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))))
1649 `(("python-wrapper" ,python-wrapper)
1652 (supported-systems '("x86_64-linux"))
1653 (home-page "http://bowtie-bio.sourceforge.net/index.shtml")
1654 (synopsis "Fast aligner for short nucleotide sequence reads")
1656 "Bowtie is a fast, memory-efficient short read aligner. It aligns short
1657 DNA sequences (reads) to the human genome at a rate of over 25 million 35-bp
1658 reads per hour. Bowtie indexes the genome with a Burrows-Wheeler index to
1659 keep its memory footprint small: typically about 2.2 GB for the human
1660 genome (2.9 GB for paired-end).")
1661 (license license:artistic2.0)))
1663 (define-public tophat
1670 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1674 "19add02kv2xhd6ihd779dr7x35ggym3jqr0m5c4315i1yfb0p11p"))
1675 (modules '((guix build utils)))
1678 ;; Remove bundled SeqAn and samtools
1679 (delete-file-recursively "src/SeqAn-1.4.2")
1680 (delete-file-recursively "src/samtools-0.1.18")
1682 (build-system gnu-build-system)
1684 '(#:parallel-build? #f ; not supported
1686 (modify-phases %standard-phases
1687 (add-after 'set-paths 'hide-default-gcc
1688 (lambda* (#:key inputs #:allow-other-keys)
1689 (let ((gcc (assoc-ref inputs "gcc")))
1690 ;; Remove the default GCC from CPLUS_INCLUDE_PATH to prevent
1691 ;; conflicts with the GCC 5 input.
1692 (setenv "CPLUS_INCLUDE_PATH"
1694 (delete (string-append gcc "/include/c++")
1695 (string-split (getenv "CPLUS_INCLUDE_PATH") #\:))
1698 (add-after 'unpack 'use-system-samtools
1699 (lambda* (#:key inputs #:allow-other-keys)
1700 (substitute* "src/Makefile.in"
1701 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1702 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1703 (("SAMPROG = samtools_0\\.1\\.18") "")
1704 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1705 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1706 (substitute* '("src/common.cpp"
1708 (("samtools_0.1.18") (which "samtools")))
1709 (substitute* '("src/common.h"
1710 "src/bam2fastx.cpp")
1711 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1712 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1713 (substitute* '("src/bwt_map.h"
1715 "src/align_status.h")
1716 (("#include <bam.h>") "#include <samtools/bam.h>")
1717 (("#include <sam.h>") "#include <samtools/sam.h>"))
1720 `(("gcc@5" ,gcc-5))) ;; doesn't build with later versions
1724 ("ncurses" ,ncurses)
1726 ("python" ,python-2)
1727 ("samtools" ,samtools-0.1)
1730 (home-page "https://ccb.jhu.edu/software/tophat/index.shtml")
1731 (synopsis "Spliced read mapper for RNA-Seq data")
1733 "TopHat is a fast splice junction mapper for nucleotide sequence
1734 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1735 mammalian-sized genomes using the ultra high-throughput short read
1736 aligner Bowtie, and then analyzes the mapping results to identify
1737 splice junctions between exons.")
1738 ;; TopHat is released under the Boost Software License, Version 1.0
1739 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1740 (license license:boost1.0)))
1749 "https://github.com/lh3/bwa/releases/download/v"
1750 version "/bwa-" version ".tar.bz2"))
1753 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1754 (build-system gnu-build-system)
1756 '(#:tests? #f ;no "check" target
1758 (modify-phases %standard-phases
1760 (lambda* (#:key outputs #:allow-other-keys)
1761 (let* ((out (assoc-ref outputs "out"))
1762 (bin (string-append out "/bin"))
1763 (lib (string-append out "/lib"))
1764 (doc (string-append out "/share/doc/bwa"))
1765 (man (string-append out "/share/man/man1")))
1766 (install-file "bwa" bin)
1767 (install-file "libbwa.a" lib)
1768 (install-file "README.md" doc)
1769 (install-file "bwa.1" man))
1771 ;; no "configure" script
1772 (delete 'configure))))
1773 (inputs `(("zlib" ,zlib)))
1774 ;; Non-portable SSE instructions are used so building fails on platforms
1775 ;; other than x86_64.
1776 (supported-systems '("x86_64-linux"))
1777 (home-page "http://bio-bwa.sourceforge.net/")
1778 (synopsis "Burrows-Wheeler sequence aligner")
1780 "BWA is a software package for mapping low-divergent sequences against a
1781 large reference genome, such as the human genome. It consists of three
1782 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1783 designed for Illumina sequence reads up to 100bp, while the rest two for
1784 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1785 features such as long-read support and split alignment, but BWA-MEM, which is
1786 the latest, is generally recommended for high-quality queries as it is faster
1787 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1788 70-100bp Illumina reads.")
1789 (license license:gpl3+)))
1791 (define-public bwa-pssm
1792 (package (inherit bwa)
1798 (url "https://github.com/pkerpedjiev/bwa-pssm")
1800 (file-name (git-file-name name version))
1803 "076c4q0cdqz8jgylb067y9zmvxglppnzi3qiscn0xiypgc6lgb5r"))))
1804 (build-system gnu-build-system)
1809 (home-page "http://bwa-pssm.binf.ku.dk/")
1810 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1812 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1813 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1814 existing aligners it is fast and sensitive. Unlike most other aligners,
1815 however, it is also adaptible in the sense that one can direct the alignment
1816 based on known biases within the data set. It is coded as a modification of
1817 the original BWA alignment program and shares the genome index structure as
1818 well as many of the command line options.")
1819 (license license:gpl3+)))
1821 (define-public bwa-meth
1828 (url "https://github.com/brentp/bwa-meth")
1829 (commit (string-append "v" version))))
1830 (file-name (git-file-name name version))
1833 "17j31i7zws5j7mhsq9x3qgkxly6mlmrgwhfq0qbflgxrmx04yaiz"))))
1834 (build-system python-build-system)
1837 (modify-phases %standard-phases
1838 (add-after 'unpack 'keep-references-to-bwa
1839 (lambda* (#:key inputs #:allow-other-keys)
1840 (substitute* "bwameth.py"
1841 (("bwa (mem|index)" _ command)
1842 (string-append (which "bwa") " " command))
1843 ;; There's an ill-advised check for "samtools" on PATH.
1849 `(("python-toolshed" ,python-toolshed)))
1850 (home-page "https://github.com/brentp/bwa-meth")
1851 (synopsis "Fast and accurante alignment of BS-Seq reads")
1853 "BWA-Meth works for single-end reads and for paired-end reads from the
1854 directional protocol (most common). It uses the method employed by
1855 methylcoder and Bismark of in silico conversion of all C's to T's in both
1856 reference and reads. It recovers the original read (needed to tabulate
1857 methylation) by attaching it as a comment which BWA appends as a tag to the
1858 read. It performs favorably to existing aligners gauged by number of on and
1859 off-target reads for a capture method that targets CpG-rich region.")
1860 (license license:expat)))
1862 (define-public python-bx-python
1864 (name "python-bx-python")
1868 (uri (pypi-uri "bx-python" version))
1871 "11kksg2rbzihpmcid823xvg42xi88m7sz58rzk29abybkxy0rszs"))))
1872 (build-system python-build-system)
1873 ;; Tests fail because test data are not included
1874 (arguments '(#:tests? #f))
1876 `(("python-numpy" ,python-numpy)
1877 ("python-six" ,python-six)))
1881 `(("python-lzo" ,python-lzo)
1882 ("python-nose" ,python-nose)
1883 ("python-cython" ,python-cython)))
1884 (home-page "https://github.com/bxlab/bx-python")
1885 (synopsis "Tools for manipulating biological data")
1887 "bx-python provides tools for manipulating biological data, particularly
1888 multiple sequence alignments.")
1889 (license license:expat)))
1891 (define-public python2-bx-python
1892 (package-with-python2 python-bx-python))
1894 (define-public python-pysam
1896 (name "python-pysam")
1900 ;; Test data is missing on PyPi.
1902 (url "https://github.com/pysam-developers/pysam")
1903 (commit (string-append "v" version))))
1904 (file-name (git-file-name name version))
1907 "1vj367w6xbn9bpmksm162l1aipf7cj97h1q83y7jcpm33ihwpf7x"))
1908 (modules '((guix build utils)))
1910 ;; Drop bundled htslib. TODO: Also remove samtools
1912 (delete-file-recursively "htslib")
1914 (build-system python-build-system)
1916 `(#:modules ((ice-9 ftw)
1918 (guix build python-build-system)
1921 (modify-phases %standard-phases
1922 (add-before 'build 'set-flags
1923 (lambda* (#:key inputs #:allow-other-keys)
1924 (setenv "HTSLIB_MODE" "external")
1925 (setenv "HTSLIB_LIBRARY_DIR"
1926 (string-append (assoc-ref inputs "htslib") "/lib"))
1927 (setenv "HTSLIB_INCLUDE_DIR"
1928 (string-append (assoc-ref inputs "htslib") "/include"))
1929 (setenv "LDFLAGS" "-lncurses")
1930 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1933 (lambda* (#:key inputs outputs #:allow-other-keys)
1934 ;; This file contains tests that require a connection to the
1936 (delete-file "tests/tabix_test.py")
1937 ;; FIXME: This test fails
1938 (delete-file "tests/AlignmentFile_test.py")
1939 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1940 (setenv "PYTHONPATH"
1942 (getenv "PYTHONPATH")
1943 ":" (getcwd) "/build/"
1944 (car (scandir "build"
1945 (negate (cut string-prefix? "." <>))))))
1946 ;; Step out of source dir so python does not import from CWD.
1947 (with-directory-excursion "tests"
1948 (setenv "HOME" "/tmp")
1949 (invoke "make" "-C" "pysam_data")
1950 (invoke "make" "-C" "cbcf_data")
1951 ;; Running nosetests without explicitly asking for a single
1952 ;; process leads to a crash. Running with multiple processes
1953 ;; fails because the tests are not designed to run in parallel.
1955 ;; FIXME: tests keep timing out on some systems.
1956 (invoke "nosetests" "-v" "--processes" "1")))))))
1958 `(("htslib" ,htslib))) ; Included from installed header files.
1960 `(("ncurses" ,ncurses)
1964 `(("python-cython" ,python-cython)
1965 ;; Dependencies below are are for tests only.
1966 ("samtools" ,samtools)
1967 ("bcftools" ,bcftools)
1968 ("python-nose" ,python-nose)))
1969 (home-page "https://github.com/pysam-developers/pysam")
1970 (synopsis "Python bindings to the SAMtools C API")
1972 "Pysam is a Python module for reading and manipulating files in the
1973 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1974 also includes an interface for tabix.")
1975 (license license:expat)))
1977 (define-public python2-pysam
1978 (package-with-python2 python-pysam))
1980 (define-public python-twobitreader
1982 (name "python-twobitreader")
1987 (url "https://github.com/benjschiller/twobitreader")
1989 (file-name (git-file-name name version))
1992 "1qbxvv1h58cismbk1anpjrkpghsaiy64a11ir3lhy6qch6xf8n62"))))
1993 (build-system python-build-system)
1994 ;; Tests are not included
1995 (arguments '(#:tests? #f))
1997 `(("python-sphinx" ,python-sphinx)))
1998 (home-page "https://github.com/benjschiller/twobitreader")
1999 (synopsis "Python library for reading .2bit files")
2001 "twobitreader is a Python library for reading .2bit files as used by the
2002 UCSC genome browser.")
2003 (license license:artistic2.0)))
2005 (define-public python2-twobitreader
2006 (package-with-python2 python-twobitreader))
2008 (define-public python-plastid
2010 (name "python-plastid")
2014 (uri (pypi-uri "plastid" version))
2017 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
2018 (build-system python-build-system)
2020 ;; Some test files are not included.
2023 `(("python-numpy" ,python-numpy)
2024 ("python-scipy" ,python-scipy)
2025 ("python-pandas" ,python-pandas)
2026 ("python-pysam" ,python-pysam)
2027 ("python-matplotlib" ,python-matplotlib)
2028 ("python-biopython" ,python-biopython)
2029 ("python-twobitreader" ,python-twobitreader)
2030 ("python-termcolor" ,python-termcolor)))
2032 `(("python-cython" ,python-cython)
2033 ("python-nose" ,python-nose)))
2034 (home-page "https://github.com/joshuagryphon/plastid")
2035 (synopsis "Python library for genomic analysis")
2037 "plastid is a Python library for genomic analysis – in particular,
2038 high-throughput sequencing data – with an emphasis on simplicity.")
2039 (license license:bsd-3)))
2041 (define-public python2-plastid
2042 (package-with-python2 python-plastid))
2044 (define-public tetoolkit
2051 (url "https://github.com/mhammell-laboratory/tetoolkit")
2053 (file-name (git-file-name name version))
2056 "1yzi0kfpzip8zpjb82x1ik6h22yzfyjiz2dv85v6as2awwqvk807"))))
2057 (build-system python-build-system)
2059 `(#:python ,python-2 ; not guaranteed to work with Python 3
2061 (modify-phases %standard-phases
2062 (add-after 'unpack 'make-writable
2064 (for-each make-file-writable (find-files "."))
2066 (add-after 'unpack 'patch-invocations
2067 (lambda* (#:key inputs #:allow-other-keys)
2068 (substitute* '("bin/TEtranscripts"
2071 (string-append "'" (which "sort") " "))
2073 (string-append "'" (which "rm") " -f "))
2074 (("'Rscript'") (string-append "'" (which "Rscript") "'")))
2075 (substitute* "TEToolkit/IO/ReadInputs.py"
2076 (("BamToBED") (which "bamToBed")))
2077 (substitute* "TEToolkit/Normalization.py"
2079 (string-append "\"" (which "Rscript") "\"")))
2081 (add-after 'install 'wrap-program
2082 (lambda* (#:key outputs #:allow-other-keys)
2083 ;; Make sure the executables find R packages.
2084 (let ((out (assoc-ref outputs "out")))
2087 (wrap-program (string-append out "/bin/" script)
2088 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
2093 `(("coreutils" ,coreutils)
2094 ("bedtools" ,bedtools)
2095 ("python-argparse" ,python2-argparse)
2096 ("python-pysam" ,python2-pysam)
2097 ("r-minimal" ,r-minimal)
2098 ("r-deseq2" ,r-deseq2)))
2099 (home-page "https://github.com/mhammell-laboratory/tetoolkit")
2100 (synopsis "Transposable elements in differential enrichment analysis")
2102 "This is package for including transposable elements in differential
2103 enrichment analysis of sequencing datasets. TEtranscripts and TEcount take
2104 RNA-seq (and similar data) and annotates reads to both genes and transposable
2105 elements. TEtranscripts then performs differential analysis using DESeq2.
2106 Note that TEtranscripts and TEcount rely on specially curated GTF files, which
2107 are not included due to their size.")
2108 (license license:gpl3+)))
2110 (define-public cd-hit
2116 (uri (string-append "https://github.com/weizhongli/cdhit"
2117 "/releases/download/V" version
2119 "-2017-0621-source.tar.gz"))
2122 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
2123 (build-system gnu-build-system)
2125 `(#:tests? #f ; there are no tests
2127 ;; Executables are copied directly to the PREFIX.
2128 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin")
2129 ;; Support longer sequences (e.g. Pacbio sequences)
2132 (modify-phases %standard-phases
2133 ;; No "configure" script
2135 ;; Remove sources of non-determinism
2136 (add-after 'unpack 'be-timeless
2138 (substitute* "cdhit-utility.c++"
2139 ((" \\(built on \" __DATE__ \"\\)") ""))
2140 (substitute* "cdhit-common.c++"
2141 (("__DATE__") "\"0\"")
2142 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
2144 ;; The "install" target does not create the target directory.
2145 (add-before 'install 'create-target-dir
2146 (lambda* (#:key outputs #:allow-other-keys)
2147 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
2151 (home-page "http://weizhongli-lab.org/cd-hit/")
2152 (synopsis "Cluster and compare protein or nucleotide sequences")
2154 "CD-HIT is a program for clustering and comparing protein or nucleotide
2155 sequences. CD-HIT is designed to be fast and handle extremely large
2157 ;; The manual says: "It can be copied under the GNU General Public License
2158 ;; version 2 (GPLv2)."
2159 (license license:gpl2)))
2161 (define-public clipper
2168 (url "https://github.com/YeoLab/clipper")
2170 (file-name (git-file-name name version))
2173 "1bcag4lb5bkzsj2vg7lrq24aw6yfgq275ifrbhd82l7kqgbbjbkv"))))
2174 (build-system python-build-system)
2177 (modify-phases %standard-phases
2178 (add-before 'reset-gzip-timestamps 'make-files-writable
2179 (lambda* (#:key outputs #:allow-other-keys)
2180 ;; Make sure .gz files are writable so that the
2181 ;; 'reset-gzip-timestamps' phase can do its work.
2182 (let ((out (assoc-ref outputs "out")))
2183 (for-each make-file-writable
2184 (find-files out "\\.gz$"))
2188 ("python-pybedtools" ,python-pybedtools)
2189 ("python-cython" ,python-cython)
2190 ("python-scikit-learn" ,python-scikit-learn)
2191 ("python-matplotlib" ,python-matplotlib)
2192 ("python-pandas" ,python-pandas)
2193 ("python-pysam" ,python-pysam)
2194 ("python-numpy" ,python-numpy)
2195 ("python-scipy" ,python-scipy)))
2197 `(("python-setuptools-git" ,python-setuptools-git)
2198 ("python-mock" ,python-mock) ; for tests
2199 ("python-nose" ,python-nose) ; for tests
2200 ("python-pytz" ,python-pytz))) ; for tests
2201 (home-page "https://github.com/YeoLab/clipper")
2202 (synopsis "CLIP peak enrichment recognition")
2204 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
2205 (license license:gpl2)))
2207 (define-public codingquarry
2209 (name "codingquarry")
2214 "mirror://sourceforge/codingquarry/CodingQuarry_v"
2218 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
2219 (build-system gnu-build-system)
2221 '(#:tests? #f ; no "check" target
2223 (modify-phases %standard-phases
2226 (lambda* (#:key outputs #:allow-other-keys)
2227 (let* ((out (assoc-ref outputs "out"))
2228 (bin (string-append out "/bin"))
2229 (doc (string-append out "/share/doc/codingquarry")))
2230 (install-file "INSTRUCTIONS.pdf" doc)
2231 (copy-recursively "QuarryFiles"
2232 (string-append out "/QuarryFiles"))
2233 (install-file "CodingQuarry" bin)
2234 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin))
2236 (inputs `(("openmpi" ,openmpi)))
2237 (native-search-paths
2238 (list (search-path-specification
2239 (variable "QUARRY_PATH")
2240 (files '("QuarryFiles")))))
2241 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
2242 (synopsis "Fungal gene predictor")
2243 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
2244 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
2245 (home-page "https://sourceforge.net/projects/codingquarry/")
2246 (license license:gpl3+)))
2248 (define-public couger
2255 "http://couger.oit.duke.edu/static/assets/COUGER"
2259 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
2260 (build-system gnu-build-system)
2264 (modify-phases %standard-phases
2269 (lambda* (#:key outputs #:allow-other-keys)
2270 (let* ((out (assoc-ref outputs "out"))
2271 (bin (string-append out "/bin")))
2272 (copy-recursively "src" (string-append out "/src"))
2274 ;; Add "src" directory to module lookup path.
2275 (substitute* "couger"
2277 (string-append "import sys\nsys.path.append(\""
2278 out "\")\nfrom argparse")))
2279 (install-file "couger" bin))
2282 'install 'wrap-program
2283 (lambda* (#:key inputs outputs #:allow-other-keys)
2284 ;; Make sure 'couger' runs with the correct PYTHONPATH.
2285 (let* ((out (assoc-ref outputs "out"))
2286 (path (getenv "PYTHONPATH")))
2287 (wrap-program (string-append out "/bin/couger")
2288 `("PYTHONPATH" ":" prefix (,path))))
2291 `(("python" ,python-2)
2292 ("python2-pillow" ,python2-pillow)
2293 ("python2-numpy" ,python2-numpy)
2294 ("python2-scipy" ,python2-scipy)
2295 ("python2-matplotlib" ,python2-matplotlib)))
2297 `(("r-minimal" ,r-minimal)
2299 ("randomjungle" ,randomjungle)))
2301 `(("unzip" ,unzip)))
2302 (home-page "http://couger.oit.duke.edu")
2303 (synopsis "Identify co-factors in sets of genomic regions")
2305 "COUGER can be applied to any two sets of genomic regions bound by
2306 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
2307 putative co-factors that provide specificity to each TF. The framework
2308 determines the genomic targets uniquely-bound by each TF, and identifies a
2309 small set of co-factors that best explain the in vivo binding differences
2310 between the two TFs.
2312 COUGER uses classification algorithms (support vector machines and random
2313 forests) with features that reflect the DNA binding specificities of putative
2314 co-factors. The features are generated either from high-throughput TF-DNA
2315 binding data (from protein binding microarray experiments), or from large
2316 collections of DNA motifs.")
2317 (license license:gpl3+)))
2319 (define-public clustal-omega
2321 (name "clustal-omega")
2325 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
2329 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
2330 (build-system gnu-build-system)
2332 `(("argtable" ,argtable)))
2333 (home-page "http://www.clustal.org/omega/")
2334 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
2336 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
2337 program for protein and DNA/RNA. It produces high quality MSAs and is capable
2338 of handling data-sets of hundreds of thousands of sequences in reasonable
2340 (license license:gpl2+)))
2342 (define-public crossmap
2348 (uri (pypi-uri "CrossMap" version))
2351 "1sb2f2qbxya4fzw3yjl09vbrs8vfmw22zrygrvz004sf9gb1vkan"))))
2352 (build-system python-build-system)
2354 `(("python-bx-python" ,python-bx-python)
2355 ("python-numpy" ,python-numpy)
2356 ("python-pybigwig" ,python-pybigwig)
2357 ("python-pysam" ,python-pysam)
2360 `(("python-cython" ,python-cython)
2361 ("python-nose" ,python-nose)))
2362 (home-page "http://crossmap.sourceforge.net/")
2363 (synopsis "Convert genome coordinates between assemblies")
2365 "CrossMap is a program for conversion of genome coordinates or annotation
2366 files between different genome assemblies. It supports most commonly used
2367 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
2368 (license license:gpl2+)))
2370 (define-public python-dnaio
2372 (name "python-dnaio")
2377 (uri (pypi-uri "dnaio" version))
2380 "0f16m7hdlm0fz1n7y5asy0v9ghyrq17ni1p9iybq22ddzyd49r27"))))
2381 (build-system python-build-system)
2383 `(("python-cython" ,python-cython)
2384 ("python-pytest" ,python-pytest)
2385 ("python-xopen" ,python-xopen)))
2386 (home-page "https://github.com/marcelm/dnaio/")
2387 (synopsis "Read FASTA and FASTQ files efficiently")
2389 "dnaio is a Python library for fast parsing of FASTQ and also FASTA
2390 files. The code was previously part of the cutadapt tool.")
2391 (license license:expat)))
2393 (define-public python-deeptoolsintervals
2395 (name "python-deeptoolsintervals")
2399 (uri (pypi-uri "deeptoolsintervals" version))
2402 "1xnl80nblysj6dylj4683wgrfa425rkx4dp5k65hvwdns9pw753x"))))
2403 (build-system python-build-system)
2406 (home-page "https://github.com/deeptools/deeptools_intervals")
2407 (synopsis "Create GTF-based interval trees with associated meta-data")
2409 "This package provides a Python module creating/accessing GTF-based
2410 interval trees with associated meta-data. It is primarily used by the
2411 @code{deeptools} package.")
2412 (license license:expat)))
2414 (define-public python-deeptools
2416 (name "python-deeptools")
2421 (url "https://github.com/deeptools/deepTools")
2423 (file-name (git-file-name name version))
2426 "0l09vyynz6s6w7fnyd94rpys4a6aja6kp4gli64pngdxdz3md1nl"))))
2427 (build-system python-build-system)
2429 `(("python-mock" ,python-mock)
2430 ("python-nose" ,python-nose)))
2432 `(("python-matplotlib" ,python-matplotlib)
2433 ("python-numpy" ,python-numpy)
2434 ("python-numpydoc" ,python-numpydoc)
2435 ("python-py2bit" ,python-py2bit)
2436 ("python-pybigwig" ,python-pybigwig)
2437 ("python-pysam" ,python-pysam)
2438 ("python-scipy" ,python-scipy)
2439 ("python-deeptoolsintervals" ,python-deeptoolsintervals)
2440 ("python-plotly" ,python-plotly-2.4.1)))
2441 (home-page "https://pypi.org/project/deepTools/")
2442 (synopsis "Useful tools for exploring deep sequencing data")
2443 (description "This package addresses the challenge of handling large amounts
2444 of data that are now routinely generated from DNA sequencing centers.
2445 @code{deepTools} contains useful modules to process the mapped reads data for
2446 multiple quality checks, creating normalized coverage files in standard bedGraph
2447 and bigWig file formats, that allow comparison between different files. Finally,
2448 using such normalized and standardized files, deepTools can create many
2449 publication-ready visualizations to identify enrichments and for functional
2450 annotations of the genome.")
2451 ;; The file deeptools/cm.py is licensed under the BSD license. The
2452 ;; remainder of the code is licensed under the MIT license.
2453 (license (list license:bsd-3 license:expat))))
2455 (define-deprecated deeptools python-deeptools)
2457 (define-public cutadapt
2463 (uri (pypi-uri "cutadapt" version))
2466 "1vqmsfkm6llxzmsz9wcfcvzx9a9f8iabvwik2rbyn7nc4wm25z89"))))
2467 (build-system python-build-system)
2469 `(("python-dnaio" ,python-dnaio)
2470 ("python-xopen" ,python-xopen)))
2472 `(("python-cython" ,python-cython)
2473 ("python-pytest" ,python-pytest)
2474 ("python-setuptools-scm" ,python-setuptools-scm)))
2475 (home-page "https://cutadapt.readthedocs.io/en/stable/")
2476 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
2478 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
2479 other types of unwanted sequence from high-throughput sequencing reads.")
2480 (license license:expat)))
2482 (define-public libbigwig
2489 (url "https://github.com/dpryan79/libBigWig")
2491 (file-name (git-file-name name version))
2494 "09693dmf1scdac5pyq6qyn8b4mcipvnmc370k9a5z41z81m3dcsj"))))
2495 (build-system gnu-build-system)
2497 `(#:test-target "test"
2498 #:tests? #f ; tests require access to the web
2501 (string-append "prefix=" (assoc-ref %outputs "out")))
2503 (modify-phases %standard-phases
2504 (delete 'configure))))
2509 `(("doxygen" ,doxygen)
2511 ("python" ,python-2)))
2512 (home-page "https://github.com/dpryan79/libBigWig")
2513 (synopsis "C library for handling bigWig files")
2515 "This package provides a C library for parsing local and remote BigWig
2517 (license license:expat)))
2519 (define-public python-pybigwig
2521 (name "python-pybigwig")
2525 (uri (pypi-uri "pyBigWig" version))
2528 "157x6v48y299zm382krf1dw08fdxg95im8lnabhp5vc94s04zxj1"))
2529 (modules '((guix build utils)))
2532 ;; Delete bundled libBigWig sources
2533 (delete-file-recursively "libBigWig")
2535 (build-system python-build-system)
2538 (modify-phases %standard-phases
2539 (add-after 'unpack 'link-with-libBigWig
2540 (lambda* (#:key inputs #:allow-other-keys)
2541 (substitute* "setup.py"
2542 (("libs=\\[") "libs=[\"BigWig\", "))
2545 `(("python-numpy" ,python-numpy)))
2547 `(("libbigwig" ,libbigwig)
2550 (home-page "https://github.com/dpryan79/pyBigWig")
2551 (synopsis "Access bigWig files in Python using libBigWig")
2553 "This package provides Python bindings to the libBigWig library for
2554 accessing bigWig files.")
2555 (license license:expat)))
2557 (define-public python2-pybigwig
2558 (package-with-python2 python-pybigwig))
2560 (define-public python-dendropy
2562 (name "python-dendropy")
2567 ;; Source from GitHub so that tests are included.
2569 (url "https://github.com/jeetsukumaran/DendroPy")
2570 (commit (string-append "v" version))))
2571 (file-name (git-file-name name version))
2574 "097hfyv2kaf4x92i4rjx0paw2cncxap48qivv8zxng4z7nhid0x9"))))
2575 (build-system python-build-system)
2576 (home-page "https://dendropy.org/")
2577 (synopsis "Library for phylogenetics and phylogenetic computing")
2579 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
2580 writing, simulation, processing and manipulation of phylogenetic
2581 trees (phylogenies) and characters.")
2582 (license license:bsd-3)))
2584 (define-public python2-dendropy
2585 (let ((base (package-with-python2 python-dendropy)))
2590 (modify-phases %standard-phases
2591 (add-after 'unpack 'remove-failing-test
2593 ;; This test fails when the full test suite is run, as documented
2594 ;; at https://github.com/jeetsukumaran/DendroPy/issues/74
2595 (substitute* "tests/test_dataio_nexml_reader_tree_list.py"
2596 (("test_collection_comments_and_annotations")
2597 "do_not_test_collection_comments_and_annotations"))
2599 ,@(package-arguments base))))))
2601 (define-public python-py2bit
2603 (name "python-py2bit")
2608 (uri (pypi-uri "py2bit" version))
2611 "1vw2nvw1yrl7ikkqsqs1pg239yr5nspvd969r1x9arms1k25a1a5"))))
2612 (build-system python-build-system)
2613 (home-page "https://github.com/dpryan79/py2bit")
2614 (synopsis "Access 2bit files using lib2bit")
2616 "This package provides Python bindings for lib2bit to access 2bit files
2618 (license license:expat)))
2620 (define-public delly
2627 (url "https://github.com/dellytools/delly")
2628 (commit (string-append "v" version))))
2629 (file-name (git-file-name name version))
2631 (base32 "034jqsxswy9gqdh2zkgc1js99qkv75ks4xvzgmh0284sraagv61z"))
2632 (modules '((guix build utils)))
2635 (delete-file-recursively "src/htslib")
2637 (build-system gnu-build-system)
2639 `(#:tests? #f ; There are no tests to run.
2641 (list "PARALLEL=1" ; Allow parallel execution at run-time.
2642 (string-append "prefix=" (assoc-ref %outputs "out")))
2644 (modify-phases %standard-phases
2645 (delete 'configure) ; There is no configure phase.
2646 (add-after 'install 'install-templates
2647 (lambda* (#:key outputs #:allow-other-keys)
2648 (let ((templates (string-append (assoc-ref outputs "out")
2649 "/share/delly/templates")))
2651 (copy-recursively "excludeTemplates" templates)
2658 (home-page "https://github.com/dellytools/delly")
2659 (synopsis "Integrated structural variant prediction method")
2660 (description "Delly is an integrated structural variant prediction method
2661 that can discover and genotype deletions, tandem duplications, inversions and
2662 translocations at single-nucleotide resolution in short-read massively parallel
2663 sequencing data. It uses paired-ends and split-reads to sensitively and
2664 accurately delineate genomic rearrangements throughout the genome.")
2665 (license license:gpl3+)))
2667 (define-public diamond
2674 (url "https://github.com/bbuchfink/diamond")
2675 (commit (string-append "v" version))))
2676 (file-name (git-file-name name version))
2679 "0k6f3kb6cniw11xw6763kkbs1sl0yack7xsy7q5fl5v170ssphq4"))))
2680 (build-system cmake-build-system)
2682 '(#:tests? #f ; no "check" target
2684 (modify-phases %standard-phases
2685 (add-after 'unpack 'remove-native-compilation
2687 (substitute* "CMakeLists.txt" (("-march=native") ""))
2691 (home-page "https://github.com/bbuchfink/diamond")
2692 (synopsis "Accelerated BLAST compatible local sequence aligner")
2694 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2695 translated DNA query sequences against a protein reference database (BLASTP
2696 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2697 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2698 data and settings.")
2699 (license license:agpl3+)))
2701 (define-public discrover
2709 (url "https://github.com/maaskola/discrover")
2711 (file-name (git-file-name name version))
2714 "173fwi2vb6a5kp406hm3jj6j7v4whww796f2qcygp4rpvamh307y"))))
2715 (build-system cmake-build-system)
2717 `(#:tests? #f ; there are no tests
2719 (modify-phases %standard-phases
2720 (add-after 'unpack 'fix-latex-errors
2722 (with-fluids ((%default-port-encoding #f))
2723 (substitute* "doc/references.bib"
2724 (("\\{S\\}illanp[^,]+,")
2725 "{S}illanp{\\\"a}{\\\"a},")))
2726 ;; XXX: I just can't get pdflatex to not complain about these
2727 ;; characters. They end up in the manual via the generated
2728 ;; discrover-cli-help.txt.
2729 (substitute* "src/hmm/cli.cpp"
2733 ;; This seems to be a syntax error.
2734 (substitute* "doc/discrover-manual.tex"
2735 (("theverbbox\\[t\\]") "theverbbox"))
2737 (add-after 'unpack 'add-missing-includes
2739 (substitute* "src/executioninformation.hpp"
2740 (("#define EXECUTIONINFORMATION_HPP" line)
2741 (string-append line "\n#include <random>")))
2742 (substitute* "src/plasma/fasta.hpp"
2743 (("#define FASTA_HPP" line)
2744 (string-append line "\n#include <random>")))
2746 ;; FIXME: this is needed because we're using texlive-union, which
2747 ;; doesn't handle fonts correctly. It expects to be able to generate
2748 ;; fonts in the home directory.
2749 (add-before 'build 'setenv-HOME
2750 (lambda _ (setenv "HOME" "/tmp") #t)))))
2754 ("rmath-standalone" ,rmath-standalone)))
2756 `(("texlive" ,(texlive-union (list texlive-fonts-cm
2757 texlive-fonts-amsfonts
2760 texlive-latex-examplep
2761 texlive-latex-hyperref
2763 texlive-latex-natbib
2764 texlive-bibtex ; style files used by natbib
2765 texlive-latex-pgf ; tikz
2766 texlive-latex-verbatimbox)))
2767 ("imagemagick" ,imagemagick)))
2768 (home-page "https://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2769 (synopsis "Discover discriminative nucleotide sequence motifs")
2770 (description "Discrover is a motif discovery method to find binding sites
2771 of nucleic acid binding proteins.")
2772 (license license:gpl3+)))
2774 (define-public eigensoft
2782 (url "https://github.com/DReichLab/EIG")
2783 (commit (string-append "v" version))))
2784 (file-name (git-file-name name version))
2787 "1c141fqvhnzibmnf22sv23vbmzm20kjjyrib44cfh75wyndp2d9k"))
2788 (modules '((guix build utils)))
2789 ;; Remove pre-built binaries.
2791 (delete-file-recursively "bin")
2794 (build-system gnu-build-system)
2796 `(#:tests? #f ; There are no tests.
2797 #:make-flags '("CC=gcc")
2799 (modify-phases %standard-phases
2800 ;; There is no configure phase, but the Makefile is in a
2803 (lambda _ (chdir "src") #t))
2804 ;; The provided install target only copies executables to
2805 ;; the "bin" directory in the build root.
2806 (add-after 'install 'actually-install
2807 (lambda* (#:key outputs #:allow-other-keys)
2808 (let* ((out (assoc-ref outputs "out"))
2809 (bin (string-append out "/bin")))
2810 (for-each (lambda (file)
2811 (install-file file bin))
2812 (find-files "../bin" ".*"))
2817 ("openblas" ,openblas)
2819 ("gfortran" ,gfortran "lib")))
2820 (home-page "https://github.com/DReichLab/EIG")
2821 (synopsis "Tools for population genetics")
2822 (description "The EIGENSOFT package provides tools for population
2823 genetics and stratification correction. EIGENSOFT implements methods commonly
2824 used in population genetics analyses such as PCA, computation of Tracy-Widom
2825 statistics, and finding related individuals in structured populations. It
2826 comes with a built-in plotting script and supports multiple file formats and
2827 quantitative phenotypes.")
2828 ;; The license of the eigensoft tools is Expat, but since it's
2829 ;; linking with the GNU Scientific Library (GSL) the effective
2830 ;; license is the GPL.
2831 (license license:gpl3+)))
2833 (define-public edirect
2836 (version "13.3.20200128")
2839 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect"
2840 "/versions/" version
2841 "/edirect-" version ".tar.gz"))
2844 "093zp7klv81ph0y8mm8d78a9hnpfxbv2kdym70gzdf3vz176rw33"))
2845 (modules '((guix build utils)))
2847 '(begin (delete-file "Mozilla-CA.tar.gz")
2848 (substitute* "rchive.go"
2849 ;; This go library does not have any license.
2850 (("github.com/fiam/gounidecode/unidecode")
2851 "golang.org/rainycape/unidecode"))
2853 (build-system perl-build-system)
2856 (modify-phases %standard-phases
2859 (delete 'check) ; simple check after install
2860 (add-after 'unpack 'patch-programs
2861 (lambda* (#:key inputs #:allow-other-keys)
2862 ;; Ignore errors about missing xtract.Linux and rchive.Linux.
2863 (substitute* "pm-refresh"
2864 (("cat \\\"\\$target")
2865 "grep ^[[:digit:]] \"$target"))
2868 (lambda* (#:key inputs outputs #:allow-other-keys)
2869 (let ((bin (string-append (assoc-ref outputs "out") "/bin"))
2870 (edirect-go (assoc-ref inputs "edirect-go-programs")))
2873 (install-file file bin))
2874 '("archive-pubmed" "asp-cp" "asp-ls" "download-ncbi-data"
2875 "download-pubmed" "edirect.pl" "efetch" "epost" "esearch"
2876 "fetch-pubmed" "ftp-cp" "ftp-ls" "has-asp" "index-pubmed"
2877 "pm-prepare" "pm-refresh" "pm-stash" "pm-collect"
2878 "pm-index" "pm-invert" "pm-merge" "pm-promote"))
2879 (symlink (string-append edirect-go "/bin/xtract.Linux")
2880 (string-append bin "/xtract"))
2881 (symlink (string-append edirect-go "/bin/rchive.Linux")
2882 (string-append bin "/rchive")))
2884 (add-after 'install 'wrap-program
2885 (lambda* (#:key outputs #:allow-other-keys)
2886 ;; Make sure everything can run in a pure environment.
2887 (let ((out (assoc-ref outputs "out"))
2888 (path (getenv "PERL5LIB")))
2892 `("PERL5LIB" ":" prefix (,path)))
2894 `("PATH" ":" prefix (,(string-append out "/bin")
2895 ,(dirname (which "sed"))
2896 ,(dirname (which "gzip"))
2897 ,(dirname (which "grep"))
2898 ,(dirname (which "perl"))
2899 ,(dirname (which "uname"))))))
2900 (find-files out ".")))
2902 (add-after 'wrap-program 'check
2903 (lambda* (#:key outputs #:allow-other-keys)
2904 (invoke (string-append (assoc-ref outputs "out")
2909 `(("edirect-go-programs" ,edirect-go-programs)
2910 ("perl-html-parser" ,perl-html-parser)
2911 ("perl-encode-locale" ,perl-encode-locale)
2912 ("perl-file-listing" ,perl-file-listing)
2913 ("perl-html-tagset" ,perl-html-tagset)
2914 ("perl-html-tree" ,perl-html-tree)
2915 ("perl-http-cookies" ,perl-http-cookies)
2916 ("perl-http-date" ,perl-http-date)
2917 ("perl-http-message" ,perl-http-message)
2918 ("perl-http-negotiate" ,perl-http-negotiate)
2919 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2920 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2921 ("perl-net-http" ,perl-net-http)
2922 ("perl-uri" ,perl-uri)
2923 ("perl-www-robotrules" ,perl-www-robotrules)
2924 ("perl-xml-simple" ,perl-xml-simple)
2926 (home-page "https://www.ncbi.nlm.nih.gov/books/NBK179288/")
2927 (synopsis "Tools for accessing the NCBI's set of databases")
2929 "Entrez Direct (EDirect) is a method for accessing the National Center
2930 for Biotechnology Information's (NCBI) set of interconnected
2931 databases (publication, sequence, structure, gene, variation, expression,
2932 etc.) from a terminal. Functions take search terms from command-line
2933 arguments. Individual operations are combined to build multi-step queries.
2934 Record retrieval and formatting normally complete the process.
2936 EDirect also provides an argument-driven function that simplifies the
2937 extraction of data from document summaries or other results that are returned
2938 in structured XML format. This can eliminate the need for writing custom
2939 software to answer ad hoc questions.")
2940 (native-search-paths
2941 ;; Ideally this should be set for LWP somewhere.
2942 (list (search-path-specification
2943 (variable "PERL_LWP_SSL_CA_FILE")
2944 (file-type 'regular)
2946 (files '("/etc/ssl/certs/ca-certificates.crt")))))
2947 (license license:public-domain)))
2949 (define-public edirect-go-programs
2952 (name "edirect-go-programs")
2953 (build-system go-build-system)
2955 `(#:install-source? #f
2956 #:tests? #f ; No tests.
2957 #:import-path "ncbi.nlm.nih.gov/entrez/edirect"
2959 (modify-phases %standard-phases
2961 (lambda* (#:key import-path #:allow-other-keys)
2962 (with-directory-excursion (string-append "src/" import-path)
2963 (invoke "go" "build" "-v" "-x" "j2x.go")
2964 (invoke "go" "build" "-v" "-x" "t2x.go")
2965 (invoke "go" "build" "-v" "-x" "-o"
2966 "xtract.Linux" "xtract.go" "common.go")
2967 (invoke "go" "build" "-v" "-x" "-o"
2968 "rchive.Linux" "rchive.go" "common.go")
2969 (invoke "go" "build" "-v" "-x" "-o" "symbols.Linux" "s2p.go"))))
2971 (lambda* (#:key outputs import-path #:allow-other-keys)
2972 (let ((dest (string-append (assoc-ref outputs "out") "/bin"))
2973 (source (string-append "src/" import-path "/")))
2974 (for-each (lambda (file)
2975 (format #t "installing ~a~%" file)
2976 (install-file (string-append source file) dest))
2977 '("j2x" "t2x" "symbols.Linux" "xtract.Linux" "rchive.Linux"))
2980 (propagated-inputs '())
2982 `(("go-github-com-fatih-color" ,go-github-com-fatih-color)
2983 ("go-github-com-fogleman-gg" ,go-github-com-fogleman-gg)
2984 ("go-github-com-gedex-inflector" ,go-github-com-gedex-inflector)
2985 ("go-github-com-golang-freetype" ,go-github-com-golang-freetype)
2986 ("go-github-com-klauspost-cpuid" ,go-github-com-klauspost-cpuid)
2987 ("go-github-com-pbnjay-memory" ,go-github-com-pbnjay-memory)
2988 ("go-github-com-surgebase-porter2" ,go-github-com-surgebase-porter2)
2989 ("go-golang-org-rainycape-unidecode" ,go-golang-org-rainycape-unidecode)
2990 ("go-golang-org-x-image" ,go-golang-org-x-image)
2991 ("go-golang-org-x-text" ,go-golang-org-x-text)))))
2993 (define-public exonerate
3002 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
3003 "exonerate-" version ".tar.gz"))
3006 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
3007 (build-system gnu-build-system)
3009 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
3011 `(("pkg-config" ,pkg-config)))
3015 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
3016 (synopsis "Generic tool for biological sequence alignment")
3018 "Exonerate is a generic tool for pairwise sequence comparison. It allows
3019 the alignment of sequences using a many alignment models, either exhaustive
3020 dynamic programming or a variety of heuristics.")
3021 (license license:gpl3)))
3023 (define-public express
3030 (url "https://github.com/adarob/eXpress")
3032 (file-name (git-file-name name version))
3035 "18nb22n7x820fzjngf4qgyb3mspqkw7xyk7v7s5ps6wfrd8qwscb"))))
3036 (build-system cmake-build-system)
3038 `(#:tests? #f ;no "check" target
3040 (modify-phases %standard-phases
3041 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
3042 (lambda* (#:key inputs #:allow-other-keys)
3043 (substitute* "CMakeLists.txt"
3044 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
3045 "set(Boost_USE_STATIC_LIBS OFF)")
3046 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
3047 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
3048 (substitute* "src/CMakeLists.txt"
3049 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
3050 (string-append (assoc-ref inputs "bamtools") "/lib"))
3051 (("libprotobuf.a") "libprotobuf.so"))
3053 (add-after 'unpack 'remove-update-check
3055 (substitute* "src/main.cpp"
3056 (("#include \"update_check.h\"") "")
3057 (("check_version\\(PACKAGE_VERSION\\);") ""))
3061 ("bamtools" ,bamtools)
3062 ("protobuf" ,protobuf)
3064 (home-page "http://bio.math.berkeley.edu/eXpress")
3065 (synopsis "Streaming quantification for high-throughput genomic sequencing")
3067 "eXpress is a streaming tool for quantifying the abundances of a set of
3068 target sequences from sampled subsequences. Example applications include
3069 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
3070 analysis (from RNA-Seq), transcription factor binding quantification in
3071 ChIP-Seq, and analysis of metagenomic data.")
3072 (license license:artistic2.0)))
3074 (define-public express-beta-diversity
3076 (name "express-beta-diversity")
3081 (url "https://github.com/dparks1134/ExpressBetaDiversity")
3082 (commit (string-append "v" version))))
3083 (file-name (git-file-name name version))
3086 "0s0yzg5c21349rh7x4w9266jsvnp7j1hp9cf8sk32hz8nvrj745x"))))
3087 (build-system gnu-build-system)
3090 (modify-phases %standard-phases
3092 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
3094 (lambda _ (invoke "../bin/ExpressBetaDiversity" "-u") #t))
3096 (lambda* (#:key outputs #:allow-other-keys)
3097 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3098 (install-file "../scripts/convertToEBD.py" bin)
3099 (install-file "../bin/ExpressBetaDiversity" bin)
3102 `(("python" ,python-2)))
3103 (home-page "https://github.com/dparks1134/ExpressBetaDiversity")
3104 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
3106 "Express Beta Diversity (EBD) calculates ecological beta diversity
3107 (dissimilarity) measures between biological communities. EBD implements a
3108 variety of diversity measures including those that make use of phylogenetic
3109 similarity of community members.")
3110 (license license:gpl3+)))
3112 (define-public fasttree
3119 "http://www.microbesonline.org/fasttree/FastTree-"
3123 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
3124 (build-system gnu-build-system)
3126 `(#:tests? #f ; no "check" target
3128 (modify-phases %standard-phases
3132 (lambda* (#:key source #:allow-other-keys)
3135 "-finline-functions"
3146 "-finline-functions"
3155 (lambda* (#:key outputs #:allow-other-keys)
3156 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3157 (install-file "FastTree" bin)
3158 (install-file "FastTreeMP" bin)
3160 (home-page "http://www.microbesonline.org/fasttree")
3161 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
3163 "FastTree can handle alignments with up to a million of sequences in a
3164 reasonable amount of time and memory. For large alignments, FastTree is
3165 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
3166 (license license:gpl2+)))
3168 (define-public fastx-toolkit
3170 (name "fastx-toolkit")
3176 "https://github.com/agordon/fastx_toolkit/releases/download/"
3177 version "/fastx_toolkit-" version ".tar.bz2"))
3180 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
3181 (build-system gnu-build-system)
3183 `(("libgtextutils" ,libgtextutils)))
3185 `(("gcc" ,gcc-6) ;; doesn't build with later versions
3186 ("pkg-config" ,pkg-config)))
3187 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
3188 (synopsis "Tools for FASTA/FASTQ file preprocessing")
3190 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
3191 FASTA/FASTQ files preprocessing.
3193 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
3194 containing multiple short-reads sequences. The main processing of such
3195 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
3196 is sometimes more productive to preprocess the files before mapping the
3197 sequences to the genome---manipulating the sequences to produce better mapping
3198 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
3199 (license license:agpl3+)))
3201 (define-public flexbar
3208 (url "https://github.com/seqan/flexbar")
3209 (commit (string-append "v" version))))
3210 (file-name (git-file-name name version))
3213 "1pq9sxvdnldl14libk234m72dqhwgzs3acgl943wchwdqlcsi5r2"))))
3214 (build-system cmake-build-system)
3217 (modify-phases %standard-phases
3218 (add-after 'unpack 'do-not-tune-to-CPU
3220 (substitute* "src/CMakeLists.txt"
3221 ((" -march=native") ""))
3224 (lambda* (#:key outputs #:allow-other-keys)
3225 (setenv "PATH" (string-append (getcwd) ":" (getenv "PATH")))
3226 (with-directory-excursion "../source/test"
3227 (invoke "bash" "flexbar_test.sh"))
3230 (lambda* (#:key outputs #:allow-other-keys)
3231 (let* ((out (string-append (assoc-ref outputs "out")))
3232 (bin (string-append out "/bin/")))
3233 (install-file "flexbar" bin))
3239 `(("pkg-config" ,pkg-config)
3241 (home-page "https://github.com/seqan/flexbar")
3242 (synopsis "Barcode and adapter removal tool for sequencing platforms")
3244 "Flexbar preprocesses high-throughput nucleotide sequencing data
3245 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
3246 Moreover, trimming and filtering features are provided. Flexbar increases
3247 read mapping rates and improves genome and transcriptome assemblies. It
3248 supports next-generation sequencing data in fasta/q and csfasta/q format from
3249 Illumina, Roche 454, and the SOLiD platform.")
3250 (license license:bsd-3)))
3252 (define-public fraggenescan
3254 (name "fraggenescan")
3260 (string-append "mirror://sourceforge/fraggenescan/"
3261 "FragGeneScan" version ".tar.gz"))
3263 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
3264 (build-system gnu-build-system)
3267 (modify-phases %standard-phases
3269 (add-before 'build 'patch-paths
3270 (lambda* (#:key outputs #:allow-other-keys)
3271 (let* ((out (string-append (assoc-ref outputs "out")))
3272 (share (string-append out "/share/fraggenescan/")))
3273 (substitute* "run_FragGeneScan.pl"
3275 (string-append "system(\"" (which "rm")))
3277 (string-append "system(\"" (which "mv")))
3278 (("\\\"awk") (string-append "\"" (which "awk")))
3279 ;; This script and other programs expect the training files
3280 ;; to be in the non-standard location bin/train/XXX. Change
3281 ;; this to be share/fraggenescan/train/XXX instead.
3282 (("^\\$train.file = \\$dir.*")
3283 (string-append "$train_file = \""
3285 "train/\".$FGS_train_file;")))
3286 (substitute* "run_hmm.c"
3287 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
3288 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
3292 (invoke "make" "clean")
3293 (invoke "make" "fgs")
3296 (lambda* (#:key outputs #:allow-other-keys)
3297 (let* ((out (string-append (assoc-ref outputs "out")))
3298 (bin (string-append out "/bin/"))
3299 (share (string-append out "/share/fraggenescan/train")))
3300 (install-file "run_FragGeneScan.pl" bin)
3301 (install-file "FragGeneScan" bin)
3302 (copy-recursively "train" share))
3305 (add-after 'install 'post-install-check
3306 ;; In lieu of 'make check', run one of the examples and check the
3307 ;; output files gets created.
3308 (lambda* (#:key outputs #:allow-other-keys)
3309 (let* ((out (string-append (assoc-ref outputs "out")))
3310 (bin (string-append out "/bin/"))
3311 (frag (string-append bin "run_FragGeneScan.pl")))
3312 ;; Test complete genome.
3314 "-genome=./example/NC_000913.fna"
3318 (unless (and (file-exists? "test2.faa")
3319 (file-exists? "test2.ffn")
3320 (file-exists? "test2.gff")
3321 (file-exists? "test2.out"))
3322 (error "Expected files do not exist."))
3323 ;; Test incomplete sequences.
3325 "-genome=./example/NC_000913-fgs.ffn"
3332 ("python" ,python-2))) ;not compatible with python 3.
3333 (home-page "https://sourceforge.net/projects/fraggenescan/")
3334 (synopsis "Finds potentially fragmented genes in short reads")
3336 "FragGeneScan is a program for predicting bacterial and archaeal genes in
3337 short and error-prone DNA sequencing reads. It can also be applied to predict
3338 genes in incomplete assemblies or complete genomes.")
3339 ;; GPL3+ according to private correspondense with the authors.
3340 (license license:gpl3+)))
3342 (define-public fxtract
3343 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
3351 (url "https://github.com/ctSkennerton/fxtract")
3353 (file-name (git-file-name name version))
3356 "0hab3gpwf4w9s87qlbswq6ws1qqybh4dcqk79q1ahyldzai5fgp5"))))
3357 (build-system gnu-build-system)
3359 `(#:make-flags (list
3360 (string-append "PREFIX=" (assoc-ref %outputs "out"))
3362 #:test-target "fxtract_test"
3364 (modify-phases %standard-phases
3366 (add-before 'build 'copy-util
3367 (lambda* (#:key inputs #:allow-other-keys)
3369 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
3371 ;; Do not use make install as this requires additional dependencies.
3373 (lambda* (#:key outputs #:allow-other-keys)
3374 (let* ((out (assoc-ref outputs "out"))
3375 (bin (string-append out"/bin")))
3376 (install-file "fxtract" bin)
3382 ;; ctskennerton-util is licensed under GPL2.
3383 `(("ctskennerton-util"
3387 (url "https://github.com/ctSkennerton/util")
3388 (commit util-commit)))
3389 (file-name (string-append
3390 "ctstennerton-util-" util-commit "-checkout"))
3393 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
3394 (home-page "https://github.com/ctSkennerton/fxtract")
3395 (synopsis "Extract sequences from FASTA and FASTQ files")
3397 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
3398 or FASTQ) file given a subsequence. It uses a simple substring search for
3399 basic tasks but can change to using POSIX regular expressions, PCRE, hash
3400 lookups or multi-pattern searching as required. By default fxtract looks in
3401 the sequence of each record but can also be told to look in the header,
3402 comment or quality sections.")
3403 ;; 'util' requires SSE instructions.
3404 (supported-systems '("x86_64-linux"))
3405 (license license:expat))))
3407 (define-public gemma
3414 (url "https://github.com/xiangzhou/GEMMA")
3415 (commit (string-append "v" version))))
3416 (file-name (git-file-name name version))
3419 "1s3ncnbn45r2hh1cvrqky1kbqq6546biypr4f5mkw1kqlrgyh0yg"))))
3422 ("gfortran" ,gfortran "lib")
3425 ("openblas" ,openblas)
3427 (build-system gnu-build-system)
3430 '(,@(match (%current-system)
3432 '("FORCE_DYNAMIC=1"))
3434 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
3436 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
3438 (modify-phases %standard-phases
3440 (add-after 'unpack 'find-eigen
3441 (lambda* (#:key inputs #:allow-other-keys)
3442 ;; Ensure that Eigen headers can be found
3443 (setenv "CPLUS_INCLUDE_PATH"
3444 (string-append (assoc-ref inputs "eigen")
3447 (add-before 'build 'bin-mkdir
3452 (lambda* (#:key outputs #:allow-other-keys)
3453 (let ((out (assoc-ref outputs "out")))
3454 (install-file "bin/gemma"
3458 #:tests? #f)) ; no tests included yet
3459 (home-page "https://github.com/xiangzhou/GEMMA")
3460 (synopsis "Tool for genome-wide efficient mixed model association")
3462 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
3463 standard linear mixed model resolver with application in genome-wide
3464 association studies (GWAS).")
3465 (license license:gpl3)))
3474 (url "https://github.com/nboley/grit")
3476 (file-name (git-file-name name version))
3479 "1l5v8vfvfbrpmgnrvbrbv40d0arhxcnmxgv2f1mlcqfa3q6bkqm9"))))
3480 (build-system python-build-system)
3482 `(#:python ,python-2
3484 (modify-phases %standard-phases
3485 (add-after 'unpack 'generate-from-cython-sources
3486 (lambda* (#:key inputs outputs #:allow-other-keys)
3487 ;; Delete these C files to force fresh generation from pyx sources.
3488 (delete-file "grit/sparsify_support_fns.c")
3489 (delete-file "grit/call_peaks_support_fns.c")
3490 (substitute* "setup.py"
3491 (("Cython.Setup") "Cython.Build"))
3494 `(("python-scipy" ,python2-scipy)
3495 ("python-numpy" ,python2-numpy)
3496 ("python-pysam" ,python2-pysam)
3497 ("python-networkx" ,python2-networkx)))
3499 `(("python-cython" ,python2-cython)))
3500 ;; The canonical <http://grit-bio.org> home page times out as of 2020-01-21.
3501 (home-page "https://github.com/nboley/grit")
3502 (synopsis "Tool for integrative analysis of RNA-seq type assays")
3504 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
3505 full length transcript models. When none of these data sources are available,
3506 GRIT can be run by providing a candidate set of TES or TSS sites. In
3507 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
3508 also be run in quantification mode, where it uses a provided GTF file and just
3509 estimates transcript expression.")
3510 (license license:gpl3+)))
3512 (define-public hisat
3519 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
3520 version "-beta-source.zip"))
3523 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
3524 (build-system gnu-build-system)
3526 `(#:tests? #f ;no check target
3527 #:make-flags '("allall"
3528 ;; Disable unsupported `popcnt' instructions on
3529 ;; architectures other than x86_64
3530 ,@(if (string-prefix? "x86_64"
3531 (or (%current-target-system)
3534 '("POPCNT_CAPABILITY=0")))
3536 (modify-phases %standard-phases
3537 (add-after 'unpack 'patch-sources
3539 ;; XXX Cannot use snippet because zip files are not supported
3540 (substitute* "Makefile"
3541 (("^CC = .*$") "CC = gcc")
3542 (("^CPP = .*$") "CPP = g++")
3543 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
3544 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
3545 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
3546 (substitute* '("hisat-build" "hisat-inspect")
3547 (("/usr/bin/env") (which "env")))
3550 (lambda* (#:key outputs #:allow-other-keys)
3551 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
3552 (for-each (lambda (file)
3553 (install-file file bin))
3556 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
3558 (delete 'configure))))
3560 `(("unzip" ,unzip)))
3565 ;; Non-portable SSE instructions are used so building fails on platforms
3566 ;; other than x86_64.
3567 (supported-systems '("x86_64-linux"))
3568 (home-page "https://ccb.jhu.edu/software/hisat/index.shtml")
3569 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
3571 "HISAT is a fast and sensitive spliced alignment program for mapping
3572 RNA-seq reads. In addition to one global FM index that represents a whole
3573 genome, HISAT uses a large set of small FM indexes that collectively cover the
3574 whole genome. These small indexes (called local indexes) combined with
3575 several alignment strategies enable effective alignment of RNA-seq reads, in
3576 particular, reads spanning multiple exons.")
3577 (license license:gpl3+)))
3579 (define-public hisat2
3586 (uri (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
3587 "/downloads/hisat2-" version "-source.zip"))
3590 "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"))))
3591 (build-system gnu-build-system)
3593 `(#:tests? #f ; no check target
3594 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
3595 #:modules ((guix build gnu-build-system)
3599 (modify-phases %standard-phases
3600 (add-after 'unpack 'make-deterministic
3602 (substitute* "Makefile"
3607 (lambda* (#:key outputs #:allow-other-keys)
3608 (let* ((out (assoc-ref outputs "out"))
3609 (bin (string-append out "/bin/"))
3610 (doc (string-append out "/share/doc/hisat2/")))
3612 (cut install-file <> bin)
3614 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
3616 (install-file "doc/manual.inc.html" doc))
3619 `(("unzip" ,unzip) ; needed for archive from ftp
3621 ("pandoc" ,pandoc))) ; for documentation
3622 (home-page "https://ccb.jhu.edu/software/hisat2/index.shtml")
3623 (synopsis "Graph-based alignment of genomic sequencing reads")
3624 (description "HISAT2 is a fast and sensitive alignment program for mapping
3625 next-generation sequencing reads (both DNA and RNA) to a population of human
3626 genomes (as well as to a single reference genome). In addition to using one
3627 global @dfn{graph FM} (GFM) index that represents a population of human
3628 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
3629 the whole genome. These small indexes, combined with several alignment
3630 strategies, enable rapid and accurate alignment of sequencing reads. This new
3631 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
3632 ;; HISAT2 contains files from Bowtie2, which is released under
3633 ;; GPLv2 or later. The HISAT2 source files are released under
3635 (license license:gpl3+)))
3637 (define-public hmmer
3645 "http://eddylab.org/software/hmmer/hmmer-" version ".tar.gz"))
3648 "171bivy6xhgjsz5nv53n81pc3frnwz29ylblawk2bv46szwjjqd5"))))
3649 (build-system gnu-build-system)
3650 (native-inputs `(("perl" ,perl)))
3651 (home-page "http://hmmer.org/")
3652 (synopsis "Biosequence analysis using profile hidden Markov models")
3654 "HMMER is used for searching sequence databases for homologs of protein
3655 sequences, and for making protein sequence alignments. It implements methods
3656 using probabilistic models called profile hidden Markov models (profile
3658 ;; hmmer uses non-portable SSE intrinsics so building fails on other
3660 (supported-systems '("x86_64-linux" "i686-linux"))
3661 (license license:bsd-3)))
3663 (define-public htseq
3669 (uri (pypi-uri "HTSeq" version))
3672 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
3673 (build-system python-build-system)
3675 `(("python-cython" ,python-cython)))
3676 ;; Numpy needs to be propagated when htseq is used as a Python library.
3678 `(("python-numpy" ,python-numpy)))
3680 `(("python-pysam" ,python-pysam)
3681 ("python-matplotlib" ,python-matplotlib)))
3682 (home-page "https://htseq.readthedocs.io/")
3683 (synopsis "Analysing high-throughput sequencing data with Python")
3685 "HTSeq is a Python package that provides infrastructure to process data
3686 from high-throughput sequencing assays.")
3687 (license license:gpl3+)))
3689 (define-public python2-htseq
3690 (package-with-python2 htseq))
3692 (define-public java-htsjdk
3694 (name "java-htsjdk")
3695 (version "2.3.0") ; last version without build dependency on gradle
3699 (url "https://github.com/samtools/htsjdk")
3701 (file-name (git-file-name name version))
3704 "1b178ixcabanm834ydjl3jiakpyxdmki32hqfv2abrzn3rcwa28i"))
3705 (modules '((guix build utils)))
3707 ;; Delete pre-built binaries
3709 (delete-file-recursively "lib")
3712 (build-system ant-build-system)
3714 `(#:tests? #f ; test require Internet access
3717 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3718 "/share/java/htsjdk/"))
3719 #:build-target "all"
3721 (modify-phases %standard-phases
3722 ;; The build phase also installs the jars
3723 (delete 'install))))
3725 `(("java-ngs" ,java-ngs)
3726 ("java-snappy-1" ,java-snappy-1)
3727 ("java-commons-compress" ,java-commons-compress)
3728 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3729 ("java-commons-jexl-2" ,java-commons-jexl-2)
3730 ("java-xz" ,java-xz)))
3732 `(("java-testng" ,java-testng)))
3733 (home-page "http://samtools.github.io/htsjdk/")
3734 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3736 "HTSJDK is an implementation of a unified Java library for accessing
3737 common file formats, such as SAM and VCF, used for high-throughput
3738 sequencing (HTS) data. There are also an number of useful utilities for
3739 manipulating HTS data.")
3740 (license license:expat)))
3742 (define-public java-htsjdk-latest
3744 (name "java-htsjdk")
3749 (url "https://github.com/samtools/htsjdk")
3751 (file-name (string-append name "-" version "-checkout"))
3754 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
3755 (build-system ant-build-system)
3757 `(#:tests? #f ; test require Scala
3759 #:jar-name "htsjdk.jar"
3761 (modify-phases %standard-phases
3762 (add-after 'unpack 'remove-useless-build.xml
3763 (lambda _ (delete-file "build.xml") #t))
3764 ;; The tests require the scalatest package.
3765 (add-after 'unpack 'remove-tests
3766 (lambda _ (delete-file-recursively "src/test") #t)))))
3768 `(("java-ngs" ,java-ngs)
3769 ("java-snappy-1" ,java-snappy-1)
3770 ("java-commons-compress" ,java-commons-compress)
3771 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3772 ("java-commons-jexl-2" ,java-commons-jexl-2)
3773 ("java-xz" ,java-xz)))
3775 `(("java-junit" ,java-junit)))
3776 (home-page "http://samtools.github.io/htsjdk/")
3777 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3779 "HTSJDK is an implementation of a unified Java library for accessing
3780 common file formats, such as SAM and VCF, used for high-throughput
3781 sequencing (HTS) data. There are also an number of useful utilities for
3782 manipulating HTS data.")
3783 (license license:expat)))
3785 ;; This is needed for picard 2.10.3
3786 (define-public java-htsjdk-2.10.1
3787 (package (inherit java-htsjdk-latest)
3788 (name "java-htsjdk")
3793 (url "https://github.com/samtools/htsjdk")
3795 (file-name (string-append name "-" version "-checkout"))
3798 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
3799 (build-system ant-build-system)
3801 `(#:tests? #f ; tests require Scala
3803 #:jar-name "htsjdk.jar"
3805 (modify-phases %standard-phases
3806 (add-after 'unpack 'remove-useless-build.xml
3807 (lambda _ (delete-file "build.xml") #t))
3808 ;; The tests require the scalatest package.
3809 (add-after 'unpack 'remove-tests
3810 (lambda _ (delete-file-recursively "src/test") #t)))))))
3812 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3813 ;; recent version of java-htsjdk, which depends on gradle.
3814 (define-public java-picard
3816 (name "java-picard")
3821 (url "https://github.com/broadinstitute/picard")
3823 (file-name (string-append "java-picard-" version "-checkout"))
3826 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3827 (modules '((guix build utils)))
3830 ;; Delete pre-built binaries.
3831 (delete-file-recursively "lib")
3833 (substitute* "build.xml"
3834 ;; Remove build-time dependency on git.
3835 (("failifexecutionfails=\"true\"")
3836 "failifexecutionfails=\"false\"")
3838 (("depends=\"compile-htsjdk, ")
3840 (("depends=\"compile-htsjdk-tests, ")
3842 ;; Build picard-lib.jar before building picard.jar
3843 (("name=\"picard-jar\" depends=\"" line)
3844 (string-append line "picard-lib-jar, ")))
3846 (build-system ant-build-system)
3848 `(#:build-target "picard-jar"
3849 #:test-target "test"
3850 ;; Tests require jacoco:coverage.
3853 (list (string-append "-Dhtsjdk_lib_dir="
3854 (assoc-ref %build-inputs "java-htsjdk")
3855 "/share/java/htsjdk/")
3856 "-Dhtsjdk-classes=dist/tmp"
3857 (string-append "-Dhtsjdk-version="
3858 ,(package-version java-htsjdk)))
3861 (modify-phases %standard-phases
3862 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3863 (delete 'generate-jar-indices)
3864 (add-after 'unpack 'use-our-htsjdk
3865 (lambda* (#:key inputs #:allow-other-keys)
3866 (substitute* "build.xml"
3867 (("\\$\\{htsjdk\\}/lib")
3868 (string-append (assoc-ref inputs "java-htsjdk")
3869 "/share/java/htsjdk/")))
3871 (add-after 'unpack 'make-test-target-independent
3872 (lambda* (#:key inputs #:allow-other-keys)
3873 (substitute* "build.xml"
3874 (("name=\"test\" depends=\"compile, ")
3875 "name=\"test\" depends=\""))
3877 (replace 'install (install-jars "dist")))))
3879 `(("java-htsjdk" ,java-htsjdk)
3880 ("java-guava" ,java-guava)))
3882 `(("java-testng" ,java-testng)))
3883 (home-page "http://broadinstitute.github.io/picard/")
3884 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3885 (description "Picard is a set of Java command line tools for manipulating
3886 high-throughput sequencing (HTS) data and formats. Picard is implemented
3887 using the HTSJDK Java library to support accessing file formats that are
3888 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3890 (license license:expat)))
3892 ;; This is needed for dropseq-tools
3893 (define-public java-picard-2.10.3
3895 (name "java-picard")
3900 (url "https://github.com/broadinstitute/picard")
3902 (file-name (string-append "java-picard-" version "-checkout"))
3905 "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi"))))
3906 (build-system ant-build-system)
3908 `(#:jar-name "picard.jar"
3909 ;; Tests require jacoco:coverage.
3912 #:main-class "picard.cmdline.PicardCommandLine"
3913 #:modules ((guix build ant-build-system)
3915 (guix build java-utils)
3920 (modify-phases %standard-phases
3921 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3922 (delete 'generate-jar-indices)
3923 (add-after 'unpack 'remove-useless-build.xml
3924 (lambda _ (delete-file "build.xml") #t))
3925 ;; This is necessary to ensure that htsjdk is found when using
3926 ;; picard.jar as an executable.
3927 (add-before 'build 'edit-classpath-in-manifest
3928 (lambda* (#:key inputs #:allow-other-keys)
3929 (chmod "build.xml" #o664)
3930 (call-with-output-file "build.xml.new"
3934 (with-input-from-file "build.xml"
3935 (lambda _ (xml->sxml #:trim-whitespace? #t)))
3936 `((target . ,(lambda (tag . kids)
3937 (let ((name ((sxpath '(name *text*))
3939 ;; FIXME: We're breaking the line
3940 ;; early with a dummy path to
3941 ;; ensure that the store reference
3942 ;; isn't broken apart and can still
3943 ;; be found by the reference
3948 ~a/share/java/htsjdk.jar${line.separator}${line.separator}"
3949 ;; maximum line length is 70
3950 (string-tabulate (const #\b) 57)
3951 (assoc-ref inputs "java-htsjdk"))))
3952 (if (member "manifest" name)
3955 (@ (file "${manifest.file}")
3956 (match "\\r\\n\\r\\n")
3957 (replace "${line.separator}")))
3960 (file "${manifest.file}")
3963 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
3964 (*text* . ,(lambda (_ txt) txt))))
3966 (rename-file "build.xml.new" "build.xml")
3969 `(("java-htsjdk" ,java-htsjdk-2.10.1)))
3971 `(("java-testng" ,java-testng)
3972 ("java-guava" ,java-guava)))
3973 (home-page "http://broadinstitute.github.io/picard/")
3974 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3975 (description "Picard is a set of Java command line tools for manipulating
3976 high-throughput sequencing (HTS) data and formats. Picard is implemented
3977 using the HTSJDK Java library to support accessing file formats that are
3978 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3980 (license license:expat)))
3982 ;; This is the last version of Picard to provide net.sf.samtools
3983 (define-public java-picard-1.113
3984 (package (inherit java-picard)
3985 (name "java-picard")
3990 (url "https://github.com/broadinstitute/picard")
3992 (file-name (string-append "java-picard-" version "-checkout"))
3995 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
3996 (modules '((guix build utils)))
3999 ;; Delete pre-built binaries.
4000 (delete-file-recursively "lib")
4003 (build-system ant-build-system)
4005 `(#:build-target "picard-jar"
4006 #:test-target "test"
4007 ;; FIXME: the class path at test time is wrong.
4008 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
4009 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
4012 ;; This is only used for tests.
4014 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
4016 (modify-phases %standard-phases
4017 ;; FIXME: This phase fails.
4018 (delete 'generate-jar-indices)
4019 ;; Do not use bundled ant bzip2.
4020 (add-after 'unpack 'use-ant-bzip
4021 (lambda* (#:key inputs #:allow-other-keys)
4022 (substitute* "build.xml"
4023 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
4024 (string-append (assoc-ref inputs "ant")
4027 (add-after 'unpack 'make-test-target-independent
4028 (lambda* (#:key inputs #:allow-other-keys)
4029 (substitute* "build.xml"
4030 (("name=\"test\" depends=\"compile, ")
4031 "name=\"test\" depends=\"compile-tests, ")
4032 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
4033 "name=\"compile\" depends=\"compile-src\""))
4035 (add-after 'unpack 'fix-deflater-path
4036 (lambda* (#:key outputs #:allow-other-keys)
4037 (substitute* "src/java/net/sf/samtools/Defaults.java"
4038 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
4039 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
4040 (assoc-ref outputs "out")
4041 "/lib/jni/libIntelDeflater.so"
4044 ;; Build the deflater library, because we've previously deleted the
4045 ;; pre-built one. This can only be built with access to the JDK
4047 (add-after 'build 'build-jni
4048 (lambda* (#:key inputs #:allow-other-keys)
4051 (invoke "tar" "--strip-components=1" "-C" "jdk-src"
4052 "-xf" (assoc-ref inputs "jdk-src"))
4053 (invoke "javah" "-jni"
4054 "-classpath" "classes"
4056 "net.sf.samtools.util.zip.IntelDeflater")
4057 (with-directory-excursion "src/c/inteldeflater"
4058 (invoke "gcc" "-I../../../lib" "-I."
4059 (string-append "-I" (assoc-ref inputs "jdk")
4061 "-I../../../jdk-src/src/share/native/common/"
4062 "-I../../../jdk-src/src/solaris/native/common/"
4063 "-c" "-O3" "-fPIC" "IntelDeflater.c")
4064 (invoke "gcc" "-shared"
4065 "-o" "../../../lib/jni/libIntelDeflater.so"
4066 "IntelDeflater.o" "-lz" "-lstdc++"))
4068 ;; We can only build everything else after building the JNI library.
4069 (add-after 'build-jni 'build-rest
4070 (lambda* (#:key make-flags #:allow-other-keys)
4071 (apply invoke `("ant" "all" ,@make-flags))
4073 (add-before 'build 'set-JAVA6_HOME
4075 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
4077 (replace 'install (install-jars "dist"))
4078 (add-after 'install 'install-jni-lib
4079 (lambda* (#:key outputs #:allow-other-keys)
4080 (let ((jni (string-append (assoc-ref outputs "out")
4083 (install-file "lib/jni/libIntelDeflater.so" jni)
4086 `(("java-snappy-1" ,java-snappy-1)
4087 ("java-commons-jexl-2" ,java-commons-jexl-2)
4088 ("java-cofoja" ,java-cofoja)
4089 ("ant" ,ant) ; for bzip2 support at runtime
4092 `(("ant-apache-bcel" ,ant-apache-bcel)
4093 ("ant-junit" ,ant-junit)
4094 ("java-testng" ,java-testng)
4095 ("java-commons-bcel" ,java-commons-bcel)
4096 ("java-jcommander" ,java-jcommander)
4097 ("jdk" ,icedtea-8 "jdk")
4098 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
4100 (define-public fastqc
4107 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
4108 "projects/fastqc/fastqc_v"
4109 version "_source.zip"))
4112 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
4113 (build-system ant-build-system)
4115 `(#:tests? #f ; there are no tests
4116 #:build-target "build"
4118 (modify-phases %standard-phases
4119 (add-after 'unpack 'fix-dependencies
4120 (lambda* (#:key inputs #:allow-other-keys)
4121 (substitute* "build.xml"
4123 (string-append (assoc-ref inputs "java-jbzip2")
4124 "/share/java/jbzip2.jar"))
4126 (string-append (assoc-ref inputs "java-picard-1.113")
4127 "/share/java/sam-1.112.jar"))
4129 (string-append (assoc-ref inputs "java-cisd-jhdf5")
4130 "/share/java/sis-jhdf5.jar")))
4132 ;; There is no installation target
4134 (lambda* (#:key inputs outputs #:allow-other-keys)
4135 (let* ((out (assoc-ref outputs "out"))
4136 (bin (string-append out "/bin"))
4137 (share (string-append out "/share/fastqc/"))
4138 (exe (string-append share "/fastqc")))
4139 (for-each mkdir-p (list bin share))
4140 (copy-recursively "bin" share)
4142 (("my \\$java_bin = 'java';")
4143 (string-append "my $java_bin = '"
4144 (assoc-ref inputs "java")
4147 (symlink exe (string-append bin "/fastqc"))
4151 ("perl" ,perl) ; needed for the wrapper script
4152 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
4153 ("java-picard-1.113" ,java-picard-1.113)
4154 ("java-jbzip2" ,java-jbzip2)))
4156 `(("unzip" ,unzip)))
4157 (home-page "https://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
4158 (synopsis "Quality control tool for high throughput sequence data")
4160 "FastQC aims to provide a simple way to do some quality control
4161 checks on raw sequence data coming from high throughput sequencing
4162 pipelines. It provides a modular set of analyses which you can use to
4163 give a quick impression of whether your data has any problems of which
4164 you should be aware before doing any further analysis.
4166 The main functions of FastQC are:
4169 @item Import of data from BAM, SAM or FastQ files (any variant);
4170 @item Providing a quick overview to tell you in which areas there may
4172 @item Summary graphs and tables to quickly assess your data;
4173 @item Export of results to an HTML based permanent report;
4174 @item Offline operation to allow automated generation of reports
4175 without running the interactive application.
4177 (license license:gpl3+)))
4179 (define-public fastp
4187 (url "https://github.com/OpenGene/fastp")
4188 (commit (string-append "v" version))))
4189 (file-name (git-file-name name version))
4192 "1r6ms5zbf5rps4rgp4z73nczadl00b5rqylw8f684isfz27dp0xh"))))
4193 (build-system gnu-build-system)
4195 `(#:tests? #f ; there are none
4197 (list (string-append "BINDIR=" (assoc-ref %outputs "out") "/bin"))
4199 (modify-phases %standard-phases
4201 (add-before 'install 'create-target-dir
4202 (lambda* (#:key outputs #:allow-other-keys)
4203 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4207 (home-page "https://github.com/OpenGene/fastp/")
4208 (synopsis "All-in-one FastQ preprocessor")
4210 "Fastp is a tool designed to provide fast all-in-one preprocessing for
4211 FastQ files. This tool has multi-threading support to afford high
4213 (license license:expat)))
4215 (define-public htslib
4222 "https://github.com/samtools/htslib/releases/download/"
4223 version "/htslib-" version ".tar.bz2"))
4226 "16ljv43sc3fxmv63w7b2ff8m1s7h89xhazwmbm1bicz8axq8fjz0"))))
4227 (build-system gnu-build-system)
4230 ("openssl" ,openssl)))
4231 ;; This is referred to in the pkg-config file as a required library.
4236 (home-page "https://www.htslib.org")
4237 (synopsis "C library for reading/writing high-throughput sequencing data")
4239 "HTSlib is a C library for reading/writing high-throughput sequencing
4240 data. It also provides the @command{bgzip}, @command{htsfile}, and
4241 @command{tabix} utilities.")
4242 ;; Files under cram/ are released under the modified BSD license;
4243 ;; the rest is released under the Expat license
4244 (license (list license:expat license:bsd-3))))
4246 ;; This package should be removed once no packages rely upon it.
4254 "https://github.com/samtools/htslib/releases/download/"
4255 version "/htslib-" version ".tar.bz2"))
4258 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
4267 (url "https://github.com/nboley/idr")
4269 (file-name (git-file-name name version))
4272 "04j876h6z444v2q79drxx283d3k5snd72kj895wbalnl42206x9g"))
4273 ;; Delete generated C code.
4275 '(begin (delete-file "idr/inv_cdf.c") #t))))
4276 (build-system python-build-system)
4277 ;; There is only one test ("test_inv_cdf.py") and it tests features that
4278 ;; are no longer part of this package. It also asserts False, which
4279 ;; causes the tests to always fail.
4280 (arguments `(#:tests? #f))
4282 `(("python-scipy" ,python-scipy)
4283 ("python-sympy" ,python-sympy)
4284 ("python-numpy" ,python-numpy)
4285 ("python-matplotlib" ,python-matplotlib)))
4287 `(("python-cython" ,python-cython)))
4288 (home-page "https://github.com/nboley/idr")
4289 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
4291 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
4292 to measure the reproducibility of findings identified from replicate
4293 experiments and provide highly stable thresholds based on reproducibility.")
4294 (license license:gpl2+)))
4296 (define-public jellyfish
4302 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
4303 "releases/download/v" version
4304 "/jellyfish-" version ".tar.gz"))
4307 "1k4pc3fvv6w1km2yph4m5sd78fbxp21d6xyzgmy0gjihzc6mb249"))))
4308 (build-system gnu-build-system)
4309 (outputs '("out" ;for library
4310 "ruby" ;for Ruby bindings
4311 "python")) ;for Python bindings
4314 (list (string-append "--enable-ruby-binding="
4315 (assoc-ref %outputs "ruby"))
4316 (string-append "--enable-python-binding="
4317 (assoc-ref %outputs "python")))
4319 (modify-phases %standard-phases
4320 (add-before 'check 'set-SHELL-variable
4322 ;; generator_manager.hpp either uses /bin/sh or $SHELL
4324 (setenv "SHELL" (which "bash"))
4330 ("python" ,python-2)
4331 ("pkg-config" ,pkg-config)))
4333 `(("htslib" ,htslib)))
4334 (synopsis "Tool for fast counting of k-mers in DNA")
4336 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
4337 DNA. A k-mer is a substring of length k, and counting the occurrences of all
4338 such substrings is a central step in many analyses of DNA sequence. Jellyfish
4339 is a command-line program that reads FASTA and multi-FASTA files containing
4340 DNA sequences. It outputs its k-mer counts in a binary format, which can be
4341 translated into a human-readable text format using the @code{jellyfish dump}
4342 command, or queried for specific k-mers with @code{jellyfish query}.")
4343 (home-page "http://www.genome.umd.edu/jellyfish.html")
4344 ;; JELLYFISH seems to be 64-bit only.
4345 (supported-systems '("x86_64-linux" "aarch64-linux" "mips64el-linux"))
4346 ;; The combined work is published under the GPLv3 or later. Individual
4347 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
4348 (license (list license:gpl3+ license:expat))))
4350 (define-public khmer
4358 (url "https://github.com/dib-lab/khmer")
4359 (commit (string-append "v" version))))
4360 (file-name (git-file-name name version))
4363 "01l4jczglkl7yfhgvzx8j0df7k54bk1r8sli9ll16i1mis0d8f37"))
4364 (modules '((guix build utils)))
4367 ;; Delete bundled libraries. We do not replace the bundled seqan
4368 ;; as it is a modified subset of the old version 1.4.1.
4370 ;; We do not replace the bundled MurmurHash as the canonical
4371 ;; repository for this code 'SMHasher' is unsuitable for providing
4373 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
4374 (delete-file-recursively "third-party/zlib")
4375 (delete-file-recursively "third-party/bzip2")
4376 (delete-file-recursively "third-party/seqan")
4377 (substitute* "setup.cfg"
4378 (("# libraries = z,bz2")
4379 "libraries = z,bz2")
4380 (("include:third-party/zlib:third-party/bzip2")
4383 (build-system python-build-system)
4386 (modify-phases %standard-phases
4387 (add-after 'unpack 'set-cc
4388 (lambda _ (setenv "CC" "gcc") #t))
4390 (add-before 'reset-gzip-timestamps 'make-files-writable
4391 (lambda* (#:key outputs #:allow-other-keys)
4392 ;; Make sure .gz files are writable so that the
4393 ;; 'reset-gzip-timestamps' phase can do its work.
4394 (let ((out (assoc-ref outputs "out")))
4395 (for-each make-file-writable
4396 (find-files out "\\.gz$"))
4399 `(("python-cython" ,python-cython)
4400 ("python-pytest" ,python-pytest)
4401 ("python-pytest-runner" ,python-pytest-runner)))
4406 ("python-screed" ,python-screed)
4407 ("python-bz2file" ,python-bz2file)))
4408 (home-page "https://khmer.readthedocs.org/")
4409 (synopsis "K-mer counting, filtering and graph traversal library")
4410 (description "The khmer software is a set of command-line tools for
4411 working with DNA shotgun sequencing data from genomes, transcriptomes,
4412 metagenomes and single cells. Khmer can make de novo assemblies faster, and
4413 sometimes better. Khmer can also identify and fix problems with shotgun
4415 ;; When building on i686, armhf and mips64el, we get the following error:
4416 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
4417 (supported-systems '("x86_64-linux" "aarch64-linux"))
4418 (license license:bsd-3)))
4420 (define-public kaiju
4427 (url "https://github.com/bioinformatics-centre/kaiju")
4428 (commit (string-append "v" version))))
4429 (file-name (git-file-name name version))
4432 "119pzi0ddzv9mjg4wwa6han0cwr3k3ssn7kirvsjfcq05mi5ka0x"))))
4433 (build-system gnu-build-system)
4435 `(#:tests? #f ; There are no tests.
4437 (modify-phases %standard-phases
4439 (add-before 'build 'move-to-src-dir
4440 (lambda _ (chdir "src") #t))
4442 (lambda* (#:key inputs outputs #:allow-other-keys)
4443 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
4446 (copy-recursively "bin" bin))
4451 (home-page "http://kaiju.binf.ku.dk/")
4452 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
4453 (description "Kaiju is a program for sensitive taxonomic classification
4454 of high-throughput sequencing reads from metagenomic whole genome sequencing
4456 (license license:gpl3+)))
4463 ;; The PyPi tarball does not contain tests.
4466 (url "https://github.com/taoliu/MACS")
4467 (commit (string-append "v" version))))
4468 (file-name (git-file-name name version))
4471 "1c5gxr0mk6hkd4vclf0k00wvyvzw2vrmk52c85338p7aqjwg6n15"))))
4472 (build-system python-build-system)
4475 (modify-phases %standard-phases
4477 (add-after 'install 'check
4478 (lambda* (#:key inputs outputs #:allow-other-keys)
4479 (add-installed-pythonpath inputs outputs)
4480 (invoke "pytest" "-v"))))))
4482 `(("python-numpy" ,python-numpy)))
4484 `(("python-pytest" ,python-pytest)))
4485 (home-page "https://github.com/taoliu/MACS/")
4486 (synopsis "Model based analysis for ChIP-Seq data")
4488 "MACS is an implementation of a ChIP-Seq analysis algorithm for
4489 identifying transcript factor binding sites named Model-based Analysis of
4490 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
4491 the significance of enriched ChIP regions and it improves the spatial
4492 resolution of binding sites through combining the information of both
4493 sequencing tag position and orientation.")
4494 (license license:bsd-3)))
4496 (define-public mafft
4503 "https://mafft.cbrc.jp/alignment/software/mafft-" version
4504 "-without-extensions-src.tgz"))
4505 (file-name (string-append name "-" version ".tgz"))
4508 "0bacjkxfg944p5khhyh5rd4y7wkjc9qk4v2jjj442sqlq0f8ar7b"))))
4509 (build-system gnu-build-system)
4511 `(#:tests? #f ; no automated tests, though there are tests in the read me
4512 #:make-flags (let ((out (assoc-ref %outputs "out")))
4513 (list (string-append "PREFIX=" out)
4514 (string-append "BINDIR="
4515 (string-append out "/bin"))))
4517 (modify-phases %standard-phases
4518 (add-after 'unpack 'enter-dir
4519 (lambda _ (chdir "core") #t))
4520 (add-after 'enter-dir 'patch-makefile
4522 ;; on advice from the MAFFT authors, there is no need to
4523 ;; distribute mafft-profile, mafft-distance, or
4524 ;; mafft-homologs.rb as they are too "specialised".
4525 (substitute* "Makefile"
4526 ;; remove mafft-homologs.rb from SCRIPTS
4527 (("^SCRIPTS = mafft mafft-homologs.rb")
4529 ;; remove mafft-homologs from MANPAGES
4530 (("^MANPAGES = mafft.1 mafft-homologs.1")
4531 "MANPAGES = mafft.1")
4532 ;; remove mafft-distance from PROGS
4533 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
4534 "PROGS = dvtditr dndfast7 dndblast sextet5")
4535 ;; remove mafft-profile from PROGS
4536 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
4537 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
4538 (("^rm -f mafft-profile mafft-profile.exe") "#")
4539 (("^rm -f mafft-distance mafft-distance.exe") ")#")
4540 ;; do not install MAN pages in libexec folder
4541 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
4542 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
4544 (add-after 'enter-dir 'patch-paths
4545 (lambda* (#:key inputs #:allow-other-keys)
4546 (substitute* '("pairash.c"
4548 (("perl") (which "perl"))
4549 (("([\"`| ])awk" _ prefix)
4550 (string-append prefix (which "awk")))
4551 (("grep") (which "grep")))
4554 (add-after 'install 'wrap-programs
4555 (lambda* (#:key outputs #:allow-other-keys)
4556 (let* ((out (assoc-ref outputs "out"))
4557 (bin (string-append out "/bin"))
4558 (path (string-append
4559 (assoc-ref %build-inputs "coreutils") "/bin:")))
4560 (for-each (lambda (file)
4562 `("PATH" ":" prefix (,path))))
4570 ("coreutils" ,coreutils)))
4571 (home-page "http://mafft.cbrc.jp/alignment/software/")
4572 (synopsis "Multiple sequence alignment program")
4574 "MAFFT offers a range of multiple alignment methods for nucleotide and
4575 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
4576 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
4578 (license (license:non-copyleft
4579 "http://mafft.cbrc.jp/alignment/software/license.txt"
4580 "BSD-3 with different formatting"))))
4589 (url "https://github.com/marbl/mash")
4590 (commit (string-append "v" version))))
4591 (file-name (git-file-name name version))
4594 "049hwcc059p2fd9vwndn63laifvvsi0wmv84i6y1fr79k15dxwy6"))
4595 (modules '((guix build utils)))
4598 ;; Delete bundled kseq.
4599 ;; TODO: Also delete bundled murmurhash and open bloom filter.
4600 (delete-file "src/mash/kseq.h")
4602 (build-system gnu-build-system)
4604 `(#:tests? #f ; No tests.
4607 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
4608 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
4609 #:make-flags (list "CC=gcc")
4611 (modify-phases %standard-phases
4612 (add-after 'unpack 'fix-includes
4614 (substitute* '("src/mash/Sketch.cpp"
4615 "src/mash/CommandFind.cpp"
4616 "src/mash/CommandScreen.cpp")
4617 (("^#include \"kseq\\.h\"")
4618 "#include \"htslib/kseq.h\""))
4620 (add-after 'fix-includes 'use-c++14
4622 ;; capnproto 0.7 requires c++14 to build
4623 (substitute* "configure.ac"
4624 (("c\\+\\+11") "c++14"))
4625 (substitute* "Makefile.in"
4626 (("c\\+\\+11") "c++14"))
4629 `(("autoconf" ,autoconf)
4630 ;; Capnproto and htslib are statically embedded in the final
4631 ;; application. Therefore we also list their licenses, below.
4632 ("capnproto" ,capnproto)
4633 ("htslib" ,htslib)))
4637 (supported-systems '("x86_64-linux"))
4638 (home-page "https://mash.readthedocs.io")
4639 (synopsis "Fast genome and metagenome distance estimation using MinHash")
4640 (description "Mash is a fast sequence distance estimator that uses the
4641 MinHash algorithm and is designed to work with genomes and metagenomes in the
4642 form of assemblies or reads.")
4643 (license (list license:bsd-3 ; Mash
4644 license:expat ; HTSlib and capnproto
4645 license:public-domain ; MurmurHash 3
4646 license:cpl1.0)))) ; Open Bloom Filter
4648 (define-public metabat
4656 (url "https://bitbucket.org/berkeleylab/metabat.git")
4657 (commit (string-append "v" version))))
4658 (file-name (git-file-name name version))
4661 "0hyg2smw1nz69mfvjpk45xyyychmda92c80a0cv7baji84ri4iyn"))
4662 (patches (search-patches "metabat-fix-compilation.patch"))))
4663 (build-system scons-build-system)
4665 `(#:scons ,scons-python2
4667 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
4668 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
4669 #:tests? #f ;; Tests are run during the build phase.
4671 (modify-phases %standard-phases
4672 (add-after 'unpack 'fix-includes
4674 (substitute* "src/BamUtils.h"
4675 (("^#include \"bam/bam\\.h\"")
4676 "#include \"samtools/bam.h\"")
4677 (("^#include \"bam/sam\\.h\"")
4678 "#include \"samtools/sam.h\""))
4679 (substitute* "src/KseqReader.h"
4680 (("^#include \"bam/kseq\\.h\"")
4681 "#include \"htslib/kseq.h\""))
4683 (add-after 'unpack 'fix-scons
4684 (lambda* (#:key inputs #:allow-other-keys)
4685 (substitute* "SConstruct"
4686 (("^htslib_dir += 'samtools'")
4687 (string-append "htslib_dir = '"
4688 (assoc-ref inputs "htslib")
4690 (("^samtools_dir = 'samtools'")
4691 (string-append "samtools_dir = '"
4692 (assoc-ref inputs "samtools")
4694 (("^findStaticOrShared\\('bam', hts_lib")
4695 (string-append "findStaticOrShared('bam', '"
4696 (assoc-ref inputs "samtools")
4698 ;; Do not distribute README.
4699 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
4704 ("samtools" ,samtools)
4707 (home-page "https://bitbucket.org/berkeleylab/metabat")
4709 "Reconstruction of single genomes from complex microbial communities")
4711 "Grouping large genomic fragments assembled from shotgun metagenomic
4712 sequences to deconvolute complex microbial communities, or metagenome binning,
4713 enables the study of individual organisms and their interactions. MetaBAT is
4714 an automated metagenome binning software, which integrates empirical
4715 probabilistic distances of genome abundance and tetranucleotide frequency.")
4716 ;; The source code contains inline assembly.
4717 (supported-systems '("x86_64-linux" "i686-linux"))
4718 (license (license:non-copyleft "file://license.txt"
4719 "See license.txt in the distribution."))))
4721 (define-public minced
4728 (url "https://github.com/ctSkennerton/minced")
4730 (file-name (git-file-name name version))
4733 "1f5h9him0gd355cnx7p6pnxpknhckd4g0v62mg8zyhfbx9as25fv"))))
4734 (build-system gnu-build-system)
4736 `(#:test-target "test"
4738 (modify-phases %standard-phases
4740 (add-before 'check 'fix-test
4742 ;; Fix test for latest version.
4743 (substitute* "t/Aquifex_aeolicus_VF5.expected"
4744 (("minced:0.1.6") "minced:0.2.0"))
4746 (replace 'install ; No install target.
4747 (lambda* (#:key inputs outputs #:allow-other-keys)
4748 (let* ((out (assoc-ref outputs "out"))
4749 (bin (string-append out "/bin"))
4750 (wrapper (string-append bin "/minced")))
4751 ;; Minced comes with a wrapper script that tries to figure out where
4752 ;; it is located before running the JAR. Since these paths are known
4753 ;; to us, we build our own wrapper to avoid coreutils dependency.
4754 (install-file "minced.jar" bin)
4755 (with-output-to-file wrapper
4759 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
4760 (assoc-ref inputs "jre") "/bin/java -jar "
4761 bin "/minced.jar \"$@\"\n"))))
4762 (chmod wrapper #o555))
4765 `(("jdk" ,icedtea "jdk")))
4768 ("jre" ,icedtea "out")))
4769 (home-page "https://github.com/ctSkennerton/minced")
4770 (synopsis "Mining CRISPRs in Environmental Datasets")
4772 "MinCED is a program to find Clustered Regularly Interspaced Short
4773 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
4774 unassembled metagenomic reads, but is mainly designed for full genomes and
4775 assembled metagenomic sequence.")
4776 (license license:gpl3+)))
4784 (uri (pypi-uri "misopy" version))
4787 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
4788 (modules '((guix build utils)))
4790 (substitute* "setup.py"
4791 ;; Use setuptools, or else the executables are not
4793 (("distutils.core") "setuptools")
4794 ;; Use "gcc" instead of "cc" for compilation.
4796 "cc.set_executables(
4800 linker_so='gcc -shared'); defines"))
4802 (build-system python-build-system)
4804 `(#:python ,python-2 ; only Python 2 is supported
4805 #:tests? #f)) ; no "test" target
4807 `(("samtools" ,samtools)
4808 ("python-numpy" ,python2-numpy)
4809 ("python-pysam" ,python2-pysam)
4810 ("python-scipy" ,python2-scipy)
4811 ("python-matplotlib" ,python2-matplotlib)))
4813 `(("python-mock" ,python2-mock) ; for tests
4814 ("python-pytz" ,python2-pytz))) ; for tests
4815 (home-page "https://www.genes.mit.edu/burgelab/miso/index.html")
4816 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
4818 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
4819 the expression level of alternatively spliced genes from RNA-Seq data, and
4820 identifies differentially regulated isoforms or exons across samples. By
4821 modeling the generative process by which reads are produced from isoforms in
4822 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
4823 that a read originated from a particular isoform.")
4824 (license license:gpl2)))
4826 (define-public muscle
4829 (version "3.8.1551")
4831 (method url-fetch/tarbomb)
4833 "http://www.drive5.com/muscle/muscle_src_"
4837 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
4838 (build-system gnu-build-system)
4840 `(#:make-flags (list "LDLIBS = -lm")
4842 (modify-phases %standard-phases
4845 ;; There are no tests, so just test if it runs.
4846 (lambda _ (invoke "./muscle" "-version") #t))
4848 (lambda* (#:key outputs #:allow-other-keys)
4849 (let* ((out (assoc-ref outputs "out"))
4850 (bin (string-append out "/bin")))
4851 (install-file "muscle" bin)
4853 (home-page "http://www.drive5.com/muscle")
4854 (synopsis "Multiple sequence alignment program")
4856 "MUSCLE aims to be a fast and accurate multiple sequence alignment
4857 program for nucleotide and protein sequences.")
4858 ;; License information found in 'muscle -h' and usage.cpp.
4859 (license license:public-domain)))
4861 (define-public newick-utils
4862 ;; There are no recent releases so we package from git.
4863 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
4865 (name "newick-utils")
4866 (version (string-append "1.6-1." (string-take commit 8)))
4870 (url "https://github.com/tjunier/newick_utils")
4872 (file-name (string-append name "-" version "-checkout"))
4875 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4876 (build-system gnu-build-system)
4878 ;; XXX: TODO: Enable Lua and Guile bindings.
4879 ;; https://github.com/tjunier/newick_utils/issues/13
4880 `(("libxml2" ,libxml2)
4884 `(("autoconf" ,autoconf)
4885 ("automake" ,automake)
4886 ("libtool" ,libtool)))
4887 (synopsis "Programs for working with newick format phylogenetic trees")
4889 "Newick-utils is a suite of utilities for processing phylogenetic trees
4890 in Newick format. Functions include re-rooting, extracting subtrees,
4891 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4892 (home-page "https://github.com/tjunier/newick_utils")
4893 (license license:bsd-3))))
4902 "https://github.com/wwood/OrfM/releases/download/v"
4903 version "/orfm-" version ".tar.gz"))
4906 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4907 (build-system gnu-build-system)
4908 (inputs `(("zlib" ,zlib)))
4910 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4911 ("ruby-rspec" ,ruby-rspec)
4913 (synopsis "Simple and not slow open reading frame (ORF) caller")
4915 "An ORF caller finds stretches of DNA that, when translated, are not
4916 interrupted by stop codons. OrfM finds and prints these ORFs.")
4917 (home-page "https://github.com/wwood/OrfM")
4918 (license license:lgpl3+)))
4920 (define-public python2-pbcore
4922 (name "python2-pbcore")
4926 (uri (pypi-uri "pbcore" version))
4929 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4930 (build-system python-build-system)
4932 `(#:python ,python-2 ;pbcore < 2.0 requires Python 2.7
4933 #:phases (modify-phases %standard-phases
4934 (add-after 'unpack 'remove-sphinx-dependency
4936 ;; Sphinx is only required for documentation tests, which
4937 ;; we do not run; furthermore it depends on python2-sphinx
4938 ;; which is no longer maintained.
4939 (substitute* "requirements-dev.txt"
4943 `(("python-cython" ,python2-cython)
4944 ("python-numpy" ,python2-numpy)
4945 ("python-pysam" ,python2-pysam)
4946 ("python-h5py" ,python2-h5py)))
4948 `(("python-nose" ,python2-nose)
4949 ("python-pyxb" ,python2-pyxb)))
4950 (home-page "https://pacificbiosciences.github.io/pbcore/")
4951 (synopsis "Library for reading and writing PacBio data files")
4953 "The pbcore package provides Python APIs for interacting with PacBio data
4954 files and writing bioinformatics applications.")
4955 (license license:bsd-3)))
4957 (define-public python2-warpedlmm
4959 (name "python2-warpedlmm")
4964 (uri (pypi-uri "WarpedLMM" version ".zip"))
4967 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4968 (build-system python-build-system)
4970 `(#:python ,python-2 ; requires Python 2.7
4971 #:tests? #f ; test data are not included
4973 (modify-phases %standard-phases
4974 (add-after 'unpack 'use-weave
4976 (substitute* "warpedlmm/util/linalg.py"
4977 (("from scipy import linalg, weave")
4978 "from scipy import linalg\nimport weave"))
4981 `(("python-scipy" ,python2-scipy)
4982 ("python-numpy" ,python2-numpy)
4983 ("python-matplotlib" ,python2-matplotlib)
4984 ("python-fastlmm" ,python2-fastlmm)
4985 ("python-pandas" ,python2-pandas)
4986 ("python-pysnptools" ,python2-pysnptools)
4987 ("python-weave" ,python2-weave)))
4989 `(("python-mock" ,python2-mock)
4990 ("python-nose" ,python2-nose)
4992 (home-page "https://github.com/PMBio/warpedLMM")
4993 (synopsis "Implementation of warped linear mixed models")
4995 "WarpedLMM is a Python implementation of the warped linear mixed model,
4996 which automatically learns an optimal warping function (or transformation) for
4997 the phenotype as it models the data.")
4998 (license license:asl2.0)))
5000 (define-public pbtranscript-tofu
5001 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
5003 (name "pbtranscript-tofu")
5004 (version (string-append "2.2.3." (string-take commit 7)))
5008 (url "https://github.com/PacificBiosciences/cDNA_primer")
5010 (file-name (string-append name "-" version "-checkout"))
5013 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
5014 (modules '((guix build utils)))
5017 ;; remove bundled Cython sources
5018 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
5020 (build-system python-build-system)
5022 `(#:python ,python-2
5023 ;; FIXME: Tests fail with "No such file or directory:
5024 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
5027 (modify-phases %standard-phases
5028 (add-after 'unpack 'enter-directory
5030 (chdir "pbtranscript-tofu/pbtranscript/")
5032 ;; With setuptools version 18.0 and later this setup.py hack causes
5033 ;; a build error, so we disable it.
5034 (add-after 'enter-directory 'patch-setuppy
5036 (substitute* "setup.py"
5037 (("if 'setuptools.extension' in sys.modules:")
5041 `(("python-numpy" ,python2-numpy)
5042 ("python-bx-python" ,python2-bx-python)
5043 ("python-networkx" ,python2-networkx)
5044 ("python-scipy" ,python2-scipy)
5045 ("python-pbcore" ,python2-pbcore)
5046 ("python-h5py" ,python2-h5py)))
5048 `(("python-cython" ,python2-cython)
5049 ("python-nose" ,python2-nose)))
5050 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
5051 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
5053 "pbtranscript-tofu contains scripts to analyze transcriptome data
5054 generated using the PacBio Iso-Seq protocol.")
5055 (license license:bsd-3))))
5057 (define-public prank
5064 "http://wasabiapp.org/download/prank/prank.source."
5068 "0nc8g9c5rkdxcir46s0in9ci1sxwzbjibxrvkksf22ybnplvagk2"))))
5069 (build-system gnu-build-system)
5072 (modify-phases %standard-phases
5073 (add-after 'unpack 'enter-src-dir
5077 (add-after 'unpack 'remove-m64-flag
5078 ;; Prank will build with the correct 'bit-ness' without this flag
5079 ;; and this allows building on 32-bit machines.
5080 (lambda _ (substitute* "src/Makefile"
5085 (lambda* (#:key outputs #:allow-other-keys)
5086 (let* ((out (assoc-ref outputs "out"))
5087 (bin (string-append out "/bin"))
5088 (man (string-append out "/share/man/man1"))
5089 (path (string-append
5090 (assoc-ref %build-inputs "mafft") "/bin:"
5091 (assoc-ref %build-inputs "exonerate") "/bin:"
5092 (assoc-ref %build-inputs "bppsuite") "/bin")))
5093 (install-file "prank" bin)
5094 (wrap-program (string-append bin "/prank")
5095 `("PATH" ":" prefix (,path)))
5096 (install-file "prank.1" man))
5100 ("exonerate" ,exonerate)
5101 ("bppsuite" ,bppsuite)))
5102 (home-page "http://wasabiapp.org/software/prank/")
5103 (synopsis "Probabilistic multiple sequence alignment program")
5105 "PRANK is a probabilistic multiple sequence alignment program for DNA,
5106 codon and amino-acid sequences. It is based on a novel algorithm that treats
5107 insertions correctly and avoids over-estimation of the number of deletion
5108 events. In addition, PRANK borrows ideas from maximum likelihood methods used
5109 in phylogenetics and correctly takes into account the evolutionary distances
5110 between sequences. Lastly, PRANK allows for defining a potential structure
5111 for sequences to be aligned and then, simultaneously with the alignment,
5112 predicts the locations of structural units in the sequences.")
5113 (license license:gpl2+)))
5115 (define-public proteinortho
5117 (name "proteinortho")
5122 (url "https://gitlab.com/paulklemm_PHD/proteinortho.git")
5123 (commit (string-append "v" version))))
5124 (file-name (git-file-name name version))
5127 "0pmy617zy2z2w6hjqxjhf3rzikf5n3mpia80ysq8233vfr7wrzff"))
5128 (modules '((guix build utils)))
5131 ;; remove pre-built scripts
5132 (delete-file-recursively "src/BUILD/")
5134 (build-system gnu-build-system)
5136 `(#:test-target "test"
5137 #:make-flags '("CC=gcc")
5139 (modify-phases %standard-phases
5141 ;; There is no configure script, so we modify the Makefile directly.
5142 (lambda* (#:key outputs #:allow-other-keys)
5143 (substitute* "Makefile"
5146 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
5148 (add-before 'install 'make-install-directory
5149 ;; The install directory is not created during 'make install'.
5150 (lambda* (#:key outputs #:allow-other-keys)
5151 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
5153 (add-after 'install 'wrap-programs
5154 (lambda* (#:key inputs outputs #:allow-other-keys)
5155 (let ((path (getenv "PATH"))
5156 (out (assoc-ref outputs "out")))
5157 (for-each (lambda (script)
5158 (wrap-script script `("PATH" ":" prefix (,path))))
5159 (cons (string-append out "/bin/proteinortho")
5160 (find-files out "\\.(pl|py)$"))))
5163 `(("guile" ,guile-3.0) ; for wrap-script
5164 ("diamond" ,diamond)
5166 ("python" ,python-wrapper)
5169 ("openblas" ,openblas)))
5171 `(("which" ,which)))
5172 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
5173 (synopsis "Detect orthologous genes across species")
5175 "Proteinortho is a tool to detect orthologous genes across different
5176 species. For doing so, it compares similarities of given gene sequences and
5177 clusters them to find significant groups. The algorithm was designed to handle
5178 large-scale data and can be applied to hundreds of species at once.")
5179 (license license:gpl3+)))
5181 (define-public pyicoteo
5189 (url "https://bitbucket.org/regulatorygenomicsupf/pyicoteo.git")
5190 (commit (string-append "v" version))))
5191 (file-name (git-file-name name version))
5194 "0hz5g8d25lbjy1wpscr490l0lmyvaix893hhax4fxnh1h9w34w8p"))))
5195 (build-system python-build-system)
5197 `(#:python ,python-2 ; does not work with Python 3
5198 #:tests? #f)) ; there are no tests
5200 `(("python2-matplotlib" ,python2-matplotlib)))
5201 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
5202 (synopsis "Analyze high-throughput genetic sequencing data")
5204 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
5205 sequencing data. It works with genomic coordinates. There are currently six
5206 different command-line tools:
5209 @item pyicoregion: for generating exploratory regions automatically;
5210 @item pyicoenrich: for differential enrichment between two conditions;
5211 @item pyicoclip: for calling CLIP-Seq peaks without a control;
5212 @item pyicos: for genomic coordinates manipulation;
5213 @item pyicoller: for peak calling on punctuated ChIP-Seq;
5214 @item pyicount: to count how many reads from N experiment files overlap in a
5216 @item pyicotrocol: to combine operations from pyicoteo.
5218 (license license:gpl3+)))
5220 (define-public prodigal
5223 ;; Check for a new home page when updating this package:
5224 ;; https://github.com/hyattpd/Prodigal/issues/36#issuecomment-536617588
5229 (url "https://github.com/hyattpd/Prodigal")
5230 (commit (string-append "v" version))))
5231 (file-name (git-file-name name version))
5234 "1fs1hqk83qjbjhrvhw6ni75zakx5ki1ayy3v6wwkn3xvahc9hi5s"))))
5235 (build-system gnu-build-system)
5237 `(#:tests? #f ; no check target
5238 #:make-flags (list (string-append "INSTALLDIR="
5239 (assoc-ref %outputs "out")
5242 (modify-phases %standard-phases
5243 (delete 'configure))))
5244 (home-page "https://github.com/hyattpd/Prodigal")
5245 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
5247 "Prodigal runs smoothly on finished genomes, draft genomes, and
5248 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
5249 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
5250 partial genes, and identifies translation initiation sites.")
5251 (license license:gpl3+)))
5253 (define-public roary
5261 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
5265 "0qxrds9wx7cfhlkihrp6697kx0flhhxymap9fwan0b3rbdhcnmff"))))
5266 (build-system perl-build-system)
5269 (modify-phases %standard-phases
5274 ;; The tests are not run by default, so we run each test file
5276 (setenv "PATH" (string-append (getcwd) "/bin" ":"
5278 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
5279 (getenv "PERL5LIB")))
5280 (for-each (lambda (file)
5281 (display file)(display "\n")
5282 (invoke "perl" file))
5283 (find-files "t" ".*\\.t$"))
5286 ;; There is no 'install' target in the Makefile.
5287 (lambda* (#:key outputs #:allow-other-keys)
5288 (let* ((out (assoc-ref outputs "out"))
5289 (bin (string-append out "/bin"))
5290 (perl (string-append out "/lib/perl5/site_perl"))
5291 (roary-plots "contrib/roary_plots"))
5294 (copy-recursively "bin" bin)
5295 (copy-recursively "lib" perl)
5297 (add-after 'install 'wrap-programs
5298 (lambda* (#:key inputs outputs #:allow-other-keys)
5299 (let* ((out (assoc-ref outputs "out"))
5300 (perl5lib (getenv "PERL5LIB"))
5301 (path (getenv "PATH")))
5302 (for-each (lambda (prog)
5303 (let ((binary (string-append out "/" prog)))
5304 (wrap-program binary
5305 `("PERL5LIB" ":" prefix
5306 (,(string-append perl5lib ":" out
5307 "/lib/perl5/site_perl"))))
5308 (wrap-program binary
5310 (,(string-append path ":" out "/bin"))))))
5311 (find-files "bin" ".*[^R]$"))
5313 (string-append out "/bin/roary-create_pan_genome_plots.R"))
5314 (r-site-lib (getenv "R_LIBS_SITE"))
5316 (string-append (assoc-ref inputs "coreutils") "/bin")))
5318 `("R_LIBS_SITE" ":" prefix
5319 (,(string-append r-site-lib ":" out "/site-library/"))))
5322 (,(string-append coreutils-path ":" out "/bin"))))))
5325 `(("perl-env-path" ,perl-env-path)
5326 ("perl-test-files" ,perl-test-files)
5327 ("perl-test-most" ,perl-test-most)
5328 ("perl-test-output" ,perl-test-output)))
5330 `(("perl-array-utils" ,perl-array-utils)
5331 ("bioperl" ,bioperl-minimal)
5332 ("perl-digest-md5-file" ,perl-digest-md5-file)
5333 ("perl-exception-class" ,perl-exception-class)
5334 ("perl-file-find-rule" ,perl-file-find-rule)
5335 ("perl-file-grep" ,perl-file-grep)
5336 ("perl-file-slurper" ,perl-file-slurper)
5337 ("perl-file-which" ,perl-file-which)
5338 ("perl-graph" ,perl-graph)
5339 ("perl-graph-readwrite" ,perl-graph-readwrite)
5340 ("perl-log-log4perl" ,perl-log-log4perl)
5341 ("perl-moose" ,perl-moose)
5342 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
5343 ("perl-text-csv" ,perl-text-csv)
5344 ("bedtools" ,bedtools)
5348 ("parallel" ,parallel)
5351 ("fasttree" ,fasttree)
5355 ("r-minimal" ,r-minimal)
5356 ("r-ggplot2" ,r-ggplot2)
5357 ("coreutils" ,coreutils)))
5358 (home-page "https://sanger-pathogens.github.io/Roary/")
5359 (synopsis "High speed stand-alone pan genome pipeline")
5361 "Roary is a high speed stand alone pan genome pipeline, which takes
5362 annotated assemblies in GFF3 format (produced by the Prokka program) and
5363 calculates the pan genome. Using a standard desktop PC, it can analyse
5364 datasets with thousands of samples, without compromising the quality of the
5365 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
5366 single processor. Roary is not intended for metagenomics or for comparing
5367 extremely diverse sets of genomes.")
5368 (license license:gpl3)))
5370 (define-public raxml
5378 (url "https://github.com/stamatak/standard-RAxML")
5379 (commit (string-append "v" version))))
5380 (file-name (git-file-name name version))
5383 "1jqjzhch0rips0vp04prvb8vmc20c5pdmsqn8knadcf91yy859fh"))))
5384 (build-system gnu-build-system)
5386 `(#:tests? #f ; There are no tests.
5387 ;; Use 'standard' Makefile rather than SSE or AVX ones.
5388 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
5390 (modify-phases %standard-phases
5393 (lambda* (#:key outputs #:allow-other-keys)
5394 (let* ((out (assoc-ref outputs "out"))
5395 (bin (string-append out "/bin"))
5396 (executable "raxmlHPC-HYBRID"))
5397 (install-file executable bin)
5398 (symlink (string-append bin "/" executable) "raxml"))
5401 `(("openmpi" ,openmpi)))
5402 (home-page "https://cme.h-its.org/exelixis/web/software/raxml/index.html")
5403 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
5405 "RAxML is a tool for phylogenetic analysis and post-analysis of large
5407 ;; The source includes x86 specific code
5408 (supported-systems '("x86_64-linux" "i686-linux"))
5409 (license license:gpl2+)))
5419 (url "https://github.com/deweylab/RSEM")
5420 (commit (string-append "v" version))))
5422 (base32 "1jlq11d1p8qp64w75yj8cnbbd1a93viq10pzsbwal7vdn8fg13j1"))
5423 (file-name (git-file-name name version))
5424 (modules '((guix build utils)))
5427 ;; remove bundled copy of boost and samtools
5428 (delete-file-recursively "boost")
5429 (delete-file-recursively "samtools-1.3")
5431 (build-system gnu-build-system)
5433 `(#:tests? #f ;no "check" target
5435 (list (string-append "BOOST="
5436 (assoc-ref %build-inputs "boost")
5438 (string-append "SAMHEADERS="
5439 (assoc-ref %build-inputs "htslib")
5440 "/include/htslib/sam.h")
5441 (string-append "SAMLIBS="
5442 (assoc-ref %build-inputs "htslib")
5445 (modify-phases %standard-phases
5446 ;; No "configure" script.
5447 ;; Do not build bundled samtools library.
5450 (substitute* "Makefile"
5451 (("^all : \\$\\(PROGRAMS\\).*") "all: $(PROGRAMS)\n")
5452 (("^\\$\\(SAMLIBS\\).*") ""))
5455 (lambda* (#:key outputs #:allow-other-keys)
5456 (let* ((out (string-append (assoc-ref outputs "out")))
5457 (bin (string-append out "/bin/"))
5458 (perl (string-append out "/lib/perl5/site_perl")))
5461 (for-each (lambda (file)
5462 (install-file file bin))
5463 (find-files "." "rsem-.*"))
5464 (install-file "rsem_perl_utils.pm" perl))
5466 (add-after 'install 'wrap-program
5467 (lambda* (#:key outputs #:allow-other-keys)
5468 (let ((out (assoc-ref outputs "out")))
5469 (for-each (lambda (prog)
5470 (wrap-program (string-append out "/bin/" prog)
5471 `("PERL5LIB" ":" prefix
5472 (,(string-append out "/lib/perl5/site_perl")))))
5473 '("rsem-calculate-expression"
5475 "rsem-generate-data-matrix"
5476 "rsem-generate-ngvector"
5477 "rsem-plot-transcript-wiggles"
5478 "rsem-prepare-reference"
5480 "rsem-run-prsem-testing-procedure")))
5484 ("r-minimal" ,r-minimal)
5486 ("htslib" ,htslib-1.3)
5488 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
5489 (synopsis "Estimate gene expression levels from RNA-Seq data")
5491 "RSEM is a software package for estimating gene and isoform expression
5492 levels from RNA-Seq data. The RSEM package provides a user-friendly
5493 interface, supports threads for parallel computation of the EM algorithm,
5494 single-end and paired-end read data, quality scores, variable-length reads and
5495 RSPD estimation. In addition, it provides posterior mean and 95% credibility
5496 interval estimates for expression levels. For visualization, it can generate
5497 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
5498 (license license:gpl3+)))
5500 (define-public rseqc
5508 (string-append "mirror://sourceforge/rseqc/"
5509 "RSeQC-" version ".tar.gz"))
5512 "0gbb9iyb7swiv5455fm5rg98r7l6qn27v564yllqjd574hncpx6m"))))
5513 (build-system python-build-system)
5515 `(("python-cython" ,python-cython)
5516 ("python-bx-python" ,python-bx-python)
5517 ("python-pybigwig" ,python-pybigwig)
5518 ("python-pysam" ,python-pysam)
5519 ("python-numpy" ,python-numpy)
5522 `(("python-nose" ,python-nose)))
5523 (home-page "http://rseqc.sourceforge.net/")
5524 (synopsis "RNA-seq quality control package")
5526 "RSeQC provides a number of modules that can comprehensively evaluate
5527 high throughput sequence data, especially RNA-seq data. Some basic modules
5528 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
5529 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
5530 distribution, coverage uniformity, strand specificity, etc.")
5531 (license license:gpl3+)))
5534 ;; There are no release tarballs. According to the installation
5535 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
5536 ;; stable release is identified by this changeset ID.
5537 (let ((changeset "2329130")
5541 (version (string-append "0-" revision "." changeset))
5545 (url "https://bitbucket.org/libsleipnir/sleipnir")
5546 (changeset changeset)))
5547 (file-name (string-append name "-" version "-checkout"))
5550 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
5551 (build-system gnu-build-system)
5553 `(#:modules ((srfi srfi-1)
5554 (guix build gnu-build-system)
5557 (let ((dirs '("SeekMiner"
5563 (modify-phases %standard-phases
5566 (substitute* "gen_tools_am"
5567 (("/usr/bin/env.*") (which "perl")))
5568 (invoke "bash" "gen_auto")
5570 (add-after 'build 'build-additional-tools
5571 (lambda* (#:key make-flags #:allow-other-keys)
5572 (for-each (lambda (dir)
5573 (with-directory-excursion (string-append "tools/" dir)
5574 (apply invoke "make" make-flags)))
5577 (add-after 'install 'install-additional-tools
5578 (lambda* (#:key make-flags #:allow-other-keys)
5579 (for-each (lambda (dir)
5580 (with-directory-excursion (string-append "tools/" dir)
5581 (apply invoke `("make" ,@make-flags "install"))))
5588 ("readline" ,readline)
5589 ("gengetopt" ,gengetopt)
5590 ("log4cpp" ,log4cpp)))
5592 `(("autoconf" ,autoconf)
5593 ("automake" ,automake)
5595 (home-page "http://seek.princeton.edu")
5596 (synopsis "Gene co-expression search engine")
5598 "SEEK is a computational gene co-expression search engine. SEEK provides
5599 biologists with a way to navigate the massive human expression compendium that
5600 now contains thousands of expression datasets. SEEK returns a robust ranking
5601 of co-expressed genes in the biological area of interest defined by the user's
5602 query genes. It also prioritizes thousands of expression datasets according
5603 to the user's query of interest.")
5604 (license license:cc-by3.0))))
5606 (define-public samtools
5614 (string-append "mirror://sourceforge/samtools/samtools/"
5615 version "/samtools-" version ".tar.bz2"))
5618 "10ilqbmm7ri8z431sn90lvbjwizd0hhkf9rcqw8j823hf26nhgq8"))
5619 (modules '((guix build utils)))
5621 ;; Delete bundled htslib.
5622 (delete-file-recursively "htslib-1.9")
5624 (build-system gnu-build-system)
5626 `(#:modules ((ice-9 ftw)
5628 (guix build gnu-build-system)
5630 #:configure-flags (list "--with-ncurses")
5632 (modify-phases %standard-phases
5633 (add-after 'unpack 'patch-tests
5635 (substitute* "test/test.pl"
5636 ;; The test script calls out to /bin/bash
5637 (("/bin/bash") (which "bash")))
5639 (add-after 'install 'install-library
5640 (lambda* (#:key outputs #:allow-other-keys)
5641 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
5642 (install-file "libbam.a" lib)
5644 (add-after 'install 'install-headers
5645 (lambda* (#:key outputs #:allow-other-keys)
5646 (let ((include (string-append (assoc-ref outputs "out")
5647 "/include/samtools/")))
5648 (for-each (lambda (file)
5649 (install-file file include))
5650 (scandir "." (lambda (name) (string-match "\\.h$" name))))
5652 (native-inputs `(("pkg-config" ,pkg-config)))
5654 `(("htslib" ,htslib)
5655 ("ncurses" ,ncurses)
5659 (home-page "http://samtools.sourceforge.net")
5660 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
5662 "Samtools implements various utilities for post-processing nucleotide
5663 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
5664 variant calling (in conjunction with bcftools), and a simple alignment
5666 (license license:expat)))
5668 (define-public samtools-0.1
5669 ;; This is the most recent version of the 0.1 line of samtools. The input
5670 ;; and output formats differ greatly from that used and produced by samtools
5671 ;; 1.x and is still used in many bioinformatics pipelines.
5672 (package (inherit samtools)
5678 (string-append "mirror://sourceforge/samtools/samtools/"
5679 version "/samtools-" version ".tar.bz2"))
5681 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
5683 `(#:tests? #f ;no "check" target
5685 (list "LIBCURSES=-lncurses")
5686 ,@(substitute-keyword-arguments (package-arguments samtools)
5688 `(modify-phases ,phases
5690 (lambda* (#:key outputs #:allow-other-keys)
5691 (let ((bin (string-append
5692 (assoc-ref outputs "out") "/bin")))
5694 (install-file "samtools" bin)
5696 (delete 'patch-tests)
5697 (delete 'configure))))))))
5699 (define-public mosaik
5700 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
5705 ;; There are no release tarballs nor tags.
5708 (url "https://github.com/wanpinglee/MOSAIK")
5710 (file-name (string-append name "-" version))
5713 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
5714 (build-system gnu-build-system)
5716 `(#:tests? #f ; no tests
5717 #:make-flags (list "CC=gcc")
5719 (modify-phases %standard-phases
5721 (lambda _ (chdir "src") #t))
5723 (lambda* (#:key outputs #:allow-other-keys)
5724 (let ((bin (string-append (assoc-ref outputs "out")
5727 (copy-recursively "../bin" bin)
5731 ("zlib:static" ,zlib "static")
5733 (supported-systems '("x86_64-linux"))
5734 (home-page "https://github.com/wanpinglee/MOSAIK")
5735 (synopsis "Map nucleotide sequence reads to reference genomes")
5737 "MOSAIK is a program for mapping second and third-generation sequencing
5738 reads to a reference genome. MOSAIK can align reads generated by all the
5739 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
5740 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
5741 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
5742 ;; code released into the public domain:
5743 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
5744 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
5745 (license (list license:gpl2+ license:public-domain)))))
5747 (define-public ngs-sdk
5754 (url "https://github.com/ncbi/ngs")
5756 (file-name (git-file-name name version))
5759 "1ix51c25hjn57w93qmwzw80xh2i34wx8j2hn7szh8p6w8i3az5qa"))))
5760 (build-system gnu-build-system)
5762 `(#:parallel-build? #f ; not supported
5763 #:tests? #f ; no "check" target
5765 (modify-phases %standard-phases
5767 (lambda* (#:key outputs #:allow-other-keys)
5768 (let ((out (assoc-ref outputs "out")))
5769 ;; Allow 'konfigure.perl' to find 'package.prl'.
5771 (string-append ".:" (getenv "PERL5LIB")))
5773 ;; The 'configure' script doesn't recognize things like
5774 ;; '--enable-fast-install'.
5775 (invoke "./configure"
5776 (string-append "--build-prefix=" (getcwd) "/build")
5777 (string-append "--prefix=" out))
5779 (add-after 'unpack 'enter-dir
5780 (lambda _ (chdir "ngs-sdk") #t)))))
5781 (native-inputs `(("perl" ,perl)))
5782 ;; According to the test
5783 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
5784 ;; in ngs-sdk/setup/konfigure.perl
5785 (supported-systems '("i686-linux" "x86_64-linux"))
5786 (home-page "https://github.com/ncbi/ngs")
5787 (synopsis "API for accessing Next Generation Sequencing data")
5789 "NGS is a domain-specific API for accessing reads, alignments and pileups
5790 produced from Next Generation Sequencing. The API itself is independent from
5791 any particular back-end implementation, and supports use of multiple back-ends
5793 (license license:public-domain)))
5795 (define-public java-ngs
5796 (package (inherit ngs-sdk)
5799 `(,@(substitute-keyword-arguments
5800 `(#:modules ((guix build gnu-build-system)
5804 ,@(package-arguments ngs-sdk))
5806 `(modify-phases ,phases
5807 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5809 `(("jdk" ,icedtea "jdk")
5810 ("ngs-sdk" ,ngs-sdk)))
5811 (synopsis "Java bindings for NGS SDK")))
5813 (define-public ncbi-vdb
5820 (url "https://github.com/ncbi/ncbi-vdb")
5822 (file-name (git-file-name name version))
5825 "0m8hlxscidsfqm9x9fyi62q6lpf1dv5115kgjjgnrkl49q9c27m6"))))
5826 (build-system gnu-build-system)
5828 `(#:parallel-build? #f ; not supported
5829 #:tests? #f ; no "check" target
5830 #:make-flags '("HAVE_HDF5=1")
5832 (modify-phases %standard-phases
5833 (add-after 'unpack 'make-files-writable
5834 (lambda _ (for-each make-file-writable (find-files "." ".*")) #t))
5835 (add-before 'configure 'set-perl-search-path
5837 ;; Work around "dotless @INC" build failure.
5839 (string-append (getcwd) "/setup:"
5840 (getenv "PERL5LIB")))
5842 ;; See https://github.com/ncbi/ncbi-vdb/issues/14
5843 (add-after 'unpack 'patch-krypto-flags
5845 (substitute* "libs/krypto/Makefile"
5846 (("-Wa,-march=generic64\\+aes") "")
5847 (("-Wa,-march=generic64\\+sse4") ""))
5850 (lambda* (#:key inputs outputs #:allow-other-keys)
5851 (let ((out (assoc-ref outputs "out")))
5852 ;; Override include path for libmagic
5853 (substitute* "setup/package.prl"
5854 (("name => 'magic', Include => '/usr/include'")
5855 (string-append "name=> 'magic', Include => '"
5856 (assoc-ref inputs "libmagic")
5859 ;; Install kdf5 library (needed by sra-tools)
5860 (substitute* "build/Makefile.install"
5861 (("LIBRARIES_TO_INSTALL =")
5862 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5864 (substitute* "build/Makefile.env"
5865 (("CFLAGS =" prefix)
5866 (string-append prefix "-msse2 ")))
5868 ;; Override search path for ngs-java
5869 (substitute* "setup/package.prl"
5870 (("/usr/local/ngs/ngs-java")
5871 (assoc-ref inputs "java-ngs")))
5873 ;; The 'configure' script doesn't recognize things like
5874 ;; '--enable-fast-install'.
5875 (invoke "./configure"
5876 (string-append "--build-prefix=" (getcwd) "/build")
5877 (string-append "--prefix=" (assoc-ref outputs "out"))
5878 (string-append "--debug")
5879 (string-append "--with-xml2-prefix="
5880 (assoc-ref inputs "libxml2"))
5881 (string-append "--with-ngs-sdk-prefix="
5882 (assoc-ref inputs "ngs-sdk"))
5883 (string-append "--with-hdf5-prefix="
5884 (assoc-ref inputs "hdf5")))
5886 (add-after 'install 'install-interfaces
5887 (lambda* (#:key outputs #:allow-other-keys)
5888 ;; Install interface libraries. On i686 the interface libraries
5889 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5890 ;; architecture name ("i386") instead of the target system prefix
5892 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5893 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5894 ,(system->linux-architecture
5895 (or (%current-target-system)
5898 (string-append (assoc-ref outputs "out")
5900 ;; Install interface headers
5901 (copy-recursively "interfaces"
5902 (string-append (assoc-ref outputs "out")
5905 ;; These files are needed by sra-tools.
5906 (add-after 'install 'install-configuration-files
5907 (lambda* (#:key outputs #:allow-other-keys)
5908 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5910 (install-file "libs/kfg/default.kfg" target)
5911 (install-file "libs/kfg/certs.kfg" target))
5914 `(("libxml2" ,libxml2)
5915 ("ngs-sdk" ,ngs-sdk)
5916 ("java-ngs" ,java-ngs)
5919 (native-inputs `(("perl" ,perl)))
5920 ;; NCBI-VDB requires SSE capability.
5921 (supported-systems '("i686-linux" "x86_64-linux"))
5922 (home-page "https://github.com/ncbi/ncbi-vdb")
5923 (synopsis "Database engine for genetic information")
5925 "The NCBI-VDB library implements a highly compressed columnar data
5926 warehousing engine that is most often used to store genetic information.
5927 Databases are stored in a portable image within the file system, and can be
5928 accessed/downloaded on demand across HTTP.")
5929 (license license:public-domain)))
5931 (define-public plink
5939 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5940 version "-src.zip"))
5942 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5943 (patches (search-patches "plink-1.07-unclobber-i.patch"
5944 "plink-endian-detection.patch"))))
5945 (build-system gnu-build-system)
5947 '(#:tests? #f ;no "check" target
5948 #:make-flags (list (string-append "LIB_LAPACK="
5949 (assoc-ref %build-inputs "lapack")
5950 "/lib/liblapack.so")
5953 ;; disable phoning home
5956 (modify-phases %standard-phases
5957 ;; no "configure" script
5960 (lambda* (#:key outputs #:allow-other-keys)
5961 (let ((bin (string-append (assoc-ref outputs "out")
5963 (install-file "plink" bin)
5967 ("lapack" ,lapack)))
5969 `(("unzip" ,unzip)))
5970 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5971 (synopsis "Whole genome association analysis toolset")
5973 "PLINK is a whole genome association analysis toolset, designed to
5974 perform a range of basic, large-scale analyses in a computationally efficient
5975 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5976 so there is no support for steps prior to this (e.g. study design and
5977 planning, generating genotype or CNV calls from raw data). Through
5978 integration with gPLINK and Haploview, there is some support for the
5979 subsequent visualization, annotation and storage of results.")
5980 ;; Code is released under GPLv2, except for fisher.h, which is under
5982 (license (list license:gpl2 license:lgpl2.1+))))
5984 (define-public plink-ng
5985 (package (inherit plink)
5992 (url "https://github.com/chrchang/plink-ng")
5993 (commit (string-append "v" version))))
5994 (file-name (git-file-name name version))
5996 (base32 "02npdwgkpfkdnhw819rhj5kw02a5k5m90b14zq9zzya4hyg929c0"))))
5997 (build-system gnu-build-system)
5999 '(#:tests? #f ;no "check" target
6000 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
6001 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
6003 "-f" "Makefile.std")
6005 (modify-phases %standard-phases
6006 (add-after 'unpack 'chdir
6007 (lambda _ (chdir "1.9") #t))
6008 (delete 'configure) ; no "configure" script
6010 (lambda* (#:key outputs #:allow-other-keys)
6011 (let ((bin (string-append (assoc-ref outputs "out")
6013 (install-file "plink" bin)
6018 ("openblas" ,openblas)))
6019 (home-page "https://www.cog-genomics.org/plink/")
6020 (license license:gpl3+)))
6022 (define-public smithlab-cpp
6023 (let ((revision "1")
6024 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
6026 (name "smithlab-cpp")
6027 (version (string-append "0." revision "." (string-take commit 7)))
6031 (url "https://github.com/smithlabcode/smithlab_cpp")
6033 (file-name (string-append name "-" version "-checkout"))
6036 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
6037 (build-system gnu-build-system)
6039 `(#:modules ((guix build gnu-build-system)
6042 #:tests? #f ;no "check" target
6044 (modify-phases %standard-phases
6045 (add-after 'unpack 'use-samtools-headers
6047 (substitute* '("SAM.cpp"
6049 (("sam.h") "samtools/sam.h"))
6052 (lambda* (#:key outputs #:allow-other-keys)
6053 (let* ((out (assoc-ref outputs "out"))
6054 (lib (string-append out "/lib"))
6055 (include (string-append out "/include/smithlab-cpp")))
6058 (for-each (cut install-file <> lib)
6059 (find-files "." "\\.o$"))
6060 (for-each (cut install-file <> include)
6061 (find-files "." "\\.hpp$")))
6063 (delete 'configure))))
6065 `(("samtools" ,samtools-0.1)
6067 (home-page "https://github.com/smithlabcode/smithlab_cpp")
6068 (synopsis "C++ helper library for functions used in Smith lab projects")
6070 "Smithlab CPP is a C++ library that includes functions used in many of
6071 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
6072 structures, classes for genomic regions, mapped sequencing reads, etc.")
6073 (license license:gpl3+))))
6075 (define-public preseq
6081 (uri (string-append "https://github.com/smithlabcode/preseq/"
6082 "releases/download/v" version
6083 "/preseq_v" version ".tar.bz2"))
6085 (base32 "149x9xmk1wy1gff85325yfzqc0qk4sgp1w6gbyj9cnji4x1dszbl"))
6086 (modules '((guix build utils)))
6088 ;; Remove bundled samtools.
6089 (delete-file-recursively "samtools")
6091 (build-system gnu-build-system)
6093 `(#:tests? #f ;no "check" target
6095 (modify-phases %standard-phases
6096 (delete 'configure))
6098 (list (string-append "PREFIX="
6099 (assoc-ref %outputs "out"))
6100 (string-append "LIBBAM="
6101 (assoc-ref %build-inputs "samtools")
6103 (string-append "SMITHLAB_CPP="
6104 (assoc-ref %build-inputs "smithlab-cpp")
6107 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
6110 ("samtools" ,samtools-0.1)
6111 ("smithlab-cpp" ,smithlab-cpp)
6113 (home-page "http://smithlabresearch.org/software/preseq/")
6114 (synopsis "Program for analyzing library complexity")
6116 "The preseq package is aimed at predicting and estimating the complexity
6117 of a genomic sequencing library, equivalent to predicting and estimating the
6118 number of redundant reads from a given sequencing depth and how many will be
6119 expected from additional sequencing using an initial sequencing experiment.
6120 The estimates can then be used to examine the utility of further sequencing,
6121 optimize the sequencing depth, or to screen multiple libraries to avoid low
6122 complexity samples.")
6123 (license license:gpl3+)))
6125 (define-public python-screed
6127 (name "python-screed")
6132 (uri (pypi-uri "screed" version))
6135 "148vcb7w2wr6a4w6vs2bsxanbqibxfk490zbcbg4m61s8669zdjx"))))
6136 (build-system python-build-system)
6139 (modify-phases %standard-phases
6140 ;; Tests must be run after installation, as the "screed" command does
6141 ;; not exist right after building.
6143 (add-after 'install 'check
6144 (lambda* (#:key inputs outputs #:allow-other-keys)
6145 (let ((out (assoc-ref outputs "out")))
6146 (setenv "PYTHONPATH"
6147 (string-append out "/lib/python"
6148 (string-take (string-take-right
6149 (assoc-ref inputs "python")
6152 (getenv "PYTHONPATH")))
6153 (setenv "PATH" (string-append out "/bin:" (getenv "PATH"))))
6154 (invoke "python" "setup.py" "test")
6157 `(("python-pytest" ,python-pytest)
6158 ("python-pytest-cov" ,python-pytest-cov)
6159 ("python-pytest-runner" ,python-pytest-runner)))
6161 `(("python-bz2file" ,python-bz2file)))
6162 (home-page "https://github.com/dib-lab/screed/")
6163 (synopsis "Short read sequence database utilities")
6164 (description "Screed parses FASTA and FASTQ files and generates databases.
6165 Values such as sequence name, sequence description, sequence quality and the
6166 sequence itself can be retrieved from these databases.")
6167 (license license:bsd-3)))
6169 (define-public python2-screed
6170 (package-with-python2 python-screed))
6172 (define-public sra-tools
6180 (url "https://github.com/ncbi/sra-tools")
6182 (file-name (git-file-name name version))
6185 "1cr2mijkfs5sm35ffjs6861qsd1qkgnhnbavdv65zg5d655abbjf"))))
6186 (build-system gnu-build-system)
6188 `(#:parallel-build? #f ; not supported
6189 #:tests? #f ; no "check" target
6191 (list (string-append "DEFAULT_CRT="
6192 (assoc-ref %build-inputs "ncbi-vdb")
6194 (string-append "DEFAULT_KFG="
6195 (assoc-ref %build-inputs "ncbi-vdb")
6197 (string-append "VDB_LIBDIR="
6198 (assoc-ref %build-inputs "ncbi-vdb")
6199 ,(if (string-prefix? "x86_64"
6200 (or (%current-target-system)
6205 (modify-phases %standard-phases
6206 (add-before 'configure 'set-perl-search-path
6208 ;; Work around "dotless @INC" build failure.
6210 (string-append (getcwd) "/setup:"
6211 (getenv "PERL5LIB")))
6214 (lambda* (#:key inputs outputs #:allow-other-keys)
6215 ;; The build system expects a directory containing the sources and
6216 ;; raw build output of ncbi-vdb, including files that are not
6217 ;; installed. Since we are building against an installed version of
6218 ;; ncbi-vdb, the following modifications are needed.
6219 (substitute* "setup/konfigure.perl"
6220 ;; Make the configure script look for the "ilib" directory of
6221 ;; "ncbi-vdb" without first checking for the existence of a
6222 ;; matching library in its "lib" directory.
6223 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
6224 "my $f = File::Spec->catdir($ilibdir, $ilib);")
6225 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
6226 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
6227 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
6230 (substitute* "tools/copycat/Makefile"
6231 (("smagic-static") "lmagic"))
6232 (substitute* "tools/driver-tool/utf8proc/Makefile"
6233 (("CC\\?=gcc") "myCC=gcc")
6234 (("\\(CC\\)") "(myCC)"))
6236 ;; The 'configure' script doesn't recognize things like
6237 ;; '--enable-fast-install'.
6238 (invoke "./configure"
6239 (string-append "--build-prefix=" (getcwd) "/build")
6240 (string-append "--prefix=" (assoc-ref outputs "out"))
6241 (string-append "--debug")
6242 (string-append "--with-fuse-prefix="
6243 (assoc-ref inputs "fuse"))
6244 (string-append "--with-magic-prefix="
6245 (assoc-ref inputs "libmagic"))
6246 ;; TODO: building with libxml2 fails with linker errors
6248 (string-append "--with-xml2-prefix="
6249 (assoc-ref inputs "libxml2"))
6250 (string-append "--with-ncbi-vdb-sources="
6251 (assoc-ref inputs "ncbi-vdb"))
6252 (string-append "--with-ncbi-vdb-build="
6253 (assoc-ref inputs "ncbi-vdb"))
6254 (string-append "--with-ngs-sdk-prefix="
6255 (assoc-ref inputs "ngs-sdk"))
6256 (string-append "--with-hdf5-prefix="
6257 (assoc-ref inputs "hdf5")))
6259 (native-inputs `(("perl" ,perl)))
6261 `(("ngs-sdk" ,ngs-sdk)
6262 ("ncbi-vdb" ,ncbi-vdb)
6267 ("python" ,python-wrapper)))
6269 "https://trace.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
6270 (synopsis "Tools and libraries for reading and writing sequencing data")
6272 "The SRA Toolkit from NCBI is a collection of tools and libraries for
6273 reading of sequencing files from the Sequence Read Archive (SRA) database and
6274 writing files into the .sra format.")
6275 (license license:public-domain)))
6277 (define-public seqan
6283 (uri (string-append "https://github.com/seqan/seqan/releases/"
6284 "download/seqan-v" version
6285 "/seqan-library-" version ".tar.xz"))
6288 "19a1rlxx03qy1i1iriicly68w64yjxbv24g9gdywnfmq998v35yx"))))
6289 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6290 ;; makes sense to split the outputs.
6291 (outputs '("out" "doc"))
6292 (build-system trivial-build-system)
6294 `(#:modules ((guix build utils))
6297 (use-modules (guix build utils))
6298 (let ((tar (assoc-ref %build-inputs "tar"))
6299 (xz (assoc-ref %build-inputs "xz"))
6300 (out (assoc-ref %outputs "out"))
6301 (doc (assoc-ref %outputs "doc")))
6302 (setenv "PATH" (string-append tar "/bin:" xz "/bin"))
6303 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6304 (chdir (string-append "seqan-library-" ,version))
6305 (copy-recursively "include" (string-append out "/include"))
6306 (copy-recursively "share" (string-append doc "/share"))
6309 `(("source" ,source)
6312 (home-page "http://www.seqan.de")
6313 (synopsis "Library for nucleotide sequence analysis")
6315 "SeqAn is a C++ library of efficient algorithms and data structures for
6316 the analysis of sequences with the focus on biological data. It contains
6317 algorithms and data structures for string representation and their
6318 manipulation, online and indexed string search, efficient I/O of
6319 bioinformatics file formats, sequence alignment, and more.")
6320 (license license:bsd-3)))
6322 (define-public seqan-1
6323 (package (inherit seqan)
6328 (uri (string-append "http://packages.seqan.de/seqan-library/"
6329 "seqan-library-" version ".tar.bz2"))
6332 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
6333 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6334 ;; makes sense to split the outputs.
6335 (outputs '("out" "doc"))
6336 (build-system trivial-build-system)
6338 `(#:modules ((guix build utils))
6341 (use-modules (guix build utils))
6342 (let ((tar (assoc-ref %build-inputs "tar"))
6343 (bzip (assoc-ref %build-inputs "bzip2"))
6344 (out (assoc-ref %outputs "out"))
6345 (doc (assoc-ref %outputs "doc")))
6346 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
6347 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6348 (chdir (string-append "seqan-library-" ,version))
6349 (copy-recursively "include" (string-append out "/include"))
6350 (copy-recursively "share" (string-append doc "/share"))
6353 `(("source" ,source)
6355 ("bzip2" ,bzip2)))))
6357 (define-public seqmagick
6364 (uri (pypi-uri "seqmagick" version))
6367 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
6368 (build-system python-build-system)
6370 `(("python-biopython" ,python-biopython)))
6372 `(("python-nose" ,python-nose)))
6373 (home-page "https://github.com/fhcrc/seqmagick")
6374 (synopsis "Tools for converting and modifying sequence files")
6376 "Bioinformaticians often have to convert sequence files between formats
6377 and do little manipulations on them, and it's not worth writing scripts for
6378 that. Seqmagick is a utility to expose the file format conversion in
6379 BioPython in a convenient way. Instead of having a big mess of scripts, there
6380 is one that takes arguments.")
6381 (license license:gpl3)))
6383 (define-public seqtk
6390 (url "https://github.com/lh3/seqtk")
6391 (commit (string-append "v" version))))
6392 (file-name (git-file-name name version))
6395 "1bfzlqa84b5s1qi22blmmw2s8xdyp9h9ydcq22pfjhh5gab3yz6l"))))
6396 (build-system gnu-build-system)
6399 (modify-phases %standard-phases
6402 ;; There are no tests, so we just run a sanity check.
6403 (lambda _ (invoke "./seqtk" "seq") #t))
6405 (lambda* (#:key outputs #:allow-other-keys)
6406 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6407 (install-file "seqtk" bin)
6411 (home-page "https://github.com/lh3/seqtk")
6412 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
6414 "Seqtk is a fast and lightweight tool for processing sequences in the
6415 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
6416 optionally compressed by gzip.")
6417 (license license:expat)))
6419 (define-public snap-aligner
6421 (name "snap-aligner")
6422 (version "1.0beta.18")
6426 (url "https://github.com/amplab/snap")
6427 (commit (string-append "v" version))))
6428 (file-name (git-file-name name version))
6431 "01w3qq4wm07z73vky0cfwlmrbf50n3w722cxrlzxfi99mnb808d8"))))
6432 (build-system gnu-build-system)
6435 (modify-phases %standard-phases
6437 (replace 'check (lambda _ (invoke "./unit_tests") #t))
6439 (lambda* (#:key outputs #:allow-other-keys)
6440 (let* ((out (assoc-ref outputs "out"))
6441 (bin (string-append out "/bin")))
6442 (install-file "snap-aligner" bin)
6443 (install-file "SNAPCommand" bin)
6447 (home-page "http://snap.cs.berkeley.edu/")
6448 (synopsis "Short read DNA sequence aligner")
6450 "SNAP is a fast and accurate aligner for short DNA reads. It is
6451 optimized for modern read lengths of 100 bases or higher, and takes advantage
6452 of these reads to align data quickly through a hash-based indexing scheme.")
6453 ;; 32-bit systems are not supported by the unpatched code.
6454 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
6455 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
6456 ;; systems without a lot of memory cannot make good use of this program.
6457 (supported-systems '("x86_64-linux"))
6458 (license license:asl2.0)))
6460 (define-public sortmerna
6468 (url "https://github.com/biocore/sortmerna")
6470 (file-name (git-file-name name version))
6473 "0j3mbz4n25738yijmjbr5r4fyvkgm8v5vn3sshyfvmyqf5q9byqf"))))
6474 (build-system gnu-build-system)
6475 (outputs '("out" ;for binaries
6476 "db")) ;for sequence databases
6479 (modify-phases %standard-phases
6481 (lambda* (#:key outputs #:allow-other-keys)
6482 (let* ((out (assoc-ref outputs "out"))
6483 (bin (string-append out "/bin"))
6484 (db (assoc-ref outputs "db"))
6486 (string-append db "/share/sortmerna/rRNA_databases")))
6487 (install-file "sortmerna" bin)
6488 (install-file "indexdb_rna" bin)
6489 (for-each (lambda (file)
6490 (install-file file share))
6491 (find-files "rRNA_databases" ".*fasta"))
6495 (home-page "https://bioinfo.lifl.fr/RNA/sortmerna/")
6496 (synopsis "Biological sequence analysis tool for NGS reads")
6498 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
6499 and operational taxonomic unit (OTU) picking of next generation
6500 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
6501 allows for fast and sensitive analyses of nucleotide sequences. The main
6502 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
6503 ;; The source includes x86 specific code
6504 (supported-systems '("x86_64-linux" "i686-linux"))
6505 (license license:lgpl3)))
6514 (url "https://github.com/alexdobin/STAR")
6516 (file-name (git-file-name name version))
6519 "1hgiqw5qhs0pc1xazzihcfd92na02xyq2kb469z04y1v51kpvvjq"))
6520 (modules '((guix build utils)))
6523 (substitute* "source/Makefile"
6525 ;; Remove pre-built binaries and bundled htslib sources.
6526 (delete-file-recursively "bin/MacOSX_x86_64")
6527 (delete-file-recursively "bin/Linux_x86_64")
6528 (delete-file-recursively "bin/Linux_x86_64_static")
6529 (delete-file-recursively "source/htslib")
6531 (build-system gnu-build-system)
6533 '(#:tests? #f ;no check target
6534 #:make-flags '("STAR")
6536 (modify-phases %standard-phases
6537 (add-after 'unpack 'enter-source-dir
6538 (lambda _ (chdir "source") #t))
6539 (add-after 'enter-source-dir 'make-reproducible
6541 (substitute* "Makefile"
6542 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
6543 (string-append pre "Built with Guix" post)))
6545 ;; See https://github.com/alexdobin/STAR/pull/562
6546 (add-after 'enter-source-dir 'add-missing-header
6548 (substitute* "SoloReadFeature_inputRecords.cpp"
6549 (("#include \"binarySearch2.h\"" h)
6550 (string-append h "\n#include <math.h>")))
6552 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
6554 (substitute* "Makefile"
6555 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
6557 (substitute* '("BAMfunctions.cpp"
6562 "bamRemoveDuplicates.cpp")
6563 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
6564 (string-append "#include <" header ">")))
6565 (substitute* "IncludeDefine.h"
6566 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
6567 (string-append "<" header ">")))
6570 (lambda* (#:key outputs #:allow-other-keys)
6571 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6572 (install-file "STAR" bin))
6574 (delete 'configure))))
6578 `(("htslib" ,htslib)
6580 (home-page "https://github.com/alexdobin/STAR")
6581 (synopsis "Universal RNA-seq aligner")
6583 "The Spliced Transcripts Alignment to a Reference (STAR) software is
6584 based on a previously undescribed RNA-seq alignment algorithm that uses
6585 sequential maximum mappable seed search in uncompressed suffix arrays followed
6586 by seed clustering and stitching procedure. In addition to unbiased de novo
6587 detection of canonical junctions, STAR can discover non-canonical splices and
6588 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
6590 ;; Only 64-bit systems are supported according to the README.
6591 (supported-systems '("x86_64-linux" "mips64el-linux"))
6592 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
6593 (license license:gpl3+)))
6595 (define-public starlong
6596 (package (inherit star)
6599 (substitute-keyword-arguments (package-arguments star)
6600 ((#:make-flags flags)
6603 `(modify-phases ,phases
6604 ;; Allow extra long sequence reads.
6605 (add-after 'unpack 'make-extra-long
6607 (substitute* "source/IncludeDefine.h"
6608 (("(#define DEF_readNameLengthMax ).*" _ match)
6609 (string-append match "900000\n")))
6612 (lambda* (#:key outputs #:allow-other-keys)
6613 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6614 (install-file "STARlong" bin))
6617 (define-public subread
6623 (uri (string-append "mirror://sourceforge/subread/subread-"
6624 version "/subread-" version "-source.tar.gz"))
6627 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
6628 (build-system gnu-build-system)
6630 `(#:tests? #f ;no "check" target
6631 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
6632 ;; optimizations by default, so we override these flags such that x86_64
6633 ;; flags are only added when the build target is an x86_64 system.
6635 (list (let ((system ,(or (%current-target-system)
6637 (flags '("-ggdb" "-fomit-frame-pointer"
6638 "-ffast-math" "-funroll-loops"
6639 "-fmessage-length=0"
6640 "-O9" "-Wall" "-DMAKE_FOR_EXON"
6642 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
6643 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
6644 (if (string-prefix? "x86_64" system)
6645 (string-append "CCFLAGS=" (string-join (append flags flags64)))
6646 (string-append "CCFLAGS=" (string-join flags))))
6647 "-f" "Makefile.Linux"
6648 "CC=gcc ${CCFLAGS}")
6650 (modify-phases %standard-phases
6651 (add-after 'unpack 'enter-dir
6652 (lambda _ (chdir "src") #t))
6654 (lambda* (#:key outputs #:allow-other-keys)
6655 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6657 (copy-recursively "../bin" bin))
6659 ;; no "configure" script
6660 (delete 'configure))))
6661 (inputs `(("zlib" ,zlib)))
6662 (home-page "http://bioinf.wehi.edu.au/subread-package/")
6663 (synopsis "Tool kit for processing next-gen sequencing data")
6665 "The subread package contains the following tools: subread aligner, a
6666 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
6667 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
6668 features; exactSNP: a SNP caller that discovers SNPs by testing signals
6669 against local background noises.")
6670 (license license:gpl3+)))
6672 (define-public stringtie
6678 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
6679 "stringtie-" version ".tar.gz"))
6682 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
6683 (modules '((guix build utils)))
6686 (delete-file-recursively "samtools-0.1.18")
6688 (build-system gnu-build-system)
6690 `(#:tests? #f ;no test suite
6692 (modify-phases %standard-phases
6693 ;; no configure script
6695 (add-before 'build 'use-system-samtools
6697 (substitute* "Makefile"
6698 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
6700 (substitute* '("gclib/GBam.h"
6702 (("#include \"(bam|sam|kstring).h\"" _ header)
6703 (string-append "#include <samtools/" header ".h>")))
6705 (add-after 'unpack 'remove-duplicate-typedef
6707 ;; This typedef conflicts with the typedef in
6708 ;; glibc-2.25/include/bits/types.h
6709 (substitute* "gclib/GThreads.h"
6710 (("typedef long long __intmax_t;") ""))
6713 (lambda* (#:key outputs #:allow-other-keys)
6714 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6715 (install-file "stringtie" bin)
6718 `(("samtools" ,samtools-0.1)
6720 (home-page "http://ccb.jhu.edu/software/stringtie/")
6721 (synopsis "Transcript assembly and quantification for RNA-Seq data")
6723 "StringTie is a fast and efficient assembler of RNA-Seq sequence
6724 alignments into potential transcripts. It uses a novel network flow algorithm
6725 as well as an optional de novo assembly step to assemble and quantitate
6726 full-length transcripts representing multiple splice variants for each gene
6727 locus. Its input can include not only the alignments of raw reads used by
6728 other transcript assemblers, but also alignments of longer sequences that have
6729 been assembled from those reads. To identify differentially expressed genes
6730 between experiments, StringTie's output can be processed either by the
6731 Cuffdiff or Ballgown programs.")
6732 (license license:artistic2.0)))
6734 (define-public taxtastic
6739 ;; The Pypi version does not include tests.
6742 (url "https://github.com/fhcrc/taxtastic")
6743 (commit (string-append "v" version))))
6744 (file-name (git-file-name name version))
6747 "1sv8mkg64jn7zdwf1jj71c16686yrwxk0apb1l8sjszy9p166g0p"))))
6748 (build-system python-build-system)
6751 (modify-phases %standard-phases
6752 (add-after 'unpack 'prepare-directory
6754 ;; The git checkout must be writable for tests.
6755 (for-each make-file-writable (find-files "."))
6756 ;; This test fails, but the error is not caught by the test
6757 ;; framework, so the tests fail...
6758 (substitute* "tests/test_taxit.py"
6759 (("self.cmd_fails\\(''\\)")
6760 "self.cmd_fails('nothing')"))
6761 ;; This version file is expected to be created with git describe.
6762 (mkdir-p "taxtastic/data")
6763 (with-output-to-file "taxtastic/data/ver"
6764 (lambda () (display ,version)))
6766 (add-after 'unpack 'python37-compatibility
6768 (substitute* "taxtastic/utils.py"
6769 (("import csv") "import csv, errno")
6770 (("os.errno") "errno"))
6773 ;; Note, this fails to run with "-v" as it tries to write to a
6774 ;; closed output stream.
6775 (lambda _ (invoke "python" "-m" "unittest") #t)))))
6777 `(("python-sqlalchemy" ,python-sqlalchemy)
6778 ("python-decorator" ,python-decorator)
6779 ("python-biopython" ,python-biopython)
6780 ("python-pandas" ,python-pandas)
6781 ("python-psycopg2" ,python-psycopg2)
6782 ("python-fastalite" ,python-fastalite)
6783 ("python-pyyaml" ,python-pyyaml)
6784 ("python-six" ,python-six)
6785 ("python-jinja2" ,python-jinja2)
6786 ("python-dendropy" ,python-dendropy)))
6787 (home-page "https://github.com/fhcrc/taxtastic")
6788 (synopsis "Tools for taxonomic naming and annotation")
6790 "Taxtastic is software written in python used to build and maintain
6791 reference packages i.e. collections of reference trees, reference alignments,
6792 profiles, and associated taxonomic information.")
6793 (license license:gpl3+)))
6795 (define-public vcftools
6802 "https://github.com/vcftools/vcftools/releases/download/v"
6803 version "/vcftools-" version ".tar.gz"))
6806 "1qqlx7flfv7axrjwkaz6njkscsl1d0jw98ns8d8bh1n1hd1pgz6v"))))
6807 (build-system gnu-build-system)
6809 `(#:tests? #f ; no "check" target
6811 "CFLAGS=-O2" ; override "-m64" flag
6812 (string-append "PREFIX=" (assoc-ref %outputs "out"))
6813 (string-append "MANDIR=" (assoc-ref %outputs "out")
6814 "/share/man/man1"))))
6816 `(("pkg-config" ,pkg-config)))
6820 (home-page "https://vcftools.github.io/")
6821 (synopsis "Tools for working with VCF files")
6823 "VCFtools is a program package designed for working with VCF files, such
6824 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
6825 provide easily accessible methods for working with complex genetic variation
6826 data in the form of VCF files.")
6827 ;; The license is declared as LGPLv3 in the README and
6828 ;; at https://vcftools.github.io/license.html
6829 (license license:lgpl3)))
6831 (define-public infernal
6837 (uri (string-append "http://eddylab.org/software/infernal/"
6838 "infernal-" version ".tar.gz"))
6841 "0pm8bm3s6nfa0av4x6m6h27lsg12b3lz3jm0fyh1mc77l2isd61v"))))
6842 (build-system gnu-build-system)
6845 ("python" ,python))) ; for tests
6846 (home-page "http://eddylab.org/infernal/")
6847 (synopsis "Inference of RNA alignments")
6848 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
6849 searching DNA sequence databases for RNA structure and sequence similarities.
6850 It is an implementation of a special case of profile stochastic context-free
6851 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
6852 profile, but it scores a combination of sequence consensus and RNA secondary
6853 structure consensus, so in many cases, it is more capable of identifying RNA
6854 homologs that conserve their secondary structure more than their primary
6856 ;; Infernal 1.1.3 requires VMX or SSE capability for parallel instructions.
6857 (supported-systems '("i686-linux" "x86_64-linux"))
6858 (license license:bsd-3)))
6860 (define-public r-scde
6867 (url "https://github.com/hms-dbmi/scde")
6869 (file-name (git-file-name name version))
6872 "10na2gyka24mszdxf92wz9h2c13hdf1ww30c68gfsw53lvvhhhxb"))))
6873 (build-system r-build-system)
6875 `(("r-rcpp" ,r-rcpp)
6876 ("r-rcpparmadillo" ,r-rcpparmadillo)
6879 ("r-rjson" ,r-rjson)
6880 ("r-cairo" ,r-cairo)
6881 ("r-rcolorbrewer" ,r-rcolorbrewer)
6882 ("r-edger" ,r-edger)
6883 ("r-quantreg" ,r-quantreg)
6885 ("r-rmtstat" ,r-rmtstat)
6886 ("r-extremes" ,r-extremes)
6887 ("r-pcamethods" ,r-pcamethods)
6888 ("r-biocparallel" ,r-biocparallel)
6889 ("r-flexmix" ,r-flexmix)))
6890 (home-page "https://hms-dbmi.github.io/scde/")
6891 (synopsis "R package for analyzing single-cell RNA-seq data")
6892 (description "The SCDE package implements a set of statistical methods for
6893 analyzing single-cell RNA-seq data. SCDE fits individual error models for
6894 single-cell RNA-seq measurements. These models can then be used for
6895 assessment of differential expression between groups of cells, as well as
6896 other types of analysis. The SCDE package also contains the pagoda framework
6897 which applies pathway and gene set overdispersion analysis to identify aspects
6898 of transcriptional heterogeneity among single cells.")
6899 ;; See https://github.com/hms-dbmi/scde/issues/38
6900 (license license:gpl2)))
6902 (define-public r-centipede
6904 (name "r-centipede")
6908 (uri (string-append "http://download.r-forge.r-project.org/"
6909 "src/contrib/CENTIPEDE_" version ".tar.gz"))
6912 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
6913 (build-system r-build-system)
6914 (home-page "http://centipede.uchicago.edu/")
6915 (synopsis "Predict transcription factor binding sites")
6917 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
6918 of the genome that are bound by particular transcription factors. It starts
6919 by identifying a set of candidate binding sites, and then aims to classify the
6920 sites according to whether each site is bound or not bound by a transcription
6921 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
6922 between two different types of motif instances using as much relevant
6923 information as possible.")
6924 (license (list license:gpl2+ license:gpl3+))))
6926 (define-public r-genefilter
6928 (name "r-genefilter")
6933 (uri (bioconductor-uri "genefilter" version))
6936 "1sbbrnq6p90fri0ik6aq2zw26kasw63nyiy7xkzrj6vgyq7x258g"))))
6937 (build-system r-build-system)
6939 `(("gfortran" ,gfortran)
6940 ("r-knitr" ,r-knitr)))
6942 `(("r-annotate" ,r-annotate)
6943 ("r-annotationdbi" ,r-annotationdbi)
6944 ("r-biobase" ,r-biobase)
6945 ("r-biocgenerics" ,r-biocgenerics)
6946 ("r-survival" ,r-survival)))
6947 (home-page "https://bioconductor.org/packages/genefilter")
6948 (synopsis "Filter genes from high-throughput experiments")
6950 "This package provides basic functions for filtering genes from
6951 high-throughput sequencing experiments.")
6952 (license license:artistic2.0)))
6954 (define-public r-deseq2
6961 (uri (bioconductor-uri "DESeq2" version))
6964 "0xh12c2skr0bbv893p05gvbismkcnqw8zwh7yz4wmycgajfzg2pp"))))
6965 (properties `((upstream-name . "DESeq2")))
6966 (build-system r-build-system)
6968 `(("r-biobase" ,r-biobase)
6969 ("r-biocgenerics" ,r-biocgenerics)
6970 ("r-biocparallel" ,r-biocparallel)
6971 ("r-genefilter" ,r-genefilter)
6972 ("r-geneplotter" ,r-geneplotter)
6973 ("r-genomicranges" ,r-genomicranges)
6974 ("r-ggplot2" ,r-ggplot2)
6975 ("r-iranges" ,r-iranges)
6976 ("r-locfit" ,r-locfit)
6978 ("r-rcpparmadillo" ,r-rcpparmadillo)
6979 ("r-s4vectors" ,r-s4vectors)
6980 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6982 `(("r-knitr" ,r-knitr)))
6983 (home-page "https://bioconductor.org/packages/DESeq2")
6984 (synopsis "Differential gene expression analysis")
6986 "This package provides functions to estimate variance-mean dependence in
6987 count data from high-throughput nucleotide sequencing assays and test for
6988 differential expression based on a model using the negative binomial
6990 (license license:lgpl3+)))
6992 (define-public r-dexseq
6999 (uri (bioconductor-uri "DEXSeq" version))
7002 "1m03awaw06mfv5gszq23k5apsqqzjqa5rcwp20y4xbpl7bywpsyl"))))
7003 (properties `((upstream-name . "DEXSeq")))
7004 (build-system r-build-system)
7006 `(("r-annotationdbi" ,r-annotationdbi)
7007 ("r-biobase" ,r-biobase)
7008 ("r-biocgenerics" ,r-biocgenerics)
7009 ("r-biocparallel" ,r-biocparallel)
7010 ("r-biomart" ,r-biomart)
7011 ("r-deseq2" ,r-deseq2)
7012 ("r-genefilter" ,r-genefilter)
7013 ("r-geneplotter" ,r-geneplotter)
7014 ("r-genomicranges" ,r-genomicranges)
7015 ("r-hwriter" ,r-hwriter)
7016 ("r-iranges" ,r-iranges)
7017 ("r-rcolorbrewer" ,r-rcolorbrewer)
7018 ("r-rsamtools" ,r-rsamtools)
7019 ("r-s4vectors" ,r-s4vectors)
7020 ("r-statmod" ,r-statmod)
7021 ("r-stringr" ,r-stringr)
7022 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7024 `(("r-knitr" ,r-knitr)))
7025 (home-page "https://bioconductor.org/packages/DEXSeq")
7026 (synopsis "Inference of differential exon usage in RNA-Seq")
7028 "This package is focused on finding differential exon usage using RNA-seq
7029 exon counts between samples with different experimental designs. It provides
7030 functions that allows the user to make the necessary statistical tests based
7031 on a model that uses the negative binomial distribution to estimate the
7032 variance between biological replicates and generalized linear models for
7033 testing. The package also provides functions for the visualization and
7034 exploration of the results.")
7035 (license license:gpl3+)))
7037 (define-public r-annotationforge
7039 (name "r-annotationforge")
7044 (uri (bioconductor-uri "AnnotationForge" version))
7047 "1a2155jxbwc6qr3dcyvp850grhdr7czc7bs3s87ff4sgdl0jp3jw"))))
7049 `((upstream-name . "AnnotationForge")))
7050 (build-system r-build-system)
7052 `(("r-annotationdbi" ,r-annotationdbi)
7053 ("r-biobase" ,r-biobase)
7054 ("r-biocgenerics" ,r-biocgenerics)
7056 ("r-rcurl" ,r-rcurl)
7057 ("r-rsqlite" ,r-rsqlite)
7058 ("r-s4vectors" ,r-s4vectors)
7061 `(("r-knitr" ,r-knitr)))
7062 (home-page "https://bioconductor.org/packages/AnnotationForge")
7063 (synopsis "Code for building annotation database packages")
7065 "This package provides code for generating Annotation packages and their
7066 databases. Packages produced are intended to be used with AnnotationDbi.")
7067 (license license:artistic2.0)))
7069 (define-public r-rbgl
7076 (uri (bioconductor-uri "RBGL" version))
7079 "079599a6xn2i7snfn2vgshkw0c00rrfhj44pvi03ap8id29bkayy"))))
7080 (properties `((upstream-name . "RBGL")))
7081 (build-system r-build-system)
7084 ("r-graph" ,r-graph)))
7085 (home-page "https://www.bioconductor.org/packages/RBGL")
7086 (synopsis "Interface to the Boost graph library")
7088 "This package provides a fairly extensive and comprehensive interface to
7089 the graph algorithms contained in the Boost library.")
7090 (license license:artistic2.0)))
7092 (define-public r-gseabase
7099 (uri (bioconductor-uri "GSEABase" version))
7102 "1k4faj53cwvqijad8cf7fcghzxcv9shlbpl8n73bsncc8k192y2j"))))
7103 (properties `((upstream-name . "GSEABase")))
7104 (build-system r-build-system)
7106 `(("r-annotate" ,r-annotate)
7107 ("r-annotationdbi" ,r-annotationdbi)
7108 ("r-biobase" ,r-biobase)
7109 ("r-biocgenerics" ,r-biocgenerics)
7110 ("r-graph" ,r-graph)
7113 `(("r-knitr" ,r-knitr)))
7114 (home-page "https://bioconductor.org/packages/GSEABase")
7115 (synopsis "Gene set enrichment data structures and methods")
7117 "This package provides classes and methods to support @dfn{Gene Set
7118 Enrichment Analysis} (GSEA).")
7119 (license license:artistic2.0)))
7121 (define-public r-category
7128 (uri (bioconductor-uri "Category" version))
7131 "1grspdzk5a4vidnxwcd1jmy1vcn494aydsp3vydx235yv7iqac1b"))))
7132 (properties `((upstream-name . "Category")))
7133 (build-system r-build-system)
7135 `(("r-annotate" ,r-annotate)
7136 ("r-annotationdbi" ,r-annotationdbi)
7137 ("r-biobase" ,r-biobase)
7138 ("r-biocgenerics" ,r-biocgenerics)
7139 ("r-genefilter" ,r-genefilter)
7140 ("r-graph" ,r-graph)
7141 ("r-gseabase" ,r-gseabase)
7142 ("r-matrix" ,r-matrix)
7145 (home-page "https://bioconductor.org/packages/Category")
7146 (synopsis "Category analysis")
7148 "This package provides a collection of tools for performing category
7150 (license license:artistic2.0)))
7152 (define-public r-gostats
7159 (uri (bioconductor-uri "GOstats" version))
7162 "00q39cyv4l28r6s9gjnd0qhl7h80vmwp4lpmchisqzj44xzyics9"))))
7163 (properties `((upstream-name . "GOstats")))
7164 (build-system r-build-system)
7166 `(("r-annotate" ,r-annotate)
7167 ("r-annotationdbi" ,r-annotationdbi)
7168 ("r-annotationforge" ,r-annotationforge)
7169 ("r-biobase" ,r-biobase)
7170 ("r-category" ,r-category)
7171 ("r-go-db" ,r-go-db)
7172 ("r-graph" ,r-graph)
7173 ("r-rgraphviz" ,r-rgraphviz)
7174 ("r-rbgl" ,r-rbgl)))
7175 (home-page "https://bioconductor.org/packages/GOstats")
7176 (synopsis "Tools for manipulating GO and microarrays")
7178 "This package provides a set of tools for interacting with GO and
7179 microarray data. A variety of basic manipulation tools for graphs, hypothesis
7180 testing and other simple calculations.")
7181 (license license:artistic2.0)))
7183 (define-public r-shortread
7185 (name "r-shortread")
7190 (uri (bioconductor-uri "ShortRead" version))
7193 "0l4kdln69y6yhln0xiv2jmpxg05fjcglln406p43a2bqvk2lr03d"))))
7194 (properties `((upstream-name . "ShortRead")))
7195 (build-system r-build-system)
7199 `(("r-biobase" ,r-biobase)
7200 ("r-biocgenerics" ,r-biocgenerics)
7201 ("r-biocparallel" ,r-biocparallel)
7202 ("r-biostrings" ,r-biostrings)
7203 ("r-genomeinfodb" ,r-genomeinfodb)
7204 ("r-genomicalignments" ,r-genomicalignments)
7205 ("r-genomicranges" ,r-genomicranges)
7206 ("r-hwriter" ,r-hwriter)
7207 ("r-iranges" ,r-iranges)
7208 ("r-lattice" ,r-lattice)
7209 ("r-latticeextra" ,r-latticeextra)
7210 ("r-rsamtools" ,r-rsamtools)
7211 ("r-s4vectors" ,r-s4vectors)
7212 ("r-xvector" ,r-xvector)
7213 ("r-zlibbioc" ,r-zlibbioc)))
7214 (home-page "https://bioconductor.org/packages/ShortRead")
7215 (synopsis "FASTQ input and manipulation tools")
7217 "This package implements sampling, iteration, and input of FASTQ files.
7218 It includes functions for filtering and trimming reads, and for generating a
7219 quality assessment report. Data are represented as
7220 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
7221 purposes. The package also contains legacy support for early single-end,
7222 ungapped alignment formats.")
7223 (license license:artistic2.0)))
7225 (define-public r-systempiper
7227 (name "r-systempiper")
7232 (uri (bioconductor-uri "systemPipeR" version))
7235 "01ilhlrvy28jfdyxjria4024yryj5zgympgqznw17g3y3az78kk2"))))
7236 (properties `((upstream-name . "systemPipeR")))
7237 (build-system r-build-system)
7239 `(("r-annotate" ,r-annotate)
7240 ("r-assertthat" ,r-assertthat)
7241 ("r-batchtools" ,r-batchtools)
7242 ("r-biostrings" ,r-biostrings)
7243 ("r-deseq2" ,r-deseq2)
7245 ("r-edger" ,r-edger)
7246 ("r-genomicfeatures" ,r-genomicfeatures)
7247 ("r-genomicranges" ,r-genomicranges)
7248 ("r-ggplot2" ,r-ggplot2)
7249 ("r-go-db" ,r-go-db)
7250 ("r-gostats" ,r-gostats)
7251 ("r-limma" ,r-limma)
7252 ("r-magrittr" ,r-magrittr)
7253 ("r-pheatmap" ,r-pheatmap)
7254 ("r-rjson" ,r-rjson)
7255 ("r-rsamtools" ,r-rsamtools)
7257 ("r-shortread" ,r-shortread)
7258 ("r-stringr" ,r-stringr)
7259 ("r-summarizedexperiment" ,r-summarizedexperiment)
7261 ("r-variantannotation" ,r-variantannotation)))
7263 `(("r-knitr" ,r-knitr)))
7264 (home-page "https://github.com/tgirke/systemPipeR")
7265 (synopsis "Next generation sequencing workflow and reporting environment")
7267 "This R package provides tools for building and running automated
7268 end-to-end analysis workflows for a wide range of @dfn{next generation
7269 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
7270 Important features include a uniform workflow interface across different NGS
7271 applications, automated report generation, and support for running both R and
7272 command-line software, such as NGS aligners or peak/variant callers, on local
7273 computers or compute clusters. Efficient handling of complex sample sets and
7274 experimental designs is facilitated by a consistently implemented sample
7275 annotation infrastructure.")
7276 (license license:artistic2.0)))
7278 (define-public r-grohmm
7285 (uri (bioconductor-uri "groHMM" version))
7288 "04z9qq1xwdsaxbqhyld37w0ybvzly9pc1hcyrnwdbyjwd7n1fncb"))))
7289 (properties `((upstream-name . "groHMM")))
7290 (build-system r-build-system)
7292 `(("r-genomeinfodb" ,r-genomeinfodb)
7293 ("r-genomicalignments" ,r-genomicalignments)
7294 ("r-genomicranges" ,r-genomicranges)
7295 ("r-iranges" ,r-iranges)
7297 ("r-rtracklayer" ,r-rtracklayer)
7298 ("r-s4vectors" ,r-s4vectors)))
7299 (home-page "https://github.com/Kraus-Lab/groHMM")
7300 (synopsis "GRO-seq analysis pipeline")
7302 "This package provides a pipeline for the analysis of GRO-seq data.")
7303 (license license:gpl3+)))
7305 (define-public vsearch
7313 (url "https://github.com/torognes/vsearch")
7314 (commit (string-append "v" version))))
7315 (file-name (git-file-name name version))
7318 "0vhrpjfdf75ba04b24xknp41790cvcgwl0vgpy7qbzj5xh2521ss"))
7319 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
7322 ;; Remove bundled cityhash sources. The vsearch source is adjusted
7323 ;; for this in the patch.
7324 (delete-file "src/city.h")
7325 (delete-file "src/citycrc.h")
7326 (delete-file "src/city.cc")
7328 (build-system gnu-build-system)
7332 ("cityhash" ,cityhash)))
7334 `(("autoconf" ,autoconf)
7335 ("automake" ,automake)))
7336 (synopsis "Sequence search tools for metagenomics")
7338 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
7339 dereplication, pairwise alignment, shuffling, subsampling, sorting and
7340 masking. The tool takes advantage of parallelism in the form of SIMD
7341 vectorization as well as multiple threads to perform accurate alignments at
7342 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
7343 Needleman-Wunsch).")
7344 (home-page "https://github.com/torognes/vsearch")
7345 ;; vsearch uses non-portable SSE intrinsics so building fails on other
7347 (supported-systems '("x86_64-linux"))
7348 ;; Dual licensed; also includes public domain source.
7349 (license (list license:gpl3 license:bsd-2))))
7351 (define-public pardre
7354 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
7359 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
7363 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
7364 (build-system gnu-build-system)
7366 `(#:tests? #f ; no tests included
7368 (modify-phases %standard-phases
7371 (lambda* (#:key outputs #:allow-other-keys)
7372 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
7373 (install-file "ParDRe" bin)
7376 `(("openmpi" ,openmpi)
7378 (synopsis "Parallel tool to remove duplicate DNA reads")
7380 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
7381 Duplicate reads can be seen as identical or nearly identical sequences with
7382 some mismatches. This tool lets users avoid the analysis of unnecessary
7383 reads, reducing the time of subsequent procedures with the
7384 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
7385 in order to exploit the parallel capabilities of multicore clusters. It is
7386 faster than multithreaded counterparts (end of 2015) for the same number of
7387 cores and, thanks to the message-passing technology, it can be executed on
7389 (home-page "https://sourceforge.net/projects/pardre/")
7390 (license license:gpl3+)))
7392 (define-public ruby-bio-kseq
7394 (name "ruby-bio-kseq")
7399 (uri (rubygems-uri "bio-kseq" version))
7402 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
7403 (build-system ruby-build-system)
7405 `(#:test-target "spec"))
7407 `(("bundler" ,bundler)
7408 ("ruby-rspec" ,ruby-rspec)
7409 ("ruby-rake-compiler" ,ruby-rake-compiler)))
7412 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
7414 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
7415 FASTQ parsing code. It provides a fast iterator over sequences and their
7417 (home-page "https://github.com/gusevfe/bio-kseq")
7418 (license license:expat)))
7420 (define-public bio-locus
7427 (uri (rubygems-uri "bio-locus" version))
7430 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
7431 (build-system ruby-build-system)
7433 `(("ruby-rspec" ,ruby-rspec)))
7434 (synopsis "Tool for fast querying of genome locations")
7436 "Bio-locus is a tabix-like tool for fast querying of genome
7437 locations. Many file formats in bioinformatics contain records that
7438 start with a chromosome name and a position for a SNP, or a start-end
7439 position for indels. Bio-locus allows users to store this chr+pos or
7440 chr+pos+alt information in a database.")
7441 (home-page "https://github.com/pjotrp/bio-locus")
7442 (license license:expat)))
7444 (define-public bio-blastxmlparser
7446 (name "bio-blastxmlparser")
7450 (uri (rubygems-uri "bio-blastxmlparser" version))
7453 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
7454 (build-system ruby-build-system)
7456 `(("ruby-bio-logger" ,ruby-bio-logger)
7457 ("ruby-nokogiri" ,ruby-nokogiri)))
7459 `(("ruby-rspec" ,ruby-rspec)))
7460 (synopsis "Fast big data BLAST XML parser and library")
7462 "Very fast parallel big-data BLAST XML file parser which can be used as
7463 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
7464 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
7465 (home-page "https://github.com/pjotrp/blastxmlparser")
7466 (license license:expat)))
7468 (define-public bioruby
7475 (uri (rubygems-uri "bio" version))
7478 "1d56amdsjv1mag7m6gv2w0xij8hqx1v5xbdjsix8sp3yp36m7938"))))
7479 (build-system ruby-build-system)
7481 `(("ruby-libxml" ,ruby-libxml)))
7483 `(("which" ,which))) ; required for test phase
7486 (modify-phases %standard-phases
7487 (add-before 'build 'patch-test-command
7489 (substitute* '("test/functional/bio/test_command.rb")
7490 (("/bin/sh") (which "sh")))
7491 (substitute* '("test/functional/bio/test_command.rb")
7492 (("/bin/ls") (which "ls")))
7493 (substitute* '("test/functional/bio/test_command.rb")
7494 (("which") (which "which")))
7495 (substitute* '("test/functional/bio/test_command.rb",
7496 "test/data/command/echoarg2.sh")
7497 (("/bin/echo") (which "echo")))
7499 (synopsis "Ruby library, shell and utilities for bioinformatics")
7500 (description "BioRuby comes with a comprehensive set of Ruby development
7501 tools and libraries for bioinformatics and molecular biology. BioRuby has
7502 components for sequence analysis, pathway analysis, protein modelling and
7503 phylogenetic analysis; it supports many widely used data formats and provides
7504 easy access to databases, external programs and public web services, including
7505 BLAST, KEGG, GenBank, MEDLINE and GO.")
7506 (home-page "http://bioruby.org/")
7507 ;; Code is released under Ruby license, except for setup
7508 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
7509 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
7511 (define-public r-biocviews
7513 (name "r-biocviews")
7517 (uri (bioconductor-uri "biocViews" version))
7520 "0kw0qfm1fw5yv2rbz6x23431rh0fnzj66f2bls7j285biyjmmx7w"))))
7522 `((upstream-name . "biocViews")))
7523 (build-system r-build-system)
7525 `(("r-biobase" ,r-biobase)
7526 ("r-biocmanager" ,r-biocmanager)
7527 ("r-graph" ,r-graph)
7529 ("r-rcurl" ,r-rcurl)
7531 ("r-runit" ,r-runit)))
7532 (home-page "https://bioconductor.org/packages/biocViews")
7533 (synopsis "Bioconductor package categorization helper")
7534 (description "The purpose of biocViews is to create HTML pages that
7535 categorize packages in a Bioconductor package repository according to keywords,
7536 also known as views, in a controlled vocabulary.")
7537 (license license:artistic2.0)))
7539 (define-public r-biocstyle
7541 (name "r-biocstyle")
7545 (uri (bioconductor-uri "BiocStyle" version))
7548 "07rjl2n4sazdg581zh7w3yykzphgr2gpz41ba4ryqs7347vh9nbf"))))
7550 `((upstream-name . "BiocStyle")))
7551 (build-system r-build-system)
7553 `(("r-biocmanager" ,r-biocmanager)
7554 ("r-bookdown" ,r-bookdown)
7555 ("r-knitr" ,r-knitr)
7556 ("r-rmarkdown" ,r-rmarkdown)
7557 ("r-yaml" ,r-yaml)))
7559 `(("r-knitr" ,r-knitr)))
7560 (home-page "https://bioconductor.org/packages/BiocStyle")
7561 (synopsis "Bioconductor formatting styles")
7562 (description "This package provides standard formatting styles for
7563 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
7565 (license license:artistic2.0)))
7567 (define-public r-bioccheck
7569 (name "r-bioccheck")
7573 (uri (bioconductor-uri "BiocCheck" version))
7576 "1p9ys18sn1crxw1iac2jdgqvwpb5hjd9nfxx0qn0ncrv0b550mny"))))
7578 `((upstream-name . "BiocCheck")))
7579 (build-system r-build-system)
7582 (modify-phases %standard-phases
7583 ;; This package can be used by calling BiocCheck(<package>) from
7584 ;; within R, or by running R CMD BiocCheck <package>. This phase
7585 ;; makes sure the latter works. For this to work, the BiocCheck
7586 ;; script must be somewhere on the PATH (not the R bin directory).
7587 (add-after 'install 'install-bioccheck-subcommand
7588 (lambda* (#:key outputs #:allow-other-keys)
7589 (let* ((out (assoc-ref outputs "out"))
7590 (dest-dir (string-append out "/bin"))
7592 (string-append out "/site-library/BiocCheck/script/")))
7594 (symlink (string-append script-dir "/checkBadDeps.R")
7595 (string-append dest-dir "/checkBadDeps.R"))
7596 (symlink (string-append script-dir "/BiocCheck")
7597 (string-append dest-dir "/BiocCheck")))
7600 `(("r-codetools" ,r-codetools)
7601 ("r-graph" ,r-graph)
7603 ("r-knitr" ,r-knitr)
7604 ("r-optparse" ,r-optparse)
7605 ("r-biocmanager" ,r-biocmanager)
7606 ("r-biocviews" ,r-biocviews)
7607 ("r-stringdist" ,r-stringdist)))
7609 `(("r-knitr" ,r-knitr)))
7610 (home-page "https://bioconductor.org/packages/BiocCheck")
7611 (synopsis "Executes Bioconductor-specific package checks")
7612 (description "This package contains tools to perform additional quality
7613 checks on R packages that are to be submitted to the Bioconductor repository.")
7614 (license license:artistic2.0)))
7616 (define-public r-s4vectors
7618 (name "r-s4vectors")
7622 (uri (bioconductor-uri "S4Vectors" version))
7625 "1ddr3ngyczx332zw9ai1a6h7442lgrbfcj8vrhvbkdkzqwj14xmb"))))
7627 `((upstream-name . "S4Vectors")))
7628 (build-system r-build-system)
7630 `(("r-biocgenerics" ,r-biocgenerics)))
7631 (home-page "https://bioconductor.org/packages/S4Vectors")
7632 (synopsis "S4 implementation of vectors and lists")
7634 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7635 classes and a set of generic functions that extend the semantic of ordinary
7636 vectors and lists in R. Package developers can easily implement vector-like
7637 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7638 In addition, a few low-level concrete subclasses of general interest (e.g.
7639 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7640 S4Vectors package itself.")
7641 (license license:artistic2.0)))
7643 (define-public r-iranges
7649 (uri (bioconductor-uri "IRanges" version))
7652 "1y24jw62806wp2afiyj1x6n00gj7d3323klqdypra9q43pg1w49d"))))
7654 `((upstream-name . "IRanges")))
7655 (build-system r-build-system)
7657 `(("r-biocgenerics" ,r-biocgenerics)
7658 ("r-s4vectors" ,r-s4vectors)))
7659 (home-page "https://bioconductor.org/packages/IRanges")
7660 (synopsis "Infrastructure for manipulating intervals on sequences")
7662 "This package provides efficient low-level and highly reusable S4 classes
7663 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7664 generally, data that can be organized sequentially (formally defined as
7665 @code{Vector} objects), as well as views on these @code{Vector} objects.
7666 Efficient list-like classes are also provided for storing big collections of
7667 instances of the basic classes. All classes in the package use consistent
7668 naming and share the same rich and consistent \"Vector API\" as much as
7670 (license license:artistic2.0)))
7672 (define-public r-genomeinfodbdata
7674 (name "r-genomeinfodbdata")
7678 ;; We cannot use bioconductor-uri here because this tarball is
7679 ;; located under "data/annotation/" instead of "bioc/".
7680 (uri (string-append "https://bioconductor.org/packages/release/"
7681 "data/annotation/src/contrib/GenomeInfoDbData_"
7685 "0di6nlqpsyqf693k2na65ayqldih563x3zfrczpqc5q2hl5kg35c"))))
7687 `((upstream-name . "GenomeInfoDbData")))
7688 (build-system r-build-system)
7689 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7690 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7691 (description "This package contains data for mapping between NCBI taxonomy
7692 ID and species. It is used by functions in the GenomeInfoDb package.")
7693 (license license:artistic2.0)))
7695 (define-public r-genomeinfodb
7697 (name "r-genomeinfodb")
7701 (uri (bioconductor-uri "GenomeInfoDb" version))
7704 "1cqs53p4m5q1dr59war72bccphy01ilw4xra24fmngrv4x32rznd"))))
7706 `((upstream-name . "GenomeInfoDb")))
7707 (build-system r-build-system)
7709 `(("r-biocgenerics" ,r-biocgenerics)
7710 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7711 ("r-iranges" ,r-iranges)
7712 ("r-rcurl" ,r-rcurl)
7713 ("r-s4vectors" ,r-s4vectors)))
7715 `(("r-knitr" ,r-knitr)))
7716 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7717 (synopsis "Utilities for manipulating chromosome identifiers")
7719 "This package contains data and functions that define and allow
7720 translation between different chromosome sequence naming conventions (e.g.,
7721 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7722 names in their natural, rather than lexicographic, order.")
7723 (license license:artistic2.0)))
7725 (define-public r-edger
7731 (uri (bioconductor-uri "edgeR" version))
7734 "1z9bkg08rgqn3jm2s4ndbj641w33wl8jd3j6m5if6h2nnw6011ic"))))
7735 (properties `((upstream-name . "edgeR")))
7736 (build-system r-build-system)
7738 `(("r-limma" ,r-limma)
7739 ("r-locfit" ,r-locfit)
7741 ("r-statmod" ,r-statmod))) ;for estimateDisp
7742 (home-page "http://bioinf.wehi.edu.au/edgeR")
7743 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7744 (description "This package can do differential expression analysis of
7745 RNA-seq expression profiles with biological replication. It implements a range
7746 of statistical methodology based on the negative binomial distributions,
7747 including empirical Bayes estimation, exact tests, generalized linear models
7748 and quasi-likelihood tests. It be applied to differential signal analysis of
7749 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7751 (license license:gpl2+)))
7753 (define-public r-variantannotation
7755 (name "r-variantannotation")
7759 (uri (bioconductor-uri "VariantAnnotation" version))
7762 "09y6ymwky839nb0y7y93w810hk9mvwqn7595q1276c28dkddiqvw"))))
7764 `((upstream-name . "VariantAnnotation")))
7768 `(("r-annotationdbi" ,r-annotationdbi)
7769 ("r-biobase" ,r-biobase)
7770 ("r-biocgenerics" ,r-biocgenerics)
7771 ("r-biostrings" ,r-biostrings)
7772 ("r-bsgenome" ,r-bsgenome)
7774 ("r-genomeinfodb" ,r-genomeinfodb)
7775 ("r-genomicfeatures" ,r-genomicfeatures)
7776 ("r-genomicranges" ,r-genomicranges)
7777 ("r-iranges" ,r-iranges)
7778 ("r-summarizedexperiment" ,r-summarizedexperiment)
7779 ("r-rhtslib" ,r-rhtslib)
7780 ("r-rsamtools" ,r-rsamtools)
7781 ("r-rtracklayer" ,r-rtracklayer)
7782 ("r-s4vectors" ,r-s4vectors)
7783 ("r-xvector" ,r-xvector)
7784 ("r-zlibbioc" ,r-zlibbioc)))
7785 (build-system r-build-system)
7786 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7787 (synopsis "Package for annotation of genetic variants")
7788 (description "This R package can annotate variants, compute amino acid
7789 coding changes and predict coding outcomes.")
7790 (license license:artistic2.0)))
7792 (define-public r-limma
7798 (uri (bioconductor-uri "limma" version))
7801 "09fnqxx4rzq5n447aqg2l6y0idfwgz2jxz99sifxsr2q8afzbcj6"))))
7802 (build-system r-build-system)
7803 (home-page "http://bioinf.wehi.edu.au/limma")
7804 (synopsis "Package for linear models for microarray and RNA-seq data")
7805 (description "This package can be used for the analysis of gene expression
7806 studies, especially the use of linear models for analysing designed experiments
7807 and the assessment of differential expression. The analysis methods apply to
7808 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7809 (license license:gpl2+)))
7811 (define-public r-xvector
7817 (uri (bioconductor-uri "XVector" version))
7820 "11h1hszv4798q1gbx8r6zf8vlaqx4v9ql0lbh2xaxybp66a03pvc"))))
7822 `((upstream-name . "XVector")))
7823 (build-system r-build-system)
7826 (modify-phases %standard-phases
7827 (add-after 'unpack 'use-system-zlib
7829 (substitute* "DESCRIPTION"
7830 (("zlibbioc, ") ""))
7831 (substitute* "NAMESPACE"
7832 (("import\\(zlibbioc\\)") ""))
7837 `(("r-biocgenerics" ,r-biocgenerics)
7838 ("r-iranges" ,r-iranges)
7839 ("r-s4vectors" ,r-s4vectors)))
7840 (home-page "https://bioconductor.org/packages/XVector")
7841 (synopsis "Representation and manpulation of external sequences")
7843 "This package provides memory efficient S4 classes for storing sequences
7844 \"externally\" (behind an R external pointer, or on disk).")
7845 (license license:artistic2.0)))
7847 (define-public r-genomicranges
7849 (name "r-genomicranges")
7853 (uri (bioconductor-uri "GenomicRanges" version))
7856 "0wn1zr2qq0rpv9z2wialgizn6xzdlcjg1w2kif67n53svz6vk2x1"))))
7858 `((upstream-name . "GenomicRanges")))
7859 (build-system r-build-system)
7861 `(("r-biocgenerics" ,r-biocgenerics)
7862 ("r-genomeinfodb" ,r-genomeinfodb)
7863 ("r-iranges" ,r-iranges)
7864 ("r-s4vectors" ,r-s4vectors)
7865 ("r-xvector" ,r-xvector)))
7867 `(("r-knitr" ,r-knitr)))
7868 (home-page "https://bioconductor.org/packages/GenomicRanges")
7869 (synopsis "Representation and manipulation of genomic intervals")
7871 "This package provides tools to efficiently represent and manipulate
7872 genomic annotations and alignments is playing a central role when it comes to
7873 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7874 GenomicRanges package defines general purpose containers for storing and
7875 manipulating genomic intervals and variables defined along a genome.")
7876 (license license:artistic2.0)))
7878 (define-public r-biobase
7884 (uri (bioconductor-uri "Biobase" version))
7887 "13p3kgnxm7hbn8cy289kbhaiyfa6rxx7l1pbvajwqzbay3cxznqp"))))
7889 `((upstream-name . "Biobase")))
7890 (build-system r-build-system)
7892 `(("r-biocgenerics" ,r-biocgenerics)))
7893 (home-page "https://bioconductor.org/packages/Biobase")
7894 (synopsis "Base functions for Bioconductor")
7896 "This package provides functions that are needed by many other packages
7897 on Bioconductor or which replace R functions.")
7898 (license license:artistic2.0)))
7900 (define-public r-annotationdbi
7902 (name "r-annotationdbi")
7906 (uri (bioconductor-uri "AnnotationDbi" version))
7909 "0qcxfn4pvaksna0nvxr74ysn2wzaxn732pkhd6ffrj8pwhkhy5p3"))))
7911 `((upstream-name . "AnnotationDbi")))
7912 (build-system r-build-system)
7914 `(("r-biobase" ,r-biobase)
7915 ("r-biocgenerics" ,r-biocgenerics)
7917 ("r-iranges" ,r-iranges)
7918 ("r-rsqlite" ,r-rsqlite)
7919 ("r-s4vectors" ,r-s4vectors)))
7921 `(("r-knitr" ,r-knitr)))
7922 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7923 (synopsis "Annotation database interface")
7925 "This package provides user interface and database connection code for
7926 annotation data packages using SQLite data storage.")
7927 (license license:artistic2.0)))
7929 (define-public r-biomart
7935 (uri (bioconductor-uri "biomaRt" version))
7938 "0np4nh3gj60mgb6312z7x0z9fg5bhrhw872sp3dzgmqc8q8b84iz"))))
7940 `((upstream-name . "biomaRt")))
7941 (build-system r-build-system)
7943 `(("r-annotationdbi" ,r-annotationdbi)
7944 ("r-biocfilecache" ,r-biocfilecache)
7946 ("r-openssl" ,r-openssl)
7947 ("r-progress" ,r-progress)
7948 ("r-rappdirs" ,r-rappdirs)
7949 ("r-stringr" ,r-stringr)
7952 `(("r-knitr" ,r-knitr)))
7953 (home-page "https://bioconductor.org/packages/biomaRt")
7954 (synopsis "Interface to BioMart databases")
7956 "biomaRt provides an interface to a growing collection of databases
7957 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7958 package enables retrieval of large amounts of data in a uniform way without
7959 the need to know the underlying database schemas or write complex SQL queries.
7960 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7961 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7962 users direct access to a diverse set of data and enable a wide range of
7963 powerful online queries from gene annotation to database mining.")
7964 (license license:artistic2.0)))
7966 (define-public r-biocparallel
7968 (name "r-biocparallel")
7972 (uri (bioconductor-uri "BiocParallel" version))
7975 "1lsg5xm5j3ly5k60fidzhkgqc9jgscyfkqngjvd9qp6yfzvsb82g"))))
7977 `((upstream-name . "BiocParallel")))
7978 (build-system r-build-system)
7980 `(("r-futile-logger" ,r-futile-logger)
7984 `(("r-knitr" ,r-knitr)))
7985 (home-page "https://bioconductor.org/packages/BiocParallel")
7986 (synopsis "Bioconductor facilities for parallel evaluation")
7988 "This package provides modified versions and novel implementation of
7989 functions for parallel evaluation, tailored to use with Bioconductor
7991 (license (list license:gpl2+ license:gpl3+))))
7993 (define-public r-biostrings
7995 (name "r-biostrings")
7999 (uri (bioconductor-uri "Biostrings" version))
8002 "0imhfz7dg8b3l5qzipjranqqshdsg2x6zc49drlhn8sc7j40cvi8"))))
8004 `((upstream-name . "Biostrings")))
8005 (build-system r-build-system)
8007 `(("r-biocgenerics" ,r-biocgenerics)
8008 ("r-crayon" ,r-crayon)
8009 ("r-iranges" ,r-iranges)
8010 ("r-s4vectors" ,r-s4vectors)
8011 ("r-xvector" ,r-xvector)))
8012 (home-page "https://bioconductor.org/packages/Biostrings")
8013 (synopsis "String objects and algorithms for biological sequences")
8015 "This package provides memory efficient string containers, string
8016 matching algorithms, and other utilities, for fast manipulation of large
8017 biological sequences or sets of sequences.")
8018 (license license:artistic2.0)))
8020 (define-public r-rsamtools
8022 (name "r-rsamtools")
8026 (uri (bioconductor-uri "Rsamtools" version))
8029 "0z01z0s71f941k7sns46nyabps28c69d6jxx6sppjpc6h4vrw0vq"))))
8031 `((upstream-name . "Rsamtools")))
8032 (build-system r-build-system)
8035 (modify-phases %standard-phases
8036 (add-after 'unpack 'use-system-zlib
8038 (substitute* "DESCRIPTION"
8039 (("zlibbioc, ") ""))
8040 (substitute* "NAMESPACE"
8041 (("import\\(zlibbioc\\)") ""))
8046 `(("r-biocgenerics" ,r-biocgenerics)
8047 ("r-biocparallel" ,r-biocparallel)
8048 ("r-biostrings" ,r-biostrings)
8049 ("r-bitops" ,r-bitops)
8050 ("r-genomeinfodb" ,r-genomeinfodb)
8051 ("r-genomicranges" ,r-genomicranges)
8052 ("r-iranges" ,r-iranges)
8053 ("r-rhtslib" ,r-rhtslib)
8054 ("r-s4vectors" ,r-s4vectors)
8055 ("r-xvector" ,r-xvector)))
8056 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
8057 (synopsis "Interface to samtools, bcftools, and tabix")
8059 "This package provides an interface to the @code{samtools},
8060 @code{bcftools}, and @code{tabix} utilities for manipulating SAM (Sequence
8061 Alignment / Map), FASTA, binary variant call (BCF) and compressed indexed
8062 tab-delimited (tabix) files.")
8063 (license license:expat)))
8065 (define-public r-delayedarray
8067 (name "r-delayedarray")
8071 (uri (bioconductor-uri "DelayedArray" version))
8074 "0xi0i621hrl7k9rsc8x8nc3ib74sk8hxhbyr2lxqclw45pk95s7v"))))
8076 `((upstream-name . "DelayedArray")))
8077 (build-system r-build-system)
8079 `(("r-biocgenerics" ,r-biocgenerics)
8080 ("r-s4vectors" ,r-s4vectors)
8081 ("r-iranges" ,r-iranges)
8082 ("r-matrix" ,r-matrix)
8083 ("r-matrixstats" ,r-matrixstats)))
8085 `(("r-knitr" ,r-knitr)))
8086 (home-page "https://bioconductor.org/packages/DelayedArray")
8087 (synopsis "Delayed operations on array-like objects")
8089 "Wrapping an array-like object (typically an on-disk object) in a
8090 @code{DelayedArray} object allows one to perform common array operations on it
8091 without loading the object in memory. In order to reduce memory usage and
8092 optimize performance, operations on the object are either delayed or executed
8093 using a block processing mechanism. Note that this also works on in-memory
8094 array-like objects like @code{DataFrame} objects (typically with Rle columns),
8095 @code{Matrix} objects, and ordinary arrays and data frames.")
8096 (license license:artistic2.0)))
8098 (define-public r-summarizedexperiment
8100 (name "r-summarizedexperiment")
8104 (uri (bioconductor-uri "SummarizedExperiment" version))
8107 "1raw5ycigr6gjgzn3kx3jls5hzww10fhnwd8c17c20hmhirf13rw"))))
8109 `((upstream-name . "SummarizedExperiment")))
8110 (build-system r-build-system)
8112 `(("r-biobase" ,r-biobase)
8113 ("r-biocgenerics" ,r-biocgenerics)
8114 ("r-delayedarray" ,r-delayedarray)
8115 ("r-genomeinfodb" ,r-genomeinfodb)
8116 ("r-genomicranges" ,r-genomicranges)
8117 ("r-iranges" ,r-iranges)
8118 ("r-matrix" ,r-matrix)
8119 ("r-s4vectors" ,r-s4vectors)))
8121 `(("r-knitr" ,r-knitr)))
8122 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
8123 (synopsis "Container for representing genomic ranges by sample")
8125 "The SummarizedExperiment container contains one or more assays, each
8126 represented by a matrix-like object of numeric or other mode. The rows
8127 typically represent genomic ranges of interest and the columns represent
8129 (license license:artistic2.0)))
8131 (define-public r-genomicalignments
8133 (name "r-genomicalignments")
8137 (uri (bioconductor-uri "GenomicAlignments" version))
8140 "0v8k6d7frm5p48cmk4zik78cw9abz4inx0zhl4zrmmx31ifyvk8d"))))
8142 `((upstream-name . "GenomicAlignments")))
8143 (build-system r-build-system)
8145 `(("r-biocgenerics" ,r-biocgenerics)
8146 ("r-biocparallel" ,r-biocparallel)
8147 ("r-biostrings" ,r-biostrings)
8148 ("r-genomeinfodb" ,r-genomeinfodb)
8149 ("r-genomicranges" ,r-genomicranges)
8150 ("r-iranges" ,r-iranges)
8151 ("r-rsamtools" ,r-rsamtools)
8152 ("r-s4vectors" ,r-s4vectors)
8153 ("r-summarizedexperiment" ,r-summarizedexperiment)))
8154 (home-page "https://bioconductor.org/packages/GenomicAlignments")
8155 (synopsis "Representation and manipulation of short genomic alignments")
8157 "This package provides efficient containers for storing and manipulating
8158 short genomic alignments (typically obtained by aligning short reads to a
8159 reference genome). This includes read counting, computing the coverage,
8160 junction detection, and working with the nucleotide content of the
8162 (license license:artistic2.0)))
8164 (define-public r-rtracklayer
8166 (name "r-rtracklayer")
8170 (uri (bioconductor-uri "rtracklayer" version))
8173 "1zcgk92sidhy4y7ws9ms4nkkh2hnccfhfh53qgna0kma9jy4v5xf"))))
8174 (build-system r-build-system)
8177 (modify-phases %standard-phases
8178 (add-after 'unpack 'use-system-zlib
8180 (substitute* "DESCRIPTION"
8181 ((" zlibbioc,") ""))
8182 (substitute* "NAMESPACE"
8183 (("import\\(zlibbioc\\)") ""))
8186 `(("pkg-config" ,pkg-config)))
8190 `(("r-biocgenerics" ,r-biocgenerics)
8191 ("r-biostrings" ,r-biostrings)
8192 ("r-genomeinfodb" ,r-genomeinfodb)
8193 ("r-genomicalignments" ,r-genomicalignments)
8194 ("r-genomicranges" ,r-genomicranges)
8195 ("r-iranges" ,r-iranges)
8196 ("r-rcurl" ,r-rcurl)
8197 ("r-rsamtools" ,r-rsamtools)
8198 ("r-s4vectors" ,r-s4vectors)
8200 ("r-xvector" ,r-xvector)))
8201 (home-page "https://bioconductor.org/packages/rtracklayer")
8202 (synopsis "R interface to genome browsers and their annotation tracks")
8204 "rtracklayer is an extensible framework for interacting with multiple
8205 genome browsers (currently UCSC built-in) and manipulating annotation tracks
8206 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
8207 built-in). The user may export/import tracks to/from the supported browsers,
8208 as well as query and modify the browser state, such as the current viewport.")
8209 (license license:artistic2.0)))
8211 (define-public r-genomicfeatures
8213 (name "r-genomicfeatures")
8217 (uri (bioconductor-uri "GenomicFeatures" version))
8220 "0zm7q957g952qyfqmvf27sldsnq6sqd0wlgnqzvmxayg9pxh0l0z"))))
8222 `((upstream-name . "GenomicFeatures")))
8223 (build-system r-build-system)
8225 `(("r-annotationdbi" ,r-annotationdbi)
8226 ("r-biobase" ,r-biobase)
8227 ("r-biocgenerics" ,r-biocgenerics)
8228 ("r-biomart" ,r-biomart)
8229 ("r-biostrings" ,r-biostrings)
8231 ("r-genomeinfodb" ,r-genomeinfodb)
8232 ("r-genomicranges" ,r-genomicranges)
8233 ("r-iranges" ,r-iranges)
8234 ("r-rcurl" ,r-rcurl)
8235 ("r-rsqlite" ,r-rsqlite)
8236 ("r-rtracklayer" ,r-rtracklayer)
8237 ("r-s4vectors" ,r-s4vectors)
8238 ("r-xvector" ,r-xvector)))
8240 `(("r-knitr" ,r-knitr)))
8241 (home-page "https://bioconductor.org/packages/GenomicFeatures")
8242 (synopsis "Tools for working with transcript centric annotations")
8244 "This package provides a set of tools and methods for making and
8245 manipulating transcript centric annotations. With these tools the user can
8246 easily download the genomic locations of the transcripts, exons and cds of a
8247 given organism, from either the UCSC Genome Browser or a BioMart
8248 database (more sources will be supported in the future). This information is
8249 then stored in a local database that keeps track of the relationship between
8250 transcripts, exons, cds and genes. Flexible methods are provided for
8251 extracting the desired features in a convenient format.")
8252 (license license:artistic2.0)))
8254 (define-public r-go-db
8260 (uri (string-append "https://www.bioconductor.org/packages/"
8261 "release/data/annotation/src/contrib/GO.db_"
8265 "0i3wcf5h3n0dawzc1hy0kv74f06j80c47n4p3g3fmrcxlhi3jpa5"))))
8267 `((upstream-name . "GO.db")))
8268 (build-system r-build-system)
8270 `(("r-annotationdbi" ,r-annotationdbi)))
8271 (home-page "https://bioconductor.org/packages/GO.db")
8272 (synopsis "Annotation maps describing the entire Gene Ontology")
8274 "The purpose of this GO.db annotation package is to provide detailed
8275 information about the latest version of the Gene Ontologies.")
8276 (license license:artistic2.0)))
8278 (define-public r-topgo
8284 (uri (bioconductor-uri "topGO" version))
8287 "13rhbvn27sj75fklf1cnjaazacx8yyjlhqlnbp5zk157q6y5cwdr"))))
8289 `((upstream-name . "topGO")))
8290 (build-system r-build-system)
8292 `(("r-annotationdbi" ,r-annotationdbi)
8294 ("r-biobase" ,r-biobase)
8295 ("r-biocgenerics" ,r-biocgenerics)
8296 ("r-go-db" ,r-go-db)
8297 ("r-graph" ,r-graph)
8298 ("r-lattice" ,r-lattice)
8299 ("r-matrixstats" ,r-matrixstats)
8300 ("r-sparsem" ,r-sparsem)))
8301 (home-page "https://bioconductor.org/packages/topGO")
8302 (synopsis "Enrichment analysis for gene ontology")
8304 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
8305 terms while accounting for the topology of the GO graph. Different test
8306 statistics and different methods for eliminating local similarities and
8307 dependencies between GO terms can be implemented and applied.")
8308 ;; Any version of the LGPL applies.
8309 (license license:lgpl2.1+)))
8311 (define-public r-bsgenome
8317 (uri (bioconductor-uri "BSgenome" version))
8320 "1jw8r1qm9fpg2s1cw2y4np243jjxm65j2xdy2785h8fc1b02msf6"))))
8322 `((upstream-name . "BSgenome")))
8323 (build-system r-build-system)
8325 `(("r-biocgenerics" ,r-biocgenerics)
8326 ("r-biostrings" ,r-biostrings)
8327 ("r-genomeinfodb" ,r-genomeinfodb)
8328 ("r-genomicranges" ,r-genomicranges)
8329 ("r-iranges" ,r-iranges)
8330 ("r-matrixstats" ,r-matrixstats)
8331 ("r-rsamtools" ,r-rsamtools)
8332 ("r-rtracklayer" ,r-rtracklayer)
8333 ("r-s4vectors" ,r-s4vectors)
8334 ("r-xvector" ,r-xvector)))
8335 (home-page "https://bioconductor.org/packages/BSgenome")
8336 (synopsis "Infrastructure for Biostrings-based genome data packages")
8338 "This package provides infrastructure shared by all Biostrings-based
8339 genome data packages and support for efficient SNP representation.")
8340 (license license:artistic2.0)))
8342 (define-public r-impute
8348 (uri (bioconductor-uri "impute" version))
8351 "161p6l1cp3wwdynkxwvg0yhrh6yv20brdlplw5w5mavn4hf1nm0h"))))
8353 `(("gfortran" ,gfortran)))
8354 (build-system r-build-system)
8355 (home-page "https://bioconductor.org/packages/impute")
8356 (synopsis "Imputation for microarray data")
8358 "This package provides a function to impute missing gene expression
8359 microarray data, using nearest neighbor averaging.")
8360 (license license:gpl2+)))
8362 (define-public r-seqpattern
8364 (name "r-seqpattern")
8368 (uri (bioconductor-uri "seqPattern" version))
8371 "0f1yvx2ri1557rzjx08q5bgml1cvkm8hjl8xn1qi4rjs64sy6mci"))))
8373 `((upstream-name . "seqPattern")))
8374 (build-system r-build-system)
8376 `(("r-biostrings" ,r-biostrings)
8377 ("r-genomicranges" ,r-genomicranges)
8378 ("r-iranges" ,r-iranges)
8379 ("r-kernsmooth" ,r-kernsmooth)
8380 ("r-plotrix" ,r-plotrix)))
8381 (home-page "https://bioconductor.org/packages/seqPattern")
8382 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
8384 "This package provides tools to visualize oligonucleotide patterns and
8385 sequence motif occurrences across a large set of sequences centred at a common
8386 reference point and sorted by a user defined feature.")
8387 (license license:gpl3+)))
8389 (define-public r-genomation
8391 (name "r-genomation")
8395 (uri (bioconductor-uri "genomation" version))
8398 "1cy8kqwddiha5jy6nda1al956i4wncbgjkrxwijdb08cmka2sfwh"))))
8399 (build-system r-build-system)
8401 `(("r-biostrings" ,r-biostrings)
8402 ("r-bsgenome" ,r-bsgenome)
8403 ("r-data-table" ,r-data-table)
8404 ("r-genomeinfodb" ,r-genomeinfodb)
8405 ("r-genomicalignments" ,r-genomicalignments)
8406 ("r-genomicranges" ,r-genomicranges)
8407 ("r-ggplot2" ,r-ggplot2)
8408 ("r-gridbase" ,r-gridbase)
8409 ("r-impute" ,r-impute)
8410 ("r-iranges" ,r-iranges)
8411 ("r-matrixstats" ,r-matrixstats)
8412 ("r-plotrix" ,r-plotrix)
8415 ("r-readr" ,r-readr)
8416 ("r-reshape2" ,r-reshape2)
8417 ("r-rsamtools" ,r-rsamtools)
8418 ("r-rtracklayer" ,r-rtracklayer)
8419 ("r-runit" ,r-runit)
8420 ("r-s4vectors" ,r-s4vectors)
8421 ("r-seqpattern" ,r-seqpattern)))
8423 `(("r-knitr" ,r-knitr)))
8424 (home-page "https://bioinformatics.mdc-berlin.de/genomation/")
8425 (synopsis "Summary, annotation and visualization of genomic data")
8427 "This package provides a package for summary and annotation of genomic
8428 intervals. Users can visualize and quantify genomic intervals over
8429 pre-defined functional regions, such as promoters, exons, introns, etc. The
8430 genomic intervals represent regions with a defined chromosome position, which
8431 may be associated with a score, such as aligned reads from HT-seq experiments,
8432 TF binding sites, methylation scores, etc. The package can use any tabular
8433 genomic feature data as long as it has minimal information on the locations of
8434 genomic intervals. In addition, it can use BAM or BigWig files as input.")
8435 (license license:artistic2.0)))
8437 (define-public r-genomationdata
8439 (name "r-genomationdata")
8443 ;; We cannot use bioconductor-uri here because this tarball is
8444 ;; located under "data/annotation/" instead of "bioc/".
8445 (uri (string-append "https://bioconductor.org/packages/"
8446 "release/data/experiment/src/contrib/"
8447 "genomationData_" version ".tar.gz"))
8450 "10xyb8akjrhmak2i0mnv1agny2ipy364q9nlibyplpzc7vdb6bw7"))))
8451 (build-system r-build-system)
8452 ;; As this package provides little more than large data files, it doesn't
8453 ;; make sense to build substitutes.
8454 (arguments `(#:substitutable? #f))
8456 `(("r-knitr" ,r-knitr)))
8457 (home-page "https://bioinformatics.mdc-berlin.de/genomation/")
8458 (synopsis "Experimental data for use with the genomation package")
8460 "This package contains experimental genetic data for use with the
8461 genomation package. Included are Chip Seq, Methylation and Cage data,
8462 downloaded from Encode.")
8463 (license license:gpl3+)))
8465 (define-public r-seqlogo
8472 (uri (bioconductor-uri "seqLogo" version))
8475 "09kkxir305fv8z2yyihvspkrzclxbw1cx5mvhfkrhl10rap6662j"))))
8476 (properties `((upstream-name . "seqLogo")))
8477 (build-system r-build-system)
8478 (home-page "https://bioconductor.org/packages/seqLogo")
8479 (synopsis "Sequence logos for DNA sequence alignments")
8481 "seqLogo takes the position weight matrix of a DNA sequence motif and
8482 plots the corresponding sequence logo as introduced by Schneider and
8484 (license license:lgpl2.0+)))
8486 (define-public r-motifrg
8493 (uri (bioconductor-uri "motifRG" version))
8496 "1ml6zyzlk8yjbnfhga2qnw8nl43rankvka0kc1yljxr2b66aqbhn"))))
8497 (properties `((upstream-name . "motifRG")))
8498 (build-system r-build-system)
8500 `(("r-biostrings" ,r-biostrings)
8501 ("r-bsgenome" ,r-bsgenome)
8502 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8503 ("r-iranges" ,r-iranges)
8504 ("r-seqlogo" ,r-seqlogo)
8505 ("r-xvector" ,r-xvector)))
8506 (home-page "https://bioconductor.org/packages/motifRG")
8507 (synopsis "Discover motifs in high throughput sequencing data")
8509 "This package provides tools for discriminative motif discovery in high
8510 throughput genetic sequencing data sets using regression methods.")
8511 (license license:artistic2.0)))
8513 (define-public r-qtl
8520 (uri (string-append "mirror://cran/src/contrib/qtl_"
8524 "0rbwcnvyy96gq1dsgpxx03pv423qya26h6ws5y0blj3blfdmj83a"))))
8525 (build-system r-build-system)
8526 (home-page "https://rqtl.org/")
8527 (synopsis "R package for analyzing QTL experiments in genetics")
8528 (description "R/qtl is an extension library for the R statistics
8529 system. It is used to analyze experimental crosses for identifying
8530 genes contributing to variation in quantitative traits (so-called
8531 quantitative trait loci, QTLs).
8533 Using a hidden Markov model, R/qtl estimates genetic maps, to
8534 identify genotyping errors, and to perform single-QTL and two-QTL,
8535 two-dimensional genome scans.")
8536 (license license:gpl3)))
8538 (define-public r-qtl2
8544 (uri (cran-uri "qtl2" version))
8546 (base32 "0dfdzjylqzc92dcszawc8cyinxccjm3p36v9vcq9ma818pqcanmr"))))
8547 (build-system r-build-system)
8549 `(("r-data-table" ,r-data-table)
8550 ("r-jsonlite" ,r-jsonlite)
8552 ("r-rcppeigen" ,r-rcppeigen)
8553 ("r-rsqlite" ,r-rsqlite)
8554 ("r-yaml" ,r-yaml)))
8555 (home-page "https://kbroman.org/qtl2/")
8556 (synopsis "Quantitative Trait Locus Mapping in Experimental Crosses")
8558 "This package provides a set of tools to perform @dfn{Quantitative Trait
8559 Locus} (QTL) analysis in experimental crosses. It is a reimplementation of the
8560 @code{R/qtl} package to better handle high-dimensional data and complex cross
8561 designs. Broman et al. (2018) <doi:10.1534/genetics.118.301595>.")
8562 (license license:gpl3)))
8564 (define-public r-zlibbioc
8570 (uri (bioconductor-uri "zlibbioc" version))
8573 "0j1l052jb2cwc1nifxzwknc9csagf4f2d092zs0i95dz0rma89l0"))))
8575 `((upstream-name . "zlibbioc")))
8576 (build-system r-build-system)
8577 (home-page "https://bioconductor.org/packages/zlibbioc")
8578 (synopsis "Provider for zlib-1.2.5 to R packages")
8579 (description "This package uses the source code of zlib-1.2.5 to create
8580 libraries for systems that do not have these available via other means.")
8581 (license license:artistic2.0)))
8583 (define-public r-r4rna
8590 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8594 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8595 (build-system r-build-system)
8597 `(("r-optparse" ,r-optparse)
8598 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8599 (home-page "https://www.e-rna.org/r-chie/index.cgi")
8600 (synopsis "Analysis framework for RNA secondary structure")
8602 "The R4RNA package aims to be a general framework for the analysis of RNA
8603 secondary structure and comparative analysis in R.")
8604 (license license:gpl3+)))
8606 (define-public r-rhtslib
8613 (uri (bioconductor-uri "Rhtslib" version))
8616 "186r7icrkzrni1c4n33ip7dlsfgys7hnqf0simvxrpl3yhh3ygdi"))))
8617 (properties `((upstream-name . "Rhtslib")))
8618 (build-system r-build-system)
8619 ;; Without this a temporary directory ends up in the Rhtslib.so binary,
8620 ;; which makes R abort the build.
8621 (arguments '(#:configure-flags '("--no-staged-install")))
8624 ("r-zlibbioc" ,r-zlibbioc)))
8628 `(("pkg-config" ,pkg-config)
8629 ("r-knitr" ,r-knitr)))
8630 (home-page "https://github.com/nhayden/Rhtslib")
8631 (synopsis "High-throughput sequencing library as an R package")
8633 "This package provides the HTSlib C library for high-throughput
8634 nucleotide sequence analysis. The package is primarily useful to developers
8635 of other R packages who wish to make use of HTSlib.")
8636 (license license:lgpl2.0+)))
8638 (define-public r-bamsignals
8640 (name "r-bamsignals")
8645 (uri (bioconductor-uri "bamsignals" version))
8648 "0p858xxfv79yc8b3lq58zl9f00irvbn3czsd8wdi5040xg42m402"))))
8649 (build-system r-build-system)
8651 `(("r-biocgenerics" ,r-biocgenerics)
8652 ("r-genomicranges" ,r-genomicranges)
8653 ("r-iranges" ,r-iranges)
8655 ("r-rhtslib" ,r-rhtslib)
8656 ("r-zlibbioc" ,r-zlibbioc)))
8660 `(("r-knitr" ,r-knitr)))
8661 (home-page "https://bioconductor.org/packages/bamsignals")
8662 (synopsis "Extract read count signals from bam files")
8664 "This package efficiently obtains count vectors from indexed bam
8665 files. It counts the number of nucleotide sequence reads in given genomic
8666 ranges and it computes reads profiles and coverage profiles. It also handles
8668 (license license:gpl2+)))
8670 (define-public r-rcas
8676 (uri (bioconductor-uri "RCAS" version))
8679 "0f812pgv3ys1zv4n9sqkgm01hj4cdd0i0h85dqbhkwd94zl6cavl"))))
8680 (properties `((upstream-name . "RCAS")))
8681 (build-system r-build-system)
8683 `(("r-biocgenerics" ,r-biocgenerics)
8684 ("r-biostrings" ,r-biostrings)
8685 ("r-bsgenome" ,r-bsgenome)
8686 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8687 ("r-cowplot" ,r-cowplot)
8688 ("r-data-table" ,r-data-table)
8690 ("r-genomation" ,r-genomation)
8691 ("r-genomeinfodb" ,r-genomeinfodb)
8692 ("r-genomicfeatures" ,r-genomicfeatures)
8693 ("r-genomicranges" ,r-genomicranges)
8694 ("r-ggplot2" ,r-ggplot2)
8695 ("r-ggseqlogo" ,r-ggseqlogo)
8696 ("r-gprofiler2" ,r-gprofiler2)
8697 ("r-iranges" ,r-iranges)
8698 ("r-pbapply" ,r-pbapply)
8699 ("r-pheatmap" ,r-pheatmap)
8700 ("r-plotly" ,r-plotly)
8701 ("r-plotrix" ,r-plotrix)
8702 ("r-proxy" ,r-proxy)
8703 ("r-ranger" ,r-ranger)
8704 ("r-rsqlite" ,r-rsqlite)
8705 ("r-rtracklayer" ,r-rtracklayer)
8706 ("r-rmarkdown" ,r-rmarkdown)
8707 ("r-s4vectors" ,r-s4vectors)
8708 ("pandoc" ,pandoc)))
8710 `(("r-knitr" ,r-knitr)))
8711 (synopsis "RNA-centric annotation system")
8713 "RCAS aims to be a standalone RNA-centric annotation system that provides
8714 intuitive reports and publication-ready graphics. This package provides the R
8715 library implementing most of the pipeline's features.")
8716 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8717 (license license:artistic2.0)))
8719 (define-public rcas-web
8726 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8727 "releases/download/v" version
8728 "/rcas-web-" version ".tar.gz"))
8731 "0wq951aj45gqki1bickg876i993lmawkp8x24agg264br5x716db"))))
8732 (build-system gnu-build-system)
8735 (modify-phases %standard-phases
8736 (add-before 'configure 'find-RCAS
8737 ;; The configure script can't find non-1.3.x versions of RCAS because
8738 ;; its R expression ‘1.10.1 >= 1.3.4’ evaluates to false.
8740 (substitute* "configure"
8741 (("1\\.3\\.4") "0.0.0"))
8743 (add-after 'install 'wrap-executable
8744 (lambda* (#:key inputs outputs #:allow-other-keys)
8745 (let* ((out (assoc-ref outputs "out"))
8746 (json (assoc-ref inputs "guile-json"))
8747 (redis (assoc-ref inputs "guile-redis"))
8748 (path (string-append
8749 json "/share/guile/site/2.2:"
8750 redis "/share/guile/site/2.2")))
8751 (wrap-program (string-append out "/bin/rcas-web")
8752 `("GUILE_LOAD_PATH" ":" = (,path))
8753 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8754 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8757 `(("r-minimal" ,r-minimal)
8759 ("guile" ,guile-2.2)
8760 ("guile-json" ,guile-json-1)
8761 ("guile-redis" ,guile2.2-redis)))
8763 `(("pkg-config" ,pkg-config)))
8764 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8765 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8766 (description "This package provides a simple web interface for the
8767 @dfn{RNA-centric annotation system} (RCAS).")
8768 (license license:agpl3+)))
8770 (define-public r-mutationalpatterns
8772 (name "r-mutationalpatterns")
8777 (uri (bioconductor-uri "MutationalPatterns" version))
8780 "02lyjiabyhmifycksvpcx29a0pb7z9xjw0hgg8n0sd0dy3afqhcm"))))
8781 (build-system r-build-system)
8783 `(("r-biocgenerics" ,r-biocgenerics)
8784 ("r-biostrings" ,r-biostrings)
8785 ;; These two packages are suggested packages
8786 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8787 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8788 ("r-genomicranges" ,r-genomicranges)
8789 ("r-genomeinfodb" ,r-genomeinfodb)
8790 ("r-ggplot2" ,r-ggplot2)
8791 ("r-iranges" ,r-iranges)
8794 ("r-pracma" ,r-pracma)
8795 ("r-reshape2" ,r-reshape2)
8796 ("r-cowplot" ,r-cowplot)
8797 ("r-ggdendro" ,r-ggdendro)
8798 ("r-s4vectors" ,r-s4vectors)
8799 ("r-summarizedexperiment" ,r-summarizedexperiment)
8800 ("r-variantannotation" ,r-variantannotation)))
8801 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8802 (synopsis "Extract and visualize mutational patterns in genomic data")
8803 (description "This package provides an extensive toolset for the
8804 characterization and visualization of a wide range of mutational patterns
8805 in SNV base substitution data.")
8806 (license license:expat)))
8808 (define-public r-chipkernels
8809 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8812 (name "r-chipkernels")
8813 (version (string-append "1.1-" revision "." (string-take commit 9)))
8818 (url "https://github.com/ManuSetty/ChIPKernels")
8820 (file-name (string-append name "-" version))
8823 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8824 (build-system r-build-system)
8826 `(("r-iranges" ,r-iranges)
8827 ("r-xvector" ,r-xvector)
8828 ("r-biostrings" ,r-biostrings)
8829 ("r-bsgenome" ,r-bsgenome)
8830 ("r-gtools" ,r-gtools)
8831 ("r-genomicranges" ,r-genomicranges)
8832 ("r-sfsmisc" ,r-sfsmisc)
8833 ("r-kernlab" ,r-kernlab)
8834 ("r-s4vectors" ,r-s4vectors)
8835 ("r-biocgenerics" ,r-biocgenerics)))
8836 (home-page "https://github.com/ManuSetty/ChIPKernels")
8837 (synopsis "Build string kernels for DNA Sequence analysis")
8838 (description "ChIPKernels is an R package for building different string
8839 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8840 must be built and this dictionary can be used for determining kernels for DNA
8842 (license license:gpl2+))))
8844 (define-public r-seqgl
8852 (url "https://github.com/ManuSetty/SeqGL")
8854 (file-name (git-file-name name version))
8857 "1r6ywvhxl3ffv48lgj7sbd582mcc6dha3ksgc2qjlvjrnkbj3799"))))
8858 (build-system r-build-system)
8860 `(("r-biostrings" ,r-biostrings)
8861 ("r-chipkernels" ,r-chipkernels)
8862 ("r-genomicranges" ,r-genomicranges)
8863 ("r-spams" ,r-spams)
8864 ("r-wgcna" ,r-wgcna)
8865 ("r-fastcluster" ,r-fastcluster)))
8866 (home-page "https://github.com/ManuSetty/SeqGL")
8867 (synopsis "Group lasso for Dnase/ChIP-seq data")
8868 (description "SeqGL is a group lasso based algorithm to extract
8869 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8870 This package presents a method which uses group lasso to discriminate between
8871 bound and non bound genomic regions to accurately identify transcription
8872 factors bound at the specific regions.")
8873 (license license:gpl2+)))
8875 (define-public r-tximport
8881 (uri (bioconductor-uri "tximport" version))
8884 "1x9959lkjl2h869rgd1b30q1idxzjkr1fyqbpndqk3kbi4q2gr40"))))
8885 (build-system r-build-system)
8887 `(("r-knitr" ,r-knitr)))
8888 (home-page "https://bioconductor.org/packages/tximport")
8889 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8891 "This package provides tools to import transcript-level abundance,
8892 estimated counts and transcript lengths, and to summarize them into matrices
8893 for use with downstream gene-level analysis packages. Average transcript
8894 length, weighted by sample-specific transcript abundance estimates, is
8895 provided as a matrix which can be used as an offset for different expression
8896 of gene-level counts.")
8897 (license license:gpl2+)))
8899 (define-public r-rhdf5
8905 (uri (bioconductor-uri "rhdf5" version))
8908 "1v6ygi0avh3gmaj2ld2nr7vww4ipw39b5kqci9w27i3ja985lb8j"))))
8909 (build-system r-build-system)
8911 `(("r-rhdf5lib" ,r-rhdf5lib)))
8915 `(("r-knitr" ,r-knitr)))
8916 (home-page "https://bioconductor.org/packages/rhdf5")
8917 (synopsis "HDF5 interface to R")
8919 "This R/Bioconductor package provides an interface between HDF5 and R.
8920 HDF5's main features are the ability to store and access very large and/or
8921 complex datasets and a wide variety of metadata on mass storage (disk) through
8922 a completely portable file format. The rhdf5 package is thus suited for the
8923 exchange of large and/or complex datasets between R and other software
8924 package, and for letting R applications work on datasets that are larger than
8925 the available RAM.")
8926 (license license:artistic2.0)))
8928 (define-public r-annotationfilter
8930 (name "r-annotationfilter")
8934 (uri (bioconductor-uri "AnnotationFilter" version))
8937 "18kh1xrhpwb48s1qj4f1v8af3jmw49pnbp5afi2myn9894hxg0cs"))))
8939 `((upstream-name . "AnnotationFilter")))
8940 (build-system r-build-system)
8942 `(("r-genomicranges" ,r-genomicranges)
8943 ("r-lazyeval" ,r-lazyeval)))
8945 `(("r-knitr" ,r-knitr)))
8946 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8947 (synopsis "Facilities for filtering Bioconductor annotation resources")
8949 "This package provides classes and other infrastructure to implement
8950 filters for manipulating Bioconductor annotation resources. The filters are
8951 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8952 (license license:artistic2.0)))
8954 (define-public emboss
8960 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8961 (version-major+minor version) ".0/"
8962 "EMBOSS-" version ".tar.gz"))
8965 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8966 (build-system gnu-build-system)
8969 (list (string-append "--with-hpdf="
8970 (assoc-ref %build-inputs "libharu")))
8972 (modify-phases %standard-phases
8973 (add-after 'unpack 'fix-checks
8975 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8976 ;; and zlib, but assume that they are all found at the same
8978 (substitute* "configure.in"
8979 (("CHECK_PNGDRIVER")
8980 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8981 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8982 AM_CONDITIONAL(AMPNG, true)"))
8984 (add-after 'fix-checks 'disable-update-check
8986 ;; At build time there is no connection to the Internet, so
8987 ;; looking for updates will not work.
8988 (substitute* "Makefile.am"
8989 (("\\$\\(bindir\\)/embossupdate") ""))
8991 (add-after 'disable-update-check 'autogen
8992 (lambda _ (invoke "autoreconf" "-vif") #t)))))
8998 ("libharu" ,libharu)
9001 `(("autoconf" ,autoconf)
9002 ("automake" ,automake)
9003 ("libtool" ,libtool)
9004 ("pkg-config" ,pkg-config)))
9005 (home-page "http://emboss.sourceforge.net")
9006 (synopsis "Molecular biology analysis suite")
9007 (description "EMBOSS is the \"European Molecular Biology Open Software
9008 Suite\". EMBOSS is an analysis package specially developed for the needs of
9009 the molecular biology (e.g. EMBnet) user community. The software
9010 automatically copes with data in a variety of formats and even allows
9011 transparent retrieval of sequence data from the web. It also provides a
9012 number of libraries for the development of software in the field of molecular
9013 biology. EMBOSS also integrates a range of currently available packages and
9014 tools for sequence analysis into a seamless whole.")
9015 (license license:gpl2+)))
9018 (let ((revision "1")
9019 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
9022 ;; The version is 2.13.0 even though no release archives have been
9023 ;; published as yet.
9024 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
9028 (url "https://github.com/arq5x/bits")
9030 (file-name (string-append name "-" version "-checkout"))
9033 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
9034 (build-system gnu-build-system)
9036 `(#:tests? #f ;no tests included
9038 (modify-phases %standard-phases
9040 (add-after 'unpack 'remove-cuda
9042 (substitute* "Makefile"
9044 (("(bits_test_intersections) \\\\" _ match) match))
9047 (lambda* (#:key outputs #:allow-other-keys)
9049 "bin" (string-append (assoc-ref outputs "out") "/bin"))
9054 (home-page "https://github.com/arq5x/bits")
9055 (synopsis "Implementation of binary interval search algorithm")
9056 (description "This package provides an implementation of the
9057 BITS (Binary Interval Search) algorithm, an approach to interval set
9058 intersection. It is especially suited for the comparison of diverse genomic
9059 datasets and the exploration of large datasets of genome
9060 intervals (e.g. genes, sequence alignments).")
9061 (license license:gpl2))))
9063 (define-public piranha
9064 ;; There is no release tarball for the latest version. The latest commit is
9065 ;; older than one year at the time of this writing.
9066 (let ((revision "1")
9067 (commit "0466d364b71117d01e4471b74c514436cc281233"))
9070 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
9074 (url "https://github.com/smithlabcode/piranha")
9076 (file-name (git-file-name name version))
9079 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
9080 (build-system gnu-build-system)
9082 `(#:test-target "test"
9084 (modify-phases %standard-phases
9085 (add-after 'unpack 'copy-smithlab-cpp
9086 (lambda* (#:key inputs #:allow-other-keys)
9087 (for-each (lambda (file)
9088 (install-file file "./src/smithlab_cpp/"))
9089 (find-files (assoc-ref inputs "smithlab-cpp")))
9091 (add-after 'install 'install-to-store
9092 (lambda* (#:key outputs #:allow-other-keys)
9093 (let* ((out (assoc-ref outputs "out"))
9094 (bin (string-append out "/bin")))
9095 (for-each (lambda (file)
9096 (install-file file bin))
9097 (find-files "bin" ".*")))
9100 (list (string-append "--with-bam_tools_headers="
9101 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
9102 (string-append "--with-bam_tools_library="
9103 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
9105 `(("bamtools" ,bamtools)
9106 ("samtools" ,samtools-0.1)
9109 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
9113 (url "https://github.com/smithlabcode/smithlab_cpp")
9115 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
9118 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
9120 `(("python" ,python-2)))
9121 (home-page "https://github.com/smithlabcode/piranha")
9122 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
9124 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
9125 RIP-seq experiments. It takes input in BED or BAM format and identifies
9126 regions of statistically significant read enrichment. Additional covariates
9127 may optionally be provided to further inform the peak-calling process.")
9128 (license license:gpl3+))))
9136 (uri (pypi-uri "PePr" version))
9139 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
9140 (build-system python-build-system)
9142 `(#:python ,python-2 ; python2 only
9143 #:tests? #f)) ; no tests included
9145 `(("python2-numpy" ,python2-numpy)
9146 ("python2-scipy" ,python2-scipy)
9147 ("python2-pysam" ,python2-pysam)))
9148 (home-page "https://github.com/shawnzhangyx/PePr")
9149 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
9151 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
9152 that is primarily designed for data with biological replicates. It uses a
9153 negative binomial distribution to model the read counts among the samples in
9154 the same group, and look for consistent differences between ChIP and control
9155 group or two ChIP groups run under different conditions.")
9156 (license license:gpl3+)))
9158 (define-public filevercmp
9159 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
9162 (version (string-append "0-1." (string-take commit 7)))
9166 (url "https://github.com/ekg/filevercmp")
9168 (file-name (git-file-name name commit))
9171 "1j9vxsy0y050v59h0q1d6501fcw1kjvj0d18l1xk2zyg0jzj247c"))))
9172 (build-system gnu-build-system)
9174 `(#:tests? #f ; There are no tests to run.
9176 (modify-phases %standard-phases
9177 (delete 'configure) ; There is no configure phase.
9179 (lambda* (#:key outputs #:allow-other-keys)
9180 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
9181 (install-file "filevercmp" bin)
9183 (home-page "https://github.com/ekg/filevercmp")
9184 (synopsis "This program compares version strings")
9185 (description "This program compares version strings. It intends to be a
9186 replacement for strverscmp.")
9187 (license license:gpl3+))))
9189 (define-public multiqc
9196 (uri (pypi-uri "multiqc" version))
9199 "02iihfl0w0hpnr4pa0sbd1y9qxrg3ycyhjp5lidkcrqh1lmzs3zy"))))
9200 (build-system python-build-system)
9202 `(("python-jinja2" ,python-jinja2)
9203 ("python-simplejson" ,python-simplejson)
9204 ("python-pyyaml" ,python-pyyaml)
9205 ("python-click" ,python-click)
9206 ("python-spectra" ,python-spectra)
9207 ("python-requests" ,python-requests)
9208 ("python-markdown" ,python-markdown)
9209 ("python-lzstring" ,python-lzstring)
9210 ("python-matplotlib" ,python-matplotlib)
9211 ("python-numpy" ,python-numpy)
9212 ;; MultQC checks for the presence of nose at runtime.
9213 ("python-nose" ,python-nose)))
9216 (modify-phases %standard-phases
9217 (add-after 'unpack 'relax-requirements
9219 (substitute* "setup.py"
9220 ;; MultiQC 1.5 ‘requires’ a version of python-matplotlib older
9221 ;; than the one in Guix, but should work fine with 2.2.2.
9222 ;; See <https://github.com/ewels/MultiQC/issues/725> and
9223 ;; <https://github.com/ewels/MultiQC/issues/732> for details.
9224 (("['\"]matplotlib.*?['\"]")
9227 (home-page "https://multiqc.info")
9228 (synopsis "Aggregate bioinformatics analysis reports")
9230 "MultiQC is a tool to aggregate bioinformatics results across many
9231 samples into a single report. It contains modules for a large number of
9232 common bioinformatics tools.")
9233 (license license:gpl3+)))
9235 (define-public variant-tools
9237 (name "variant-tools")
9243 (url "https://github.com/vatlab/varianttools")
9244 ;; There is no tag corresponding to version 3.1.2
9245 (commit "813ae4a90d25b69abc8a40f4f70441fe09015249")))
9246 (file-name (git-file-name name version))
9249 "12ibdmksj7icyqhks4xyvd61bygk4pjmxn618kp6vgk1af01y34g"))))
9250 (build-system python-build-system)
9253 ("c-blosc" ,c-blosc)
9256 ("hdf5-blosc" ,hdf5-blosc)
9257 ("python-cython" ,python-cython)
9260 `(("python-numpy" ,python-numpy)
9261 ("python-pycurl" ,python-pycurl)
9262 ("python-pyzmq" ,python-pyzmq)
9263 ("python-scipy" ,python-scipy)
9264 ("python-tables" ,python-tables)))
9265 (home-page "https://vatlab.github.io/vat-docs/")
9266 (synopsis "Analyze genetic variants from Next-Gen sequencing studies")
9268 "Variant tools is a tool for the manipulation, annotation,
9269 selection, simulation, and analysis of variants in the context of next-gen
9270 sequencing analysis. Unlike some other tools used for next-gen sequencing
9271 analysis, variant tools is project based and provides a whole set of tools to
9272 manipulate and analyze genetic variants.")
9273 (license license:gpl3+)))
9275 (define-public r-chipseq
9282 (uri (bioconductor-uri "chipseq" version))
9285 "0lh859s0aq73vac1phcgagf6n000qgq2xsk0bmfr61n5swifml2a"))))
9286 (build-system r-build-system)
9288 `(("r-biocgenerics" ,r-biocgenerics)
9289 ("r-genomicranges" ,r-genomicranges)
9290 ("r-iranges" ,r-iranges)
9291 ("r-lattice" ,r-lattice)
9292 ("r-s4vectors" ,r-s4vectors)
9293 ("r-shortread" ,r-shortread)))
9294 (home-page "https://bioconductor.org/packages/chipseq")
9295 (synopsis "Package for analyzing ChIPseq data")
9297 "This package provides tools for processing short read data from ChIPseq
9299 (license license:artistic2.0)))
9301 (define-public r-copyhelper
9303 (name "r-copyhelper")
9308 (uri (string-append "https://bioconductor.org/packages/release/"
9309 "data/experiment/src/contrib/CopyhelpeR_"
9313 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
9314 (properties `((upstream-name . "CopyhelpeR")))
9315 (build-system r-build-system)
9316 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
9317 (synopsis "Helper files for CopywriteR")
9319 "This package contains the helper files that are required to run the
9320 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
9321 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
9322 mm10. In addition, it contains a blacklist filter to remove regions that
9323 display copy number variation. Files are stored as GRanges objects from the
9324 GenomicRanges Bioconductor package.")
9325 (license license:gpl2)))
9327 (define-public r-copywriter
9329 (name "r-copywriter")
9334 (uri (bioconductor-uri "CopywriteR" version))
9337 "0c36wpv0rygkbqpf3dwh5xmc3lr7p8lrdzsq2fbbpw04skl6i7m2"))))
9338 (properties `((upstream-name . "CopywriteR")))
9339 (build-system r-build-system)
9341 `(("r-biocparallel" ,r-biocparallel)
9342 ("r-chipseq" ,r-chipseq)
9343 ("r-copyhelper" ,r-copyhelper)
9344 ("r-data-table" ,r-data-table)
9345 ("r-dnacopy" ,r-dnacopy)
9346 ("r-futile-logger" ,r-futile-logger)
9347 ("r-genomeinfodb" ,r-genomeinfodb)
9348 ("r-genomicalignments" ,r-genomicalignments)
9349 ("r-genomicranges" ,r-genomicranges)
9350 ("r-gtools" ,r-gtools)
9351 ("r-iranges" ,r-iranges)
9352 ("r-matrixstats" ,r-matrixstats)
9353 ("r-rsamtools" ,r-rsamtools)
9354 ("r-s4vectors" ,r-s4vectors)))
9355 (home-page "https://github.com/PeeperLab/CopywriteR")
9356 (synopsis "Copy number information from targeted sequencing")
9358 "CopywriteR extracts DNA copy number information from targeted sequencing
9359 by utilizing off-target reads. It allows for extracting uniformly distributed
9360 copy number information, can be used without reference, and can be applied to
9361 sequencing data obtained from various techniques including chromatin
9362 immunoprecipitation and target enrichment on small gene panels. Thereby,
9363 CopywriteR constitutes a widely applicable alternative to available copy
9364 number detection tools.")
9365 (license license:gpl2)))
9367 (define-public r-methylkit
9369 (name "r-methylkit")
9373 (uri (bioconductor-uri "methylKit" version))
9376 "1qr13d2712ypbn96ijic2z5adr5dsd61kzscx7shw6vyj360rlm5"))))
9377 (properties `((upstream-name . "methylKit")))
9378 (build-system r-build-system)
9380 `(("r-data-table" ,r-data-table)
9381 ("r-emdbook" ,r-emdbook)
9382 ("r-fastseg" ,r-fastseg)
9383 ("r-genomeinfodb" ,r-genomeinfodb)
9384 ("r-genomicranges" ,r-genomicranges)
9385 ("r-gtools" ,r-gtools)
9386 ("r-iranges" ,r-iranges)
9387 ("r-kernsmooth" ,r-kernsmooth)
9388 ("r-limma" ,r-limma)
9389 ("r-mclust" ,r-mclust)
9391 ("r-qvalue" ,r-qvalue)
9392 ("r-r-utils" ,r-r-utils)
9394 ("r-rhtslib" ,r-rhtslib)
9395 ("r-rsamtools" ,r-rsamtools)
9396 ("r-rtracklayer" ,r-rtracklayer)
9397 ("r-s4vectors" ,r-s4vectors)
9398 ("r-zlibbioc" ,r-zlibbioc)))
9400 `(("r-knitr" ,r-knitr))) ; for vignettes
9403 (home-page "https://github.com/al2na/methylKit")
9405 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9407 "MethylKit is an R package for DNA methylation analysis and annotation
9408 from high-throughput bisulfite sequencing. The package is designed to deal
9409 with sequencing data from @dfn{Reduced representation bisulfite
9410 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9411 genome bisulfite sequencing. It also has functions to analyze base-pair
9412 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9414 (license license:artistic2.0)))
9416 (define-public r-sva
9423 (uri (bioconductor-uri "sva" version))
9426 "0xa1lm0k1a6nig90mab6xh4gln88rbs5l1cdr6ik6agg7jhs7ji4"))))
9427 (build-system r-build-system)
9429 `(("r-edger" ,r-edger)
9430 ("r-genefilter" ,r-genefilter)
9432 ("r-biocparallel" ,r-biocparallel)
9433 ("r-matrixstats" ,r-matrixstats)
9434 ("r-limma" ,r-limma)))
9435 (home-page "https://bioconductor.org/packages/sva")
9436 (synopsis "Surrogate variable analysis")
9438 "This package contains functions for removing batch effects and other
9439 unwanted variation in high-throughput experiment. It also contains functions
9440 for identifying and building surrogate variables for high-dimensional data
9441 sets. Surrogate variables are covariates constructed directly from
9442 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9443 imaging data that can be used in subsequent analyses to adjust for unknown,
9444 unmodeled, or latent sources of noise.")
9445 (license license:artistic2.0)))
9447 (define-public r-seqminer
9454 (uri (cran-uri "seqminer" version))
9457 "00jzj8mwb0zaiwlifd41b26mrq9mzigj18nc29dydi0r42hxg16i"))))
9458 (build-system r-build-system)
9461 (home-page "http://seqminer.genomic.codes")
9462 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9464 "This package provides tools to integrate nucleotide sequencing
9465 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9466 ;; Any version of the GPL is acceptable
9467 (license (list license:gpl2+ license:gpl3+))))
9469 (define-public r-raremetals2
9471 (name "r-raremetals2")
9476 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9477 "b/b7/RareMETALS2_" version ".tar.gz"))
9480 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9481 (properties `((upstream-name . "RareMETALS2")))
9482 (build-system r-build-system)
9484 `(("r-seqminer" ,r-seqminer)
9485 ("r-mvtnorm" ,r-mvtnorm)
9487 ("r-compquadform" ,r-compquadform)
9488 ("r-getopt" ,r-getopt)))
9489 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9490 (synopsis "Analyze gene-level association tests for binary trait")
9492 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9493 It was designed to meta-analyze gene-level association tests for binary trait.
9494 While rareMETALS offers a near-complete solution for meta-analysis of
9495 gene-level tests for quantitative trait, it does not offer the optimal
9496 solution for binary trait. The package rareMETALS2 offers improved features
9497 for analyzing gene-level association tests in meta-analyses for binary
9499 (license license:gpl3)))
9501 (define-public r-maldiquant
9503 (name "r-maldiquant")
9508 (uri (cran-uri "MALDIquant" version))
9511 "0b7kdz3x4sdq413h1q09l1qhcvdnnwv6fqsqwllks1cd3xy34c57"))))
9512 (properties `((upstream-name . "MALDIquant")))
9513 (build-system r-build-system)
9514 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9515 (synopsis "Quantitative analysis of mass spectrometry data")
9517 "This package provides a complete analysis pipeline for matrix-assisted
9518 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9519 two-dimensional mass spectrometry data. In addition to commonly used plotting
9520 and processing methods it includes distinctive features, namely baseline
9521 subtraction methods such as morphological filters (TopHat) or the
9522 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9523 alignment using warping functions, handling of replicated measurements as well
9524 as allowing spectra with different resolutions.")
9525 (license license:gpl3+)))
9527 (define-public r-protgenerics
9529 (name "r-protgenerics")
9534 (uri (bioconductor-uri "ProtGenerics" version))
9537 "14xzdh7vxss8vmrw91hcwrszdn3ikm71mah8875b2lkrkrfzbl73"))))
9538 (properties `((upstream-name . "ProtGenerics")))
9539 (build-system r-build-system)
9540 (home-page "https://github.com/lgatto/ProtGenerics")
9541 (synopsis "S4 generic functions for proteomics infrastructure")
9543 "This package provides S4 generic functions needed by Bioconductor
9544 proteomics packages.")
9545 (license license:artistic2.0)))
9547 (define-public r-mzr
9554 (uri (bioconductor-uri "mzR" version))
9557 "1r8j8yiz5lcan7j4h37sza2kwczl48dxvld3da3ghjjq67cdc2cm"))
9558 (modules '((guix build utils)))
9561 (delete-file-recursively "src/boost")
9563 (properties `((upstream-name . "mzR")))
9564 (build-system r-build-system)
9567 (modify-phases %standard-phases
9568 (add-after 'unpack 'use-system-boost
9570 (substitute* "src/Makevars"
9571 (("\\./boost/libs.*") "")
9572 (("ARCH_OBJS=" line)
9574 "\nARCH_LIBS=-lboost_system -lboost_regex \
9575 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9578 `(;; Our default boost package won't work here, unfortunately, even with
9579 ;; mzR version 2.22.0.
9580 ("boost" ,boost-for-mysql) ; use this instead of the bundled boost sources
9583 `(("r-biobase" ,r-biobase)
9584 ("r-biocgenerics" ,r-biocgenerics)
9585 ("r-ncdf4" ,r-ncdf4)
9586 ("r-protgenerics" ,r-protgenerics)
9588 ("r-rhdf5lib" ,r-rhdf5lib)
9589 ("r-zlibbioc" ,r-zlibbioc)))
9591 `(("r-knitr" ,r-knitr)))
9592 (home-page "https://github.com/sneumann/mzR/")
9593 (synopsis "Parser for mass spectrometry data files")
9595 "The mzR package provides a unified API to the common file formats and
9596 parsers available for mass spectrometry data. It comes with a wrapper for the
9597 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9598 The package contains the original code written by the ISB, and a subset of the
9599 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9600 previously been used in XCMS.")
9601 (license license:artistic2.0)))
9603 (define-public r-affyio
9610 (uri (bioconductor-uri "affyio" version))
9613 "0j1f61409yq6hmkqrpzamfm7dx35rlq33ccs7wb1qcqx3d3nb75q"))))
9614 (build-system r-build-system)
9616 `(("r-zlibbioc" ,r-zlibbioc)))
9619 (home-page "https://github.com/bmbolstad/affyio")
9620 (synopsis "Tools for parsing Affymetrix data files")
9622 "This package provides routines for parsing Affymetrix data files based
9623 upon file format information. The primary focus is on accessing the CEL and
9625 (license license:lgpl2.0+)))
9627 (define-public r-affy
9634 (uri (bioconductor-uri "affy" version))
9637 "0m6hkyjxmsf80n3anhwh9k26csxczv6v92fkb7klnchdski61pyc"))))
9638 (build-system r-build-system)
9640 `(("r-affyio" ,r-affyio)
9641 ("r-biobase" ,r-biobase)
9642 ("r-biocgenerics" ,r-biocgenerics)
9643 ("r-biocmanager" ,r-biocmanager)
9644 ("r-preprocesscore" ,r-preprocesscore)
9645 ("r-zlibbioc" ,r-zlibbioc)))
9648 (home-page "https://bioconductor.org/packages/affy")
9649 (synopsis "Methods for affymetrix oligonucleotide arrays")
9651 "This package contains functions for exploratory oligonucleotide array
9653 (license license:lgpl2.0+)))
9655 (define-public r-vsn
9662 (uri (bioconductor-uri "vsn" version))
9665 "1k82dikrv1gcync5y1131wg7z1kxv2z2jl4nndg20bixc3398h58"))))
9666 (build-system r-build-system)
9668 `(("r-affy" ,r-affy)
9669 ("r-biobase" ,r-biobase)
9670 ("r-ggplot2" ,r-ggplot2)
9671 ("r-lattice" ,r-lattice)
9672 ("r-limma" ,r-limma)))
9674 `(("r-knitr" ,r-knitr))) ; for vignettes
9675 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9676 (synopsis "Variance stabilization and calibration for microarray data")
9678 "The package implements a method for normalising microarray intensities,
9679 and works for single- and multiple-color arrays. It can also be used for data
9680 from other technologies, as long as they have similar format. The method uses
9681 a robust variant of the maximum-likelihood estimator for an
9682 additive-multiplicative error model and affine calibration. The model
9683 incorporates data calibration step (a.k.a. normalization), a model for the
9684 dependence of the variance on the mean intensity and a variance stabilizing
9685 data transformation. Differences between transformed intensities are
9686 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9687 their variance is independent of the mean, and they are usually more sensitive
9688 and specific in detecting differential transcription.")
9689 (license license:artistic2.0)))
9691 (define-public r-mzid
9698 (uri (bioconductor-uri "mzID" version))
9701 "0y50lzkdamkpz67f6r5whp246qsxpbammjil7g8vjprx0c4jk5n5"))))
9702 (properties `((upstream-name . "mzID")))
9703 (build-system r-build-system)
9705 `(("r-doparallel" ,r-doparallel)
9706 ("r-foreach" ,r-foreach)
9707 ("r-iterators" ,r-iterators)
9709 ("r-protgenerics" ,r-protgenerics)
9713 `(("r-knitr" ,r-knitr)))
9714 (home-page "https://bioconductor.org/packages/mzID")
9715 (synopsis "Parser for mzIdentML files")
9717 "This package provides a parser for mzIdentML files implemented using the
9718 XML package. The parser tries to be general and able to handle all types of
9719 mzIdentML files with the drawback of having less pretty output than a vendor
9721 (license license:gpl2+)))
9723 (define-public r-pcamethods
9725 (name "r-pcamethods")
9730 (uri (bioconductor-uri "pcaMethods" version))
9733 "10cww4jxyynkwxbbsx804nwac31j0hh8dgisygld0q663gaxkgni"))))
9734 (properties `((upstream-name . "pcaMethods")))
9735 (build-system r-build-system)
9737 `(("r-biobase" ,r-biobase)
9738 ("r-biocgenerics" ,r-biocgenerics)
9740 ("r-rcpp" ,r-rcpp)))
9741 (home-page "https://github.com/hredestig/pcamethods")
9742 (synopsis "Collection of PCA methods")
9744 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9745 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9746 for missing value estimation is included for comparison. BPCA, PPCA and
9747 NipalsPCA may be used to perform PCA on incomplete data as well as for
9748 accurate missing value estimation. A set of methods for printing and plotting
9749 the results is also provided. All PCA methods make use of the same data
9750 structure (pcaRes) to provide a common interface to the PCA results.")
9751 (license license:gpl3+)))
9753 (define-public r-msnbase
9760 (uri (bioconductor-uri "MSnbase" version))
9763 "17vlv9gh41s1hp043b7j1jfqiw52alh1misjzy1kxl0g90rld00l"))))
9764 (properties `((upstream-name . "MSnbase")))
9765 (build-system r-build-system)
9767 `(("r-affy" ,r-affy)
9768 ("r-biobase" ,r-biobase)
9769 ("r-biocgenerics" ,r-biocgenerics)
9770 ("r-biocparallel" ,r-biocparallel)
9771 ("r-digest" ,r-digest)
9772 ("r-ggplot2" ,r-ggplot2)
9773 ("r-impute" ,r-impute)
9774 ("r-iranges" ,r-iranges)
9775 ("r-lattice" ,r-lattice)
9776 ("r-maldiquant" ,r-maldiquant)
9780 ("r-pcamethods" ,r-pcamethods)
9782 ("r-preprocesscore" ,r-preprocesscore)
9783 ("r-protgenerics" ,r-protgenerics)
9785 ("r-s4vectors" ,r-s4vectors)
9786 ("r-scales" ,r-scales)
9790 `(("r-knitr" ,r-knitr)))
9791 (home-page "https://github.com/lgatto/MSnbase")
9792 (synopsis "Base functions and classes for MS-based proteomics")
9794 "This package provides basic plotting, data manipulation and processing
9795 of mass spectrometry based proteomics data.")
9796 (license license:artistic2.0)))
9798 (define-public r-msnid
9805 (uri (bioconductor-uri "MSnID" version))
9808 "0dwa6j2nqb3223a8g4f453aznjh69wngrpvdi12iy69j1psbbjcc"))))
9809 (properties `((upstream-name . "MSnID")))
9810 (build-system r-build-system)
9812 `(("r-biobase" ,r-biobase)
9813 ("r-data-table" ,r-data-table)
9814 ("r-doparallel" ,r-doparallel)
9815 ("r-dplyr" ,r-dplyr)
9816 ("r-foreach" ,r-foreach)
9817 ("r-iterators" ,r-iterators)
9818 ("r-msnbase" ,r-msnbase)
9821 ("r-protgenerics" ,r-protgenerics)
9822 ("r-r-cache" ,r-r-cache)
9824 ("r-reshape2" ,r-reshape2)))
9825 (home-page "https://bioconductor.org/packages/MSnID")
9826 (synopsis "Utilities for LC-MSn proteomics identifications")
9828 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9829 from mzIdentML (leveraging the mzID package) or text files. After collating
9830 the search results from multiple datasets it assesses their identification
9831 quality and optimize filtering criteria to achieve the maximum number of
9832 identifications while not exceeding a specified false discovery rate. It also
9833 contains a number of utilities to explore the MS/MS results and assess missed
9834 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9835 (license license:artistic2.0)))
9837 (define-public r-seurat
9843 (uri (cran-uri "Seurat" version))
9846 "1vj3dlsqakgnn4x1jz9fkl2cy0jzc5s65h1c20fnamr7lk45pnf2"))))
9847 (properties `((upstream-name . "Seurat")))
9848 (build-system r-build-system)
9851 ("r-cluster" ,r-cluster)
9852 ("r-cowplot" ,r-cowplot)
9853 ("r-fitdistrplus" ,r-fitdistrplus)
9854 ("r-future" ,r-future)
9855 ("r-future-apply" ,r-future-apply)
9856 ("r-ggplot2" ,r-ggplot2)
9857 ("r-ggrepel" ,r-ggrepel)
9858 ("r-ggridges" ,r-ggridges)
9861 ("r-igraph" ,r-igraph)
9862 ("r-irlba" ,r-irlba)
9863 ("r-jsonlite" ,r-jsonlite)
9864 ("r-kernsmooth" ,r-kernsmooth)
9865 ("r-leiden" ,r-leiden)
9866 ("r-lmtest" ,r-lmtest)
9868 ("r-matrix" ,r-matrix)
9869 ("r-miniui" ,r-miniui)
9870 ("r-patchwork" ,r-patchwork)
9871 ("r-pbapply" ,r-pbapply)
9872 ("r-plotly" ,r-plotly)
9875 ("r-rcolorbrewer" ,r-rcolorbrewer)
9877 ("r-rcppannoy" ,r-rcppannoy)
9878 ("r-rcppeigen" ,r-rcppeigen)
9879 ("r-rcppprogress" ,r-rcppprogress)
9880 ("r-reticulate" ,r-reticulate)
9881 ("r-rlang" ,r-rlang)
9884 ("r-rtsne" ,r-rtsne)
9885 ("r-scales" ,r-scales)
9886 ("r-sctransform" ,r-sctransform)
9887 ("r-shiny" ,r-shiny)
9888 ("r-spatstat" ,r-spatstat)
9889 ("r-tibble" ,r-tibble)
9890 ("r-uwot" ,r-uwot)))
9891 (home-page "http://www.satijalab.org/seurat")
9892 (synopsis "Seurat is an R toolkit for single cell genomics")
9894 "This package is an R package designed for QC, analysis, and
9895 exploration of single cell RNA-seq data. It easily enables widely-used
9896 analytical techniques, including the identification of highly variable genes,
9897 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9898 algorithms; density clustering, hierarchical clustering, k-means, and the
9899 discovery of differentially expressed genes and markers.")
9900 (license license:gpl3)))
9902 (define-public r-aroma-light
9904 (name "r-aroma-light")
9909 (uri (bioconductor-uri "aroma.light" version))
9912 "19y5f2minx2pp73zdh43v1qkwpkaxygkl8cwlnwja15i46s0bcyc"))))
9913 (properties `((upstream-name . "aroma.light")))
9914 (build-system r-build-system)
9916 `(("r-matrixstats" ,r-matrixstats)
9917 ("r-r-methodss3" ,r-r-methodss3)
9919 ("r-r-utils" ,r-r-utils)))
9920 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9921 (synopsis "Methods for normalization and visualization of microarray data")
9923 "This package provides methods for microarray analysis that take basic
9924 data types such as matrices and lists of vectors. These methods can be used
9925 standalone, be utilized in other packages, or be wrapped up in higher-level
9927 (license license:gpl2+)))
9929 (define-public r-deseq
9936 (uri (bioconductor-uri "DESeq" version))
9939 "047hph5aqmjnz1aqprziw0smdn5lf96hmwpnvqrxv1j2yfvcf3h1"))))
9940 (properties `((upstream-name . "DESeq")))
9941 (build-system r-build-system)
9943 `(("r-biobase" ,r-biobase)
9944 ("r-biocgenerics" ,r-biocgenerics)
9945 ("r-genefilter" ,r-genefilter)
9946 ("r-geneplotter" ,r-geneplotter)
9947 ("r-lattice" ,r-lattice)
9948 ("r-locfit" ,r-locfit)
9950 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9951 (home-page "https://www-huber.embl.de/users/anders/DESeq/")
9952 (synopsis "Differential gene expression analysis")
9954 "This package provides tools for estimating variance-mean dependence in
9955 count data from high-throughput genetic sequencing assays and for testing for
9956 differential expression based on a model using the negative binomial
9958 (license license:gpl3+)))
9960 (define-public r-edaseq
9967 (uri (bioconductor-uri "EDASeq" version))
9970 "12gzxjh73qshlwvsf92lbrf4bi199kxg2snrkprh1z4yqf7bjfm4"))))
9971 (properties `((upstream-name . "EDASeq")))
9972 (build-system r-build-system)
9974 `(("r-annotationdbi" ,r-annotationdbi)
9975 ("r-aroma-light" ,r-aroma-light)
9976 ("r-biobase" ,r-biobase)
9977 ("r-biocgenerics" ,r-biocgenerics)
9978 ("r-biocmanager" ,r-biocmanager)
9979 ("r-biomart" ,r-biomart)
9980 ("r-biostrings" ,r-biostrings)
9981 ("r-deseq" ,r-deseq)
9982 ("r-genomicfeatures" ,r-genomicfeatures)
9983 ("r-genomicranges" ,r-genomicranges)
9984 ("r-iranges" ,r-iranges)
9985 ("r-rsamtools" ,r-rsamtools)
9986 ("r-shortread" ,r-shortread)))
9988 `(("r-knitr" ,r-knitr)))
9989 (home-page "https://github.com/drisso/EDASeq")
9990 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9992 "This package provides support for numerical and graphical summaries of
9993 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9994 adjust for GC-content effect (or other gene-level effects) on read counts:
9995 loess robust local regression, global-scaling, and full-quantile
9996 normalization. Between-lane normalization procedures to adjust for
9997 distributional differences between lanes (e.g., sequencing depth):
9998 global-scaling and full-quantile normalization.")
9999 (license license:artistic2.0)))
10001 (define-public r-interactivedisplaybase
10003 (name "r-interactivedisplaybase")
10008 (uri (bioconductor-uri "interactiveDisplayBase" version))
10011 "1x5vipqa4pgwpd62c1c58shnlpv3zyzzpf4wdwr00q1swkdb7wv3"))))
10013 `((upstream-name . "interactiveDisplayBase")))
10014 (build-system r-build-system)
10016 `(("r-biocgenerics" ,r-biocgenerics)
10018 ("r-shiny" ,r-shiny)))
10020 `(("r-knitr" ,r-knitr)))
10021 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
10022 (synopsis "Base package for web displays of Bioconductor objects")
10024 "This package contains the basic methods needed to generate interactive
10025 Shiny-based display methods for Bioconductor objects.")
10026 (license license:artistic2.0)))
10028 (define-public r-annotationhub
10030 (name "r-annotationhub")
10035 (uri (bioconductor-uri "AnnotationHub" version))
10038 "04bz91m2wx1zm61rvpr0syyklz232fw74wrl73d965wi3x8fyda5"))))
10039 (properties `((upstream-name . "AnnotationHub")))
10040 (build-system r-build-system)
10042 `(("r-annotationdbi" ,r-annotationdbi)
10043 ("r-biocfilecache" ,r-biocfilecache)
10044 ("r-biocgenerics" ,r-biocgenerics)
10045 ("r-biocmanager" ,r-biocmanager)
10046 ("r-biocversion" ,r-biocversion)
10048 ("r-dplyr" ,r-dplyr)
10050 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
10051 ("r-rappdirs" ,r-rappdirs)
10052 ("r-rsqlite" ,r-rsqlite)
10053 ("r-s4vectors" ,r-s4vectors)
10054 ("r-yaml" ,r-yaml)))
10056 `(("r-knitr" ,r-knitr)))
10057 (home-page "https://bioconductor.org/packages/AnnotationHub")
10058 (synopsis "Client to access AnnotationHub resources")
10060 "This package provides a client for the Bioconductor AnnotationHub web
10061 resource. The AnnotationHub web resource provides a central location where
10062 genomic files (e.g. VCF, bed, wig) and other resources from standard
10063 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
10064 metadata about each resource, e.g., a textual description, tags, and date of
10065 modification. The client creates and manages a local cache of files retrieved
10066 by the user, helping with quick and reproducible access.")
10067 (license license:artistic2.0)))
10069 (define-public r-fastseg
10076 (uri (bioconductor-uri "fastseg" version))
10079 "1d48n245pzmvcpsz93lxb4frqh222gfhpmlvm0sb74skn16way63"))))
10080 (build-system r-build-system)
10082 `(("r-biobase" ,r-biobase)
10083 ("r-biocgenerics" ,r-biocgenerics)
10084 ("r-genomicranges" ,r-genomicranges)
10085 ("r-iranges" ,r-iranges)
10086 ("r-s4vectors" ,r-s4vectors)))
10087 (home-page "https://www.bioinf.jku.at/software/fastseg/index.html")
10088 (synopsis "Fast segmentation algorithm for genetic sequencing data")
10090 "Fastseg implements a very fast and efficient segmentation algorithm.
10091 It can segment data from DNA microarrays and data from next generation
10092 sequencing for example to detect copy number segments. Further it can segment
10093 data from RNA microarrays like tiling arrays to identify transcripts. Most
10094 generally, it can segment data given as a matrix or as a vector. Various data
10095 formats can be used as input to fastseg like expression set objects for
10096 microarrays or GRanges for sequencing data.")
10097 (license license:lgpl2.0+)))
10099 (define-public r-keggrest
10101 (name "r-keggrest")
10106 (uri (bioconductor-uri "KEGGREST" version))
10109 "0q76w17fya2x0z7mvyhkk5kqh07flldgih13ma44vhcy1bdlm6j1"))))
10110 (properties `((upstream-name . "KEGGREST")))
10111 (build-system r-build-system)
10113 `(("r-biostrings" ,r-biostrings)
10117 `(("r-knitr" ,r-knitr)))
10118 (home-page "https://bioconductor.org/packages/KEGGREST")
10119 (synopsis "Client-side REST access to KEGG")
10121 "This package provides a package that provides a client interface to the
10122 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
10123 (license license:artistic2.0)))
10125 (define-public r-gage
10132 (uri (bioconductor-uri "gage" version))
10135 "1bqmvjiya1df0b3h491lp1jxahiyidvaf9n094z0sk84x5y3xh2p"))))
10136 (build-system r-build-system)
10138 `(("r-annotationdbi" ,r-annotationdbi)
10139 ("r-go-db" ,r-go-db)
10140 ("r-graph" ,r-graph)
10141 ("r-keggrest" ,r-keggrest)))
10142 (home-page (string-append "https://bmcbioinformatics.biomedcentral.com/"
10143 "articles/10.1186/1471-2105-10-161"))
10144 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
10146 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
10147 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
10148 data attributes including sample sizes, experimental designs, assay platforms,
10149 and other types of heterogeneity. The gage package provides functions for
10150 basic GAGE analysis, result processing and presentation. In addition, it
10151 provides demo microarray data and commonly used gene set data based on KEGG
10152 pathways and GO terms. These functions and data are also useful for gene set
10153 analysis using other methods.")
10154 (license license:gpl2+)))
10156 (define-public r-genomicfiles
10158 (name "r-genomicfiles")
10163 (uri (bioconductor-uri "GenomicFiles" version))
10166 "1k3824pzf9fdqvcv6cz2742q3mabpmncrc72hwa21ac8wy1b04n4"))))
10167 (properties `((upstream-name . "GenomicFiles")))
10168 (build-system r-build-system)
10170 `(("r-biocgenerics" ,r-biocgenerics)
10171 ("r-biocparallel" ,r-biocparallel)
10172 ("r-genomeinfodb" ,r-genomeinfodb)
10173 ("r-genomicalignments" ,r-genomicalignments)
10174 ("r-genomicranges" ,r-genomicranges)
10175 ("r-iranges" ,r-iranges)
10176 ("r-rsamtools" ,r-rsamtools)
10177 ("r-rtracklayer" ,r-rtracklayer)
10178 ("r-s4vectors" ,r-s4vectors)
10179 ("r-summarizedexperiment" ,r-summarizedexperiment)
10180 ("r-variantannotation" ,r-variantannotation)))
10181 (home-page "https://bioconductor.org/packages/GenomicFiles")
10182 (synopsis "Distributed computing by file or by range")
10184 "This package provides infrastructure for parallel computations
10185 distributed by file or by range. User defined mapper and reducer functions
10186 provide added flexibility for data combination and manipulation.")
10187 (license license:artistic2.0)))
10189 (define-public r-complexheatmap
10191 (name "r-complexheatmap")
10196 (uri (bioconductor-uri "ComplexHeatmap" version))
10199 "1gx0hzrkla92pgmfkrm2zp0ccnhizq6rs26zgzpi5x8a5lvghh5q"))))
10201 `((upstream-name . "ComplexHeatmap")))
10202 (build-system r-build-system)
10204 `(("r-circlize" ,r-circlize)
10206 ("r-colorspace" ,r-colorspace)
10207 ("r-getoptlong" ,r-getoptlong)
10208 ("r-globaloptions" ,r-globaloptions)
10210 ("r-rcolorbrewer" ,r-rcolorbrewer)))
10212 `(("r-knitr" ,r-knitr)))
10214 "https://github.com/jokergoo/ComplexHeatmap")
10215 (synopsis "Making Complex Heatmaps")
10217 "Complex heatmaps are efficient to visualize associations between
10218 different sources of data sets and reveal potential structures. This package
10219 provides a highly flexible way to arrange multiple heatmaps and supports
10220 self-defined annotation graphics.")
10221 (license license:gpl2+)))
10223 (define-public r-dirichletmultinomial
10225 (name "r-dirichletmultinomial")
10230 (uri (bioconductor-uri "DirichletMultinomial" version))
10233 "1m9dsrddrllb2i88qzik1867iv9mggrgdkn0dlp8sq7gl69vmalb"))))
10235 `((upstream-name . "DirichletMultinomial")))
10236 (build-system r-build-system)
10240 `(("r-biocgenerics" ,r-biocgenerics)
10241 ("r-iranges" ,r-iranges)
10242 ("r-s4vectors" ,r-s4vectors)))
10243 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
10244 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
10246 "Dirichlet-multinomial mixture models can be used to describe variability
10247 in microbial metagenomic data. This package is an interface to code
10248 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
10250 (license license:lgpl3)))
10252 (define-public r-ensembldb
10254 (name "r-ensembldb")
10259 (uri (bioconductor-uri "ensembldb" version))
10262 "1vvchc04nshxc768fp31rxb603aj3hmq8xlh5qabcwf2c3z9719g"))))
10263 (build-system r-build-system)
10265 `(("r-annotationdbi" ,r-annotationdbi)
10266 ("r-annotationfilter" ,r-annotationfilter)
10267 ("r-biobase" ,r-biobase)
10268 ("r-biocgenerics" ,r-biocgenerics)
10269 ("r-biostrings" ,r-biostrings)
10272 ("r-genomeinfodb" ,r-genomeinfodb)
10273 ("r-genomicfeatures" ,r-genomicfeatures)
10274 ("r-genomicranges" ,r-genomicranges)
10275 ("r-iranges" ,r-iranges)
10276 ("r-protgenerics" ,r-protgenerics)
10277 ("r-rsamtools" ,r-rsamtools)
10278 ("r-rsqlite" ,r-rsqlite)
10279 ("r-rtracklayer" ,r-rtracklayer)
10280 ("r-s4vectors" ,r-s4vectors)))
10282 `(("r-knitr" ,r-knitr)))
10283 (home-page "https://github.com/jotsetung/ensembldb")
10284 (synopsis "Utilities to create and use Ensembl-based annotation databases")
10286 "The package provides functions to create and use transcript-centric
10287 annotation databases/packages. The annotation for the databases are directly
10288 fetched from Ensembl using their Perl API. The functionality and data is
10289 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
10290 but, in addition to retrieve all gene/transcript models and annotations from
10291 the database, the @code{ensembldb} package also provides a filter framework
10292 allowing to retrieve annotations for specific entries like genes encoded on a
10293 chromosome region or transcript models of lincRNA genes.")
10294 ;; No version specified
10295 (license license:lgpl3+)))
10297 (define-public r-organismdbi
10299 (name "r-organismdbi")
10304 (uri (bioconductor-uri "OrganismDbi" version))
10307 "194h5576inq44qr666snzq0ygnc77rk5ljkn9bn8zs6x6gb3cwaw"))))
10308 (properties `((upstream-name . "OrganismDbi")))
10309 (build-system r-build-system)
10311 `(("r-annotationdbi" ,r-annotationdbi)
10312 ("r-biobase" ,r-biobase)
10313 ("r-biocgenerics" ,r-biocgenerics)
10314 ("r-biocmanager" ,r-biocmanager)
10316 ("r-genomicfeatures" ,r-genomicfeatures)
10317 ("r-genomicranges" ,r-genomicranges)
10318 ("r-graph" ,r-graph)
10319 ("r-iranges" ,r-iranges)
10321 ("r-s4vectors" ,r-s4vectors)))
10322 (home-page "https://bioconductor.org/packages/OrganismDbi")
10323 (synopsis "Software to enable the smooth interfacing of database packages")
10324 (description "The package enables a simple unified interface to several
10325 annotation packages each of which has its own schema by taking advantage of
10326 the fact that each of these packages implements a select methods.")
10327 (license license:artistic2.0)))
10329 (define-public r-biovizbase
10331 (name "r-biovizbase")
10336 (uri (bioconductor-uri "biovizBase" version))
10339 "1vq2mxa2jkljgw75zqjdkyml0ppi5dspvwj4cznfhi31cq8ds0qh"))))
10340 (properties `((upstream-name . "biovizBase")))
10341 (build-system r-build-system)
10343 `(("r-annotationdbi" ,r-annotationdbi)
10344 ("r-annotationfilter" ,r-annotationfilter)
10345 ("r-biocgenerics" ,r-biocgenerics)
10346 ("r-biostrings" ,r-biostrings)
10347 ("r-dichromat" ,r-dichromat)
10348 ("r-ensembldb" ,r-ensembldb)
10349 ("r-genomeinfodb" ,r-genomeinfodb)
10350 ("r-genomicalignments" ,r-genomicalignments)
10351 ("r-genomicfeatures" ,r-genomicfeatures)
10352 ("r-genomicranges" ,r-genomicranges)
10353 ("r-hmisc" ,r-hmisc)
10354 ("r-iranges" ,r-iranges)
10355 ("r-rcolorbrewer" ,r-rcolorbrewer)
10356 ("r-rlang" ,r-rlang)
10357 ("r-rsamtools" ,r-rsamtools)
10358 ("r-s4vectors" ,r-s4vectors)
10359 ("r-scales" ,r-scales)
10360 ("r-summarizedexperiment" ,r-summarizedexperiment)
10361 ("r-variantannotation" ,r-variantannotation)))
10362 (home-page "https://bioconductor.org/packages/biovizBase")
10363 (synopsis "Basic graphic utilities for visualization of genomic data")
10365 "The biovizBase package is designed to provide a set of utilities, color
10366 schemes and conventions for genomic data. It serves as the base for various
10367 high-level packages for biological data visualization. This saves development
10368 effort and encourages consistency.")
10369 (license license:artistic2.0)))
10371 (define-public r-ggbio
10378 (uri (bioconductor-uri "ggbio" version))
10381 "11ggnqjq42fi2hm9xlvrrlr2xhy4kglvl1a0mycp1s4v67lxw5h5"))))
10382 (build-system r-build-system)
10385 (modify-phases %standard-phases
10386 ;; See https://github.com/tengfei/ggbio/issues/117
10387 ;; This fix will be included in the next release.
10388 (add-after 'unpack 'fix-typo
10390 (substitute* "R/GGbio-class.R"
10391 (("fechable") "fetchable"))
10394 `(("r-annotationdbi" ,r-annotationdbi)
10395 ("r-annotationfilter" ,r-annotationfilter)
10396 ("r-biobase" ,r-biobase)
10397 ("r-biocgenerics" ,r-biocgenerics)
10398 ("r-biostrings" ,r-biostrings)
10399 ("r-biovizbase" ,r-biovizbase)
10400 ("r-bsgenome" ,r-bsgenome)
10401 ("r-ensembldb" ,r-ensembldb)
10402 ("r-genomeinfodb" ,r-genomeinfodb)
10403 ("r-genomicalignments" ,r-genomicalignments)
10404 ("r-genomicfeatures" ,r-genomicfeatures)
10405 ("r-genomicranges" ,r-genomicranges)
10406 ("r-ggally" ,r-ggally)
10407 ("r-ggplot2" ,r-ggplot2)
10408 ("r-gridextra" ,r-gridextra)
10409 ("r-gtable" ,r-gtable)
10410 ("r-hmisc" ,r-hmisc)
10411 ("r-iranges" ,r-iranges)
10412 ("r-organismdbi" ,r-organismdbi)
10413 ("r-reshape2" ,r-reshape2)
10414 ("r-rlang" ,r-rlang)
10415 ("r-rsamtools" ,r-rsamtools)
10416 ("r-rtracklayer" ,r-rtracklayer)
10417 ("r-s4vectors" ,r-s4vectors)
10418 ("r-scales" ,r-scales)
10419 ("r-summarizedexperiment" ,r-summarizedexperiment)
10420 ("r-variantannotation" ,r-variantannotation)))
10422 `(("r-knitr" ,r-knitr)))
10423 (home-page "http://www.tengfei.name/ggbio/")
10424 (synopsis "Visualization tools for genomic data")
10426 "The ggbio package extends and specializes the grammar of graphics for
10427 biological data. The graphics are designed to answer common scientific
10428 questions, in particular those often asked of high throughput genomics data.
10429 All core Bioconductor data structures are supported, where appropriate. The
10430 package supports detailed views of particular genomic regions, as well as
10431 genome-wide overviews. Supported overviews include ideograms and grand linear
10432 views. High-level plots include sequence fragment length, edge-linked
10433 interval to data view, mismatch pileup, and several splicing summaries.")
10434 (license license:artistic2.0)))
10436 (define-public r-gqtlbase
10438 (name "r-gqtlbase")
10443 (uri (bioconductor-uri "gQTLBase" version))
10446 "06xvzp4fn3qfa46ggg8kxi267gbyd821vvx4040173xkqxpr0g5j"))))
10447 (properties `((upstream-name . "gQTLBase")))
10448 (build-system r-build-system)
10450 `(("r-batchjobs" ,r-batchjobs)
10451 ("r-bbmisc" ,r-bbmisc)
10452 ("r-biocgenerics" ,r-biocgenerics)
10454 ("r-doparallel" ,r-doparallel)
10456 ("r-ffbase" ,r-ffbase)
10457 ("r-foreach" ,r-foreach)
10458 ("r-genomicfiles" ,r-genomicfiles)
10459 ("r-genomicranges" ,r-genomicranges)
10460 ("r-rtracklayer" ,r-rtracklayer)
10461 ("r-s4vectors" ,r-s4vectors)
10462 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10464 `(("r-knitr" ,r-knitr)))
10465 (home-page "https://bioconductor.org/packages/gQTLBase")
10466 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10468 "The purpose of this package is to simplify the storage and interrogation
10469 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10471 (license license:artistic2.0)))
10473 (define-public r-snpstats
10475 (name "r-snpstats")
10480 (uri (bioconductor-uri "snpStats" version))
10483 "1qv3nqqr30d3n66mawqd9dbl95dl89r4bcjvkc5iassy1yrwr8wq"))))
10484 (properties `((upstream-name . "snpStats")))
10485 (build-system r-build-system)
10486 (inputs `(("zlib" ,zlib)))
10488 `(("r-biocgenerics" ,r-biocgenerics)
10489 ("r-matrix" ,r-matrix)
10490 ("r-survival" ,r-survival)
10491 ("r-zlibbioc" ,r-zlibbioc)))
10492 (home-page "https://bioconductor.org/packages/snpStats")
10493 (synopsis "Methods for SNP association studies")
10495 "This package provides classes and statistical methods for large
10496 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10497 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10498 (license license:gpl3)))
10500 (define-public r-homo-sapiens
10502 (name "r-homo-sapiens")
10506 ;; We cannot use bioconductor-uri here because this tarball is
10507 ;; located under "data/annotation/" instead of "bioc/".
10508 (uri (string-append "https://www.bioconductor.org/packages/"
10509 "release/data/annotation/src/contrib/"
10511 version ".tar.gz"))
10514 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10516 `((upstream-name . "Homo.sapiens")))
10517 (build-system r-build-system)
10519 `(("r-genomicfeatures" ,r-genomicfeatures)
10520 ("r-go-db" ,r-go-db)
10521 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10522 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10523 ("r-organismdbi" ,r-organismdbi)
10524 ("r-annotationdbi" ,r-annotationdbi)))
10525 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10526 (synopsis "Annotation package for the Homo.sapiens object")
10528 "This package contains the Homo.sapiens object to access data from
10529 several related annotation packages.")
10530 (license license:artistic2.0)))
10532 (define-public r-erma
10539 (uri (bioconductor-uri "erma" version))
10542 "1ccfbq0r48sr3h8050w8zv8402h7nx09adr0xdyqlg7kwp9vd2l3"))))
10543 (build-system r-build-system)
10545 `(("r-annotationdbi" ,r-annotationdbi)
10546 ("r-biobase" ,r-biobase)
10547 ("r-biocgenerics" ,r-biocgenerics)
10548 ("r-biocparallel" ,r-biocparallel)
10549 ("r-genomeinfodb" ,r-genomeinfodb)
10550 ("r-genomicfiles" ,r-genomicfiles)
10551 ("r-genomicranges" ,r-genomicranges)
10552 ("r-ggplot2" ,r-ggplot2)
10553 ("r-homo-sapiens" ,r-homo-sapiens)
10554 ("r-iranges" ,r-iranges)
10555 ("r-rtracklayer" ,r-rtracklayer)
10556 ("r-s4vectors" ,r-s4vectors)
10557 ("r-shiny" ,r-shiny)
10558 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10560 `(("r-knitr" ,r-knitr)))
10561 (home-page "https://bioconductor.org/packages/erma")
10562 (synopsis "Epigenomic road map adventures")
10564 "The epigenomics road map describes locations of epigenetic marks in DNA
10565 from a variety of cell types. Of interest are locations of histone
10566 modifications, sites of DNA methylation, and regions of accessible chromatin.
10567 This package presents a selection of elements of the road map including
10568 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10569 by Ernst and Kellis.")
10570 (license license:artistic2.0)))
10572 (define-public r-ldblock
10579 (uri (bioconductor-uri "ldblock" version))
10582 "0plw00n2zfgh029ab41dnydzgv2yxrapjp770147rx9pff4dngrv"))))
10583 (build-system r-build-system)
10585 `(("r-biocgenerics" ,r-biocgenerics)
10586 ("r-ensdb-hsapiens-v75" ,r-ensdb-hsapiens-v75)
10587 ("r-ensembldb" ,r-ensembldb)
10588 ("r-genomeinfodb" ,r-genomeinfodb)
10589 ("r-genomicfiles" ,r-genomicfiles)
10591 ("r-matrix" ,r-matrix)
10592 ("r-rsamtools" ,r-rsamtools)
10593 ("r-snpstats" ,r-snpstats)
10594 ("r-variantannotation" ,r-variantannotation)))
10596 `(("r-knitr" ,r-knitr)))
10597 (home-page "https://bioconductor.org/packages/ldblock")
10598 (synopsis "Data structures for linkage disequilibrium measures in populations")
10600 "This package defines data structures for @dfn{linkage
10601 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10602 handling of existing population-level data for the purpose of flexibly
10603 defining LD blocks.")
10604 (license license:artistic2.0)))
10606 (define-public r-gqtlstats
10608 (name "r-gqtlstats")
10613 (uri (bioconductor-uri "gQTLstats" version))
10616 "1jjqfpjp93nmxjn757j5mzcax96bzcqdd1gr3rsdxg7ap008l2w7"))))
10617 (properties `((upstream-name . "gQTLstats")))
10618 (build-system r-build-system)
10620 `(("r-annotationdbi" ,r-annotationdbi)
10621 ("r-batchjobs" ,r-batchjobs)
10622 ("r-bbmisc" ,r-bbmisc)
10623 ("r-beeswarm" ,r-beeswarm)
10624 ("r-biobase" ,r-biobase)
10625 ("r-biocgenerics" ,r-biocgenerics)
10626 ("r-doparallel" ,r-doparallel)
10627 ("r-dplyr" ,r-dplyr)
10629 ("r-ffbase" ,r-ffbase)
10630 ("r-foreach" ,r-foreach)
10631 ("r-genomeinfodb" ,r-genomeinfodb)
10632 ("r-genomicfeatures" ,r-genomicfeatures)
10633 ("r-genomicfiles" ,r-genomicfiles)
10634 ("r-genomicranges" ,r-genomicranges)
10635 ("r-ggbeeswarm" ,r-ggbeeswarm)
10636 ("r-ggplot2" ,r-ggplot2)
10637 ("r-gqtlbase" ,r-gqtlbase)
10638 ("r-hardyweinberg" ,r-hardyweinberg)
10639 ("r-homo-sapiens" ,r-homo-sapiens)
10640 ("r-iranges" ,r-iranges)
10641 ("r-limma" ,r-limma)
10643 ("r-plotly" ,r-plotly)
10644 ("r-reshape2" ,r-reshape2)
10645 ("r-s4vectors" ,r-s4vectors)
10646 ("r-shiny" ,r-shiny)
10647 ("r-snpstats" ,r-snpstats)
10648 ("r-summarizedexperiment" ,r-summarizedexperiment)
10649 ("r-variantannotation" ,r-variantannotation)))
10651 `(("r-knitr" ,r-knitr)))
10652 (home-page "https://bioconductor.org/packages/gQTLstats")
10653 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10655 "This package provides tools for the computationally efficient analysis
10656 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10657 The software in this package aims to support refinements and functional
10658 interpretation of members of a collection of association statistics on a
10659 family of feature/genome hypotheses.")
10660 (license license:artistic2.0)))
10662 (define-public r-gviz
10669 (uri (bioconductor-uri "Gviz" version))
10672 "0cgkp0ciyy2qykqgh3vzp5mx9b4vsvacjh2jnsj3wldiapzlz08a"))))
10673 (properties `((upstream-name . "Gviz")))
10674 (build-system r-build-system)
10676 `(("r-annotationdbi" ,r-annotationdbi)
10677 ("r-biobase" ,r-biobase)
10678 ("r-biocgenerics" ,r-biocgenerics)
10679 ("r-biomart" ,r-biomart)
10680 ("r-biostrings" ,r-biostrings)
10681 ("r-biovizbase" ,r-biovizbase)
10682 ("r-bsgenome" ,r-bsgenome)
10683 ("r-digest" ,r-digest)
10684 ("r-ensembldb" ,r-ensembldb)
10685 ("r-genomeinfodb" ,r-genomeinfodb)
10686 ("r-genomicalignments" ,r-genomicalignments)
10687 ("r-genomicfeatures" ,r-genomicfeatures)
10688 ("r-genomicranges" ,r-genomicranges)
10689 ("r-iranges" ,r-iranges)
10690 ("r-lattice" ,r-lattice)
10691 ("r-latticeextra" ,r-latticeextra)
10692 ("r-matrixstats" ,r-matrixstats)
10693 ("r-rcolorbrewer" ,r-rcolorbrewer)
10694 ("r-rsamtools" ,r-rsamtools)
10695 ("r-rtracklayer" ,r-rtracklayer)
10696 ("r-s4vectors" ,r-s4vectors)
10697 ("r-xvector" ,r-xvector)))
10699 `(("r-knitr" ,r-knitr)))
10700 (home-page "https://bioconductor.org/packages/Gviz")
10701 (synopsis "Plotting data and annotation information along genomic coordinates")
10703 "Genomic data analyses requires integrated visualization of known genomic
10704 information and new experimental data. Gviz uses the biomaRt and the
10705 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10706 and translates this to e.g. gene/transcript structures in viewports of the
10707 grid graphics package. This results in genomic information plotted together
10709 (license license:artistic2.0)))
10711 (define-public r-gwascat
10718 (uri (bioconductor-uri "gwascat" version))
10721 "1cq5cmdrf0a0arr841yvkh6d8drc15p7mif1afr215l1s3y2dwd4"))))
10722 (build-system r-build-system)
10724 `(("r-annotationdbi" ,r-annotationdbi)
10725 ("r-biocgenerics" ,r-biocgenerics)
10726 ("r-biostrings" ,r-biostrings)
10727 ("r-genomeinfodb" ,r-genomeinfodb)
10728 ("r-genomicfeatures" ,r-genomicfeatures)
10729 ("r-genomicranges" ,r-genomicranges)
10730 ("r-ggplot2" ,r-ggplot2)
10731 ("r-iranges" ,r-iranges)
10732 ("r-rsamtools" ,r-rsamtools)
10733 ("r-rtracklayer" ,r-rtracklayer)
10734 ("r-s4vectors" ,r-s4vectors)))
10736 `(("r-knitr" ,r-knitr)))
10737 (home-page "https://bioconductor.org/packages/gwascat")
10738 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10740 "This package provides tools for representing and modeling data in the
10741 EMBL-EBI GWAS catalog.")
10742 (license license:artistic2.0)))
10744 (define-public r-sushi
10750 (uri (bioconductor-uri "Sushi" version))
10753 "17j3d5qjq5nbv99by5mq8rwr0jgh2jyyfn2nwxmwgzlmk3lgi1rb"))))
10754 (properties `((upstream-name . "Sushi")))
10755 (build-system r-build-system)
10757 `(("r-biomart" ,r-biomart)
10759 (home-page "https://bioconductor.org/packages/Sushi")
10760 (synopsis "Tools for visualizing genomics data")
10762 "This package provides flexible, quantitative, and integrative genomic
10763 visualizations for publication-quality multi-panel figures.")
10764 (license license:gpl2+)))
10766 (define-public r-fithic
10772 (uri (bioconductor-uri "FitHiC" version))
10775 "1dffkdxm08wq4kjd9j2v2625x3p6vbrk33a2zx94pwpgkghr72yp"))))
10776 (properties `((upstream-name . "FitHiC")))
10777 (build-system r-build-system)
10779 `(("r-data-table" ,r-data-table)
10780 ("r-fdrtool" ,r-fdrtool)
10781 ("r-rcpp" ,r-rcpp)))
10783 `(("r-knitr" ,r-knitr)))
10784 (home-page "https://bioconductor.org/packages/FitHiC")
10785 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10787 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10788 intra-chromosomal contact maps produced by genome-wide genome architecture
10789 assays such as Hi-C.")
10790 (license license:gpl2+)))
10792 (define-public r-hitc
10798 (uri (bioconductor-uri "HiTC" version))
10801 "1jx2pfa7sbdz7xi466lz1h5xv126g56z73n0a5l2wrq28k47qaxy"))))
10802 (properties `((upstream-name . "HiTC")))
10803 (build-system r-build-system)
10805 `(("r-biostrings" ,r-biostrings)
10806 ("r-genomeinfodb" ,r-genomeinfodb)
10807 ("r-genomicranges" ,r-genomicranges)
10808 ("r-iranges" ,r-iranges)
10809 ("r-matrix" ,r-matrix)
10810 ("r-rcolorbrewer" ,r-rcolorbrewer)
10811 ("r-rtracklayer" ,r-rtracklayer)))
10812 (home-page "https://bioconductor.org/packages/HiTC")
10813 (synopsis "High throughput chromosome conformation capture analysis")
10815 "The HiTC package was developed to explore high-throughput \"C\" data
10816 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10817 quality controls, normalization, visualization, and further analysis are also
10819 (license license:artistic2.0)))
10821 (define-public r-hdf5array
10823 (name "r-hdf5array")
10828 (uri (bioconductor-uri "HDF5Array" version))
10831 "01767v90nl0499jcicpxngbbs0af5p9c5aasi5va01w3v5bnqddn"))))
10832 (properties `((upstream-name . "HDF5Array")))
10833 (build-system r-build-system)
10837 `(("r-biocgenerics" ,r-biocgenerics)
10838 ("r-delayedarray" ,r-delayedarray)
10839 ("r-iranges" ,r-iranges)
10840 ("r-matrix" ,r-matrix)
10841 ("r-rhdf5" ,r-rhdf5)
10842 ("r-rhdf5lib" ,r-rhdf5lib)
10843 ("r-s4vectors" ,r-s4vectors)))
10844 (home-page "https://bioconductor.org/packages/HDF5Array")
10845 (synopsis "HDF5 back end for DelayedArray objects")
10846 (description "This package provides an array-like container for convenient
10847 access and manipulation of HDF5 datasets. It supports delayed operations and
10848 block processing.")
10849 (license license:artistic2.0)))
10851 (define-public r-rhdf5lib
10853 (name "r-rhdf5lib")
10858 (uri (bioconductor-uri "Rhdf5lib" version))
10861 "0f45sqrvzj6x4mckalyp8366hm8v0rrmzklx3xd4gs6l2wallcn9"))
10862 (modules '((guix build utils)))
10865 ;; Delete bundled binaries
10866 (delete-file-recursively "src/wininclude/")
10867 (delete-file-recursively "src/winlib-4.9.3/")
10868 (delete-file-recursively "src/winlib-8.3.0/")
10869 (delete-file "src/hdf5small_cxx_hl_1.10.6.tar.gz")
10871 (properties `((upstream-name . "Rhdf5lib")))
10872 (build-system r-build-system)
10875 (modify-phases %standard-phases
10876 (add-after 'unpack 'do-not-use-bundled-hdf5
10877 (lambda* (#:key inputs #:allow-other-keys)
10878 (for-each delete-file '("configure" "configure.ac"))
10879 ;; Do not make other packages link with the proprietary libsz.
10880 (substitute* "R/zzz.R"
10881 ((" \"%s/libsz.a\"") ""))
10882 (with-directory-excursion "src"
10883 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10884 (rename-file (string-append "hdf5-" ,(package-version hdf5-1.10))
10886 ;; Remove timestamp and host system information to make
10887 ;; the build reproducible.
10888 (substitute* "hdf5/src/libhdf5.settings.in"
10889 (("Configured on: @CONFIG_DATE@")
10890 "Configured on: Guix")
10891 (("Uname information:.*")
10892 "Uname information: Linux\n")
10893 ;; Remove unnecessary store reference.
10895 "C Compiler: GCC\n"))
10896 (rename-file "Makevars.in" "Makevars")
10897 (substitute* "Makevars"
10898 (("@ZLIB_LIB@") "-lz")
10899 (("@ZLIB_INCLUDE@") "")
10900 (("HDF5_CXX_LIB=.*")
10901 (string-append "HDF5_CXX_LIB="
10902 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10904 (string-append "HDF5_LIB="
10905 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10906 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10907 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10908 (("HDF5_HL_INCLUDE=.*") "HDF5_HL_INCLUDE=./hdf5/hl/src\n")
10909 (("HDF5_HL_CXX_INCLUDE=.*") "HDF5_HL_CXX_INCLUDE=./hdf5/hl/c++/src\n")
10910 (("HDF5_HL_LIB=.*")
10911 (string-append "HDF5_HL_LIB="
10912 (assoc-ref inputs "hdf5") "/lib/libhdf5_hl.a\n"))
10913 (("HDF5_HL_CXX_LIB=.*")
10914 (string-append "HDF5_HL_CXX_LIB="
10915 (assoc-ref inputs "hdf5") "/lib/libhdf5_hl_cpp.a\n"))
10916 ;; szip is non-free software
10917 (("cp \"\\$\\{SZIP_LIB\\}.*") "")
10918 (("PKG_LIBS =.*") "PKG_LIBS = -lz -lhdf5\n")))
10923 `(("hdf5" ,hdf5-1.10)))
10925 `(("hdf5-source" ,(package-source hdf5-1.10))
10926 ("r-knitr" ,r-knitr)))
10927 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10928 (synopsis "HDF5 library as an R package")
10929 (description "This package provides C and C++ HDF5 libraries for use in R
10931 (license license:artistic2.0)))
10933 (define-public r-beachmat
10935 (name "r-beachmat")
10940 (uri (bioconductor-uri "beachmat" version))
10943 "1vl6jbf9ia78cm4ikdb8vz04jv4b46zhvg5i006c63a9pzw7zhxi"))))
10944 (build-system r-build-system)
10946 `(("r-biocgenerics" ,r-biocgenerics)
10947 ("r-delayedarray" ,r-delayedarray)
10948 ("r-matrix" ,r-matrix)))
10950 `(("r-knitr" ,r-knitr)))
10951 (home-page "https://bioconductor.org/packages/beachmat")
10952 (synopsis "Compiling Bioconductor to handle each matrix type")
10953 (description "This package provides a consistent C++ class interface for a
10954 variety of commonly used matrix types, including sparse and HDF5-backed
10956 (license license:gpl3)))
10958 (define-public r-singlecellexperiment
10960 (name "r-singlecellexperiment")
10965 (uri (bioconductor-uri "SingleCellExperiment" version))
10968 "092wvk11n7pa234vlwhxm3gdi4k3sbnz1splhxalbdhz3jf02zfp"))))
10970 `((upstream-name . "SingleCellExperiment")))
10971 (build-system r-build-system)
10973 `(("r-biocgenerics" ,r-biocgenerics)
10974 ("r-s4vectors" ,r-s4vectors)
10975 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10977 `(("r-knitr" ,r-knitr)))
10978 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10979 (synopsis "S4 classes for single cell data")
10980 (description "This package defines an S4 class for storing data from
10981 single-cell experiments. This includes specialized methods to store and
10982 retrieve spike-in information, dimensionality reduction coordinates and size
10983 factors for each cell, along with the usual metadata for genes and
10985 (license license:gpl3)))
10987 (define-public r-scater
10993 (uri (bioconductor-uri "scater" version))
10996 "1pa5wvgjb30rw1vsjwbnn07ss3sc5n8ck5d7khdby4r2s9177s33"))))
10997 (build-system r-build-system)
10999 `(("r-beachmat" ,r-beachmat)
11000 ("r-biocgenerics" ,r-biocgenerics)
11001 ("r-biocneighbors" ,r-biocneighbors)
11002 ("r-biocparallel" ,r-biocparallel)
11003 ("r-biocsingular" ,r-biocsingular)
11004 ("r-delayedarray" ,r-delayedarray)
11005 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
11006 ("r-ggbeeswarm" ,r-ggbeeswarm)
11007 ("r-ggplot2" ,r-ggplot2)
11008 ("r-matrix" ,r-matrix)
11010 ("r-rlang" ,r-rlang)
11011 ("r-s4vectors" ,r-s4vectors)
11012 ("r-singlecellexperiment" ,r-singlecellexperiment)
11013 ("r-summarizedexperiment" ,r-summarizedexperiment)
11014 ("r-viridis" ,r-viridis)))
11016 `(("r-knitr" ,r-knitr)))
11017 (home-page "https://github.com/davismcc/scater")
11018 (synopsis "Single-cell analysis toolkit for gene expression data in R")
11019 (description "This package provides a collection of tools for doing
11020 various analyses of single-cell RNA-seq gene expression data, with a focus on
11022 (license license:gpl2+)))
11024 (define-public r-scran
11031 (uri (bioconductor-uri "scran" version))
11034 "1gm4ys4aq8h1pn45k1rxk384wjyf55izivw8kgxbrflj6j4xvvsv"))))
11035 (build-system r-build-system)
11037 `(("r-beachmat" ,r-beachmat)
11039 ("r-biocgenerics" ,r-biocgenerics)
11040 ("r-biocneighbors" ,r-biocneighbors)
11041 ("r-biocparallel" ,r-biocparallel)
11042 ("r-biocsingular" ,r-biocsingular)
11043 ("r-delayedarray" ,r-delayedarray)
11044 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
11045 ("r-dqrng" ,r-dqrng)
11046 ("r-edger" ,r-edger)
11047 ("r-igraph" ,r-igraph)
11048 ("r-iranges" ,r-iranges)
11049 ("r-limma" ,r-limma)
11050 ("r-matrix" ,r-matrix)
11052 ("r-s4vectors" ,r-s4vectors)
11053 ("r-scater" ,r-scater)
11054 ("r-singlecellexperiment" ,r-singlecellexperiment)
11055 ("r-statmod" ,r-statmod)
11056 ("r-summarizedexperiment" ,r-summarizedexperiment)))
11058 `(("r-knitr" ,r-knitr)))
11059 (home-page "https://bioconductor.org/packages/scran")
11060 (synopsis "Methods for single-cell RNA-Seq data analysis")
11061 (description "This package implements a variety of low-level analyses of
11062 single-cell RNA-seq data. Methods are provided for normalization of
11063 cell-specific biases, assignment of cell cycle phase, and detection of highly
11064 variable and significantly correlated genes.")
11065 (license license:gpl3)))
11067 (define-public r-delayedmatrixstats
11069 (name "r-delayedmatrixstats")
11074 (uri (bioconductor-uri "DelayedMatrixStats" version))
11077 "046sam0rz42ph0m7jz7v3bck7d3h2mp45gzywh5dvc1qkjq6fdxx"))))
11079 `((upstream-name . "DelayedMatrixStats")))
11080 (build-system r-build-system)
11082 `(("r-biocparallel" ,r-biocparallel)
11083 ("r-delayedarray" ,r-delayedarray)
11084 ("r-hdf5array" ,r-hdf5array)
11085 ("r-iranges" ,r-iranges)
11086 ("r-matrix" ,r-matrix)
11087 ("r-matrixstats" ,r-matrixstats)
11088 ("r-s4vectors" ,r-s4vectors)))
11090 `(("r-knitr" ,r-knitr)))
11091 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
11092 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
11094 "This package provides a port of the @code{matrixStats} API for use with
11095 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
11096 contains high-performing functions operating on rows and columns of
11097 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
11098 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
11099 are optimized per data type and for subsetted calculations such that both
11100 memory usage and processing time is minimized.")
11101 (license license:expat)))
11103 (define-public r-phangorn
11105 (name "r-phangorn")
11110 (uri (cran-uri "phangorn" version))
11113 "0ihkaykqjmf80d8wrk3saphxvnv58zma6pd13633bd3cwanc33f5"))))
11114 (build-system r-build-system)
11117 ("r-fastmatch" ,r-fastmatch)
11118 ("r-igraph" ,r-igraph)
11119 ("r-magrittr" ,r-magrittr)
11120 ("r-matrix" ,r-matrix)
11121 ("r-quadprog" ,r-quadprog)
11122 ("r-rcpp" ,r-rcpp)))
11123 (home-page "https://github.com/KlausVigo/phangorn")
11124 (synopsis "Phylogenetic analysis in R")
11126 "Phangorn is a package for phylogenetic analysis in R. It supports
11127 estimation of phylogenetic trees and networks using Maximum Likelihood,
11128 Maximum Parsimony, distance methods and Hadamard conjugation.")
11129 (license license:gpl2+)))
11131 (define-public r-dropbead
11132 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
11135 (name "r-dropbead")
11136 (version (string-append "0-" revision "." (string-take commit 7)))
11140 (uri (git-reference
11141 (url "https://github.com/rajewsky-lab/dropbead")
11143 (file-name (git-file-name name version))
11146 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
11147 (build-system r-build-system)
11149 `(("r-ggplot2" ,r-ggplot2)
11150 ("r-rcolorbrewer" ,r-rcolorbrewer)
11151 ("r-gridextra" ,r-gridextra)
11152 ("r-gplots" ,r-gplots)
11153 ("r-plyr" ,r-plyr)))
11154 (home-page "https://github.com/rajewsky-lab/dropbead")
11155 (synopsis "Basic exploration and analysis of Drop-seq data")
11156 (description "This package offers a quick and straight-forward way to
11157 explore and perform basic analysis of single cell sequencing data coming from
11158 droplet sequencing. It has been particularly tailored for Drop-seq.")
11159 (license license:gpl3))))
11161 (define htslib-for-sambamba
11162 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
11165 (name "htslib-for-sambamba")
11166 (version (string-append "1.3.1-1." (string-take commit 9)))
11170 (uri (git-reference
11171 (url "https://github.com/lomereiter/htslib")
11173 (file-name (string-append "htslib-" version "-checkout"))
11176 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
11178 `(("autoconf" ,autoconf)
11179 ("automake" ,automake)
11180 ,@(package-native-inputs htslib))))))
11182 (define-public sambamba
11189 (uri (git-reference
11190 (url "https://github.com/lomereiter/sambamba")
11191 (commit (string-append "v" version))))
11192 (file-name (string-append name "-" version "-checkout"))
11195 "111h05b60pj8dxbidiamy4imc92x2962b3lmb7wgysl6lx064qis"))))
11196 (build-system gnu-build-system)
11198 `(#:tests? #f ; there is no test target
11199 #:parallel-build? #f ; not supported
11201 (modify-phases %standard-phases
11202 (delete 'configure)
11203 (add-after 'unpack 'fix-ldc-version
11205 (substitute* "gen_ldc_version_info.py"
11206 (("/usr/bin/env.*") (which "python3")))
11207 (substitute* "Makefile"
11208 ;; We use ldc2 instead of ldmd2 to compile sambamba.
11209 (("\\$\\(shell which ldmd2\\)") (which "ldc2")))
11211 (add-after 'unpack 'place-biod-and-undead
11212 (lambda* (#:key inputs #:allow-other-keys)
11213 (copy-recursively (assoc-ref inputs "biod") "BioD")
11215 (add-after 'unpack 'unbundle-prerequisites
11217 (substitute* "Makefile"
11218 (("htslib/libhts.a lz4/lib/liblz4.a")
11220 ((" lz4-static htslib-static") ""))
11223 (lambda* (#:key outputs #:allow-other-keys)
11224 (let* ((out (assoc-ref outputs "out"))
11225 (bin (string-append out "/bin")))
11227 (copy-file (string-append "bin/sambamba-" ,version)
11228 (string-append bin "/sambamba"))
11235 ,(let ((commit "7969eb0a847b05874e83ffddead26e193ece8101"))
11238 (uri (git-reference
11239 (url "https://github.com/biod/BioD")
11241 (file-name (string-append "biod-"
11242 (string-take commit 9)
11246 "0mjxsmbmv0jxl3pq21p8j5r829d648if8q58ka50b2956lc6qkpm")))))))
11249 ("htslib" ,htslib-for-sambamba)))
11250 (home-page "https://lomereiter.github.io/sambamba/")
11251 (synopsis "Tools for working with SAM/BAM data")
11252 (description "Sambamba is a high performance modern robust and
11253 fast tool (and library), written in the D programming language, for
11254 working with SAM and BAM files. Current parallelised functionality is
11255 an important subset of samtools functionality, including view, index,
11256 sort, markdup, and depth.")
11257 (license license:gpl2+)))
11259 (define-public ritornello
11261 (name "ritornello")
11265 (uri (git-reference
11266 (url "https://github.com/KlugerLab/Ritornello")
11267 (commit (string-append "v" version))))
11268 (file-name (git-file-name name version))
11271 "1xahvq215qld7x1w8vpa5zbrsj6p9crb9shqa2x89sb0aaxa02jk"))))
11272 (build-system gnu-build-system)
11274 `(#:tests? #f ; there are no tests
11276 (modify-phases %standard-phases
11277 (add-after 'unpack 'patch-samtools-references
11278 (lambda* (#:key inputs #:allow-other-keys)
11279 (substitute* '("src/SamStream.h"
11281 (("<sam.h>") "<samtools/sam.h>"))
11283 (delete 'configure)
11285 (lambda* (#:key inputs outputs #:allow-other-keys)
11286 (let* ((out (assoc-ref outputs "out"))
11287 (bin (string-append out "/bin/")))
11289 (install-file "bin/Ritornello" bin)
11292 `(("samtools" ,samtools-0.1)
11296 (home-page "https://github.com/KlugerLab/Ritornello")
11297 (synopsis "Control-free peak caller for ChIP-seq data")
11298 (description "Ritornello is a ChIP-seq peak calling algorithm based on
11299 signal processing that can accurately call binding events without the need to
11300 do a pair total DNA input or IgG control sample. It has been tested for use
11301 with narrow binding events such as transcription factor ChIP-seq.")
11302 (license license:gpl3+)))
11304 (define-public trim-galore
11306 (name "trim-galore")
11311 (uri (git-reference
11312 (url "https://github.com/FelixKrueger/TrimGalore")
11314 (file-name (git-file-name name version))
11317 "1y31wbxwkm9xqzr5zv1pk5q418whnmlmgmfyxxpnl12h83m2i9iv"))))
11318 (build-system gnu-build-system)
11320 `(#:tests? #f ; no tests
11322 (modify-phases %standard-phases
11323 (replace 'configure
11325 ;; Trim Galore tries to figure out what version of Python
11326 ;; cutadapt is using by looking at the shebang. Of course that
11327 ;; doesn't work, because cutadapt is wrapped in a shell script.
11328 (substitute* "trim_galore"
11329 (("my \\$python_return.*")
11330 "my $python_return = \"Python 3.999\";\n"))
11333 (add-after 'unpack 'hardcode-tool-references
11334 (lambda* (#:key inputs #:allow-other-keys)
11335 (substitute* "trim_galore"
11336 (("\\$path_to_cutadapt = 'cutadapt'")
11337 (string-append "$path_to_cutadapt = '"
11338 (assoc-ref inputs "cutadapt")
11340 (("\\$compression_path = \"gzip\"")
11341 (string-append "$compression_path = \""
11342 (assoc-ref inputs "gzip")
11345 (string-append "\""
11346 (assoc-ref inputs "gzip")
11349 (string-append "\""
11350 (assoc-ref inputs "pigz")
11354 (lambda* (#:key outputs #:allow-other-keys)
11355 (let ((bin (string-append (assoc-ref outputs "out")
11358 (install-file "trim_galore" bin)
11364 ("cutadapt" ,cutadapt)))
11366 `(("unzip" ,unzip)))
11367 (home-page "https://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
11368 (synopsis "Wrapper around Cutadapt and FastQC")
11369 (description "Trim Galore! is a wrapper script to automate quality and
11370 adapter trimming as well as quality control, with some added functionality to
11371 remove biased methylation positions for RRBS sequence files.")
11372 (license license:gpl3+)))
11374 (define-public gess
11380 (uri (string-append "http://compbio.uthscsa.edu/"
11382 "gess-" version ".src.tar.gz"))
11385 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
11386 (build-system gnu-build-system)
11388 `(#:tests? #f ; no tests
11390 (modify-phases %standard-phases
11391 (delete 'configure)
11394 (lambda* (#:key inputs outputs #:allow-other-keys)
11395 (let* ((python (assoc-ref inputs "python"))
11396 (out (assoc-ref outputs "out"))
11397 (bin (string-append out "/bin/"))
11398 (target (string-append
11400 ,(version-major+minor
11401 (package-version python))
11402 "/site-packages/gess/")))
11404 (copy-recursively "." target)
11405 ;; Make GESS.py executable
11406 (chmod (string-append target "GESS.py") #o555)
11407 ;; Add Python shebang to the top and make Matplotlib
11409 (substitute* (string-append target "GESS.py")
11410 (("\"\"\"Description:" line)
11411 (string-append "#!" (which "python") "
11413 matplotlib.use('Agg')
11415 ;; Make sure GESS has all modules in its path
11416 (wrap-script (string-append target "GESS.py")
11417 `("PYTHONPATH" ":" = (,target ,(getenv "PYTHONPATH"))))
11419 (symlink (string-append target "GESS.py")
11420 (string-append bin "GESS.py"))
11423 `(("python" ,python-2)
11424 ("python2-pysam" ,python2-pysam)
11425 ("python2-scipy" ,python2-scipy)
11426 ("python2-numpy" ,python2-numpy)
11427 ("python2-networkx" ,python2-networkx)
11428 ("python2-biopython" ,python2-biopython)
11429 ("guile" ,guile-3.0))) ; for the script wrapper
11430 (home-page "https://compbio.uthscsa.edu/GESS_Web/")
11431 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11433 "GESS is an implementation of a novel computational method to detect de
11434 novo exon-skipping events directly from raw RNA-seq data without the prior
11435 knowledge of gene annotation information. GESS stands for the graph-based
11436 exon-skipping scanner detection scheme.")
11437 (license license:bsd-3)))
11439 (define-public phylip
11446 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11447 "download/phylip-" version ".tar.gz"))
11450 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11451 (build-system gnu-build-system)
11453 `(#:tests? #f ; no check target
11454 #:make-flags (list "-f" "Makefile.unx" "install")
11455 #:parallel-build? #f ; not supported
11457 (modify-phases %standard-phases
11458 (add-after 'unpack 'enter-dir
11459 (lambda _ (chdir "src") #t))
11460 (delete 'configure)
11462 (lambda* (#:key inputs outputs #:allow-other-keys)
11463 (let ((target (string-append (assoc-ref outputs "out")
11466 (for-each (lambda (file)
11467 (install-file file target))
11468 (find-files "../exe" ".*")))
11470 (home-page "http://evolution.genetics.washington.edu/phylip/")
11471 (synopsis "Tools for inferring phylogenies")
11472 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11473 programs for inferring phylogenies (evolutionary trees).")
11474 (license license:bsd-2)))
11483 (uri (string-append "https://integrativemodeling.org/"
11484 version "/download/imp-" version ".tar.gz"))
11487 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
11488 (build-system cmake-build-system)
11490 `(;; FIXME: Some tests fail because they produce warnings, others fail
11491 ;; because the PYTHONPATH does not include the modeller's directory.
11499 ("python" ,python-2)))
11501 `(("python2-numpy" ,python2-numpy)
11502 ("python2-scipy" ,python2-scipy)
11503 ("python2-pandas" ,python2-pandas)
11504 ("python2-scikit-learn" ,python2-scikit-learn)
11505 ("python2-networkx" ,python2-networkx)))
11506 (home-page "https://integrativemodeling.org")
11507 (synopsis "Integrative modeling platform")
11508 (description "IMP's broad goal is to contribute to a comprehensive
11509 structural characterization of biomolecules ranging in size and complexity
11510 from small peptides to large macromolecular assemblies, by integrating data
11511 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11512 Python toolbox for solving complex modeling problems, and a number of
11513 applications for tackling some common problems in a user-friendly way.")
11514 ;; IMP is largely available under the GNU Lesser GPL; see the file
11515 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11516 ;; available under the GNU GPL (see the file COPYING.GPL).
11517 (license (list license:lgpl2.1+
11520 (define-public tadbit
11526 (uri (git-reference
11527 (url "https://github.com/3DGenomes/TADbit")
11528 (commit (string-append "v" version))))
11529 (file-name (git-file-name name version))
11532 "07g3aj648prmsvxp9caz5yl41k0y0647vxh0f5p3w8376mfiljd0"))))
11533 (build-system python-build-system)
11535 `(;; Tests are included and must be run after installation, but
11536 ;; they are incomplete and thus cannot be run.
11540 (modify-phases %standard-phases
11541 (add-after 'unpack 'fix-problems-with-setup.py
11542 (lambda* (#:key outputs #:allow-other-keys)
11543 ;; setup.py opens these files for writing
11544 (chmod "_pytadbit/_version.py" #o664)
11545 (chmod "README.rst" #o664)
11547 ;; Don't attempt to install the bash completions to
11548 ;; the home directory.
11549 (rename-file "extras/.bash_completion"
11551 (substitute* "setup.py"
11552 (("\\(path.expanduser\\('~'\\)")
11553 (string-append "(\""
11554 (assoc-ref outputs "out")
11555 "/etc/bash_completion.d\""))
11556 (("extras/\\.bash_completion")
11560 ;; TODO: add Chimera for visualization
11563 ("python2-scipy" ,python2-scipy)
11564 ("python2-numpy" ,python2-numpy)
11565 ("python2-matplotlib" ,python2-matplotlib)
11566 ("python2-pysam" ,python2-pysam)))
11567 (home-page "https://3dgenomes.github.io/TADbit/")
11568 (synopsis "Analyze, model, and explore 3C-based data")
11570 "TADbit is a complete Python library to deal with all steps to analyze,
11571 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11572 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11573 correct interaction matrices, identify and compare the so-called
11574 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11575 interaction matrices, and finally, extract structural properties from the
11576 models. TADbit is complemented by TADkit for visualizing 3D models.")
11577 (license license:gpl3+)))
11579 (define-public kentutils
11582 ;; 302.1.0 is out, but the only difference is the inclusion of
11583 ;; pre-built binaries.
11584 (version "302.0.0")
11588 (uri (git-reference
11589 (url "https://github.com/ENCODE-DCC/kentUtils")
11590 (commit (string-append "v" version))))
11591 (file-name (git-file-name name version))
11594 "0n1wbyjpzii2b9qhyp9r1q76j623cggpg3y8fmw78ld3z4y7ivha"))
11595 (modules '((guix build utils)
11600 ;; Only the contents of the specified directories are free
11601 ;; for all uses, so we remove the rest. "hg/autoSql" and
11602 ;; "hg/autoXml" are nominally free, but they depend on a
11603 ;; library that is built from the sources in "hg/lib",
11604 ;; which is nonfree.
11605 (let ((free (list "." ".."
11606 "utils" "lib" "inc" "tagStorm"
11607 "parasol" "htslib"))
11608 (directory? (lambda (file)
11609 (eq? 'directory (stat:type (stat file))))))
11610 (for-each (lambda (file)
11611 (and (directory? file)
11612 (delete-file-recursively file)))
11613 (map (cut string-append "src/" <>)
11616 (not (member file free)))))))
11617 ;; Only make the utils target, not the userApps target,
11618 ;; because that requires libraries we won't build.
11619 (substitute* "Makefile"
11620 ((" userApps") " utils"))
11621 ;; Only build libraries that are free.
11622 (substitute* "src/makefile"
11623 (("DIRS =.*") "DIRS =\n")
11624 (("cd jkOwnLib.*") "")
11627 (substitute* "src/utils/makefile"
11628 ;; These tools depend on "jkhgap.a", which is part of the
11629 ;; nonfree "src/hg/lib" directory.
11630 (("raSqlQuery") "")
11631 (("pslLiftSubrangeBlat") "")
11633 ;; Do not build UCSC tools, which may require nonfree
11635 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11637 (build-system gnu-build-system)
11639 `( ;; There is no global test target and the test target for
11640 ;; individual tools depends on input files that are not
11644 (modify-phases %standard-phases
11645 (add-after 'unpack 'fix-permissions
11646 (lambda _ (make-file-writable "src/inc/localEnvironment.mk") #t))
11647 (add-after 'unpack 'fix-paths
11649 (substitute* "Makefile"
11650 (("/bin/echo") (which "echo")))
11652 (add-after 'unpack 'prepare-samtabix
11653 (lambda* (#:key inputs #:allow-other-keys)
11654 (copy-recursively (assoc-ref inputs "samtabix")
11657 (delete 'configure)
11659 (lambda* (#:key outputs #:allow-other-keys)
11660 (let ((bin (string-append (assoc-ref outputs "out")
11662 (copy-recursively "bin" bin))
11668 (uri (git-reference
11669 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11670 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11673 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11679 ("mariadb" ,mariadb "lib")
11680 ("mariadb-dev" ,mariadb "dev")
11681 ("openssl" ,openssl-1.0)))
11682 (home-page "https://genome.cse.ucsc.edu/index.html")
11683 (synopsis "Assorted bioinformatics utilities")
11684 (description "This package provides the kentUtils, a selection of
11685 bioinformatics utilities used in combination with the UCSC genome
11687 ;; Only a subset of the sources are released under a non-copyleft
11688 ;; free software license. All other sources are removed in a
11689 ;; snippet. See this bug report for an explanation of how the
11690 ;; license statements apply:
11691 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11692 (license (license:non-copyleft
11693 "http://genome.ucsc.edu/license/"
11694 "The contents of this package are free for all uses."))))
11696 (define-public f-seq
11697 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11701 (version (string-append "1.1-" revision "." (string-take commit 7)))
11704 (uri (git-reference
11705 (url "https://github.com/aboyle/F-seq")
11707 (file-name (string-append name "-" version))
11710 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11711 (modules '((guix build utils)))
11712 ;; Remove bundled Java library archives.
11715 (for-each delete-file (find-files "lib" ".*"))
11717 (build-system ant-build-system)
11719 `(#:tests? #f ; no tests included
11721 (modify-phases %standard-phases
11723 (lambda* (#:key inputs outputs #:allow-other-keys)
11724 (let* ((target (assoc-ref outputs "out"))
11725 (bin (string-append target "/bin"))
11726 (doc (string-append target "/share/doc/f-seq"))
11727 (lib (string-append target "/lib")))
11730 (substitute* "bin/linux/fseq"
11731 (("java") (which "java"))
11732 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11733 (string-append (assoc-ref inputs "java-commons-cli")
11734 "/share/java/commons-cli.jar"))
11736 (string-append "REALDIR=" bin "\n")))
11737 (install-file "README.txt" doc)
11738 (install-file "bin/linux/fseq" bin)
11739 (install-file "build~/fseq.jar" lib)
11740 (copy-recursively "lib" lib)
11744 ("java-commons-cli" ,java-commons-cli)))
11745 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11746 (synopsis "Feature density estimator for high-throughput sequence tags")
11748 "F-Seq is a software package that generates a continuous tag sequence
11749 density estimation allowing identification of biologically meaningful sites
11750 such as transcription factor binding sites (ChIP-seq) or regions of open
11751 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11753 (license license:gpl3+))))
11755 (define-public bismark
11762 (uri (git-reference
11763 (url "https://github.com/FelixKrueger/Bismark")
11765 (file-name (string-append name "-" version "-checkout"))
11768 "0xchm3rgilj6vfjnyzfzzymfd7djr64sbrmrvs3njbwi66jqbzw9"))))
11769 (build-system perl-build-system)
11771 `(#:tests? #f ; there are no tests
11772 #:modules ((guix build utils)
11775 (guix build perl-build-system))
11777 (modify-phases %standard-phases
11778 ;; The bundled plotly.js is minified.
11779 (add-after 'unpack 'replace-plotly.js
11780 (lambda* (#:key inputs #:allow-other-keys)
11781 (let* ((file (assoc-ref inputs "plotly.js"))
11782 (installed "plotly/plotly.js"))
11783 (let ((minified (open-pipe* OPEN_READ "uglify-js" file)))
11784 (call-with-output-file installed
11785 (cut dump-port minified <>))))
11787 (delete 'configure)
11790 (lambda* (#:key inputs outputs #:allow-other-keys)
11791 (let* ((out (assoc-ref outputs "out"))
11792 (bin (string-append out "/bin"))
11793 (share (string-append out "/share/bismark"))
11794 (docdir (string-append out "/share/doc/bismark"))
11795 (docs '("Docs/Bismark_User_Guide.html"))
11796 (scripts '("bismark"
11797 "bismark_genome_preparation"
11798 "bismark_methylation_extractor"
11801 "coverage2cytosine"
11802 "deduplicate_bismark"
11803 "filter_non_conversion"
11806 "NOMe_filtering")))
11807 (substitute* "bismark2report"
11808 (("\\$RealBin/plotly")
11809 (string-append share "/plotly")))
11813 (for-each (lambda (file) (install-file file bin))
11815 (for-each (lambda (file) (install-file file docdir))
11817 (copy-recursively "Docs/Images" (string-append docdir "/Images"))
11818 (copy-recursively "plotly"
11819 (string-append share "/plotly"))
11821 ;; Fix references to gunzip
11822 (substitute* (map (lambda (file)
11823 (string-append bin "/" file))
11826 (string-append "\"" (assoc-ref inputs "gzip")
11827 "/bin/gunzip -c")))
11831 ("perl-carp" ,perl-carp)
11832 ("perl-getopt-long" ,perl-getopt-long)))
11837 (uri (string-append "https://raw.githubusercontent.com/plotly/plotly.js/"
11838 "v1.39.4/dist/plotly.js"))
11840 (base32 "138mwsr4nf5qif4mrxx286mpnagxd1xwl6k8aidrjgknaqg88zyr"))))
11841 ("uglify-js" ,uglify-js)))
11842 (home-page "https://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11843 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11844 (description "Bismark is a program to map bisulfite treated sequencing
11845 reads to a genome of interest and perform methylation calls in a single step.
11846 The output can be easily imported into a genome viewer, such as SeqMonk, and
11847 enables a researcher to analyse the methylation levels of their samples
11848 straight away. Its main features are:
11851 @item Bisulfite mapping and methylation calling in one single step
11852 @item Supports single-end and paired-end read alignments
11853 @item Supports ungapped and gapped alignments
11854 @item Alignment seed length, number of mismatches etc are adjustable
11855 @item Output discriminates between cytosine methylation in CpG, CHG
11858 (license license:gpl3+)))
11860 (define-public paml
11866 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11867 "paml" version ".tgz"))
11870 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11871 (modules '((guix build utils)))
11872 ;; Remove Windows binaries
11875 (for-each delete-file (find-files "." "\\.exe$"))
11876 ;; Some files in the original tarball have restrictive
11877 ;; permissions, which makes repackaging fail
11878 (for-each (lambda (file) (chmod file #o644)) (find-files "."))
11880 (build-system gnu-build-system)
11882 `(#:tests? #f ; there are no tests
11883 #:make-flags '("CC=gcc")
11885 (modify-phases %standard-phases
11886 (replace 'configure
11888 (substitute* "src/BFdriver.c"
11889 (("/bin/bash") (which "bash")))
11893 (lambda* (#:key outputs #:allow-other-keys)
11894 (let ((tools '("baseml" "basemlg" "codeml"
11895 "pamp" "evolver" "yn00" "chi2"))
11896 (bin (string-append (assoc-ref outputs "out") "/bin"))
11897 (docdir (string-append (assoc-ref outputs "out")
11898 "/share/doc/paml")))
11900 (for-each (lambda (file) (install-file file bin)) tools)
11901 (copy-recursively "../doc" docdir)
11903 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11904 (synopsis "Phylogentic analysis by maximum likelihood")
11905 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11906 contains a few programs for model fitting and phylogenetic tree reconstruction
11907 using nucleotide or amino-acid sequence data.")
11909 (license license:gpl3)))
11911 (define-public kallisto
11917 (uri (git-reference
11918 (url "https://github.com/pachterlab/kallisto")
11919 (commit (string-append "v" version))))
11920 (file-name (git-file-name name version))
11923 "0nj382jiywqnpgvyhichajpkkh5r0bapn43f4dx40zdaq5v4m40m"))))
11924 (build-system cmake-build-system)
11926 `(#:tests? #f ; no "check" target
11928 (modify-phases %standard-phases
11929 (add-after 'unpack 'do-not-use-bundled-htslib
11931 (substitute* "CMakeLists.txt"
11932 (("^ExternalProject_Add" m)
11933 (string-append "if (NEVER)\n" m))
11935 (string-append ")\nendif(NEVER)"))
11936 (("include_directories\\(\\$\\{htslib_PREFIX.*" m)
11937 (string-append "# " m)))
11938 (substitute* "src/CMakeLists.txt"
11939 (("target_link_libraries\\(kallisto kallisto_core pthread \
11940 \\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/../ext/htslib/libhts.a\\)")
11941 "target_link_libraries(kallisto kallisto_core pthread hts)")
11942 (("include_directories\\(\\.\\./ext/htslib\\)") ""))
11948 (home-page "https://pachterlab.github.io/kallisto/")
11949 (synopsis "Near-optimal RNA-Seq quantification")
11951 "Kallisto is a program for quantifying abundances of transcripts from
11952 RNA-Seq data, or more generally of target sequences using high-throughput
11953 sequencing reads. It is based on the novel idea of pseudoalignment for
11954 rapidly determining the compatibility of reads with targets, without the need
11955 for alignment. Pseudoalignment of reads preserves the key information needed
11956 for quantification, and kallisto is therefore not only fast, but also as
11957 accurate as existing quantification tools.")
11958 (license license:bsd-2)))
11960 (define-public libgff
11966 (uri (git-reference
11967 (url "https://github.com/Kingsford-Group/libgff")
11968 (commit (string-append "v" version))))
11969 (file-name (git-file-name name version))
11972 "0n6vfjnq7a2mianipscbshrvbncss8z4zkgkbjw754p9043nfkps"))))
11973 (build-system cmake-build-system)
11974 (arguments `(#:tests? #f)) ; no tests included
11975 (home-page "https://github.com/Kingsford-Group/libgff")
11976 (synopsis "Parser library for reading/writing GFF files")
11977 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11978 code that is used in the Cufflinks codebase. The goal of this library is to
11979 provide this functionality without the necessity of drawing in a heavy-weight
11980 dependency like SeqAn.")
11981 (license (license:x11-style "https://www.boost.org/LICENSE_1_0.txt"))))
11983 (define-public sailfish
11989 (uri (git-reference
11990 (url "https://github.com/kingsfordgroup/sailfish")
11991 (commit (string-append "v" version))))
11992 (file-name (git-file-name name version))
11995 "1amcc5hqvsl42hg4x19bi9vy47cl874s0lw1fmi0hwsdk9i8c03v"))
11996 (modules '((guix build utils)))
11999 ;; Delete bundled headers for eigen3.
12000 (delete-file-recursively "include/eigen3/")
12002 (build-system cmake-build-system)
12004 `(#:configure-flags
12005 (list (string-append "-DBOOST_INCLUDEDIR="
12006 (assoc-ref %build-inputs "boost")
12008 (string-append "-DBOOST_LIBRARYDIR="
12009 (assoc-ref %build-inputs "boost")
12011 (string-append "-DBoost_LIBRARIES="
12012 "-lboost_iostreams "
12013 "-lboost_filesystem "
12018 "-lboost_program_options")
12019 "-DBoost_FOUND=TRUE"
12020 ;; Don't download RapMap---we already have it!
12021 "-DFETCHED_RAPMAP=1")
12022 ;; Tests must be run after installation and the location of the test
12023 ;; data file must be overridden. But the tests fail. It looks like
12024 ;; they are not really meant to be run.
12027 (modify-phases %standard-phases
12028 ;; Boost cannot be found, even though it's right there.
12029 (add-after 'unpack 'do-not-look-for-boost
12030 (lambda* (#:key inputs #:allow-other-keys)
12031 (substitute* "CMakeLists.txt"
12032 (("find_package\\(Boost 1\\.53\\.0") "#"))
12034 (add-after 'unpack 'do-not-assign-to-macro
12036 (substitute* "include/spdlog/details/format.cc"
12037 (("const unsigned CHAR_WIDTH = 1;") ""))
12039 (add-after 'unpack 'prepare-rapmap
12040 (lambda* (#:key inputs #:allow-other-keys)
12041 (let ((src "external/install/src/rapmap/")
12042 (include "external/install/include/rapmap/")
12043 (rapmap (assoc-ref inputs "rapmap")))
12044 (mkdir-p "/tmp/rapmap")
12046 (assoc-ref inputs "rapmap")
12048 "--strip-components=1")
12051 (for-each (lambda (file)
12052 (install-file file src))
12053 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
12054 (copy-recursively "/tmp/rapmap/include" include))
12056 (add-after 'unpack 'use-system-libraries
12057 (lambda* (#:key inputs #:allow-other-keys)
12058 (substitute* '("src/SailfishIndexer.cpp"
12059 "src/SailfishUtils.cpp"
12060 "src/SailfishQuantify.cpp"
12061 "src/FASTAParser.cpp"
12063 "include/SailfishUtils.hpp"
12064 "include/SailfishIndex.hpp"
12065 "include/CollapsedEMOptimizer.hpp"
12066 "src/CollapsedEMOptimizer.cpp")
12067 (("#include \"jellyfish/config.h\"") ""))
12068 (substitute* "src/CMakeLists.txt"
12069 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
12070 (string-append (assoc-ref inputs "jellyfish")
12071 "/include/jellyfish-" ,(package-version jellyfish)))
12072 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
12073 (string-append (assoc-ref inputs "jellyfish")
12074 "/lib/libjellyfish-2.0.a"))
12075 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12076 (string-append (assoc-ref inputs "libdivsufsort")
12077 "/lib/libdivsufsort.so"))
12078 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12079 (string-append (assoc-ref inputs "libdivsufsort")
12080 "/lib/libdivsufsort64.so")))
12081 (substitute* "CMakeLists.txt"
12082 ;; Don't prefer static libs
12083 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12084 (("find_package\\(Jellyfish.*") "")
12085 (("ExternalProject_Add\\(libjellyfish") "message(")
12086 (("ExternalProject_Add\\(libgff") "message(")
12087 (("ExternalProject_Add\\(libsparsehash") "message(")
12088 (("ExternalProject_Add\\(libdivsufsort") "message("))
12090 ;; Ensure that Eigen headers can be found
12091 (setenv "CPLUS_INCLUDE_PATH"
12092 (string-append (assoc-ref inputs "eigen")
12094 (or (getenv "CPLUS_INCLUDE_PATH") "")))
12099 ("jemalloc" ,jemalloc)
12100 ("jellyfish" ,jellyfish)
12101 ("sparsehash" ,sparsehash)
12104 (uri (git-reference
12105 (url "https://github.com/COMBINE-lab/RapMap")
12106 (commit (string-append "sf-v" version))))
12107 (file-name (string-append "rapmap-sf-v" version "-checkout"))
12110 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
12111 (modules '((guix build utils)))
12112 ;; These files are expected to be excluded.
12114 '(begin (delete-file-recursively "include/spdlog")
12115 (for-each delete-file '("include/xxhash.h"
12118 ("libdivsufsort" ,libdivsufsort)
12123 `(("pkg-config" ,pkg-config)))
12124 (home-page "https://www.cs.cmu.edu/~ckingsf/software/sailfish/")
12125 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
12126 (description "Sailfish is a tool for genomic transcript quantification
12127 from RNA-seq data. It requires a set of target transcripts (either from a
12128 reference or de-novo assembly) to quantify. All you need to run sailfish is a
12129 fasta file containing your reference transcripts and a (set of) fasta/fastq
12130 file(s) containing your reads.")
12131 (license license:gpl3+)))
12133 (define libstadenio-for-salmon
12135 (name "libstadenio")
12139 (uri (git-reference
12140 (url "https://github.com/COMBINE-lab/staden-io_lib")
12141 (commit (string-append "v" version))))
12142 (file-name (string-append name "-" version "-checkout"))
12145 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
12146 (build-system gnu-build-system)
12147 (arguments '(#:parallel-tests? #f)) ; not supported
12151 `(("perl" ,perl))) ; for tests
12152 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
12153 (synopsis "General purpose trace and experiment file library")
12154 (description "This package provides a library of file reading and writing
12155 code to provide a general purpose Trace file (and Experiment File) reading
12158 The following file formats are supported:
12161 @item SCF trace files
12162 @item ABI trace files
12163 @item ALF trace files
12164 @item ZTR trace files
12165 @item SFF trace archives
12166 @item SRF trace archives
12167 @item Experiment files
12168 @item Plain text files
12169 @item SAM/BAM sequence files
12170 @item CRAM sequence files
12172 (license license:bsd-3)))
12174 (define-public salmon
12180 (uri (git-reference
12181 (url "https://github.com/COMBINE-lab/salmon")
12182 (commit (string-append "v" version))))
12183 (file-name (git-file-name name version))
12186 "1i2z4aivicmiixdz9bxalp7vmfzi3k92fxa63iqa8kgvfw5a4aq5"))
12187 (modules '((guix build utils)))
12190 ;; Delete bundled headers for eigen3.
12191 (delete-file-recursively "include/eigen3/")
12193 (build-system cmake-build-system)
12195 `(#:configure-flags
12196 (list (string-append "-DBOOST_INCLUDEDIR="
12197 (assoc-ref %build-inputs "boost")
12199 (string-append "-DBOOST_LIBRARYDIR="
12200 (assoc-ref %build-inputs "boost")
12202 (string-append "-DBoost_LIBRARIES="
12203 "-lboost_iostreams "
12204 "-lboost_filesystem "
12209 "-lboost_program_options")
12210 "-DBoost_FOUND=TRUE"
12211 "-DTBB_LIBRARIES=tbb tbbmalloc"
12212 ;; Don't download RapMap---we already have it!
12213 "-DFETCHED_RAPMAP=1")
12215 (modify-phases %standard-phases
12216 ;; Boost cannot be found, even though it's right there.
12217 (add-after 'unpack 'do-not-look-for-boost
12218 (lambda* (#:key inputs #:allow-other-keys)
12219 (substitute* "CMakeLists.txt"
12220 (("find_package\\(Boost 1\\.59\\.0") "#"))
12222 (add-after 'unpack 'do-not-phone-home
12224 (substitute* "src/Salmon.cpp"
12225 (("getVersionMessage\\(\\)") "\"\""))
12227 (add-after 'unpack 'prepare-rapmap
12228 (lambda* (#:key inputs #:allow-other-keys)
12229 (let ((src "external/install/src/rapmap/")
12230 (include "external/install/include/rapmap/")
12231 (rapmap (assoc-ref inputs "rapmap")))
12234 (copy-recursively (string-append rapmap "/src") src)
12235 (copy-recursively (string-append rapmap "/include") include)
12236 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
12237 "external/install/include/rapmap/FastxParser.hpp"
12238 "external/install/include/rapmap/concurrentqueue.h"
12239 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
12240 "external/install/src/rapmap/FastxParser.cpp"
12241 "external/install/src/rapmap/xxhash.c"))
12242 (delete-file-recursively "external/install/include/rapmap/spdlog"))
12244 (add-after 'unpack 'use-system-libraries
12245 (lambda* (#:key inputs #:allow-other-keys)
12246 (substitute* "CMakeLists.txt"
12247 ;; Don't prefer static libs
12248 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12249 (("set\\(TBB_LIBRARIES") "message(")
12250 ;; Don't download anything
12251 (("DOWNLOAD_COMMAND") "DOWNLOAD_COMMAND echo")
12252 (("externalproject_add\\(libcereal") "message(")
12253 (("externalproject_add\\(libgff") "message(")
12254 (("externalproject_add\\(libtbb") "message(")
12255 (("externalproject_add\\(libdivsufsort") "message(")
12256 (("externalproject_add\\(libstadenio") "message(")
12257 (("externalproject_add_step\\(") "message("))
12258 (substitute* "src/CMakeLists.txt"
12259 (("add_dependencies") "#")
12260 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
12261 (string-append (assoc-ref inputs "libstadenio-for-salmon")
12262 "/lib/libstaden-read.so"))
12263 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12264 (string-append (assoc-ref inputs "libdivsufsort")
12265 "/lib/libdivsufsort.so"))
12266 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12267 (string-append (assoc-ref inputs "libdivsufsort")
12268 "/lib/libdivsufsort64.so"))
12269 (("lib/libdivsufsort.a") "/lib/libdivsufsort.so"))
12271 ;; Ensure that all headers can be found
12272 (setenv "CPLUS_INCLUDE_PATH"
12273 (string-append (or (getenv "CPLUS_INCLUDE_PATH") "")
12275 (assoc-ref inputs "eigen")
12276 "/include/eigen3"))
12278 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
12279 ;; run. It only exists after the install phase.
12280 (add-after 'unpack 'fix-tests
12282 (substitute* "src/CMakeLists.txt"
12283 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
12284 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
12293 (uri (git-reference
12294 (url "https://github.com/COMBINE-lab/RapMap")
12295 (commit (string-append "salmon-v" version))))
12296 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
12299 "1biplxf0csc7a8h1wf219b0vmjkvw6wk2zylhdklb577kgmihdms"))))
12300 ("jemalloc" ,jemalloc)
12303 ("libdivsufsort" ,libdivsufsort)
12304 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
12308 `(("pkg-config" ,pkg-config)))
12309 (home-page "https://github.com/COMBINE-lab/salmon")
12310 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
12311 (description "Salmon is a program to produce highly-accurate,
12312 transcript-level quantification estimates from RNA-seq data. Salmon achieves
12313 its accuracy and speed via a number of different innovations, including the
12314 use of lightweight alignments (accurate but fast-to-compute proxies for
12315 traditional read alignments) and massively-parallel stochastic collapsed
12316 variational inference.")
12317 (license license:gpl3+)))
12319 (define-public python-loompy
12321 (name "python-loompy")
12323 ;; The tarball on Pypi does not include the tests.
12326 (uri (git-reference
12327 (url "https://github.com/linnarsson-lab/loompy")
12329 (file-name (git-file-name name version))
12332 "12a5kjgiikapv93wahfw0frszx1lblnppyz3vs5gy8fgmgngra07"))))
12333 (build-system python-build-system)
12336 (modify-phases %standard-phases
12339 (setenv "PYTHONPATH"
12340 (string-append (getcwd) ":"
12341 (getenv "PYTHONPATH")))
12342 (invoke "pytest" "tests")
12345 `(("python-h5py" ,python-h5py)
12346 ("python-numpy" ,python-numpy)
12347 ("python-pandas" ,python-pandas)
12348 ("python-scipy" ,python-scipy)))
12350 `(("python-pytest" ,python-pytest)))
12351 (home-page "https://github.com/linnarsson-lab/loompy")
12352 (synopsis "Work with .loom files for single-cell RNA-seq data")
12353 (description "The loom file format is an efficient format for very large
12354 omics datasets, consisting of a main matrix, optional additional layers, a
12355 variable number of row and column annotations. Loom also supports sparse
12356 graphs. This library makes it easy to work with @file{.loom} files for
12357 single-cell RNA-seq data.")
12358 (license license:bsd-3)))
12360 ;; We cannot use the latest commit because it requires Java 9.
12361 (define-public java-forester
12362 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
12365 (name "java-forester")
12366 (version (string-append "0-" revision "." (string-take commit 7)))
12369 (uri (git-reference
12370 (url "https://github.com/cmzmasek/forester")
12372 (file-name (string-append name "-" version "-checkout"))
12375 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12376 (modules '((guix build utils)))
12379 ;; Delete bundled jars and pre-built classes
12380 (delete-file-recursively "forester/java/resources")
12381 (delete-file-recursively "forester/java/classes")
12382 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12383 ;; Delete bundled applications
12384 (delete-file-recursively "forester_applications")
12386 (build-system ant-build-system)
12388 `(#:tests? #f ; there are none
12390 #:modules ((guix build ant-build-system)
12392 (guix build java-utils)
12396 (modify-phases %standard-phases
12397 (add-after 'unpack 'chdir
12398 (lambda _ (chdir "forester/java") #t))
12399 (add-after 'chdir 'fix-dependencies
12401 (chmod "build.xml" #o664)
12402 (call-with-output-file "build.xml.new"
12406 (with-input-from-file "build.xml"
12407 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12408 `(;; Remove all unjar tags to avoid repacking classes.
12409 (unjar . ,(lambda _ '()))
12410 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12411 (*text* . ,(lambda (_ txt) txt))))
12413 (rename-file "build.xml.new" "build.xml")
12415 ;; FIXME: itext is difficult to package as it depends on a few
12416 ;; unpackaged libraries.
12417 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12419 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12420 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12421 (("pdf_written_to = PdfExporter.*")
12422 "throw new IOException(\"PDF export is not available.\");"))
12424 ;; There is no install target
12425 (replace 'install (install-jars ".")))))
12427 `(("java-commons-codec" ,java-commons-codec)
12428 ("java-openchart2" ,java-openchart2)))
12429 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12430 (synopsis "Phylogenomics libraries for Java")
12431 (description "Forester is a collection of Java libraries for
12432 phylogenomics and evolutionary biology research. It includes support for
12433 reading, writing, and exporting phylogenetic trees.")
12434 (license license:lgpl2.1+))))
12436 (define-public java-forester-1.005
12438 (name "java-forester")
12442 (uri (string-append "https://repo1.maven.org/maven2/"
12443 "org/biojava/thirdparty/forester/"
12444 version "/forester-" version "-sources.jar"))
12445 (file-name (string-append name "-" version ".jar"))
12448 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12449 (build-system ant-build-system)
12451 `(#:tests? #f ; there are none
12453 #:modules ((guix build ant-build-system)
12455 (guix build java-utils)
12459 (modify-phases %standard-phases
12460 (add-after 'unpack 'fix-dependencies
12461 (lambda* (#:key inputs #:allow-other-keys)
12462 (call-with-output-file "build.xml"
12466 (with-input-from-file "src/build.xml"
12467 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12468 `(;; Remove all unjar tags to avoid repacking classes.
12469 (unjar . ,(lambda _ '()))
12470 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12471 (*text* . ,(lambda (_ txt) txt))))
12473 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12474 "synth_look_and_feel_1.xml")
12475 (copy-file (assoc-ref inputs "phyloxml.xsd")
12477 (substitute* "build.xml"
12478 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12479 "synth_look_and_feel_1.xml")
12480 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12483 ;; FIXME: itext is difficult to package as it depends on a few
12484 ;; unpackaged libraries.
12485 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12487 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12488 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12489 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12490 (("pdf_written_to = PdfExporter.*")
12491 "throw new IOException(\"PDF export is not available.\"); /*")
12492 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12493 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12495 (add-after 'unpack 'delete-pre-built-classes
12496 (lambda _ (delete-file-recursively "src/classes") #t))
12497 ;; There is no install target
12498 (replace 'install (install-jars ".")))))
12500 `(("java-commons-codec" ,java-commons-codec)
12501 ("java-openchart2" ,java-openchart2)))
12502 ;; The source archive does not contain the resources.
12507 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12508 "b61cc2dcede0bede317db362472333115756b8c6/"
12509 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12510 (file-name (string-append name "-phyloxml-" version ".xsd"))
12513 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12514 ("synth_look_and_feel_1.xml"
12517 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12518 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12519 "forester/java/classes/resources/"
12520 "synth_look_and_feel_1.xml"))
12521 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12524 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12525 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12526 (synopsis "Phylogenomics libraries for Java")
12527 (description "Forester is a collection of Java libraries for
12528 phylogenomics and evolutionary biology research. It includes support for
12529 reading, writing, and exporting phylogenetic trees.")
12530 (license license:lgpl2.1+)))
12532 (define-public java-biojava-core
12534 (name "java-biojava-core")
12538 (uri (git-reference
12539 (url "https://github.com/biojava/biojava")
12540 (commit (string-append "biojava-" version))))
12541 (file-name (string-append name "-" version "-checkout"))
12544 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12545 (build-system ant-build-system)
12548 #:jar-name "biojava-core.jar"
12549 #:source-dir "biojava-core/src/main/java/"
12550 #:test-dir "biojava-core/src/test"
12551 ;; These tests seem to require internet access.
12552 #:test-exclude (list "**/SearchIOTest.java"
12553 "**/BlastXMLParserTest.java"
12554 "**/GenbankCookbookTest.java"
12555 "**/GenbankProxySequenceReaderTest.java")
12557 (modify-phases %standard-phases
12558 (add-before 'build 'copy-resources
12560 (copy-recursively "biojava-core/src/main/resources"
12563 (add-before 'check 'copy-test-resources
12565 (copy-recursively "biojava-core/src/test/resources"
12566 "build/test-classes")
12569 `(("java-log4j-api" ,java-log4j-api)
12570 ("java-log4j-core" ,java-log4j-core)
12571 ("java-slf4j-api" ,java-slf4j-api)
12572 ("java-slf4j-simple" ,java-slf4j-simple)))
12574 `(("java-junit" ,java-junit)
12575 ("java-hamcrest-core" ,java-hamcrest-core)))
12576 (home-page "https://biojava.org")
12577 (synopsis "Core libraries of Java framework for processing biological data")
12578 (description "BioJava is a project dedicated to providing a Java framework
12579 for processing biological data. It provides analytical and statistical
12580 routines, parsers for common file formats, reference implementations of
12581 popular algorithms, and allows the manipulation of sequences and 3D
12582 structures. The goal of the biojava project is to facilitate rapid
12583 application development for bioinformatics.
12585 This package provides the core libraries.")
12586 (license license:lgpl2.1+)))
12588 (define-public java-biojava-phylo
12589 (package (inherit java-biojava-core)
12590 (name "java-biojava-phylo")
12591 (build-system ant-build-system)
12594 #:jar-name "biojava-phylo.jar"
12595 #:source-dir "biojava-phylo/src/main/java/"
12596 #:test-dir "biojava-phylo/src/test"
12598 (modify-phases %standard-phases
12599 (add-before 'build 'copy-resources
12601 (copy-recursively "biojava-phylo/src/main/resources"
12604 (add-before 'check 'copy-test-resources
12606 (copy-recursively "biojava-phylo/src/test/resources"
12607 "build/test-classes")
12610 `(("java-log4j-api" ,java-log4j-api)
12611 ("java-log4j-core" ,java-log4j-core)
12612 ("java-slf4j-api" ,java-slf4j-api)
12613 ("java-slf4j-simple" ,java-slf4j-simple)
12614 ("java-biojava-core" ,java-biojava-core)
12615 ("java-forester" ,java-forester)))
12617 `(("java-junit" ,java-junit)
12618 ("java-hamcrest-core" ,java-hamcrest-core)))
12619 (home-page "https://biojava.org")
12620 (synopsis "Biojava interface to the forester phylogenomics library")
12621 (description "The phylo module provides a biojava interface layer to the
12622 forester phylogenomics library for constructing phylogenetic trees.")))
12624 (define-public java-biojava-alignment
12625 (package (inherit java-biojava-core)
12626 (name "java-biojava-alignment")
12627 (build-system ant-build-system)
12630 #:jar-name "biojava-alignment.jar"
12631 #:source-dir "biojava-alignment/src/main/java/"
12632 #:test-dir "biojava-alignment/src/test"
12634 (modify-phases %standard-phases
12635 (add-before 'build 'copy-resources
12637 (copy-recursively "biojava-alignment/src/main/resources"
12640 (add-before 'check 'copy-test-resources
12642 (copy-recursively "biojava-alignment/src/test/resources"
12643 "build/test-classes")
12646 `(("java-log4j-api" ,java-log4j-api)
12647 ("java-log4j-core" ,java-log4j-core)
12648 ("java-slf4j-api" ,java-slf4j-api)
12649 ("java-slf4j-simple" ,java-slf4j-simple)
12650 ("java-biojava-core" ,java-biojava-core)
12651 ("java-biojava-phylo" ,java-biojava-phylo)
12652 ("java-forester" ,java-forester)))
12654 `(("java-junit" ,java-junit)
12655 ("java-hamcrest-core" ,java-hamcrest-core)))
12656 (home-page "https://biojava.org")
12657 (synopsis "Biojava API for genetic sequence alignment")
12658 (description "The alignment module of BioJava provides an API that
12662 @item implementations of dynamic programming algorithms for sequence
12664 @item reading and writing of popular alignment file formats;
12665 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12668 (define-public java-biojava-core-4.0
12669 (package (inherit java-biojava-core)
12670 (name "java-biojava-core")
12674 (uri (git-reference
12675 (url "https://github.com/biojava/biojava")
12676 (commit (string-append "biojava-" version))))
12677 (file-name (string-append name "-" version "-checkout"))
12680 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12682 (define-public java-biojava-phylo-4.0
12683 (package (inherit java-biojava-core-4.0)
12684 (name "java-biojava-phylo")
12685 (build-system ant-build-system)
12688 #:jar-name "biojava-phylo.jar"
12689 #:source-dir "biojava-phylo/src/main/java/"
12690 #:test-dir "biojava-phylo/src/test"
12692 (modify-phases %standard-phases
12693 (add-before 'build 'copy-resources
12695 (copy-recursively "biojava-phylo/src/main/resources"
12698 (add-before 'check 'copy-test-resources
12700 (copy-recursively "biojava-phylo/src/test/resources"
12701 "build/test-classes")
12704 `(("java-log4j-api" ,java-log4j-api)
12705 ("java-log4j-core" ,java-log4j-core)
12706 ("java-slf4j-api" ,java-slf4j-api)
12707 ("java-slf4j-simple" ,java-slf4j-simple)
12708 ("java-biojava-core" ,java-biojava-core-4.0)
12709 ("java-forester" ,java-forester-1.005)))
12711 `(("java-junit" ,java-junit)
12712 ("java-hamcrest-core" ,java-hamcrest-core)))
12713 (home-page "https://biojava.org")
12714 (synopsis "Biojava interface to the forester phylogenomics library")
12715 (description "The phylo module provides a biojava interface layer to the
12716 forester phylogenomics library for constructing phylogenetic trees.")))
12718 (define-public java-biojava-alignment-4.0
12719 (package (inherit java-biojava-core-4.0)
12720 (name "java-biojava-alignment")
12721 (build-system ant-build-system)
12724 #:jar-name "biojava-alignment.jar"
12725 #:source-dir "biojava-alignment/src/main/java/"
12726 #:test-dir "biojava-alignment/src/test"
12728 (modify-phases %standard-phases
12729 (add-before 'build 'copy-resources
12731 (copy-recursively "biojava-alignment/src/main/resources"
12734 (add-before 'check 'copy-test-resources
12736 (copy-recursively "biojava-alignment/src/test/resources"
12737 "build/test-classes")
12740 `(("java-log4j-api" ,java-log4j-api)
12741 ("java-log4j-core" ,java-log4j-core)
12742 ("java-slf4j-api" ,java-slf4j-api)
12743 ("java-slf4j-simple" ,java-slf4j-simple)
12744 ("java-biojava-core" ,java-biojava-core-4.0)
12745 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12746 ("java-forester" ,java-forester-1.005)))
12748 `(("java-junit" ,java-junit)
12749 ("java-hamcrest-core" ,java-hamcrest-core)))
12750 (home-page "https://biojava.org")
12751 (synopsis "Biojava API for genetic sequence alignment")
12752 (description "The alignment module of BioJava provides an API that
12756 @item implementations of dynamic programming algorithms for sequence
12758 @item reading and writing of popular alignment file formats;
12759 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12762 (define-public dropseq-tools
12764 (name "dropseq-tools")
12769 (uri "http://mccarrolllab.com/download/1276/")
12770 (file-name (string-append "dropseq-tools-" version ".zip"))
12773 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12774 ;; Delete bundled libraries
12775 (modules '((guix build utils)))
12778 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12779 (delete-file-recursively "3rdParty")
12781 (build-system ant-build-system)
12783 `(#:tests? #f ; test data are not included
12784 #:test-target "test"
12785 #:build-target "all"
12786 #:source-dir "public/src/"
12789 (list (string-append "-Dpicard.executable.dir="
12790 (assoc-ref %build-inputs "java-picard")
12792 #:modules ((ice-9 match)
12795 (guix build java-utils)
12796 (guix build ant-build-system))
12798 (modify-phases %standard-phases
12799 ;; FIXME: fails with "java.io.FileNotFoundException:
12800 ;; /gnu/store/…-dropseq-tools-1.13/share/java/lib/biojava-alignment.jar"
12801 (delete 'generate-jar-indices)
12802 ;; All dependencies must be linked to "lib", because that's where
12803 ;; they will be searched for when the Class-Path property of the
12804 ;; manifest is computed.
12805 (add-after 'unpack 'record-references
12806 (lambda* (#:key inputs #:allow-other-keys)
12807 (mkdir-p "jar/lib")
12808 (let ((dirs (filter-map (match-lambda
12810 (if (and (string-prefix? "java-" name)
12811 (not (string=? name "java-testng")))
12814 (for-each (lambda (jar)
12815 (symlink jar (string-append "jar/lib/" (basename jar))))
12816 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12819 ;; There is no installation target
12821 (lambda* (#:key inputs outputs #:allow-other-keys)
12822 (let* ((out (assoc-ref outputs "out"))
12823 (bin (string-append out "/bin"))
12824 (share (string-append out "/share/java/"))
12825 (lib (string-append share "/lib/"))
12826 (scripts (list "BAMTagHistogram"
12827 "BAMTagofTagCounts"
12828 "BaseDistributionAtReadPosition"
12829 "CollapseBarcodesInPlace"
12830 "CollapseTagWithContext"
12832 "CreateIntervalsFiles"
12833 "DetectBeadSynthesisErrors"
12834 "DigitalExpression"
12835 "Drop-seq_alignment.sh"
12838 "GatherGeneGCLength"
12839 "GatherMolecularBarcodeDistributionByGene"
12840 "GatherReadQualityMetrics"
12843 "SelectCellsByNumTranscripts"
12844 "SingleCellRnaSeqMetricsCollector"
12845 "TagBamWithReadSequenceExtended"
12846 "TagReadWithGeneExon"
12847 "TagReadWithInterval"
12848 "TrimStartingSequence"
12849 "ValidateReference")))
12850 (for-each mkdir-p (list bin share lib))
12851 (install-file "dist/dropseq.jar" share)
12852 (for-each (lambda (script)
12853 (chmod script #o555)
12854 (install-file script bin))
12856 (substitute* (map (lambda (script)
12857 (string-append bin "/" script))
12859 (("^java") (which "java"))
12860 (("jar_deploy_dir=.*")
12861 (string-append "jar_deploy_dir=" share "\n"))))
12863 ;; FIXME: We do this after stripping jars because we don't want it to
12864 ;; copy all these jars and strip them. We only want to install
12865 ;; links. Arguably, this is a problem with the ant-build-system.
12866 (add-after 'strip-jar-timestamps 'install-links
12867 (lambda* (#:key outputs #:allow-other-keys)
12868 (let* ((out (assoc-ref outputs "out"))
12869 (share (string-append out "/share/java/"))
12870 (lib (string-append share "/lib/")))
12871 (for-each (lambda (jar)
12872 (symlink (readlink jar)
12873 (string-append lib (basename jar))))
12874 (find-files "jar/lib" "\\.jar$")))
12877 `(("jdk" ,icedtea-8)
12878 ("java-picard" ,java-picard-2.10.3)
12879 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12880 ("java-commons-math3" ,java-commons-math3)
12881 ("java-commons-jexl2" ,java-commons-jexl-2)
12882 ("java-commons-collections4" ,java-commons-collections4)
12883 ("java-commons-lang2" ,java-commons-lang)
12884 ("java-commons-io" ,java-commons-io)
12885 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12886 ("java-guava" ,java-guava)
12887 ("java-la4j" ,java-la4j)
12888 ("java-biojava-core" ,java-biojava-core-4.0)
12889 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12890 ("java-jdistlib" ,java-jdistlib)
12891 ("java-simple-xml" ,java-simple-xml)
12892 ("java-snakeyaml" ,java-snakeyaml)))
12895 ("java-testng" ,java-testng)))
12896 (home-page "http://mccarrolllab.com/dropseq/")
12897 (synopsis "Tools for Drop-seq analyses")
12898 (description "Drop-seq is a technology to enable biologists to
12899 analyze RNA expression genome-wide in thousands of individual cells at
12900 once. This package provides tools to perform Drop-seq analyses.")
12901 (license license:expat)))
12903 (define-public pigx-rnaseq
12905 (name "pigx-rnaseq")
12909 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12910 "releases/download/v" version
12911 "/pigx_rnaseq-" version ".tar.gz"))
12914 "0z3hr120wk2vrlmlpz1vp3n9wy3rq4y2mnzh2vf08qgqn2xfdwcw"))))
12915 (build-system gnu-build-system)
12917 `(#:parallel-tests? #f ; not supported
12919 (modify-phases %standard-phases
12920 ;; "test.sh" runs STAR, which requires excessive amounts of memory.
12921 (add-after 'unpack 'disable-resource-intensive-test
12923 (substitute* "Makefile.in"
12924 (("(^ tests/test_trim_galore/test.sh).*" _ m) m)
12925 (("^ tests/test_multiqc/test.sh") "")
12926 (("^ test.sh") ""))
12929 `(("coreutils" ,coreutils)
12932 ("snakemake" ,snakemake)
12934 ("multiqc" ,multiqc)
12936 ("trim-galore" ,trim-galore)
12938 ("samtools" ,samtools)
12939 ("r-minimal" ,r-minimal)
12940 ("r-rmarkdown" ,r-rmarkdown)
12941 ("r-ggplot2" ,r-ggplot2)
12942 ("r-ggrepel" ,r-ggrepel)
12943 ("r-gprofiler" ,r-gprofiler)
12944 ("r-deseq2" ,r-deseq2)
12946 ("r-knitr" ,r-knitr)
12947 ("r-pheatmap" ,r-pheatmap)
12948 ("r-corrplot" ,r-corrplot)
12949 ("r-reshape2" ,r-reshape2)
12950 ("r-plotly" ,r-plotly)
12951 ("r-scales" ,r-scales)
12952 ("r-summarizedexperiment" ,r-summarizedexperiment)
12953 ("r-crosstalk" ,r-crosstalk)
12954 ("r-tximport" ,r-tximport)
12955 ("r-rtracklayer" ,r-rtracklayer)
12956 ("r-rjson" ,r-rjson)
12959 ("pandoc-citeproc" ,pandoc-citeproc)
12960 ("python-wrapper" ,python-wrapper)
12961 ("python-pyyaml" ,python-pyyaml)))
12962 (home-page "https://bioinformatics.mdc-berlin.de/pigx/")
12963 (synopsis "Analysis pipeline for RNA sequencing experiments")
12964 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
12965 reporting for RNA sequencing experiments. It is easy to use and produces high
12966 quality reports. The inputs are reads files from the sequencing experiment,
12967 and a configuration file which describes the experiment. In addition to
12968 quality control of the experiment, the pipeline produces a differential
12969 expression report comparing samples in an easily configurable manner.")
12970 (license license:gpl3+)))
12972 (define-public pigx-chipseq
12974 (name "pigx-chipseq")
12978 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
12979 "releases/download/v" version
12980 "/pigx_chipseq-" version ".tar.gz"))
12983 "0426i31b7mqqkbss5dgrvf5prkj4z1qrd7yrpd27vybs01xhdlks"))))
12984 (build-system gnu-build-system)
12985 ;; parts of the tests rely on access to the network
12986 (arguments '(#:tests? #f))
12989 ("coreutils" ,coreutils)
12990 ("r-minimal" ,r-minimal)
12991 ("r-argparser" ,r-argparser)
12992 ("r-biocparallel" ,r-biocparallel)
12993 ("r-biostrings" ,r-biostrings)
12994 ("r-chipseq" ,r-chipseq)
12995 ("r-data-table" ,r-data-table)
12996 ("r-dplyr" ,r-dplyr)
12997 ("r-genomation" ,r-genomation)
12998 ("r-genomicalignments" ,r-genomicalignments)
12999 ("r-genomicranges" ,r-genomicranges)
13000 ("r-rsamtools" ,r-rsamtools)
13001 ("r-rtracklayer" ,r-rtracklayer)
13002 ("r-s4vectors" ,r-s4vectors)
13003 ("r-stringr" ,r-stringr)
13004 ("r-tibble" ,r-tibble)
13005 ("r-tidyr" ,r-tidyr)
13006 ("r-jsonlite" ,r-jsonlite)
13007 ("r-heatmaply" ,r-heatmaply)
13008 ("r-htmlwidgets" ,r-htmlwidgets)
13009 ("r-ggplot2" ,r-ggplot2)
13010 ("r-plotly" ,r-plotly)
13011 ("r-rmarkdown" ,r-rmarkdown)
13012 ("python-wrapper" ,python-wrapper)
13013 ("python-pyyaml" ,python-pyyaml)
13014 ("python-magic" ,python-magic)
13015 ("python-xlrd" ,python-xlrd)
13016 ("trim-galore" ,trim-galore)
13018 ("multiqc" ,multiqc)
13021 ("pandoc-citeproc" ,pandoc-citeproc)
13025 ("snakemake" ,snakemake)
13026 ("samtools" ,samtools)
13027 ("bedtools" ,bedtools)
13028 ("kentutils" ,kentutils)))
13030 `(("python-pytest" ,python-pytest)))
13031 (home-page "https://bioinformatics.mdc-berlin.de/pigx/")
13032 (synopsis "Analysis pipeline for ChIP sequencing experiments")
13033 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
13034 calling and reporting for ChIP sequencing experiments. It is easy to use and
13035 produces high quality reports. The inputs are reads files from the sequencing
13036 experiment, and a configuration file which describes the experiment. In
13037 addition to quality control of the experiment, the pipeline enables to set up
13038 multiple peak calling analysis and allows the generation of a UCSC track hub
13039 in an easily configurable manner.")
13040 (license license:gpl3+)))
13042 (define-public pigx-bsseq
13044 (name "pigx-bsseq")
13048 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
13049 "releases/download/v" version
13050 "/pigx_bsseq-" version ".tar.gz"))
13053 "0mpzlay2d5cjpmrcp7knff6rg1c2mqszd638n7lw0mc0cycbp9f8"))))
13054 (build-system gnu-build-system)
13056 `(;; TODO: tests currently require 12+GB of RAM. See
13057 ;; https://github.com/BIMSBbioinfo/pigx_bsseq/issues/164
13060 (modify-phases %standard-phases
13061 (add-before 'check 'set-timezone
13062 ;; The readr package is picky about timezones.
13063 (lambda* (#:key inputs #:allow-other-keys)
13064 (setenv "TZ" "UTC+1")
13066 (string-append (assoc-ref inputs "tzdata")
13067 "/share/zoneinfo"))
13070 `(("tzdata" ,tzdata)))
13072 `(("coreutils" ,coreutils)
13075 ("r-minimal" ,r-minimal)
13076 ("r-annotationhub" ,r-annotationhub)
13078 ("r-genomation" ,r-genomation)
13079 ("r-ggrepel" ,r-ggrepel)
13080 ("r-methylkit" ,r-methylkit)
13081 ("r-rtracklayer" ,r-rtracklayer)
13082 ("r-rmarkdown" ,r-rmarkdown)
13083 ("r-bookdown" ,r-bookdown)
13084 ("r-ggplot2" ,r-ggplot2)
13085 ("r-ggbio" ,r-ggbio)
13087 ("pandoc-citeproc" ,pandoc-citeproc)
13088 ("python-wrapper" ,python-wrapper)
13089 ("python-pyyaml" ,python-pyyaml)
13090 ("snakemake" ,snakemake)
13091 ("bismark" ,bismark)
13093 ("bwa-meth" ,bwa-meth)
13095 ("methyldackel" ,methyldackel)
13096 ("multiqc" ,multiqc)
13097 ("trim-galore" ,trim-galore)
13098 ("cutadapt" ,cutadapt)
13099 ("samblaster" ,samblaster)
13100 ("samtools" ,samtools)))
13101 (home-page "https://bioinformatics.mdc-berlin.de/pigx/")
13102 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
13103 (description "PiGx BSseq is a data processing pipeline for raw fastq read
13104 data of bisulfite experiments; it produces reports on aggregate methylation
13105 and coverage and can be used to produce information on differential
13106 methylation and segmentation.")
13107 (license license:gpl3+)))
13109 (define-public pigx-scrnaseq
13111 (name "pigx-scrnaseq")
13115 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/"
13116 "releases/download/v" version
13117 "/pigx_scrnaseq-" version ".tar.gz"))
13120 "1d5l3gywypi67yz9advxq5xkgfhr4733gj0bwnngm723i3hdf5w9"))))
13121 (build-system gnu-build-system)
13123 `(("coreutils" ,coreutils)
13126 ("flexbar" ,flexbar)
13127 ("java" ,icedtea-8)
13128 ("jellyfish" ,jellyfish)
13129 ("python-wrapper" ,python-wrapper)
13130 ("python-pyyaml" ,python-pyyaml)
13131 ("python-pandas" ,python-pandas)
13132 ("python-magic" ,python-magic)
13133 ("python-numpy" ,python-numpy)
13134 ("python-loompy" ,python-loompy)
13136 ("pandoc-citeproc" ,pandoc-citeproc)
13137 ("samtools" ,samtools)
13138 ("snakemake" ,snakemake)
13140 ("r-minimal" ,r-minimal)
13141 ("r-argparser" ,r-argparser)
13142 ("r-cowplot" ,r-cowplot)
13143 ("r-data-table" ,r-data-table)
13144 ("r-delayedarray" ,r-delayedarray)
13145 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
13146 ("r-dplyr" ,r-dplyr)
13147 ("r-dropbead" ,r-dropbead)
13149 ("r-genomicalignments" ,r-genomicalignments)
13150 ("r-genomicfiles" ,r-genomicfiles)
13151 ("r-genomicranges" ,r-genomicranges)
13152 ("r-ggplot2" ,r-ggplot2)
13153 ("r-hdf5array" ,r-hdf5array)
13154 ("r-pheatmap" ,r-pheatmap)
13155 ("r-rmarkdown" ,r-rmarkdown)
13156 ("r-rsamtools" ,r-rsamtools)
13157 ("r-rtracklayer" ,r-rtracklayer)
13158 ("r-rtsne" ,r-rtsne)
13159 ("r-scater" ,r-scater)
13160 ("r-scran" ,r-scran)
13161 ("r-seurat" ,r-seurat)
13162 ("r-singlecellexperiment" ,r-singlecellexperiment)
13163 ("r-stringr" ,r-stringr)
13164 ("r-yaml" ,r-yaml)))
13165 (home-page "https://bioinformatics.mdc-berlin.de/pigx/")
13166 (synopsis "Analysis pipeline for single-cell RNA sequencing experiments")
13167 (description "PiGX scRNAseq is an analysis pipeline for preprocessing and
13168 quality control for single cell RNA sequencing experiments. The inputs are
13169 read files from the sequencing experiment, and a configuration file which
13170 describes the experiment. It produces processed files for downstream analysis
13171 and interactive quality reports. The pipeline is designed to work with UMI
13173 (license license:gpl3+)))
13175 (define-public pigx
13181 (uri (string-append "https://github.com/BIMSBbioinfo/pigx/"
13182 "releases/download/v" version
13183 "/pigx-" version ".tar.gz"))
13186 "1i5njdy1clj5ncw45d16p7mwmqvb1ilikl9n797pxklc3f4s7mq7"))))
13187 (build-system gnu-build-system)
13189 `(("python" ,python)
13190 ("pigx-bsseq" ,pigx-bsseq)
13191 ("pigx-chipseq" ,pigx-chipseq)
13192 ("pigx-rnaseq" ,pigx-rnaseq)
13193 ("pigx-scrnaseq" ,pigx-scrnaseq)))
13194 (home-page "https://bioinformatics.mdc-berlin.de/pigx/")
13195 (synopsis "Analysis pipelines for genomics")
13196 (description "PiGx is a collection of genomics pipelines. It includes the
13197 following pipelines:
13200 @item PiGx BSseq for raw fastq read data of bisulfite experiments
13201 @item PiGx RNAseq for RNAseq samples
13202 @item PiGx scRNAseq for single cell dropseq analysis
13203 @item PiGx ChIPseq for reads from ChIPseq experiments
13206 All pipelines are easily configured with a simple sample sheet and a
13207 descriptive settings file. The result is a set of comprehensive, interactive
13208 HTML reports with interesting findings about your samples.")
13209 (license license:gpl3+)))
13211 (define-public genrich
13217 (uri (git-reference
13218 (url "https://github.com/jsh58/Genrich")
13219 (commit (string-append "v" version))))
13220 (file-name (git-file-name name version))
13223 "0x0q6z0208n3cxzqjla4rgjqpyqgwpmz27852lcvzkzaigymq4zp"))))
13224 (build-system gnu-build-system)
13226 `(#:tests? #f ; there are none
13228 (modify-phases %standard-phases
13229 (delete 'configure)
13231 (lambda* (#:key outputs #:allow-other-keys)
13232 (install-file "Genrich" (string-append (assoc-ref outputs "out") "/bin"))
13236 (home-page "https://github.com/jsh58/Genrich")
13237 (synopsis "Detecting sites of genomic enrichment")
13238 (description "Genrich is a peak-caller for genomic enrichment
13239 assays (e.g. ChIP-seq, ATAC-seq). It analyzes alignment files generated
13240 following the assay and produces a file detailing peaks of significant
13242 (license license:expat)))
13244 (define-public mantis
13245 (let ((commit "4ffd171632c2cb0056a86d709dfd2bf21bc69b84")
13249 (version (git-version "0" revision commit))
13252 (uri (git-reference
13253 (url "https://github.com/splatlab/mantis")
13255 (file-name (git-file-name name version))
13258 "0iqbr0dhmlc8mzpirmm2s4pkzkwdgrcx50yx6cv3wlr2qi064p55"))))
13259 (build-system cmake-build-system)
13260 (arguments '(#:tests? #f)) ; there are none
13262 `(("sdsl-lite" ,sdsl-lite)
13263 ("openssl" ,openssl)
13265 (home-page "https://github.com/splatlab/mantis")
13266 (synopsis "Large-scale sequence-search index data structure")
13267 (description "Mantis is a space-efficient data structure that can be
13268 used to index thousands of raw-read genomics experiments and facilitate
13269 large-scale sequence searches on those experiments. Mantis uses counting
13270 quotient filters instead of Bloom filters, enabling rapid index builds and
13271 queries, small indexes, and exact results, i.e., no false positives or
13272 negatives. Furthermore, Mantis is also a colored de Bruijn graph
13273 representation, so it supports fast graph traversal and other topological
13274 analyses in addition to large-scale sequence-level searches.")
13275 ;; uses __uint128_t and inline assembly
13276 (supported-systems '("x86_64-linux"))
13277 (license license:bsd-3))))
13279 (define-public r-diversitree
13281 (name "r-diversitree")
13286 (uri (cran-uri "diversitree" version))
13289 "00vi4klywi35hd170ksjv3xja3hqqbkcidcnrrlpgv4179k0azix"))))
13290 (build-system r-build-system)
13292 `(("gfortran" ,gfortran)))
13293 (inputs `(("fftw" ,fftw) ("gsl" ,gsl)))
13296 ("r-desolve" ,r-desolve)
13298 ("r-subplex" ,r-subplex)))
13299 (home-page "https://www.zoology.ubc.ca/prog/diversitree")
13300 (synopsis "Comparative 'phylogenetic' analyses of diversification")
13301 (description "This package contains a number of comparative \"phylogenetic\"
13302 methods, mostly focusing on analysing diversification and character evolution.
13303 Contains implementations of \"BiSSE\" (Binary State Speciation and Extinction)
13304 and its unresolved tree extensions, \"MuSSE\" (Multiple State Speciation and
13305 Extinction), \"QuaSSE\", \"GeoSSE\", and \"BiSSE-ness\" Other included methods
13306 include Markov models of discrete and continuous trait evolution and constant
13307 rate speciation and extinction.")
13308 (license license:gpl2+)))
13310 (define-public sjcount
13311 ;; There is no tag for version 3.2, nor is there a release archive.
13312 (let ((commit "292d3917cadb3f6834c81e509c30e61cd7ead6e5")
13316 (version (git-version "3.2" revision commit))
13319 (uri (git-reference
13320 (url "https://github.com/pervouchine/sjcount-full")
13322 (file-name (string-append name "-" version "-checkout"))
13325 "0gdgj35j249f04rqgq8ymcc1xg1vi9kzbajnjqpaq2wpbh8bl234"))))
13326 (build-system gnu-build-system)
13328 `(#:tests? #f ; requires a 1.4G test file
13330 (list (string-append "SAMTOOLS_DIR="
13331 (assoc-ref %build-inputs "samtools")
13334 (modify-phases %standard-phases
13335 (replace 'configure
13336 (lambda* (#:key inputs #:allow-other-keys)
13337 (substitute* "makefile"
13338 (("-I \\$\\{SAMTOOLS_DIR\\}")
13339 (string-append "-I" (assoc-ref inputs "samtools")
13340 "/include/samtools"))
13341 (("-lz ") "-lz -lpthread "))
13344 (lambda* (#:key outputs #:allow-other-keys)
13345 (for-each (lambda (tool)
13347 (string-append (assoc-ref outputs "out")
13349 '("j_count" "b_count" "sjcount"))
13352 `(("samtools" ,samtools-0.1)
13354 (home-page "https://github.com/pervouchine/sjcount-full/")
13355 (synopsis "Annotation-agnostic splice junction counting pipeline")
13356 (description "Sjcount is a utility for fast quantification of splice
13357 junctions in RNA-seq data. It is annotation-agnostic and offset-aware. This
13358 version does count multisplits.")
13359 (license license:gpl3+))))
13361 (define-public minimap2
13368 (uri (string-append "https://github.com/lh3/minimap2/"
13369 "releases/download/v" version "/"
13370 "minimap2-" version ".tar.bz2"))
13373 "0hi7i9pzxhvjj44khzzzj1lrn5gb5837arr4wgln7k1k5n4ci2mn"))))
13374 (build-system gnu-build-system)
13376 `(#:tests? #f ; there are none
13379 (let ((system ,(or (%current-target-system)
13380 (%current-system))))
13382 ((string-prefix? "x86_64" system)
13384 ((or (string-prefix? "armhf" system)
13385 (string-prefix? "aarch64" system))
13387 (else "sse2only=1"))))
13389 (modify-phases %standard-phases
13390 (delete 'configure)
13392 (lambda* (#:key outputs #:allow-other-keys)
13393 (let* ((out (assoc-ref outputs "out"))
13394 (bin (string-append out "/bin"))
13395 (man (string-append out "/share/man/man1")))
13396 (install-file "minimap2" bin)
13398 (install-file "minimap2.1" man))
13402 (home-page "https://lh3.github.io/minimap2/")
13403 (synopsis "Pairwise aligner for genomic and spliced nucleotide sequences")
13404 (description "Minimap2 is a versatile sequence alignment program that
13405 aligns DNA or mRNA sequences against a large reference database. Typical use
13409 @item mapping PacBio or Oxford Nanopore genomic reads to the human genome;
13410 @item finding overlaps between long reads with error rate up to ~15%;
13411 @item splice-aware alignment of PacBio Iso-Seq or Nanopore cDNA or Direct RNA
13412 reads against a reference genome;
13413 @item aligning Illumina single- or paired-end reads;
13414 @item assembly-to-assembly alignment;
13415 @item full-genome alignment between two closely related species with
13416 divergence below ~15%.
13418 (license license:expat)))
13420 (define-public miniasm
13426 (uri (git-reference
13427 (url "https://github.com/lh3/miniasm")
13428 (commit (string-append "v" version))))
13429 (file-name (git-file-name name version))
13432 "04dv5wv8bhsw1imxwyd438bnn9kby7svp44nbcz8lsadzjjci5gs"))))
13433 (build-system gnu-build-system)
13437 `(#:tests? #f ; There are no tests.
13439 (modify-phases %standard-phases
13440 (delete 'configure)
13442 (lambda* (#:key inputs outputs #:allow-other-keys)
13443 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
13444 (install-file "miniasm" bin)
13445 (install-file "minidot" bin)
13447 (home-page "https://github.com/lh3/miniasm")
13448 (synopsis "Ultrafast de novo assembly for long noisy reads")
13449 (description "Miniasm is a very fast OLC-based de novo assembler for noisy
13450 long reads. It takes all-vs-all read self-mappings (typically by minimap) as
13451 input and outputs an assembly graph in the GFA format. Different from
13452 mainstream assemblers, miniasm does not have a consensus step. It simply
13453 concatenates pieces of read sequences to generate the final unitig sequences.
13454 Thus the per-base error rate is similar to the raw input reads.")
13455 (license license:expat)))
13457 (define-public r-circus
13464 (uri (git-reference
13465 (url "https://github.com/BIMSBbioinfo/ciRcus")
13466 (commit (string-append "v" version))))
13467 (file-name (git-file-name name version))
13470 "0jhjn3ilb057hbf6yzrihj13ifxxs32y7nkby8l3lkm28dg4p97h"))))
13471 (build-system r-build-system)
13473 `(("r-annotationdbi" ,r-annotationdbi)
13474 ("r-annotationhub" ,r-annotationhub)
13475 ("r-biomart" ,r-biomart)
13476 ("r-data-table" ,r-data-table)
13478 ("r-genomicfeatures" ,r-genomicfeatures)
13479 ("r-genomicranges" ,r-genomicranges)
13480 ("r-ggplot2" ,r-ggplot2)
13482 ("r-iranges" ,r-iranges)
13483 ("r-rcolorbrewer" ,r-rcolorbrewer)
13484 ("r-rmysql" ,r-rmysql)
13485 ("r-s4vectors" ,r-s4vectors)
13486 ("r-stringr" ,r-stringr)
13487 ("r-summarizedexperiment" ,r-summarizedexperiment)))
13489 `(("r-knitr" ,r-knitr)))
13490 (home-page "https://github.com/BIMSBbioinfo/ciRcus")
13491 (synopsis "Annotation, analysis and visualization of circRNA data")
13492 (description "Circus is an R package for annotation, analysis and
13493 visualization of circRNA data. Users can annotate their circRNA candidates
13494 with host genes, gene featrues they are spliced from, and discriminate between
13495 known and yet unknown splice junctions. Circular-to-linear ratios of circRNAs
13496 can be calculated, and a number of descriptive plots easily generated.")
13497 (license license:artistic2.0)))
13499 (define-public gffread
13500 ;; We cannot use the tagged release because it is not in sync with gclib.
13501 ;; See https://github.com/gpertea/gffread/issues/26
13502 (let ((commit "ba7535fcb3cea55a6e5a491d916e93b454e87fd0")
13506 (version (git-version "0.9.12" revision commit))
13510 (uri (git-reference
13511 (url "https://github.com/gpertea/gffread")
13513 (file-name (git-file-name name version))
13516 "1dl2nbcg96lxpd0drg48ssa8343nf7pw9s9mkrc4mjjmfwsin3ki"))))
13517 (build-system gnu-build-system)
13519 `(#:tests? #f ; no check target
13521 (list "GCLDIR=gclib")
13523 (modify-phases %standard-phases
13524 (delete 'configure)
13525 (add-after 'unpack 'copy-gclib-source
13526 (lambda* (#:key inputs #:allow-other-keys)
13528 (copy-recursively (assoc-ref inputs "gclib-source") "gclib")
13530 ;; There is no install target
13532 (lambda* (#:key outputs #:allow-other-keys)
13533 (let* ((out (assoc-ref outputs "out"))
13534 (bin (string-append out "/bin")))
13535 (install-file "gffread" bin))
13539 ,(let ((version "0.10.3")
13540 (commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13544 (uri (git-reference
13545 (url "https://github.com/gpertea/gclib")
13547 (file-name (git-file-name "gclib" version))
13550 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13551 (home-page "https://github.com/gpertea/gffread/")
13552 (synopsis "Parse and convert GFF/GTF files")
13554 "This package provides a GFF/GTF file parsing utility providing format
13555 conversions, region filtering, FASTA sequence extraction and more.")
13556 ;; gffread is under Expat, but gclib is under Artistic 2.0
13557 (license (list license:expat
13558 license:artistic2.0)))))
13560 (define-public find-circ
13561 ;; The last release was in 2015. The license was clarified in 2017, so we
13562 ;; take the latest commit.
13563 (let ((commit "8655dca54970fcf7e92e22fbf57e1188724dda7d")
13567 (version (git-version "1.2" revision commit))
13571 (uri (git-reference
13572 (url "https://github.com/marvin-jens/find_circ")
13574 (file-name (git-file-name name version))
13577 "0p77pbqbclqr4srms34y1b9b4njybfpjiknc11ki84f3p8skb3cg"))))
13578 (build-system gnu-build-system)
13580 `(#:tests? #f ; there are none
13582 ;; There is no actual build system.
13583 (modify-phases %standard-phases
13584 (delete 'configure)
13587 (lambda* (#:key outputs #:allow-other-keys)
13588 (let* ((out (assoc-ref outputs "out"))
13589 (bin (string-append out "/bin"))
13590 (path (getenv "PYTHONPATH")))
13591 (for-each (lambda (script)
13592 (install-file script bin)
13593 (wrap-program (string-append bin "/" script)
13594 `("PYTHONPATH" ":" prefix (,path))))
13599 "unmapped2anchors.py")))
13602 `(("python2" ,python-2)
13603 ("python2-pysam" ,python2-pysam)
13604 ("python2-numpy" ,python2-numpy)))
13605 (home-page "https://github.com/marvin-jens/find_circ")
13606 (synopsis "circRNA detection from RNA-seq reads")
13607 (description "This package provides tools to detect head-to-tail
13608 spliced (back-spliced) sequencing reads, indicative of circular RNA (circRNA)
13610 (license license:gpl3))))
13612 (define-public python-scanpy
13614 (name "python-scanpy")
13619 (uri (pypi-uri "scanpy" version))
13622 "0s2b6cvaigx4wzw3850qb93sjwwxbzh22kpbp498zklc5rjpbz4l"))))
13623 (build-system python-build-system)
13626 (modify-phases %standard-phases
13628 (lambda* (#:key inputs #:allow-other-keys)
13629 ;; These tests require Internet access.
13630 (delete-file-recursively "scanpy/tests/notebooks")
13631 (delete-file "scanpy/tests/test_clustering.py")
13632 (delete-file "scanpy/tests/test_datasets.py")
13634 ;; TODO: I can't get the plotting tests to work, even with Xvfb.
13635 (delete-file "scanpy/tests/test_plotting.py")
13636 (delete-file "scanpy/tests/test_preprocessing.py")
13637 (delete-file "scanpy/tests/test_read_10x.py")
13639 (setenv "PYTHONPATH"
13640 (string-append (getcwd) ":"
13641 (getenv "PYTHONPATH")))
13645 `(("python-anndata" ,python-anndata)
13646 ("python-h5py" ,python-h5py)
13647 ("python-igraph" ,python-igraph)
13648 ("python-joblib" ,python-joblib)
13649 ("python-legacy-api-wrap" ,python-legacy-api-wrap)
13650 ("python-louvain" ,python-louvain)
13651 ("python-matplotlib" ,python-matplotlib)
13652 ("python-natsort" ,python-natsort)
13653 ("python-networkx" ,python-networkx)
13654 ("python-numba" ,python-numba)
13655 ("python-packaging" ,python-packaging)
13656 ("python-pandas" ,python-pandas)
13657 ("python-patsy" ,python-patsy)
13658 ("python-scikit-learn" ,python-scikit-learn)
13659 ("python-scipy" ,python-scipy)
13660 ("python-seaborn" ,python-seaborn)
13661 ("python-statsmodels" ,python-statsmodels)
13662 ("python-tables" ,python-tables)
13663 ("python-tqdm" ,python-tqdm)
13664 ("python-umap-learn" ,python-umap-learn)))
13666 `(("python-pytest" ,python-pytest)
13667 ("python-setuptools-scm" ,python-setuptools-scm)))
13668 (home-page "https://github.com/theislab/scanpy")
13669 (synopsis "Single-Cell Analysis in Python.")
13670 (description "Scanpy is a scalable toolkit for analyzing single-cell gene
13671 expression data. It includes preprocessing, visualization, clustering,
13672 pseudotime and trajectory inference and differential expression testing. The
13673 Python-based implementation efficiently deals with datasets of more than one
13675 (license license:bsd-3)))
13677 (define-public python-bbknn
13679 (name "python-bbknn")
13684 (uri (pypi-uri "bbknn" version))
13687 "1jbsh01f57zj4bhvjr3jh4532zznqd6nccmgrl3qi9gnhkf7c4y0"))))
13688 (build-system python-build-system)
13690 `(#:tests? #f)) ; TODO: Enable after migration to scikit-learn.
13692 `(("python-annoy" ,python-annoy)
13693 ("python-cython" ,python-cython)
13694 ("python-numpy" ,python-numpy)
13695 ("python-scipy" ,python-scipy)
13696 ("python-umap-learn" ,python-umap-learn)))
13697 (home-page "https://github.com/Teichlab/bbknn")
13698 (synopsis "Batch balanced KNN")
13699 (description "BBKNN is a batch effect removal tool that can be directly
13700 used in the Scanpy workflow. It serves as an alternative to
13701 @code{scanpy.api.pp.neighbors()}, with both functions creating a neighbour
13702 graph for subsequent use in clustering, pseudotime and UMAP visualisation. If
13703 technical artifacts are present in the data, they will make it challenging to
13704 link corresponding cell types across different batches. BBKNN actively
13705 combats this effect by splitting your data into batches and finding a smaller
13706 number of neighbours for each cell within each of the groups. This helps
13707 create connections between analogous cells in different batches without
13708 altering the counts or PCA space.")
13709 (license license:expat)))
13711 (define-public gffcompare
13712 (let ((commit "be56ef4349ea3966c12c6397f85e49e047361c41")
13715 (name "gffcompare")
13716 (version (git-version "0.10.15" revision commit))
13720 (uri (git-reference
13721 (url "https://github.com/gpertea/gffcompare/")
13723 (file-name (git-file-name name version))
13725 (base32 "0cp5qpxdhw4mxpya5dld8wi3jk00zyklm6rcri426wydinrnfmkg"))))
13726 (build-system gnu-build-system)
13728 `(#:tests? #f ; no check target
13730 (modify-phases %standard-phases
13731 (delete 'configure)
13732 (add-before 'build 'copy-gclib-source
13733 (lambda* (#:key inputs #:allow-other-keys)
13736 (assoc-ref inputs "gclib-source") "../gclib")
13739 (lambda* (#:key outputs #:allow-other-keys)
13740 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
13741 (install-file "gffcompare" bin)
13744 `(("gclib-source" ; see 'README.md' of gffcompare
13745 ,(let ((commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13748 (version (git-version "0.10.3" revision commit)))
13751 (uri (git-reference
13752 (url "https://github.com/gpertea/gclib/")
13754 (file-name (git-file-name name version))
13756 (base32 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13757 (home-page "https://github.com/gpertea/gffcompare/")
13758 (synopsis "Tool for comparing or classifing transcripts of RNA-Seq")
13760 "@code{gffcompare} is a tool that can:
13762 @item compare and evaluate the accuracy of RNA-Seq transcript assemblers
13763 (Cufflinks, Stringtie);
13764 @item collapse (merge) duplicate transcripts from multiple GTF/GFF3 files (e.g.
13765 resulted from assembly of different samples);
13766 @item classify transcripts from one or multiple GTF/GFF3 files as they relate to
13767 reference transcripts provided in a annotation file (also in GTF/GFF3 format).
13771 license:expat ;license for gffcompare
13772 license:artistic2.0))))) ;license for gclib
13774 (define-public intervaltree
13775 (let ((commit "b90527f9e6d51cd36ecbb50429e4524d3a418ea5"))
13777 (name "intervaltree")
13778 (version (git-version "0.0.0" "1" commit))
13782 (uri (git-reference
13783 (url "https://github.com/ekg/intervaltree/")
13785 (file-name (git-file-name name version))
13787 (base32 "0rgv6q5fl4x5d74n6p5wvdna6zmbdbqpb4jqqh6vq3670gn08xad"))))
13788 (build-system gnu-build-system)
13790 '(#:tests? #f ; No tests.
13791 #:make-flags (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
13794 (modify-phases %standard-phases
13795 (delete 'configure)))) ; There is no configure phase.
13796 (home-page "https://github.com/ekg/intervaltree")
13797 (synopsis "Minimal C++ interval tree implementation")
13798 (description "An interval tree can be used to efficiently find a set of
13799 numeric intervals overlapping or containing another interval. This library
13800 provides a basic implementation of an interval tree using C++ templates,
13801 allowing the insertion of arbitrary types into the tree.")
13802 (license license:expat))))
13804 (define-public python-intervaltree
13806 (name "python-intervaltree")
13811 (uri (pypi-uri "intervaltree" version))
13814 "0wz234g6irlm4hivs2qzmnywk0ss06ckagwh15nflkyb3p462kyb"))))
13815 (build-system python-build-system)
13818 (modify-phases %standard-phases
13819 ;; pytest seems to have a check to make sure the user is testing
13820 ;; their checked-out code and not an installed, potentially
13821 ;; out-of-date copy. This is harmless here, since we just installed
13822 ;; the package, so we disable the check to avoid skipping tests
13824 (add-before 'check 'import-mismatch-error-workaround
13826 (setenv "PY_IGNORE_IMPORTMISMATCH" "1")
13829 `(("python-sortedcontainers" ,python-sortedcontainers)))
13831 `(("python-pytest" ,python-pytest)))
13832 (home-page "https://github.com/chaimleib/intervaltree")
13833 (synopsis "Editable interval tree data structure")
13835 "This package provides a mutable, self-balancing interval tree
13836 implementation for Python. Queries may be by point, by range overlap, or by
13837 range envelopment. This library was designed to allow tagging text and time
13838 intervals, where the intervals include the lower bound but not the upper
13840 (license license:asl2.0)))
13842 (define-public python-pypairix
13844 (name "python-pypairix")
13846 ;; The tarball on pypi does not include the makefile to build the
13851 (uri (git-reference
13852 (url "https://github.com/4dn-dcic/pairix")
13854 (file-name (git-file-name name version))
13857 "1snr3lrmsld8sy77ng6ba6wcmd33xjccf1l2f3m6pi29xis9nd6p"))))
13858 (build-system python-build-system)
13861 (modify-phases %standard-phases
13862 (add-before 'build 'build-programs
13863 (lambda _ (invoke "make")))
13864 (add-after 'install 'install-programs
13865 (lambda* (#:key outputs #:allow-other-keys)
13866 (copy-recursively "bin" (string-append
13867 (assoc-ref outputs "out")
13872 (home-page "https://github.com/4dn-dcic/pairix")
13873 (synopsis "Support for querying pairix-indexed bgzipped text files")
13875 "Pypairix is a Python module for fast querying on a pairix-indexed
13876 bgzipped text file that contains a pair of genomic coordinates per line.")
13877 (license license:expat)))
13879 (define-public python-pyfaidx
13881 (name "python-pyfaidx")
13886 (uri (pypi-uri "pyfaidx" version))
13889 "038xi3a6zvrxbyyfpp64ka8pcjgsdq4fgw9cl5lpxbvmm1bzzw2q"))))
13890 (build-system python-build-system)
13892 `(("python-six" ,python-six)))
13893 (home-page "http://mattshirley.com")
13894 (synopsis "Random access to fasta subsequences")
13896 "This package provides procedures for efficient pythonic random access to
13897 fasta subsequences.")
13898 (license license:bsd-3)))
13900 (define-public python2-pyfaidx
13901 (package-with-python2 python-pyfaidx))
13903 (define-public python-cooler
13905 (name "python-cooler")
13910 (uri (pypi-uri "cooler" version))
13913 "01g6gqix9ba27sappz6nfyiwabzrlf8i5fn8kwcz8ra356cq9crp"))))
13914 (build-system python-build-system)
13916 `(("python-asciitree" ,python-asciitree)
13917 ("python-biopython" ,python-biopython)
13918 ("python-click" ,python-click)
13919 ("python-cytoolz" ,python-cytoolz)
13920 ("python-dask" ,python-dask)
13921 ("python-h5py" ,python-h5py)
13922 ("python-multiprocess" ,python-multiprocess)
13923 ("python-numpy" ,python-numpy)
13924 ("python-pandas" ,python-pandas)
13925 ("python-pyfaidx" ,python-pyfaidx)
13926 ("python-pypairix" ,python-pypairix)
13927 ("python-pysam" ,python-pysam)
13928 ("python-pyyaml" ,python-pyyaml)
13929 ("python-scipy" ,python-scipy)
13930 ("python-simplejson" ,python-simplejson)))
13932 `(("python-mock" ,python-mock)
13933 ("python-pytest" ,python-pytest)))
13934 (home-page "https://github.com/mirnylab/cooler")
13935 (synopsis "Sparse binary format for genomic interaction matrices")
13937 "Cooler is a support library for a sparse, compressed, binary persistent
13938 storage format, called @code{cool}, used to store genomic interaction data,
13939 such as Hi-C contact matrices.")
13940 (license license:bsd-3)))
13942 (define-public python-hicmatrix
13944 (name "python-hicmatrix")
13948 ;; Version 12 is not available on pypi.
13950 (uri (git-reference
13951 (url "https://github.com/deeptools/HiCMatrix")
13953 (file-name (git-file-name name version))
13956 "1xhdyx16f3brgxgxybixdi64ki8nbbkq5vk4h9ahi11pzpjfn1pj"))))
13957 (build-system python-build-system)
13960 (modify-phases %standard-phases
13961 (add-after 'unpack 'relax-requirements
13963 (substitute* '("requirements.txt"
13965 (("cooler *=+ *0.8.5")
13969 `(("python-cooler" ,python-cooler)
13970 ("python-intervaltree" ,python-intervaltree)
13971 ("python-numpy" ,python-numpy)
13972 ("python-pandas" ,python-pandas)
13973 ("python-scipy" ,python-scipy)
13974 ("python-tables" ,python-tables)))
13975 (home-page "https://github.com/deeptools/HiCMatrix/")
13976 (synopsis "HiCMatrix class for HiCExplorer and pyGenomeTracks")
13978 "This helper package implements the @code{HiCMatrix} class for
13979 the HiCExplorer and pyGenomeTracks packages.")
13980 (license license:gpl3+)))
13982 (define-public python-hicexplorer
13984 (name "python-hicexplorer")
13988 ;; The latest version is not available on Pypi.
13990 (uri (git-reference
13991 (url "https://github.com/deeptools/HiCExplorer")
13993 (file-name (git-file-name name version))
13996 "0q5gpbzmrkvygqgw524q36b4nrivcmyi5v194vsx0qw7b3gcmq08"))))
13997 (build-system python-build-system)
14000 (modify-phases %standard-phases
14001 (add-after 'unpack 'loosen-up-requirements
14003 (substitute* "setup.py"
14007 `(("python-biopython" ,python-biopython)
14008 ("python-configparser" ,python-configparser)
14009 ("python-cooler" ,python-cooler)
14010 ("python-future" ,python-future)
14011 ("python-intervaltree" ,python-intervaltree)
14012 ("python-jinja2" ,python-jinja2)
14013 ("python-matplotlib" ,python-matplotlib)
14014 ("python-numpy" ,python-numpy)
14015 ("python-pandas" ,python-pandas)
14016 ("python-pybigwig" ,python-pybigwig)
14017 ("python-pysam" ,python-pysam)
14018 ("python-scipy" ,python-scipy)
14019 ("python-six" ,python-six)
14020 ("python-tables" ,python-tables)
14021 ("python-unidecode" ,python-unidecode)))
14022 (home-page "https://hicexplorer.readthedocs.io")
14023 (synopsis "Process, analyze and visualize Hi-C data")
14025 "HiCExplorer is a powerful and easy to use set of tools to process,
14026 normalize and visualize Hi-C data. HiCExplorer facilitates the creation of
14027 contact matrices, correction of contacts, TAD detection, A/B compartments,
14028 merging, reordering or chromosomes, conversion from different formats
14029 including cooler and detection of long-range contacts. Moreover, it allows
14030 the visualization of multiple contact matrices along with other types of data
14031 like genes, compartments, ChIP-seq coverage tracks (and in general any type of
14032 genomic scores), long range contacts and the visualization of viewpoints.")
14033 (license license:gpl3)))
14035 (define-public python-pygenometracks
14037 (name "python-pygenometracks")
14042 (uri (pypi-uri "pyGenomeTracks" version))
14045 "16laa0wnf4qn9fb9ych4w1vqhqwjss70v0y0f6wp4gwqfrlgac0f"))))
14046 (build-system python-build-system)
14048 `(#:tests? #f ; there are none
14050 (modify-phases %standard-phases
14051 (add-after 'unpack 'relax-requirements
14053 (substitute* "setup.py"
14054 (("matplotlib ==3.1.1")
14055 "matplotlib >=3.1.1"))
14058 `(("python-future" ,python-future)
14059 ("python-gffutils" ,python-gffutils)
14060 ("python-hicmatrix" ,python-hicmatrix)
14061 ("python-intervaltree" ,python-intervaltree)
14062 ("python-matplotlib" ,python-matplotlib)
14063 ("python-numpy" ,python-numpy)
14064 ("python-pybigwig" ,python-pybigwig)
14065 ("python-pysam" ,python-pysam)
14066 ("python-tqdm" ,python-tqdm)))
14068 `(("python-pytest" ,python-pytest)))
14069 (home-page "https://pygenometracks.readthedocs.io")
14070 (synopsis "Program and library to plot beautiful genome browser tracks")
14072 "This package aims to produce high-quality genome browser tracks that
14073 are highly customizable. Currently, it is possible to plot: bigwig, bed (many
14074 options), bedgraph, links (represented as arcs), and Hi-C matrices.
14075 pyGenomeTracks can make plots with or without Hi-C data.")
14076 (license license:gpl3+)))
14078 (define-public python-hic2cool
14080 (name "python-hic2cool")
14085 (uri (pypi-uri "hic2cool" version))
14088 "0xy6mhfns2lzib1kcr6419jjp6pmh0qx8z8na55lmiwn0ds8q9cl"))))
14089 (build-system python-build-system)
14090 (arguments '(#:tests? #f)) ; no tests included
14092 `(("python-cooler" ,python-cooler)))
14093 (home-page "https://github.com/4dn-dcic/hic2cool")
14094 (synopsis "Converter for .hic and .cool files")
14096 "This package provides a converter between @code{.hic} files (from
14097 juicer) and single-resolution or multi-resolution @code{.cool} files (for
14098 cooler). Both @code{hic} and @code{cool} files describe Hi-C contact
14100 (license license:expat)))
14102 (define-public r-pore
14110 (string-append "mirror://sourceforge/rpore/" version
14111 "/poRe_" version ".tar.gz"))
14113 (base32 "0pih9nljbv8g4x8rkk29i7aqq681b782r5s5ynp4nw9yzqnmmksv"))))
14114 (properties `((upstream-name . "poRe")))
14115 (build-system r-build-system)
14117 `(("r-bit64" ,r-bit64)
14118 ("r-data-table" ,r-data-table)
14119 ("r-rhdf5" ,r-rhdf5)
14120 ("r-shiny" ,r-shiny)
14121 ("r-svdialogs" ,r-svdialogs)))
14122 (home-page "https://sourceforge.net/projects/rpore/")
14123 (synopsis "Visualize Nanopore sequencing data")
14125 "This package provides graphical user interfaces to organize and visualize Nanopore
14127 ;; This is free software but the license variant is unclear:
14128 ;; <https://github.com/mw55309/poRe_docs/issues/10>.
14129 (license license:bsd-3)))
14131 (define-public r-xbioc
14132 (let ((revision "1")
14133 (commit "6ff0670a37ab3036aaf1d94aa4b208310946b0b5"))
14136 (version (git-version "0.1.16" revision commit))
14139 (uri (git-reference
14140 (url "https://github.com/renozao/xbioc")
14142 (file-name (git-file-name name version))
14145 "0w8bsq5myiwkfhh83nm6is5ichiyvwa1axx2szvxnzq39x6knf66"))))
14146 (build-system r-build-system)
14148 `(("r-annotationdbi" ,r-annotationdbi)
14149 ("r-assertthat" ,r-assertthat)
14150 ("r-biobase" ,r-biobase)
14151 ("r-biocmanager" ,r-biocmanager)
14152 ("r-digest" ,r-digest)
14153 ("r-pkgmaker" ,r-pkgmaker)
14155 ("r-reshape2" ,r-reshape2)
14156 ("r-stringr" ,r-stringr)))
14157 (home-page "https://github.com/renozao/xbioc/")
14158 (synopsis "Extra base functions for Bioconductor")
14159 (description "This package provides extra utility functions to perform
14160 common tasks in the analysis of omics data, leveraging and enhancing features
14161 provided by Bioconductor packages.")
14162 (license license:gpl3+))))
14164 (define-public r-cssam
14165 (let ((revision "1")
14166 (commit "9ec58c982fa551af0d80b1a266890d92954833f2"))
14169 (version (git-version "1.4" revision commit))
14172 (uri (git-reference
14173 (url "https://github.com/shenorrLab/csSAM")
14175 (file-name (git-file-name name version))
14178 "128syf9v39gk0z3ip000qpsjbg6l1siyq6c8b0hz41dzg5achyb3"))))
14179 (build-system r-build-system)
14181 `(("r-formula" ,r-formula)
14182 ("r-ggplot2" ,r-ggplot2)
14183 ("r-pkgmaker" ,r-pkgmaker)
14185 ("r-rngtools" ,r-rngtools)
14186 ("r-scales" ,r-scales)))
14187 (home-page "https://github.com/shenorrLab/csSAM/")
14188 (synopsis "Cell type-specific statistical analysis of microarray")
14189 (description "This package implements the method csSAM that computes
14190 cell-specific differential expression from measured cell proportions using
14193 (license license:lgpl2.1+))))
14195 (define-public r-bseqsc
14196 (let ((revision "1")
14197 (commit "fef3f3e38dcf3df37103348b5780937982b43b98"))
14200 (version (git-version "1.0" revision commit))
14203 (uri (git-reference
14204 (url "https://github.com/shenorrLab/bseqsc")
14206 (file-name (git-file-name name version))
14209 "1prw13wa20f7wlc3gkkls66n1kxz8d28qrb8icfqdwdnnv8w5qg8"))))
14210 (build-system r-build-system)
14212 `(("r-abind" ,r-abind)
14213 ("r-annotationdbi" ,r-annotationdbi)
14214 ("r-biobase" ,r-biobase)
14215 ("r-cssam" ,r-cssam)
14216 ("r-dplyr" ,r-dplyr)
14217 ("r-e1071" ,r-e1071)
14218 ("r-edger" ,r-edger)
14219 ("r-ggplot2" ,r-ggplot2)
14221 ("r-openxlsx" ,r-openxlsx)
14222 ("r-pkgmaker" ,r-pkgmaker)
14224 ("r-preprocesscore" ,r-preprocesscore)
14225 ("r-rngtools" ,r-rngtools)
14226 ("r-scales" ,r-scales)
14227 ("r-stringr" ,r-stringr)
14228 ("r-xbioc" ,r-xbioc)))
14229 (home-page "https://github.com/shenorrLab/bseqsc")
14230 (synopsis "Deconvolution of bulk sequencing experiments using single cell data")
14231 (description "BSeq-sc is a bioinformatics analysis pipeline that
14232 leverages single-cell sequencing data to estimate cell type proportion and
14233 cell type-specific gene expression differences from RNA-seq data from bulk
14234 tissue samples. This is a companion package to the publication \"A
14235 single-cell transcriptomic map of the human and mouse pancreas reveals inter-
14236 and intra-cell population structure.\" Baron et al. Cell Systems (2016)
14237 @url{https://www.ncbi.nlm.nih.gov/pubmed/27667365}.")
14238 (license license:gpl2+))))
14240 (define-public porechop
14241 ;; The recommended way to install is to clone the git repository
14242 ;; https://github.com/rrwick/Porechop#installation
14243 (let ((commit "289d5dca4a5fc327f97b3f8cecb68ecaf1014861")
14247 (version (git-version "0.2.3" revision commit))
14251 (uri (git-reference
14252 (url "https://github.com/rrwick/Porechop")
14254 (file-name (git-file-name name version))
14256 (base32 "05ps43gig0d3ia9x5lj84lb00hbsl6ba9n7y7jz927npxbr2ym23"))))
14257 (build-system python-build-system)
14258 (home-page "https://github.com/rrwick/porechop")
14259 (synopsis "Finding, trimming or splitting adapters, in Oxford Nanopore reads")
14261 "The porechop package is a tool for finding and removing adapters from Oxford
14262 Nanopore reads. Adapters on the ends of reads are trimmed off, and when a read
14263 has an adapter in its middle, it is treated as chimeric and chopped into
14264 separate reads. Porechop performs thorough alignments to effectively find
14265 adapters, even at low sequence identity. Porechop also supports demultiplexing
14266 of Nanopore reads that were barcoded with the Native Barcoding Kit, PCR
14267 Barcoding Kit or Rapid Barcoding Kit.")
14268 (license license:gpl3+))))
14270 (define-public poretools
14271 ;; The latest release was in 2016 and the latest commit is from 2017
14272 ;; the recommended way to install is to clone the git repository
14273 ;; https://poretools.readthedocs.io/en/latest/content/installation.html
14274 (let ((commit "e426b1f09e86ac259a00c261c79df91510777407")
14278 (version (git-version "0.6.0" revision commit))
14282 (uri (git-reference
14283 (url "https://github.com/arq5x/poretools")
14285 (file-name (git-file-name name version))
14287 (base32 "0bglj833wxpp3cq430p1d3xp085ls221js2y90w7ir2x5ay8l7am"))))
14288 (build-system python-build-system)
14289 ;; requires python >=2.7, <3.0, and the same for python dependencies
14290 (arguments `(#:python ,python-2))
14294 `(("python-dateutil" ,python2-dateutil)
14295 ("python-h5py" ,python2-h5py)
14296 ("python-matplotlib" ,python2-matplotlib)
14297 ("python-pandas" ,python2-pandas)
14298 ("python-seaborn" ,python2-seaborn)))
14299 (home-page "https://poretools.readthedocs.io")
14300 (synopsis "Toolkit for working with nanopore sequencing data")
14302 "The MinION from Oxford Nanopore Technologies is a nanopore sequencer.
14303 This @code{poretools} package is a flexible toolkit for exploring datasets
14304 generated by nanopore sequencing devices for the purposes of quality control and
14305 downstream analysis. Poretools operates directly on the native FAST5, a variant
14306 of the Hierarchical Data Format (HDF5) standard.")
14307 (license license:expat))))
14309 (define-public r-absfiltergsea
14311 (name "r-absfiltergsea")
14316 (uri (cran-uri "AbsFilterGSEA" version))
14318 (base32 "15srxkxsvn38kd5frdrwfdf0ad8gskrd0h01wmdf9hglq8fjrp7w"))))
14319 (properties `((upstream-name . "AbsFilterGSEA")))
14320 (build-system r-build-system)
14322 `(("r-biobase" ,r-biobase)
14323 ("r-deseq" ,r-deseq)
14324 ("r-limma" ,r-limma)
14326 ("r-rcpparmadillo" ,r-rcpparmadillo)))
14327 (home-page "https://cran.r-project.org/web/packages/AbsFilterGSEA/")
14328 (synopsis "Improved false positive control of gene-permuting with absolute filtering")
14330 "This package provides a function that performs gene-permuting of a gene-set
14331 enrichment analysis (GSEA) calculation with or without the absolute filtering.
14332 Without filtering, users can perform (original) two-tailed or one-tailed
14334 (license license:gpl2)))
14336 (define-public jamm
14339 (version "1.0.7.6")
14343 (uri (git-reference
14344 (url "https://github.com/mahmoudibrahim/JAMM")
14345 (commit (string-append "JAMMv" version))))
14346 (file-name (git-file-name name version))
14349 "0bsa5mf9n9q5jz7mmacrra41l7r8rac5vgsn6wv1fb52ya58b970"))))
14350 (build-system gnu-build-system)
14352 `(#:tests? #f ; there are none
14354 (modify-phases %standard-phases
14355 (delete 'configure)
14358 (lambda* (#:key inputs outputs #:allow-other-keys)
14359 (let* ((out (assoc-ref outputs "out"))
14360 (libexec (string-append out "/libexec/jamm"))
14361 (bin (string-append out "/bin")))
14362 (substitute* '("JAMM.sh"
14363 "SignalGenerator.sh")
14365 (string-append "sPath=\"" libexec "\"\n")))
14366 (for-each (lambda (file)
14367 (install-file file libexec))
14368 (list "bincalculator.r"
14380 (chmod script #o555)
14381 (install-file script bin)
14382 (wrap-program (string-append bin "/" script)
14383 `("PATH" ":" prefix
14384 (,(string-append (assoc-ref inputs "coreutils") "/bin")
14385 ,(string-append (assoc-ref inputs "gawk") "/bin")
14386 ,(string-append (assoc-ref inputs "perl") "/bin")
14387 ,(string-append (assoc-ref inputs "r-minimal") "/bin")))
14388 `("PERL5LIB" ":" prefix (,(getenv "PERL5LIB")))
14389 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
14390 (list "JAMM.sh" "SignalGenerator.sh")))
14394 ("coreutils" ,coreutils)
14397 ("r-minimal" ,r-minimal)
14398 ;;("r-parallel" ,r-parallel)
14399 ("r-signal" ,r-signal)
14400 ("r-mclust" ,r-mclust)))
14401 (home-page "https://github.com/mahmoudibrahim/JAMM")
14402 (synopsis "Peak finder for NGS datasets")
14404 "JAMM is a peak finder for next generation sequencing datasets (ChIP-Seq,
14405 ATAC-Seq, DNase-Seq, etc.) that can integrate replicates and assign peak
14406 boundaries accurately. JAMM is applicable to both broad and narrow
14408 (license license:gpl3+)))
14410 (define-public ngless
14417 (uri (git-reference
14418 (url "https://gitlab.com/ngless/ngless.git")
14419 (commit (string-append "v" version))))
14420 (file-name (git-file-name name version))
14423 "1wim8wpqyff080dfcazynrmjwqas38m24m0v350w245mmhrapdma"))))
14424 (build-system haskell-build-system)
14426 `(#:haddock? #f ; The haddock phase fails with: NGLess/CmdArgs.hs:20:1:
14427 ; error: parse error on input import
14428 ; import Options.Applicative
14430 (modify-phases %standard-phases
14431 (add-after 'unpack 'create-Versions.hs
14433 (substitute* "Makefile"
14434 (("BWA_VERSION = .*")
14435 (string-append "BWA_VERSION = "
14436 ,(package-version bwa) "\n"))
14437 (("SAM_VERSION = .*")
14438 (string-append "SAM_VERSION = "
14439 ,(package-version samtools) "\n"))
14440 (("PRODIGAL_VERSION = .*")
14441 (string-append "PRODIGAL_VERSION = "
14442 ,(package-version prodigal) "\n"))
14443 (("MINIMAP2_VERSION = .*")
14444 (string-append "MINIMAP2_VERSION = "
14445 ,(package-version minimap2) "\n")))
14446 (invoke "make" "NGLess/Dependencies/Versions.hs")
14448 (add-after 'create-Versions.hs 'create-cabal-file
14449 (lambda _ (invoke "hpack") #t))
14450 ;; These tools are expected to be installed alongside ngless.
14451 (add-after 'install 'link-tools
14452 (lambda* (#:key inputs outputs #:allow-other-keys)
14453 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
14454 (symlink (string-append (assoc-ref inputs "prodigal")
14456 (string-append bin "ngless-" ,version "-prodigal"))
14457 (symlink (string-append (assoc-ref inputs "minimap2")
14459 (string-append bin "ngless-" ,version "-minimap2"))
14460 (symlink (string-append (assoc-ref inputs "samtools")
14462 (string-append bin "ngless-" ,version "-samtools"))
14463 (symlink (string-append (assoc-ref inputs "bwa")
14465 (string-append bin "ngless-" ,version "-bwa"))
14468 `(("prodigal" ,prodigal)
14470 ("samtools" ,samtools)
14471 ("minimap2" ,minimap2)
14472 ("ghc-aeson" ,ghc-aeson)
14473 ("ghc-ansi-terminal" ,ghc-ansi-terminal)
14474 ("ghc-async" ,ghc-async)
14475 ("ghc-atomic-write" ,ghc-atomic-write)
14476 ("ghc-bytestring-lexing" ,ghc-bytestring-lexing)
14477 ("ghc-conduit" ,ghc-conduit)
14478 ("ghc-conduit-algorithms" ,ghc-conduit-algorithms)
14479 ("ghc-conduit-extra" ,ghc-conduit-extra)
14480 ("ghc-configurator" ,ghc-configurator)
14481 ("ghc-convertible" ,ghc-convertible)
14482 ("ghc-data-default" ,ghc-data-default)
14483 ("ghc-diagrams-core" ,ghc-diagrams-core)
14484 ("ghc-diagrams-lib" ,ghc-diagrams-lib)
14485 ("ghc-diagrams-svg" ,ghc-diagrams-svg)
14486 ("ghc-double-conversion" ,ghc-double-conversion)
14487 ("ghc-edit-distance" ,ghc-edit-distance)
14488 ("ghc-either" ,ghc-either)
14489 ("ghc-errors" ,ghc-errors)
14490 ("ghc-extra" ,ghc-extra)
14491 ("ghc-filemanip" ,ghc-filemanip)
14492 ("ghc-file-embed" ,ghc-file-embed)
14493 ("ghc-gitrev" ,ghc-gitrev)
14494 ("ghc-hashtables" ,ghc-hashtables)
14495 ("ghc-http-conduit" ,ghc-http-conduit)
14496 ("ghc-inline-c" ,ghc-inline-c)
14497 ("ghc-inline-c-cpp" ,ghc-inline-c-cpp)
14498 ("ghc-intervalmap" ,ghc-intervalmap)
14499 ("ghc-missingh" ,ghc-missingh)
14500 ("ghc-optparse-applicative" ,ghc-optparse-applicative)
14501 ("ghc-regex" ,ghc-regex)
14502 ("ghc-safe" ,ghc-safe)
14503 ("ghc-safeio" ,ghc-safeio)
14504 ("ghc-strict" ,ghc-strict)
14505 ("ghc-tar" ,ghc-tar)
14506 ("ghc-tar-conduit" ,ghc-tar-conduit)
14507 ("ghc-unliftio" ,ghc-unliftio)
14508 ("ghc-unliftio-core" ,ghc-unliftio-core)
14509 ("ghc-vector" ,ghc-vector)
14510 ("ghc-yaml" ,ghc-yaml)
14511 ("ghc-zlib" ,ghc-zlib)))
14514 ("r-hdf5r" ,r-hdf5r)
14515 ("r-iterators" ,r-iterators)
14516 ("r-itertools" ,r-itertools)
14517 ("r-matrix" ,r-matrix)))
14519 `(("ghc-hpack" ,ghc-hpack)
14520 ("ghc-quickcheck" ,ghc-quickcheck)
14521 ("ghc-test-framework" ,ghc-test-framework)
14522 ("ghc-test-framework-hunit",ghc-test-framework-hunit)
14523 ("ghc-test-framework-quickcheck2" ,ghc-test-framework-quickcheck2)
14524 ("ghc-test-framework-th" ,ghc-test-framework-th)))
14525 (home-page "https://gitlab.com/ngless/ngless")
14526 (synopsis "DSL for processing next-generation sequencing data")
14527 (description "Ngless is a domain-specific language for
14528 @dfn{next-generation sequencing} (NGS) data processing.")
14529 (license license:expat)))
14531 (define-public filtlong
14532 ;; The recommended way to install is to clone the git repository
14533 ;; https://github.com/rrwick/Filtlong#installation
14534 ;; and the lastest release is more than nine months old
14535 (let ((commit "d1bb46dfe8bc7efe6257b5ce222c04bfe8aedaab")
14539 (version (git-version "0.2.0" revision commit))
14543 (uri (git-reference
14544 (url "https://github.com/rrwick/Filtlong")
14546 (file-name (git-file-name name version))
14548 (base32 "1xr92r820x8qlkcr3b57iw223yq8vjgyi42jr79w2xgw47qzr575"))))
14549 (build-system gnu-build-system)
14551 `(#:tests? #f ; no check target
14553 (modify-phases %standard-phases
14554 (delete 'configure)
14556 (lambda* (#:key outputs #:allow-other-keys)
14557 (let* ((out (assoc-ref outputs "out"))
14558 (bin (string-append out "/bin"))
14559 (scripts (string-append out "/share/filtlong/scripts")))
14560 (install-file "bin/filtlong" bin)
14561 (install-file "scripts/histogram.py" scripts)
14562 (install-file "scripts/read_info_histograms.sh" scripts))
14564 (add-after 'install 'wrap-program
14565 (lambda* (#:key inputs outputs #:allow-other-keys)
14566 (let* ((out (assoc-ref outputs "out"))
14567 (path (getenv "PYTHONPATH")))
14568 (wrap-program (string-append out
14569 "/share/filtlong/scripts/histogram.py")
14570 `("PYTHONPATH" ":" prefix (,path))))
14572 (add-before 'check 'patch-tests
14574 (substitute* "scripts/read_info_histograms.sh"
14575 (("awk") (which "gawk")))
14578 `(("gawk" ,gawk) ;for read_info_histograms.sh
14579 ("python" ,python-2) ;required for histogram.py
14581 (home-page "https://github.com/rrwick/Filtlong/")
14582 (synopsis "Tool for quality filtering of Nanopore and PacBio data")
14584 "The Filtlong package is a tool for filtering long reads by quality.
14585 It can take a set of long reads and produce a smaller, better subset. It uses
14586 both read length (longer is better) and read identity (higher is better) when
14587 choosing which reads pass the filter.")
14588 (license (list license:gpl3 ;filtlong
14589 license:asl2.0))))) ;histogram.py
14591 (define-public nanopolish
14592 ;; The recommended way to install is to clone the git repository
14593 ;; <https://github.com/jts/nanopolish#installing-a-particular-release>.
14594 ;; Also, the differences between release and current version seem to be
14596 (let ((commit "6331dc4f15b9dfabb954ba3fae9d76b6c3ca6377")
14599 (name "nanopolish")
14600 (version (git-version "0.11.1" revision commit))
14604 (uri (git-reference
14605 (url "https://github.com/jts/nanopolish")
14608 (file-name (git-file-name name version))
14610 (base32 "15ikl3d37y49pwd7vx36xksgsqajhf24q7qqsnpl15dqqyy5qgbc"))
14611 (modules '((guix build utils)))
14614 (delete-file-recursively "htslib")
14616 (build-system gnu-build-system)
14619 `("HDF5=noinstall" "EIGEN=noinstall" "HTS=noinstall" "CC=gcc")
14620 #:tests? #f ; no check target
14622 (modify-phases %standard-phases
14623 (add-after 'unpack 'find-eigen
14624 (lambda* (#:key inputs #:allow-other-keys)
14626 (string-append (assoc-ref inputs "eigen")
14628 (or (getenv "CPATH") "")))
14630 (delete 'configure)
14632 (lambda* (#:key outputs #:allow-other-keys)
14633 (let* ((out (assoc-ref outputs "out"))
14634 (bin (string-append out "/bin"))
14635 (scripts (string-append out "/share/nanopolish/scripts")))
14637 (install-file "nanopolish" bin)
14638 (for-each (lambda (file) (install-file file scripts))
14639 (find-files "scripts" ".*"))
14641 (add-after 'install 'wrap-programs
14642 (lambda* (#:key outputs #:allow-other-keys)
14643 (for-each (lambda (file)
14644 (wrap-program file `("PYTHONPATH" ":" prefix (,path))))
14645 (find-files "/share/nanopolish/scripts" "\\.py"))
14646 (for-each (lambda (file)
14647 (wrap-program file `("PERL5LIB" ":" prefix (,path))))
14648 (find-files "/share/nanopolish/scripts" "\\.pl"))
14655 ("python" ,python-wrapper)
14656 ("python-biopython" ,python-biopython)
14657 ("python-numpy" ,python-numpy)
14658 ("python-pysam" ,python-pysam)
14659 ("python-scikit-learn" , python-scikit-learn)
14660 ("python-scipy" ,python-scipy)
14662 (home-page "https://github.com/jts/nanopolish")
14663 (synopsis "Signal-level analysis of Oxford Nanopore sequencing data")
14665 "This package analyses the Oxford Nanopore sequencing data at signal-level.
14666 Nanopolish can calculate an improved consensus sequence for a draft genome
14667 assembly, detect base modifications, call SNPs (Single nucleotide
14668 polymorphisms) and indels with respect to a reference genome and more.")
14669 (license license:expat))))
14671 (define-public cnvkit
14678 (uri (git-reference
14679 (url "https://github.com/etal/cnvkit")
14680 (commit (string-append "v" version))))
14681 (file-name (git-file-name name version))
14683 (base32 "0g2f78k68yglmj4fsfmgs8idqv3di9aj53fg0ld0hqljg8chhh82"))))
14684 (build-system python-build-system)
14686 `(("python-biopython" ,python-biopython)
14687 ("python-future" ,python-future)
14688 ("python-matplotlib" ,python-matplotlib)
14689 ("python-numpy" ,python-numpy)
14690 ("python-reportlab" ,python-reportlab)
14691 ("python-pandas" ,python-pandas)
14692 ("python-pysam" ,python-pysam)
14693 ("python-pyfaidx" ,python-pyfaidx)
14694 ("python-scipy" ,python-scipy)
14696 ("r-dnacopy" ,r-dnacopy)))
14697 (home-page "https://cnvkit.readthedocs.org/")
14698 (synopsis "Copy number variant detection from targeted DNA sequencing")
14700 "CNVkit is a Python library and command-line software toolkit to infer
14701 and visualize copy number from high-throughput DNA sequencing data. It is
14702 designed for use with hybrid capture, including both whole-exome and custom
14703 target panels, and short-read sequencing platforms such as Illumina and Ion
14705 (license license:asl2.0)))
14707 (define-public python-pyfit-sne
14709 (name "python-pyfit-sne")
14714 (uri (git-reference
14715 (url "https://github.com/KlugerLab/pyFIt-SNE")
14717 (file-name (git-file-name name version))
14719 (base32 "13wh3qkzs56azmmgnxib6xfr29g7xh09sxylzjpni5j0pp0rc5qw"))))
14720 (build-system python-build-system)
14722 `(("python-numpy" ,python-numpy)))
14726 `(("python-cython" ,python-cython)))
14727 (home-page "https://github.com/KlugerLab/pyFIt-SNE")
14728 (synopsis "FFT-accelerated Interpolation-based t-SNE")
14730 "t-Stochastic Neighborhood Embedding (t-SNE) is a highly successful
14731 method for dimensionality reduction and visualization of high dimensional
14732 datasets. A popular implementation of t-SNE uses the Barnes-Hut algorithm to
14733 approximate the gradient at each iteration of gradient descent. This package
14734 is a Cython wrapper for FIt-SNE.")
14735 (license license:bsd-4)))
14737 (define-public bbmap
14743 (uri (string-append
14744 "mirror://sourceforge/bbmap/BBMap_" version ".tar.gz"))
14747 "1q4rfhxcb6z3gm8zg2davjz98w22lkf4hm9ikxz9kdl93pil3wkd"))))
14748 (build-system ant-build-system)
14750 `(#:build-target "dist"
14751 #:tests? #f ; there are none
14753 (list (string-append "-Dmpijar="
14754 (assoc-ref %build-inputs "java-openmpi")
14756 #:modules ((guix build ant-build-system)
14758 (guix build java-utils))
14760 (modify-phases %standard-phases
14761 (add-after 'build 'build-jni-library
14763 (with-directory-excursion "jni"
14764 (invoke "make" "-f" "makefile.linux"))))
14765 ;; There is no install target
14766 (replace 'install (install-jars "dist"))
14767 (add-after 'install 'install-scripts-and-documentation
14768 (lambda* (#:key outputs #:allow-other-keys)
14769 (substitute* "calcmem.sh"
14770 (("\\| awk ") (string-append "| " (which "awk") " ")))
14771 (let* ((scripts (find-files "." "\\.sh$"))
14772 (out (assoc-ref outputs "out"))
14773 (bin (string-append out "/bin"))
14774 (doc (string-append out "/share/doc/bbmap"))
14775 (jni (string-append out "/lib/jni")))
14776 (substitute* scripts
14777 (("\\$DIR\"\"docs") doc)
14779 (string-append "CP=" out "/share/java/BBTools.jar\n"))
14780 (("^NATIVELIBDIR.*")
14781 (string-append "NATIVELIBDIR=" jni "\n"))
14783 (string-append "CMD=\"" (which "java"))))
14784 (for-each (lambda (script) (install-file script bin)) scripts)
14786 ;; Install JNI library
14787 (install-file "jni/libbbtoolsjni.so" jni)
14789 ;; Install documentation
14790 (install-file "docs/readme.txt" doc)
14791 (copy-recursively "docs/guides" doc))
14796 ("java-eclipse-jdt-core" ,java-eclipse-jdt-core)
14797 ("java-eclipse-jdt-compiler-apt" ,java-eclipse-jdt-compiler-apt)
14798 ("java-openmpi" ,java-openmpi)))
14799 (home-page "https://sourceforge.net/projects/bbmap/")
14800 (synopsis "Aligner and other tools for short sequencing reads")
14802 "This package provides bioinformatic tools to align, deduplicate,
14803 reformat, filter and normalize DNA and RNA-seq data. It includes the
14804 following tools: BBMap, a short read aligner for DNA and RNA-seq data; BBNorm,
14805 a kmer-based error-correction and normalization tool; Dedupe, a tool to
14806 simplify assemblies by removing duplicate or contained subsequences that share
14807 a target percent identity; Reformat, to convert reads between
14808 fasta/fastq/scarf/fasta+qual/sam, interleaved/paired, and ASCII-33/64, at over
14809 500 MB/s; and BBDuk, a tool to filter, trim, or mask reads with kmer matches
14810 to an artifact/contaminant file.")
14811 (license license:bsd-3)))
14813 (define-public velvet
14819 (uri (string-append "https://www.ebi.ac.uk/~zerbino/velvet/"
14820 "velvet_" version ".tgz"))
14823 "0h3njwy66p6bx14r3ar1byb0ccaxmxka4c65rn4iybyiqa4d8kc8"))
14824 ;; Delete bundled libraries
14825 (modules '((guix build utils)))
14828 (delete-file "Manual.pdf")
14829 (delete-file-recursively "third-party")
14831 (build-system gnu-build-system)
14833 `(#:make-flags '("OPENMP=t")
14834 #:test-target "test"
14836 (modify-phases %standard-phases
14837 (delete 'configure)
14838 (add-after 'unpack 'fix-zlib-include
14840 (substitute* "src/binarySequences.c"
14841 (("../third-party/zlib-1.2.3/zlib.h") "zlib.h"))
14844 (lambda* (#:key outputs #:allow-other-keys)
14845 (let* ((out (assoc-ref outputs "out"))
14846 (bin (string-append out "/bin"))
14847 (doc (string-append out "/share/doc/velvet")))
14850 (install-file "velveth" bin)
14851 (install-file "velvetg" bin)
14852 (install-file "Manual.pdf" doc)
14853 (install-file "Columbus_manual.pdf" doc)
14856 `(("openmpi" ,openmpi)
14859 `(("texlive" ,(texlive-union (list texlive-latex-graphics
14860 texlive-latex-hyperref)))))
14861 (home-page "https://www.ebi.ac.uk/~zerbino/velvet/")
14862 (synopsis "Nucleic acid sequence assembler for very short reads")
14864 "Velvet is a de novo genomic assembler specially designed for short read
14865 sequencing technologies, such as Solexa or 454. Velvet currently takes in
14866 short read sequences, removes errors then produces high quality unique
14867 contigs. It then uses paired read information, if available, to retrieve the
14868 repeated areas between contigs.")
14869 (license license:gpl2+)))
14871 (define-public python-velocyto
14873 (name "python-velocyto")
14874 (version "0.17.17")
14878 (uri (pypi-uri "velocyto" version))
14881 "0fgygyzqgrq32dv6a00biq1p1cwi6kbl5iqblxq1kklj6b2mzmhs"))))
14882 (build-system python-build-system)
14884 `(("python-joblib" ,python-joblib)))
14886 `(("python-click" ,python-click)
14887 ("python-cython" ,python-cython)
14888 ("python-h5py" ,python-h5py)
14889 ("python-loompy" ,python-loompy)
14890 ("python-matplotlib" ,python-matplotlib)
14891 ("python-numba" ,python-numba)
14892 ("python-numpy" ,python-numpy)
14893 ("python-pandas" ,python-pandas)
14894 ("python-pysam" ,python-pysam)
14895 ("python-scikit-learn" ,python-scikit-learn)
14896 ("python-scipy" ,python-scipy)))
14897 (home-page "https://github.com/velocyto-team/velocyto.py")
14898 (synopsis "RNA velocity analysis for single cell RNA-seq data")
14900 "Velocyto is a library for the analysis of RNA velocity. Velocyto
14901 includes a command line tool and an analysis pipeline.")
14902 (license license:bsd-2)))
14904 (define-public arriba
14911 (uri (string-append "https://github.com/suhrig/arriba/releases/"
14912 "download/v" version "/arriba_v" version ".tar.gz"))
14915 "0jx9656ry766vb8z08m1c3im87b0c82qpnjby9wz4kcz8vn87dx2"))))
14916 (build-system gnu-build-system)
14918 `(#:tests? #f ; there are none
14920 (modify-phases %standard-phases
14921 (replace 'configure
14922 (lambda* (#:key inputs #:allow-other-keys)
14923 (let ((htslib (assoc-ref inputs "htslib")))
14924 (substitute* "Makefile"
14925 (("-I\\$\\(HTSLIB\\)/htslib")
14926 (string-append "-I" htslib "/include/htslib"))
14927 ((" \\$\\(HTSLIB\\)/libhts.a")
14928 (string-append " " htslib "/lib/libhts.so"))))
14929 (substitute* "run_arriba.sh"
14930 (("^STAR ") (string-append (which "STAR") " "))
14931 (("samtools --version-only")
14932 (string-append (which "samtools") " --version-only"))
14933 (("samtools index")
14934 (string-append (which "samtools") " index"))
14936 (string-append (which "samtools") " sort")))
14939 (lambda* (#:key outputs #:allow-other-keys)
14940 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
14941 (install-file "arriba" bin)
14942 (install-file "run_arriba.sh" bin)
14943 (install-file "draw_fusions.R" bin)
14944 (wrap-program (string-append bin "/draw_fusions.R")
14945 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
14948 `(("htslib" ,htslib)
14949 ("r-minimal" ,r-minimal)
14950 ("r-circlize" ,r-circlize)
14951 ("r-genomicalignments" ,r-genomicalignments)
14952 ("r-genomicranges" ,r-genomicranges)
14953 ("samtools" ,samtools)
14956 (home-page "https://github.com/suhrig/arriba")
14957 (synopsis "Gene fusion detection from RNA-Seq data ")
14959 "Arriba is a command-line tool for the detection of gene fusions from
14960 RNA-Seq data. It was developed for the use in a clinical research setting.
14961 Therefore, short runtimes and high sensitivity were important design criteria.
14962 It is based on the fast STAR aligner and the post-alignment runtime is
14963 typically just around two minutes. In contrast to many other fusion detection
14964 tools which build on STAR, Arriba does not require to reduce the
14965 @code{alignIntronMax} parameter of STAR to detect small deletions.")
14966 ;; All code is under the Expat license with the exception of
14967 ;; "draw_fusions.R", which is under GPLv3.
14968 (license (list license:expat license:gpl3))))
14970 (define-public adapterremoval
14972 (name "adapterremoval")
14977 (uri (git-reference
14978 (url "https://github.com/MikkelSchubert/adapterremoval")
14979 (commit (string-append "v" version))))
14980 (file-name (git-file-name name version))
14983 "1nf3ki5pfzalhrx2fr1y6pfqfi133yj2m7q4fj9irf5fb94bapwr"))))
14984 (build-system gnu-build-system)
14986 `(#:make-flags (list "COLOR_BUILD=no"
14987 (string-append "PREFIX="
14988 (assoc-ref %outputs "out")))
14989 #:test-target "test"
14991 (modify-phases %standard-phases
14992 (delete 'configure))))
14995 (home-page "https://adapterremoval.readthedocs.io/")
14996 (synopsis "Rapid sequence adapter trimming, identification, and read merging")
14998 "This program searches for and removes remnant adapter sequences from
14999 @dfn{High-Throughput Sequencing} (HTS) data and (optionally) trims low quality
15000 bases from the 3' end of reads following adapter removal. AdapterRemoval can
15001 analyze both single end and paired end data, and can be used to merge
15002 overlapping paired-ended reads into (longer) consensus sequences.
15003 Additionally, the AdapterRemoval may be used to recover a consensus adapter
15004 sequence for paired-ended data, for which this information is not available.")
15005 (license license:gpl3+)))
15007 (define-public pplacer
15008 (let ((commit "807f6f3"))
15011 ;; The commit should be updated with each version change.
15012 (version "1.1.alpha19")
15016 (uri (git-reference
15017 (url "https://github.com/matsen/pplacer")
15018 (commit (string-append "v" version))))
15019 (file-name (git-file-name name version))
15021 (base32 "11ppbbbx20p2g9wj3ff64dhnarb12q79v7qh4rk0gj6lkbz4n7cn"))))
15022 (build-system ocaml-build-system)
15024 `(#:modules ((guix build ocaml-build-system)
15028 (modify-phases %standard-phases
15029 (delete 'configure)
15030 (add-after 'unpack 'fix-build-with-latest-ocaml
15032 (substitute* "myocamlbuild.ml"
15033 (("dep \\[\"c_pam\"\\]" m)
15034 (string-append "flag [\"ocaml\"; \"compile\"] (A \"-unsafe-string\");\n"
15036 (("let run_and_read" m)
15041 let pos = String.index s ch in
15042 x := (String.before s pos)::!x;
15043 go (String.after s (pos + 1))
15046 with Not_found -> !x
15047 let split_nl s = split s '\\n'
15048 let before_space s =
15049 try String.before s (String.index s ' ')
15050 with Not_found -> s
15053 (("run_and_read \"ocamlfind list \\| cut -d' ' -f1\"" m)
15054 (string-append "List.map before_space (split_nl & " m ")"))
15055 ((" blank_sep_strings &") "")
15056 ((" Lexing.from_string &") ""))
15058 (add-after 'unpack 'replace-bundled-cddlib
15059 (lambda* (#:key inputs #:allow-other-keys)
15060 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
15061 (local-dir "cddlib_guix"))
15063 (with-directory-excursion local-dir
15064 (invoke "tar" "xvf" cddlib-src))
15065 (let ((cddlib-src-folder
15066 (string-append local-dir "/"
15067 (list-ref (scandir local-dir) 2)
15069 (for-each make-file-writable (find-files "cdd_src" ".*"))
15073 (string-append "cdd_src/" (basename file))))
15074 (find-files cddlib-src-folder ".*[ch]$")))
15076 (add-after 'unpack 'fix-makefile
15078 ;; Remove system calls to 'git'.
15079 (substitute* "Makefile"
15080 (("^DESCRIPT:=pplacer-.*")
15082 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
15083 (substitute* "myocamlbuild.ml"
15084 (("git describe --tags --long .*\\\" with")
15086 "echo -n v" ,version "-" ,commit "\" with")))
15089 (lambda* (#:key outputs #:allow-other-keys)
15090 (let* ((out (assoc-ref outputs "out"))
15091 (bin (string-append out "/bin")))
15092 (copy-recursively "bin" bin))
15094 #:ocaml ,ocaml-4.07
15095 #:findlib ,ocaml4.07-findlib))
15097 `(("zlib" ,zlib "static")
15099 ("ocaml-ounit" ,(package-with-ocaml4.07 ocaml-ounit))
15100 ("ocaml-batteries" ,(package-with-ocaml4.07 ocaml-batteries))
15101 ("ocaml-camlzip" ,(package-with-ocaml4.07 camlzip))
15102 ("ocaml-csv" ,(package-with-ocaml4.07 ocaml-csv))
15103 ("ocaml-sqlite3" ,ocaml4.07-sqlite3)
15104 ("ocaml-xmlm" ,(package-with-ocaml4.07 ocaml-xmlm))
15105 ("ocaml-mcl" ,(package-with-ocaml4.07 ocaml-mcl))
15106 ("ocaml-gsl" ,ocaml4.07-gsl-1)))
15108 `(("cddlib-src" ,(package-source cddlib))
15109 ("ocamlbuild" ,(package-with-ocaml4.07 ocamlbuild))
15110 ("pkg-config" ,pkg-config)))
15112 `(("pplacer-scripts" ,pplacer-scripts)))
15113 (synopsis "Phylogenetic placement of biological sequences")
15115 "Pplacer places query sequences on a fixed reference phylogenetic tree
15116 to maximize phylogenetic likelihood or posterior probability according to a
15117 reference alignment. Pplacer is designed to be fast, to give useful
15118 information about uncertainty, and to offer advanced visualization and
15119 downstream analysis.")
15120 (home-page "https://matsen.fhcrc.org/pplacer/")
15121 (license license:gpl3))))
15123 ;; This package is installed alongside 'pplacer'. It is a separate package so
15124 ;; that it can use the python-build-system for the scripts that are
15125 ;; distributed alongside the main OCaml binaries.
15126 (define pplacer-scripts
15129 (name "pplacer-scripts")
15130 (build-system python-build-system)
15132 `(#:python ,python-2
15134 (modify-phases %standard-phases
15135 (add-after 'unpack 'enter-scripts-dir
15136 (lambda _ (chdir "scripts") #t))
15138 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t))
15139 (add-after 'install 'wrap-executables
15140 (lambda* (#:key inputs outputs #:allow-other-keys)
15141 (let* ((out (assoc-ref outputs "out"))
15142 (bin (string-append out "/bin")))
15143 (let ((path (string-append
15144 (assoc-ref inputs "hmmer") "/bin:"
15145 (assoc-ref inputs "infernal") "/bin")))
15147 (wrap-program (string-append bin "/refpkg_align.py")
15148 `("PATH" ":" prefix (,path))))
15149 (let ((path (string-append
15150 (assoc-ref inputs "hmmer") "/bin")))
15151 (wrap-program (string-append bin "/hrefpkg_query.py")
15152 `("PATH" ":" prefix (,path)))))
15155 `(("infernal" ,infernal)
15158 `(("python-biopython" ,python2-biopython)
15159 ("taxtastic" ,taxtastic)))
15160 (synopsis "Pplacer Python scripts")))
15162 (define-public python2-checkm-genome
15164 (name "python2-checkm-genome")
15169 (uri (pypi-uri "checkm-genome" version))
15172 "0bm8gpxjmzxsxxl8lzwqhgx8g1dlnmp6znz7wv3hgb0gdjbf9dzz"))))
15173 (build-system python-build-system)
15175 `(#:python ,python-2
15176 #:tests? #f)) ; some tests are interactive
15178 `(("python-dendropy" ,python2-dendropy)
15179 ("python-matplotlib" ,python2-matplotlib)
15180 ("python-numpy" ,python2-numpy)
15181 ("python-pysam" ,python2-pysam)
15182 ("python-scipy" ,python2-scipy)))
15183 (home-page "https://pypi.org/project/Checkm/")
15184 (synopsis "Assess the quality of putative genome bins")
15186 "CheckM provides a set of tools for assessing the quality of genomes
15187 recovered from isolates, single cells, or metagenomes. It provides robust
15188 estimates of genome completeness and contamination by using collocated sets of
15189 genes that are ubiquitous and single-copy within a phylogenetic lineage.
15190 Assessment of genome quality can also be examined using plots depicting key
15191 genomic characteristics (e.g., GC, coding density) which highlight sequences
15192 outside the expected distributions of a typical genome. CheckM also provides
15193 tools for identifying genome bins that are likely candidates for merging based
15194 on marker set compatibility, similarity in genomic characteristics, and
15195 proximity within a reference genome.")
15196 (license license:gpl3+)))
15198 (define-public umi-tools
15205 (uri (pypi-uri "umi_tools" version))
15208 "08y3vz1vcx09whmbsn722lcs6jl9wyrh9i4p3k8j4cb1i32bij4a"))))
15209 (build-system python-build-system)
15211 `(("python-pandas" ,python-pandas)
15212 ("python-future" ,python-future)
15213 ("python-scipy" ,python-scipy)
15214 ("python-matplotlib" ,python-matplotlib)
15215 ("python-regex" ,python-regex)
15216 ("python-pysam" ,python-pysam)))
15218 `(("python-cython" ,python-cython)))
15219 (home-page "https://github.com/CGATOxford/UMI-tools")
15220 (synopsis "Tools for analyzing unique modular identifiers")
15221 (description "This package provides tools for dealing with @dfn{Unique
15222 Molecular Identifiers} (UMIs) and @dfn{Random Molecular Tags} (RMTs) in
15223 genetic sequences. There are six tools: the @code{extract} and
15224 @code{whitelist} commands are used to prepare a fastq containing UMIs @code{+/-}
15225 cell barcodes for alignment. The remaining commands, @code{group},
15226 @code{dedup}, and @{count}/@code{count_tab}, are used to identify PCR
15227 duplicates using the UMIs and perform different levels of analysis depending
15228 on the needs of the user.")
15229 (license license:expat)))
15231 (define-public ataqv
15238 (uri (git-reference
15239 (url "https://github.com/ParkerLab/ataqv")
15241 (file-name (git-file-name name version))
15244 "031xr6jx1aprh26y5b1lv3gzrlmzg4alfl73vvshymx8cq8asrqi"))))
15245 (build-system gnu-build-system)
15248 (list (string-append "prefix=" (assoc-ref %outputs "out"))
15249 (string-append "BOOST_ROOT="
15250 (assoc-ref %build-inputs "boost"))
15251 (string-append "HTSLIB_ROOT="
15252 (assoc-ref %build-inputs "htslib")))
15253 #:test-target "test"
15255 (modify-phases %standard-phases
15256 (delete 'configure))))
15260 ("ncurses" ,ncurses)
15264 (home-page "https://github.com/ParkerLab/ataqv")
15265 (synopsis "Toolkit for quality control and visualization of ATAC-seq data")
15266 (description "This package provides a toolkit for measuring and comparing
15267 ATAC-seq results. It was written to make it easier to spot differences that
15268 might be caused by ATAC-seq library prep or sequencing. The main program,
15269 @code{ataqv}, examines aligned reads and reports some basic metrics.")
15270 (license license:gpl3+)))
15272 (define-public r-psiplot
15279 (uri (git-reference
15280 (url "https://github.com/kcha/psiplot")
15281 (commit (string-append "v" version))))
15282 (file-name (git-file-name name version))
15284 (base32 "08438h16cfry5kqh3y9hs8q1b1a8bxhblsm75knviz5r6q0n1jxh"))))
15285 (build-system r-build-system)
15287 `(("r-mass" ,r-mass)
15288 ("r-dplyr" ,r-dplyr)
15289 ("r-tidyr" ,r-tidyr)
15290 ("r-purrr" ,r-purrr)
15291 ("r-readr" ,r-readr)
15292 ("r-magrittr" ,r-magrittr)
15293 ("r-ggplot2" ,r-ggplot2)))
15294 (home-page "https://github.com/kcha/psiplot")
15295 (synopsis "Plot percent spliced-in values of alternatively-spliced exons")
15297 "PSIplot is an R package for generating plots of @dfn{percent
15298 spliced-in} (PSI) values of alternatively-spliced exons that were computed by
15299 vast-tools, an RNA-Seq pipeline for alternative splicing analysis. The plots
15300 are generated using @code{ggplot2}.")
15301 (license license:expat)))
15303 (define-public python-ont-fast5-api
15305 (name "python-ont-fast5-api")
15310 (uri (git-reference
15311 (url "https://github.com/nanoporetech/ont_fast5_api")
15312 (commit (string-append "release_" version))))
15313 (file-name (git-file-name name version))
15316 "03cbq4zbbwhll8ml2m9k8sa31mirsvcbjkrq1yna0kkzz9fad5fm"))))
15317 (build-system python-build-system)
15319 `(("python-numpy" ,python-numpy)
15320 ("python-six" ,python-six)
15321 ("python-h5py" ,python-h5py)
15322 ("python-progressbar33" ,python-progressbar33)))
15323 (home-page "https://github.com/nanoporetech/ont_fast5_api")
15324 (synopsis "Interface to HDF5 files of the Oxford Nanopore fast5 file format")
15326 "This package provides a concrete implementation of the fast5 file schema
15327 using the generic @code{h5py} library, plain-named methods to interact with
15328 and reflect the fast5 file schema, and tools to convert between
15329 @code{multi_read} and @code{single_read} formats.")
15330 (license license:mpl2.0)))
15332 (define-public tbsp
15333 (let ((commit "ec8fff4410cfb13a677dbbb95cbbc60217e64907")
15337 (version (git-version "1.0.0" revision commit))
15341 (uri (git-reference
15342 (url "https://github.com/phoenixding/tbsp")
15344 (file-name (git-file-name name version))
15347 "025ym14x8gbd6hb55lsinqj6f5qzw36i10klgs7ldzxxd7s39ki1"))))
15348 (build-system python-build-system)
15349 (arguments '(#:tests? #f)) ; no tests included
15351 `(("python-matplotlib" ,python-matplotlib)
15352 ("python-networkx" ,python-networkx)
15353 ("python-numpy" ,python-numpy)
15354 ("python-pybigwig" ,python-pybigwig)
15355 ("python-biopython" ,python-biopython)
15356 ("python-scikit-learn" ,python-scikit-learn)
15357 ("python-scipy" ,python-scipy)))
15358 (home-page "https://github.com/phoenixding/tbsp/")
15359 (synopsis "SNP-based trajectory inference")
15361 "Several studies focus on the inference of developmental and response
15362 trajectories from single cell RNA-Seq (scRNA-Seq) data. A number of
15363 computational methods, often referred to as pseudo-time ordering, have been
15364 developed for this task. CRISPR has also been used to reconstruct lineage
15365 trees by inserting random mutations. The tbsp package implements an
15366 alternative method to detect significant, cell type specific sequence
15367 mutations from scRNA-Seq data.")
15368 (license license:expat))))
15370 (define-public tabixpp
15376 (uri (git-reference
15377 (url "https://github.com/ekg/tabixpp")
15378 (commit (string-append "v" version))))
15379 (file-name (git-file-name name version))
15381 (base32 "1k2a3vbq96ic4lw72iwp5s3mwwc4xhdffjj584yn6l9637q9j1yd"))
15382 (modules '((guix build utils)))
15385 (delete-file-recursively "htslib") #t))))
15386 (build-system gnu-build-system)
15388 `(("htslib" ,htslib)
15391 `(#:tests? #f ; There are no tests to run.
15393 (modify-phases %standard-phases
15394 (delete 'configure) ; There is no configure phase.
15395 ;; The build phase needs overriding the location of htslib.
15397 (lambda* (#:key inputs #:allow-other-keys)
15398 (let ((htslib-ref (assoc-ref inputs "htslib")))
15400 (string-append "HTS_LIB=" htslib-ref "/lib/libhts.a")
15401 (string-append "INCLUDES= -I" htslib-ref "/include/htslib")
15402 "HTS_HEADERS=" ; No need to check for headers here.
15403 (string-append "LIBPATH=-L. -L" htslib-ref "/include"))
15404 (invoke "g++" "-shared" "-o" "libtabixpp.so" "tabix.o" "-lhts")
15405 (invoke "ar" "rcs" "libtabixpp.a" "tabix.o"))))
15407 (lambda* (#:key outputs #:allow-other-keys)
15408 (let* ((out (assoc-ref outputs "out"))
15409 (lib (string-append out "/lib"))
15410 (bin (string-append out "/bin")))
15411 (install-file "tabix++" bin)
15412 (install-file "libtabixpp.so" lib)
15413 (install-file "libtabixpp.a" lib)
15414 (install-file "tabix.hpp" (string-append out "/include"))
15415 (mkdir-p (string-append lib "/pkgconfig"))
15416 (with-output-to-file (string-append lib "/pkgconfig/tabixpp.pc")
15418 (format #t "prefix=~a~@
15419 exec_prefix=${prefix}~@
15420 libdir=${exec_prefix}/lib~@
15421 includedir=${prefix}/include~@
15426 Description: C++ wrapper around tabix project~@
15427 Libs: -L${libdir} -ltabixpp~@
15428 Cflags: -I${includedir}~%"
15431 (home-page "https://github.com/ekg/tabixpp")
15432 (synopsis "C++ wrapper around tabix project")
15433 (description "This is a C++ wrapper around the Tabix project which abstracts
15434 some of the details of opening and jumping in tabix-indexed files.")
15435 (license license:expat)))
15437 (define-public smithwaterman
15438 (let ((commit "2610e259611ae4cde8f03c72499d28f03f6d38a7"))
15440 (name "smithwaterman")
15441 (version (git-version "0.0.0" "2" commit))
15444 (uri (git-reference
15445 (url "https://github.com/ekg/smithwaterman/")
15447 (file-name (git-file-name name version))
15449 (base32 "0i9d8zrxpiracw3mxzd9siybpy62p06rqz9mc2w93arajgbk45bs"))))
15450 (build-system gnu-build-system)
15452 `(#:tests? #f ; There are no tests to run.
15453 #:make-flags '("libsw.a" "all")
15455 (modify-phases %standard-phases
15456 (delete 'configure) ; There is no configure phase.
15457 (add-after 'unpack 'patch-source
15459 (substitute* "Makefile"
15460 (("-c ") "-c -fPIC "))
15462 (add-after 'build 'build-dynamic
15465 "-shared" "-o" "libsmithwaterman.so"
15466 "smithwaterman.o" "SmithWatermanGotoh.o"
15467 "disorder.o" "BandedSmithWaterman.o"
15468 "LeftAlign.o" "Repeats.o" "IndelAllele.o")))
15470 (lambda* (#:key outputs #:allow-other-keys)
15471 (let* ((out (assoc-ref outputs "out"))
15472 (bin (string-append out "/bin"))
15473 (lib (string-append out "/lib")))
15474 (install-file "smithwaterman" bin)
15477 (install-file file (string-append out "/include/smithwaterman")))
15478 (find-files "." "\\.h$"))
15479 (install-file "libsmithwaterman.so" lib)
15480 (install-file "libsw.a" lib)
15481 (mkdir-p (string-append lib "/pkgconfig"))
15482 (with-output-to-file (string-append lib "/pkgconfig/smithwaterman.pc")
15484 (format #t "prefix=~a~@
15485 exec_prefix=${prefix}~@
15486 libdir=${exec_prefix}/lib~@
15487 includedir=${prefix}/include/smithwaterman~@
15490 Name: smithwaterman~@
15492 Description: smith-waterman-gotoh alignment algorithm~@
15493 Libs: -L${libdir} -lsmithwaterman~@
15494 Cflags: -I${includedir}~%"
15497 (home-page "https://github.com/ekg/smithwaterman")
15498 (synopsis "Implementation of the Smith-Waterman algorithm")
15499 (description "Implementation of the Smith-Waterman algorithm.")
15500 ;; The licensing terms are unclear: https://github.com/ekg/smithwaterman/issues/9.
15501 (license (list license:gpl2 license:expat)))))
15503 (define-public multichoose
15505 (name "multichoose")
15509 (uri (git-reference
15510 (url "https://github.com/ekg/multichoose/")
15511 (commit (string-append "v" version))))
15512 (file-name (git-file-name name version))
15514 (base32 "0ci5fqvmpamwgxvmyd79ygj6n3bnbl3vc7b6h1sxz58186sm3pfs"))))
15515 (build-system gnu-build-system)
15517 `(#:tests? #f ; Tests require node.
15519 (modify-phases %standard-phases
15520 (delete 'configure) ; There is no configure phase.
15522 (lambda* (#:key outputs #:allow-other-keys)
15523 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15524 ;; TODO: There are Python modules for these programs too.
15525 (install-file "multichoose" bin)
15526 (install-file "multipermute" bin))
15528 (home-page "https://github.com/ekg/multichoose")
15529 (synopsis "Efficient loopless multiset combination generation algorithm")
15530 (description "This library implements an efficient loopless multiset
15531 combination generation algorithm which is (approximately) described in
15532 \"Loopless algorithms for generating permutations, combinations, and other
15533 combinatorial configurations.\", G. Ehrlich - Journal of the ACM (JACM),
15534 1973. (Algorithm 7.)")
15535 (license license:expat)))
15537 (define-public fsom
15538 (let ((commit "a6ef318fbd347c53189384aef7f670c0e6ce89a3"))
15541 (version (git-version "0.0.0" "1" commit))
15544 (uri (git-reference
15545 (url "https://github.com/ekg/fsom/")
15547 (file-name (git-file-name name version))
15549 (base32 "0gw1lpvr812pywg9y546x0h1hhj261xwls41r6kqhddjlrcjc0pi"))))
15550 (build-system gnu-build-system)
15552 `(#:tests? #f ; There are no tests to run.
15554 (modify-phases %standard-phases
15555 (delete 'configure) ; There is no configure phase.
15557 (lambda* (#:key outputs #:allow-other-keys)
15558 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15559 (install-file "fsom" bin))
15561 (home-page "https://github.com/ekg/fsom")
15562 (synopsis "Manage SOM (Self-Organizing Maps) neural networks")
15563 (description "A tiny C library for managing SOM (Self-Organizing Maps)
15565 (license license:gpl3))))
15567 (define-public fastahack
15573 (uri (git-reference
15574 (url "https://github.com/ekg/fastahack/")
15575 (commit (string-append "v" version))))
15576 (file-name (git-file-name name version))
15578 (base32 "0rp1blskhzxf7vbh253ibpxbgl9wwgyzf1wbkxndi08d3j4vcss9"))))
15579 (build-system gnu-build-system)
15581 `(#:tests? #f ; Unclear how to run tests: https://github.com/ekg/fastahack/issues/15
15583 (modify-phases %standard-phases
15584 (delete 'configure) ; There is no configure phase.
15585 (add-after 'unpack 'patch-source
15587 (substitute* "Makefile"
15588 (("-c ") "-c -fPIC "))
15590 (add-after 'build 'build-dynamic
15593 "-shared" "-o" "libfastahack.so"
15594 "Fasta.o" "FastaHack.o" "split.o" "disorder.o")))
15596 (lambda* (#:key outputs #:allow-other-keys)
15597 (let* ((out (assoc-ref outputs "out"))
15598 (lib (string-append out "/lib"))
15599 (bin (string-append out "/bin")))
15600 (mkdir-p (string-append out "/include/fastahack"))
15603 (install-file file (string-append out "/include/fastahack")))
15604 (find-files "." "\\.h$"))
15605 (install-file "fastahack" bin)
15606 (install-file "libfastahack.so" lib)
15607 (mkdir-p (string-append lib "/pkgconfig"))
15608 (with-output-to-file (string-append lib "/pkgconfig/fastahack.pc")
15610 (format #t "prefix=~a~@
15611 exec_prefix=${prefix}~@
15612 libdir=${exec_prefix}/lib~@
15613 includedir=${prefix}/include/fastahack~@
15618 Description: Indexing and sequence extraction from FASTA files~@
15619 Libs: -L${libdir} -lfastahack~@
15620 Cflags: -I${includedir}~%"
15623 (home-page "https://github.com/ekg/fastahack")
15624 (synopsis "Indexing and sequence extraction from FASTA files")
15625 (description "Fastahack is a small application for indexing and
15626 extracting sequences and subsequences from FASTA files. The included library
15627 provides a FASTA reader and indexer that can be embedded into applications
15628 which would benefit from directly reading subsequences from FASTA files. The
15629 library automatically handles index file generation and use.")
15630 (license (list license:expat license:gpl2))))
15632 (define-public vcflib
15639 (uri (string-append "https://github.com/vcflib/vcflib/releases/"
15640 "download/v" version
15641 "/vcflib-" version "-src.tar.gz"))
15643 (base32 "14zzrg8hg8cq9cvq2wdvp21j7nmxxkjrbagw2apd2yqv2kyx42lm"))
15644 (patches (search-patches "vcflib-use-shared-libraries.patch"))
15645 (modules '((guix build utils)))
15648 (substitute* (find-files "." "\\.(h|c)(pp)?$")
15649 (("\"SmithWatermanGotoh.h\"") "<smithwaterman/SmithWatermanGotoh.h>")
15650 (("\"convert.h\"") "<smithwaterman/convert.h>")
15651 (("\"disorder.h\"") "<smithwaterman/disorder.h>")
15652 (("\"tabix.hpp\"") "<tabix.hpp>")
15653 (("\"Fasta.h\"") "<fastahack/Fasta.h>"))
15654 (for-each delete-file-recursively
15655 '("fastahack" "filevercmp" "fsom" "googletest" "intervaltree"
15656 "libVCFH" "multichoose" "smithwaterman" "tabixpp"))
15658 (build-system gnu-build-system)
15660 `(("htslib" ,htslib)
15661 ("fastahack" ,fastahack)
15664 ("smithwaterman" ,smithwaterman)
15665 ("tabixpp" ,tabixpp)
15669 `(("pkg-config" ,pkg-config)
15671 ;; This package builds against the .o files so we need to extract the source.
15672 ("filevercmp-src" ,(package-source filevercmp))
15673 ("intervaltree-src" ,(package-source intervaltree))
15674 ("multichoose-src" ,(package-source multichoose))))
15676 `(#:tests? #f ; no tests
15678 (modify-phases %standard-phases
15679 (add-after 'unpack 'set-flags
15680 (lambda* (#:key outputs #:allow-other-keys)
15681 (substitute* "Makefile"
15683 (string-append "LDFLAGS = -Wl,-rpath="
15684 (assoc-ref outputs "out") "/lib ")))
15685 (substitute* "filevercmp/Makefile"
15686 (("-c") "-c -fPIC"))
15688 (delete 'configure)
15689 (add-after 'unpack 'unpack-submodule-sources
15690 (lambda* (#:key inputs #:allow-other-keys)
15691 (let ((unpack (lambda (source target)
15693 (with-directory-excursion target
15694 (if (file-is-directory? (assoc-ref inputs source))
15695 (copy-recursively (assoc-ref inputs source) ".")
15696 (invoke "tar" "xvf"
15697 (assoc-ref inputs source)
15698 "--strip-components=1"))))))
15700 (unpack "filevercmp-src" "filevercmp")
15701 (unpack "intervaltree-src" "intervaltree")
15702 (unpack "multichoose-src" "multichoose")))))
15704 (lambda* (#:key outputs #:allow-other-keys)
15705 (let* ((out (assoc-ref outputs "out"))
15706 (bin (string-append out "/bin"))
15707 (lib (string-append out "/lib")))
15708 (for-each (lambda (file)
15709 (install-file file bin))
15710 (find-files "bin" ".*"))
15711 (install-file "libvcflib.so" lib)
15712 (install-file "libvcflib.a" lib)
15715 (install-file file (string-append out "/include")))
15716 (find-files "include" "\\.h(pp)?$"))
15717 (mkdir-p (string-append lib "/pkgconfig"))
15718 (with-output-to-file (string-append lib "/pkgconfig/vcflib.pc")
15720 (format #t "prefix=~a~@
15721 exec_prefix=${prefix}~@
15722 libdir=${exec_prefix}/lib~@
15723 includedir=${prefix}/include~@
15728 Requires: smithwaterman, fastahack~@
15729 Description: C++ library for parsing and manipulating VCF files~@
15730 Libs: -L${libdir} -lvcflib~@
15731 Cflags: -I${includedir}~%"
15734 (home-page "https://github.com/vcflib/vcflib/")
15735 (synopsis "Library for parsing and manipulating VCF files")
15736 (description "Vcflib provides methods to manipulate and interpret
15737 sequence variation as it can be described by VCF. It is both an API for parsing
15738 and operating on records of genomic variation as it can be described by the VCF
15739 format, and a collection of command-line utilities for executing complex
15740 manipulations on VCF files.")
15741 (license license:expat)))
15743 (define-public freebayes
15744 (let ((commit "3ce827d8ebf89bb3bdc097ee0fe7f46f9f30d5fb")
15749 (version (git-version version revision commit))
15752 (uri (git-reference
15753 (url "https://github.com/ekg/freebayes")
15755 (file-name (git-file-name name version))
15757 (base32 "1sbzwmcbn78ybymjnhwk7qc5r912azy5vqz2y7y81616yc3ba2a2"))))
15758 (build-system gnu-build-system)
15760 `(("bamtools" ,bamtools)
15764 `(("bc" ,bc) ; Needed for running tests.
15765 ("samtools" ,samtools) ; Needed for running tests.
15766 ("parallel" ,parallel) ; Needed for running tests.
15767 ("perl" ,perl) ; Needed for running tests.
15768 ("procps" ,procps) ; Needed for running tests.
15769 ("python" ,python-2) ; Needed for running tests.
15770 ("vcflib-src" ,(package-source vcflib))
15771 ;; These are submodules for the vcflib version used in freebayes.
15772 ;; This package builds against the .o files so we need to extract the source.
15773 ("tabixpp-src" ,(package-source tabixpp))
15774 ("smithwaterman-src" ,(package-source smithwaterman))
15775 ("multichoose-src" ,(package-source multichoose))
15776 ("fsom-src" ,(package-source fsom))
15777 ("filevercmp-src" ,(package-source filevercmp))
15778 ("fastahack-src" ,(package-source fastahack))
15779 ("intervaltree-src" ,(package-source intervaltree))
15780 ;; These submodules are needed to run the tests.
15781 ("bash-tap-src" ,(package-source bash-tap))
15782 ("test-simple-bash-src"
15785 (uri (git-reference
15786 (url "https://github.com/ingydotnet/test-simple-bash/")
15787 (commit "124673ff204b01c8e96b7fc9f9b32ee35d898acc")))
15788 (file-name "test-simple-bash-src-checkout")
15790 (base32 "043plp6z0x9yf7mdpky1fw7zcpwn1p47px95w9mh16603zqqqpga"))))))
15794 (string-append "BAMTOOLS_ROOT="
15795 (assoc-ref %build-inputs "bamtools")))
15796 #:test-target "test"
15798 (modify-phases %standard-phases
15799 (delete 'configure)
15800 (add-after 'unpack 'fix-tests
15802 (substitute* "test/t/01_call_variants.t"
15803 (("grep -P \"\\(\\\\t500\\$\\|\\\\t11000\\$\\|\\\\t1000\\$\\)\"")
15804 "grep -E ' (500|11000|1000)$'"))
15806 (add-after 'unpack 'unpack-submodule-sources
15807 (lambda* (#:key inputs #:allow-other-keys)
15808 (let ((unpack (lambda (source target)
15809 (with-directory-excursion target
15810 (if (file-is-directory? (assoc-ref inputs source))
15811 (copy-recursively (assoc-ref inputs source) ".")
15812 (invoke "tar" "xvf"
15813 (assoc-ref inputs source)
15814 "--strip-components=1"))))))
15816 (unpack "vcflib-src" "vcflib")
15817 (unpack "fastahack-src" "vcflib/fastahack")
15818 (unpack "filevercmp-src" "vcflib/filevercmp")
15819 (unpack "fsom-src" "vcflib/fsom")
15820 (unpack "intervaltree-src" "vcflib/intervaltree")
15821 (unpack "multichoose-src" "vcflib/multichoose")
15822 (unpack "smithwaterman-src" "vcflib/smithwaterman")
15823 (unpack "tabixpp-src" "vcflib/tabixpp")
15824 (unpack "test-simple-bash-src" "test/test-simple-bash")
15825 (unpack "bash-tap-src" "test/bash-tap")))))
15826 (add-after 'unpack-submodule-sources 'fix-makefiles
15828 ;; We don't have the .git folder to get the version tag from.
15829 (substitute* "vcflib/Makefile"
15830 (("^GIT_VERSION.*")
15831 (string-append "GIT_VERSION = v" ,version)))
15832 (substitute* "src/Makefile"
15833 (("-I\\$\\(BAMTOOLS_ROOT\\)/src")
15834 "-I$(BAMTOOLS_ROOT)/include/bamtools"))
15836 (add-before 'build 'build-tabixpp-and-vcflib
15837 (lambda* (#:key inputs make-flags #:allow-other-keys)
15838 (with-directory-excursion "vcflib"
15839 (with-directory-excursion "tabixpp"
15840 (apply invoke "make"
15841 (string-append "HTS_LIB="
15842 (assoc-ref inputs "htslib")
15845 (apply invoke "make"
15846 (string-append "CFLAGS=-Itabixpp")
15850 (lambda* (#:key outputs #:allow-other-keys)
15851 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15852 (install-file "bin/freebayes" bin)
15853 (install-file "bin/bamleftalign" bin))
15855 (home-page "https://github.com/ekg/freebayes")
15856 (synopsis "Haplotype-based variant detector")
15857 (description "FreeBayes is a Bayesian genetic variant detector designed to
15858 find small polymorphisms, specifically SNPs (single-nucleotide polymorphisms),
15859 indels (insertions and deletions), MNPs (multi-nucleotide polymorphisms), and
15860 complex events (composite insertion and substitution events) smaller than the
15861 length of a short-read sequencing alignment.")
15862 (license license:expat))))
15864 (define-public samblaster
15866 (name "samblaster")
15870 (uri (git-reference
15871 (url "https://github.com/GregoryFaust/samblaster")
15872 (commit (string-append "v." version))))
15873 (file-name (git-file-name name version))
15876 "0iv2ddfw8363vb2x8gr3p8g88whb6mb9m0pf71i2cqsbv6jghap7"))))
15877 (build-system gnu-build-system)
15879 `(#:tests? #f ; there are none
15881 (modify-phases %standard-phases
15882 (delete 'configure) ; There is no configure phase.
15884 (lambda* (#:key outputs #:allow-other-keys)
15885 (install-file "samblaster"
15886 (string-append (assoc-ref outputs "out") "/bin"))
15888 (home-page "https://github.com/GregoryFaust/samblaster")
15889 (synopsis "Mark duplicates in paired-end SAM files")
15890 (description "Samblaster is a fast and flexible program for marking
15891 duplicates in read-id grouped paired-end SAM files. It can also optionally
15892 output discordant read pairs and/or split read mappings to separate SAM files,
15893 and/or unmapped/clipped reads to a separate FASTQ file. When marking
15894 duplicates, samblaster will require approximately 20MB of memory per 1M read
15896 (license license:expat)))
15898 (define-public r-velocyto
15899 (let ((commit "d7790346cb99f49ab9c2b23ba70dcf9d2c9fc350")
15902 (name "r-velocyto")
15903 (version (git-version "0.6" revision commit))
15907 (uri (git-reference
15908 (url "https://github.com/velocyto-team/velocyto.R")
15910 (file-name (git-file-name name version))
15913 "16wqf70j7rd7pay2q513iyz12i8n9vrpg1bisah4lddbcpx5dz1n"))))
15914 (build-system r-build-system)
15916 `(("boost" ,boost)))
15918 `(("r-hdf5r" ,r-hdf5r)
15921 ("r-pcamethods" ,r-pcamethods)
15923 ("r-rcpparmadillo" ,r-rcpparmadillo)
15924 ;; Suggested packages
15925 ("r-rtsne" ,r-rtsne)
15926 ("r-cluster" ,r-cluster)
15927 ("r-abind" ,r-abind)
15929 ("r-biocgenerics" ,r-biocgenerics)
15930 ("r-genomicalignments" ,r-genomicalignments)
15931 ("r-rsamtools" ,r-rsamtools)
15932 ("r-edger" ,r-edger)
15933 ("r-igraph" ,r-igraph)))
15934 (home-page "https://velocyto.org")
15935 (synopsis "RNA velocity estimation in R")
15937 "This package provides basic routines for estimation of gene-specific
15938 transcriptional derivatives and visualization of the resulting velocity
15940 (license license:gpl3))))
15942 (define-public methyldackel
15944 (name "methyldackel")
15948 (uri (git-reference
15949 (url "https://github.com/dpryan79/MethylDackel")
15951 (file-name (git-file-name name version))
15954 "10gh8k0ca92kywnrw5pkacq3g6r8s976s12k8jhp8g3g49q9a97g"))))
15955 (build-system gnu-build-system)
15957 `(#:test-target "test"
15960 (string-append "prefix="
15961 (assoc-ref %outputs "out") "/bin/"))
15963 (modify-phases %standard-phases
15964 (replace 'configure
15965 (lambda* (#:key outputs #:allow-other-keys)
15966 (substitute* "Makefile"
15967 (("install MethylDackel \\$\\(prefix\\)" match)
15968 (string-append "install -d $(prefix); " match)))
15971 `(("htslib" ,htslib)
15973 ;; Needed for tests
15975 `(("python" ,python-wrapper)))
15976 (home-page "https://github.com/dpryan79/MethylDackel")
15977 (synopsis "Universal methylation extractor for BS-seq experiments")
15979 "MethylDackel will process a coordinate-sorted and indexed BAM or CRAM
15980 file containing some form of BS-seq alignments and extract per-base
15981 methylation metrics from them. MethylDackel requires an indexed fasta file
15982 containing the reference genome as well.")
15983 ;; See https://github.com/dpryan79/MethylDackel/issues/85
15984 (license license:expat)))
15986 ;; This package bundles PCRE 8.02 and cannot be built with the current
15988 (define-public phast
15994 (uri (git-reference
15995 (url "https://github.com/CshlSiepelLab/phast")
15996 (commit (string-append "v" version))))
15997 (file-name (git-file-name name version))
16000 "10lpbllvny923jjbbyrpxahhd1m5h7sbj9gx7rd123rg10mlidki"))))
16001 (build-system gnu-build-system)
16005 (string-append "DESTDIR=" (assoc-ref %outputs "out")))
16007 (modify-phases %standard-phases
16008 (replace 'configure
16009 (lambda* (#:key inputs outputs #:allow-other-keys)
16011 (substitute* "test/Makefile"
16013 (substitute* "Makefile"
16014 (("CLAPACKPATH=/usr/lib")
16015 (string-append "CLAPACKPATH="
16016 (assoc-ref inputs "clapack") "/lib")))
16017 ;; Renaming the libraries is not necessary with our version of
16019 (substitute* "src/lib/Makefile"
16020 (("ifdef CLAPACKPATH") "ifdef UNNECESSARY"))
16021 (substitute* "src/make-include.mk"
16022 (("-lblaswr") "-lblas")
16023 (("-ltmg") "-ltmglib")
16024 (("liblapack.a") "liblapack.so")
16025 (("libblas.a") "libblas.so")
16026 (("libf2c.a") "libf2c.so"))
16027 (substitute* "src/Makefile"
16028 (("/opt") "/share")
16034 (string-append (getcwd) "/bin:" (getenv "PATH")))
16035 ;; Disable broken test
16036 (substitute* "test/Makefile"
16037 ((".*if.*hmrc_summary" m) (string-append "#" m)))
16038 ;; Only run the msa_view tests because the others fail for
16039 ;; unknown reasons.
16040 (invoke "make" "-C" "test" "msa_view"))))))
16042 `(("clapack" ,clapack)))
16045 (home-page "http://compgen.cshl.edu/phast/")
16046 (synopsis "Phylogenetic analysis with space/time models")
16048 "Phylogenetic Analysis with Space/Time models (PHAST) is a collection of
16049 command-line programs and supporting libraries for comparative and
16050 evolutionary genomics. Best known as the search engine behind the
16051 Conservation tracks in the University of California, Santa Cruz (UCSC) Genome
16052 Browser, PHAST also includes several tools for phylogenetic modeling,
16053 functional element identification, as well as utilities for manipulating
16054 alignments, trees and genomic annotations.")
16055 (license license:bsd-3)))
16057 (define-public python-gffutils
16058 ;; The latest release is older more than a year than the latest commit
16059 (let ((commit "4034c54600813b1402945e12faa91b3a53162cf1")
16062 (name "python-gffutils")
16063 (version (git-version "0.9" revision commit))
16067 (uri (git-reference
16068 (url "https://github.com/daler/gffutils")
16070 (file-name (git-file-name name version))
16073 "1rwafjdnbir5wnk0ap06ww4lra3p5frhy7mfs03rlldgfnwxymsn"))))
16074 (build-system python-build-system)
16077 (modify-phases %standard-phases
16080 ;; Tests need to access the HOME directory
16081 (setenv "HOME" "/tmp")
16082 (invoke "nosetests" "-a" "!slow")))
16083 (add-after 'unpack 'make-gz-files-writable
16085 (for-each make-file-writable
16086 (find-files "." "\\.gz"))
16089 `(("python-argcomplete" ,python-argcomplete)
16090 ("python-argh" ,python-argh)
16091 ("python-biopython" ,python-biopython)
16092 ("python-pybedtools" ,python-pybedtools)
16093 ("python-pyfaidx" ,python-pyfaidx)
16094 ("python-simplejson" ,python-simplejson)
16095 ("python-six" ,python-six)))
16097 `(("python-nose" , python-nose)))
16098 (home-page "https://github.com/daler/gffutils")
16099 (synopsis "Tool for manipulation of GFF and GTF files")
16101 "python-gffutils is a Python package for working with and manipulating
16102 the GFF and GTF format files typically used for genomic annotations. The
16103 files are loaded into a SQLite database, allowing much more complex
16104 manipulation of hierarchical features (e.g., genes, transcripts, and exons)
16105 than is possible with plain-text methods alone.")
16106 (license license:expat))))
16108 (define-public libsbml
16114 (uri (string-append "mirror://sourceforge/sbml/libsbml/"
16115 version "/stable/libSBML-"
16116 version "-core-src.tar.gz"))
16119 "0slkagrk3nfi2qsksv6b1brj6zhx4bj4bkib2sdycvrcd10ql2lh"))))
16120 (build-system cmake-build-system)
16122 `(#:test-target "test"
16124 (list "-DWITH_CHECK=ON"
16125 (string-append "-DLIBXML_LIBRARY="
16126 (assoc-ref %build-inputs "libxml2")
16128 (string-append "-DLIBXML_INCLUDE_DIR="
16129 (assoc-ref %build-inputs "libxml2")
16130 "/include/libxml2"))))
16132 `(("libxml2" ,libxml2)))
16136 (home-page "http://sbml.org/Software/libSBML")
16137 (synopsis "Process SBML files and data streams")
16138 (description "LibSBML is a library to help you read, write, manipulate,
16139 translate, and validate SBML files and data streams. The @dfn{Systems Biology
16140 Markup Language} (SBML) is an interchange format for computer models of
16141 biological processes. SBML is useful for models of metabolism, cell
16142 signaling, and more. It continues to be evolved and expanded by an
16143 international community.")
16144 (license license:lgpl2.1+)))
16146 (define-public grocsvs
16147 ;; The last release is out of date and new features have been added.
16148 (let ((commit "ecd956a65093a0b2c41849050e4512d46fecea5d")
16152 (version (git-version "0.2.6.1" revision commit))
16155 (uri (git-reference
16156 (url "https://github.com/grocsvs/grocsvs")
16158 (file-name (git-file-name name version))
16160 (base32 "14505725gr7qxc17cxxf0k6lzcwmgi64pija4mwf29aw70qn35cc"))
16161 (patches (search-patches "grocsvs-dont-use-admiral.patch"))))
16162 (build-system python-build-system)
16164 `(#:tests? #f ; No test suite.
16165 #:python ,python-2)) ; Only python-2 supported.
16167 `(("python2-h5py" ,python2-h5py)
16168 ("python2-ipython-cluster-helper" ,python2-ipython-cluster-helper)
16169 ("python2-networkx" ,python2-networkx)
16170 ("python2-psutil" ,python2-psutil)
16171 ("python2-pandas" ,python2-pandas)
16172 ("python2-pybedtools" ,python2-pybedtools)
16173 ("python2-pyfaidx" ,python2-pyfaidx)
16174 ("python2-pygraphviz" ,python2-pygraphviz)
16175 ("python2-pysam" ,python2-pysam)
16176 ("python2-scipy" ,python2-scipy)))
16177 (home-page "https://github.com/grocsvs/grocsvs")
16178 (synopsis "Genome-wide reconstruction of complex structural variants")
16180 "@dfn{Genome-wide Reconstruction of Complex Structural Variants}
16181 (GROC-SVs) is a software pipeline for identifying large-scale structural
16182 variants, performing sequence assembly at the breakpoints, and reconstructing
16183 the complex structural variants using the long-fragment information from the
16184 10x Genomics platform.")
16185 (license license:expat))))