-centipede
7120 (name "r-centipede")
7124 (uri (string-append "http://download.r-forge.r-project.org/"
7125 "src/contrib/CENTIPEDE_" version ".tar.gz"))
7128 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
7129 (build-system r-build-system)
7130 (home-page "http://centipede.uchicago.edu/")
7131 (synopsis "Predict transcription factor binding sites")
7133 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
7134 of the genome that are bound by particular transcription factors. It starts
7135 by identifying a set of candidate binding sites, and then aims to classify the
7136 sites according to whether each site is bound or not bound by a transcription
7137 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
7138 between two different types of motif instances using as much relevant
7139 information as possible.")
7140 (license (list license:gpl2+ license:gpl3+))))
7142 (define-public r-genefilter
7144 (name "r-genefilter")
7149 (uri (bioconductor-uri "genefilter" version))
7152 "0929g6c4v2qhgipgrh1a5gv6444sm2dp52x9c3qbk03i8wzc6633"))))
7153 (build-system r-build-system)
7155 `(("gfortran" ,gfortran)
7156 ("r-knitr" ,r-knitr)))
7158 `(("r-annotate" ,r-annotate)
7159 ("r-annotationdbi" ,r-annotationdbi)
7160 ("r-biobase" ,r-biobase)
7161 ("r-biocgenerics" ,r-biocgenerics)
7162 ("r-survival" ,r-survival)))
7163 (home-page "https://bioconductor.org/packages/genefilter")
7164 (synopsis "Filter genes from high-throughput experiments")
7166 "This package provides basic functions for filtering genes from
7167 high-throughput sequencing experiments.")
7168 (license license:artistic2.0)))
7170 (define-public r-deseq2
7177 (uri (bioconductor-uri "DESeq2" version))
7180 "0q2f9cywrcmp1p7ii8f45g4dk4hsnjflq3yqhsxgnpv9fw338qpp"))))
7181 (properties `((upstream-name . "DESeq2")))
7182 (build-system r-build-system)
7184 `(("r-biobase" ,r-biobase)
7185 ("r-biocgenerics" ,r-biocgenerics)
7186 ("r-biocparallel" ,r-biocparallel)
7187 ("r-genefilter" ,r-genefilter)
7188 ("r-geneplotter" ,r-geneplotter)
7189 ("r-genomicranges" ,r-genomicranges)
7190 ("r-ggplot2" ,r-ggplot2)
7191 ("r-iranges" ,r-iranges)
7192 ("r-locfit" ,r-locfit)
7194 ("r-rcpparmadillo" ,r-rcpparmadillo)
7195 ("r-s4vectors" ,r-s4vectors)
7196 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7198 `(("r-knitr" ,r-knitr)))
7199 (home-page "https://bioconductor.org/packages/DESeq2")
7200 (synopsis "Differential gene expression analysis")
7202 "This package provides functions to estimate variance-mean dependence in
7203 count data from high-throughput nucleotide sequencing assays and test for
7204 differential expression based on a model using the negative binomial
7206 (license license:lgpl3+)))
7208 (define-public r-dexseq
7215 (uri (bioconductor-uri "DEXSeq" version))
7218 "0wfjb42xcr4wjy8a654b74411dky8hp6sp8xdwf0sxqgsxy106qi"))))
7219 (properties `((upstream-name . "DEXSeq")))
7220 (build-system r-build-system)
7222 `(("r-annotationdbi" ,r-annotationdbi)
7223 ("r-biobase" ,r-biobase)
7224 ("r-biocgenerics" ,r-biocgenerics)
7225 ("r-biocparallel" ,r-biocparallel)
7226 ("r-biomart" ,r-biomart)
7227 ("r-deseq2" ,r-deseq2)
7228 ("r-genefilter" ,r-genefilter)
7229 ("r-geneplotter" ,r-geneplotter)
7230 ("r-genomicranges" ,r-genomicranges)
7231 ("r-hwriter" ,r-hwriter)
7232 ("r-iranges" ,r-iranges)
7233 ("r-rcolorbrewer" ,r-rcolorbrewer)
7234 ("r-rsamtools" ,r-rsamtools)
7235 ("r-s4vectors" ,r-s4vectors)
7236 ("r-statmod" ,r-statmod)
7237 ("r-stringr" ,r-stringr)
7238 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7240 `(("r-knitr" ,r-knitr)))
7241 (home-page "https://bioconductor.org/packages/DEXSeq")
7242 (synopsis "Inference of differential exon usage in RNA-Seq")
7244 "This package is focused on finding differential exon usage using RNA-seq
7245 exon counts between samples with different experimental designs. It provides
7246 functions that allows the user to make the necessary statistical tests based
7247 on a model that uses the negative binomial distribution to estimate the
7248 variance between biological replicates and generalized linear models for
7249 testing. The package also provides functions for the visualization and
7250 exploration of the results.")
7251 (license license:gpl3+)))
7253 (define-public r-annotationforge
7255 (name "r-annotationforge")
7260 (uri (bioconductor-uri "AnnotationForge" version))
7263 "0y3820dkvwz09wlmz9drx6gqpsr9cwppaiz40zafwfxbz65y8px7"))))
7265 `((upstream-name . "AnnotationForge")))
7266 (build-system r-build-system)
7268 `(("r-annotationdbi" ,r-annotationdbi)
7269 ("r-biobase" ,r-biobase)
7270 ("r-biocgenerics" ,r-biocgenerics)
7272 ("r-rcurl" ,r-rcurl)
7273 ("r-rsqlite" ,r-rsqlite)
7274 ("r-s4vectors" ,r-s4vectors)
7277 `(("r-knitr" ,r-knitr)))
7278 (home-page "https://bioconductor.org/packages/AnnotationForge")
7279 (synopsis "Code for building annotation database packages")
7281 "This package provides code for generating Annotation packages and their
7282 databases. Packages produced are intended to be used with AnnotationDbi.")
7283 (license license:artistic2.0)))
7285 (define-public r-rbgl
7292 (uri (bioconductor-uri "RBGL" version))
7295 "016vyzgixb3gjpzi21rbs6ngnnqcxr77krwjjf1ldnzzj8vqrqsz"))))
7296 (properties `((upstream-name . "RBGL")))
7297 (build-system r-build-system)
7300 ("r-graph" ,r-graph)))
7301 (home-page "https://www.bioconductor.org/packages/RBGL")
7302 (synopsis "Interface to the Boost graph library")
7304 "This package provides a fairly extensive and comprehensive interface to
7305 the graph algorithms contained in the Boost library.")
7306 (license license:artistic2.0)))
7308 (define-public r-gseabase
7315 (uri (bioconductor-uri "GSEABase" version))
7318 "0lcxbxfg62zdf2nql49asn3555cqrrxpjm2xsxf7vlxv84dl6r44"))))
7319 (properties `((upstream-name . "GSEABase")))
7320 (build-system r-build-system)
7322 `(("r-annotate" ,r-annotate)
7323 ("r-annotationdbi" ,r-annotationdbi)
7324 ("r-biobase" ,r-biobase)
7325 ("r-biocgenerics" ,r-biocgenerics)
7326 ("r-graph" ,r-graph)
7329 `(("r-knitr" ,r-knitr)))
7330 (home-page "https://bioconductor.org/packages/GSEABase")
7331 (synopsis "Gene set enrichment data structures and methods")
7333 "This package provides classes and methods to support @dfn{Gene Set
7334 Enrichment Analysis} (GSEA).")
7335 (license license:artistic2.0)))
7337 (define-public r-category
7344 (uri (bioconductor-uri "Category" version))
7347 "0m77wpnica0h2ia9ajdaiga4plgz1s9wls6pdnxzk7kwl8a68wkr"))))
7348 (properties `((upstream-name . "Category")))
7349 (build-system r-build-system)
7351 `(("r-annotate" ,r-annotate)
7352 ("r-annotationdbi" ,r-annotationdbi)
7353 ("r-biobase" ,r-biobase)
7354 ("r-biocgenerics" ,r-biocgenerics)
7355 ("r-genefilter" ,r-genefilter)
7356 ("r-graph" ,r-graph)
7357 ("r-gseabase" ,r-gseabase)
7358 ("r-matrix" ,r-matrix)
7361 (home-page "https://bioconductor.org/packages/Category")
7362 (synopsis "Category analysis")
7364 "This package provides a collection of tools for performing category
7366 (license license:artistic2.0)))
7368 (define-public r-gostats
7375 (uri (bioconductor-uri "GOstats" version))
7378 "18q8p0fv9fl2r6zjxknfjwqxr69dlyxy6c8amzn6c6dwjq1cxk6j"))))
7379 (properties `((upstream-name . "GOstats")))
7380 (build-system r-build-system)
7382 `(("r-annotate" ,r-annotate)
7383 ("r-annotationdbi" ,r-annotationdbi)
7384 ("r-annotationforge" ,r-annotationforge)
7385 ("r-biobase" ,r-biobase)
7386 ("r-category" ,r-category)
7387 ("r-go-db" ,r-go-db)
7388 ("r-graph" ,r-graph)
7389 ("r-rgraphviz" ,r-rgraphviz)
7390 ("r-rbgl" ,r-rbgl)))
7391 (home-page "https://bioconductor.org/packages/GOstats")
7392 (synopsis "Tools for manipulating GO and microarrays")
7394 "This package provides a set of tools for interacting with GO and
7395 microarray data. A variety of basic manipulation tools for graphs, hypothesis
7396 testing and other simple calculations.")
7397 (license license:artistic2.0)))
7399 (define-public r-shortread
7401 (name "r-shortread")
7406 (uri (bioconductor-uri "ShortRead" version))
7409 "0w4m8d3h660mmr2ymp206r1n4aqssxmkv8yxkbr5y1swrahxzfk9"))))
7410 (properties `((upstream-name . "ShortRead")))
7411 (build-system r-build-system)
7415 `(("r-biobase" ,r-biobase)
7416 ("r-biocgenerics" ,r-biocgenerics)
7417 ("r-biocparallel" ,r-biocparallel)
7418 ("r-biostrings" ,r-biostrings)
7419 ("r-genomeinfodb" ,r-genomeinfodb)
7420 ("r-genomicalignments" ,r-genomicalignments)
7421 ("r-genomicranges" ,r-genomicranges)
7422 ("r-rhtslib" ,r-rhtslib)
7423 ("r-hwriter" ,r-hwriter)
7424 ("r-iranges" ,r-iranges)
7425 ("r-lattice" ,r-lattice)
7426 ("r-latticeextra" ,r-latticeextra)
7427 ("r-rsamtools" ,r-rsamtools)
7428 ("r-s4vectors" ,r-s4vectors)
7429 ("r-xvector" ,r-xvector)
7430 ("r-zlibbioc" ,r-zlibbioc)))
7431 (home-page "https://bioconductor.org/packages/ShortRead")
7432 (synopsis "FASTQ input and manipulation tools")
7434 "This package implements sampling, iteration, and input of FASTQ files.
7435 It includes functions for filtering and trimming reads, and for generating a
7436 quality assessment report. Data are represented as
7437 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
7438 purposes. The package also contains legacy support for early single-end,
7439 ungapped alignment formats.")
7440 (license license:artistic2.0)))
7442 (define-public r-systempiper
7444 (name "r-systempiper")
7449 (uri (bioconductor-uri "systemPipeR" version))
7452 "0blvvci57q12sl18yvw07233rfnj47mfadzm0pdpig1ll5z6ld2j"))))
7453 (properties `((upstream-name . "systemPipeR")))
7454 (build-system r-build-system)
7456 `(("r-annotate" ,r-annotate)
7457 ("r-assertthat" ,r-assertthat)
7458 ("r-batchtools" ,r-batchtools)
7459 ("r-biostrings" ,r-biostrings)
7460 ("r-deseq2" ,r-deseq2)
7462 ("r-edger" ,r-edger)
7463 ("r-genomicfeatures" ,r-genomicfeatures)
7464 ("r-genomicranges" ,r-genomicranges)
7465 ("r-ggplot2" ,r-ggplot2)
7466 ("r-go-db" ,r-go-db)
7467 ("r-gostats" ,r-gostats)
7468 ("r-iranges" ,r-iranges)
7469 ("r-limma" ,r-limma)
7470 ("r-magrittr" ,r-magrittr)
7471 ("r-pheatmap" ,r-pheatmap)
7472 ("r-rjson" ,r-rjson)
7473 ("r-rsamtools" ,r-rsamtools)
7475 ("r-shortread" ,r-shortread)
7476 ("r-stringr" ,r-stringr)
7477 ("r-summarizedexperiment" ,r-summarizedexperiment)
7479 ("r-variantannotation" ,r-variantannotation)))
7481 `(("r-knitr" ,r-knitr)))
7482 (home-page "https://github.com/tgirke/systemPipeR")
7483 (synopsis "Next generation sequencing workflow and reporting environment")
7485 "This R package provides tools for building and running automated
7486 end-to-end analysis workflows for a wide range of @dfn{next generation
7487 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
7488 Important features include a uniform workflow interface across different NGS
7489 applications, automated report generation, and support for running both R and
7490 command-line software, such as NGS aligners or peak/variant callers, on local
7491 computers or compute clusters. Efficient handling of complex sample sets and
7492 experimental designs is facilitated by a consistently implemented sample
7493 annotation infrastructure.")
7494 (license license:artistic2.0)))
7496 (define-public r-grohmm
7503 (uri (bioconductor-uri "groHMM" version))
7506 "08pap9wsaxl4jjlc1py0rc019gmi6daa0f9cr3ih1d97wybncanx"))))
7507 (properties `((upstream-name . "groHMM")))
7508 (build-system r-build-system)
7510 `(("r-genomeinfodb" ,r-genomeinfodb)
7511 ("r-genomicalignments" ,r-genomicalignments)
7512 ("r-genomicranges" ,r-genomicranges)
7513 ("r-iranges" ,r-iranges)
7515 ("r-rtracklayer" ,r-rtracklayer)
7516 ("r-s4vectors" ,r-s4vectors)))
7517 (home-page "https://github.com/Kraus-Lab/groHMM")
7518 (synopsis "GRO-seq analysis pipeline")
7520 "This package provides a pipeline for the analysis of GRO-seq data.")
7521 (license license:gpl3+)))
7523 (define-public vsearch
7531 (url "https://github.com/torognes/vsearch")
7532 (commit (string-append "v" version))))
7533 (file-name (git-file-name name version))
7536 "0vhrpjfdf75ba04b24xknp41790cvcgwl0vgpy7qbzj5xh2521ss"))
7537 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
7540 ;; Remove bundled cityhash sources. The vsearch source is adjusted
7541 ;; for this in the patch.
7542 (delete-file "src/city.h")
7543 (delete-file "src/citycrc.h")
7544 (delete-file "src/city.cc")
7546 (build-system gnu-build-system)
7550 ("cityhash" ,cityhash)))
7552 `(("autoconf" ,autoconf)
7553 ("automake" ,automake)))
7554 (synopsis "Sequence search tools for metagenomics")
7556 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
7557 dereplication, pairwise alignment, shuffling, subsampling, sorting and
7558 masking. The tool takes advantage of parallelism in the form of SIMD
7559 vectorization as well as multiple threads to perform accurate alignments at
7560 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
7561 Needleman-Wunsch).")
7562 (home-page "https://github.com/torognes/vsearch")
7563 ;; vsearch uses non-portable SSE intrinsics so building fails on other
7565 (supported-systems '("x86_64-linux"))
7566 ;; Dual licensed; also includes public domain source.
7567 (license (list license:gpl3 license:bsd-2))))
7569 (define-public pardre
7572 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
7577 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
7581 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
7582 (build-system gnu-build-system)
7584 `(#:tests? #f ; no tests included
7586 (modify-phases %standard-phases
7589 (lambda* (#:key outputs #:allow-other-keys)
7590 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
7591 (install-file "ParDRe" bin)
7594 `(("openmpi" ,openmpi)
7596 (synopsis "Parallel tool to remove duplicate DNA reads")
7598 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
7599 Duplicate reads can be seen as identical or nearly identical sequences with
7600 some mismatches. This tool lets users avoid the analysis of unnecessary
7601 reads, reducing the time of subsequent procedures with the
7602 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
7603 in order to exploit the parallel capabilities of multicore clusters. It is
7604 faster than multithreaded counterparts (end of 2015) for the same number of
7605 cores and, thanks to the message-passing technology, it can be executed on
7607 (home-page "https://sourceforge.net/projects/pardre/")
7608 (license license:gpl3+)))
7610 (define-public ruby-bio-kseq
7612 (name "ruby-bio-kseq")
7617 (uri (rubygems-uri "bio-kseq" version))
7620 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
7621 (build-system ruby-build-system)
7623 `(#:test-target "spec"))
7625 `(("bundler" ,bundler)
7626 ("ruby-rspec" ,ruby-rspec)
7627 ("ruby-rake-compiler" ,ruby-rake-compiler)))
7630 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
7632 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
7633 FASTQ parsing code. It provides a fast iterator over sequences and their
7635 (home-page "https://github.com/gusevfe/bio-kseq")
7636 (license license:expat)))
7638 (define-public bio-locus
7645 (uri (rubygems-uri "bio-locus" version))
7648 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
7649 (build-system ruby-build-system)
7651 `(("ruby-rspec" ,ruby-rspec)))
7652 (synopsis "Tool for fast querying of genome locations")
7654 "Bio-locus is a tabix-like tool for fast querying of genome
7655 locations. Many file formats in bioinformatics contain records that
7656 start with a chromosome name and a position for a SNP, or a start-end
7657 position for indels. Bio-locus allows users to store this chr+pos or
7658 chr+pos+alt information in a database.")
7659 (home-page "https://github.com/pjotrp/bio-locus")
7660 (license license:expat)))
7662 (define-public bio-blastxmlparser
7664 (name "bio-blastxmlparser")
7668 (uri (rubygems-uri "bio-blastxmlparser" version))
7671 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
7672 (build-system ruby-build-system)
7674 `(("ruby-bio-logger" ,ruby-bio-logger)
7675 ("ruby-nokogiri" ,ruby-nokogiri)))
7677 `(("ruby-rspec" ,ruby-rspec)))
7678 (synopsis "Fast big data BLAST XML parser and library")
7680 "Very fast parallel big-data BLAST XML file parser which can be used as
7681 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
7682 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
7683 (home-page "https://github.com/pjotrp/blastxmlparser")
7684 (license license:expat)))
7686 (define-public bioruby
7693 (uri (rubygems-uri "bio" version))
7696 "1d56amdsjv1mag7m6gv2w0xij8hqx1v5xbdjsix8sp3yp36m7938"))))
7697 (build-system ruby-build-system)
7699 `(("ruby-libxml" ,ruby-libxml)))
7701 `(("which" ,which))) ; required for test phase
7704 (modify-phases %standard-phases
7705 (add-before 'build 'patch-test-command
7707 (substitute* '("test/functional/bio/test_command.rb")
7708 (("/bin/sh") (which "sh")))
7709 (substitute* '("test/functional/bio/test_command.rb")
7710 (("/bin/ls") (which "ls")))
7711 (substitute* '("test/functional/bio/test_command.rb")
7712 (("which") (which "which")))
7713 (substitute* '("test/functional/bio/test_command.rb",
7714 "test/data/command/echoarg2.sh")
7715 (("/bin/echo") (which "echo")))
7717 (synopsis "Ruby library, shell and utilities for bioinformatics")
7718 (description "BioRuby comes with a comprehensive set of Ruby development
7719 tools and libraries for bioinformatics and molecular biology. BioRuby has
7720 components for sequence analysis, pathway analysis, protein modelling and
7721 phylogenetic analysis; it supports many widely used data formats and provides
7722 easy access to databases, external programs and public web services, including
7723 BLAST, KEGG, GenBank, MEDLINE and GO.")
7724 (home-page "http://bioruby.org/")
7725 ;; Code is released under Ruby license, except for setup
7726 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
7727 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
7729 (define-public r-biocviews
7731 (name "r-biocviews")
7735 (uri (bioconductor-uri "biocViews" version))
7738 "0f0aa51h9x8n114zz6q6iw45d78i9wzl4ycbpiy0bdn23167pd84"))))
7740 `((upstream-name . "biocViews")))
7741 (build-system r-build-system)
7743 `(("r-biobase" ,r-biobase)
7744 ("r-biocmanager" ,r-biocmanager)
7745 ("r-graph" ,r-graph)
7747 ("r-rcurl" ,r-rcurl)
7749 ("r-runit" ,r-runit)))
7750 (home-page "https://bioconductor.org/packages/biocViews")
7751 (synopsis "Bioconductor package categorization helper")
7752 (description "The purpose of biocViews is to create HTML pages that
7753 categorize packages in a Bioconductor package repository according to keywords,
7754 also known as views, in a controlled vocabulary.")
7755 (license license:artistic2.0)))
7757 (define-public r-biocstyle
7759 (name "r-biocstyle")
7763 (uri (bioconductor-uri "BiocStyle" version))
7766 "1hfdvld0n9py45mxm05kbb0sq0s9p8yky3s6jb02gzhlxkk3q4fs"))))
7768 `((upstream-name . "BiocStyle")))
7769 (build-system r-build-system)
7771 `(("r-biocmanager" ,r-biocmanager)
7772 ("r-bookdown" ,r-bookdown)
7773 ("r-knitr" ,r-knitr)
7774 ("r-rmarkdown" ,r-rmarkdown)
7775 ("r-yaml" ,r-yaml)))
7777 `(("r-knitr" ,r-knitr)))
7778 (home-page "https://bioconductor.org/packages/BiocStyle")
7779 (synopsis "Bioconductor formatting styles")
7780 (description "This package provides standard formatting styles for
7781 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
7783 (license license:artistic2.0)))
7785 (define-public r-bioccheck
7787 (name "r-bioccheck")
7791 (uri (bioconductor-uri "BiocCheck" version))
7794 "1hyncn9zqj432da95k86rm5b28nbwrvzm52jbhisifkxj1j43cib"))))
7796 `((upstream-name . "BiocCheck")))
7797 (build-system r-build-system)
7800 (modify-phases %standard-phases
7801 ;; This package can be used by calling BiocCheck(<package>) from
7802 ;; within R, or by running R CMD BiocCheck <package>. This phase
7803 ;; makes sure the latter works. For this to work, the BiocCheck
7804 ;; script must be somewhere on the PATH (not the R bin directory).
7805 (add-after 'install 'install-bioccheck-subcommand
7806 (lambda* (#:key outputs #:allow-other-keys)
7807 (let* ((out (assoc-ref outputs "out"))
7808 (dest-dir (string-append out "/bin"))
7810 (string-append out "/site-library/BiocCheck/script/")))
7812 (symlink (string-append script-dir "/checkBadDeps.R")
7813 (string-append dest-dir "/checkBadDeps.R"))
7814 (symlink (string-append script-dir "/BiocCheck")
7815 (string-append dest-dir "/BiocCheck")))
7818 `(("r-codetools" ,r-codetools)
7819 ("r-graph" ,r-graph)
7821 ("r-knitr" ,r-knitr)
7822 ("r-optparse" ,r-optparse)
7823 ("r-biocmanager" ,r-biocmanager)
7824 ("r-biocviews" ,r-biocviews)
7825 ("r-stringdist" ,r-stringdist)))
7827 `(("r-knitr" ,r-knitr)))
7828 (home-page "https://bioconductor.org/packages/BiocCheck")
7829 (synopsis "Executes Bioconductor-specific package checks")
7830 (description "This package contains tools to perform additional quality
7831 checks on R packages that are to be submitted to the Bioconductor repository.")
7832 (license license:artistic2.0)))
7834 (define-public r-s4vectors
7836 (name "r-s4vectors")
7840 (uri (bioconductor-uri "S4Vectors" version))
7843 "0rfn46g2mfda01s75vpcfn5jc7xkp0jrl5v79gyd40jm37p4j1zv"))))
7845 `((upstream-name . "S4Vectors")))
7846 (build-system r-build-system)
7848 `(("r-biocgenerics" ,r-biocgenerics)))
7849 (home-page "https://bioconductor.org/packages/S4Vectors")
7850 (synopsis "S4 implementation of vectors and lists")
7852 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7853 classes and a set of generic functions that extend the semantic of ordinary
7854 vectors and lists in R. Package developers can easily implement vector-like
7855 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7856 In addition, a few low-level concrete subclasses of general interest (e.g.
7857 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7858 S4Vectors package itself.")
7859 (license license:artistic2.0)))
7861 (define-public r-iranges
7867 (uri (bioconductor-uri "IRanges" version))
7870 "1lfc8xz45v63y3q40im00i944hi0p9idwhx50w3nzkwdpk79315b"))))
7872 `((upstream-name . "IRanges")))
7873 (build-system r-build-system)
7875 `(("r-biocgenerics" ,r-biocgenerics)
7876 ("r-s4vectors" ,r-s4vectors)))
7877 (home-page "https://bioconductor.org/packages/IRanges")
7878 (synopsis "Infrastructure for manipulating intervals on sequences")
7880 "This package provides efficient low-level and highly reusable S4 classes
7881 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7882 generally, data that can be organized sequentially (formally defined as
7883 @code{Vector} objects), as well as views on these @code{Vector} objects.
7884 Efficient list-like classes are also provided for storing big collections of
7885 instances of the basic classes. All classes in the package use consistent
7886 naming and share the same rich and consistent \"Vector API\" as much as
7888 (license license:artistic2.0)))
7890 (define-public r-genomeinfodbdata
7892 (name "r-genomeinfodbdata")
7896 ;; We cannot use bioconductor-uri here because this tarball is
7897 ;; located under "data/annotation/" instead of "bioc/".
7898 (uri (string-append "https://bioconductor.org/packages/release/"
7899 "data/annotation/src/contrib/GenomeInfoDbData_"
7903 "0di6nlqpsyqf693k2na65ayqldih563x3zfrczpqc5q2hl5kg35c"))))
7905 `((upstream-name . "GenomeInfoDbData")))
7906 (build-system r-build-system)
7907 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7908 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7909 (description "This package contains data for mapping between NCBI taxonomy
7910 ID and species. It is used by functions in the GenomeInfoDb package.")
7911 (license license:artistic2.0)))
7913 (define-public r-genomeinfodb
7915 (name "r-genomeinfodb")
7919 (uri (bioconductor-uri "GenomeInfoDb" version))
7922 "1xfhz7gmccijy2z015w07lh04g0ijh7zi6k7q6m4lripgban93g9"))))
7924 `((upstream-name . "GenomeInfoDb")))
7925 (build-system r-build-system)
7927 `(("r-biocgenerics" ,r-biocgenerics)
7928 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7929 ("r-iranges" ,r-iranges)
7930 ("r-rcurl" ,r-rcurl)
7931 ("r-s4vectors" ,r-s4vectors)))
7933 `(("r-knitr" ,r-knitr)))
7934 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7935 (synopsis "Utilities for manipulating chromosome identifiers")
7937 "This package contains data and functions that define and allow
7938 translation between different chromosome sequence naming conventions (e.g.,
7939 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7940 names in their natural, rather than lexicographic, order.")
7941 (license license:artistic2.0)))
7943 (define-public r-edger
7949 (uri (bioconductor-uri "edgeR" version))
7952 "0dkjd6li270icy1x5qbzpakk9bx712mdm5k32lrr3yrggq92jhjg"))))
7953 (properties `((upstream-name . "edgeR")))
7954 (build-system r-build-system)
7956 `(("r-limma" ,r-limma)
7957 ("r-locfit" ,r-locfit)
7959 ("r-statmod" ,r-statmod))) ;for estimateDisp
7960 (home-page "http://bioinf.wehi.edu.au/edgeR")
7961 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7962 (description "This package can do differential expression analysis of
7963 RNA-seq expression profiles with biological replication. It implements a range
7964 of statistical methodology based on the negative binomial distributions,
7965 including empirical Bayes estimation, exact tests, generalized linear models
7966 and quasi-likelihood tests. It be applied to differential signal analysis of
7967 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7969 (license license:gpl2+)))
7971 (define-public r-variantannotation
7973 (name "r-variantannotation")
7977 (uri (bioconductor-uri "VariantAnnotation" version))
7980 "1sl0l6v05lfglj281nszma0h5k234md7rn2pdah8vs2d4iq3kimw"))))
7982 `((upstream-name . "VariantAnnotation")))
7986 `(("r-annotationdbi" ,r-annotationdbi)
7987 ("r-biobase" ,r-biobase)
7988 ("r-biocgenerics" ,r-biocgenerics)
7989 ("r-biostrings" ,r-biostrings)
7990 ("r-bsgenome" ,r-bsgenome)
7992 ("r-genomeinfodb" ,r-genomeinfodb)
7993 ("r-genomicfeatures" ,r-genomicfeatures)
7994 ("r-genomicranges" ,r-genomicranges)
7995 ("r-iranges" ,r-iranges)
7996 ("r-matrixgenerics" ,r-matrixgenerics)
7997 ("r-summarizedexperiment" ,r-summarizedexperiment)
7998 ("r-rhtslib" ,r-rhtslib)
7999 ("r-rsamtools" ,r-rsamtools)
8000 ("r-rtracklayer" ,r-rtracklayer)
8001 ("r-s4vectors" ,r-s4vectors)
8002 ("r-xvector" ,r-xvector)
8003 ("r-zlibbioc" ,r-zlibbioc)))
8004 (build-system r-build-system)
8005 (home-page "https://bioconductor.org/packages/VariantAnnotation")
8006 (synopsis "Package for annotation of genetic variants")
8007 (description "This R package can annotate variants, compute amino acid
8008 coding changes and predict coding outcomes.")
8009 (license license:artistic2.0)))
8011 (define-public r-limma
8017 (uri (bioconductor-uri "limma" version))
8020 "1xxv493q1kip9bjfv7v7k5dnq7hz7gvl80i983v4mvwavhgnbxfz"))))
8021 (build-system r-build-system)
8022 (home-page "http://bioinf.wehi.edu.au/limma")
8023 (synopsis "Package for linear models for microarray and RNA-seq data")
8024 (description "This package can be used for the analysis of gene expression
8025 studies, especially the use of linear models for analysing designed experiments
8026 and the assessment of differential expression. The analysis methods apply to
8027 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
8028 (license license:gpl2+)))
8030 (define-public r-xvector
8036 (uri (bioconductor-uri "XVector" version))
8039 "1pqljikg4f6jb7wgm5537zwgq5b013nyz1agjrwfq2cljb0ym6lq"))))
8041 `((upstream-name . "XVector")))
8042 (build-system r-build-system)
8045 (modify-phases %standard-phases
8046 (add-after 'unpack 'use-system-zlib
8048 (substitute* "DESCRIPTION"
8049 (("zlibbioc, ") ""))
8050 (substitute* "NAMESPACE"
8051 (("import\\(zlibbioc\\)") ""))
8056 `(("r-biocgenerics" ,r-biocgenerics)
8057 ("r-iranges" ,r-iranges)
8058 ("r-s4vectors" ,r-s4vectors)))
8059 (home-page "https://bioconductor.org/packages/XVector")
8060 (synopsis "Representation and manpulation of external sequences")
8062 "This package provides memory efficient S4 classes for storing sequences
8063 \"externally\" (behind an R external pointer, or on disk).")
8064 (license license:artistic2.0)))
8066 (define-public r-genomicranges
8068 (name "r-genomicranges")
8072 (uri (bioconductor-uri "GenomicRanges" version))
8075 "0j4py5g6pdj35xhlaqhxxhg55j9l4mcdk3yck4dgyavv5f2dh24i"))))
8077 `((upstream-name . "GenomicRanges")))
8078 (build-system r-build-system)
8080 `(("r-biocgenerics" ,r-biocgenerics)
8081 ("r-genomeinfodb" ,r-genomeinfodb)
8082 ("r-iranges" ,r-iranges)
8083 ("r-s4vectors" ,r-s4vectors)
8084 ("r-xvector" ,r-xvector)))
8086 `(("r-knitr" ,r-knitr)))
8087 (home-page "https://bioconductor.org/packages/GenomicRanges")
8088 (synopsis "Representation and manipulation of genomic intervals")
8090 "This package provides tools to efficiently represent and manipulate
8091 genomic annotations and alignments is playing a central role when it comes to
8092 analyzing high-throughput sequencing data (a.k.a. NGS data). The
8093 GenomicRanges package defines general purpose containers for storing and
8094 manipulating genomic intervals and variables defined along a genome.")
8095 (license license:artistic2.0)))
8097 (define-public r-biobase
8103 (uri (bioconductor-uri "Biobase" version))
8106 "11kgc4flywlm3i18603558l8ksv91c24vkc5fnnbcd375i2dhhd4"))))
8108 `((upstream-name . "Biobase")))
8109 (build-system r-build-system)
8111 `(("r-biocgenerics" ,r-biocgenerics)))
8112 (home-page "https://bioconductor.org/packages/Biobase")
8113 (synopsis "Base functions for Bioconductor")
8115 "This package provides functions that are needed by many other packages
8116 on Bioconductor or which replace R functions.")
8117 (license license:artistic2.0)))
8119 (define-public r-annotationdbi
8121 (name "r-annotationdbi")
8125 (uri (bioconductor-uri "AnnotationDbi" version))
8128 "0zqxgh3nx6y8ry12s2vss2f4axz5vpqxha1y4ifhhcx4zhpzsglr"))))
8130 `((upstream-name . "AnnotationDbi")))
8131 (build-system r-build-system)
8133 `(("r-biobase" ,r-biobase)
8134 ("r-biocgenerics" ,r-biocgenerics)
8136 ("r-iranges" ,r-iranges)
8137 ("r-rsqlite" ,r-rsqlite)
8138 ("r-s4vectors" ,r-s4vectors)))
8140 `(("r-knitr" ,r-knitr)))
8141 (home-page "https://bioconductor.org/packages/AnnotationDbi")
8142 (synopsis "Annotation database interface")
8144 "This package provides user interface and database connection code for
8145 annotation data packages using SQLite data storage.")
8146 (license license:artistic2.0)))
8148 (define-public r-biomart
8154 (uri (bioconductor-uri "biomaRt" version))
8157 "1zpdm8nw1d0m31pdmzw1dccbd6iczfhiklhm4d325zkzf3jrkvxf"))))
8159 `((upstream-name . "biomaRt")))
8160 (build-system r-build-system)
8162 `(("r-annotationdbi" ,r-annotationdbi)
8163 ("r-biocfilecache" ,r-biocfilecache)
8165 ("r-openssl" ,r-openssl)
8166 ("r-progress" ,r-progress)
8167 ("r-rappdirs" ,r-rappdirs)
8168 ("r-stringr" ,r-stringr)
8170 ("r-xml2" ,r-xml2)))
8172 `(("r-knitr" ,r-knitr)))
8173 (home-page "https://bioconductor.org/packages/biomaRt")
8174 (synopsis "Interface to BioMart databases")
8176 "biomaRt provides an interface to a growing collection of databases
8177 implementing the @url{BioMart software suite, http://www.biomart.org}. The
8178 package enables retrieval of large amounts of data in a uniform way without
8179 the need to know the underlying database schemas or write complex SQL queries.
8180 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
8181 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
8182 users direct access to a diverse set of data and enable a wide range of
8183 powerful online queries from gene annotation to database mining.")
8184 (license license:artistic2.0)))
8186 (define-public r-biocparallel
8188 (name "r-biocparallel")
8192 (uri (bioconductor-uri "BiocParallel" version))
8195 "1iryicvmcagcrj29kp49mqhiq2kn72j4idj380hi9illmdrg9ism"))))
8197 `((upstream-name . "BiocParallel")))
8198 (build-system r-build-system)
8200 `(("r-futile-logger" ,r-futile-logger)
8204 `(("r-knitr" ,r-knitr)))
8205 (home-page "https://bioconductor.org/packages/BiocParallel")
8206 (synopsis "Bioconductor facilities for parallel evaluation")
8208 "This package provides modified versions and novel implementation of
8209 functions for parallel evaluation, tailored to use with Bioconductor
8211 (license (list license:gpl2+ license:gpl3+))))
8213 (define-public r-biostrings
8215 (name "r-biostrings")
8219 (uri (bioconductor-uri "Biostrings" version))
8222 "1rbqhs73mhfr1gi0rx28jiyan7i3hb45ai3jpl1656fnrhgjfxq5"))))
8224 `((upstream-name . "Biostrings")))
8225 (build-system r-build-system)
8227 `(("r-biocgenerics" ,r-biocgenerics)
8228 ("r-crayon" ,r-crayon)
8229 ("r-iranges" ,r-iranges)
8230 ("r-s4vectors" ,r-s4vectors)
8231 ("r-xvector" ,r-xvector)))
8232 (home-page "https://bioconductor.org/packages/Biostrings")
8233 (synopsis "String objects and algorithms for biological sequences")
8235 "This package provides memory efficient string containers, string
8236 matching algorithms, and other utilities, for fast manipulation of large
8237 biological sequences or sets of sequences.")
8238 (license license:artistic2.0)))
8240 (define-public r-rsamtools
8242 (name "r-rsamtools")
8246 (uri (bioconductor-uri "Rsamtools" version))
8249 "040pggkwglc6wy90qnc7xcdnaj0v3iqlykvvsl74241409qly554"))))
8251 `((upstream-name . "Rsamtools")))
8252 (build-system r-build-system)
8255 (modify-phases %standard-phases
8256 (add-after 'unpack 'use-system-zlib
8258 (substitute* "DESCRIPTION"
8259 (("zlibbioc, ") ""))
8260 (substitute* "NAMESPACE"
8261 (("import\\(zlibbioc\\)") ""))
8266 `(("r-biocgenerics" ,r-biocgenerics)
8267 ("r-biocparallel" ,r-biocparallel)
8268 ("r-biostrings" ,r-biostrings)
8269 ("r-bitops" ,r-bitops)
8270 ("r-genomeinfodb" ,r-genomeinfodb)
8271 ("r-genomicranges" ,r-genomicranges)
8272 ("r-iranges" ,r-iranges)
8273 ("r-rhtslib" ,r-rhtslib)
8274 ("r-s4vectors" ,r-s4vectors)
8275 ("r-xvector" ,r-xvector)))
8276 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
8277 (synopsis "Interface to samtools, bcftools, and tabix")
8279 "This package provides an interface to the @code{samtools},
8280 @code{bcftools}, and @code{tabix} utilities for manipulating SAM (Sequence
8281 Alignment / Map), FASTA, binary variant call (BCF) and compressed indexed
8282 tab-delimited (tabix) files.")
8283 (license license:expat)))
8285 (define-public r-delayedarray
8287 (name "r-delayedarray")
8291 (uri (bioconductor-uri "DelayedArray" version))
8294 "1564wnradxw15nsnv6w2wd3xngcs3xa1mlibbq3hygi5fcx4fk3g"))))
8296 `((upstream-name . "DelayedArray")))
8297 (build-system r-build-system)
8299 `(("r-biocgenerics" ,r-biocgenerics)
8300 ("r-s4vectors" ,r-s4vectors)
8301 ("r-iranges" ,r-iranges)
8302 ("r-matrix" ,r-matrix)
8303 ("r-matrixgenerics" ,r-matrixgenerics)))
8305 `(("r-knitr" ,r-knitr)))
8306 (home-page "https://bioconductor.org/packages/DelayedArray")
8307 (synopsis "Delayed operations on array-like objects")
8309 "Wrapping an array-like object (typically an on-disk object) in a
8310 @code{DelayedArray} object allows one to perform common array operations on it
8311 without loading the object in memory. In order to reduce memory usage and
8312 optimize performance, operations on the object are either delayed or executed
8313 using a block processing mechanism. Note that this also works on in-memory
8314 array-like objects like @code{DataFrame} objects (typically with Rle columns),
8315 @code{Matrix} objects, and ordinary arrays and data frames.")
8316 (license license:artistic2.0)))
8318 (define-public r-summarizedexperiment
8320 (name "r-summarizedexperiment")
8324 (uri (bioconductor-uri "SummarizedExperiment" version))
8327 "04x6d4mcsnvz6glkmf6k2cv3fs8zk03i9rvv0ahpl793n8l411ps"))))
8329 `((upstream-name . "SummarizedExperiment")))
8330 (build-system r-build-system)
8332 `(("r-biobase" ,r-biobase)
8333 ("r-biocgenerics" ,r-biocgenerics)
8334 ("r-delayedarray" ,r-delayedarray)
8335 ("r-genomeinfodb" ,r-genomeinfodb)
8336 ("r-genomicranges" ,r-genomicranges)
8337 ("r-iranges" ,r-iranges)
8338 ("r-matrix" ,r-matrix)
8339 ("r-matrixgenerics" ,r-matrixgenerics)
8340 ("r-s4vectors" ,r-s4vectors)))
8342 `(("r-knitr" ,r-knitr)))
8343 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
8344 (synopsis "Container for representing genomic ranges by sample")
8346 "The SummarizedExperiment container contains one or more assays, each
8347 represented by a matrix-like object of numeric or other mode. The rows
8348 typically represent genomic ranges of interest and the columns represent
8350 (license license:artistic2.0)))
8352 (define-public r-genomicalignments
8354 (name "r-genomicalignments")
8358 (uri (bioconductor-uri "GenomicAlignments" version))
8361 "1q95px6s6snsax4ax955zzpdlrwp5liwf70wqq0lrk9mp6lq0hbr"))))
8363 `((upstream-name . "GenomicAlignments")))
8364 (build-system r-build-system)
8366 `(("r-biocgenerics" ,r-biocgenerics)
8367 ("r-biocparallel" ,r-biocparallel)
8368 ("r-biostrings" ,r-biostrings)
8369 ("r-genomeinfodb" ,r-genomeinfodb)
8370 ("r-genomicranges" ,r-genomicranges)
8371 ("r-iranges" ,r-iranges)
8372 ("r-rsamtools" ,r-rsamtools)
8373 ("r-s4vectors" ,r-s4vectors)
8374 ("r-summarizedexperiment" ,r-summarizedexperiment)))
8375 (home-page "https://bioconductor.org/packages/GenomicAlignments")
8376 (synopsis "Representation and manipulation of short genomic alignments")
8378 "This package provides efficient containers for storing and manipulating
8379 short genomic alignments (typically obtained by aligning short reads to a
8380 reference genome). This includes read counting, computing the coverage,
8381 junction detection, and working with the nucleotide content of the
8383 (license license:artistic2.0)))
8385 (define-public r-rtracklayer
8387 (name "r-rtracklayer")
8391 (uri (bioconductor-uri "rtracklayer" version))
8394 "12zimhpdzjyzd81wrzz5hdbzvlgzcs22x1nnaf2jq4cba3ch5px8"))))
8395 (build-system r-build-system)
8398 (modify-phases %standard-phases
8399 (add-after 'unpack 'use-system-zlib
8401 (substitute* "DESCRIPTION"
8402 ((" zlibbioc,") ""))
8403 (substitute* "NAMESPACE"
8404 (("import\\(zlibbioc\\)") ""))
8407 `(("pkg-config" ,pkg-config)))
8411 `(("r-biocgenerics" ,r-biocgenerics)
8412 ("r-biostrings" ,r-biostrings)
8413 ("r-genomeinfodb" ,r-genomeinfodb)
8414 ("r-genomicalignments" ,r-genomicalignments)
8415 ("r-genomicranges" ,r-genomicranges)
8416 ("r-iranges" ,r-iranges)
8417 ("r-rcurl" ,r-rcurl)
8418 ("r-rsamtools" ,r-rsamtools)
8419 ("r-s4vectors" ,r-s4vectors)
8421 ("r-xvector" ,r-xvector)
8422 ("r-zlibbioc" ,r-zlibbioc)))
8423 (home-page "https://bioconductor.org/packages/rtracklayer")
8424 (synopsis "R interface to genome browsers and their annotation tracks")
8426 "rtracklayer is an extensible framework for interacting with multiple
8427 genome browsers (currently UCSC built-in) and manipulating annotation tracks
8428 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
8429 built-in). The user may export/import tracks to/from the supported browsers,
8430 as well as query and modify the browser state, such as the current viewport.")
8431 (license license:artistic2.0)))
8433 (define-public r-genomicfeatures
8435 (name "r-genomicfeatures")
8439 (uri (bioconductor-uri "GenomicFeatures" version))
8442 "17dyd9hcw6pw16y353dh55wfhxmkxka99lbsxsp9xyrhffwrxi0s"))))
8444 `((upstream-name . "GenomicFeatures")))
8445 (build-system r-build-system)
8447 `(("r-annotationdbi" ,r-annotationdbi)
8448 ("r-biobase" ,r-biobase)
8449 ("r-biocgenerics" ,r-biocgenerics)
8450 ("r-biomart" ,r-biomart)
8451 ("r-biostrings" ,r-biostrings)
8453 ("r-genomeinfodb" ,r-genomeinfodb)
8454 ("r-genomicranges" ,r-genomicranges)
8455 ("r-iranges" ,r-iranges)
8456 ("r-rcurl" ,r-rcurl)
8457 ("r-rsqlite" ,r-rsqlite)
8458 ("r-rtracklayer" ,r-rtracklayer)
8459 ("r-s4vectors" ,r-s4vectors)
8460 ("r-xvector" ,r-xvector)))
8462 `(("r-knitr" ,r-knitr)))
8463 (home-page "https://bioconductor.org/packages/GenomicFeatures")
8464 (synopsis "Tools for working with transcript centric annotations")
8466 "This package provides a set of tools and methods for making and
8467 manipulating transcript centric annotations. With these tools the user can
8468 easily download the genomic locations of the transcripts, exons and cds of a
8469 given organism, from either the UCSC Genome Browser or a BioMart
8470 database (more sources will be supported in the future). This information is
8471 then stored in a local database that keeps track of the relationship between
8472 transcripts, exons, cds and genes. Flexible methods are provided for
8473 extracting the desired features in a convenient format.")
8474 (license license:artistic2.0)))
8476 (define-public r-go-db
8482 (uri (string-append "https://www.bioconductor.org/packages/"
8483 "release/data/annotation/src/contrib/GO.db_"
8487 "0i3wcf5h3n0dawzc1hy0kv74f06j80c47n4p3g3fmrcxlhi3jpa5"))))
8489 `((upstream-name . "GO.db")))
8490 (build-system r-build-system)
8492 `(("r-annotationdbi" ,r-annotationdbi)))
8493 (home-page "https://bioconductor.org/packages/GO.db")
8494 (synopsis "Annotation maps describing the entire Gene Ontology")
8496 "The purpose of this GO.db annotation package is to provide detailed
8497 information about the latest version of the Gene Ontologies.")
8498 (license license:artistic2.0)))
8500 (define-public r-topgo
8506 (uri (bioconductor-uri "topGO" version))
8509 "0vr3l9gvd3dhy446k3fkj6rm7z1abxi56rbnrs64297yzxaz1ngl"))))
8511 `((upstream-name . "topGO")))
8512 (build-system r-build-system)
8514 `(("r-annotationdbi" ,r-annotationdbi)
8516 ("r-biobase" ,r-biobase)
8517 ("r-biocgenerics" ,r-biocgenerics)
8518 ("r-go-db" ,r-go-db)
8519 ("r-graph" ,r-graph)
8520 ("r-lattice" ,r-lattice)
8521 ("r-matrixstats" ,r-matrixstats)
8522 ("r-sparsem" ,r-sparsem)))
8523 (home-page "https://bioconductor.org/packages/topGO")
8524 (synopsis "Enrichment analysis for gene ontology")
8526 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
8527 terms while accounting for the topology of the GO graph. Different test
8528 statistics and different methods for eliminating local similarities and
8529 dependencies between GO terms can be implemented and applied.")
8530 ;; Any version of the LGPL applies.
8531 (license license:lgpl2.1+)))
8533 (define-public r-bsgenome
8539 (uri (bioconductor-uri "BSgenome" version))
8542 "1gbvmxr6r57smgvhqgwspbcnwyk4hsfkxkpzzcs6470q03zfb4wq"))))
8544 `((upstream-name . "BSgenome")))
8545 (build-system r-build-system)
8547 `(("r-biocgenerics" ,r-biocgenerics)
8548 ("r-biostrings" ,r-biostrings)
8549 ("r-genomeinfodb" ,r-genomeinfodb)
8550 ("r-genomicranges" ,r-genomicranges)
8551 ("r-iranges" ,r-iranges)
8552 ("r-matrixstats" ,r-matrixstats)
8553 ("r-rsamtools" ,r-rsamtools)
8554 ("r-rtracklayer" ,r-rtracklayer)
8555 ("r-s4vectors" ,r-s4vectors)
8556 ("r-xvector" ,r-xvector)))
8557 (home-page "https://bioconductor.org/packages/BSgenome")
8558 (synopsis "Infrastructure for Biostrings-based genome data packages")
8560 "This package provides infrastructure shared by all Biostrings-based
8561 genome data packages and support for efficient SNP representation.")
8562 (license license:artistic2.0)))
8564 (define-public r-impute
8570 (uri (bioconductor-uri "impute" version))
8573 "1pnjasw9i19nmxwjzrd9jbln31yc5jilfvwk414ya5zbqfsazvxa"))))
8575 `(("gfortran" ,gfortran)))
8576 (build-system r-build-system)
8577 (home-page "https://bioconductor.org/packages/impute")
8578 (synopsis "Imputation for microarray data")
8580 "This package provides a function to impute missing gene expression
8581 microarray data, using nearest neighbor averaging.")
8582 (license license:gpl2+)))
8584 (define-public r-seqpattern
8586 (name "r-seqpattern")
8590 (uri (bioconductor-uri "seqPattern" version))
8593 "0j68n6fwycxjpl2va5fw7ajb123n758s2pq997d76dysxghmrlzq"))))
8595 `((upstream-name . "seqPattern")))
8596 (build-system r-build-system)
8598 `(("r-biostrings" ,r-biostrings)
8599 ("r-genomicranges" ,r-genomicranges)
8600 ("r-iranges" ,r-iranges)
8601 ("r-kernsmooth" ,r-kernsmooth)
8602 ("r-plotrix" ,r-plotrix)))
8603 (home-page "https://bioconductor.org/packages/seqPattern")
8604 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
8606 "This package provides tools to visualize oligonucleotide patterns and
8607 sequence motif occurrences across a large set of sequences centred at a common
8608 reference point and sorted by a user defined feature.")
8609 (license license:gpl3+)))
8611 (define-public r-genomation
8613 (name "r-genomation")
8617 (uri (bioconductor-uri "genomation" version))
8620 "1ana06irlpdgnmk8mb329nws9sm8n6max4qargf1xdcdf3rnk45g"))))
8621 (build-system r-build-system)
8623 `(("r-biostrings" ,r-biostrings)
8624 ("r-bsgenome" ,r-bsgenome)
8625 ("r-data-table" ,r-data-table)
8626 ("r-genomeinfodb" ,r-genomeinfodb)
8627 ("r-genomicalignments" ,r-genomicalignments)
8628 ("r-genomicranges" ,r-genomicranges)
8629 ("r-ggplot2" ,r-ggplot2)
8630 ("r-gridbase" ,r-gridbase)
8631 ("r-impute" ,r-impute)
8632 ("r-iranges" ,r-iranges)
8633 ("r-matrixstats" ,r-matrixstats)
8634 ("r-plotrix" ,r-plotrix)
8637 ("r-readr" ,r-readr)
8638 ("r-reshape2" ,r-reshape2)
8639 ("r-rsamtools" ,r-rsamtools)
8640 ("r-rtracklayer" ,r-rtracklayer)
8641 ("r-runit" ,r-runit)
8642 ("r-s4vectors" ,r-s4vectors)
8643 ("r-seqpattern" ,r-seqpattern)))
8645 `(("r-knitr" ,r-knitr)))
8646 (home-page "https://bioinformatics.mdc-berlin.de/genomation/")
8647 (synopsis "Summary, annotation and visualization of genomic data")
8649 "This package provides a package for summary and annotation of genomic
8650 intervals. Users can visualize and quantify genomic intervals over
8651 pre-defined functional regions, such as promoters, exons, introns, etc. The
8652 genomic intervals represent regions with a defined chromosome position, which
8653 may be associated with a score, such as aligned reads from HT-seq experiments,
8654 TF binding sites, methylation scores, etc. The package can use any tabular
8655 genomic feature data as long as it has minimal information on the locations of
8656 genomic intervals. In addition, it can use BAM or BigWig files as input.")
8657 (license license:artistic2.0)))
8659 (define-public r-genomationdata
8661 (name "r-genomationdata")
8665 ;; We cannot use bioconductor-uri here because this tarball is
8666 ;; located under "data/annotation/" instead of "bioc/".
8667 (uri (string-append "https://bioconductor.org/packages/"
8668 "release/data/experiment/src/contrib/"
8669 "genomationData_" version ".tar.gz"))
8672 "10xyb8akjrhmak2i0mnv1agny2ipy364q9nlibyplpzc7vdb6bw7"))))
8673 (build-system r-build-system)
8674 ;; As this package provides little more than large data files, it doesn't
8675 ;; make sense to build substitutes.
8676 (arguments `(#:substitutable? #f))
8678 `(("r-knitr" ,r-knitr)))
8679 (home-page "https://bioinformatics.mdc-berlin.de/genomation/")
8680 (synopsis "Experimental data for use with the genomation package")
8682 "This package contains experimental genetic data for use with the
8683 genomation package. Included are Chip Seq, Methylation and Cage data,
8684 downloaded from Encode.")
8685 (license license:gpl3+)))
8687 (define-public r-seqlogo
8694 (uri (bioconductor-uri "seqLogo" version))
8697 "02rpzjjfg5chlwwfbvv72cm78cg2vfmdwzars0cin9hz1hd7rnq1"))))
8698 (properties `((upstream-name . "seqLogo")))
8699 (build-system r-build-system)
8701 `(("r-knitr" ,r-knitr)))
8702 (home-page "https://bioconductor.org/packages/seqLogo")
8703 (synopsis "Sequence logos for DNA sequence alignments")
8705 "seqLogo takes the position weight matrix of a DNA sequence motif and
8706 plots the corresponding sequence logo as introduced by Schneider and
8708 (license license:lgpl2.0+)))
8710 (define-public r-motifrg
8717 (uri (bioconductor-uri "motifRG" version))
8720 "1ml6zyzlk8yjbnfhga2qnw8nl43rankvka0kc1yljxr2b66aqbhn"))))
8721 (properties `((upstream-name . "motifRG")))
8722 (build-system r-build-system)
8724 `(("r-biostrings" ,r-biostrings)
8725 ("r-bsgenome" ,r-bsgenome)
8726 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8727 ("r-iranges" ,r-iranges)
8728 ("r-seqlogo" ,r-seqlogo)
8729 ("r-xvector" ,r-xvector)))
8730 (home-page "https://bioconductor.org/packages/motifRG")
8731 (synopsis "Discover motifs in high throughput sequencing data")
8733 "This package provides tools for discriminative motif discovery in high
8734 throughput genetic sequencing data sets using regression methods.")
8735 (license license:artistic2.0)))
8737 (define-public r-zlibbioc
8743 (uri (bioconductor-uri "zlibbioc" version))
8746 "0m36ddss0znvm19dhnxcclxjhgjplw8ajk8v419h20ab8an6khxg"))))
8748 `((upstream-name . "zlibbioc")))
8749 (build-system r-build-system)
8750 (home-page "https://bioconductor.org/packages/zlibbioc")
8751 (synopsis "Provider for zlib-1.2.5 to R packages")
8752 (description "This package uses the source code of zlib-1.2.5 to create
8753 libraries for systems that do not have these available via other means.")
8754 (license license:artistic2.0)))
8756 (define-public r-r4rna
8763 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8767 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8768 (build-system r-build-system)
8770 `(("r-optparse" ,r-optparse)
8771 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8772 (home-page "https://www.e-rna.org/r-chie/index.cgi")
8773 (synopsis "Analysis framework for RNA secondary structure")
8775 "The R4RNA package aims to be a general framework for the analysis of RNA
8776 secondary structure and comparative analysis in R.")
8777 (license license:gpl3+)))
8779 (define-public r-rhtslib
8786 (uri (bioconductor-uri "Rhtslib" version))
8789 "18wag2jnpda6078xjkpfdvar1gkb2myhw83gg03l39sabh35qya4"))))
8790 (properties `((upstream-name . "Rhtslib")))
8791 (build-system r-build-system)
8792 ;; Without this a temporary directory ends up in the Rhtslib.so binary,
8793 ;; which makes R abort the build.
8794 (arguments '(#:configure-flags '("--no-staged-install")))
8797 ("r-zlibbioc" ,r-zlibbioc)))
8801 `(("pkg-config" ,pkg-config)
8802 ("r-knitr" ,r-knitr)))
8803 (home-page "https://github.com/nhayden/Rhtslib")
8804 (synopsis "High-throughput sequencing library as an R package")
8806 "This package provides the HTSlib C library for high-throughput
8807 nucleotide sequence analysis. The package is primarily useful to developers
8808 of other R packages who wish to make use of HTSlib.")
8809 (license license:lgpl2.0+)))
8811 (define-public r-bamsignals
8813 (name "r-bamsignals")
8818 (uri (bioconductor-uri "bamsignals" version))
8821 "0p3r9z9z5sfkd0b951cgr751k4z0yviyn1jfw9d4fcnyld7g1jxv"))))
8822 (build-system r-build-system)
8824 `(("r-biocgenerics" ,r-biocgenerics)
8825 ("r-genomicranges" ,r-genomicranges)
8826 ("r-iranges" ,r-iranges)
8828 ("r-rhtslib" ,r-rhtslib)
8829 ("r-zlibbioc" ,r-zlibbioc)))
8833 `(("r-knitr" ,r-knitr)))
8834 (home-page "https://bioconductor.org/packages/bamsignals")
8835 (synopsis "Extract read count signals from bam files")
8837 "This package efficiently obtains count vectors from indexed bam
8838 files. It counts the number of nucleotide sequence reads in given genomic
8839 ranges and it computes reads profiles and coverage profiles. It also handles
8841 (license license:gpl2+)))
8843 (define-public r-rcas
8849 (uri (bioconductor-uri "RCAS" version))
8852 "0vdxml618vqvf8xyh0zxs307p9zby0cj9dqyiiz625ilyq1hkw2m"))))
8853 (properties `((upstream-name . "RCAS")))
8854 (build-system r-build-system)
8856 `(("r-biocgenerics" ,r-biocgenerics)
8857 ("r-biostrings" ,r-biostrings)
8858 ("r-bsgenome" ,r-bsgenome)
8859 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8860 ("r-cowplot" ,r-cowplot)
8861 ("r-data-table" ,r-data-table)
8863 ("r-genomation" ,r-genomation)
8864 ("r-genomeinfodb" ,r-genomeinfodb)
8865 ("r-genomicfeatures" ,r-genomicfeatures)
8866 ("r-genomicranges" ,r-genomicranges)
8867 ("r-ggplot2" ,r-ggplot2)
8868 ("r-ggseqlogo" ,r-ggseqlogo)
8869 ("r-gprofiler2" ,r-gprofiler2)
8870 ("r-iranges" ,r-iranges)
8871 ("r-pbapply" ,r-pbapply)
8872 ("r-pheatmap" ,r-pheatmap)
8873 ("r-plotly" ,r-plotly)
8874 ("r-plotrix" ,r-plotrix)
8875 ("r-proxy" ,r-proxy)
8876 ("r-ranger" ,r-ranger)
8877 ("r-rsqlite" ,r-rsqlite)
8878 ("r-rtracklayer" ,r-rtracklayer)
8879 ("r-rmarkdown" ,r-rmarkdown)
8880 ("r-s4vectors" ,r-s4vectors)
8881 ("pandoc" ,pandoc)))
8883 `(("r-knitr" ,r-knitr)))
8884 (synopsis "RNA-centric annotation system")
8886 "RCAS aims to be a standalone RNA-centric annotation system that provides
8887 intuitive reports and publication-ready graphics. This package provides the R
8888 library implementing most of the pipeline's features.")
8889 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8890 (license license:artistic2.0)))
8892 (define-public rcas-web
8899 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8900 "releases/download/v" version
8901 "/rcas-web-" version ".tar.gz"))
8904 "0wq951aj45gqki1bickg876i993lmawkp8x24agg264br5x716db"))))
8905 (build-system gnu-build-system)
8908 (modify-phases %standard-phases
8909 (add-before 'configure 'find-RCAS
8910 ;; The configure script can't find non-1.3.x versions of RCAS because
8911 ;; its R expression ‘1.10.1 >= 1.3.4’ evaluates to false.
8913 (substitute* "configure"
8914 (("1\\.3\\.4") "0.0.0"))
8916 (add-after 'install 'wrap-executable
8917 (lambda* (#:key inputs outputs #:allow-other-keys)
8918 (let* ((out (assoc-ref outputs "out"))
8919 (json (assoc-ref inputs "guile-json"))
8920 (redis (assoc-ref inputs "guile-redis"))
8921 (path (string-append
8922 json "/share/guile/site/2.2:"
8923 redis "/share/guile/site/2.2")))
8924 (wrap-program (string-append out "/bin/rcas-web")
8925 `("GUILE_LOAD_PATH" ":" = (,path))
8926 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8927 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8930 `(("r-minimal" ,r-minimal)
8932 ("guile" ,guile-2.2)
8933 ("guile-json" ,guile-json-1)
8934 ("guile-redis" ,guile2.2-redis)))
8936 `(("pkg-config" ,pkg-config)))
8937 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8938 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8939 (description "This package provides a simple web interface for the
8940 @dfn{RNA-centric annotation system} (RCAS).")
8941 (license license:agpl3+)))
8943 (define-public r-mutationalpatterns
8945 (name "r-mutationalpatterns")
8950 (uri (bioconductor-uri "MutationalPatterns" version))
8953 "1988kjjgq8af0hj7chhpxi88717wwmzs9qgrwapjh0hm2hjwhn35"))))
8954 (build-system r-build-system)
8956 `(("r-knitr" ,r-knitr)))
8958 `(("r-biocgenerics" ,r-biocgenerics)
8959 ("r-biostrings" ,r-biostrings)
8960 ("r-bsgenome" ,r-bsgenome)
8961 ;; These two packages are suggested packages
8962 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8963 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8964 ("r-cowplot" ,r-cowplot)
8965 ("r-dplyr" ,r-dplyr)
8966 ("r-genomeinfodb" ,r-genomeinfodb)
8967 ("r-genomicranges" ,r-genomicranges)
8968 ("r-ggalluvial" ,r-ggalluvial)
8969 ("r-ggdendro" ,r-ggdendro)
8970 ("r-ggplot2" ,r-ggplot2)
8971 ("r-iranges" ,r-iranges)
8972 ("r-magrittr" ,r-magrittr)
8974 ("r-pracma" ,r-pracma)
8975 ("r-purrr" ,r-purrr)
8976 ("r-s4vectors" ,r-s4vectors)
8977 ("r-stringr" ,r-stringr)
8978 ("r-tibble" ,r-tibble)
8979 ("r-tidyr" ,r-tidyr)
8980 ("r-variantannotation" ,r-variantannotation)))
8981 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8982 (synopsis "Extract and visualize mutational patterns in genomic data")
8983 (description "This package provides an extensive toolset for the
8984 characterization and visualization of a wide range of mutational patterns
8985 in SNV base substitution data.")
8986 (license license:expat)))
8988 (define-public r-chipkernels
8989 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8992 (name "r-chipkernels")
8993 (version (string-append "1.1-" revision "." (string-take commit 9)))
8998 (url "https://github.com/ManuSetty/ChIPKernels")
9000 (file-name (string-append name "-" version))
9003 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
9004 (build-system r-build-system)
9006 `(("r-iranges" ,r-iranges)
9007 ("r-xvector" ,r-xvector)
9008 ("r-biostrings" ,r-biostrings)
9009 ("r-bsgenome" ,r-bsgenome)
9010 ("r-gtools" ,r-gtools)
9011 ("r-genomicranges" ,r-genomicranges)
9012 ("r-sfsmisc" ,r-sfsmisc)
9013 ("r-kernlab" ,r-kernlab)
9014 ("r-s4vectors" ,r-s4vectors)
9015 ("r-biocgenerics" ,r-biocgenerics)))
9016 (home-page "https://github.com/ManuSetty/ChIPKernels")
9017 (synopsis "Build string kernels for DNA Sequence analysis")
9018 (description "ChIPKernels is an R package for building different string
9019 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
9020 must be built and this dictionary can be used for determining kernels for DNA
9022 (license license:gpl2+))))
9024 (define-public r-seqgl
9032 (url "https://github.com/ManuSetty/SeqGL")
9034 (file-name (git-file-name name version))
9037 "1r6ywvhxl3ffv48lgj7sbd582mcc6dha3ksgc2qjlvjrnkbj3799"))))
9038 (build-system r-build-system)
9040 `(("r-biostrings" ,r-biostrings)
9041 ("r-chipkernels" ,r-chipkernels)
9042 ("r-genomicranges" ,r-genomicranges)
9043 ("r-spams" ,r-spams)
9044 ("r-wgcna" ,r-wgcna)
9045 ("r-fastcluster" ,r-fastcluster)))
9046 (home-page "https://github.com/ManuSetty/SeqGL")
9047 (synopsis "Group lasso for Dnase/ChIP-seq data")
9048 (description "SeqGL is a group lasso based algorithm to extract
9049 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
9050 This package presents a method which uses group lasso to discriminate between
9051 bound and non bound genomic regions to accurately identify transcription
9052 factors bound at the specific regions.")
9053 (license license:gpl2+)))
9055 (define-public r-tximport
9061 (uri (bioconductor-uri "tximport" version))
9064 "1nxnlvl4iv2392xa72j0lzy2xnb3vrvyhfrdj9l54znwkrryyq34"))))
9065 (build-system r-build-system)
9067 `(("r-knitr" ,r-knitr)))
9068 (home-page "https://bioconductor.org/packages/tximport")
9069 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
9071 "This package provides tools to import transcript-level abundance,
9072 estimated counts and transcript lengths, and to summarize them into matrices
9073 for use with downstream gene-level analysis packages. Average transcript
9074 length, weighted by sample-specific transcript abundance estimates, is
9075 provided as a matrix which can be used as an offset for different expression
9076 of gene-level counts.")
9077 (license license:gpl2+)))
9079 (define-public r-rhdf5
9085 (uri (bioconductor-uri "rhdf5" version))
9088 "0fnx60dpf6s2qwq48lg98g18g8k7wgm66pw0kamlbb7l2hnwycvf"))))
9089 (build-system r-build-system)
9091 `(("r-rhdf5lib" ,r-rhdf5lib)))
9095 `(("r-knitr" ,r-knitr)))
9096 (home-page "https://bioconductor.org/packages/rhdf5")
9097 (synopsis "HDF5 interface to R")
9099 "This R/Bioconductor package provides an interface between HDF5 and R.
9100 HDF5's main features are the ability to store and access very large and/or
9101 complex datasets and a wide variety of metadata on mass storage (disk) through
9102 a completely portable file format. The rhdf5 package is thus suited for the
9103 exchange of large and/or complex datasets between R and other software
9104 package, and for letting R applications work on datasets that are larger than
9105 the available RAM.")
9106 (license license:artistic2.0)))
9108 (define-public r-annotationfilter
9110 (name "r-annotationfilter")
9114 (uri (bioconductor-uri "AnnotationFilter" version))
9117 "0npk0laa2rc93rsh6yikj886zf2fl53a050j07fj9w67j0q0h3s9"))))
9119 `((upstream-name . "AnnotationFilter")))
9120 (build-system r-build-system)
9122 `(("r-genomicranges" ,r-genomicranges)
9123 ("r-lazyeval" ,r-lazyeval)))
9125 `(("r-knitr" ,r-knitr)))
9126 (home-page "https://github.com/Bioconductor/AnnotationFilter")
9127 (synopsis "Facilities for filtering Bioconductor annotation resources")
9129 "This package provides classes and other infrastructure to implement
9130 filters for manipulating Bioconductor annotation resources. The filters are
9131 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
9132 (license license:artistic2.0)))
9134 (define-public emboss
9140 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
9141 (version-major+minor version) ".0/"
9142 "EMBOSS-" version ".tar.gz"))
9145 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
9146 (build-system gnu-build-system)
9149 (list (string-append "--with-hpdf="
9150 (assoc-ref %build-inputs "libharu")))
9152 (modify-phases %standard-phases
9153 (add-after 'unpack 'fix-checks
9155 ;; The PNGDRIVER tests check for the presence of libgd, libpng
9156 ;; and zlib, but assume that they are all found at the same
9158 (substitute* "configure.in"
9159 (("CHECK_PNGDRIVER")
9160 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
9161 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
9162 AM_CONDITIONAL(AMPNG, true)"))
9164 (add-after 'fix-checks 'disable-update-check
9166 ;; At build time there is no connection to the Internet, so
9167 ;; looking for updates will not work.
9168 (substitute* "Makefile.am"
9169 (("\\$\\(bindir\\)/embossupdate") ""))
9171 (add-after 'disable-update-check 'autogen
9172 (lambda _ (invoke "autoreconf" "-vif") #t)))))
9178 ("libharu" ,libharu)
9181 `(("autoconf" ,autoconf)
9182 ("automake" ,automake)
9183 ("libtool" ,libtool)
9184 ("pkg-config" ,pkg-config)))
9185 (home-page "http://emboss.sourceforge.net")
9186 (synopsis "Molecular biology analysis suite")
9187 (description "EMBOSS is the \"European Molecular Biology Open Software
9188 Suite\". EMBOSS is an analysis package specially developed for the needs of
9189 the molecular biology (e.g. EMBnet) user community. The software
9190 automatically copes with data in a variety of formats and even allows
9191 transparent retrieval of sequence data from the web. It also provides a
9192 number of libraries for the development of software in the field of molecular
9193 biology. EMBOSS also integrates a range of currently available packages and
9194 tools for sequence analysis into a seamless whole.")
9195 (license license:gpl2+)))
9198 (let ((revision "1")
9199 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
9202 ;; The version is 2.13.0 even though no release archives have been
9203 ;; published as yet.
9204 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
9208 (url "https://github.com/arq5x/bits")
9210 (file-name (string-append name "-" version "-checkout"))
9213 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
9214 (build-system gnu-build-system)
9216 `(#:tests? #f ;no tests included
9218 (modify-phases %standard-phases
9220 (add-after 'unpack 'remove-cuda
9222 (substitute* "Makefile"
9224 (("(bits_test_intersections) \\\\" _ match) match))
9227 (lambda* (#:key outputs #:allow-other-keys)
9229 "bin" (string-append (assoc-ref outputs "out") "/bin"))
9234 (home-page "https://github.com/arq5x/bits")
9235 (synopsis "Implementation of binary interval search algorithm")
9236 (description "This package provides an implementation of the
9237 BITS (Binary Interval Search) algorithm, an approach to interval set
9238 intersection. It is especially suited for the comparison of diverse genomic
9239 datasets and the exploration of large datasets of genome
9240 intervals (e.g. genes, sequence alignments).")
9241 (license license:gpl2))))
9243 (define-public piranha
9244 ;; There is no release tarball for the latest version. The latest commit is
9245 ;; older than one year at the time of this writing.
9246 (let ((revision "1")
9247 (commit "0466d364b71117d01e4471b74c514436cc281233"))
9250 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
9254 (url "https://github.com/smithlabcode/piranha")
9256 (file-name (git-file-name name version))
9259 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
9260 (build-system gnu-build-system)
9262 `(#:test-target "test"
9264 (modify-phases %standard-phases
9265 (add-after 'unpack 'copy-smithlab-cpp
9266 (lambda* (#:key inputs #:allow-other-keys)
9267 (for-each (lambda (file)
9268 (install-file file "./src/smithlab_cpp/"))
9269 (find-files (assoc-ref inputs "smithlab-cpp")))
9271 (add-after 'install 'install-to-store
9272 (lambda* (#:key outputs #:allow-other-keys)
9273 (let* ((out (assoc-ref outputs "out"))
9274 (bin (string-append out "/bin")))
9275 (for-each (lambda (file)
9276 (install-file file bin))
9277 (find-files "bin" ".*")))
9280 (list (string-append "--with-bam_tools_headers="
9281 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
9282 (string-append "--with-bam_tools_library="
9283 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
9285 `(("bamtools" ,bamtools)
9286 ("samtools" ,samtools-0.1)
9289 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
9293 (url "https://github.com/smithlabcode/smithlab_cpp")
9295 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
9298 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
9300 `(("python" ,python-2)))
9301 (home-page "https://github.com/smithlabcode/piranha")
9302 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
9304 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
9305 RIP-seq experiments. It takes input in BED or BAM format and identifies
9306 regions of statistically significant read enrichment. Additional covariates
9307 may optionally be provided to further inform the peak-calling process.")
9308 (license license:gpl3+))))
9316 (uri (pypi-uri "PePr" version))
9319 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
9320 (build-system python-build-system)
9322 `(#:python ,python-2 ; python2 only
9323 #:tests? #f)) ; no tests included
9325 `(("python2-numpy" ,python2-numpy)
9326 ("python2-scipy" ,python2-scipy)
9327 ("python2-pysam" ,python2-pysam)))
9328 (home-page "https://github.com/shawnzhangyx/PePr")
9329 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
9331 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
9332 that is primarily designed for data with biological replicates. It uses a
9333 negative binomial distribution to model the read counts among the samples in
9334 the same group, and look for consistent differences between ChIP and control
9335 group or two ChIP groups run under different conditions.")
9336 (license license:gpl3+)))
9338 (define-public filevercmp
9339 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
9342 (version (string-append "0-1." (string-take commit 7)))
9346 (url "https://github.com/ekg/filevercmp")
9348 (file-name (git-file-name name commit))
9351 "1j9vxsy0y050v59h0q1d6501fcw1kjvj0d18l1xk2zyg0jzj247c"))))
9352 (build-system gnu-build-system)
9354 `(#:tests? #f ; There are no tests to run.
9356 (modify-phases %standard-phases
9357 (delete 'configure) ; There is no configure phase.
9359 (lambda* (#:key outputs #:allow-other-keys)
9360 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
9361 (install-file "filevercmp" bin)
9363 (home-page "https://github.com/ekg/filevercmp")
9364 (synopsis "This program compares version strings")
9365 (description "This program compares version strings. It intends to be a
9366 replacement for strverscmp.")
9367 (license license:gpl3+))))
9369 (define-public multiqc
9376 (uri (pypi-uri "multiqc" version))
9379 "02iihfl0w0hpnr4pa0sbd1y9qxrg3ycyhjp5lidkcrqh1lmzs3zy"))))
9380 (build-system python-build-system)
9382 `(("python-jinja2" ,python-jinja2)
9383 ("python-simplejson" ,python-simplejson)
9384 ("python-pyyaml" ,python-pyyaml)
9385 ("python-click" ,python-click)
9386 ("python-spectra" ,python-spectra)
9387 ("python-requests" ,python-requests)
9388 ("python-markdown" ,python-markdown)
9389 ("python-lzstring" ,python-lzstring)
9390 ("python-matplotlib" ,python-matplotlib)
9391 ("python-numpy" ,python-numpy)
9392 ;; MultQC checks for the presence of nose at runtime.
9393 ("python-nose" ,python-nose)))
9396 (modify-phases %standard-phases
9397 (add-after 'unpack 'relax-requirements
9399 (substitute* "setup.py"
9400 ;; MultiQC 1.5 ‘requires’ a version of python-matplotlib older
9401 ;; than the one in Guix, but should work fine with 2.2.2.
9402 ;; See <https://github.com/ewels/MultiQC/issues/725> and
9403 ;; <https://github.com/ewels/MultiQC/issues/732> for details.
9404 (("['\"]matplotlib.*?['\"]")
9407 (home-page "https://multiqc.info")
9408 (synopsis "Aggregate bioinformatics analysis reports")
9410 "MultiQC is a tool to aggregate bioinformatics results across many
9411 samples into a single report. It contains modules for a large number of
9412 common bioinformatics tools.")
9413 (license license:gpl3+)))
9415 (define-public variant-tools
9417 (name "variant-tools")
9423 (url "https://github.com/vatlab/varianttools")
9424 ;; There is no tag corresponding to version 3.1.2
9425 (commit "813ae4a90d25b69abc8a40f4f70441fe09015249")))
9426 (file-name (git-file-name name version))
9429 "12ibdmksj7icyqhks4xyvd61bygk4pjmxn618kp6vgk1af01y34g"))))
9430 (build-system python-build-system)
9433 ("c-blosc" ,c-blosc)
9436 ("hdf5-blosc" ,hdf5-blosc)
9437 ("python-cython" ,python-cython)
9440 `(("python-numpy" ,python-numpy)
9441 ("python-pycurl" ,python-pycurl)
9442 ("python-pyzmq" ,python-pyzmq)
9443 ("python-scipy" ,python-scipy)
9444 ("python-tables" ,python-tables)))
9445 (home-page "https://vatlab.github.io/vat-docs/")
9446 (synopsis "Analyze genetic variants from Next-Gen sequencing studies")
9448 "Variant tools is a tool for the manipulation, annotation,
9449 selection, simulation, and analysis of variants in the context of next-gen
9450 sequencing analysis. Unlike some other tools used for next-gen sequencing
9451 analysis, variant tools is project based and provides a whole set of tools to
9452 manipulate and analyze genetic variants.")
9453 (license license:gpl3+)))
9455 (define-public r-chipseq
9462 (uri (bioconductor-uri "chipseq" version))
9465 "12pzq24aarvgxfmhcad0l5g951xqdvvi7bspgbsvlvmfkqd74j2v"))))
9466 (build-system r-build-system)
9468 `(("r-biocgenerics" ,r-biocgenerics)
9469 ("r-genomicranges" ,r-genomicranges)
9470 ("r-iranges" ,r-iranges)
9471 ("r-lattice" ,r-lattice)
9472 ("r-s4vectors" ,r-s4vectors)
9473 ("r-shortread" ,r-shortread)))
9474 (home-page "https://bioconductor.org/packages/chipseq")
9475 (synopsis "Package for analyzing ChIPseq data")
9477 "This package provides tools for processing short read data from ChIPseq
9479 (license license:artistic2.0)))
9481 (define-public r-copyhelper
9483 (name "r-copyhelper")
9488 (uri (string-append "https://bioconductor.org/packages/release/"
9489 "data/experiment/src/contrib/CopyhelpeR_"
9493 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
9494 (properties `((upstream-name . "CopyhelpeR")))
9495 (build-system r-build-system)
9496 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
9497 (synopsis "Helper files for CopywriteR")
9499 "This package contains the helper files that are required to run the
9500 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
9501 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
9502 mm10. In addition, it contains a blacklist filter to remove regions that
9503 display copy number variation. Files are stored as GRanges objects from the
9504 GenomicRanges Bioconductor package.")
9505 (license license:gpl2)))
9507 (define-public r-copywriter
9509 (name "r-copywriter")
9514 (uri (bioconductor-uri "CopywriteR" version))
9517 "060p6l6l8i6b15hyyz5v5kkxih3h4wcciixii51m9mn82z23xr2f"))))
9518 (properties `((upstream-name . "CopywriteR")))
9519 (build-system r-build-system)
9521 `(("r-biocparallel" ,r-biocparallel)
9522 ("r-chipseq" ,r-chipseq)
9523 ("r-copyhelper" ,r-copyhelper)
9524 ("r-data-table" ,r-data-table)
9525 ("r-dnacopy" ,r-dnacopy)
9526 ("r-futile-logger" ,r-futile-logger)
9527 ("r-genomeinfodb" ,r-genomeinfodb)
9528 ("r-genomicalignments" ,r-genomicalignments)
9529 ("r-genomicranges" ,r-genomicranges)
9530 ("r-gtools" ,r-gtools)
9531 ("r-iranges" ,r-iranges)
9532 ("r-matrixstats" ,r-matrixstats)
9533 ("r-rsamtools" ,r-rsamtools)
9534 ("r-s4vectors" ,r-s4vectors)))
9535 (home-page "https://github.com/PeeperLab/CopywriteR")
9536 (synopsis "Copy number information from targeted sequencing")
9538 "CopywriteR extracts DNA copy number information from targeted sequencing
9539 by utilizing off-target reads. It allows for extracting uniformly distributed
9540 copy number information, can be used without reference, and can be applied to
9541 sequencing data obtained from various techniques including chromatin
9542 immunoprecipitation and target enrichment on small gene panels. Thereby,
9543 CopywriteR constitutes a widely applicable alternative to available copy
9544 number detection tools.")
9545 (license license:gpl2)))
9547 (define-public r-methylkit
9549 (name "r-methylkit")
9553 (uri (bioconductor-uri "methylKit" version))
9556 "11pmn191n0ga28x1w20cm2cmw8kddl29q6h2xfjjba5bspp2g613"))))
9557 (properties `((upstream-name . "methylKit")))
9558 (build-system r-build-system)
9560 `(("r-data-table" ,r-data-table)
9561 ("r-emdbook" ,r-emdbook)
9562 ("r-fastseg" ,r-fastseg)
9563 ("r-genomeinfodb" ,r-genomeinfodb)
9564 ("r-genomicranges" ,r-genomicranges)
9565 ("r-gtools" ,r-gtools)
9566 ("r-iranges" ,r-iranges)
9567 ("r-kernsmooth" ,r-kernsmooth)
9568 ("r-limma" ,r-limma)
9569 ("r-mclust" ,r-mclust)
9571 ("r-qvalue" ,r-qvalue)
9572 ("r-r-utils" ,r-r-utils)
9574 ("r-rhtslib" ,r-rhtslib)
9575 ("r-rsamtools" ,r-rsamtools)
9576 ("r-rtracklayer" ,r-rtracklayer)
9577 ("r-s4vectors" ,r-s4vectors)
9578 ("r-zlibbioc" ,r-zlibbioc)))
9580 `(("r-knitr" ,r-knitr))) ; for vignettes
9583 (home-page "https://github.com/al2na/methylKit")
9585 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9587 "MethylKit is an R package for DNA methylation analysis and annotation
9588 from high-throughput bisulfite sequencing. The package is designed to deal
9589 with sequencing data from @dfn{Reduced representation bisulfite
9590 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9591 genome bisulfite sequencing. It also has functions to analyze base-pair
9592 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9594 (license license:artistic2.0)))
9596 (define-public r-sva
9603 (uri (bioconductor-uri "sva" version))
9606 "1hpzzg3qrgkd8kwg1m5gq94cikjgk9j4l1wk58fxl49s6fmd13zy"))))
9607 (build-system r-build-system)
9609 `(("r-edger" ,r-edger)
9610 ("r-genefilter" ,r-genefilter)
9612 ("r-biocparallel" ,r-biocparallel)
9613 ("r-matrixstats" ,r-matrixstats)
9614 ("r-limma" ,r-limma)))
9615 (home-page "https://bioconductor.org/packages/sva")
9616 (synopsis "Surrogate variable analysis")
9618 "This package contains functions for removing batch effects and other
9619 unwanted variation in high-throughput experiment. It also contains functions
9620 for identifying and building surrogate variables for high-dimensional data
9621 sets. Surrogate variables are covariates constructed directly from
9622 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9623 imaging data that can be used in subsequent analyses to adjust for unknown,
9624 unmodeled, or latent sources of noise.")
9625 (license license:artistic2.0)))
9627 (define-public r-raremetals2
9629 (name "r-raremetals2")
9634 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9635 "b/b7/RareMETALS2_" version ".tar.gz"))
9638 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9639 (properties `((upstream-name . "RareMETALS2")))
9640 (build-system r-build-system)
9642 `(("r-seqminer" ,r-seqminer)
9643 ("r-mvtnorm" ,r-mvtnorm)
9645 ("r-compquadform" ,r-compquadform)
9646 ("r-getopt" ,r-getopt)))
9647 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9648 (synopsis "Analyze gene-level association tests for binary trait")
9650 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9651 It was designed to meta-analyze gene-level association tests for binary trait.
9652 While rareMETALS offers a near-complete solution for meta-analysis of
9653 gene-level tests for quantitative trait, it does not offer the optimal
9654 solution for binary trait. The package rareMETALS2 offers improved features
9655 for analyzing gene-level association tests in meta-analyses for binary
9657 (license license:gpl3)))
9659 (define-public r-protgenerics
9661 (name "r-protgenerics")
9666 (uri (bioconductor-uri "ProtGenerics" version))
9669 "0yihxphgkshvfv1sn67wc4zvr2zlzws2j7ki3zabm6vyfkfdkfiz"))))
9670 (properties `((upstream-name . "ProtGenerics")))
9671 (build-system r-build-system)
9672 (home-page "https://github.com/lgatto/ProtGenerics")
9673 (synopsis "S4 generic functions for proteomics infrastructure")
9675 "This package provides S4 generic functions needed by Bioconductor
9676 proteomics packages.")
9677 (license license:artistic2.0)))
9679 (define-public r-mzr
9686 (uri (bioconductor-uri "mzR" version))
9689 "0ik0yrjhvk8r5pm990chn2aadp0gqzzkkm0027682ky34xp142sg"))
9690 (modules '((guix build utils)))
9693 (delete-file-recursively "src/boost")
9695 (properties `((upstream-name . "mzR")))
9696 (build-system r-build-system)
9699 (modify-phases %standard-phases
9700 (add-after 'unpack 'use-system-boost
9702 (substitute* "src/Makevars"
9703 (("\\./boost/libs.*") "")
9704 ;; This is to avoid having a plain directory on the list of
9705 ;; libraries to link.
9706 (("\\(RHDF5_LIBS\\)" match)
9707 (string-append match "/libhdf5.a"))
9708 (("PKG_LIBS=") "PKG_LIBS=$(BOOST_LIBS) ")
9709 (("\\ARCH_OBJS=" line)
9711 "\nBOOST_LIBS=-lboost_system -lboost_regex \
9712 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9715 `(;; Our default boost package won't work here, unfortunately, even with
9716 ;; mzR version 2.24.1.
9717 ("boost" ,boost-for-mysql) ; use this instead of the bundled boost sources
9720 `(("r-biobase" ,r-biobase)
9721 ("r-biocgenerics" ,r-biocgenerics)
9722 ("r-ncdf4" ,r-ncdf4)
9723 ("r-protgenerics" ,r-protgenerics)
9725 ("r-rhdf5lib" ,r-rhdf5lib)
9726 ("r-zlibbioc" ,r-zlibbioc)))
9728 `(("r-knitr" ,r-knitr)))
9729 (home-page "https://github.com/sneumann/mzR/")
9730 (synopsis "Parser for mass spectrometry data files")
9732 "The mzR package provides a unified API to the common file formats and
9733 parsers available for mass spectrometry data. It comes with a wrapper for the
9734 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9735 The package contains the original code written by the ISB, and a subset of the
9736 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9737 previously been used in XCMS.")
9738 (license license:artistic2.0)))
9740 (define-public r-affyio
9747 (uri (bioconductor-uri "affyio" version))
9750 "14xnzrxrvgxgixjhq5a9fdgcmrxam2j74hwidkc9if92ffv6s83h"))))
9751 (build-system r-build-system)
9753 `(("r-zlibbioc" ,r-zlibbioc)))
9756 (home-page "https://github.com/bmbolstad/affyio")
9757 (synopsis "Tools for parsing Affymetrix data files")
9759 "This package provides routines for parsing Affymetrix data files based
9760 upon file format information. The primary focus is on accessing the CEL and
9762 (license license:lgpl2.0+)))
9764 (define-public r-affy
9771 (uri (bioconductor-uri "affy" version))
9774 "0ywz548cbzk2k1njnxhlk5ydzvz2dk78ka8kx53gwrmdc4sc2b06"))))
9775 (build-system r-build-system)
9777 `(("r-affyio" ,r-affyio)
9778 ("r-biobase" ,r-biobase)
9779 ("r-biocgenerics" ,r-biocgenerics)
9780 ("r-biocmanager" ,r-biocmanager)
9781 ("r-preprocesscore" ,r-preprocesscore)
9782 ("r-zlibbioc" ,r-zlibbioc)))
9785 (home-page "https://bioconductor.org/packages/affy")
9786 (synopsis "Methods for affymetrix oligonucleotide arrays")
9788 "This package contains functions for exploratory oligonucleotide array
9790 (license license:lgpl2.0+)))
9792 (define-public r-vsn
9799 (uri (bioconductor-uri "vsn" version))
9802 "0dfrfflidpnphwyqzmmfiz9blfqv6qa09xlwgfabhpfsf3ml2rlb"))))
9803 (build-system r-build-system)
9805 `(("r-affy" ,r-affy)
9806 ("r-biobase" ,r-biobase)
9807 ("r-ggplot2" ,r-ggplot2)
9808 ("r-lattice" ,r-lattice)
9809 ("r-limma" ,r-limma)))
9811 `(("r-knitr" ,r-knitr))) ; for vignettes
9812 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9813 (synopsis "Variance stabilization and calibration for microarray data")
9815 "The package implements a method for normalising microarray intensities,
9816 and works for single- and multiple-color arrays. It can also be used for data
9817 from other technologies, as long as they have similar format. The method uses
9818 a robust variant of the maximum-likelihood estimator for an
9819 additive-multiplicative error model and affine calibration. The model
9820 incorporates data calibration step (a.k.a. normalization), a model for the
9821 dependence of the variance on the mean intensity and a variance stabilizing
9822 data transformation. Differences between transformed intensities are
9823 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9824 their variance is independent of the mean, and they are usually more sensitive
9825 and specific in detecting differential transcription.")
9826 (license license:artistic2.0)))
9828 (define-public r-mzid
9835 (uri (bioconductor-uri "mzID" version))
9838 "0s7d6cz1li7v3ni6n6hrdspl93yiyr283kmbbd3hhkfgzgx6kpq2"))))
9839 (properties `((upstream-name . "mzID")))
9840 (build-system r-build-system)
9842 `(("r-doparallel" ,r-doparallel)
9843 ("r-foreach" ,r-foreach)
9844 ("r-iterators" ,r-iterators)
9846 ("r-protgenerics" ,r-protgenerics)
9849 `(("r-knitr" ,r-knitr)))
9850 (home-page "https://bioconductor.org/packages/mzID")
9851 (synopsis "Parser for mzIdentML files")
9853 "This package provides a parser for mzIdentML files implemented using the
9854 XML package. The parser tries to be general and able to handle all types of
9855 mzIdentML files with the drawback of having less pretty output than a vendor
9857 (license license:gpl2+)))
9859 (define-public r-pcamethods
9861 (name "r-pcamethods")
9866 (uri (bioconductor-uri "pcaMethods" version))
9869 "04xb4vjky6hq58l30i1iq9rv5gzjdxnidjxpnzg7pvg67vz8pgf0"))))
9870 (properties `((upstream-name . "pcaMethods")))
9871 (build-system r-build-system)
9873 `(("r-biobase" ,r-biobase)
9874 ("r-biocgenerics" ,r-biocgenerics)
9876 ("r-rcpp" ,r-rcpp)))
9877 (home-page "https://github.com/hredestig/pcamethods")
9878 (synopsis "Collection of PCA methods")
9880 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9881 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9882 for missing value estimation is included for comparison. BPCA, PPCA and
9883 NipalsPCA may be used to perform PCA on incomplete data as well as for
9884 accurate missing value estimation. A set of methods for printing and plotting
9885 the results is also provided. All PCA methods make use of the same data
9886 structure (pcaRes) to provide a common interface to the PCA results.")
9887 (license license:gpl3+)))
9889 (define-public r-msnbase
9896 (uri (bioconductor-uri "MSnbase" version))
9899 "0cvcdmq1glifga5qwv9j3lgj31dcrcc6ql4kkk83jy4y43v2zxlx"))))
9900 (properties `((upstream-name . "MSnbase")))
9901 (build-system r-build-system)
9903 `(("r-affy" ,r-affy)
9904 ("r-biobase" ,r-biobase)
9905 ("r-biocgenerics" ,r-biocgenerics)
9906 ("r-biocparallel" ,r-biocparallel)
9907 ("r-digest" ,r-digest)
9908 ("r-ggplot2" ,r-ggplot2)
9909 ("r-impute" ,r-impute)
9910 ("r-iranges" ,r-iranges)
9911 ("r-lattice" ,r-lattice)
9912 ("r-maldiquant" ,r-maldiquant)
9916 ("r-pcamethods" ,r-pcamethods)
9918 ("r-preprocesscore" ,r-preprocesscore)
9919 ("r-protgenerics" ,r-protgenerics)
9921 ("r-s4vectors" ,r-s4vectors)
9922 ("r-scales" ,r-scales)
9926 `(("r-knitr" ,r-knitr)))
9927 (home-page "https://github.com/lgatto/MSnbase")
9928 (synopsis "Base functions and classes for MS-based proteomics")
9930 "This package provides basic plotting, data manipulation and processing
9931 of mass spectrometry based proteomics data.")
9932 (license license:artistic2.0)))
9934 (define-public r-msnid
9941 (uri (bioconductor-uri "MSnID" version))
9944 "05bncy7lw2a3h8xgnavjiz56pc6mk8q7l6qdd81197nawxs3j02d"))))
9945 (properties `((upstream-name . "MSnID")))
9946 (build-system r-build-system)
9948 `(("r-annotationdbi" ,r-annotationdbi)
9949 ("r-annotationhub" ,r-annotationhub)
9950 ("r-biobase" ,r-biobase)
9951 ("r-biocgenerics" ,r-biocgenerics)
9952 ("r-biocstyle" ,r-biocstyle)
9953 ("r-biostrings" ,r-biostrings)
9954 ("r-data-table" ,r-data-table)
9955 ("r-doparallel" ,r-doparallel)
9956 ("r-dplyr" ,r-dplyr)
9957 ("r-foreach" ,r-foreach)
9958 ("r-ggplot2" ,r-ggplot2)
9959 ("r-iterators" ,r-iterators)
9960 ("r-msnbase" ,r-msnbase)
9961 ("r-msmstests" ,r-msmstests)
9964 ("r-protgenerics" ,r-protgenerics)
9965 ("r-purrr" ,r-purrr)
9966 ("r-r-cache" ,r-r-cache)
9968 ("r-reshape2" ,r-reshape2)
9969 ("r-rlang" ,r-rlang)
9970 ("r-runit" ,r-runit)
9971 ("r-stringr" ,r-stringr)
9972 ("r-tibble" ,r-tibble)
9973 ("r-xtable" ,r-xtable)))
9974 (home-page "https://bioconductor.org/packages/MSnID")
9975 (synopsis "Utilities for LC-MSn proteomics identifications")
9977 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9978 from mzIdentML (leveraging the mzID package) or text files. After collating
9979 the search results from multiple datasets it assesses their identification
9980 quality and optimize filtering criteria to achieve the maximum number of
9981 identifications while not exceeding a specified false discovery rate. It also
9982 contains a number of utilities to explore the MS/MS results and assess missed
9983 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9984 (license license:artistic2.0)))
9986 (define-public r-aroma-light
9988 (name "r-aroma-light")
9993 (uri (bioconductor-uri "aroma.light" version))
9996 "0pi37rlfqh24p9wd7l1xb3f7c7938xdscgcc5agp8c9qhajq25a0"))))
9997 (properties `((upstream-name . "aroma.light")))
9998 (build-system r-build-system)
10000 `(("r-matrixstats" ,r-matrixstats)
10001 ("r-r-methodss3" ,r-r-methodss3)
10003 ("r-r-utils" ,r-r-utils)))
10004 (home-page "https://github.com/HenrikBengtsson/aroma.light")
10005 (synopsis "Methods for normalization and visualization of microarray data")
10007 "This package provides methods for microarray analysis that take basic
10008 data types such as matrices and lists of vectors. These methods can be used
10009 standalone, be utilized in other packages, or be wrapped up in higher-level
10011 (license license:gpl2+)))
10013 (define-public r-deseq
10020 (uri (bioconductor-uri "DESeq" version))
10023 "047hph5aqmjnz1aqprziw0smdn5lf96hmwpnvqrxv1j2yfvcf3h1"))))
10024 (properties `((upstream-name . "DESeq")))
10025 (build-system r-build-system)
10027 `(("r-biobase" ,r-biobase)
10028 ("r-biocgenerics" ,r-biocgenerics)
10029 ("r-genefilter" ,r-genefilter)
10030 ("r-geneplotter" ,r-geneplotter)
10031 ("r-lattice" ,r-lattice)
10032 ("r-locfit" ,r-locfit)
10034 ("r-rcolorbrewer" ,r-rcolorbrewer)))
10035 (home-page "https://www-huber.embl.de/users/anders/DESeq/")
10036 (synopsis "Differential gene expression analysis")
10038 "This package provides tools for estimating variance-mean dependence in
10039 count data from high-throughput genetic sequencing assays and for testing for
10040 differential expression based on a model using the negative binomial
10042 (license license:gpl3+)))
10044 (define-public r-edaseq
10051 (uri (bioconductor-uri "EDASeq" version))
10054 "0fznj7lsgkss1svv4rq8g87s1gmnbd7hccim41dv1c2w2nl0n2ip"))))
10055 (properties `((upstream-name . "EDASeq")))
10056 (build-system r-build-system)
10058 `(("r-annotationdbi" ,r-annotationdbi)
10059 ("r-aroma-light" ,r-aroma-light)
10060 ("r-biobase" ,r-biobase)
10061 ("r-biocgenerics" ,r-biocgenerics)
10062 ("r-biocmanager" ,r-biocmanager)
10063 ("r-biomart" ,r-biomart)
10064 ("r-biostrings" ,r-biostrings)
10065 ("r-genomicfeatures" ,r-genomicfeatures)
10066 ("r-genomicranges" ,r-genomicranges)
10067 ("r-iranges" ,r-iranges)
10068 ("r-rsamtools" ,r-rsamtools)
10069 ("r-shortread" ,r-shortread)))
10071 `(("r-knitr" ,r-knitr)))
10072 (home-page "https://github.com/drisso/EDASeq")
10073 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
10075 "This package provides support for numerical and graphical summaries of
10076 RNA-Seq genomic read data. Provided within-lane normalization procedures to
10077 adjust for GC-content effect (or other gene-level effects) on read counts:
10078 loess robust local regression, global-scaling, and full-quantile
10079 normalization. Between-lane normalization procedures to adjust for
10080 distributional differences between lanes (e.g., sequencing depth):
10081 global-scaling and full-quantile normalization.")
10082 (license license:artistic2.0)))
10084 (define-public r-interactivedisplaybase
10086 (name "r-interactivedisplaybase")
10091 (uri (bioconductor-uri "interactiveDisplayBase" version))
10094 "08id2hkx4ssxj34dildx00a4j3z0nv171b7b0wl6xjks7wk6lv01"))))
10096 `((upstream-name . "interactiveDisplayBase")))
10097 (build-system r-build-system)
10099 `(("r-biocgenerics" ,r-biocgenerics)
10101 ("r-shiny" ,r-shiny)))
10103 `(("r-knitr" ,r-knitr)))
10104 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
10105 (synopsis "Base package for web displays of Bioconductor objects")
10107 "This package contains the basic methods needed to generate interactive
10108 Shiny-based display methods for Bioconductor objects.")
10109 (license license:artistic2.0)))
10111 (define-public r-annotationhub
10113 (name "r-annotationhub")
10118 (uri (bioconductor-uri "AnnotationHub" version))
10121 "1950x654ffqx53b154kbph808zdh2xm5vmj9vzmc5nxc28fi2z5g"))))
10122 (properties `((upstream-name . "AnnotationHub")))
10123 (build-system r-build-system)
10125 `(("r-annotationdbi" ,r-annotationdbi)
10126 ("r-biocfilecache" ,r-biocfilecache)
10127 ("r-biocgenerics" ,r-biocgenerics)
10128 ("r-biocmanager" ,r-biocmanager)
10129 ("r-biocversion" ,r-biocversion)
10131 ("r-dplyr" ,r-dplyr)
10133 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
10134 ("r-rappdirs" ,r-rappdirs)
10135 ("r-rsqlite" ,r-rsqlite)
10136 ("r-s4vectors" ,r-s4vectors)
10137 ("r-yaml" ,r-yaml)))
10139 `(("r-knitr" ,r-knitr)))
10140 (home-page "https://bioconductor.org/packages/AnnotationHub")
10141 (synopsis "Client to access AnnotationHub resources")
10143 "This package provides a client for the Bioconductor AnnotationHub web
10144 resource. The AnnotationHub web resource provides a central location where
10145 genomic files (e.g. VCF, bed, wig) and other resources from standard
10146 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
10147 metadata about each resource, e.g., a textual description, tags, and date of
10148 modification. The client creates and manages a local cache of files retrieved
10149 by the user, helping with quick and reproducible access.")
10150 (license license:artistic2.0)))
10152 (define-public r-fastseg
10159 (uri (bioconductor-uri "fastseg" version))
10162 "1ln6w93ag4wanp0nrm0pqngbfc88w95zq2kcj583hbxy885dkg4f"))))
10163 (build-system r-build-system)
10165 `(("r-biobase" ,r-biobase)
10166 ("r-biocgenerics" ,r-biocgenerics)
10167 ("r-genomicranges" ,r-genomicranges)
10168 ("r-iranges" ,r-iranges)
10169 ("r-s4vectors" ,r-s4vectors)))
10170 (home-page "https://www.bioinf.jku.at/software/fastseg/index.html")
10171 (synopsis "Fast segmentation algorithm for genetic sequencing data")
10173 "Fastseg implements a very fast and efficient segmentation algorithm.
10174 It can segment data from DNA microarrays and data from next generation
10175 sequencing for example to detect copy number segments. Further it can segment
10176 data from RNA microarrays like tiling arrays to identify transcripts. Most
10177 generally, it can segment data given as a matrix or as a vector. Various data
10178 formats can be used as input to fastseg like expression set objects for
10179 microarrays or GRanges for sequencing data.")
10180 (license license:lgpl2.0+)))
10182 (define-public r-keggrest
10184 (name "r-keggrest")
10189 (uri (bioconductor-uri "KEGGREST" version))
10192 "0awg0hmxj25rpmqyf6jz6kbkswmimz3h352xx15xhkamwcxykng6"))))
10193 (properties `((upstream-name . "KEGGREST")))
10194 (build-system r-build-system)
10196 `(("r-biostrings" ,r-biostrings)
10200 `(("r-knitr" ,r-knitr)))
10201 (home-page "https://bioconductor.org/packages/KEGGREST")
10202 (synopsis "Client-side REST access to KEGG")
10204 "This package provides a package that provides a client interface to the
10205 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
10206 (license license:artistic2.0)))
10208 (define-public r-gage
10215 (uri (bioconductor-uri "gage" version))
10218 "0xm50wgjjjymv71mbv1clnhx4m12nrd1pc6vfplpdqr5q49v3yd5"))))
10219 (build-system r-build-system)
10221 `(("r-annotationdbi" ,r-annotationdbi)
10222 ("r-go-db" ,r-go-db)
10223 ("r-graph" ,r-graph)
10224 ("r-keggrest" ,r-keggrest)))
10225 (home-page (string-append "https://bmcbioinformatics.biomedcentral.com/"
10226 "articles/10.1186/1471-2105-10-161"))
10227 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
10229 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
10230 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
10231 data attributes including sample sizes, experimental designs, assay platforms,
10232 and other types of heterogeneity. The gage package provides functions for
10233 basic GAGE analysis, result processing and presentation. In addition, it
10234 provides demo microarray data and commonly used gene set data based on KEGG
10235 pathways and GO terms. These functions and data are also useful for gene set
10236 analysis using other methods.")
10237 (license license:gpl2+)))
10239 (define-public r-genomicfiles
10241 (name "r-genomicfiles")
10246 (uri (bioconductor-uri "GenomicFiles" version))
10249 "0awnf0m1pz7cw9wvh9cfxz9k7xm6wnvjm7xbxf139lrhd4nlyqjz"))))
10250 (properties `((upstream-name . "GenomicFiles")))
10251 (build-system r-build-system)
10253 `(("r-biocgenerics" ,r-biocgenerics)
10254 ("r-biocparallel" ,r-biocparallel)
10255 ("r-genomeinfodb" ,r-genomeinfodb)
10256 ("r-genomicalignments" ,r-genomicalignments)
10257 ("r-genomicranges" ,r-genomicranges)
10258 ("r-iranges" ,r-iranges)
10259 ("r-matrixgenerics" ,r-matrixgenerics)
10260 ("r-rsamtools" ,r-rsamtools)
10261 ("r-rtracklayer" ,r-rtracklayer)
10262 ("r-s4vectors" ,r-s4vectors)
10263 ("r-summarizedexperiment" ,r-summarizedexperiment)
10264 ("r-variantannotation" ,r-variantannotation)))
10265 (home-page "https://bioconductor.org/packages/GenomicFiles")
10266 (synopsis "Distributed computing by file or by range")
10268 "This package provides infrastructure for parallel computations
10269 distributed by file or by range. User defined mapper and reducer functions
10270 provide added flexibility for data combination and manipulation.")
10271 (license license:artistic2.0)))
10273 (define-public r-complexheatmap
10275 (name "r-complexheatmap")
10280 (uri (bioconductor-uri "ComplexHeatmap" version))
10283 "1nx1xxpq8zrvi990v9fmvx3msl85pdz5dp1gp6m78q6i4s2alg5x"))))
10285 `((upstream-name . "ComplexHeatmap")))
10286 (build-system r-build-system)
10288 `(("r-cairo" ,r-cairo)
10289 ("r-circlize" ,r-circlize)
10291 ("r-colorspace" ,r-colorspace)
10292 ("r-digest" ,r-digest)
10293 ("r-getoptlong" ,r-getoptlong)
10294 ("r-globaloptions" ,r-globaloptions)
10295 ("r-iranges" ,r-iranges)
10296 ("r-matrixstats" ,r-matrixstats)
10298 ("r-rcolorbrewer" ,r-rcolorbrewer)
10299 ("r-s4vectors" ,r-s4vectors)))
10301 `(("r-knitr" ,r-knitr)))
10303 "https://github.com/jokergoo/ComplexHeatmap")
10304 (synopsis "Making Complex Heatmaps")
10306 "Complex heatmaps are efficient to visualize associations between
10307 different sources of data sets and reveal potential structures. This package
10308 provides a highly flexible way to arrange multiple heatmaps and supports
10309 self-defined annotation graphics.")
10310 (license license:gpl2+)))
10312 (define-public r-dirichletmultinomial
10314 (name "r-dirichletmultinomial")
10319 (uri (bioconductor-uri "DirichletMultinomial" version))
10322 "098zql6ryd1b0gkq4cjybblyh0x8xidxxfygqq5a5x9asl8y4vsk"))))
10324 `((upstream-name . "DirichletMultinomial")))
10325 (build-system r-build-system)
10329 `(("r-biocgenerics" ,r-biocgenerics)
10330 ("r-iranges" ,r-iranges)
10331 ("r-s4vectors" ,r-s4vectors)))
10332 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
10333 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
10335 "Dirichlet-multinomial mixture models can be used to describe variability
10336 in microbial metagenomic data. This package is an interface to code
10337 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
10339 (license license:lgpl3)))
10341 (define-public r-ensembldb
10343 (name "r-ensembldb")
10348 (uri (bioconductor-uri "ensembldb" version))
10351 "04il99gcrqzakvc0bxchdp9gghkn1sp9lpiian0iz4y7r67z3wpy"))))
10352 (build-system r-build-system)
10354 `(("r-annotationdbi" ,r-annotationdbi)
10355 ("r-annotationfilter" ,r-annotationfilter)
10356 ("r-biobase" ,r-biobase)
10357 ("r-biocgenerics" ,r-biocgenerics)
10358 ("r-biostrings" ,r-biostrings)
10361 ("r-genomeinfodb" ,r-genomeinfodb)
10362 ("r-genomicfeatures" ,r-genomicfeatures)
10363 ("r-genomicranges" ,r-genomicranges)
10364 ("r-iranges" ,r-iranges)
10365 ("r-protgenerics" ,r-protgenerics)
10366 ("r-rsamtools" ,r-rsamtools)
10367 ("r-rsqlite" ,r-rsqlite)
10368 ("r-rtracklayer" ,r-rtracklayer)
10369 ("r-s4vectors" ,r-s4vectors)))
10371 `(("r-knitr" ,r-knitr)))
10372 (home-page "https://github.com/jotsetung/ensembldb")
10373 (synopsis "Utilities to create and use Ensembl-based annotation databases")
10375 "The package provides functions to create and use transcript-centric
10376 annotation databases/packages. The annotation for the databases are directly
10377 fetched from Ensembl using their Perl API. The functionality and data is
10378 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
10379 but, in addition to retrieve all gene/transcript models and annotations from
10380 the database, the @code{ensembldb} package also provides a filter framework
10381 allowing to retrieve annotations for specific entries like genes encoded on a
10382 chromosome region or transcript models of lincRNA genes.")
10383 ;; No version specified
10384 (license license:lgpl3+)))
10386 (define-public r-organismdbi
10388 (name "r-organismdbi")
10393 (uri (bioconductor-uri "OrganismDbi" version))
10396 "1mklnzs0d0ygcdibwfnk5xqr8ln6wpa00qcaw9c68m342kql0jqw"))))
10397 (properties `((upstream-name . "OrganismDbi")))
10398 (build-system r-build-system)
10400 `(("r-annotationdbi" ,r-annotationdbi)
10401 ("r-biobase" ,r-biobase)
10402 ("r-biocgenerics" ,r-biocgenerics)
10403 ("r-biocmanager" ,r-biocmanager)
10405 ("r-genomicfeatures" ,r-genomicfeatures)
10406 ("r-genomicranges" ,r-genomicranges)
10407 ("r-graph" ,r-graph)
10408 ("r-iranges" ,r-iranges)
10410 ("r-s4vectors" ,r-s4vectors)))
10411 (home-page "https://bioconductor.org/packages/OrganismDbi")
10412 (synopsis "Software to enable the smooth interfacing of database packages")
10413 (description "The package enables a simple unified interface to several
10414 annotation packages each of which has its own schema by taking advantage of
10415 the fact that each of these packages implements a select methods.")
10416 (license license:artistic2.0)))
10418 (define-public r-biovizbase
10420 (name "r-biovizbase")
10425 (uri (bioconductor-uri "biovizBase" version))
10428 "10jflvadfcgxq2jnfxkpn417xd8ibh3zllz9rsqnq5w3wgfr4fhq"))))
10429 (properties `((upstream-name . "biovizBase")))
10430 (build-system r-build-system)
10432 `(("r-annotationdbi" ,r-annotationdbi)
10433 ("r-annotationfilter" ,r-annotationfilter)
10434 ("r-biocgenerics" ,r-biocgenerics)
10435 ("r-biostrings" ,r-biostrings)
10436 ("r-dichromat" ,r-dichromat)
10437 ("r-ensembldb" ,r-ensembldb)
10438 ("r-genomeinfodb" ,r-genomeinfodb)
10439 ("r-genomicalignments" ,r-genomicalignments)
10440 ("r-genomicfeatures" ,r-genomicfeatures)
10441 ("r-genomicranges" ,r-genomicranges)
10442 ("r-hmisc" ,r-hmisc)
10443 ("r-iranges" ,r-iranges)
10444 ("r-rcolorbrewer" ,r-rcolorbrewer)
10445 ("r-rlang" ,r-rlang)
10446 ("r-rsamtools" ,r-rsamtools)
10447 ("r-s4vectors" ,r-s4vectors)
10448 ("r-scales" ,r-scales)
10449 ("r-summarizedexperiment" ,r-summarizedexperiment)
10450 ("r-variantannotation" ,r-variantannotation)))
10451 (home-page "https://bioconductor.org/packages/biovizBase")
10452 (synopsis "Basic graphic utilities for visualization of genomic data")
10454 "The biovizBase package is designed to provide a set of utilities, color
10455 schemes and conventions for genomic data. It serves as the base for various
10456 high-level packages for biological data visualization. This saves development
10457 effort and encourages consistency.")
10458 (license license:artistic2.0)))
10460 (define-public r-ggbio
10467 (uri (bioconductor-uri "ggbio" version))
10470 "0vabil4jzrlv01aibqjhdkvrv2bf2kkpsidrkjj06isqr5fz54lw"))))
10471 (build-system r-build-system)
10474 (modify-phases %standard-phases
10475 ;; See https://github.com/tengfei/ggbio/issues/117
10476 ;; This fix will be included in the next release.
10477 (add-after 'unpack 'fix-typo
10479 (substitute* "R/GGbio-class.R"
10480 (("fechable") "fetchable"))
10483 `(("r-annotationdbi" ,r-annotationdbi)
10484 ("r-annotationfilter" ,r-annotationfilter)
10485 ("r-biobase" ,r-biobase)
10486 ("r-biocgenerics" ,r-biocgenerics)
10487 ("r-biostrings" ,r-biostrings)
10488 ("r-biovizbase" ,r-biovizbase)
10489 ("r-bsgenome" ,r-bsgenome)
10490 ("r-ensembldb" ,r-ensembldb)
10491 ("r-genomeinfodb" ,r-genomeinfodb)
10492 ("r-genomicalignments" ,r-genomicalignments)
10493 ("r-genomicfeatures" ,r-genomicfeatures)
10494 ("r-genomicranges" ,r-genomicranges)
10495 ("r-ggally" ,r-ggally)
10496 ("r-ggplot2" ,r-ggplot2)
10497 ("r-gridextra" ,r-gridextra)
10498 ("r-gtable" ,r-gtable)
10499 ("r-hmisc" ,r-hmisc)
10500 ("r-iranges" ,r-iranges)
10501 ("r-organismdbi" ,r-organismdbi)
10502 ("r-reshape2" ,r-reshape2)
10503 ("r-rlang" ,r-rlang)
10504 ("r-rsamtools" ,r-rsamtools)
10505 ("r-rtracklayer" ,r-rtracklayer)
10506 ("r-s4vectors" ,r-s4vectors)
10507 ("r-scales" ,r-scales)
10508 ("r-summarizedexperiment" ,r-summarizedexperiment)
10509 ("r-variantannotation" ,r-variantannotation)))
10511 `(("r-knitr" ,r-knitr)))
10512 (home-page "http://www.tengfei.name/ggbio/")
10513 (synopsis "Visualization tools for genomic data")
10515 "The ggbio package extends and specializes the grammar of graphics for
10516 biological data. The graphics are designed to answer common scientific
10517 questions, in particular those often asked of high throughput genomics data.
10518 All core Bioconductor data structures are supported, where appropriate. The
10519 package supports detailed views of particular genomic regions, as well as
10520 genome-wide overviews. Supported overviews include ideograms and grand linear
10521 views. High-level plots include sequence fragment length, edge-linked
10522 interval to data view, mismatch pileup, and several splicing summaries.")
10523 (license license:artistic2.0)))
10525 (define-public r-gqtlbase
10527 (name "r-gqtlbase")
10532 (uri (bioconductor-uri "gQTLBase" version))
10535 "1ly14vhhqxjpbxjypi6ppd37dycabdhf4ny4nsvp9969k418zv41"))))
10536 (properties `((upstream-name . "gQTLBase")))
10537 (build-system r-build-system)
10539 `(("r-batchjobs" ,r-batchjobs)
10540 ("r-bbmisc" ,r-bbmisc)
10541 ("r-biocgenerics" ,r-biocgenerics)
10543 ("r-doparallel" ,r-doparallel)
10545 ("r-ffbase" ,r-ffbase)
10546 ("r-foreach" ,r-foreach)
10547 ("r-genomicfiles" ,r-genomicfiles)
10548 ("r-genomicranges" ,r-genomicranges)
10549 ("r-rtracklayer" ,r-rtracklayer)
10550 ("r-s4vectors" ,r-s4vectors)
10551 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10553 `(("r-knitr" ,r-knitr)))
10554 (home-page "https://bioconductor.org/packages/gQTLBase")
10555 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10557 "The purpose of this package is to simplify the storage and interrogation
10558 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10560 (license license:artistic2.0)))
10562 (define-public r-snpstats
10564 (name "r-snpstats")
10569 (uri (bioconductor-uri "snpStats" version))
10572 "1298a71swwav53yf9kfqkdpach3818plqcbw0lgb6sibs8y8ff24"))))
10573 (properties `((upstream-name . "snpStats")))
10574 (build-system r-build-system)
10575 (inputs `(("zlib" ,zlib)))
10577 `(("r-biocgenerics" ,r-biocgenerics)
10578 ("r-matrix" ,r-matrix)
10579 ("r-survival" ,r-survival)
10580 ("r-zlibbioc" ,r-zlibbioc)))
10581 (home-page "https://bioconductor.org/packages/snpStats")
10582 (synopsis "Methods for SNP association studies")
10584 "This package provides classes and statistical methods for large
10585 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10586 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10587 (license license:gpl3)))
10589 (define-public r-homo-sapiens
10591 (name "r-homo-sapiens")
10595 ;; We cannot use bioconductor-uri here because this tarball is
10596 ;; located under "data/annotation/" instead of "bioc/".
10597 (uri (string-append "https://www.bioconductor.org/packages/"
10598 "release/data/annotation/src/contrib/"
10600 version ".tar.gz"))
10603 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10605 `((upstream-name . "Homo.sapiens")))
10606 (build-system r-build-system)
10608 `(("r-genomicfeatures" ,r-genomicfeatures)
10609 ("r-go-db" ,r-go-db)
10610 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10611 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10612 ("r-organismdbi" ,r-organismdbi)
10613 ("r-annotationdbi" ,r-annotationdbi)))
10614 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10615 (synopsis "Annotation package for the Homo.sapiens object")
10617 "This package contains the Homo.sapiens object to access data from
10618 several related annotation packages.")
10619 (license license:artistic2.0)))
10621 (define-public r-erma
10628 (uri (bioconductor-uri "erma" version))
10631 "1k2j1xhv0vwn45xmh8ds0gz812px5hnpgzvp37ngsdn4j5ai1l0k"))))
10632 (build-system r-build-system)
10634 `(("r-annotationdbi" ,r-annotationdbi)
10635 ("r-biobase" ,r-biobase)
10636 ("r-biocgenerics" ,r-biocgenerics)
10637 ("r-biocparallel" ,r-biocparallel)
10638 ("r-genomeinfodb" ,r-genomeinfodb)
10639 ("r-genomicfiles" ,r-genomicfiles)
10640 ("r-genomicranges" ,r-genomicranges)
10641 ("r-ggplot2" ,r-ggplot2)
10642 ("r-homo-sapiens" ,r-homo-sapiens)
10643 ("r-iranges" ,r-iranges)
10644 ("r-rtracklayer" ,r-rtracklayer)
10645 ("r-s4vectors" ,r-s4vectors)
10646 ("r-shiny" ,r-shiny)
10647 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10649 `(("r-knitr" ,r-knitr)))
10650 (home-page "https://bioconductor.org/packages/erma")
10651 (synopsis "Epigenomic road map adventures")
10653 "The epigenomics road map describes locations of epigenetic marks in DNA
10654 from a variety of cell types. Of interest are locations of histone
10655 modifications, sites of DNA methylation, and regions of accessible chromatin.
10656 This package presents a selection of elements of the road map including
10657 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10658 by Ernst and Kellis.")
10659 (license license:artistic2.0)))
10661 (define-public r-ldblock
10668 (uri (bioconductor-uri "ldblock" version))
10671 "09i3ikv0axks9g842z1pjsc8x0fba51zyyc218h0bylbi1n9cdkm"))))
10672 (build-system r-build-system)
10674 `(("r-biocgenerics" ,r-biocgenerics)
10675 ("r-ensdb-hsapiens-v75" ,r-ensdb-hsapiens-v75)
10676 ("r-ensembldb" ,r-ensembldb)
10677 ("r-genomeinfodb" ,r-genomeinfodb)
10678 ("r-genomicfiles" ,r-genomicfiles)
10680 ("r-matrix" ,r-matrix)
10681 ("r-rsamtools" ,r-rsamtools)
10682 ("r-snpstats" ,r-snpstats)
10683 ("r-variantannotation" ,r-variantannotation)))
10685 `(("r-knitr" ,r-knitr)))
10686 (home-page "https://bioconductor.org/packages/ldblock")
10687 (synopsis "Data structures for linkage disequilibrium measures in populations")
10689 "This package defines data structures for @dfn{linkage
10690 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10691 handling of existing population-level data for the purpose of flexibly
10692 defining LD blocks.")
10693 (license license:artistic2.0)))
10695 (define-public r-gqtlstats
10697 (name "r-gqtlstats")
10702 (uri (bioconductor-uri "gQTLstats" version))
10705 "1jjqfpjp93nmxjn757j5mzcax96bzcqdd1gr3rsdxg7ap008l2w7"))))
10706 (properties `((upstream-name . "gQTLstats")))
10707 (build-system r-build-system)
10709 `(("r-annotationdbi" ,r-annotationdbi)
10710 ("r-batchjobs" ,r-batchjobs)
10711 ("r-bbmisc" ,r-bbmisc)
10712 ("r-beeswarm" ,r-beeswarm)
10713 ("r-biobase" ,r-biobase)
10714 ("r-biocgenerics" ,r-biocgenerics)
10715 ("r-doparallel" ,r-doparallel)
10716 ("r-dplyr" ,r-dplyr)
10718 ("r-ffbase" ,r-ffbase)
10719 ("r-foreach" ,r-foreach)
10720 ("r-genomeinfodb" ,r-genomeinfodb)
10721 ("r-genomicfeatures" ,r-genomicfeatures)
10722 ("r-genomicfiles" ,r-genomicfiles)
10723 ("r-genomicranges" ,r-genomicranges)
10724 ("r-ggbeeswarm" ,r-ggbeeswarm)
10725 ("r-ggplot2" ,r-ggplot2)
10726 ("r-gqtlbase" ,r-gqtlbase)
10727 ("r-hardyweinberg" ,r-hardyweinberg)
10728 ("r-homo-sapiens" ,r-homo-sapiens)
10729 ("r-iranges" ,r-iranges)
10730 ("r-limma" ,r-limma)
10732 ("r-plotly" ,r-plotly)
10733 ("r-reshape2" ,r-reshape2)
10734 ("r-s4vectors" ,r-s4vectors)
10735 ("r-shiny" ,r-shiny)
10736 ("r-snpstats" ,r-snpstats)
10737 ("r-summarizedexperiment" ,r-summarizedexperiment)
10738 ("r-variantannotation" ,r-variantannotation)))
10740 `(("r-knitr" ,r-knitr)))
10741 (home-page "https://bioconductor.org/packages/gQTLstats")
10742 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10744 "This package provides tools for the computationally efficient analysis
10745 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10746 The software in this package aims to support refinements and functional
10747 interpretation of members of a collection of association statistics on a
10748 family of feature/genome hypotheses.")
10749 (license license:artistic2.0)))
10751 (define-public r-gviz
10758 (uri (bioconductor-uri "Gviz" version))
10761 "0v7bz46b91dnrr55ah42ljj1i2xs3090s4w0lw8098pag00p4vh2"))))
10762 (properties `((upstream-name . "Gviz")))
10763 (build-system r-build-system)
10765 `(("r-annotationdbi" ,r-annotationdbi)
10766 ("r-biobase" ,r-biobase)
10767 ("r-biocgenerics" ,r-biocgenerics)
10768 ("r-biomart" ,r-biomart)
10769 ("r-biostrings" ,r-biostrings)
10770 ("r-biovizbase" ,r-biovizbase)
10771 ("r-bsgenome" ,r-bsgenome)
10772 ("r-digest" ,r-digest)
10773 ("r-ensembldb" ,r-ensembldb)
10774 ("r-genomeinfodb" ,r-genomeinfodb)
10775 ("r-genomicalignments" ,r-genomicalignments)
10776 ("r-genomicfeatures" ,r-genomicfeatures)
10777 ("r-genomicranges" ,r-genomicranges)
10778 ("r-iranges" ,r-iranges)
10779 ("r-lattice" ,r-lattice)
10780 ("r-latticeextra" ,r-latticeextra)
10781 ("r-matrixstats" ,r-matrixstats)
10782 ("r-rcolorbrewer" ,r-rcolorbrewer)
10783 ("r-rsamtools" ,r-rsamtools)
10784 ("r-rtracklayer" ,r-rtracklayer)
10785 ("r-s4vectors" ,r-s4vectors)
10786 ("r-xvector" ,r-xvector)))
10788 `(("r-knitr" ,r-knitr)))
10789 (home-page "https://bioconductor.org/packages/Gviz")
10790 (synopsis "Plotting data and annotation information along genomic coordinates")
10792 "Genomic data analyses requires integrated visualization of known genomic
10793 information and new experimental data. Gviz uses the biomaRt and the
10794 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10795 and translates this to e.g. gene/transcript structures in viewports of the
10796 grid graphics package. This results in genomic information plotted together
10798 (license license:artistic2.0)))
10800 (define-public r-gwascat
10807 (uri (bioconductor-uri "gwascat" version))
10810 "1aqi1ny93virnzsxkh9ccx3mws70bgv0r8nwgla09vffb7f16nna"))))
10811 (build-system r-build-system)
10813 `(("r-annotationdbi" ,r-annotationdbi)
10814 ("r-biocfilecache" ,r-biocfilecache)
10815 ("r-biostrings" ,r-biostrings)
10816 ("r-genomeinfodb" ,r-genomeinfodb)
10817 ("r-genomicfeatures" ,r-genomicfeatures)
10818 ("r-genomicranges" ,r-genomicranges)
10819 ("r-iranges" ,r-iranges)
10820 ("r-readr" ,r-readr)
10821 ("r-s4vectors" ,r-s4vectors)
10822 ("r-snpstats" ,r-snpstats)
10823 ("r-variantannotation" ,r-variantannotation)))
10825 `(("r-knitr" ,r-knitr)))
10826 (home-page "https://bioconductor.org/packages/gwascat")
10827 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10829 "This package provides tools for representing and modeling data in the
10830 EMBL-EBI GWAS catalog.")
10831 (license license:artistic2.0)))
10833 (define-public r-sushi
10839 (uri (bioconductor-uri "Sushi" version))
10842 "17j3d5qjq5nbv99by5mq8rwr0jgh2jyyfn2nwxmwgzlmk3lgi1rb"))))
10843 (properties `((upstream-name . "Sushi")))
10844 (build-system r-build-system)
10846 `(("r-biomart" ,r-biomart)
10848 (home-page "https://bioconductor.org/packages/Sushi")
10849 (synopsis "Tools for visualizing genomics data")
10851 "This package provides flexible, quantitative, and integrative genomic
10852 visualizations for publication-quality multi-panel figures.")
10853 (license license:gpl2+)))
10855 (define-public r-dropbead
10856 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
10859 (name "r-dropbead")
10860 (version (string-append "0-" revision "." (string-take commit 7)))
10864 (uri (git-reference
10865 (url "https://github.com/rajewsky-lab/dropbead")
10867 (file-name (git-file-name name version))
10870 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
10871 (build-system r-build-system)
10873 `(("r-ggplot2" ,r-ggplot2)
10874 ("r-rcolorbrewer" ,r-rcolorbrewer)
10875 ("r-gridextra" ,r-gridextra)
10876 ("r-gplots" ,r-gplots)
10877 ("r-plyr" ,r-plyr)))
10878 (home-page "https://github.com/rajewsky-lab/dropbead")
10879 (synopsis "Basic exploration and analysis of Drop-seq data")
10880 (description "This package offers a quick and straight-forward way to
10881 explore and perform basic analysis of single cell sequencing data coming from
10882 droplet sequencing. It has been particularly tailored for Drop-seq.")
10883 (license license:gpl3))))
10885 (define htslib-for-sambamba
10886 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
10889 (name "htslib-for-sambamba")
10890 (version (string-append "1.3.1-1." (string-take commit 9)))
10894 (uri (git-reference
10895 (url "https://github.com/lomereiter/htslib")
10897 (file-name (string-append "htslib-" version "-checkout"))
10900 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
10902 `(("autoconf" ,autoconf)
10903 ("automake" ,automake)
10904 ,@(package-native-inputs htslib))))))
10906 (define-public sambamba
10913 (uri (git-reference
10914 (url "https://github.com/lomereiter/sambamba")
10915 (commit (string-append "v" version))))
10916 (file-name (string-append name "-" version "-checkout"))
10919 "111h05b60pj8dxbidiamy4imc92x2962b3lmb7wgysl6lx064qis"))))
10920 (build-system gnu-build-system)
10922 `(#:tests? #f ; there is no test target
10923 #:parallel-build? #f ; not supported
10925 (modify-phases %standard-phases
10926 (delete 'configure)
10927 (add-after 'unpack 'fix-ldc-version
10929 (substitute* "gen_ldc_version_info.py"
10930 (("/usr/bin/env.*") (which "python3")))
10931 (substitute* "Makefile"
10932 ;; We use ldc2 instead of ldmd2 to compile sambamba.
10933 (("\\$\\(shell which ldmd2\\)") (which "ldc2")))
10935 (add-after 'unpack 'place-biod-and-undead
10936 (lambda* (#:key inputs #:allow-other-keys)
10937 (copy-recursively (assoc-ref inputs "biod") "BioD")
10939 (add-after 'unpack 'unbundle-prerequisites
10941 (substitute* "Makefile"
10942 (("htslib/libhts.a lz4/lib/liblz4.a")
10944 ((" lz4-static htslib-static") ""))
10947 (lambda* (#:key outputs #:allow-other-keys)
10948 (let* ((out (assoc-ref outputs "out"))
10949 (bin (string-append out "/bin")))
10951 (copy-file (string-append "bin/sambamba-" ,version)
10952 (string-append bin "/sambamba"))
10959 ,(let ((commit "7969eb0a847b05874e83ffddead26e193ece8101"))
10962 (uri (git-reference
10963 (url "https://github.com/biod/BioD")
10965 (file-name (string-append "biod-"
10966 (string-take commit 9)
10970 "0mjxsmbmv0jxl3pq21p8j5r829d648if8q58ka50b2956lc6qkpm")))))))
10973 ("htslib" ,htslib-for-sambamba)))
10974 (home-page "https://lomereiter.github.io/sambamba/")
10975 (synopsis "Tools for working with SAM/BAM data")
10976 (description "Sambamba is a high performance modern robust and
10977 fast tool (and library), written in the D programming language, for
10978 working with SAM and BAM files. Current parallelised functionality is
10979 an important subset of samtools functionality, including view, index,
10980 sort, markdup, and depth.")
10981 (license license:gpl2+)))
10983 (define-public ritornello
10985 (name "ritornello")
10989 (uri (git-reference
10990 (url "https://github.com/KlugerLab/Ritornello")
10991 (commit (string-append "v" version))))
10992 (file-name (git-file-name name version))
10995 "1xahvq215qld7x1w8vpa5zbrsj6p9crb9shqa2x89sb0aaxa02jk"))))
10996 (build-system gnu-build-system)
10998 `(#:tests? #f ; there are no tests
11000 (modify-phases %standard-phases
11001 (add-after 'unpack 'patch-samtools-references
11002 (lambda* (#:key inputs #:allow-other-keys)
11003 (substitute* '("src/SamStream.h"
11005 (("<sam.h>") "<samtools/sam.h>"))
11007 (delete 'configure)
11009 (lambda* (#:key inputs outputs #:allow-other-keys)
11010 (let* ((out (assoc-ref outputs "out"))
11011 (bin (string-append out "/bin/")))
11013 (install-file "bin/Ritornello" bin)
11016 `(("samtools" ,samtools-0.1)
11020 (home-page "https://github.com/KlugerLab/Ritornello")
11021 (synopsis "Control-free peak caller for ChIP-seq data")
11022 (description "Ritornello is a ChIP-seq peak calling algorithm based on
11023 signal processing that can accurately call binding events without the need to
11024 do a pair total DNA input or IgG control sample. It has been tested for use
11025 with narrow binding events such as transcription factor ChIP-seq.")
11026 (license license:gpl3+)))
11028 (define-public trim-galore
11030 (name "trim-galore")
11035 (uri (git-reference
11036 (url "https://github.com/FelixKrueger/TrimGalore")
11038 (file-name (git-file-name name version))
11041 "1y31wbxwkm9xqzr5zv1pk5q418whnmlmgmfyxxpnl12h83m2i9iv"))))
11042 (build-system gnu-build-system)
11044 `(#:tests? #f ; no tests
11046 (modify-phases %standard-phases
11047 (replace 'configure
11049 ;; Trim Galore tries to figure out what version of Python
11050 ;; cutadapt is using by looking at the shebang. Of course that
11051 ;; doesn't work, because cutadapt is wrapped in a shell script.
11052 (substitute* "trim_galore"
11053 (("my \\$python_return.*")
11054 "my $python_return = \"Python 3.999\";\n"))
11057 (add-after 'unpack 'hardcode-tool-references
11058 (lambda* (#:key inputs #:allow-other-keys)
11059 (substitute* "trim_galore"
11060 (("\\$path_to_cutadapt = 'cutadapt'")
11061 (string-append "$path_to_cutadapt = '"
11062 (assoc-ref inputs "cutadapt")
11064 (("\\$compression_path = \"gzip\"")
11065 (string-append "$compression_path = \""
11066 (assoc-ref inputs "gzip")
11069 (string-append "\""
11070 (assoc-ref inputs "gzip")
11073 (string-append "\""
11074 (assoc-ref inputs "pigz")
11078 (lambda* (#:key outputs #:allow-other-keys)
11079 (let ((bin (string-append (assoc-ref outputs "out")
11082 (install-file "trim_galore" bin)
11088 ("cutadapt" ,cutadapt)))
11090 `(("unzip" ,unzip)))
11091 (home-page "https://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
11092 (synopsis "Wrapper around Cutadapt and FastQC")
11093 (description "Trim Galore! is a wrapper script to automate quality and
11094 adapter trimming as well as quality control, with some added functionality to
11095 remove biased methylation positions for RRBS sequence files.")
11096 (license license:gpl3+)))
11098 (define-public gess
11104 (uri (string-append "http://compbio.uthscsa.edu/"
11106 "gess-" version ".src.tar.gz"))
11109 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
11110 (build-system gnu-build-system)
11112 `(#:tests? #f ; no tests
11114 (modify-phases %standard-phases
11115 (delete 'configure)
11118 (lambda* (#:key inputs outputs #:allow-other-keys)
11119 (let* ((python (assoc-ref inputs "python"))
11120 (out (assoc-ref outputs "out"))
11121 (bin (string-append out "/bin/"))
11122 (target (string-append
11124 ,(version-major+minor
11125 (package-version python))
11126 "/site-packages/gess/")))
11128 (copy-recursively "." target)
11129 ;; Make GESS.py executable
11130 (chmod (string-append target "GESS.py") #o555)
11131 ;; Add Python shebang to the top and make Matplotlib
11133 (substitute* (string-append target "GESS.py")
11134 (("\"\"\"Description:" line)
11135 (string-append "#!" (which "python") "
11137 matplotlib.use('Agg')
11139 ;; Make sure GESS has all modules in its path
11140 (wrap-script (string-append target "GESS.py")
11141 `("PYTHONPATH" ":" = (,target ,(getenv "PYTHONPATH"))))
11143 (symlink (string-append target "GESS.py")
11144 (string-append bin "GESS.py"))
11147 `(("python" ,python-2)
11148 ("python2-pysam" ,python2-pysam)
11149 ("python2-scipy" ,python2-scipy)
11150 ("python2-numpy" ,python2-numpy)
11151 ("python2-networkx" ,python2-networkx)
11152 ("python2-biopython" ,python2-biopython)
11153 ("guile" ,guile-3.0))) ; for the script wrapper
11154 (home-page "https://compbio.uthscsa.edu/GESS_Web/")
11155 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11157 "GESS is an implementation of a novel computational method to detect de
11158 novo exon-skipping events directly from raw RNA-seq data without the prior
11159 knowledge of gene annotation information. GESS stands for the graph-based
11160 exon-skipping scanner detection scheme.")
11161 (license license:bsd-3)))
11163 (define-public phylip
11170 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11171 "download/phylip-" version ".tar.gz"))
11174 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11175 (build-system gnu-build-system)
11177 `(#:tests? #f ; no check target
11178 #:make-flags (list "-f" "Makefile.unx" "install")
11179 #:parallel-build? #f ; not supported
11181 (modify-phases %standard-phases
11182 (add-after 'unpack 'enter-dir
11183 (lambda _ (chdir "src") #t))
11184 (delete 'configure)
11186 (lambda* (#:key inputs outputs #:allow-other-keys)
11187 (let ((target (string-append (assoc-ref outputs "out")
11190 (for-each (lambda (file)
11191 (install-file file target))
11192 (find-files "../exe" ".*")))
11194 (home-page "http://evolution.genetics.washington.edu/phylip/")
11195 (synopsis "Tools for inferring phylogenies")
11196 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11197 programs for inferring phylogenies (evolutionary trees).")
11198 (license license:bsd-2)))
11207 (uri (string-append "https://integrativemodeling.org/"
11208 version "/download/imp-" version ".tar.gz"))
11211 "1z1vcpwbylixk0zywngg5iw0jv083jj1bqphi817jpg3fb9fx2jj"))))
11212 (build-system cmake-build-system)
11214 `( ;; CMake 3.17 or newer is required for the CMAKE_TEST_ARGUMENTS used
11215 ;; below to have an effect.
11218 (let ((disabled-tests
11219 '("expensive" ;exclude expensive tests
11220 "IMP.modeller" ;fail to import its own modules
11221 "IMP.parallel-test_sge.py" ;fail in build container
11222 ;; The following test fails non-reproducibly on
11223 ;; an inexact numbers assertion.
11224 "IMP.em-medium_test_local_fitting.py")))
11227 "-DCMAKE_CTEST_ARGUMENTS="
11229 (list "-L" "-tests?-" ;select only tests
11230 "-E" (format #f "'(~a)'" (string-join disabled-tests "|")))
11233 `(("python" ,python-wrapper)
11242 ;; Enabling MPI causes the build to use all the available memory and
11243 ;; fail (tested on a machine with 32 GiB of RAM).
11245 ("opencv" ,opencv)))
11247 `(("python-numpy" ,python-numpy)
11248 ("python-scipy" ,python-scipy)
11249 ("python-pandas" ,python-pandas)
11250 ("python-scikit-learn" ,python-scikit-learn)
11251 ("python-networkx" ,python-networkx)))
11252 (home-page "https://integrativemodeling.org")
11253 (synopsis "Integrative modeling platform")
11254 (description "IMP's broad goal is to contribute to a comprehensive
11255 structural characterization of biomolecules ranging in size and complexity
11256 from small peptides to large macromolecular assemblies, by integrating data
11257 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11258 Python toolbox for solving complex modeling problems, and a number of
11259 applications for tackling some common problems in a user-friendly way.")
11260 ;; IMP is largely available under the GNU Lesser GPL; see the file
11261 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11262 ;; available under the GNU GPL (see the file COPYING.GPL).
11263 (license (list license:lgpl2.1+
11266 (define-public tadbit
11272 (uri (git-reference
11273 (url "https://github.com/3DGenomes/TADbit")
11274 (commit (string-append "v" version))))
11275 (file-name (git-file-name name version))
11278 "0hqrlymh2a2bimcfdvlssy1x5h1lp3h1c5a7jj11hmcqczzqn3ni"))))
11279 (build-system python-build-system)
11282 (modify-phases %standard-phases
11283 (add-after 'unpack 'fix-problems-with-setup.py
11284 (lambda* (#:key outputs #:allow-other-keys)
11285 ;; Don't attempt to install the bash completions to
11286 ;; the home directory.
11287 (rename-file "extras/.bash_completion"
11289 (substitute* "setup.py"
11290 (("\\(path.expanduser\\('~'\\)")
11291 (string-append "(\""
11292 (assoc-ref outputs "out")
11293 "/etc/bash_completion.d\""))
11294 (("extras/\\.bash_completion")
11298 (lambda* (#:key inputs outputs #:allow-other-keys)
11299 (add-installed-pythonpath inputs outputs)
11300 (invoke "python3" "test/test_all.py")
11303 `(("glib" ,glib "bin") ;for gtester
11304 ("pkg-config" ,pkg-config)))
11306 ;; TODO: add Chimera for visualization
11309 ("python-future" ,python-future)
11310 ("python-h5py" ,python-h5py)
11311 ("python-scipy" ,python-scipy)
11312 ("python-numpy" ,python-numpy)
11313 ("python-matplotlib" ,python-matplotlib)
11314 ("python-pysam" ,python-pysam)))
11315 (home-page "https://3dgenomes.github.io/TADbit/")
11316 (synopsis "Analyze, model, and explore 3C-based data")
11318 "TADbit is a complete Python library to deal with all steps to analyze,
11319 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11320 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11321 correct interaction matrices, identify and compare the so-called
11322 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11323 interaction matrices, and finally, extract structural properties from the
11324 models. TADbit is complemented by TADkit for visualizing 3D models.")
11325 (license license:gpl3+)))
11327 (define-public kentutils
11330 ;; 302.1.0 is out, but the only difference is the inclusion of
11331 ;; pre-built binaries.
11332 (version "302.0.0")
11336 (uri (git-reference
11337 (url "https://github.com/ENCODE-DCC/kentUtils")
11338 (commit (string-append "v" version))))
11339 (file-name (git-file-name name version))
11342 "0n1wbyjpzii2b9qhyp9r1q76j623cggpg3y8fmw78ld3z4y7ivha"))
11343 (modules '((guix build utils)
11348 ;; Only the contents of the specified directories are free
11349 ;; for all uses, so we remove the rest. "hg/autoSql" and
11350 ;; "hg/autoXml" are nominally free, but they depend on a
11351 ;; library that is built from the sources in "hg/lib",
11352 ;; which is nonfree.
11353 (let ((free (list "." ".."
11354 "utils" "lib" "inc" "tagStorm"
11355 "parasol" "htslib"))
11356 (directory? (lambda (file)
11357 (eq? 'directory (stat:type (stat file))))))
11358 (for-each (lambda (file)
11359 (and (directory? file)
11360 (delete-file-recursively file)))
11361 (map (cut string-append "src/" <>)
11364 (not (member file free)))))))
11365 ;; Only make the utils target, not the userApps target,
11366 ;; because that requires libraries we won't build.
11367 (substitute* "Makefile"
11368 ((" userApps") " utils"))
11369 ;; Only build libraries that are free.
11370 (substitute* "src/makefile"
11371 (("DIRS =.*") "DIRS =\n")
11372 (("cd jkOwnLib.*") "")
11375 (substitute* "src/utils/makefile"
11376 ;; These tools depend on "jkhgap.a", which is part of the
11377 ;; nonfree "src/hg/lib" directory.
11378 (("raSqlQuery") "")
11379 (("pslLiftSubrangeBlat") "")
11381 ;; Do not build UCSC tools, which may require nonfree
11383 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11385 (build-system gnu-build-system)
11387 `( ;; There is no global test target and the test target for
11388 ;; individual tools depends on input files that are not
11392 (modify-phases %standard-phases
11393 (add-after 'unpack 'fix-permissions
11394 (lambda _ (make-file-writable "src/inc/localEnvironment.mk") #t))
11395 (add-after 'unpack 'fix-paths
11397 (substitute* "Makefile"
11398 (("/bin/echo") (which "echo")))
11400 (add-after 'unpack 'prepare-samtabix
11401 (lambda* (#:key inputs #:allow-other-keys)
11402 (copy-recursively (assoc-ref inputs "samtabix")
11405 (delete 'configure)
11407 (lambda* (#:key outputs #:allow-other-keys)
11408 (let ((bin (string-append (assoc-ref outputs "out")
11410 (copy-recursively "bin" bin))
11416 (uri (git-reference
11417 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11418 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11421 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11427 ("mariadb-dev" ,mariadb "dev")
11428 ("openssl" ,openssl-1.0)))
11429 (home-page "https://genome.cse.ucsc.edu/index.html")
11430 (synopsis "Assorted bioinformatics utilities")
11431 (description "This package provides the kentUtils, a selection of
11432 bioinformatics utilities used in combination with the UCSC genome
11434 ;; Only a subset of the sources are released under a non-copyleft
11435 ;; free software license. All other sources are removed in a
11436 ;; snippet. See this bug report for an explanation of how the
11437 ;; license statements apply:
11438 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11439 (license (license:non-copyleft
11440 "http://genome.ucsc.edu/license/"
11441 "The contents of this package are free for all uses."))))
11443 (define-public f-seq
11444 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11448 (version (string-append "1.1-" revision "." (string-take commit 7)))
11451 (uri (git-reference
11452 (url "https://github.com/aboyle/F-seq")
11454 (file-name (string-append name "-" version))
11457 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11458 (modules '((guix build utils)))
11459 ;; Remove bundled Java library archives.
11462 (for-each delete-file (find-files "lib" ".*"))
11464 (build-system ant-build-system)
11466 `(#:tests? #f ; no tests included
11468 (modify-phases %standard-phases
11470 (lambda* (#:key inputs outputs #:allow-other-keys)
11471 (let* ((target (assoc-ref outputs "out"))
11472 (bin (string-append target "/bin"))
11473 (doc (string-append target "/share/doc/f-seq"))
11474 (lib (string-append target "/lib")))
11477 (substitute* "bin/linux/fseq"
11478 (("java") (which "java"))
11479 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11480 (string-append (assoc-ref inputs "java-commons-cli")
11481 "/share/java/commons-cli.jar"))
11483 (string-append "REALDIR=" bin "\n")))
11484 (install-file "README.txt" doc)
11485 (install-file "bin/linux/fseq" bin)
11486 (install-file "build~/fseq.jar" lib)
11487 (copy-recursively "lib" lib)
11491 ("java-commons-cli" ,java-commons-cli)))
11492 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11493 (synopsis "Feature density estimator for high-throughput sequence tags")
11495 "F-Seq is a software package that generates a continuous tag sequence
11496 density estimation allowing identification of biologically meaningful sites
11497 such as transcription factor binding sites (ChIP-seq) or regions of open
11498 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11500 (license license:gpl3+))))
11502 (define-public bismark
11509 (uri (git-reference
11510 (url "https://github.com/FelixKrueger/Bismark")
11512 (file-name (string-append name "-" version "-checkout"))
11515 "0xchm3rgilj6vfjnyzfzzymfd7djr64sbrmrvs3njbwi66jqbzw9"))))
11516 (build-system perl-build-system)
11518 `(#:tests? #f ; there are no tests
11519 #:modules ((guix build utils)
11522 (guix build perl-build-system))
11524 (modify-phases %standard-phases
11525 ;; The bundled plotly.js is minified.
11526 (add-after 'unpack 'replace-plotly.js
11527 (lambda* (#:key inputs #:allow-other-keys)
11528 (let* ((file (assoc-ref inputs "plotly.js"))
11529 (installed "plotly/plotly.js"))
11530 (let ((minified (open-pipe* OPEN_READ "uglify-js" file)))
11531 (call-with-output-file installed
11532 (cut dump-port minified <>))))
11534 (delete 'configure)
11537 (lambda* (#:key inputs outputs #:allow-other-keys)
11538 (let* ((out (assoc-ref outputs "out"))
11539 (bin (string-append out "/bin"))
11540 (share (string-append out "/share/bismark"))
11541 (docdir (string-append out "/share/doc/bismark"))
11542 (docs '("Docs/Bismark_User_Guide.html"))
11543 (scripts '("bismark"
11544 "bismark_genome_preparation"
11545 "bismark_methylation_extractor"
11548 "coverage2cytosine"
11549 "deduplicate_bismark"
11550 "filter_non_conversion"
11553 "NOMe_filtering")))
11554 (substitute* "bismark2report"
11555 (("\\$RealBin/plotly")
11556 (string-append share "/plotly")))
11560 (for-each (lambda (file) (install-file file bin))
11562 (for-each (lambda (file) (install-file file docdir))
11564 (copy-recursively "Docs/Images" (string-append docdir "/Images"))
11565 (copy-recursively "plotly"
11566 (string-append share "/plotly"))
11568 ;; Fix references to gunzip
11569 (substitute* (map (lambda (file)
11570 (string-append bin "/" file))
11573 (string-append "\"" (assoc-ref inputs "gzip")
11574 "/bin/gunzip -c")))
11578 ("perl-carp" ,perl-carp)
11579 ("perl-getopt-long" ,perl-getopt-long)))
11584 (uri (string-append "https://raw.githubusercontent.com/plotly/plotly.js/"
11585 "v1.39.4/dist/plotly.js"))
11587 (base32 "138mwsr4nf5qif4mrxx286mpnagxd1xwl6k8aidrjgknaqg88zyr"))))
11588 ("uglify-js" ,uglify-js)))
11589 (home-page "https://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11590 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11591 (description "Bismark is a program to map bisulfite treated sequencing
11592 reads to a genome of interest and perform methylation calls in a single step.
11593 The output can be easily imported into a genome viewer, such as SeqMonk, and
11594 enables a researcher to analyse the methylation levels of their samples
11595 straight away. Its main features are:
11598 @item Bisulfite mapping and methylation calling in one single step
11599 @item Supports single-end and paired-end read alignments
11600 @item Supports ungapped and gapped alignments
11601 @item Alignment seed length, number of mismatches etc are adjustable
11602 @item Output discriminates between cytosine methylation in CpG, CHG
11605 (license license:gpl3+)))
11607 (define-public paml
11613 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11614 "paml" version ".tgz"))
11617 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11618 (modules '((guix build utils)))
11619 ;; Remove Windows binaries
11622 (for-each delete-file (find-files "." "\\.exe$"))
11623 ;; Some files in the original tarball have restrictive
11624 ;; permissions, which makes repackaging fail
11625 (for-each (lambda (file) (chmod file #o644)) (find-files "."))
11627 (build-system gnu-build-system)
11629 `(#:tests? #f ; there are no tests
11630 #:make-flags '("CC=gcc")
11632 (modify-phases %standard-phases
11633 (replace 'configure
11635 (substitute* "src/BFdriver.c"
11636 (("/bin/bash") (which "bash")))
11640 (lambda* (#:key outputs #:allow-other-keys)
11641 (let ((tools '("baseml" "basemlg" "codeml"
11642 "pamp" "evolver" "yn00" "chi2"))
11643 (bin (string-append (assoc-ref outputs "out") "/bin"))
11644 (docdir (string-append (assoc-ref outputs "out")
11645 "/share/doc/paml")))
11647 (for-each (lambda (file) (install-file file bin)) tools)
11648 (copy-recursively "../doc" docdir)
11650 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11651 (synopsis "Phylogentic analysis by maximum likelihood")
11652 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11653 contains a few programs for model fitting and phylogenetic tree reconstruction
11654 using nucleotide or amino-acid sequence data.")
11656 (license license:gpl3)))
11658 (define-public kallisto
11664 (uri (git-reference
11665 (url "https://github.com/pachterlab/kallisto")
11666 (commit (string-append "v" version))))
11667 (file-name (git-file-name name version))
11670 "0nj382jiywqnpgvyhichajpkkh5r0bapn43f4dx40zdaq5v4m40m"))))
11671 (build-system cmake-build-system)
11673 `(#:tests? #f ; no "check" target
11675 (modify-phases %standard-phases
11676 (add-after 'unpack 'do-not-use-bundled-htslib
11678 (substitute* "CMakeLists.txt"
11679 (("^ExternalProject_Add" m)
11680 (string-append "if (NEVER)\n" m))
11682 (string-append ")\nendif(NEVER)"))
11683 (("include_directories\\(\\$\\{htslib_PREFIX.*" m)
11684 (string-append "# " m)))
11685 (substitute* "src/CMakeLists.txt"
11686 (("target_link_libraries\\(kallisto kallisto_core pthread \
11687 \\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/../ext/htslib/libhts.a\\)")
11688 "target_link_libraries(kallisto kallisto_core pthread hts)")
11689 (("include_directories\\(\\.\\./ext/htslib\\)") ""))
11695 (home-page "https://pachterlab.github.io/kallisto/")
11696 (synopsis "Near-optimal RNA-Seq quantification")
11698 "Kallisto is a program for quantifying abundances of transcripts from
11699 RNA-Seq data, or more generally of target sequences using high-throughput
11700 sequencing reads. It is based on the novel idea of pseudoalignment for
11701 rapidly determining the compatibility of reads with targets, without the need
11702 for alignment. Pseudoalignment of reads preserves the key information needed
11703 for quantification, and kallisto is therefore not only fast, but also as
11704 accurate as existing quantification tools.")
11705 (license license:bsd-2)))
11707 (define-public libgff
11713 (uri (git-reference
11714 (url "https://github.com/Kingsford-Group/libgff")
11715 (commit (string-append "v" version))))
11716 (file-name (git-file-name name version))
11719 "0n6vfjnq7a2mianipscbshrvbncss8z4zkgkbjw754p9043nfkps"))))
11720 (build-system cmake-build-system)
11721 (arguments `(#:tests? #f)) ; no tests included
11722 (home-page "https://github.com/Kingsford-Group/libgff")
11723 (synopsis "Parser library for reading/writing GFF files")
11724 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11725 code that is used in the Cufflinks codebase. The goal of this library is to
11726 provide this functionality without the necessity of drawing in a heavy-weight
11727 dependency like SeqAn.")
11728 (license (license:x11-style "https://www.boost.org/LICENSE_1_0.txt"))))
11730 (define-public sailfish
11736 (uri (git-reference
11737 (url "https://github.com/kingsfordgroup/sailfish")
11738 (commit (string-append "v" version))))
11739 (file-name (git-file-name name version))
11742 "1amcc5hqvsl42hg4x19bi9vy47cl874s0lw1fmi0hwsdk9i8c03v"))
11743 (modules '((guix build utils)))
11746 ;; Delete bundled headers for eigen3.
11747 (delete-file-recursively "include/eigen3/")
11749 (build-system cmake-build-system)
11751 `(#:configure-flags
11752 (list (string-append "-DBOOST_INCLUDEDIR="
11753 (assoc-ref %build-inputs "boost")
11755 (string-append "-DBOOST_LIBRARYDIR="
11756 (assoc-ref %build-inputs "boost")
11758 (string-append "-DBoost_LIBRARIES="
11759 "-lboost_iostreams "
11760 "-lboost_filesystem "
11765 "-lboost_program_options")
11766 "-DBoost_FOUND=TRUE"
11767 ;; Don't download RapMap---we already have it!
11768 "-DFETCHED_RAPMAP=1")
11769 ;; Tests must be run after installation and the location of the test
11770 ;; data file must be overridden. But the tests fail. It looks like
11771 ;; they are not really meant to be run.
11774 (modify-phases %standard-phases
11775 ;; Boost cannot be found, even though it's right there.
11776 (add-after 'unpack 'do-not-look-for-boost
11777 (lambda* (#:key inputs #:allow-other-keys)
11778 (substitute* "CMakeLists.txt"
11779 (("find_package\\(Boost 1\\.53\\.0") "#"))
11781 (add-after 'unpack 'do-not-assign-to-macro
11783 (substitute* "include/spdlog/details/format.cc"
11784 (("const unsigned CHAR_WIDTH = 1;") ""))
11786 (add-after 'unpack 'prepare-rapmap
11787 (lambda* (#:key inputs #:allow-other-keys)
11788 (let ((src "external/install/src/rapmap/")
11789 (include "external/install/include/rapmap/")
11790 (rapmap (assoc-ref inputs "rapmap")))
11791 (mkdir-p "/tmp/rapmap")
11793 (assoc-ref inputs "rapmap")
11795 "--strip-components=1")
11798 (for-each (lambda (file)
11799 (install-file file src))
11800 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
11801 (copy-recursively "/tmp/rapmap/include" include))
11803 (add-after 'unpack 'use-system-libraries
11804 (lambda* (#:key inputs #:allow-other-keys)
11805 (substitute* '("src/SailfishIndexer.cpp"
11806 "src/SailfishUtils.cpp"
11807 "src/SailfishQuantify.cpp"
11808 "src/FASTAParser.cpp"
11810 "include/SailfishUtils.hpp"
11811 "include/SailfishIndex.hpp"
11812 "include/CollapsedEMOptimizer.hpp"
11813 "src/CollapsedEMOptimizer.cpp")
11814 (("#include \"jellyfish/config.h\"") ""))
11815 (substitute* "src/CMakeLists.txt"
11816 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11817 (string-append (assoc-ref inputs "jellyfish")
11818 "/include/jellyfish-" ,(package-version jellyfish)))
11819 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11820 (string-append (assoc-ref inputs "jellyfish")
11821 "/lib/libjellyfish-2.0.a"))
11822 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11823 (string-append (assoc-ref inputs "libdivsufsort")
11824 "/lib/libdivsufsort.so"))
11825 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11826 (string-append (assoc-ref inputs "libdivsufsort")
11827 "/lib/libdivsufsort64.so")))
11828 (substitute* "CMakeLists.txt"
11829 ;; Don't prefer static libs
11830 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11831 (("find_package\\(Jellyfish.*") "")
11832 (("ExternalProject_Add\\(libjellyfish") "message(")
11833 (("ExternalProject_Add\\(libgff") "message(")
11834 (("ExternalProject_Add\\(libsparsehash") "message(")
11835 (("ExternalProject_Add\\(libdivsufsort") "message("))
11837 ;; Ensure that Eigen headers can be found
11838 (setenv "CPLUS_INCLUDE_PATH"
11839 (string-append (assoc-ref inputs "eigen")
11841 (or (getenv "CPLUS_INCLUDE_PATH") "")))
11846 ("jemalloc" ,jemalloc)
11847 ("jellyfish" ,jellyfish)
11848 ("sparsehash" ,sparsehash)
11851 (uri (git-reference
11852 (url "https://github.com/COMBINE-lab/RapMap")
11853 (commit (string-append "sf-v" version))))
11854 (file-name (string-append "rapmap-sf-v" version "-checkout"))
11857 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
11858 (modules '((guix build utils)))
11859 ;; These files are expected to be excluded.
11861 '(begin (delete-file-recursively "include/spdlog")
11862 (for-each delete-file '("include/xxhash.h"
11865 ("libdivsufsort" ,libdivsufsort)
11870 `(("pkg-config" ,pkg-config)))
11871 (home-page "https://www.cs.cmu.edu/~ckingsf/software/sailfish/")
11872 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
11873 (description "Sailfish is a tool for genomic transcript quantification
11874 from RNA-seq data. It requires a set of target transcripts (either from a
11875 reference or de-novo assembly) to quantify. All you need to run sailfish is a
11876 fasta file containing your reference transcripts and a (set of) fasta/fastq
11877 file(s) containing your reads.")
11878 (license license:gpl3+)))
11880 (define libstadenio-for-salmon
11882 (name "libstadenio")
11886 (uri (git-reference
11887 (url "https://github.com/COMBINE-lab/staden-io_lib")
11888 (commit (string-append "v" version))))
11889 (file-name (string-append name "-" version "-checkout"))
11892 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
11893 (build-system gnu-build-system)
11894 (arguments '(#:parallel-tests? #f)) ; not supported
11898 `(("perl" ,perl))) ; for tests
11899 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
11900 (synopsis "General purpose trace and experiment file library")
11901 (description "This package provides a library of file reading and writing
11902 code to provide a general purpose Trace file (and Experiment File) reading
11905 The following file formats are supported:
11908 @item SCF trace files
11909 @item ABI trace files
11910 @item ALF trace files
11911 @item ZTR trace files
11912 @item SFF trace archives
11913 @item SRF trace archives
11914 @item Experiment files
11915 @item Plain text files
11916 @item SAM/BAM sequence files
11917 @item CRAM sequence files
11919 (license license:bsd-3)))
11921 (define-public salmon
11927 (uri (git-reference
11928 (url "https://github.com/COMBINE-lab/salmon")
11929 (commit (string-append "v" version))))
11930 (file-name (git-file-name name version))
11933 "1i2z4aivicmiixdz9bxalp7vmfzi3k92fxa63iqa8kgvfw5a4aq5"))
11934 (modules '((guix build utils)))
11937 ;; Delete bundled headers for eigen3.
11938 (delete-file-recursively "include/eigen3/")
11940 (build-system cmake-build-system)
11942 `(#:configure-flags
11943 (list (string-append "-DBOOST_INCLUDEDIR="
11944 (assoc-ref %build-inputs "boost")
11946 (string-append "-DBOOST_LIBRARYDIR="
11947 (assoc-ref %build-inputs "boost")
11949 (string-append "-DBoost_LIBRARIES="
11950 "-lboost_iostreams "
11951 "-lboost_filesystem "
11956 "-lboost_program_options")
11957 "-DBoost_FOUND=TRUE"
11958 "-DTBB_LIBRARIES=tbb tbbmalloc"
11959 ;; Don't download RapMap---we already have it!
11960 "-DFETCHED_RAPMAP=1")
11962 (modify-phases %standard-phases
11963 ;; Boost cannot be found, even though it's right there.
11964 (add-after 'unpack 'do-not-look-for-boost
11965 (lambda* (#:key inputs #:allow-other-keys)
11966 (substitute* "CMakeLists.txt"
11967 (("find_package\\(Boost 1\\.59\\.0") "#"))
11969 (add-after 'unpack 'do-not-phone-home
11971 (substitute* "src/Salmon.cpp"
11972 (("getVersionMessage\\(\\)") "\"\""))
11974 (add-after 'unpack 'prepare-rapmap
11975 (lambda* (#:key inputs #:allow-other-keys)
11976 (let ((src "external/install/src/rapmap/")
11977 (include "external/install/include/rapmap/")
11978 (rapmap (assoc-ref inputs "rapmap")))
11981 (copy-recursively (string-append rapmap "/src") src)
11982 (copy-recursively (string-append rapmap "/include") include)
11983 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
11984 "external/install/include/rapmap/FastxParser.hpp"
11985 "external/install/include/rapmap/concurrentqueue.h"
11986 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
11987 "external/install/src/rapmap/FastxParser.cpp"
11988 "external/install/src/rapmap/xxhash.c"))
11989 (delete-file-recursively "external/install/include/rapmap/spdlog"))
11991 (add-after 'unpack 'use-system-libraries
11992 (lambda* (#:key inputs #:allow-other-keys)
11993 (substitute* "CMakeLists.txt"
11994 ;; Don't prefer static libs
11995 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11996 (("set\\(TBB_LIBRARIES") "message(")
11997 ;; Don't download anything
11998 (("DOWNLOAD_COMMAND") "DOWNLOAD_COMMAND echo")
11999 (("externalproject_add\\(libcereal") "message(")
12000 (("externalproject_add\\(libgff") "message(")
12001 (("externalproject_add\\(libtbb") "message(")
12002 (("externalproject_add\\(libdivsufsort") "message(")
12003 (("externalproject_add\\(libstadenio") "message(")
12004 (("externalproject_add_step\\(") "message("))
12005 (substitute* "src/CMakeLists.txt"
12006 (("add_dependencies") "#")
12007 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
12008 (string-append (assoc-ref inputs "libstadenio-for-salmon")
12009 "/lib/libstaden-read.so"))
12010 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12011 (string-append (assoc-ref inputs "libdivsufsort")
12012 "/lib/libdivsufsort.so"))
12013 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12014 (string-append (assoc-ref inputs "libdivsufsort")
12015 "/lib/libdivsufsort64.so"))
12016 (("lib/libdivsufsort.a") "/lib/libdivsufsort.so"))
12018 ;; Ensure that all headers can be found
12019 (setenv "CPLUS_INCLUDE_PATH"
12020 (string-append (or (getenv "CPLUS_INCLUDE_PATH") "")
12022 (assoc-ref inputs "eigen")
12023 "/include/eigen3"))
12025 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
12026 ;; run. It only exists after the install phase.
12027 (add-after 'unpack 'fix-tests
12029 (substitute* "src/CMakeLists.txt"
12030 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
12031 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
12040 (uri (git-reference
12041 (url "https://github.com/COMBINE-lab/RapMap")
12042 (commit (string-append "salmon-v" version))))
12043 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
12046 "1biplxf0csc7a8h1wf219b0vmjkvw6wk2zylhdklb577kgmihdms"))))
12047 ("jemalloc" ,jemalloc)
12050 ("libdivsufsort" ,libdivsufsort)
12051 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
12055 `(("pkg-config" ,pkg-config)))
12056 (home-page "https://github.com/COMBINE-lab/salmon")
12057 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
12058 (description "Salmon is a program to produce highly-accurate,
12059 transcript-level quantification estimates from RNA-seq data. Salmon achieves
12060 its accuracy and speed via a number of different innovations, including the
12061 use of lightweight alignments (accurate but fast-to-compute proxies for
12062 traditional read alignments) and massively-parallel stochastic collapsed
12063 variational inference.")
12064 (license license:gpl3+)))
12066 (define-public python-loompy
12068 (name "python-loompy")
12070 ;; The tarball on Pypi does not include the tests.
12073 (uri (git-reference
12074 (url "https://github.com/linnarsson-lab/loompy")
12076 (file-name (git-file-name name version))
12079 "12a5kjgiikapv93wahfw0frszx1lblnppyz3vs5gy8fgmgngra07"))))
12080 (build-system python-build-system)
12083 (modify-phases %standard-phases
12086 (setenv "PYTHONPATH"
12087 (string-append (getcwd) ":"
12088 (getenv "PYTHONPATH")))
12089 (invoke "pytest" "tests")
12092 `(("python-h5py" ,python-h5py)
12093 ("python-numpy" ,python-numpy)
12094 ("python-pandas" ,python-pandas)
12095 ("python-scipy" ,python-scipy)))
12097 `(("python-pytest" ,python-pytest)))
12098 (home-page "https://github.com/linnarsson-lab/loompy")
12099 (synopsis "Work with .loom files for single-cell RNA-seq data")
12100 (description "The loom file format is an efficient format for very large
12101 omics datasets, consisting of a main matrix, optional additional layers, a
12102 variable number of row and column annotations. Loom also supports sparse
12103 graphs. This library makes it easy to work with @file{.loom} files for
12104 single-cell RNA-seq data.")
12105 (license license:bsd-3)))
12107 ;; We cannot use the latest commit because it requires Java 9.
12108 (define-public java-forester
12109 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
12112 (name "java-forester")
12113 (version (string-append "0-" revision "." (string-take commit 7)))
12116 (uri (git-reference
12117 (url "https://github.com/cmzmasek/forester")
12119 (file-name (string-append name "-" version "-checkout"))
12122 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12123 (modules '((guix build utils)))
12126 ;; Delete bundled jars and pre-built classes
12127 (delete-file-recursively "forester/java/resources")
12128 (delete-file-recursively "forester/java/classes")
12129 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12130 ;; Delete bundled applications
12131 (delete-file-recursively "forester_applications")
12133 (build-system ant-build-system)
12135 `(#:tests? #f ; there are none
12137 #:modules ((guix build ant-build-system)
12139 (guix build java-utils)
12143 (modify-phases %standard-phases
12144 (add-after 'unpack 'chdir
12145 (lambda _ (chdir "forester/java") #t))
12146 (add-after 'chdir 'fix-dependencies
12148 (chmod "build.xml" #o664)
12149 (call-with-output-file "build.xml.new"
12153 (with-input-from-file "build.xml"
12154 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12155 `(;; Remove all unjar tags to avoid repacking classes.
12156 (unjar . ,(lambda _ '()))
12157 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12158 (*text* . ,(lambda (_ txt) txt))))
12160 (rename-file "build.xml.new" "build.xml")
12162 ;; FIXME: itext is difficult to package as it depends on a few
12163 ;; unpackaged libraries.
12164 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12166 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12167 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12168 (("pdf_written_to = PdfExporter.*")
12169 "throw new IOException(\"PDF export is not available.\");"))
12171 ;; There is no install target
12172 (replace 'install (install-jars ".")))))
12174 `(("java-commons-codec" ,java-commons-codec)
12175 ("java-openchart2" ,java-openchart2)))
12176 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12177 (synopsis "Phylogenomics libraries for Java")
12178 (description "Forester is a collection of Java libraries for
12179 phylogenomics and evolutionary biology research. It includes support for
12180 reading, writing, and exporting phylogenetic trees.")
12181 (license license:lgpl2.1+))))
12183 (define-public java-forester-1.005
12185 (name "java-forester")
12189 (uri (string-append "https://repo1.maven.org/maven2/"
12190 "org/biojava/thirdparty/forester/"
12191 version "/forester-" version "-sources.jar"))
12192 (file-name (string-append name "-" version ".jar"))
12195 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12196 (build-system ant-build-system)
12198 `(#:tests? #f ; there are none
12200 #:modules ((guix build ant-build-system)
12202 (guix build java-utils)
12206 (modify-phases %standard-phases
12207 (add-after 'unpack 'fix-dependencies
12208 (lambda* (#:key inputs #:allow-other-keys)
12209 (call-with-output-file "build.xml"
12213 (with-input-from-file "src/build.xml"
12214 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12215 `(;; Remove all unjar tags to avoid repacking classes.
12216 (unjar . ,(lambda _ '()))
12217 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12218 (*text* . ,(lambda (_ txt) txt))))
12220 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12221 "synth_look_and_feel_1.xml")
12222 (copy-file (assoc-ref inputs "phyloxml.xsd")
12224 (substitute* "build.xml"
12225 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12226 "synth_look_and_feel_1.xml")
12227 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12230 ;; FIXME: itext is difficult to package as it depends on a few
12231 ;; unpackaged libraries.
12232 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12234 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12235 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12236 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12237 (("pdf_written_to = PdfExporter.*")
12238 "throw new IOException(\"PDF export is not available.\"); /*")
12239 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12240 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12242 (add-after 'unpack 'delete-pre-built-classes
12243 (lambda _ (delete-file-recursively "src/classes") #t))
12244 ;; There is no install target
12245 (replace 'install (install-jars ".")))))
12247 `(("java-commons-codec" ,java-commons-codec)
12248 ("java-openchart2" ,java-openchart2)))
12249 ;; The source archive does not contain the resources.
12254 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12255 "b61cc2dcede0bede317db362472333115756b8c6/"
12256 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12257 (file-name (string-append name "-phyloxml-" version ".xsd"))
12260 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12261 ("synth_look_and_feel_1.xml"
12264 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12265 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12266 "forester/java/classes/resources/"
12267 "synth_look_and_feel_1.xml"))
12268 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12271 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12272 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12273 (synopsis "Phylogenomics libraries for Java")
12274 (description "Forester is a collection of Java libraries for
12275 phylogenomics and evolutionary biology research. It includes support for
12276 reading, writing, and exporting phylogenetic trees.")
12277 (license license:lgpl2.1+)))
12279 (define-public java-biojava-core
12281 (name "java-biojava-core")
12285 (uri (git-reference
12286 (url "https://github.com/biojava/biojava")
12287 (commit (string-append "biojava-" version))))
12288 (file-name (string-append name "-" version "-checkout"))
12291 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12292 (build-system ant-build-system)
12295 #:jar-name "biojava-core.jar"
12296 #:source-dir "biojava-core/src/main/java/"
12297 #:test-dir "biojava-core/src/test"
12298 ;; These tests seem to require internet access.
12299 #:test-exclude (list "**/SearchIOTest.java"
12300 "**/BlastXMLParserTest.java"
12301 "**/GenbankCookbookTest.java"
12302 "**/GenbankProxySequenceReaderTest.java")
12304 (modify-phases %standard-phases
12305 (add-before 'build 'copy-resources
12307 (copy-recursively "biojava-core/src/main/resources"
12310 (add-before 'check 'copy-test-resources
12312 (copy-recursively "biojava-core/src/test/resources"
12313 "build/test-classes")
12316 `(("java-log4j-api" ,java-log4j-api)
12317 ("java-log4j-core" ,java-log4j-core)
12318 ("java-slf4j-api" ,java-slf4j-api)
12319 ("java-slf4j-simple" ,java-slf4j-simple)))
12321 `(("java-junit" ,java-junit)
12322 ("java-hamcrest-core" ,java-hamcrest-core)))
12323 (home-page "https://biojava.org")
12324 (synopsis "Core libraries of Java framework for processing biological data")
12325 (description "BioJava is a project dedicated to providing a Java framework
12326 for processing biological data. It provides analytical and statistical
12327 routines, parsers for common file formats, reference implementations of
12328 popular algorithms, and allows the manipulation of sequences and 3D
12329 structures. The goal of the biojava project is to facilitate rapid
12330 application development for bioinformatics.
12332 This package provides the core libraries.")
12333 (license license:lgpl2.1+)))
12335 (define-public java-biojava-phylo
12336 (package (inherit java-biojava-core)
12337 (name "java-biojava-phylo")
12338 (build-system ant-build-system)
12341 #:jar-name "biojava-phylo.jar"
12342 #:source-dir "biojava-phylo/src/main/java/"
12343 #:test-dir "biojava-phylo/src/test"
12345 (modify-phases %standard-phases
12346 (add-before 'build 'copy-resources
12348 (copy-recursively "biojava-phylo/src/main/resources"
12351 (add-before 'check 'copy-test-resources
12353 (copy-recursively "biojava-phylo/src/test/resources"
12354 "build/test-classes")
12357 `(("java-log4j-api" ,java-log4j-api)
12358 ("java-log4j-core" ,java-log4j-core)
12359 ("java-slf4j-api" ,java-slf4j-api)
12360 ("java-slf4j-simple" ,java-slf4j-simple)
12361 ("java-biojava-core" ,java-biojava-core)
12362 ("java-forester" ,java-forester)))
12364 `(("java-junit" ,java-junit)
12365 ("java-hamcrest-core" ,java-hamcrest-core)))
12366 (home-page "https://biojava.org")
12367 (synopsis "Biojava interface to the forester phylogenomics library")
12368 (description "The phylo module provides a biojava interface layer to the
12369 forester phylogenomics library for constructing phylogenetic trees.")))
12371 (define-public java-biojava-alignment
12372 (package (inherit java-biojava-core)
12373 (name "java-biojava-alignment")
12374 (build-system ant-build-system)
12377 #:jar-name "biojava-alignment.jar"
12378 #:source-dir "biojava-alignment/src/main/java/"
12379 #:test-dir "biojava-alignment/src/test"
12381 (modify-phases %standard-phases
12382 (add-before 'build 'copy-resources
12384 (copy-recursively "biojava-alignment/src/main/resources"
12387 (add-before 'check 'copy-test-resources
12389 (copy-recursively "biojava-alignment/src/test/resources"
12390 "build/test-classes")
12393 `(("java-log4j-api" ,java-log4j-api)
12394 ("java-log4j-core" ,java-log4j-core)
12395 ("java-slf4j-api" ,java-slf4j-api)
12396 ("java-slf4j-simple" ,java-slf4j-simple)
12397 ("java-biojava-core" ,java-biojava-core)
12398 ("java-biojava-phylo" ,java-biojava-phylo)
12399 ("java-forester" ,java-forester)))
12401 `(("java-junit" ,java-junit)
12402 ("java-hamcrest-core" ,java-hamcrest-core)))
12403 (home-page "https://biojava.org")
12404 (synopsis "Biojava API for genetic sequence alignment")
12405 (description "The alignment module of BioJava provides an API that
12409 @item implementations of dynamic programming algorithms for sequence
12411 @item reading and writing of popular alignment file formats;
12412 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12415 (define-public java-biojava-core-4.0
12416 (package (inherit java-biojava-core)
12417 (name "java-biojava-core")
12421 (uri (git-reference
12422 (url "https://github.com/biojava/biojava")
12423 (commit (string-append "biojava-" version))))
12424 (file-name (string-append name "-" version "-checkout"))
12427 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12429 (define-public java-biojava-phylo-4.0
12430 (package (inherit java-biojava-core-4.0)
12431 (name "java-biojava-phylo")
12432 (build-system ant-build-system)
12435 #:jar-name "biojava-phylo.jar"
12436 #:source-dir "biojava-phylo/src/main/java/"
12437 #:test-dir "biojava-phylo/src/test"
12439 (modify-phases %standard-phases
12440 (add-before 'build 'copy-resources
12442 (copy-recursively "biojava-phylo/src/main/resources"
12445 (add-before 'check 'copy-test-resources
12447 (copy-recursively "biojava-phylo/src/test/resources"
12448 "build/test-classes")
12451 `(("java-log4j-api" ,java-log4j-api)
12452 ("java-log4j-core" ,java-log4j-core)
12453 ("java-slf4j-api" ,java-slf4j-api)
12454 ("java-slf4j-simple" ,java-slf4j-simple)
12455 ("java-biojava-core" ,java-biojava-core-4.0)
12456 ("java-forester" ,java-forester-1.005)))
12458 `(("java-junit" ,java-junit)
12459 ("java-hamcrest-core" ,java-hamcrest-core)))
12460 (home-page "https://biojava.org")
12461 (synopsis "Biojava interface to the forester phylogenomics library")
12462 (description "The phylo module provides a biojava interface layer to the
12463 forester phylogenomics library for constructing phylogenetic trees.")))
12465 (define-public java-biojava-alignment-4.0
12466 (package (inherit java-biojava-core-4.0)
12467 (name "java-biojava-alignment")
12468 (build-system ant-build-system)
12471 #:jar-name "biojava-alignment.jar"
12472 #:source-dir "biojava-alignment/src/main/java/"
12473 #:test-dir "biojava-alignment/src/test"
12475 (modify-phases %standard-phases
12476 (add-before 'build 'copy-resources
12478 (copy-recursively "biojava-alignment/src/main/resources"
12481 (add-before 'check 'copy-test-resources
12483 (copy-recursively "biojava-alignment/src/test/resources"
12484 "build/test-classes")
12487 `(("java-log4j-api" ,java-log4j-api)
12488 ("java-log4j-core" ,java-log4j-core)
12489 ("java-slf4j-api" ,java-slf4j-api)
12490 ("java-slf4j-simple" ,java-slf4j-simple)
12491 ("java-biojava-core" ,java-biojava-core-4.0)
12492 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12493 ("java-forester" ,java-forester-1.005)))
12495 `(("java-junit" ,java-junit)
12496 ("java-hamcrest-core" ,java-hamcrest-core)))
12497 (home-page "https://biojava.org")
12498 (synopsis "Biojava API for genetic sequence alignment")
12499 (description "The alignment module of BioJava provides an API that
12503 @item implementations of dynamic programming algorithms for sequence
12505 @item reading and writing of popular alignment file formats;
12506 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12509 (define-public dropseq-tools
12511 (name "dropseq-tools")
12516 (uri "http://mccarrolllab.com/download/1276/")
12517 (file-name (string-append "dropseq-tools-" version ".zip"))
12520 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12521 ;; Delete bundled libraries
12522 (modules '((guix build utils)))
12525 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12526 (delete-file-recursively "3rdParty")
12528 (build-system ant-build-system)
12530 `(#:tests? #f ; test data are not included
12531 #:test-target "test"
12532 #:build-target "all"
12533 #:source-dir "public/src/"
12536 (list (string-append "-Dpicard.executable.dir="
12537 (assoc-ref %build-inputs "java-picard")
12539 #:modules ((ice-9 match)
12542 (guix build java-utils)
12543 (guix build ant-build-system))
12545 (modify-phases %standard-phases
12546 ;; FIXME: fails with "java.io.FileNotFoundException:
12547 ;; /gnu/store/…-dropseq-tools-1.13/share/java/lib/biojava-alignment.jar"
12548 (delete 'generate-jar-indices)
12549 ;; All dependencies must be linked to "lib", because that's where
12550 ;; they will be searched for when the Class-Path property of the
12551 ;; manifest is computed.
12552 (add-after 'unpack 'record-references
12553 (lambda* (#:key inputs #:allow-other-keys)
12554 (mkdir-p "jar/lib")
12555 (let ((dirs (filter-map (match-lambda
12557 (if (and (string-prefix? "java-" name)
12558 (not (string=? name "java-testng")))
12561 (for-each (lambda (jar)
12562 (symlink jar (string-append "jar/lib/" (basename jar))))
12563 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12566 ;; There is no installation target
12568 (lambda* (#:key inputs outputs #:allow-other-keys)
12569 (let* ((out (assoc-ref outputs "out"))
12570 (bin (string-append out "/bin"))
12571 (share (string-append out "/share/java/"))
12572 (lib (string-append share "/lib/"))
12573 (scripts (list "BAMTagHistogram"
12574 "BAMTagofTagCounts"
12575 "BaseDistributionAtReadPosition"
12576 "CollapseBarcodesInPlace"
12577 "CollapseTagWithContext"
12579 "CreateIntervalsFiles"
12580 "DetectBeadSynthesisErrors"
12581 "DigitalExpression"
12582 "Drop-seq_alignment.sh"
12585 "GatherGeneGCLength"
12586 "GatherMolecularBarcodeDistributionByGene"
12587 "GatherReadQualityMetrics"
12590 "SelectCellsByNumTranscripts"
12591 "SingleCellRnaSeqMetricsCollector"
12592 "TagBamWithReadSequenceExtended"
12593 "TagReadWithGeneExon"
12594 "TagReadWithInterval"
12595 "TrimStartingSequence"
12596 "ValidateReference")))
12597 (for-each mkdir-p (list bin share lib))
12598 (install-file "dist/dropseq.jar" share)
12599 (for-each (lambda (script)
12600 (chmod script #o555)
12601 (install-file script bin))
12603 (substitute* (map (lambda (script)
12604 (string-append bin "/" script))
12606 (("^java") (which "java"))
12607 (("jar_deploy_dir=.*")
12608 (string-append "jar_deploy_dir=" share "\n"))))
12610 ;; FIXME: We do this after stripping jars because we don't want it to
12611 ;; copy all these jars and strip them. We only want to install
12612 ;; links. Arguably, this is a problem with the ant-build-system.
12613 (add-after 'strip-jar-timestamps 'install-links
12614 (lambda* (#:key outputs #:allow-other-keys)
12615 (let* ((out (assoc-ref outputs "out"))
12616 (share (string-append out "/share/java/"))
12617 (lib (string-append share "/lib/")))
12618 (for-each (lambda (jar)
12619 (symlink (readlink jar)
12620 (string-append lib (basename jar))))
12621 (find-files "jar/lib" "\\.jar$")))
12624 `(("jdk" ,icedtea-8)
12625 ("java-picard" ,java-picard-2.10.3)
12626 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12627 ("java-commons-math3" ,java-commons-math3)
12628 ("java-commons-jexl2" ,java-commons-jexl-2)
12629 ("java-commons-collections4" ,java-commons-collections4)
12630 ("java-commons-lang2" ,java-commons-lang)
12631 ("java-commons-io" ,java-commons-io)
12632 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12633 ("java-guava" ,java-guava)
12634 ("java-la4j" ,java-la4j)
12635 ("java-biojava-core" ,java-biojava-core-4.0)
12636 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12637 ("java-jdistlib" ,java-jdistlib)
12638 ("java-simple-xml" ,java-simple-xml)
12639 ("java-snakeyaml" ,java-snakeyaml)))
12642 ("java-testng" ,java-testng)))
12643 (home-page "http://mccarrolllab.com/dropseq/")
12644 (synopsis "Tools for Drop-seq analyses")
12645 (description "Drop-seq is a technology to enable biologists to
12646 analyze RNA expression genome-wide in thousands of individual cells at
12647 once. This package provides tools to perform Drop-seq analyses.")
12648 (license license:expat)))
12650 (define-public pigx-rnaseq
12652 (name "pigx-rnaseq")
12656 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12657 "releases/download/v" version
12658 "/pigx_rnaseq-" version ".tar.gz"))
12661 "0z3hr120wk2vrlmlpz1vp3n9wy3rq4y2mnzh2vf08qgqn2xfdwcw"))))
12662 (build-system gnu-build-system)
12664 `(#:parallel-tests? #f ; not supported
12666 (modify-phases %standard-phases
12667 ;; "test.sh" runs STAR, which requires excessive amounts of memory.
12668 (add-after 'unpack 'disable-resource-intensive-test
12670 (substitute* "Makefile.in"
12671 (("(^ tests/test_trim_galore/test.sh).*" _ m) m)
12672 (("^ tests/test_multiqc/test.sh") "")
12673 (("^ test.sh") ""))
12676 `(("coreutils" ,coreutils)
12679 ("snakemake" ,snakemake)
12681 ("multiqc" ,multiqc)
12683 ("trim-galore" ,trim-galore)
12685 ("samtools" ,samtools)
12686 ("r-minimal" ,r-minimal)
12687 ("r-rmarkdown" ,r-rmarkdown)
12688 ("r-ggplot2" ,r-ggplot2)
12689 ("r-ggrepel" ,r-ggrepel)
12690 ("r-gprofiler" ,r-gprofiler)
12691 ("r-deseq2" ,r-deseq2)
12693 ("r-knitr" ,r-knitr)
12694 ("r-pheatmap" ,r-pheatmap)
12695 ("r-corrplot" ,r-corrplot)
12696 ("r-reshape2" ,r-reshape2)
12697 ("r-plotly" ,r-plotly)
12698 ("r-scales" ,r-scales)
12699 ("r-summarizedexperiment" ,r-summarizedexperiment)
12700 ("r-crosstalk" ,r-crosstalk)
12701 ("r-tximport" ,r-tximport)
12702 ("r-rtracklayer" ,r-rtracklayer)
12703 ("r-rjson" ,r-rjson)
12706 ("pandoc-citeproc" ,pandoc-citeproc)
12707 ("python-wrapper" ,python-wrapper)
12708 ("python-pyyaml" ,python-pyyaml)))
12709 (home-page "https://bioinformatics.mdc-berlin.de/pigx/")
12710 (synopsis "Analysis pipeline for RNA sequencing experiments")
12711 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
12712 reporting for RNA sequencing experiments. It is easy to use and produces high
12713 quality reports. The inputs are reads files from the sequencing experiment,
12714 and a configuration file which describes the experiment. In addition to
12715 quality control of the experiment, the pipeline produces a differential
12716 expression report comparing samples in an easily configurable manner.")
12717 (license license:gpl3+)))
12719 (define-public pigx-chipseq
12721 (name "pigx-chipseq")
12725 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
12726 "releases/download/v" version
12727 "/pigx_chipseq-" version ".tar.gz"))
12730 "0bb6hzpl0qq0jd57pgd1m5ns547rfipr6071a4m12vxlm4nlpi5q"))))
12731 (build-system gnu-build-system)
12732 ;; parts of the tests rely on access to the network
12733 (arguments '(#:tests? #f))
12736 ("coreutils" ,coreutils)
12737 ("r-minimal" ,r-minimal)
12738 ("r-argparser" ,r-argparser)
12739 ("r-biocparallel" ,r-biocparallel)
12740 ("r-biostrings" ,r-biostrings)
12741 ("r-chipseq" ,r-chipseq)
12742 ("r-corrplot" ,r-corrplot)
12743 ("r-data-table" ,r-data-table)
12744 ("r-deseq2" ,r-deseq2)
12745 ("r-dplyr" ,r-dplyr)
12747 ("r-genomation" ,r-genomation)
12748 ("r-genomicalignments" ,r-genomicalignments)
12749 ("r-genomicranges" ,r-genomicranges)
12750 ("r-ggplot2" ,r-ggplot2)
12751 ("r-ggrepel" ,r-ggrepel)
12752 ("r-gprofiler2" ,r-gprofiler2)
12753 ("r-heatmaply" ,r-heatmaply)
12754 ("r-htmlwidgets" ,r-htmlwidgets)
12755 ("r-jsonlite" ,r-jsonlite)
12756 ("r-pheatmap" ,r-pheatmap)
12757 ("r-plotly" ,r-plotly)
12758 ("r-rmarkdown" ,r-rmarkdown)
12759 ("r-rsamtools" ,r-rsamtools)
12760 ("r-rsubread" ,r-rsubread)
12761 ("r-rtracklayer" ,r-rtracklayer)
12762 ("r-s4vectors" ,r-s4vectors)
12763 ("r-stringr" ,r-stringr)
12764 ("r-tibble" ,r-tibble)
12765 ("r-tidyr" ,r-tidyr)
12766 ("python-wrapper" ,python-wrapper)
12767 ("python-pyyaml" ,python-pyyaml)
12768 ("python-magic" ,python-magic)
12769 ("python-xlrd" ,python-xlrd)
12770 ("trim-galore" ,trim-galore)
12772 ("multiqc" ,multiqc)
12775 ("pandoc-citeproc" ,pandoc-citeproc)
12779 ("snakemake" ,snakemake)
12780 ("samtools" ,samtools)
12781 ("bedtools" ,bedtools)
12782 ("kentutils" ,kentutils)))
12784 `(("python-pytest" ,python-pytest)))
12785 (home-page "https://bioinformatics.mdc-berlin.de/pigx/")
12786 (synopsis "Analysis pipeline for ChIP sequencing experiments")
12787 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
12788 calling and reporting for ChIP sequencing experiments. It is easy to use and
12789 produces high quality reports. The inputs are reads files from the sequencing
12790 experiment, and a configuration file which describes the experiment. In
12791 addition to quality control of the experiment, the pipeline enables to set up
12792 multiple peak calling analysis and allows the generation of a UCSC track hub
12793 in an easily configurable manner.")
12794 (license license:gpl3+)))
12796 (define-public pigx-bsseq
12798 (name "pigx-bsseq")
12802 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
12803 "releases/download/v" version
12804 "/pigx_bsseq-" version ".tar.gz"))
12807 "0mpzlay2d5cjpmrcp7knff6rg1c2mqszd638n7lw0mc0cycbp9f8"))))
12808 (build-system gnu-build-system)
12810 `(;; TODO: tests currently require 12+GB of RAM. See
12811 ;; https://github.com/BIMSBbioinfo/pigx_bsseq/issues/164
12814 (modify-phases %standard-phases
12815 (add-before 'check 'set-timezone
12816 ;; The readr package is picky about timezones.
12817 (lambda* (#:key inputs #:allow-other-keys)
12818 (setenv "TZ" "UTC+1")
12820 (string-append (assoc-ref inputs "tzdata")
12821 "/share/zoneinfo"))
12824 `(("tzdata" ,tzdata)))
12826 `(("coreutils" ,coreutils)
12829 ("r-minimal" ,r-minimal)
12830 ("r-annotationhub" ,r-annotationhub)
12832 ("r-genomation" ,r-genomation)
12833 ("r-ggrepel" ,r-ggrepel)
12834 ("r-methylkit" ,r-methylkit)
12835 ("r-rtracklayer" ,r-rtracklayer)
12836 ("r-rmarkdown" ,r-rmarkdown)
12837 ("r-bookdown" ,r-bookdown)
12838 ("r-ggplot2" ,r-ggplot2)
12839 ("r-ggbio" ,r-ggbio)
12841 ("pandoc-citeproc" ,pandoc-citeproc)
12842 ("python-wrapper" ,python-wrapper)
12843 ("python-pyyaml" ,python-pyyaml)
12844 ("snakemake" ,snakemake)
12845 ("bismark" ,bismark)
12847 ("bwa-meth" ,bwa-meth)
12849 ("methyldackel" ,methyldackel)
12850 ("multiqc" ,multiqc)
12851 ("trim-galore" ,trim-galore)
12852 ("cutadapt" ,cutadapt)
12853 ("samblaster" ,samblaster)
12854 ("samtools" ,samtools)))
12855 (home-page "https://bioinformatics.mdc-berlin.de/pigx/")
12856 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
12857 (description "PiGx BSseq is a data processing pipeline for raw fastq read
12858 data of bisulfite experiments; it produces reports on aggregate methylation
12859 and coverage and can be used to produce information on differential
12860 methylation and segmentation.")
12861 (license license:gpl3+)))
12863 (define-public pigx-scrnaseq
12865 (name "pigx-scrnaseq")
12869 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/"
12870 "releases/download/v" version
12871 "/pigx_scrnaseq-" version ".tar.gz"))
12874 "1h5mcxzwj3cidlkvy9ly5wmi48vwfsjf8dxjfirknqxr9a92hwlx"))))
12875 (build-system gnu-build-system)
12877 `(("coreutils" ,coreutils)
12880 ("flexbar" ,flexbar)
12881 ("java" ,icedtea-8)
12882 ("jellyfish" ,jellyfish)
12883 ("python-wrapper" ,python-wrapper)
12884 ("python-pyyaml" ,python-pyyaml)
12885 ("python-pandas" ,python-pandas)
12886 ("python-magic" ,python-magic)
12887 ("python-numpy" ,python-numpy)
12888 ("python-loompy" ,python-loompy)
12890 ("pandoc-citeproc" ,pandoc-citeproc)
12891 ("samtools" ,samtools)
12892 ("snakemake" ,snakemake)
12894 ("r-minimal" ,r-minimal)
12895 ("r-argparser" ,r-argparser)
12896 ("r-cowplot" ,r-cowplot)
12897 ("r-data-table" ,r-data-table)
12898 ("r-delayedarray" ,r-delayedarray)
12899 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
12900 ("r-dplyr" ,r-dplyr)
12901 ("r-dropbead" ,r-dropbead)
12903 ("r-genomicalignments" ,r-genomicalignments)
12904 ("r-genomicfiles" ,r-genomicfiles)
12905 ("r-genomicranges" ,r-genomicranges)
12906 ("r-ggplot2" ,r-ggplot2)
12907 ("r-hdf5array" ,r-hdf5array)
12908 ("r-pheatmap" ,r-pheatmap)
12909 ("r-rmarkdown" ,r-rmarkdown)
12910 ("r-rsamtools" ,r-rsamtools)
12911 ("r-rtracklayer" ,r-rtracklayer)
12912 ("r-rtsne" ,r-rtsne)
12913 ("r-scater" ,r-scater)
12914 ("r-scran" ,r-scran)
12915 ("r-seurat" ,r-seurat)
12916 ("r-singlecellexperiment" ,r-singlecellexperiment)
12917 ("r-stringr" ,r-stringr)
12918 ("r-yaml" ,r-yaml)))
12919 (home-page "https://bioinformatics.mdc-berlin.de/pigx/")
12920 (synopsis "Analysis pipeline for single-cell RNA sequencing experiments")
12921 (description "PiGX scRNAseq is an analysis pipeline for preprocessing and
12922 quality control for single cell RNA sequencing experiments. The inputs are
12923 read files from the sequencing experiment, and a configuration file which
12924 describes the experiment. It produces processed files for downstream analysis
12925 and interactive quality reports. The pipeline is designed to work with UMI
12927 (license license:gpl3+)))
12929 (define-public pigx
12935 (uri (string-append "https://github.com/BIMSBbioinfo/pigx/"
12936 "releases/download/v" version
12937 "/pigx-" version ".tar.gz"))
12940 "1i5njdy1clj5ncw45d16p7mwmqvb1ilikl9n797pxklc3f4s7mq7"))))
12941 (build-system gnu-build-system)
12943 `(("python" ,python)
12944 ("pigx-bsseq" ,pigx-bsseq)
12945 ("pigx-chipseq" ,pigx-chipseq)
12946 ("pigx-rnaseq" ,pigx-rnaseq)
12947 ("pigx-scrnaseq" ,pigx-scrnaseq)))
12948 (home-page "https://bioinformatics.mdc-berlin.de/pigx/")
12949 (synopsis "Analysis pipelines for genomics")
12950 (description "PiGx is a collection of genomics pipelines. It includes the
12951 following pipelines:
12954 @item PiGx BSseq for raw fastq read data of bisulfite experiments
12955 @item PiGx RNAseq for RNAseq samples
12956 @item PiGx scRNAseq for single cell dropseq analysis
12957 @item PiGx ChIPseq for reads from ChIPseq experiments
12960 All pipelines are easily configured with a simple sample sheet and a
12961 descriptive settings file. The result is a set of comprehensive, interactive
12962 HTML reports with interesting findings about your samples.")
12963 (license license:gpl3+)))
12965 (define-public genrich
12971 (uri (git-reference
12972 (url "https://github.com/jsh58/Genrich")
12973 (commit (string-append "v" version))))
12974 (file-name (git-file-name name version))
12977 "0x0q6z0208n3cxzqjla4rgjqpyqgwpmz27852lcvzkzaigymq4zp"))))
12978 (build-system gnu-build-system)
12980 `(#:tests? #f ; there are none
12982 (modify-phases %standard-phases
12983 (delete 'configure)
12985 (lambda* (#:key outputs #:allow-other-keys)
12986 (install-file "Genrich" (string-append (assoc-ref outputs "out") "/bin"))
12990 (home-page "https://github.com/jsh58/Genrich")
12991 (synopsis "Detecting sites of genomic enrichment")
12992 (description "Genrich is a peak-caller for genomic enrichment
12993 assays (e.g. ChIP-seq, ATAC-seq). It analyzes alignment files generated
12994 following the assay and produces a file detailing peaks of significant
12996 (license license:expat)))
12998 (define-public mantis
12999 (let ((commit "4ffd171632c2cb0056a86d709dfd2bf21bc69b84")
13003 (version (git-version "0" revision commit))
13006 (uri (git-reference
13007 (url "https://github.com/splatlab/mantis")
13009 (file-name (git-file-name name version))
13012 "0iqbr0dhmlc8mzpirmm2s4pkzkwdgrcx50yx6cv3wlr2qi064p55"))))
13013 (build-system cmake-build-system)
13014 (arguments '(#:tests? #f)) ; there are none
13016 `(("sdsl-lite" ,sdsl-lite)
13017 ("openssl" ,openssl)
13019 (home-page "https://github.com/splatlab/mantis")
13020 (synopsis "Large-scale sequence-search index data structure")
13021 (description "Mantis is a space-efficient data structure that can be
13022 used to index thousands of raw-read genomics experiments and facilitate
13023 large-scale sequence searches on those experiments. Mantis uses counting
13024 quotient filters instead of Bloom filters, enabling rapid index builds and
13025 queries, small indexes, and exact results, i.e., no false positives or
13026 negatives. Furthermore, Mantis is also a colored de Bruijn graph
13027 representation, so it supports fast graph traversal and other topological
13028 analyses in addition to large-scale sequence-level searches.")
13029 ;; uses __uint128_t and inline assembly
13030 (supported-systems '("x86_64-linux"))
13031 (license license:bsd-3))))
13033 (define-public sjcount
13034 ;; There is no tag for version 3.2, nor is there a release archive.
13035 (let ((commit "292d3917cadb3f6834c81e509c30e61cd7ead6e5")
13039 (version (git-version "3.2" revision commit))
13042 (uri (git-reference
13043 (url "https://github.com/pervouchine/sjcount-full")
13045 (file-name (string-append name "-" version "-checkout"))
13048 "0gdgj35j249f04rqgq8ymcc1xg1vi9kzbajnjqpaq2wpbh8bl234"))))
13049 (build-system gnu-build-system)
13051 `(#:tests? #f ; requires a 1.4G test file
13053 (list (string-append "SAMTOOLS_DIR="
13054 (assoc-ref %build-inputs "samtools")
13057 (modify-phases %standard-phases
13058 (replace 'configure
13059 (lambda* (#:key inputs #:allow-other-keys)
13060 (substitute* "makefile"
13061 (("-I \\$\\{SAMTOOLS_DIR\\}")
13062 (string-append "-I" (assoc-ref inputs "samtools")
13063 "/include/samtools"))
13064 (("-lz ") "-lz -lpthread "))
13067 (lambda* (#:key outputs #:allow-other-keys)
13068 (for-each (lambda (tool)
13070 (string-append (assoc-ref outputs "out")
13072 '("j_count" "b_count" "sjcount"))
13075 `(("samtools" ,samtools-0.1)
13077 (home-page "https://github.com/pervouchine/sjcount-full/")
13078 (synopsis "Annotation-agnostic splice junction counting pipeline")
13079 (description "Sjcount is a utility for fast quantification of splice
13080 junctions in RNA-seq data. It is annotation-agnostic and offset-aware. This
13081 version does count multisplits.")
13082 (license license:gpl3+))))
13084 (define-public minimap2
13091 (uri (string-append "https://github.com/lh3/minimap2/"
13092 "releases/download/v" version "/"
13093 "minimap2-" version ".tar.bz2"))
13096 "0hi7i9pzxhvjj44khzzzj1lrn5gb5837arr4wgln7k1k5n4ci2mn"))
13097 (patches (search-patches "minimap2-aarch64-support.patch"))))
13098 (build-system gnu-build-system)
13100 `(#:tests? #f ; there are none
13102 (list (string-append "CC=" ,(cc-for-target))
13103 (let ((system ,(or (%current-target-system)
13104 (%current-system))))
13106 ((string-prefix? "x86_64" system)
13108 ((or (string-prefix? "i586" system)
13109 (string-prefix? "i686" system))
13111 ((string-prefix? "armhf" system)
13113 ((string-prefix? "aarch64" system)
13117 (modify-phases %standard-phases
13118 (delete 'configure)
13120 (lambda* (#:key outputs #:allow-other-keys)
13121 (let* ((out (assoc-ref outputs "out"))
13122 (bin (string-append out "/bin"))
13123 (man (string-append out "/share/man/man1")))
13124 (install-file "minimap2" bin)
13126 (install-file "minimap2.1" man))
13130 (home-page "https://lh3.github.io/minimap2/")
13131 (synopsis "Pairwise aligner for genomic and spliced nucleotide sequences")
13132 (description "Minimap2 is a versatile sequence alignment program that
13133 aligns DNA or mRNA sequences against a large reference database. Typical use
13137 @item mapping PacBio or Oxford Nanopore genomic reads to the human genome;
13138 @item finding overlaps between long reads with error rate up to ~15%;
13139 @item splice-aware alignment of PacBio Iso-Seq or Nanopore cDNA or Direct RNA
13140 reads against a reference genome;
13141 @item aligning Illumina single- or paired-end reads;
13142 @item assembly-to-assembly alignment;
13143 @item full-genome alignment between two closely related species with
13144 divergence below ~15%.
13146 (license license:expat)))
13148 (define-public miniasm
13154 (uri (git-reference
13155 (url "https://github.com/lh3/miniasm")
13156 (commit (string-append "v" version))))
13157 (file-name (git-file-name name version))
13160 "04dv5wv8bhsw1imxwyd438bnn9kby7svp44nbcz8lsadzjjci5gs"))))
13161 (build-system gnu-build-system)
13165 `(#:tests? #f ; There are no tests.
13167 (modify-phases %standard-phases
13168 (delete 'configure)
13170 (lambda* (#:key inputs outputs #:allow-other-keys)
13171 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
13172 (install-file "miniasm" bin)
13173 (install-file "minidot" bin)
13175 (home-page "https://github.com/lh3/miniasm")
13176 (synopsis "Ultrafast de novo assembly for long noisy reads")
13177 (description "Miniasm is a very fast OLC-based de novo assembler for noisy
13178 long reads. It takes all-vs-all read self-mappings (typically by minimap) as
13179 input and outputs an assembly graph in the GFA format. Different from
13180 mainstream assemblers, miniasm does not have a consensus step. It simply
13181 concatenates pieces of read sequences to generate the final unitig sequences.
13182 Thus the per-base error rate is similar to the raw input reads.")
13183 (license license:expat)))
13185 (define-public r-circus
13192 (uri (git-reference
13193 (url "https://github.com/BIMSBbioinfo/ciRcus")
13194 (commit (string-append "v" version))))
13195 (file-name (git-file-name name version))
13198 "0jhjn3ilb057hbf6yzrihj13ifxxs32y7nkby8l3lkm28dg4p97h"))))
13199 (build-system r-build-system)
13201 `(("r-annotationdbi" ,r-annotationdbi)
13202 ("r-annotationhub" ,r-annotationhub)
13203 ("r-biomart" ,r-biomart)
13204 ("r-data-table" ,r-data-table)
13206 ("r-genomicfeatures" ,r-genomicfeatures)
13207 ("r-genomicranges" ,r-genomicranges)
13208 ("r-ggplot2" ,r-ggplot2)
13210 ("r-iranges" ,r-iranges)
13211 ("r-rcolorbrewer" ,r-rcolorbrewer)
13212 ("r-rmysql" ,r-rmysql)
13213 ("r-s4vectors" ,r-s4vectors)
13214 ("r-stringr" ,r-stringr)
13215 ("r-summarizedexperiment" ,r-summarizedexperiment)))
13217 `(("r-knitr" ,r-knitr)))
13218 (home-page "https://github.com/BIMSBbioinfo/ciRcus")
13219 (synopsis "Annotation, analysis and visualization of circRNA data")
13220 (description "Circus is an R package for annotation, analysis and
13221 visualization of circRNA data. Users can annotate their circRNA candidates
13222 with host genes, gene featrues they are spliced from, and discriminate between
13223 known and yet unknown splice junctions. Circular-to-linear ratios of circRNAs
13224 can be calculated, and a number of descriptive plots easily generated.")
13225 (license license:artistic2.0)))
13227 (define-public gffread
13228 ;; We cannot use the tagged release because it is not in sync with gclib.
13229 ;; See https://github.com/gpertea/gffread/issues/26
13230 (let ((commit "ba7535fcb3cea55a6e5a491d916e93b454e87fd0")
13234 (version (git-version "0.9.12" revision commit))
13238 (uri (git-reference
13239 (url "https://github.com/gpertea/gffread")
13241 (file-name (git-file-name name version))
13244 "1dl2nbcg96lxpd0drg48ssa8343nf7pw9s9mkrc4mjjmfwsin3ki"))))
13245 (build-system gnu-build-system)
13247 `(#:tests? #f ; no check target
13249 (list "GCLDIR=gclib")
13251 (modify-phases %standard-phases
13252 (delete 'configure)
13253 (add-after 'unpack 'copy-gclib-source
13254 (lambda* (#:key inputs #:allow-other-keys)
13256 (copy-recursively (assoc-ref inputs "gclib-source") "gclib")
13258 ;; There is no install target
13260 (lambda* (#:key outputs #:allow-other-keys)
13261 (let* ((out (assoc-ref outputs "out"))
13262 (bin (string-append out "/bin")))
13263 (install-file "gffread" bin))
13267 ,(let ((version "0.10.3")
13268 (commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13272 (uri (git-reference
13273 (url "https://github.com/gpertea/gclib")
13275 (file-name (git-file-name "gclib" version))
13278 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13279 (home-page "https://github.com/gpertea/gffread/")
13280 (synopsis "Parse and convert GFF/GTF files")
13282 "This package provides a GFF/GTF file parsing utility providing format
13283 conversions, region filtering, FASTA sequence extraction and more.")
13284 ;; gffread is under Expat, but gclib is under Artistic 2.0
13285 (license (list license:expat
13286 license:artistic2.0)))))
13288 (define-public find-circ
13289 ;; The last release was in 2015. The license was clarified in 2017, so we
13290 ;; take the latest commit.
13291 (let ((commit "8655dca54970fcf7e92e22fbf57e1188724dda7d")
13295 (version (git-version "1.2" revision commit))
13299 (uri (git-reference
13300 (url "https://github.com/marvin-jens/find_circ")
13302 (file-name (git-file-name name version))
13305 "0p77pbqbclqr4srms34y1b9b4njybfpjiknc11ki84f3p8skb3cg"))))
13306 (build-system gnu-build-system)
13308 `(#:tests? #f ; there are none
13310 ;; There is no actual build system.
13311 (modify-phases %standard-phases
13312 (delete 'configure)
13315 (lambda* (#:key outputs #:allow-other-keys)
13316 (let* ((out (assoc-ref outputs "out"))
13317 (bin (string-append out "/bin"))
13318 (path (getenv "PYTHONPATH")))
13319 (for-each (lambda (script)
13320 (install-file script bin)
13321 (wrap-program (string-append bin "/" script)
13322 `("PYTHONPATH" ":" prefix (,path))))
13327 "unmapped2anchors.py")))
13330 `(("python2" ,python-2)
13331 ("python2-pysam" ,python2-pysam)
13332 ("python2-numpy" ,python2-numpy)))
13333 (home-page "https://github.com/marvin-jens/find_circ")
13334 (synopsis "circRNA detection from RNA-seq reads")
13335 (description "This package provides tools to detect head-to-tail
13336 spliced (back-spliced) sequencing reads, indicative of circular RNA (circRNA)
13338 (license license:gpl3))))
13340 (define-public python-scanpy
13342 (name "python-scanpy")
13347 (uri (pypi-uri "scanpy" version))
13350 "0s2b6cvaigx4wzw3850qb93sjwwxbzh22kpbp498zklc5rjpbz4l"))))
13351 (build-system python-build-system)
13354 (modify-phases %standard-phases
13356 (lambda* (#:key inputs #:allow-other-keys)
13357 ;; These tests require Internet access.
13358 (delete-file-recursively "scanpy/tests/notebooks")
13359 (delete-file "scanpy/tests/test_clustering.py")
13360 (delete-file "scanpy/tests/test_datasets.py")
13362 ;; TODO: I can't get the plotting tests to work, even with Xvfb.
13363 (delete-file "scanpy/tests/test_plotting.py")
13364 (delete-file "scanpy/tests/test_preprocessing.py")
13365 (delete-file "scanpy/tests/test_read_10x.py")
13367 (setenv "PYTHONPATH"
13368 (string-append (getcwd) ":"
13369 (getenv "PYTHONPATH")))
13373 `(("python-anndata" ,python-anndata)
13374 ("python-h5py" ,python-h5py)
13375 ("python-igraph" ,python-igraph)
13376 ("python-joblib" ,python-joblib)
13377 ("python-legacy-api-wrap" ,python-legacy-api-wrap)
13378 ("python-louvain" ,python-louvain)
13379 ("python-matplotlib" ,python-matplotlib)
13380 ("python-natsort" ,python-natsort)
13381 ("python-networkx" ,python-networkx)
13382 ("python-numba" ,python-numba)
13383 ("python-packaging" ,python-packaging)
13384 ("python-pandas" ,python-pandas)
13385 ("python-patsy" ,python-patsy)
13386 ("python-scikit-learn" ,python-scikit-learn)
13387 ("python-scipy" ,python-scipy)
13388 ("python-seaborn" ,python-seaborn)
13389 ("python-statsmodels" ,python-statsmodels)
13390 ("python-tables" ,python-tables)
13391 ("python-tqdm" ,python-tqdm)
13392 ("python-umap-learn" ,python-umap-learn)))
13394 `(("python-pytest" ,python-pytest)
13395 ("python-setuptools-scm" ,python-setuptools-scm)))
13396 (home-page "https://github.com/theislab/scanpy")
13397 (synopsis "Single-Cell Analysis in Python.")
13398 (description "Scanpy is a scalable toolkit for analyzing single-cell gene
13399 expression data. It includes preprocessing, visualization, clustering,
13400 pseudotime and trajectory inference and differential expression testing. The
13401 Python-based implementation efficiently deals with datasets of more than one
13403 (license license:bsd-3)))
13405 (define-public python-bbknn
13407 (name "python-bbknn")
13412 (uri (pypi-uri "bbknn" version))
13415 "1jbsh01f57zj4bhvjr3jh4532zznqd6nccmgrl3qi9gnhkf7c4y0"))))
13416 (build-system python-build-system)
13418 `(#:tests? #f)) ; TODO: Enable after migration to scikit-learn.
13420 `(("python-annoy" ,python-annoy)
13421 ("python-cython" ,python-cython)
13422 ("python-numpy" ,python-numpy)
13423 ("python-scipy" ,python-scipy)
13424 ("python-umap-learn" ,python-umap-learn)))
13425 (home-page "https://github.com/Teichlab/bbknn")
13426 (synopsis "Batch balanced KNN")
13427 (description "BBKNN is a batch effect removal tool that can be directly
13428 used in the Scanpy workflow. It serves as an alternative to
13429 @code{scanpy.api.pp.neighbors()}, with both functions creating a neighbour
13430 graph for subsequent use in clustering, pseudotime and UMAP visualisation. If
13431 technical artifacts are present in the data, they will make it challenging to
13432 link corresponding cell types across different batches. BBKNN actively
13433 combats this effect by splitting your data into batches and finding a smaller
13434 number of neighbours for each cell within each of the groups. This helps
13435 create connections between analogous cells in different batches without
13436 altering the counts or PCA space.")
13437 (license license:expat)))
13439 (define-public gffcompare
13440 (let ((commit "be56ef4349ea3966c12c6397f85e49e047361c41")
13443 (name "gffcompare")
13444 (version (git-version "0.10.15" revision commit))
13448 (uri (git-reference
13449 (url "https://github.com/gpertea/gffcompare/")
13451 (file-name (git-file-name name version))
13453 (base32 "0cp5qpxdhw4mxpya5dld8wi3jk00zyklm6rcri426wydinrnfmkg"))))
13454 (build-system gnu-build-system)
13456 `(#:tests? #f ; no check target
13458 (modify-phases %standard-phases
13459 (delete 'configure)
13460 (add-before 'build 'copy-gclib-source
13461 (lambda* (#:key inputs #:allow-other-keys)
13464 (assoc-ref inputs "gclib-source") "../gclib")
13467 (lambda* (#:key outputs #:allow-other-keys)
13468 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
13469 (install-file "gffcompare" bin)
13472 `(("gclib-source" ; see 'README.md' of gffcompare
13473 ,(let ((commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13476 (version (git-version "0.10.3" revision commit)))
13479 (uri (git-reference
13480 (url "https://github.com/gpertea/gclib/")
13482 (file-name (git-file-name name version))
13484 (base32 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13485 (home-page "https://github.com/gpertea/gffcompare/")
13486 (synopsis "Tool for comparing or classifing transcripts of RNA-Seq")
13488 "@code{gffcompare} is a tool that can:
13490 @item compare and evaluate the accuracy of RNA-Seq transcript assemblers
13491 (Cufflinks, Stringtie);
13492 @item collapse (merge) duplicate transcripts from multiple GTF/GFF3 files (e.g.
13493 resulted from assembly of different samples);
13494 @item classify transcripts from one or multiple GTF/GFF3 files as they relate to
13495 reference transcripts provided in a annotation file (also in GTF/GFF3 format).
13499 license:expat ;license for gffcompare
13500 license:artistic2.0))))) ;license for gclib
13502 (define-public intervaltree
13503 (let ((commit "b90527f9e6d51cd36ecbb50429e4524d3a418ea5"))
13505 (name "intervaltree")
13506 (version (git-version "0.0.0" "1" commit))
13510 (uri (git-reference
13511 (url "https://github.com/ekg/intervaltree/")
13513 (file-name (git-file-name name version))
13515 (base32 "0rgv6q5fl4x5d74n6p5wvdna6zmbdbqpb4jqqh6vq3670gn08xad"))))
13516 (build-system gnu-build-system)
13518 '(#:tests? #f ; No tests.
13519 #:make-flags (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
13522 (modify-phases %standard-phases
13523 (delete 'configure)))) ; There is no configure phase.
13524 (home-page "https://github.com/ekg/intervaltree")
13525 (synopsis "Minimal C++ interval tree implementation")
13526 (description "An interval tree can be used to efficiently find a set of
13527 numeric intervals overlapping or containing another interval. This library
13528 provides a basic implementation of an interval tree using C++ templates,
13529 allowing the insertion of arbitrary types into the tree.")
13530 (license license:expat))))
13532 (define-public python-intervaltree
13534 (name "python-intervaltree")
13539 (uri (pypi-uri "intervaltree" version))
13542 "0wz234g6irlm4hivs2qzmnywk0ss06ckagwh15nflkyb3p462kyb"))))
13543 (build-system python-build-system)
13546 (modify-phases %standard-phases
13547 ;; pytest seems to have a check to make sure the user is testing
13548 ;; their checked-out code and not an installed, potentially
13549 ;; out-of-date copy. This is harmless here, since we just installed
13550 ;; the package, so we disable the check to avoid skipping tests
13552 (add-before 'check 'import-mismatch-error-workaround
13554 (setenv "PY_IGNORE_IMPORTMISMATCH" "1")
13557 `(("python-sortedcontainers" ,python-sortedcontainers)))
13559 `(("python-pytest" ,python-pytest)))
13560 (home-page "https://github.com/chaimleib/intervaltree")
13561 (synopsis "Editable interval tree data structure")
13563 "This package provides a mutable, self-balancing interval tree
13564 implementation for Python. Queries may be by point, by range overlap, or by
13565 range envelopment. This library was designed to allow tagging text and time
13566 intervals, where the intervals include the lower bound but not the upper
13568 (license license:asl2.0)))
13570 (define-public python-pypairix
13572 (name "python-pypairix")
13574 ;; The tarball on pypi does not include the makefile to build the
13579 (uri (git-reference
13580 (url "https://github.com/4dn-dcic/pairix")
13582 (file-name (git-file-name name version))
13585 "1snr3lrmsld8sy77ng6ba6wcmd33xjccf1l2f3m6pi29xis9nd6p"))))
13586 (build-system python-build-system)
13589 (modify-phases %standard-phases
13590 (add-before 'build 'build-programs
13591 (lambda _ (invoke "make")))
13592 (add-after 'install 'install-programs
13593 (lambda* (#:key outputs #:allow-other-keys)
13594 (copy-recursively "bin" (string-append
13595 (assoc-ref outputs "out")
13600 (home-page "https://github.com/4dn-dcic/pairix")
13601 (synopsis "Support for querying pairix-indexed bgzipped text files")
13603 "Pypairix is a Python module for fast querying on a pairix-indexed
13604 bgzipped text file that contains a pair of genomic coordinates per line.")
13605 (license license:expat)))
13607 (define-public python-pyfaidx
13609 (name "python-pyfaidx")
13614 (uri (pypi-uri "pyfaidx" version))
13617 "038xi3a6zvrxbyyfpp64ka8pcjgsdq4fgw9cl5lpxbvmm1bzzw2q"))))
13618 (build-system python-build-system)
13620 `(("python-six" ,python-six)))
13621 (home-page "http://mattshirley.com")
13622 (synopsis "Random access to fasta subsequences")
13624 "This package provides procedures for efficient pythonic random access to
13625 fasta subsequences.")
13626 (license license:bsd-3)))
13628 (define-public python2-pyfaidx
13629 (package-with-python2 python-pyfaidx))
13631 (define-public python-cooler
13633 (name "python-cooler")
13638 (uri (pypi-uri "cooler" version))
13641 "01g6gqix9ba27sappz6nfyiwabzrlf8i5fn8kwcz8ra356cq9crp"))))
13642 (build-system python-build-system)
13644 `(("python-asciitree" ,python-asciitree)
13645 ("python-biopython" ,python-biopython)
13646 ("python-click" ,python-click)
13647 ("python-cytoolz" ,python-cytoolz)
13648 ("python-dask" ,python-dask)
13649 ("python-h5py" ,python-h5py)
13650 ("python-multiprocess" ,python-multiprocess)
13651 ("python-numpy" ,python-numpy)
13652 ("python-pandas" ,python-pandas)
13653 ("python-pyfaidx" ,python-pyfaidx)
13654 ("python-pypairix" ,python-pypairix)
13655 ("python-pysam" ,python-pysam)
13656 ("python-pyyaml" ,python-pyyaml)
13657 ("python-scipy" ,python-scipy)
13658 ("python-simplejson" ,python-simplejson)))
13660 `(("python-mock" ,python-mock)
13661 ("python-pytest" ,python-pytest)))
13662 (home-page "https://github.com/mirnylab/cooler")
13663 (synopsis "Sparse binary format for genomic interaction matrices")
13665 "Cooler is a support library for a sparse, compressed, binary persistent
13666 storage format, called @code{cool}, used to store genomic interaction data,
13667 such as Hi-C contact matrices.")
13668 (license license:bsd-3)))
13670 (define-public python-hicmatrix
13672 (name "python-hicmatrix")
13676 ;; Version 12 is not available on pypi.
13678 (uri (git-reference
13679 (url "https://github.com/deeptools/HiCMatrix")
13681 (file-name (git-file-name name version))
13684 "1xhdyx16f3brgxgxybixdi64ki8nbbkq5vk4h9ahi11pzpjfn1pj"))))
13685 (build-system python-build-system)
13688 (modify-phases %standard-phases
13689 (add-after 'unpack 'relax-requirements
13691 (substitute* '("requirements.txt"
13693 (("cooler *=+ *0.8.5")
13697 `(("python-cooler" ,python-cooler)
13698 ("python-intervaltree" ,python-intervaltree)
13699 ("python-numpy" ,python-numpy)
13700 ("python-pandas" ,python-pandas)
13701 ("python-scipy" ,python-scipy)
13702 ("python-tables" ,python-tables)))
13703 (home-page "https://github.com/deeptools/HiCMatrix/")
13704 (synopsis "HiCMatrix class for HiCExplorer and pyGenomeTracks")
13706 "This helper package implements the @code{HiCMatrix} class for
13707 the HiCExplorer and pyGenomeTracks packages.")
13708 (license license:gpl3+)))
13710 (define-public python-hicexplorer
13712 (name "python-hicexplorer")
13716 ;; The latest version is not available on Pypi.
13718 (uri (git-reference
13719 (url "https://github.com/deeptools/HiCExplorer")
13721 (file-name (git-file-name name version))
13724 "0q5gpbzmrkvygqgw524q36b4nrivcmyi5v194vsx0qw7b3gcmq08"))))
13725 (build-system python-build-system)
13728 (modify-phases %standard-phases
13729 (add-after 'unpack 'loosen-up-requirements
13731 (substitute* "setup.py"
13735 `(("python-biopython" ,python-biopython)
13736 ("python-configparser" ,python-configparser)
13737 ("python-cooler" ,python-cooler)
13738 ("python-future" ,python-future)
13739 ("python-intervaltree" ,python-intervaltree)
13740 ("python-jinja2" ,python-jinja2)
13741 ("python-matplotlib" ,python-matplotlib)
13742 ("python-numpy" ,python-numpy)
13743 ("python-pandas" ,python-pandas)
13744 ("python-pybigwig" ,python-pybigwig)
13745 ("python-pysam" ,python-pysam)
13746 ("python-scipy" ,python-scipy)
13747 ("python-six" ,python-six)
13748 ("python-tables" ,python-tables)
13749 ("python-unidecode" ,python-unidecode)))
13750 (home-page "https://hicexplorer.readthedocs.io")
13751 (synopsis "Process, analyze and visualize Hi-C data")
13753 "HiCExplorer is a powerful and easy to use set of tools to process,
13754 normalize and visualize Hi-C data. HiCExplorer facilitates the creation of
13755 contact matrices, correction of contacts, TAD detection, A/B compartments,
13756 merging, reordering or chromosomes, conversion from different formats
13757 including cooler and detection of long-range contacts. Moreover, it allows
13758 the visualization of multiple contact matrices along with other types of data
13759 like genes, compartments, ChIP-seq coverage tracks (and in general any type of
13760 genomic scores), long range contacts and the visualization of viewpoints.")
13761 (license license:gpl3)))
13763 (define-public python-pygenometracks
13765 (name "python-pygenometracks")
13770 (uri (pypi-uri "pyGenomeTracks" version))
13773 "16laa0wnf4qn9fb9ych4w1vqhqwjss70v0y0f6wp4gwqfrlgac0f"))))
13774 (build-system python-build-system)
13776 `(#:tests? #f ; there are none
13778 (modify-phases %standard-phases
13779 (add-after 'unpack 'relax-requirements
13781 (substitute* "setup.py"
13782 (("matplotlib ==3.1.1")
13783 "matplotlib >=3.1.1"))
13786 `(("python-future" ,python-future)
13787 ("python-gffutils" ,python-gffutils)
13788 ("python-hicmatrix" ,python-hicmatrix)
13789 ("python-intervaltree" ,python-intervaltree)
13790 ("python-matplotlib" ,python-matplotlib)
13791 ("python-numpy" ,python-numpy)
13792 ("python-pybigwig" ,python-pybigwig)
13793 ("python-pysam" ,python-pysam)
13794 ("python-tqdm" ,python-tqdm)))
13796 `(("python-pytest" ,python-pytest)))
13797 (home-page "https://pygenometracks.readthedocs.io")
13798 (synopsis "Program and library to plot beautiful genome browser tracks")
13800 "This package aims to produce high-quality genome browser tracks that
13801 are highly customizable. Currently, it is possible to plot: bigwig, bed (many
13802 options), bedgraph, links (represented as arcs), and Hi-C matrices.
13803 pyGenomeTracks can make plots with or without Hi-C data.")
13804 (license license:gpl3+)))
13806 (define-public python-hic2cool
13808 (name "python-hic2cool")
13813 (uri (pypi-uri "hic2cool" version))
13816 "0xy6mhfns2lzib1kcr6419jjp6pmh0qx8z8na55lmiwn0ds8q9cl"))))
13817 (build-system python-build-system)
13818 (arguments '(#:tests? #f)) ; no tests included
13820 `(("python-cooler" ,python-cooler)))
13821 (home-page "https://github.com/4dn-dcic/hic2cool")
13822 (synopsis "Converter for .hic and .cool files")
13824 "This package provides a converter between @code{.hic} files (from
13825 juicer) and single-resolution or multi-resolution @code{.cool} files (for
13826 cooler). Both @code{hic} and @code{cool} files describe Hi-C contact
13828 (license license:expat)))
13830 (define-public r-pore
13838 (string-append "mirror://sourceforge/rpore/" version
13839 "/poRe_" version ".tar.gz"))
13841 (base32 "0pih9nljbv8g4x8rkk29i7aqq681b782r5s5ynp4nw9yzqnmmksv"))))
13842 (properties `((upstream-name . "poRe")))
13843 (build-system r-build-system)
13845 `(("r-bit64" ,r-bit64)
13846 ("r-data-table" ,r-data-table)
13847 ("r-rhdf5" ,r-rhdf5)
13848 ("r-shiny" ,r-shiny)
13849 ("r-svdialogs" ,r-svdialogs)))
13850 (home-page "https://sourceforge.net/projects/rpore/")
13851 (synopsis "Visualize Nanopore sequencing data")
13853 "This package provides graphical user interfaces to organize and visualize Nanopore
13855 ;; This is free software but the license variant is unclear:
13856 ;; <https://github.com/mw55309/poRe_docs/issues/10>.
13857 (license license:bsd-3)))
13859 (define-public r-xbioc
13860 (let ((revision "1")
13861 (commit "6ff0670a37ab3036aaf1d94aa4b208310946b0b5"))
13864 (version (git-version "0.1.16" revision commit))
13867 (uri (git-reference
13868 (url "https://github.com/renozao/xbioc")
13870 (file-name (git-file-name name version))
13873 "0w8bsq5myiwkfhh83nm6is5ichiyvwa1axx2szvxnzq39x6knf66"))))
13874 (build-system r-build-system)
13876 `(("r-annotationdbi" ,r-annotationdbi)
13877 ("r-assertthat" ,r-assertthat)
13878 ("r-biobase" ,r-biobase)
13879 ("r-biocmanager" ,r-biocmanager)
13880 ("r-digest" ,r-digest)
13881 ("r-pkgmaker" ,r-pkgmaker)
13883 ("r-reshape2" ,r-reshape2)
13884 ("r-stringr" ,r-stringr)))
13885 (home-page "https://github.com/renozao/xbioc/")
13886 (synopsis "Extra base functions for Bioconductor")
13887 (description "This package provides extra utility functions to perform
13888 common tasks in the analysis of omics data, leveraging and enhancing features
13889 provided by Bioconductor packages.")
13890 (license license:gpl3+))))
13892 (define-public r-cssam
13893 (let ((revision "1")
13894 (commit "9ec58c982fa551af0d80b1a266890d92954833f2"))
13897 (version (git-version "1.4" revision commit))
13900 (uri (git-reference
13901 (url "https://github.com/shenorrLab/csSAM")
13903 (file-name (git-file-name name version))
13906 "128syf9v39gk0z3ip000qpsjbg6l1siyq6c8b0hz41dzg5achyb3"))))
13907 (build-system r-build-system)
13909 `(("r-formula" ,r-formula)
13910 ("r-ggplot2" ,r-ggplot2)
13911 ("r-pkgmaker" ,r-pkgmaker)
13913 ("r-rngtools" ,r-rngtools)
13914 ("r-scales" ,r-scales)))
13915 (home-page "https://github.com/shenorrLab/csSAM/")
13916 (synopsis "Cell type-specific statistical analysis of microarray")
13917 (description "This package implements the method csSAM that computes
13918 cell-specific differential expression from measured cell proportions using
13921 (license license:lgpl2.1+))))
13923 (define-public r-bseqsc
13924 (let ((revision "1")
13925 (commit "fef3f3e38dcf3df37103348b5780937982b43b98"))
13928 (version (git-version "1.0" revision commit))
13931 (uri (git-reference
13932 (url "https://github.com/shenorrLab/bseqsc")
13934 (file-name (git-file-name name version))
13937 "1prw13wa20f7wlc3gkkls66n1kxz8d28qrb8icfqdwdnnv8w5qg8"))))
13938 (build-system r-build-system)
13940 `(("r-abind" ,r-abind)
13941 ("r-annotationdbi" ,r-annotationdbi)
13942 ("r-biobase" ,r-biobase)
13943 ("r-cssam" ,r-cssam)
13944 ("r-dplyr" ,r-dplyr)
13945 ("r-e1071" ,r-e1071)
13946 ("r-edger" ,r-edger)
13947 ("r-ggplot2" ,r-ggplot2)
13949 ("r-openxlsx" ,r-openxlsx)
13950 ("r-pkgmaker" ,r-pkgmaker)
13952 ("r-preprocesscore" ,r-preprocesscore)
13953 ("r-rngtools" ,r-rngtools)
13954 ("r-scales" ,r-scales)
13955 ("r-stringr" ,r-stringr)
13956 ("r-xbioc" ,r-xbioc)))
13957 (home-page "https://github.com/shenorrLab/bseqsc")
13958 (synopsis "Deconvolution of bulk sequencing experiments using single cell data")
13959 (description "BSeq-sc is a bioinformatics analysis pipeline that
13960 leverages single-cell sequencing data to estimate cell type proportion and
13961 cell type-specific gene expression differences from RNA-seq data from bulk
13962 tissue samples. This is a companion package to the publication \"A
13963 single-cell transcriptomic map of the human and mouse pancreas reveals inter-
13964 and intra-cell population structure.\" Baron et al. Cell Systems (2016)
13965 @url{https://www.ncbi.nlm.nih.gov/pubmed/27667365}.")
13966 (license license:gpl2+))))
13968 (define-public porechop
13969 ;; The recommended way to install is to clone the git repository
13970 ;; https://github.com/rrwick/Porechop#installation
13971 (let ((commit "289d5dca4a5fc327f97b3f8cecb68ecaf1014861")
13975 (version (git-version "0.2.3" revision commit))
13979 (uri (git-reference
13980 (url "https://github.com/rrwick/Porechop")
13982 (file-name (git-file-name name version))
13984 (base32 "05ps43gig0d3ia9x5lj84lb00hbsl6ba9n7y7jz927npxbr2ym23"))))
13985 (build-system python-build-system)
13986 (home-page "https://github.com/rrwick/porechop")
13987 (synopsis "Finding, trimming or splitting adapters, in Oxford Nanopore reads")
13989 "The porechop package is a tool for finding and removing adapters from Oxford
13990 Nanopore reads. Adapters on the ends of reads are trimmed off, and when a read
13991 has an adapter in its middle, it is treated as chimeric and chopped into
13992 separate reads. Porechop performs thorough alignments to effectively find
13993 adapters, even at low sequence identity. Porechop also supports demultiplexing
13994 of Nanopore reads that were barcoded with the Native Barcoding Kit, PCR
13995 Barcoding Kit or Rapid Barcoding Kit.")
13996 (license license:gpl3+))))
13998 (define-public poretools
13999 ;; The latest release was in 2016 and the latest commit is from 2017
14000 ;; the recommended way to install is to clone the git repository
14001 ;; https://poretools.readthedocs.io/en/latest/content/installation.html
14002 (let ((commit "e426b1f09e86ac259a00c261c79df91510777407")
14006 (version (git-version "0.6.0" revision commit))
14010 (uri (git-reference
14011 (url "https://github.com/arq5x/poretools")
14013 (file-name (git-file-name name version))
14015 (base32 "0bglj833wxpp3cq430p1d3xp085ls221js2y90w7ir2x5ay8l7am"))))
14016 (build-system python-build-system)
14017 ;; requires python >=2.7, <3.0, and the same for python dependencies
14018 (arguments `(#:python ,python-2))
14022 `(("python-dateutil" ,python2-dateutil)
14023 ("python-h5py" ,python2-h5py)
14024 ("python-matplotlib" ,python2-matplotlib)
14025 ("python-pandas" ,python2-pandas)
14026 ("python-seaborn" ,python2-seaborn)))
14027 (home-page "https://poretools.readthedocs.io")
14028 (synopsis "Toolkit for working with nanopore sequencing data")
14030 "The MinION from Oxford Nanopore Technologies is a nanopore sequencer.
14031 This @code{poretools} package is a flexible toolkit for exploring datasets
14032 generated by nanopore sequencing devices for the purposes of quality control and
14033 downstream analysis. Poretools operates directly on the native FAST5, a variant
14034 of the Hierarchical Data Format (HDF5) standard.")
14035 (license license:expat))))
14037 (define-public jamm
14040 (version "1.0.7.6")
14044 (uri (git-reference
14045 (url "https://github.com/mahmoudibrahim/JAMM")
14046 (commit (string-append "JAMMv" version))))
14047 (file-name (git-file-name name version))
14050 "0bsa5mf9n9q5jz7mmacrra41l7r8rac5vgsn6wv1fb52ya58b970"))))
14051 (build-system gnu-build-system)
14053 `(#:tests? #f ; there are none
14055 (modify-phases %standard-phases
14056 (delete 'configure)
14059 (lambda* (#:key inputs outputs #:allow-other-keys)
14060 (let* ((out (assoc-ref outputs "out"))
14061 (libexec (string-append out "/libexec/jamm"))
14062 (bin (string-append out "/bin")))
14063 (substitute* '("JAMM.sh"
14064 "SignalGenerator.sh")
14066 (string-append "sPath=\"" libexec "\"\n")))
14067 (for-each (lambda (file)
14068 (install-file file libexec))
14069 (list "bincalculator.r"
14081 (chmod script #o555)
14082 (install-file script bin)
14083 (wrap-program (string-append bin "/" script)
14084 `("PATH" ":" prefix
14085 (,(string-append (assoc-ref inputs "coreutils") "/bin")
14086 ,(string-append (assoc-ref inputs "gawk") "/bin")
14087 ,(string-append (assoc-ref inputs "perl") "/bin")
14088 ,(string-append (assoc-ref inputs "r-minimal") "/bin")))
14089 `("PERL5LIB" ":" prefix (,(getenv "PERL5LIB")))
14090 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
14091 (list "JAMM.sh" "SignalGenerator.sh")))
14095 ("coreutils" ,coreutils)
14098 ("r-minimal" ,r-minimal)
14099 ;;("r-parallel" ,r-parallel)
14100 ("r-signal" ,r-signal)
14101 ("r-mclust" ,r-mclust)))
14102 (home-page "https://github.com/mahmoudibrahim/JAMM")
14103 (synopsis "Peak finder for NGS datasets")
14105 "JAMM is a peak finder for next generation sequencing datasets (ChIP-Seq,
14106 ATAC-Seq, DNase-Seq, etc.) that can integrate replicates and assign peak
14107 boundaries accurately. JAMM is applicable to both broad and narrow
14109 (license license:gpl3+)))
14111 (define-public ngless
14118 (uri (git-reference
14119 (url "https://gitlab.com/ngless/ngless.git")
14120 (commit (string-append "v" version))))
14121 (file-name (git-file-name name version))
14124 "1wim8wpqyff080dfcazynrmjwqas38m24m0v350w245mmhrapdma"))))
14125 (build-system haskell-build-system)
14127 `(#:haddock? #f ; The haddock phase fails with: NGLess/CmdArgs.hs:20:1:
14128 ; error: parse error on input import
14129 ; import Options.Applicative
14131 (modify-phases %standard-phases
14132 (add-after 'unpack 'create-Versions.hs
14134 (substitute* "Makefile"
14135 (("BWA_VERSION = .*")
14136 (string-append "BWA_VERSION = "
14137 ,(package-version bwa) "\n"))
14138 (("SAM_VERSION = .*")
14139 (string-append "SAM_VERSION = "
14140 ,(package-version samtools) "\n"))
14141 (("PRODIGAL_VERSION = .*")
14142 (string-append "PRODIGAL_VERSION = "
14143 ,(package-version prodigal) "\n"))
14144 (("MINIMAP2_VERSION = .*")
14145 (string-append "MINIMAP2_VERSION = "
14146 ,(package-version minimap2) "\n")))
14147 (invoke "make" "NGLess/Dependencies/Versions.hs")
14149 (add-after 'create-Versions.hs 'create-cabal-file
14150 (lambda _ (invoke "hpack") #t))
14151 ;; These tools are expected to be installed alongside ngless.
14152 (add-after 'install 'link-tools
14153 (lambda* (#:key inputs outputs #:allow-other-keys)
14154 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
14155 (symlink (string-append (assoc-ref inputs "prodigal")
14157 (string-append bin "ngless-" ,version "-prodigal"))
14158 (symlink (string-append (assoc-ref inputs "minimap2")
14160 (string-append bin "ngless-" ,version "-minimap2"))
14161 (symlink (string-append (assoc-ref inputs "samtools")
14163 (string-append bin "ngless-" ,version "-samtools"))
14164 (symlink (string-append (assoc-ref inputs "bwa")
14166 (string-append bin "ngless-" ,version "-bwa"))
14169 `(("prodigal" ,prodigal)
14171 ("samtools" ,samtools)
14172 ("minimap2" ,minimap2)
14173 ("ghc-aeson" ,ghc-aeson)
14174 ("ghc-ansi-terminal" ,ghc-ansi-terminal)
14175 ("ghc-async" ,ghc-async)
14176 ("ghc-atomic-write" ,ghc-atomic-write)
14177 ("ghc-bytestring-lexing" ,ghc-bytestring-lexing)
14178 ("ghc-conduit" ,ghc-conduit)
14179 ("ghc-conduit-algorithms" ,ghc-conduit-algorithms)
14180 ("ghc-conduit-extra" ,ghc-conduit-extra)
14181 ("ghc-configurator" ,ghc-configurator)
14182 ("ghc-convertible" ,ghc-convertible)
14183 ("ghc-data-default" ,ghc-data-default)
14184 ("ghc-diagrams-core" ,ghc-diagrams-core)
14185 ("ghc-diagrams-lib" ,ghc-diagrams-lib)
14186 ("ghc-diagrams-svg" ,ghc-diagrams-svg)
14187 ("ghc-double-conversion" ,ghc-double-conversion)
14188 ("ghc-edit-distance" ,ghc-edit-distance)
14189 ("ghc-either" ,ghc-either)
14190 ("ghc-errors" ,ghc-errors)
14191 ("ghc-extra" ,ghc-extra)
14192 ("ghc-filemanip" ,ghc-filemanip)
14193 ("ghc-file-embed" ,ghc-file-embed)
14194 ("ghc-gitrev" ,ghc-gitrev)
14195 ("ghc-hashtables" ,ghc-hashtables)
14196 ("ghc-http-conduit" ,ghc-http-conduit)
14197 ("ghc-inline-c" ,ghc-inline-c)
14198 ("ghc-inline-c-cpp" ,ghc-inline-c-cpp)
14199 ("ghc-intervalmap" ,ghc-intervalmap)
14200 ("ghc-missingh" ,ghc-missingh)
14201 ("ghc-optparse-applicative" ,ghc-optparse-applicative)
14202 ("ghc-regex" ,ghc-regex)
14203 ("ghc-safe" ,ghc-safe)
14204 ("ghc-safeio" ,ghc-safeio)
14205 ("ghc-strict" ,ghc-strict)
14206 ("ghc-tar" ,ghc-tar)
14207 ("ghc-tar-conduit" ,ghc-tar-conduit)
14208 ("ghc-unliftio" ,ghc-unliftio)
14209 ("ghc-unliftio-core" ,ghc-unliftio-core)
14210 ("ghc-vector" ,ghc-vector)
14211 ("ghc-yaml" ,ghc-yaml)
14212 ("ghc-zlib" ,ghc-zlib)))
14215 ("r-hdf5r" ,r-hdf5r)
14216 ("r-iterators" ,r-iterators)
14217 ("r-itertools" ,r-itertools)
14218 ("r-matrix" ,r-matrix)))
14220 `(("ghc-hpack" ,ghc-hpack)
14221 ("ghc-quickcheck" ,ghc-quickcheck)
14222 ("ghc-test-framework" ,ghc-test-framework)
14223 ("ghc-test-framework-hunit",ghc-test-framework-hunit)
14224 ("ghc-test-framework-quickcheck2" ,ghc-test-framework-quickcheck2)
14225 ("ghc-test-framework-th" ,ghc-test-framework-th)))
14226 (home-page "https://gitlab.com/ngless/ngless")
14227 (synopsis "DSL for processing next-generation sequencing data")
14228 (description "Ngless is a domain-specific language for
14229 @dfn{next-generation sequencing} (NGS) data processing.")
14230 (license license:expat)))
14232 (define-public filtlong
14233 ;; The recommended way to install is to clone the git repository
14234 ;; https://github.com/rrwick/Filtlong#installation
14235 ;; and the lastest release is more than nine months old
14236 (let ((commit "d1bb46dfe8bc7efe6257b5ce222c04bfe8aedaab")
14240 (version (git-version "0.2.0" revision commit))
14244 (uri (git-reference
14245 (url "https://github.com/rrwick/Filtlong")
14247 (file-name (git-file-name name version))
14249 (base32 "1xr92r820x8qlkcr3b57iw223yq8vjgyi42jr79w2xgw47qzr575"))))
14250 (build-system gnu-build-system)
14252 `(#:tests? #f ; no check target
14254 (modify-phases %standard-phases
14255 (delete 'configure)
14257 (lambda* (#:key outputs #:allow-other-keys)
14258 (let* ((out (assoc-ref outputs "out"))
14259 (bin (string-append out "/bin"))
14260 (scripts (string-append out "/share/filtlong/scripts")))
14261 (install-file "bin/filtlong" bin)
14262 (install-file "scripts/histogram.py" scripts)
14263 (install-file "scripts/read_info_histograms.sh" scripts))
14265 (add-after 'install 'wrap-program
14266 (lambda* (#:key inputs outputs #:allow-other-keys)
14267 (let* ((out (assoc-ref outputs "out"))
14268 (path (getenv "PYTHONPATH")))
14269 (wrap-program (string-append out
14270 "/share/filtlong/scripts/histogram.py")
14271 `("PYTHONPATH" ":" prefix (,path))))
14273 (add-before 'check 'patch-tests
14275 (substitute* "scripts/read_info_histograms.sh"
14276 (("awk") (which "gawk")))
14279 `(("gawk" ,gawk) ;for read_info_histograms.sh
14280 ("python" ,python-2) ;required for histogram.py
14282 (home-page "https://github.com/rrwick/Filtlong/")
14283 (synopsis "Tool for quality filtering of Nanopore and PacBio data")
14285 "The Filtlong package is a tool for filtering long reads by quality.
14286 It can take a set of long reads and produce a smaller, better subset. It uses
14287 both read length (longer is better) and read identity (higher is better) when
14288 choosing which reads pass the filter.")
14289 (license (list license:gpl3 ;filtlong
14290 license:asl2.0))))) ;histogram.py
14292 (define-public nanopolish
14293 ;; The recommended way to install is to clone the git repository
14294 ;; <https://github.com/jts/nanopolish#installing-a-particular-release>.
14295 ;; Also, the differences between release and current version seem to be
14297 (let ((commit "6331dc4f15b9dfabb954ba3fae9d76b6c3ca6377")
14300 (name "nanopolish")
14301 (version (git-version "0.11.1" revision commit))
14305 (uri (git-reference
14306 (url "https://github.com/jts/nanopolish")
14309 (file-name (git-file-name name version))
14311 (base32 "15ikl3d37y49pwd7vx36xksgsqajhf24q7qqsnpl15dqqyy5qgbc"))
14312 (modules '((guix build utils)))
14315 (delete-file-recursively "htslib")
14317 (build-system gnu-build-system)
14320 `("HDF5=noinstall" "EIGEN=noinstall" "HTS=noinstall" "CC=gcc")
14321 #:tests? #f ; no check target
14323 (modify-phases %standard-phases
14324 (add-after 'unpack 'find-eigen
14325 (lambda* (#:key inputs #:allow-other-keys)
14327 (string-append (assoc-ref inputs "eigen")
14329 (or (getenv "CPATH") "")))
14331 (delete 'configure)
14333 (lambda* (#:key outputs #:allow-other-keys)
14334 (let* ((out (assoc-ref outputs "out"))
14335 (bin (string-append out "/bin"))
14336 (scripts (string-append out "/share/nanopolish/scripts")))
14338 (install-file "nanopolish" bin)
14339 (for-each (lambda (file) (install-file file scripts))
14340 (find-files "scripts" ".*"))
14342 (add-after 'install 'wrap-programs
14343 (lambda* (#:key outputs #:allow-other-keys)
14344 (for-each (lambda (file)
14345 (wrap-program file `("PYTHONPATH" ":" prefix (,path))))
14346 (find-files "/share/nanopolish/scripts" "\\.py"))
14347 (for-each (lambda (file)
14348 (wrap-program file `("PERL5LIB" ":" prefix (,path))))
14349 (find-files "/share/nanopolish/scripts" "\\.pl"))
14356 ("python" ,python-wrapper)
14357 ("python-biopython" ,python-biopython)
14358 ("python-numpy" ,python-numpy)
14359 ("python-pysam" ,python-pysam)
14360 ("python-scikit-learn" , python-scikit-learn)
14361 ("python-scipy" ,python-scipy)
14363 (home-page "https://github.com/jts/nanopolish")
14364 (synopsis "Signal-level analysis of Oxford Nanopore sequencing data")
14366 "This package analyses the Oxford Nanopore sequencing data at signal-level.
14367 Nanopolish can calculate an improved consensus sequence for a draft genome
14368 assembly, detect base modifications, call SNPs (Single nucleotide
14369 polymorphisms) and indels with respect to a reference genome and more.")
14370 (license license:expat))))
14372 (define-public cnvkit
14379 (uri (git-reference
14380 (url "https://github.com/etal/cnvkit")
14381 (commit (string-append "v" version))))
14382 (file-name (git-file-name name version))
14384 (base32 "0g2f78k68yglmj4fsfmgs8idqv3di9aj53fg0ld0hqljg8chhh82"))))
14385 (build-system python-build-system)
14387 `(("python-biopython" ,python-biopython)
14388 ("python-future" ,python-future)
14389 ("python-matplotlib" ,python-matplotlib)
14390 ("python-numpy" ,python-numpy)
14391 ("python-reportlab" ,python-reportlab)
14392 ("python-pandas" ,python-pandas)
14393 ("python-pysam" ,python-pysam)
14394 ("python-pyfaidx" ,python-pyfaidx)
14395 ("python-scipy" ,python-scipy)
14397 ("r-dnacopy" ,r-dnacopy)))
14398 (home-page "https://cnvkit.readthedocs.org/")
14399 (synopsis "Copy number variant detection from targeted DNA sequencing")
14401 "CNVkit is a Python library and command-line software toolkit to infer
14402 and visualize copy number from high-throughput DNA sequencing data. It is
14403 designed for use with hybrid capture, including both whole-exome and custom
14404 target panels, and short-read sequencing platforms such as Illumina and Ion
14406 (license license:asl2.0)))
14408 (define-public python-pyfit-sne
14410 (name "python-pyfit-sne")
14415 (uri (git-reference
14416 (url "https://github.com/KlugerLab/pyFIt-SNE")
14418 (file-name (git-file-name name version))
14420 (base32 "13wh3qkzs56azmmgnxib6xfr29g7xh09sxylzjpni5j0pp0rc5qw"))))
14421 (build-system python-build-system)
14423 `(("python-numpy" ,python-numpy)))
14427 `(("python-cython" ,python-cython)))
14428 (home-page "https://github.com/KlugerLab/pyFIt-SNE")
14429 (synopsis "FFT-accelerated Interpolation-based t-SNE")
14431 "t-Stochastic Neighborhood Embedding (t-SNE) is a highly successful
14432 method for dimensionality reduction and visualization of high dimensional
14433 datasets. A popular implementation of t-SNE uses the Barnes-Hut algorithm to
14434 approximate the gradient at each iteration of gradient descent. This package
14435 is a Cython wrapper for FIt-SNE.")
14436 (license license:bsd-4)))
14438 (define-public bbmap
14444 (uri (string-append
14445 "mirror://sourceforge/bbmap/BBMap_" version ".tar.gz"))
14448 "1q4rfhxcb6z3gm8zg2davjz98w22lkf4hm9ikxz9kdl93pil3wkd"))))
14449 (build-system ant-build-system)
14451 `(#:build-target "dist"
14452 #:tests? #f ; there are none
14454 (list (string-append "-Dmpijar="
14455 (assoc-ref %build-inputs "java-openmpi")
14457 #:modules ((guix build ant-build-system)
14459 (guix build java-utils))
14461 (modify-phases %standard-phases
14462 (add-after 'build 'build-jni-library
14464 (with-directory-excursion "jni"
14465 (invoke "make" "-f" "makefile.linux"))))
14466 ;; There is no install target
14467 (replace 'install (install-jars "dist"))
14468 (add-after 'install 'install-scripts-and-documentation
14469 (lambda* (#:key outputs #:allow-other-keys)
14470 (substitute* "calcmem.sh"
14471 (("\\| awk ") (string-append "| " (which "awk") " ")))
14472 (let* ((scripts (find-files "." "\\.sh$"))
14473 (out (assoc-ref outputs "out"))
14474 (bin (string-append out "/bin"))
14475 (doc (string-append out "/share/doc/bbmap"))
14476 (jni (string-append out "/lib/jni")))
14477 (substitute* scripts
14478 (("\\$DIR\"\"docs") doc)
14480 (string-append "CP=" out "/share/java/BBTools.jar\n"))
14481 (("^NATIVELIBDIR.*")
14482 (string-append "NATIVELIBDIR=" jni "\n"))
14484 (string-append "CMD=\"" (which "java"))))
14485 (for-each (lambda (script) (install-file script bin)) scripts)
14487 ;; Install JNI library
14488 (install-file "jni/libbbtoolsjni.so" jni)
14490 ;; Install documentation
14491 (install-file "docs/readme.txt" doc)
14492 (copy-recursively "docs/guides" doc))
14497 ("java-eclipse-jdt-core" ,java-eclipse-jdt-core)
14498 ("java-eclipse-jdt-compiler-apt" ,java-eclipse-jdt-compiler-apt)
14499 ("java-openmpi" ,java-openmpi)))
14500 (home-page "https://sourceforge.net/projects/bbmap/")
14501 (synopsis "Aligner and other tools for short sequencing reads")
14503 "This package provides bioinformatic tools to align, deduplicate,
14504 reformat, filter and normalize DNA and RNA-seq data. It includes the
14505 following tools: BBMap, a short read aligner for DNA and RNA-seq data; BBNorm,
14506 a kmer-based error-correction and normalization tool; Dedupe, a tool to
14507 simplify assemblies by removing duplicate or contained subsequences that share
14508 a target percent identity; Reformat, to convert reads between
14509 fasta/fastq/scarf/fasta+qual/sam, interleaved/paired, and ASCII-33/64, at over
14510 500 MB/s; and BBDuk, a tool to filter, trim, or mask reads with kmer matches
14511 to an artifact/contaminant file.")
14512 (license license:bsd-3)))
14514 (define-public velvet
14520 (uri (string-append "https://www.ebi.ac.uk/~zerbino/velvet/"
14521 "velvet_" version ".tgz"))
14524 "0h3njwy66p6bx14r3ar1byb0ccaxmxka4c65rn4iybyiqa4d8kc8"))
14525 ;; Delete bundled libraries
14526 (modules '((guix build utils)))
14529 (delete-file "Manual.pdf")
14530 (delete-file-recursively "third-party")
14532 (build-system gnu-build-system)
14534 `(#:make-flags '("OPENMP=t")
14535 #:test-target "test"
14537 (modify-phases %standard-phases
14538 (delete 'configure)
14539 (add-after 'unpack 'fix-zlib-include
14541 (substitute* "src/binarySequences.c"
14542 (("../third-party/zlib-1.2.3/zlib.h") "zlib.h"))
14545 (lambda* (#:key outputs #:allow-other-keys)
14546 (let* ((out (assoc-ref outputs "out"))
14547 (bin (string-append out "/bin"))
14548 (doc (string-append out "/share/doc/velvet")))
14551 (install-file "velveth" bin)
14552 (install-file "velvetg" bin)
14553 (install-file "Manual.pdf" doc)
14554 (install-file "Columbus_manual.pdf" doc)
14557 `(("openmpi" ,openmpi)
14560 `(("texlive" ,(texlive-union (list texlive-latex-graphics
14561 texlive-latex-hyperref)))))
14562 (home-page "https://www.ebi.ac.uk/~zerbino/velvet/")
14563 (synopsis "Nucleic acid sequence assembler for very short reads")
14565 "Velvet is a de novo genomic assembler specially designed for short read
14566 sequencing technologies, such as Solexa or 454. Velvet currently takes in
14567 short read sequences, removes errors then produces high quality unique
14568 contigs. It then uses paired read information, if available, to retrieve the
14569 repeated areas between contigs.")
14570 (license license:gpl2+)))
14572 (define-public python-velocyto
14574 (name "python-velocyto")
14575 (version "0.17.17")
14579 (uri (pypi-uri "velocyto" version))
14582 "0fgygyzqgrq32dv6a00biq1p1cwi6kbl5iqblxq1kklj6b2mzmhs"))))
14583 (build-system python-build-system)
14585 `(("python-joblib" ,python-joblib)))
14587 `(("python-click" ,python-click)
14588 ("python-cython" ,python-cython)
14589 ("python-h5py" ,python-h5py)
14590 ("python-loompy" ,python-loompy)
14591 ("python-matplotlib" ,python-matplotlib)
14592 ("python-numba" ,python-numba)
14593 ("python-numpy" ,python-numpy)
14594 ("python-pandas" ,python-pandas)
14595 ("python-pysam" ,python-pysam)
14596 ("python-scikit-learn" ,python-scikit-learn)
14597 ("python-scipy" ,python-scipy)))
14598 (home-page "https://github.com/velocyto-team/velocyto.py")
14599 (synopsis "RNA velocity analysis for single cell RNA-seq data")
14601 "Velocyto is a library for the analysis of RNA velocity. Velocyto
14602 includes a command line tool and an analysis pipeline.")
14603 (license license:bsd-2)))
14605 (define-public arriba
14612 (uri (string-append "https://github.com/suhrig/arriba/releases/"
14613 "download/v" version "/arriba_v" version ".tar.gz"))
14616 "0jx9656ry766vb8z08m1c3im87b0c82qpnjby9wz4kcz8vn87dx2"))))
14617 (build-system gnu-build-system)
14619 `(#:tests? #f ; there are none
14621 (modify-phases %standard-phases
14622 (replace 'configure
14623 (lambda* (#:key inputs #:allow-other-keys)
14624 (let ((htslib (assoc-ref inputs "htslib")))
14625 (substitute* "Makefile"
14626 (("-I\\$\\(HTSLIB\\)/htslib")
14627 (string-append "-I" htslib "/include/htslib"))
14628 ((" \\$\\(HTSLIB\\)/libhts.a")
14629 (string-append " " htslib "/lib/libhts.so"))))
14630 (substitute* "run_arriba.sh"
14631 (("^STAR ") (string-append (which "STAR") " "))
14632 (("samtools --version-only")
14633 (string-append (which "samtools") " --version-only"))
14634 (("samtools index")
14635 (string-append (which "samtools") " index"))
14637 (string-append (which "samtools") " sort")))
14640 (lambda* (#:key outputs #:allow-other-keys)
14641 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
14642 (install-file "arriba" bin)
14643 (install-file "run_arriba.sh" bin)
14644 (install-file "draw_fusions.R" bin)
14645 (wrap-program (string-append bin "/draw_fusions.R")
14646 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
14649 `(("htslib" ,htslib)
14650 ("r-minimal" ,r-minimal)
14651 ("r-circlize" ,r-circlize)
14652 ("r-genomicalignments" ,r-genomicalignments)
14653 ("r-genomicranges" ,r-genomicranges)
14654 ("samtools" ,samtools)
14657 (home-page "https://github.com/suhrig/arriba")
14658 (synopsis "Gene fusion detection from RNA-Seq data ")
14660 "Arriba is a command-line tool for the detection of gene fusions from
14661 RNA-Seq data. It was developed for the use in a clinical research setting.
14662 Therefore, short runtimes and high sensitivity were important design criteria.
14663 It is based on the fast STAR aligner and the post-alignment runtime is
14664 typically just around two minutes. In contrast to many other fusion detection
14665 tools which build on STAR, Arriba does not require to reduce the
14666 @code{alignIntronMax} parameter of STAR to detect small deletions.")
14667 ;; All code is under the Expat license with the exception of
14668 ;; "draw_fusions.R", which is under GPLv3.
14669 (license (list license:expat license:gpl3))))
14671 (define-public adapterremoval
14673 (name "adapterremoval")
14678 (uri (git-reference
14679 (url "https://github.com/MikkelSchubert/adapterremoval")
14680 (commit (string-append "v" version))))
14681 (file-name (git-file-name name version))
14684 "1nf3ki5pfzalhrx2fr1y6pfqfi133yj2m7q4fj9irf5fb94bapwr"))))
14685 (build-system gnu-build-system)
14687 `(#:make-flags (list "COLOR_BUILD=no"
14688 (string-append "PREFIX="
14689 (assoc-ref %outputs "out")))
14690 #:test-target "test"
14692 (modify-phases %standard-phases
14693 (delete 'configure))))
14696 (home-page "https://adapterremoval.readthedocs.io/")
14697 (synopsis "Rapid sequence adapter trimming, identification, and read merging")
14699 "This program searches for and removes remnant adapter sequences from
14700 @dfn{High-Throughput Sequencing} (HTS) data and (optionally) trims low quality
14701 bases from the 3' end of reads following adapter removal. AdapterRemoval can
14702 analyze both single end and paired end data, and can be used to merge
14703 overlapping paired-ended reads into (longer) consensus sequences.
14704 Additionally, the AdapterRemoval may be used to recover a consensus adapter
14705 sequence for paired-ended data, for which this information is not available.")
14706 (license license:gpl3+)))
14708 (define-public pplacer
14709 (let ((commit "807f6f3"))
14712 ;; The commit should be updated with each version change.
14713 (version "1.1.alpha19")
14717 (uri (git-reference
14718 (url "https://github.com/matsen/pplacer")
14719 (commit (string-append "v" version))))
14720 (file-name (git-file-name name version))
14722 (base32 "11ppbbbx20p2g9wj3ff64dhnarb12q79v7qh4rk0gj6lkbz4n7cn"))))
14723 (build-system ocaml-build-system)
14725 `(#:modules ((guix build ocaml-build-system)
14729 (modify-phases %standard-phases
14730 (delete 'configure)
14731 (add-after 'unpack 'fix-build-with-latest-ocaml
14733 (substitute* "myocamlbuild.ml"
14734 (("dep \\[\"c_pam\"\\]" m)
14735 (string-append "flag [\"ocaml\"; \"compile\"] (A \"-unsafe-string\");\n"
14737 (("let run_and_read" m)
14742 let pos = String.index s ch in
14743 x := (String.before s pos)::!x;
14744 go (String.after s (pos + 1))
14747 with Not_found -> !x
14748 let split_nl s = split s '\\n'
14749 let before_space s =
14750 try String.before s (String.index s ' ')
14751 with Not_found -> s
14754 (("run_and_read \"ocamlfind list \\| cut -d' ' -f1\"" m)
14755 (string-append "List.map before_space (split_nl & " m ")"))
14756 ((" blank_sep_strings &") "")
14757 ((" Lexing.from_string &") ""))
14759 (add-after 'unpack 'replace-bundled-cddlib
14760 (lambda* (#:key inputs #:allow-other-keys)
14761 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
14762 (local-dir "cddlib_guix"))
14764 (with-directory-excursion local-dir
14765 (invoke "tar" "xvf" cddlib-src))
14766 (let ((cddlib-src-folder
14767 (string-append local-dir "/"
14768 (list-ref (scandir local-dir) 2)
14770 (for-each make-file-writable (find-files "cdd_src" ".*"))
14774 (string-append "cdd_src/" (basename file))))
14775 (find-files cddlib-src-folder ".*[ch]$")))
14777 (add-after 'unpack 'fix-makefile
14779 ;; Remove system calls to 'git'.
14780 (substitute* "Makefile"
14781 (("^DESCRIPT:=pplacer-.*")
14783 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
14784 (substitute* "myocamlbuild.ml"
14785 (("git describe --tags --long .*\\\" with")
14787 "echo -n v" ,version "-" ,commit "\" with")))
14790 (lambda* (#:key outputs #:allow-other-keys)
14791 (let* ((out (assoc-ref outputs "out"))
14792 (bin (string-append out "/bin")))
14793 (copy-recursively "bin" bin))
14795 #:ocaml ,ocaml-4.07
14796 #:findlib ,ocaml4.07-findlib))
14798 `(("zlib" ,zlib "static")
14800 ("ocaml-ounit" ,(package-with-ocaml4.07 ocaml-ounit))
14801 ("ocaml-batteries" ,(package-with-ocaml4.07 ocaml-batteries))
14802 ("ocaml-camlzip" ,(package-with-ocaml4.07 camlzip))
14803 ("ocaml-csv" ,(package-with-ocaml4.07 ocaml-csv))
14804 ("ocaml-sqlite3" ,ocaml4.07-sqlite3)
14805 ("ocaml-xmlm" ,(package-with-ocaml4.07 ocaml-xmlm))
14806 ("ocaml-mcl" ,(package-with-ocaml4.07 ocaml-mcl))
14807 ("ocaml-gsl" ,ocaml4.07-gsl-1)))
14809 `(("cddlib-src" ,(package-source cddlib))
14810 ("ocamlbuild" ,(package-with-ocaml4.07 ocamlbuild))
14811 ("pkg-config" ,pkg-config)))
14813 `(("pplacer-scripts" ,pplacer-scripts)))
14814 (synopsis "Phylogenetic placement of biological sequences")
14816 "Pplacer places query sequences on a fixed reference phylogenetic tree
14817 to maximize phylogenetic likelihood or posterior probability according to a
14818 reference alignment. Pplacer is designed to be fast, to give useful
14819 information about uncertainty, and to offer advanced visualization and
14820 downstream analysis.")
14821 (home-page "https://matsen.fhcrc.org/pplacer/")
14822 (license license:gpl3))))
14824 ;; This package is installed alongside 'pplacer'. It is a separate package so
14825 ;; that it can use the python-build-system for the scripts that are
14826 ;; distributed alongside the main OCaml binaries.
14827 (define pplacer-scripts
14830 (name "pplacer-scripts")
14831 (build-system python-build-system)
14833 `(#:python ,python-2
14835 (modify-phases %standard-phases
14836 (add-after 'unpack 'enter-scripts-dir
14837 (lambda _ (chdir "scripts") #t))
14839 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t))
14840 (add-after 'install 'wrap-executables
14841 (lambda* (#:key inputs outputs #:allow-other-keys)
14842 (let* ((out (assoc-ref outputs "out"))
14843 (bin (string-append out "/bin")))
14844 (let ((path (string-append
14845 (assoc-ref inputs "hmmer") "/bin:"
14846 (assoc-ref inputs "infernal") "/bin")))
14848 (wrap-program (string-append bin "/refpkg_align.py")
14849 `("PATH" ":" prefix (,path))))
14850 (let ((path (string-append
14851 (assoc-ref inputs "hmmer") "/bin")))
14852 (wrap-program (string-append bin "/hrefpkg_query.py")
14853 `("PATH" ":" prefix (,path)))))
14856 `(("infernal" ,infernal)
14859 `(("python-biopython" ,python2-biopython)
14860 ("taxtastic" ,taxtastic)))
14861 (synopsis "Pplacer Python scripts")))
14863 (define-public python2-checkm-genome
14865 (name "python2-checkm-genome")
14870 (uri (pypi-uri "checkm-genome" version))
14873 "0bm8gpxjmzxsxxl8lzwqhgx8g1dlnmp6znz7wv3hgb0gdjbf9dzz"))))
14874 (build-system python-build-system)
14876 `(#:python ,python-2
14877 #:tests? #f)) ; some tests are interactive
14879 `(("python-dendropy" ,python2-dendropy)
14880 ("python-matplotlib" ,python2-matplotlib)
14881 ("python-numpy" ,python2-numpy)
14882 ("python-pysam" ,python2-pysam)
14883 ("python-scipy" ,python2-scipy)))
14884 (home-page "https://pypi.org/project/Checkm/")
14885 (synopsis "Assess the quality of putative genome bins")
14887 "CheckM provides a set of tools for assessing the quality of genomes
14888 recovered from isolates, single cells, or metagenomes. It provides robust
14889 estimates of genome completeness and contamination by using collocated sets of
14890 genes that are ubiquitous and single-copy within a phylogenetic lineage.
14891 Assessment of genome quality can also be examined using plots depicting key
14892 genomic characteristics (e.g., GC, coding density) which highlight sequences
14893 outside the expected distributions of a typical genome. CheckM also provides
14894 tools for identifying genome bins that are likely candidates for merging based
14895 on marker set compatibility, similarity in genomic characteristics, and
14896 proximity within a reference genome.")
14897 (license license:gpl3+)))
14899 (define-public umi-tools
14906 (uri (pypi-uri "umi_tools" version))
14909 "08y3vz1vcx09whmbsn722lcs6jl9wyrh9i4p3k8j4cb1i32bij4a"))))
14910 (build-system python-build-system)
14912 `(("python-pandas" ,python-pandas)
14913 ("python-future" ,python-future)
14914 ("python-scipy" ,python-scipy)
14915 ("python-matplotlib" ,python-matplotlib)
14916 ("python-regex" ,python-regex)
14917 ("python-pysam" ,python-pysam)))
14919 `(("python-cython" ,python-cython)))
14920 (home-page "https://github.com/CGATOxford/UMI-tools")
14921 (synopsis "Tools for analyzing unique modular identifiers")
14922 (description "This package provides tools for dealing with @dfn{Unique
14923 Molecular Identifiers} (UMIs) and @dfn{Random Molecular Tags} (RMTs) in
14924 genetic sequences. There are six tools: the @code{extract} and
14925 @code{whitelist} commands are used to prepare a fastq containing UMIs @code{+/-}
14926 cell barcodes for alignment. The remaining commands, @code{group},
14927 @code{dedup}, and @{count}/@code{count_tab}, are used to identify PCR
14928 duplicates using the UMIs and perform different levels of analysis depending
14929 on the needs of the user.")
14930 (license license:expat)))
14932 (define-public ataqv
14939 (uri (git-reference
14940 (url "https://github.com/ParkerLab/ataqv")
14942 (file-name (git-file-name name version))
14945 "031xr6jx1aprh26y5b1lv3gzrlmzg4alfl73vvshymx8cq8asrqi"))))
14946 (build-system gnu-build-system)
14949 (list (string-append "prefix=" (assoc-ref %outputs "out"))
14950 (string-append "BOOST_ROOT="
14951 (assoc-ref %build-inputs "boost"))
14952 (string-append "HTSLIB_ROOT="
14953 (assoc-ref %build-inputs "htslib")))
14954 #:test-target "test"
14956 (modify-phases %standard-phases
14957 (delete 'configure))))
14961 ("ncurses" ,ncurses)
14965 (home-page "https://github.com/ParkerLab/ataqv")
14966 (synopsis "Toolkit for quality control and visualization of ATAC-seq data")
14967 (description "This package provides a toolkit for measuring and comparing
14968 ATAC-seq results. It was written to make it easier to spot differences that
14969 might be caused by ATAC-seq library prep or sequencing. The main program,
14970 @code{ataqv}, examines aligned reads and reports some basic metrics.")
14971 (license license:gpl3+)))
14973 (define-public r-psiplot
14980 (uri (git-reference
14981 (url "https://github.com/kcha/psiplot")
14982 (commit (string-append "v" version))))
14983 (file-name (git-file-name name version))
14985 (base32 "08438h16cfry5kqh3y9hs8q1b1a8bxhblsm75knviz5r6q0n1jxh"))))
14986 (build-system r-build-system)
14988 `(("r-mass" ,r-mass)
14989 ("r-dplyr" ,r-dplyr)
14990 ("r-tidyr" ,r-tidyr)
14991 ("r-purrr" ,r-purrr)
14992 ("r-readr" ,r-readr)
14993 ("r-magrittr" ,r-magrittr)
14994 ("r-ggplot2" ,r-ggplot2)))
14995 (home-page "https://github.com/kcha/psiplot")
14996 (synopsis "Plot percent spliced-in values of alternatively-spliced exons")
14998 "PSIplot is an R package for generating plots of @dfn{percent
14999 spliced-in} (PSI) values of alternatively-spliced exons that were computed by
15000 vast-tools, an RNA-Seq pipeline for alternative splicing analysis. The plots
15001 are generated using @code{ggplot2}.")
15002 (license license:expat)))
15004 (define-public python-ont-fast5-api
15006 (name "python-ont-fast5-api")
15011 (uri (git-reference
15012 (url "https://github.com/nanoporetech/ont_fast5_api")
15013 (commit (string-append "release_" version))))
15014 (file-name (git-file-name name version))
15017 "03cbq4zbbwhll8ml2m9k8sa31mirsvcbjkrq1yna0kkzz9fad5fm"))))
15018 (build-system python-build-system)
15020 `(("python-numpy" ,python-numpy)
15021 ("python-six" ,python-six)
15022 ("python-h5py" ,python-h5py)
15023 ("python-progressbar33" ,python-progressbar33)))
15024 (home-page "https://github.com/nanoporetech/ont_fast5_api")
15025 (synopsis "Interface to HDF5 files of the Oxford Nanopore fast5 file format")
15027 "This package provides a concrete implementation of the fast5 file schema
15028 using the generic @code{h5py} library, plain-named methods to interact with
15029 and reflect the fast5 file schema, and tools to convert between
15030 @code{multi_read} and @code{single_read} formats.")
15031 (license license:mpl2.0)))
15033 (define-public tbsp
15034 (let ((commit "ec8fff4410cfb13a677dbbb95cbbc60217e64907")
15038 (version (git-version "1.0.0" revision commit))
15042 (uri (git-reference
15043 (url "https://github.com/phoenixding/tbsp")
15045 (file-name (git-file-name name version))
15048 "025ym14x8gbd6hb55lsinqj6f5qzw36i10klgs7ldzxxd7s39ki1"))))
15049 (build-system python-build-system)
15050 (arguments '(#:tests? #f)) ; no tests included
15052 `(("python-matplotlib" ,python-matplotlib)
15053 ("python-networkx" ,python-networkx)
15054 ("python-numpy" ,python-numpy)
15055 ("python-pybigwig" ,python-pybigwig)
15056 ("python-biopython" ,python-biopython)
15057 ("python-scikit-learn" ,python-scikit-learn)
15058 ("python-scipy" ,python-scipy)))
15059 (home-page "https://github.com/phoenixding/tbsp/")
15060 (synopsis "SNP-based trajectory inference")
15062 "Several studies focus on the inference of developmental and response
15063 trajectories from single cell RNA-Seq (scRNA-Seq) data. A number of
15064 computational methods, often referred to as pseudo-time ordering, have been
15065 developed for this task. CRISPR has also been used to reconstruct lineage
15066 trees by inserting random mutations. The tbsp package implements an
15067 alternative method to detect significant, cell type specific sequence
15068 mutations from scRNA-Seq data.")
15069 (license license:expat))))
15071 (define-public tabixpp
15077 (uri (git-reference
15078 (url "https://github.com/ekg/tabixpp")
15079 (commit (string-append "v" version))))
15080 (file-name (git-file-name name version))
15082 (base32 "1k2a3vbq96ic4lw72iwp5s3mwwc4xhdffjj584yn6l9637q9j1yd"))
15083 (modules '((guix build utils)))
15086 (delete-file-recursively "htslib") #t))))
15087 (build-system gnu-build-system)
15089 `(("htslib" ,htslib)
15092 `(#:tests? #f ; There are no tests to run.
15094 (modify-phases %standard-phases
15095 (delete 'configure) ; There is no configure phase.
15096 ;; The build phase needs overriding the location of htslib.
15098 (lambda* (#:key inputs #:allow-other-keys)
15099 (let ((htslib-ref (assoc-ref inputs "htslib")))
15101 (string-append "HTS_LIB=" htslib-ref "/lib/libhts.a")
15102 (string-append "INCLUDES= -I" htslib-ref "/include/htslib")
15103 "HTS_HEADERS=" ; No need to check for headers here.
15104 (string-append "LIBPATH=-L. -L" htslib-ref "/include"))
15105 (invoke "g++" "-shared" "-o" "libtabixpp.so" "tabix.o" "-lhts")
15106 (invoke "ar" "rcs" "libtabixpp.a" "tabix.o"))))
15108 (lambda* (#:key outputs #:allow-other-keys)
15109 (let* ((out (assoc-ref outputs "out"))
15110 (lib (string-append out "/lib"))
15111 (bin (string-append out "/bin")))
15112 (install-file "tabix++" bin)
15113 (install-file "libtabixpp.so" lib)
15114 (install-file "libtabixpp.a" lib)
15115 (install-file "tabix.hpp" (string-append out "/include"))
15116 (mkdir-p (string-append lib "/pkgconfig"))
15117 (with-output-to-file (string-append lib "/pkgconfig/tabixpp.pc")
15119 (format #t "prefix=~a~@
15120 exec_prefix=${prefix}~@
15121 libdir=${exec_prefix}/lib~@
15122 includedir=${prefix}/include~@
15127 Description: C++ wrapper around tabix project~@
15128 Libs: -L${libdir} -ltabixpp~@
15129 Cflags: -I${includedir}~%"
15132 (home-page "https://github.com/ekg/tabixpp")
15133 (synopsis "C++ wrapper around tabix project")
15134 (description "This is a C++ wrapper around the Tabix project which abstracts
15135 some of the details of opening and jumping in tabix-indexed files.")
15136 (license license:expat)))
15138 (define-public smithwaterman
15139 (let ((commit "2610e259611ae4cde8f03c72499d28f03f6d38a7"))
15141 (name "smithwaterman")
15142 (version (git-version "0.0.0" "2" commit))
15145 (uri (git-reference
15146 (url "https://github.com/ekg/smithwaterman/")
15148 (file-name (git-file-name name version))
15150 (base32 "0i9d8zrxpiracw3mxzd9siybpy62p06rqz9mc2w93arajgbk45bs"))))
15151 (build-system gnu-build-system)
15153 `(#:tests? #f ; There are no tests to run.
15154 #:make-flags '("libsw.a" "all")
15156 (modify-phases %standard-phases
15157 (delete 'configure) ; There is no configure phase.
15158 (add-after 'unpack 'patch-source
15160 (substitute* "Makefile"
15161 (("-c ") "-c -fPIC "))
15163 (add-after 'build 'build-dynamic
15166 "-shared" "-o" "libsmithwaterman.so"
15167 "smithwaterman.o" "SmithWatermanGotoh.o"
15168 "disorder.o" "BandedSmithWaterman.o"
15169 "LeftAlign.o" "Repeats.o" "IndelAllele.o")))
15171 (lambda* (#:key outputs #:allow-other-keys)
15172 (let* ((out (assoc-ref outputs "out"))
15173 (bin (string-append out "/bin"))
15174 (lib (string-append out "/lib")))
15175 (install-file "smithwaterman" bin)
15178 (install-file file (string-append out "/include/smithwaterman")))
15179 (find-files "." "\\.h$"))
15180 (install-file "libsmithwaterman.so" lib)
15181 (install-file "libsw.a" lib)
15182 (mkdir-p (string-append lib "/pkgconfig"))
15183 (with-output-to-file (string-append lib "/pkgconfig/smithwaterman.pc")
15185 (format #t "prefix=~a~@
15186 exec_prefix=${prefix}~@
15187 libdir=${exec_prefix}/lib~@
15188 includedir=${prefix}/include/smithwaterman~@
15191 Name: smithwaterman~@
15193 Description: smith-waterman-gotoh alignment algorithm~@
15194 Libs: -L${libdir} -lsmithwaterman~@
15195 Cflags: -I${includedir}~%"
15198 (home-page "https://github.com/ekg/smithwaterman")
15199 (synopsis "Implementation of the Smith-Waterman algorithm")
15200 (description "Implementation of the Smith-Waterman algorithm.")
15201 ;; The licensing terms are unclear: https://github.com/ekg/smithwaterman/issues/9.
15202 (license (list license:gpl2 license:expat)))))
15204 (define-public multichoose
15206 (name "multichoose")
15210 (uri (git-reference
15211 (url "https://github.com/ekg/multichoose/")
15212 (commit (string-append "v" version))))
15213 (file-name (git-file-name name version))
15215 (base32 "0ci5fqvmpamwgxvmyd79ygj6n3bnbl3vc7b6h1sxz58186sm3pfs"))))
15216 (build-system gnu-build-system)
15218 `(#:tests? #f ; Tests require node.
15220 (modify-phases %standard-phases
15221 (delete 'configure) ; There is no configure phase.
15223 (lambda* (#:key outputs #:allow-other-keys)
15224 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15225 ;; TODO: There are Python modules for these programs too.
15226 (install-file "multichoose" bin)
15227 (install-file "multipermute" bin))
15229 (home-page "https://github.com/ekg/multichoose")
15230 (synopsis "Efficient loopless multiset combination generation algorithm")
15231 (description "This library implements an efficient loopless multiset
15232 combination generation algorithm which is (approximately) described in
15233 \"Loopless algorithms for generating permutations, combinations, and other
15234 combinatorial configurations.\", G. Ehrlich - Journal of the ACM (JACM),
15235 1973. (Algorithm 7.)")
15236 (license license:expat)))
15238 (define-public fsom
15239 (let ((commit "a6ef318fbd347c53189384aef7f670c0e6ce89a3"))
15242 (version (git-version "0.0.0" "1" commit))
15245 (uri (git-reference
15246 (url "https://github.com/ekg/fsom/")
15248 (file-name (git-file-name name version))
15250 (base32 "0gw1lpvr812pywg9y546x0h1hhj261xwls41r6kqhddjlrcjc0pi"))))
15251 (build-system gnu-build-system)
15253 `(#:tests? #f ; There are no tests to run.
15255 (modify-phases %standard-phases
15256 (delete 'configure) ; There is no configure phase.
15258 (lambda* (#:key outputs #:allow-other-keys)
15259 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15260 (install-file "fsom" bin))
15262 (home-page "https://github.com/ekg/fsom")
15263 (synopsis "Manage SOM (Self-Organizing Maps) neural networks")
15264 (description "A tiny C library for managing SOM (Self-Organizing Maps)
15266 (license license:gpl3))))
15268 (define-public fastahack
15274 (uri (git-reference
15275 (url "https://github.com/ekg/fastahack/")
15276 (commit (string-append "v" version))))
15277 (file-name (git-file-name name version))
15279 (base32 "0rp1blskhzxf7vbh253ibpxbgl9wwgyzf1wbkxndi08d3j4vcss9"))))
15280 (build-system gnu-build-system)
15282 `(#:tests? #f ; Unclear how to run tests: https://github.com/ekg/fastahack/issues/15
15284 (modify-phases %standard-phases
15285 (delete 'configure) ; There is no configure phase.
15286 (add-after 'unpack 'patch-source
15288 (substitute* "Makefile"
15289 (("-c ") "-c -fPIC "))
15291 (add-after 'build 'build-dynamic
15294 "-shared" "-o" "libfastahack.so"
15295 "Fasta.o" "FastaHack.o" "split.o" "disorder.o")))
15297 (lambda* (#:key outputs #:allow-other-keys)
15298 (let* ((out (assoc-ref outputs "out"))
15299 (lib (string-append out "/lib"))
15300 (bin (string-append out "/bin")))
15301 (mkdir-p (string-append out "/include/fastahack"))
15304 (install-file file (string-append out "/include/fastahack")))
15305 (find-files "." "\\.h$"))
15306 (install-file "fastahack" bin)
15307 (install-file "libfastahack.so" lib)
15308 (mkdir-p (string-append lib "/pkgconfig"))
15309 (with-output-to-file (string-append lib "/pkgconfig/fastahack.pc")
15311 (format #t "prefix=~a~@
15312 exec_prefix=${prefix}~@
15313 libdir=${exec_prefix}/lib~@
15314 includedir=${prefix}/include/fastahack~@
15319 Description: Indexing and sequence extraction from FASTA files~@
15320 Libs: -L${libdir} -lfastahack~@
15321 Cflags: -I${includedir}~%"
15324 (home-page "https://github.com/ekg/fastahack")
15325 (synopsis "Indexing and sequence extraction from FASTA files")
15326 (description "Fastahack is a small application for indexing and
15327 extracting sequences and subsequences from FASTA files. The included library
15328 provides a FASTA reader and indexer that can be embedded into applications
15329 which would benefit from directly reading subsequences from FASTA files. The
15330 library automatically handles index file generation and use.")
15331 (license (list license:expat license:gpl2))))
15333 (define-public vcflib
15340 (uri (string-append "https://github.com/vcflib/vcflib/releases/"
15341 "download/v" version
15342 "/vcflib-" version "-src.tar.gz"))
15344 (base32 "14zzrg8hg8cq9cvq2wdvp21j7nmxxkjrbagw2apd2yqv2kyx42lm"))
15345 (patches (search-patches "vcflib-use-shared-libraries.patch"))
15346 (modules '((guix build utils)))
15349 (substitute* (find-files "." "\\.(h|c)(pp)?$")
15350 (("\"SmithWatermanGotoh.h\"") "<smithwaterman/SmithWatermanGotoh.h>")
15351 (("\"convert.h\"") "<smithwaterman/convert.h>")
15352 (("\"disorder.h\"") "<smithwaterman/disorder.h>")
15353 (("\"tabix.hpp\"") "<tabix.hpp>")
15354 (("\"Fasta.h\"") "<fastahack/Fasta.h>"))
15355 (for-each delete-file-recursively
15356 '("fastahack" "filevercmp" "fsom" "googletest" "intervaltree"
15357 "libVCFH" "multichoose" "smithwaterman" "tabixpp"))
15359 (build-system gnu-build-system)
15361 `(("htslib" ,htslib)
15362 ("fastahack" ,fastahack)
15365 ("smithwaterman" ,smithwaterman)
15366 ("tabixpp" ,tabixpp)
15370 `(("pkg-config" ,pkg-config)
15372 ;; This package builds against the .o files so we need to extract the source.
15373 ("filevercmp-src" ,(package-source filevercmp))
15374 ("intervaltree-src" ,(package-source intervaltree))
15375 ("multichoose-src" ,(package-source multichoose))))
15377 `(#:tests? #f ; no tests
15379 (modify-phases %standard-phases
15380 (add-after 'unpack 'set-flags
15381 (lambda* (#:key outputs #:allow-other-keys)
15382 (substitute* "Makefile"
15384 (string-append "LDFLAGS = -Wl,-rpath="
15385 (assoc-ref outputs "out") "/lib ")))
15386 (substitute* "filevercmp/Makefile"
15387 (("-c") "-c -fPIC"))
15389 (delete 'configure)
15390 (add-after 'unpack 'unpack-submodule-sources
15391 (lambda* (#:key inputs #:allow-other-keys)
15392 (let ((unpack (lambda (source target)
15394 (with-directory-excursion target
15395 (if (file-is-directory? (assoc-ref inputs source))
15396 (copy-recursively (assoc-ref inputs source) ".")
15397 (invoke "tar" "xvf"
15398 (assoc-ref inputs source)
15399 "--strip-components=1"))))))
15401 (unpack "filevercmp-src" "filevercmp")
15402 (unpack "intervaltree-src" "intervaltree")
15403 (unpack "multichoose-src" "multichoose")))))
15405 (lambda* (#:key outputs #:allow-other-keys)
15406 (let* ((out (assoc-ref outputs "out"))
15407 (bin (string-append out "/bin"))
15408 (lib (string-append out "/lib")))
15409 (for-each (lambda (file)
15410 (install-file file bin))
15411 (find-files "bin" ".*"))
15412 (install-file "libvcflib.so" lib)
15413 (install-file "libvcflib.a" lib)
15416 (install-file file (string-append out "/include")))
15417 (find-files "include" "\\.h(pp)?$"))
15418 (mkdir-p (string-append lib "/pkgconfig"))
15419 (with-output-to-file (string-append lib "/pkgconfig/vcflib.pc")
15421 (format #t "prefix=~a~@
15422 exec_prefix=${prefix}~@
15423 libdir=${exec_prefix}/lib~@
15424 includedir=${prefix}/include~@
15429 Requires: smithwaterman, fastahack~@
15430 Description: C++ library for parsing and manipulating VCF files~@
15431 Libs: -L${libdir} -lvcflib~@
15432 Cflags: -I${includedir}~%"
15435 (home-page "https://github.com/vcflib/vcflib/")
15436 (synopsis "Library for parsing and manipulating VCF files")
15437 (description "Vcflib provides methods to manipulate and interpret
15438 sequence variation as it can be described by VCF. It is both an API for parsing
15439 and operating on records of genomic variation as it can be described by the VCF
15440 format, and a collection of command-line utilities for executing complex
15441 manipulations on VCF files.")
15442 (license license:expat)))
15444 (define-public freebayes
15445 (let ((commit "3ce827d8ebf89bb3bdc097ee0fe7f46f9f30d5fb")
15450 (version (git-version version revision commit))
15453 (uri (git-reference
15454 (url "https://github.com/ekg/freebayes")
15456 (file-name (git-file-name name version))
15458 (base32 "1sbzwmcbn78ybymjnhwk7qc5r912azy5vqz2y7y81616yc3ba2a2"))))
15459 (build-system gnu-build-system)
15461 `(("bamtools" ,bamtools)
15465 `(("bc" ,bc) ; Needed for running tests.
15466 ("samtools" ,samtools) ; Needed for running tests.
15467 ("parallel" ,parallel) ; Needed for running tests.
15468 ("perl" ,perl) ; Needed for running tests.
15469 ("procps" ,procps) ; Needed for running tests.
15470 ("python" ,python-2) ; Needed for running tests.
15471 ("vcflib-src" ,(package-source vcflib))
15472 ;; These are submodules for the vcflib version used in freebayes.
15473 ;; This package builds against the .o files so we need to extract the source.
15474 ("tabixpp-src" ,(package-source tabixpp))
15475 ("smithwaterman-src" ,(package-source smithwaterman))
15476 ("multichoose-src" ,(package-source multichoose))
15477 ("fsom-src" ,(package-source fsom))
15478 ("filevercmp-src" ,(package-source filevercmp))
15479 ("fastahack-src" ,(package-source fastahack))
15480 ("intervaltree-src" ,(package-source intervaltree))
15481 ;; These submodules are needed to run the tests.
15482 ("bash-tap-src" ,(package-source bash-tap))
15483 ("test-simple-bash-src"
15486 (uri (git-reference
15487 (url "https://github.com/ingydotnet/test-simple-bash/")
15488 (commit "124673ff204b01c8e96b7fc9f9b32ee35d898acc")))
15489 (file-name "test-simple-bash-src-checkout")
15491 (base32 "043plp6z0x9yf7mdpky1fw7zcpwn1p47px95w9mh16603zqqqpga"))))))
15495 (string-append "BAMTOOLS_ROOT="
15496 (assoc-ref %build-inputs "bamtools")))
15497 #:test-target "test"
15499 (modify-phases %standard-phases
15500 (delete 'configure)
15501 (add-after 'unpack 'fix-tests
15503 (substitute* "test/t/01_call_variants.t"
15504 (("grep -P \"\\(\\\\t500\\$\\|\\\\t11000\\$\\|\\\\t1000\\$\\)\"")
15505 "grep -E ' (500|11000|1000)$'"))
15507 (add-after 'unpack 'unpack-submodule-sources
15508 (lambda* (#:key inputs #:allow-other-keys)
15509 (let ((unpack (lambda (source target)
15510 (with-directory-excursion target
15511 (if (file-is-directory? (assoc-ref inputs source))
15512 (copy-recursively (assoc-ref inputs source) ".")
15513 (invoke "tar" "xvf"
15514 (assoc-ref inputs source)
15515 "--strip-components=1"))))))
15517 (unpack "vcflib-src" "vcflib")
15518 (unpack "fastahack-src" "vcflib/fastahack")
15519 (unpack "filevercmp-src" "vcflib/filevercmp")
15520 (unpack "fsom-src" "vcflib/fsom")
15521 (unpack "intervaltree-src" "vcflib/intervaltree")
15522 (unpack "multichoose-src" "vcflib/multichoose")
15523 (unpack "smithwaterman-src" "vcflib/smithwaterman")
15524 (unpack "tabixpp-src" "vcflib/tabixpp")
15525 (unpack "test-simple-bash-src" "test/test-simple-bash")
15526 (unpack "bash-tap-src" "test/bash-tap")))))
15527 (add-after 'unpack-submodule-sources 'fix-makefiles
15529 ;; We don't have the .git folder to get the version tag from.
15530 (substitute* "vcflib/Makefile"
15531 (("^GIT_VERSION.*")
15532 (string-append "GIT_VERSION = v" ,version)))
15533 (substitute* "src/Makefile"
15534 (("-I\\$\\(BAMTOOLS_ROOT\\)/src")
15535 "-I$(BAMTOOLS_ROOT)/include/bamtools"))
15537 (add-before 'build 'build-tabixpp-and-vcflib
15538 (lambda* (#:key inputs make-flags #:allow-other-keys)
15539 (with-directory-excursion "vcflib"
15540 (with-directory-excursion "tabixpp"
15541 (apply invoke "make"
15542 (string-append "HTS_LIB="
15543 (assoc-ref inputs "htslib")
15546 (apply invoke "make"
15547 (string-append "CFLAGS=-Itabixpp")
15551 (lambda* (#:key outputs #:allow-other-keys)
15552 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15553 (install-file "bin/freebayes" bin)
15554 (install-file "bin/bamleftalign" bin))
15556 (home-page "https://github.com/ekg/freebayes")
15557 (synopsis "Haplotype-based variant detector")
15558 (description "FreeBayes is a Bayesian genetic variant detector designed to
15559 find small polymorphisms, specifically SNPs (single-nucleotide polymorphisms),
15560 indels (insertions and deletions), MNPs (multi-nucleotide polymorphisms), and
15561 complex events (composite insertion and substitution events) smaller than the
15562 length of a short-read sequencing alignment.")
15563 (license license:expat))))
15565 (define-public samblaster
15567 (name "samblaster")
15571 (uri (git-reference
15572 (url "https://github.com/GregoryFaust/samblaster")
15573 (commit (string-append "v." version))))
15574 (file-name (git-file-name name version))
15577 "0iv2ddfw8363vb2x8gr3p8g88whb6mb9m0pf71i2cqsbv6jghap7"))))
15578 (build-system gnu-build-system)
15580 `(#:tests? #f ; there are none
15582 (modify-phases %standard-phases
15583 (delete 'configure) ; There is no configure phase.
15585 (lambda* (#:key outputs #:allow-other-keys)
15586 (install-file "samblaster"
15587 (string-append (assoc-ref outputs "out") "/bin"))
15589 (home-page "https://github.com/GregoryFaust/samblaster")
15590 (synopsis "Mark duplicates in paired-end SAM files")
15591 (description "Samblaster is a fast and flexible program for marking
15592 duplicates in read-id grouped paired-end SAM files. It can also optionally
15593 output discordant read pairs and/or split read mappings to separate SAM files,
15594 and/or unmapped/clipped reads to a separate FASTQ file. When marking
15595 duplicates, samblaster will require approximately 20MB of memory per 1M read
15597 (license license:expat)))
15599 (define-public r-velocyto
15600 (let ((commit "d7790346cb99f49ab9c2b23ba70dcf9d2c9fc350")
15603 (name "r-velocyto")
15604 (version (git-version "0.6" revision commit))
15608 (uri (git-reference
15609 (url "https://github.com/velocyto-team/velocyto.R")
15611 (file-name (git-file-name name version))
15614 "16wqf70j7rd7pay2q513iyz12i8n9vrpg1bisah4lddbcpx5dz1n"))))
15615 (build-system r-build-system)
15617 `(("boost" ,boost)))
15619 `(("r-hdf5r" ,r-hdf5r)
15622 ("r-pcamethods" ,r-pcamethods)
15624 ("r-rcpparmadillo" ,r-rcpparmadillo)
15625 ;; Suggested packages
15626 ("r-rtsne" ,r-rtsne)
15627 ("r-cluster" ,r-cluster)
15628 ("r-abind" ,r-abind)
15630 ("r-biocgenerics" ,r-biocgenerics)
15631 ("r-genomicalignments" ,r-genomicalignments)
15632 ("r-rsamtools" ,r-rsamtools)
15633 ("r-edger" ,r-edger)
15634 ("r-igraph" ,r-igraph)))
15635 (home-page "https://velocyto.org")
15636 (synopsis "RNA velocity estimation in R")
15638 "This package provides basic routines for estimation of gene-specific
15639 transcriptional derivatives and visualization of the resulting velocity
15641 (license license:gpl3))))
15643 (define-public methyldackel
15645 (name "methyldackel")
15649 (uri (git-reference
15650 (url "https://github.com/dpryan79/MethylDackel")
15652 (file-name (git-file-name name version))
15655 "1sfhf2ap75qxpnmy1ifgmxqs18rq8mah9mcgkby73vc6h0sw99ws"))))
15656 (build-system gnu-build-system)
15658 `(#:test-target "test"
15661 (string-append "prefix="
15662 (assoc-ref %outputs "out") "/bin/"))
15664 (modify-phases %standard-phases
15665 (replace 'configure
15666 (lambda* (#:key outputs #:allow-other-keys)
15667 (substitute* "Makefile"
15668 (("-lhts ") "-lhts -lBigWig ")
15669 (("install MethylDackel \\$\\(prefix\\)" match)
15670 (string-append "install -d $(prefix); " match)))
15673 `(("curl" ,curl) ; XXX: needed by libbigwig
15674 ("htslib" ,htslib-1.9)
15675 ("libbigwig" ,libbigwig)
15677 ;; Needed for tests
15679 `(("python" ,python-wrapper)))
15680 (home-page "https://github.com/dpryan79/MethylDackel")
15681 (synopsis "Universal methylation extractor for BS-seq experiments")
15683 "MethylDackel will process a coordinate-sorted and indexed BAM or CRAM
15684 file containing some form of BS-seq alignments and extract per-base
15685 methylation metrics from them. MethylDackel requires an indexed fasta file
15686 containing the reference genome as well.")
15687 ;; See https://github.com/dpryan79/MethylDackel/issues/85
15688 (license license:expat)))
15690 ;; This package bundles PCRE 8.02 and cannot be built with the current
15692 (define-public phast
15698 (uri (git-reference
15699 (url "https://github.com/CshlSiepelLab/phast")
15700 (commit (string-append "v" version))))
15701 (file-name (git-file-name name version))
15704 "10lpbllvny923jjbbyrpxahhd1m5h7sbj9gx7rd123rg10mlidki"))))
15705 (build-system gnu-build-system)
15709 (string-append "DESTDIR=" (assoc-ref %outputs "out")))
15711 (modify-phases %standard-phases
15712 (replace 'configure
15713 (lambda* (#:key inputs outputs #:allow-other-keys)
15715 (substitute* "test/Makefile"
15717 (substitute* "Makefile"
15718 (("CLAPACKPATH=/usr/lib")
15719 (string-append "CLAPACKPATH="
15720 (assoc-ref inputs "clapack") "/lib")))
15721 ;; Renaming the libraries is not necessary with our version of
15723 (substitute* "src/lib/Makefile"
15724 (("ifdef CLAPACKPATH") "ifdef UNNECESSARY"))
15725 (substitute* "src/make-include.mk"
15726 (("-lblaswr") "-lblas")
15727 (("-ltmg") "-ltmglib")
15728 (("liblapack.a") "liblapack.so")
15729 (("libblas.a") "libblas.so")
15730 (("libf2c.a") "libf2c.so"))
15731 (substitute* "src/Makefile"
15732 (("/opt") "/share")
15738 (string-append (getcwd) "/bin:" (getenv "PATH")))
15739 ;; Disable broken test
15740 (substitute* "test/Makefile"
15741 ((".*if.*hmrc_summary" m) (string-append "#" m)))
15742 ;; Only run the msa_view tests because the others fail for
15743 ;; unknown reasons.
15744 (invoke "make" "-C" "test" "msa_view"))))))
15746 `(("clapack" ,clapack)))
15749 (home-page "http://compgen.cshl.edu/phast/")
15750 (synopsis "Phylogenetic analysis with space/time models")
15752 "Phylogenetic Analysis with Space/Time models (PHAST) is a collection of
15753 command-line programs and supporting libraries for comparative and
15754 evolutionary genomics. Best known as the search engine behind the
15755 Conservation tracks in the University of California, Santa Cruz (UCSC) Genome
15756 Browser, PHAST also includes several tools for phylogenetic modeling,
15757 functional element identification, as well as utilities for manipulating
15758 alignments, trees and genomic annotations.")
15759 (license license:bsd-3)))
15761 (define-public python-gffutils
15762 ;; The latest release is older more than a year than the latest commit
15763 (let ((commit "4034c54600813b1402945e12faa91b3a53162cf1")
15766 (name "python-gffutils")
15767 (version (git-version "0.9" revision commit))
15771 (uri (git-reference
15772 (url "https://github.com/daler/gffutils")
15774 (file-name (git-file-name name version))
15777 "1rwafjdnbir5wnk0ap06ww4lra3p5frhy7mfs03rlldgfnwxymsn"))))
15778 (build-system python-build-system)
15781 (modify-phases %standard-phases
15784 ;; Tests need to access the HOME directory
15785 (setenv "HOME" "/tmp")
15786 (invoke "nosetests" "-a" "!slow")))
15787 (add-after 'unpack 'make-gz-files-writable
15789 (for-each make-file-writable
15790 (find-files "." "\\.gz"))
15793 `(("python-argcomplete" ,python-argcomplete)
15794 ("python-argh" ,python-argh)
15795 ("python-biopython" ,python-biopython)
15796 ("python-pybedtools" ,python-pybedtools)
15797 ("python-pyfaidx" ,python-pyfaidx)
15798 ("python-simplejson" ,python-simplejson)
15799 ("python-six" ,python-six)))
15801 `(("python-nose" , python-nose)))
15802 (home-page "https://github.com/daler/gffutils")
15803 (synopsis "Tool for manipulation of GFF and GTF files")
15805 "python-gffutils is a Python package for working with and manipulating
15806 the GFF and GTF format files typically used for genomic annotations. The
15807 files are loaded into a SQLite database, allowing much more complex
15808 manipulation of hierarchical features (e.g., genes, transcripts, and exons)
15809 than is possible with plain-text methods alone.")
15810 (license license:expat))))
15812 (define-public libsbml
15818 (uri (string-append "mirror://sourceforge/sbml/libsbml/"
15819 version "/stable/libSBML-"
15820 version "-core-src.tar.gz"))
15823 "0slkagrk3nfi2qsksv6b1brj6zhx4bj4bkib2sdycvrcd10ql2lh"))))
15824 (build-system cmake-build-system)
15826 `(#:test-target "test"
15828 (list "-DWITH_CHECK=ON"
15829 (string-append "-DLIBXML_LIBRARY="
15830 (assoc-ref %build-inputs "libxml2")
15832 (string-append "-DLIBXML_INCLUDE_DIR="
15833 (assoc-ref %build-inputs "libxml2")
15834 "/include/libxml2"))))
15836 `(("libxml2" ,libxml2)))
15838 `(("check" ,check-0.14)
15840 (home-page "http://sbml.org/Software/libSBML")
15841 (synopsis "Process SBML files and data streams")
15842 (description "LibSBML is a library to help you read, write, manipulate,
15843 translate, and validate SBML files and data streams. The @dfn{Systems Biology
15844 Markup Language} (SBML) is an interchange format for computer models of
15845 biological processes. SBML is useful for models of metabolism, cell
15846 signaling, and more. It continues to be evolved and expanded by an
15847 international community.")
15848 (license license:lgpl2.1+)))
15850 (define-public grocsvs
15851 ;; The last release is out of date and new features have been added.
15852 (let ((commit "ecd956a65093a0b2c41849050e4512d46fecea5d")
15856 (version (git-version "0.2.6.1" revision commit))
15859 (uri (git-reference
15860 (url "https://github.com/grocsvs/grocsvs")
15862 (file-name (git-file-name name version))
15864 (base32 "14505725gr7qxc17cxxf0k6lzcwmgi64pija4mwf29aw70qn35cc"))
15865 (patches (search-patches "grocsvs-dont-use-admiral.patch"))))
15866 (build-system python-build-system)
15868 `(#:tests? #f ; No test suite.
15869 #:python ,python-2)) ; Only python-2 supported.
15871 `(("python2-h5py" ,python2-h5py)
15872 ("python2-ipython-cluster-helper" ,python2-ipython-cluster-helper)
15873 ("python2-networkx" ,python2-networkx)
15874 ("python2-psutil" ,python2-psutil)
15875 ("python2-pandas" ,python2-pandas)
15876 ("python2-pybedtools" ,python2-pybedtools)
15877 ("python2-pyfaidx" ,python2-pyfaidx)
15878 ("python2-pygraphviz" ,python2-pygraphviz)
15879 ("python2-pysam" ,python2-pysam)
15880 ("python2-scipy" ,python2-scipy)))
15881 (home-page "https://github.com/grocsvs/grocsvs")
15882 (synopsis "Genome-wide reconstruction of complex structural variants")
15884 "@dfn{Genome-wide Reconstruction of Complex Structural Variants}
15885 (GROC-SVs) is a software pipeline for identifying large-scale structural
15886 variants, performing sequence assembly at the breakpoints, and reconstructing
15887 the complex structural variants using the long-fragment information from the
15888 10x Genomics platform.")
15889 (license license:expat))))