1 ;;; GNU Guix --- Functional package management for GNU
2 ;;; Copyright © 2014, 2015, 2016, 2017, 2018, 2019, 2020 Ricardo Wurmus <rekado@elephly.net>
3 ;;; Copyright © 2015, 2016, 2017, 2018 Ben Woodcroft <donttrustben@gmail.com>
4 ;;; Copyright © 2015, 2016 Pjotr Prins <pjotr.guix@thebird.nl>
5 ;;; Copyright © 2015 Andreas Enge <andreas@enge.fr>
6 ;;; Copyright © 2016, 2020 Roel Janssen <roel@gnu.org>
7 ;;; Copyright © 2016, 2017, 2018, 2019, 2020 Efraim Flashner <efraim@flashner.co.il>
8 ;;; Copyright © 2016, 2020 Marius Bakke <mbakke@fastmail.com>
9 ;;; Copyright © 2016, 2018 Raoul Bonnal <ilpuccio.febo@gmail.com>
10 ;;; Copyright © 2017, 2018 Tobias Geerinckx-Rice <me@tobias.gr>
11 ;;; Copyright © 2017 Arun Isaac <arunisaac@systemreboot.net>
12 ;;; Copyright © 2018 Joshua Sierles, Nextjournal <joshua@nextjournal.com>
13 ;;; Copyright © 2018 Gábor Boskovits <boskovits@gmail.com>
14 ;;; Copyright © 2018, 2019 Mădălin Ionel Patrașcu <madalinionel.patrascu@mdc-berlin.de>
15 ;;; Copyright © 2019 Maxim Cournoyer <maxim.cournoyer@gmail.com>
16 ;;; Copyright © 2019 Brian Leung <bkleung89@gmail.com>
17 ;;; Copyright © 2019 Brett Gilio <brettg@gnu.org>
18 ;;; Copyright © 2020 Björn Höfling <bjoern.hoefling@bjoernhoefling.de>
19 ;;; Copyright © 2020 Jakub Kądziołka <kuba@kadziolka.net>
20 ;;; Copyright © 2020 Pierre Langlois <pierre.langlois@gmx.com>
22 ;;; This file is part of GNU Guix.
24 ;;; GNU Guix is free software; you can redistribute it and/or modify it
25 ;;; under the terms of the GNU General Public License as published by
26 ;;; the Free Software Foundation; either version 3 of the License, or (at
27 ;;; your option) any later version.
29 ;;; GNU Guix is distributed in the hope that it will be useful, but
30 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
31 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
32 ;;; GNU General Public License for more details.
34 ;;; You should have received a copy of the GNU General Public License
35 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
37 (define-module (gnu packages bioinformatics)
38 #:use-module ((guix licenses) #:prefix license:)
39 #:use-module (guix packages)
40 #:use-module (guix utils)
41 #:use-module (guix download)
42 #:use-module (guix git-download)
43 #:use-module (guix hg-download)
44 #:use-module (guix build-system ant)
45 #:use-module (guix build-system gnu)
46 #:use-module (guix build-system cmake)
47 #:use-module (guix build-system go)
48 #:use-module (guix build-system haskell)
49 #:use-module (guix build-system meson)
50 #:use-module (guix build-system ocaml)
51 #:use-module (guix build-system perl)
52 #:use-module (guix build-system python)
53 #:use-module (guix build-system r)
54 #:use-module (guix build-system ruby)
55 #:use-module (guix build-system scons)
56 #:use-module (guix build-system trivial)
57 #:use-module (guix deprecation)
58 #:use-module (gnu packages)
59 #:use-module (gnu packages autotools)
60 #:use-module (gnu packages algebra)
61 #:use-module (gnu packages base)
62 #:use-module (gnu packages bash)
63 #:use-module (gnu packages bison)
64 #:use-module (gnu packages bioconductor)
65 #:use-module (gnu packages boost)
66 #:use-module (gnu packages check)
67 #:use-module (gnu packages code)
68 #:use-module (gnu packages compression)
69 #:use-module (gnu packages cpio)
70 #:use-module (gnu packages cran)
71 #:use-module (gnu packages curl)
72 #:use-module (gnu packages documentation)
73 #:use-module (gnu packages databases)
74 #:use-module (gnu packages datastructures)
75 #:use-module (gnu packages dlang)
76 #:use-module (gnu packages file)
77 #:use-module (gnu packages flex)
78 #:use-module (gnu packages gawk)
79 #:use-module (gnu packages gcc)
80 #:use-module (gnu packages gd)
81 #:use-module (gnu packages golang)
82 #:use-module (gnu packages glib)
83 #:use-module (gnu packages graph)
84 #:use-module (gnu packages graphviz)
85 #:use-module (gnu packages groff)
86 #:use-module (gnu packages gtk)
87 #:use-module (gnu packages guile)
88 #:use-module (gnu packages guile-xyz)
89 #:use-module (gnu packages haskell-check)
90 #:use-module (gnu packages haskell-web)
91 #:use-module (gnu packages haskell-xyz)
92 #:use-module (gnu packages image)
93 #:use-module (gnu packages imagemagick)
94 #:use-module (gnu packages java)
95 #:use-module (gnu packages java-compression)
96 #:use-module (gnu packages jemalloc)
97 #:use-module (gnu packages linux)
98 #:use-module (gnu packages lisp-xyz)
99 #:use-module (gnu packages logging)
100 #:use-module (gnu packages machine-learning)
101 #:use-module (gnu packages man)
102 #:use-module (gnu packages maths)
103 #:use-module (gnu packages mpi)
104 #:use-module (gnu packages ncurses)
105 #:use-module (gnu packages ocaml)
106 #:use-module (gnu packages pcre)
107 #:use-module (gnu packages parallel)
108 #:use-module (gnu packages pdf)
109 #:use-module (gnu packages perl)
110 #:use-module (gnu packages perl-check)
111 #:use-module (gnu packages pkg-config)
112 #:use-module (gnu packages popt)
113 #:use-module (gnu packages protobuf)
114 #:use-module (gnu packages python)
115 #:use-module (gnu packages python-compression)
116 #:use-module (gnu packages python-science)
117 #:use-module (gnu packages python-web)
118 #:use-module (gnu packages python-xyz)
119 #:use-module (gnu packages readline)
120 #:use-module (gnu packages ruby)
121 #:use-module (gnu packages serialization)
122 #:use-module (gnu packages shells)
123 #:use-module (gnu packages sphinx)
124 #:use-module (gnu packages statistics)
125 #:use-module (gnu packages swig)
126 #:use-module (gnu packages tbb)
127 #:use-module (gnu packages tex)
128 #:use-module (gnu packages texinfo)
129 #:use-module (gnu packages textutils)
130 #:use-module (gnu packages time)
131 #:use-module (gnu packages tls)
132 #:use-module (gnu packages vim)
133 #:use-module (gnu packages web)
134 #:use-module (gnu packages xml)
135 #:use-module (gnu packages xorg)
136 #:use-module (srfi srfi-1)
137 #:use-module (ice-9 match))
139 (define-public aragorn
146 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
150 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
151 (build-system gnu-build-system)
153 `(#:tests? #f ; there are no tests
155 (modify-phases %standard-phases
165 (string-append "aragorn" ,version ".c"))
168 (lambda* (#:key outputs #:allow-other-keys)
169 (let* ((out (assoc-ref outputs "out"))
170 (bin (string-append out "/bin"))
171 (man (string-append out "/share/man/man1")))
172 (install-file "aragorn" bin)
173 (install-file "aragorn.1" man))
175 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
176 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
178 "Aragorn identifies transfer RNA, mitochondrial RNA and
179 transfer-messenger RNA from nucleotide sequences, based on homology to known
180 tRNA consensus sequences and RNA structure. It also outputs the secondary
181 structure of the predicted RNA.")
182 (license license:gpl2)))
190 ;; BamM is not available on pypi.
192 (url "https://github.com/Ecogenomics/BamM")
195 (file-name (git-file-name name version))
198 "1p83ahi984ipslxlg4yqy1gdnya9rkn1v71z8djgxkm9d2chw4c5"))
199 (modules '((guix build utils)))
202 ;; Delete bundled htslib.
203 (delete-file-recursively "c/htslib-1.3.1")
205 (build-system python-build-system)
207 `(#:python ,python-2 ; BamM is Python 2 only.
208 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
209 ;; been modified from its original form.
211 (let ((htslib (assoc-ref %build-inputs "htslib")))
212 (list "--with-libhts-lib" (string-append htslib "/lib")
213 "--with-libhts-inc" (string-append htslib "/include/htslib")))
215 (modify-phases %standard-phases
216 (add-after 'unpack 'autogen
218 (with-directory-excursion "c"
219 (let ((sh (which "sh")))
220 (for-each make-file-writable (find-files "." ".*"))
221 ;; Use autogen so that 'configure' works.
222 (substitute* "autogen.sh" (("/bin/sh") sh))
223 (setenv "CONFIG_SHELL" sh)
224 (invoke "./autogen.sh")))
227 ;; Run tests after installation so compilation only happens once.
229 (add-after 'install 'wrap-executable
230 (lambda* (#:key outputs #:allow-other-keys)
231 (let* ((out (assoc-ref outputs "out"))
232 (path (getenv "PATH")))
233 (wrap-program (string-append out "/bin/bamm")
234 `("PATH" ":" prefix (,path))))
236 (add-after 'wrap-executable 'post-install-check
237 (lambda* (#:key inputs outputs #:allow-other-keys)
239 (string-append (assoc-ref outputs "out")
244 (assoc-ref outputs "out")
246 (string-take (string-take-right
247 (assoc-ref inputs "python") 5) 3)
249 (getenv "PYTHONPATH")))
250 ;; There are 2 errors printed, but they are safe to ignore:
251 ;; 1) [E::hts_open_format] fail to open file ...
252 ;; 2) samtools view: failed to open ...
256 `(("autoconf" ,autoconf)
257 ("automake" ,automake)
260 ("python-nose" ,python2-nose)
261 ("python-pysam" ,python2-pysam)))
263 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
264 ("samtools" ,samtools)
268 ("coreutils" ,coreutils)))
270 `(("python-numpy" ,python2-numpy)))
271 (home-page "https://ecogenomics.github.io/BamM/")
272 (synopsis "Metagenomics-focused BAM file manipulator")
274 "BamM is a C library, wrapped in python, to efficiently generate and
275 parse BAM files, specifically for the analysis of metagenomic data. For
276 instance, it implements several methods to assess contig-wise read coverage.")
277 (license license:lgpl3+)))
279 (define-public bamtools
286 (url "https://github.com/pezmaster31/bamtools")
287 (commit (string-append "v" version))))
288 (file-name (git-file-name name version))
291 "0nfb2ypcx9959xnbz6wxh6py3xfizgmg8nrknxl95c507m9hmq8b"))))
292 (build-system cmake-build-system)
294 `(#:tests? #f ;no "check" target
296 (modify-phases %standard-phases
298 'configure 'set-ldflags
299 (lambda* (#:key outputs #:allow-other-keys)
303 (assoc-ref outputs "out") "/lib/bamtools"))
305 (inputs `(("zlib" ,zlib)))
306 (home-page "https://github.com/pezmaster31/bamtools")
307 (synopsis "C++ API and command-line toolkit for working with BAM data")
309 "BamTools provides both a C++ API and a command-line toolkit for handling
311 (license license:expat)))
313 (define-public bcftools
319 (uri (string-append "https://github.com/samtools/bcftools/"
321 version "/bcftools-" version ".tar.bz2"))
324 "1j3h638i8kgihzyrlnpj82xg1b23sijibys9hvwari3fy7kd0dkg"))
325 (modules '((guix build utils)))
327 ;; Delete bundled htslib.
328 (delete-file-recursively "htslib-1.9")
330 (build-system gnu-build-system)
333 (list "--enable-libgsl")
336 (modify-phases %standard-phases
337 (add-before 'check 'patch-tests
339 (substitute* "test/test.pl"
340 (("/bin/bash") (which "bash")))
348 (home-page "https://samtools.github.io/bcftools/")
349 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
351 "BCFtools is a set of utilities that manipulate variant calls in the
352 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
353 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
354 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
355 (license (list license:gpl3+ license:expat))))
357 (define-public bedops
364 (url "https://github.com/bedops/bedops")
365 (commit (string-append "v" version))))
366 (file-name (git-file-name name version))
369 "0mmgsgwz5r9w76hzgxkxc9s9lkdhhaf7vr6i02b09vbswvs1fyqx"))))
370 (build-system gnu-build-system)
373 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
375 (modify-phases %standard-phases
376 (add-after 'unpack 'unpack-tarballs
378 ;; FIXME: Bedops includes tarballs of minimally patched upstream
379 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
380 ;; libraries because at least one of the libraries (zlib) is
381 ;; patched to add a C++ function definition (deflateInit2cpp).
382 ;; Until the Bedops developers offer a way to link against system
383 ;; libraries we have to build the in-tree copies of these three
386 ;; See upstream discussion:
387 ;; https://github.com/bedops/bedops/issues/124
389 ;; Unpack the tarballs to benefit from shebang patching.
390 (with-directory-excursion "third-party"
391 (invoke "tar" "xvf" "jansson-2.6.tar.bz2")
392 (invoke "tar" "xvf" "zlib-1.2.7.tar.bz2")
393 (invoke "tar" "xvf" "bzip2-1.0.6.tar.bz2"))
394 ;; Disable unpacking of tarballs in Makefile.
395 (substitute* "system.mk/Makefile.linux"
396 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
397 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
398 (substitute* "third-party/zlib-1.2.7/Makefile.in"
399 (("^SHELL=.*$") "SHELL=bash\n"))
401 (delete 'configure))))
402 (home-page "https://github.com/bedops/bedops")
403 (synopsis "Tools for high-performance genomic feature operations")
405 "BEDOPS is a suite of tools to address common questions raised in genomic
406 studies---mostly with regard to overlap and proximity relationships between
407 data sets. It aims to be scalable and flexible, facilitating the efficient
408 and accurate analysis and management of large-scale genomic data.
410 BEDOPS provides tools that perform highly efficient and scalable Boolean and
411 other set operations, statistical calculations, archiving, conversion and
412 other management of genomic data of arbitrary scale. Tasks can be easily
413 split by chromosome for distributing whole-genome analyses across a
414 computational cluster.")
415 (license license:gpl2+)))
417 (define-public bedtools
423 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
424 "download/v" version "/"
425 "bedtools-" version ".tar.gz"))
428 "0m3hk6548846w83a9s5drsczvy67n2azx41kj71n03klb2gbzwg3"))))
429 (build-system gnu-build-system)
431 '(#:test-target "test"
433 (list (string-append "prefix=" (assoc-ref %outputs "out")))
435 (modify-phases %standard-phases
436 (delete 'configure))))
438 `(("python" ,python-wrapper)))
440 `(("samtools" ,samtools)
442 (home-page "https://github.com/arq5x/bedtools2")
443 (synopsis "Tools for genome analysis and arithmetic")
445 "Collectively, the bedtools utilities are a swiss-army knife of tools for
446 a wide-range of genomics analysis tasks. The most widely-used tools enable
447 genome arithmetic: that is, set theory on the genome. For example, bedtools
448 allows one to intersect, merge, count, complement, and shuffle genomic
449 intervals from multiple files in widely-used genomic file formats such as BAM,
451 (license license:expat)))
453 ;; Later releases of bedtools produce files with more columns than
454 ;; what Ribotaper expects.
455 (define-public bedtools-2.18
456 (package (inherit bedtools)
461 (uri (string-append "https://github.com/arq5x/bedtools2/"
462 "releases/download/v" version
463 "/bedtools-" version ".tar.gz"))
466 "11rvca19ncg03kxd0wzlfx5ws7r3nisd0z8s9j9n182d8ksp2pxz"))))
468 '(#:test-target "test"
470 (modify-phases %standard-phases
473 (lambda* (#:key outputs #:allow-other-keys)
474 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
475 (for-each (lambda (file)
476 (install-file file bin))
477 (find-files "bin" ".*")))
487 (url "https://github.com/PacificBiosciences/pbbam")
489 (file-name (git-file-name name version))
492 "0h9gkrpf2lrxklxp72xfl5bi3h5zcm5hprrya9gf0hr3xwlbpp0x"))))
493 (build-system meson-build-system)
496 (modify-phases %standard-phases
497 (add-after 'unpack 'find-googletest
498 (lambda* (#:key inputs #:allow-other-keys)
499 ;; It doesn't find gtest_main because there's no pkg-config file
500 ;; for it. Find it another way.
501 (substitute* "tests/meson.build"
502 (("pbbam_gtest_dep = dependency\\('gtest_main'.*")
503 (format #f "cpp = meson.get_compiler('cpp')
504 pbbam_gtest_dep = cpp.find_library('gtest_main', dirs : '~a')\n"
505 (assoc-ref inputs "googletest"))))
507 ;; TODO: tests/pbbam_test cannot be linked
508 ;; ld: tests/59830eb@@pbbam_test@exe/src_test_Accuracy.cpp.o:
509 ;; undefined reference to symbol '_ZTIN7testing4TestE'
510 ;; ld: /gnu/store/...-googletest-1.8.0/lib/libgtest.so:
511 ;; error adding symbols: DSO missing from command line
513 #:configure-flags '("-Dtests=false")))
514 ;; These libraries are listed as "Required" in the pkg-config file.
520 ("samtools" ,samtools)))
522 `(("googletest" ,googletest)
523 ("pkg-config" ,pkg-config)
524 ("python" ,python-wrapper))) ; for tests
525 (home-page "https://github.com/PacificBiosciences/pbbam")
526 (synopsis "Work with PacBio BAM files")
528 "The pbbam software package provides components to create, query, and
529 edit PacBio BAM files and associated indices. These components include a core
530 C++ library, bindings for additional languages, and command-line utilities.
531 This library is not intended to be used as a general-purpose BAM utility - all
532 input and output BAMs must adhere to the PacBio BAM format specification.
533 Non-PacBio BAMs will cause exceptions to be thrown.")
534 (license license:bsd-3)))
536 (define-public blasr-libcpp
538 (name "blasr-libcpp")
543 (url "https://github.com/PacificBiosciences/blasr_libcpp")
545 (file-name (git-file-name name version))
548 "0cn5l42zyq67sj0g2imqkhayz2iqvv0a1pgpbmlq0qynjmsrbfd2"))))
549 (build-system meson-build-system)
552 (modify-phases %standard-phases
553 (add-after 'unpack 'link-with-hdf5
554 (lambda* (#:key inputs #:allow-other-keys)
555 (let ((hdf5 (assoc-ref inputs "hdf5")))
556 (substitute* "meson.build"
557 (("libblasr_deps = \\[" m)
560 (format #f "cpp.find_library('hdf5', dirs : '~a'), \
561 cpp.find_library('hdf5_cpp', dirs : '~a'), "
564 (add-after 'unpack 'find-googletest
565 (lambda* (#:key inputs #:allow-other-keys)
566 ;; It doesn't find gtest_main because there's no pkg-config file
567 ;; for it. Find it another way.
568 (substitute* "unittest/meson.build"
569 (("libblasr_gtest_dep = dependency\\('gtest_main'.*")
570 (format #f "cpp = meson.get_compiler('cpp')
571 libblasr_gtest_dep = cpp.find_library('gtest_main', dirs : '~a')\n"
572 (assoc-ref inputs "googletest"))))
574 ;; TODO: unittest/libblasr_unittest cannot be linked
575 ;; ld: ;; unittest/df08227@@libblasr_unittest@exe/alignment_utils_FileUtils_gtest.cpp.o:
576 ;; undefined reference to symbol
577 ;; '_ZN7testing8internal9DeathTest6CreateEPKcPKNS0_2REES3_iPPS1_'
578 ;; ld: /gnu/store/...-googletest-1.8.0/lib/libgtest.so:
579 ;; error adding symbols: DSO missing from command line
581 #:configure-flags '("-Dtests=false")))
588 `(("googletest" ,googletest)
589 ("pkg-config" ,pkg-config)))
590 (home-page "https://github.com/PacificBiosciences/blasr_libcpp")
591 (synopsis "Library for analyzing PacBio genomic sequences")
593 "This package provides three libraries used by applications for analyzing
594 PacBio genomic sequences. This library contains three sub-libraries: pbdata,
596 (license license:bsd-3)))
605 (url "https://github.com/PacificBiosciences/blasr")
607 (file-name (git-file-name name version))
610 "1skgy2mvz8gsgfh1gc2nfgwvpyzb1hpmp2cf2773h5wsj8nw22kl"))))
611 (build-system meson-build-system)
614 (modify-phases %standard-phases
615 (add-after 'unpack 'link-with-hdf5
616 (lambda* (#:key inputs #:allow-other-keys)
617 (let ((hdf5 (assoc-ref inputs "hdf5")))
618 (substitute* "meson.build"
619 (("blasr_deps = \\[" m)
622 (format #f "cpp.find_library('hdf5', dirs : '~a'), \
623 cpp.find_library('hdf5_cpp', dirs : '~a'), "
626 ;; Tests require "cram" executable, which is not packaged.
628 #:configure-flags '("-Dtests=false")))
631 ("blasr-libcpp" ,blasr-libcpp)
636 `(("pkg-config" ,pkg-config)))
637 (home-page "https://github.com/PacificBiosciences/blasr")
638 (synopsis "PacBio long read aligner")
640 "Blasr is a genomic sequence aligner for processing PacBio long reads.")
641 (license license:bsd-3)))
643 (define-public ribotaper
649 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
650 "files/RiboTaper/RiboTaper_Version_"
654 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
655 (build-system gnu-build-system)
658 (modify-phases %standard-phases
659 (add-after 'install 'wrap-executables
660 (lambda* (#:key inputs outputs #:allow-other-keys)
661 (let* ((out (assoc-ref outputs "out")))
664 (wrap-program (string-append out "/bin/" script)
665 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
666 '("create_annotations_files.bash"
667 "create_metaplots.bash"
668 "Ribotaper_ORF_find.sh"
672 `(("bedtools" ,bedtools-2.18)
673 ("samtools" ,samtools-0.1)
674 ("r-minimal" ,r-minimal)
675 ("r-foreach" ,r-foreach)
676 ("r-xnomial" ,r-xnomial)
678 ("r-multitaper" ,r-multitaper)
679 ("r-seqinr" ,r-seqinr)))
680 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
681 (synopsis "Define translated ORFs using ribosome profiling data")
683 "Ribotaper is a method for defining translated @dfn{open reading
684 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
685 provides the Ribotaper pipeline.")
686 (license license:gpl3+)))
688 (define-public ribodiff
696 (url "https://github.com/ratschlab/RiboDiff")
697 (commit (string-append "v" version))))
698 (file-name (git-file-name name version))
701 "0x75nlp7qnmm64jasbi6l21f2cy99r2cjyl6b4hr8zf2bq22drnz"))))
702 (build-system python-build-system)
706 (modify-phases %standard-phases
707 ;; Generate an installable executable script wrapper.
708 (add-after 'unpack 'patch-setup.py
710 (substitute* "setup.py"
711 (("^(.*)packages=.*" line prefix)
712 (string-append line "\n"
713 prefix "scripts=['scripts/TE.py'],\n")))
716 `(("python-numpy" ,python2-numpy)
717 ("python-matplotlib" ,python2-matplotlib)
718 ("python-scipy" ,python2-scipy)
719 ("python-statsmodels" ,python2-statsmodels)))
721 `(("python-mock" ,python2-mock)
722 ("python-nose" ,python2-nose)))
723 (home-page "https://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
724 (synopsis "Detect translation efficiency changes from ribosome footprints")
725 (description "RiboDiff is a statistical tool that detects the protein
726 translational efficiency change from Ribo-Seq (ribosome footprinting) and
727 RNA-Seq data. It uses a generalized linear model to detect genes showing
728 difference in translational profile taking mRNA abundance into account. It
729 facilitates us to decipher the translational regulation that behave
730 independently with transcriptional regulation.")
731 (license license:gpl3+)))
733 (define-public bioawk
740 (url "https://github.com/lh3/bioawk")
741 (commit (string-append "v" version))))
742 (file-name (git-file-name name version))
745 "1pxc3zdnirxbf9a0az698hd8xdik7qkhypm7v6hn922x8y9qmspm"))))
746 (build-system gnu-build-system)
752 `(#:tests? #f ; There are no tests to run.
753 ;; Bison must generate files, before other targets can build.
756 (modify-phases %standard-phases
757 (delete 'configure) ; There is no configure phase.
759 (lambda* (#:key outputs #:allow-other-keys)
760 (let* ((out (assoc-ref outputs "out"))
761 (bin (string-append out "/bin"))
762 (man (string-append out "/share/man/man1")))
764 (copy-file "awk.1" (string-append man "/bioawk.1"))
765 (install-file "bioawk" bin))
767 (home-page "https://github.com/lh3/bioawk")
768 (synopsis "AWK with bioinformatics extensions")
769 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
770 support of several common biological data formats, including optionally gzip'ed
771 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
772 also adds a few built-in functions and a command line option to use TAB as the
773 input/output delimiter. When the new functionality is not used, bioawk is
774 intended to behave exactly the same as the original BWK awk.")
775 (license license:x11)))
777 (define-public python-pybedtools
779 (name "python-pybedtools")
783 (uri (pypi-uri "pybedtools" version))
786 "14w5i40gi25clrr7h4wa2pcpnyipya8hrqi7nq77553zc5wf0df0"))))
787 (build-system python-build-system)
789 `(#:modules ((ice-9 ftw)
793 (guix build python-build-system))
794 ;; See https://github.com/daler/pybedtools/issues/192
796 (modify-phases %standard-phases
797 (add-after 'unpack 'disable-broken-tests
799 (substitute* "pybedtools/test/test_scripts.py"
800 ;; This test freezes.
801 (("def test_intron_exon_reads")
802 "def _do_not_test_intron_exon_reads")
803 ;; This test fails in the Python 2 build.
804 (("def test_venn_mpl")
805 "def _do_not_test_venn_mpl"))
806 (substitute* "pybedtools/test/test_helpers.py"
807 ;; Requires internet access.
808 (("def test_chromsizes")
809 "def _do_not_test_chromsizes")
810 ;; Broken as a result of the workaround used in the check phase
811 ;; (see: https://github.com/daler/pybedtools/issues/192).
812 (("def test_getting_example_beds")
813 "def _do_not_test_getting_example_beds"))
814 ;; This issue still occurs on python2
815 (substitute* "pybedtools/test/test_issues.py"
816 (("def test_issue_303")
817 "def _test_issue_303"))
819 ;; TODO: Remove phase after it's part of PYTHON-BUILD-SYSTEM.
821 ;; Force the Cythonization of C++ files to guard against compilation
823 (add-after 'unpack 'remove-cython-generated-files
825 (let ((cython-sources (map (cut string-drop-right <> 4)
826 (find-files "." "\\.pyx$")))
827 (c/c++-files (find-files "." "\\.(c|cpp|cxx)$")))
828 (define (strip-extension filename)
829 (string-take filename (string-index-right filename #\.)))
830 (define (cythonized? c/c++-file)
831 (member (strip-extension c/c++-file) cython-sources))
832 (for-each delete-file (filter cythonized? c/c++-files))
834 (add-after 'remove-cython-generated-files 'generate-cython-extensions
836 (invoke "python" "setup.py" "cythonize")))
839 (let* ((cwd (getcwd))
840 (build-root-directory (string-append cwd "/build/"))
841 (build (string-append
843 (find (cut string-prefix? "lib" <>)
844 (scandir (string-append
845 build-root-directory)))))
846 (scripts (string-append
848 (find (cut string-prefix? "scripts" <>)
849 (scandir build-root-directory)))))
851 (string-append build ":" (getenv "PYTHONPATH")))
852 ;; Executable scripts such as 'intron_exon_reads.py' must be
853 ;; available in the PATH.
855 (string-append scripts ":" (getenv "PATH"))))
856 ;; The tests need to be run from elsewhere...
857 (mkdir-p "/tmp/test")
858 (copy-recursively "pybedtools/test" "/tmp/test")
859 (with-directory-excursion "/tmp/test"
860 (invoke "pytest" "-v" "--doctest-modules")))))))
862 `(("bedtools" ,bedtools)
863 ("samtools" ,samtools)
864 ("python-matplotlib" ,python-matplotlib)
865 ("python-pysam" ,python-pysam)
866 ("python-pyyaml" ,python-pyyaml)))
868 `(("python-numpy" ,python-numpy)
869 ("python-pandas" ,python-pandas)
870 ("python-cython" ,python-cython)
871 ("kentutils" ,kentutils) ; for bedGraphToBigWig
872 ("python-six" ,python-six)
873 ;; For the test suite.
874 ("python-pytest" ,python-pytest)
875 ("python-psutil" ,python-psutil)))
876 (home-page "https://pythonhosted.org/pybedtools/")
877 (synopsis "Python wrapper for BEDtools programs")
879 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
880 which are widely used for genomic interval manipulation or \"genome algebra\".
881 pybedtools extends BEDTools by offering feature-level manipulations from with
883 (license license:gpl2+)))
885 (define-public python2-pybedtools
886 (let ((pybedtools (package-with-python2 python-pybedtools)))
890 `(("python2-pathlib" ,python2-pathlib)
891 ,@(package-native-inputs pybedtools))))))
893 (define-public python-biom-format
895 (name "python-biom-format")
900 ;; Use GitHub as source because PyPI distribution does not contain
901 ;; test data: https://github.com/biocore/biom-format/issues/693
903 (url "https://github.com/biocore/biom-format")
905 (file-name (git-file-name name version))
908 "1rna16lyk5aqhnv0dp77wwaplias93f1vw28ad3jmyw6hwkai05v"))
909 (modules '((guix build utils)))
911 ;; Delete generated C files.
912 (for-each delete-file (find-files "." "\\.c"))
914 (build-system python-build-system)
917 (modify-phases %standard-phases
918 (add-after 'unpack 'use-cython
919 (lambda _ (setenv "USE_CYTHON" "1") #t))
920 (add-after 'unpack 'disable-broken-tests
922 (substitute* "biom/tests/test_cli/test_validate_table.py"
923 (("^(.+)def test_invalid_hdf5" m indent)
924 (string-append indent
925 "@npt.dec.skipif(True, msg='Guix')\n"
927 (substitute* "biom/tests/test_table.py"
928 (("^(.+)def test_from_hdf5_issue_731" m indent)
929 (string-append indent
930 "@npt.dec.skipif(True, msg='Guix')\n"
933 (add-before 'reset-gzip-timestamps 'make-files-writable
934 (lambda* (#:key outputs #:allow-other-keys)
935 (let ((out (assoc-ref outputs "out")))
936 (for-each (lambda (file) (chmod file #o644))
937 (find-files out "\\.gz"))
940 `(("python-numpy" ,python-numpy)
941 ("python-scipy" ,python-scipy)
942 ("python-flake8" ,python-flake8)
943 ("python-future" ,python-future)
944 ("python-click" ,python-click)
945 ("python-h5py" ,python-h5py)
946 ;; FIXME: Upgrade to pandas 1.0 when
947 ;; https://github.com/biocore/biom-format/issues/837 is resolved.
948 ("python-pandas" ,python-pandas-0.25)))
950 `(("python-cython" ,python-cython)
951 ("python-pytest" ,python-pytest)
952 ("python-pytest-cov" ,python-pytest-cov)
953 ("python-nose" ,python-nose)))
954 (home-page "http://www.biom-format.org")
955 (synopsis "Biological Observation Matrix (BIOM) format utilities")
957 "The BIOM file format is designed to be a general-use format for
958 representing counts of observations e.g. operational taxonomic units, KEGG
959 orthology groups or lipid types, in one or more biological samples
960 e.g. microbiome samples, genomes, metagenomes.")
961 (license license:bsd-3)
962 (properties `((python2-variant . ,(delay python2-biom-format))))))
964 (define-public python2-biom-format
965 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
969 (substitute-keyword-arguments (package-arguments base)
971 `(modify-phases ,phases
972 ;; Do not require the unmaintained pyqi library.
973 (add-after 'unpack 'remove-pyqi
975 (substitute* "setup.py"
976 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
979 (define-public python-pairtools
981 (name "python-pairtools")
986 (url "https://github.com/mirnylab/pairtools")
987 (commit (string-append "v" version))))
988 (file-name (git-file-name name version))
991 "0gr8y13q7sd6yai6df4aavl2470n1f9s3cib6r473z4hr8hcbwmc"))))
992 (build-system python-build-system)
995 (modify-phases %standard-phases
996 (add-after 'unpack 'fix-references
998 (substitute* '("pairtools/pairtools_merge.py"
999 "pairtools/pairtools_sort.py")
1000 (("/bin/bash") (which "bash")))
1003 (lambda* (#:key inputs outputs #:allow-other-keys)
1004 (add-installed-pythonpath inputs outputs)
1005 (with-directory-excursion "/tmp"
1006 (invoke "pytest" "-v")))))))
1008 `(("python-cython" ,python-cython)
1009 ("python-nose" ,python-nose)
1010 ("python-pytest" ,python-pytest)))
1012 `(("python" ,python-wrapper)))
1014 `(("htslib" ,htslib) ; for bgzip, looked up in PATH
1015 ("samtools" ,samtools) ; looked up in PATH
1016 ("lz4" ,lz4) ; for lz4c
1017 ("python-click" ,python-click)
1018 ("python-numpy" ,python-numpy)))
1019 (home-page "https://github.com/mirnylab/pairtools")
1020 (synopsis "Process mapped Hi-C data")
1021 (description "Pairtools is a simple and fast command-line framework to
1022 process sequencing data from a Hi-C experiment. Process pair-end sequence
1023 alignments and perform the following operations:
1026 @item detect ligation junctions (a.k.a. Hi-C pairs) in aligned paired-end
1027 sequences of Hi-C DNA molecules
1028 @item sort @code{.pairs} files for downstream analyses
1029 @item detect, tag and remove PCR/optical duplicates
1030 @item generate extensive statistics of Hi-C datasets
1031 @item select Hi-C pairs given flexibly defined criteria
1032 @item restore @code{.sam} alignments from Hi-C pairs.
1035 (license license:expat)))
1037 (define-public bioperl-minimal
1038 (let* ((inputs `(("perl-module-build" ,perl-module-build)
1039 ("perl-data-stag" ,perl-data-stag)
1040 ("perl-libwww" ,perl-libwww)
1041 ("perl-uri" ,perl-uri)))
1043 (map (compose package-name cadr)
1046 (map (compose package-transitive-target-inputs cadr) inputs))))))
1048 (name "bioperl-minimal")
1054 (url "https://github.com/bioperl/bioperl-live")
1055 (commit (string-append "release-"
1056 (string-map (lambda (c)
1058 #\- c)) version)))))
1059 (file-name (git-file-name name version))
1062 "0wl8yvzcls59pwwk6m8ahy87pwg6nnibzy5cldbvmcwg2x2w7783"))))
1063 (build-system perl-build-system)
1066 (modify-phases %standard-phases
1068 'install 'wrap-programs
1069 (lambda* (#:key outputs #:allow-other-keys)
1070 ;; Make sure all executables in "bin" find the required Perl
1071 ;; modules at runtime. As the PERL5LIB variable contains also
1072 ;; the paths of native inputs, we pick the transitive target
1073 ;; inputs from %build-inputs.
1074 (let* ((out (assoc-ref outputs "out"))
1075 (bin (string-append out "/bin/"))
1077 (cons (string-append out "/lib/perl5/site_perl")
1079 (assoc-ref %build-inputs name))
1080 ',transitive-inputs))
1082 (for-each (lambda (file)
1084 `("PERL5LIB" ":" prefix (,path))))
1085 (find-files bin "\\.pl$"))
1089 `(("perl-test-most" ,perl-test-most)))
1090 (home-page "https://metacpan.org/release/BioPerl")
1091 (synopsis "Bioinformatics toolkit")
1093 "BioPerl is the product of a community effort to produce Perl code which
1094 is useful in biology. Examples include Sequence objects, Alignment objects
1095 and database searching objects. These objects not only do what they are
1096 advertised to do in the documentation, but they also interact - Alignment
1097 objects are made from the Sequence objects, Sequence objects have access to
1098 Annotation and SeqFeature objects and databases, Blast objects can be
1099 converted to Alignment objects, and so on. This means that the objects
1100 provide a coordinated and extensible framework to do computational biology.")
1101 (license license:perl-license))))
1103 (define-public python-biopython
1105 (name "python-biopython")
1109 ;; use PyPi rather than biopython.org to ease updating
1110 (uri (pypi-uri "biopython" version))
1113 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
1114 (build-system python-build-system)
1117 (modify-phases %standard-phases
1118 (add-before 'check 'set-home
1119 ;; Some tests require a home directory to be set.
1120 (lambda _ (setenv "HOME" "/tmp") #t)))))
1122 `(("python-numpy" ,python-numpy)))
1123 (home-page "https://biopython.org/")
1124 (synopsis "Tools for biological computation in Python")
1126 "Biopython is a set of tools for biological computation including parsers
1127 for bioinformatics files into Python data structures; interfaces to common
1128 bioinformatics programs; a standard sequence class and tools for performing
1129 common operations on them; code to perform data classification; code for
1130 dealing with alignments; code making it easy to split up parallelizable tasks
1131 into separate processes; and more.")
1132 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
1134 (define-public python2-biopython
1135 (package-with-python2 python-biopython))
1137 (define-public python-fastalite
1139 (name "python-fastalite")
1144 (uri (pypi-uri "fastalite" version))
1147 "1qli6pxp77i9xn2wfciq2zaxhl82bdxb33cpzqzj1z25yd036wqj"))))
1148 (build-system python-build-system)
1150 `(#:tests? #f)) ; Test data is not distributed.
1151 (home-page "https://github.com/nhoffman/fastalite")
1152 (synopsis "Simplest possible FASTA parser")
1153 (description "This library implements a FASTA and a FASTQ parser without
1154 relying on a complex dependency tree.")
1155 (license license:expat)))
1157 (define-public python2-fastalite
1158 (package-with-python2 python-fastalite))
1160 (define-public bpp-core
1161 ;; The last release was in 2014 and the recommended way to install from source
1162 ;; is to clone the git repository, so we do this.
1163 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1164 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
1167 (version (string-append "2.2.0-1." (string-take commit 7)))
1171 (url "http://biopp.univ-montp2.fr/git/bpp-core")
1173 (file-name (string-append name "-" version "-checkout"))
1176 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
1177 (build-system cmake-build-system)
1179 `(#:parallel-build? #f))
1180 (home-page "http://biopp.univ-montp2.fr")
1181 (synopsis "C++ libraries for Bioinformatics")
1183 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1184 analysis, phylogenetics, molecular evolution and population genetics. It is
1185 Object Oriented and is designed to be both easy to use and computer efficient.
1186 Bio++ intends to help programmers to write computer expensive programs, by
1187 providing them a set of re-usable tools.")
1188 (license license:cecill-c))))
1190 (define-public bpp-phyl
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 "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
1197 (version (string-append "2.2.0-1." (string-take commit 7)))
1201 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
1203 (file-name (string-append name "-" version "-checkout"))
1206 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
1207 (build-system cmake-build-system)
1209 `(#:parallel-build? #f
1210 ;; If out-of-source, test data is not copied into the build directory
1211 ;; so the tests fail.
1212 #:out-of-source? #f))
1214 `(("bpp-core" ,bpp-core)
1215 ("bpp-seq" ,bpp-seq)))
1216 (home-page "http://biopp.univ-montp2.fr")
1217 (synopsis "Bio++ phylogenetic Library")
1219 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1220 analysis, phylogenetics, molecular evolution and population genetics. This
1221 library provides phylogenetics-related modules.")
1222 (license license:cecill-c))))
1224 (define-public bpp-popgen
1225 ;; The last release was in 2014 and the recommended way to install from source
1226 ;; is to clone the git repository, so we do this.
1227 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1228 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
1231 (version (string-append "2.2.0-1." (string-take commit 7)))
1235 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
1237 (file-name (string-append name "-" version "-checkout"))
1240 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
1241 (build-system cmake-build-system)
1243 `(#:parallel-build? #f
1244 #:tests? #f)) ; There are no tests.
1246 `(("bpp-core" ,bpp-core)
1247 ("bpp-seq" ,bpp-seq)))
1248 (home-page "http://biopp.univ-montp2.fr")
1249 (synopsis "Bio++ population genetics library")
1251 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1252 analysis, phylogenetics, molecular evolution and population genetics. This
1253 library provides population genetics-related modules.")
1254 (license license:cecill-c))))
1256 (define-public bpp-seq
1257 ;; The last release was in 2014 and the recommended way to install from source
1258 ;; is to clone the git repository, so we do this.
1259 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1260 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
1263 (version (string-append "2.2.0-1." (string-take commit 7)))
1267 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
1269 (file-name (string-append name "-" version "-checkout"))
1272 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
1273 (build-system cmake-build-system)
1275 `(#:parallel-build? #f
1276 ;; If out-of-source, test data is not copied into the build directory
1277 ;; so the tests fail.
1278 #:out-of-source? #f))
1280 `(("bpp-core" ,bpp-core)))
1281 (home-page "http://biopp.univ-montp2.fr")
1282 (synopsis "Bio++ sequence library")
1284 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1285 analysis, phylogenetics, molecular evolution and population genetics. This
1286 library provides sequence-related modules.")
1287 (license license:cecill-c))))
1289 (define-public bppsuite
1290 ;; The last release was in 2014 and the recommended way to install from source
1291 ;; is to clone the git repository, so we do this.
1292 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1293 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
1296 (version (string-append "2.2.0-1." (string-take commit 7)))
1300 (url "http://biopp.univ-montp2.fr/git/bppsuite")
1302 (file-name (string-append name "-" version "-checkout"))
1305 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
1306 (build-system cmake-build-system)
1308 `(#:parallel-build? #f
1309 #:tests? #f)) ; There are no tests.
1313 ("texinfo" ,texinfo)))
1315 `(("bpp-core" ,bpp-core)
1316 ("bpp-seq" ,bpp-seq)
1317 ("bpp-phyl" ,bpp-phyl)
1318 ("bpp-phyl" ,bpp-popgen)))
1319 (home-page "http://biopp.univ-montp2.fr")
1320 (synopsis "Bioinformatics tools written with the Bio++ libraries")
1322 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1323 analysis, phylogenetics, molecular evolution and population genetics. This
1324 package provides command line tools using the Bio++ library.")
1325 (license license:cecill-c))))
1327 (define-public blast+
1334 "https://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
1335 version "/ncbi-blast-" version "+-src.tar.gz"))
1338 "11kvrrl0mcwww6530r55hccpg3x3msmhr3051fwnjbq8rzg2j1qi"))
1339 (modules '((guix build utils)))
1342 ;; Remove bundled bzip2, zlib and pcre.
1343 (delete-file-recursively "c++/src/util/compress/bzip2")
1344 (delete-file-recursively "c++/src/util/compress/zlib")
1345 (delete-file-recursively "c++/src/util/regexp")
1346 (substitute* "c++/src/util/compress/Makefile.in"
1347 (("bzip2 zlib api") "api"))
1348 ;; Remove useless msbuild directory
1349 (delete-file-recursively
1350 "c++/src/build-system/project_tree_builder/msbuild")
1352 (build-system gnu-build-system)
1354 `(;; There are two(!) tests for this massive library, and both fail with
1355 ;; "unparsable timing stats".
1356 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
1357 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
1360 #:parallel-build? #f ; not supported
1362 (modify-phases %standard-phases
1363 (add-before 'configure 'set-HOME
1364 ;; $HOME needs to be set at some point during the configure phase
1365 (lambda _ (setenv "HOME" "/tmp") #t))
1366 (add-after 'unpack 'enter-dir
1367 (lambda _ (chdir "c++") #t))
1368 (add-after 'enter-dir 'fix-build-system
1370 (define (which* cmd)
1371 (cond ((string=? cmd "date")
1372 ;; make call to "date" deterministic
1377 (format (current-error-port)
1378 "WARNING: Unable to find absolute path for ~s~%"
1382 ;; Rewrite hardcoded paths to various tools
1383 (substitute* (append '("src/build-system/configure.ac"
1384 "src/build-system/configure"
1385 "src/build-system/helpers/run_with_lock.c"
1386 "scripts/common/impl/if_diff.sh"
1387 "scripts/common/impl/run_with_lock.sh"
1388 "src/build-system/Makefile.configurables.real"
1389 "src/build-system/Makefile.in.top"
1390 "src/build-system/Makefile.meta.gmake=no"
1391 "src/build-system/Makefile.meta.in"
1392 "src/build-system/Makefile.meta_l"
1393 "src/build-system/Makefile.meta_p"
1394 "src/build-system/Makefile.meta_r"
1395 "src/build-system/Makefile.mk.in"
1396 "src/build-system/Makefile.requirements"
1397 "src/build-system/Makefile.rules_with_autodep.in")
1398 (find-files "scripts/common/check" "\\.sh$"))
1399 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1400 (or (which* cmd) all)))
1402 (substitute* (find-files "src/build-system" "^config.*")
1403 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1406 ;; rewrite "/var/tmp" in check script
1407 (substitute* "scripts/common/check/check_make_unix.sh"
1408 (("/var/tmp") "/tmp"))
1410 ;; do not reset PATH
1411 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1413 (("action=/bin/") "action=")
1414 (("export PATH") ":"))
1417 (lambda* (#:key inputs outputs #:allow-other-keys)
1418 (let ((out (assoc-ref outputs "out"))
1419 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1420 (include (string-append (assoc-ref outputs "include")
1421 "/include/ncbi-tools++")))
1422 ;; The 'configure' script doesn't recognize things like
1423 ;; '--enable-fast-install'.
1424 (invoke "./configure.orig"
1425 (string-append "--with-build-root=" (getcwd) "/build")
1426 (string-append "--prefix=" out)
1427 (string-append "--libdir=" lib)
1428 (string-append "--includedir=" include)
1429 (string-append "--with-bz2="
1430 (assoc-ref inputs "bzip2"))
1431 (string-append "--with-z="
1432 (assoc-ref inputs "zlib"))
1433 (string-append "--with-pcre="
1434 (assoc-ref inputs "pcre"))
1435 ;; Each library is built twice by default, once
1436 ;; with "-static" in its name, and again
1441 (outputs '("out" ; 21 MB
1450 ("python" ,python-wrapper)))
1453 (home-page "https://blast.ncbi.nlm.nih.gov")
1454 (synopsis "Basic local alignment search tool")
1456 "BLAST is a popular method of performing a DNA or protein sequence
1457 similarity search, using heuristics to produce results quickly. It also
1458 calculates an “expect value” that estimates how many matches would have
1459 occurred at a given score by chance, which can aid a user in judging how much
1460 confidence to have in an alignment.")
1461 ;; Most of the sources are in the public domain, with the following
1464 ;; * ./c++/include/util/bitset/
1465 ;; * ./c++/src/html/ncbi_menu*.js
1467 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1469 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1471 ;; * ./c++/src/corelib/teamcity_*
1472 (license (list license:public-domain
1478 (define-public bless
1484 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1488 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1489 (modules '((guix build utils)))
1492 ;; Remove bundled boost, pigz, zlib, and .git directory
1493 ;; FIXME: also remove bundled sources for murmurhash3 and
1494 ;; kmc once packaged.
1495 (delete-file-recursively "boost")
1496 (delete-file-recursively "pigz")
1497 (delete-file-recursively "google-sparsehash")
1498 (delete-file-recursively "zlib")
1499 (delete-file-recursively ".git")
1501 (build-system gnu-build-system)
1503 '(#:tests? #f ;no "check" target
1505 (list (string-append "ZLIB="
1506 (assoc-ref %build-inputs "zlib:static")
1508 (string-append "LDFLAGS="
1509 (string-join '("-lboost_filesystem"
1515 (modify-phases %standard-phases
1516 (add-after 'unpack 'do-not-build-bundled-pigz
1517 (lambda* (#:key inputs outputs #:allow-other-keys)
1518 (substitute* "Makefile"
1519 (("cd pigz/pigz-2.3.3; make") ""))
1521 (add-after 'unpack 'patch-paths-to-executables
1522 (lambda* (#:key inputs outputs #:allow-other-keys)
1523 (substitute* "parse_args.cpp"
1524 (("kmc_binary = .*")
1525 (string-append "kmc_binary = \""
1526 (assoc-ref outputs "out")
1528 (("pigz_binary = .*")
1529 (string-append "pigz_binary = \""
1530 (assoc-ref inputs "pigz")
1534 (lambda* (#:key outputs #:allow-other-keys)
1535 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1536 (for-each (lambda (file)
1537 (install-file file bin))
1538 '("bless" "kmc/bin/kmc"))
1540 (delete 'configure))))
1544 `(("openmpi" ,openmpi)
1546 ("sparsehash" ,sparsehash)
1548 ("zlib:static" ,zlib "static")
1550 (supported-systems '("x86_64-linux"))
1551 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1552 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1554 "@dfn{Bloom-filter-based error correction solution for high-throughput
1555 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1556 correction tool for genomic reads produced by @dfn{Next-generation
1557 sequencing} (NGS). BLESS produces accurate correction results with much less
1558 memory compared with previous solutions and is also able to tolerate a higher
1559 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1560 errors at the end of reads.")
1561 (license license:gpl3+)))
1563 (define-public bowtie
1570 (url "https://github.com/BenLangmead/bowtie2")
1571 (commit (string-append "v" version))))
1572 (file-name (git-file-name name version))
1575 "1zl3cf327y2p7p03cavymbh7b00djc7lncfaqih33n96iy9q8ibp"))
1576 (modules '((guix build utils)))
1579 (substitute* "Makefile"
1580 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1581 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1582 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
1584 (build-system gnu-build-system)
1589 (string-append "prefix=" (assoc-ref %outputs "out")))
1591 (modify-phases %standard-phases
1596 "scripts/test/simple_tests.pl"
1597 "--bowtie2=./bowtie2"
1598 "--bowtie2-build=./bowtie2-build")
1603 ("python" ,python-wrapper)))
1606 ("perl-clone" ,perl-clone)
1607 ("perl-test-deep" ,perl-test-deep)
1608 ("perl-test-simple" ,perl-test-simple)))
1609 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1610 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1612 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1613 reads to long reference sequences. It is particularly good at aligning reads
1614 of about 50 up to 100s or 1,000s of characters, and particularly good at
1615 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1616 genome with an FM Index to keep its memory footprint small: for the human
1617 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1618 gapped, local, and paired-end alignment modes.")
1619 (supported-systems '("x86_64-linux"))
1620 (license license:gpl3+)))
1622 (define-public bowtie1
1628 (uri (string-append "mirror://sourceforge/bowtie-bio/bowtie/"
1629 version "/bowtie-src-x86_64.zip"))
1632 "0vmiqdhc9dzyfy9sh6vgi7k9xy2hiw8g87vbamnc6cgpm179zsa4"))
1633 (modules '((guix build utils)))
1635 '(substitute* "Makefile"
1636 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1637 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1638 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1639 (build-system gnu-build-system)
1641 '(#:tests? #f ; no "check" target
1644 (string-append "prefix=" (assoc-ref %outputs "out")))
1646 (modify-phases %standard-phases
1647 (delete 'configure))))
1651 (supported-systems '("x86_64-linux"))
1652 (home-page "http://bowtie-bio.sourceforge.net/index.shtml")
1653 (synopsis "Fast aligner for short nucleotide sequence reads")
1655 "Bowtie is a fast, memory-efficient short read aligner. It aligns short
1656 DNA sequences (reads) to the human genome at a rate of over 25 million 35-bp
1657 reads per hour. Bowtie indexes the genome with a Burrows-Wheeler index to
1658 keep its memory footprint small: typically about 2.2 GB for the human
1659 genome (2.9 GB for paired-end).")
1660 (license license:artistic2.0)))
1662 (define-public tophat
1669 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1673 "19add02kv2xhd6ihd779dr7x35ggym3jqr0m5c4315i1yfb0p11p"))
1674 (modules '((guix build utils)))
1677 ;; Remove bundled SeqAn and samtools
1678 (delete-file-recursively "src/SeqAn-1.4.2")
1679 (delete-file-recursively "src/samtools-0.1.18")
1681 (build-system gnu-build-system)
1683 '(#:parallel-build? #f ; not supported
1685 (modify-phases %standard-phases
1686 (add-after 'unpack 'use-system-samtools
1687 (lambda* (#:key inputs #:allow-other-keys)
1688 (substitute* "src/Makefile.in"
1689 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1690 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1691 (("SAMPROG = samtools_0\\.1\\.18") "")
1692 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1693 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1694 (substitute* '("src/common.cpp"
1696 (("samtools_0.1.18") (which "samtools")))
1697 (substitute* '("src/common.h"
1698 "src/bam2fastx.cpp")
1699 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1700 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1701 (substitute* '("src/bwt_map.h"
1703 "src/align_status.h")
1704 (("#include <bam.h>") "#include <samtools/bam.h>")
1705 (("#include <sam.h>") "#include <samtools/sam.h>"))
1708 `(("gcc" ,gcc-5))) ;; doesn't build with later versions
1712 ("ncurses" ,ncurses)
1714 ("python" ,python-2)
1715 ("samtools" ,samtools-0.1)
1718 (home-page "https://ccb.jhu.edu/software/tophat/index.shtml")
1719 (synopsis "Spliced read mapper for RNA-Seq data")
1721 "TopHat is a fast splice junction mapper for nucleotide sequence
1722 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1723 mammalian-sized genomes using the ultra high-throughput short read
1724 aligner Bowtie, and then analyzes the mapping results to identify
1725 splice junctions between exons.")
1726 ;; TopHat is released under the Boost Software License, Version 1.0
1727 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1728 (license license:boost1.0)))
1737 "https://github.com/lh3/bwa/releases/download/v"
1738 version "/bwa-" version ".tar.bz2"))
1741 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1742 (build-system gnu-build-system)
1744 '(#:tests? #f ;no "check" target
1746 (modify-phases %standard-phases
1748 (lambda* (#:key outputs #:allow-other-keys)
1749 (let* ((out (assoc-ref outputs "out"))
1750 (bin (string-append out "/bin"))
1751 (lib (string-append out "/lib"))
1752 (doc (string-append out "/share/doc/bwa"))
1753 (man (string-append out "/share/man/man1")))
1754 (install-file "bwa" bin)
1755 (install-file "libbwa.a" lib)
1756 (install-file "README.md" doc)
1757 (install-file "bwa.1" man))
1759 ;; no "configure" script
1760 (delete 'configure))))
1761 (inputs `(("zlib" ,zlib)))
1762 ;; Non-portable SSE instructions are used so building fails on platforms
1763 ;; other than x86_64.
1764 (supported-systems '("x86_64-linux"))
1765 (home-page "http://bio-bwa.sourceforge.net/")
1766 (synopsis "Burrows-Wheeler sequence aligner")
1768 "BWA is a software package for mapping low-divergent sequences against a
1769 large reference genome, such as the human genome. It consists of three
1770 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1771 designed for Illumina sequence reads up to 100bp, while the rest two for
1772 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1773 features such as long-read support and split alignment, but BWA-MEM, which is
1774 the latest, is generally recommended for high-quality queries as it is faster
1775 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1776 70-100bp Illumina reads.")
1777 (license license:gpl3+)))
1779 (define-public bwa-pssm
1780 (package (inherit bwa)
1786 (url "https://github.com/pkerpedjiev/bwa-pssm")
1788 (file-name (git-file-name name version))
1791 "076c4q0cdqz8jgylb067y9zmvxglppnzi3qiscn0xiypgc6lgb5r"))))
1792 (build-system gnu-build-system)
1797 (home-page "http://bwa-pssm.binf.ku.dk/")
1798 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1800 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1801 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1802 existing aligners it is fast and sensitive. Unlike most other aligners,
1803 however, it is also adaptible in the sense that one can direct the alignment
1804 based on known biases within the data set. It is coded as a modification of
1805 the original BWA alignment program and shares the genome index structure as
1806 well as many of the command line options.")
1807 (license license:gpl3+)))
1809 (define-public bwa-meth
1816 (url "https://github.com/brentp/bwa-meth")
1817 (commit (string-append "v" version))))
1818 (file-name (git-file-name name version))
1821 "17j31i7zws5j7mhsq9x3qgkxly6mlmrgwhfq0qbflgxrmx04yaiz"))))
1822 (build-system python-build-system)
1825 (modify-phases %standard-phases
1826 (add-after 'unpack 'keep-references-to-bwa
1827 (lambda* (#:key inputs #:allow-other-keys)
1828 (substitute* "bwameth.py"
1829 (("bwa (mem|index)" _ command)
1830 (string-append (which "bwa") " " command))
1831 ;; There's an ill-advised check for "samtools" on PATH.
1837 `(("python-toolshed" ,python-toolshed)))
1838 (home-page "https://github.com/brentp/bwa-meth")
1839 (synopsis "Fast and accurante alignment of BS-Seq reads")
1841 "BWA-Meth works for single-end reads and for paired-end reads from the
1842 directional protocol (most common). It uses the method employed by
1843 methylcoder and Bismark of in silico conversion of all C's to T's in both
1844 reference and reads. It recovers the original read (needed to tabulate
1845 methylation) by attaching it as a comment which BWA appends as a tag to the
1846 read. It performs favorably to existing aligners gauged by number of on and
1847 off-target reads for a capture method that targets CpG-rich region.")
1848 (license license:expat)))
1850 (define-public python-bx-python
1852 (name "python-bx-python")
1856 (uri (pypi-uri "bx-python" version))
1859 "11kksg2rbzihpmcid823xvg42xi88m7sz58rzk29abybkxy0rszs"))))
1860 (build-system python-build-system)
1861 ;; Tests fail because test data are not included
1862 (arguments '(#:tests? #f))
1864 `(("python-numpy" ,python-numpy)
1865 ("python-six" ,python-six)))
1869 `(("python-lzo" ,python-lzo)
1870 ("python-nose" ,python-nose)
1871 ("python-cython" ,python-cython)))
1872 (home-page "https://github.com/bxlab/bx-python")
1873 (synopsis "Tools for manipulating biological data")
1875 "bx-python provides tools for manipulating biological data, particularly
1876 multiple sequence alignments.")
1877 (license license:expat)))
1879 (define-public python2-bx-python
1880 (package-with-python2 python-bx-python))
1882 (define-public python-pysam
1884 (name "python-pysam")
1888 ;; Test data is missing on PyPi.
1890 (url "https://github.com/pysam-developers/pysam")
1891 (commit (string-append "v" version))))
1892 (file-name (git-file-name name version))
1895 "1vj367w6xbn9bpmksm162l1aipf7cj97h1q83y7jcpm33ihwpf7x"))
1896 (modules '((guix build utils)))
1898 ;; Drop bundled htslib. TODO: Also remove samtools
1900 (delete-file-recursively "htslib")
1902 (build-system python-build-system)
1904 `(#:modules ((ice-9 ftw)
1906 (guix build python-build-system)
1909 (modify-phases %standard-phases
1910 (add-before 'build 'set-flags
1911 (lambda* (#:key inputs #:allow-other-keys)
1912 (setenv "HTSLIB_MODE" "external")
1913 (setenv "HTSLIB_LIBRARY_DIR"
1914 (string-append (assoc-ref inputs "htslib") "/lib"))
1915 (setenv "HTSLIB_INCLUDE_DIR"
1916 (string-append (assoc-ref inputs "htslib") "/include"))
1917 (setenv "LDFLAGS" "-lncurses")
1918 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1921 (lambda* (#:key inputs outputs #:allow-other-keys)
1922 ;; This file contains tests that require a connection to the
1924 (delete-file "tests/tabix_test.py")
1925 ;; FIXME: This test fails
1926 (delete-file "tests/AlignmentFile_test.py")
1927 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1928 (setenv "PYTHONPATH"
1930 (getenv "PYTHONPATH")
1931 ":" (getcwd) "/build/"
1932 (car (scandir "build"
1933 (negate (cut string-prefix? "." <>))))))
1934 ;; Step out of source dir so python does not import from CWD.
1935 (with-directory-excursion "tests"
1936 (setenv "HOME" "/tmp")
1937 (invoke "make" "-C" "pysam_data")
1938 (invoke "make" "-C" "cbcf_data")
1939 ;; Running nosetests without explicitly asking for a single
1940 ;; process leads to a crash. Running with multiple processes
1941 ;; fails because the tests are not designed to run in parallel.
1943 ;; FIXME: tests keep timing out on some systems.
1944 (invoke "nosetests" "-v" "--processes" "1")))))))
1946 `(("htslib" ,htslib))) ; Included from installed header files.
1948 `(("ncurses" ,ncurses)
1952 `(("python-cython" ,python-cython)
1953 ;; Dependencies below are are for tests only.
1954 ("samtools" ,samtools)
1955 ("bcftools" ,bcftools)
1956 ("python-nose" ,python-nose)))
1957 (home-page "https://github.com/pysam-developers/pysam")
1958 (synopsis "Python bindings to the SAMtools C API")
1960 "Pysam is a Python module for reading and manipulating files in the
1961 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1962 also includes an interface for tabix.")
1963 (license license:expat)))
1965 (define-public python2-pysam
1966 (package-with-python2 python-pysam))
1968 (define-public python-twobitreader
1970 (name "python-twobitreader")
1975 (url "https://github.com/benjschiller/twobitreader")
1977 (file-name (git-file-name name version))
1980 "1qbxvv1h58cismbk1anpjrkpghsaiy64a11ir3lhy6qch6xf8n62"))))
1981 (build-system python-build-system)
1982 ;; Tests are not included
1983 (arguments '(#:tests? #f))
1985 `(("python-sphinx" ,python-sphinx)))
1986 (home-page "https://github.com/benjschiller/twobitreader")
1987 (synopsis "Python library for reading .2bit files")
1989 "twobitreader is a Python library for reading .2bit files as used by the
1990 UCSC genome browser.")
1991 (license license:artistic2.0)))
1993 (define-public python2-twobitreader
1994 (package-with-python2 python-twobitreader))
1996 (define-public python-plastid
1998 (name "python-plastid")
2002 (uri (pypi-uri "plastid" version))
2005 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
2006 (build-system python-build-system)
2008 ;; Some test files are not included.
2011 `(("python-numpy" ,python-numpy)
2012 ("python-scipy" ,python-scipy)
2013 ("python-pandas" ,python-pandas)
2014 ("python-pysam" ,python-pysam)
2015 ("python-matplotlib" ,python-matplotlib)
2016 ("python-biopython" ,python-biopython)
2017 ("python-twobitreader" ,python-twobitreader)
2018 ("python-termcolor" ,python-termcolor)))
2020 `(("python-cython" ,python-cython)
2021 ("python-nose" ,python-nose)))
2022 (home-page "https://github.com/joshuagryphon/plastid")
2023 (synopsis "Python library for genomic analysis")
2025 "plastid is a Python library for genomic analysis – in particular,
2026 high-throughput sequencing data – with an emphasis on simplicity.")
2027 (license license:bsd-3)))
2029 (define-public python2-plastid
2030 (package-with-python2 python-plastid))
2032 (define-public tetoolkit
2039 (url "https://github.com/mhammell-laboratory/tetoolkit")
2041 (file-name (git-file-name name version))
2044 "1yzi0kfpzip8zpjb82x1ik6h22yzfyjiz2dv85v6as2awwqvk807"))))
2045 (build-system python-build-system)
2047 `(#:python ,python-2 ; not guaranteed to work with Python 3
2049 (modify-phases %standard-phases
2050 (add-after 'unpack 'make-writable
2052 (for-each make-file-writable (find-files "."))
2054 (add-after 'unpack 'patch-invocations
2055 (lambda* (#:key inputs #:allow-other-keys)
2056 (substitute* '("bin/TEtranscripts"
2059 (string-append "'" (which "sort") " "))
2061 (string-append "'" (which "rm") " -f "))
2062 (("'Rscript'") (string-append "'" (which "Rscript") "'")))
2063 (substitute* "TEToolkit/IO/ReadInputs.py"
2064 (("BamToBED") (which "bamToBed")))
2065 (substitute* "TEToolkit/Normalization.py"
2067 (string-append "\"" (which "Rscript") "\"")))
2069 (add-after 'install 'wrap-program
2070 (lambda* (#:key outputs #:allow-other-keys)
2071 ;; Make sure the executables find R packages.
2072 (let ((out (assoc-ref outputs "out")))
2075 (wrap-program (string-append out "/bin/" script)
2076 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
2081 `(("coreutils" ,coreutils)
2082 ("bedtools" ,bedtools)
2083 ("python-argparse" ,python2-argparse)
2084 ("python-pysam" ,python2-pysam)
2085 ("r-minimal" ,r-minimal)
2086 ("r-deseq2" ,r-deseq2)))
2087 (home-page "https://github.com/mhammell-laboratory/tetoolkit")
2088 (synopsis "Transposable elements in differential enrichment analysis")
2090 "This is package for including transposable elements in differential
2091 enrichment analysis of sequencing datasets. TEtranscripts and TEcount take
2092 RNA-seq (and similar data) and annotates reads to both genes and transposable
2093 elements. TEtranscripts then performs differential analysis using DESeq2.
2094 Note that TEtranscripts and TEcount rely on specially curated GTF files, which
2095 are not included due to their size.")
2096 (license license:gpl3+)))
2098 (define-public cd-hit
2104 (uri (string-append "https://github.com/weizhongli/cdhit"
2105 "/releases/download/V" version
2107 "-2017-0621-source.tar.gz"))
2110 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
2111 (build-system gnu-build-system)
2113 `(#:tests? #f ; there are no tests
2115 ;; Executables are copied directly to the PREFIX.
2116 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin")
2117 ;; Support longer sequences (e.g. Pacbio sequences)
2120 (modify-phases %standard-phases
2121 ;; No "configure" script
2123 ;; Remove sources of non-determinism
2124 (add-after 'unpack 'be-timeless
2126 (substitute* "cdhit-utility.c++"
2127 ((" \\(built on \" __DATE__ \"\\)") ""))
2128 (substitute* "cdhit-common.c++"
2129 (("__DATE__") "\"0\"")
2130 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
2132 ;; The "install" target does not create the target directory.
2133 (add-before 'install 'create-target-dir
2134 (lambda* (#:key outputs #:allow-other-keys)
2135 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
2139 (home-page "http://weizhongli-lab.org/cd-hit/")
2140 (synopsis "Cluster and compare protein or nucleotide sequences")
2142 "CD-HIT is a program for clustering and comparing protein or nucleotide
2143 sequences. CD-HIT is designed to be fast and handle extremely large
2145 ;; The manual says: "It can be copied under the GNU General Public License
2146 ;; version 2 (GPLv2)."
2147 (license license:gpl2)))
2149 (define-public clipper
2156 (url "https://github.com/YeoLab/clipper")
2158 (file-name (git-file-name name version))
2161 "1bcag4lb5bkzsj2vg7lrq24aw6yfgq275ifrbhd82l7kqgbbjbkv"))))
2162 (build-system python-build-system)
2165 (modify-phases %standard-phases
2166 (add-before 'reset-gzip-timestamps 'make-files-writable
2167 (lambda* (#:key outputs #:allow-other-keys)
2168 ;; Make sure .gz files are writable so that the
2169 ;; 'reset-gzip-timestamps' phase can do its work.
2170 (let ((out (assoc-ref outputs "out")))
2171 (for-each make-file-writable
2172 (find-files out "\\.gz$"))
2176 ("python-pybedtools" ,python-pybedtools)
2177 ("python-cython" ,python-cython)
2178 ("python-scikit-learn" ,python-scikit-learn)
2179 ("python-matplotlib" ,python-matplotlib)
2180 ("python-pandas" ,python-pandas)
2181 ("python-pysam" ,python-pysam)
2182 ("python-numpy" ,python-numpy)
2183 ("python-scipy" ,python-scipy)))
2185 `(("python-setuptools-git" ,python-setuptools-git)
2186 ("python-mock" ,python-mock) ; for tests
2187 ("python-nose" ,python-nose) ; for tests
2188 ("python-pytz" ,python-pytz))) ; for tests
2189 (home-page "https://github.com/YeoLab/clipper")
2190 (synopsis "CLIP peak enrichment recognition")
2192 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
2193 (license license:gpl2)))
2195 (define-public codingquarry
2197 (name "codingquarry")
2202 "mirror://sourceforge/codingquarry/CodingQuarry_v"
2206 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
2207 (build-system gnu-build-system)
2209 '(#:tests? #f ; no "check" target
2211 (modify-phases %standard-phases
2214 (lambda* (#:key outputs #:allow-other-keys)
2215 (let* ((out (assoc-ref outputs "out"))
2216 (bin (string-append out "/bin"))
2217 (doc (string-append out "/share/doc/codingquarry")))
2218 (install-file "INSTRUCTIONS.pdf" doc)
2219 (copy-recursively "QuarryFiles"
2220 (string-append out "/QuarryFiles"))
2221 (install-file "CodingQuarry" bin)
2222 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin))
2224 (inputs `(("openmpi" ,openmpi)))
2225 (native-search-paths
2226 (list (search-path-specification
2227 (variable "QUARRY_PATH")
2228 (files '("QuarryFiles")))))
2229 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
2230 (synopsis "Fungal gene predictor")
2231 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
2232 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
2233 (home-page "https://sourceforge.net/projects/codingquarry/")
2234 (license license:gpl3+)))
2236 (define-public couger
2243 "http://couger.oit.duke.edu/static/assets/COUGER"
2247 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
2248 (build-system gnu-build-system)
2252 (modify-phases %standard-phases
2257 (lambda* (#:key outputs #:allow-other-keys)
2258 (let* ((out (assoc-ref outputs "out"))
2259 (bin (string-append out "/bin")))
2260 (copy-recursively "src" (string-append out "/src"))
2262 ;; Add "src" directory to module lookup path.
2263 (substitute* "couger"
2265 (string-append "import sys\nsys.path.append(\""
2266 out "\")\nfrom argparse")))
2267 (install-file "couger" bin))
2270 'install 'wrap-program
2271 (lambda* (#:key inputs outputs #:allow-other-keys)
2272 ;; Make sure 'couger' runs with the correct PYTHONPATH.
2273 (let* ((out (assoc-ref outputs "out"))
2274 (path (getenv "PYTHONPATH")))
2275 (wrap-program (string-append out "/bin/couger")
2276 `("PYTHONPATH" ":" prefix (,path))))
2279 `(("python" ,python-2)
2280 ("python2-pillow" ,python2-pillow)
2281 ("python2-numpy" ,python2-numpy)
2282 ("python2-scipy" ,python2-scipy)
2283 ("python2-matplotlib" ,python2-matplotlib)))
2285 `(("r-minimal" ,r-minimal)
2287 ("randomjungle" ,randomjungle)))
2289 `(("unzip" ,unzip)))
2290 (home-page "http://couger.oit.duke.edu")
2291 (synopsis "Identify co-factors in sets of genomic regions")
2293 "COUGER can be applied to any two sets of genomic regions bound by
2294 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
2295 putative co-factors that provide specificity to each TF. The framework
2296 determines the genomic targets uniquely-bound by each TF, and identifies a
2297 small set of co-factors that best explain the in vivo binding differences
2298 between the two TFs.
2300 COUGER uses classification algorithms (support vector machines and random
2301 forests) with features that reflect the DNA binding specificities of putative
2302 co-factors. The features are generated either from high-throughput TF-DNA
2303 binding data (from protein binding microarray experiments), or from large
2304 collections of DNA motifs.")
2305 (license license:gpl3+)))
2307 (define-public clustal-omega
2309 (name "clustal-omega")
2313 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
2317 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
2318 (build-system gnu-build-system)
2320 `(("argtable" ,argtable)))
2321 (home-page "http://www.clustal.org/omega/")
2322 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
2324 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
2325 program for protein and DNA/RNA. It produces high quality MSAs and is capable
2326 of handling data-sets of hundreds of thousands of sequences in reasonable
2328 (license license:gpl2+)))
2330 (define-public crossmap
2336 (uri (pypi-uri "CrossMap" version))
2339 "1sb2f2qbxya4fzw3yjl09vbrs8vfmw22zrygrvz004sf9gb1vkan"))))
2340 (build-system python-build-system)
2342 `(("python-bx-python" ,python-bx-python)
2343 ("python-numpy" ,python-numpy)
2344 ("python-pybigwig" ,python-pybigwig)
2345 ("python-pysam" ,python-pysam)
2348 `(("python-cython" ,python-cython)
2349 ("python-nose" ,python-nose)))
2350 (home-page "http://crossmap.sourceforge.net/")
2351 (synopsis "Convert genome coordinates between assemblies")
2353 "CrossMap is a program for conversion of genome coordinates or annotation
2354 files between different genome assemblies. It supports most commonly used
2355 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
2356 (license license:gpl2+)))
2358 (define-public python-dnaio
2360 (name "python-dnaio")
2365 (uri (pypi-uri "dnaio" version))
2368 "0f16m7hdlm0fz1n7y5asy0v9ghyrq17ni1p9iybq22ddzyd49r27"))))
2369 (build-system python-build-system)
2371 `(("python-cython" ,python-cython)
2372 ("python-pytest" ,python-pytest)
2373 ("python-xopen" ,python-xopen)))
2374 (home-page "https://github.com/marcelm/dnaio/")
2375 (synopsis "Read FASTA and FASTQ files efficiently")
2377 "dnaio is a Python library for fast parsing of FASTQ and also FASTA
2378 files. The code was previously part of the cutadapt tool.")
2379 (license license:expat)))
2381 (define-public python-deeptoolsintervals
2383 (name "python-deeptoolsintervals")
2387 (uri (pypi-uri "deeptoolsintervals" version))
2390 "1xnl80nblysj6dylj4683wgrfa425rkx4dp5k65hvwdns9pw753x"))))
2391 (build-system python-build-system)
2394 (home-page "https://github.com/deeptools/deeptools_intervals")
2395 (synopsis "Create GTF-based interval trees with associated meta-data")
2397 "This package provides a Python module creating/accessing GTF-based
2398 interval trees with associated meta-data. It is primarily used by the
2399 @code{deeptools} package.")
2400 (license license:expat)))
2402 (define-public python-deeptools
2404 (name "python-deeptools")
2409 (url "https://github.com/deeptools/deepTools")
2411 (file-name (git-file-name name version))
2414 "0l09vyynz6s6w7fnyd94rpys4a6aja6kp4gli64pngdxdz3md1nl"))))
2415 (build-system python-build-system)
2417 `(("python-mock" ,python-mock)
2418 ("python-nose" ,python-nose)))
2420 `(("python-matplotlib" ,python-matplotlib)
2421 ("python-numpy" ,python-numpy)
2422 ("python-numpydoc" ,python-numpydoc)
2423 ("python-py2bit" ,python-py2bit)
2424 ("python-pybigwig" ,python-pybigwig)
2425 ("python-pysam" ,python-pysam)
2426 ("python-scipy" ,python-scipy)
2427 ("python-deeptoolsintervals" ,python-deeptoolsintervals)
2428 ("python-plotly" ,python-plotly-2.4.1)))
2429 (home-page "https://pypi.org/project/deepTools/")
2430 (synopsis "Useful tools for exploring deep sequencing data")
2431 (description "This package addresses the challenge of handling large amounts
2432 of data that are now routinely generated from DNA sequencing centers.
2433 @code{deepTools} contains useful modules to process the mapped reads data for
2434 multiple quality checks, creating normalized coverage files in standard bedGraph
2435 and bigWig file formats, that allow comparison between different files. Finally,
2436 using such normalized and standardized files, deepTools can create many
2437 publication-ready visualizations to identify enrichments and for functional
2438 annotations of the genome.")
2439 ;; The file deeptools/cm.py is licensed under the BSD license. The
2440 ;; remainder of the code is licensed under the MIT license.
2441 (license (list license:bsd-3 license:expat))))
2443 (define-deprecated deeptools python-deeptools)
2445 (define-public cutadapt
2451 (uri (pypi-uri "cutadapt" version))
2454 "1vqmsfkm6llxzmsz9wcfcvzx9a9f8iabvwik2rbyn7nc4wm25z89"))))
2455 (build-system python-build-system)
2457 `(("python-dnaio" ,python-dnaio)
2458 ("python-xopen" ,python-xopen)))
2460 `(("python-cython" ,python-cython)
2461 ("python-pytest" ,python-pytest)
2462 ("python-setuptools-scm" ,python-setuptools-scm)))
2463 (home-page "https://cutadapt.readthedocs.io/en/stable/")
2464 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
2466 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
2467 other types of unwanted sequence from high-throughput sequencing reads.")
2468 (license license:expat)))
2470 (define-public libbigwig
2477 (url "https://github.com/dpryan79/libBigWig")
2479 (file-name (git-file-name name version))
2482 "09693dmf1scdac5pyq6qyn8b4mcipvnmc370k9a5z41z81m3dcsj"))))
2483 (build-system gnu-build-system)
2485 `(#:test-target "test"
2486 #:tests? #f ; tests require access to the web
2489 (string-append "prefix=" (assoc-ref %outputs "out")))
2491 (modify-phases %standard-phases
2492 (delete 'configure))))
2497 `(("doxygen" ,doxygen)
2499 ("python" ,python-2)))
2500 (home-page "https://github.com/dpryan79/libBigWig")
2501 (synopsis "C library for handling bigWig files")
2503 "This package provides a C library for parsing local and remote BigWig
2505 (license license:expat)))
2507 (define-public python-pybigwig
2509 (name "python-pybigwig")
2513 (uri (pypi-uri "pyBigWig" version))
2516 "157x6v48y299zm382krf1dw08fdxg95im8lnabhp5vc94s04zxj1"))
2517 (modules '((guix build utils)))
2520 ;; Delete bundled libBigWig sources
2521 (delete-file-recursively "libBigWig")
2523 (build-system python-build-system)
2526 (modify-phases %standard-phases
2527 (add-after 'unpack 'link-with-libBigWig
2528 (lambda* (#:key inputs #:allow-other-keys)
2529 (substitute* "setup.py"
2530 (("libs=\\[") "libs=[\"BigWig\", "))
2533 `(("python-numpy" ,python-numpy)))
2535 `(("libbigwig" ,libbigwig)
2538 (home-page "https://github.com/dpryan79/pyBigWig")
2539 (synopsis "Access bigWig files in Python using libBigWig")
2541 "This package provides Python bindings to the libBigWig library for
2542 accessing bigWig files.")
2543 (license license:expat)))
2545 (define-public python2-pybigwig
2546 (package-with-python2 python-pybigwig))
2548 (define-public python-dendropy
2550 (name "python-dendropy")
2555 ;; Source from GitHub so that tests are included.
2557 (url "https://github.com/jeetsukumaran/DendroPy")
2558 (commit (string-append "v" version))))
2559 (file-name (git-file-name name version))
2562 "097hfyv2kaf4x92i4rjx0paw2cncxap48qivv8zxng4z7nhid0x9"))))
2563 (build-system python-build-system)
2564 (home-page "https://dendropy.org/")
2565 (synopsis "Library for phylogenetics and phylogenetic computing")
2567 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
2568 writing, simulation, processing and manipulation of phylogenetic
2569 trees (phylogenies) and characters.")
2570 (license license:bsd-3)))
2572 (define-public python2-dendropy
2573 (let ((base (package-with-python2 python-dendropy)))
2578 (modify-phases %standard-phases
2579 (add-after 'unpack 'remove-failing-test
2581 ;; This test fails when the full test suite is run, as documented
2582 ;; at https://github.com/jeetsukumaran/DendroPy/issues/74
2583 (substitute* "tests/test_dataio_nexml_reader_tree_list.py"
2584 (("test_collection_comments_and_annotations")
2585 "do_not_test_collection_comments_and_annotations"))
2587 ,@(package-arguments base))))))
2589 (define-public python-py2bit
2591 (name "python-py2bit")
2596 (uri (pypi-uri "py2bit" version))
2599 "1vw2nvw1yrl7ikkqsqs1pg239yr5nspvd969r1x9arms1k25a1a5"))))
2600 (build-system python-build-system)
2601 (home-page "https://github.com/dpryan79/py2bit")
2602 (synopsis "Access 2bit files using lib2bit")
2604 "This package provides Python bindings for lib2bit to access 2bit files
2606 (license license:expat)))
2608 (define-public delly
2615 (url "https://github.com/dellytools/delly")
2616 (commit (string-append "v" version))))
2617 (file-name (git-file-name name version))
2619 (base32 "034jqsxswy9gqdh2zkgc1js99qkv75ks4xvzgmh0284sraagv61z"))
2620 (modules '((guix build utils)))
2623 (delete-file-recursively "src/htslib")
2625 (build-system gnu-build-system)
2627 `(#:tests? #f ; There are no tests to run.
2629 (list "PARALLEL=1" ; Allow parallel execution at run-time.
2630 (string-append "prefix=" (assoc-ref %outputs "out")))
2632 (modify-phases %standard-phases
2633 (delete 'configure) ; There is no configure phase.
2634 (add-after 'install 'install-templates
2635 (lambda* (#:key outputs #:allow-other-keys)
2636 (let ((templates (string-append (assoc-ref outputs "out")
2637 "/share/delly/templates")))
2639 (copy-recursively "excludeTemplates" templates)
2646 (home-page "https://github.com/dellytools/delly")
2647 (synopsis "Integrated structural variant prediction method")
2648 (description "Delly is an integrated structural variant prediction method
2649 that can discover and genotype deletions, tandem duplications, inversions and
2650 translocations at single-nucleotide resolution in short-read massively parallel
2651 sequencing data. It uses paired-ends and split-reads to sensitively and
2652 accurately delineate genomic rearrangements throughout the genome.")
2653 (license license:gpl3+)))
2655 (define-public diamond
2662 (url "https://github.com/bbuchfink/diamond")
2663 (commit (string-append "v" version))))
2664 (file-name (git-file-name name version))
2667 "0k6f3kb6cniw11xw6763kkbs1sl0yack7xsy7q5fl5v170ssphq4"))))
2668 (build-system cmake-build-system)
2670 '(#:tests? #f ; no "check" target
2672 (modify-phases %standard-phases
2673 (add-after 'unpack 'remove-native-compilation
2675 (substitute* "CMakeLists.txt" (("-march=native") ""))
2679 (home-page "https://github.com/bbuchfink/diamond")
2680 (synopsis "Accelerated BLAST compatible local sequence aligner")
2682 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2683 translated DNA query sequences against a protein reference database (BLASTP
2684 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2685 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2686 data and settings.")
2687 (license license:agpl3+)))
2689 (define-public discrover
2697 (url "https://github.com/maaskola/discrover")
2699 (file-name (git-file-name name version))
2702 "173fwi2vb6a5kp406hm3jj6j7v4whww796f2qcygp4rpvamh307y"))))
2703 (build-system cmake-build-system)
2705 `(#:tests? #f ; there are no tests
2707 (modify-phases %standard-phases
2708 (add-after 'unpack 'fix-latex-errors
2710 (with-fluids ((%default-port-encoding #f))
2711 (substitute* "doc/references.bib"
2712 (("\\{S\\}illanp[^,]+,")
2713 "{S}illanp{\\\"a}{\\\"a},")))
2714 ;; XXX: I just can't get pdflatex to not complain about these
2715 ;; characters. They end up in the manual via the generated
2716 ;; discrover-cli-help.txt.
2717 (substitute* "src/hmm/cli.cpp"
2721 ;; This seems to be a syntax error.
2722 (substitute* "doc/discrover-manual.tex"
2723 (("theverbbox\\[t\\]") "theverbbox"))
2725 (add-after 'unpack 'add-missing-includes
2727 (substitute* "src/executioninformation.hpp"
2728 (("#define EXECUTIONINFORMATION_HPP" line)
2729 (string-append line "\n#include <random>")))
2730 (substitute* "src/plasma/fasta.hpp"
2731 (("#define FASTA_HPP" line)
2732 (string-append line "\n#include <random>")))
2734 ;; FIXME: this is needed because we're using texlive-union, which
2735 ;; doesn't handle fonts correctly. It expects to be able to generate
2736 ;; fonts in the home directory.
2737 (add-before 'build 'setenv-HOME
2738 (lambda _ (setenv "HOME" "/tmp") #t)))))
2742 ("rmath-standalone" ,rmath-standalone)))
2744 `(("texlive" ,(texlive-union (list texlive-fonts-cm
2745 texlive-fonts-amsfonts
2748 texlive-latex-examplep
2749 texlive-latex-hyperref
2751 texlive-latex-natbib
2752 texlive-bibtex ; style files used by natbib
2753 texlive-latex-pgf ; tikz
2754 texlive-latex-verbatimbox)))
2755 ("imagemagick" ,imagemagick)))
2756 (home-page "https://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2757 (synopsis "Discover discriminative nucleotide sequence motifs")
2758 (description "Discrover is a motif discovery method to find binding sites
2759 of nucleic acid binding proteins.")
2760 (license license:gpl3+)))
2762 (define-public eigensoft
2770 (url "https://github.com/DReichLab/EIG")
2771 (commit (string-append "v" version))))
2772 (file-name (git-file-name name version))
2775 "1c141fqvhnzibmnf22sv23vbmzm20kjjyrib44cfh75wyndp2d9k"))
2776 (modules '((guix build utils)))
2777 ;; Remove pre-built binaries.
2779 (delete-file-recursively "bin")
2782 (build-system gnu-build-system)
2784 `(#:tests? #f ; There are no tests.
2785 #:make-flags '("CC=gcc")
2787 (modify-phases %standard-phases
2788 ;; There is no configure phase, but the Makefile is in a
2791 (lambda _ (chdir "src") #t))
2792 ;; The provided install target only copies executables to
2793 ;; the "bin" directory in the build root.
2794 (add-after 'install 'actually-install
2795 (lambda* (#:key outputs #:allow-other-keys)
2796 (let* ((out (assoc-ref outputs "out"))
2797 (bin (string-append out "/bin")))
2798 (for-each (lambda (file)
2799 (install-file file bin))
2800 (find-files "../bin" ".*"))
2805 ("openblas" ,openblas)
2807 ("gfortran" ,gfortran "lib")))
2808 (home-page "https://github.com/DReichLab/EIG")
2809 (synopsis "Tools for population genetics")
2810 (description "The EIGENSOFT package provides tools for population
2811 genetics and stratification correction. EIGENSOFT implements methods commonly
2812 used in population genetics analyses such as PCA, computation of Tracy-Widom
2813 statistics, and finding related individuals in structured populations. It
2814 comes with a built-in plotting script and supports multiple file formats and
2815 quantitative phenotypes.")
2816 ;; The license of the eigensoft tools is Expat, but since it's
2817 ;; linking with the GNU Scientific Library (GSL) the effective
2818 ;; license is the GPL.
2819 (license license:gpl3+)))
2821 (define-public edirect
2824 (version "13.3.20200128")
2827 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect"
2828 "/versions/" version
2829 "/edirect-" version ".tar.gz"))
2832 "093zp7klv81ph0y8mm8d78a9hnpfxbv2kdym70gzdf3vz176rw33"))
2833 (modules '((guix build utils)))
2835 '(begin (delete-file "Mozilla-CA.tar.gz")
2836 (substitute* "rchive.go"
2837 ;; This go library does not have any license.
2838 (("github.com/fiam/gounidecode/unidecode")
2839 "golang.org/rainycape/unidecode"))
2841 (build-system perl-build-system)
2844 (modify-phases %standard-phases
2847 (delete 'check) ; simple check after install
2848 (add-after 'unpack 'patch-programs
2849 (lambda* (#:key inputs #:allow-other-keys)
2850 ;; Ignore errors about missing xtract.Linux and rchive.Linux.
2851 (substitute* "pm-refresh"
2852 (("cat \\\"\\$target")
2853 "grep ^[[:digit:]] \"$target"))
2856 (lambda* (#:key inputs outputs #:allow-other-keys)
2857 (let ((bin (string-append (assoc-ref outputs "out") "/bin"))
2858 (edirect-go (assoc-ref inputs "edirect-go-programs")))
2861 (install-file file bin))
2862 '("archive-pubmed" "asp-cp" "asp-ls" "download-ncbi-data"
2863 "download-pubmed" "edirect.pl" "efetch" "epost" "esearch"
2864 "fetch-pubmed" "ftp-cp" "ftp-ls" "has-asp" "index-pubmed"
2865 "pm-prepare" "pm-refresh" "pm-stash" "pm-collect"
2866 "pm-index" "pm-invert" "pm-merge" "pm-promote"))
2867 (symlink (string-append edirect-go "/bin/xtract.Linux")
2868 (string-append bin "/xtract"))
2869 (symlink (string-append edirect-go "/bin/rchive.Linux")
2870 (string-append bin "/rchive")))
2872 (add-after 'install 'wrap-program
2873 (lambda* (#:key outputs #:allow-other-keys)
2874 ;; Make sure everything can run in a pure environment.
2875 (let ((out (assoc-ref outputs "out"))
2876 (path (getenv "PERL5LIB")))
2880 `("PERL5LIB" ":" prefix (,path)))
2882 `("PATH" ":" prefix (,(string-append out "/bin")
2883 ,(dirname (which "sed"))
2884 ,(dirname (which "gzip"))
2885 ,(dirname (which "grep"))
2886 ,(dirname (which "perl"))
2887 ,(dirname (which "uname"))))))
2888 (find-files out ".")))
2890 (add-after 'wrap-program 'check
2891 (lambda* (#:key outputs #:allow-other-keys)
2892 (invoke (string-append (assoc-ref outputs "out")
2897 `(("edirect-go-programs" ,edirect-go-programs)
2898 ("perl-html-parser" ,perl-html-parser)
2899 ("perl-encode-locale" ,perl-encode-locale)
2900 ("perl-file-listing" ,perl-file-listing)
2901 ("perl-html-tagset" ,perl-html-tagset)
2902 ("perl-html-tree" ,perl-html-tree)
2903 ("perl-http-cookies" ,perl-http-cookies)
2904 ("perl-http-date" ,perl-http-date)
2905 ("perl-http-message" ,perl-http-message)
2906 ("perl-http-negotiate" ,perl-http-negotiate)
2907 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2908 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2909 ("perl-net-http" ,perl-net-http)
2910 ("perl-uri" ,perl-uri)
2911 ("perl-www-robotrules" ,perl-www-robotrules)
2912 ("perl-xml-simple" ,perl-xml-simple)
2914 (home-page "https://www.ncbi.nlm.nih.gov/books/NBK179288/")
2915 (synopsis "Tools for accessing the NCBI's set of databases")
2917 "Entrez Direct (EDirect) is a method for accessing the National Center
2918 for Biotechnology Information's (NCBI) set of interconnected
2919 databases (publication, sequence, structure, gene, variation, expression,
2920 etc.) from a terminal. Functions take search terms from command-line
2921 arguments. Individual operations are combined to build multi-step queries.
2922 Record retrieval and formatting normally complete the process.
2924 EDirect also provides an argument-driven function that simplifies the
2925 extraction of data from document summaries or other results that are returned
2926 in structured XML format. This can eliminate the need for writing custom
2927 software to answer ad hoc questions.")
2928 (native-search-paths
2929 ;; Ideally this should be set for LWP somewhere.
2930 (list (search-path-specification
2931 (variable "PERL_LWP_SSL_CA_FILE")
2932 (file-type 'regular)
2934 (files '("/etc/ssl/certs/ca-certificates.crt")))))
2935 (license license:public-domain)))
2937 (define-public edirect-go-programs
2940 (name "edirect-go-programs")
2941 (build-system go-build-system)
2943 `(#:install-source? #f
2944 #:tests? #f ; No tests.
2945 #:import-path "ncbi.nlm.nih.gov/entrez/edirect"
2947 (modify-phases %standard-phases
2949 (lambda* (#:key import-path #:allow-other-keys)
2950 (with-directory-excursion (string-append "src/" import-path)
2951 (invoke "go" "build" "-v" "-x" "j2x.go")
2952 (invoke "go" "build" "-v" "-x" "t2x.go")
2953 (invoke "go" "build" "-v" "-x" "-o"
2954 "xtract.Linux" "xtract.go" "common.go")
2955 (invoke "go" "build" "-v" "-x" "-o"
2956 "rchive.Linux" "rchive.go" "common.go")
2957 (invoke "go" "build" "-v" "-x" "-o" "symbols.Linux" "s2p.go"))))
2959 (lambda* (#:key outputs import-path #:allow-other-keys)
2960 (let ((dest (string-append (assoc-ref outputs "out") "/bin"))
2961 (source (string-append "src/" import-path "/")))
2962 (for-each (lambda (file)
2963 (format #t "installing ~a~%" file)
2964 (install-file (string-append source file) dest))
2965 '("j2x" "t2x" "symbols.Linux" "xtract.Linux" "rchive.Linux"))
2968 (propagated-inputs '())
2970 `(("go-github-com-fatih-color" ,go-github-com-fatih-color)
2971 ("go-github-com-fogleman-gg" ,go-github-com-fogleman-gg)
2972 ("go-github-com-gedex-inflector" ,go-github-com-gedex-inflector)
2973 ("go-github-com-golang-freetype" ,go-github-com-golang-freetype)
2974 ("go-github-com-klauspost-cpuid" ,go-github-com-klauspost-cpuid)
2975 ("go-github-com-pbnjay-memory" ,go-github-com-pbnjay-memory)
2976 ("go-github-com-surgebase-porter2" ,go-github-com-surgebase-porter2)
2977 ("go-golang-org-rainycape-unidecode" ,go-golang-org-rainycape-unidecode)
2978 ("go-golang-org-x-image" ,go-golang-org-x-image)
2979 ("go-golang-org-x-text" ,go-golang-org-x-text)))))
2981 (define-public exonerate
2990 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2991 "exonerate-" version ".tar.gz"))
2994 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2995 (build-system gnu-build-system)
2997 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2999 `(("pkg-config" ,pkg-config)))
3003 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
3004 (synopsis "Generic tool for biological sequence alignment")
3006 "Exonerate is a generic tool for pairwise sequence comparison. It allows
3007 the alignment of sequences using a many alignment models, either exhaustive
3008 dynamic programming or a variety of heuristics.")
3009 (license license:gpl3)))
3011 (define-public express
3018 (url "https://github.com/adarob/eXpress")
3020 (file-name (git-file-name name version))
3023 "18nb22n7x820fzjngf4qgyb3mspqkw7xyk7v7s5ps6wfrd8qwscb"))))
3024 (build-system cmake-build-system)
3026 `(#:tests? #f ;no "check" target
3028 (modify-phases %standard-phases
3029 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
3030 (lambda* (#:key inputs #:allow-other-keys)
3031 (substitute* "CMakeLists.txt"
3032 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
3033 "set(Boost_USE_STATIC_LIBS OFF)")
3034 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
3035 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
3036 (substitute* "src/CMakeLists.txt"
3037 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
3038 (string-append (assoc-ref inputs "bamtools") "/lib"))
3039 (("libprotobuf.a") "libprotobuf.so"))
3041 (add-after 'unpack 'remove-update-check
3043 (substitute* "src/main.cpp"
3044 (("#include \"update_check.h\"") "")
3045 (("check_version\\(PACKAGE_VERSION\\);") ""))
3049 ("bamtools" ,bamtools)
3050 ("protobuf" ,protobuf)
3052 (home-page "http://bio.math.berkeley.edu/eXpress")
3053 (synopsis "Streaming quantification for high-throughput genomic sequencing")
3055 "eXpress is a streaming tool for quantifying the abundances of a set of
3056 target sequences from sampled subsequences. Example applications include
3057 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
3058 analysis (from RNA-Seq), transcription factor binding quantification in
3059 ChIP-Seq, and analysis of metagenomic data.")
3060 (license license:artistic2.0)))
3062 (define-public express-beta-diversity
3064 (name "express-beta-diversity")
3069 (url "https://github.com/dparks1134/ExpressBetaDiversity")
3070 (commit (string-append "v" version))))
3071 (file-name (git-file-name name version))
3074 "0s0yzg5c21349rh7x4w9266jsvnp7j1hp9cf8sk32hz8nvrj745x"))))
3075 (build-system gnu-build-system)
3078 (modify-phases %standard-phases
3080 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
3082 (lambda _ (invoke "../bin/ExpressBetaDiversity" "-u") #t))
3084 (lambda* (#:key outputs #:allow-other-keys)
3085 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3086 (install-file "../scripts/convertToEBD.py" bin)
3087 (install-file "../bin/ExpressBetaDiversity" bin)
3090 `(("python" ,python-2)))
3091 (home-page "https://github.com/dparks1134/ExpressBetaDiversity")
3092 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
3094 "Express Beta Diversity (EBD) calculates ecological beta diversity
3095 (dissimilarity) measures between biological communities. EBD implements a
3096 variety of diversity measures including those that make use of phylogenetic
3097 similarity of community members.")
3098 (license license:gpl3+)))
3100 (define-public fasttree
3107 "http://www.microbesonline.org/fasttree/FastTree-"
3111 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
3112 (build-system gnu-build-system)
3114 `(#:tests? #f ; no "check" target
3116 (modify-phases %standard-phases
3120 (lambda* (#:key source #:allow-other-keys)
3123 "-finline-functions"
3134 "-finline-functions"
3143 (lambda* (#:key outputs #:allow-other-keys)
3144 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3145 (install-file "FastTree" bin)
3146 (install-file "FastTreeMP" bin)
3148 (home-page "http://www.microbesonline.org/fasttree")
3149 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
3151 "FastTree can handle alignments with up to a million of sequences in a
3152 reasonable amount of time and memory. For large alignments, FastTree is
3153 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
3154 (license license:gpl2+)))
3156 (define-public fastx-toolkit
3158 (name "fastx-toolkit")
3164 "https://github.com/agordon/fastx_toolkit/releases/download/"
3165 version "/fastx_toolkit-" version ".tar.bz2"))
3168 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
3169 (build-system gnu-build-system)
3171 `(("libgtextutils" ,libgtextutils)))
3173 `(("gcc" ,gcc-6) ;; doesn't build with later versions
3174 ("pkg-config" ,pkg-config)))
3175 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
3176 (synopsis "Tools for FASTA/FASTQ file preprocessing")
3178 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
3179 FASTA/FASTQ files preprocessing.
3181 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
3182 containing multiple short-reads sequences. The main processing of such
3183 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
3184 is sometimes more productive to preprocess the files before mapping the
3185 sequences to the genome---manipulating the sequences to produce better mapping
3186 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
3187 (license license:agpl3+)))
3189 (define-public flexbar
3196 (url "https://github.com/seqan/flexbar")
3197 (commit (string-append "v" version))))
3198 (file-name (git-file-name name version))
3201 "1pq9sxvdnldl14libk234m72dqhwgzs3acgl943wchwdqlcsi5r2"))))
3202 (build-system cmake-build-system)
3205 (modify-phases %standard-phases
3206 (add-after 'unpack 'do-not-tune-to-CPU
3208 (substitute* "src/CMakeLists.txt"
3209 ((" -march=native") ""))
3212 (lambda* (#:key outputs #:allow-other-keys)
3213 (setenv "PATH" (string-append (getcwd) ":" (getenv "PATH")))
3214 (with-directory-excursion "../source/test"
3215 (invoke "bash" "flexbar_test.sh"))
3218 (lambda* (#:key outputs #:allow-other-keys)
3219 (let* ((out (string-append (assoc-ref outputs "out")))
3220 (bin (string-append out "/bin/")))
3221 (install-file "flexbar" bin))
3227 `(("pkg-config" ,pkg-config)
3229 (home-page "https://github.com/seqan/flexbar")
3230 (synopsis "Barcode and adapter removal tool for sequencing platforms")
3232 "Flexbar preprocesses high-throughput nucleotide sequencing data
3233 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
3234 Moreover, trimming and filtering features are provided. Flexbar increases
3235 read mapping rates and improves genome and transcriptome assemblies. It
3236 supports next-generation sequencing data in fasta/q and csfasta/q format from
3237 Illumina, Roche 454, and the SOLiD platform.")
3238 (license license:bsd-3)))
3240 (define-public fraggenescan
3242 (name "fraggenescan")
3248 (string-append "mirror://sourceforge/fraggenescan/"
3249 "FragGeneScan" version ".tar.gz"))
3251 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
3252 (build-system gnu-build-system)
3255 (modify-phases %standard-phases
3257 (add-before 'build 'patch-paths
3258 (lambda* (#:key outputs #:allow-other-keys)
3259 (let* ((out (string-append (assoc-ref outputs "out")))
3260 (share (string-append out "/share/fraggenescan/")))
3261 (substitute* "run_FragGeneScan.pl"
3263 (string-append "system(\"" (which "rm")))
3265 (string-append "system(\"" (which "mv")))
3266 (("\\\"awk") (string-append "\"" (which "awk")))
3267 ;; This script and other programs expect the training files
3268 ;; to be in the non-standard location bin/train/XXX. Change
3269 ;; this to be share/fraggenescan/train/XXX instead.
3270 (("^\\$train.file = \\$dir.*")
3271 (string-append "$train_file = \""
3273 "train/\".$FGS_train_file;")))
3274 (substitute* "run_hmm.c"
3275 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
3276 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
3280 (invoke "make" "clean")
3281 (invoke "make" "fgs")
3284 (lambda* (#:key outputs #:allow-other-keys)
3285 (let* ((out (string-append (assoc-ref outputs "out")))
3286 (bin (string-append out "/bin/"))
3287 (share (string-append out "/share/fraggenescan/train")))
3288 (install-file "run_FragGeneScan.pl" bin)
3289 (install-file "FragGeneScan" bin)
3290 (copy-recursively "train" share))
3293 (add-after 'install 'post-install-check
3294 ;; In lieu of 'make check', run one of the examples and check the
3295 ;; output files gets created.
3296 (lambda* (#:key outputs #:allow-other-keys)
3297 (let* ((out (string-append (assoc-ref outputs "out")))
3298 (bin (string-append out "/bin/"))
3299 (frag (string-append bin "run_FragGeneScan.pl")))
3300 ;; Test complete genome.
3302 "-genome=./example/NC_000913.fna"
3306 (unless (and (file-exists? "test2.faa")
3307 (file-exists? "test2.ffn")
3308 (file-exists? "test2.gff")
3309 (file-exists? "test2.out"))
3310 (error "Expected files do not exist."))
3311 ;; Test incomplete sequences.
3313 "-genome=./example/NC_000913-fgs.ffn"
3320 ("python" ,python-2))) ;not compatible with python 3.
3321 (home-page "https://sourceforge.net/projects/fraggenescan/")
3322 (synopsis "Finds potentially fragmented genes in short reads")
3324 "FragGeneScan is a program for predicting bacterial and archaeal genes in
3325 short and error-prone DNA sequencing reads. It can also be applied to predict
3326 genes in incomplete assemblies or complete genomes.")
3327 ;; GPL3+ according to private correspondense with the authors.
3328 (license license:gpl3+)))
3330 (define-public fxtract
3331 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
3339 (url "https://github.com/ctSkennerton/fxtract")
3341 (file-name (git-file-name name version))
3344 "0hab3gpwf4w9s87qlbswq6ws1qqybh4dcqk79q1ahyldzai5fgp5"))))
3345 (build-system gnu-build-system)
3347 `(#:make-flags (list
3348 (string-append "PREFIX=" (assoc-ref %outputs "out"))
3350 #:test-target "fxtract_test"
3352 (modify-phases %standard-phases
3354 (add-before 'build 'copy-util
3355 (lambda* (#:key inputs #:allow-other-keys)
3357 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
3359 ;; Do not use make install as this requires additional dependencies.
3361 (lambda* (#:key outputs #:allow-other-keys)
3362 (let* ((out (assoc-ref outputs "out"))
3363 (bin (string-append out"/bin")))
3364 (install-file "fxtract" bin)
3370 ;; ctskennerton-util is licensed under GPL2.
3371 `(("ctskennerton-util"
3375 (url "https://github.com/ctSkennerton/util")
3376 (commit util-commit)))
3377 (file-name (string-append
3378 "ctstennerton-util-" util-commit "-checkout"))
3381 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
3382 (home-page "https://github.com/ctSkennerton/fxtract")
3383 (synopsis "Extract sequences from FASTA and FASTQ files")
3385 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
3386 or FASTQ) file given a subsequence. It uses a simple substring search for
3387 basic tasks but can change to using POSIX regular expressions, PCRE, hash
3388 lookups or multi-pattern searching as required. By default fxtract looks in
3389 the sequence of each record but can also be told to look in the header,
3390 comment or quality sections.")
3391 ;; 'util' requires SSE instructions.
3392 (supported-systems '("x86_64-linux"))
3393 (license license:expat))))
3395 (define-public gemma
3402 (url "https://github.com/xiangzhou/GEMMA")
3403 (commit (string-append "v" version))))
3404 (file-name (git-file-name name version))
3407 "1s3ncnbn45r2hh1cvrqky1kbqq6546biypr4f5mkw1kqlrgyh0yg"))))
3410 ("gfortran" ,gfortran "lib")
3413 ("openblas" ,openblas)
3415 (build-system gnu-build-system)
3418 '(,@(match (%current-system)
3420 '("FORCE_DYNAMIC=1"))
3422 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
3424 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
3426 (modify-phases %standard-phases
3428 (add-after 'unpack 'find-eigen
3429 (lambda* (#:key inputs #:allow-other-keys)
3430 ;; Ensure that Eigen headers can be found
3431 (setenv "CPLUS_INCLUDE_PATH"
3432 (string-append (assoc-ref inputs "eigen")
3435 (add-before 'build 'bin-mkdir
3440 (lambda* (#:key outputs #:allow-other-keys)
3441 (let ((out (assoc-ref outputs "out")))
3442 (install-file "bin/gemma"
3446 #:tests? #f)) ; no tests included yet
3447 (home-page "https://github.com/xiangzhou/GEMMA")
3448 (synopsis "Tool for genome-wide efficient mixed model association")
3450 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
3451 standard linear mixed model resolver with application in genome-wide
3452 association studies (GWAS).")
3453 (license license:gpl3)))
3462 (url "https://github.com/nboley/grit")
3464 (file-name (git-file-name name version))
3467 "1l5v8vfvfbrpmgnrvbrbv40d0arhxcnmxgv2f1mlcqfa3q6bkqm9"))))
3468 (build-system python-build-system)
3470 `(#:python ,python-2
3472 (modify-phases %standard-phases
3473 (add-after 'unpack 'generate-from-cython-sources
3474 (lambda* (#:key inputs outputs #:allow-other-keys)
3475 ;; Delete these C files to force fresh generation from pyx sources.
3476 (delete-file "grit/sparsify_support_fns.c")
3477 (delete-file "grit/call_peaks_support_fns.c")
3478 (substitute* "setup.py"
3479 (("Cython.Setup") "Cython.Build"))
3482 `(("python-scipy" ,python2-scipy)
3483 ("python-numpy" ,python2-numpy)
3484 ("python-pysam" ,python2-pysam)
3485 ("python-networkx" ,python2-networkx)))
3487 `(("python-cython" ,python2-cython)))
3488 ;; The canonical <http://grit-bio.org> home page times out as of 2020-01-21.
3489 (home-page "https://github.com/nboley/grit")
3490 (synopsis "Tool for integrative analysis of RNA-seq type assays")
3492 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
3493 full length transcript models. When none of these data sources are available,
3494 GRIT can be run by providing a candidate set of TES or TSS sites. In
3495 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
3496 also be run in quantification mode, where it uses a provided GTF file and just
3497 estimates transcript expression.")
3498 (license license:gpl3+)))
3500 (define-public hisat
3507 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
3508 version "-beta-source.zip"))
3511 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
3512 (build-system gnu-build-system)
3514 `(#:tests? #f ;no check target
3515 #:make-flags '("allall"
3516 ;; Disable unsupported `popcnt' instructions on
3517 ;; architectures other than x86_64
3518 ,@(if (string-prefix? "x86_64"
3519 (or (%current-target-system)
3522 '("POPCNT_CAPABILITY=0")))
3524 (modify-phases %standard-phases
3525 (add-after 'unpack 'patch-sources
3527 ;; XXX Cannot use snippet because zip files are not supported
3528 (substitute* "Makefile"
3529 (("^CC = .*$") "CC = gcc")
3530 (("^CPP = .*$") "CPP = g++")
3531 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
3532 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
3533 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
3534 (substitute* '("hisat-build" "hisat-inspect")
3535 (("/usr/bin/env") (which "env")))
3538 (lambda* (#:key outputs #:allow-other-keys)
3539 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
3540 (for-each (lambda (file)
3541 (install-file file bin))
3544 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
3546 (delete 'configure))))
3548 `(("unzip" ,unzip)))
3553 ;; Non-portable SSE instructions are used so building fails on platforms
3554 ;; other than x86_64.
3555 (supported-systems '("x86_64-linux"))
3556 (home-page "https://ccb.jhu.edu/software/hisat/index.shtml")
3557 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
3559 "HISAT is a fast and sensitive spliced alignment program for mapping
3560 RNA-seq reads. In addition to one global FM index that represents a whole
3561 genome, HISAT uses a large set of small FM indexes that collectively cover the
3562 whole genome. These small indexes (called local indexes) combined with
3563 several alignment strategies enable effective alignment of RNA-seq reads, in
3564 particular, reads spanning multiple exons.")
3565 (license license:gpl3+)))
3567 (define-public hisat2
3574 (uri (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
3575 "/downloads/hisat2-" version "-source.zip"))
3578 "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"))))
3579 (build-system gnu-build-system)
3581 `(#:tests? #f ; no check target
3582 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
3583 #:modules ((guix build gnu-build-system)
3587 (modify-phases %standard-phases
3588 (add-after 'unpack 'make-deterministic
3590 (substitute* "Makefile"
3595 (lambda* (#:key outputs #:allow-other-keys)
3596 (let* ((out (assoc-ref outputs "out"))
3597 (bin (string-append out "/bin/"))
3598 (doc (string-append out "/share/doc/hisat2/")))
3600 (cut install-file <> bin)
3602 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
3604 (install-file "doc/manual.inc.html" doc))
3607 `(("unzip" ,unzip) ; needed for archive from ftp
3609 ("pandoc" ,ghc-pandoc))) ; for documentation
3610 (home-page "https://ccb.jhu.edu/software/hisat2/index.shtml")
3611 (synopsis "Graph-based alignment of genomic sequencing reads")
3612 (description "HISAT2 is a fast and sensitive alignment program for mapping
3613 next-generation sequencing reads (both DNA and RNA) to a population of human
3614 genomes (as well as to a single reference genome). In addition to using one
3615 global @dfn{graph FM} (GFM) index that represents a population of human
3616 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
3617 the whole genome. These small indexes, combined with several alignment
3618 strategies, enable rapid and accurate alignment of sequencing reads. This new
3619 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
3620 ;; HISAT2 contains files from Bowtie2, which is released under
3621 ;; GPLv2 or later. The HISAT2 source files are released under
3623 (license license:gpl3+)))
3625 (define-public hmmer
3633 "http://eddylab.org/software/hmmer/hmmer-" version ".tar.gz"))
3636 "171bivy6xhgjsz5nv53n81pc3frnwz29ylblawk2bv46szwjjqd5"))))
3637 (build-system gnu-build-system)
3638 (native-inputs `(("perl" ,perl)))
3639 (home-page "http://hmmer.org/")
3640 (synopsis "Biosequence analysis using profile hidden Markov models")
3642 "HMMER is used for searching sequence databases for homologs of protein
3643 sequences, and for making protein sequence alignments. It implements methods
3644 using probabilistic models called profile hidden Markov models (profile
3646 ;; hmmer uses non-portable SSE intrinsics so building fails on other
3648 (supported-systems '("x86_64-linux" "i686-linux"))
3649 (license license:bsd-3)))
3651 (define-public htseq
3657 (uri (pypi-uri "HTSeq" version))
3660 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
3661 (build-system python-build-system)
3663 `(("python-cython" ,python-cython)))
3664 ;; Numpy needs to be propagated when htseq is used as a Python library.
3666 `(("python-numpy" ,python-numpy)))
3668 `(("python-pysam" ,python-pysam)
3669 ("python-matplotlib" ,python-matplotlib)))
3670 (home-page "https://htseq.readthedocs.io/")
3671 (synopsis "Analysing high-throughput sequencing data with Python")
3673 "HTSeq is a Python package that provides infrastructure to process data
3674 from high-throughput sequencing assays.")
3675 (license license:gpl3+)))
3677 (define-public python2-htseq
3678 (package-with-python2 htseq))
3680 (define-public java-htsjdk
3682 (name "java-htsjdk")
3683 (version "2.3.0") ; last version without build dependency on gradle
3687 (url "https://github.com/samtools/htsjdk")
3689 (file-name (git-file-name name version))
3692 "1b178ixcabanm834ydjl3jiakpyxdmki32hqfv2abrzn3rcwa28i"))
3693 (modules '((guix build utils)))
3695 ;; Delete pre-built binaries
3697 (delete-file-recursively "lib")
3700 (build-system ant-build-system)
3702 `(#:tests? #f ; test require Internet access
3705 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3706 "/share/java/htsjdk/"))
3707 #:build-target "all"
3709 (modify-phases %standard-phases
3710 ;; The build phase also installs the jars
3711 (delete 'install))))
3713 `(("java-ngs" ,java-ngs)
3714 ("java-snappy-1" ,java-snappy-1)
3715 ("java-commons-compress" ,java-commons-compress)
3716 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3717 ("java-commons-jexl-2" ,java-commons-jexl-2)
3718 ("java-xz" ,java-xz)))
3720 `(("java-testng" ,java-testng)))
3721 (home-page "http://samtools.github.io/htsjdk/")
3722 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3724 "HTSJDK is an implementation of a unified Java library for accessing
3725 common file formats, such as SAM and VCF, used for high-throughput
3726 sequencing (HTS) data. There are also an number of useful utilities for
3727 manipulating HTS data.")
3728 (license license:expat)))
3730 (define-public java-htsjdk-latest
3732 (name "java-htsjdk")
3737 (url "https://github.com/samtools/htsjdk")
3739 (file-name (string-append name "-" version "-checkout"))
3742 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
3743 (build-system ant-build-system)
3745 `(#:tests? #f ; test require Scala
3747 #:jar-name "htsjdk.jar"
3749 (modify-phases %standard-phases
3750 (add-after 'unpack 'remove-useless-build.xml
3751 (lambda _ (delete-file "build.xml") #t))
3752 ;; The tests require the scalatest package.
3753 (add-after 'unpack 'remove-tests
3754 (lambda _ (delete-file-recursively "src/test") #t)))))
3756 `(("java-ngs" ,java-ngs)
3757 ("java-snappy-1" ,java-snappy-1)
3758 ("java-commons-compress" ,java-commons-compress)
3759 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3760 ("java-commons-jexl-2" ,java-commons-jexl-2)
3761 ("java-xz" ,java-xz)))
3763 `(("java-junit" ,java-junit)))
3764 (home-page "http://samtools.github.io/htsjdk/")
3765 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3767 "HTSJDK is an implementation of a unified Java library for accessing
3768 common file formats, such as SAM and VCF, used for high-throughput
3769 sequencing (HTS) data. There are also an number of useful utilities for
3770 manipulating HTS data.")
3771 (license license:expat)))
3773 ;; This is needed for picard 2.10.3
3774 (define-public java-htsjdk-2.10.1
3775 (package (inherit java-htsjdk-latest)
3776 (name "java-htsjdk")
3781 (url "https://github.com/samtools/htsjdk")
3783 (file-name (string-append name "-" version "-checkout"))
3786 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
3787 (build-system ant-build-system)
3789 `(#:tests? #f ; tests require Scala
3791 #:jar-name "htsjdk.jar"
3793 (modify-phases %standard-phases
3794 (add-after 'unpack 'remove-useless-build.xml
3795 (lambda _ (delete-file "build.xml") #t))
3796 ;; The tests require the scalatest package.
3797 (add-after 'unpack 'remove-tests
3798 (lambda _ (delete-file-recursively "src/test") #t)))))))
3800 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3801 ;; recent version of java-htsjdk, which depends on gradle.
3802 (define-public java-picard
3804 (name "java-picard")
3809 (url "https://github.com/broadinstitute/picard")
3811 (file-name (string-append "java-picard-" version "-checkout"))
3814 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3815 (modules '((guix build utils)))
3818 ;; Delete pre-built binaries.
3819 (delete-file-recursively "lib")
3821 (substitute* "build.xml"
3822 ;; Remove build-time dependency on git.
3823 (("failifexecutionfails=\"true\"")
3824 "failifexecutionfails=\"false\"")
3826 (("depends=\"compile-htsjdk, ")
3828 (("depends=\"compile-htsjdk-tests, ")
3830 ;; Build picard-lib.jar before building picard.jar
3831 (("name=\"picard-jar\" depends=\"" line)
3832 (string-append line "picard-lib-jar, ")))
3834 (build-system ant-build-system)
3836 `(#:build-target "picard-jar"
3837 #:test-target "test"
3838 ;; Tests require jacoco:coverage.
3841 (list (string-append "-Dhtsjdk_lib_dir="
3842 (assoc-ref %build-inputs "java-htsjdk")
3843 "/share/java/htsjdk/")
3844 "-Dhtsjdk-classes=dist/tmp"
3845 (string-append "-Dhtsjdk-version="
3846 ,(package-version java-htsjdk)))
3849 (modify-phases %standard-phases
3850 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3851 (delete 'generate-jar-indices)
3852 (add-after 'unpack 'use-our-htsjdk
3853 (lambda* (#:key inputs #:allow-other-keys)
3854 (substitute* "build.xml"
3855 (("\\$\\{htsjdk\\}/lib")
3856 (string-append (assoc-ref inputs "java-htsjdk")
3857 "/share/java/htsjdk/")))
3859 (add-after 'unpack 'make-test-target-independent
3860 (lambda* (#:key inputs #:allow-other-keys)
3861 (substitute* "build.xml"
3862 (("name=\"test\" depends=\"compile, ")
3863 "name=\"test\" depends=\""))
3865 (replace 'install (install-jars "dist")))))
3867 `(("java-htsjdk" ,java-htsjdk)
3868 ("java-guava" ,java-guava)))
3870 `(("java-testng" ,java-testng)))
3871 (home-page "http://broadinstitute.github.io/picard/")
3872 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3873 (description "Picard is a set of Java command line tools for manipulating
3874 high-throughput sequencing (HTS) data and formats. Picard is implemented
3875 using the HTSJDK Java library to support accessing file formats that are
3876 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3878 (license license:expat)))
3880 ;; This is needed for dropseq-tools
3881 (define-public java-picard-2.10.3
3883 (name "java-picard")
3888 (url "https://github.com/broadinstitute/picard")
3890 (file-name (string-append "java-picard-" version "-checkout"))
3893 "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi"))))
3894 (build-system ant-build-system)
3896 `(#:jar-name "picard.jar"
3897 ;; Tests require jacoco:coverage.
3900 #:main-class "picard.cmdline.PicardCommandLine"
3901 #:modules ((guix build ant-build-system)
3903 (guix build java-utils)
3908 (modify-phases %standard-phases
3909 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3910 (delete 'generate-jar-indices)
3911 (add-after 'unpack 'remove-useless-build.xml
3912 (lambda _ (delete-file "build.xml") #t))
3913 ;; This is necessary to ensure that htsjdk is found when using
3914 ;; picard.jar as an executable.
3915 (add-before 'build 'edit-classpath-in-manifest
3916 (lambda* (#:key inputs #:allow-other-keys)
3917 (chmod "build.xml" #o664)
3918 (call-with-output-file "build.xml.new"
3922 (with-input-from-file "build.xml"
3923 (lambda _ (xml->sxml #:trim-whitespace? #t)))
3924 `((target . ,(lambda (tag . kids)
3925 (let ((name ((sxpath '(name *text*))
3927 ;; FIXME: We're breaking the line
3928 ;; early with a dummy path to
3929 ;; ensure that the store reference
3930 ;; isn't broken apart and can still
3931 ;; be found by the reference
3936 ~a/share/java/htsjdk.jar${line.separator}${line.separator}"
3937 ;; maximum line length is 70
3938 (string-tabulate (const #\b) 57)
3939 (assoc-ref inputs "java-htsjdk"))))
3940 (if (member "manifest" name)
3943 (@ (file "${manifest.file}")
3944 (match "\\r\\n\\r\\n")
3945 (replace "${line.separator}")))
3948 (file "${manifest.file}")
3951 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
3952 (*text* . ,(lambda (_ txt) txt))))
3954 (rename-file "build.xml.new" "build.xml")
3957 `(("java-htsjdk" ,java-htsjdk-2.10.1)))
3959 `(("java-testng" ,java-testng)
3960 ("java-guava" ,java-guava)))
3961 (home-page "http://broadinstitute.github.io/picard/")
3962 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3963 (description "Picard is a set of Java command line tools for manipulating
3964 high-throughput sequencing (HTS) data and formats. Picard is implemented
3965 using the HTSJDK Java library to support accessing file formats that are
3966 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3968 (license license:expat)))
3970 ;; This is the last version of Picard to provide net.sf.samtools
3971 (define-public java-picard-1.113
3972 (package (inherit java-picard)
3973 (name "java-picard")
3978 (url "https://github.com/broadinstitute/picard")
3980 (file-name (string-append "java-picard-" version "-checkout"))
3983 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
3984 (modules '((guix build utils)))
3987 ;; Delete pre-built binaries.
3988 (delete-file-recursively "lib")
3991 (build-system ant-build-system)
3993 `(#:build-target "picard-jar"
3994 #:test-target "test"
3995 ;; FIXME: the class path at test time is wrong.
3996 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
3997 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
4000 ;; This is only used for tests.
4002 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
4004 (modify-phases %standard-phases
4005 ;; FIXME: This phase fails.
4006 (delete 'generate-jar-indices)
4007 ;; Do not use bundled ant bzip2.
4008 (add-after 'unpack 'use-ant-bzip
4009 (lambda* (#:key inputs #:allow-other-keys)
4010 (substitute* "build.xml"
4011 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
4012 (string-append (assoc-ref inputs "ant")
4015 (add-after 'unpack 'make-test-target-independent
4016 (lambda* (#:key inputs #:allow-other-keys)
4017 (substitute* "build.xml"
4018 (("name=\"test\" depends=\"compile, ")
4019 "name=\"test\" depends=\"compile-tests, ")
4020 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
4021 "name=\"compile\" depends=\"compile-src\""))
4023 (add-after 'unpack 'fix-deflater-path
4024 (lambda* (#:key outputs #:allow-other-keys)
4025 (substitute* "src/java/net/sf/samtools/Defaults.java"
4026 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
4027 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
4028 (assoc-ref outputs "out")
4029 "/lib/jni/libIntelDeflater.so"
4032 ;; Build the deflater library, because we've previously deleted the
4033 ;; pre-built one. This can only be built with access to the JDK
4035 (add-after 'build 'build-jni
4036 (lambda* (#:key inputs #:allow-other-keys)
4039 (invoke "tar" "--strip-components=1" "-C" "jdk-src"
4040 "-xf" (assoc-ref inputs "jdk-src"))
4041 (invoke "javah" "-jni"
4042 "-classpath" "classes"
4044 "net.sf.samtools.util.zip.IntelDeflater")
4045 (with-directory-excursion "src/c/inteldeflater"
4046 (invoke "gcc" "-I../../../lib" "-I."
4047 (string-append "-I" (assoc-ref inputs "jdk")
4049 "-I../../../jdk-src/src/share/native/common/"
4050 "-I../../../jdk-src/src/solaris/native/common/"
4051 "-c" "-O3" "-fPIC" "IntelDeflater.c")
4052 (invoke "gcc" "-shared"
4053 "-o" "../../../lib/jni/libIntelDeflater.so"
4054 "IntelDeflater.o" "-lz" "-lstdc++"))
4056 ;; We can only build everything else after building the JNI library.
4057 (add-after 'build-jni 'build-rest
4058 (lambda* (#:key make-flags #:allow-other-keys)
4059 (apply invoke `("ant" "all" ,@make-flags))
4061 (add-before 'build 'set-JAVA6_HOME
4063 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
4065 (replace 'install (install-jars "dist"))
4066 (add-after 'install 'install-jni-lib
4067 (lambda* (#:key outputs #:allow-other-keys)
4068 (let ((jni (string-append (assoc-ref outputs "out")
4071 (install-file "lib/jni/libIntelDeflater.so" jni)
4074 `(("java-snappy-1" ,java-snappy-1)
4075 ("java-commons-jexl-2" ,java-commons-jexl-2)
4076 ("java-cofoja" ,java-cofoja)
4077 ("ant" ,ant) ; for bzip2 support at runtime
4080 `(("ant-apache-bcel" ,ant-apache-bcel)
4081 ("ant-junit" ,ant-junit)
4082 ("java-testng" ,java-testng)
4083 ("java-commons-bcel" ,java-commons-bcel)
4084 ("java-jcommander" ,java-jcommander)
4085 ("jdk" ,icedtea-8 "jdk")
4086 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
4088 (define-public fastqc
4095 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
4096 "projects/fastqc/fastqc_v"
4097 version "_source.zip"))
4100 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
4101 (build-system ant-build-system)
4103 `(#:tests? #f ; there are no tests
4104 #:build-target "build"
4106 (modify-phases %standard-phases
4107 (add-after 'unpack 'fix-dependencies
4108 (lambda* (#:key inputs #:allow-other-keys)
4109 (substitute* "build.xml"
4111 (string-append (assoc-ref inputs "java-jbzip2")
4112 "/share/java/jbzip2.jar"))
4114 (string-append (assoc-ref inputs "java-picard-1.113")
4115 "/share/java/sam-1.112.jar"))
4117 (string-append (assoc-ref inputs "java-cisd-jhdf5")
4118 "/share/java/sis-jhdf5.jar")))
4120 ;; There is no installation target
4122 (lambda* (#:key inputs outputs #:allow-other-keys)
4123 (let* ((out (assoc-ref outputs "out"))
4124 (bin (string-append out "/bin"))
4125 (share (string-append out "/share/fastqc/"))
4126 (exe (string-append share "/fastqc")))
4127 (for-each mkdir-p (list bin share))
4128 (copy-recursively "bin" share)
4130 (("my \\$java_bin = 'java';")
4131 (string-append "my $java_bin = '"
4132 (assoc-ref inputs "java")
4135 (symlink exe (string-append bin "/fastqc"))
4139 ("perl" ,perl) ; needed for the wrapper script
4140 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
4141 ("java-picard-1.113" ,java-picard-1.113)
4142 ("java-jbzip2" ,java-jbzip2)))
4144 `(("unzip" ,unzip)))
4145 (home-page "https://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
4146 (synopsis "Quality control tool for high throughput sequence data")
4148 "FastQC aims to provide a simple way to do some quality control
4149 checks on raw sequence data coming from high throughput sequencing
4150 pipelines. It provides a modular set of analyses which you can use to
4151 give a quick impression of whether your data has any problems of which
4152 you should be aware before doing any further analysis.
4154 The main functions of FastQC are:
4157 @item Import of data from BAM, SAM or FastQ files (any variant);
4158 @item Providing a quick overview to tell you in which areas there may
4160 @item Summary graphs and tables to quickly assess your data;
4161 @item Export of results to an HTML based permanent report;
4162 @item Offline operation to allow automated generation of reports
4163 without running the interactive application.
4165 (license license:gpl3+)))
4167 (define-public fastp
4175 (url "https://github.com/OpenGene/fastp")
4176 (commit (string-append "v" version))))
4177 (file-name (git-file-name name version))
4180 "1r6ms5zbf5rps4rgp4z73nczadl00b5rqylw8f684isfz27dp0xh"))))
4181 (build-system gnu-build-system)
4183 `(#:tests? #f ; there are none
4185 (list (string-append "BINDIR=" (assoc-ref %outputs "out") "/bin"))
4187 (modify-phases %standard-phases
4189 (add-before 'install 'create-target-dir
4190 (lambda* (#:key outputs #:allow-other-keys)
4191 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4195 (home-page "https://github.com/OpenGene/fastp/")
4196 (synopsis "All-in-one FastQ preprocessor")
4198 "Fastp is a tool designed to provide fast all-in-one preprocessing for
4199 FastQ files. This tool has multi-threading support to afford high
4201 (license license:expat)))
4203 (define-public htslib
4210 "https://github.com/samtools/htslib/releases/download/"
4211 version "/htslib-" version ".tar.bz2"))
4214 "16ljv43sc3fxmv63w7b2ff8m1s7h89xhazwmbm1bicz8axq8fjz0"))))
4215 (build-system gnu-build-system)
4218 ("openssl" ,openssl)))
4219 ;; This is referred to in the pkg-config file as a required library.
4224 (home-page "https://www.htslib.org")
4225 (synopsis "C library for reading/writing high-throughput sequencing data")
4227 "HTSlib is a C library for reading/writing high-throughput sequencing
4228 data. It also provides the @command{bgzip}, @command{htsfile}, and
4229 @command{tabix} utilities.")
4230 ;; Files under cram/ are released under the modified BSD license;
4231 ;; the rest is released under the Expat license
4232 (license (list license:expat license:bsd-3))))
4234 ;; This package should be removed once no packages rely upon it.
4242 "https://github.com/samtools/htslib/releases/download/"
4243 version "/htslib-" version ".tar.bz2"))
4246 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
4255 (url "https://github.com/nboley/idr")
4257 (file-name (git-file-name name version))
4260 "04j876h6z444v2q79drxx283d3k5snd72kj895wbalnl42206x9g"))
4261 ;; Delete generated C code.
4263 '(begin (delete-file "idr/inv_cdf.c") #t))))
4264 (build-system python-build-system)
4265 ;; There is only one test ("test_inv_cdf.py") and it tests features that
4266 ;; are no longer part of this package. It also asserts False, which
4267 ;; causes the tests to always fail.
4268 (arguments `(#:tests? #f))
4270 `(("python-scipy" ,python-scipy)
4271 ("python-sympy" ,python-sympy)
4272 ("python-numpy" ,python-numpy)
4273 ("python-matplotlib" ,python-matplotlib)))
4275 `(("python-cython" ,python-cython)))
4276 (home-page "https://github.com/nboley/idr")
4277 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
4279 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
4280 to measure the reproducibility of findings identified from replicate
4281 experiments and provide highly stable thresholds based on reproducibility.")
4282 (license license:gpl2+)))
4284 (define-public jellyfish
4290 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
4291 "releases/download/v" version
4292 "/jellyfish-" version ".tar.gz"))
4295 "1k4pc3fvv6w1km2yph4m5sd78fbxp21d6xyzgmy0gjihzc6mb249"))))
4296 (build-system gnu-build-system)
4297 (outputs '("out" ;for library
4298 "ruby" ;for Ruby bindings
4299 "python")) ;for Python bindings
4302 (list (string-append "--enable-ruby-binding="
4303 (assoc-ref %outputs "ruby"))
4304 (string-append "--enable-python-binding="
4305 (assoc-ref %outputs "python")))
4307 (modify-phases %standard-phases
4308 (add-before 'check 'set-SHELL-variable
4310 ;; generator_manager.hpp either uses /bin/sh or $SHELL
4312 (setenv "SHELL" (which "bash"))
4318 ("python" ,python-2)
4319 ("pkg-config" ,pkg-config)))
4321 `(("htslib" ,htslib)))
4322 (synopsis "Tool for fast counting of k-mers in DNA")
4324 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
4325 DNA. A k-mer is a substring of length k, and counting the occurrences of all
4326 such substrings is a central step in many analyses of DNA sequence. Jellyfish
4327 is a command-line program that reads FASTA and multi-FASTA files containing
4328 DNA sequences. It outputs its k-mer counts in a binary format, which can be
4329 translated into a human-readable text format using the @code{jellyfish dump}
4330 command, or queried for specific k-mers with @code{jellyfish query}.")
4331 (home-page "http://www.genome.umd.edu/jellyfish.html")
4332 ;; JELLYFISH seems to be 64-bit only.
4333 (supported-systems '("x86_64-linux" "aarch64-linux" "mips64el-linux"))
4334 ;; The combined work is published under the GPLv3 or later. Individual
4335 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
4336 (license (list license:gpl3+ license:expat))))
4338 (define-public khmer
4346 (url "https://github.com/dib-lab/khmer")
4347 (commit (string-append "v" version))))
4348 (file-name (git-file-name name version))
4351 "01l4jczglkl7yfhgvzx8j0df7k54bk1r8sli9ll16i1mis0d8f37"))
4352 (modules '((guix build utils)))
4355 ;; Delete bundled libraries. We do not replace the bundled seqan
4356 ;; as it is a modified subset of the old version 1.4.1.
4358 ;; We do not replace the bundled MurmurHash as the canonical
4359 ;; repository for this code 'SMHasher' is unsuitable for providing
4361 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
4362 (delete-file-recursively "third-party/zlib")
4363 (delete-file-recursively "third-party/bzip2")
4364 (delete-file-recursively "third-party/seqan")
4365 (substitute* "setup.cfg"
4366 (("# libraries = z,bz2")
4367 "libraries = z,bz2")
4368 (("include:third-party/zlib:third-party/bzip2")
4371 (build-system python-build-system)
4374 (modify-phases %standard-phases
4375 (add-after 'unpack 'set-cc
4376 (lambda _ (setenv "CC" "gcc") #t))
4378 (add-before 'reset-gzip-timestamps 'make-files-writable
4379 (lambda* (#:key outputs #:allow-other-keys)
4380 ;; Make sure .gz files are writable so that the
4381 ;; 'reset-gzip-timestamps' phase can do its work.
4382 (let ((out (assoc-ref outputs "out")))
4383 (for-each make-file-writable
4384 (find-files out "\\.gz$"))
4387 `(("python-cython" ,python-cython)
4388 ("python-pytest" ,python-pytest)
4389 ("python-pytest-runner" ,python-pytest-runner)))
4394 ("python-screed" ,python-screed)
4395 ("python-bz2file" ,python-bz2file)))
4396 (home-page "https://khmer.readthedocs.org/")
4397 (synopsis "K-mer counting, filtering and graph traversal library")
4398 (description "The khmer software is a set of command-line tools for
4399 working with DNA shotgun sequencing data from genomes, transcriptomes,
4400 metagenomes and single cells. Khmer can make de novo assemblies faster, and
4401 sometimes better. Khmer can also identify and fix problems with shotgun
4403 ;; When building on i686, armhf and mips64el, we get the following error:
4404 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
4405 (supported-systems '("x86_64-linux" "aarch64-linux"))
4406 (license license:bsd-3)))
4408 (define-public kaiju
4415 (url "https://github.com/bioinformatics-centre/kaiju")
4416 (commit (string-append "v" version))))
4417 (file-name (git-file-name name version))
4420 "119pzi0ddzv9mjg4wwa6han0cwr3k3ssn7kirvsjfcq05mi5ka0x"))))
4421 (build-system gnu-build-system)
4423 `(#:tests? #f ; There are no tests.
4425 (modify-phases %standard-phases
4427 (add-before 'build 'move-to-src-dir
4428 (lambda _ (chdir "src") #t))
4430 (lambda* (#:key inputs outputs #:allow-other-keys)
4431 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
4434 (copy-recursively "bin" bin))
4439 (home-page "http://kaiju.binf.ku.dk/")
4440 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
4441 (description "Kaiju is a program for sensitive taxonomic classification
4442 of high-throughput sequencing reads from metagenomic whole genome sequencing
4444 (license license:gpl3+)))
4451 ;; The PyPi tarball does not contain tests.
4454 (url "https://github.com/taoliu/MACS")
4455 (commit (string-append "v" version))))
4456 (file-name (git-file-name name version))
4459 "1c5gxr0mk6hkd4vclf0k00wvyvzw2vrmk52c85338p7aqjwg6n15"))))
4460 (build-system python-build-system)
4463 (modify-phases %standard-phases
4465 (add-after 'install 'check
4466 (lambda* (#:key inputs outputs #:allow-other-keys)
4467 (add-installed-pythonpath inputs outputs)
4468 (invoke "pytest" "-v"))))))
4470 `(("python-numpy" ,python-numpy)))
4472 `(("python-pytest" ,python-pytest)))
4473 (home-page "https://github.com/taoliu/MACS/")
4474 (synopsis "Model based analysis for ChIP-Seq data")
4476 "MACS is an implementation of a ChIP-Seq analysis algorithm for
4477 identifying transcript factor binding sites named Model-based Analysis of
4478 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
4479 the significance of enriched ChIP regions and it improves the spatial
4480 resolution of binding sites through combining the information of both
4481 sequencing tag position and orientation.")
4482 (license license:bsd-3)))
4484 (define-public mafft
4491 "https://mafft.cbrc.jp/alignment/software/mafft-" version
4492 "-without-extensions-src.tgz"))
4493 (file-name (string-append name "-" version ".tgz"))
4496 "0bacjkxfg944p5khhyh5rd4y7wkjc9qk4v2jjj442sqlq0f8ar7b"))))
4497 (build-system gnu-build-system)
4499 `(#:tests? #f ; no automated tests, though there are tests in the read me
4500 #:make-flags (let ((out (assoc-ref %outputs "out")))
4501 (list (string-append "PREFIX=" out)
4502 (string-append "BINDIR="
4503 (string-append out "/bin"))))
4505 (modify-phases %standard-phases
4506 (add-after 'unpack 'enter-dir
4507 (lambda _ (chdir "core") #t))
4508 (add-after 'enter-dir 'patch-makefile
4510 ;; on advice from the MAFFT authors, there is no need to
4511 ;; distribute mafft-profile, mafft-distance, or
4512 ;; mafft-homologs.rb as they are too "specialised".
4513 (substitute* "Makefile"
4514 ;; remove mafft-homologs.rb from SCRIPTS
4515 (("^SCRIPTS = mafft mafft-homologs.rb")
4517 ;; remove mafft-homologs from MANPAGES
4518 (("^MANPAGES = mafft.1 mafft-homologs.1")
4519 "MANPAGES = mafft.1")
4520 ;; remove mafft-distance from PROGS
4521 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
4522 "PROGS = dvtditr dndfast7 dndblast sextet5")
4523 ;; remove mafft-profile from PROGS
4524 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
4525 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
4526 (("^rm -f mafft-profile mafft-profile.exe") "#")
4527 (("^rm -f mafft-distance mafft-distance.exe") ")#")
4528 ;; do not install MAN pages in libexec folder
4529 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
4530 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
4532 (add-after 'enter-dir 'patch-paths
4533 (lambda* (#:key inputs #:allow-other-keys)
4534 (substitute* '("pairash.c"
4536 (("perl") (which "perl"))
4537 (("([\"`| ])awk" _ prefix)
4538 (string-append prefix (which "awk")))
4539 (("grep") (which "grep")))
4542 (add-after 'install 'wrap-programs
4543 (lambda* (#:key outputs #:allow-other-keys)
4544 (let* ((out (assoc-ref outputs "out"))
4545 (bin (string-append out "/bin"))
4546 (path (string-append
4547 (assoc-ref %build-inputs "coreutils") "/bin:")))
4548 (for-each (lambda (file)
4550 `("PATH" ":" prefix (,path))))
4558 ("coreutils" ,coreutils)))
4559 (home-page "http://mafft.cbrc.jp/alignment/software/")
4560 (synopsis "Multiple sequence alignment program")
4562 "MAFFT offers a range of multiple alignment methods for nucleotide and
4563 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
4564 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
4566 (license (license:non-copyleft
4567 "http://mafft.cbrc.jp/alignment/software/license.txt"
4568 "BSD-3 with different formatting"))))
4577 (url "https://github.com/marbl/mash")
4578 (commit (string-append "v" version))))
4579 (file-name (git-file-name name version))
4582 "049hwcc059p2fd9vwndn63laifvvsi0wmv84i6y1fr79k15dxwy6"))
4583 (modules '((guix build utils)))
4586 ;; Delete bundled kseq.
4587 ;; TODO: Also delete bundled murmurhash and open bloom filter.
4588 (delete-file "src/mash/kseq.h")
4590 (build-system gnu-build-system)
4592 `(#:tests? #f ; No tests.
4595 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
4596 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
4597 #:make-flags (list "CC=gcc")
4599 (modify-phases %standard-phases
4600 (add-after 'unpack 'fix-includes
4602 (substitute* '("src/mash/Sketch.cpp"
4603 "src/mash/CommandFind.cpp"
4604 "src/mash/CommandScreen.cpp")
4605 (("^#include \"kseq\\.h\"")
4606 "#include \"htslib/kseq.h\""))
4608 (add-after 'fix-includes 'use-c++14
4610 ;; capnproto 0.7 requires c++14 to build
4611 (substitute* "configure.ac"
4612 (("c\\+\\+11") "c++14"))
4613 (substitute* "Makefile.in"
4614 (("c\\+\\+11") "c++14"))
4617 `(("autoconf" ,autoconf)
4618 ;; Capnproto and htslib are statically embedded in the final
4619 ;; application. Therefore we also list their licenses, below.
4620 ("capnproto" ,capnproto)
4621 ("htslib" ,htslib)))
4625 (supported-systems '("x86_64-linux"))
4626 (home-page "https://mash.readthedocs.io")
4627 (synopsis "Fast genome and metagenome distance estimation using MinHash")
4628 (description "Mash is a fast sequence distance estimator that uses the
4629 MinHash algorithm and is designed to work with genomes and metagenomes in the
4630 form of assemblies or reads.")
4631 (license (list license:bsd-3 ; Mash
4632 license:expat ; HTSlib and capnproto
4633 license:public-domain ; MurmurHash 3
4634 license:cpl1.0)))) ; Open Bloom Filter
4636 (define-public metabat
4644 (url "https://bitbucket.org/berkeleylab/metabat.git")
4645 (commit (string-append "v" version))))
4646 (file-name (git-file-name name version))
4649 "0hyg2smw1nz69mfvjpk45xyyychmda92c80a0cv7baji84ri4iyn"))
4650 (patches (search-patches "metabat-fix-compilation.patch"))))
4651 (build-system scons-build-system)
4653 `(#:scons ,scons-python2
4655 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
4656 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
4657 #:tests? #f ;; Tests are run during the build phase.
4659 (modify-phases %standard-phases
4660 (add-after 'unpack 'fix-includes
4662 (substitute* "src/BamUtils.h"
4663 (("^#include \"bam/bam\\.h\"")
4664 "#include \"samtools/bam.h\"")
4665 (("^#include \"bam/sam\\.h\"")
4666 "#include \"samtools/sam.h\""))
4667 (substitute* "src/KseqReader.h"
4668 (("^#include \"bam/kseq\\.h\"")
4669 "#include \"htslib/kseq.h\""))
4671 (add-after 'unpack 'fix-scons
4672 (lambda* (#:key inputs #:allow-other-keys)
4673 (substitute* "SConstruct"
4674 (("^htslib_dir += 'samtools'")
4675 (string-append "htslib_dir = '"
4676 (assoc-ref inputs "htslib")
4678 (("^samtools_dir = 'samtools'")
4679 (string-append "samtools_dir = '"
4680 (assoc-ref inputs "samtools")
4682 (("^findStaticOrShared\\('bam', hts_lib")
4683 (string-append "findStaticOrShared('bam', '"
4684 (assoc-ref inputs "samtools")
4686 ;; Do not distribute README.
4687 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
4692 ("samtools" ,samtools)
4695 (home-page "https://bitbucket.org/berkeleylab/metabat")
4697 "Reconstruction of single genomes from complex microbial communities")
4699 "Grouping large genomic fragments assembled from shotgun metagenomic
4700 sequences to deconvolute complex microbial communities, or metagenome binning,
4701 enables the study of individual organisms and their interactions. MetaBAT is
4702 an automated metagenome binning software, which integrates empirical
4703 probabilistic distances of genome abundance and tetranucleotide frequency.")
4704 ;; The source code contains inline assembly.
4705 (supported-systems '("x86_64-linux" "i686-linux"))
4706 (license (license:non-copyleft "file://license.txt"
4707 "See license.txt in the distribution."))))
4709 (define-public minced
4716 (url "https://github.com/ctSkennerton/minced")
4718 (file-name (git-file-name name version))
4721 "1f5h9him0gd355cnx7p6pnxpknhckd4g0v62mg8zyhfbx9as25fv"))))
4722 (build-system gnu-build-system)
4724 `(#:test-target "test"
4726 (modify-phases %standard-phases
4728 (add-before 'check 'fix-test
4730 ;; Fix test for latest version.
4731 (substitute* "t/Aquifex_aeolicus_VF5.expected"
4732 (("minced:0.1.6") "minced:0.2.0"))
4734 (replace 'install ; No install target.
4735 (lambda* (#:key inputs outputs #:allow-other-keys)
4736 (let* ((out (assoc-ref outputs "out"))
4737 (bin (string-append out "/bin"))
4738 (wrapper (string-append bin "/minced")))
4739 ;; Minced comes with a wrapper script that tries to figure out where
4740 ;; it is located before running the JAR. Since these paths are known
4741 ;; to us, we build our own wrapper to avoid coreutils dependency.
4742 (install-file "minced.jar" bin)
4743 (with-output-to-file wrapper
4747 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
4748 (assoc-ref inputs "jre") "/bin/java -jar "
4749 bin "/minced.jar \"$@\"\n"))))
4750 (chmod wrapper #o555))
4753 `(("jdk" ,icedtea "jdk")))
4756 ("jre" ,icedtea "out")))
4757 (home-page "https://github.com/ctSkennerton/minced")
4758 (synopsis "Mining CRISPRs in Environmental Datasets")
4760 "MinCED is a program to find Clustered Regularly Interspaced Short
4761 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
4762 unassembled metagenomic reads, but is mainly designed for full genomes and
4763 assembled metagenomic sequence.")
4764 (license license:gpl3+)))
4772 (uri (pypi-uri "misopy" version))
4775 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
4776 (modules '((guix build utils)))
4778 (substitute* "setup.py"
4779 ;; Use setuptools, or else the executables are not
4781 (("distutils.core") "setuptools")
4782 ;; Use "gcc" instead of "cc" for compilation.
4784 "cc.set_executables(
4788 linker_so='gcc -shared'); defines"))
4790 (build-system python-build-system)
4792 `(#:python ,python-2 ; only Python 2 is supported
4793 #:tests? #f)) ; no "test" target
4795 `(("samtools" ,samtools)
4796 ("python-numpy" ,python2-numpy)
4797 ("python-pysam" ,python2-pysam)
4798 ("python-scipy" ,python2-scipy)
4799 ("python-matplotlib" ,python2-matplotlib)))
4801 `(("python-mock" ,python2-mock) ; for tests
4802 ("python-pytz" ,python2-pytz))) ; for tests
4803 (home-page "https://www.genes.mit.edu/burgelab/miso/index.html")
4804 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
4806 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
4807 the expression level of alternatively spliced genes from RNA-Seq data, and
4808 identifies differentially regulated isoforms or exons across samples. By
4809 modeling the generative process by which reads are produced from isoforms in
4810 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
4811 that a read originated from a particular isoform.")
4812 (license license:gpl2)))
4814 (define-public muscle
4817 (version "3.8.1551")
4819 (method url-fetch/tarbomb)
4821 "http://www.drive5.com/muscle/muscle_src_"
4825 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
4826 (build-system gnu-build-system)
4828 `(#:make-flags (list "LDLIBS = -lm")
4830 (modify-phases %standard-phases
4833 ;; There are no tests, so just test if it runs.
4834 (lambda _ (invoke "./muscle" "-version") #t))
4836 (lambda* (#:key outputs #:allow-other-keys)
4837 (let* ((out (assoc-ref outputs "out"))
4838 (bin (string-append out "/bin")))
4839 (install-file "muscle" bin)
4841 (home-page "http://www.drive5.com/muscle")
4842 (synopsis "Multiple sequence alignment program")
4844 "MUSCLE aims to be a fast and accurate multiple sequence alignment
4845 program for nucleotide and protein sequences.")
4846 ;; License information found in 'muscle -h' and usage.cpp.
4847 (license license:public-domain)))
4849 (define-public newick-utils
4850 ;; There are no recent releases so we package from git.
4851 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
4853 (name "newick-utils")
4854 (version (string-append "1.6-1." (string-take commit 8)))
4858 (url "https://github.com/tjunier/newick_utils")
4860 (file-name (string-append name "-" version "-checkout"))
4863 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4864 (build-system gnu-build-system)
4866 ;; XXX: TODO: Enable Lua and Guile bindings.
4867 ;; https://github.com/tjunier/newick_utils/issues/13
4868 `(("libxml2" ,libxml2)
4872 `(("autoconf" ,autoconf)
4873 ("automake" ,automake)
4874 ("libtool" ,libtool)))
4875 (synopsis "Programs for working with newick format phylogenetic trees")
4877 "Newick-utils is a suite of utilities for processing phylogenetic trees
4878 in Newick format. Functions include re-rooting, extracting subtrees,
4879 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4880 (home-page "https://github.com/tjunier/newick_utils")
4881 (license license:bsd-3))))
4890 "https://github.com/wwood/OrfM/releases/download/v"
4891 version "/orfm-" version ".tar.gz"))
4894 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4895 (build-system gnu-build-system)
4896 (inputs `(("zlib" ,zlib)))
4898 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4899 ("ruby-rspec" ,ruby-rspec)
4901 (synopsis "Simple and not slow open reading frame (ORF) caller")
4903 "An ORF caller finds stretches of DNA that, when translated, are not
4904 interrupted by stop codons. OrfM finds and prints these ORFs.")
4905 (home-page "https://github.com/wwood/OrfM")
4906 (license license:lgpl3+)))
4908 (define-public python2-pbcore
4910 (name "python2-pbcore")
4914 (uri (pypi-uri "pbcore" version))
4917 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4918 (build-system python-build-system)
4920 `(#:python ,python-2 ;pbcore < 2.0 requires Python 2.7
4921 #:phases (modify-phases %standard-phases
4922 (add-after 'unpack 'remove-sphinx-dependency
4924 ;; Sphinx is only required for documentation tests, which
4925 ;; we do not run; furthermore it depends on python2-sphinx
4926 ;; which is no longer maintained.
4927 (substitute* "requirements-dev.txt"
4931 `(("python-cython" ,python2-cython)
4932 ("python-numpy" ,python2-numpy)
4933 ("python-pysam" ,python2-pysam)
4934 ("python-h5py" ,python2-h5py)))
4936 `(("python-nose" ,python2-nose)
4937 ("python-pyxb" ,python2-pyxb)))
4938 (home-page "https://pacificbiosciences.github.io/pbcore/")
4939 (synopsis "Library for reading and writing PacBio data files")
4941 "The pbcore package provides Python APIs for interacting with PacBio data
4942 files and writing bioinformatics applications.")
4943 (license license:bsd-3)))
4945 (define-public python2-warpedlmm
4947 (name "python2-warpedlmm")
4952 (uri (pypi-uri "WarpedLMM" version ".zip"))
4955 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4956 (build-system python-build-system)
4958 `(#:python ,python-2 ; requires Python 2.7
4959 #:tests? #f ; test data are not included
4961 (modify-phases %standard-phases
4962 (add-after 'unpack 'use-weave
4964 (substitute* "warpedlmm/util/linalg.py"
4965 (("from scipy import linalg, weave")
4966 "from scipy import linalg\nimport weave"))
4969 `(("python-scipy" ,python2-scipy)
4970 ("python-numpy" ,python2-numpy)
4971 ("python-matplotlib" ,python2-matplotlib)
4972 ("python-fastlmm" ,python2-fastlmm)
4973 ("python-pandas" ,python2-pandas)
4974 ("python-pysnptools" ,python2-pysnptools)
4975 ("python-weave" ,python2-weave)))
4977 `(("python-mock" ,python2-mock)
4978 ("python-nose" ,python2-nose)
4980 (home-page "https://github.com/PMBio/warpedLMM")
4981 (synopsis "Implementation of warped linear mixed models")
4983 "WarpedLMM is a Python implementation of the warped linear mixed model,
4984 which automatically learns an optimal warping function (or transformation) for
4985 the phenotype as it models the data.")
4986 (license license:asl2.0)))
4988 (define-public pbtranscript-tofu
4989 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
4991 (name "pbtranscript-tofu")
4992 (version (string-append "2.2.3." (string-take commit 7)))
4996 (url "https://github.com/PacificBiosciences/cDNA_primer")
4998 (file-name (string-append name "-" version "-checkout"))
5001 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
5002 (modules '((guix build utils)))
5005 ;; remove bundled Cython sources
5006 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
5008 (build-system python-build-system)
5010 `(#:python ,python-2
5011 ;; FIXME: Tests fail with "No such file or directory:
5012 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
5015 (modify-phases %standard-phases
5016 (add-after 'unpack 'enter-directory
5018 (chdir "pbtranscript-tofu/pbtranscript/")
5020 ;; With setuptools version 18.0 and later this setup.py hack causes
5021 ;; a build error, so we disable it.
5022 (add-after 'enter-directory 'patch-setuppy
5024 (substitute* "setup.py"
5025 (("if 'setuptools.extension' in sys.modules:")
5029 `(("python-numpy" ,python2-numpy)
5030 ("python-bx-python" ,python2-bx-python)
5031 ("python-networkx" ,python2-networkx)
5032 ("python-scipy" ,python2-scipy)
5033 ("python-pbcore" ,python2-pbcore)
5034 ("python-h5py" ,python2-h5py)))
5036 `(("python-cython" ,python2-cython)
5037 ("python-nose" ,python2-nose)))
5038 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
5039 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
5041 "pbtranscript-tofu contains scripts to analyze transcriptome data
5042 generated using the PacBio Iso-Seq protocol.")
5043 (license license:bsd-3))))
5045 (define-public prank
5052 "http://wasabiapp.org/download/prank/prank.source."
5056 "0nc8g9c5rkdxcir46s0in9ci1sxwzbjibxrvkksf22ybnplvagk2"))))
5057 (build-system gnu-build-system)
5060 (modify-phases %standard-phases
5061 (add-after 'unpack 'enter-src-dir
5065 (add-after 'unpack 'remove-m64-flag
5066 ;; Prank will build with the correct 'bit-ness' without this flag
5067 ;; and this allows building on 32-bit machines.
5068 (lambda _ (substitute* "src/Makefile"
5073 (lambda* (#:key outputs #:allow-other-keys)
5074 (let* ((out (assoc-ref outputs "out"))
5075 (bin (string-append out "/bin"))
5076 (man (string-append out "/share/man/man1"))
5077 (path (string-append
5078 (assoc-ref %build-inputs "mafft") "/bin:"
5079 (assoc-ref %build-inputs "exonerate") "/bin:"
5080 (assoc-ref %build-inputs "bppsuite") "/bin")))
5081 (install-file "prank" bin)
5082 (wrap-program (string-append bin "/prank")
5083 `("PATH" ":" prefix (,path)))
5084 (install-file "prank.1" man))
5088 ("exonerate" ,exonerate)
5089 ("bppsuite" ,bppsuite)))
5090 (home-page "http://wasabiapp.org/software/prank/")
5091 (synopsis "Probabilistic multiple sequence alignment program")
5093 "PRANK is a probabilistic multiple sequence alignment program for DNA,
5094 codon and amino-acid sequences. It is based on a novel algorithm that treats
5095 insertions correctly and avoids over-estimation of the number of deletion
5096 events. In addition, PRANK borrows ideas from maximum likelihood methods used
5097 in phylogenetics and correctly takes into account the evolutionary distances
5098 between sequences. Lastly, PRANK allows for defining a potential structure
5099 for sequences to be aligned and then, simultaneously with the alignment,
5100 predicts the locations of structural units in the sequences.")
5101 (license license:gpl2+)))
5103 (define-public proteinortho
5105 (name "proteinortho")
5110 (url "https://gitlab.com/paulklemm_PHD/proteinortho.git")
5111 (commit (string-append "v" version))))
5112 (file-name (git-file-name name version))
5115 "0pmy617zy2z2w6hjqxjhf3rzikf5n3mpia80ysq8233vfr7wrzff"))
5116 (modules '((guix build utils)))
5119 ;; remove pre-built scripts
5120 (delete-file-recursively "src/BUILD/")
5122 (build-system gnu-build-system)
5124 `(#:test-target "test"
5125 #:make-flags '("CC=gcc")
5127 (modify-phases %standard-phases
5129 ;; There is no configure script, so we modify the Makefile directly.
5130 (lambda* (#:key outputs #:allow-other-keys)
5131 (substitute* "Makefile"
5134 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
5136 (add-before 'install 'make-install-directory
5137 ;; The install directory is not created during 'make install'.
5138 (lambda* (#:key outputs #:allow-other-keys)
5139 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
5141 (add-after 'install 'wrap-programs
5142 (lambda* (#:key inputs outputs #:allow-other-keys)
5143 (let ((path (getenv "PATH"))
5144 (out (assoc-ref outputs "out")))
5145 (for-each (lambda (script)
5146 (wrap-script script `("PATH" ":" prefix (,path))))
5147 (cons (string-append out "/bin/proteinortho")
5148 (find-files out "\\.(pl|py)$"))))
5151 `(("guile" ,guile-3.0) ; for wrap-script
5152 ("diamond" ,diamond)
5154 ("python" ,python-wrapper)
5157 ("openblas" ,openblas)))
5159 `(("which" ,which)))
5160 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
5161 (synopsis "Detect orthologous genes across species")
5163 "Proteinortho is a tool to detect orthologous genes across different
5164 species. For doing so, it compares similarities of given gene sequences and
5165 clusters them to find significant groups. The algorithm was designed to handle
5166 large-scale data and can be applied to hundreds of species at once.")
5167 (license license:gpl3+)))
5169 (define-public pyicoteo
5177 (url "https://bitbucket.org/regulatorygenomicsupf/pyicoteo.git")
5178 (commit (string-append "v" version))))
5179 (file-name (git-file-name name version))
5182 "0hz5g8d25lbjy1wpscr490l0lmyvaix893hhax4fxnh1h9w34w8p"))))
5183 (build-system python-build-system)
5185 `(#:python ,python-2 ; does not work with Python 3
5186 #:tests? #f)) ; there are no tests
5188 `(("python2-matplotlib" ,python2-matplotlib)))
5189 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
5190 (synopsis "Analyze high-throughput genetic sequencing data")
5192 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
5193 sequencing data. It works with genomic coordinates. There are currently six
5194 different command-line tools:
5197 @item pyicoregion: for generating exploratory regions automatically;
5198 @item pyicoenrich: for differential enrichment between two conditions;
5199 @item pyicoclip: for calling CLIP-Seq peaks without a control;
5200 @item pyicos: for genomic coordinates manipulation;
5201 @item pyicoller: for peak calling on punctuated ChIP-Seq;
5202 @item pyicount: to count how many reads from N experiment files overlap in a
5204 @item pyicotrocol: to combine operations from pyicoteo.
5206 (license license:gpl3+)))
5208 (define-public prodigal
5211 ;; Check for a new home page when updating this package:
5212 ;; https://github.com/hyattpd/Prodigal/issues/36#issuecomment-536617588
5217 (url "https://github.com/hyattpd/Prodigal")
5218 (commit (string-append "v" version))))
5219 (file-name (git-file-name name version))
5222 "1fs1hqk83qjbjhrvhw6ni75zakx5ki1ayy3v6wwkn3xvahc9hi5s"))))
5223 (build-system gnu-build-system)
5225 `(#:tests? #f ; no check target
5226 #:make-flags (list (string-append "INSTALLDIR="
5227 (assoc-ref %outputs "out")
5230 (modify-phases %standard-phases
5231 (delete 'configure))))
5232 (home-page "https://github.com/hyattpd/Prodigal")
5233 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
5235 "Prodigal runs smoothly on finished genomes, draft genomes, and
5236 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
5237 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
5238 partial genes, and identifies translation initiation sites.")
5239 (license license:gpl3+)))
5241 (define-public roary
5249 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
5253 "0qxrds9wx7cfhlkihrp6697kx0flhhxymap9fwan0b3rbdhcnmff"))))
5254 (build-system perl-build-system)
5257 (modify-phases %standard-phases
5262 ;; The tests are not run by default, so we run each test file
5264 (setenv "PATH" (string-append (getcwd) "/bin" ":"
5266 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
5267 (getenv "PERL5LIB")))
5268 (for-each (lambda (file)
5269 (display file)(display "\n")
5270 (invoke "perl" file))
5271 (find-files "t" ".*\\.t$"))
5274 ;; There is no 'install' target in the Makefile.
5275 (lambda* (#:key outputs #:allow-other-keys)
5276 (let* ((out (assoc-ref outputs "out"))
5277 (bin (string-append out "/bin"))
5278 (perl (string-append out "/lib/perl5/site_perl"))
5279 (roary-plots "contrib/roary_plots"))
5282 (copy-recursively "bin" bin)
5283 (copy-recursively "lib" perl)
5285 (add-after 'install 'wrap-programs
5286 (lambda* (#:key inputs outputs #:allow-other-keys)
5287 (let* ((out (assoc-ref outputs "out"))
5288 (perl5lib (getenv "PERL5LIB"))
5289 (path (getenv "PATH")))
5290 (for-each (lambda (prog)
5291 (let ((binary (string-append out "/" prog)))
5292 (wrap-program binary
5293 `("PERL5LIB" ":" prefix
5294 (,(string-append perl5lib ":" out
5295 "/lib/perl5/site_perl"))))
5296 (wrap-program binary
5298 (,(string-append path ":" out "/bin"))))))
5299 (find-files "bin" ".*[^R]$"))
5301 (string-append out "/bin/roary-create_pan_genome_plots.R"))
5302 (r-site-lib (getenv "R_LIBS_SITE"))
5304 (string-append (assoc-ref inputs "coreutils") "/bin")))
5306 `("R_LIBS_SITE" ":" prefix
5307 (,(string-append r-site-lib ":" out "/site-library/"))))
5310 (,(string-append coreutils-path ":" out "/bin"))))))
5313 `(("perl-env-path" ,perl-env-path)
5314 ("perl-test-files" ,perl-test-files)
5315 ("perl-test-most" ,perl-test-most)
5316 ("perl-test-output" ,perl-test-output)))
5318 `(("perl-array-utils" ,perl-array-utils)
5319 ("bioperl" ,bioperl-minimal)
5320 ("perl-digest-md5-file" ,perl-digest-md5-file)
5321 ("perl-exception-class" ,perl-exception-class)
5322 ("perl-file-find-rule" ,perl-file-find-rule)
5323 ("perl-file-grep" ,perl-file-grep)
5324 ("perl-file-slurper" ,perl-file-slurper)
5325 ("perl-file-which" ,perl-file-which)
5326 ("perl-graph" ,perl-graph)
5327 ("perl-graph-readwrite" ,perl-graph-readwrite)
5328 ("perl-log-log4perl" ,perl-log-log4perl)
5329 ("perl-moose" ,perl-moose)
5330 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
5331 ("perl-text-csv" ,perl-text-csv)
5332 ("bedtools" ,bedtools)
5336 ("parallel" ,parallel)
5339 ("fasttree" ,fasttree)
5343 ("r-minimal" ,r-minimal)
5344 ("r-ggplot2" ,r-ggplot2)
5345 ("coreutils" ,coreutils)))
5346 (home-page "https://sanger-pathogens.github.io/Roary/")
5347 (synopsis "High speed stand-alone pan genome pipeline")
5349 "Roary is a high speed stand alone pan genome pipeline, which takes
5350 annotated assemblies in GFF3 format (produced by the Prokka program) and
5351 calculates the pan genome. Using a standard desktop PC, it can analyse
5352 datasets with thousands of samples, without compromising the quality of the
5353 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
5354 single processor. Roary is not intended for metagenomics or for comparing
5355 extremely diverse sets of genomes.")
5356 (license license:gpl3)))
5358 (define-public raxml
5366 (url "https://github.com/stamatak/standard-RAxML")
5367 (commit (string-append "v" version))))
5368 (file-name (git-file-name name version))
5371 "1jqjzhch0rips0vp04prvb8vmc20c5pdmsqn8knadcf91yy859fh"))))
5372 (build-system gnu-build-system)
5374 `(#:tests? #f ; There are no tests.
5375 ;; Use 'standard' Makefile rather than SSE or AVX ones.
5376 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
5378 (modify-phases %standard-phases
5381 (lambda* (#:key outputs #:allow-other-keys)
5382 (let* ((out (assoc-ref outputs "out"))
5383 (bin (string-append out "/bin"))
5384 (executable "raxmlHPC-HYBRID"))
5385 (install-file executable bin)
5386 (symlink (string-append bin "/" executable) "raxml"))
5389 `(("openmpi" ,openmpi)))
5390 (home-page "https://cme.h-its.org/exelixis/web/software/raxml/index.html")
5391 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
5393 "RAxML is a tool for phylogenetic analysis and post-analysis of large
5395 ;; The source includes x86 specific code
5396 (supported-systems '("x86_64-linux" "i686-linux"))
5397 (license license:gpl2+)))
5407 (url "https://github.com/deweylab/RSEM")
5408 (commit (string-append "v" version))))
5410 (base32 "1jlq11d1p8qp64w75yj8cnbbd1a93viq10pzsbwal7vdn8fg13j1"))
5411 (file-name (git-file-name name version))
5412 (modules '((guix build utils)))
5415 ;; remove bundled copy of boost and samtools
5416 (delete-file-recursively "boost")
5417 (delete-file-recursively "samtools-1.3")
5419 (build-system gnu-build-system)
5421 `(#:tests? #f ;no "check" target
5423 (list (string-append "BOOST="
5424 (assoc-ref %build-inputs "boost")
5426 (string-append "SAMHEADERS="
5427 (assoc-ref %build-inputs "htslib")
5428 "/include/htslib/sam.h")
5429 (string-append "SAMLIBS="
5430 (assoc-ref %build-inputs "htslib")
5433 (modify-phases %standard-phases
5434 ;; No "configure" script.
5435 ;; Do not build bundled samtools library.
5438 (substitute* "Makefile"
5439 (("^all : \\$\\(PROGRAMS\\).*") "all: $(PROGRAMS)\n")
5440 (("^\\$\\(SAMLIBS\\).*") ""))
5443 (lambda* (#:key outputs #:allow-other-keys)
5444 (let* ((out (string-append (assoc-ref outputs "out")))
5445 (bin (string-append out "/bin/"))
5446 (perl (string-append out "/lib/perl5/site_perl")))
5449 (for-each (lambda (file)
5450 (install-file file bin))
5451 (find-files "." "rsem-.*"))
5452 (install-file "rsem_perl_utils.pm" perl))
5454 (add-after 'install 'wrap-program
5455 (lambda* (#:key outputs #:allow-other-keys)
5456 (let ((out (assoc-ref outputs "out")))
5457 (for-each (lambda (prog)
5458 (wrap-program (string-append out "/bin/" prog)
5459 `("PERL5LIB" ":" prefix
5460 (,(string-append out "/lib/perl5/site_perl")))))
5461 '("rsem-calculate-expression"
5463 "rsem-generate-data-matrix"
5464 "rsem-generate-ngvector"
5465 "rsem-plot-transcript-wiggles"
5466 "rsem-prepare-reference"
5468 "rsem-run-prsem-testing-procedure")))
5472 ("r-minimal" ,r-minimal)
5474 ("htslib" ,htslib-1.3)
5476 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
5477 (synopsis "Estimate gene expression levels from RNA-Seq data")
5479 "RSEM is a software package for estimating gene and isoform expression
5480 levels from RNA-Seq data. The RSEM package provides a user-friendly
5481 interface, supports threads for parallel computation of the EM algorithm,
5482 single-end and paired-end read data, quality scores, variable-length reads and
5483 RSPD estimation. In addition, it provides posterior mean and 95% credibility
5484 interval estimates for expression levels. For visualization, it can generate
5485 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
5486 (license license:gpl3+)))
5488 (define-public rseqc
5496 (string-append "mirror://sourceforge/rseqc/"
5497 "RSeQC-" version ".tar.gz"))
5500 "0gbb9iyb7swiv5455fm5rg98r7l6qn27v564yllqjd574hncpx6m"))))
5501 (build-system python-build-system)
5503 `(("python-cython" ,python-cython)
5504 ("python-bx-python" ,python-bx-python)
5505 ("python-pybigwig" ,python-pybigwig)
5506 ("python-pysam" ,python-pysam)
5507 ("python-numpy" ,python-numpy)
5510 `(("python-nose" ,python-nose)))
5511 (home-page "http://rseqc.sourceforge.net/")
5512 (synopsis "RNA-seq quality control package")
5514 "RSeQC provides a number of modules that can comprehensively evaluate
5515 high throughput sequence data, especially RNA-seq data. Some basic modules
5516 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
5517 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
5518 distribution, coverage uniformity, strand specificity, etc.")
5519 (license license:gpl3+)))
5522 ;; There are no release tarballs. According to the installation
5523 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
5524 ;; stable release is identified by this changeset ID.
5525 (let ((changeset "2329130")
5529 (version (string-append "0-" revision "." changeset))
5533 (url "https://bitbucket.org/libsleipnir/sleipnir")
5534 (changeset changeset)))
5535 (file-name (string-append name "-" version "-checkout"))
5538 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
5539 (build-system gnu-build-system)
5541 `(#:modules ((srfi srfi-1)
5542 (guix build gnu-build-system)
5545 (let ((dirs '("SeekMiner"
5551 (modify-phases %standard-phases
5554 (substitute* "gen_tools_am"
5555 (("/usr/bin/env.*") (which "perl")))
5556 (invoke "bash" "gen_auto")
5558 (add-after 'build 'build-additional-tools
5559 (lambda* (#:key make-flags #:allow-other-keys)
5560 (for-each (lambda (dir)
5561 (with-directory-excursion (string-append "tools/" dir)
5562 (apply invoke "make" make-flags)))
5565 (add-after 'install 'install-additional-tools
5566 (lambda* (#:key make-flags #:allow-other-keys)
5567 (for-each (lambda (dir)
5568 (with-directory-excursion (string-append "tools/" dir)
5569 (apply invoke `("make" ,@make-flags "install"))))
5576 ("readline" ,readline)
5577 ("gengetopt" ,gengetopt)
5578 ("log4cpp" ,log4cpp)))
5580 `(("autoconf" ,autoconf)
5581 ("automake" ,automake)
5583 (home-page "http://seek.princeton.edu")
5584 (synopsis "Gene co-expression search engine")
5586 "SEEK is a computational gene co-expression search engine. SEEK provides
5587 biologists with a way to navigate the massive human expression compendium that
5588 now contains thousands of expression datasets. SEEK returns a robust ranking
5589 of co-expressed genes in the biological area of interest defined by the user's
5590 query genes. It also prioritizes thousands of expression datasets according
5591 to the user's query of interest.")
5592 (license license:cc-by3.0))))
5594 (define-public samtools
5602 (string-append "mirror://sourceforge/samtools/samtools/"
5603 version "/samtools-" version ".tar.bz2"))
5606 "10ilqbmm7ri8z431sn90lvbjwizd0hhkf9rcqw8j823hf26nhgq8"))
5607 (modules '((guix build utils)))
5609 ;; Delete bundled htslib.
5610 (delete-file-recursively "htslib-1.9")
5612 (build-system gnu-build-system)
5614 `(#:modules ((ice-9 ftw)
5616 (guix build gnu-build-system)
5618 #:configure-flags (list "--with-ncurses")
5620 (modify-phases %standard-phases
5621 (add-after 'unpack 'patch-tests
5623 (substitute* "test/test.pl"
5624 ;; The test script calls out to /bin/bash
5625 (("/bin/bash") (which "bash")))
5627 (add-after 'install 'install-library
5628 (lambda* (#:key outputs #:allow-other-keys)
5629 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
5630 (install-file "libbam.a" lib)
5632 (add-after 'install 'install-headers
5633 (lambda* (#:key outputs #:allow-other-keys)
5634 (let ((include (string-append (assoc-ref outputs "out")
5635 "/include/samtools/")))
5636 (for-each (lambda (file)
5637 (install-file file include))
5638 (scandir "." (lambda (name) (string-match "\\.h$" name))))
5640 (native-inputs `(("pkg-config" ,pkg-config)))
5642 `(("htslib" ,htslib)
5643 ("ncurses" ,ncurses)
5647 (home-page "http://samtools.sourceforge.net")
5648 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
5650 "Samtools implements various utilities for post-processing nucleotide
5651 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
5652 variant calling (in conjunction with bcftools), and a simple alignment
5654 (license license:expat)))
5656 (define-public samtools-0.1
5657 ;; This is the most recent version of the 0.1 line of samtools. The input
5658 ;; and output formats differ greatly from that used and produced by samtools
5659 ;; 1.x and is still used in many bioinformatics pipelines.
5660 (package (inherit samtools)
5666 (string-append "mirror://sourceforge/samtools/samtools/"
5667 version "/samtools-" version ".tar.bz2"))
5669 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
5671 `(#:tests? #f ;no "check" target
5673 (list "LIBCURSES=-lncurses")
5674 ,@(substitute-keyword-arguments (package-arguments samtools)
5676 `(modify-phases ,phases
5678 (lambda* (#:key outputs #:allow-other-keys)
5679 (let ((bin (string-append
5680 (assoc-ref outputs "out") "/bin")))
5682 (install-file "samtools" bin)
5684 (delete 'patch-tests)
5685 (delete 'configure))))))))
5687 (define-public mosaik
5688 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
5693 ;; There are no release tarballs nor tags.
5696 (url "https://github.com/wanpinglee/MOSAIK")
5698 (file-name (string-append name "-" version))
5701 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
5702 (build-system gnu-build-system)
5704 `(#:tests? #f ; no tests
5705 #:make-flags (list "CC=gcc")
5707 (modify-phases %standard-phases
5709 (lambda _ (chdir "src") #t))
5711 (lambda* (#:key outputs #:allow-other-keys)
5712 (let ((bin (string-append (assoc-ref outputs "out")
5715 (copy-recursively "../bin" bin)
5719 ("zlib:static" ,zlib "static")
5721 (supported-systems '("x86_64-linux"))
5722 (home-page "https://github.com/wanpinglee/MOSAIK")
5723 (synopsis "Map nucleotide sequence reads to reference genomes")
5725 "MOSAIK is a program for mapping second and third-generation sequencing
5726 reads to a reference genome. MOSAIK can align reads generated by all the
5727 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
5728 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
5729 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
5730 ;; code released into the public domain:
5731 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
5732 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
5733 (license (list license:gpl2+ license:public-domain)))))
5735 (define-public ngs-sdk
5742 (url "https://github.com/ncbi/ngs")
5744 (file-name (git-file-name name version))
5747 "1ix51c25hjn57w93qmwzw80xh2i34wx8j2hn7szh8p6w8i3az5qa"))))
5748 (build-system gnu-build-system)
5750 `(#:parallel-build? #f ; not supported
5751 #:tests? #f ; no "check" target
5753 (modify-phases %standard-phases
5755 (lambda* (#:key outputs #:allow-other-keys)
5756 (let ((out (assoc-ref outputs "out")))
5757 ;; Allow 'konfigure.perl' to find 'package.prl'.
5759 (string-append ".:" (getenv "PERL5LIB")))
5761 ;; The 'configure' script doesn't recognize things like
5762 ;; '--enable-fast-install'.
5763 (invoke "./configure"
5764 (string-append "--build-prefix=" (getcwd) "/build")
5765 (string-append "--prefix=" out))
5767 (add-after 'unpack 'enter-dir
5768 (lambda _ (chdir "ngs-sdk") #t)))))
5769 (native-inputs `(("perl" ,perl)))
5770 ;; According to the test
5771 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
5772 ;; in ngs-sdk/setup/konfigure.perl
5773 (supported-systems '("i686-linux" "x86_64-linux"))
5774 (home-page "https://github.com/ncbi/ngs")
5775 (synopsis "API for accessing Next Generation Sequencing data")
5777 "NGS is a domain-specific API for accessing reads, alignments and pileups
5778 produced from Next Generation Sequencing. The API itself is independent from
5779 any particular back-end implementation, and supports use of multiple back-ends
5781 (license license:public-domain)))
5783 (define-public java-ngs
5784 (package (inherit ngs-sdk)
5787 `(,@(substitute-keyword-arguments
5788 `(#:modules ((guix build gnu-build-system)
5792 ,@(package-arguments ngs-sdk))
5794 `(modify-phases ,phases
5795 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5797 `(("jdk" ,icedtea "jdk")
5798 ("ngs-sdk" ,ngs-sdk)))
5799 (synopsis "Java bindings for NGS SDK")))
5801 (define-public ncbi-vdb
5808 (url "https://github.com/ncbi/ncbi-vdb")
5810 (file-name (git-file-name name version))
5813 "0m8hlxscidsfqm9x9fyi62q6lpf1dv5115kgjjgnrkl49q9c27m6"))))
5814 (build-system gnu-build-system)
5816 `(#:parallel-build? #f ; not supported
5817 #:tests? #f ; no "check" target
5818 #:make-flags '("HAVE_HDF5=1")
5820 (modify-phases %standard-phases
5821 (add-after 'unpack 'make-files-writable
5822 (lambda _ (for-each make-file-writable (find-files "." ".*")) #t))
5823 (add-before 'configure 'set-perl-search-path
5825 ;; Work around "dotless @INC" build failure.
5827 (string-append (getcwd) "/setup:"
5828 (getenv "PERL5LIB")))
5830 ;; See https://github.com/ncbi/ncbi-vdb/issues/14
5831 (add-after 'unpack 'patch-krypto-flags
5833 (substitute* "libs/krypto/Makefile"
5834 (("-Wa,-march=generic64\\+aes") "")
5835 (("-Wa,-march=generic64\\+sse4") ""))
5838 (lambda* (#:key inputs outputs #:allow-other-keys)
5839 (let ((out (assoc-ref outputs "out")))
5840 ;; Override include path for libmagic
5841 (substitute* "setup/package.prl"
5842 (("name => 'magic', Include => '/usr/include'")
5843 (string-append "name=> 'magic', Include => '"
5844 (assoc-ref inputs "libmagic")
5847 ;; Install kdf5 library (needed by sra-tools)
5848 (substitute* "build/Makefile.install"
5849 (("LIBRARIES_TO_INSTALL =")
5850 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5852 (substitute* "build/Makefile.env"
5853 (("CFLAGS =" prefix)
5854 (string-append prefix "-msse2 ")))
5856 ;; Override search path for ngs-java
5857 (substitute* "setup/package.prl"
5858 (("/usr/local/ngs/ngs-java")
5859 (assoc-ref inputs "java-ngs")))
5861 ;; The 'configure' script doesn't recognize things like
5862 ;; '--enable-fast-install'.
5863 (invoke "./configure"
5864 (string-append "--build-prefix=" (getcwd) "/build")
5865 (string-append "--prefix=" (assoc-ref outputs "out"))
5866 (string-append "--debug")
5867 (string-append "--with-xml2-prefix="
5868 (assoc-ref inputs "libxml2"))
5869 (string-append "--with-ngs-sdk-prefix="
5870 (assoc-ref inputs "ngs-sdk"))
5871 (string-append "--with-hdf5-prefix="
5872 (assoc-ref inputs "hdf5")))
5874 (add-after 'install 'install-interfaces
5875 (lambda* (#:key outputs #:allow-other-keys)
5876 ;; Install interface libraries. On i686 the interface libraries
5877 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5878 ;; architecture name ("i386") instead of the target system prefix
5880 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5881 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5882 ,(system->linux-architecture
5883 (or (%current-target-system)
5886 (string-append (assoc-ref outputs "out")
5888 ;; Install interface headers
5889 (copy-recursively "interfaces"
5890 (string-append (assoc-ref outputs "out")
5893 ;; These files are needed by sra-tools.
5894 (add-after 'install 'install-configuration-files
5895 (lambda* (#:key outputs #:allow-other-keys)
5896 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5898 (install-file "libs/kfg/default.kfg" target)
5899 (install-file "libs/kfg/certs.kfg" target))
5902 `(("libxml2" ,libxml2)
5903 ("ngs-sdk" ,ngs-sdk)
5904 ("java-ngs" ,java-ngs)
5907 (native-inputs `(("perl" ,perl)))
5908 ;; NCBI-VDB requires SSE capability.
5909 (supported-systems '("i686-linux" "x86_64-linux"))
5910 (home-page "https://github.com/ncbi/ncbi-vdb")
5911 (synopsis "Database engine for genetic information")
5913 "The NCBI-VDB library implements a highly compressed columnar data
5914 warehousing engine that is most often used to store genetic information.
5915 Databases are stored in a portable image within the file system, and can be
5916 accessed/downloaded on demand across HTTP.")
5917 (license license:public-domain)))
5919 (define-public plink
5927 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5928 version "-src.zip"))
5930 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5931 (patches (search-patches "plink-1.07-unclobber-i.patch"
5932 "plink-endian-detection.patch"))))
5933 (build-system gnu-build-system)
5935 '(#:tests? #f ;no "check" target
5936 #:make-flags (list (string-append "LIB_LAPACK="
5937 (assoc-ref %build-inputs "lapack")
5938 "/lib/liblapack.so")
5941 ;; disable phoning home
5944 (modify-phases %standard-phases
5945 ;; no "configure" script
5948 (lambda* (#:key outputs #:allow-other-keys)
5949 (let ((bin (string-append (assoc-ref outputs "out")
5951 (install-file "plink" bin)
5955 ("lapack" ,lapack)))
5957 `(("unzip" ,unzip)))
5958 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5959 (synopsis "Whole genome association analysis toolset")
5961 "PLINK is a whole genome association analysis toolset, designed to
5962 perform a range of basic, large-scale analyses in a computationally efficient
5963 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5964 so there is no support for steps prior to this (e.g. study design and
5965 planning, generating genotype or CNV calls from raw data). Through
5966 integration with gPLINK and Haploview, there is some support for the
5967 subsequent visualization, annotation and storage of results.")
5968 ;; Code is released under GPLv2, except for fisher.h, which is under
5970 (license (list license:gpl2 license:lgpl2.1+))))
5972 (define-public plink-ng
5973 (package (inherit plink)
5980 (url "https://github.com/chrchang/plink-ng")
5981 (commit (string-append "v" version))))
5982 (file-name (git-file-name name version))
5984 (base32 "02npdwgkpfkdnhw819rhj5kw02a5k5m90b14zq9zzya4hyg929c0"))))
5985 (build-system gnu-build-system)
5987 '(#:tests? #f ;no "check" target
5988 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5989 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5991 "-f" "Makefile.std")
5993 (modify-phases %standard-phases
5994 (add-after 'unpack 'chdir
5995 (lambda _ (chdir "1.9") #t))
5996 (delete 'configure) ; no "configure" script
5998 (lambda* (#:key outputs #:allow-other-keys)
5999 (let ((bin (string-append (assoc-ref outputs "out")
6001 (install-file "plink" bin)
6006 ("openblas" ,openblas)))
6007 (home-page "https://www.cog-genomics.org/plink/")
6008 (license license:gpl3+)))
6010 (define-public smithlab-cpp
6011 (let ((revision "1")
6012 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
6014 (name "smithlab-cpp")
6015 (version (string-append "0." revision "." (string-take commit 7)))
6019 (url "https://github.com/smithlabcode/smithlab_cpp")
6021 (file-name (string-append name "-" version "-checkout"))
6024 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
6025 (build-system gnu-build-system)
6027 `(#:modules ((guix build gnu-build-system)
6030 #:tests? #f ;no "check" target
6032 (modify-phases %standard-phases
6033 (add-after 'unpack 'use-samtools-headers
6035 (substitute* '("SAM.cpp"
6037 (("sam.h") "samtools/sam.h"))
6040 (lambda* (#:key outputs #:allow-other-keys)
6041 (let* ((out (assoc-ref outputs "out"))
6042 (lib (string-append out "/lib"))
6043 (include (string-append out "/include/smithlab-cpp")))
6046 (for-each (cut install-file <> lib)
6047 (find-files "." "\\.o$"))
6048 (for-each (cut install-file <> include)
6049 (find-files "." "\\.hpp$")))
6051 (delete 'configure))))
6053 `(("samtools" ,samtools-0.1)
6055 (home-page "https://github.com/smithlabcode/smithlab_cpp")
6056 (synopsis "C++ helper library for functions used in Smith lab projects")
6058 "Smithlab CPP is a C++ library that includes functions used in many of
6059 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
6060 structures, classes for genomic regions, mapped sequencing reads, etc.")
6061 (license license:gpl3+))))
6063 (define-public preseq
6069 (uri (string-append "https://github.com/smithlabcode/preseq/"
6070 "releases/download/v" version
6071 "/preseq_v" version ".tar.bz2"))
6073 (base32 "149x9xmk1wy1gff85325yfzqc0qk4sgp1w6gbyj9cnji4x1dszbl"))
6074 (modules '((guix build utils)))
6076 ;; Remove bundled samtools.
6077 (delete-file-recursively "samtools")
6079 (build-system gnu-build-system)
6081 `(#:tests? #f ;no "check" target
6083 (modify-phases %standard-phases
6084 (delete 'configure))
6086 (list (string-append "PREFIX="
6087 (assoc-ref %outputs "out"))
6088 (string-append "LIBBAM="
6089 (assoc-ref %build-inputs "samtools")
6091 (string-append "SMITHLAB_CPP="
6092 (assoc-ref %build-inputs "smithlab-cpp")
6095 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
6098 ("samtools" ,samtools-0.1)
6099 ("smithlab-cpp" ,smithlab-cpp)
6101 (home-page "http://smithlabresearch.org/software/preseq/")
6102 (synopsis "Program for analyzing library complexity")
6104 "The preseq package is aimed at predicting and estimating the complexity
6105 of a genomic sequencing library, equivalent to predicting and estimating the
6106 number of redundant reads from a given sequencing depth and how many will be
6107 expected from additional sequencing using an initial sequencing experiment.
6108 The estimates can then be used to examine the utility of further sequencing,
6109 optimize the sequencing depth, or to screen multiple libraries to avoid low
6110 complexity samples.")
6111 (license license:gpl3+)))
6113 (define-public python-screed
6115 (name "python-screed")
6120 (uri (pypi-uri "screed" version))
6123 "148vcb7w2wr6a4w6vs2bsxanbqibxfk490zbcbg4m61s8669zdjx"))))
6124 (build-system python-build-system)
6127 (modify-phases %standard-phases
6128 ;; Tests must be run after installation, as the "screed" command does
6129 ;; not exist right after building.
6131 (add-after 'install 'check
6132 (lambda* (#:key inputs outputs #:allow-other-keys)
6133 (let ((out (assoc-ref outputs "out")))
6134 (setenv "PYTHONPATH"
6135 (string-append out "/lib/python"
6136 (string-take (string-take-right
6137 (assoc-ref inputs "python")
6140 (getenv "PYTHONPATH")))
6141 (setenv "PATH" (string-append out "/bin:" (getenv "PATH"))))
6142 (invoke "python" "setup.py" "test")
6145 `(("python-pytest" ,python-pytest)
6146 ("python-pytest-cov" ,python-pytest-cov)
6147 ("python-pytest-runner" ,python-pytest-runner)))
6149 `(("python-bz2file" ,python-bz2file)))
6150 (home-page "https://github.com/dib-lab/screed/")
6151 (synopsis "Short read sequence database utilities")
6152 (description "Screed parses FASTA and FASTQ files and generates databases.
6153 Values such as sequence name, sequence description, sequence quality and the
6154 sequence itself can be retrieved from these databases.")
6155 (license license:bsd-3)))
6157 (define-public python2-screed
6158 (package-with-python2 python-screed))
6160 (define-public sra-tools
6168 (url "https://github.com/ncbi/sra-tools")
6170 (file-name (git-file-name name version))
6173 "1cr2mijkfs5sm35ffjs6861qsd1qkgnhnbavdv65zg5d655abbjf"))))
6174 (build-system gnu-build-system)
6176 `(#:parallel-build? #f ; not supported
6177 #:tests? #f ; no "check" target
6179 (list (string-append "DEFAULT_CRT="
6180 (assoc-ref %build-inputs "ncbi-vdb")
6182 (string-append "DEFAULT_KFG="
6183 (assoc-ref %build-inputs "ncbi-vdb")
6185 (string-append "VDB_LIBDIR="
6186 (assoc-ref %build-inputs "ncbi-vdb")
6187 ,(if (string-prefix? "x86_64"
6188 (or (%current-target-system)
6193 (modify-phases %standard-phases
6194 (add-before 'configure 'set-perl-search-path
6196 ;; Work around "dotless @INC" build failure.
6198 (string-append (getcwd) "/setup:"
6199 (getenv "PERL5LIB")))
6202 (lambda* (#:key inputs outputs #:allow-other-keys)
6203 ;; The build system expects a directory containing the sources and
6204 ;; raw build output of ncbi-vdb, including files that are not
6205 ;; installed. Since we are building against an installed version of
6206 ;; ncbi-vdb, the following modifications are needed.
6207 (substitute* "setup/konfigure.perl"
6208 ;; Make the configure script look for the "ilib" directory of
6209 ;; "ncbi-vdb" without first checking for the existence of a
6210 ;; matching library in its "lib" directory.
6211 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
6212 "my $f = File::Spec->catdir($ilibdir, $ilib);")
6213 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
6214 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
6215 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
6218 (substitute* "tools/copycat/Makefile"
6219 (("smagic-static") "lmagic"))
6220 (substitute* "tools/driver-tool/utf8proc/Makefile"
6221 (("CC\\?=gcc") "myCC=gcc")
6222 (("\\(CC\\)") "(myCC)"))
6224 ;; The 'configure' script doesn't recognize things like
6225 ;; '--enable-fast-install'.
6226 (invoke "./configure"
6227 (string-append "--build-prefix=" (getcwd) "/build")
6228 (string-append "--prefix=" (assoc-ref outputs "out"))
6229 (string-append "--debug")
6230 (string-append "--with-fuse-prefix="
6231 (assoc-ref inputs "fuse"))
6232 (string-append "--with-magic-prefix="
6233 (assoc-ref inputs "libmagic"))
6234 ;; TODO: building with libxml2 fails with linker errors
6236 (string-append "--with-xml2-prefix="
6237 (assoc-ref inputs "libxml2"))
6238 (string-append "--with-ncbi-vdb-sources="
6239 (assoc-ref inputs "ncbi-vdb"))
6240 (string-append "--with-ncbi-vdb-build="
6241 (assoc-ref inputs "ncbi-vdb"))
6242 (string-append "--with-ngs-sdk-prefix="
6243 (assoc-ref inputs "ngs-sdk"))
6244 (string-append "--with-hdf5-prefix="
6245 (assoc-ref inputs "hdf5")))
6247 (native-inputs `(("perl" ,perl)))
6249 `(("ngs-sdk" ,ngs-sdk)
6250 ("ncbi-vdb" ,ncbi-vdb)
6255 ("python" ,python-wrapper)))
6257 "https://trace.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
6258 (synopsis "Tools and libraries for reading and writing sequencing data")
6260 "The SRA Toolkit from NCBI is a collection of tools and libraries for
6261 reading of sequencing files from the Sequence Read Archive (SRA) database and
6262 writing files into the .sra format.")
6263 (license license:public-domain)))
6265 (define-public seqan
6271 (uri (string-append "https://github.com/seqan/seqan/releases/"
6272 "download/seqan-v" version
6273 "/seqan-library-" version ".tar.xz"))
6276 "19a1rlxx03qy1i1iriicly68w64yjxbv24g9gdywnfmq998v35yx"))))
6277 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6278 ;; makes sense to split the outputs.
6279 (outputs '("out" "doc"))
6280 (build-system trivial-build-system)
6282 `(#:modules ((guix build utils))
6285 (use-modules (guix build utils))
6286 (let ((tar (assoc-ref %build-inputs "tar"))
6287 (xz (assoc-ref %build-inputs "xz"))
6288 (out (assoc-ref %outputs "out"))
6289 (doc (assoc-ref %outputs "doc")))
6290 (setenv "PATH" (string-append tar "/bin:" xz "/bin"))
6291 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6292 (chdir (string-append "seqan-library-" ,version))
6293 (copy-recursively "include" (string-append out "/include"))
6294 (copy-recursively "share" (string-append doc "/share"))
6297 `(("source" ,source)
6300 (home-page "http://www.seqan.de")
6301 (synopsis "Library for nucleotide sequence analysis")
6303 "SeqAn is a C++ library of efficient algorithms and data structures for
6304 the analysis of sequences with the focus on biological data. It contains
6305 algorithms and data structures for string representation and their
6306 manipulation, online and indexed string search, efficient I/O of
6307 bioinformatics file formats, sequence alignment, and more.")
6308 (license license:bsd-3)))
6310 (define-public seqan-1
6311 (package (inherit seqan)
6316 (uri (string-append "http://packages.seqan.de/seqan-library/"
6317 "seqan-library-" version ".tar.bz2"))
6320 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
6321 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6322 ;; makes sense to split the outputs.
6323 (outputs '("out" "doc"))
6324 (build-system trivial-build-system)
6326 `(#:modules ((guix build utils))
6329 (use-modules (guix build utils))
6330 (let ((tar (assoc-ref %build-inputs "tar"))
6331 (bzip (assoc-ref %build-inputs "bzip2"))
6332 (out (assoc-ref %outputs "out"))
6333 (doc (assoc-ref %outputs "doc")))
6334 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
6335 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6336 (chdir (string-append "seqan-library-" ,version))
6337 (copy-recursively "include" (string-append out "/include"))
6338 (copy-recursively "share" (string-append doc "/share"))
6341 `(("source" ,source)
6343 ("bzip2" ,bzip2)))))
6345 (define-public seqmagick
6352 (uri (pypi-uri "seqmagick" version))
6355 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
6356 (build-system python-build-system)
6358 `(("python-biopython" ,python-biopython)))
6360 `(("python-nose" ,python-nose)))
6361 (home-page "https://github.com/fhcrc/seqmagick")
6362 (synopsis "Tools for converting and modifying sequence files")
6364 "Bioinformaticians often have to convert sequence files between formats
6365 and do little manipulations on them, and it's not worth writing scripts for
6366 that. Seqmagick is a utility to expose the file format conversion in
6367 BioPython in a convenient way. Instead of having a big mess of scripts, there
6368 is one that takes arguments.")
6369 (license license:gpl3)))
6371 (define-public seqtk
6378 (url "https://github.com/lh3/seqtk")
6379 (commit (string-append "v" version))))
6380 (file-name (git-file-name name version))
6383 "1bfzlqa84b5s1qi22blmmw2s8xdyp9h9ydcq22pfjhh5gab3yz6l"))))
6384 (build-system gnu-build-system)
6387 (modify-phases %standard-phases
6390 ;; There are no tests, so we just run a sanity check.
6391 (lambda _ (invoke "./seqtk" "seq") #t))
6393 (lambda* (#:key outputs #:allow-other-keys)
6394 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6395 (install-file "seqtk" bin)
6399 (home-page "https://github.com/lh3/seqtk")
6400 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
6402 "Seqtk is a fast and lightweight tool for processing sequences in the
6403 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
6404 optionally compressed by gzip.")
6405 (license license:expat)))
6407 (define-public snap-aligner
6409 (name "snap-aligner")
6410 (version "1.0beta.18")
6414 (url "https://github.com/amplab/snap")
6415 (commit (string-append "v" version))))
6416 (file-name (git-file-name name version))
6419 "01w3qq4wm07z73vky0cfwlmrbf50n3w722cxrlzxfi99mnb808d8"))))
6420 (build-system gnu-build-system)
6423 (modify-phases %standard-phases
6425 (replace 'check (lambda _ (invoke "./unit_tests") #t))
6427 (lambda* (#:key outputs #:allow-other-keys)
6428 (let* ((out (assoc-ref outputs "out"))
6429 (bin (string-append out "/bin")))
6430 (install-file "snap-aligner" bin)
6431 (install-file "SNAPCommand" bin)
6435 (home-page "http://snap.cs.berkeley.edu/")
6436 (synopsis "Short read DNA sequence aligner")
6438 "SNAP is a fast and accurate aligner for short DNA reads. It is
6439 optimized for modern read lengths of 100 bases or higher, and takes advantage
6440 of these reads to align data quickly through a hash-based indexing scheme.")
6441 ;; 32-bit systems are not supported by the unpatched code.
6442 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
6443 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
6444 ;; systems without a lot of memory cannot make good use of this program.
6445 (supported-systems '("x86_64-linux"))
6446 (license license:asl2.0)))
6448 (define-public sortmerna
6456 (url "https://github.com/biocore/sortmerna")
6458 (file-name (git-file-name name version))
6461 "0j3mbz4n25738yijmjbr5r4fyvkgm8v5vn3sshyfvmyqf5q9byqf"))))
6462 (build-system gnu-build-system)
6463 (outputs '("out" ;for binaries
6464 "db")) ;for sequence databases
6467 (modify-phases %standard-phases
6469 (lambda* (#:key outputs #:allow-other-keys)
6470 (let* ((out (assoc-ref outputs "out"))
6471 (bin (string-append out "/bin"))
6472 (db (assoc-ref outputs "db"))
6474 (string-append db "/share/sortmerna/rRNA_databases")))
6475 (install-file "sortmerna" bin)
6476 (install-file "indexdb_rna" bin)
6477 (for-each (lambda (file)
6478 (install-file file share))
6479 (find-files "rRNA_databases" ".*fasta"))
6483 (home-page "https://bioinfo.lifl.fr/RNA/sortmerna/")
6484 (synopsis "Biological sequence analysis tool for NGS reads")
6486 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
6487 and operational taxonomic unit (OTU) picking of next generation
6488 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
6489 allows for fast and sensitive analyses of nucleotide sequences. The main
6490 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
6491 ;; The source includes x86 specific code
6492 (supported-systems '("x86_64-linux" "i686-linux"))
6493 (license license:lgpl3)))
6502 (url "https://github.com/alexdobin/STAR")
6504 (file-name (git-file-name name version))
6507 "1hgiqw5qhs0pc1xazzihcfd92na02xyq2kb469z04y1v51kpvvjq"))
6508 (modules '((guix build utils)))
6511 (substitute* "source/Makefile"
6513 ;; Remove pre-built binaries and bundled htslib sources.
6514 (delete-file-recursively "bin/MacOSX_x86_64")
6515 (delete-file-recursively "bin/Linux_x86_64")
6516 (delete-file-recursively "bin/Linux_x86_64_static")
6517 (delete-file-recursively "source/htslib")
6519 (build-system gnu-build-system)
6521 '(#:tests? #f ;no check target
6522 #:make-flags '("STAR")
6524 (modify-phases %standard-phases
6525 (add-after 'unpack 'enter-source-dir
6526 (lambda _ (chdir "source") #t))
6527 (add-after 'enter-source-dir 'make-reproducible
6529 (substitute* "Makefile"
6530 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
6531 (string-append pre "Built with Guix" post)))
6533 ;; See https://github.com/alexdobin/STAR/pull/562
6534 (add-after 'enter-source-dir 'add-missing-header
6536 (substitute* "SoloReadFeature_inputRecords.cpp"
6537 (("#include \"binarySearch2.h\"" h)
6538 (string-append h "\n#include <math.h>")))
6540 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
6542 (substitute* "Makefile"
6543 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
6545 (substitute* '("BAMfunctions.cpp"
6550 "bamRemoveDuplicates.cpp")
6551 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
6552 (string-append "#include <" header ">")))
6553 (substitute* "IncludeDefine.h"
6554 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
6555 (string-append "<" header ">")))
6558 (lambda* (#:key outputs #:allow-other-keys)
6559 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6560 (install-file "STAR" bin))
6562 (delete 'configure))))
6566 `(("htslib" ,htslib)
6568 (home-page "https://github.com/alexdobin/STAR")
6569 (synopsis "Universal RNA-seq aligner")
6571 "The Spliced Transcripts Alignment to a Reference (STAR) software is
6572 based on a previously undescribed RNA-seq alignment algorithm that uses
6573 sequential maximum mappable seed search in uncompressed suffix arrays followed
6574 by seed clustering and stitching procedure. In addition to unbiased de novo
6575 detection of canonical junctions, STAR can discover non-canonical splices and
6576 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
6578 ;; Only 64-bit systems are supported according to the README.
6579 (supported-systems '("x86_64-linux" "mips64el-linux"))
6580 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
6581 (license license:gpl3+)))
6583 (define-public starlong
6584 (package (inherit star)
6587 (substitute-keyword-arguments (package-arguments star)
6588 ((#:make-flags flags)
6591 `(modify-phases ,phases
6592 ;; Allow extra long sequence reads.
6593 (add-after 'unpack 'make-extra-long
6595 (substitute* "source/IncludeDefine.h"
6596 (("(#define DEF_readNameLengthMax ).*" _ match)
6597 (string-append match "900000\n")))
6600 (lambda* (#:key outputs #:allow-other-keys)
6601 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6602 (install-file "STARlong" bin))
6605 (define-public subread
6611 (uri (string-append "mirror://sourceforge/subread/subread-"
6612 version "/subread-" version "-source.tar.gz"))
6615 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
6616 (build-system gnu-build-system)
6618 `(#:tests? #f ;no "check" target
6619 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
6620 ;; optimizations by default, so we override these flags such that x86_64
6621 ;; flags are only added when the build target is an x86_64 system.
6623 (list (let ((system ,(or (%current-target-system)
6625 (flags '("-ggdb" "-fomit-frame-pointer"
6626 "-ffast-math" "-funroll-loops"
6627 "-fmessage-length=0"
6628 "-O9" "-Wall" "-DMAKE_FOR_EXON"
6630 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
6631 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
6632 (if (string-prefix? "x86_64" system)
6633 (string-append "CCFLAGS=" (string-join (append flags flags64)))
6634 (string-append "CCFLAGS=" (string-join flags))))
6635 "-f" "Makefile.Linux"
6636 "CC=gcc ${CCFLAGS}")
6638 (modify-phases %standard-phases
6639 (add-after 'unpack 'enter-dir
6640 (lambda _ (chdir "src") #t))
6642 (lambda* (#:key outputs #:allow-other-keys)
6643 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6645 (copy-recursively "../bin" bin))
6647 ;; no "configure" script
6648 (delete 'configure))))
6649 (inputs `(("zlib" ,zlib)))
6650 (home-page "http://bioinf.wehi.edu.au/subread-package/")
6651 (synopsis "Tool kit for processing next-gen sequencing data")
6653 "The subread package contains the following tools: subread aligner, a
6654 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
6655 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
6656 features; exactSNP: a SNP caller that discovers SNPs by testing signals
6657 against local background noises.")
6658 (license license:gpl3+)))
6660 (define-public stringtie
6666 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
6667 "stringtie-" version ".tar.gz"))
6670 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
6671 (modules '((guix build utils)))
6674 (delete-file-recursively "samtools-0.1.18")
6676 (build-system gnu-build-system)
6678 `(#:tests? #f ;no test suite
6680 (modify-phases %standard-phases
6681 ;; no configure script
6683 (add-before 'build 'use-system-samtools
6685 (substitute* "Makefile"
6686 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
6688 (substitute* '("gclib/GBam.h"
6690 (("#include \"(bam|sam|kstring).h\"" _ header)
6691 (string-append "#include <samtools/" header ".h>")))
6693 (add-after 'unpack 'remove-duplicate-typedef
6695 ;; This typedef conflicts with the typedef in
6696 ;; glibc-2.25/include/bits/types.h
6697 (substitute* "gclib/GThreads.h"
6698 (("typedef long long __intmax_t;") ""))
6701 (lambda* (#:key outputs #:allow-other-keys)
6702 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6703 (install-file "stringtie" bin)
6706 `(("samtools" ,samtools-0.1)
6708 (home-page "http://ccb.jhu.edu/software/stringtie/")
6709 (synopsis "Transcript assembly and quantification for RNA-Seq data")
6711 "StringTie is a fast and efficient assembler of RNA-Seq sequence
6712 alignments into potential transcripts. It uses a novel network flow algorithm
6713 as well as an optional de novo assembly step to assemble and quantitate
6714 full-length transcripts representing multiple splice variants for each gene
6715 locus. Its input can include not only the alignments of raw reads used by
6716 other transcript assemblers, but also alignments of longer sequences that have
6717 been assembled from those reads. To identify differentially expressed genes
6718 between experiments, StringTie's output can be processed either by the
6719 Cuffdiff or Ballgown programs.")
6720 (license license:artistic2.0)))
6722 (define-public taxtastic
6727 ;; The Pypi version does not include tests.
6730 (url "https://github.com/fhcrc/taxtastic")
6731 (commit (string-append "v" version))))
6732 (file-name (git-file-name name version))
6735 "1sv8mkg64jn7zdwf1jj71c16686yrwxk0apb1l8sjszy9p166g0p"))))
6736 (build-system python-build-system)
6739 (modify-phases %standard-phases
6740 (add-after 'unpack 'prepare-directory
6742 ;; The git checkout must be writable for tests.
6743 (for-each make-file-writable (find-files "."))
6744 ;; This test fails, but the error is not caught by the test
6745 ;; framework, so the tests fail...
6746 (substitute* "tests/test_taxit.py"
6747 (("self.cmd_fails\\(''\\)")
6748 "self.cmd_fails('nothing')"))
6749 ;; This version file is expected to be created with git describe.
6750 (mkdir-p "taxtastic/data")
6751 (with-output-to-file "taxtastic/data/ver"
6752 (lambda () (display ,version)))
6754 (add-after 'unpack 'python37-compatibility
6756 (substitute* "taxtastic/utils.py"
6757 (("import csv") "import csv, errno")
6758 (("os.errno") "errno"))
6761 ;; Note, this fails to run with "-v" as it tries to write to a
6762 ;; closed output stream.
6763 (lambda _ (invoke "python" "-m" "unittest") #t)))))
6765 `(("python-sqlalchemy" ,python-sqlalchemy)
6766 ("python-decorator" ,python-decorator)
6767 ("python-biopython" ,python-biopython)
6768 ("python-pandas" ,python-pandas)
6769 ("python-psycopg2" ,python-psycopg2)
6770 ("python-fastalite" ,python-fastalite)
6771 ("python-pyyaml" ,python-pyyaml)
6772 ("python-six" ,python-six)
6773 ("python-jinja2" ,python-jinja2)
6774 ("python-dendropy" ,python-dendropy)))
6775 (home-page "https://github.com/fhcrc/taxtastic")
6776 (synopsis "Tools for taxonomic naming and annotation")
6778 "Taxtastic is software written in python used to build and maintain
6779 reference packages i.e. collections of reference trees, reference alignments,
6780 profiles, and associated taxonomic information.")
6781 (license license:gpl3+)))
6783 (define-public vcftools
6790 "https://github.com/vcftools/vcftools/releases/download/v"
6791 version "/vcftools-" version ".tar.gz"))
6794 "1qqlx7flfv7axrjwkaz6njkscsl1d0jw98ns8d8bh1n1hd1pgz6v"))))
6795 (build-system gnu-build-system)
6797 `(#:tests? #f ; no "check" target
6799 "CFLAGS=-O2" ; override "-m64" flag
6800 (string-append "PREFIX=" (assoc-ref %outputs "out"))
6801 (string-append "MANDIR=" (assoc-ref %outputs "out")
6802 "/share/man/man1"))))
6804 `(("pkg-config" ,pkg-config)))
6808 (home-page "https://vcftools.github.io/")
6809 (synopsis "Tools for working with VCF files")
6811 "VCFtools is a program package designed for working with VCF files, such
6812 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
6813 provide easily accessible methods for working with complex genetic variation
6814 data in the form of VCF files.")
6815 ;; The license is declared as LGPLv3 in the README and
6816 ;; at https://vcftools.github.io/license.html
6817 (license license:lgpl3)))
6819 (define-public infernal
6825 (uri (string-append "http://eddylab.org/software/infernal/"
6826 "infernal-" version ".tar.gz"))
6829 "0pm8bm3s6nfa0av4x6m6h27lsg12b3lz3jm0fyh1mc77l2isd61v"))))
6830 (build-system gnu-build-system)
6833 ("python" ,python))) ; for tests
6834 (home-page "http://eddylab.org/infernal/")
6835 (synopsis "Inference of RNA alignments")
6836 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
6837 searching DNA sequence databases for RNA structure and sequence similarities.
6838 It is an implementation of a special case of profile stochastic context-free
6839 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
6840 profile, but it scores a combination of sequence consensus and RNA secondary
6841 structure consensus, so in many cases, it is more capable of identifying RNA
6842 homologs that conserve their secondary structure more than their primary
6844 ;; Infernal 1.1.3 requires VMX or SSE capability for parallel instructions.
6845 (supported-systems '("i686-linux" "x86_64-linux"))
6846 (license license:bsd-3)))
6848 (define-public r-scde
6855 (url "https://github.com/hms-dbmi/scde")
6857 (file-name (git-file-name name version))
6860 "10na2gyka24mszdxf92wz9h2c13hdf1ww30c68gfsw53lvvhhhxb"))))
6861 (build-system r-build-system)
6863 `(("r-rcpp" ,r-rcpp)
6864 ("r-rcpparmadillo" ,r-rcpparmadillo)
6867 ("r-rjson" ,r-rjson)
6868 ("r-cairo" ,r-cairo)
6869 ("r-rcolorbrewer" ,r-rcolorbrewer)
6870 ("r-edger" ,r-edger)
6871 ("r-quantreg" ,r-quantreg)
6873 ("r-rmtstat" ,r-rmtstat)
6874 ("r-extremes" ,r-extremes)
6875 ("r-pcamethods" ,r-pcamethods)
6876 ("r-biocparallel" ,r-biocparallel)
6877 ("r-flexmix" ,r-flexmix)))
6878 (home-page "https://hms-dbmi.github.io/scde/")
6879 (synopsis "R package for analyzing single-cell RNA-seq data")
6880 (description "The SCDE package implements a set of statistical methods for
6881 analyzing single-cell RNA-seq data. SCDE fits individual error models for
6882 single-cell RNA-seq measurements. These models can then be used for
6883 assessment of differential expression between groups of cells, as well as
6884 other types of analysis. The SCDE package also contains the pagoda framework
6885 which applies pathway and gene set overdispersion analysis to identify aspects
6886 of transcriptional heterogeneity among single cells.")
6887 ;; See https://github.com/hms-dbmi/scde/issues/38
6888 (license license:gpl2)))
6890 (define-public r-centipede
6892 (name "r-centipede")
6896 (uri (string-append "http://download.r-forge.r-project.org/"
6897 "src/contrib/CENTIPEDE_" version ".tar.gz"))
6900 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
6901 (build-system r-build-system)
6902 (home-page "http://centipede.uchicago.edu/")
6903 (synopsis "Predict transcription factor binding sites")
6905 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
6906 of the genome that are bound by particular transcription factors. It starts
6907 by identifying a set of candidate binding sites, and then aims to classify the
6908 sites according to whether each site is bound or not bound by a transcription
6909 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
6910 between two different types of motif instances using as much relevant
6911 information as possible.")
6912 (license (list license:gpl2+ license:gpl3+))))
6914 (define-public r-genefilter
6916 (name "r-genefilter")
6921 (uri (bioconductor-uri "genefilter" version))
6924 "1sbbrnq6p90fri0ik6aq2zw26kasw63nyiy7xkzrj6vgyq7x258g"))))
6925 (build-system r-build-system)
6927 `(("gfortran" ,gfortran)
6928 ("r-knitr" ,r-knitr)))
6930 `(("r-annotate" ,r-annotate)
6931 ("r-annotationdbi" ,r-annotationdbi)
6932 ("r-biobase" ,r-biobase)
6933 ("r-biocgenerics" ,r-biocgenerics)
6934 ("r-survival" ,r-survival)))
6935 (home-page "https://bioconductor.org/packages/genefilter")
6936 (synopsis "Filter genes from high-throughput experiments")
6938 "This package provides basic functions for filtering genes from
6939 high-throughput sequencing experiments.")
6940 (license license:artistic2.0)))
6942 (define-public r-deseq2
6949 (uri (bioconductor-uri "DESeq2" version))
6952 "0xh12c2skr0bbv893p05gvbismkcnqw8zwh7yz4wmycgajfzg2pp"))))
6953 (properties `((upstream-name . "DESeq2")))
6954 (build-system r-build-system)
6956 `(("r-biobase" ,r-biobase)
6957 ("r-biocgenerics" ,r-biocgenerics)
6958 ("r-biocparallel" ,r-biocparallel)
6959 ("r-genefilter" ,r-genefilter)
6960 ("r-geneplotter" ,r-geneplotter)
6961 ("r-genomicranges" ,r-genomicranges)
6962 ("r-ggplot2" ,r-ggplot2)
6963 ("r-iranges" ,r-iranges)
6964 ("r-locfit" ,r-locfit)
6966 ("r-rcpparmadillo" ,r-rcpparmadillo)
6967 ("r-s4vectors" ,r-s4vectors)
6968 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6970 `(("r-knitr" ,r-knitr)))
6971 (home-page "https://bioconductor.org/packages/DESeq2")
6972 (synopsis "Differential gene expression analysis")
6974 "This package provides functions to estimate variance-mean dependence in
6975 count data from high-throughput nucleotide sequencing assays and test for
6976 differential expression based on a model using the negative binomial
6978 (license license:lgpl3+)))
6980 (define-public r-dexseq
6987 (uri (bioconductor-uri "DEXSeq" version))
6990 "1m03awaw06mfv5gszq23k5apsqqzjqa5rcwp20y4xbpl7bywpsyl"))))
6991 (properties `((upstream-name . "DEXSeq")))
6992 (build-system r-build-system)
6994 `(("r-annotationdbi" ,r-annotationdbi)
6995 ("r-biobase" ,r-biobase)
6996 ("r-biocgenerics" ,r-biocgenerics)
6997 ("r-biocparallel" ,r-biocparallel)
6998 ("r-biomart" ,r-biomart)
6999 ("r-deseq2" ,r-deseq2)
7000 ("r-genefilter" ,r-genefilter)
7001 ("r-geneplotter" ,r-geneplotter)
7002 ("r-genomicranges" ,r-genomicranges)
7003 ("r-hwriter" ,r-hwriter)
7004 ("r-iranges" ,r-iranges)
7005 ("r-rcolorbrewer" ,r-rcolorbrewer)
7006 ("r-rsamtools" ,r-rsamtools)
7007 ("r-s4vectors" ,r-s4vectors)
7008 ("r-statmod" ,r-statmod)
7009 ("r-stringr" ,r-stringr)
7010 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7012 `(("r-knitr" ,r-knitr)))
7013 (home-page "https://bioconductor.org/packages/DEXSeq")
7014 (synopsis "Inference of differential exon usage in RNA-Seq")
7016 "This package is focused on finding differential exon usage using RNA-seq
7017 exon counts between samples with different experimental designs. It provides
7018 functions that allows the user to make the necessary statistical tests based
7019 on a model that uses the negative binomial distribution to estimate the
7020 variance between biological replicates and generalized linear models for
7021 testing. The package also provides functions for the visualization and
7022 exploration of the results.")
7023 (license license:gpl3+)))
7025 (define-public r-annotationforge
7027 (name "r-annotationforge")
7032 (uri (bioconductor-uri "AnnotationForge" version))
7035 "1a2155jxbwc6qr3dcyvp850grhdr7czc7bs3s87ff4sgdl0jp3jw"))))
7037 `((upstream-name . "AnnotationForge")))
7038 (build-system r-build-system)
7040 `(("r-annotationdbi" ,r-annotationdbi)
7041 ("r-biobase" ,r-biobase)
7042 ("r-biocgenerics" ,r-biocgenerics)
7044 ("r-rcurl" ,r-rcurl)
7045 ("r-rsqlite" ,r-rsqlite)
7046 ("r-s4vectors" ,r-s4vectors)
7049 `(("r-knitr" ,r-knitr)))
7050 (home-page "https://bioconductor.org/packages/AnnotationForge")
7051 (synopsis "Code for building annotation database packages")
7053 "This package provides code for generating Annotation packages and their
7054 databases. Packages produced are intended to be used with AnnotationDbi.")
7055 (license license:artistic2.0)))
7057 (define-public r-rbgl
7064 (uri (bioconductor-uri "RBGL" version))
7067 "079599a6xn2i7snfn2vgshkw0c00rrfhj44pvi03ap8id29bkayy"))))
7068 (properties `((upstream-name . "RBGL")))
7069 (build-system r-build-system)
7072 ("r-graph" ,r-graph)))
7073 (home-page "https://www.bioconductor.org/packages/RBGL")
7074 (synopsis "Interface to the Boost graph library")
7076 "This package provides a fairly extensive and comprehensive interface to
7077 the graph algorithms contained in the Boost library.")
7078 (license license:artistic2.0)))
7080 (define-public r-gseabase
7087 (uri (bioconductor-uri "GSEABase" version))
7090 "1k4faj53cwvqijad8cf7fcghzxcv9shlbpl8n73bsncc8k192y2j"))))
7091 (properties `((upstream-name . "GSEABase")))
7092 (build-system r-build-system)
7094 `(("r-annotate" ,r-annotate)
7095 ("r-annotationdbi" ,r-annotationdbi)
7096 ("r-biobase" ,r-biobase)
7097 ("r-biocgenerics" ,r-biocgenerics)
7098 ("r-graph" ,r-graph)
7101 `(("r-knitr" ,r-knitr)))
7102 (home-page "https://bioconductor.org/packages/GSEABase")
7103 (synopsis "Gene set enrichment data structures and methods")
7105 "This package provides classes and methods to support @dfn{Gene Set
7106 Enrichment Analysis} (GSEA).")
7107 (license license:artistic2.0)))
7109 (define-public r-category
7116 (uri (bioconductor-uri "Category" version))
7119 "1grspdzk5a4vidnxwcd1jmy1vcn494aydsp3vydx235yv7iqac1b"))))
7120 (properties `((upstream-name . "Category")))
7121 (build-system r-build-system)
7123 `(("r-annotate" ,r-annotate)
7124 ("r-annotationdbi" ,r-annotationdbi)
7125 ("r-biobase" ,r-biobase)
7126 ("r-biocgenerics" ,r-biocgenerics)
7127 ("r-genefilter" ,r-genefilter)
7128 ("r-graph" ,r-graph)
7129 ("r-gseabase" ,r-gseabase)
7130 ("r-matrix" ,r-matrix)
7133 (home-page "https://bioconductor.org/packages/Category")
7134 (synopsis "Category analysis")
7136 "This package provides a collection of tools for performing category
7138 (license license:artistic2.0)))
7140 (define-public r-gostats
7147 (uri (bioconductor-uri "GOstats" version))
7150 "00q39cyv4l28r6s9gjnd0qhl7h80vmwp4lpmchisqzj44xzyics9"))))
7151 (properties `((upstream-name . "GOstats")))
7152 (build-system r-build-system)
7154 `(("r-annotate" ,r-annotate)
7155 ("r-annotationdbi" ,r-annotationdbi)
7156 ("r-annotationforge" ,r-annotationforge)
7157 ("r-biobase" ,r-biobase)
7158 ("r-category" ,r-category)
7159 ("r-go-db" ,r-go-db)
7160 ("r-graph" ,r-graph)
7161 ("r-rgraphviz" ,r-rgraphviz)
7162 ("r-rbgl" ,r-rbgl)))
7163 (home-page "https://bioconductor.org/packages/GOstats")
7164 (synopsis "Tools for manipulating GO and microarrays")
7166 "This package provides a set of tools for interacting with GO and
7167 microarray data. A variety of basic manipulation tools for graphs, hypothesis
7168 testing and other simple calculations.")
7169 (license license:artistic2.0)))
7171 (define-public r-shortread
7173 (name "r-shortread")
7178 (uri (bioconductor-uri "ShortRead" version))
7181 "0l4kdln69y6yhln0xiv2jmpxg05fjcglln406p43a2bqvk2lr03d"))))
7182 (properties `((upstream-name . "ShortRead")))
7183 (build-system r-build-system)
7187 `(("r-biobase" ,r-biobase)
7188 ("r-biocgenerics" ,r-biocgenerics)
7189 ("r-biocparallel" ,r-biocparallel)
7190 ("r-biostrings" ,r-biostrings)
7191 ("r-genomeinfodb" ,r-genomeinfodb)
7192 ("r-genomicalignments" ,r-genomicalignments)
7193 ("r-genomicranges" ,r-genomicranges)
7194 ("r-hwriter" ,r-hwriter)
7195 ("r-iranges" ,r-iranges)
7196 ("r-lattice" ,r-lattice)
7197 ("r-latticeextra" ,r-latticeextra)
7198 ("r-rsamtools" ,r-rsamtools)
7199 ("r-s4vectors" ,r-s4vectors)
7200 ("r-xvector" ,r-xvector)
7201 ("r-zlibbioc" ,r-zlibbioc)))
7202 (home-page "https://bioconductor.org/packages/ShortRead")
7203 (synopsis "FASTQ input and manipulation tools")
7205 "This package implements sampling, iteration, and input of FASTQ files.
7206 It includes functions for filtering and trimming reads, and for generating a
7207 quality assessment report. Data are represented as
7208 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
7209 purposes. The package also contains legacy support for early single-end,
7210 ungapped alignment formats.")
7211 (license license:artistic2.0)))
7213 (define-public r-systempiper
7215 (name "r-systempiper")
7220 (uri (bioconductor-uri "systemPipeR" version))
7223 "01ilhlrvy28jfdyxjria4024yryj5zgympgqznw17g3y3az78kk2"))))
7224 (properties `((upstream-name . "systemPipeR")))
7225 (build-system r-build-system)
7227 `(("r-annotate" ,r-annotate)
7228 ("r-assertthat" ,r-assertthat)
7229 ("r-batchtools" ,r-batchtools)
7230 ("r-biostrings" ,r-biostrings)
7231 ("r-deseq2" ,r-deseq2)
7233 ("r-edger" ,r-edger)
7234 ("r-genomicfeatures" ,r-genomicfeatures)
7235 ("r-genomicranges" ,r-genomicranges)
7236 ("r-ggplot2" ,r-ggplot2)
7237 ("r-go-db" ,r-go-db)
7238 ("r-gostats" ,r-gostats)
7239 ("r-limma" ,r-limma)
7240 ("r-magrittr" ,r-magrittr)
7241 ("r-pheatmap" ,r-pheatmap)
7242 ("r-rjson" ,r-rjson)
7243 ("r-rsamtools" ,r-rsamtools)
7245 ("r-shortread" ,r-shortread)
7246 ("r-stringr" ,r-stringr)
7247 ("r-summarizedexperiment" ,r-summarizedexperiment)
7249 ("r-variantannotation" ,r-variantannotation)))
7251 `(("r-knitr" ,r-knitr)))
7252 (home-page "https://github.com/tgirke/systemPipeR")
7253 (synopsis "Next generation sequencing workflow and reporting environment")
7255 "This R package provides tools for building and running automated
7256 end-to-end analysis workflows for a wide range of @dfn{next generation
7257 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
7258 Important features include a uniform workflow interface across different NGS
7259 applications, automated report generation, and support for running both R and
7260 command-line software, such as NGS aligners or peak/variant callers, on local
7261 computers or compute clusters. Efficient handling of complex sample sets and
7262 experimental designs is facilitated by a consistently implemented sample
7263 annotation infrastructure.")
7264 (license license:artistic2.0)))
7266 (define-public r-grohmm
7273 (uri (bioconductor-uri "groHMM" version))
7276 "04z9qq1xwdsaxbqhyld37w0ybvzly9pc1hcyrnwdbyjwd7n1fncb"))))
7277 (properties `((upstream-name . "groHMM")))
7278 (build-system r-build-system)
7280 `(("r-genomeinfodb" ,r-genomeinfodb)
7281 ("r-genomicalignments" ,r-genomicalignments)
7282 ("r-genomicranges" ,r-genomicranges)
7283 ("r-iranges" ,r-iranges)
7285 ("r-rtracklayer" ,r-rtracklayer)
7286 ("r-s4vectors" ,r-s4vectors)))
7287 (home-page "https://github.com/Kraus-Lab/groHMM")
7288 (synopsis "GRO-seq analysis pipeline")
7290 "This package provides a pipeline for the analysis of GRO-seq data.")
7291 (license license:gpl3+)))
7293 (define-public vsearch
7301 (url "https://github.com/torognes/vsearch")
7302 (commit (string-append "v" version))))
7303 (file-name (git-file-name name version))
7306 "0vhrpjfdf75ba04b24xknp41790cvcgwl0vgpy7qbzj5xh2521ss"))
7307 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
7310 ;; Remove bundled cityhash sources. The vsearch source is adjusted
7311 ;; for this in the patch.
7312 (delete-file "src/city.h")
7313 (delete-file "src/citycrc.h")
7314 (delete-file "src/city.cc")
7316 (build-system gnu-build-system)
7320 ("cityhash" ,cityhash)))
7322 `(("autoconf" ,autoconf)
7323 ("automake" ,automake)))
7324 (synopsis "Sequence search tools for metagenomics")
7326 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
7327 dereplication, pairwise alignment, shuffling, subsampling, sorting and
7328 masking. The tool takes advantage of parallelism in the form of SIMD
7329 vectorization as well as multiple threads to perform accurate alignments at
7330 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
7331 Needleman-Wunsch).")
7332 (home-page "https://github.com/torognes/vsearch")
7333 ;; vsearch uses non-portable SSE intrinsics so building fails on other
7335 (supported-systems '("x86_64-linux"))
7336 ;; Dual licensed; also includes public domain source.
7337 (license (list license:gpl3 license:bsd-2))))
7339 (define-public pardre
7342 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
7347 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
7351 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
7352 (build-system gnu-build-system)
7354 `(#:tests? #f ; no tests included
7356 (modify-phases %standard-phases
7359 (lambda* (#:key outputs #:allow-other-keys)
7360 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
7361 (install-file "ParDRe" bin)
7364 `(("openmpi" ,openmpi)
7366 (synopsis "Parallel tool to remove duplicate DNA reads")
7368 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
7369 Duplicate reads can be seen as identical or nearly identical sequences with
7370 some mismatches. This tool lets users avoid the analysis of unnecessary
7371 reads, reducing the time of subsequent procedures with the
7372 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
7373 in order to exploit the parallel capabilities of multicore clusters. It is
7374 faster than multithreaded counterparts (end of 2015) for the same number of
7375 cores and, thanks to the message-passing technology, it can be executed on
7377 (home-page "https://sourceforge.net/projects/pardre/")
7378 (license license:gpl3+)))
7380 (define-public ruby-bio-kseq
7382 (name "ruby-bio-kseq")
7387 (uri (rubygems-uri "bio-kseq" version))
7390 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
7391 (build-system ruby-build-system)
7393 `(#:test-target "spec"))
7395 `(("bundler" ,bundler)
7396 ("ruby-rspec" ,ruby-rspec)
7397 ("ruby-rake-compiler" ,ruby-rake-compiler)))
7400 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
7402 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
7403 FASTQ parsing code. It provides a fast iterator over sequences and their
7405 (home-page "https://github.com/gusevfe/bio-kseq")
7406 (license license:expat)))
7408 (define-public bio-locus
7415 (uri (rubygems-uri "bio-locus" version))
7418 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
7419 (build-system ruby-build-system)
7421 `(("ruby-rspec" ,ruby-rspec)))
7422 (synopsis "Tool for fast querying of genome locations")
7424 "Bio-locus is a tabix-like tool for fast querying of genome
7425 locations. Many file formats in bioinformatics contain records that
7426 start with a chromosome name and a position for a SNP, or a start-end
7427 position for indels. Bio-locus allows users to store this chr+pos or
7428 chr+pos+alt information in a database.")
7429 (home-page "https://github.com/pjotrp/bio-locus")
7430 (license license:expat)))
7432 (define-public bio-blastxmlparser
7434 (name "bio-blastxmlparser")
7438 (uri (rubygems-uri "bio-blastxmlparser" version))
7441 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
7442 (build-system ruby-build-system)
7444 `(("ruby-bio-logger" ,ruby-bio-logger)
7445 ("ruby-nokogiri" ,ruby-nokogiri)))
7447 `(("ruby-rspec" ,ruby-rspec)))
7448 (synopsis "Fast big data BLAST XML parser and library")
7450 "Very fast parallel big-data BLAST XML file parser which can be used as
7451 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
7452 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
7453 (home-page "https://github.com/pjotrp/blastxmlparser")
7454 (license license:expat)))
7456 (define-public bioruby
7463 (uri (rubygems-uri "bio" version))
7466 "1d56amdsjv1mag7m6gv2w0xij8hqx1v5xbdjsix8sp3yp36m7938"))))
7467 (build-system ruby-build-system)
7469 `(("ruby-libxml" ,ruby-libxml)))
7471 `(("which" ,which))) ; required for test phase
7474 (modify-phases %standard-phases
7475 (add-before 'build 'patch-test-command
7477 (substitute* '("test/functional/bio/test_command.rb")
7478 (("/bin/sh") (which "sh")))
7479 (substitute* '("test/functional/bio/test_command.rb")
7480 (("/bin/ls") (which "ls")))
7481 (substitute* '("test/functional/bio/test_command.rb")
7482 (("which") (which "which")))
7483 (substitute* '("test/functional/bio/test_command.rb",
7484 "test/data/command/echoarg2.sh")
7485 (("/bin/echo") (which "echo")))
7487 (synopsis "Ruby library, shell and utilities for bioinformatics")
7488 (description "BioRuby comes with a comprehensive set of Ruby development
7489 tools and libraries for bioinformatics and molecular biology. BioRuby has
7490 components for sequence analysis, pathway analysis, protein modelling and
7491 phylogenetic analysis; it supports many widely used data formats and provides
7492 easy access to databases, external programs and public web services, including
7493 BLAST, KEGG, GenBank, MEDLINE and GO.")
7494 (home-page "http://bioruby.org/")
7495 ;; Code is released under Ruby license, except for setup
7496 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
7497 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
7499 (define-public r-biocviews
7501 (name "r-biocviews")
7505 (uri (bioconductor-uri "biocViews" version))
7508 "0zcx8gha3x3jc0ra6ii6wwq2vfsmffrrnilknbq8h5xjrl55m6ci"))))
7510 `((upstream-name . "biocViews")))
7511 (build-system r-build-system)
7513 `(("r-biobase" ,r-biobase)
7514 ("r-biocmanager" ,r-biocmanager)
7515 ("r-graph" ,r-graph)
7517 ("r-rcurl" ,r-rcurl)
7519 ("r-runit" ,r-runit)))
7520 (home-page "https://bioconductor.org/packages/biocViews")
7521 (synopsis "Bioconductor package categorization helper")
7522 (description "The purpose of biocViews is to create HTML pages that
7523 categorize packages in a Bioconductor package repository according to keywords,
7524 also known as views, in a controlled vocabulary.")
7525 (license license:artistic2.0)))
7527 (define-public r-biocstyle
7529 (name "r-biocstyle")
7533 (uri (bioconductor-uri "BiocStyle" version))
7536 "07rjl2n4sazdg581zh7w3yykzphgr2gpz41ba4ryqs7347vh9nbf"))))
7538 `((upstream-name . "BiocStyle")))
7539 (build-system r-build-system)
7541 `(("r-biocmanager" ,r-biocmanager)
7542 ("r-bookdown" ,r-bookdown)
7543 ("r-knitr" ,r-knitr)
7544 ("r-rmarkdown" ,r-rmarkdown)
7545 ("r-yaml" ,r-yaml)))
7547 `(("r-knitr" ,r-knitr)))
7548 (home-page "https://bioconductor.org/packages/BiocStyle")
7549 (synopsis "Bioconductor formatting styles")
7550 (description "This package provides standard formatting styles for
7551 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
7553 (license license:artistic2.0)))
7555 (define-public r-bioccheck
7557 (name "r-bioccheck")
7561 (uri (bioconductor-uri "BiocCheck" version))
7564 "1p9ys18sn1crxw1iac2jdgqvwpb5hjd9nfxx0qn0ncrv0b550mny"))))
7566 `((upstream-name . "BiocCheck")))
7567 (build-system r-build-system)
7570 (modify-phases %standard-phases
7571 ;; This package can be used by calling BiocCheck(<package>) from
7572 ;; within R, or by running R CMD BiocCheck <package>. This phase
7573 ;; makes sure the latter works. For this to work, the BiocCheck
7574 ;; script must be somewhere on the PATH (not the R bin directory).
7575 (add-after 'install 'install-bioccheck-subcommand
7576 (lambda* (#:key outputs #:allow-other-keys)
7577 (let* ((out (assoc-ref outputs "out"))
7578 (dest-dir (string-append out "/bin"))
7580 (string-append out "/site-library/BiocCheck/script/")))
7582 (symlink (string-append script-dir "/checkBadDeps.R")
7583 (string-append dest-dir "/checkBadDeps.R"))
7584 (symlink (string-append script-dir "/BiocCheck")
7585 (string-append dest-dir "/BiocCheck")))
7588 `(("r-codetools" ,r-codetools)
7589 ("r-graph" ,r-graph)
7591 ("r-knitr" ,r-knitr)
7592 ("r-optparse" ,r-optparse)
7593 ("r-biocmanager" ,r-biocmanager)
7594 ("r-biocviews" ,r-biocviews)
7595 ("r-stringdist" ,r-stringdist)))
7597 `(("r-knitr" ,r-knitr)))
7598 (home-page "https://bioconductor.org/packages/BiocCheck")
7599 (synopsis "Executes Bioconductor-specific package checks")
7600 (description "This package contains tools to perform additional quality
7601 checks on R packages that are to be submitted to the Bioconductor repository.")
7602 (license license:artistic2.0)))
7604 (define-public r-s4vectors
7606 (name "r-s4vectors")
7610 (uri (bioconductor-uri "S4Vectors" version))
7613 "1ddr3ngyczx332zw9ai1a6h7442lgrbfcj8vrhvbkdkzqwj14xmb"))))
7615 `((upstream-name . "S4Vectors")))
7616 (build-system r-build-system)
7618 `(("r-biocgenerics" ,r-biocgenerics)))
7619 (home-page "https://bioconductor.org/packages/S4Vectors")
7620 (synopsis "S4 implementation of vectors and lists")
7622 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7623 classes and a set of generic functions that extend the semantic of ordinary
7624 vectors and lists in R. Package developers can easily implement vector-like
7625 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7626 In addition, a few low-level concrete subclasses of general interest (e.g.
7627 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7628 S4Vectors package itself.")
7629 (license license:artistic2.0)))
7631 (define-public r-iranges
7637 (uri (bioconductor-uri "IRanges" version))
7640 "1y24jw62806wp2afiyj1x6n00gj7d3323klqdypra9q43pg1w49d"))))
7642 `((upstream-name . "IRanges")))
7643 (build-system r-build-system)
7645 `(("r-biocgenerics" ,r-biocgenerics)
7646 ("r-s4vectors" ,r-s4vectors)))
7647 (home-page "https://bioconductor.org/packages/IRanges")
7648 (synopsis "Infrastructure for manipulating intervals on sequences")
7650 "This package provides efficient low-level and highly reusable S4 classes
7651 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7652 generally, data that can be organized sequentially (formally defined as
7653 @code{Vector} objects), as well as views on these @code{Vector} objects.
7654 Efficient list-like classes are also provided for storing big collections of
7655 instances of the basic classes. All classes in the package use consistent
7656 naming and share the same rich and consistent \"Vector API\" as much as
7658 (license license:artistic2.0)))
7660 (define-public r-genomeinfodbdata
7662 (name "r-genomeinfodbdata")
7666 ;; We cannot use bioconductor-uri here because this tarball is
7667 ;; located under "data/annotation/" instead of "bioc/".
7668 (uri (string-append "https://bioconductor.org/packages/release/"
7669 "data/annotation/src/contrib/GenomeInfoDbData_"
7673 "0di6nlqpsyqf693k2na65ayqldih563x3zfrczpqc5q2hl5kg35c"))))
7675 `((upstream-name . "GenomeInfoDbData")))
7676 (build-system r-build-system)
7677 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7678 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7679 (description "This package contains data for mapping between NCBI taxonomy
7680 ID and species. It is used by functions in the GenomeInfoDb package.")
7681 (license license:artistic2.0)))
7683 (define-public r-genomeinfodb
7685 (name "r-genomeinfodb")
7689 (uri (bioconductor-uri "GenomeInfoDb" version))
7692 "1cqs53p4m5q1dr59war72bccphy01ilw4xra24fmngrv4x32rznd"))))
7694 `((upstream-name . "GenomeInfoDb")))
7695 (build-system r-build-system)
7697 `(("r-biocgenerics" ,r-biocgenerics)
7698 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7699 ("r-iranges" ,r-iranges)
7700 ("r-rcurl" ,r-rcurl)
7701 ("r-s4vectors" ,r-s4vectors)))
7703 `(("r-knitr" ,r-knitr)))
7704 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7705 (synopsis "Utilities for manipulating chromosome identifiers")
7707 "This package contains data and functions that define and allow
7708 translation between different chromosome sequence naming conventions (e.g.,
7709 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7710 names in their natural, rather than lexicographic, order.")
7711 (license license:artistic2.0)))
7713 (define-public r-edger
7719 (uri (bioconductor-uri "edgeR" version))
7722 "1z9bkg08rgqn3jm2s4ndbj641w33wl8jd3j6m5if6h2nnw6011ic"))))
7723 (properties `((upstream-name . "edgeR")))
7724 (build-system r-build-system)
7726 `(("r-limma" ,r-limma)
7727 ("r-locfit" ,r-locfit)
7729 ("r-statmod" ,r-statmod))) ;for estimateDisp
7730 (home-page "http://bioinf.wehi.edu.au/edgeR")
7731 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7732 (description "This package can do differential expression analysis of
7733 RNA-seq expression profiles with biological replication. It implements a range
7734 of statistical methodology based on the negative binomial distributions,
7735 including empirical Bayes estimation, exact tests, generalized linear models
7736 and quasi-likelihood tests. It be applied to differential signal analysis of
7737 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7739 (license license:gpl2+)))
7741 (define-public r-variantannotation
7743 (name "r-variantannotation")
7747 (uri (bioconductor-uri "VariantAnnotation" version))
7750 "09y6ymwky839nb0y7y93w810hk9mvwqn7595q1276c28dkddiqvw"))))
7752 `((upstream-name . "VariantAnnotation")))
7756 `(("r-annotationdbi" ,r-annotationdbi)
7757 ("r-biobase" ,r-biobase)
7758 ("r-biocgenerics" ,r-biocgenerics)
7759 ("r-biostrings" ,r-biostrings)
7760 ("r-bsgenome" ,r-bsgenome)
7762 ("r-genomeinfodb" ,r-genomeinfodb)
7763 ("r-genomicfeatures" ,r-genomicfeatures)
7764 ("r-genomicranges" ,r-genomicranges)
7765 ("r-iranges" ,r-iranges)
7766 ("r-summarizedexperiment" ,r-summarizedexperiment)
7767 ("r-rhtslib" ,r-rhtslib)
7768 ("r-rsamtools" ,r-rsamtools)
7769 ("r-rtracklayer" ,r-rtracklayer)
7770 ("r-s4vectors" ,r-s4vectors)
7771 ("r-xvector" ,r-xvector)
7772 ("r-zlibbioc" ,r-zlibbioc)))
7773 (build-system r-build-system)
7774 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7775 (synopsis "Package for annotation of genetic variants")
7776 (description "This R package can annotate variants, compute amino acid
7777 coding changes and predict coding outcomes.")
7778 (license license:artistic2.0)))
7780 (define-public r-limma
7786 (uri (bioconductor-uri "limma" version))
7789 "09fnqxx4rzq5n447aqg2l6y0idfwgz2jxz99sifxsr2q8afzbcj6"))))
7790 (build-system r-build-system)
7791 (home-page "http://bioinf.wehi.edu.au/limma")
7792 (synopsis "Package for linear models for microarray and RNA-seq data")
7793 (description "This package can be used for the analysis of gene expression
7794 studies, especially the use of linear models for analysing designed experiments
7795 and the assessment of differential expression. The analysis methods apply to
7796 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7797 (license license:gpl2+)))
7799 (define-public r-xvector
7805 (uri (bioconductor-uri "XVector" version))
7808 "11h1hszv4798q1gbx8r6zf8vlaqx4v9ql0lbh2xaxybp66a03pvc"))))
7810 `((upstream-name . "XVector")))
7811 (build-system r-build-system)
7814 (modify-phases %standard-phases
7815 (add-after 'unpack 'use-system-zlib
7817 (substitute* "DESCRIPTION"
7818 (("zlibbioc, ") ""))
7819 (substitute* "NAMESPACE"
7820 (("import\\(zlibbioc\\)") ""))
7825 `(("r-biocgenerics" ,r-biocgenerics)
7826 ("r-iranges" ,r-iranges)
7827 ("r-s4vectors" ,r-s4vectors)))
7828 (home-page "https://bioconductor.org/packages/XVector")
7829 (synopsis "Representation and manpulation of external sequences")
7831 "This package provides memory efficient S4 classes for storing sequences
7832 \"externally\" (behind an R external pointer, or on disk).")
7833 (license license:artistic2.0)))
7835 (define-public r-genomicranges
7837 (name "r-genomicranges")
7841 (uri (bioconductor-uri "GenomicRanges" version))
7844 "0wn1zr2qq0rpv9z2wialgizn6xzdlcjg1w2kif67n53svz6vk2x1"))))
7846 `((upstream-name . "GenomicRanges")))
7847 (build-system r-build-system)
7849 `(("r-biocgenerics" ,r-biocgenerics)
7850 ("r-genomeinfodb" ,r-genomeinfodb)
7851 ("r-iranges" ,r-iranges)
7852 ("r-s4vectors" ,r-s4vectors)
7853 ("r-xvector" ,r-xvector)))
7855 `(("r-knitr" ,r-knitr)))
7856 (home-page "https://bioconductor.org/packages/GenomicRanges")
7857 (synopsis "Representation and manipulation of genomic intervals")
7859 "This package provides tools to efficiently represent and manipulate
7860 genomic annotations and alignments is playing a central role when it comes to
7861 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7862 GenomicRanges package defines general purpose containers for storing and
7863 manipulating genomic intervals and variables defined along a genome.")
7864 (license license:artistic2.0)))
7866 (define-public r-biobase
7872 (uri (bioconductor-uri "Biobase" version))
7875 "13p3kgnxm7hbn8cy289kbhaiyfa6rxx7l1pbvajwqzbay3cxznqp"))))
7877 `((upstream-name . "Biobase")))
7878 (build-system r-build-system)
7880 `(("r-biocgenerics" ,r-biocgenerics)))
7881 (home-page "https://bioconductor.org/packages/Biobase")
7882 (synopsis "Base functions for Bioconductor")
7884 "This package provides functions that are needed by many other packages
7885 on Bioconductor or which replace R functions.")
7886 (license license:artistic2.0)))
7888 (define-public r-annotationdbi
7890 (name "r-annotationdbi")
7894 (uri (bioconductor-uri "AnnotationDbi" version))
7897 "00pd8lsdppxlmx0l65phw0jhsm0qkwjc4wsdxpvgc31iiz9yslbj"))))
7899 `((upstream-name . "AnnotationDbi")))
7900 (build-system r-build-system)
7902 `(("r-biobase" ,r-biobase)
7903 ("r-biocgenerics" ,r-biocgenerics)
7905 ("r-iranges" ,r-iranges)
7906 ("r-rsqlite" ,r-rsqlite)
7907 ("r-s4vectors" ,r-s4vectors)))
7909 `(("r-knitr" ,r-knitr)))
7910 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7911 (synopsis "Annotation database interface")
7913 "This package provides user interface and database connection code for
7914 annotation data packages using SQLite data storage.")
7915 (license license:artistic2.0)))
7917 (define-public r-biomart
7923 (uri (bioconductor-uri "biomaRt" version))
7926 "0np4nh3gj60mgb6312z7x0z9fg5bhrhw872sp3dzgmqc8q8b84iz"))))
7928 `((upstream-name . "biomaRt")))
7929 (build-system r-build-system)
7931 `(("r-annotationdbi" ,r-annotationdbi)
7932 ("r-biocfilecache" ,r-biocfilecache)
7934 ("r-openssl" ,r-openssl)
7935 ("r-progress" ,r-progress)
7936 ("r-rappdirs" ,r-rappdirs)
7937 ("r-stringr" ,r-stringr)
7940 `(("r-knitr" ,r-knitr)))
7941 (home-page "https://bioconductor.org/packages/biomaRt")
7942 (synopsis "Interface to BioMart databases")
7944 "biomaRt provides an interface to a growing collection of databases
7945 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7946 package enables retrieval of large amounts of data in a uniform way without
7947 the need to know the underlying database schemas or write complex SQL queries.
7948 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7949 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7950 users direct access to a diverse set of data and enable a wide range of
7951 powerful online queries from gene annotation to database mining.")
7952 (license license:artistic2.0)))
7954 (define-public r-biocparallel
7956 (name "r-biocparallel")
7960 (uri (bioconductor-uri "BiocParallel" version))
7963 "1lsg5xm5j3ly5k60fidzhkgqc9jgscyfkqngjvd9qp6yfzvsb82g"))))
7965 `((upstream-name . "BiocParallel")))
7966 (build-system r-build-system)
7968 `(("r-futile-logger" ,r-futile-logger)
7972 `(("r-knitr" ,r-knitr)))
7973 (home-page "https://bioconductor.org/packages/BiocParallel")
7974 (synopsis "Bioconductor facilities for parallel evaluation")
7976 "This package provides modified versions and novel implementation of
7977 functions for parallel evaluation, tailored to use with Bioconductor
7979 (license (list license:gpl2+ license:gpl3+))))
7981 (define-public r-biostrings
7983 (name "r-biostrings")
7987 (uri (bioconductor-uri "Biostrings" version))
7990 "0imhfz7dg8b3l5qzipjranqqshdsg2x6zc49drlhn8sc7j40cvi8"))))
7992 `((upstream-name . "Biostrings")))
7993 (build-system r-build-system)
7995 `(("r-biocgenerics" ,r-biocgenerics)
7996 ("r-crayon" ,r-crayon)
7997 ("r-iranges" ,r-iranges)
7998 ("r-s4vectors" ,r-s4vectors)
7999 ("r-xvector" ,r-xvector)))
8000 (home-page "https://bioconductor.org/packages/Biostrings")
8001 (synopsis "String objects and algorithms for biological sequences")
8003 "This package provides memory efficient string containers, string
8004 matching algorithms, and other utilities, for fast manipulation of large
8005 biological sequences or sets of sequences.")
8006 (license license:artistic2.0)))
8008 (define-public r-rsamtools
8010 (name "r-rsamtools")
8014 (uri (bioconductor-uri "Rsamtools" version))
8017 "0z01z0s71f941k7sns46nyabps28c69d6jxx6sppjpc6h4vrw0vq"))))
8019 `((upstream-name . "Rsamtools")))
8020 (build-system r-build-system)
8023 (modify-phases %standard-phases
8024 (add-after 'unpack 'use-system-zlib
8026 (substitute* "DESCRIPTION"
8027 (("zlibbioc, ") ""))
8028 (substitute* "NAMESPACE"
8029 (("import\\(zlibbioc\\)") ""))
8034 `(("r-biocgenerics" ,r-biocgenerics)
8035 ("r-biocparallel" ,r-biocparallel)
8036 ("r-biostrings" ,r-biostrings)
8037 ("r-bitops" ,r-bitops)
8038 ("r-genomeinfodb" ,r-genomeinfodb)
8039 ("r-genomicranges" ,r-genomicranges)
8040 ("r-iranges" ,r-iranges)
8041 ("r-rhtslib" ,r-rhtslib)
8042 ("r-s4vectors" ,r-s4vectors)
8043 ("r-xvector" ,r-xvector)))
8044 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
8045 (synopsis "Interface to samtools, bcftools, and tabix")
8047 "This package provides an interface to the @code{samtools},
8048 @code{bcftools}, and @code{tabix} utilities for manipulating SAM (Sequence
8049 Alignment / Map), FASTA, binary variant call (BCF) and compressed indexed
8050 tab-delimited (tabix) files.")
8051 (license license:expat)))
8053 (define-public r-delayedarray
8055 (name "r-delayedarray")
8059 (uri (bioconductor-uri "DelayedArray" version))
8062 "1lz7a0rrlfv3w44n073mk8pw39z7lfs0njdxp5vpp0rdsmvdf1qk"))))
8064 `((upstream-name . "DelayedArray")))
8065 (build-system r-build-system)
8067 `(("r-biocgenerics" ,r-biocgenerics)
8068 ("r-s4vectors" ,r-s4vectors)
8069 ("r-iranges" ,r-iranges)
8070 ("r-matrix" ,r-matrix)
8071 ("r-matrixstats" ,r-matrixstats)))
8073 `(("r-knitr" ,r-knitr)))
8074 (home-page "https://bioconductor.org/packages/DelayedArray")
8075 (synopsis "Delayed operations on array-like objects")
8077 "Wrapping an array-like object (typically an on-disk object) in a
8078 @code{DelayedArray} object allows one to perform common array operations on it
8079 without loading the object in memory. In order to reduce memory usage and
8080 optimize performance, operations on the object are either delayed or executed
8081 using a block processing mechanism. Note that this also works on in-memory
8082 array-like objects like @code{DataFrame} objects (typically with Rle columns),
8083 @code{Matrix} objects, and ordinary arrays and data frames.")
8084 (license license:artistic2.0)))
8086 (define-public r-summarizedexperiment
8088 (name "r-summarizedexperiment")
8092 (uri (bioconductor-uri "SummarizedExperiment" version))
8095 "1raw5ycigr6gjgzn3kx3jls5hzww10fhnwd8c17c20hmhirf13rw"))))
8097 `((upstream-name . "SummarizedExperiment")))
8098 (build-system r-build-system)
8100 `(("r-biobase" ,r-biobase)
8101 ("r-biocgenerics" ,r-biocgenerics)
8102 ("r-delayedarray" ,r-delayedarray)
8103 ("r-genomeinfodb" ,r-genomeinfodb)
8104 ("r-genomicranges" ,r-genomicranges)
8105 ("r-iranges" ,r-iranges)
8106 ("r-matrix" ,r-matrix)
8107 ("r-s4vectors" ,r-s4vectors)))
8109 `(("r-knitr" ,r-knitr)))
8110 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
8111 (synopsis "Container for representing genomic ranges by sample")
8113 "The SummarizedExperiment container contains one or more assays, each
8114 represented by a matrix-like object of numeric or other mode. The rows
8115 typically represent genomic ranges of interest and the columns represent
8117 (license license:artistic2.0)))
8119 (define-public r-genomicalignments
8121 (name "r-genomicalignments")
8125 (uri (bioconductor-uri "GenomicAlignments" version))
8128 "0v8k6d7frm5p48cmk4zik78cw9abz4inx0zhl4zrmmx31ifyvk8d"))))
8130 `((upstream-name . "GenomicAlignments")))
8131 (build-system r-build-system)
8133 `(("r-biocgenerics" ,r-biocgenerics)
8134 ("r-biocparallel" ,r-biocparallel)
8135 ("r-biostrings" ,r-biostrings)
8136 ("r-genomeinfodb" ,r-genomeinfodb)
8137 ("r-genomicranges" ,r-genomicranges)
8138 ("r-iranges" ,r-iranges)
8139 ("r-rsamtools" ,r-rsamtools)
8140 ("r-s4vectors" ,r-s4vectors)
8141 ("r-summarizedexperiment" ,r-summarizedexperiment)))
8142 (home-page "https://bioconductor.org/packages/GenomicAlignments")
8143 (synopsis "Representation and manipulation of short genomic alignments")
8145 "This package provides efficient containers for storing and manipulating
8146 short genomic alignments (typically obtained by aligning short reads to a
8147 reference genome). This includes read counting, computing the coverage,
8148 junction detection, and working with the nucleotide content of the
8150 (license license:artistic2.0)))
8152 (define-public r-rtracklayer
8154 (name "r-rtracklayer")
8158 (uri (bioconductor-uri "rtracklayer" version))
8161 "1zcgk92sidhy4y7ws9ms4nkkh2hnccfhfh53qgna0kma9jy4v5xf"))))
8162 (build-system r-build-system)
8165 (modify-phases %standard-phases
8166 (add-after 'unpack 'use-system-zlib
8168 (substitute* "DESCRIPTION"
8169 ((" zlibbioc,") ""))
8170 (substitute* "NAMESPACE"
8171 (("import\\(zlibbioc\\)") ""))
8174 `(("pkg-config" ,pkg-config)))
8178 `(("r-biocgenerics" ,r-biocgenerics)
8179 ("r-biostrings" ,r-biostrings)
8180 ("r-genomeinfodb" ,r-genomeinfodb)
8181 ("r-genomicalignments" ,r-genomicalignments)
8182 ("r-genomicranges" ,r-genomicranges)
8183 ("r-iranges" ,r-iranges)
8184 ("r-rcurl" ,r-rcurl)
8185 ("r-rsamtools" ,r-rsamtools)
8186 ("r-s4vectors" ,r-s4vectors)
8188 ("r-xvector" ,r-xvector)))
8189 (home-page "https://bioconductor.org/packages/rtracklayer")
8190 (synopsis "R interface to genome browsers and their annotation tracks")
8192 "rtracklayer is an extensible framework for interacting with multiple
8193 genome browsers (currently UCSC built-in) and manipulating annotation tracks
8194 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
8195 built-in). The user may export/import tracks to/from the supported browsers,
8196 as well as query and modify the browser state, such as the current viewport.")
8197 (license license:artistic2.0)))
8199 (define-public r-genomicfeatures
8201 (name "r-genomicfeatures")
8205 (uri (bioconductor-uri "GenomicFeatures" version))
8208 "0zm7q957g952qyfqmvf27sldsnq6sqd0wlgnqzvmxayg9pxh0l0z"))))
8210 `((upstream-name . "GenomicFeatures")))
8211 (build-system r-build-system)
8213 `(("r-annotationdbi" ,r-annotationdbi)
8214 ("r-biobase" ,r-biobase)
8215 ("r-biocgenerics" ,r-biocgenerics)
8216 ("r-biomart" ,r-biomart)
8217 ("r-biostrings" ,r-biostrings)
8219 ("r-genomeinfodb" ,r-genomeinfodb)
8220 ("r-genomicranges" ,r-genomicranges)
8221 ("r-iranges" ,r-iranges)
8222 ("r-rcurl" ,r-rcurl)
8223 ("r-rsqlite" ,r-rsqlite)
8224 ("r-rtracklayer" ,r-rtracklayer)
8225 ("r-s4vectors" ,r-s4vectors)
8226 ("r-xvector" ,r-xvector)))
8228 `(("r-knitr" ,r-knitr)))
8229 (home-page "https://bioconductor.org/packages/GenomicFeatures")
8230 (synopsis "Tools for working with transcript centric annotations")
8232 "This package provides a set of tools and methods for making and
8233 manipulating transcript centric annotations. With these tools the user can
8234 easily download the genomic locations of the transcripts, exons and cds of a
8235 given organism, from either the UCSC Genome Browser or a BioMart
8236 database (more sources will be supported in the future). This information is
8237 then stored in a local database that keeps track of the relationship between
8238 transcripts, exons, cds and genes. Flexible methods are provided for
8239 extracting the desired features in a convenient format.")
8240 (license license:artistic2.0)))
8242 (define-public r-go-db
8248 (uri (string-append "https://www.bioconductor.org/packages/"
8249 "release/data/annotation/src/contrib/GO.db_"
8253 "0i3wcf5h3n0dawzc1hy0kv74f06j80c47n4p3g3fmrcxlhi3jpa5"))))
8255 `((upstream-name . "GO.db")))
8256 (build-system r-build-system)
8258 `(("r-annotationdbi" ,r-annotationdbi)))
8259 (home-page "https://bioconductor.org/packages/GO.db")
8260 (synopsis "Annotation maps describing the entire Gene Ontology")
8262 "The purpose of this GO.db annotation package is to provide detailed
8263 information about the latest version of the Gene Ontologies.")
8264 (license license:artistic2.0)))
8266 (define-public r-topgo
8272 (uri (bioconductor-uri "topGO" version))
8275 "13rhbvn27sj75fklf1cnjaazacx8yyjlhqlnbp5zk157q6y5cwdr"))))
8277 `((upstream-name . "topGO")))
8278 (build-system r-build-system)
8280 `(("r-annotationdbi" ,r-annotationdbi)
8282 ("r-biobase" ,r-biobase)
8283 ("r-biocgenerics" ,r-biocgenerics)
8284 ("r-go-db" ,r-go-db)
8285 ("r-graph" ,r-graph)
8286 ("r-lattice" ,r-lattice)
8287 ("r-matrixstats" ,r-matrixstats)
8288 ("r-sparsem" ,r-sparsem)))
8289 (home-page "https://bioconductor.org/packages/topGO")
8290 (synopsis "Enrichment analysis for gene ontology")
8292 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
8293 terms while accounting for the topology of the GO graph. Different test
8294 statistics and different methods for eliminating local similarities and
8295 dependencies between GO terms can be implemented and applied.")
8296 ;; Any version of the LGPL applies.
8297 (license license:lgpl2.1+)))
8299 (define-public r-bsgenome
8305 (uri (bioconductor-uri "BSgenome" version))
8308 "1jw8r1qm9fpg2s1cw2y4np243jjxm65j2xdy2785h8fc1b02msf6"))))
8310 `((upstream-name . "BSgenome")))
8311 (build-system r-build-system)
8313 `(("r-biocgenerics" ,r-biocgenerics)
8314 ("r-biostrings" ,r-biostrings)
8315 ("r-genomeinfodb" ,r-genomeinfodb)
8316 ("r-genomicranges" ,r-genomicranges)
8317 ("r-iranges" ,r-iranges)
8318 ("r-matrixstats" ,r-matrixstats)
8319 ("r-rsamtools" ,r-rsamtools)
8320 ("r-rtracklayer" ,r-rtracklayer)
8321 ("r-s4vectors" ,r-s4vectors)
8322 ("r-xvector" ,r-xvector)))
8323 (home-page "https://bioconductor.org/packages/BSgenome")
8324 (synopsis "Infrastructure for Biostrings-based genome data packages")
8326 "This package provides infrastructure shared by all Biostrings-based
8327 genome data packages and support for efficient SNP representation.")
8328 (license license:artistic2.0)))
8330 (define-public r-impute
8336 (uri (bioconductor-uri "impute" version))
8339 "161p6l1cp3wwdynkxwvg0yhrh6yv20brdlplw5w5mavn4hf1nm0h"))))
8341 `(("gfortran" ,gfortran)))
8342 (build-system r-build-system)
8343 (home-page "https://bioconductor.org/packages/impute")
8344 (synopsis "Imputation for microarray data")
8346 "This package provides a function to impute missing gene expression
8347 microarray data, using nearest neighbor averaging.")
8348 (license license:gpl2+)))
8350 (define-public r-seqpattern
8352 (name "r-seqpattern")
8356 (uri (bioconductor-uri "seqPattern" version))
8359 "0f1yvx2ri1557rzjx08q5bgml1cvkm8hjl8xn1qi4rjs64sy6mci"))))
8361 `((upstream-name . "seqPattern")))
8362 (build-system r-build-system)
8364 `(("r-biostrings" ,r-biostrings)
8365 ("r-genomicranges" ,r-genomicranges)
8366 ("r-iranges" ,r-iranges)
8367 ("r-kernsmooth" ,r-kernsmooth)
8368 ("r-plotrix" ,r-plotrix)))
8369 (home-page "https://bioconductor.org/packages/seqPattern")
8370 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
8372 "This package provides tools to visualize oligonucleotide patterns and
8373 sequence motif occurrences across a large set of sequences centred at a common
8374 reference point and sorted by a user defined feature.")
8375 (license license:gpl3+)))
8377 (define-public r-genomation
8379 (name "r-genomation")
8383 (uri (bioconductor-uri "genomation" version))
8386 "1cy8kqwddiha5jy6nda1al956i4wncbgjkrxwijdb08cmka2sfwh"))))
8387 (build-system r-build-system)
8389 `(("r-biostrings" ,r-biostrings)
8390 ("r-bsgenome" ,r-bsgenome)
8391 ("r-data-table" ,r-data-table)
8392 ("r-genomeinfodb" ,r-genomeinfodb)
8393 ("r-genomicalignments" ,r-genomicalignments)
8394 ("r-genomicranges" ,r-genomicranges)
8395 ("r-ggplot2" ,r-ggplot2)
8396 ("r-gridbase" ,r-gridbase)
8397 ("r-impute" ,r-impute)
8398 ("r-iranges" ,r-iranges)
8399 ("r-matrixstats" ,r-matrixstats)
8400 ("r-plotrix" ,r-plotrix)
8403 ("r-readr" ,r-readr)
8404 ("r-reshape2" ,r-reshape2)
8405 ("r-rsamtools" ,r-rsamtools)
8406 ("r-rtracklayer" ,r-rtracklayer)
8407 ("r-runit" ,r-runit)
8408 ("r-s4vectors" ,r-s4vectors)
8409 ("r-seqpattern" ,r-seqpattern)))
8411 `(("r-knitr" ,r-knitr)))
8412 (home-page "https://bioinformatics.mdc-berlin.de/genomation/")
8413 (synopsis "Summary, annotation and visualization of genomic data")
8415 "This package provides a package for summary and annotation of genomic
8416 intervals. Users can visualize and quantify genomic intervals over
8417 pre-defined functional regions, such as promoters, exons, introns, etc. The
8418 genomic intervals represent regions with a defined chromosome position, which
8419 may be associated with a score, such as aligned reads from HT-seq experiments,
8420 TF binding sites, methylation scores, etc. The package can use any tabular
8421 genomic feature data as long as it has minimal information on the locations of
8422 genomic intervals. In addition, it can use BAM or BigWig files as input.")
8423 (license license:artistic2.0)))
8425 (define-public r-genomationdata
8427 (name "r-genomationdata")
8431 ;; We cannot use bioconductor-uri here because this tarball is
8432 ;; located under "data/annotation/" instead of "bioc/".
8433 (uri (string-append "https://bioconductor.org/packages/"
8434 "release/data/experiment/src/contrib/"
8435 "genomationData_" version ".tar.gz"))
8438 "10xyb8akjrhmak2i0mnv1agny2ipy364q9nlibyplpzc7vdb6bw7"))))
8439 (build-system r-build-system)
8440 ;; As this package provides little more than large data files, it doesn't
8441 ;; make sense to build substitutes.
8442 (arguments `(#:substitutable? #f))
8444 `(("r-knitr" ,r-knitr)))
8445 (home-page "https://bioinformatics.mdc-berlin.de/genomation/")
8446 (synopsis "Experimental data for use with the genomation package")
8448 "This package contains experimental genetic data for use with the
8449 genomation package. Included are Chip Seq, Methylation and Cage data,
8450 downloaded from Encode.")
8451 (license license:gpl3+)))
8453 (define-public r-seqlogo
8460 (uri (bioconductor-uri "seqLogo" version))
8463 "09kkxir305fv8z2yyihvspkrzclxbw1cx5mvhfkrhl10rap6662j"))))
8464 (properties `((upstream-name . "seqLogo")))
8465 (build-system r-build-system)
8466 (home-page "https://bioconductor.org/packages/seqLogo")
8467 (synopsis "Sequence logos for DNA sequence alignments")
8469 "seqLogo takes the position weight matrix of a DNA sequence motif and
8470 plots the corresponding sequence logo as introduced by Schneider and
8472 (license license:lgpl2.0+)))
8474 (define-public r-motifrg
8481 (uri (bioconductor-uri "motifRG" version))
8484 "1ml6zyzlk8yjbnfhga2qnw8nl43rankvka0kc1yljxr2b66aqbhn"))))
8485 (properties `((upstream-name . "motifRG")))
8486 (build-system r-build-system)
8488 `(("r-biostrings" ,r-biostrings)
8489 ("r-bsgenome" ,r-bsgenome)
8490 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8491 ("r-iranges" ,r-iranges)
8492 ("r-seqlogo" ,r-seqlogo)
8493 ("r-xvector" ,r-xvector)))
8494 (home-page "https://bioconductor.org/packages/motifRG")
8495 (synopsis "Discover motifs in high throughput sequencing data")
8497 "This package provides tools for discriminative motif discovery in high
8498 throughput genetic sequencing data sets using regression methods.")
8499 (license license:artistic2.0)))
8501 (define-public r-qtl
8508 (uri (string-append "mirror://cran/src/contrib/qtl_"
8512 "0rbwcnvyy96gq1dsgpxx03pv423qya26h6ws5y0blj3blfdmj83a"))))
8513 (build-system r-build-system)
8514 (home-page "https://rqtl.org/")
8515 (synopsis "R package for analyzing QTL experiments in genetics")
8516 (description "R/qtl is an extension library for the R statistics
8517 system. It is used to analyze experimental crosses for identifying
8518 genes contributing to variation in quantitative traits (so-called
8519 quantitative trait loci, QTLs).
8521 Using a hidden Markov model, R/qtl estimates genetic maps, to
8522 identify genotyping errors, and to perform single-QTL and two-QTL,
8523 two-dimensional genome scans.")
8524 (license license:gpl3)))
8526 (define-public r-qtl2
8532 (uri (cran-uri "qtl2" version))
8534 (base32 "0dfdzjylqzc92dcszawc8cyinxccjm3p36v9vcq9ma818pqcanmr"))))
8535 (build-system r-build-system)
8537 `(("r-data-table" ,r-data-table)
8538 ("r-jsonlite" ,r-jsonlite)
8540 ("r-rcppeigen" ,r-rcppeigen)
8541 ("r-rsqlite" ,r-rsqlite)
8542 ("r-yaml" ,r-yaml)))
8543 (home-page "https://kbroman.org/qtl2/")
8544 (synopsis "Quantitative Trait Locus Mapping in Experimental Crosses")
8546 "This package provides a set of tools to perform @dfn{Quantitative Trait
8547 Locus} (QTL) analysis in experimental crosses. It is a reimplementation of the
8548 @code{R/qtl} package to better handle high-dimensional data and complex cross
8549 designs. Broman et al. (2018) <doi:10.1534/genetics.118.301595>.")
8550 (license license:gpl3)))
8552 (define-public r-zlibbioc
8558 (uri (bioconductor-uri "zlibbioc" version))
8561 "0j1l052jb2cwc1nifxzwknc9csagf4f2d092zs0i95dz0rma89l0"))))
8563 `((upstream-name . "zlibbioc")))
8564 (build-system r-build-system)
8565 (home-page "https://bioconductor.org/packages/zlibbioc")
8566 (synopsis "Provider for zlib-1.2.5 to R packages")
8567 (description "This package uses the source code of zlib-1.2.5 to create
8568 libraries for systems that do not have these available via other means.")
8569 (license license:artistic2.0)))
8571 (define-public r-r4rna
8578 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8582 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8583 (build-system r-build-system)
8585 `(("r-optparse" ,r-optparse)
8586 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8587 (home-page "https://www.e-rna.org/r-chie/index.cgi")
8588 (synopsis "Analysis framework for RNA secondary structure")
8590 "The R4RNA package aims to be a general framework for the analysis of RNA
8591 secondary structure and comparative analysis in R.")
8592 (license license:gpl3+)))
8594 (define-public r-rhtslib
8601 (uri (bioconductor-uri "Rhtslib" version))
8604 "186r7icrkzrni1c4n33ip7dlsfgys7hnqf0simvxrpl3yhh3ygdi"))))
8605 (properties `((upstream-name . "Rhtslib")))
8606 (build-system r-build-system)
8607 ;; Without this a temporary directory ends up in the Rhtslib.so binary,
8608 ;; which makes R abort the build.
8609 (arguments '(#:configure-flags '("--no-staged-install")))
8612 ("r-zlibbioc" ,r-zlibbioc)))
8616 `(("pkg-config" ,pkg-config)
8617 ("r-knitr" ,r-knitr)))
8618 (home-page "https://github.com/nhayden/Rhtslib")
8619 (synopsis "High-throughput sequencing library as an R package")
8621 "This package provides the HTSlib C library for high-throughput
8622 nucleotide sequence analysis. The package is primarily useful to developers
8623 of other R packages who wish to make use of HTSlib.")
8624 (license license:lgpl2.0+)))
8626 (define-public r-bamsignals
8628 (name "r-bamsignals")
8633 (uri (bioconductor-uri "bamsignals" version))
8636 "0p858xxfv79yc8b3lq58zl9f00irvbn3czsd8wdi5040xg42m402"))))
8637 (build-system r-build-system)
8639 `(("r-biocgenerics" ,r-biocgenerics)
8640 ("r-genomicranges" ,r-genomicranges)
8641 ("r-iranges" ,r-iranges)
8643 ("r-rhtslib" ,r-rhtslib)
8644 ("r-zlibbioc" ,r-zlibbioc)))
8648 `(("r-knitr" ,r-knitr)))
8649 (home-page "https://bioconductor.org/packages/bamsignals")
8650 (synopsis "Extract read count signals from bam files")
8652 "This package efficiently obtains count vectors from indexed bam
8653 files. It counts the number of nucleotide sequence reads in given genomic
8654 ranges and it computes reads profiles and coverage profiles. It also handles
8656 (license license:gpl2+)))
8658 (define-public r-rcas
8664 (uri (bioconductor-uri "RCAS" version))
8667 "0f812pgv3ys1zv4n9sqkgm01hj4cdd0i0h85dqbhkwd94zl6cavl"))))
8668 (properties `((upstream-name . "RCAS")))
8669 (build-system r-build-system)
8671 `(("r-biocgenerics" ,r-biocgenerics)
8672 ("r-biostrings" ,r-biostrings)
8673 ("r-bsgenome" ,r-bsgenome)
8674 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8675 ("r-cowplot" ,r-cowplot)
8676 ("r-data-table" ,r-data-table)
8678 ("r-genomation" ,r-genomation)
8679 ("r-genomeinfodb" ,r-genomeinfodb)
8680 ("r-genomicfeatures" ,r-genomicfeatures)
8681 ("r-genomicranges" ,r-genomicranges)
8682 ("r-ggplot2" ,r-ggplot2)
8683 ("r-ggseqlogo" ,r-ggseqlogo)
8684 ("r-gprofiler2" ,r-gprofiler2)
8685 ("r-iranges" ,r-iranges)
8686 ("r-pbapply" ,r-pbapply)
8687 ("r-pheatmap" ,r-pheatmap)
8688 ("r-plotly" ,r-plotly)
8689 ("r-plotrix" ,r-plotrix)
8690 ("r-proxy" ,r-proxy)
8691 ("r-ranger" ,r-ranger)
8692 ("r-rsqlite" ,r-rsqlite)
8693 ("r-rtracklayer" ,r-rtracklayer)
8694 ("r-rmarkdown" ,r-rmarkdown)
8695 ("r-s4vectors" ,r-s4vectors)
8696 ("pandoc" ,ghc-pandoc)))
8698 `(("r-knitr" ,r-knitr)))
8699 (synopsis "RNA-centric annotation system")
8701 "RCAS aims to be a standalone RNA-centric annotation system that provides
8702 intuitive reports and publication-ready graphics. This package provides the R
8703 library implementing most of the pipeline's features.")
8704 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8705 (license license:artistic2.0)))
8707 (define-public rcas-web
8714 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8715 "releases/download/v" version
8716 "/rcas-web-" version ".tar.gz"))
8719 "0wq951aj45gqki1bickg876i993lmawkp8x24agg264br5x716db"))))
8720 (build-system gnu-build-system)
8723 (modify-phases %standard-phases
8724 (add-before 'configure 'find-RCAS
8725 ;; The configure script can't find non-1.3.x versions of RCAS because
8726 ;; its R expression ‘1.10.1 >= 1.3.4’ evaluates to false.
8728 (substitute* "configure"
8729 (("1\\.3\\.4") "0.0.0"))
8731 (add-after 'install 'wrap-executable
8732 (lambda* (#:key inputs outputs #:allow-other-keys)
8733 (let* ((out (assoc-ref outputs "out"))
8734 (json (assoc-ref inputs "guile-json"))
8735 (redis (assoc-ref inputs "guile-redis"))
8736 (path (string-append
8737 json "/share/guile/site/2.2:"
8738 redis "/share/guile/site/2.2")))
8739 (wrap-program (string-append out "/bin/rcas-web")
8740 `("GUILE_LOAD_PATH" ":" = (,path))
8741 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8742 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8745 `(("r-minimal" ,r-minimal)
8747 ("guile" ,guile-2.2)
8748 ("guile-json" ,guile-json-1)
8749 ("guile-redis" ,guile2.2-redis)))
8751 `(("pkg-config" ,pkg-config)))
8752 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8753 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8754 (description "This package provides a simple web interface for the
8755 @dfn{RNA-centric annotation system} (RCAS).")
8756 (license license:agpl3+)))
8758 (define-public r-mutationalpatterns
8760 (name "r-mutationalpatterns")
8765 (uri (bioconductor-uri "MutationalPatterns" version))
8768 "02lyjiabyhmifycksvpcx29a0pb7z9xjw0hgg8n0sd0dy3afqhcm"))))
8769 (build-system r-build-system)
8771 `(("r-biocgenerics" ,r-biocgenerics)
8772 ("r-biostrings" ,r-biostrings)
8773 ;; These two packages are suggested packages
8774 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8775 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8776 ("r-genomicranges" ,r-genomicranges)
8777 ("r-genomeinfodb" ,r-genomeinfodb)
8778 ("r-ggplot2" ,r-ggplot2)
8779 ("r-iranges" ,r-iranges)
8782 ("r-pracma" ,r-pracma)
8783 ("r-reshape2" ,r-reshape2)
8784 ("r-cowplot" ,r-cowplot)
8785 ("r-ggdendro" ,r-ggdendro)
8786 ("r-s4vectors" ,r-s4vectors)
8787 ("r-summarizedexperiment" ,r-summarizedexperiment)
8788 ("r-variantannotation" ,r-variantannotation)))
8789 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8790 (synopsis "Extract and visualize mutational patterns in genomic data")
8791 (description "This package provides an extensive toolset for the
8792 characterization and visualization of a wide range of mutational patterns
8793 in SNV base substitution data.")
8794 (license license:expat)))
8796 (define-public r-chipkernels
8797 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8800 (name "r-chipkernels")
8801 (version (string-append "1.1-" revision "." (string-take commit 9)))
8806 (url "https://github.com/ManuSetty/ChIPKernels")
8808 (file-name (string-append name "-" version))
8811 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8812 (build-system r-build-system)
8814 `(("r-iranges" ,r-iranges)
8815 ("r-xvector" ,r-xvector)
8816 ("r-biostrings" ,r-biostrings)
8817 ("r-bsgenome" ,r-bsgenome)
8818 ("r-gtools" ,r-gtools)
8819 ("r-genomicranges" ,r-genomicranges)
8820 ("r-sfsmisc" ,r-sfsmisc)
8821 ("r-kernlab" ,r-kernlab)
8822 ("r-s4vectors" ,r-s4vectors)
8823 ("r-biocgenerics" ,r-biocgenerics)))
8824 (home-page "https://github.com/ManuSetty/ChIPKernels")
8825 (synopsis "Build string kernels for DNA Sequence analysis")
8826 (description "ChIPKernels is an R package for building different string
8827 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8828 must be built and this dictionary can be used for determining kernels for DNA
8830 (license license:gpl2+))))
8832 (define-public r-seqgl
8840 (url "https://github.com/ManuSetty/SeqGL")
8842 (file-name (git-file-name name version))
8845 "1r6ywvhxl3ffv48lgj7sbd582mcc6dha3ksgc2qjlvjrnkbj3799"))))
8846 (build-system r-build-system)
8848 `(("r-biostrings" ,r-biostrings)
8849 ("r-chipkernels" ,r-chipkernels)
8850 ("r-genomicranges" ,r-genomicranges)
8851 ("r-spams" ,r-spams)
8852 ("r-wgcna" ,r-wgcna)
8853 ("r-fastcluster" ,r-fastcluster)))
8854 (home-page "https://github.com/ManuSetty/SeqGL")
8855 (synopsis "Group lasso for Dnase/ChIP-seq data")
8856 (description "SeqGL is a group lasso based algorithm to extract
8857 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8858 This package presents a method which uses group lasso to discriminate between
8859 bound and non bound genomic regions to accurately identify transcription
8860 factors bound at the specific regions.")
8861 (license license:gpl2+)))
8863 (define-public r-tximport
8869 (uri (bioconductor-uri "tximport" version))
8872 "1x9959lkjl2h869rgd1b30q1idxzjkr1fyqbpndqk3kbi4q2gr40"))))
8873 (build-system r-build-system)
8875 `(("r-knitr" ,r-knitr)))
8876 (home-page "https://bioconductor.org/packages/tximport")
8877 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8879 "This package provides tools to import transcript-level abundance,
8880 estimated counts and transcript lengths, and to summarize them into matrices
8881 for use with downstream gene-level analysis packages. Average transcript
8882 length, weighted by sample-specific transcript abundance estimates, is
8883 provided as a matrix which can be used as an offset for different expression
8884 of gene-level counts.")
8885 (license license:gpl2+)))
8887 (define-public r-rhdf5
8893 (uri (bioconductor-uri "rhdf5" version))
8896 "1v6ygi0avh3gmaj2ld2nr7vww4ipw39b5kqci9w27i3ja985lb8j"))))
8897 (build-system r-build-system)
8899 `(("r-rhdf5lib" ,r-rhdf5lib)))
8903 `(("r-knitr" ,r-knitr)))
8904 (home-page "https://bioconductor.org/packages/rhdf5")
8905 (synopsis "HDF5 interface to R")
8907 "This R/Bioconductor package provides an interface between HDF5 and R.
8908 HDF5's main features are the ability to store and access very large and/or
8909 complex datasets and a wide variety of metadata on mass storage (disk) through
8910 a completely portable file format. The rhdf5 package is thus suited for the
8911 exchange of large and/or complex datasets between R and other software
8912 package, and for letting R applications work on datasets that are larger than
8913 the available RAM.")
8914 (license license:artistic2.0)))
8916 (define-public r-annotationfilter
8918 (name "r-annotationfilter")
8922 (uri (bioconductor-uri "AnnotationFilter" version))
8925 "18kh1xrhpwb48s1qj4f1v8af3jmw49pnbp5afi2myn9894hxg0cs"))))
8927 `((upstream-name . "AnnotationFilter")))
8928 (build-system r-build-system)
8930 `(("r-genomicranges" ,r-genomicranges)
8931 ("r-lazyeval" ,r-lazyeval)))
8933 `(("r-knitr" ,r-knitr)))
8934 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8935 (synopsis "Facilities for filtering Bioconductor annotation resources")
8937 "This package provides classes and other infrastructure to implement
8938 filters for manipulating Bioconductor annotation resources. The filters are
8939 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8940 (license license:artistic2.0)))
8942 (define-public emboss
8948 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8949 (version-major+minor version) ".0/"
8950 "EMBOSS-" version ".tar.gz"))
8953 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8954 (build-system gnu-build-system)
8957 (list (string-append "--with-hpdf="
8958 (assoc-ref %build-inputs "libharu")))
8960 (modify-phases %standard-phases
8961 (add-after 'unpack 'fix-checks
8963 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8964 ;; and zlib, but assume that they are all found at the same
8966 (substitute* "configure.in"
8967 (("CHECK_PNGDRIVER")
8968 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8969 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8970 AM_CONDITIONAL(AMPNG, true)"))
8972 (add-after 'fix-checks 'disable-update-check
8974 ;; At build time there is no connection to the Internet, so
8975 ;; looking for updates will not work.
8976 (substitute* "Makefile.am"
8977 (("\\$\\(bindir\\)/embossupdate") ""))
8979 (add-after 'disable-update-check 'autogen
8980 (lambda _ (invoke "autoreconf" "-vif") #t)))))
8986 ("libharu" ,libharu)
8989 `(("autoconf" ,autoconf)
8990 ("automake" ,automake)
8991 ("libtool" ,libtool)
8992 ("pkg-config" ,pkg-config)))
8993 (home-page "http://emboss.sourceforge.net")
8994 (synopsis "Molecular biology analysis suite")
8995 (description "EMBOSS is the \"European Molecular Biology Open Software
8996 Suite\". EMBOSS is an analysis package specially developed for the needs of
8997 the molecular biology (e.g. EMBnet) user community. The software
8998 automatically copes with data in a variety of formats and even allows
8999 transparent retrieval of sequence data from the web. It also provides a
9000 number of libraries for the development of software in the field of molecular
9001 biology. EMBOSS also integrates a range of currently available packages and
9002 tools for sequence analysis into a seamless whole.")
9003 (license license:gpl2+)))
9006 (let ((revision "1")
9007 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
9010 ;; The version is 2.13.0 even though no release archives have been
9011 ;; published as yet.
9012 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
9016 (url "https://github.com/arq5x/bits")
9018 (file-name (string-append name "-" version "-checkout"))
9021 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
9022 (build-system gnu-build-system)
9024 `(#:tests? #f ;no tests included
9026 (modify-phases %standard-phases
9028 (add-after 'unpack 'remove-cuda
9030 (substitute* "Makefile"
9032 (("(bits_test_intersections) \\\\" _ match) match))
9035 (lambda* (#:key outputs #:allow-other-keys)
9037 "bin" (string-append (assoc-ref outputs "out") "/bin"))
9042 (home-page "https://github.com/arq5x/bits")
9043 (synopsis "Implementation of binary interval search algorithm")
9044 (description "This package provides an implementation of the
9045 BITS (Binary Interval Search) algorithm, an approach to interval set
9046 intersection. It is especially suited for the comparison of diverse genomic
9047 datasets and the exploration of large datasets of genome
9048 intervals (e.g. genes, sequence alignments).")
9049 (license license:gpl2))))
9051 (define-public piranha
9052 ;; There is no release tarball for the latest version. The latest commit is
9053 ;; older than one year at the time of this writing.
9054 (let ((revision "1")
9055 (commit "0466d364b71117d01e4471b74c514436cc281233"))
9058 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
9062 (url "https://github.com/smithlabcode/piranha")
9064 (file-name (git-file-name name version))
9067 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
9068 (build-system gnu-build-system)
9070 `(#:test-target "test"
9072 (modify-phases %standard-phases
9073 (add-after 'unpack 'copy-smithlab-cpp
9074 (lambda* (#:key inputs #:allow-other-keys)
9075 (for-each (lambda (file)
9076 (install-file file "./src/smithlab_cpp/"))
9077 (find-files (assoc-ref inputs "smithlab-cpp")))
9079 (add-after 'install 'install-to-store
9080 (lambda* (#:key outputs #:allow-other-keys)
9081 (let* ((out (assoc-ref outputs "out"))
9082 (bin (string-append out "/bin")))
9083 (for-each (lambda (file)
9084 (install-file file bin))
9085 (find-files "bin" ".*")))
9088 (list (string-append "--with-bam_tools_headers="
9089 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
9090 (string-append "--with-bam_tools_library="
9091 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
9093 `(("bamtools" ,bamtools)
9094 ("samtools" ,samtools-0.1)
9097 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
9101 (url "https://github.com/smithlabcode/smithlab_cpp")
9103 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
9106 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
9108 `(("python" ,python-2)))
9109 (home-page "https://github.com/smithlabcode/piranha")
9110 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
9112 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
9113 RIP-seq experiments. It takes input in BED or BAM format and identifies
9114 regions of statistically significant read enrichment. Additional covariates
9115 may optionally be provided to further inform the peak-calling process.")
9116 (license license:gpl3+))))
9124 (uri (pypi-uri "PePr" version))
9127 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
9128 (build-system python-build-system)
9130 `(#:python ,python-2 ; python2 only
9131 #:tests? #f)) ; no tests included
9133 `(("python2-numpy" ,python2-numpy)
9134 ("python2-scipy" ,python2-scipy)
9135 ("python2-pysam" ,python2-pysam)))
9136 (home-page "https://github.com/shawnzhangyx/PePr")
9137 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
9139 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
9140 that is primarily designed for data with biological replicates. It uses a
9141 negative binomial distribution to model the read counts among the samples in
9142 the same group, and look for consistent differences between ChIP and control
9143 group or two ChIP groups run under different conditions.")
9144 (license license:gpl3+)))
9146 (define-public filevercmp
9147 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
9150 (version (string-append "0-1." (string-take commit 7)))
9154 (url "https://github.com/ekg/filevercmp")
9156 (file-name (git-file-name name commit))
9159 "1j9vxsy0y050v59h0q1d6501fcw1kjvj0d18l1xk2zyg0jzj247c"))))
9160 (build-system gnu-build-system)
9162 `(#:tests? #f ; There are no tests to run.
9164 (modify-phases %standard-phases
9165 (delete 'configure) ; There is no configure phase.
9167 (lambda* (#:key outputs #:allow-other-keys)
9168 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
9169 (install-file "filevercmp" bin)
9171 (home-page "https://github.com/ekg/filevercmp")
9172 (synopsis "This program compares version strings")
9173 (description "This program compares version strings. It intends to be a
9174 replacement for strverscmp.")
9175 (license license:gpl3+))))
9177 (define-public multiqc
9184 (uri (pypi-uri "multiqc" version))
9187 "02iihfl0w0hpnr4pa0sbd1y9qxrg3ycyhjp5lidkcrqh1lmzs3zy"))))
9188 (build-system python-build-system)
9190 `(("python-jinja2" ,python-jinja2)
9191 ("python-simplejson" ,python-simplejson)
9192 ("python-pyyaml" ,python-pyyaml)
9193 ("python-click" ,python-click)
9194 ("python-spectra" ,python-spectra)
9195 ("python-requests" ,python-requests)
9196 ("python-markdown" ,python-markdown)
9197 ("python-lzstring" ,python-lzstring)
9198 ("python-matplotlib" ,python-matplotlib)
9199 ("python-numpy" ,python-numpy)
9200 ;; MultQC checks for the presence of nose at runtime.
9201 ("python-nose" ,python-nose)))
9204 (modify-phases %standard-phases
9205 (add-after 'unpack 'relax-requirements
9207 (substitute* "setup.py"
9208 ;; MultiQC 1.5 ‘requires’ a version of python-matplotlib older
9209 ;; than the one in Guix, but should work fine with 2.2.2.
9210 ;; See <https://github.com/ewels/MultiQC/issues/725> and
9211 ;; <https://github.com/ewels/MultiQC/issues/732> for details.
9212 (("['\"]matplotlib.*?['\"]")
9215 (home-page "https://multiqc.info")
9216 (synopsis "Aggregate bioinformatics analysis reports")
9218 "MultiQC is a tool to aggregate bioinformatics results across many
9219 samples into a single report. It contains modules for a large number of
9220 common bioinformatics tools.")
9221 (license license:gpl3+)))
9223 (define-public variant-tools
9225 (name "variant-tools")
9231 (url "https://github.com/vatlab/varianttools")
9232 ;; There is no tag corresponding to version 3.1.2
9233 (commit "813ae4a90d25b69abc8a40f4f70441fe09015249")))
9234 (file-name (git-file-name name version))
9237 "12ibdmksj7icyqhks4xyvd61bygk4pjmxn618kp6vgk1af01y34g"))))
9238 (build-system python-build-system)
9241 ("c-blosc" ,c-blosc)
9244 ("hdf5-blosc" ,hdf5-blosc)
9245 ("python-cython" ,python-cython)
9248 `(("python-numpy" ,python-numpy)
9249 ("python-pycurl" ,python-pycurl)
9250 ("python-pyzmq" ,python-pyzmq)
9251 ("python-scipy" ,python-scipy)
9252 ("python-tables" ,python-tables)))
9253 (home-page "https://vatlab.github.io/vat-docs/")
9254 (synopsis "Analyze genetic variants from Next-Gen sequencing studies")
9256 "Variant tools is a tool for the manipulation, annotation,
9257 selection, simulation, and analysis of variants in the context of next-gen
9258 sequencing analysis. Unlike some other tools used for next-gen sequencing
9259 analysis, variant tools is project based and provides a whole set of tools to
9260 manipulate and analyze genetic variants.")
9261 (license license:gpl3+)))
9263 (define-public r-chipseq
9270 (uri (bioconductor-uri "chipseq" version))
9273 "0lh859s0aq73vac1phcgagf6n000qgq2xsk0bmfr61n5swifml2a"))))
9274 (build-system r-build-system)
9276 `(("r-biocgenerics" ,r-biocgenerics)
9277 ("r-genomicranges" ,r-genomicranges)
9278 ("r-iranges" ,r-iranges)
9279 ("r-lattice" ,r-lattice)
9280 ("r-s4vectors" ,r-s4vectors)
9281 ("r-shortread" ,r-shortread)))
9282 (home-page "https://bioconductor.org/packages/chipseq")
9283 (synopsis "Package for analyzing ChIPseq data")
9285 "This package provides tools for processing short read data from ChIPseq
9287 (license license:artistic2.0)))
9289 (define-public r-copyhelper
9291 (name "r-copyhelper")
9296 (uri (string-append "https://bioconductor.org/packages/release/"
9297 "data/experiment/src/contrib/CopyhelpeR_"
9301 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
9302 (properties `((upstream-name . "CopyhelpeR")))
9303 (build-system r-build-system)
9304 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
9305 (synopsis "Helper files for CopywriteR")
9307 "This package contains the helper files that are required to run the
9308 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
9309 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
9310 mm10. In addition, it contains a blacklist filter to remove regions that
9311 display copy number variation. Files are stored as GRanges objects from the
9312 GenomicRanges Bioconductor package.")
9313 (license license:gpl2)))
9315 (define-public r-copywriter
9317 (name "r-copywriter")
9322 (uri (bioconductor-uri "CopywriteR" version))
9325 "0c36wpv0rygkbqpf3dwh5xmc3lr7p8lrdzsq2fbbpw04skl6i7m2"))))
9326 (properties `((upstream-name . "CopywriteR")))
9327 (build-system r-build-system)
9329 `(("r-biocparallel" ,r-biocparallel)
9330 ("r-chipseq" ,r-chipseq)
9331 ("r-copyhelper" ,r-copyhelper)
9332 ("r-data-table" ,r-data-table)
9333 ("r-dnacopy" ,r-dnacopy)
9334 ("r-futile-logger" ,r-futile-logger)
9335 ("r-genomeinfodb" ,r-genomeinfodb)
9336 ("r-genomicalignments" ,r-genomicalignments)
9337 ("r-genomicranges" ,r-genomicranges)
9338 ("r-gtools" ,r-gtools)
9339 ("r-iranges" ,r-iranges)
9340 ("r-matrixstats" ,r-matrixstats)
9341 ("r-rsamtools" ,r-rsamtools)
9342 ("r-s4vectors" ,r-s4vectors)))
9343 (home-page "https://github.com/PeeperLab/CopywriteR")
9344 (synopsis "Copy number information from targeted sequencing")
9346 "CopywriteR extracts DNA copy number information from targeted sequencing
9347 by utilizing off-target reads. It allows for extracting uniformly distributed
9348 copy number information, can be used without reference, and can be applied to
9349 sequencing data obtained from various techniques including chromatin
9350 immunoprecipitation and target enrichment on small gene panels. Thereby,
9351 CopywriteR constitutes a widely applicable alternative to available copy
9352 number detection tools.")
9353 (license license:gpl2)))
9355 (define-public r-methylkit
9357 (name "r-methylkit")
9361 (uri (bioconductor-uri "methylKit" version))
9364 "1qr13d2712ypbn96ijic2z5adr5dsd61kzscx7shw6vyj360rlm5"))))
9365 (properties `((upstream-name . "methylKit")))
9366 (build-system r-build-system)
9368 `(("r-data-table" ,r-data-table)
9369 ("r-emdbook" ,r-emdbook)
9370 ("r-fastseg" ,r-fastseg)
9371 ("r-genomeinfodb" ,r-genomeinfodb)
9372 ("r-genomicranges" ,r-genomicranges)
9373 ("r-gtools" ,r-gtools)
9374 ("r-iranges" ,r-iranges)
9375 ("r-kernsmooth" ,r-kernsmooth)
9376 ("r-limma" ,r-limma)
9377 ("r-mclust" ,r-mclust)
9379 ("r-qvalue" ,r-qvalue)
9380 ("r-r-utils" ,r-r-utils)
9382 ("r-rhtslib" ,r-rhtslib)
9383 ("r-rsamtools" ,r-rsamtools)
9384 ("r-rtracklayer" ,r-rtracklayer)
9385 ("r-s4vectors" ,r-s4vectors)
9386 ("r-zlibbioc" ,r-zlibbioc)))
9388 `(("r-knitr" ,r-knitr))) ; for vignettes
9391 (home-page "https://github.com/al2na/methylKit")
9393 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9395 "MethylKit is an R package for DNA methylation analysis and annotation
9396 from high-throughput bisulfite sequencing. The package is designed to deal
9397 with sequencing data from @dfn{Reduced representation bisulfite
9398 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9399 genome bisulfite sequencing. It also has functions to analyze base-pair
9400 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9402 (license license:artistic2.0)))
9404 (define-public r-sva
9411 (uri (bioconductor-uri "sva" version))
9414 "0xa1lm0k1a6nig90mab6xh4gln88rbs5l1cdr6ik6agg7jhs7ji4"))))
9415 (build-system r-build-system)
9417 `(("r-edger" ,r-edger)
9418 ("r-genefilter" ,r-genefilter)
9420 ("r-biocparallel" ,r-biocparallel)
9421 ("r-matrixstats" ,r-matrixstats)
9422 ("r-limma" ,r-limma)))
9423 (home-page "https://bioconductor.org/packages/sva")
9424 (synopsis "Surrogate variable analysis")
9426 "This package contains functions for removing batch effects and other
9427 unwanted variation in high-throughput experiment. It also contains functions
9428 for identifying and building surrogate variables for high-dimensional data
9429 sets. Surrogate variables are covariates constructed directly from
9430 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9431 imaging data that can be used in subsequent analyses to adjust for unknown,
9432 unmodeled, or latent sources of noise.")
9433 (license license:artistic2.0)))
9435 (define-public r-seqminer
9442 (uri (cran-uri "seqminer" version))
9445 "00jzj8mwb0zaiwlifd41b26mrq9mzigj18nc29dydi0r42hxg16i"))))
9446 (build-system r-build-system)
9449 (home-page "http://seqminer.genomic.codes")
9450 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9452 "This package provides tools to integrate nucleotide sequencing
9453 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9454 ;; Any version of the GPL is acceptable
9455 (license (list license:gpl2+ license:gpl3+))))
9457 (define-public r-raremetals2
9459 (name "r-raremetals2")
9464 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9465 "b/b7/RareMETALS2_" version ".tar.gz"))
9468 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9469 (properties `((upstream-name . "RareMETALS2")))
9470 (build-system r-build-system)
9472 `(("r-seqminer" ,r-seqminer)
9473 ("r-mvtnorm" ,r-mvtnorm)
9475 ("r-compquadform" ,r-compquadform)
9476 ("r-getopt" ,r-getopt)))
9477 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9478 (synopsis "Analyze gene-level association tests for binary trait")
9480 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9481 It was designed to meta-analyze gene-level association tests for binary trait.
9482 While rareMETALS offers a near-complete solution for meta-analysis of
9483 gene-level tests for quantitative trait, it does not offer the optimal
9484 solution for binary trait. The package rareMETALS2 offers improved features
9485 for analyzing gene-level association tests in meta-analyses for binary
9487 (license license:gpl3)))
9489 (define-public r-maldiquant
9491 (name "r-maldiquant")
9496 (uri (cran-uri "MALDIquant" version))
9499 "0b7kdz3x4sdq413h1q09l1qhcvdnnwv6fqsqwllks1cd3xy34c57"))))
9500 (properties `((upstream-name . "MALDIquant")))
9501 (build-system r-build-system)
9502 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9503 (synopsis "Quantitative analysis of mass spectrometry data")
9505 "This package provides a complete analysis pipeline for matrix-assisted
9506 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9507 two-dimensional mass spectrometry data. In addition to commonly used plotting
9508 and processing methods it includes distinctive features, namely baseline
9509 subtraction methods such as morphological filters (TopHat) or the
9510 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9511 alignment using warping functions, handling of replicated measurements as well
9512 as allowing spectra with different resolutions.")
9513 (license license:gpl3+)))
9515 (define-public r-protgenerics
9517 (name "r-protgenerics")
9522 (uri (bioconductor-uri "ProtGenerics" version))
9525 "14xzdh7vxss8vmrw91hcwrszdn3ikm71mah8875b2lkrkrfzbl73"))))
9526 (properties `((upstream-name . "ProtGenerics")))
9527 (build-system r-build-system)
9528 (home-page "https://github.com/lgatto/ProtGenerics")
9529 (synopsis "S4 generic functions for proteomics infrastructure")
9531 "This package provides S4 generic functions needed by Bioconductor
9532 proteomics packages.")
9533 (license license:artistic2.0)))
9535 (define-public r-mzr
9542 (uri (bioconductor-uri "mzR" version))
9545 "1r8j8yiz5lcan7j4h37sza2kwczl48dxvld3da3ghjjq67cdc2cm"))
9546 (modules '((guix build utils)))
9549 (delete-file-recursively "src/boost")
9551 (properties `((upstream-name . "mzR")))
9552 (build-system r-build-system)
9555 (modify-phases %standard-phases
9556 (add-after 'unpack 'use-system-boost
9558 (substitute* "src/Makevars"
9559 (("\\./boost/libs.*") "")
9560 (("ARCH_OBJS=" line)
9562 "\nARCH_LIBS=-lboost_system -lboost_regex \
9563 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9566 `(;; Our default boost package won't work here, unfortunately, even with
9567 ;; mzR version 2.22.0.
9568 ("boost" ,boost-for-mysql) ; use this instead of the bundled boost sources
9571 `(("r-biobase" ,r-biobase)
9572 ("r-biocgenerics" ,r-biocgenerics)
9573 ("r-ncdf4" ,r-ncdf4)
9574 ("r-protgenerics" ,r-protgenerics)
9576 ("r-rhdf5lib" ,r-rhdf5lib)
9577 ("r-zlibbioc" ,r-zlibbioc)))
9579 `(("r-knitr" ,r-knitr)))
9580 (home-page "https://github.com/sneumann/mzR/")
9581 (synopsis "Parser for mass spectrometry data files")
9583 "The mzR package provides a unified API to the common file formats and
9584 parsers available for mass spectrometry data. It comes with a wrapper for the
9585 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9586 The package contains the original code written by the ISB, and a subset of the
9587 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9588 previously been used in XCMS.")
9589 (license license:artistic2.0)))
9591 (define-public r-affyio
9598 (uri (bioconductor-uri "affyio" version))
9601 "0j1f61409yq6hmkqrpzamfm7dx35rlq33ccs7wb1qcqx3d3nb75q"))))
9602 (build-system r-build-system)
9604 `(("r-zlibbioc" ,r-zlibbioc)))
9607 (home-page "https://github.com/bmbolstad/affyio")
9608 (synopsis "Tools for parsing Affymetrix data files")
9610 "This package provides routines for parsing Affymetrix data files based
9611 upon file format information. The primary focus is on accessing the CEL and
9613 (license license:lgpl2.0+)))
9615 (define-public r-affy
9622 (uri (bioconductor-uri "affy" version))
9625 "0m6hkyjxmsf80n3anhwh9k26csxczv6v92fkb7klnchdski61pyc"))))
9626 (build-system r-build-system)
9628 `(("r-affyio" ,r-affyio)
9629 ("r-biobase" ,r-biobase)
9630 ("r-biocgenerics" ,r-biocgenerics)
9631 ("r-biocmanager" ,r-biocmanager)
9632 ("r-preprocesscore" ,r-preprocesscore)
9633 ("r-zlibbioc" ,r-zlibbioc)))
9636 (home-page "https://bioconductor.org/packages/affy")
9637 (synopsis "Methods for affymetrix oligonucleotide arrays")
9639 "This package contains functions for exploratory oligonucleotide array
9641 (license license:lgpl2.0+)))
9643 (define-public r-vsn
9650 (uri (bioconductor-uri "vsn" version))
9653 "1k82dikrv1gcync5y1131wg7z1kxv2z2jl4nndg20bixc3398h58"))))
9654 (build-system r-build-system)
9656 `(("r-affy" ,r-affy)
9657 ("r-biobase" ,r-biobase)
9658 ("r-ggplot2" ,r-ggplot2)
9659 ("r-lattice" ,r-lattice)
9660 ("r-limma" ,r-limma)))
9662 `(("r-knitr" ,r-knitr))) ; for vignettes
9663 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9664 (synopsis "Variance stabilization and calibration for microarray data")
9666 "The package implements a method for normalising microarray intensities,
9667 and works for single- and multiple-color arrays. It can also be used for data
9668 from other technologies, as long as they have similar format. The method uses
9669 a robust variant of the maximum-likelihood estimator for an
9670 additive-multiplicative error model and affine calibration. The model
9671 incorporates data calibration step (a.k.a. normalization), a model for the
9672 dependence of the variance on the mean intensity and a variance stabilizing
9673 data transformation. Differences between transformed intensities are
9674 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9675 their variance is independent of the mean, and they are usually more sensitive
9676 and specific in detecting differential transcription.")
9677 (license license:artistic2.0)))
9679 (define-public r-mzid
9686 (uri (bioconductor-uri "mzID" version))
9689 "0y50lzkdamkpz67f6r5whp246qsxpbammjil7g8vjprx0c4jk5n5"))))
9690 (properties `((upstream-name . "mzID")))
9691 (build-system r-build-system)
9693 `(("r-doparallel" ,r-doparallel)
9694 ("r-foreach" ,r-foreach)
9695 ("r-iterators" ,r-iterators)
9697 ("r-protgenerics" ,r-protgenerics)
9701 `(("r-knitr" ,r-knitr)))
9702 (home-page "https://bioconductor.org/packages/mzID")
9703 (synopsis "Parser for mzIdentML files")
9705 "This package provides a parser for mzIdentML files implemented using the
9706 XML package. The parser tries to be general and able to handle all types of
9707 mzIdentML files with the drawback of having less pretty output than a vendor
9709 (license license:gpl2+)))
9711 (define-public r-pcamethods
9713 (name "r-pcamethods")
9718 (uri (bioconductor-uri "pcaMethods" version))
9721 "10cww4jxyynkwxbbsx804nwac31j0hh8dgisygld0q663gaxkgni"))))
9722 (properties `((upstream-name . "pcaMethods")))
9723 (build-system r-build-system)
9725 `(("r-biobase" ,r-biobase)
9726 ("r-biocgenerics" ,r-biocgenerics)
9728 ("r-rcpp" ,r-rcpp)))
9729 (home-page "https://github.com/hredestig/pcamethods")
9730 (synopsis "Collection of PCA methods")
9732 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9733 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9734 for missing value estimation is included for comparison. BPCA, PPCA and
9735 NipalsPCA may be used to perform PCA on incomplete data as well as for
9736 accurate missing value estimation. A set of methods for printing and plotting
9737 the results is also provided. All PCA methods make use of the same data
9738 structure (pcaRes) to provide a common interface to the PCA results.")
9739 (license license:gpl3+)))
9741 (define-public r-msnbase
9748 (uri (bioconductor-uri "MSnbase" version))
9751 "17vlv9gh41s1hp043b7j1jfqiw52alh1misjzy1kxl0g90rld00l"))))
9752 (properties `((upstream-name . "MSnbase")))
9753 (build-system r-build-system)
9755 `(("r-affy" ,r-affy)
9756 ("r-biobase" ,r-biobase)
9757 ("r-biocgenerics" ,r-biocgenerics)
9758 ("r-biocparallel" ,r-biocparallel)
9759 ("r-digest" ,r-digest)
9760 ("r-ggplot2" ,r-ggplot2)
9761 ("r-impute" ,r-impute)
9762 ("r-iranges" ,r-iranges)
9763 ("r-lattice" ,r-lattice)
9764 ("r-maldiquant" ,r-maldiquant)
9768 ("r-pcamethods" ,r-pcamethods)
9770 ("r-preprocesscore" ,r-preprocesscore)
9771 ("r-protgenerics" ,r-protgenerics)
9773 ("r-s4vectors" ,r-s4vectors)
9774 ("r-scales" ,r-scales)
9778 `(("r-knitr" ,r-knitr)))
9779 (home-page "https://github.com/lgatto/MSnbase")
9780 (synopsis "Base functions and classes for MS-based proteomics")
9782 "This package provides basic plotting, data manipulation and processing
9783 of mass spectrometry based proteomics data.")
9784 (license license:artistic2.0)))
9786 (define-public r-msnid
9793 (uri (bioconductor-uri "MSnID" version))
9796 "0dwa6j2nqb3223a8g4f453aznjh69wngrpvdi12iy69j1psbbjcc"))))
9797 (properties `((upstream-name . "MSnID")))
9798 (build-system r-build-system)
9800 `(("r-biobase" ,r-biobase)
9801 ("r-data-table" ,r-data-table)
9802 ("r-doparallel" ,r-doparallel)
9803 ("r-dplyr" ,r-dplyr)
9804 ("r-foreach" ,r-foreach)
9805 ("r-iterators" ,r-iterators)
9806 ("r-msnbase" ,r-msnbase)
9809 ("r-protgenerics" ,r-protgenerics)
9810 ("r-r-cache" ,r-r-cache)
9812 ("r-reshape2" ,r-reshape2)))
9813 (home-page "https://bioconductor.org/packages/MSnID")
9814 (synopsis "Utilities for LC-MSn proteomics identifications")
9816 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9817 from mzIdentML (leveraging the mzID package) or text files. After collating
9818 the search results from multiple datasets it assesses their identification
9819 quality and optimize filtering criteria to achieve the maximum number of
9820 identifications while not exceeding a specified false discovery rate. It also
9821 contains a number of utilities to explore the MS/MS results and assess missed
9822 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9823 (license license:artistic2.0)))
9825 (define-public r-seurat
9831 (uri (cran-uri "Seurat" version))
9834 "1lbq2pqhb6ih6iqawlnzdh05zff71pwbw1cpfv2sld3pd7kz0zkm"))))
9835 (properties `((upstream-name . "Seurat")))
9836 (build-system r-build-system)
9839 ("r-cluster" ,r-cluster)
9840 ("r-cowplot" ,r-cowplot)
9841 ("r-fitdistrplus" ,r-fitdistrplus)
9842 ("r-future" ,r-future)
9843 ("r-future-apply" ,r-future-apply)
9844 ("r-ggplot2" ,r-ggplot2)
9845 ("r-ggrepel" ,r-ggrepel)
9846 ("r-ggridges" ,r-ggridges)
9849 ("r-igraph" ,r-igraph)
9850 ("r-irlba" ,r-irlba)
9851 ("r-kernsmooth" ,r-kernsmooth)
9852 ("r-leiden" ,r-leiden)
9853 ("r-lmtest" ,r-lmtest)
9855 ("r-matrix" ,r-matrix)
9856 ("r-patchwork" ,r-patchwork)
9857 ("r-pbapply" ,r-pbapply)
9858 ("r-plotly" ,r-plotly)
9861 ("r-rcolorbrewer" ,r-rcolorbrewer)
9863 ("r-rcppannoy" ,r-rcppannoy)
9864 ("r-rcppeigen" ,r-rcppeigen)
9865 ("r-rcppprogress" ,r-rcppprogress)
9866 ("r-reticulate" ,r-reticulate)
9867 ("r-rlang" ,r-rlang)
9870 ("r-rtsne" ,r-rtsne)
9871 ("r-scales" ,r-scales)
9872 ("r-sctransform" ,r-sctransform)
9874 ("r-uwot" ,r-uwot)))
9875 (home-page "http://www.satijalab.org/seurat")
9876 (synopsis "Seurat is an R toolkit for single cell genomics")
9878 "This package is an R package designed for QC, analysis, and
9879 exploration of single cell RNA-seq data. It easily enables widely-used
9880 analytical techniques, including the identification of highly variable genes,
9881 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9882 algorithms; density clustering, hierarchical clustering, k-means, and the
9883 discovery of differentially expressed genes and markers.")
9884 (license license:gpl3)))
9886 (define-public r-aroma-light
9888 (name "r-aroma-light")
9893 (uri (bioconductor-uri "aroma.light" version))
9896 "19y5f2minx2pp73zdh43v1qkwpkaxygkl8cwlnwja15i46s0bcyc"))))
9897 (properties `((upstream-name . "aroma.light")))
9898 (build-system r-build-system)
9900 `(("r-matrixstats" ,r-matrixstats)
9901 ("r-r-methodss3" ,r-r-methodss3)
9903 ("r-r-utils" ,r-r-utils)))
9904 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9905 (synopsis "Methods for normalization and visualization of microarray data")
9907 "This package provides methods for microarray analysis that take basic
9908 data types such as matrices and lists of vectors. These methods can be used
9909 standalone, be utilized in other packages, or be wrapped up in higher-level
9911 (license license:gpl2+)))
9913 (define-public r-deseq
9920 (uri (bioconductor-uri "DESeq" version))
9923 "047hph5aqmjnz1aqprziw0smdn5lf96hmwpnvqrxv1j2yfvcf3h1"))))
9924 (properties `((upstream-name . "DESeq")))
9925 (build-system r-build-system)
9927 `(("r-biobase" ,r-biobase)
9928 ("r-biocgenerics" ,r-biocgenerics)
9929 ("r-genefilter" ,r-genefilter)
9930 ("r-geneplotter" ,r-geneplotter)
9931 ("r-lattice" ,r-lattice)
9932 ("r-locfit" ,r-locfit)
9934 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9935 (home-page "https://www-huber.embl.de/users/anders/DESeq/")
9936 (synopsis "Differential gene expression analysis")
9938 "This package provides tools for estimating variance-mean dependence in
9939 count data from high-throughput genetic sequencing assays and for testing for
9940 differential expression based on a model using the negative binomial
9942 (license license:gpl3+)))
9944 (define-public r-edaseq
9951 (uri (bioconductor-uri "EDASeq" version))
9954 "12gzxjh73qshlwvsf92lbrf4bi199kxg2snrkprh1z4yqf7bjfm4"))))
9955 (properties `((upstream-name . "EDASeq")))
9956 (build-system r-build-system)
9958 `(("r-annotationdbi" ,r-annotationdbi)
9959 ("r-aroma-light" ,r-aroma-light)
9960 ("r-biobase" ,r-biobase)
9961 ("r-biocgenerics" ,r-biocgenerics)
9962 ("r-biocmanager" ,r-biocmanager)
9963 ("r-biomart" ,r-biomart)
9964 ("r-biostrings" ,r-biostrings)
9965 ("r-deseq" ,r-deseq)
9966 ("r-genomicfeatures" ,r-genomicfeatures)
9967 ("r-genomicranges" ,r-genomicranges)
9968 ("r-iranges" ,r-iranges)
9969 ("r-rsamtools" ,r-rsamtools)
9970 ("r-shortread" ,r-shortread)))
9972 `(("r-knitr" ,r-knitr)))
9973 (home-page "https://github.com/drisso/EDASeq")
9974 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9976 "This package provides support for numerical and graphical summaries of
9977 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9978 adjust for GC-content effect (or other gene-level effects) on read counts:
9979 loess robust local regression, global-scaling, and full-quantile
9980 normalization. Between-lane normalization procedures to adjust for
9981 distributional differences between lanes (e.g., sequencing depth):
9982 global-scaling and full-quantile normalization.")
9983 (license license:artistic2.0)))
9985 (define-public r-interactivedisplaybase
9987 (name "r-interactivedisplaybase")
9992 (uri (bioconductor-uri "interactiveDisplayBase" version))
9995 "1x5vipqa4pgwpd62c1c58shnlpv3zyzzpf4wdwr00q1swkdb7wv3"))))
9997 `((upstream-name . "interactiveDisplayBase")))
9998 (build-system r-build-system)
10000 `(("r-biocgenerics" ,r-biocgenerics)
10002 ("r-shiny" ,r-shiny)))
10004 `(("r-knitr" ,r-knitr)))
10005 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
10006 (synopsis "Base package for web displays of Bioconductor objects")
10008 "This package contains the basic methods needed to generate interactive
10009 Shiny-based display methods for Bioconductor objects.")
10010 (license license:artistic2.0)))
10012 (define-public r-annotationhub
10014 (name "r-annotationhub")
10019 (uri (bioconductor-uri "AnnotationHub" version))
10022 "0r4xzf93bm9cpys5cg70wg0b8hxli80hvqwgh4hzbd45yyf5c4wz"))))
10023 (properties `((upstream-name . "AnnotationHub")))
10024 (build-system r-build-system)
10026 `(("r-annotationdbi" ,r-annotationdbi)
10027 ("r-biocfilecache" ,r-biocfilecache)
10028 ("r-biocgenerics" ,r-biocgenerics)
10029 ("r-biocmanager" ,r-biocmanager)
10030 ("r-biocversion" ,r-biocversion)
10032 ("r-dplyr" ,r-dplyr)
10034 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
10035 ("r-rappdirs" ,r-rappdirs)
10036 ("r-rsqlite" ,r-rsqlite)
10037 ("r-s4vectors" ,r-s4vectors)
10038 ("r-yaml" ,r-yaml)))
10040 `(("r-knitr" ,r-knitr)))
10041 (home-page "https://bioconductor.org/packages/AnnotationHub")
10042 (synopsis "Client to access AnnotationHub resources")
10044 "This package provides a client for the Bioconductor AnnotationHub web
10045 resource. The AnnotationHub web resource provides a central location where
10046 genomic files (e.g. VCF, bed, wig) and other resources from standard
10047 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
10048 metadata about each resource, e.g., a textual description, tags, and date of
10049 modification. The client creates and manages a local cache of files retrieved
10050 by the user, helping with quick and reproducible access.")
10051 (license license:artistic2.0)))
10053 (define-public r-fastseg
10060 (uri (bioconductor-uri "fastseg" version))
10063 "1d48n245pzmvcpsz93lxb4frqh222gfhpmlvm0sb74skn16way63"))))
10064 (build-system r-build-system)
10066 `(("r-biobase" ,r-biobase)
10067 ("r-biocgenerics" ,r-biocgenerics)
10068 ("r-genomicranges" ,r-genomicranges)
10069 ("r-iranges" ,r-iranges)
10070 ("r-s4vectors" ,r-s4vectors)))
10071 (home-page "https://www.bioinf.jku.at/software/fastseg/index.html")
10072 (synopsis "Fast segmentation algorithm for genetic sequencing data")
10074 "Fastseg implements a very fast and efficient segmentation algorithm.
10075 It can segment data from DNA microarrays and data from next generation
10076 sequencing for example to detect copy number segments. Further it can segment
10077 data from RNA microarrays like tiling arrays to identify transcripts. Most
10078 generally, it can segment data given as a matrix or as a vector. Various data
10079 formats can be used as input to fastseg like expression set objects for
10080 microarrays or GRanges for sequencing data.")
10081 (license license:lgpl2.0+)))
10083 (define-public r-keggrest
10085 (name "r-keggrest")
10090 (uri (bioconductor-uri "KEGGREST" version))
10093 "0q76w17fya2x0z7mvyhkk5kqh07flldgih13ma44vhcy1bdlm6j1"))))
10094 (properties `((upstream-name . "KEGGREST")))
10095 (build-system r-build-system)
10097 `(("r-biostrings" ,r-biostrings)
10101 `(("r-knitr" ,r-knitr)))
10102 (home-page "https://bioconductor.org/packages/KEGGREST")
10103 (synopsis "Client-side REST access to KEGG")
10105 "This package provides a package that provides a client interface to the
10106 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
10107 (license license:artistic2.0)))
10109 (define-public r-gage
10116 (uri (bioconductor-uri "gage" version))
10119 "1zfaas4x6g7wiml6cmxa7b4f43az9s0lrw80k6sf7c96hsh1jijr"))))
10120 (build-system r-build-system)
10122 `(("r-annotationdbi" ,r-annotationdbi)
10123 ("r-graph" ,r-graph)
10124 ("r-keggrest" ,r-keggrest)))
10125 (home-page (string-append "https://bmcbioinformatics.biomedcentral.com/"
10126 "articles/10.1186/1471-2105-10-161"))
10127 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
10129 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
10130 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
10131 data attributes including sample sizes, experimental designs, assay platforms,
10132 and other types of heterogeneity. The gage package provides functions for
10133 basic GAGE analysis, result processing and presentation. In addition, it
10134 provides demo microarray data and commonly used gene set data based on KEGG
10135 pathways and GO terms. These functions and data are also useful for gene set
10136 analysis using other methods.")
10137 (license license:gpl2+)))
10139 (define-public r-genomicfiles
10141 (name "r-genomicfiles")
10146 (uri (bioconductor-uri "GenomicFiles" version))
10149 "1k3824pzf9fdqvcv6cz2742q3mabpmncrc72hwa21ac8wy1b04n4"))))
10150 (properties `((upstream-name . "GenomicFiles")))
10151 (build-system r-build-system)
10153 `(("r-biocgenerics" ,r-biocgenerics)
10154 ("r-biocparallel" ,r-biocparallel)
10155 ("r-genomeinfodb" ,r-genomeinfodb)
10156 ("r-genomicalignments" ,r-genomicalignments)
10157 ("r-genomicranges" ,r-genomicranges)
10158 ("r-iranges" ,r-iranges)
10159 ("r-rsamtools" ,r-rsamtools)
10160 ("r-rtracklayer" ,r-rtracklayer)
10161 ("r-s4vectors" ,r-s4vectors)
10162 ("r-summarizedexperiment" ,r-summarizedexperiment)
10163 ("r-variantannotation" ,r-variantannotation)))
10164 (home-page "https://bioconductor.org/packages/GenomicFiles")
10165 (synopsis "Distributed computing by file or by range")
10167 "This package provides infrastructure for parallel computations
10168 distributed by file or by range. User defined mapper and reducer functions
10169 provide added flexibility for data combination and manipulation.")
10170 (license license:artistic2.0)))
10172 (define-public r-complexheatmap
10174 (name "r-complexheatmap")
10179 (uri (bioconductor-uri "ComplexHeatmap" version))
10182 "01jxxwxhf9n8baxgja4rb592p5210s4ppd7a5b4xby5aalhzkr0l"))))
10184 `((upstream-name . "ComplexHeatmap")))
10185 (build-system r-build-system)
10187 `(("r-circlize" ,r-circlize)
10189 ("r-colorspace" ,r-colorspace)
10190 ("r-getoptlong" ,r-getoptlong)
10191 ("r-globaloptions" ,r-globaloptions)
10193 ("r-rcolorbrewer" ,r-rcolorbrewer)))
10195 `(("r-knitr" ,r-knitr)))
10197 "https://github.com/jokergoo/ComplexHeatmap")
10198 (synopsis "Making Complex Heatmaps")
10200 "Complex heatmaps are efficient to visualize associations between
10201 different sources of data sets and reveal potential structures. This package
10202 provides a highly flexible way to arrange multiple heatmaps and supports
10203 self-defined annotation graphics.")
10204 (license license:gpl2+)))
10206 (define-public r-dirichletmultinomial
10208 (name "r-dirichletmultinomial")
10213 (uri (bioconductor-uri "DirichletMultinomial" version))
10216 "1m9dsrddrllb2i88qzik1867iv9mggrgdkn0dlp8sq7gl69vmalb"))))
10218 `((upstream-name . "DirichletMultinomial")))
10219 (build-system r-build-system)
10223 `(("r-biocgenerics" ,r-biocgenerics)
10224 ("r-iranges" ,r-iranges)
10225 ("r-s4vectors" ,r-s4vectors)))
10226 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
10227 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
10229 "Dirichlet-multinomial mixture models can be used to describe variability
10230 in microbial metagenomic data. This package is an interface to code
10231 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
10233 (license license:lgpl3)))
10235 (define-public r-ensembldb
10237 (name "r-ensembldb")
10242 (uri (bioconductor-uri "ensembldb" version))
10245 "1vvchc04nshxc768fp31rxb603aj3hmq8xlh5qabcwf2c3z9719g"))))
10246 (build-system r-build-system)
10248 `(("r-annotationdbi" ,r-annotationdbi)
10249 ("r-annotationfilter" ,r-annotationfilter)
10250 ("r-biobase" ,r-biobase)
10251 ("r-biocgenerics" ,r-biocgenerics)
10252 ("r-biostrings" ,r-biostrings)
10255 ("r-genomeinfodb" ,r-genomeinfodb)
10256 ("r-genomicfeatures" ,r-genomicfeatures)
10257 ("r-genomicranges" ,r-genomicranges)
10258 ("r-iranges" ,r-iranges)
10259 ("r-protgenerics" ,r-protgenerics)
10260 ("r-rsamtools" ,r-rsamtools)
10261 ("r-rsqlite" ,r-rsqlite)
10262 ("r-rtracklayer" ,r-rtracklayer)
10263 ("r-s4vectors" ,r-s4vectors)))
10265 `(("r-knitr" ,r-knitr)))
10266 (home-page "https://github.com/jotsetung/ensembldb")
10267 (synopsis "Utilities to create and use Ensembl-based annotation databases")
10269 "The package provides functions to create and use transcript-centric
10270 annotation databases/packages. The annotation for the databases are directly
10271 fetched from Ensembl using their Perl API. The functionality and data is
10272 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
10273 but, in addition to retrieve all gene/transcript models and annotations from
10274 the database, the @code{ensembldb} package also provides a filter framework
10275 allowing to retrieve annotations for specific entries like genes encoded on a
10276 chromosome region or transcript models of lincRNA genes.")
10277 ;; No version specified
10278 (license license:lgpl3+)))
10280 (define-public r-organismdbi
10282 (name "r-organismdbi")
10287 (uri (bioconductor-uri "OrganismDbi" version))
10290 "194h5576inq44qr666snzq0ygnc77rk5ljkn9bn8zs6x6gb3cwaw"))))
10291 (properties `((upstream-name . "OrganismDbi")))
10292 (build-system r-build-system)
10294 `(("r-annotationdbi" ,r-annotationdbi)
10295 ("r-biobase" ,r-biobase)
10296 ("r-biocgenerics" ,r-biocgenerics)
10297 ("r-biocmanager" ,r-biocmanager)
10299 ("r-genomicfeatures" ,r-genomicfeatures)
10300 ("r-genomicranges" ,r-genomicranges)
10301 ("r-graph" ,r-graph)
10302 ("r-iranges" ,r-iranges)
10304 ("r-s4vectors" ,r-s4vectors)))
10305 (home-page "https://bioconductor.org/packages/OrganismDbi")
10306 (synopsis "Software to enable the smooth interfacing of database packages")
10307 (description "The package enables a simple unified interface to several
10308 annotation packages each of which has its own schema by taking advantage of
10309 the fact that each of these packages implements a select methods.")
10310 (license license:artistic2.0)))
10312 (define-public r-biovizbase
10314 (name "r-biovizbase")
10319 (uri (bioconductor-uri "biovizBase" version))
10322 "1vq2mxa2jkljgw75zqjdkyml0ppi5dspvwj4cznfhi31cq8ds0qh"))))
10323 (properties `((upstream-name . "biovizBase")))
10324 (build-system r-build-system)
10326 `(("r-annotationdbi" ,r-annotationdbi)
10327 ("r-annotationfilter" ,r-annotationfilter)
10328 ("r-biocgenerics" ,r-biocgenerics)
10329 ("r-biostrings" ,r-biostrings)
10330 ("r-dichromat" ,r-dichromat)
10331 ("r-ensembldb" ,r-ensembldb)
10332 ("r-genomeinfodb" ,r-genomeinfodb)
10333 ("r-genomicalignments" ,r-genomicalignments)
10334 ("r-genomicfeatures" ,r-genomicfeatures)
10335 ("r-genomicranges" ,r-genomicranges)
10336 ("r-hmisc" ,r-hmisc)
10337 ("r-iranges" ,r-iranges)
10338 ("r-rcolorbrewer" ,r-rcolorbrewer)
10339 ("r-rlang" ,r-rlang)
10340 ("r-rsamtools" ,r-rsamtools)
10341 ("r-s4vectors" ,r-s4vectors)
10342 ("r-scales" ,r-scales)
10343 ("r-summarizedexperiment" ,r-summarizedexperiment)
10344 ("r-variantannotation" ,r-variantannotation)))
10345 (home-page "https://bioconductor.org/packages/biovizBase")
10346 (synopsis "Basic graphic utilities for visualization of genomic data")
10348 "The biovizBase package is designed to provide a set of utilities, color
10349 schemes and conventions for genomic data. It serves as the base for various
10350 high-level packages for biological data visualization. This saves development
10351 effort and encourages consistency.")
10352 (license license:artistic2.0)))
10354 (define-public r-ggbio
10361 (uri (bioconductor-uri "ggbio" version))
10364 "11ggnqjq42fi2hm9xlvrrlr2xhy4kglvl1a0mycp1s4v67lxw5h5"))))
10365 (build-system r-build-system)
10368 (modify-phases %standard-phases
10369 ;; See https://github.com/tengfei/ggbio/issues/117
10370 ;; This fix will be included in the next release.
10371 (add-after 'unpack 'fix-typo
10373 (substitute* "R/GGbio-class.R"
10374 (("fechable") "fetchable"))
10377 `(("r-annotationdbi" ,r-annotationdbi)
10378 ("r-annotationfilter" ,r-annotationfilter)
10379 ("r-biobase" ,r-biobase)
10380 ("r-biocgenerics" ,r-biocgenerics)
10381 ("r-biostrings" ,r-biostrings)
10382 ("r-biovizbase" ,r-biovizbase)
10383 ("r-bsgenome" ,r-bsgenome)
10384 ("r-ensembldb" ,r-ensembldb)
10385 ("r-genomeinfodb" ,r-genomeinfodb)
10386 ("r-genomicalignments" ,r-genomicalignments)
10387 ("r-genomicfeatures" ,r-genomicfeatures)
10388 ("r-genomicranges" ,r-genomicranges)
10389 ("r-ggally" ,r-ggally)
10390 ("r-ggplot2" ,r-ggplot2)
10391 ("r-gridextra" ,r-gridextra)
10392 ("r-gtable" ,r-gtable)
10393 ("r-hmisc" ,r-hmisc)
10394 ("r-iranges" ,r-iranges)
10395 ("r-organismdbi" ,r-organismdbi)
10396 ("r-reshape2" ,r-reshape2)
10397 ("r-rlang" ,r-rlang)
10398 ("r-rsamtools" ,r-rsamtools)
10399 ("r-rtracklayer" ,r-rtracklayer)
10400 ("r-s4vectors" ,r-s4vectors)
10401 ("r-scales" ,r-scales)
10402 ("r-summarizedexperiment" ,r-summarizedexperiment)
10403 ("r-variantannotation" ,r-variantannotation)))
10405 `(("r-knitr" ,r-knitr)))
10406 (home-page "http://www.tengfei.name/ggbio/")
10407 (synopsis "Visualization tools for genomic data")
10409 "The ggbio package extends and specializes the grammar of graphics for
10410 biological data. The graphics are designed to answer common scientific
10411 questions, in particular those often asked of high throughput genomics data.
10412 All core Bioconductor data structures are supported, where appropriate. The
10413 package supports detailed views of particular genomic regions, as well as
10414 genome-wide overviews. Supported overviews include ideograms and grand linear
10415 views. High-level plots include sequence fragment length, edge-linked
10416 interval to data view, mismatch pileup, and several splicing summaries.")
10417 (license license:artistic2.0)))
10419 (define-public r-gqtlbase
10421 (name "r-gqtlbase")
10426 (uri (bioconductor-uri "gQTLBase" version))
10429 "06xvzp4fn3qfa46ggg8kxi267gbyd821vvx4040173xkqxpr0g5j"))))
10430 (properties `((upstream-name . "gQTLBase")))
10431 (build-system r-build-system)
10433 `(("r-batchjobs" ,r-batchjobs)
10434 ("r-bbmisc" ,r-bbmisc)
10435 ("r-biocgenerics" ,r-biocgenerics)
10437 ("r-doparallel" ,r-doparallel)
10439 ("r-ffbase" ,r-ffbase)
10440 ("r-foreach" ,r-foreach)
10441 ("r-genomicfiles" ,r-genomicfiles)
10442 ("r-genomicranges" ,r-genomicranges)
10443 ("r-rtracklayer" ,r-rtracklayer)
10444 ("r-s4vectors" ,r-s4vectors)
10445 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10447 `(("r-knitr" ,r-knitr)))
10448 (home-page "https://bioconductor.org/packages/gQTLBase")
10449 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10451 "The purpose of this package is to simplify the storage and interrogation
10452 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10454 (license license:artistic2.0)))
10456 (define-public r-snpstats
10458 (name "r-snpstats")
10463 (uri (bioconductor-uri "snpStats" version))
10466 "1qv3nqqr30d3n66mawqd9dbl95dl89r4bcjvkc5iassy1yrwr8wq"))))
10467 (properties `((upstream-name . "snpStats")))
10468 (build-system r-build-system)
10469 (inputs `(("zlib" ,zlib)))
10471 `(("r-biocgenerics" ,r-biocgenerics)
10472 ("r-matrix" ,r-matrix)
10473 ("r-survival" ,r-survival)
10474 ("r-zlibbioc" ,r-zlibbioc)))
10475 (home-page "https://bioconductor.org/packages/snpStats")
10476 (synopsis "Methods for SNP association studies")
10478 "This package provides classes and statistical methods for large
10479 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10480 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10481 (license license:gpl3)))
10483 (define-public r-homo-sapiens
10485 (name "r-homo-sapiens")
10489 ;; We cannot use bioconductor-uri here because this tarball is
10490 ;; located under "data/annotation/" instead of "bioc/".
10491 (uri (string-append "https://www.bioconductor.org/packages/"
10492 "release/data/annotation/src/contrib/"
10494 version ".tar.gz"))
10497 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10499 `((upstream-name . "Homo.sapiens")))
10500 (build-system r-build-system)
10502 `(("r-genomicfeatures" ,r-genomicfeatures)
10503 ("r-go-db" ,r-go-db)
10504 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10505 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10506 ("r-organismdbi" ,r-organismdbi)
10507 ("r-annotationdbi" ,r-annotationdbi)))
10508 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10509 (synopsis "Annotation package for the Homo.sapiens object")
10511 "This package contains the Homo.sapiens object to access data from
10512 several related annotation packages.")
10513 (license license:artistic2.0)))
10515 (define-public r-erma
10522 (uri (bioconductor-uri "erma" version))
10525 "1ccfbq0r48sr3h8050w8zv8402h7nx09adr0xdyqlg7kwp9vd2l3"))))
10526 (build-system r-build-system)
10528 `(("r-annotationdbi" ,r-annotationdbi)
10529 ("r-biobase" ,r-biobase)
10530 ("r-biocgenerics" ,r-biocgenerics)
10531 ("r-biocparallel" ,r-biocparallel)
10532 ("r-genomeinfodb" ,r-genomeinfodb)
10533 ("r-genomicfiles" ,r-genomicfiles)
10534 ("r-genomicranges" ,r-genomicranges)
10535 ("r-ggplot2" ,r-ggplot2)
10536 ("r-homo-sapiens" ,r-homo-sapiens)
10537 ("r-iranges" ,r-iranges)
10538 ("r-rtracklayer" ,r-rtracklayer)
10539 ("r-s4vectors" ,r-s4vectors)
10540 ("r-shiny" ,r-shiny)
10541 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10543 `(("r-knitr" ,r-knitr)))
10544 (home-page "https://bioconductor.org/packages/erma")
10545 (synopsis "Epigenomic road map adventures")
10547 "The epigenomics road map describes locations of epigenetic marks in DNA
10548 from a variety of cell types. Of interest are locations of histone
10549 modifications, sites of DNA methylation, and regions of accessible chromatin.
10550 This package presents a selection of elements of the road map including
10551 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10552 by Ernst and Kellis.")
10553 (license license:artistic2.0)))
10555 (define-public r-ldblock
10562 (uri (bioconductor-uri "ldblock" version))
10565 "0plw00n2zfgh029ab41dnydzgv2yxrapjp770147rx9pff4dngrv"))))
10566 (build-system r-build-system)
10568 `(("r-biocgenerics" ,r-biocgenerics)
10569 ("r-ensdb-hsapiens-v75" ,r-ensdb-hsapiens-v75)
10570 ("r-ensembldb" ,r-ensembldb)
10571 ("r-genomeinfodb" ,r-genomeinfodb)
10572 ("r-genomicfiles" ,r-genomicfiles)
10574 ("r-matrix" ,r-matrix)
10575 ("r-rsamtools" ,r-rsamtools)
10576 ("r-snpstats" ,r-snpstats)
10577 ("r-variantannotation" ,r-variantannotation)))
10579 `(("r-knitr" ,r-knitr)))
10580 (home-page "https://bioconductor.org/packages/ldblock")
10581 (synopsis "Data structures for linkage disequilibrium measures in populations")
10583 "This package defines data structures for @dfn{linkage
10584 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10585 handling of existing population-level data for the purpose of flexibly
10586 defining LD blocks.")
10587 (license license:artistic2.0)))
10589 (define-public r-gqtlstats
10591 (name "r-gqtlstats")
10596 (uri (bioconductor-uri "gQTLstats" version))
10599 "1jjqfpjp93nmxjn757j5mzcax96bzcqdd1gr3rsdxg7ap008l2w7"))))
10600 (properties `((upstream-name . "gQTLstats")))
10601 (build-system r-build-system)
10603 `(("r-annotationdbi" ,r-annotationdbi)
10604 ("r-batchjobs" ,r-batchjobs)
10605 ("r-bbmisc" ,r-bbmisc)
10606 ("r-beeswarm" ,r-beeswarm)
10607 ("r-biobase" ,r-biobase)
10608 ("r-biocgenerics" ,r-biocgenerics)
10609 ("r-doparallel" ,r-doparallel)
10610 ("r-dplyr" ,r-dplyr)
10612 ("r-ffbase" ,r-ffbase)
10613 ("r-foreach" ,r-foreach)
10614 ("r-genomeinfodb" ,r-genomeinfodb)
10615 ("r-genomicfeatures" ,r-genomicfeatures)
10616 ("r-genomicfiles" ,r-genomicfiles)
10617 ("r-genomicranges" ,r-genomicranges)
10618 ("r-ggbeeswarm" ,r-ggbeeswarm)
10619 ("r-ggplot2" ,r-ggplot2)
10620 ("r-gqtlbase" ,r-gqtlbase)
10621 ("r-hardyweinberg" ,r-hardyweinberg)
10622 ("r-homo-sapiens" ,r-homo-sapiens)
10623 ("r-iranges" ,r-iranges)
10624 ("r-limma" ,r-limma)
10626 ("r-plotly" ,r-plotly)
10627 ("r-reshape2" ,r-reshape2)
10628 ("r-s4vectors" ,r-s4vectors)
10629 ("r-shiny" ,r-shiny)
10630 ("r-snpstats" ,r-snpstats)
10631 ("r-summarizedexperiment" ,r-summarizedexperiment)
10632 ("r-variantannotation" ,r-variantannotation)))
10634 `(("r-knitr" ,r-knitr)))
10635 (home-page "https://bioconductor.org/packages/gQTLstats")
10636 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10638 "This package provides tools for the computationally efficient analysis
10639 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10640 The software in this package aims to support refinements and functional
10641 interpretation of members of a collection of association statistics on a
10642 family of feature/genome hypotheses.")
10643 (license license:artistic2.0)))
10645 (define-public r-gviz
10652 (uri (bioconductor-uri "Gviz" version))
10655 "0cgkp0ciyy2qykqgh3vzp5mx9b4vsvacjh2jnsj3wldiapzlz08a"))))
10656 (properties `((upstream-name . "Gviz")))
10657 (build-system r-build-system)
10659 `(("r-annotationdbi" ,r-annotationdbi)
10660 ("r-biobase" ,r-biobase)
10661 ("r-biocgenerics" ,r-biocgenerics)
10662 ("r-biomart" ,r-biomart)
10663 ("r-biostrings" ,r-biostrings)
10664 ("r-biovizbase" ,r-biovizbase)
10665 ("r-bsgenome" ,r-bsgenome)
10666 ("r-digest" ,r-digest)
10667 ("r-ensembldb" ,r-ensembldb)
10668 ("r-genomeinfodb" ,r-genomeinfodb)
10669 ("r-genomicalignments" ,r-genomicalignments)
10670 ("r-genomicfeatures" ,r-genomicfeatures)
10671 ("r-genomicranges" ,r-genomicranges)
10672 ("r-iranges" ,r-iranges)
10673 ("r-lattice" ,r-lattice)
10674 ("r-latticeextra" ,r-latticeextra)
10675 ("r-matrixstats" ,r-matrixstats)
10676 ("r-rcolorbrewer" ,r-rcolorbrewer)
10677 ("r-rsamtools" ,r-rsamtools)
10678 ("r-rtracklayer" ,r-rtracklayer)
10679 ("r-s4vectors" ,r-s4vectors)
10680 ("r-xvector" ,r-xvector)))
10682 `(("r-knitr" ,r-knitr)))
10683 (home-page "https://bioconductor.org/packages/Gviz")
10684 (synopsis "Plotting data and annotation information along genomic coordinates")
10686 "Genomic data analyses requires integrated visualization of known genomic
10687 information and new experimental data. Gviz uses the biomaRt and the
10688 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10689 and translates this to e.g. gene/transcript structures in viewports of the
10690 grid graphics package. This results in genomic information plotted together
10692 (license license:artistic2.0)))
10694 (define-public r-gwascat
10701 (uri (bioconductor-uri "gwascat" version))
10704 "1cq5cmdrf0a0arr841yvkh6d8drc15p7mif1afr215l1s3y2dwd4"))))
10705 (build-system r-build-system)
10707 `(("r-annotationdbi" ,r-annotationdbi)
10708 ("r-biocgenerics" ,r-biocgenerics)
10709 ("r-biostrings" ,r-biostrings)
10710 ("r-genomeinfodb" ,r-genomeinfodb)
10711 ("r-genomicfeatures" ,r-genomicfeatures)
10712 ("r-genomicranges" ,r-genomicranges)
10713 ("r-ggplot2" ,r-ggplot2)
10714 ("r-iranges" ,r-iranges)
10715 ("r-rsamtools" ,r-rsamtools)
10716 ("r-rtracklayer" ,r-rtracklayer)
10717 ("r-s4vectors" ,r-s4vectors)))
10719 `(("r-knitr" ,r-knitr)))
10720 (home-page "https://bioconductor.org/packages/gwascat")
10721 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10723 "This package provides tools for representing and modeling data in the
10724 EMBL-EBI GWAS catalog.")
10725 (license license:artistic2.0)))
10727 (define-public r-sushi
10733 (uri (bioconductor-uri "Sushi" version))
10736 "17j3d5qjq5nbv99by5mq8rwr0jgh2jyyfn2nwxmwgzlmk3lgi1rb"))))
10737 (properties `((upstream-name . "Sushi")))
10738 (build-system r-build-system)
10740 `(("r-biomart" ,r-biomart)
10742 (home-page "https://bioconductor.org/packages/Sushi")
10743 (synopsis "Tools for visualizing genomics data")
10745 "This package provides flexible, quantitative, and integrative genomic
10746 visualizations for publication-quality multi-panel figures.")
10747 (license license:gpl2+)))
10749 (define-public r-fithic
10755 (uri (bioconductor-uri "FitHiC" version))
10758 "1dffkdxm08wq4kjd9j2v2625x3p6vbrk33a2zx94pwpgkghr72yp"))))
10759 (properties `((upstream-name . "FitHiC")))
10760 (build-system r-build-system)
10762 `(("r-data-table" ,r-data-table)
10763 ("r-fdrtool" ,r-fdrtool)
10764 ("r-rcpp" ,r-rcpp)))
10766 `(("r-knitr" ,r-knitr)))
10767 (home-page "https://bioconductor.org/packages/FitHiC")
10768 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10770 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10771 intra-chromosomal contact maps produced by genome-wide genome architecture
10772 assays such as Hi-C.")
10773 (license license:gpl2+)))
10775 (define-public r-hitc
10781 (uri (bioconductor-uri "HiTC" version))
10784 "1jx2pfa7sbdz7xi466lz1h5xv126g56z73n0a5l2wrq28k47qaxy"))))
10785 (properties `((upstream-name . "HiTC")))
10786 (build-system r-build-system)
10788 `(("r-biostrings" ,r-biostrings)
10789 ("r-genomeinfodb" ,r-genomeinfodb)
10790 ("r-genomicranges" ,r-genomicranges)
10791 ("r-iranges" ,r-iranges)
10792 ("r-matrix" ,r-matrix)
10793 ("r-rcolorbrewer" ,r-rcolorbrewer)
10794 ("r-rtracklayer" ,r-rtracklayer)))
10795 (home-page "https://bioconductor.org/packages/HiTC")
10796 (synopsis "High throughput chromosome conformation capture analysis")
10798 "The HiTC package was developed to explore high-throughput \"C\" data
10799 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10800 quality controls, normalization, visualization, and further analysis are also
10802 (license license:artistic2.0)))
10804 (define-public r-hdf5array
10806 (name "r-hdf5array")
10811 (uri (bioconductor-uri "HDF5Array" version))
10814 "01767v90nl0499jcicpxngbbs0af5p9c5aasi5va01w3v5bnqddn"))))
10815 (properties `((upstream-name . "HDF5Array")))
10816 (build-system r-build-system)
10820 `(("r-biocgenerics" ,r-biocgenerics)
10821 ("r-delayedarray" ,r-delayedarray)
10822 ("r-iranges" ,r-iranges)
10823 ("r-matrix" ,r-matrix)
10824 ("r-rhdf5" ,r-rhdf5)
10825 ("r-rhdf5lib" ,r-rhdf5lib)
10826 ("r-s4vectors" ,r-s4vectors)))
10827 (home-page "https://bioconductor.org/packages/HDF5Array")
10828 (synopsis "HDF5 back end for DelayedArray objects")
10829 (description "This package provides an array-like container for convenient
10830 access and manipulation of HDF5 datasets. It supports delayed operations and
10831 block processing.")
10832 (license license:artistic2.0)))
10834 (define-public r-rhdf5lib
10836 (name "r-rhdf5lib")
10841 (uri (bioconductor-uri "Rhdf5lib" version))
10844 "0f45sqrvzj6x4mckalyp8366hm8v0rrmzklx3xd4gs6l2wallcn9"))
10845 (modules '((guix build utils)))
10848 ;; Delete bundled binaries
10849 (delete-file-recursively "src/wininclude/")
10850 (delete-file-recursively "src/winlib-4.9.3/")
10851 (delete-file-recursively "src/winlib-8.3.0/")
10852 (delete-file "src/hdf5small_cxx_hl_1.10.6.tar.gz")
10854 (properties `((upstream-name . "Rhdf5lib")))
10855 (build-system r-build-system)
10858 (modify-phases %standard-phases
10859 (add-after 'unpack 'do-not-use-bundled-hdf5
10860 (lambda* (#:key inputs #:allow-other-keys)
10861 (for-each delete-file '("configure" "configure.ac"))
10862 ;; Do not make other packages link with the proprietary libsz.
10863 (substitute* "R/zzz.R"
10864 ((" \"%s/libsz.a\"") ""))
10865 (with-directory-excursion "src"
10866 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10867 (rename-file (string-append "hdf5-" ,(package-version hdf5-1.10))
10869 ;; Remove timestamp and host system information to make
10870 ;; the build reproducible.
10871 (substitute* "hdf5/src/libhdf5.settings.in"
10872 (("Configured on: @CONFIG_DATE@")
10873 "Configured on: Guix")
10874 (("Uname information:.*")
10875 "Uname information: Linux\n")
10876 ;; Remove unnecessary store reference.
10878 "C Compiler: GCC\n"))
10879 (rename-file "Makevars.in" "Makevars")
10880 (substitute* "Makevars"
10881 (("@ZLIB_LIB@") "-lz")
10882 (("@ZLIB_INCLUDE@") "")
10883 (("HDF5_CXX_LIB=.*")
10884 (string-append "HDF5_CXX_LIB="
10885 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10887 (string-append "HDF5_LIB="
10888 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10889 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10890 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10891 (("HDF5_HL_INCLUDE=.*") "HDF5_HL_INCLUDE=./hdf5/hl/src\n")
10892 (("HDF5_HL_CXX_INCLUDE=.*") "HDF5_HL_CXX_INCLUDE=./hdf5/hl/c++/src\n")
10893 (("HDF5_HL_LIB=.*")
10894 (string-append "HDF5_HL_LIB="
10895 (assoc-ref inputs "hdf5") "/lib/libhdf5_hl.a\n"))
10896 (("HDF5_HL_CXX_LIB=.*")
10897 (string-append "HDF5_HL_CXX_LIB="
10898 (assoc-ref inputs "hdf5") "/lib/libhdf5_hl_cpp.a\n"))
10899 ;; szip is non-free software
10900 (("cp \"\\$\\{SZIP_LIB\\}.*") "")
10901 (("PKG_LIBS =.*") "PKG_LIBS = -lz -lhdf5\n")))
10906 `(("hdf5" ,hdf5-1.10)))
10908 `(("hdf5-source" ,(package-source hdf5-1.10))
10909 ("r-knitr" ,r-knitr)))
10910 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10911 (synopsis "HDF5 library as an R package")
10912 (description "This package provides C and C++ HDF5 libraries for use in R
10914 (license license:artistic2.0)))
10916 (define-public r-beachmat
10918 (name "r-beachmat")
10923 (uri (bioconductor-uri "beachmat" version))
10926 "1vl6jbf9ia78cm4ikdb8vz04jv4b46zhvg5i006c63a9pzw7zhxi"))))
10927 (build-system r-build-system)
10929 `(("r-biocgenerics" ,r-biocgenerics)
10930 ("r-delayedarray" ,r-delayedarray)
10931 ("r-matrix" ,r-matrix)))
10933 `(("r-knitr" ,r-knitr)))
10934 (home-page "https://bioconductor.org/packages/beachmat")
10935 (synopsis "Compiling Bioconductor to handle each matrix type")
10936 (description "This package provides a consistent C++ class interface for a
10937 variety of commonly used matrix types, including sparse and HDF5-backed
10939 (license license:gpl3)))
10941 (define-public r-singlecellexperiment
10943 (name "r-singlecellexperiment")
10948 (uri (bioconductor-uri "SingleCellExperiment" version))
10951 "092wvk11n7pa234vlwhxm3gdi4k3sbnz1splhxalbdhz3jf02zfp"))))
10953 `((upstream-name . "SingleCellExperiment")))
10954 (build-system r-build-system)
10956 `(("r-biocgenerics" ,r-biocgenerics)
10957 ("r-s4vectors" ,r-s4vectors)
10958 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10960 `(("r-knitr" ,r-knitr)))
10961 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10962 (synopsis "S4 classes for single cell data")
10963 (description "This package defines an S4 class for storing data from
10964 single-cell experiments. This includes specialized methods to store and
10965 retrieve spike-in information, dimensionality reduction coordinates and size
10966 factors for each cell, along with the usual metadata for genes and
10968 (license license:gpl3)))
10970 (define-public r-scater
10976 (uri (bioconductor-uri "scater" version))
10979 "1pa5wvgjb30rw1vsjwbnn07ss3sc5n8ck5d7khdby4r2s9177s33"))))
10980 (build-system r-build-system)
10982 `(("r-beachmat" ,r-beachmat)
10983 ("r-biocgenerics" ,r-biocgenerics)
10984 ("r-biocneighbors" ,r-biocneighbors)
10985 ("r-biocparallel" ,r-biocparallel)
10986 ("r-biocsingular" ,r-biocsingular)
10987 ("r-delayedarray" ,r-delayedarray)
10988 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10989 ("r-ggbeeswarm" ,r-ggbeeswarm)
10990 ("r-ggplot2" ,r-ggplot2)
10991 ("r-matrix" ,r-matrix)
10993 ("r-rlang" ,r-rlang)
10994 ("r-s4vectors" ,r-s4vectors)
10995 ("r-singlecellexperiment" ,r-singlecellexperiment)
10996 ("r-summarizedexperiment" ,r-summarizedexperiment)
10997 ("r-viridis" ,r-viridis)))
10999 `(("r-knitr" ,r-knitr)))
11000 (home-page "https://github.com/davismcc/scater")
11001 (synopsis "Single-cell analysis toolkit for gene expression data in R")
11002 (description "This package provides a collection of tools for doing
11003 various analyses of single-cell RNA-seq gene expression data, with a focus on
11005 (license license:gpl2+)))
11007 (define-public r-scran
11014 (uri (bioconductor-uri "scran" version))
11017 "1gm4ys4aq8h1pn45k1rxk384wjyf55izivw8kgxbrflj6j4xvvsv"))))
11018 (build-system r-build-system)
11020 `(("r-beachmat" ,r-beachmat)
11022 ("r-biocgenerics" ,r-biocgenerics)
11023 ("r-biocneighbors" ,r-biocneighbors)
11024 ("r-biocparallel" ,r-biocparallel)
11025 ("r-biocsingular" ,r-biocsingular)
11026 ("r-delayedarray" ,r-delayedarray)
11027 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
11028 ("r-dqrng" ,r-dqrng)
11029 ("r-edger" ,r-edger)
11030 ("r-igraph" ,r-igraph)
11031 ("r-iranges" ,r-iranges)
11032 ("r-limma" ,r-limma)
11033 ("r-matrix" ,r-matrix)
11035 ("r-s4vectors" ,r-s4vectors)
11036 ("r-scater" ,r-scater)
11037 ("r-singlecellexperiment" ,r-singlecellexperiment)
11038 ("r-statmod" ,r-statmod)
11039 ("r-summarizedexperiment" ,r-summarizedexperiment)))
11041 `(("r-knitr" ,r-knitr)))
11042 (home-page "https://bioconductor.org/packages/scran")
11043 (synopsis "Methods for single-cell RNA-Seq data analysis")
11044 (description "This package implements a variety of low-level analyses of
11045 single-cell RNA-seq data. Methods are provided for normalization of
11046 cell-specific biases, assignment of cell cycle phase, and detection of highly
11047 variable and significantly correlated genes.")
11048 (license license:gpl3)))
11050 (define-public r-delayedmatrixstats
11052 (name "r-delayedmatrixstats")
11057 (uri (bioconductor-uri "DelayedMatrixStats" version))
11060 "046sam0rz42ph0m7jz7v3bck7d3h2mp45gzywh5dvc1qkjq6fdxx"))))
11062 `((upstream-name . "DelayedMatrixStats")))
11063 (build-system r-build-system)
11065 `(("r-biocparallel" ,r-biocparallel)
11066 ("r-delayedarray" ,r-delayedarray)
11067 ("r-hdf5array" ,r-hdf5array)
11068 ("r-iranges" ,r-iranges)
11069 ("r-matrix" ,r-matrix)
11070 ("r-matrixstats" ,r-matrixstats)
11071 ("r-s4vectors" ,r-s4vectors)))
11073 `(("r-knitr" ,r-knitr)))
11074 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
11075 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
11077 "This package provides a port of the @code{matrixStats} API for use with
11078 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
11079 contains high-performing functions operating on rows and columns of
11080 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
11081 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
11082 are optimized per data type and for subsetted calculations such that both
11083 memory usage and processing time is minimized.")
11084 (license license:expat)))
11086 (define-public r-phangorn
11088 (name "r-phangorn")
11093 (uri (cran-uri "phangorn" version))
11096 "0ihkaykqjmf80d8wrk3saphxvnv58zma6pd13633bd3cwanc33f5"))))
11097 (build-system r-build-system)
11100 ("r-fastmatch" ,r-fastmatch)
11101 ("r-igraph" ,r-igraph)
11102 ("r-magrittr" ,r-magrittr)
11103 ("r-matrix" ,r-matrix)
11104 ("r-quadprog" ,r-quadprog)
11105 ("r-rcpp" ,r-rcpp)))
11106 (home-page "https://github.com/KlausVigo/phangorn")
11107 (synopsis "Phylogenetic analysis in R")
11109 "Phangorn is a package for phylogenetic analysis in R. It supports
11110 estimation of phylogenetic trees and networks using Maximum Likelihood,
11111 Maximum Parsimony, distance methods and Hadamard conjugation.")
11112 (license license:gpl2+)))
11114 (define-public r-dropbead
11115 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
11118 (name "r-dropbead")
11119 (version (string-append "0-" revision "." (string-take commit 7)))
11123 (uri (git-reference
11124 (url "https://github.com/rajewsky-lab/dropbead")
11126 (file-name (git-file-name name version))
11129 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
11130 (build-system r-build-system)
11132 `(("r-ggplot2" ,r-ggplot2)
11133 ("r-rcolorbrewer" ,r-rcolorbrewer)
11134 ("r-gridextra" ,r-gridextra)
11135 ("r-gplots" ,r-gplots)
11136 ("r-plyr" ,r-plyr)))
11137 (home-page "https://github.com/rajewsky-lab/dropbead")
11138 (synopsis "Basic exploration and analysis of Drop-seq data")
11139 (description "This package offers a quick and straight-forward way to
11140 explore and perform basic analysis of single cell sequencing data coming from
11141 droplet sequencing. It has been particularly tailored for Drop-seq.")
11142 (license license:gpl3))))
11144 (define htslib-for-sambamba
11145 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
11148 (name "htslib-for-sambamba")
11149 (version (string-append "1.3.1-1." (string-take commit 9)))
11153 (uri (git-reference
11154 (url "https://github.com/lomereiter/htslib")
11156 (file-name (string-append "htslib-" version "-checkout"))
11159 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
11161 `(("autoconf" ,autoconf)
11162 ("automake" ,automake)
11163 ,@(package-native-inputs htslib))))))
11165 (define-public sambamba
11172 (uri (git-reference
11173 (url "https://github.com/lomereiter/sambamba")
11174 (commit (string-append "v" version))))
11175 (file-name (string-append name "-" version "-checkout"))
11178 "111h05b60pj8dxbidiamy4imc92x2962b3lmb7wgysl6lx064qis"))))
11179 (build-system gnu-build-system)
11181 `(#:tests? #f ; there is no test target
11182 #:parallel-build? #f ; not supported
11184 (modify-phases %standard-phases
11185 (delete 'configure)
11186 (add-after 'unpack 'fix-ldc-version
11188 (substitute* "gen_ldc_version_info.py"
11189 (("/usr/bin/env.*") (which "python3")))
11190 (substitute* "Makefile"
11191 ;; We use ldc2 instead of ldmd2 to compile sambamba.
11192 (("\\$\\(shell which ldmd2\\)") (which "ldc2")))
11194 (add-after 'unpack 'place-biod-and-undead
11195 (lambda* (#:key inputs #:allow-other-keys)
11196 (copy-recursively (assoc-ref inputs "biod") "BioD")
11198 (add-after 'unpack 'unbundle-prerequisites
11200 (substitute* "Makefile"
11201 (("htslib/libhts.a lz4/lib/liblz4.a")
11203 ((" lz4-static htslib-static") ""))
11206 (lambda* (#:key outputs #:allow-other-keys)
11207 (let* ((out (assoc-ref outputs "out"))
11208 (bin (string-append out "/bin")))
11210 (copy-file (string-append "bin/sambamba-" ,version)
11211 (string-append bin "/sambamba"))
11218 ,(let ((commit "7969eb0a847b05874e83ffddead26e193ece8101"))
11221 (uri (git-reference
11222 (url "https://github.com/biod/BioD")
11224 (file-name (string-append "biod-"
11225 (string-take commit 9)
11229 "0mjxsmbmv0jxl3pq21p8j5r829d648if8q58ka50b2956lc6qkpm")))))))
11232 ("htslib" ,htslib-for-sambamba)))
11233 (home-page "https://lomereiter.github.io/sambamba/")
11234 (synopsis "Tools for working with SAM/BAM data")
11235 (description "Sambamba is a high performance modern robust and
11236 fast tool (and library), written in the D programming language, for
11237 working with SAM and BAM files. Current parallelised functionality is
11238 an important subset of samtools functionality, including view, index,
11239 sort, markdup, and depth.")
11240 (license license:gpl2+)))
11242 (define-public ritornello
11244 (name "ritornello")
11248 (uri (git-reference
11249 (url "https://github.com/KlugerLab/Ritornello")
11250 (commit (string-append "v" version))))
11251 (file-name (git-file-name name version))
11254 "1xahvq215qld7x1w8vpa5zbrsj6p9crb9shqa2x89sb0aaxa02jk"))))
11255 (build-system gnu-build-system)
11257 `(#:tests? #f ; there are no tests
11259 (modify-phases %standard-phases
11260 (add-after 'unpack 'patch-samtools-references
11261 (lambda* (#:key inputs #:allow-other-keys)
11262 (substitute* '("src/SamStream.h"
11264 (("<sam.h>") "<samtools/sam.h>"))
11266 (delete 'configure)
11268 (lambda* (#:key inputs outputs #:allow-other-keys)
11269 (let* ((out (assoc-ref outputs "out"))
11270 (bin (string-append out "/bin/")))
11272 (install-file "bin/Ritornello" bin)
11275 `(("samtools" ,samtools-0.1)
11279 (home-page "https://github.com/KlugerLab/Ritornello")
11280 (synopsis "Control-free peak caller for ChIP-seq data")
11281 (description "Ritornello is a ChIP-seq peak calling algorithm based on
11282 signal processing that can accurately call binding events without the need to
11283 do a pair total DNA input or IgG control sample. It has been tested for use
11284 with narrow binding events such as transcription factor ChIP-seq.")
11285 (license license:gpl3+)))
11287 (define-public trim-galore
11289 (name "trim-galore")
11294 (uri (git-reference
11295 (url "https://github.com/FelixKrueger/TrimGalore")
11297 (file-name (git-file-name name version))
11300 "1y31wbxwkm9xqzr5zv1pk5q418whnmlmgmfyxxpnl12h83m2i9iv"))))
11301 (build-system gnu-build-system)
11303 `(#:tests? #f ; no tests
11305 (modify-phases %standard-phases
11306 (replace 'configure
11308 ;; Trim Galore tries to figure out what version of Python
11309 ;; cutadapt is using by looking at the shebang. Of course that
11310 ;; doesn't work, because cutadapt is wrapped in a shell script.
11311 (substitute* "trim_galore"
11312 (("my \\$python_return.*")
11313 "my $python_return = \"Python 3.999\";\n"))
11316 (add-after 'unpack 'hardcode-tool-references
11317 (lambda* (#:key inputs #:allow-other-keys)
11318 (substitute* "trim_galore"
11319 (("\\$path_to_cutadapt = 'cutadapt'")
11320 (string-append "$path_to_cutadapt = '"
11321 (assoc-ref inputs "cutadapt")
11323 (("\\$compression_path = \"gzip\"")
11324 (string-append "$compression_path = \""
11325 (assoc-ref inputs "gzip")
11328 (string-append "\""
11329 (assoc-ref inputs "gzip")
11332 (string-append "\""
11333 (assoc-ref inputs "pigz")
11337 (lambda* (#:key outputs #:allow-other-keys)
11338 (let ((bin (string-append (assoc-ref outputs "out")
11341 (install-file "trim_galore" bin)
11347 ("cutadapt" ,cutadapt)))
11349 `(("unzip" ,unzip)))
11350 (home-page "https://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
11351 (synopsis "Wrapper around Cutadapt and FastQC")
11352 (description "Trim Galore! is a wrapper script to automate quality and
11353 adapter trimming as well as quality control, with some added functionality to
11354 remove biased methylation positions for RRBS sequence files.")
11355 (license license:gpl3+)))
11357 (define-public gess
11363 (uri (string-append "http://compbio.uthscsa.edu/"
11365 "gess-" version ".src.tar.gz"))
11368 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
11369 (build-system gnu-build-system)
11371 `(#:tests? #f ; no tests
11373 (modify-phases %standard-phases
11374 (delete 'configure)
11377 (lambda* (#:key inputs outputs #:allow-other-keys)
11378 (let* ((python (assoc-ref inputs "python"))
11379 (out (assoc-ref outputs "out"))
11380 (bin (string-append out "/bin/"))
11381 (target (string-append
11383 ,(version-major+minor
11384 (package-version python))
11385 "/site-packages/gess/")))
11387 (copy-recursively "." target)
11388 ;; Make GESS.py executable
11389 (chmod (string-append target "GESS.py") #o555)
11390 ;; Add Python shebang to the top and make Matplotlib
11392 (substitute* (string-append target "GESS.py")
11393 (("\"\"\"Description:" line)
11394 (string-append "#!" (which "python") "
11396 matplotlib.use('Agg')
11398 ;; Make sure GESS has all modules in its path
11399 (wrap-script (string-append target "GESS.py")
11400 `("PYTHONPATH" ":" = (,target ,(getenv "PYTHONPATH"))))
11402 (symlink (string-append target "GESS.py")
11403 (string-append bin "GESS.py"))
11406 `(("python" ,python-2)
11407 ("python2-pysam" ,python2-pysam)
11408 ("python2-scipy" ,python2-scipy)
11409 ("python2-numpy" ,python2-numpy)
11410 ("python2-networkx" ,python2-networkx)
11411 ("python2-biopython" ,python2-biopython)
11412 ("guile" ,guile-3.0))) ; for the script wrapper
11413 (home-page "https://compbio.uthscsa.edu/GESS_Web/")
11414 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11416 "GESS is an implementation of a novel computational method to detect de
11417 novo exon-skipping events directly from raw RNA-seq data without the prior
11418 knowledge of gene annotation information. GESS stands for the graph-based
11419 exon-skipping scanner detection scheme.")
11420 (license license:bsd-3)))
11422 (define-public phylip
11429 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11430 "download/phylip-" version ".tar.gz"))
11433 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11434 (build-system gnu-build-system)
11436 `(#:tests? #f ; no check target
11437 #:make-flags (list "-f" "Makefile.unx" "install")
11438 #:parallel-build? #f ; not supported
11440 (modify-phases %standard-phases
11441 (add-after 'unpack 'enter-dir
11442 (lambda _ (chdir "src") #t))
11443 (delete 'configure)
11445 (lambda* (#:key inputs outputs #:allow-other-keys)
11446 (let ((target (string-append (assoc-ref outputs "out")
11449 (for-each (lambda (file)
11450 (install-file file target))
11451 (find-files "../exe" ".*")))
11453 (home-page "http://evolution.genetics.washington.edu/phylip/")
11454 (synopsis "Tools for inferring phylogenies")
11455 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11456 programs for inferring phylogenies (evolutionary trees).")
11457 (license license:bsd-2)))
11466 (uri (string-append "https://integrativemodeling.org/"
11467 version "/download/imp-" version ".tar.gz"))
11470 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
11471 (build-system cmake-build-system)
11473 `(;; FIXME: Some tests fail because they produce warnings, others fail
11474 ;; because the PYTHONPATH does not include the modeller's directory.
11482 ("python" ,python-2)))
11484 `(("python2-numpy" ,python2-numpy)
11485 ("python2-scipy" ,python2-scipy)
11486 ("python2-pandas" ,python2-pandas)
11487 ("python2-scikit-learn" ,python2-scikit-learn)
11488 ("python2-networkx" ,python2-networkx)))
11489 (home-page "https://integrativemodeling.org")
11490 (synopsis "Integrative modeling platform")
11491 (description "IMP's broad goal is to contribute to a comprehensive
11492 structural characterization of biomolecules ranging in size and complexity
11493 from small peptides to large macromolecular assemblies, by integrating data
11494 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11495 Python toolbox for solving complex modeling problems, and a number of
11496 applications for tackling some common problems in a user-friendly way.")
11497 ;; IMP is largely available under the GNU Lesser GPL; see the file
11498 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11499 ;; available under the GNU GPL (see the file COPYING.GPL).
11500 (license (list license:lgpl2.1+
11503 (define-public tadbit
11509 (uri (git-reference
11510 (url "https://github.com/3DGenomes/TADbit")
11511 (commit (string-append "v" version))))
11512 (file-name (git-file-name name version))
11515 "07g3aj648prmsvxp9caz5yl41k0y0647vxh0f5p3w8376mfiljd0"))))
11516 (build-system python-build-system)
11518 `(;; Tests are included and must be run after installation, but
11519 ;; they are incomplete and thus cannot be run.
11523 (modify-phases %standard-phases
11524 (add-after 'unpack 'fix-problems-with-setup.py
11525 (lambda* (#:key outputs #:allow-other-keys)
11526 ;; setup.py opens these files for writing
11527 (chmod "_pytadbit/_version.py" #o664)
11528 (chmod "README.rst" #o664)
11530 ;; Don't attempt to install the bash completions to
11531 ;; the home directory.
11532 (rename-file "extras/.bash_completion"
11534 (substitute* "setup.py"
11535 (("\\(path.expanduser\\('~'\\)")
11536 (string-append "(\""
11537 (assoc-ref outputs "out")
11538 "/etc/bash_completion.d\""))
11539 (("extras/\\.bash_completion")
11543 ;; TODO: add Chimera for visualization
11546 ("python2-scipy" ,python2-scipy)
11547 ("python2-numpy" ,python2-numpy)
11548 ("python2-matplotlib" ,python2-matplotlib)
11549 ("python2-pysam" ,python2-pysam)))
11550 (home-page "https://3dgenomes.github.io/TADbit/")
11551 (synopsis "Analyze, model, and explore 3C-based data")
11553 "TADbit is a complete Python library to deal with all steps to analyze,
11554 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11555 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11556 correct interaction matrices, identify and compare the so-called
11557 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11558 interaction matrices, and finally, extract structural properties from the
11559 models. TADbit is complemented by TADkit for visualizing 3D models.")
11560 (license license:gpl3+)))
11562 (define-public kentutils
11565 ;; 302.1.0 is out, but the only difference is the inclusion of
11566 ;; pre-built binaries.
11567 (version "302.0.0")
11571 (uri (git-reference
11572 (url "https://github.com/ENCODE-DCC/kentUtils")
11573 (commit (string-append "v" version))))
11574 (file-name (git-file-name name version))
11577 "0n1wbyjpzii2b9qhyp9r1q76j623cggpg3y8fmw78ld3z4y7ivha"))
11578 (modules '((guix build utils)
11583 ;; Only the contents of the specified directories are free
11584 ;; for all uses, so we remove the rest. "hg/autoSql" and
11585 ;; "hg/autoXml" are nominally free, but they depend on a
11586 ;; library that is built from the sources in "hg/lib",
11587 ;; which is nonfree.
11588 (let ((free (list "." ".."
11589 "utils" "lib" "inc" "tagStorm"
11590 "parasol" "htslib"))
11591 (directory? (lambda (file)
11592 (eq? 'directory (stat:type (stat file))))))
11593 (for-each (lambda (file)
11594 (and (directory? file)
11595 (delete-file-recursively file)))
11596 (map (cut string-append "src/" <>)
11599 (not (member file free)))))))
11600 ;; Only make the utils target, not the userApps target,
11601 ;; because that requires libraries we won't build.
11602 (substitute* "Makefile"
11603 ((" userApps") " utils"))
11604 ;; Only build libraries that are free.
11605 (substitute* "src/makefile"
11606 (("DIRS =.*") "DIRS =\n")
11607 (("cd jkOwnLib.*") "")
11610 (substitute* "src/utils/makefile"
11611 ;; These tools depend on "jkhgap.a", which is part of the
11612 ;; nonfree "src/hg/lib" directory.
11613 (("raSqlQuery") "")
11614 (("pslLiftSubrangeBlat") "")
11616 ;; Do not build UCSC tools, which may require nonfree
11618 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11620 (build-system gnu-build-system)
11622 `( ;; There is no global test target and the test target for
11623 ;; individual tools depends on input files that are not
11627 (modify-phases %standard-phases
11628 (add-after 'unpack 'fix-permissions
11629 (lambda _ (make-file-writable "src/inc/localEnvironment.mk") #t))
11630 (add-after 'unpack 'fix-paths
11632 (substitute* "Makefile"
11633 (("/bin/echo") (which "echo")))
11635 (add-after 'unpack 'prepare-samtabix
11636 (lambda* (#:key inputs #:allow-other-keys)
11637 (copy-recursively (assoc-ref inputs "samtabix")
11640 (delete 'configure)
11642 (lambda* (#:key outputs #:allow-other-keys)
11643 (let ((bin (string-append (assoc-ref outputs "out")
11645 (copy-recursively "bin" bin))
11651 (uri (git-reference
11652 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11653 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11656 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11662 ("mariadb" ,mariadb "lib")
11663 ("mariadb-dev" ,mariadb "dev")
11664 ("openssl" ,openssl-1.0)))
11665 (home-page "https://genome.cse.ucsc.edu/index.html")
11666 (synopsis "Assorted bioinformatics utilities")
11667 (description "This package provides the kentUtils, a selection of
11668 bioinformatics utilities used in combination with the UCSC genome
11670 ;; Only a subset of the sources are released under a non-copyleft
11671 ;; free software license. All other sources are removed in a
11672 ;; snippet. See this bug report for an explanation of how the
11673 ;; license statements apply:
11674 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11675 (license (license:non-copyleft
11676 "http://genome.ucsc.edu/license/"
11677 "The contents of this package are free for all uses."))))
11679 (define-public f-seq
11680 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11684 (version (string-append "1.1-" revision "." (string-take commit 7)))
11687 (uri (git-reference
11688 (url "https://github.com/aboyle/F-seq")
11690 (file-name (string-append name "-" version))
11693 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11694 (modules '((guix build utils)))
11695 ;; Remove bundled Java library archives.
11698 (for-each delete-file (find-files "lib" ".*"))
11700 (build-system ant-build-system)
11702 `(#:tests? #f ; no tests included
11704 (modify-phases %standard-phases
11706 (lambda* (#:key inputs outputs #:allow-other-keys)
11707 (let* ((target (assoc-ref outputs "out"))
11708 (bin (string-append target "/bin"))
11709 (doc (string-append target "/share/doc/f-seq"))
11710 (lib (string-append target "/lib")))
11713 (substitute* "bin/linux/fseq"
11714 (("java") (which "java"))
11715 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11716 (string-append (assoc-ref inputs "java-commons-cli")
11717 "/share/java/commons-cli.jar"))
11719 (string-append "REALDIR=" bin "\n")))
11720 (install-file "README.txt" doc)
11721 (install-file "bin/linux/fseq" bin)
11722 (install-file "build~/fseq.jar" lib)
11723 (copy-recursively "lib" lib)
11727 ("java-commons-cli" ,java-commons-cli)))
11728 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11729 (synopsis "Feature density estimator for high-throughput sequence tags")
11731 "F-Seq is a software package that generates a continuous tag sequence
11732 density estimation allowing identification of biologically meaningful sites
11733 such as transcription factor binding sites (ChIP-seq) or regions of open
11734 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11736 (license license:gpl3+))))
11738 (define-public bismark
11745 (uri (git-reference
11746 (url "https://github.com/FelixKrueger/Bismark")
11748 (file-name (string-append name "-" version "-checkout"))
11751 "0xchm3rgilj6vfjnyzfzzymfd7djr64sbrmrvs3njbwi66jqbzw9"))))
11752 (build-system perl-build-system)
11754 `(#:tests? #f ; there are no tests
11755 #:modules ((guix build utils)
11758 (guix build perl-build-system))
11760 (modify-phases %standard-phases
11761 ;; The bundled plotly.js is minified.
11762 (add-after 'unpack 'replace-plotly.js
11763 (lambda* (#:key inputs #:allow-other-keys)
11764 (let* ((file (assoc-ref inputs "plotly.js"))
11765 (installed "plotly/plotly.js"))
11766 (let ((minified (open-pipe* OPEN_READ "uglify-js" file)))
11767 (call-with-output-file installed
11768 (cut dump-port minified <>))))
11770 (delete 'configure)
11773 (lambda* (#:key inputs outputs #:allow-other-keys)
11774 (let* ((out (assoc-ref outputs "out"))
11775 (bin (string-append out "/bin"))
11776 (share (string-append out "/share/bismark"))
11777 (docdir (string-append out "/share/doc/bismark"))
11778 (docs '("Docs/Bismark_User_Guide.html"))
11779 (scripts '("bismark"
11780 "bismark_genome_preparation"
11781 "bismark_methylation_extractor"
11784 "coverage2cytosine"
11785 "deduplicate_bismark"
11786 "filter_non_conversion"
11789 "NOMe_filtering")))
11790 (substitute* "bismark2report"
11791 (("\\$RealBin/plotly")
11792 (string-append share "/plotly")))
11796 (for-each (lambda (file) (install-file file bin))
11798 (for-each (lambda (file) (install-file file docdir))
11800 (copy-recursively "Docs/Images" (string-append docdir "/Images"))
11801 (copy-recursively "plotly"
11802 (string-append share "/plotly"))
11804 ;; Fix references to gunzip
11805 (substitute* (map (lambda (file)
11806 (string-append bin "/" file))
11809 (string-append "\"" (assoc-ref inputs "gzip")
11810 "/bin/gunzip -c")))
11814 ("perl-carp" ,perl-carp)
11815 ("perl-getopt-long" ,perl-getopt-long)))
11820 (uri (string-append "https://raw.githubusercontent.com/plotly/plotly.js/"
11821 "v1.39.4/dist/plotly.js"))
11823 (base32 "138mwsr4nf5qif4mrxx286mpnagxd1xwl6k8aidrjgknaqg88zyr"))))
11824 ("uglify-js" ,uglify-js)))
11825 (home-page "https://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11826 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11827 (description "Bismark is a program to map bisulfite treated sequencing
11828 reads to a genome of interest and perform methylation calls in a single step.
11829 The output can be easily imported into a genome viewer, such as SeqMonk, and
11830 enables a researcher to analyse the methylation levels of their samples
11831 straight away. Its main features are:
11834 @item Bisulfite mapping and methylation calling in one single step
11835 @item Supports single-end and paired-end read alignments
11836 @item Supports ungapped and gapped alignments
11837 @item Alignment seed length, number of mismatches etc are adjustable
11838 @item Output discriminates between cytosine methylation in CpG, CHG
11841 (license license:gpl3+)))
11843 (define-public paml
11849 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11850 "paml" version ".tgz"))
11853 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11854 (modules '((guix build utils)))
11855 ;; Remove Windows binaries
11858 (for-each delete-file (find-files "." "\\.exe$"))
11859 ;; Some files in the original tarball have restrictive
11860 ;; permissions, which makes repackaging fail
11861 (for-each (lambda (file) (chmod file #o644)) (find-files "."))
11863 (build-system gnu-build-system)
11865 `(#:tests? #f ; there are no tests
11866 #:make-flags '("CC=gcc")
11868 (modify-phases %standard-phases
11869 (replace 'configure
11871 (substitute* "src/BFdriver.c"
11872 (("/bin/bash") (which "bash")))
11876 (lambda* (#:key outputs #:allow-other-keys)
11877 (let ((tools '("baseml" "basemlg" "codeml"
11878 "pamp" "evolver" "yn00" "chi2"))
11879 (bin (string-append (assoc-ref outputs "out") "/bin"))
11880 (docdir (string-append (assoc-ref outputs "out")
11881 "/share/doc/paml")))
11883 (for-each (lambda (file) (install-file file bin)) tools)
11884 (copy-recursively "../doc" docdir)
11886 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11887 (synopsis "Phylogentic analysis by maximum likelihood")
11888 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11889 contains a few programs for model fitting and phylogenetic tree reconstruction
11890 using nucleotide or amino-acid sequence data.")
11892 (license license:gpl3)))
11894 (define-public kallisto
11900 (uri (git-reference
11901 (url "https://github.com/pachterlab/kallisto")
11902 (commit (string-append "v" version))))
11903 (file-name (git-file-name name version))
11906 "0nj382jiywqnpgvyhichajpkkh5r0bapn43f4dx40zdaq5v4m40m"))))
11907 (build-system cmake-build-system)
11909 `(#:tests? #f ; no "check" target
11911 (modify-phases %standard-phases
11912 (add-after 'unpack 'do-not-use-bundled-htslib
11914 (substitute* "CMakeLists.txt"
11915 (("^ExternalProject_Add" m)
11916 (string-append "if (NEVER)\n" m))
11918 (string-append ")\nendif(NEVER)"))
11919 (("include_directories\\(\\$\\{htslib_PREFIX.*" m)
11920 (string-append "# " m)))
11921 (substitute* "src/CMakeLists.txt"
11922 (("target_link_libraries\\(kallisto kallisto_core pthread \
11923 \\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/../ext/htslib/libhts.a\\)")
11924 "target_link_libraries(kallisto kallisto_core pthread hts)")
11925 (("include_directories\\(\\.\\./ext/htslib\\)") ""))
11931 (home-page "https://pachterlab.github.io/kallisto/")
11932 (synopsis "Near-optimal RNA-Seq quantification")
11934 "Kallisto is a program for quantifying abundances of transcripts from
11935 RNA-Seq data, or more generally of target sequences using high-throughput
11936 sequencing reads. It is based on the novel idea of pseudoalignment for
11937 rapidly determining the compatibility of reads with targets, without the need
11938 for alignment. Pseudoalignment of reads preserves the key information needed
11939 for quantification, and kallisto is therefore not only fast, but also as
11940 accurate as existing quantification tools.")
11941 (license license:bsd-2)))
11943 (define-public libgff
11949 (uri (git-reference
11950 (url "https://github.com/Kingsford-Group/libgff")
11951 (commit (string-append "v" version))))
11952 (file-name (git-file-name name version))
11955 "0n6vfjnq7a2mianipscbshrvbncss8z4zkgkbjw754p9043nfkps"))))
11956 (build-system cmake-build-system)
11957 (arguments `(#:tests? #f)) ; no tests included
11958 (home-page "https://github.com/Kingsford-Group/libgff")
11959 (synopsis "Parser library for reading/writing GFF files")
11960 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11961 code that is used in the Cufflinks codebase. The goal of this library is to
11962 provide this functionality without the necessity of drawing in a heavy-weight
11963 dependency like SeqAn.")
11964 (license (license:x11-style "https://www.boost.org/LICENSE_1_0.txt"))))
11966 (define-public sailfish
11972 (uri (git-reference
11973 (url "https://github.com/kingsfordgroup/sailfish")
11974 (commit (string-append "v" version))))
11975 (file-name (git-file-name name version))
11978 "1amcc5hqvsl42hg4x19bi9vy47cl874s0lw1fmi0hwsdk9i8c03v"))
11979 (modules '((guix build utils)))
11982 ;; Delete bundled headers for eigen3.
11983 (delete-file-recursively "include/eigen3/")
11985 (build-system cmake-build-system)
11987 `(#:configure-flags
11988 (list (string-append "-DBOOST_INCLUDEDIR="
11989 (assoc-ref %build-inputs "boost")
11991 (string-append "-DBOOST_LIBRARYDIR="
11992 (assoc-ref %build-inputs "boost")
11994 (string-append "-DBoost_LIBRARIES="
11995 "-lboost_iostreams "
11996 "-lboost_filesystem "
12001 "-lboost_program_options")
12002 "-DBoost_FOUND=TRUE"
12003 ;; Don't download RapMap---we already have it!
12004 "-DFETCHED_RAPMAP=1")
12005 ;; Tests must be run after installation and the location of the test
12006 ;; data file must be overridden. But the tests fail. It looks like
12007 ;; they are not really meant to be run.
12010 (modify-phases %standard-phases
12011 ;; Boost cannot be found, even though it's right there.
12012 (add-after 'unpack 'do-not-look-for-boost
12013 (lambda* (#:key inputs #:allow-other-keys)
12014 (substitute* "CMakeLists.txt"
12015 (("find_package\\(Boost 1\\.53\\.0") "#"))
12017 (add-after 'unpack 'do-not-assign-to-macro
12019 (substitute* "include/spdlog/details/format.cc"
12020 (("const unsigned CHAR_WIDTH = 1;") ""))
12022 (add-after 'unpack 'prepare-rapmap
12023 (lambda* (#:key inputs #:allow-other-keys)
12024 (let ((src "external/install/src/rapmap/")
12025 (include "external/install/include/rapmap/")
12026 (rapmap (assoc-ref inputs "rapmap")))
12027 (mkdir-p "/tmp/rapmap")
12029 (assoc-ref inputs "rapmap")
12031 "--strip-components=1")
12034 (for-each (lambda (file)
12035 (install-file file src))
12036 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
12037 (copy-recursively "/tmp/rapmap/include" include))
12039 (add-after 'unpack 'use-system-libraries
12040 (lambda* (#:key inputs #:allow-other-keys)
12041 (substitute* '("src/SailfishIndexer.cpp"
12042 "src/SailfishUtils.cpp"
12043 "src/SailfishQuantify.cpp"
12044 "src/FASTAParser.cpp"
12046 "include/SailfishUtils.hpp"
12047 "include/SailfishIndex.hpp"
12048 "include/CollapsedEMOptimizer.hpp"
12049 "src/CollapsedEMOptimizer.cpp")
12050 (("#include \"jellyfish/config.h\"") ""))
12051 (substitute* "src/CMakeLists.txt"
12052 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
12053 (string-append (assoc-ref inputs "jellyfish")
12054 "/include/jellyfish-" ,(package-version jellyfish)))
12055 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
12056 (string-append (assoc-ref inputs "jellyfish")
12057 "/lib/libjellyfish-2.0.a"))
12058 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12059 (string-append (assoc-ref inputs "libdivsufsort")
12060 "/lib/libdivsufsort.so"))
12061 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12062 (string-append (assoc-ref inputs "libdivsufsort")
12063 "/lib/libdivsufsort64.so")))
12064 (substitute* "CMakeLists.txt"
12065 ;; Don't prefer static libs
12066 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12067 (("find_package\\(Jellyfish.*") "")
12068 (("ExternalProject_Add\\(libjellyfish") "message(")
12069 (("ExternalProject_Add\\(libgff") "message(")
12070 (("ExternalProject_Add\\(libsparsehash") "message(")
12071 (("ExternalProject_Add\\(libdivsufsort") "message("))
12073 ;; Ensure that Eigen headers can be found
12074 (setenv "CPLUS_INCLUDE_PATH"
12075 (string-append (assoc-ref inputs "eigen")
12077 (or (getenv "CPLUS_INCLUDE_PATH") "")))
12082 ("jemalloc" ,jemalloc)
12083 ("jellyfish" ,jellyfish)
12084 ("sparsehash" ,sparsehash)
12087 (uri (git-reference
12088 (url "https://github.com/COMBINE-lab/RapMap")
12089 (commit (string-append "sf-v" version))))
12090 (file-name (string-append "rapmap-sf-v" version "-checkout"))
12093 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
12094 (modules '((guix build utils)))
12095 ;; These files are expected to be excluded.
12097 '(begin (delete-file-recursively "include/spdlog")
12098 (for-each delete-file '("include/xxhash.h"
12101 ("libdivsufsort" ,libdivsufsort)
12106 `(("pkg-config" ,pkg-config)))
12107 (home-page "https://www.cs.cmu.edu/~ckingsf/software/sailfish/")
12108 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
12109 (description "Sailfish is a tool for genomic transcript quantification
12110 from RNA-seq data. It requires a set of target transcripts (either from a
12111 reference or de-novo assembly) to quantify. All you need to run sailfish is a
12112 fasta file containing your reference transcripts and a (set of) fasta/fastq
12113 file(s) containing your reads.")
12114 (license license:gpl3+)))
12116 (define libstadenio-for-salmon
12118 (name "libstadenio")
12122 (uri (git-reference
12123 (url "https://github.com/COMBINE-lab/staden-io_lib")
12124 (commit (string-append "v" version))))
12125 (file-name (string-append name "-" version "-checkout"))
12128 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
12129 (build-system gnu-build-system)
12130 (arguments '(#:parallel-tests? #f)) ; not supported
12134 `(("perl" ,perl))) ; for tests
12135 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
12136 (synopsis "General purpose trace and experiment file library")
12137 (description "This package provides a library of file reading and writing
12138 code to provide a general purpose Trace file (and Experiment File) reading
12141 The following file formats are supported:
12144 @item SCF trace files
12145 @item ABI trace files
12146 @item ALF trace files
12147 @item ZTR trace files
12148 @item SFF trace archives
12149 @item SRF trace archives
12150 @item Experiment files
12151 @item Plain text files
12152 @item SAM/BAM sequence files
12153 @item CRAM sequence files
12155 (license license:bsd-3)))
12157 (define-public salmon
12163 (uri (git-reference
12164 (url "https://github.com/COMBINE-lab/salmon")
12165 (commit (string-append "v" version))))
12166 (file-name (git-file-name name version))
12169 "1i2z4aivicmiixdz9bxalp7vmfzi3k92fxa63iqa8kgvfw5a4aq5"))
12170 (modules '((guix build utils)))
12173 ;; Delete bundled headers for eigen3.
12174 (delete-file-recursively "include/eigen3/")
12176 (build-system cmake-build-system)
12178 `(#:configure-flags
12179 (list (string-append "-DBOOST_INCLUDEDIR="
12180 (assoc-ref %build-inputs "boost")
12182 (string-append "-DBOOST_LIBRARYDIR="
12183 (assoc-ref %build-inputs "boost")
12185 (string-append "-DBoost_LIBRARIES="
12186 "-lboost_iostreams "
12187 "-lboost_filesystem "
12192 "-lboost_program_options")
12193 "-DBoost_FOUND=TRUE"
12194 "-DTBB_LIBRARIES=tbb tbbmalloc"
12195 ;; Don't download RapMap---we already have it!
12196 "-DFETCHED_RAPMAP=1")
12198 (modify-phases %standard-phases
12199 ;; Boost cannot be found, even though it's right there.
12200 (add-after 'unpack 'do-not-look-for-boost
12201 (lambda* (#:key inputs #:allow-other-keys)
12202 (substitute* "CMakeLists.txt"
12203 (("find_package\\(Boost 1\\.59\\.0") "#"))
12205 (add-after 'unpack 'do-not-phone-home
12207 (substitute* "src/Salmon.cpp"
12208 (("getVersionMessage\\(\\)") "\"\""))
12210 (add-after 'unpack 'prepare-rapmap
12211 (lambda* (#:key inputs #:allow-other-keys)
12212 (let ((src "external/install/src/rapmap/")
12213 (include "external/install/include/rapmap/")
12214 (rapmap (assoc-ref inputs "rapmap")))
12217 (copy-recursively (string-append rapmap "/src") src)
12218 (copy-recursively (string-append rapmap "/include") include)
12219 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
12220 "external/install/include/rapmap/FastxParser.hpp"
12221 "external/install/include/rapmap/concurrentqueue.h"
12222 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
12223 "external/install/src/rapmap/FastxParser.cpp"
12224 "external/install/src/rapmap/xxhash.c"))
12225 (delete-file-recursively "external/install/include/rapmap/spdlog"))
12227 (add-after 'unpack 'use-system-libraries
12228 (lambda* (#:key inputs #:allow-other-keys)
12229 (substitute* "CMakeLists.txt"
12230 ;; Don't prefer static libs
12231 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12232 (("set\\(TBB_LIBRARIES") "message(")
12233 ;; Don't download anything
12234 (("DOWNLOAD_COMMAND") "DOWNLOAD_COMMAND echo")
12235 (("externalproject_add\\(libcereal") "message(")
12236 (("externalproject_add\\(libgff") "message(")
12237 (("externalproject_add\\(libtbb") "message(")
12238 (("externalproject_add\\(libdivsufsort") "message(")
12239 (("externalproject_add\\(libstadenio") "message(")
12240 (("externalproject_add_step\\(") "message("))
12241 (substitute* "src/CMakeLists.txt"
12242 (("add_dependencies") "#")
12243 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
12244 (string-append (assoc-ref inputs "libstadenio-for-salmon")
12245 "/lib/libstaden-read.so"))
12246 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12247 (string-append (assoc-ref inputs "libdivsufsort")
12248 "/lib/libdivsufsort.so"))
12249 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12250 (string-append (assoc-ref inputs "libdivsufsort")
12251 "/lib/libdivsufsort64.so"))
12252 (("lib/libdivsufsort.a") "/lib/libdivsufsort.so"))
12254 ;; Ensure that all headers can be found
12255 (setenv "CPLUS_INCLUDE_PATH"
12256 (string-append (or (getenv "CPLUS_INCLUDE_PATH") "")
12258 (assoc-ref inputs "eigen")
12259 "/include/eigen3"))
12261 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
12262 ;; run. It only exists after the install phase.
12263 (add-after 'unpack 'fix-tests
12265 (substitute* "src/CMakeLists.txt"
12266 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
12267 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
12276 (uri (git-reference
12277 (url "https://github.com/COMBINE-lab/RapMap")
12278 (commit (string-append "salmon-v" version))))
12279 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
12282 "1biplxf0csc7a8h1wf219b0vmjkvw6wk2zylhdklb577kgmihdms"))))
12283 ("jemalloc" ,jemalloc)
12286 ("libdivsufsort" ,libdivsufsort)
12287 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
12291 `(("pkg-config" ,pkg-config)))
12292 (home-page "https://github.com/COMBINE-lab/salmon")
12293 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
12294 (description "Salmon is a program to produce highly-accurate,
12295 transcript-level quantification estimates from RNA-seq data. Salmon achieves
12296 its accuracy and speed via a number of different innovations, including the
12297 use of lightweight alignments (accurate but fast-to-compute proxies for
12298 traditional read alignments) and massively-parallel stochastic collapsed
12299 variational inference.")
12300 (license license:gpl3+)))
12302 (define-public python-loompy
12304 (name "python-loompy")
12306 ;; The tarball on Pypi does not include the tests.
12309 (uri (git-reference
12310 (url "https://github.com/linnarsson-lab/loompy")
12312 (file-name (git-file-name name version))
12315 "12a5kjgiikapv93wahfw0frszx1lblnppyz3vs5gy8fgmgngra07"))))
12316 (build-system python-build-system)
12319 (modify-phases %standard-phases
12322 (setenv "PYTHONPATH"
12323 (string-append (getcwd) ":"
12324 (getenv "PYTHONPATH")))
12325 (invoke "pytest" "tests")
12328 `(("python-h5py" ,python-h5py)
12329 ("python-numpy" ,python-numpy)
12330 ("python-pandas" ,python-pandas)
12331 ("python-scipy" ,python-scipy)))
12333 `(("python-pytest" ,python-pytest)))
12334 (home-page "https://github.com/linnarsson-lab/loompy")
12335 (synopsis "Work with .loom files for single-cell RNA-seq data")
12336 (description "The loom file format is an efficient format for very large
12337 omics datasets, consisting of a main matrix, optional additional layers, a
12338 variable number of row and column annotations. Loom also supports sparse
12339 graphs. This library makes it easy to work with @file{.loom} files for
12340 single-cell RNA-seq data.")
12341 (license license:bsd-3)))
12343 ;; We cannot use the latest commit because it requires Java 9.
12344 (define-public java-forester
12345 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
12348 (name "java-forester")
12349 (version (string-append "0-" revision "." (string-take commit 7)))
12352 (uri (git-reference
12353 (url "https://github.com/cmzmasek/forester")
12355 (file-name (string-append name "-" version "-checkout"))
12358 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12359 (modules '((guix build utils)))
12362 ;; Delete bundled jars and pre-built classes
12363 (delete-file-recursively "forester/java/resources")
12364 (delete-file-recursively "forester/java/classes")
12365 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12366 ;; Delete bundled applications
12367 (delete-file-recursively "forester_applications")
12369 (build-system ant-build-system)
12371 `(#:tests? #f ; there are none
12373 #:modules ((guix build ant-build-system)
12375 (guix build java-utils)
12379 (modify-phases %standard-phases
12380 (add-after 'unpack 'chdir
12381 (lambda _ (chdir "forester/java") #t))
12382 (add-after 'chdir 'fix-dependencies
12384 (chmod "build.xml" #o664)
12385 (call-with-output-file "build.xml.new"
12389 (with-input-from-file "build.xml"
12390 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12391 `(;; Remove all unjar tags to avoid repacking classes.
12392 (unjar . ,(lambda _ '()))
12393 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12394 (*text* . ,(lambda (_ txt) txt))))
12396 (rename-file "build.xml.new" "build.xml")
12398 ;; FIXME: itext is difficult to package as it depends on a few
12399 ;; unpackaged libraries.
12400 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12402 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12403 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12404 (("pdf_written_to = PdfExporter.*")
12405 "throw new IOException(\"PDF export is not available.\");"))
12407 ;; There is no install target
12408 (replace 'install (install-jars ".")))))
12410 `(("java-commons-codec" ,java-commons-codec)
12411 ("java-openchart2" ,java-openchart2)))
12412 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12413 (synopsis "Phylogenomics libraries for Java")
12414 (description "Forester is a collection of Java libraries for
12415 phylogenomics and evolutionary biology research. It includes support for
12416 reading, writing, and exporting phylogenetic trees.")
12417 (license license:lgpl2.1+))))
12419 (define-public java-forester-1.005
12421 (name "java-forester")
12425 (uri (string-append "https://repo1.maven.org/maven2/"
12426 "org/biojava/thirdparty/forester/"
12427 version "/forester-" version "-sources.jar"))
12428 (file-name (string-append name "-" version ".jar"))
12431 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12432 (build-system ant-build-system)
12434 `(#:tests? #f ; there are none
12436 #:modules ((guix build ant-build-system)
12438 (guix build java-utils)
12442 (modify-phases %standard-phases
12443 (add-after 'unpack 'fix-dependencies
12444 (lambda* (#:key inputs #:allow-other-keys)
12445 (call-with-output-file "build.xml"
12449 (with-input-from-file "src/build.xml"
12450 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12451 `(;; Remove all unjar tags to avoid repacking classes.
12452 (unjar . ,(lambda _ '()))
12453 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12454 (*text* . ,(lambda (_ txt) txt))))
12456 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12457 "synth_look_and_feel_1.xml")
12458 (copy-file (assoc-ref inputs "phyloxml.xsd")
12460 (substitute* "build.xml"
12461 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12462 "synth_look_and_feel_1.xml")
12463 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12466 ;; FIXME: itext is difficult to package as it depends on a few
12467 ;; unpackaged libraries.
12468 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12470 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12471 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12472 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12473 (("pdf_written_to = PdfExporter.*")
12474 "throw new IOException(\"PDF export is not available.\"); /*")
12475 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12476 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12478 (add-after 'unpack 'delete-pre-built-classes
12479 (lambda _ (delete-file-recursively "src/classes") #t))
12480 ;; There is no install target
12481 (replace 'install (install-jars ".")))))
12483 `(("java-commons-codec" ,java-commons-codec)
12484 ("java-openchart2" ,java-openchart2)))
12485 ;; The source archive does not contain the resources.
12490 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12491 "b61cc2dcede0bede317db362472333115756b8c6/"
12492 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12493 (file-name (string-append name "-phyloxml-" version ".xsd"))
12496 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12497 ("synth_look_and_feel_1.xml"
12500 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12501 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12502 "forester/java/classes/resources/"
12503 "synth_look_and_feel_1.xml"))
12504 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12507 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12508 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12509 (synopsis "Phylogenomics libraries for Java")
12510 (description "Forester is a collection of Java libraries for
12511 phylogenomics and evolutionary biology research. It includes support for
12512 reading, writing, and exporting phylogenetic trees.")
12513 (license license:lgpl2.1+)))
12515 (define-public java-biojava-core
12517 (name "java-biojava-core")
12521 (uri (git-reference
12522 (url "https://github.com/biojava/biojava")
12523 (commit (string-append "biojava-" version))))
12524 (file-name (string-append name "-" version "-checkout"))
12527 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12528 (build-system ant-build-system)
12531 #:jar-name "biojava-core.jar"
12532 #:source-dir "biojava-core/src/main/java/"
12533 #:test-dir "biojava-core/src/test"
12534 ;; These tests seem to require internet access.
12535 #:test-exclude (list "**/SearchIOTest.java"
12536 "**/BlastXMLParserTest.java"
12537 "**/GenbankCookbookTest.java"
12538 "**/GenbankProxySequenceReaderTest.java")
12540 (modify-phases %standard-phases
12541 (add-before 'build 'copy-resources
12543 (copy-recursively "biojava-core/src/main/resources"
12546 (add-before 'check 'copy-test-resources
12548 (copy-recursively "biojava-core/src/test/resources"
12549 "build/test-classes")
12552 `(("java-log4j-api" ,java-log4j-api)
12553 ("java-log4j-core" ,java-log4j-core)
12554 ("java-slf4j-api" ,java-slf4j-api)
12555 ("java-slf4j-simple" ,java-slf4j-simple)))
12557 `(("java-junit" ,java-junit)
12558 ("java-hamcrest-core" ,java-hamcrest-core)))
12559 (home-page "https://biojava.org")
12560 (synopsis "Core libraries of Java framework for processing biological data")
12561 (description "BioJava is a project dedicated to providing a Java framework
12562 for processing biological data. It provides analytical and statistical
12563 routines, parsers for common file formats, reference implementations of
12564 popular algorithms, and allows the manipulation of sequences and 3D
12565 structures. The goal of the biojava project is to facilitate rapid
12566 application development for bioinformatics.
12568 This package provides the core libraries.")
12569 (license license:lgpl2.1+)))
12571 (define-public java-biojava-phylo
12572 (package (inherit java-biojava-core)
12573 (name "java-biojava-phylo")
12574 (build-system ant-build-system)
12577 #:jar-name "biojava-phylo.jar"
12578 #:source-dir "biojava-phylo/src/main/java/"
12579 #:test-dir "biojava-phylo/src/test"
12581 (modify-phases %standard-phases
12582 (add-before 'build 'copy-resources
12584 (copy-recursively "biojava-phylo/src/main/resources"
12587 (add-before 'check 'copy-test-resources
12589 (copy-recursively "biojava-phylo/src/test/resources"
12590 "build/test-classes")
12593 `(("java-log4j-api" ,java-log4j-api)
12594 ("java-log4j-core" ,java-log4j-core)
12595 ("java-slf4j-api" ,java-slf4j-api)
12596 ("java-slf4j-simple" ,java-slf4j-simple)
12597 ("java-biojava-core" ,java-biojava-core)
12598 ("java-forester" ,java-forester)))
12600 `(("java-junit" ,java-junit)
12601 ("java-hamcrest-core" ,java-hamcrest-core)))
12602 (home-page "https://biojava.org")
12603 (synopsis "Biojava interface to the forester phylogenomics library")
12604 (description "The phylo module provides a biojava interface layer to the
12605 forester phylogenomics library for constructing phylogenetic trees.")))
12607 (define-public java-biojava-alignment
12608 (package (inherit java-biojava-core)
12609 (name "java-biojava-alignment")
12610 (build-system ant-build-system)
12613 #:jar-name "biojava-alignment.jar"
12614 #:source-dir "biojava-alignment/src/main/java/"
12615 #:test-dir "biojava-alignment/src/test"
12617 (modify-phases %standard-phases
12618 (add-before 'build 'copy-resources
12620 (copy-recursively "biojava-alignment/src/main/resources"
12623 (add-before 'check 'copy-test-resources
12625 (copy-recursively "biojava-alignment/src/test/resources"
12626 "build/test-classes")
12629 `(("java-log4j-api" ,java-log4j-api)
12630 ("java-log4j-core" ,java-log4j-core)
12631 ("java-slf4j-api" ,java-slf4j-api)
12632 ("java-slf4j-simple" ,java-slf4j-simple)
12633 ("java-biojava-core" ,java-biojava-core)
12634 ("java-biojava-phylo" ,java-biojava-phylo)
12635 ("java-forester" ,java-forester)))
12637 `(("java-junit" ,java-junit)
12638 ("java-hamcrest-core" ,java-hamcrest-core)))
12639 (home-page "https://biojava.org")
12640 (synopsis "Biojava API for genetic sequence alignment")
12641 (description "The alignment module of BioJava provides an API that
12645 @item implementations of dynamic programming algorithms for sequence
12647 @item reading and writing of popular alignment file formats;
12648 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12651 (define-public java-biojava-core-4.0
12652 (package (inherit java-biojava-core)
12653 (name "java-biojava-core")
12657 (uri (git-reference
12658 (url "https://github.com/biojava/biojava")
12659 (commit (string-append "biojava-" version))))
12660 (file-name (string-append name "-" version "-checkout"))
12663 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12665 (define-public java-biojava-phylo-4.0
12666 (package (inherit java-biojava-core-4.0)
12667 (name "java-biojava-phylo")
12668 (build-system ant-build-system)
12671 #:jar-name "biojava-phylo.jar"
12672 #:source-dir "biojava-phylo/src/main/java/"
12673 #:test-dir "biojava-phylo/src/test"
12675 (modify-phases %standard-phases
12676 (add-before 'build 'copy-resources
12678 (copy-recursively "biojava-phylo/src/main/resources"
12681 (add-before 'check 'copy-test-resources
12683 (copy-recursively "biojava-phylo/src/test/resources"
12684 "build/test-classes")
12687 `(("java-log4j-api" ,java-log4j-api)
12688 ("java-log4j-core" ,java-log4j-core)
12689 ("java-slf4j-api" ,java-slf4j-api)
12690 ("java-slf4j-simple" ,java-slf4j-simple)
12691 ("java-biojava-core" ,java-biojava-core-4.0)
12692 ("java-forester" ,java-forester-1.005)))
12694 `(("java-junit" ,java-junit)
12695 ("java-hamcrest-core" ,java-hamcrest-core)))
12696 (home-page "https://biojava.org")
12697 (synopsis "Biojava interface to the forester phylogenomics library")
12698 (description "The phylo module provides a biojava interface layer to the
12699 forester phylogenomics library for constructing phylogenetic trees.")))
12701 (define-public java-biojava-alignment-4.0
12702 (package (inherit java-biojava-core-4.0)
12703 (name "java-biojava-alignment")
12704 (build-system ant-build-system)
12707 #:jar-name "biojava-alignment.jar"
12708 #:source-dir "biojava-alignment/src/main/java/"
12709 #:test-dir "biojava-alignment/src/test"
12711 (modify-phases %standard-phases
12712 (add-before 'build 'copy-resources
12714 (copy-recursively "biojava-alignment/src/main/resources"
12717 (add-before 'check 'copy-test-resources
12719 (copy-recursively "biojava-alignment/src/test/resources"
12720 "build/test-classes")
12723 `(("java-log4j-api" ,java-log4j-api)
12724 ("java-log4j-core" ,java-log4j-core)
12725 ("java-slf4j-api" ,java-slf4j-api)
12726 ("java-slf4j-simple" ,java-slf4j-simple)
12727 ("java-biojava-core" ,java-biojava-core-4.0)
12728 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12729 ("java-forester" ,java-forester-1.005)))
12731 `(("java-junit" ,java-junit)
12732 ("java-hamcrest-core" ,java-hamcrest-core)))
12733 (home-page "https://biojava.org")
12734 (synopsis "Biojava API for genetic sequence alignment")
12735 (description "The alignment module of BioJava provides an API that
12739 @item implementations of dynamic programming algorithms for sequence
12741 @item reading and writing of popular alignment file formats;
12742 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12745 (define-public dropseq-tools
12747 (name "dropseq-tools")
12752 (uri "http://mccarrolllab.com/download/1276/")
12753 (file-name (string-append "dropseq-tools-" version ".zip"))
12756 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12757 ;; Delete bundled libraries
12758 (modules '((guix build utils)))
12761 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12762 (delete-file-recursively "3rdParty")
12764 (build-system ant-build-system)
12766 `(#:tests? #f ; test data are not included
12767 #:test-target "test"
12768 #:build-target "all"
12769 #:source-dir "public/src/"
12772 (list (string-append "-Dpicard.executable.dir="
12773 (assoc-ref %build-inputs "java-picard")
12775 #:modules ((ice-9 match)
12778 (guix build java-utils)
12779 (guix build ant-build-system))
12781 (modify-phases %standard-phases
12782 ;; FIXME: fails with "java.io.FileNotFoundException:
12783 ;; /gnu/store/…-dropseq-tools-1.13/share/java/lib/biojava-alignment.jar"
12784 (delete 'generate-jar-indices)
12785 ;; All dependencies must be linked to "lib", because that's where
12786 ;; they will be searched for when the Class-Path property of the
12787 ;; manifest is computed.
12788 (add-after 'unpack 'record-references
12789 (lambda* (#:key inputs #:allow-other-keys)
12790 (mkdir-p "jar/lib")
12791 (let ((dirs (filter-map (match-lambda
12793 (if (and (string-prefix? "java-" name)
12794 (not (string=? name "java-testng")))
12797 (for-each (lambda (jar)
12798 (symlink jar (string-append "jar/lib/" (basename jar))))
12799 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12802 ;; There is no installation target
12804 (lambda* (#:key inputs outputs #:allow-other-keys)
12805 (let* ((out (assoc-ref outputs "out"))
12806 (bin (string-append out "/bin"))
12807 (share (string-append out "/share/java/"))
12808 (lib (string-append share "/lib/"))
12809 (scripts (list "BAMTagHistogram"
12810 "BAMTagofTagCounts"
12811 "BaseDistributionAtReadPosition"
12812 "CollapseBarcodesInPlace"
12813 "CollapseTagWithContext"
12815 "CreateIntervalsFiles"
12816 "DetectBeadSynthesisErrors"
12817 "DigitalExpression"
12818 "Drop-seq_alignment.sh"
12821 "GatherGeneGCLength"
12822 "GatherMolecularBarcodeDistributionByGene"
12823 "GatherReadQualityMetrics"
12826 "SelectCellsByNumTranscripts"
12827 "SingleCellRnaSeqMetricsCollector"
12828 "TagBamWithReadSequenceExtended"
12829 "TagReadWithGeneExon"
12830 "TagReadWithInterval"
12831 "TrimStartingSequence"
12832 "ValidateReference")))
12833 (for-each mkdir-p (list bin share lib))
12834 (install-file "dist/dropseq.jar" share)
12835 (for-each (lambda (script)
12836 (chmod script #o555)
12837 (install-file script bin))
12839 (substitute* (map (lambda (script)
12840 (string-append bin "/" script))
12842 (("^java") (which "java"))
12843 (("jar_deploy_dir=.*")
12844 (string-append "jar_deploy_dir=" share "\n"))))
12846 ;; FIXME: We do this after stripping jars because we don't want it to
12847 ;; copy all these jars and strip them. We only want to install
12848 ;; links. Arguably, this is a problem with the ant-build-system.
12849 (add-after 'strip-jar-timestamps 'install-links
12850 (lambda* (#:key outputs #:allow-other-keys)
12851 (let* ((out (assoc-ref outputs "out"))
12852 (share (string-append out "/share/java/"))
12853 (lib (string-append share "/lib/")))
12854 (for-each (lambda (jar)
12855 (symlink (readlink jar)
12856 (string-append lib (basename jar))))
12857 (find-files "jar/lib" "\\.jar$")))
12860 `(("jdk" ,icedtea-8)
12861 ("java-picard" ,java-picard-2.10.3)
12862 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12863 ("java-commons-math3" ,java-commons-math3)
12864 ("java-commons-jexl2" ,java-commons-jexl-2)
12865 ("java-commons-collections4" ,java-commons-collections4)
12866 ("java-commons-lang2" ,java-commons-lang)
12867 ("java-commons-io" ,java-commons-io)
12868 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12869 ("java-guava" ,java-guava)
12870 ("java-la4j" ,java-la4j)
12871 ("java-biojava-core" ,java-biojava-core-4.0)
12872 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12873 ("java-jdistlib" ,java-jdistlib)
12874 ("java-simple-xml" ,java-simple-xml)
12875 ("java-snakeyaml" ,java-snakeyaml)))
12878 ("java-testng" ,java-testng)))
12879 (home-page "http://mccarrolllab.com/dropseq/")
12880 (synopsis "Tools for Drop-seq analyses")
12881 (description "Drop-seq is a technology to enable biologists to
12882 analyze RNA expression genome-wide in thousands of individual cells at
12883 once. This package provides tools to perform Drop-seq analyses.")
12884 (license license:expat)))
12886 (define-public pigx-rnaseq
12888 (name "pigx-rnaseq")
12892 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12893 "releases/download/v" version
12894 "/pigx_rnaseq-" version ".tar.gz"))
12897 "0z3hr120wk2vrlmlpz1vp3n9wy3rq4y2mnzh2vf08qgqn2xfdwcw"))))
12898 (build-system gnu-build-system)
12900 `(#:parallel-tests? #f ; not supported
12902 (modify-phases %standard-phases
12903 ;; "test.sh" runs STAR, which requires excessive amounts of memory.
12904 (add-after 'unpack 'disable-resource-intensive-test
12906 (substitute* "Makefile.in"
12907 (("(^ tests/test_trim_galore/test.sh).*" _ m) m)
12908 (("^ tests/test_multiqc/test.sh") "")
12909 (("^ test.sh") ""))
12912 `(("coreutils" ,coreutils)
12915 ("snakemake" ,snakemake)
12917 ("multiqc" ,multiqc)
12919 ("trim-galore" ,trim-galore)
12921 ("samtools" ,samtools)
12922 ("r-minimal" ,r-minimal)
12923 ("r-rmarkdown" ,r-rmarkdown)
12924 ("r-ggplot2" ,r-ggplot2)
12925 ("r-ggrepel" ,r-ggrepel)
12926 ("r-gprofiler" ,r-gprofiler)
12927 ("r-deseq2" ,r-deseq2)
12929 ("r-knitr" ,r-knitr)
12930 ("r-pheatmap" ,r-pheatmap)
12931 ("r-corrplot" ,r-corrplot)
12932 ("r-reshape2" ,r-reshape2)
12933 ("r-plotly" ,r-plotly)
12934 ("r-scales" ,r-scales)
12935 ("r-summarizedexperiment" ,r-summarizedexperiment)
12936 ("r-crosstalk" ,r-crosstalk)
12937 ("r-tximport" ,r-tximport)
12938 ("r-rtracklayer" ,r-rtracklayer)
12939 ("r-rjson" ,r-rjson)
12941 ("ghc-pandoc" ,ghc-pandoc)
12942 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12943 ("python-wrapper" ,python-wrapper)
12944 ("python-pyyaml" ,python-pyyaml)))
12945 (home-page "https://bioinformatics.mdc-berlin.de/pigx/")
12946 (synopsis "Analysis pipeline for RNA sequencing experiments")
12947 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
12948 reporting for RNA sequencing experiments. It is easy to use and produces high
12949 quality reports. The inputs are reads files from the sequencing experiment,
12950 and a configuration file which describes the experiment. In addition to
12951 quality control of the experiment, the pipeline produces a differential
12952 expression report comparing samples in an easily configurable manner.")
12953 (license license:gpl3+)))
12955 (define-public pigx-chipseq
12957 (name "pigx-chipseq")
12961 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
12962 "releases/download/v" version
12963 "/pigx_chipseq-" version ".tar.gz"))
12966 "0xbvgqpk32a8iczhvac56cacr46rdkqb0allhhpvmj940idf72bi"))))
12967 (build-system gnu-build-system)
12968 ;; parts of the tests rely on access to the network
12969 (arguments '(#:tests? #f))
12972 ("coreutils" ,coreutils)
12973 ("r-minimal" ,r-minimal)
12974 ("r-argparser" ,r-argparser)
12975 ("r-biocparallel" ,r-biocparallel)
12976 ("r-biostrings" ,r-biostrings)
12977 ("r-chipseq" ,r-chipseq)
12978 ("r-data-table" ,r-data-table)
12979 ("r-dplyr" ,r-dplyr)
12980 ("r-genomation" ,r-genomation)
12981 ("r-genomicalignments" ,r-genomicalignments)
12982 ("r-genomicranges" ,r-genomicranges)
12983 ("r-rsamtools" ,r-rsamtools)
12984 ("r-rtracklayer" ,r-rtracklayer)
12985 ("r-s4vectors" ,r-s4vectors)
12986 ("r-stringr" ,r-stringr)
12987 ("r-tibble" ,r-tibble)
12988 ("r-tidyr" ,r-tidyr)
12989 ("r-jsonlite" ,r-jsonlite)
12990 ("r-heatmaply" ,r-heatmaply)
12991 ("r-htmlwidgets" ,r-htmlwidgets)
12992 ("r-ggplot2" ,r-ggplot2)
12993 ("r-plotly" ,r-plotly)
12994 ("r-rmarkdown" ,r-rmarkdown)
12995 ("python-wrapper" ,python-wrapper)
12996 ("python-pyyaml" ,python-pyyaml)
12997 ("python-magic" ,python-magic)
12998 ("python-xlrd" ,python-xlrd)
12999 ("trim-galore" ,trim-galore)
13001 ("multiqc" ,multiqc)
13003 ("ghc-pandoc" ,ghc-pandoc)
13004 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
13008 ("snakemake" ,snakemake)
13009 ("samtools" ,samtools)
13010 ("bedtools" ,bedtools)
13011 ("kentutils" ,kentutils)))
13013 `(("python-pytest" ,python-pytest)))
13014 (home-page "https://bioinformatics.mdc-berlin.de/pigx/")
13015 (synopsis "Analysis pipeline for ChIP sequencing experiments")
13016 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
13017 calling and reporting for ChIP sequencing experiments. It is easy to use and
13018 produces high quality reports. The inputs are reads files from the sequencing
13019 experiment, and a configuration file which describes the experiment. In
13020 addition to quality control of the experiment, the pipeline enables to set up
13021 multiple peak calling analysis and allows the generation of a UCSC track hub
13022 in an easily configurable manner.")
13023 (license license:gpl3+)))
13025 (define-public pigx-bsseq
13027 (name "pigx-bsseq")
13031 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
13032 "releases/download/v" version
13033 "/pigx_bsseq-" version ".tar.gz"))
13036 "0l97wvkq4diq8lcarraj33bby1zzf0w804jwi8mlc5qddp8idwhy"))))
13037 (build-system gnu-build-system)
13040 (modify-phases %standard-phases
13041 (add-before 'check 'set-timezone
13042 ;; The readr package is picky about timezones.
13043 (lambda* (#:key inputs #:allow-other-keys)
13044 (setenv "TZ" "UTC+1")
13046 (string-append (assoc-ref inputs "tzdata")
13047 "/share/zoneinfo"))
13050 `(("tzdata" ,tzdata)))
13052 `(("coreutils" ,coreutils)
13055 ("r-minimal" ,r-minimal)
13056 ("r-annotationhub" ,r-annotationhub)
13058 ("r-genomation" ,r-genomation)
13059 ("r-methylkit" ,r-methylkit)
13060 ("r-rtracklayer" ,r-rtracklayer)
13061 ("r-rmarkdown" ,r-rmarkdown)
13062 ("r-bookdown" ,r-bookdown)
13063 ("r-ggplot2" ,r-ggplot2)
13064 ("r-ggbio" ,r-ggbio)
13065 ("ghc-pandoc" ,ghc-pandoc)
13066 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
13067 ("python-wrapper" ,python-wrapper)
13068 ("python-pyyaml" ,python-pyyaml)
13069 ("snakemake" ,snakemake)
13070 ("bismark" ,bismark)
13073 ("trim-galore" ,trim-galore)
13074 ("cutadapt" ,cutadapt)
13075 ("samtools" ,samtools)))
13076 (home-page "https://bioinformatics.mdc-berlin.de/pigx/")
13077 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
13078 (description "PiGx BSseq is a data processing pipeline for raw fastq read
13079 data of bisulfite experiments; it produces reports on aggregate methylation
13080 and coverage and can be used to produce information on differential
13081 methylation and segmentation.")
13082 (license license:gpl3+)))
13084 (define-public pigx-scrnaseq
13086 (name "pigx-scrnaseq")
13090 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/"
13091 "releases/download/v" version
13092 "/pigx_scrnaseq-" version ".tar.gz"))
13095 "1d5l3gywypi67yz9advxq5xkgfhr4733gj0bwnngm723i3hdf5w9"))))
13096 (build-system gnu-build-system)
13098 `(("coreutils" ,coreutils)
13101 ("flexbar" ,flexbar)
13102 ("java" ,icedtea-8)
13103 ("jellyfish" ,jellyfish)
13104 ("python-wrapper" ,python-wrapper)
13105 ("python-pyyaml" ,python-pyyaml)
13106 ("python-pandas" ,python-pandas)
13107 ("python-magic" ,python-magic)
13108 ("python-numpy" ,python-numpy)
13109 ("python-loompy" ,python-loompy)
13110 ("ghc-pandoc" ,ghc-pandoc)
13111 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
13112 ("samtools" ,samtools)
13113 ("snakemake" ,snakemake)
13115 ("r-minimal" ,r-minimal)
13116 ("r-argparser" ,r-argparser)
13117 ("r-cowplot" ,r-cowplot)
13118 ("r-data-table" ,r-data-table)
13119 ("r-delayedarray" ,r-delayedarray)
13120 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
13121 ("r-dplyr" ,r-dplyr)
13122 ("r-dropbead" ,r-dropbead)
13124 ("r-genomicalignments" ,r-genomicalignments)
13125 ("r-genomicfiles" ,r-genomicfiles)
13126 ("r-genomicranges" ,r-genomicranges)
13127 ("r-ggplot2" ,r-ggplot2)
13128 ("r-hdf5array" ,r-hdf5array)
13129 ("r-pheatmap" ,r-pheatmap)
13130 ("r-rmarkdown" ,r-rmarkdown)
13131 ("r-rsamtools" ,r-rsamtools)
13132 ("r-rtracklayer" ,r-rtracklayer)
13133 ("r-rtsne" ,r-rtsne)
13134 ("r-scater" ,r-scater)
13135 ("r-scran" ,r-scran)
13136 ("r-seurat" ,r-seurat)
13137 ("r-singlecellexperiment" ,r-singlecellexperiment)
13138 ("r-stringr" ,r-stringr)
13139 ("r-yaml" ,r-yaml)))
13140 (home-page "https://bioinformatics.mdc-berlin.de/pigx/")
13141 (synopsis "Analysis pipeline for single-cell RNA sequencing experiments")
13142 (description "PiGX scRNAseq is an analysis pipeline for preprocessing and
13143 quality control for single cell RNA sequencing experiments. The inputs are
13144 read files from the sequencing experiment, and a configuration file which
13145 describes the experiment. It produces processed files for downstream analysis
13146 and interactive quality reports. The pipeline is designed to work with UMI
13148 (license license:gpl3+)))
13150 (define-public pigx
13156 (uri (string-append "https://github.com/BIMSBbioinfo/pigx/"
13157 "releases/download/v" version
13158 "/pigx-" version ".tar.gz"))
13161 "1i5njdy1clj5ncw45d16p7mwmqvb1ilikl9n797pxklc3f4s7mq7"))))
13162 (build-system gnu-build-system)
13164 `(("python" ,python)
13165 ("pigx-bsseq" ,pigx-bsseq)
13166 ("pigx-chipseq" ,pigx-chipseq)
13167 ("pigx-rnaseq" ,pigx-rnaseq)
13168 ("pigx-scrnaseq" ,pigx-scrnaseq)))
13169 (home-page "https://bioinformatics.mdc-berlin.de/pigx/")
13170 (synopsis "Analysis pipelines for genomics")
13171 (description "PiGx is a collection of genomics pipelines. It includes the
13172 following pipelines:
13175 @item PiGx BSseq for raw fastq read data of bisulfite experiments
13176 @item PiGx RNAseq for RNAseq samples
13177 @item PiGx scRNAseq for single cell dropseq analysis
13178 @item PiGx ChIPseq for reads from ChIPseq experiments
13181 All pipelines are easily configured with a simple sample sheet and a
13182 descriptive settings file. The result is a set of comprehensive, interactive
13183 HTML reports with interesting findings about your samples.")
13184 (license license:gpl3+)))
13186 (define-public genrich
13192 (uri (git-reference
13193 (url "https://github.com/jsh58/Genrich")
13194 (commit (string-append "v" version))))
13195 (file-name (git-file-name name version))
13198 "0x0q6z0208n3cxzqjla4rgjqpyqgwpmz27852lcvzkzaigymq4zp"))))
13199 (build-system gnu-build-system)
13201 `(#:tests? #f ; there are none
13203 (modify-phases %standard-phases
13204 (delete 'configure)
13206 (lambda* (#:key outputs #:allow-other-keys)
13207 (install-file "Genrich" (string-append (assoc-ref outputs "out") "/bin"))
13211 (home-page "https://github.com/jsh58/Genrich")
13212 (synopsis "Detecting sites of genomic enrichment")
13213 (description "Genrich is a peak-caller for genomic enrichment
13214 assays (e.g. ChIP-seq, ATAC-seq). It analyzes alignment files generated
13215 following the assay and produces a file detailing peaks of significant
13217 (license license:expat)))
13219 (define-public mantis
13220 (let ((commit "4ffd171632c2cb0056a86d709dfd2bf21bc69b84")
13224 (version (git-version "0" revision commit))
13227 (uri (git-reference
13228 (url "https://github.com/splatlab/mantis")
13230 (file-name (git-file-name name version))
13233 "0iqbr0dhmlc8mzpirmm2s4pkzkwdgrcx50yx6cv3wlr2qi064p55"))))
13234 (build-system cmake-build-system)
13235 (arguments '(#:tests? #f)) ; there are none
13237 `(("sdsl-lite" ,sdsl-lite)
13238 ("openssl" ,openssl)
13240 (home-page "https://github.com/splatlab/mantis")
13241 (synopsis "Large-scale sequence-search index data structure")
13242 (description "Mantis is a space-efficient data structure that can be
13243 used to index thousands of raw-read genomics experiments and facilitate
13244 large-scale sequence searches on those experiments. Mantis uses counting
13245 quotient filters instead of Bloom filters, enabling rapid index builds and
13246 queries, small indexes, and exact results, i.e., no false positives or
13247 negatives. Furthermore, Mantis is also a colored de Bruijn graph
13248 representation, so it supports fast graph traversal and other topological
13249 analyses in addition to large-scale sequence-level searches.")
13250 ;; uses __uint128_t and inline assembly
13251 (supported-systems '("x86_64-linux"))
13252 (license license:bsd-3))))
13254 (define-public r-diversitree
13256 (name "r-diversitree")
13261 (uri (cran-uri "diversitree" version))
13264 "00vi4klywi35hd170ksjv3xja3hqqbkcidcnrrlpgv4179k0azix"))))
13265 (build-system r-build-system)
13267 `(("gfortran" ,gfortran)))
13268 (inputs `(("fftw" ,fftw) ("gsl" ,gsl)))
13271 ("r-desolve" ,r-desolve)
13273 ("r-subplex" ,r-subplex)))
13274 (home-page "https://www.zoology.ubc.ca/prog/diversitree")
13275 (synopsis "Comparative 'phylogenetic' analyses of diversification")
13276 (description "This package contains a number of comparative \"phylogenetic\"
13277 methods, mostly focusing on analysing diversification and character evolution.
13278 Contains implementations of \"BiSSE\" (Binary State Speciation and Extinction)
13279 and its unresolved tree extensions, \"MuSSE\" (Multiple State Speciation and
13280 Extinction), \"QuaSSE\", \"GeoSSE\", and \"BiSSE-ness\" Other included methods
13281 include Markov models of discrete and continuous trait evolution and constant
13282 rate speciation and extinction.")
13283 (license license:gpl2+)))
13285 (define-public sjcount
13286 ;; There is no tag for version 3.2, nor is there a release archive.
13287 (let ((commit "292d3917cadb3f6834c81e509c30e61cd7ead6e5")
13291 (version (git-version "3.2" revision commit))
13294 (uri (git-reference
13295 (url "https://github.com/pervouchine/sjcount-full")
13297 (file-name (string-append name "-" version "-checkout"))
13300 "0gdgj35j249f04rqgq8ymcc1xg1vi9kzbajnjqpaq2wpbh8bl234"))))
13301 (build-system gnu-build-system)
13303 `(#:tests? #f ; requires a 1.4G test file
13305 (list (string-append "SAMTOOLS_DIR="
13306 (assoc-ref %build-inputs "samtools")
13309 (modify-phases %standard-phases
13310 (replace 'configure
13311 (lambda* (#:key inputs #:allow-other-keys)
13312 (substitute* "makefile"
13313 (("-I \\$\\{SAMTOOLS_DIR\\}")
13314 (string-append "-I" (assoc-ref inputs "samtools")
13315 "/include/samtools"))
13316 (("-lz ") "-lz -lpthread "))
13319 (lambda* (#:key outputs #:allow-other-keys)
13320 (for-each (lambda (tool)
13322 (string-append (assoc-ref outputs "out")
13324 '("j_count" "b_count" "sjcount"))
13327 `(("samtools" ,samtools-0.1)
13329 (home-page "https://github.com/pervouchine/sjcount-full/")
13330 (synopsis "Annotation-agnostic splice junction counting pipeline")
13331 (description "Sjcount is a utility for fast quantification of splice
13332 junctions in RNA-seq data. It is annotation-agnostic and offset-aware. This
13333 version does count multisplits.")
13334 (license license:gpl3+))))
13336 (define-public minimap2
13343 (uri (string-append "https://github.com/lh3/minimap2/"
13344 "releases/download/v" version "/"
13345 "minimap2-" version ".tar.bz2"))
13348 "0hi7i9pzxhvjj44khzzzj1lrn5gb5837arr4wgln7k1k5n4ci2mn"))))
13349 (build-system gnu-build-system)
13351 `(#:tests? #f ; there are none
13354 (let ((system ,(or (%current-target-system)
13355 (%current-system))))
13357 ((string-prefix? "x86_64" system)
13359 ((or (string-prefix? "armhf" system)
13360 (string-prefix? "aarch64" system))
13362 (else "sse2only=1"))))
13364 (modify-phases %standard-phases
13365 (delete 'configure)
13367 (lambda* (#:key outputs #:allow-other-keys)
13368 (let* ((out (assoc-ref outputs "out"))
13369 (bin (string-append out "/bin"))
13370 (man (string-append out "/share/man/man1")))
13371 (install-file "minimap2" bin)
13373 (install-file "minimap2.1" man))
13377 (home-page "https://lh3.github.io/minimap2/")
13378 (synopsis "Pairwise aligner for genomic and spliced nucleotide sequences")
13379 (description "Minimap2 is a versatile sequence alignment program that
13380 aligns DNA or mRNA sequences against a large reference database. Typical use
13384 @item mapping PacBio or Oxford Nanopore genomic reads to the human genome;
13385 @item finding overlaps between long reads with error rate up to ~15%;
13386 @item splice-aware alignment of PacBio Iso-Seq or Nanopore cDNA or Direct RNA
13387 reads against a reference genome;
13388 @item aligning Illumina single- or paired-end reads;
13389 @item assembly-to-assembly alignment;
13390 @item full-genome alignment between two closely related species with
13391 divergence below ~15%.
13393 (license license:expat)))
13395 (define-public miniasm
13401 (uri (git-reference
13402 (url "https://github.com/lh3/miniasm")
13403 (commit (string-append "v" version))))
13404 (file-name (git-file-name name version))
13407 "04dv5wv8bhsw1imxwyd438bnn9kby7svp44nbcz8lsadzjjci5gs"))))
13408 (build-system gnu-build-system)
13412 `(#:tests? #f ; There are no tests.
13414 (modify-phases %standard-phases
13415 (delete 'configure)
13417 (lambda* (#:key inputs outputs #:allow-other-keys)
13418 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
13419 (install-file "miniasm" bin)
13420 (install-file "minidot" bin)
13422 (home-page "https://github.com/lh3/miniasm")
13423 (synopsis "Ultrafast de novo assembly for long noisy reads")
13424 (description "Miniasm is a very fast OLC-based de novo assembler for noisy
13425 long reads. It takes all-vs-all read self-mappings (typically by minimap) as
13426 input and outputs an assembly graph in the GFA format. Different from
13427 mainstream assemblers, miniasm does not have a consensus step. It simply
13428 concatenates pieces of read sequences to generate the final unitig sequences.
13429 Thus the per-base error rate is similar to the raw input reads.")
13430 (license license:expat)))
13432 (define-public r-circus
13439 (uri (git-reference
13440 (url "https://github.com/BIMSBbioinfo/ciRcus")
13441 (commit (string-append "v" version))))
13442 (file-name (git-file-name name version))
13445 "0jhjn3ilb057hbf6yzrihj13ifxxs32y7nkby8l3lkm28dg4p97h"))))
13446 (build-system r-build-system)
13448 `(("r-annotationdbi" ,r-annotationdbi)
13449 ("r-annotationhub" ,r-annotationhub)
13450 ("r-biomart" ,r-biomart)
13451 ("r-data-table" ,r-data-table)
13453 ("r-genomicfeatures" ,r-genomicfeatures)
13454 ("r-genomicranges" ,r-genomicranges)
13455 ("r-ggplot2" ,r-ggplot2)
13457 ("r-iranges" ,r-iranges)
13458 ("r-rcolorbrewer" ,r-rcolorbrewer)
13459 ("r-rmysql" ,r-rmysql)
13460 ("r-s4vectors" ,r-s4vectors)
13461 ("r-stringr" ,r-stringr)
13462 ("r-summarizedexperiment" ,r-summarizedexperiment)))
13464 `(("r-knitr" ,r-knitr)))
13465 (home-page "https://github.com/BIMSBbioinfo/ciRcus")
13466 (synopsis "Annotation, analysis and visualization of circRNA data")
13467 (description "Circus is an R package for annotation, analysis and
13468 visualization of circRNA data. Users can annotate their circRNA candidates
13469 with host genes, gene featrues they are spliced from, and discriminate between
13470 known and yet unknown splice junctions. Circular-to-linear ratios of circRNAs
13471 can be calculated, and a number of descriptive plots easily generated.")
13472 (license license:artistic2.0)))
13474 (define-public gffread
13475 ;; We cannot use the tagged release because it is not in sync with gclib.
13476 ;; See https://github.com/gpertea/gffread/issues/26
13477 (let ((commit "ba7535fcb3cea55a6e5a491d916e93b454e87fd0")
13481 (version (git-version "0.9.12" revision commit))
13485 (uri (git-reference
13486 (url "https://github.com/gpertea/gffread")
13488 (file-name (git-file-name name version))
13491 "1dl2nbcg96lxpd0drg48ssa8343nf7pw9s9mkrc4mjjmfwsin3ki"))))
13492 (build-system gnu-build-system)
13494 `(#:tests? #f ; no check target
13496 (list "GCLDIR=gclib")
13498 (modify-phases %standard-phases
13499 (delete 'configure)
13500 (add-after 'unpack 'copy-gclib-source
13501 (lambda* (#:key inputs #:allow-other-keys)
13503 (copy-recursively (assoc-ref inputs "gclib-source") "gclib")
13505 ;; There is no install target
13507 (lambda* (#:key outputs #:allow-other-keys)
13508 (let* ((out (assoc-ref outputs "out"))
13509 (bin (string-append out "/bin")))
13510 (install-file "gffread" bin))
13514 ,(let ((version "0.10.3")
13515 (commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13519 (uri (git-reference
13520 (url "https://github.com/gpertea/gclib")
13522 (file-name (git-file-name "gclib" version))
13525 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13526 (home-page "https://github.com/gpertea/gffread/")
13527 (synopsis "Parse and convert GFF/GTF files")
13529 "This package provides a GFF/GTF file parsing utility providing format
13530 conversions, region filtering, FASTA sequence extraction and more.")
13531 ;; gffread is under Expat, but gclib is under Artistic 2.0
13532 (license (list license:expat
13533 license:artistic2.0)))))
13535 (define-public find-circ
13536 ;; The last release was in 2015. The license was clarified in 2017, so we
13537 ;; take the latest commit.
13538 (let ((commit "8655dca54970fcf7e92e22fbf57e1188724dda7d")
13542 (version (git-version "1.2" revision commit))
13546 (uri (git-reference
13547 (url "https://github.com/marvin-jens/find_circ")
13549 (file-name (git-file-name name version))
13552 "0p77pbqbclqr4srms34y1b9b4njybfpjiknc11ki84f3p8skb3cg"))))
13553 (build-system gnu-build-system)
13555 `(#:tests? #f ; there are none
13557 ;; There is no actual build system.
13558 (modify-phases %standard-phases
13559 (delete 'configure)
13562 (lambda* (#:key outputs #:allow-other-keys)
13563 (let* ((out (assoc-ref outputs "out"))
13564 (bin (string-append out "/bin"))
13565 (path (getenv "PYTHONPATH")))
13566 (for-each (lambda (script)
13567 (install-file script bin)
13568 (wrap-program (string-append bin "/" script)
13569 `("PYTHONPATH" ":" prefix (,path))))
13574 "unmapped2anchors.py")))
13577 `(("python2" ,python-2)
13578 ("python2-pysam" ,python2-pysam)
13579 ("python2-numpy" ,python2-numpy)))
13580 (home-page "https://github.com/marvin-jens/find_circ")
13581 (synopsis "circRNA detection from RNA-seq reads")
13582 (description "This package provides tools to detect head-to-tail
13583 spliced (back-spliced) sequencing reads, indicative of circular RNA (circRNA)
13585 (license license:gpl3))))
13587 (define-public python-scanpy
13589 (name "python-scanpy")
13594 (uri (pypi-uri "scanpy" version))
13597 "0s2b6cvaigx4wzw3850qb93sjwwxbzh22kpbp498zklc5rjpbz4l"))))
13598 (build-system python-build-system)
13601 (modify-phases %standard-phases
13603 (lambda* (#:key inputs #:allow-other-keys)
13604 ;; These tests require Internet access.
13605 (delete-file-recursively "scanpy/tests/notebooks")
13606 (delete-file "scanpy/tests/test_clustering.py")
13607 (delete-file "scanpy/tests/test_datasets.py")
13609 ;; TODO: I can't get the plotting tests to work, even with Xvfb.
13610 (delete-file "scanpy/tests/test_plotting.py")
13611 (delete-file "scanpy/tests/test_preprocessing.py")
13612 (delete-file "scanpy/tests/test_read_10x.py")
13614 (setenv "PYTHONPATH"
13615 (string-append (getcwd) ":"
13616 (getenv "PYTHONPATH")))
13620 `(("python-anndata" ,python-anndata)
13621 ("python-h5py" ,python-h5py)
13622 ("python-igraph" ,python-igraph)
13623 ("python-joblib" ,python-joblib)
13624 ("python-legacy-api-wrap" ,python-legacy-api-wrap)
13625 ("python-louvain" ,python-louvain)
13626 ("python-matplotlib" ,python-matplotlib)
13627 ("python-natsort" ,python-natsort)
13628 ("python-networkx" ,python-networkx)
13629 ("python-numba" ,python-numba)
13630 ("python-packaging" ,python-packaging)
13631 ("python-pandas" ,python-pandas)
13632 ("python-patsy" ,python-patsy)
13633 ("python-scikit-learn" ,python-scikit-learn)
13634 ("python-scipy" ,python-scipy)
13635 ("python-seaborn" ,python-seaborn)
13636 ("python-statsmodels" ,python-statsmodels)
13637 ("python-tables" ,python-tables)
13638 ("python-tqdm" ,python-tqdm)
13639 ("python-umap-learn" ,python-umap-learn)))
13641 `(("python-pytest" ,python-pytest)
13642 ("python-setuptools-scm" ,python-setuptools-scm)))
13643 (home-page "https://github.com/theislab/scanpy")
13644 (synopsis "Single-Cell Analysis in Python.")
13645 (description "Scanpy is a scalable toolkit for analyzing single-cell gene
13646 expression data. It includes preprocessing, visualization, clustering,
13647 pseudotime and trajectory inference and differential expression testing. The
13648 Python-based implementation efficiently deals with datasets of more than one
13650 (license license:bsd-3)))
13652 (define-public python-bbknn
13654 (name "python-bbknn")
13659 (uri (pypi-uri "bbknn" version))
13662 "1jbsh01f57zj4bhvjr3jh4532zznqd6nccmgrl3qi9gnhkf7c4y0"))))
13663 (build-system python-build-system)
13665 `(#:tests? #f)) ; TODO: Enable after migration to scikit-learn.
13667 `(("python-annoy" ,python-annoy)
13668 ("python-cython" ,python-cython)
13669 ("python-numpy" ,python-numpy)
13670 ("python-scipy" ,python-scipy)
13671 ("python-umap-learn" ,python-umap-learn)))
13672 (home-page "https://github.com/Teichlab/bbknn")
13673 (synopsis "Batch balanced KNN")
13674 (description "BBKNN is a batch effect removal tool that can be directly
13675 used in the Scanpy workflow. It serves as an alternative to
13676 @code{scanpy.api.pp.neighbors()}, with both functions creating a neighbour
13677 graph for subsequent use in clustering, pseudotime and UMAP visualisation. If
13678 technical artifacts are present in the data, they will make it challenging to
13679 link corresponding cell types across different batches. BBKNN actively
13680 combats this effect by splitting your data into batches and finding a smaller
13681 number of neighbours for each cell within each of the groups. This helps
13682 create connections between analogous cells in different batches without
13683 altering the counts or PCA space.")
13684 (license license:expat)))
13686 (define-public gffcompare
13687 (let ((commit "be56ef4349ea3966c12c6397f85e49e047361c41")
13690 (name "gffcompare")
13691 (version (git-version "0.10.15" revision commit))
13695 (uri (git-reference
13696 (url "https://github.com/gpertea/gffcompare/")
13698 (file-name (git-file-name name version))
13700 (base32 "0cp5qpxdhw4mxpya5dld8wi3jk00zyklm6rcri426wydinrnfmkg"))))
13701 (build-system gnu-build-system)
13703 `(#:tests? #f ; no check target
13705 (modify-phases %standard-phases
13706 (delete 'configure)
13707 (add-before 'build 'copy-gclib-source
13708 (lambda* (#:key inputs #:allow-other-keys)
13711 (assoc-ref inputs "gclib-source") "../gclib")
13714 (lambda* (#:key outputs #:allow-other-keys)
13715 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
13716 (install-file "gffcompare" bin)
13719 `(("gclib-source" ; see 'README.md' of gffcompare
13720 ,(let ((commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13723 (version (git-version "0.10.3" revision commit)))
13726 (uri (git-reference
13727 (url "https://github.com/gpertea/gclib/")
13729 (file-name (git-file-name name version))
13731 (base32 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13732 (home-page "https://github.com/gpertea/gffcompare/")
13733 (synopsis "Tool for comparing or classifing transcripts of RNA-Seq")
13735 "@code{gffcompare} is a tool that can:
13737 @item compare and evaluate the accuracy of RNA-Seq transcript assemblers
13738 (Cufflinks, Stringtie);
13739 @item collapse (merge) duplicate transcripts from multiple GTF/GFF3 files (e.g.
13740 resulted from assembly of different samples);
13741 @item classify transcripts from one or multiple GTF/GFF3 files as they relate to
13742 reference transcripts provided in a annotation file (also in GTF/GFF3 format).
13746 license:expat ;license for gffcompare
13747 license:artistic2.0))))) ;license for gclib
13749 (define-public intervaltree
13750 (let ((commit "b90527f9e6d51cd36ecbb50429e4524d3a418ea5"))
13752 (name "intervaltree")
13753 (version (git-version "0.0.0" "1" commit))
13757 (uri (git-reference
13758 (url "https://github.com/ekg/intervaltree/")
13760 (file-name (git-file-name name version))
13762 (base32 "0rgv6q5fl4x5d74n6p5wvdna6zmbdbqpb4jqqh6vq3670gn08xad"))))
13763 (build-system gnu-build-system)
13765 '(#:tests? #f ; No tests.
13766 #:make-flags (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
13769 (modify-phases %standard-phases
13770 (delete 'configure)))) ; There is no configure phase.
13771 (home-page "https://github.com/ekg/intervaltree")
13772 (synopsis "Minimal C++ interval tree implementation")
13773 (description "An interval tree can be used to efficiently find a set of
13774 numeric intervals overlapping or containing another interval. This library
13775 provides a basic implementation of an interval tree using C++ templates,
13776 allowing the insertion of arbitrary types into the tree.")
13777 (license license:expat))))
13779 (define-public python-intervaltree
13781 (name "python-intervaltree")
13786 (uri (pypi-uri "intervaltree" version))
13789 "0wz234g6irlm4hivs2qzmnywk0ss06ckagwh15nflkyb3p462kyb"))))
13790 (build-system python-build-system)
13793 (modify-phases %standard-phases
13794 ;; pytest seems to have a check to make sure the user is testing
13795 ;; their checked-out code and not an installed, potentially
13796 ;; out-of-date copy. This is harmless here, since we just installed
13797 ;; the package, so we disable the check to avoid skipping tests
13799 (add-before 'check 'import-mismatch-error-workaround
13801 (setenv "PY_IGNORE_IMPORTMISMATCH" "1")
13804 `(("python-sortedcontainers" ,python-sortedcontainers)))
13806 `(("python-pytest" ,python-pytest)))
13807 (home-page "https://github.com/chaimleib/intervaltree")
13808 (synopsis "Editable interval tree data structure")
13810 "This package provides a mutable, self-balancing interval tree
13811 implementation for Python. Queries may be by point, by range overlap, or by
13812 range envelopment. This library was designed to allow tagging text and time
13813 intervals, where the intervals include the lower bound but not the upper
13815 (license license:asl2.0)))
13817 (define-public python-pypairix
13819 (name "python-pypairix")
13821 ;; The tarball on pypi does not include the makefile to build the
13826 (uri (git-reference
13827 (url "https://github.com/4dn-dcic/pairix")
13829 (file-name (git-file-name name version))
13832 "1snr3lrmsld8sy77ng6ba6wcmd33xjccf1l2f3m6pi29xis9nd6p"))))
13833 (build-system python-build-system)
13836 (modify-phases %standard-phases
13837 (add-before 'build 'build-programs
13838 (lambda _ (invoke "make")))
13839 (add-after 'install 'install-programs
13840 (lambda* (#:key outputs #:allow-other-keys)
13841 (copy-recursively "bin" (string-append
13842 (assoc-ref outputs "out")
13847 (home-page "https://github.com/4dn-dcic/pairix")
13848 (synopsis "Support for querying pairix-indexed bgzipped text files")
13850 "Pypairix is a Python module for fast querying on a pairix-indexed
13851 bgzipped text file that contains a pair of genomic coordinates per line.")
13852 (license license:expat)))
13854 (define-public python-pyfaidx
13856 (name "python-pyfaidx")
13861 (uri (pypi-uri "pyfaidx" version))
13864 "038xi3a6zvrxbyyfpp64ka8pcjgsdq4fgw9cl5lpxbvmm1bzzw2q"))))
13865 (build-system python-build-system)
13867 `(("python-six" ,python-six)))
13868 (home-page "http://mattshirley.com")
13869 (synopsis "Random access to fasta subsequences")
13871 "This package provides procedures for efficient pythonic random access to
13872 fasta subsequences.")
13873 (license license:bsd-3)))
13875 (define-public python2-pyfaidx
13876 (package-with-python2 python-pyfaidx))
13878 (define-public python-cooler
13880 (name "python-cooler")
13885 (uri (pypi-uri "cooler" version))
13888 "01g6gqix9ba27sappz6nfyiwabzrlf8i5fn8kwcz8ra356cq9crp"))))
13889 (build-system python-build-system)
13891 `(("python-asciitree" ,python-asciitree)
13892 ("python-biopython" ,python-biopython)
13893 ("python-click" ,python-click)
13894 ("python-cytoolz" ,python-cytoolz)
13895 ("python-dask" ,python-dask)
13896 ("python-h5py" ,python-h5py)
13897 ("python-multiprocess" ,python-multiprocess)
13898 ("python-numpy" ,python-numpy)
13899 ("python-pandas" ,python-pandas)
13900 ("python-pyfaidx" ,python-pyfaidx)
13901 ("python-pypairix" ,python-pypairix)
13902 ("python-pysam" ,python-pysam)
13903 ("python-pyyaml" ,python-pyyaml)
13904 ("python-scipy" ,python-scipy)
13905 ("python-simplejson" ,python-simplejson)))
13907 `(("python-mock" ,python-mock)
13908 ("python-pytest" ,python-pytest)))
13909 (home-page "https://github.com/mirnylab/cooler")
13910 (synopsis "Sparse binary format for genomic interaction matrices")
13912 "Cooler is a support library for a sparse, compressed, binary persistent
13913 storage format, called @code{cool}, used to store genomic interaction data,
13914 such as Hi-C contact matrices.")
13915 (license license:bsd-3)))
13917 (define-public python-hicmatrix
13919 (name "python-hicmatrix")
13923 ;; Version 12 is not available on pypi.
13925 (uri (git-reference
13926 (url "https://github.com/deeptools/HiCMatrix")
13928 (file-name (git-file-name name version))
13931 "1xhdyx16f3brgxgxybixdi64ki8nbbkq5vk4h9ahi11pzpjfn1pj"))))
13932 (build-system python-build-system)
13935 (modify-phases %standard-phases
13936 (add-after 'unpack 'relax-requirements
13938 (substitute* '("requirements.txt"
13940 (("cooler *=+ *0.8.5")
13944 `(("python-cooler" ,python-cooler)
13945 ("python-intervaltree" ,python-intervaltree)
13946 ("python-numpy" ,python-numpy)
13947 ("python-pandas" ,python-pandas)
13948 ("python-scipy" ,python-scipy)
13949 ("python-tables" ,python-tables)))
13950 (home-page "https://github.com/deeptools/HiCMatrix/")
13951 (synopsis "HiCMatrix class for HiCExplorer and pyGenomeTracks")
13953 "This helper package implements the @code{HiCMatrix} class for
13954 the HiCExplorer and pyGenomeTracks packages.")
13955 (license license:gpl3+)))
13957 (define-public python-hicexplorer
13959 (name "python-hicexplorer")
13963 ;; The latest version is not available on Pypi.
13965 (uri (git-reference
13966 (url "https://github.com/deeptools/HiCExplorer")
13968 (file-name (git-file-name name version))
13971 "0q5gpbzmrkvygqgw524q36b4nrivcmyi5v194vsx0qw7b3gcmq08"))))
13972 (build-system python-build-system)
13975 (modify-phases %standard-phases
13976 (add-after 'unpack 'loosen-up-requirements
13978 (substitute* "setup.py"
13982 `(("python-biopython" ,python-biopython)
13983 ("python-configparser" ,python-configparser)
13984 ("python-cooler" ,python-cooler)
13985 ("python-future" ,python-future)
13986 ("python-intervaltree" ,python-intervaltree)
13987 ("python-jinja2" ,python-jinja2)
13988 ("python-matplotlib" ,python-matplotlib)
13989 ("python-numpy" ,python-numpy)
13990 ("python-pandas" ,python-pandas)
13991 ("python-pybigwig" ,python-pybigwig)
13992 ("python-pysam" ,python-pysam)
13993 ("python-scipy" ,python-scipy)
13994 ("python-six" ,python-six)
13995 ("python-tables" ,python-tables)
13996 ("python-unidecode" ,python-unidecode)))
13997 (home-page "https://hicexplorer.readthedocs.io")
13998 (synopsis "Process, analyze and visualize Hi-C data")
14000 "HiCExplorer is a powerful and easy to use set of tools to process,
14001 normalize and visualize Hi-C data. HiCExplorer facilitates the creation of
14002 contact matrices, correction of contacts, TAD detection, A/B compartments,
14003 merging, reordering or chromosomes, conversion from different formats
14004 including cooler and detection of long-range contacts. Moreover, it allows
14005 the visualization of multiple contact matrices along with other types of data
14006 like genes, compartments, ChIP-seq coverage tracks (and in general any type of
14007 genomic scores), long range contacts and the visualization of viewpoints.")
14008 (license license:gpl3)))
14010 (define-public python-pygenometracks
14012 (name "python-pygenometracks")
14017 (uri (pypi-uri "pyGenomeTracks" version))
14020 "16laa0wnf4qn9fb9ych4w1vqhqwjss70v0y0f6wp4gwqfrlgac0f"))))
14021 (build-system python-build-system)
14023 `(#:tests? #f ; there are none
14025 (modify-phases %standard-phases
14026 (add-after 'unpack 'relax-requirements
14028 (substitute* "setup.py"
14029 (("matplotlib ==3.1.1")
14030 "matplotlib >=3.1.1"))
14033 `(("python-future" ,python-future)
14034 ("python-gffutils" ,python-gffutils)
14035 ("python-hicmatrix" ,python-hicmatrix)
14036 ("python-intervaltree" ,python-intervaltree)
14037 ("python-matplotlib" ,python-matplotlib)
14038 ("python-numpy" ,python-numpy)
14039 ("python-pybigwig" ,python-pybigwig)
14040 ("python-pysam" ,python-pysam)
14041 ("python-tqdm" ,python-tqdm)))
14043 `(("python-pytest" ,python-pytest)))
14044 (home-page "https://pygenometracks.readthedocs.io")
14045 (synopsis "Program and library to plot beautiful genome browser tracks")
14047 "This package aims to produce high-quality genome browser tracks that
14048 are highly customizable. Currently, it is possible to plot: bigwig, bed (many
14049 options), bedgraph, links (represented as arcs), and Hi-C matrices.
14050 pyGenomeTracks can make plots with or without Hi-C data.")
14051 (license license:gpl3+)))
14053 (define-public python-hic2cool
14055 (name "python-hic2cool")
14060 (uri (pypi-uri "hic2cool" version))
14063 "0xy6mhfns2lzib1kcr6419jjp6pmh0qx8z8na55lmiwn0ds8q9cl"))))
14064 (build-system python-build-system)
14065 (arguments '(#:tests? #f)) ; no tests included
14067 `(("python-cooler" ,python-cooler)))
14068 (home-page "https://github.com/4dn-dcic/hic2cool")
14069 (synopsis "Converter for .hic and .cool files")
14071 "This package provides a converter between @code{.hic} files (from
14072 juicer) and single-resolution or multi-resolution @code{.cool} files (for
14073 cooler). Both @code{hic} and @code{cool} files describe Hi-C contact
14075 (license license:expat)))
14077 (define-public r-pore
14085 (string-append "mirror://sourceforge/rpore/" version
14086 "/poRe_" version ".tar.gz"))
14088 (base32 "0pih9nljbv8g4x8rkk29i7aqq681b782r5s5ynp4nw9yzqnmmksv"))))
14089 (properties `((upstream-name . "poRe")))
14090 (build-system r-build-system)
14092 `(("r-bit64" ,r-bit64)
14093 ("r-data-table" ,r-data-table)
14094 ("r-rhdf5" ,r-rhdf5)
14095 ("r-shiny" ,r-shiny)
14096 ("r-svdialogs" ,r-svdialogs)))
14097 (home-page "https://sourceforge.net/projects/rpore/")
14098 (synopsis "Visualize Nanopore sequencing data")
14100 "This package provides graphical user interfaces to organize and visualize Nanopore
14102 ;; This is free software but the license variant is unclear:
14103 ;; <https://github.com/mw55309/poRe_docs/issues/10>.
14104 (license license:bsd-3)))
14106 (define-public r-xbioc
14107 (let ((revision "1")
14108 (commit "6ff0670a37ab3036aaf1d94aa4b208310946b0b5"))
14111 (version (git-version "0.1.16" revision commit))
14114 (uri (git-reference
14115 (url "https://github.com/renozao/xbioc")
14117 (file-name (git-file-name name version))
14120 "0w8bsq5myiwkfhh83nm6is5ichiyvwa1axx2szvxnzq39x6knf66"))))
14121 (build-system r-build-system)
14123 `(("r-annotationdbi" ,r-annotationdbi)
14124 ("r-assertthat" ,r-assertthat)
14125 ("r-biobase" ,r-biobase)
14126 ("r-biocmanager" ,r-biocmanager)
14127 ("r-digest" ,r-digest)
14128 ("r-pkgmaker" ,r-pkgmaker)
14130 ("r-reshape2" ,r-reshape2)
14131 ("r-stringr" ,r-stringr)))
14132 (home-page "https://github.com/renozao/xbioc/")
14133 (synopsis "Extra base functions for Bioconductor")
14134 (description "This package provides extra utility functions to perform
14135 common tasks in the analysis of omics data, leveraging and enhancing features
14136 provided by Bioconductor packages.")
14137 (license license:gpl3+))))
14139 (define-public r-cssam
14140 (let ((revision "1")
14141 (commit "9ec58c982fa551af0d80b1a266890d92954833f2"))
14144 (version (git-version "1.4" revision commit))
14147 (uri (git-reference
14148 (url "https://github.com/shenorrLab/csSAM")
14150 (file-name (git-file-name name version))
14153 "128syf9v39gk0z3ip000qpsjbg6l1siyq6c8b0hz41dzg5achyb3"))))
14154 (build-system r-build-system)
14156 `(("r-formula" ,r-formula)
14157 ("r-ggplot2" ,r-ggplot2)
14158 ("r-pkgmaker" ,r-pkgmaker)
14160 ("r-rngtools" ,r-rngtools)
14161 ("r-scales" ,r-scales)))
14162 (home-page "https://github.com/shenorrLab/csSAM/")
14163 (synopsis "Cell type-specific statistical analysis of microarray")
14164 (description "This package implements the method csSAM that computes
14165 cell-specific differential expression from measured cell proportions using
14168 (license license:lgpl2.1+))))
14170 (define-public r-bseqsc
14171 (let ((revision "1")
14172 (commit "fef3f3e38dcf3df37103348b5780937982b43b98"))
14175 (version (git-version "1.0" revision commit))
14178 (uri (git-reference
14179 (url "https://github.com/shenorrLab/bseqsc")
14181 (file-name (git-file-name name version))
14184 "1prw13wa20f7wlc3gkkls66n1kxz8d28qrb8icfqdwdnnv8w5qg8"))))
14185 (build-system r-build-system)
14187 `(("r-abind" ,r-abind)
14188 ("r-annotationdbi" ,r-annotationdbi)
14189 ("r-biobase" ,r-biobase)
14190 ("r-cssam" ,r-cssam)
14191 ("r-dplyr" ,r-dplyr)
14192 ("r-e1071" ,r-e1071)
14193 ("r-edger" ,r-edger)
14194 ("r-ggplot2" ,r-ggplot2)
14196 ("r-openxlsx" ,r-openxlsx)
14197 ("r-pkgmaker" ,r-pkgmaker)
14199 ("r-preprocesscore" ,r-preprocesscore)
14200 ("r-rngtools" ,r-rngtools)
14201 ("r-scales" ,r-scales)
14202 ("r-stringr" ,r-stringr)
14203 ("r-xbioc" ,r-xbioc)))
14204 (home-page "https://github.com/shenorrLab/bseqsc")
14205 (synopsis "Deconvolution of bulk sequencing experiments using single cell data")
14206 (description "BSeq-sc is a bioinformatics analysis pipeline that
14207 leverages single-cell sequencing data to estimate cell type proportion and
14208 cell type-specific gene expression differences from RNA-seq data from bulk
14209 tissue samples. This is a companion package to the publication \"A
14210 single-cell transcriptomic map of the human and mouse pancreas reveals inter-
14211 and intra-cell population structure.\" Baron et al. Cell Systems (2016)
14212 @url{https://www.ncbi.nlm.nih.gov/pubmed/27667365}.")
14213 (license license:gpl2+))))
14215 (define-public porechop
14216 ;; The recommended way to install is to clone the git repository
14217 ;; https://github.com/rrwick/Porechop#installation
14218 (let ((commit "289d5dca4a5fc327f97b3f8cecb68ecaf1014861")
14222 (version (git-version "0.2.3" revision commit))
14226 (uri (git-reference
14227 (url "https://github.com/rrwick/Porechop")
14229 (file-name (git-file-name name version))
14231 (base32 "05ps43gig0d3ia9x5lj84lb00hbsl6ba9n7y7jz927npxbr2ym23"))))
14232 (build-system python-build-system)
14233 (home-page "https://github.com/rrwick/porechop")
14234 (synopsis "Finding, trimming or splitting adapters, in Oxford Nanopore reads")
14236 "The porechop package is a tool for finding and removing adapters from Oxford
14237 Nanopore reads. Adapters on the ends of reads are trimmed off, and when a read
14238 has an adapter in its middle, it is treated as chimeric and chopped into
14239 separate reads. Porechop performs thorough alignments to effectively find
14240 adapters, even at low sequence identity. Porechop also supports demultiplexing
14241 of Nanopore reads that were barcoded with the Native Barcoding Kit, PCR
14242 Barcoding Kit or Rapid Barcoding Kit.")
14243 (license license:gpl3+))))
14245 (define-public poretools
14246 ;; The latest release was in 2016 and the latest commit is from 2017
14247 ;; the recommended way to install is to clone the git repository
14248 ;; https://poretools.readthedocs.io/en/latest/content/installation.html
14249 (let ((commit "e426b1f09e86ac259a00c261c79df91510777407")
14253 (version (git-version "0.6.0" revision commit))
14257 (uri (git-reference
14258 (url "https://github.com/arq5x/poretools")
14260 (file-name (git-file-name name version))
14262 (base32 "0bglj833wxpp3cq430p1d3xp085ls221js2y90w7ir2x5ay8l7am"))))
14263 (build-system python-build-system)
14264 ;; requires python >=2.7, <3.0, and the same for python dependencies
14265 (arguments `(#:python ,python-2))
14269 `(("python-dateutil" ,python2-dateutil)
14270 ("python-h5py" ,python2-h5py)
14271 ("python-matplotlib" ,python2-matplotlib)
14272 ("python-pandas" ,python2-pandas)
14273 ("python-seaborn" ,python2-seaborn)))
14274 (home-page "https://poretools.readthedocs.io")
14275 (synopsis "Toolkit for working with nanopore sequencing data")
14277 "The MinION from Oxford Nanopore Technologies is a nanopore sequencer.
14278 This @code{poretools} package is a flexible toolkit for exploring datasets
14279 generated by nanopore sequencing devices for the purposes of quality control and
14280 downstream analysis. Poretools operates directly on the native FAST5, a variant
14281 of the Hierarchical Data Format (HDF5) standard.")
14282 (license license:expat))))
14284 (define-public r-absfiltergsea
14286 (name "r-absfiltergsea")
14291 (uri (cran-uri "AbsFilterGSEA" version))
14293 (base32 "15srxkxsvn38kd5frdrwfdf0ad8gskrd0h01wmdf9hglq8fjrp7w"))))
14294 (properties `((upstream-name . "AbsFilterGSEA")))
14295 (build-system r-build-system)
14297 `(("r-biobase" ,r-biobase)
14298 ("r-deseq" ,r-deseq)
14299 ("r-limma" ,r-limma)
14301 ("r-rcpparmadillo" ,r-rcpparmadillo)))
14302 (home-page "https://cran.r-project.org/web/packages/AbsFilterGSEA/")
14303 (synopsis "Improved false positive control of gene-permuting with absolute filtering")
14305 "This package provides a function that performs gene-permuting of a gene-set
14306 enrichment analysis (GSEA) calculation with or without the absolute filtering.
14307 Without filtering, users can perform (original) two-tailed or one-tailed
14309 (license license:gpl2)))
14311 (define-public jamm
14314 (version "1.0.7.6")
14318 (uri (git-reference
14319 (url "https://github.com/mahmoudibrahim/JAMM")
14320 (commit (string-append "JAMMv" version))))
14321 (file-name (git-file-name name version))
14324 "0bsa5mf9n9q5jz7mmacrra41l7r8rac5vgsn6wv1fb52ya58b970"))))
14325 (build-system gnu-build-system)
14327 `(#:tests? #f ; there are none
14329 (modify-phases %standard-phases
14330 (delete 'configure)
14333 (lambda* (#:key inputs outputs #:allow-other-keys)
14334 (let* ((out (assoc-ref outputs "out"))
14335 (libexec (string-append out "/libexec/jamm"))
14336 (bin (string-append out "/bin")))
14337 (substitute* '("JAMM.sh"
14338 "SignalGenerator.sh")
14340 (string-append "sPath=\"" libexec "\"\n")))
14341 (for-each (lambda (file)
14342 (install-file file libexec))
14343 (list "bincalculator.r"
14355 (chmod script #o555)
14356 (install-file script bin)
14357 (wrap-program (string-append bin "/" script)
14358 `("PATH" ":" prefix
14359 (,(string-append (assoc-ref inputs "coreutils") "/bin")
14360 ,(string-append (assoc-ref inputs "gawk") "/bin")
14361 ,(string-append (assoc-ref inputs "perl") "/bin")
14362 ,(string-append (assoc-ref inputs "r-minimal") "/bin")))
14363 `("PERL5LIB" ":" prefix (,(getenv "PERL5LIB")))
14364 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
14365 (list "JAMM.sh" "SignalGenerator.sh")))
14369 ("coreutils" ,coreutils)
14372 ("r-minimal" ,r-minimal)
14373 ;;("r-parallel" ,r-parallel)
14374 ("r-signal" ,r-signal)
14375 ("r-mclust" ,r-mclust)))
14376 (home-page "https://github.com/mahmoudibrahim/JAMM")
14377 (synopsis "Peak finder for NGS datasets")
14379 "JAMM is a peak finder for next generation sequencing datasets (ChIP-Seq,
14380 ATAC-Seq, DNase-Seq, etc.) that can integrate replicates and assign peak
14381 boundaries accurately. JAMM is applicable to both broad and narrow
14383 (license license:gpl3+)))
14385 (define-public ngless
14392 (uri (git-reference
14393 (url "https://gitlab.com/ngless/ngless.git")
14394 (commit (string-append "v" version))))
14395 (file-name (git-file-name name version))
14398 "1wim8wpqyff080dfcazynrmjwqas38m24m0v350w245mmhrapdma"))))
14399 (build-system haskell-build-system)
14401 `(#:haddock? #f ; The haddock phase fails with: NGLess/CmdArgs.hs:20:1:
14402 ; error: parse error on input import
14403 ; import Options.Applicative
14405 (modify-phases %standard-phases
14406 (add-after 'unpack 'create-Versions.hs
14408 (substitute* "Makefile"
14409 (("BWA_VERSION = .*")
14410 (string-append "BWA_VERSION = "
14411 ,(package-version bwa) "\n"))
14412 (("SAM_VERSION = .*")
14413 (string-append "SAM_VERSION = "
14414 ,(package-version samtools) "\n"))
14415 (("PRODIGAL_VERSION = .*")
14416 (string-append "PRODIGAL_VERSION = "
14417 ,(package-version prodigal) "\n"))
14418 (("MINIMAP2_VERSION = .*")
14419 (string-append "MINIMAP2_VERSION = "
14420 ,(package-version minimap2) "\n")))
14421 (invoke "make" "NGLess/Dependencies/Versions.hs")
14423 (add-after 'create-Versions.hs 'create-cabal-file
14424 (lambda _ (invoke "hpack") #t))
14425 ;; These tools are expected to be installed alongside ngless.
14426 (add-after 'install 'link-tools
14427 (lambda* (#:key inputs outputs #:allow-other-keys)
14428 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
14429 (symlink (string-append (assoc-ref inputs "prodigal")
14431 (string-append bin "ngless-" ,version "-prodigal"))
14432 (symlink (string-append (assoc-ref inputs "minimap2")
14434 (string-append bin "ngless-" ,version "-minimap2"))
14435 (symlink (string-append (assoc-ref inputs "samtools")
14437 (string-append bin "ngless-" ,version "-samtools"))
14438 (symlink (string-append (assoc-ref inputs "bwa")
14440 (string-append bin "ngless-" ,version "-bwa"))
14443 `(("prodigal" ,prodigal)
14445 ("samtools" ,samtools)
14446 ("minimap2" ,minimap2)
14447 ("ghc-aeson" ,ghc-aeson)
14448 ("ghc-ansi-terminal" ,ghc-ansi-terminal)
14449 ("ghc-async" ,ghc-async)
14450 ("ghc-atomic-write" ,ghc-atomic-write)
14451 ("ghc-bytestring-lexing" ,ghc-bytestring-lexing)
14452 ("ghc-conduit" ,ghc-conduit)
14453 ("ghc-conduit-algorithms" ,ghc-conduit-algorithms)
14454 ("ghc-conduit-extra" ,ghc-conduit-extra)
14455 ("ghc-configurator" ,ghc-configurator)
14456 ("ghc-convertible" ,ghc-convertible)
14457 ("ghc-data-default" ,ghc-data-default)
14458 ("ghc-diagrams-core" ,ghc-diagrams-core)
14459 ("ghc-diagrams-lib" ,ghc-diagrams-lib)
14460 ("ghc-diagrams-svg" ,ghc-diagrams-svg)
14461 ("ghc-double-conversion" ,ghc-double-conversion)
14462 ("ghc-edit-distance" ,ghc-edit-distance)
14463 ("ghc-either" ,ghc-either)
14464 ("ghc-errors" ,ghc-errors)
14465 ("ghc-extra" ,ghc-extra)
14466 ("ghc-filemanip" ,ghc-filemanip)
14467 ("ghc-file-embed" ,ghc-file-embed)
14468 ("ghc-gitrev" ,ghc-gitrev)
14469 ("ghc-hashtables" ,ghc-hashtables)
14470 ("ghc-http-conduit" ,ghc-http-conduit)
14471 ("ghc-inline-c" ,ghc-inline-c)
14472 ("ghc-inline-c-cpp" ,ghc-inline-c-cpp)
14473 ("ghc-intervalmap" ,ghc-intervalmap)
14474 ("ghc-missingh" ,ghc-missingh)
14475 ("ghc-optparse-applicative" ,ghc-optparse-applicative)
14476 ("ghc-regex" ,ghc-regex)
14477 ("ghc-safe" ,ghc-safe)
14478 ("ghc-safeio" ,ghc-safeio)
14479 ("ghc-strict" ,ghc-strict)
14480 ("ghc-tar" ,ghc-tar)
14481 ("ghc-tar-conduit" ,ghc-tar-conduit)
14482 ("ghc-unliftio" ,ghc-unliftio)
14483 ("ghc-unliftio-core" ,ghc-unliftio-core)
14484 ("ghc-vector" ,ghc-vector)
14485 ("ghc-yaml" ,ghc-yaml)
14486 ("ghc-zlib" ,ghc-zlib)))
14489 ("r-hdf5r" ,r-hdf5r)
14490 ("r-iterators" ,r-iterators)
14491 ("r-itertools" ,r-itertools)
14492 ("r-matrix" ,r-matrix)))
14494 `(("ghc-hpack" ,ghc-hpack)
14495 ("ghc-quickcheck" ,ghc-quickcheck)
14496 ("ghc-test-framework" ,ghc-test-framework)
14497 ("ghc-test-framework-hunit",ghc-test-framework-hunit)
14498 ("ghc-test-framework-quickcheck2" ,ghc-test-framework-quickcheck2)
14499 ("ghc-test-framework-th" ,ghc-test-framework-th)))
14500 (home-page "https://gitlab.com/ngless/ngless")
14501 (synopsis "DSL for processing next-generation sequencing data")
14502 (description "Ngless is a domain-specific language for
14503 @dfn{next-generation sequencing} (NGS) data processing.")
14504 (license license:expat)))
14506 (define-public filtlong
14507 ;; The recommended way to install is to clone the git repository
14508 ;; https://github.com/rrwick/Filtlong#installation
14509 ;; and the lastest release is more than nine months old
14510 (let ((commit "d1bb46dfe8bc7efe6257b5ce222c04bfe8aedaab")
14514 (version (git-version "0.2.0" revision commit))
14518 (uri (git-reference
14519 (url "https://github.com/rrwick/Filtlong")
14521 (file-name (git-file-name name version))
14523 (base32 "1xr92r820x8qlkcr3b57iw223yq8vjgyi42jr79w2xgw47qzr575"))))
14524 (build-system gnu-build-system)
14526 `(#:tests? #f ; no check target
14528 (modify-phases %standard-phases
14529 (delete 'configure)
14531 (lambda* (#:key outputs #:allow-other-keys)
14532 (let* ((out (assoc-ref outputs "out"))
14533 (bin (string-append out "/bin"))
14534 (scripts (string-append out "/share/filtlong/scripts")))
14535 (install-file "bin/filtlong" bin)
14536 (install-file "scripts/histogram.py" scripts)
14537 (install-file "scripts/read_info_histograms.sh" scripts))
14539 (add-after 'install 'wrap-program
14540 (lambda* (#:key inputs outputs #:allow-other-keys)
14541 (let* ((out (assoc-ref outputs "out"))
14542 (path (getenv "PYTHONPATH")))
14543 (wrap-program (string-append out
14544 "/share/filtlong/scripts/histogram.py")
14545 `("PYTHONPATH" ":" prefix (,path))))
14547 (add-before 'check 'patch-tests
14549 (substitute* "scripts/read_info_histograms.sh"
14550 (("awk") (which "gawk")))
14553 `(("gawk" ,gawk) ;for read_info_histograms.sh
14554 ("python" ,python-2) ;required for histogram.py
14556 (home-page "https://github.com/rrwick/Filtlong/")
14557 (synopsis "Tool for quality filtering of Nanopore and PacBio data")
14559 "The Filtlong package is a tool for filtering long reads by quality.
14560 It can take a set of long reads and produce a smaller, better subset. It uses
14561 both read length (longer is better) and read identity (higher is better) when
14562 choosing which reads pass the filter.")
14563 (license (list license:gpl3 ;filtlong
14564 license:asl2.0))))) ;histogram.py
14566 (define-public nanopolish
14567 ;; The recommended way to install is to clone the git repository
14568 ;; <https://github.com/jts/nanopolish#installing-a-particular-release>.
14569 ;; Also, the differences between release and current version seem to be
14571 (let ((commit "6331dc4f15b9dfabb954ba3fae9d76b6c3ca6377")
14574 (name "nanopolish")
14575 (version (git-version "0.11.1" revision commit))
14579 (uri (git-reference
14580 (url "https://github.com/jts/nanopolish")
14583 (file-name (git-file-name name version))
14585 (base32 "15ikl3d37y49pwd7vx36xksgsqajhf24q7qqsnpl15dqqyy5qgbc"))
14586 (modules '((guix build utils)))
14589 (delete-file-recursively "htslib")
14591 (build-system gnu-build-system)
14594 `("HDF5=noinstall" "EIGEN=noinstall" "HTS=noinstall" "CC=gcc")
14595 #:tests? #f ; no check target
14597 (modify-phases %standard-phases
14598 (add-after 'unpack 'find-eigen
14599 (lambda* (#:key inputs #:allow-other-keys)
14601 (string-append (assoc-ref inputs "eigen")
14603 (or (getenv "CPATH") "")))
14605 (delete 'configure)
14607 (lambda* (#:key outputs #:allow-other-keys)
14608 (let* ((out (assoc-ref outputs "out"))
14609 (bin (string-append out "/bin"))
14610 (scripts (string-append out "/share/nanopolish/scripts")))
14612 (install-file "nanopolish" bin)
14613 (for-each (lambda (file) (install-file file scripts))
14614 (find-files "scripts" ".*"))
14616 (add-after 'install 'wrap-programs
14617 (lambda* (#:key outputs #:allow-other-keys)
14618 (for-each (lambda (file)
14619 (wrap-program file `("PYTHONPATH" ":" prefix (,path))))
14620 (find-files "/share/nanopolish/scripts" "\\.py"))
14621 (for-each (lambda (file)
14622 (wrap-program file `("PERL5LIB" ":" prefix (,path))))
14623 (find-files "/share/nanopolish/scripts" "\\.pl"))
14630 ("python" ,python-wrapper)
14631 ("python-biopython" ,python-biopython)
14632 ("python-numpy" ,python-numpy)
14633 ("python-pysam" ,python-pysam)
14634 ("python-scikit-learn" , python-scikit-learn)
14635 ("python-scipy" ,python-scipy)
14637 (home-page "https://github.com/jts/nanopolish")
14638 (synopsis "Signal-level analysis of Oxford Nanopore sequencing data")
14640 "This package analyses the Oxford Nanopore sequencing data at signal-level.
14641 Nanopolish can calculate an improved consensus sequence for a draft genome
14642 assembly, detect base modifications, call SNPs (Single nucleotide
14643 polymorphisms) and indels with respect to a reference genome and more.")
14644 (license license:expat))))
14646 (define-public cnvkit
14653 (uri (git-reference
14654 (url "https://github.com/etal/cnvkit")
14655 (commit (string-append "v" version))))
14656 (file-name (git-file-name name version))
14658 (base32 "0g2f78k68yglmj4fsfmgs8idqv3di9aj53fg0ld0hqljg8chhh82"))))
14659 (build-system python-build-system)
14661 `(("python-biopython" ,python-biopython)
14662 ("python-future" ,python-future)
14663 ("python-matplotlib" ,python-matplotlib)
14664 ("python-numpy" ,python-numpy)
14665 ("python-reportlab" ,python-reportlab)
14666 ("python-pandas" ,python-pandas)
14667 ("python-pysam" ,python-pysam)
14668 ("python-pyfaidx" ,python-pyfaidx)
14669 ("python-scipy" ,python-scipy)
14671 ("r-dnacopy" ,r-dnacopy)))
14672 (home-page "https://cnvkit.readthedocs.org/")
14673 (synopsis "Copy number variant detection from targeted DNA sequencing")
14675 "CNVkit is a Python library and command-line software toolkit to infer
14676 and visualize copy number from high-throughput DNA sequencing data. It is
14677 designed for use with hybrid capture, including both whole-exome and custom
14678 target panels, and short-read sequencing platforms such as Illumina and Ion
14680 (license license:asl2.0)))
14682 (define-public python-pyfit-sne
14684 (name "python-pyfit-sne")
14689 (uri (git-reference
14690 (url "https://github.com/KlugerLab/pyFIt-SNE")
14692 (file-name (git-file-name name version))
14694 (base32 "13wh3qkzs56azmmgnxib6xfr29g7xh09sxylzjpni5j0pp0rc5qw"))))
14695 (build-system python-build-system)
14697 `(("python-numpy" ,python-numpy)))
14701 `(("python-cython" ,python-cython)))
14702 (home-page "https://github.com/KlugerLab/pyFIt-SNE")
14703 (synopsis "FFT-accelerated Interpolation-based t-SNE")
14705 "t-Stochastic Neighborhood Embedding (t-SNE) is a highly successful
14706 method for dimensionality reduction and visualization of high dimensional
14707 datasets. A popular implementation of t-SNE uses the Barnes-Hut algorithm to
14708 approximate the gradient at each iteration of gradient descent. This package
14709 is a Cython wrapper for FIt-SNE.")
14710 (license license:bsd-4)))
14712 (define-public bbmap
14718 (uri (string-append
14719 "mirror://sourceforge/bbmap/BBMap_" version ".tar.gz"))
14722 "1q4rfhxcb6z3gm8zg2davjz98w22lkf4hm9ikxz9kdl93pil3wkd"))))
14723 (build-system ant-build-system)
14725 `(#:build-target "dist"
14726 #:tests? #f ; there are none
14728 (list (string-append "-Dmpijar="
14729 (assoc-ref %build-inputs "java-openmpi")
14731 #:modules ((guix build ant-build-system)
14733 (guix build java-utils))
14735 (modify-phases %standard-phases
14736 (add-after 'build 'build-jni-library
14738 (with-directory-excursion "jni"
14739 (invoke "make" "-f" "makefile.linux"))))
14740 ;; There is no install target
14741 (replace 'install (install-jars "dist"))
14742 (add-after 'install 'install-scripts-and-documentation
14743 (lambda* (#:key outputs #:allow-other-keys)
14744 (substitute* "calcmem.sh"
14745 (("\\| awk ") (string-append "| " (which "awk") " ")))
14746 (let* ((scripts (find-files "." "\\.sh$"))
14747 (out (assoc-ref outputs "out"))
14748 (bin (string-append out "/bin"))
14749 (doc (string-append out "/share/doc/bbmap"))
14750 (jni (string-append out "/lib/jni")))
14751 (substitute* scripts
14752 (("\\$DIR\"\"docs") doc)
14754 (string-append "CP=" out "/share/java/BBTools.jar\n"))
14755 (("^NATIVELIBDIR.*")
14756 (string-append "NATIVELIBDIR=" jni "\n"))
14758 (string-append "CMD=\"" (which "java"))))
14759 (for-each (lambda (script) (install-file script bin)) scripts)
14761 ;; Install JNI library
14762 (install-file "jni/libbbtoolsjni.so" jni)
14764 ;; Install documentation
14765 (install-file "docs/readme.txt" doc)
14766 (copy-recursively "docs/guides" doc))
14771 ("java-eclipse-jdt-core" ,java-eclipse-jdt-core)
14772 ("java-eclipse-jdt-compiler-apt" ,java-eclipse-jdt-compiler-apt)
14773 ("java-openmpi" ,java-openmpi)))
14774 (home-page "https://sourceforge.net/projects/bbmap/")
14775 (synopsis "Aligner and other tools for short sequencing reads")
14777 "This package provides bioinformatic tools to align, deduplicate,
14778 reformat, filter and normalize DNA and RNA-seq data. It includes the
14779 following tools: BBMap, a short read aligner for DNA and RNA-seq data; BBNorm,
14780 a kmer-based error-correction and normalization tool; Dedupe, a tool to
14781 simplify assemblies by removing duplicate or contained subsequences that share
14782 a target percent identity; Reformat, to convert reads between
14783 fasta/fastq/scarf/fasta+qual/sam, interleaved/paired, and ASCII-33/64, at over
14784 500 MB/s; and BBDuk, a tool to filter, trim, or mask reads with kmer matches
14785 to an artifact/contaminant file.")
14786 (license license:bsd-3)))
14788 (define-public velvet
14794 (uri (string-append "https://www.ebi.ac.uk/~zerbino/velvet/"
14795 "velvet_" version ".tgz"))
14798 "0h3njwy66p6bx14r3ar1byb0ccaxmxka4c65rn4iybyiqa4d8kc8"))
14799 ;; Delete bundled libraries
14800 (modules '((guix build utils)))
14803 (delete-file "Manual.pdf")
14804 (delete-file-recursively "third-party")
14806 (build-system gnu-build-system)
14808 `(#:make-flags '("OPENMP=t")
14809 #:test-target "test"
14811 (modify-phases %standard-phases
14812 (delete 'configure)
14813 (add-after 'unpack 'fix-zlib-include
14815 (substitute* "src/binarySequences.c"
14816 (("../third-party/zlib-1.2.3/zlib.h") "zlib.h"))
14819 (lambda* (#:key outputs #:allow-other-keys)
14820 (let* ((out (assoc-ref outputs "out"))
14821 (bin (string-append out "/bin"))
14822 (doc (string-append out "/share/doc/velvet")))
14825 (install-file "velveth" bin)
14826 (install-file "velvetg" bin)
14827 (install-file "Manual.pdf" doc)
14828 (install-file "Columbus_manual.pdf" doc)
14831 `(("openmpi" ,openmpi)
14834 `(("texlive" ,(texlive-union (list texlive-latex-graphics
14835 texlive-latex-hyperref)))))
14836 (home-page "https://www.ebi.ac.uk/~zerbino/velvet/")
14837 (synopsis "Nucleic acid sequence assembler for very short reads")
14839 "Velvet is a de novo genomic assembler specially designed for short read
14840 sequencing technologies, such as Solexa or 454. Velvet currently takes in
14841 short read sequences, removes errors then produces high quality unique
14842 contigs. It then uses paired read information, if available, to retrieve the
14843 repeated areas between contigs.")
14844 (license license:gpl2+)))
14846 (define-public python-velocyto
14848 (name "python-velocyto")
14849 (version "0.17.17")
14853 (uri (pypi-uri "velocyto" version))
14856 "0fgygyzqgrq32dv6a00biq1p1cwi6kbl5iqblxq1kklj6b2mzmhs"))))
14857 (build-system python-build-system)
14859 `(("python-joblib" ,python-joblib)))
14861 `(("python-click" ,python-click)
14862 ("python-cython" ,python-cython)
14863 ("python-h5py" ,python-h5py)
14864 ("python-loompy" ,python-loompy)
14865 ("python-matplotlib" ,python-matplotlib)
14866 ("python-numba" ,python-numba)
14867 ("python-numpy" ,python-numpy)
14868 ("python-pandas" ,python-pandas)
14869 ("python-pysam" ,python-pysam)
14870 ("python-scikit-learn" ,python-scikit-learn)
14871 ("python-scipy" ,python-scipy)))
14872 (home-page "https://github.com/velocyto-team/velocyto.py")
14873 (synopsis "RNA velocity analysis for single cell RNA-seq data")
14875 "Velocyto is a library for the analysis of RNA velocity. Velocyto
14876 includes a command line tool and an analysis pipeline.")
14877 (license license:bsd-2)))
14879 (define-public arriba
14886 (uri (string-append "https://github.com/suhrig/arriba/releases/"
14887 "download/v" version "/arriba_v" version ".tar.gz"))
14890 "0jx9656ry766vb8z08m1c3im87b0c82qpnjby9wz4kcz8vn87dx2"))))
14891 (build-system gnu-build-system)
14893 `(#:tests? #f ; there are none
14895 (modify-phases %standard-phases
14896 (replace 'configure
14897 (lambda* (#:key inputs #:allow-other-keys)
14898 (let ((htslib (assoc-ref inputs "htslib")))
14899 (substitute* "Makefile"
14900 (("-I\\$\\(HTSLIB\\)/htslib")
14901 (string-append "-I" htslib "/include/htslib"))
14902 ((" \\$\\(HTSLIB\\)/libhts.a")
14903 (string-append " " htslib "/lib/libhts.so"))))
14904 (substitute* "run_arriba.sh"
14905 (("^STAR ") (string-append (which "STAR") " "))
14906 (("samtools --version-only")
14907 (string-append (which "samtools") " --version-only"))
14908 (("samtools index")
14909 (string-append (which "samtools") " index"))
14911 (string-append (which "samtools") " sort")))
14914 (lambda* (#:key outputs #:allow-other-keys)
14915 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
14916 (install-file "arriba" bin)
14917 (install-file "run_arriba.sh" bin)
14918 (install-file "draw_fusions.R" bin)
14919 (wrap-program (string-append bin "/draw_fusions.R")
14920 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
14923 `(("htslib" ,htslib)
14924 ("r-minimal" ,r-minimal)
14925 ("r-circlize" ,r-circlize)
14926 ("r-genomicalignments" ,r-genomicalignments)
14927 ("r-genomicranges" ,r-genomicranges)
14928 ("samtools" ,samtools)
14931 (home-page "https://github.com/suhrig/arriba")
14932 (synopsis "Gene fusion detection from RNA-Seq data ")
14934 "Arriba is a command-line tool for the detection of gene fusions from
14935 RNA-Seq data. It was developed for the use in a clinical research setting.
14936 Therefore, short runtimes and high sensitivity were important design criteria.
14937 It is based on the fast STAR aligner and the post-alignment runtime is
14938 typically just around two minutes. In contrast to many other fusion detection
14939 tools which build on STAR, Arriba does not require to reduce the
14940 @code{alignIntronMax} parameter of STAR to detect small deletions.")
14941 ;; All code is under the Expat license with the exception of
14942 ;; "draw_fusions.R", which is under GPLv3.
14943 (license (list license:expat license:gpl3))))
14945 (define-public adapterremoval
14947 (name "adapterremoval")
14952 (uri (git-reference
14953 (url "https://github.com/MikkelSchubert/adapterremoval")
14954 (commit (string-append "v" version))))
14955 (file-name (git-file-name name version))
14958 "1nf3ki5pfzalhrx2fr1y6pfqfi133yj2m7q4fj9irf5fb94bapwr"))))
14959 (build-system gnu-build-system)
14961 `(#:make-flags (list "COLOR_BUILD=no"
14962 (string-append "PREFIX="
14963 (assoc-ref %outputs "out")))
14964 #:test-target "test"
14966 (modify-phases %standard-phases
14967 (delete 'configure))))
14970 (home-page "https://adapterremoval.readthedocs.io/")
14971 (synopsis "Rapid sequence adapter trimming, identification, and read merging")
14973 "This program searches for and removes remnant adapter sequences from
14974 @dfn{High-Throughput Sequencing} (HTS) data and (optionally) trims low quality
14975 bases from the 3' end of reads following adapter removal. AdapterRemoval can
14976 analyze both single end and paired end data, and can be used to merge
14977 overlapping paired-ended reads into (longer) consensus sequences.
14978 Additionally, the AdapterRemoval may be used to recover a consensus adapter
14979 sequence for paired-ended data, for which this information is not available.")
14980 (license license:gpl3+)))
14982 (define-public pplacer
14983 (let ((commit "807f6f3"))
14986 ;; The commit should be updated with each version change.
14987 (version "1.1.alpha19")
14991 (uri (git-reference
14992 (url "https://github.com/matsen/pplacer")
14993 (commit (string-append "v" version))))
14994 (file-name (git-file-name name version))
14996 (base32 "11ppbbbx20p2g9wj3ff64dhnarb12q79v7qh4rk0gj6lkbz4n7cn"))))
14997 (build-system ocaml-build-system)
14999 `(#:modules ((guix build ocaml-build-system)
15003 (modify-phases %standard-phases
15004 (delete 'configure)
15005 (add-after 'unpack 'fix-build-with-latest-ocaml
15007 (substitute* "myocamlbuild.ml"
15008 (("dep \\[\"c_pam\"\\]" m)
15009 (string-append "flag [\"ocaml\"; \"compile\"] (A \"-unsafe-string\");\n"
15011 (("let run_and_read" m)
15016 let pos = String.index s ch in
15017 x := (String.before s pos)::!x;
15018 go (String.after s (pos + 1))
15021 with Not_found -> !x
15022 let split_nl s = split s '\\n'
15023 let before_space s =
15024 try String.before s (String.index s ' ')
15025 with Not_found -> s
15028 (("run_and_read \"ocamlfind list \\| cut -d' ' -f1\"" m)
15029 (string-append "List.map before_space (split_nl & " m ")"))
15030 ((" blank_sep_strings &") "")
15031 ((" Lexing.from_string &") ""))
15033 (add-after 'unpack 'replace-bundled-cddlib
15034 (lambda* (#:key inputs #:allow-other-keys)
15035 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
15036 (local-dir "cddlib_guix"))
15038 (with-directory-excursion local-dir
15039 (invoke "tar" "xvf" cddlib-src))
15040 (let ((cddlib-src-folder
15041 (string-append local-dir "/"
15042 (list-ref (scandir local-dir) 2)
15044 (for-each make-file-writable (find-files "cdd_src" ".*"))
15048 (string-append "cdd_src/" (basename file))))
15049 (find-files cddlib-src-folder ".*[ch]$")))
15051 (add-after 'unpack 'fix-makefile
15053 ;; Remove system calls to 'git'.
15054 (substitute* "Makefile"
15055 (("^DESCRIPT:=pplacer-.*")
15057 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
15058 (substitute* "myocamlbuild.ml"
15059 (("git describe --tags --long .*\\\" with")
15061 "echo -n v" ,version "-" ,commit "\" with")))
15064 (lambda* (#:key outputs #:allow-other-keys)
15065 (let* ((out (assoc-ref outputs "out"))
15066 (bin (string-append out "/bin")))
15067 (copy-recursively "bin" bin))
15069 #:ocaml ,ocaml-4.07
15070 #:findlib ,ocaml4.07-findlib))
15072 `(("zlib" ,zlib "static")
15074 ("ocaml-ounit" ,(package-with-ocaml4.07 ocaml-ounit))
15075 ("ocaml-batteries" ,(package-with-ocaml4.07 ocaml-batteries))
15076 ("ocaml-camlzip" ,(package-with-ocaml4.07 camlzip))
15077 ("ocaml-csv" ,(package-with-ocaml4.07 ocaml-csv))
15078 ("ocaml-sqlite3" ,ocaml4.07-sqlite3)
15079 ("ocaml-xmlm" ,(package-with-ocaml4.07 ocaml-xmlm))
15080 ("ocaml-mcl" ,(package-with-ocaml4.07 ocaml-mcl))
15081 ("ocaml-gsl" ,ocaml4.07-gsl-1)))
15083 `(("cddlib-src" ,(package-source cddlib))
15084 ("ocamlbuild" ,(package-with-ocaml4.07 ocamlbuild))
15085 ("pkg-config" ,pkg-config)))
15087 `(("pplacer-scripts" ,pplacer-scripts)))
15088 (synopsis "Phylogenetic placement of biological sequences")
15090 "Pplacer places query sequences on a fixed reference phylogenetic tree
15091 to maximize phylogenetic likelihood or posterior probability according to a
15092 reference alignment. Pplacer is designed to be fast, to give useful
15093 information about uncertainty, and to offer advanced visualization and
15094 downstream analysis.")
15095 (home-page "https://matsen.fhcrc.org/pplacer/")
15096 (license license:gpl3))))
15098 ;; This package is installed alongside 'pplacer'. It is a separate package so
15099 ;; that it can use the python-build-system for the scripts that are
15100 ;; distributed alongside the main OCaml binaries.
15101 (define pplacer-scripts
15104 (name "pplacer-scripts")
15105 (build-system python-build-system)
15107 `(#:python ,python-2
15109 (modify-phases %standard-phases
15110 (add-after 'unpack 'enter-scripts-dir
15111 (lambda _ (chdir "scripts") #t))
15113 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t))
15114 (add-after 'install 'wrap-executables
15115 (lambda* (#:key inputs outputs #:allow-other-keys)
15116 (let* ((out (assoc-ref outputs "out"))
15117 (bin (string-append out "/bin")))
15118 (let ((path (string-append
15119 (assoc-ref inputs "hmmer") "/bin:"
15120 (assoc-ref inputs "infernal") "/bin")))
15122 (wrap-program (string-append bin "/refpkg_align.py")
15123 `("PATH" ":" prefix (,path))))
15124 (let ((path (string-append
15125 (assoc-ref inputs "hmmer") "/bin")))
15126 (wrap-program (string-append bin "/hrefpkg_query.py")
15127 `("PATH" ":" prefix (,path)))))
15130 `(("infernal" ,infernal)
15133 `(("python-biopython" ,python2-biopython)
15134 ("taxtastic" ,taxtastic)))
15135 (synopsis "Pplacer Python scripts")))
15137 (define-public python2-checkm-genome
15139 (name "python2-checkm-genome")
15144 (uri (pypi-uri "checkm-genome" version))
15147 "0bm8gpxjmzxsxxl8lzwqhgx8g1dlnmp6znz7wv3hgb0gdjbf9dzz"))))
15148 (build-system python-build-system)
15150 `(#:python ,python-2
15151 #:tests? #f)) ; some tests are interactive
15153 `(("python-dendropy" ,python2-dendropy)
15154 ("python-matplotlib" ,python2-matplotlib)
15155 ("python-numpy" ,python2-numpy)
15156 ("python-pysam" ,python2-pysam)
15157 ("python-scipy" ,python2-scipy)))
15158 (home-page "https://pypi.org/project/Checkm/")
15159 (synopsis "Assess the quality of putative genome bins")
15161 "CheckM provides a set of tools for assessing the quality of genomes
15162 recovered from isolates, single cells, or metagenomes. It provides robust
15163 estimates of genome completeness and contamination by using collocated sets of
15164 genes that are ubiquitous and single-copy within a phylogenetic lineage.
15165 Assessment of genome quality can also be examined using plots depicting key
15166 genomic characteristics (e.g., GC, coding density) which highlight sequences
15167 outside the expected distributions of a typical genome. CheckM also provides
15168 tools for identifying genome bins that are likely candidates for merging based
15169 on marker set compatibility, similarity in genomic characteristics, and
15170 proximity within a reference genome.")
15171 (license license:gpl3+)))
15173 (define-public umi-tools
15180 (uri (pypi-uri "umi_tools" version))
15183 "08y3vz1vcx09whmbsn722lcs6jl9wyrh9i4p3k8j4cb1i32bij4a"))))
15184 (build-system python-build-system)
15186 `(("python-pandas" ,python-pandas)
15187 ("python-future" ,python-future)
15188 ("python-scipy" ,python-scipy)
15189 ("python-matplotlib" ,python-matplotlib)
15190 ("python-regex" ,python-regex)
15191 ("python-pysam" ,python-pysam)))
15193 `(("python-cython" ,python-cython)))
15194 (home-page "https://github.com/CGATOxford/UMI-tools")
15195 (synopsis "Tools for analyzing unique modular identifiers")
15196 (description "This package provides tools for dealing with @dfn{Unique
15197 Molecular Identifiers} (UMIs) and @dfn{Random Molecular Tags} (RMTs) in
15198 genetic sequences. There are six tools: the @code{extract} and
15199 @code{whitelist} commands are used to prepare a fastq containing UMIs @code{+/-}
15200 cell barcodes for alignment. The remaining commands, @code{group},
15201 @code{dedup}, and @{count}/@code{count_tab}, are used to identify PCR
15202 duplicates using the UMIs and perform different levels of analysis depending
15203 on the needs of the user.")
15204 (license license:expat)))
15206 (define-public ataqv
15213 (uri (git-reference
15214 (url "https://github.com/ParkerLab/ataqv")
15216 (file-name (git-file-name name version))
15219 "031xr6jx1aprh26y5b1lv3gzrlmzg4alfl73vvshymx8cq8asrqi"))))
15220 (build-system gnu-build-system)
15223 (list (string-append "prefix=" (assoc-ref %outputs "out"))
15224 (string-append "BOOST_ROOT="
15225 (assoc-ref %build-inputs "boost"))
15226 (string-append "HTSLIB_ROOT="
15227 (assoc-ref %build-inputs "htslib")))
15228 #:test-target "test"
15230 (modify-phases %standard-phases
15231 (delete 'configure))))
15235 ("ncurses" ,ncurses)
15239 (home-page "https://github.com/ParkerLab/ataqv")
15240 (synopsis "Toolkit for quality control and visualization of ATAC-seq data")
15241 (description "This package provides a toolkit for measuring and comparing
15242 ATAC-seq results. It was written to make it easier to spot differences that
15243 might be caused by ATAC-seq library prep or sequencing. The main program,
15244 @code{ataqv}, examines aligned reads and reports some basic metrics.")
15245 (license license:gpl3+)))
15247 (define-public r-psiplot
15254 (uri (git-reference
15255 (url "https://github.com/kcha/psiplot")
15256 (commit (string-append "v" version))))
15257 (file-name (git-file-name name version))
15259 (base32 "08438h16cfry5kqh3y9hs8q1b1a8bxhblsm75knviz5r6q0n1jxh"))))
15260 (build-system r-build-system)
15262 `(("r-mass" ,r-mass)
15263 ("r-dplyr" ,r-dplyr)
15264 ("r-tidyr" ,r-tidyr)
15265 ("r-purrr" ,r-purrr)
15266 ("r-readr" ,r-readr)
15267 ("r-magrittr" ,r-magrittr)
15268 ("r-ggplot2" ,r-ggplot2)))
15269 (home-page "https://github.com/kcha/psiplot")
15270 (synopsis "Plot percent spliced-in values of alternatively-spliced exons")
15272 "PSIplot is an R package for generating plots of @dfn{percent
15273 spliced-in} (PSI) values of alternatively-spliced exons that were computed by
15274 vast-tools, an RNA-Seq pipeline for alternative splicing analysis. The plots
15275 are generated using @code{ggplot2}.")
15276 (license license:expat)))
15278 (define-public python-ont-fast5-api
15280 (name "python-ont-fast5-api")
15285 (uri (git-reference
15286 (url "https://github.com/nanoporetech/ont_fast5_api")
15287 (commit (string-append "release_" version))))
15288 (file-name (git-file-name name version))
15291 "03cbq4zbbwhll8ml2m9k8sa31mirsvcbjkrq1yna0kkzz9fad5fm"))))
15292 (build-system python-build-system)
15294 `(("python-numpy" ,python-numpy)
15295 ("python-six" ,python-six)
15296 ("python-h5py" ,python-h5py)
15297 ("python-progressbar33" ,python-progressbar33)))
15298 (home-page "https://github.com/nanoporetech/ont_fast5_api")
15299 (synopsis "Interface to HDF5 files of the Oxford Nanopore fast5 file format")
15301 "This package provides a concrete implementation of the fast5 file schema
15302 using the generic @code{h5py} library, plain-named methods to interact with
15303 and reflect the fast5 file schema, and tools to convert between
15304 @code{multi_read} and @code{single_read} formats.")
15305 (license license:mpl2.0)))
15307 (define-public tbsp
15308 (let ((commit "ec8fff4410cfb13a677dbbb95cbbc60217e64907")
15312 (version (git-version "1.0.0" revision commit))
15316 (uri (git-reference
15317 (url "https://github.com/phoenixding/tbsp")
15319 (file-name (git-file-name name version))
15322 "025ym14x8gbd6hb55lsinqj6f5qzw36i10klgs7ldzxxd7s39ki1"))))
15323 (build-system python-build-system)
15324 (arguments '(#:tests? #f)) ; no tests included
15326 `(("python-matplotlib" ,python-matplotlib)
15327 ("python-networkx" ,python-networkx)
15328 ("python-numpy" ,python-numpy)
15329 ("python-pybigwig" ,python-pybigwig)
15330 ("python-biopython" ,python-biopython)
15331 ("python-scikit-learn" ,python-scikit-learn)
15332 ("python-scipy" ,python-scipy)))
15333 (home-page "https://github.com/phoenixding/tbsp/")
15334 (synopsis "SNP-based trajectory inference")
15336 "Several studies focus on the inference of developmental and response
15337 trajectories from single cell RNA-Seq (scRNA-Seq) data. A number of
15338 computational methods, often referred to as pseudo-time ordering, have been
15339 developed for this task. CRISPR has also been used to reconstruct lineage
15340 trees by inserting random mutations. The tbsp package implements an
15341 alternative method to detect significant, cell type specific sequence
15342 mutations from scRNA-Seq data.")
15343 (license license:expat))))
15345 (define-public tabixpp
15351 (uri (git-reference
15352 (url "https://github.com/ekg/tabixpp")
15353 (commit (string-append "v" version))))
15354 (file-name (git-file-name name version))
15356 (base32 "1k2a3vbq96ic4lw72iwp5s3mwwc4xhdffjj584yn6l9637q9j1yd"))
15357 (modules '((guix build utils)))
15360 (delete-file-recursively "htslib") #t))))
15361 (build-system gnu-build-system)
15363 `(("htslib" ,htslib)
15366 `(#:tests? #f ; There are no tests to run.
15368 (modify-phases %standard-phases
15369 (delete 'configure) ; There is no configure phase.
15370 ;; The build phase needs overriding the location of htslib.
15372 (lambda* (#:key inputs #:allow-other-keys)
15373 (let ((htslib-ref (assoc-ref inputs "htslib")))
15375 (string-append "HTS_LIB=" htslib-ref "/lib/libhts.a")
15376 (string-append "INCLUDES= -I" htslib-ref "/include/htslib")
15377 "HTS_HEADERS=" ; No need to check for headers here.
15378 (string-append "LIBPATH=-L. -L" htslib-ref "/include")))))
15380 (lambda* (#:key outputs #:allow-other-keys)
15381 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15382 (install-file "tabix++" bin))
15384 (home-page "https://github.com/ekg/tabixpp")
15385 (synopsis "C++ wrapper around tabix project")
15386 (description "This is a C++ wrapper around the Tabix project which abstracts
15387 some of the details of opening and jumping in tabix-indexed files.")
15388 (license license:expat)))
15390 (define-public smithwaterman
15391 (let ((commit "2610e259611ae4cde8f03c72499d28f03f6d38a7"))
15393 (name "smithwaterman")
15394 (version (git-version "0.0.0" "2" commit))
15397 (uri (git-reference
15398 (url "https://github.com/ekg/smithwaterman/")
15400 (file-name (git-file-name name version))
15402 (base32 "0i9d8zrxpiracw3mxzd9siybpy62p06rqz9mc2w93arajgbk45bs"))))
15403 (build-system gnu-build-system)
15405 `(#:tests? #f ; There are no tests to run.
15406 #:make-flags '("libsw.a" "all")
15408 (modify-phases %standard-phases
15409 (delete 'configure) ; There is no configure phase.
15411 (lambda* (#:key outputs #:allow-other-keys)
15412 (let* ((out (assoc-ref outputs "out"))
15413 (bin (string-append out "/bin"))
15414 (lib (string-append out "/lib")))
15415 (install-file "smithwaterman" bin)
15416 (install-file "libsw.a" lib))
15418 (home-page "https://github.com/ekg/smithwaterman")
15419 (synopsis "Implementation of the Smith-Waterman algorithm")
15420 (description "Implementation of the Smith-Waterman algorithm.")
15421 ;; The licensing terms are unclear: https://github.com/ekg/smithwaterman/issues/9.
15422 (license (list license:gpl2 license:expat)))))
15424 (define-public multichoose
15426 (name "multichoose")
15430 (uri (git-reference
15431 (url "https://github.com/ekg/multichoose/")
15432 (commit (string-append "v" version))))
15433 (file-name (git-file-name name version))
15435 (base32 "0ci5fqvmpamwgxvmyd79ygj6n3bnbl3vc7b6h1sxz58186sm3pfs"))))
15436 (build-system gnu-build-system)
15438 `(#:tests? #f ; Tests require node.
15440 (modify-phases %standard-phases
15441 (delete 'configure) ; There is no configure phase.
15443 (lambda* (#:key outputs #:allow-other-keys)
15444 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15445 ;; TODO: There are Python modules for these programs too.
15446 (install-file "multichoose" bin)
15447 (install-file "multipermute" bin))
15449 (home-page "https://github.com/ekg/multichoose")
15450 (synopsis "Efficient loopless multiset combination generation algorithm")
15451 (description "This library implements an efficient loopless multiset
15452 combination generation algorithm which is (approximately) described in
15453 \"Loopless algorithms for generating permutations, combinations, and other
15454 combinatorial configurations.\", G. Ehrlich - Journal of the ACM (JACM),
15455 1973. (Algorithm 7.)")
15456 (license license:expat)))
15458 (define-public fsom
15459 (let ((commit "a6ef318fbd347c53189384aef7f670c0e6ce89a3"))
15462 (version (git-version "0.0.0" "1" commit))
15465 (uri (git-reference
15466 (url "https://github.com/ekg/fsom/")
15468 (file-name (git-file-name name version))
15470 (base32 "0gw1lpvr812pywg9y546x0h1hhj261xwls41r6kqhddjlrcjc0pi"))))
15471 (build-system gnu-build-system)
15473 `(#:tests? #f ; There are no tests to run.
15475 (modify-phases %standard-phases
15476 (delete 'configure) ; There is no configure phase.
15478 (lambda* (#:key outputs #:allow-other-keys)
15479 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15480 (install-file "fsom" bin))
15482 (home-page "https://github.com/ekg/fsom")
15483 (synopsis "Manage SOM (Self-Organizing Maps) neural networks")
15484 (description "A tiny C library for managing SOM (Self-Organizing Maps)
15486 (license license:gpl3))))
15488 (define-public fastahack
15494 (uri (git-reference
15495 (url "https://github.com/ekg/fastahack/")
15496 (commit (string-append "v" version))))
15497 (file-name (git-file-name name version))
15499 (base32 "0rp1blskhzxf7vbh253ibpxbgl9wwgyzf1wbkxndi08d3j4vcss9"))))
15500 (build-system gnu-build-system)
15502 `(#:tests? #f ; Unclear how to run tests: https://github.com/ekg/fastahack/issues/15
15504 (modify-phases %standard-phases
15505 (delete 'configure) ; There is no configure phase.
15507 (lambda* (#:key outputs #:allow-other-keys)
15508 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15509 (install-file "fastahack" bin))
15511 (home-page "https://github.com/ekg/fastahack")
15512 (synopsis "Indexing and sequence extraction from FASTA files")
15513 (description "Fastahack is a small application for indexing and
15514 extracting sequences and subsequences from FASTA files. The included library
15515 provides a FASTA reader and indexer that can be embedded into applications
15516 which would benefit from directly reading subsequences from FASTA files. The
15517 library automatically handles index file generation and use.")
15518 (license (list license:expat license:gpl2))))
15520 (define-public vcflib
15527 (uri (string-append "https://github.com/vcflib/vcflib/releases/"
15528 "download/v" version
15529 "/vcflib-" version "-src.tar.gz"))
15531 (base32 "14zzrg8hg8cq9cvq2wdvp21j7nmxxkjrbagw2apd2yqv2kyx42lm"))
15532 (modules '((guix build utils)))
15535 (for-each delete-file-recursively
15536 '("fastahack" "filevercmp" "fsom" "googletest" "intervaltree"
15537 "libVCFH" "multichoose" "smithwaterman" "tabixpp"))
15539 (build-system gnu-build-system)
15541 `(("htslib" ,htslib)
15547 ;; This package builds against the .o files so we need to extract the source.
15548 ("fastahack-src" ,(package-source fastahack))
15549 ("filevercmp-src" ,(package-source filevercmp))
15550 ("fsom-src" ,(package-source fsom))
15551 ("intervaltree-src" ,(package-source intervaltree))
15552 ("multichoose-src" ,(package-source multichoose))
15553 ("smithwaterman-src" ,(package-source smithwaterman))
15554 ("tabixpp-src" ,(package-source tabixpp))))
15556 `(#:tests? #f ; no tests
15557 #:make-flags (list (string-append "HTS_LIB="
15558 (assoc-ref %build-inputs "htslib")
15560 (string-append "HTS_INCLUDES= -I"
15561 (assoc-ref %build-inputs "htslib")
15563 (string-append "HTS_LDFLAGS= -L"
15564 (assoc-ref %build-inputs "htslib")
15565 "/include/htslib" " -lhts"))
15567 (modify-phases %standard-phases
15568 (delete 'configure)
15570 (add-after 'unpack 'unpack-submodule-sources
15571 (lambda* (#:key inputs #:allow-other-keys)
15572 (let ((unpack (lambda (source target)
15574 (with-directory-excursion target
15575 (if (file-is-directory? (assoc-ref inputs source))
15576 (copy-recursively (assoc-ref inputs source) ".")
15577 (invoke "tar" "xvf"
15578 (assoc-ref inputs source)
15579 "--strip-components=1"))))))
15581 (unpack "fastahack-src" "fastahack")
15582 (unpack "filevercmp-src" "filevercmp")
15583 (unpack "fsom-src" "fsom")
15584 (unpack "intervaltree-src" "intervaltree")
15585 (unpack "multichoose-src" "multichoose")
15586 (unpack "smithwaterman-src" "smithwaterman")
15587 (unpack "tabixpp-src" "tabixpp")))))
15589 (lambda* (#:key inputs make-flags #:allow-other-keys)
15590 (let ((htslib (assoc-ref inputs "htslib")))
15591 (with-directory-excursion "tabixpp"
15592 (substitute* "Makefile"
15593 (("-Ihtslib") (string-append "-I" htslib "/include/htslib"))
15594 (("-Lhtslib") (string-append "-L" htslib "/lib/htslib"))
15595 (("htslib/htslib") (string-append htslib "/include/htslib")))
15597 (string-append "HTS_LIB=" htslib "/lib/libhts.a")))
15598 (apply invoke "make" "CC=gcc" "CFLAGS=-Itabixpp" make-flags))))
15600 (lambda* (#:key outputs #:allow-other-keys)
15601 (let ((bin (string-append (assoc-ref outputs "out") "/bin"))
15602 (lib (string-append (assoc-ref outputs "out") "/lib")))
15603 (for-each (lambda (file)
15604 (install-file file bin))
15605 (find-files "bin" ".*"))
15606 ;; The header files in src/ do not interface libvcflib,
15607 ;; therefore they are left out.
15608 (install-file "libvcflib.a" lib))
15610 (home-page "https://github.com/vcflib/vcflib/")
15611 (synopsis "Library for parsing and manipulating VCF files")
15612 (description "Vcflib provides methods to manipulate and interpret
15613 sequence variation as it can be described by VCF. It is both an API for parsing
15614 and operating on records of genomic variation as it can be described by the VCF
15615 format, and a collection of command-line utilities for executing complex
15616 manipulations on VCF files.")
15617 (license license:expat)))
15619 (define-public freebayes
15620 (let ((commit "3ce827d8ebf89bb3bdc097ee0fe7f46f9f30d5fb")
15625 (version (git-version version revision commit))
15628 (uri (git-reference
15629 (url "https://github.com/ekg/freebayes")
15631 (file-name (git-file-name name version))
15633 (base32 "1sbzwmcbn78ybymjnhwk7qc5r912azy5vqz2y7y81616yc3ba2a2"))))
15634 (build-system gnu-build-system)
15636 `(("bamtools" ,bamtools)
15640 `(("bc" ,bc) ; Needed for running tests.
15641 ("samtools" ,samtools) ; Needed for running tests.
15642 ("parallel" ,parallel) ; Needed for running tests.
15643 ("perl" ,perl) ; Needed for running tests.
15644 ("procps" ,procps) ; Needed for running tests.
15645 ("python" ,python-2) ; Needed for running tests.
15646 ("vcflib-src" ,(package-source vcflib))
15647 ;; These are submodules for the vcflib version used in freebayes.
15648 ;; This package builds against the .o files so we need to extract the source.
15649 ("tabixpp-src" ,(package-source tabixpp))
15650 ("smithwaterman-src" ,(package-source smithwaterman))
15651 ("multichoose-src" ,(package-source multichoose))
15652 ("fsom-src" ,(package-source fsom))
15653 ("filevercmp-src" ,(package-source filevercmp))
15654 ("fastahack-src" ,(package-source fastahack))
15655 ("intervaltree-src" ,(package-source intervaltree))
15656 ;; These submodules are needed to run the tests.
15657 ("bash-tap-src" ,(package-source bash-tap))
15658 ("test-simple-bash-src"
15661 (uri (git-reference
15662 (url "https://github.com/ingydotnet/test-simple-bash/")
15663 (commit "124673ff204b01c8e96b7fc9f9b32ee35d898acc")))
15664 (file-name "test-simple-bash-src-checkout")
15666 (base32 "043plp6z0x9yf7mdpky1fw7zcpwn1p47px95w9mh16603zqqqpga"))))))
15670 (string-append "BAMTOOLS_ROOT="
15671 (assoc-ref %build-inputs "bamtools")))
15672 #:test-target "test"
15674 (modify-phases %standard-phases
15675 (delete 'configure)
15676 (add-after 'unpack 'fix-tests
15678 (substitute* "test/t/01_call_variants.t"
15679 (("grep -P \"\\(\\\\t500\\$\\|\\\\t11000\\$\\|\\\\t1000\\$\\)\"")
15680 "grep -E ' (500|11000|1000)$'"))
15682 (add-after 'unpack 'unpack-submodule-sources
15683 (lambda* (#:key inputs #:allow-other-keys)
15684 (let ((unpack (lambda (source target)
15685 (with-directory-excursion target
15686 (if (file-is-directory? (assoc-ref inputs source))
15687 (copy-recursively (assoc-ref inputs source) ".")
15688 (invoke "tar" "xvf"
15689 (assoc-ref inputs source)
15690 "--strip-components=1"))))))
15692 (unpack "vcflib-src" "vcflib")
15693 (unpack "fastahack-src" "vcflib/fastahack")
15694 (unpack "filevercmp-src" "vcflib/filevercmp")
15695 (unpack "fsom-src" "vcflib/fsom")
15696 (unpack "intervaltree-src" "vcflib/intervaltree")
15697 (unpack "multichoose-src" "vcflib/multichoose")
15698 (unpack "smithwaterman-src" "vcflib/smithwaterman")
15699 (unpack "tabixpp-src" "vcflib/tabixpp")
15700 (unpack "test-simple-bash-src" "test/test-simple-bash")
15701 (unpack "bash-tap-src" "test/bash-tap")))))
15702 (add-after 'unpack-submodule-sources 'fix-makefiles
15704 ;; We don't have the .git folder to get the version tag from.
15705 (substitute* "vcflib/Makefile"
15706 (("^GIT_VERSION.*")
15707 (string-append "GIT_VERSION = v" ,version)))
15708 (substitute* "src/Makefile"
15709 (("-I\\$\\(BAMTOOLS_ROOT\\)/src")
15710 "-I$(BAMTOOLS_ROOT)/include/bamtools"))
15712 (add-before 'build 'build-tabixpp-and-vcflib
15713 (lambda* (#:key inputs make-flags #:allow-other-keys)
15714 (with-directory-excursion "vcflib"
15715 (with-directory-excursion "tabixpp"
15716 (apply invoke "make"
15717 (string-append "HTS_LIB="
15718 (assoc-ref inputs "htslib")
15721 (apply invoke "make"
15722 (string-append "CFLAGS=-Itabixpp")
15726 (lambda* (#:key outputs #:allow-other-keys)
15727 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15728 (install-file "bin/freebayes" bin)
15729 (install-file "bin/bamleftalign" bin))
15731 (home-page "https://github.com/ekg/freebayes")
15732 (synopsis "Haplotype-based variant detector")
15733 (description "FreeBayes is a Bayesian genetic variant detector designed to
15734 find small polymorphisms, specifically SNPs (single-nucleotide polymorphisms),
15735 indels (insertions and deletions), MNPs (multi-nucleotide polymorphisms), and
15736 complex events (composite insertion and substitution events) smaller than the
15737 length of a short-read sequencing alignment.")
15738 (license license:expat))))
15740 (define-public samblaster
15742 (name "samblaster")
15746 (uri (git-reference
15747 (url "https://github.com/GregoryFaust/samblaster")
15748 (commit (string-append "v." version))))
15749 (file-name (git-file-name name version))
15752 "0iv2ddfw8363vb2x8gr3p8g88whb6mb9m0pf71i2cqsbv6jghap7"))))
15753 (build-system gnu-build-system)
15755 `(#:tests? #f ; there are none
15757 (modify-phases %standard-phases
15758 (delete 'configure) ; There is no configure phase.
15760 (lambda* (#:key outputs #:allow-other-keys)
15761 (install-file "samblaster"
15762 (string-append (assoc-ref outputs "out") "/bin"))
15764 (home-page "https://github.com/GregoryFaust/samblaster")
15765 (synopsis "Mark duplicates in paired-end SAM files")
15766 (description "Samblaster is a fast and flexible program for marking
15767 duplicates in read-id grouped paired-end SAM files. It can also optionally
15768 output discordant read pairs and/or split read mappings to separate SAM files,
15769 and/or unmapped/clipped reads to a separate FASTQ file. When marking
15770 duplicates, samblaster will require approximately 20MB of memory per 1M read
15772 (license license:expat)))
15774 (define-public r-velocyto
15775 (let ((commit "d7790346cb99f49ab9c2b23ba70dcf9d2c9fc350")
15778 (name "r-velocyto")
15779 (version (git-version "0.6" revision commit))
15783 (uri (git-reference
15784 (url "https://github.com/velocyto-team/velocyto.R")
15786 (file-name (git-file-name name version))
15789 "16wqf70j7rd7pay2q513iyz12i8n9vrpg1bisah4lddbcpx5dz1n"))))
15790 (build-system r-build-system)
15792 `(("boost" ,boost)))
15794 `(("r-hdf5r" ,r-hdf5r)
15797 ("r-pcamethods" ,r-pcamethods)
15799 ("r-rcpparmadillo" ,r-rcpparmadillo)
15800 ;; Suggested packages
15801 ("r-rtsne" ,r-rtsne)
15802 ("r-cluster" ,r-cluster)
15803 ("r-abind" ,r-abind)
15805 ("r-biocgenerics" ,r-biocgenerics)
15806 ("r-genomicalignments" ,r-genomicalignments)
15807 ("r-rsamtools" ,r-rsamtools)
15808 ("r-edger" ,r-edger)
15809 ("r-igraph" ,r-igraph)))
15810 (home-page "https://velocyto.org")
15811 (synopsis "RNA velocity estimation in R")
15813 "This package provides basic routines for estimation of gene-specific
15814 transcriptional derivatives and visualization of the resulting velocity
15816 (license license:gpl3))))
15818 (define-public methyldackel
15820 (name "methyldackel")
15824 (uri (git-reference
15825 (url "https://github.com/dpryan79/MethylDackel")
15827 (file-name (git-file-name name version))
15830 "10gh8k0ca92kywnrw5pkacq3g6r8s976s12k8jhp8g3g49q9a97g"))))
15831 (build-system gnu-build-system)
15833 `(#:test-target "test"
15836 (string-append "prefix="
15837 (assoc-ref %outputs "out") "/bin/"))
15839 (modify-phases %standard-phases
15840 (replace 'configure
15841 (lambda* (#:key outputs #:allow-other-keys)
15842 (substitute* "Makefile"
15843 (("install MethylDackel \\$\\(prefix\\)" match)
15844 (string-append "install -d $(prefix); " match)))
15847 `(("htslib" ,htslib)
15849 ;; Needed for tests
15851 `(("python" ,python-wrapper)))
15852 (home-page "https://github.com/dpryan79/MethylDackel")
15853 (synopsis "Universal methylation extractor for BS-seq experiments")
15855 "MethylDackel will process a coordinate-sorted and indexed BAM or CRAM
15856 file containing some form of BS-seq alignments and extract per-base
15857 methylation metrics from them. MethylDackel requires an indexed fasta file
15858 containing the reference genome as well.")
15859 ;; See https://github.com/dpryan79/MethylDackel/issues/85
15860 (license license:expat)))
15862 (define-public python-gffutils
15863 ;; The latest release is older more than a year than the latest commit
15864 (let ((commit "4034c54600813b1402945e12faa91b3a53162cf1")
15867 (name "python-gffutils")
15868 (version (git-version "0.9" revision commit))
15872 (uri (git-reference
15873 (url "https://github.com/daler/gffutils")
15875 (file-name (git-file-name name version))
15878 "1rwafjdnbir5wnk0ap06ww4lra3p5frhy7mfs03rlldgfnwxymsn"))))
15879 (build-system python-build-system)
15882 (modify-phases %standard-phases
15885 ;; Tests need to access the HOME directory
15886 (setenv "HOME" "/tmp")
15887 (invoke "nosetests" "-a" "!slow")))
15888 (add-after 'unpack 'make-gz-files-writable
15890 (for-each make-file-writable
15891 (find-files "." "\\.gz"))
15894 `(("python-argcomplete" ,python-argcomplete)
15895 ("python-argh" ,python-argh)
15896 ("python-biopython" ,python-biopython)
15897 ("python-pybedtools" ,python-pybedtools)
15898 ("python-pyfaidx" ,python-pyfaidx)
15899 ("python-simplejson" ,python-simplejson)
15900 ("python-six" ,python-six)))
15902 `(("python-nose" , python-nose)))
15903 (home-page "https://github.com/daler/gffutils")
15904 (synopsis "Tool for manipulation of GFF and GTF files")
15906 "python-gffutils is a Python package for working with and manipulating
15907 the GFF and GTF format files typically used for genomic annotations. The
15908 files are loaded into a SQLite database, allowing much more complex
15909 manipulation of hierarchical features (e.g., genes, transcripts, and exons)
15910 than is possible with plain-text methods alone.")
15911 (license license:expat))))
15913 (define-public libsbml
15919 (uri (string-append "mirror://sourceforge/sbml/libsbml/"
15920 version "/stable/libSBML-"
15921 version "-core-src.tar.gz"))
15924 "0slkagrk3nfi2qsksv6b1brj6zhx4bj4bkib2sdycvrcd10ql2lh"))))
15925 (build-system cmake-build-system)
15927 `(#:test-target "test"
15929 (list "-DWITH_CHECK=ON"
15930 (string-append "-DLIBXML_LIBRARY="
15931 (assoc-ref %build-inputs "libxml2")
15933 (string-append "-DLIBXML_INCLUDE_DIR="
15934 (assoc-ref %build-inputs "libxml2")
15935 "/include/libxml2"))))
15937 `(("libxml2" ,libxml2)))
15941 (home-page "http://sbml.org/Software/libSBML")
15942 (synopsis "Process SBML files and data streams")
15943 (description "LibSBML is a library to help you read, write, manipulate,
15944 translate, and validate SBML files and data streams. The @dfn{Systems Biology
15945 Markup Language} (SBML) is an interchange format for computer models of
15946 biological processes. SBML is useful for models of metabolism, cell
15947 signaling, and more. It continues to be evolved and expanded by an
15948 international community.")
15949 (license license:lgpl2.1+)))
15951 (define-public grocsvs
15952 ;; The last release is out of date and new features have been added.
15953 (let ((commit "ecd956a65093a0b2c41849050e4512d46fecea5d")
15957 (version (git-version "0.2.6.1" revision commit))
15960 (uri (git-reference
15961 (url "https://github.com/grocsvs/grocsvs")
15963 (file-name (git-file-name name version))
15965 (base32 "14505725gr7qxc17cxxf0k6lzcwmgi64pija4mwf29aw70qn35cc"))
15966 (patches (search-patches "grocsvs-dont-use-admiral.patch"))))
15967 (build-system python-build-system)
15969 `(#:tests? #f ; No test suite.
15970 #:python ,python-2)) ; Only python-2 supported.
15972 `(("python2-h5py" ,python2-h5py)
15973 ("python2-ipython-cluster-helper" ,python2-ipython-cluster-helper)
15974 ("python2-networkx" ,python2-networkx)
15975 ("python2-psutil" ,python2-psutil)
15976 ("python2-pandas" ,python2-pandas)
15977 ("python2-pybedtools" ,python2-pybedtools)
15978 ("python2-pyfaidx" ,python2-pyfaidx)
15979 ("python2-pygraphviz" ,python2-pygraphviz)
15980 ("python2-pysam" ,python2-pysam)
15981 ("python2-scipy" ,python2-scipy)))
15982 (home-page "https://github.com/grocsvs/grocsvs")
15983 (synopsis "Genome-wide reconstruction of complex structural variants")
15985 "@dfn{Genome-wide Reconstruction of Complex Structural Variants}
15986 (GROC-SVs) is a software pipeline for identifying large-scale structural
15987 variants, performing sequence assembly at the breakpoints, and reconstructing
15988 the complex structural variants using the long-fragment information from the
15989 10x Genomics platform.")
15990 (license license:expat))))