1 ;;; GNU Guix --- Functional package management for GNU
2 ;;; Copyright © 2014, 2015, 2016, 2017, 2018, 2019, 2020, 2021 Ricardo Wurmus <rekado@elephly.net>
3 ;;; Copyright © 2015, 2016, 2017, 2018 Ben Woodcroft <donttrustben@gmail.com>
4 ;;; Copyright © 2015, 2016, 2018, 2019, 2020 Pjotr Prins <pjotr.guix@thebird.nl>
5 ;;; Copyright © 2015 Andreas Enge <andreas@enge.fr>
6 ;;; Copyright © 2016, 2020 Roel Janssen <roel@gnu.org>
7 ;;; Copyright © 2016, 2017, 2018, 2019, 2020, 2021 Efraim Flashner <efraim@flashner.co.il>
8 ;;; Copyright © 2016, 2020 Marius Bakke <mbakke@fastmail.com>
9 ;;; Copyright © 2016, 2018 Raoul Bonnal <ilpuccio.febo@gmail.com>
10 ;;; Copyright © 2017, 2018 Tobias Geerinckx-Rice <me@tobias.gr>
11 ;;; Copyright © 2017 Arun Isaac <arunisaac@systemreboot.net>
12 ;;; Copyright © 2018 Joshua Sierles, Nextjournal <joshua@nextjournal.com>
13 ;;; Copyright © 2018 Gábor Boskovits <boskovits@gmail.com>
14 ;;; Copyright © 2018, 2019, 2020, 2021 Mădălin Ionel Patrașcu <madalinionel.patrascu@mdc-berlin.de>
15 ;;; Copyright © 2019, 2020 Maxim Cournoyer <maxim.cournoyer@gmail.com>
16 ;;; Copyright © 2019 Brian Leung <bkleung89@gmail.com>
17 ;;; Copyright © 2019 Brett Gilio <brettg@gnu.org>
18 ;;; Copyright © 2020 Björn Höfling <bjoern.hoefling@bjoernhoefling.de>
19 ;;; Copyright © 2020 Jakub Kądziołka <kuba@kadziolka.net>
20 ;;; Copyright © 2020 Pierre Langlois <pierre.langlois@gmx.com>
21 ;;; Copyright © 2020 Bonface Munyoki Kilyungi <bonfacemunyoki@gmail.com>
22 ;;; Copyright © 2021 Tim Howes <timhowes@lavabit.com>
24 ;;; This file is part of GNU Guix.
26 ;;; GNU Guix is free software; you can redistribute it and/or modify it
27 ;;; under the terms of the GNU General Public License as published by
28 ;;; the Free Software Foundation; either version 3 of the License, or (at
29 ;;; your option) any later version.
31 ;;; GNU Guix is distributed in the hope that it will be useful, but
32 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
33 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
34 ;;; GNU General Public License for more details.
36 ;;; You should have received a copy of the GNU General Public License
37 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
39 (define-module (gnu packages bioinformatics)
40 #:use-module ((guix licenses) #:prefix license:)
41 #:use-module (guix packages)
42 #:use-module (guix utils)
43 #:use-module (guix download)
44 #:use-module (guix git-download)
45 #:use-module (guix hg-download)
46 #:use-module (guix build-system ant)
47 #:use-module (guix build-system gnu)
48 #:use-module (guix build-system cmake)
49 #:use-module (guix build-system go)
50 #:use-module (guix build-system haskell)
51 #:use-module (guix build-system meson)
52 #:use-module (guix build-system ocaml)
53 #:use-module (guix build-system perl)
54 #:use-module (guix build-system python)
55 #:use-module (guix build-system qt)
56 #:use-module (guix build-system r)
57 #:use-module (guix build-system ruby)
58 #:use-module (guix build-system scons)
59 #:use-module (guix build-system trivial)
60 #:use-module (guix deprecation)
61 #:use-module (gnu packages)
62 #:use-module (gnu packages assembly)
63 #:use-module (gnu packages autotools)
64 #:use-module (gnu packages algebra)
65 #:use-module (gnu packages base)
66 #:use-module (gnu packages bash)
67 #:use-module (gnu packages bison)
68 #:use-module (gnu packages bioconductor)
69 #:use-module (gnu packages boost)
70 #:use-module (gnu packages check)
71 #:use-module (gnu packages code)
72 #:use-module (gnu packages commencement)
73 #:use-module (gnu packages cmake)
74 #:use-module (gnu packages compression)
75 #:use-module (gnu packages cpio)
76 #:use-module (gnu packages cran)
77 #:use-module (gnu packages curl)
78 #:use-module (gnu packages documentation)
79 #:use-module (gnu packages databases)
80 #:use-module (gnu packages datastructures)
81 #:use-module (gnu packages dlang)
82 #:use-module (gnu packages file)
83 #:use-module (gnu packages flex)
84 #:use-module (gnu packages gawk)
85 #:use-module (gnu packages gcc)
86 #:use-module (gnu packages gd)
87 #:use-module (gnu packages golang)
88 #:use-module (gnu packages glib)
89 #:use-module (gnu packages graph)
90 #:use-module (gnu packages graphics)
91 #:use-module (gnu packages graphviz)
92 #:use-module (gnu packages groff)
93 #:use-module (gnu packages gtk)
94 #:use-module (gnu packages guile)
95 #:use-module (gnu packages guile-xyz)
96 #:use-module (gnu packages haskell-check)
97 #:use-module (gnu packages haskell-web)
98 #:use-module (gnu packages haskell-xyz)
99 #:use-module (gnu packages image)
100 #:use-module (gnu packages image-processing)
101 #:use-module (gnu packages imagemagick)
102 #:use-module (gnu packages java)
103 #:use-module (gnu packages java-compression)
104 #:use-module (gnu packages jemalloc)
105 #:use-module (gnu packages linux)
106 #:use-module (gnu packages lisp-xyz)
107 #:use-module (gnu packages logging)
108 #:use-module (gnu packages machine-learning)
109 #:use-module (gnu packages man)
110 #:use-module (gnu packages maths)
111 #:use-module (gnu packages mpi)
112 #:use-module (gnu packages ncurses)
113 #:use-module (gnu packages node)
114 #:use-module (gnu packages ocaml)
115 #:use-module (gnu packages pcre)
116 #:use-module (gnu packages parallel)
117 #:use-module (gnu packages pdf)
118 #:use-module (gnu packages perl)
119 #:use-module (gnu packages perl-check)
120 #:use-module (gnu packages pkg-config)
121 #:use-module (gnu packages popt)
122 #:use-module (gnu packages protobuf)
123 #:use-module (gnu packages python)
124 #:use-module (gnu packages python-check)
125 #:use-module (gnu packages python-compression)
126 #:use-module (gnu packages python-science)
127 #:use-module (gnu packages python-web)
128 #:use-module (gnu packages python-xyz)
129 #:use-module (gnu packages qt)
130 #:use-module (gnu packages rdf)
131 #:use-module (gnu packages readline)
132 #:use-module (gnu packages ruby)
133 #:use-module (gnu packages serialization)
134 #:use-module (gnu packages shells)
135 #:use-module (gnu packages sphinx)
136 #:use-module (gnu packages statistics)
137 #:use-module (gnu packages swig)
138 #:use-module (gnu packages tbb)
139 #:use-module (gnu packages tex)
140 #:use-module (gnu packages texinfo)
141 #:use-module (gnu packages textutils)
142 #:use-module (gnu packages time)
143 #:use-module (gnu packages tls)
144 #:use-module (gnu packages vim)
145 #:use-module (gnu packages web)
146 #:use-module (gnu packages xml)
147 #:use-module (gnu packages xorg)
148 #:use-module (srfi srfi-1)
149 #:use-module (srfi srfi-26)
150 #:use-module (ice-9 match))
152 (define-public aragorn
159 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
163 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
164 (build-system gnu-build-system)
166 `(#:tests? #f ; there are no tests
168 (modify-phases %standard-phases
178 (string-append "aragorn" ,version ".c"))
181 (lambda* (#:key outputs #:allow-other-keys)
182 (let* ((out (assoc-ref outputs "out"))
183 (bin (string-append out "/bin"))
184 (man (string-append out "/share/man/man1")))
185 (install-file "aragorn" bin)
186 (install-file "aragorn.1" man))
188 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
189 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
191 "Aragorn identifies transfer RNA, mitochondrial RNA and
192 transfer-messenger RNA from nucleotide sequences, based on homology to known
193 tRNA consensus sequences and RNA structure. It also outputs the secondary
194 structure of the predicted RNA.")
195 (license license:gpl2)))
203 ;; BamM is not available on pypi.
205 (url "https://github.com/Ecogenomics/BamM")
208 (file-name (git-file-name name version))
211 "1p83ahi984ipslxlg4yqy1gdnya9rkn1v71z8djgxkm9d2chw4c5"))
212 (modules '((guix build utils)))
215 ;; Delete bundled htslib.
216 (delete-file-recursively "c/htslib-1.3.1")
218 (build-system python-build-system)
220 `(#:python ,python-2 ; BamM is Python 2 only.
221 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
222 ;; been modified from its original form.
224 (let ((htslib (assoc-ref %build-inputs "htslib")))
225 (list "--with-libhts-lib" (string-append htslib "/lib")
226 "--with-libhts-inc" (string-append htslib "/include/htslib")))
228 (modify-phases %standard-phases
229 (add-after 'unpack 'autogen
231 (with-directory-excursion "c"
232 (let ((sh (which "sh")))
233 (for-each make-file-writable (find-files "." ".*"))
234 ;; Use autogen so that 'configure' works.
235 (substitute* "autogen.sh" (("/bin/sh") sh))
236 (setenv "CONFIG_SHELL" sh)
237 (invoke "./autogen.sh")))
240 ;; Run tests after installation so compilation only happens once.
242 (add-after 'install 'wrap-executable
243 (lambda* (#:key outputs #:allow-other-keys)
244 (let* ((out (assoc-ref outputs "out"))
245 (path (getenv "PATH")))
246 (wrap-program (string-append out "/bin/bamm")
247 `("PATH" ":" prefix (,path))))
249 (add-after 'wrap-executable 'post-install-check
250 (lambda* (#:key inputs outputs #:allow-other-keys)
252 (string-append (assoc-ref outputs "out")
257 (assoc-ref outputs "out")
259 (string-take (string-take-right
260 (assoc-ref inputs "python") 5) 3)
262 (getenv "PYTHONPATH")))
263 ;; There are 2 errors printed, but they are safe to ignore:
264 ;; 1) [E::hts_open_format] fail to open file ...
265 ;; 2) samtools view: failed to open ...
269 `(("autoconf" ,autoconf)
270 ("automake" ,automake)
273 ("python-nose" ,python2-nose)
274 ("python-pysam" ,python2-pysam)))
276 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
277 ("samtools" ,samtools)
281 ("coreutils" ,coreutils)))
283 `(("python-numpy" ,python2-numpy)))
284 (home-page "https://ecogenomics.github.io/BamM/")
285 (synopsis "Metagenomics-focused BAM file manipulator")
287 "BamM is a C library, wrapped in python, to efficiently generate and
288 parse BAM files, specifically for the analysis of metagenomic data. For
289 instance, it implements several methods to assess contig-wise read coverage.")
290 (license license:lgpl3+)))
292 (define-public bamtools
299 (url "https://github.com/pezmaster31/bamtools")
300 (commit (string-append "v" version))))
301 (file-name (git-file-name name version))
304 "0nfb2ypcx9959xnbz6wxh6py3xfizgmg8nrknxl95c507m9hmq8b"))))
305 (build-system cmake-build-system)
307 `(#:tests? #f ;no "check" target
309 (modify-phases %standard-phases
311 'configure 'set-ldflags
312 (lambda* (#:key outputs #:allow-other-keys)
316 (assoc-ref outputs "out") "/lib/bamtools"))
318 (inputs `(("zlib" ,zlib)))
319 (home-page "https://github.com/pezmaster31/bamtools")
320 (synopsis "C++ API and command-line toolkit for working with BAM data")
322 "BamTools provides both a C++ API and a command-line toolkit for handling
324 (license license:expat)))
326 (define-public bcftools
332 (uri (string-append "https://github.com/samtools/bcftools/"
334 version "/bcftools-" version ".tar.bz2"))
337 "0r508mp15pqzf8r1269kb4v5naw9zsvbwd3cz8s1yj7carsf9viw"))
338 (modules '((guix build utils)))
340 ;; Delete bundled htslib.
341 (delete-file-recursively "htslib-1.11")
343 (build-system gnu-build-system)
346 (list "--enable-libgsl")
349 (modify-phases %standard-phases
350 (add-before 'check 'patch-tests
352 (substitute* "test/test.pl"
353 (("/bin/bash") (which "bash")))
361 (home-page "https://samtools.github.io/bcftools/")
362 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
364 "BCFtools is a set of utilities that manipulate variant calls in the
365 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
366 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
367 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
368 (license (list license:gpl3+ license:expat))))
370 (define-public bcftools-1.9
371 (package (inherit bcftools)
376 (uri (string-append "https://github.com/samtools/bcftools/"
378 version "/bcftools-" version ".tar.bz2"))
381 "1j3h638i8kgihzyrlnpj82xg1b23sijibys9hvwari3fy7kd0dkg"))
382 (modules '((guix build utils)))
384 ;; Delete bundled htslib.
385 (delete-file-recursively "htslib-1.9")
387 (build-system gnu-build-system)
389 `(("htslib" ,htslib-1.9)
392 (define-public bedops
399 (url "https://github.com/bedops/bedops")
400 (commit (string-append "v" version))))
401 (file-name (git-file-name name version))
404 "0mmgsgwz5r9w76hzgxkxc9s9lkdhhaf7vr6i02b09vbswvs1fyqx"))))
405 (build-system gnu-build-system)
408 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
410 (modify-phases %standard-phases
411 (add-after 'unpack 'unpack-tarballs
413 ;; FIXME: Bedops includes tarballs of minimally patched upstream
414 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
415 ;; libraries because at least one of the libraries (zlib) is
416 ;; patched to add a C++ function definition (deflateInit2cpp).
417 ;; Until the Bedops developers offer a way to link against system
418 ;; libraries we have to build the in-tree copies of these three
421 ;; See upstream discussion:
422 ;; https://github.com/bedops/bedops/issues/124
424 ;; Unpack the tarballs to benefit from shebang patching.
425 (with-directory-excursion "third-party"
426 (invoke "tar" "xvf" "jansson-2.6.tar.bz2")
427 (invoke "tar" "xvf" "zlib-1.2.7.tar.bz2")
428 (invoke "tar" "xvf" "bzip2-1.0.6.tar.bz2"))
429 ;; Disable unpacking of tarballs in Makefile.
430 (substitute* "system.mk/Makefile.linux"
431 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
432 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
433 (substitute* "third-party/zlib-1.2.7/Makefile.in"
434 (("^SHELL=.*$") "SHELL=bash\n"))
436 (delete 'configure))))
437 (home-page "https://github.com/bedops/bedops")
438 (synopsis "Tools for high-performance genomic feature operations")
440 "BEDOPS is a suite of tools to address common questions raised in genomic
441 studies---mostly with regard to overlap and proximity relationships between
442 data sets. It aims to be scalable and flexible, facilitating the efficient
443 and accurate analysis and management of large-scale genomic data.
445 BEDOPS provides tools that perform highly efficient and scalable Boolean and
446 other set operations, statistical calculations, archiving, conversion and
447 other management of genomic data of arbitrary scale. Tasks can be easily
448 split by chromosome for distributing whole-genome analyses across a
449 computational cluster.")
450 (license license:gpl2+)))
452 (define-public bedtools
458 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
459 "download/v" version "/"
460 "bedtools-" version ".tar.gz"))
463 "0m3hk6548846w83a9s5drsczvy67n2azx41kj71n03klb2gbzwg3"))))
464 (build-system gnu-build-system)
466 '(#:test-target "test"
468 (list (string-append "prefix=" (assoc-ref %outputs "out")))
470 (modify-phases %standard-phases
471 (delete 'configure))))
473 `(("python" ,python-wrapper)))
475 `(("samtools" ,samtools-1.9)
477 (home-page "https://github.com/arq5x/bedtools2")
478 (synopsis "Tools for genome analysis and arithmetic")
480 "Collectively, the bedtools utilities are a swiss-army knife of tools for
481 a wide-range of genomics analysis tasks. The most widely-used tools enable
482 genome arithmetic: that is, set theory on the genome. For example, bedtools
483 allows one to intersect, merge, count, complement, and shuffle genomic
484 intervals from multiple files in widely-used genomic file formats such as BAM,
486 (license license:expat)))
488 ;; Later releases of bedtools produce files with more columns than
489 ;; what Ribotaper expects.
490 (define-public bedtools-2.18
491 (package (inherit bedtools)
496 (uri (string-append "https://github.com/arq5x/bedtools2/"
497 "releases/download/v" version
498 "/bedtools-" version ".tar.gz"))
501 "11rvca19ncg03kxd0wzlfx5ws7r3nisd0z8s9j9n182d8ksp2pxz"))))
503 '(#:test-target "test"
505 (modify-phases %standard-phases
508 (lambda* (#:key outputs #:allow-other-keys)
509 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
510 (for-each (lambda (file)
511 (install-file file bin))
512 (find-files "bin" ".*")))
522 (url "https://github.com/PacificBiosciences/pbbam")
524 (file-name (git-file-name name version))
527 "0h9gkrpf2lrxklxp72xfl5bi3h5zcm5hprrya9gf0hr3xwlbpp0x"))))
528 (build-system meson-build-system)
531 (modify-phases %standard-phases
532 (add-after 'unpack 'find-googletest
533 (lambda* (#:key inputs #:allow-other-keys)
534 ;; It doesn't find gtest_main because there's no pkg-config file
535 ;; for it. Find it another way.
536 (substitute* "tests/meson.build"
537 (("pbbam_gtest_dep = dependency\\('gtest_main'.*")
538 (format #f "cpp = meson.get_compiler('cpp')
539 pbbam_gtest_dep = cpp.find_library('gtest_main', dirs : '~a')\n"
540 (assoc-ref inputs "googletest"))))
542 ;; TODO: tests/pbbam_test cannot be linked
543 ;; ld: tests/59830eb@@pbbam_test@exe/src_test_Accuracy.cpp.o:
544 ;; undefined reference to symbol '_ZTIN7testing4TestE'
545 ;; ld: /gnu/store/...-googletest-1.8.0/lib/libgtest.so:
546 ;; error adding symbols: DSO missing from command line
548 #:configure-flags '("-Dtests=false")))
549 ;; These libraries are listed as "Required" in the pkg-config file.
555 ("samtools" ,samtools)))
557 `(("googletest" ,googletest)
558 ("pkg-config" ,pkg-config)
559 ("python" ,python-wrapper))) ; for tests
560 (home-page "https://github.com/PacificBiosciences/pbbam")
561 (synopsis "Work with PacBio BAM files")
563 "The pbbam software package provides components to create, query, and
564 edit PacBio BAM files and associated indices. These components include a core
565 C++ library, bindings for additional languages, and command-line utilities.
566 This library is not intended to be used as a general-purpose BAM utility - all
567 input and output BAMs must adhere to the PacBio BAM format specification.
568 Non-PacBio BAMs will cause exceptions to be thrown.")
569 (license license:bsd-3)))
571 (define-public blasr-libcpp
573 (name "blasr-libcpp")
578 (url "https://github.com/PacificBiosciences/blasr_libcpp")
580 (file-name (git-file-name name version))
583 "0cn5l42zyq67sj0g2imqkhayz2iqvv0a1pgpbmlq0qynjmsrbfd2"))))
584 (build-system meson-build-system)
587 (modify-phases %standard-phases
588 (add-after 'unpack 'link-with-hdf5
589 (lambda* (#:key inputs #:allow-other-keys)
590 (let ((hdf5 (assoc-ref inputs "hdf5")))
591 (substitute* "meson.build"
592 (("libblasr_deps = \\[" m)
595 (format #f "cpp.find_library('hdf5', dirs : '~a'), \
596 cpp.find_library('hdf5_cpp', dirs : '~a'), "
599 (add-after 'unpack 'find-googletest
600 (lambda* (#:key inputs #:allow-other-keys)
601 ;; It doesn't find gtest_main because there's no pkg-config file
602 ;; for it. Find it another way.
603 (substitute* "unittest/meson.build"
604 (("libblasr_gtest_dep = dependency\\('gtest_main'.*")
605 (format #f "cpp = meson.get_compiler('cpp')
606 libblasr_gtest_dep = cpp.find_library('gtest_main', dirs : '~a')\n"
607 (assoc-ref inputs "googletest"))))
609 ;; TODO: unittest/libblasr_unittest cannot be linked
610 ;; ld: ;; unittest/df08227@@libblasr_unittest@exe/alignment_utils_FileUtils_gtest.cpp.o:
611 ;; undefined reference to symbol
612 ;; '_ZN7testing8internal9DeathTest6CreateEPKcPKNS0_2REES3_iPPS1_'
613 ;; ld: /gnu/store/...-googletest-1.8.0/lib/libgtest.so:
614 ;; error adding symbols: DSO missing from command line
616 #:configure-flags '("-Dtests=false")))
623 `(("googletest" ,googletest)
624 ("pkg-config" ,pkg-config)))
625 (home-page "https://github.com/PacificBiosciences/blasr_libcpp")
626 (synopsis "Library for analyzing PacBio genomic sequences")
628 "This package provides three libraries used by applications for analyzing
629 PacBio genomic sequences. This library contains three sub-libraries: pbdata,
631 (license license:bsd-3)))
640 (url "https://github.com/PacificBiosciences/blasr")
642 (file-name (git-file-name name version))
645 "1skgy2mvz8gsgfh1gc2nfgwvpyzb1hpmp2cf2773h5wsj8nw22kl"))))
646 (build-system meson-build-system)
649 (modify-phases %standard-phases
650 (add-after 'unpack 'link-with-hdf5
651 (lambda* (#:key inputs #:allow-other-keys)
652 (let ((hdf5 (assoc-ref inputs "hdf5")))
653 (substitute* "meson.build"
654 (("blasr_deps = \\[" m)
657 (format #f "cpp.find_library('hdf5', dirs : '~a'), \
658 cpp.find_library('hdf5_cpp', dirs : '~a'), "
661 ;; Tests require "cram" executable, which is not packaged.
663 #:configure-flags '("-Dtests=false")))
666 ("blasr-libcpp" ,blasr-libcpp)
671 `(("pkg-config" ,pkg-config)))
672 (home-page "https://github.com/PacificBiosciences/blasr")
673 (synopsis "PacBio long read aligner")
675 "Blasr is a genomic sequence aligner for processing PacBio long reads.")
676 (license license:bsd-3)))
678 (define-public ribotaper
684 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
685 "files/RiboTaper/RiboTaper_Version_"
689 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
690 (build-system gnu-build-system)
693 (modify-phases %standard-phases
694 (add-after 'install 'wrap-executables
695 (lambda* (#:key inputs outputs #:allow-other-keys)
696 (let* ((out (assoc-ref outputs "out")))
699 (wrap-program (string-append out "/bin/" script)
700 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
701 '("create_annotations_files.bash"
702 "create_metaplots.bash"
703 "Ribotaper_ORF_find.sh"
707 `(("bedtools" ,bedtools-2.18)
708 ("samtools" ,samtools-0.1)
709 ("r-minimal" ,r-minimal)
710 ("r-foreach" ,r-foreach)
711 ("r-xnomial" ,r-xnomial)
713 ("r-multitaper" ,r-multitaper)
714 ("r-seqinr" ,r-seqinr)))
715 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
716 (synopsis "Define translated ORFs using ribosome profiling data")
718 "Ribotaper is a method for defining translated @dfn{open reading
719 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
720 provides the Ribotaper pipeline.")
721 (license license:gpl3+)))
723 (define-public ribodiff
731 (url "https://github.com/ratschlab/RiboDiff")
732 (commit (string-append "v" version))))
733 (file-name (git-file-name name version))
736 "0x75nlp7qnmm64jasbi6l21f2cy99r2cjyl6b4hr8zf2bq22drnz"))))
737 (build-system python-build-system)
741 (modify-phases %standard-phases
742 ;; Generate an installable executable script wrapper.
743 (add-after 'unpack 'patch-setup.py
745 (substitute* "setup.py"
746 (("^(.*)packages=.*" line prefix)
747 (string-append line "\n"
748 prefix "scripts=['scripts/TE.py'],\n")))
751 `(("python-numpy" ,python2-numpy)
752 ("python-matplotlib" ,python2-matplotlib)
753 ("python-scipy" ,python2-scipy)
754 ("python-statsmodels" ,python2-statsmodels)))
756 `(("python-mock" ,python2-mock)
757 ("python-nose" ,python2-nose)))
758 (home-page "https://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
759 (synopsis "Detect translation efficiency changes from ribosome footprints")
760 (description "RiboDiff is a statistical tool that detects the protein
761 translational efficiency change from Ribo-Seq (ribosome footprinting) and
762 RNA-Seq data. It uses a generalized linear model to detect genes showing
763 difference in translational profile taking mRNA abundance into account. It
764 facilitates us to decipher the translational regulation that behave
765 independently with transcriptional regulation.")
766 (license license:gpl3+)))
768 (define-public bioawk
775 (url "https://github.com/lh3/bioawk")
776 (commit (string-append "v" version))))
777 (file-name (git-file-name name version))
780 "1pxc3zdnirxbf9a0az698hd8xdik7qkhypm7v6hn922x8y9qmspm"))))
781 (build-system gnu-build-system)
787 `(#:tests? #f ; There are no tests to run.
788 ;; Bison must generate files, before other targets can build.
791 (modify-phases %standard-phases
792 (delete 'configure) ; There is no configure phase.
794 (lambda* (#:key outputs #:allow-other-keys)
795 (let* ((out (assoc-ref outputs "out"))
796 (bin (string-append out "/bin"))
797 (man (string-append out "/share/man/man1")))
799 (copy-file "awk.1" (string-append man "/bioawk.1"))
800 (install-file "bioawk" bin))
802 (home-page "https://github.com/lh3/bioawk")
803 (synopsis "AWK with bioinformatics extensions")
804 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
805 support of several common biological data formats, including optionally gzip'ed
806 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
807 also adds a few built-in functions and a command line option to use TAB as the
808 input/output delimiter. When the new functionality is not used, bioawk is
809 intended to behave exactly the same as the original BWK awk.")
810 (license license:x11)))
812 (define-public python-pybedtools
814 (name "python-pybedtools")
818 (uri (pypi-uri "pybedtools" version))
821 "14w5i40gi25clrr7h4wa2pcpnyipya8hrqi7nq77553zc5wf0df0"))))
822 (build-system python-build-system)
824 `(#:modules ((ice-9 ftw)
828 (guix build python-build-system))
829 ;; See https://github.com/daler/pybedtools/issues/192
831 (modify-phases %standard-phases
832 (add-after 'unpack 'disable-broken-tests
834 (substitute* "pybedtools/test/test_scripts.py"
835 ;; This test freezes.
836 (("def test_intron_exon_reads")
837 "def _do_not_test_intron_exon_reads")
838 ;; This test fails in the Python 2 build.
839 (("def test_venn_mpl")
840 "def _do_not_test_venn_mpl"))
841 (substitute* "pybedtools/test/test_helpers.py"
842 ;; Requires internet access.
843 (("def test_chromsizes")
844 "def _do_not_test_chromsizes")
845 ;; Broken as a result of the workaround used in the check phase
846 ;; (see: https://github.com/daler/pybedtools/issues/192).
847 (("def test_getting_example_beds")
848 "def _do_not_test_getting_example_beds"))
849 ;; This issue still occurs on python2
850 (substitute* "pybedtools/test/test_issues.py"
851 (("def test_issue_303")
852 "def _test_issue_303"))
854 ;; TODO: Remove phase after it's part of PYTHON-BUILD-SYSTEM.
856 ;; Force the Cythonization of C++ files to guard against compilation
858 (add-after 'unpack 'remove-cython-generated-files
860 (let ((cython-sources (map (cut string-drop-right <> 4)
861 (find-files "." "\\.pyx$")))
862 (c/c++-files (find-files "." "\\.(c|cpp|cxx)$")))
863 (define (strip-extension filename)
864 (string-take filename (string-index-right filename #\.)))
865 (define (cythonized? c/c++-file)
866 (member (strip-extension c/c++-file) cython-sources))
867 (for-each delete-file (filter cythonized? c/c++-files))
869 (add-after 'remove-cython-generated-files 'generate-cython-extensions
871 (invoke "python" "setup.py" "cythonize")))
874 (let* ((cwd (getcwd))
875 (build-root-directory (string-append cwd "/build/"))
876 (build (string-append
878 (find (cut string-prefix? "lib" <>)
879 (scandir (string-append
880 build-root-directory)))))
881 (scripts (string-append
883 (find (cut string-prefix? "scripts" <>)
884 (scandir build-root-directory)))))
886 (string-append build ":" (getenv "PYTHONPATH")))
887 ;; Executable scripts such as 'intron_exon_reads.py' must be
888 ;; available in the PATH.
890 (string-append scripts ":" (getenv "PATH"))))
891 ;; The tests need to be run from elsewhere...
892 (mkdir-p "/tmp/test")
893 (copy-recursively "pybedtools/test" "/tmp/test")
894 (with-directory-excursion "/tmp/test"
895 (invoke "pytest" "-v" "--doctest-modules")))))))
897 `(("bedtools" ,bedtools)
898 ("samtools" ,samtools)
899 ("python-matplotlib" ,python-matplotlib)
900 ("python-pysam" ,python-pysam)
901 ("python-pyyaml" ,python-pyyaml)))
903 `(("python-numpy" ,python-numpy)
904 ("python-pandas" ,python-pandas)
905 ("python-cython" ,python-cython)
906 ("kentutils" ,kentutils) ; for bedGraphToBigWig
907 ("python-six" ,python-six)
908 ;; For the test suite.
909 ("python-pytest" ,python-pytest)
910 ("python-psutil" ,python-psutil)))
911 (home-page "https://pythonhosted.org/pybedtools/")
912 (synopsis "Python wrapper for BEDtools programs")
914 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
915 which are widely used for genomic interval manipulation or \"genome algebra\".
916 pybedtools extends BEDTools by offering feature-level manipulations from with
918 (license license:gpl2+)))
920 (define-public python2-pybedtools
921 (let ((pybedtools (package-with-python2 python-pybedtools)))
925 `(("python2-pathlib" ,python2-pathlib)
926 ,@(package-native-inputs pybedtools))))))
928 (define-public python-biom-format
930 (name "python-biom-format")
935 ;; Use GitHub as source because PyPI distribution does not contain
936 ;; test data: https://github.com/biocore/biom-format/issues/693
938 (url "https://github.com/biocore/biom-format")
940 (file-name (git-file-name name version))
943 "1rna16lyk5aqhnv0dp77wwaplias93f1vw28ad3jmyw6hwkai05v"))
944 (modules '((guix build utils)))
946 ;; Delete generated C files.
947 (for-each delete-file (find-files "." "\\.c"))
949 (build-system python-build-system)
952 (modify-phases %standard-phases
953 (add-after 'unpack 'use-cython
954 (lambda _ (setenv "USE_CYTHON" "1") #t))
955 (add-after 'unpack 'disable-broken-tests
957 (substitute* "biom/tests/test_cli/test_validate_table.py"
958 (("^(.+)def test_invalid_hdf5" m indent)
959 (string-append indent
960 "@npt.dec.skipif(True, msg='Guix')\n"
962 (substitute* "biom/tests/test_table.py"
963 (("^(.+)def test_from_hdf5_issue_731" m indent)
964 (string-append indent
965 "@npt.dec.skipif(True, msg='Guix')\n"
968 (add-before 'reset-gzip-timestamps 'make-files-writable
969 (lambda* (#:key outputs #:allow-other-keys)
970 (let ((out (assoc-ref outputs "out")))
971 (for-each (lambda (file) (chmod file #o644))
972 (find-files out "\\.gz"))
975 `(("python-numpy" ,python-numpy)
976 ("python-scipy" ,python-scipy)
977 ("python-flake8" ,python-flake8)
978 ("python-future" ,python-future)
979 ("python-click" ,python-click)
980 ("python-h5py" ,python-h5py)
981 ;; FIXME: Upgrade to pandas 1.0 when
982 ;; https://github.com/biocore/biom-format/issues/837 is resolved.
983 ("python-pandas" ,python-pandas-0.25)))
985 `(("python-cython" ,python-cython)
986 ("python-pytest" ,python-pytest)
987 ("python-pytest-cov" ,python-pytest-cov)
988 ("python-nose" ,python-nose)))
989 (home-page "http://www.biom-format.org")
990 (synopsis "Biological Observation Matrix (BIOM) format utilities")
992 "The BIOM file format is designed to be a general-use format for
993 representing counts of observations e.g. operational taxonomic units, KEGG
994 orthology groups or lipid types, in one or more biological samples
995 e.g. microbiome samples, genomes, metagenomes.")
996 (license license:bsd-3)
997 (properties `((python2-variant . ,(delay python2-biom-format))))))
999 (define-public python2-biom-format
1000 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
1004 (substitute-keyword-arguments (package-arguments base)
1006 `(modify-phases ,phases
1007 ;; Do not require the unmaintained pyqi library.
1008 (add-after 'unpack 'remove-pyqi
1010 (substitute* "setup.py"
1011 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
1014 (define-public python-pairtools
1016 (name "python-pairtools")
1021 (url "https://github.com/mirnylab/pairtools")
1022 (commit (string-append "v" version))))
1023 (file-name (git-file-name name version))
1026 "0gr8y13q7sd6yai6df4aavl2470n1f9s3cib6r473z4hr8hcbwmc"))))
1027 (build-system python-build-system)
1030 (modify-phases %standard-phases
1031 (add-after 'unpack 'fix-references
1033 (substitute* '("pairtools/pairtools_merge.py"
1034 "pairtools/pairtools_sort.py")
1035 (("/bin/bash") (which "bash")))
1038 (lambda* (#:key inputs outputs #:allow-other-keys)
1039 (add-installed-pythonpath inputs outputs)
1040 (with-directory-excursion "/tmp"
1041 (invoke "pytest" "-v")))))))
1043 `(("python-cython" ,python-cython)
1044 ("python-nose" ,python-nose)
1045 ("python-pytest" ,python-pytest)))
1047 `(("python" ,python-wrapper)))
1049 `(("htslib" ,htslib) ; for bgzip, looked up in PATH
1050 ("samtools" ,samtools) ; looked up in PATH
1051 ("lz4" ,lz4) ; for lz4c
1052 ("python-click" ,python-click)
1053 ("python-numpy" ,python-numpy)))
1054 (home-page "https://github.com/mirnylab/pairtools")
1055 (synopsis "Process mapped Hi-C data")
1056 (description "Pairtools is a simple and fast command-line framework to
1057 process sequencing data from a Hi-C experiment. Process pair-end sequence
1058 alignments and perform the following operations:
1061 @item detect ligation junctions (a.k.a. Hi-C pairs) in aligned paired-end
1062 sequences of Hi-C DNA molecules
1063 @item sort @code{.pairs} files for downstream analyses
1064 @item detect, tag and remove PCR/optical duplicates
1065 @item generate extensive statistics of Hi-C datasets
1066 @item select Hi-C pairs given flexibly defined criteria
1067 @item restore @code{.sam} alignments from Hi-C pairs.
1070 (license license:expat)))
1072 (define-public bioperl-minimal
1073 (let* ((inputs `(("perl-module-build" ,perl-module-build)
1074 ("perl-data-stag" ,perl-data-stag)
1075 ("perl-libwww" ,perl-libwww)
1076 ("perl-uri" ,perl-uri)))
1078 (map (compose package-name cadr)
1081 (map (compose package-transitive-target-inputs cadr) inputs))))))
1083 (name "bioperl-minimal")
1089 (url "https://github.com/bioperl/bioperl-live")
1090 (commit (string-append "release-"
1091 (string-map (lambda (c)
1093 #\- c)) version)))))
1094 (file-name (git-file-name name version))
1097 "0wl8yvzcls59pwwk6m8ahy87pwg6nnibzy5cldbvmcwg2x2w7783"))))
1098 (build-system perl-build-system)
1101 (modify-phases %standard-phases
1103 'install 'wrap-programs
1104 (lambda* (#:key outputs #:allow-other-keys)
1105 ;; Make sure all executables in "bin" find the required Perl
1106 ;; modules at runtime. As the PERL5LIB variable contains also
1107 ;; the paths of native inputs, we pick the transitive target
1108 ;; inputs from %build-inputs.
1109 (let* ((out (assoc-ref outputs "out"))
1110 (bin (string-append out "/bin/"))
1112 (cons (string-append out "/lib/perl5/site_perl")
1114 (assoc-ref %build-inputs name))
1115 ',transitive-inputs))
1117 (for-each (lambda (file)
1119 `("PERL5LIB" ":" prefix (,path))))
1120 (find-files bin "\\.pl$"))
1124 `(("perl-test-most" ,perl-test-most)))
1125 (home-page "https://metacpan.org/release/BioPerl")
1126 (synopsis "Bioinformatics toolkit")
1128 "BioPerl is the product of a community effort to produce Perl code which
1129 is useful in biology. Examples include Sequence objects, Alignment objects
1130 and database searching objects. These objects not only do what they are
1131 advertised to do in the documentation, but they also interact - Alignment
1132 objects are made from the Sequence objects, Sequence objects have access to
1133 Annotation and SeqFeature objects and databases, Blast objects can be
1134 converted to Alignment objects, and so on. This means that the objects
1135 provide a coordinated and extensible framework to do computational biology.")
1136 (license license:perl-license))))
1138 (define-public python-biopython
1140 (name "python-biopython")
1144 ;; use PyPi rather than biopython.org to ease updating
1145 (uri (pypi-uri "biopython" version))
1148 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
1149 (build-system python-build-system)
1152 (modify-phases %standard-phases
1153 (add-before 'check 'set-home
1154 ;; Some tests require a home directory to be set.
1155 (lambda _ (setenv "HOME" "/tmp") #t)))))
1157 `(("python-numpy" ,python-numpy)))
1158 (home-page "https://biopython.org/")
1159 (synopsis "Tools for biological computation in Python")
1161 "Biopython is a set of tools for biological computation including parsers
1162 for bioinformatics files into Python data structures; interfaces to common
1163 bioinformatics programs; a standard sequence class and tools for performing
1164 common operations on them; code to perform data classification; code for
1165 dealing with alignments; code making it easy to split up parallelizable tasks
1166 into separate processes; and more.")
1167 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
1169 (define-public python2-biopython
1170 (package-with-python2 python-biopython))
1172 (define-public python-fastalite
1174 (name "python-fastalite")
1179 (uri (pypi-uri "fastalite" version))
1182 "1qli6pxp77i9xn2wfciq2zaxhl82bdxb33cpzqzj1z25yd036wqj"))))
1183 (build-system python-build-system)
1185 `(#:tests? #f)) ; Test data is not distributed.
1186 (home-page "https://github.com/nhoffman/fastalite")
1187 (synopsis "Simplest possible FASTA parser")
1188 (description "This library implements a FASTA and a FASTQ parser without
1189 relying on a complex dependency tree.")
1190 (license license:expat)))
1192 (define-public python2-fastalite
1193 (package-with-python2 python-fastalite))
1195 (define-public bpp-core
1196 ;; The last release was in 2014 and the recommended way to install from source
1197 ;; is to clone the git repository, so we do this.
1198 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1199 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
1202 (version (string-append "2.2.0-1." (string-take commit 7)))
1206 (url "http://biopp.univ-montp2.fr/git/bpp-core")
1208 (file-name (string-append name "-" version "-checkout"))
1211 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
1212 (build-system cmake-build-system)
1214 `(#:parallel-build? #f))
1215 (home-page "http://biopp.univ-montp2.fr")
1216 (synopsis "C++ libraries for Bioinformatics")
1218 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1219 analysis, phylogenetics, molecular evolution and population genetics. It is
1220 Object Oriented and is designed to be both easy to use and computer efficient.
1221 Bio++ intends to help programmers to write computer expensive programs, by
1222 providing them a set of re-usable tools.")
1223 (license license:cecill-c))))
1225 (define-public bpp-phyl
1226 ;; The last release was in 2014 and the recommended way to install from source
1227 ;; is to clone the git repository, so we do this.
1228 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1229 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
1232 (version (string-append "2.2.0-1." (string-take commit 7)))
1236 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
1238 (file-name (string-append name "-" version "-checkout"))
1241 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
1242 (build-system cmake-build-system)
1244 `(#:parallel-build? #f
1245 ;; If out-of-source, test data is not copied into the build directory
1246 ;; so the tests fail.
1247 #:out-of-source? #f))
1249 `(("bpp-core" ,bpp-core)
1250 ("bpp-seq" ,bpp-seq)))
1251 (home-page "http://biopp.univ-montp2.fr")
1252 (synopsis "Bio++ phylogenetic Library")
1254 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1255 analysis, phylogenetics, molecular evolution and population genetics. This
1256 library provides phylogenetics-related modules.")
1257 (license license:cecill-c))))
1259 (define-public bpp-popgen
1260 ;; The last release was in 2014 and the recommended way to install from source
1261 ;; is to clone the git repository, so we do this.
1262 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1263 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
1266 (version (string-append "2.2.0-1." (string-take commit 7)))
1270 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
1272 (file-name (string-append name "-" version "-checkout"))
1275 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
1276 (build-system cmake-build-system)
1278 `(#:parallel-build? #f
1279 #:tests? #f)) ; There are no tests.
1281 `(("bpp-core" ,bpp-core)
1282 ("bpp-seq" ,bpp-seq)))
1283 (home-page "http://biopp.univ-montp2.fr")
1284 (synopsis "Bio++ population genetics library")
1286 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1287 analysis, phylogenetics, molecular evolution and population genetics. This
1288 library provides population genetics-related modules.")
1289 (license license:cecill-c))))
1291 (define-public bpp-seq
1292 ;; The last release was in 2014 and the recommended way to install from source
1293 ;; is to clone the git repository, so we do this.
1294 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1295 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
1298 (version (string-append "2.2.0-1." (string-take commit 7)))
1302 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
1304 (file-name (string-append name "-" version "-checkout"))
1307 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
1308 (build-system cmake-build-system)
1310 `(#:parallel-build? #f
1311 ;; If out-of-source, test data is not copied into the build directory
1312 ;; so the tests fail.
1313 #:out-of-source? #f))
1315 `(("bpp-core" ,bpp-core)))
1316 (home-page "http://biopp.univ-montp2.fr")
1317 (synopsis "Bio++ sequence library")
1319 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1320 analysis, phylogenetics, molecular evolution and population genetics. This
1321 library provides sequence-related modules.")
1322 (license license:cecill-c))))
1324 (define-public bppsuite
1325 ;; The last release was in 2014 and the recommended way to install from source
1326 ;; is to clone the git repository, so we do this.
1327 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1328 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
1331 (version (string-append "2.2.0-1." (string-take commit 7)))
1335 (url "http://biopp.univ-montp2.fr/git/bppsuite")
1337 (file-name (string-append name "-" version "-checkout"))
1340 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
1341 (build-system cmake-build-system)
1343 `(#:parallel-build? #f
1344 #:tests? #f)) ; There are no tests.
1348 ("texinfo" ,texinfo)))
1350 `(("bpp-core" ,bpp-core)
1351 ("bpp-seq" ,bpp-seq)
1352 ("bpp-phyl" ,bpp-phyl)
1353 ("bpp-phyl" ,bpp-popgen)))
1354 (home-page "http://biopp.univ-montp2.fr")
1355 (synopsis "Bioinformatics tools written with the Bio++ libraries")
1357 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1358 analysis, phylogenetics, molecular evolution and population genetics. This
1359 package provides command line tools using the Bio++ library.")
1360 (license license:cecill-c))))
1362 (define-public blast+
1369 "https://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
1370 version "/ncbi-blast-" version "+-src.tar.gz"))
1373 "11kvrrl0mcwww6530r55hccpg3x3msmhr3051fwnjbq8rzg2j1qi"))
1374 (modules '((guix build utils)))
1377 ;; Remove bundled bzip2, zlib and pcre.
1378 (delete-file-recursively "c++/src/util/compress/bzip2")
1379 (delete-file-recursively "c++/src/util/compress/zlib")
1380 (delete-file-recursively "c++/src/util/regexp")
1381 (substitute* "c++/src/util/compress/Makefile.in"
1382 (("bzip2 zlib api") "api"))
1383 ;; Remove useless msbuild directory
1384 (delete-file-recursively
1385 "c++/src/build-system/project_tree_builder/msbuild")
1387 (build-system gnu-build-system)
1389 `(;; There are two(!) tests for this massive library, and both fail with
1390 ;; "unparsable timing stats".
1391 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
1392 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
1395 #:parallel-build? #f ; not supported
1397 (modify-phases %standard-phases
1398 (add-before 'configure 'set-HOME
1399 ;; $HOME needs to be set at some point during the configure phase
1400 (lambda _ (setenv "HOME" "/tmp") #t))
1401 (add-after 'unpack 'enter-dir
1402 (lambda _ (chdir "c++") #t))
1403 (add-after 'enter-dir 'fix-build-system
1405 (define (which* cmd)
1406 (cond ((string=? cmd "date")
1407 ;; make call to "date" deterministic
1412 (format (current-error-port)
1413 "WARNING: Unable to find absolute path for ~s~%"
1417 ;; Rewrite hardcoded paths to various tools
1418 (substitute* (append '("src/build-system/configure.ac"
1419 "src/build-system/configure"
1420 "src/build-system/helpers/run_with_lock.c"
1421 "scripts/common/impl/if_diff.sh"
1422 "scripts/common/impl/run_with_lock.sh"
1423 "src/build-system/Makefile.configurables.real"
1424 "src/build-system/Makefile.in.top"
1425 "src/build-system/Makefile.meta.gmake=no"
1426 "src/build-system/Makefile.meta.in"
1427 "src/build-system/Makefile.meta_l"
1428 "src/build-system/Makefile.meta_p"
1429 "src/build-system/Makefile.meta_r"
1430 "src/build-system/Makefile.mk.in"
1431 "src/build-system/Makefile.requirements"
1432 "src/build-system/Makefile.rules_with_autodep.in")
1433 (find-files "scripts/common/check" "\\.sh$"))
1434 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1435 (or (which* cmd) all)))
1437 (substitute* (find-files "src/build-system" "^config.*")
1438 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1441 ;; rewrite "/var/tmp" in check script
1442 (substitute* "scripts/common/check/check_make_unix.sh"
1443 (("/var/tmp") "/tmp"))
1445 ;; do not reset PATH
1446 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1448 (("action=/bin/") "action=")
1449 (("export PATH") ":"))
1452 (lambda* (#:key inputs outputs #:allow-other-keys)
1453 (let ((out (assoc-ref outputs "out"))
1454 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1455 (include (string-append (assoc-ref outputs "include")
1456 "/include/ncbi-tools++")))
1457 ;; The 'configure' script doesn't recognize things like
1458 ;; '--enable-fast-install'.
1459 (invoke "./configure.orig"
1460 (string-append "--with-build-root=" (getcwd) "/build")
1461 (string-append "--prefix=" out)
1462 (string-append "--libdir=" lib)
1463 (string-append "--includedir=" include)
1464 (string-append "--with-bz2="
1465 (assoc-ref inputs "bzip2"))
1466 (string-append "--with-z="
1467 (assoc-ref inputs "zlib"))
1468 (string-append "--with-pcre="
1469 (assoc-ref inputs "pcre"))
1470 ;; Each library is built twice by default, once
1471 ;; with "-static" in its name, and again
1476 (outputs '("out" ; 21 MB
1485 ("python" ,python-wrapper)))
1488 (home-page "https://blast.ncbi.nlm.nih.gov")
1489 (synopsis "Basic local alignment search tool")
1491 "BLAST is a popular method of performing a DNA or protein sequence
1492 similarity search, using heuristics to produce results quickly. It also
1493 calculates an “expect value” that estimates how many matches would have
1494 occurred at a given score by chance, which can aid a user in judging how much
1495 confidence to have in an alignment.")
1496 ;; Most of the sources are in the public domain, with the following
1499 ;; * ./c++/include/util/bitset/
1500 ;; * ./c++/src/html/ncbi_menu*.js
1502 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1504 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1506 ;; * ./c++/src/corelib/teamcity_*
1507 (license (list license:public-domain
1513 (define-public bless
1519 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1523 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1524 (modules '((guix build utils)))
1527 ;; Remove bundled boost, pigz, zlib, and .git directory
1528 ;; FIXME: also remove bundled sources for murmurhash3 and
1529 ;; kmc once packaged.
1530 (delete-file-recursively "boost")
1531 (delete-file-recursively "pigz")
1532 (delete-file-recursively "google-sparsehash")
1533 (delete-file-recursively "zlib")
1534 (delete-file-recursively ".git")
1536 (build-system gnu-build-system)
1538 '(#:tests? #f ;no "check" target
1540 (list (string-append "ZLIB="
1541 (assoc-ref %build-inputs "zlib:static")
1543 (string-append "LDFLAGS="
1544 (string-join '("-lboost_filesystem"
1550 (modify-phases %standard-phases
1551 (add-after 'unpack 'do-not-build-bundled-pigz
1552 (lambda* (#:key inputs outputs #:allow-other-keys)
1553 (substitute* "Makefile"
1554 (("cd pigz/pigz-2.3.3; make") ""))
1556 (add-after 'unpack 'patch-paths-to-executables
1557 (lambda* (#:key inputs outputs #:allow-other-keys)
1558 (substitute* "parse_args.cpp"
1559 (("kmc_binary = .*")
1560 (string-append "kmc_binary = \""
1561 (assoc-ref outputs "out")
1563 (("pigz_binary = .*")
1564 (string-append "pigz_binary = \""
1565 (assoc-ref inputs "pigz")
1569 (lambda* (#:key outputs #:allow-other-keys)
1570 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1571 (for-each (lambda (file)
1572 (install-file file bin))
1573 '("bless" "kmc/bin/kmc"))
1575 (delete 'configure))))
1579 `(("openmpi" ,openmpi)
1581 ("sparsehash" ,sparsehash)
1583 ("zlib:static" ,zlib "static")
1585 (supported-systems '("x86_64-linux"))
1586 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1587 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1589 "@dfn{Bloom-filter-based error correction solution for high-throughput
1590 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1591 correction tool for genomic reads produced by @dfn{Next-generation
1592 sequencing} (NGS). BLESS produces accurate correction results with much less
1593 memory compared with previous solutions and is also able to tolerate a higher
1594 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1595 errors at the end of reads.")
1596 (license license:gpl3+)))
1598 (define-public bowtie
1605 (url "https://github.com/BenLangmead/bowtie2")
1606 (commit (string-append "v" version))))
1607 (file-name (git-file-name name version))
1610 "1zl3cf327y2p7p03cavymbh7b00djc7lncfaqih33n96iy9q8ibp"))
1611 (modules '((guix build utils)))
1614 (substitute* "Makefile"
1615 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1616 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1617 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
1619 (build-system gnu-build-system)
1624 (string-append "prefix=" (assoc-ref %outputs "out")))
1626 (modify-phases %standard-phases
1631 "scripts/test/simple_tests.pl"
1632 "--bowtie2=./bowtie2"
1633 "--bowtie2-build=./bowtie2-build")
1638 ("python" ,python-wrapper)))
1641 ("perl-clone" ,perl-clone)
1642 ("perl-test-deep" ,perl-test-deep)
1643 ("perl-test-simple" ,perl-test-simple)))
1644 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1645 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1647 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1648 reads to long reference sequences. It is particularly good at aligning reads
1649 of about 50 up to 100s or 1,000s of characters, and particularly good at
1650 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1651 genome with an FM Index to keep its memory footprint small: for the human
1652 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1653 gapped, local, and paired-end alignment modes.")
1654 (supported-systems '("x86_64-linux"))
1655 (license license:gpl3+)))
1657 (define-public bowtie1
1663 (uri (string-append "mirror://sourceforge/bowtie-bio/bowtie/"
1664 version "/bowtie-" version "-src.zip"))
1667 "11dbihdnrizc6qhx9xsw77w3q5ssx642alaqzvhxx32ak9glvq04"))
1668 (modules '((guix build utils)))
1670 '(substitute* "Makefile"
1671 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1672 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1673 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1674 (build-system gnu-build-system)
1676 '(#:tests? #f ; no "check" target
1678 (list "CC=gcc" "all"
1679 (string-append "prefix=" (assoc-ref %outputs "out")))
1681 (modify-phases %standard-phases
1682 (delete 'configure))))
1684 `(("python-wrapper" ,python-wrapper)
1687 (supported-systems '("x86_64-linux"))
1688 (home-page "http://bowtie-bio.sourceforge.net/index.shtml")
1689 (synopsis "Fast aligner for short nucleotide sequence reads")
1691 "Bowtie is a fast, memory-efficient short read aligner. It aligns short
1692 DNA sequences (reads) to the human genome at a rate of over 25 million 35-bp
1693 reads per hour. Bowtie indexes the genome with a Burrows-Wheeler index to
1694 keep its memory footprint small: typically about 2.2 GB for the human
1695 genome (2.9 GB for paired-end).")
1696 (license license:artistic2.0)))
1698 (define-public tophat
1705 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1709 "19add02kv2xhd6ihd779dr7x35ggym3jqr0m5c4315i1yfb0p11p"))
1710 (modules '((guix build utils)))
1713 ;; Remove bundled SeqAn and samtools
1714 (delete-file-recursively "src/SeqAn-1.4.2")
1715 (delete-file-recursively "src/samtools-0.1.18")
1717 (build-system gnu-build-system)
1719 '(#:parallel-build? #f ; not supported
1721 (modify-phases %standard-phases
1722 (add-after 'set-paths 'hide-default-gcc
1723 (lambda* (#:key inputs #:allow-other-keys)
1724 (let ((gcc (assoc-ref inputs "gcc")))
1725 ;; Remove the default GCC from CPLUS_INCLUDE_PATH to prevent
1726 ;; conflicts with the GCC 5 input.
1727 (setenv "CPLUS_INCLUDE_PATH"
1729 (delete (string-append gcc "/include/c++")
1730 (string-split (getenv "CPLUS_INCLUDE_PATH") #\:))
1733 (add-after 'unpack 'use-system-samtools
1734 (lambda* (#:key inputs #:allow-other-keys)
1735 (substitute* "src/Makefile.in"
1736 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1737 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1738 (("SAMPROG = samtools_0\\.1\\.18") "")
1739 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1740 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1741 (substitute* '("src/common.cpp"
1743 (("samtools_0.1.18") (which "samtools")))
1744 (substitute* '("src/common.h"
1745 "src/bam2fastx.cpp")
1746 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1747 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1748 (substitute* '("src/bwt_map.h"
1750 "src/align_status.h")
1751 (("#include <bam.h>") "#include <samtools/bam.h>")
1752 (("#include <sam.h>") "#include <samtools/sam.h>"))
1755 `(("gcc@5" ,gcc-5))) ;; doesn't build with later versions
1759 ("ncurses" ,ncurses)
1761 ("python" ,python-2)
1762 ("samtools" ,samtools-0.1)
1765 (home-page "https://ccb.jhu.edu/software/tophat/index.shtml")
1766 (synopsis "Spliced read mapper for RNA-Seq data")
1768 "TopHat is a fast splice junction mapper for nucleotide sequence
1769 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1770 mammalian-sized genomes using the ultra high-throughput short read
1771 aligner Bowtie, and then analyzes the mapping results to identify
1772 splice junctions between exons.")
1773 ;; TopHat is released under the Boost Software License, Version 1.0
1774 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1775 (license license:boost1.0)))
1784 "https://github.com/lh3/bwa/releases/download/v"
1785 version "/bwa-" version ".tar.bz2"))
1788 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1789 (build-system gnu-build-system)
1791 '(#:tests? #f ;no "check" target
1793 (modify-phases %standard-phases
1795 (lambda* (#:key outputs #:allow-other-keys)
1796 (let* ((out (assoc-ref outputs "out"))
1797 (bin (string-append out "/bin"))
1798 (lib (string-append out "/lib"))
1799 (doc (string-append out "/share/doc/bwa"))
1800 (man (string-append out "/share/man/man1")))
1801 (install-file "bwa" bin)
1802 (install-file "libbwa.a" lib)
1803 (install-file "README.md" doc)
1804 (install-file "bwa.1" man))
1806 ;; no "configure" script
1807 (delete 'configure))))
1808 (inputs `(("zlib" ,zlib)))
1809 ;; Non-portable SSE instructions are used so building fails on platforms
1810 ;; other than x86_64.
1811 (supported-systems '("x86_64-linux"))
1812 (home-page "http://bio-bwa.sourceforge.net/")
1813 (synopsis "Burrows-Wheeler sequence aligner")
1815 "BWA is a software package for mapping low-divergent sequences against a
1816 large reference genome, such as the human genome. It consists of three
1817 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1818 designed for Illumina sequence reads up to 100bp, while the rest two for
1819 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1820 features such as long-read support and split alignment, but BWA-MEM, which is
1821 the latest, is generally recommended for high-quality queries as it is faster
1822 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1823 70-100bp Illumina reads.")
1824 (license license:gpl3+)))
1826 (define-public bwa-pssm
1827 (package (inherit bwa)
1833 (url "https://github.com/pkerpedjiev/bwa-pssm")
1835 (file-name (git-file-name name version))
1838 "076c4q0cdqz8jgylb067y9zmvxglppnzi3qiscn0xiypgc6lgb5r"))))
1839 (build-system gnu-build-system)
1844 (home-page "http://bwa-pssm.binf.ku.dk/")
1845 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1847 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1848 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1849 existing aligners it is fast and sensitive. Unlike most other aligners,
1850 however, it is also adaptible in the sense that one can direct the alignment
1851 based on known biases within the data set. It is coded as a modification of
1852 the original BWA alignment program and shares the genome index structure as
1853 well as many of the command line options.")
1854 (license license:gpl3+)))
1856 (define-public bwa-meth
1863 (url "https://github.com/brentp/bwa-meth")
1864 (commit (string-append "v" version))))
1865 (file-name (git-file-name name version))
1868 "17j31i7zws5j7mhsq9x3qgkxly6mlmrgwhfq0qbflgxrmx04yaiz"))))
1869 (build-system python-build-system)
1872 (modify-phases %standard-phases
1873 (add-after 'unpack 'keep-references-to-bwa
1874 (lambda* (#:key inputs #:allow-other-keys)
1875 (substitute* "bwameth.py"
1876 (("bwa (mem|index)" _ command)
1877 (string-append (which "bwa") " " command))
1878 ;; There's an ill-advised check for "samtools" on PATH.
1884 `(("python-toolshed" ,python-toolshed)))
1885 (home-page "https://github.com/brentp/bwa-meth")
1886 (synopsis "Fast and accurante alignment of BS-Seq reads")
1888 "BWA-Meth works for single-end reads and for paired-end reads from the
1889 directional protocol (most common). It uses the method employed by
1890 methylcoder and Bismark of in silico conversion of all C's to T's in both
1891 reference and reads. It recovers the original read (needed to tabulate
1892 methylation) by attaching it as a comment which BWA appends as a tag to the
1893 read. It performs favorably to existing aligners gauged by number of on and
1894 off-target reads for a capture method that targets CpG-rich region.")
1895 (license license:expat)))
1897 (define-public python-bx-python
1899 (name "python-bx-python")
1903 (uri (pypi-uri "bx-python" version))
1906 "11kksg2rbzihpmcid823xvg42xi88m7sz58rzk29abybkxy0rszs"))))
1907 (build-system python-build-system)
1908 ;; Tests fail because test data are not included
1909 (arguments '(#:tests? #f))
1911 `(("python-numpy" ,python-numpy)
1912 ("python-six" ,python-six)))
1916 `(("python-lzo" ,python-lzo)
1917 ("python-nose" ,python-nose)
1918 ("python-cython" ,python-cython)))
1919 (home-page "https://github.com/bxlab/bx-python")
1920 (synopsis "Tools for manipulating biological data")
1922 "bx-python provides tools for manipulating biological data, particularly
1923 multiple sequence alignments.")
1924 (license license:expat)))
1926 (define-public python2-bx-python
1927 (package-with-python2 python-bx-python))
1929 (define-public python-pysam
1931 (name "python-pysam")
1935 ;; Test data is missing on PyPi.
1937 (url "https://github.com/pysam-developers/pysam")
1938 (commit (string-append "v" version))))
1939 (file-name (git-file-name name version))
1942 "1vj367w6xbn9bpmksm162l1aipf7cj97h1q83y7jcpm33ihwpf7x"))
1943 (modules '((guix build utils)))
1945 ;; Drop bundled htslib. TODO: Also remove samtools
1947 (delete-file-recursively "htslib")
1949 (build-system python-build-system)
1951 `(#:modules ((ice-9 ftw)
1953 (guix build python-build-system)
1956 (modify-phases %standard-phases
1957 (add-before 'build 'set-flags
1958 (lambda* (#:key inputs #:allow-other-keys)
1959 (setenv "HTSLIB_MODE" "external")
1960 (setenv "HTSLIB_LIBRARY_DIR"
1961 (string-append (assoc-ref inputs "htslib") "/lib"))
1962 (setenv "HTSLIB_INCLUDE_DIR"
1963 (string-append (assoc-ref inputs "htslib") "/include"))
1964 (setenv "LDFLAGS" "-lncurses")
1965 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1968 (lambda* (#:key inputs outputs #:allow-other-keys)
1969 ;; This file contains tests that require a connection to the
1971 (delete-file "tests/tabix_test.py")
1972 ;; FIXME: This test fails
1973 (delete-file "tests/AlignmentFile_test.py")
1974 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1975 (setenv "PYTHONPATH"
1977 (getenv "PYTHONPATH")
1978 ":" (getcwd) "/build/"
1979 (car (scandir "build"
1980 (negate (cut string-prefix? "." <>))))))
1981 ;; Step out of source dir so python does not import from CWD.
1982 (with-directory-excursion "tests"
1983 (setenv "HOME" "/tmp")
1984 (invoke "make" "-C" "pysam_data")
1985 (invoke "make" "-C" "cbcf_data")
1986 ;; Running nosetests without explicitly asking for a single
1987 ;; process leads to a crash. Running with multiple processes
1988 ;; fails because the tests are not designed to run in parallel.
1990 ;; FIXME: tests keep timing out on some systems.
1991 (invoke "nosetests" "-v" "--processes" "1")))))))
1993 `(("htslib" ,htslib-1.9))) ; Included from installed header files.
1995 `(("ncurses" ,ncurses)
1999 `(("python-cython" ,python-cython)
2000 ;; Dependencies below are are for tests only.
2001 ("samtools" ,samtools-1.9)
2002 ("bcftools" ,bcftools-1.9)
2003 ("python-nose" ,python-nose)))
2004 (home-page "https://github.com/pysam-developers/pysam")
2005 (synopsis "Python bindings to the SAMtools C API")
2007 "Pysam is a Python module for reading and manipulating files in the
2008 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
2009 also includes an interface for tabix.")
2010 (license license:expat)))
2012 (define-public python2-pysam
2013 (package-with-python2 python-pysam))
2015 (define-public python-twobitreader
2017 (name "python-twobitreader")
2022 (url "https://github.com/benjschiller/twobitreader")
2024 (file-name (git-file-name name version))
2027 "1qbxvv1h58cismbk1anpjrkpghsaiy64a11ir3lhy6qch6xf8n62"))))
2028 (build-system python-build-system)
2029 ;; Tests are not included
2030 (arguments '(#:tests? #f))
2032 `(("python-sphinx" ,python-sphinx)))
2033 (home-page "https://github.com/benjschiller/twobitreader")
2034 (synopsis "Python library for reading .2bit files")
2036 "twobitreader is a Python library for reading .2bit files as used by the
2037 UCSC genome browser.")
2038 (license license:artistic2.0)))
2040 (define-public python2-twobitreader
2041 (package-with-python2 python-twobitreader))
2043 (define-public python-plastid
2045 (name "python-plastid")
2049 (uri (pypi-uri "plastid" version))
2052 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
2053 (build-system python-build-system)
2055 ;; Some test files are not included.
2058 `(("python-numpy" ,python-numpy)
2059 ("python-scipy" ,python-scipy)
2060 ("python-pandas" ,python-pandas)
2061 ("python-pysam" ,python-pysam)
2062 ("python-matplotlib" ,python-matplotlib)
2063 ("python-biopython" ,python-biopython)
2064 ("python-twobitreader" ,python-twobitreader)
2065 ("python-termcolor" ,python-termcolor)))
2067 `(("python-cython" ,python-cython)
2068 ("python-nose" ,python-nose)))
2069 (home-page "https://github.com/joshuagryphon/plastid")
2070 (synopsis "Python library for genomic analysis")
2072 "plastid is a Python library for genomic analysis – in particular,
2073 high-throughput sequencing data – with an emphasis on simplicity.")
2074 (license license:bsd-3)))
2076 (define-public python2-plastid
2077 (package-with-python2 python-plastid))
2079 (define-public tetoolkit
2086 (url "https://github.com/mhammell-laboratory/tetoolkit")
2088 (file-name (git-file-name name version))
2091 "1yzi0kfpzip8zpjb82x1ik6h22yzfyjiz2dv85v6as2awwqvk807"))))
2092 (build-system python-build-system)
2094 `(#:python ,python-2 ; not guaranteed to work with Python 3
2096 (modify-phases %standard-phases
2097 (add-after 'unpack 'make-writable
2099 (for-each make-file-writable (find-files "."))
2101 (add-after 'unpack 'patch-invocations
2102 (lambda* (#:key inputs #:allow-other-keys)
2103 (substitute* '("bin/TEtranscripts"
2106 (string-append "'" (which "sort") " "))
2108 (string-append "'" (which "rm") " -f "))
2109 (("'Rscript'") (string-append "'" (which "Rscript") "'")))
2110 (substitute* "TEToolkit/IO/ReadInputs.py"
2111 (("BamToBED") (which "bamToBed")))
2112 (substitute* "TEToolkit/Normalization.py"
2114 (string-append "\"" (which "Rscript") "\"")))
2116 (add-after 'install 'wrap-program
2117 (lambda* (#:key outputs #:allow-other-keys)
2118 ;; Make sure the executables find R packages.
2119 (let ((out (assoc-ref outputs "out")))
2122 (wrap-program (string-append out "/bin/" script)
2123 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
2128 `(("coreutils" ,coreutils)
2129 ("bedtools" ,bedtools)
2130 ("python-argparse" ,python2-argparse)
2131 ("python-pysam" ,python2-pysam)
2132 ("r-minimal" ,r-minimal)
2133 ("r-deseq2" ,r-deseq2)))
2134 (home-page "https://github.com/mhammell-laboratory/tetoolkit")
2135 (synopsis "Transposable elements in differential enrichment analysis")
2137 "This is package for including transposable elements in differential
2138 enrichment analysis of sequencing datasets. TEtranscripts and TEcount take
2139 RNA-seq (and similar data) and annotates reads to both genes and transposable
2140 elements. TEtranscripts then performs differential analysis using DESeq2.
2141 Note that TEtranscripts and TEcount rely on specially curated GTF files, which
2142 are not included due to their size.")
2143 (license license:gpl3+)))
2145 (define-public cd-hit
2151 (uri (string-append "https://github.com/weizhongli/cdhit"
2152 "/releases/download/V" version
2154 "-2017-0621-source.tar.gz"))
2157 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
2158 (build-system gnu-build-system)
2160 `(#:tests? #f ; there are no tests
2162 ;; Executables are copied directly to the PREFIX.
2163 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin")
2164 ;; Support longer sequences (e.g. Pacbio sequences)
2167 (modify-phases %standard-phases
2168 ;; No "configure" script
2170 ;; Remove sources of non-determinism
2171 (add-after 'unpack 'be-timeless
2173 (substitute* "cdhit-utility.c++"
2174 ((" \\(built on \" __DATE__ \"\\)") ""))
2175 (substitute* "cdhit-common.c++"
2176 (("__DATE__") "\"0\"")
2177 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
2179 ;; The "install" target does not create the target directory.
2180 (add-before 'install 'create-target-dir
2181 (lambda* (#:key outputs #:allow-other-keys)
2182 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
2186 (home-page "http://weizhongli-lab.org/cd-hit/")
2187 (synopsis "Cluster and compare protein or nucleotide sequences")
2189 "CD-HIT is a program for clustering and comparing protein or nucleotide
2190 sequences. CD-HIT is designed to be fast and handle extremely large
2192 ;; The manual says: "It can be copied under the GNU General Public License
2193 ;; version 2 (GPLv2)."
2194 (license license:gpl2)))
2196 (define-public clipper
2203 (url "https://github.com/YeoLab/clipper")
2205 (file-name (git-file-name name version))
2208 "1bcag4lb5bkzsj2vg7lrq24aw6yfgq275ifrbhd82l7kqgbbjbkv"))))
2209 (build-system python-build-system)
2212 (modify-phases %standard-phases
2213 (add-before 'reset-gzip-timestamps 'make-files-writable
2214 (lambda* (#:key outputs #:allow-other-keys)
2215 ;; Make sure .gz files are writable so that the
2216 ;; 'reset-gzip-timestamps' phase can do its work.
2217 (let ((out (assoc-ref outputs "out")))
2218 (for-each make-file-writable
2219 (find-files out "\\.gz$"))
2223 ("python-pybedtools" ,python-pybedtools)
2224 ("python-cython" ,python-cython)
2225 ("python-scikit-learn" ,python-scikit-learn)
2226 ("python-matplotlib" ,python-matplotlib)
2227 ("python-pandas" ,python-pandas)
2228 ("python-pysam" ,python-pysam)
2229 ("python-numpy" ,python-numpy)
2230 ("python-scipy" ,python-scipy)))
2232 `(("python-setuptools-git" ,python-setuptools-git)
2233 ("python-mock" ,python-mock) ; for tests
2234 ("python-nose" ,python-nose) ; for tests
2235 ("python-pytz" ,python-pytz))) ; for tests
2236 (home-page "https://github.com/YeoLab/clipper")
2237 (synopsis "CLIP peak enrichment recognition")
2239 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
2240 (license license:gpl2)))
2242 (define-public codingquarry
2244 (name "codingquarry")
2249 "mirror://sourceforge/codingquarry/CodingQuarry_v"
2253 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
2254 (build-system gnu-build-system)
2256 '(#:tests? #f ; no "check" target
2258 (modify-phases %standard-phases
2261 (lambda* (#:key outputs #:allow-other-keys)
2262 (let* ((out (assoc-ref outputs "out"))
2263 (bin (string-append out "/bin"))
2264 (doc (string-append out "/share/doc/codingquarry")))
2265 (install-file "INSTRUCTIONS.pdf" doc)
2266 (copy-recursively "QuarryFiles"
2267 (string-append out "/QuarryFiles"))
2268 (install-file "CodingQuarry" bin)
2269 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin))
2271 (inputs `(("openmpi" ,openmpi)))
2272 (native-search-paths
2273 (list (search-path-specification
2274 (variable "QUARRY_PATH")
2275 (files '("QuarryFiles")))))
2276 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
2277 (synopsis "Fungal gene predictor")
2278 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
2279 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
2280 (home-page "https://sourceforge.net/projects/codingquarry/")
2281 (license license:gpl3+)))
2283 (define-public couger
2290 "http://couger.oit.duke.edu/static/assets/COUGER"
2294 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
2295 (build-system gnu-build-system)
2299 (modify-phases %standard-phases
2304 (lambda* (#:key outputs #:allow-other-keys)
2305 (let* ((out (assoc-ref outputs "out"))
2306 (bin (string-append out "/bin")))
2307 (copy-recursively "src" (string-append out "/src"))
2309 ;; Add "src" directory to module lookup path.
2310 (substitute* "couger"
2312 (string-append "import sys\nsys.path.append(\""
2313 out "\")\nfrom argparse")))
2314 (install-file "couger" bin))
2317 'install 'wrap-program
2318 (lambda* (#:key inputs outputs #:allow-other-keys)
2319 ;; Make sure 'couger' runs with the correct PYTHONPATH.
2320 (let* ((out (assoc-ref outputs "out"))
2321 (path (getenv "PYTHONPATH")))
2322 (wrap-program (string-append out "/bin/couger")
2323 `("PYTHONPATH" ":" prefix (,path))))
2326 `(("python" ,python-2)
2327 ("python2-pillow" ,python2-pillow)
2328 ("python2-numpy" ,python2-numpy)
2329 ("python2-scipy" ,python2-scipy)
2330 ("python2-matplotlib" ,python2-matplotlib)))
2332 `(("r-minimal" ,r-minimal)
2334 ("randomjungle" ,randomjungle)))
2336 `(("unzip" ,unzip)))
2337 (home-page "http://couger.oit.duke.edu")
2338 (synopsis "Identify co-factors in sets of genomic regions")
2340 "COUGER can be applied to any two sets of genomic regions bound by
2341 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
2342 putative co-factors that provide specificity to each TF. The framework
2343 determines the genomic targets uniquely-bound by each TF, and identifies a
2344 small set of co-factors that best explain the in vivo binding differences
2345 between the two TFs.
2347 COUGER uses classification algorithms (support vector machines and random
2348 forests) with features that reflect the DNA binding specificities of putative
2349 co-factors. The features are generated either from high-throughput TF-DNA
2350 binding data (from protein binding microarray experiments), or from large
2351 collections of DNA motifs.")
2352 (license license:gpl3+)))
2354 (define-public clustal-omega
2356 (name "clustal-omega")
2360 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
2364 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
2365 (build-system gnu-build-system)
2367 `(("argtable" ,argtable)))
2368 (home-page "http://www.clustal.org/omega/")
2369 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
2371 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
2372 program for protein and DNA/RNA. It produces high quality MSAs and is capable
2373 of handling data-sets of hundreds of thousands of sequences in reasonable
2375 (license license:gpl2+)))
2377 (define-public crossmap
2383 (uri (pypi-uri "CrossMap" version))
2386 "1sb2f2qbxya4fzw3yjl09vbrs8vfmw22zrygrvz004sf9gb1vkan"))))
2387 (build-system python-build-system)
2389 `(("python-bx-python" ,python-bx-python)
2390 ("python-numpy" ,python-numpy)
2391 ("python-pybigwig" ,python-pybigwig)
2392 ("python-pysam" ,python-pysam)
2395 `(("python-cython" ,python-cython)
2396 ("python-nose" ,python-nose)))
2397 (home-page "http://crossmap.sourceforge.net/")
2398 (synopsis "Convert genome coordinates between assemblies")
2400 "CrossMap is a program for conversion of genome coordinates or annotation
2401 files between different genome assemblies. It supports most commonly used
2402 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
2403 (license license:gpl2+)))
2405 (define-public python-dnaio
2407 (name "python-dnaio")
2412 (uri (pypi-uri "dnaio" version))
2415 "0f16m7hdlm0fz1n7y5asy0v9ghyrq17ni1p9iybq22ddzyd49r27"))))
2416 (build-system python-build-system)
2418 `(("python-cython" ,python-cython)
2419 ("python-pytest" ,python-pytest)
2420 ("python-xopen" ,python-xopen)))
2421 (home-page "https://github.com/marcelm/dnaio/")
2422 (synopsis "Read FASTA and FASTQ files efficiently")
2424 "dnaio is a Python library for fast parsing of FASTQ and also FASTA
2425 files. The code was previously part of the cutadapt tool.")
2426 (license license:expat)))
2428 (define-public python-deeptoolsintervals
2430 (name "python-deeptoolsintervals")
2434 (uri (pypi-uri "deeptoolsintervals" version))
2437 "1xnl80nblysj6dylj4683wgrfa425rkx4dp5k65hvwdns9pw753x"))))
2438 (build-system python-build-system)
2441 (home-page "https://github.com/deeptools/deeptools_intervals")
2442 (synopsis "Create GTF-based interval trees with associated meta-data")
2444 "This package provides a Python module creating/accessing GTF-based
2445 interval trees with associated meta-data. It is primarily used by the
2446 @code{deeptools} package.")
2447 (license license:expat)))
2449 (define-public python-deeptools
2451 (name "python-deeptools")
2456 (url "https://github.com/deeptools/deepTools")
2458 (file-name (git-file-name name version))
2461 "0l09vyynz6s6w7fnyd94rpys4a6aja6kp4gli64pngdxdz3md1nl"))))
2462 (build-system python-build-system)
2464 `(("python-mock" ,python-mock)
2465 ("python-nose" ,python-nose)))
2467 `(("python-matplotlib" ,python-matplotlib)
2468 ("python-numpy" ,python-numpy)
2469 ("python-numpydoc" ,python-numpydoc)
2470 ("python-py2bit" ,python-py2bit)
2471 ("python-pybigwig" ,python-pybigwig)
2472 ("python-pysam" ,python-pysam)
2473 ("python-scipy" ,python-scipy)
2474 ("python-deeptoolsintervals" ,python-deeptoolsintervals)
2475 ("python-plotly" ,python-plotly-2.4.1)))
2476 (home-page "https://pypi.org/project/deepTools/")
2477 (synopsis "Useful tools for exploring deep sequencing data")
2478 (description "This package addresses the challenge of handling large amounts
2479 of data that are now routinely generated from DNA sequencing centers.
2480 @code{deepTools} contains useful modules to process the mapped reads data for
2481 multiple quality checks, creating normalized coverage files in standard bedGraph
2482 and bigWig file formats, that allow comparison between different files. Finally,
2483 using such normalized and standardized files, deepTools can create many
2484 publication-ready visualizations to identify enrichments and for functional
2485 annotations of the genome.")
2486 ;; The file deeptools/cm.py is licensed under the BSD license. The
2487 ;; remainder of the code is licensed under the MIT license.
2488 (license (list license:bsd-3 license:expat))))
2490 (define-deprecated deeptools python-deeptools)
2492 (define-public cutadapt
2498 (uri (pypi-uri "cutadapt" version))
2501 "1vqmsfkm6llxzmsz9wcfcvzx9a9f8iabvwik2rbyn7nc4wm25z89"))))
2502 (build-system python-build-system)
2504 `(("python-dnaio" ,python-dnaio)
2505 ("python-xopen" ,python-xopen)))
2507 `(("python-cython" ,python-cython)
2508 ("python-pytest" ,python-pytest)
2509 ("python-setuptools-scm" ,python-setuptools-scm)))
2510 (home-page "https://cutadapt.readthedocs.io/en/stable/")
2511 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
2513 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
2514 other types of unwanted sequence from high-throughput sequencing reads.")
2515 (license license:expat)))
2517 (define-public libbigwig
2524 (url "https://github.com/dpryan79/libBigWig")
2526 (file-name (git-file-name name version))
2529 "09693dmf1scdac5pyq6qyn8b4mcipvnmc370k9a5z41z81m3dcsj"))))
2530 (build-system gnu-build-system)
2532 `(#:test-target "test"
2533 #:tests? #f ; tests require access to the web
2536 (string-append "prefix=" (assoc-ref %outputs "out")))
2538 (modify-phases %standard-phases
2539 (delete 'configure))))
2544 `(("doxygen" ,doxygen)
2546 ("python" ,python-2)))
2547 (home-page "https://github.com/dpryan79/libBigWig")
2548 (synopsis "C library for handling bigWig files")
2550 "This package provides a C library for parsing local and remote BigWig
2552 (license license:expat)))
2554 (define-public python-pybigwig
2556 (name "python-pybigwig")
2560 (uri (pypi-uri "pyBigWig" version))
2563 "157x6v48y299zm382krf1dw08fdxg95im8lnabhp5vc94s04zxj1"))
2564 (modules '((guix build utils)))
2567 ;; Delete bundled libBigWig sources
2568 (delete-file-recursively "libBigWig")
2570 (build-system python-build-system)
2573 (modify-phases %standard-phases
2574 (add-after 'unpack 'link-with-libBigWig
2575 (lambda* (#:key inputs #:allow-other-keys)
2576 (substitute* "setup.py"
2577 (("libs=\\[") "libs=[\"BigWig\", "))
2580 `(("python-numpy" ,python-numpy)))
2582 `(("libbigwig" ,libbigwig)
2585 (home-page "https://github.com/dpryan79/pyBigWig")
2586 (synopsis "Access bigWig files in Python using libBigWig")
2588 "This package provides Python bindings to the libBigWig library for
2589 accessing bigWig files.")
2590 (license license:expat)))
2592 (define-public python2-pybigwig
2593 (package-with-python2 python-pybigwig))
2595 (define-public python-schema-salad
2597 (name "python-schema-salad")
2598 (version "7.0.20200811075006")
2602 (uri (pypi-uri "schema-salad" version))
2605 "0wanbwmqb189x1m0vacnhpivfsr8rwbqknngivzxxs8j46yj80bg"))))
2606 (build-system python-build-system)
2608 `(("python-cachecontrol" ,python-cachecontrol-0.11)
2609 ("python-lockfile" ,python-lockfile)
2610 ("python-mistune" ,python-mistune)
2611 ("python-rdflib" ,python-rdflib)
2612 ("python-rdflib-jsonld" ,python-rdflib-jsonld)
2613 ("python-requests" ,python-requests)
2614 ("python-ruamel.yaml" ,python-ruamel.yaml)
2615 ("python-typing-extensions" ,python-typing-extensions)))
2617 `(("python-pytest" ,python-pytest)
2618 ("python-pytest-runner" ,python-pytest-runner)))
2619 (home-page "https://github.com/common-workflow-language/schema_salad")
2620 (synopsis "Schema Annotations for Linked Avro Data (SALAD)")
2622 "Salad is a schema language for describing JSON or YAML structured linked
2623 data documents. Salad schema describes rules for preprocessing, structural
2624 validation, and hyperlink checking for documents described by a Salad schema.
2625 Salad supports rich data modeling with inheritance, template specialization,
2626 object identifiers, object references, documentation generation, code
2627 generation, and transformation to RDF. Salad provides a bridge between document
2628 and record oriented data modeling and the Semantic Web.")
2629 (license license:asl2.0)))
2631 (define-public cwltool
2634 (version "3.0.20201121085451")
2638 (url "https://github.com/common-workflow-language/cwltool")
2640 (file-name (git-file-name name version))
2643 "1awf99n7aglxc5zszrlrv6jxp355jp45ws7wpsgjlgcdv7advn0w"))))
2644 (build-system python-build-system)
2647 (modify-phases %standard-phases
2648 (add-after 'unpack 'loosen-version-restrictions
2650 (substitute* "setup.py"
2651 (("== 1.5.1") ">=1.5.1") ; prov
2652 ((", < 3.5") "")) ; shellescape
2654 (add-after 'unpack 'dont-use-git
2656 (substitute* "gittaggers.py"
2657 (("self.git_timestamp_tag\\(\\)")
2658 (string-append "time.strftime('.%Y%m%d%H%M%S', time.gmtime(int("
2659 (string-drop ,version 4) ")))")))
2661 (add-after 'unpack 'modify-tests
2663 ;; Tries to connect to the internet.
2664 (delete-file "tests/test_udocker.py")
2665 (delete-file "tests/test_http_input.py")
2666 (substitute* "tests/test_load_tool.py"
2667 (("def test_load_graph_fragment_from_packed")
2668 (string-append "@pytest.mark.skip(reason=\"Disabled by Guix\")\n"
2669 "def test_load_graph_fragment_from_packed")))
2670 (substitute* "tests/test_examples.py"
2671 (("def test_env_filtering")
2672 (string-append "@pytest.mark.skip(reason=\"Disabled by Guix\")\n"
2673 "def test_env_filtering")))
2674 ;; Tries to use cwl-runners.
2675 (substitute* "tests/test_examples.py"
2676 (("def test_v1_0_arg_empty_prefix_separate_false")
2677 (string-append "@pytest.mark.skip(reason=\"Disabled by Guix\")\n"
2678 "def test_v1_0_arg_empty_prefix_separate_false")))
2681 `(("python-argcomplete" ,python-argcomplete)
2682 ("python-bagit" ,python-bagit)
2683 ("python-coloredlogs" ,python-coloredlogs)
2684 ("python-mypy-extensions" ,python-mypy-extensions)
2685 ("python-prov" ,python-prov)
2686 ("python-pydot" ,python-pydot)
2687 ("python-psutil" ,python-psutil)
2688 ("python-rdflib" ,python-rdflib)
2689 ("python-requests" ,python-requests)
2690 ("python-ruamel.yaml" ,python-ruamel.yaml)
2691 ("python-schema-salad" ,python-schema-salad)
2692 ("python-shellescape" ,python-shellescape)
2693 ("python-typing-extensions" ,python-typing-extensions)
2694 ;; Not listed as needed but still necessary:
2697 `(("python-arcp" ,python-arcp)
2698 ("python-humanfriendly" ,python-humanfriendly)
2699 ("python-mock" ,python-mock)
2700 ("python-pytest" ,python-pytest)
2701 ("python-pytest-cov" ,python-pytest-cov)
2702 ("python-pytest-mock" ,python-pytest-mock)
2703 ("python-pytest-runner" ,python-pytest-runner)
2704 ("python-rdflib-jsonld" ,python-rdflib-jsonld)))
2706 "https://github.com/common-workflow-language/common-workflow-language")
2707 (synopsis "Common Workflow Language reference implementation")
2709 "This is the reference implementation of the @acronym{CWL, Common Workflow
2710 Language} standards. The CWL open standards are for describing analysis
2711 workflows and tools in a way that makes them portable and scalable across a
2712 variety of software and hardware environments, from workstations to cluster,
2713 cloud, and high performance computing (HPC) environments. CWL is designed to
2714 meet the needs of data-intensive science, such as Bioinformatics, Medical
2715 Imaging, Astronomy, Physics, and Chemistry. The @acronym{cwltool, CWL reference
2716 implementation} is intended to be feature complete and to provide comprehensive
2717 validation of CWL files as well as provide other tools related to working with
2719 (license license:asl2.0)))
2721 (define-public python-dendropy
2723 (name "python-dendropy")
2728 ;; Source from GitHub so that tests are included.
2730 (url "https://github.com/jeetsukumaran/DendroPy")
2731 (commit (string-append "v" version))))
2732 (file-name (git-file-name name version))
2735 "097hfyv2kaf4x92i4rjx0paw2cncxap48qivv8zxng4z7nhid0x9"))))
2736 (build-system python-build-system)
2737 (home-page "https://dendropy.org/")
2738 (synopsis "Library for phylogenetics and phylogenetic computing")
2740 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
2741 writing, simulation, processing and manipulation of phylogenetic
2742 trees (phylogenies) and characters.")
2743 (license license:bsd-3)))
2745 (define-public python2-dendropy
2746 (let ((base (package-with-python2 python-dendropy)))
2751 (modify-phases %standard-phases
2752 (add-after 'unpack 'remove-failing-test
2754 ;; This test fails when the full test suite is run, as documented
2755 ;; at https://github.com/jeetsukumaran/DendroPy/issues/74
2756 (substitute* "tests/test_dataio_nexml_reader_tree_list.py"
2757 (("test_collection_comments_and_annotations")
2758 "do_not_test_collection_comments_and_annotations"))
2760 ,@(package-arguments base))))))
2762 (define-public python-py2bit
2764 (name "python-py2bit")
2769 (uri (pypi-uri "py2bit" version))
2772 "1vw2nvw1yrl7ikkqsqs1pg239yr5nspvd969r1x9arms1k25a1a5"))))
2773 (build-system python-build-system)
2774 (home-page "https://github.com/dpryan79/py2bit")
2775 (synopsis "Access 2bit files using lib2bit")
2777 "This package provides Python bindings for lib2bit to access 2bit files
2779 (license license:expat)))
2781 (define-public delly
2788 (url "https://github.com/dellytools/delly")
2789 (commit (string-append "v" version))))
2790 (file-name (git-file-name name version))
2792 (base32 "1ibnplgfzj96w8glkx17v7sld3pm402fr5ybmf3h0rlcryabxrqy"))
2793 (modules '((guix build utils)))
2796 (delete-file-recursively "src/htslib")
2798 (build-system gnu-build-system)
2800 `(#:tests? #f ; There are no tests to run.
2802 (list "PARALLEL=1" ; Allow parallel execution at run-time.
2803 (string-append "prefix=" (assoc-ref %outputs "out")))
2805 (modify-phases %standard-phases
2806 (delete 'configure) ; There is no configure phase.
2807 (add-after 'install 'install-templates
2808 (lambda* (#:key outputs #:allow-other-keys)
2809 (let ((templates (string-append (assoc-ref outputs "out")
2810 "/share/delly/templates")))
2812 (copy-recursively "excludeTemplates" templates)
2819 (home-page "https://github.com/dellytools/delly")
2820 (synopsis "Integrated structural variant prediction method")
2821 (description "Delly is an integrated structural variant prediction method
2822 that can discover and genotype deletions, tandem duplications, inversions and
2823 translocations at single-nucleotide resolution in short-read massively parallel
2824 sequencing data. It uses paired-ends and split-reads to sensitively and
2825 accurately delineate genomic rearrangements throughout the genome.")
2826 (license license:gpl3+)))
2835 (url "https://github.com/Benson-Genomics-Lab/TRF")
2836 (commit (string-append "v" version))))
2837 (file-name (git-file-name name version))
2839 (base32 "0fhwr4s1mf8nw8fr5imwjvjr42b59p97zr961ifm8xl1bajz4wpg"))))
2840 (build-system gnu-build-system)
2841 (home-page "https://github.com/Benson-Genomics-Lab/TRF")
2842 (synopsis "Tandem Repeats Finder: a program to analyze DNA sequences")
2843 (description "A tandem repeat in DNA is two or more adjacent, approximate
2844 copies of a pattern of nucleotides. Tandem Repeats Finder is a program to
2845 locate and display tandem repeats in DNA sequences. In order to use the
2846 program, the user submits a sequence in FASTA format. The output consists of
2847 two files: a repeat table file and an alignment file. Submitted sequences may
2848 be of arbitrary length. Repeats with pattern size in the range from 1 to 2000
2849 bases are detected.")
2850 (license license:agpl3+)))
2852 (define-public repeat-masker
2854 (name "repeat-masker")
2858 (uri (string-append "http://www.repeatmasker.org/"
2859 "RepeatMasker/RepeatMasker-"
2862 (base32 "03144sl9kh5ni2i33phi7x2pjndzbm5bjw3r4kqvmm6hxyb4k4x2"))))
2863 (build-system gnu-build-system)
2865 `(#:tests? #false ; there are none
2867 (modify-phases %standard-phases
2870 (lambda* (#:key inputs outputs #:allow-other-keys)
2871 (let ((share (string-append (assoc-ref outputs "out")
2872 "/share/RepeatMasker")))
2874 (copy-recursively "." share)
2875 (with-directory-excursion share
2876 (invoke "perl" "configure"
2877 "--trf_prgm" (which "trf")
2879 (string-append (assoc-ref inputs "hmmer")
2882 (lambda* (#:key outputs #:allow-other-keys)
2883 (let* ((out (assoc-ref outputs "out"))
2884 (share (string-append out "/share/RepeatMasker"))
2885 (bin (string-append out "/bin"))
2886 (path (getenv "PERL5LIB")))
2887 (install-file (string-append share "/RepeatMasker") bin)
2888 (wrap-program (string-append bin "/RepeatMasker")
2889 `("PERL5LIB" ":" prefix (,path ,share)))))))))
2892 ("perl-text-soundex" ,perl-text-soundex)
2894 ("python-h5py" ,python-h5py)
2897 (home-page "https://github.com/Benson-Genomics-Lab/TRF")
2898 (synopsis "Tandem Repeats Finder: a program to analyze DNA sequences")
2899 (description "A tandem repeat in DNA is two or more adjacent, approximate
2900 copies of a pattern of nucleotides. Tandem Repeats Finder is a program to
2901 locate and display tandem repeats in DNA sequences. In order to use the
2902 program, the user submits a sequence in FASTA format. The output consists of
2903 two files: a repeat table file and an alignment file. Submitted sequences may
2904 be of arbitrary length. Repeats with pattern size in the range from 1 to 2000
2905 bases are detected.")
2906 (license license:osl2.1)))
2908 (define-public diamond
2915 (url "https://github.com/bbuchfink/diamond")
2916 (commit (string-append "v" version))))
2917 (file-name (git-file-name name version))
2920 "0k6f3kb6cniw11xw6763kkbs1sl0yack7xsy7q5fl5v170ssphq4"))))
2921 (build-system cmake-build-system)
2923 '(#:tests? #f ; no "check" target
2925 (modify-phases %standard-phases
2926 (add-after 'unpack 'remove-native-compilation
2928 (substitute* "CMakeLists.txt" (("-march=native") ""))
2932 (home-page "https://github.com/bbuchfink/diamond")
2933 (synopsis "Accelerated BLAST compatible local sequence aligner")
2935 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2936 translated DNA query sequences against a protein reference database (BLASTP
2937 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2938 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2939 data and settings.")
2940 (license license:agpl3+)))
2942 (define-public discrover
2950 (url "https://github.com/maaskola/discrover")
2952 (file-name (git-file-name name version))
2955 "173fwi2vb6a5kp406hm3jj6j7v4whww796f2qcygp4rpvamh307y"))))
2956 (build-system cmake-build-system)
2958 `(#:tests? #f ; there are no tests
2960 (modify-phases %standard-phases
2961 (add-after 'unpack 'fix-latex-errors
2963 (with-fluids ((%default-port-encoding #f))
2964 (substitute* "doc/references.bib"
2965 (("\\{S\\}illanp[^,]+,")
2966 "{S}illanp{\\\"a}{\\\"a},")))
2967 ;; XXX: I just can't get pdflatex to not complain about these
2968 ;; characters. They end up in the manual via the generated
2969 ;; discrover-cli-help.txt.
2970 (substitute* "src/hmm/cli.cpp"
2974 ;; This seems to be a syntax error.
2975 (substitute* "doc/discrover-manual.tex"
2976 (("theverbbox\\[t\\]") "theverbbox"))
2978 (add-after 'unpack 'add-missing-includes
2980 (substitute* "src/executioninformation.hpp"
2981 (("#define EXECUTIONINFORMATION_HPP" line)
2982 (string-append line "\n#include <random>")))
2983 (substitute* "src/plasma/fasta.hpp"
2984 (("#define FASTA_HPP" line)
2985 (string-append line "\n#include <random>")))
2987 ;; FIXME: this is needed because we're using texlive-union, which
2988 ;; doesn't handle fonts correctly. It expects to be able to generate
2989 ;; fonts in the home directory.
2990 (add-before 'build 'setenv-HOME
2991 (lambda _ (setenv "HOME" "/tmp") #t)))))
2995 ("rmath-standalone" ,rmath-standalone)))
2997 `(("texlive" ,(texlive-union (list texlive-fonts-cm
2998 texlive-fonts-amsfonts
3001 texlive-latex-examplep
3002 texlive-latex-hyperref
3004 texlive-latex-natbib
3005 texlive-bibtex ; style files used by natbib
3006 texlive-latex-pgf ; tikz
3007 texlive-latex-verbatimbox)))
3008 ("imagemagick" ,imagemagick)))
3009 (home-page "https://dorina.mdc-berlin.de/public/rajewsky/discrover/")
3010 (synopsis "Discover discriminative nucleotide sequence motifs")
3011 (description "Discrover is a motif discovery method to find binding sites
3012 of nucleic acid binding proteins.")
3013 (license license:gpl3+)))
3015 (define-public eigensoft
3023 (url "https://github.com/DReichLab/EIG")
3024 (commit (string-append "v" version))))
3025 (file-name (git-file-name name version))
3028 "1c141fqvhnzibmnf22sv23vbmzm20kjjyrib44cfh75wyndp2d9k"))
3029 (modules '((guix build utils)))
3030 ;; Remove pre-built binaries.
3032 (delete-file-recursively "bin")
3035 (build-system gnu-build-system)
3037 `(#:tests? #f ; There are no tests.
3038 #:make-flags '("CC=gcc")
3040 (modify-phases %standard-phases
3041 ;; There is no configure phase, but the Makefile is in a
3044 (lambda _ (chdir "src") #t))
3045 ;; The provided install target only copies executables to
3046 ;; the "bin" directory in the build root.
3047 (add-after 'install 'actually-install
3048 (lambda* (#:key outputs #:allow-other-keys)
3049 (let* ((out (assoc-ref outputs "out"))
3050 (bin (string-append out "/bin")))
3051 (for-each (lambda (file)
3052 (install-file file bin))
3053 (find-files "../bin" ".*"))
3058 ("openblas" ,openblas)
3060 ("gfortran" ,gfortran "lib")))
3061 (home-page "https://github.com/DReichLab/EIG")
3062 (synopsis "Tools for population genetics")
3063 (description "The EIGENSOFT package provides tools for population
3064 genetics and stratification correction. EIGENSOFT implements methods commonly
3065 used in population genetics analyses such as PCA, computation of Tracy-Widom
3066 statistics, and finding related individuals in structured populations. It
3067 comes with a built-in plotting script and supports multiple file formats and
3068 quantitative phenotypes.")
3069 ;; The license of the eigensoft tools is Expat, but since it's
3070 ;; linking with the GNU Scientific Library (GSL) the effective
3071 ;; license is the GPL.
3072 (license license:gpl3+)))
3074 (define-public edirect
3077 (version "13.3.20200128")
3080 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect"
3081 "/versions/" version
3082 "/edirect-" version ".tar.gz"))
3085 "093zp7klv81ph0y8mm8d78a9hnpfxbv2kdym70gzdf3vz176rw33"))
3086 (modules '((guix build utils)))
3088 '(begin (delete-file "Mozilla-CA.tar.gz")
3089 (substitute* "rchive.go"
3090 ;; This go library does not have any license.
3091 (("github.com/fiam/gounidecode/unidecode")
3092 "golang.org/rainycape/unidecode"))
3094 (build-system perl-build-system)
3097 (modify-phases %standard-phases
3100 (delete 'check) ; simple check after install
3101 (add-after 'unpack 'patch-programs
3102 (lambda* (#:key inputs #:allow-other-keys)
3103 ;; Ignore errors about missing xtract.Linux and rchive.Linux.
3104 (substitute* "pm-refresh"
3105 (("cat \\\"\\$target")
3106 "grep ^[[:digit:]] \"$target"))
3109 (lambda* (#:key inputs outputs #:allow-other-keys)
3110 (let ((bin (string-append (assoc-ref outputs "out") "/bin"))
3111 (edirect-go (assoc-ref inputs "edirect-go-programs")))
3114 (install-file file bin))
3115 '("archive-pubmed" "asp-cp" "asp-ls" "download-ncbi-data"
3116 "download-pubmed" "edirect.pl" "efetch" "epost" "esearch"
3117 "fetch-pubmed" "ftp-cp" "ftp-ls" "has-asp" "index-pubmed"
3118 "pm-prepare" "pm-refresh" "pm-stash" "pm-collect"
3119 "pm-index" "pm-invert" "pm-merge" "pm-promote"))
3120 (symlink (string-append edirect-go "/bin/xtract.Linux")
3121 (string-append bin "/xtract"))
3122 (symlink (string-append edirect-go "/bin/rchive.Linux")
3123 (string-append bin "/rchive")))
3125 (add-after 'install 'wrap-program
3126 (lambda* (#:key outputs #:allow-other-keys)
3127 ;; Make sure everything can run in a pure environment.
3128 (let ((out (assoc-ref outputs "out"))
3129 (path (getenv "PERL5LIB")))
3133 `("PERL5LIB" ":" prefix (,path)))
3135 `("PATH" ":" prefix (,(string-append out "/bin")
3136 ,(dirname (which "sed"))
3137 ,(dirname (which "gzip"))
3138 ,(dirname (which "grep"))
3139 ,(dirname (which "perl"))
3140 ,(dirname (which "uname"))))))
3141 (find-files out ".")))
3143 (add-after 'wrap-program 'check
3144 (lambda* (#:key outputs #:allow-other-keys)
3145 (invoke (string-append (assoc-ref outputs "out")
3150 `(("edirect-go-programs" ,edirect-go-programs)
3151 ("perl-html-parser" ,perl-html-parser)
3152 ("perl-encode-locale" ,perl-encode-locale)
3153 ("perl-file-listing" ,perl-file-listing)
3154 ("perl-html-tagset" ,perl-html-tagset)
3155 ("perl-html-tree" ,perl-html-tree)
3156 ("perl-http-cookies" ,perl-http-cookies)
3157 ("perl-http-date" ,perl-http-date)
3158 ("perl-http-message" ,perl-http-message)
3159 ("perl-http-negotiate" ,perl-http-negotiate)
3160 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
3161 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
3162 ("perl-net-http" ,perl-net-http)
3163 ("perl-uri" ,perl-uri)
3164 ("perl-www-robotrules" ,perl-www-robotrules)
3165 ("perl-xml-simple" ,perl-xml-simple)
3167 (home-page "https://www.ncbi.nlm.nih.gov/books/NBK179288/")
3168 (synopsis "Tools for accessing the NCBI's set of databases")
3170 "Entrez Direct (EDirect) is a method for accessing the National Center
3171 for Biotechnology Information's (NCBI) set of interconnected
3172 databases (publication, sequence, structure, gene, variation, expression,
3173 etc.) from a terminal. Functions take search terms from command-line
3174 arguments. Individual operations are combined to build multi-step queries.
3175 Record retrieval and formatting normally complete the process.
3177 EDirect also provides an argument-driven function that simplifies the
3178 extraction of data from document summaries or other results that are returned
3179 in structured XML format. This can eliminate the need for writing custom
3180 software to answer ad hoc questions.")
3181 (native-search-paths
3182 ;; Ideally this should be set for LWP somewhere.
3183 (list (search-path-specification
3184 (variable "PERL_LWP_SSL_CA_FILE")
3185 (file-type 'regular)
3187 (files '("/etc/ssl/certs/ca-certificates.crt")))))
3188 (license license:public-domain)))
3190 (define-public edirect-go-programs
3193 (name "edirect-go-programs")
3194 (build-system go-build-system)
3196 `(#:install-source? #f
3197 #:tests? #f ; No tests.
3198 #:import-path "ncbi.nlm.nih.gov/entrez/edirect"
3200 (modify-phases %standard-phases
3202 (lambda* (#:key import-path #:allow-other-keys)
3203 (with-directory-excursion (string-append "src/" import-path)
3204 (invoke "go" "build" "-v" "-x" "j2x.go")
3205 (invoke "go" "build" "-v" "-x" "t2x.go")
3206 (invoke "go" "build" "-v" "-x" "-o"
3207 "xtract.Linux" "xtract.go" "common.go")
3208 (invoke "go" "build" "-v" "-x" "-o"
3209 "rchive.Linux" "rchive.go" "common.go")
3210 (invoke "go" "build" "-v" "-x" "-o" "symbols.Linux" "s2p.go"))))
3212 (lambda* (#:key outputs import-path #:allow-other-keys)
3213 (let ((dest (string-append (assoc-ref outputs "out") "/bin"))
3214 (source (string-append "src/" import-path "/")))
3215 (for-each (lambda (file)
3216 (format #t "installing ~a~%" file)
3217 (install-file (string-append source file) dest))
3218 '("j2x" "t2x" "symbols.Linux" "xtract.Linux" "rchive.Linux"))
3221 (propagated-inputs '())
3223 `(("go-github-com-fatih-color" ,go-github-com-fatih-color)
3224 ("go-github-com-fogleman-gg" ,go-github-com-fogleman-gg)
3225 ("go-github-com-gedex-inflector" ,go-github-com-gedex-inflector)
3226 ("go-github-com-golang-freetype" ,go-github-com-golang-freetype)
3227 ("go-github-com-klauspost-cpuid" ,go-github-com-klauspost-cpuid)
3228 ("go-github-com-pbnjay-memory" ,go-github-com-pbnjay-memory)
3229 ("go-github-com-surgebase-porter2" ,go-github-com-surgebase-porter2)
3230 ("go-golang-org-rainycape-unidecode" ,go-golang-org-rainycape-unidecode)
3231 ("go-golang-org-x-image" ,go-golang-org-x-image)
3232 ("go-golang-org-x-text" ,go-golang-org-x-text)))))
3234 (define-public exonerate
3243 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
3244 "exonerate-" version ".tar.gz"))
3247 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
3248 (build-system gnu-build-system)
3250 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
3252 `(("pkg-config" ,pkg-config)))
3256 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
3257 (synopsis "Generic tool for biological sequence alignment")
3259 "Exonerate is a generic tool for pairwise sequence comparison. It allows
3260 the alignment of sequences using a many alignment models, either exhaustive
3261 dynamic programming or a variety of heuristics.")
3262 (license license:gpl3)))
3264 (define-public express
3271 (url "https://github.com/adarob/eXpress")
3273 (file-name (git-file-name name version))
3276 "18nb22n7x820fzjngf4qgyb3mspqkw7xyk7v7s5ps6wfrd8qwscb"))))
3277 (build-system cmake-build-system)
3279 `(#:tests? #f ;no "check" target
3281 (modify-phases %standard-phases
3282 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
3283 (lambda* (#:key inputs #:allow-other-keys)
3284 (substitute* "CMakeLists.txt"
3285 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
3286 "set(Boost_USE_STATIC_LIBS OFF)")
3287 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
3288 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
3289 (substitute* "src/CMakeLists.txt"
3290 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
3291 (string-append (assoc-ref inputs "bamtools") "/lib"))
3292 (("libprotobuf.a") "libprotobuf.so"))
3294 (add-after 'unpack 'remove-update-check
3296 (substitute* "src/main.cpp"
3297 (("#include \"update_check.h\"") "")
3298 (("check_version\\(PACKAGE_VERSION\\);") ""))
3302 ("bamtools" ,bamtools)
3303 ("protobuf" ,protobuf)
3305 (home-page "http://bio.math.berkeley.edu/eXpress")
3306 (synopsis "Streaming quantification for high-throughput genomic sequencing")
3308 "eXpress is a streaming tool for quantifying the abundances of a set of
3309 target sequences from sampled subsequences. Example applications include
3310 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
3311 analysis (from RNA-Seq), transcription factor binding quantification in
3312 ChIP-Seq, and analysis of metagenomic data.")
3313 (license license:artistic2.0)))
3315 (define-public express-beta-diversity
3317 (name "express-beta-diversity")
3322 (url "https://github.com/dparks1134/ExpressBetaDiversity")
3323 (commit (string-append "v" version))))
3324 (file-name (git-file-name name version))
3327 "0s0yzg5c21349rh7x4w9266jsvnp7j1hp9cf8sk32hz8nvrj745x"))))
3328 (build-system gnu-build-system)
3331 (modify-phases %standard-phases
3333 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
3335 (lambda _ (invoke "../bin/ExpressBetaDiversity" "-u") #t))
3337 (lambda* (#:key outputs #:allow-other-keys)
3338 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3339 (install-file "../scripts/convertToEBD.py" bin)
3340 (install-file "../bin/ExpressBetaDiversity" bin)
3343 `(("python" ,python-2)))
3344 (home-page "https://github.com/dparks1134/ExpressBetaDiversity")
3345 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
3347 "Express Beta Diversity (EBD) calculates ecological beta diversity
3348 (dissimilarity) measures between biological communities. EBD implements a
3349 variety of diversity measures including those that make use of phylogenetic
3350 similarity of community members.")
3351 (license license:gpl3+)))
3353 (define-public fasttree
3360 "http://www.microbesonline.org/fasttree/FastTree-"
3364 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
3365 (build-system gnu-build-system)
3367 `(#:tests? #f ; no "check" target
3369 (modify-phases %standard-phases
3373 (lambda* (#:key source #:allow-other-keys)
3376 "-finline-functions"
3387 "-finline-functions"
3396 (lambda* (#:key outputs #:allow-other-keys)
3397 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3398 (install-file "FastTree" bin)
3399 (install-file "FastTreeMP" bin)
3401 (home-page "http://www.microbesonline.org/fasttree")
3402 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
3404 "FastTree can handle alignments with up to a million of sequences in a
3405 reasonable amount of time and memory. For large alignments, FastTree is
3406 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
3407 (license license:gpl2+)))
3409 (define-public fastx-toolkit
3411 (name "fastx-toolkit")
3417 "https://github.com/agordon/fastx_toolkit/releases/download/"
3418 version "/fastx_toolkit-" version ".tar.bz2"))
3421 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
3422 (build-system gnu-build-system)
3424 `(("libgtextutils" ,libgtextutils)))
3426 `(("gcc" ,gcc-6) ;; doesn't build with later versions
3427 ("pkg-config" ,pkg-config)))
3428 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
3429 (synopsis "Tools for FASTA/FASTQ file preprocessing")
3431 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
3432 FASTA/FASTQ files preprocessing.
3434 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
3435 containing multiple short-reads sequences. The main processing of such
3436 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
3437 is sometimes more productive to preprocess the files before mapping the
3438 sequences to the genome---manipulating the sequences to produce better mapping
3439 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
3440 (license license:agpl3+)))
3442 (define-public flexbar
3449 (url "https://github.com/seqan/flexbar")
3450 (commit (string-append "v" version))))
3451 (file-name (git-file-name name version))
3454 "1pq9sxvdnldl14libk234m72dqhwgzs3acgl943wchwdqlcsi5r2"))))
3455 (build-system cmake-build-system)
3458 (modify-phases %standard-phases
3459 (add-after 'unpack 'do-not-tune-to-CPU
3461 (substitute* "src/CMakeLists.txt"
3462 ((" -march=native") ""))
3465 (lambda* (#:key outputs #:allow-other-keys)
3466 (setenv "PATH" (string-append (getcwd) ":" (getenv "PATH")))
3467 (with-directory-excursion "../source/test"
3468 (invoke "bash" "flexbar_test.sh"))
3471 (lambda* (#:key outputs #:allow-other-keys)
3472 (let* ((out (string-append (assoc-ref outputs "out")))
3473 (bin (string-append out "/bin/")))
3474 (install-file "flexbar" bin))
3480 `(("pkg-config" ,pkg-config)
3482 (home-page "https://github.com/seqan/flexbar")
3483 (synopsis "Barcode and adapter removal tool for sequencing platforms")
3485 "Flexbar preprocesses high-throughput nucleotide sequencing data
3486 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
3487 Moreover, trimming and filtering features are provided. Flexbar increases
3488 read mapping rates and improves genome and transcriptome assemblies. It
3489 supports next-generation sequencing data in fasta/q and csfasta/q format from
3490 Illumina, Roche 454, and the SOLiD platform.")
3491 (license license:bsd-3)))
3493 (define-public fraggenescan
3495 (name "fraggenescan")
3501 (string-append "mirror://sourceforge/fraggenescan/"
3502 "FragGeneScan" version ".tar.gz"))
3504 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
3505 (build-system gnu-build-system)
3508 (modify-phases %standard-phases
3510 (add-before 'build 'patch-paths
3511 (lambda* (#:key outputs #:allow-other-keys)
3512 (let* ((out (string-append (assoc-ref outputs "out")))
3513 (share (string-append out "/share/fraggenescan/")))
3514 (substitute* "run_FragGeneScan.pl"
3516 (string-append "system(\"" (which "rm")))
3518 (string-append "system(\"" (which "mv")))
3519 (("\\\"awk") (string-append "\"" (which "awk")))
3520 ;; This script and other programs expect the training files
3521 ;; to be in the non-standard location bin/train/XXX. Change
3522 ;; this to be share/fraggenescan/train/XXX instead.
3523 (("^\\$train.file = \\$dir.*")
3524 (string-append "$train_file = \""
3526 "train/\".$FGS_train_file;")))
3527 (substitute* "run_hmm.c"
3528 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
3529 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
3533 (invoke "make" "clean")
3534 (invoke "make" "fgs")
3537 (lambda* (#:key outputs #:allow-other-keys)
3538 (let* ((out (string-append (assoc-ref outputs "out")))
3539 (bin (string-append out "/bin/"))
3540 (share (string-append out "/share/fraggenescan/train")))
3541 (install-file "run_FragGeneScan.pl" bin)
3542 (install-file "FragGeneScan" bin)
3543 (copy-recursively "train" share))
3546 (add-after 'install 'post-install-check
3547 ;; In lieu of 'make check', run one of the examples and check the
3548 ;; output files gets created.
3549 (lambda* (#:key outputs #:allow-other-keys)
3550 (let* ((out (string-append (assoc-ref outputs "out")))
3551 (bin (string-append out "/bin/"))
3552 (frag (string-append bin "run_FragGeneScan.pl")))
3553 ;; Test complete genome.
3555 "-genome=./example/NC_000913.fna"
3559 (unless (and (file-exists? "test2.faa")
3560 (file-exists? "test2.ffn")
3561 (file-exists? "test2.gff")
3562 (file-exists? "test2.out"))
3563 (error "Expected files do not exist."))
3564 ;; Test incomplete sequences.
3566 "-genome=./example/NC_000913-fgs.ffn"
3573 ("python" ,python-2))) ;not compatible with python 3.
3574 (home-page "https://sourceforge.net/projects/fraggenescan/")
3575 (synopsis "Finds potentially fragmented genes in short reads")
3577 "FragGeneScan is a program for predicting bacterial and archaeal genes in
3578 short and error-prone DNA sequencing reads. It can also be applied to predict
3579 genes in incomplete assemblies or complete genomes.")
3580 ;; GPL3+ according to private correspondense with the authors.
3581 (license license:gpl3+)))
3583 (define-public fxtract
3584 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
3592 (url "https://github.com/ctSkennerton/fxtract")
3594 (file-name (git-file-name name version))
3597 "0hab3gpwf4w9s87qlbswq6ws1qqybh4dcqk79q1ahyldzai5fgp5"))))
3598 (build-system gnu-build-system)
3600 `(#:make-flags (list
3601 (string-append "PREFIX=" (assoc-ref %outputs "out"))
3603 #:test-target "fxtract_test"
3605 (modify-phases %standard-phases
3607 (add-before 'build 'copy-util
3608 (lambda* (#:key inputs #:allow-other-keys)
3610 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
3612 ;; Do not use make install as this requires additional dependencies.
3614 (lambda* (#:key outputs #:allow-other-keys)
3615 (let* ((out (assoc-ref outputs "out"))
3616 (bin (string-append out"/bin")))
3617 (install-file "fxtract" bin)
3623 ;; ctskennerton-util is licensed under GPL2.
3624 `(("ctskennerton-util"
3628 (url "https://github.com/ctSkennerton/util")
3629 (commit util-commit)))
3630 (file-name (string-append
3631 "ctstennerton-util-" util-commit "-checkout"))
3634 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
3635 (home-page "https://github.com/ctSkennerton/fxtract")
3636 (synopsis "Extract sequences from FASTA and FASTQ files")
3638 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
3639 or FASTQ) file given a subsequence. It uses a simple substring search for
3640 basic tasks but can change to using POSIX regular expressions, PCRE, hash
3641 lookups or multi-pattern searching as required. By default fxtract looks in
3642 the sequence of each record but can also be told to look in the header,
3643 comment or quality sections.")
3644 ;; 'util' requires SSE instructions.
3645 (supported-systems '("x86_64-linux"))
3646 (license license:expat))))
3648 (define-public gemma
3655 (url "https://github.com/genetics-statistics/GEMMA")
3657 (file-name (git-file-name name version))
3660 "1p8a7kkfn1mmrg017aziy544aha8i9h6wd1x2dk3w2794wl33qb7"))
3661 (modules '((guix build utils)))
3664 (delete-file-recursively "contrib")
3666 (build-system gnu-build-system)
3669 ("openblas" ,openblas)
3672 `(("catch" ,catch-framework2-1)
3674 ("shunit2" ,shunit2)
3678 (modify-phases %standard-phases
3680 (add-after 'unpack 'prepare-build
3681 (lambda* (#:key inputs #:allow-other-keys)
3683 (substitute* "Makefile"
3684 (("/usr/local/opt/openblas")
3685 (assoc-ref inputs "openblas")))
3688 (lambda* (#:key tests? #:allow-other-keys)
3690 ;; 'make slow-check' expects shunit2-2.0.3.
3691 (with-directory-excursion "test"
3692 (invoke "./test_suite.sh"))
3695 (lambda* (#:key outputs #:allow-other-keys)
3696 (install-file "bin/gemma"
3697 (string-append (assoc-ref outputs "out") "/bin"))
3699 (home-page "https://github.com/genetics-statistics/GEMMA")
3700 (synopsis "Tool for genome-wide efficient mixed model association")
3702 "@acronym{GEMMA, Genome-wide Efficient Mixed Model Association} provides a
3703 standard linear mixed model resolver with application in @acronym{GWAS,
3704 genome-wide association studies}.")
3705 (license license:gpl3)))
3714 (url "https://github.com/nboley/grit")
3716 (file-name (git-file-name name version))
3719 "1l5v8vfvfbrpmgnrvbrbv40d0arhxcnmxgv2f1mlcqfa3q6bkqm9"))))
3720 (build-system python-build-system)
3722 `(#:python ,python-2
3724 (modify-phases %standard-phases
3725 (add-after 'unpack 'generate-from-cython-sources
3726 (lambda* (#:key inputs outputs #:allow-other-keys)
3727 ;; Delete these C files to force fresh generation from pyx sources.
3728 (delete-file "grit/sparsify_support_fns.c")
3729 (delete-file "grit/call_peaks_support_fns.c")
3730 (substitute* "setup.py"
3731 (("Cython.Setup") "Cython.Build"))
3734 `(("python-scipy" ,python2-scipy)
3735 ("python-numpy" ,python2-numpy)
3736 ("python-pysam" ,python2-pysam)
3737 ("python-networkx" ,python2-networkx)))
3739 `(("python-cython" ,python2-cython)))
3740 ;; The canonical <http://grit-bio.org> home page times out as of 2020-01-21.
3741 (home-page "https://github.com/nboley/grit")
3742 (synopsis "Tool for integrative analysis of RNA-seq type assays")
3744 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
3745 full length transcript models. When none of these data sources are available,
3746 GRIT can be run by providing a candidate set of TES or TSS sites. In
3747 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
3748 also be run in quantification mode, where it uses a provided GTF file and just
3749 estimates transcript expression.")
3750 (license license:gpl3+)))
3752 (define-public hisat
3759 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
3760 version "-beta-source.zip"))
3763 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
3764 (build-system gnu-build-system)
3766 `(#:tests? #f ;no check target
3767 #:make-flags '("allall"
3768 ;; Disable unsupported `popcnt' instructions on
3769 ;; architectures other than x86_64
3770 ,@(if (string-prefix? "x86_64"
3771 (or (%current-target-system)
3774 '("POPCNT_CAPABILITY=0")))
3776 (modify-phases %standard-phases
3777 (add-after 'unpack 'patch-sources
3779 ;; XXX Cannot use snippet because zip files are not supported
3780 (substitute* "Makefile"
3781 (("^CC = .*$") "CC = gcc")
3782 (("^CPP = .*$") "CPP = g++")
3783 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
3784 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
3785 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
3786 (substitute* '("hisat-build" "hisat-inspect")
3787 (("/usr/bin/env") (which "env")))
3790 (lambda* (#:key outputs #:allow-other-keys)
3791 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
3792 (for-each (lambda (file)
3793 (install-file file bin))
3796 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
3798 (delete 'configure))))
3800 `(("unzip" ,unzip)))
3805 ;; Non-portable SSE instructions are used so building fails on platforms
3806 ;; other than x86_64.
3807 (supported-systems '("x86_64-linux"))
3808 (home-page "https://ccb.jhu.edu/software/hisat/index.shtml")
3809 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
3811 "HISAT is a fast and sensitive spliced alignment program for mapping
3812 RNA-seq reads. In addition to one global FM index that represents a whole
3813 genome, HISAT uses a large set of small FM indexes that collectively cover the
3814 whole genome. These small indexes (called local indexes) combined with
3815 several alignment strategies enable effective alignment of RNA-seq reads, in
3816 particular, reads spanning multiple exons.")
3817 (license license:gpl3+)))
3819 (define-public hisat2
3826 (uri (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
3827 "/downloads/hisat2-" version "-source.zip"))
3830 "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"))))
3831 (build-system gnu-build-system)
3833 `(#:tests? #f ; no check target
3834 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
3835 #:modules ((guix build gnu-build-system)
3839 (modify-phases %standard-phases
3840 (add-after 'unpack 'make-deterministic
3842 (substitute* "Makefile"
3847 (lambda* (#:key outputs #:allow-other-keys)
3848 (let* ((out (assoc-ref outputs "out"))
3849 (bin (string-append out "/bin/"))
3850 (doc (string-append out "/share/doc/hisat2/")))
3852 (cut install-file <> bin)
3854 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
3856 (install-file "doc/manual.inc.html" doc))
3859 `(("unzip" ,unzip) ; needed for archive from ftp
3861 ("pandoc" ,pandoc))) ; for documentation
3862 (home-page "https://ccb.jhu.edu/software/hisat2/index.shtml")
3863 (synopsis "Graph-based alignment of genomic sequencing reads")
3864 (description "HISAT2 is a fast and sensitive alignment program for mapping
3865 next-generation sequencing reads (both DNA and RNA) to a population of human
3866 genomes (as well as to a single reference genome). In addition to using one
3867 global @dfn{graph FM} (GFM) index that represents a population of human
3868 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
3869 the whole genome. These small indexes, combined with several alignment
3870 strategies, enable rapid and accurate alignment of sequencing reads. This new
3871 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
3872 ;; HISAT2 contains files from Bowtie2, which is released under
3873 ;; GPLv2 or later. The HISAT2 source files are released under
3875 (license license:gpl3+)))
3877 (define-public hmmer
3885 "http://eddylab.org/software/hmmer/hmmer-" version ".tar.gz"))
3888 "0s9wf6n0qanbx8qs6igfl3vyjikwbrvh4d9d6mv54yp3xysykzlj"))))
3889 (build-system gnu-build-system)
3890 (native-inputs `(("perl" ,perl)
3891 ("python" ,python))) ; for tests
3892 (home-page "http://hmmer.org/")
3893 (synopsis "Biosequence analysis using profile hidden Markov models")
3895 "HMMER is used for searching sequence databases for homologs of protein
3896 sequences, and for making protein sequence alignments. It implements methods
3897 using probabilistic models called profile hidden Markov models (profile
3899 ;; hmmer uses non-portable SSE intrinsics so building fails on other
3901 (supported-systems '("x86_64-linux" "i686-linux"))
3902 (license license:bsd-3)))
3904 (define-public htseq
3910 (uri (pypi-uri "HTSeq" version))
3913 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
3914 (build-system python-build-system)
3916 `(("python-cython" ,python-cython)))
3917 ;; Numpy needs to be propagated when htseq is used as a Python library.
3919 `(("python-numpy" ,python-numpy)))
3921 `(("python-pysam" ,python-pysam)
3922 ("python-matplotlib" ,python-matplotlib)))
3923 (home-page "https://htseq.readthedocs.io/")
3924 (synopsis "Analysing high-throughput sequencing data with Python")
3926 "HTSeq is a Python package that provides infrastructure to process data
3927 from high-throughput sequencing assays.")
3928 (license license:gpl3+)))
3930 (define-public python2-htseq
3931 (package-with-python2 htseq))
3933 (define-public java-htsjdk
3935 (name "java-htsjdk")
3936 (version "2.3.0") ; last version without build dependency on gradle
3940 (url "https://github.com/samtools/htsjdk")
3942 (file-name (git-file-name name version))
3945 "1b178ixcabanm834ydjl3jiakpyxdmki32hqfv2abrzn3rcwa28i"))
3946 (modules '((guix build utils)))
3948 ;; Delete pre-built binaries
3950 (delete-file-recursively "lib")
3953 (build-system ant-build-system)
3955 `(#:tests? #f ; test require Internet access
3958 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3959 "/share/java/htsjdk/"))
3960 #:build-target "all"
3962 (modify-phases %standard-phases
3963 ;; The build phase also installs the jars
3964 (delete 'install))))
3966 `(("java-ngs" ,java-ngs)
3967 ("java-snappy-1" ,java-snappy-1)
3968 ("java-commons-compress" ,java-commons-compress)
3969 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3970 ("java-commons-jexl-2" ,java-commons-jexl-2)
3971 ("java-xz" ,java-xz)))
3973 `(("java-testng" ,java-testng)))
3974 (home-page "http://samtools.github.io/htsjdk/")
3975 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3977 "HTSJDK is an implementation of a unified Java library for accessing
3978 common file formats, such as SAM and VCF, used for high-throughput
3979 sequencing (HTS) data. There are also an number of useful utilities for
3980 manipulating HTS data.")
3981 (license license:expat)))
3983 (define-public java-htsjdk-latest
3985 (name "java-htsjdk")
3990 (url "https://github.com/samtools/htsjdk")
3992 (file-name (string-append name "-" version "-checkout"))
3995 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
3996 (build-system ant-build-system)
3998 `(#:tests? #f ; test require Scala
4000 #:jar-name "htsjdk.jar"
4002 (modify-phases %standard-phases
4003 (add-after 'unpack 'remove-useless-build.xml
4004 (lambda _ (delete-file "build.xml") #t))
4005 ;; The tests require the scalatest package.
4006 (add-after 'unpack 'remove-tests
4007 (lambda _ (delete-file-recursively "src/test") #t)))))
4009 `(("java-ngs" ,java-ngs)
4010 ("java-snappy-1" ,java-snappy-1)
4011 ("java-commons-compress" ,java-commons-compress)
4012 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
4013 ("java-commons-jexl-2" ,java-commons-jexl-2)
4014 ("java-xz" ,java-xz)))
4016 `(("java-junit" ,java-junit)))
4017 (home-page "http://samtools.github.io/htsjdk/")
4018 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
4020 "HTSJDK is an implementation of a unified Java library for accessing
4021 common file formats, such as SAM and VCF, used for high-throughput
4022 sequencing (HTS) data. There are also an number of useful utilities for
4023 manipulating HTS data.")
4024 (license license:expat)))
4026 ;; This is needed for picard 2.10.3
4027 (define-public java-htsjdk-2.10.1
4028 (package (inherit java-htsjdk-latest)
4029 (name "java-htsjdk")
4034 (url "https://github.com/samtools/htsjdk")
4036 (file-name (string-append name "-" version "-checkout"))
4039 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
4040 (build-system ant-build-system)
4042 `(#:tests? #f ; tests require Scala
4044 #:jar-name "htsjdk.jar"
4046 (modify-phases %standard-phases
4047 (add-after 'unpack 'remove-useless-build.xml
4048 (lambda _ (delete-file "build.xml") #t))
4049 ;; The tests require the scalatest package.
4050 (add-after 'unpack 'remove-tests
4051 (lambda _ (delete-file-recursively "src/test") #t)))))))
4053 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
4054 ;; recent version of java-htsjdk, which depends on gradle.
4055 (define-public java-picard
4057 (name "java-picard")
4062 (url "https://github.com/broadinstitute/picard")
4064 (file-name (string-append "java-picard-" version "-checkout"))
4067 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
4068 (modules '((guix build utils)))
4071 ;; Delete pre-built binaries.
4072 (delete-file-recursively "lib")
4074 (substitute* "build.xml"
4075 ;; Remove build-time dependency on git.
4076 (("failifexecutionfails=\"true\"")
4077 "failifexecutionfails=\"false\"")
4079 (("depends=\"compile-htsjdk, ")
4081 (("depends=\"compile-htsjdk-tests, ")
4083 ;; Build picard-lib.jar before building picard.jar
4084 (("name=\"picard-jar\" depends=\"" line)
4085 (string-append line "picard-lib-jar, ")))
4087 (build-system ant-build-system)
4089 `(#:build-target "picard-jar"
4090 #:test-target "test"
4091 ;; Tests require jacoco:coverage.
4094 (list (string-append "-Dhtsjdk_lib_dir="
4095 (assoc-ref %build-inputs "java-htsjdk")
4096 "/share/java/htsjdk/")
4097 "-Dhtsjdk-classes=dist/tmp"
4098 (string-append "-Dhtsjdk-version="
4099 ,(package-version java-htsjdk)))
4102 (modify-phases %standard-phases
4103 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
4104 (delete 'generate-jar-indices)
4105 (add-after 'unpack 'use-our-htsjdk
4106 (lambda* (#:key inputs #:allow-other-keys)
4107 (substitute* "build.xml"
4108 (("\\$\\{htsjdk\\}/lib")
4109 (string-append (assoc-ref inputs "java-htsjdk")
4110 "/share/java/htsjdk/")))
4112 (add-after 'unpack 'make-test-target-independent
4113 (lambda* (#:key inputs #:allow-other-keys)
4114 (substitute* "build.xml"
4115 (("name=\"test\" depends=\"compile, ")
4116 "name=\"test\" depends=\""))
4118 (replace 'install (install-jars "dist")))))
4120 `(("java-htsjdk" ,java-htsjdk)
4121 ("java-guava" ,java-guava)))
4123 `(("java-testng" ,java-testng)))
4124 (home-page "http://broadinstitute.github.io/picard/")
4125 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
4126 (description "Picard is a set of Java command line tools for manipulating
4127 high-throughput sequencing (HTS) data and formats. Picard is implemented
4128 using the HTSJDK Java library to support accessing file formats that are
4129 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
4131 (license license:expat)))
4133 ;; This is needed for dropseq-tools
4134 (define-public java-picard-2.10.3
4136 (name "java-picard")
4141 (url "https://github.com/broadinstitute/picard")
4143 (file-name (string-append "java-picard-" version "-checkout"))
4146 "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi"))))
4147 (build-system ant-build-system)
4149 `(#:jar-name "picard.jar"
4150 ;; Tests require jacoco:coverage.
4153 #:main-class "picard.cmdline.PicardCommandLine"
4154 #:modules ((guix build ant-build-system)
4156 (guix build java-utils)
4161 (modify-phases %standard-phases
4162 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
4163 (delete 'generate-jar-indices)
4164 (add-after 'unpack 'remove-useless-build.xml
4165 (lambda _ (delete-file "build.xml") #t))
4166 ;; This is necessary to ensure that htsjdk is found when using
4167 ;; picard.jar as an executable.
4168 (add-before 'build 'edit-classpath-in-manifest
4169 (lambda* (#:key inputs #:allow-other-keys)
4170 (chmod "build.xml" #o664)
4171 (call-with-output-file "build.xml.new"
4175 (with-input-from-file "build.xml"
4176 (lambda _ (xml->sxml #:trim-whitespace? #t)))
4177 `((target . ,(lambda (tag . kids)
4178 (let ((name ((sxpath '(name *text*))
4180 ;; FIXME: We're breaking the line
4181 ;; early with a dummy path to
4182 ;; ensure that the store reference
4183 ;; isn't broken apart and can still
4184 ;; be found by the reference
4189 ~a/share/java/htsjdk.jar${line.separator}${line.separator}"
4190 ;; maximum line length is 70
4191 (string-tabulate (const #\b) 57)
4192 (assoc-ref inputs "java-htsjdk"))))
4193 (if (member "manifest" name)
4196 (@ (file "${manifest.file}")
4197 (match "\\r\\n\\r\\n")
4198 (replace "${line.separator}")))
4201 (file "${manifest.file}")
4204 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
4205 (*text* . ,(lambda (_ txt) txt))))
4207 (rename-file "build.xml.new" "build.xml")
4210 `(("java-htsjdk" ,java-htsjdk-2.10.1)))
4212 `(("java-testng" ,java-testng)
4213 ("java-guava" ,java-guava)))
4214 (home-page "http://broadinstitute.github.io/picard/")
4215 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
4216 (description "Picard is a set of Java command line tools for manipulating
4217 high-throughput sequencing (HTS) data and formats. Picard is implemented
4218 using the HTSJDK Java library to support accessing file formats that are
4219 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
4221 (license license:expat)))
4223 ;; This is the last version of Picard to provide net.sf.samtools
4224 (define-public java-picard-1.113
4225 (package (inherit java-picard)
4226 (name "java-picard")
4231 (url "https://github.com/broadinstitute/picard")
4233 (file-name (string-append "java-picard-" version "-checkout"))
4236 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
4237 (modules '((guix build utils)))
4240 ;; Delete pre-built binaries.
4241 (delete-file-recursively "lib")
4244 (build-system ant-build-system)
4246 `(#:build-target "picard-jar"
4247 #:test-target "test"
4248 ;; FIXME: the class path at test time is wrong.
4249 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
4250 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
4254 ;; This is only used for tests.
4256 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
4258 (modify-phases %standard-phases
4259 ;; FIXME: This phase fails.
4260 (delete 'generate-jar-indices)
4261 ;; Do not use bundled ant bzip2.
4262 (add-after 'unpack 'use-ant-bzip
4263 (lambda* (#:key inputs #:allow-other-keys)
4264 (substitute* "build.xml"
4265 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
4266 (string-append (assoc-ref inputs "ant")
4269 (add-after 'unpack 'make-test-target-independent
4270 (lambda* (#:key inputs #:allow-other-keys)
4271 (substitute* "build.xml"
4272 (("name=\"test\" depends=\"compile, ")
4273 "name=\"test\" depends=\"compile-tests, ")
4274 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
4275 "name=\"compile\" depends=\"compile-src\""))
4277 (add-after 'unpack 'fix-deflater-path
4278 (lambda* (#:key outputs #:allow-other-keys)
4279 (substitute* "src/java/net/sf/samtools/Defaults.java"
4280 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
4281 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
4282 (assoc-ref outputs "out")
4283 "/lib/jni/libIntelDeflater.so"
4286 ;; Build the deflater library, because we've previously deleted the
4287 ;; pre-built one. This can only be built with access to the JDK
4289 (add-after 'build 'build-jni
4290 (lambda* (#:key inputs #:allow-other-keys)
4293 (invoke "tar" "--strip-components=1" "-C" "jdk-src"
4294 "-xf" (assoc-ref inputs "jdk-src"))
4295 (invoke "javah" "-jni"
4296 "-classpath" "classes"
4298 "net.sf.samtools.util.zip.IntelDeflater")
4299 (with-directory-excursion "src/c/inteldeflater"
4300 (invoke "gcc" "-I../../../lib" "-I."
4301 (string-append "-I" (assoc-ref inputs "jdk")
4303 "-I../../../jdk-src/src/share/native/common/"
4304 "-I../../../jdk-src/src/solaris/native/common/"
4305 "-c" "-O3" "-fPIC" "IntelDeflater.c")
4306 (invoke "gcc" "-shared"
4307 "-o" "../../../lib/jni/libIntelDeflater.so"
4308 "IntelDeflater.o" "-lz" "-lstdc++"))
4310 ;; We can only build everything else after building the JNI library.
4311 (add-after 'build-jni 'build-rest
4312 (lambda* (#:key make-flags #:allow-other-keys)
4313 (apply invoke `("ant" "all" ,@make-flags))
4315 (add-before 'build 'set-JAVA6_HOME
4317 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
4319 (replace 'install (install-jars "dist"))
4320 (add-after 'install 'install-jni-lib
4321 (lambda* (#:key outputs #:allow-other-keys)
4322 (let ((jni (string-append (assoc-ref outputs "out")
4325 (install-file "lib/jni/libIntelDeflater.so" jni)
4328 `(("java-snappy-1" ,java-snappy-1)
4329 ("java-commons-jexl-2" ,java-commons-jexl-2)
4330 ("java-cofoja" ,java-cofoja)
4331 ("ant" ,ant/java8) ; for bzip2 support at runtime
4334 `(("ant-apache-bcel" ,ant-apache-bcel)
4335 ("ant-junit" ,ant-junit)
4336 ("java-testng" ,java-testng)
4337 ("java-commons-bcel" ,java-commons-bcel)
4338 ("java-jcommander" ,java-jcommander)
4339 ("jdk" ,icedtea-8 "jdk")
4340 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
4342 (define-public fastqc
4349 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
4350 "projects/fastqc/fastqc_v"
4351 version "_source.zip"))
4354 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
4355 (build-system ant-build-system)
4357 `(#:tests? #f ; there are no tests
4358 #:build-target "build"
4360 (modify-phases %standard-phases
4361 (add-after 'unpack 'fix-dependencies
4362 (lambda* (#:key inputs #:allow-other-keys)
4363 (substitute* "build.xml"
4365 (string-append (assoc-ref inputs "java-jbzip2")
4366 "/share/java/jbzip2.jar"))
4368 (string-append (assoc-ref inputs "java-picard-1.113")
4369 "/share/java/sam-1.112.jar"))
4371 (string-append (assoc-ref inputs "java-cisd-jhdf5")
4372 "/share/java/sis-jhdf5.jar")))
4374 ;; There is no installation target
4376 (lambda* (#:key inputs outputs #:allow-other-keys)
4377 (let* ((out (assoc-ref outputs "out"))
4378 (bin (string-append out "/bin"))
4379 (share (string-append out "/share/fastqc/"))
4380 (exe (string-append share "/fastqc")))
4381 (for-each mkdir-p (list bin share))
4382 (copy-recursively "bin" share)
4384 (("my \\$java_bin = 'java';")
4385 (string-append "my $java_bin = '"
4386 (assoc-ref inputs "java")
4389 (symlink exe (string-append bin "/fastqc"))
4393 ("perl" ,perl) ; needed for the wrapper script
4394 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
4395 ("java-picard-1.113" ,java-picard-1.113)
4396 ("java-jbzip2" ,java-jbzip2)))
4398 `(("unzip" ,unzip)))
4399 (home-page "https://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
4400 (synopsis "Quality control tool for high throughput sequence data")
4402 "FastQC aims to provide a simple way to do some quality control
4403 checks on raw sequence data coming from high throughput sequencing
4404 pipelines. It provides a modular set of analyses which you can use to
4405 give a quick impression of whether your data has any problems of which
4406 you should be aware before doing any further analysis.
4408 The main functions of FastQC are:
4411 @item Import of data from BAM, SAM or FastQ files (any variant);
4412 @item Providing a quick overview to tell you in which areas there may
4414 @item Summary graphs and tables to quickly assess your data;
4415 @item Export of results to an HTML based permanent report;
4416 @item Offline operation to allow automated generation of reports
4417 without running the interactive application.
4419 (license license:gpl3+)))
4421 (define-public fastp
4429 (url "https://github.com/OpenGene/fastp")
4430 (commit (string-append "v" version))))
4431 (file-name (git-file-name name version))
4434 "1r6ms5zbf5rps4rgp4z73nczadl00b5rqylw8f684isfz27dp0xh"))))
4435 (build-system gnu-build-system)
4437 `(#:tests? #f ; there are none
4439 (list (string-append "BINDIR=" (assoc-ref %outputs "out") "/bin"))
4441 (modify-phases %standard-phases
4443 (add-before 'install 'create-target-dir
4444 (lambda* (#:key outputs #:allow-other-keys)
4445 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4449 (home-page "https://github.com/OpenGene/fastp/")
4450 (synopsis "All-in-one FastQ preprocessor")
4452 "Fastp is a tool designed to provide fast all-in-one preprocessing for
4453 FastQ files. This tool has multi-threading support to afford high
4455 (license license:expat)))
4457 (define-public htslib
4464 "https://github.com/samtools/htslib/releases/download/"
4465 version "/htslib-" version ".tar.bz2"))
4468 "1mrq4mihzx37yqhj3sfz6da6mw49niia808bzsw2gkkgmadxvyng"))))
4469 (build-system gnu-build-system)
4470 ;; Let htslib translate "gs://" and "s3://" to regular https links with
4471 ;; "--enable-gcs" and "--enable-s3". For these options to work, we also
4472 ;; need to set "--enable-libcurl".
4474 `(#:configure-flags '("--enable-gcs"
4479 ("openssl" ,openssl)))
4480 ;; This is referred to in the pkg-config file as a required library.
4485 (home-page "https://www.htslib.org")
4486 (synopsis "C library for reading/writing high-throughput sequencing data")
4488 "HTSlib is a C library for reading/writing high-throughput sequencing
4489 data. It also provides the @command{bgzip}, @command{htsfile}, and
4490 @command{tabix} utilities.")
4491 ;; Files under cram/ are released under the modified BSD license;
4492 ;; the rest is released under the Expat license
4493 (license (list license:expat license:bsd-3))))
4495 (define-public htslib-1.9
4496 (package (inherit htslib)
4502 "https://github.com/samtools/htslib/releases/download/"
4503 version "/htslib-" version ".tar.bz2"))
4506 "16ljv43sc3fxmv63w7b2ff8m1s7h89xhazwmbm1bicz8axq8fjz0"))))))
4508 ;; This package should be removed once no packages rely upon it.
4516 "https://github.com/samtools/htslib/releases/download/"
4517 version "/htslib-" version ".tar.bz2"))
4520 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
4529 (url "https://github.com/nboley/idr")
4531 (file-name (git-file-name name version))
4534 "04j876h6z444v2q79drxx283d3k5snd72kj895wbalnl42206x9g"))
4535 ;; Delete generated C code.
4537 '(begin (delete-file "idr/inv_cdf.c") #t))))
4538 (build-system python-build-system)
4539 ;; There is only one test ("test_inv_cdf.py") and it tests features that
4540 ;; are no longer part of this package. It also asserts False, which
4541 ;; causes the tests to always fail.
4542 (arguments `(#:tests? #f))
4544 `(("python-scipy" ,python-scipy)
4545 ("python-sympy" ,python-sympy)
4546 ("python-numpy" ,python-numpy)
4547 ("python-matplotlib" ,python-matplotlib)))
4549 `(("python-cython" ,python-cython)))
4550 (home-page "https://github.com/nboley/idr")
4551 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
4553 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
4554 to measure the reproducibility of findings identified from replicate
4555 experiments and provide highly stable thresholds based on reproducibility.")
4556 (license license:gpl2+)))
4558 (define-public jellyfish
4564 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
4565 "releases/download/v" version
4566 "/jellyfish-" version ".tar.gz"))
4569 "1k4pc3fvv6w1km2yph4m5sd78fbxp21d6xyzgmy0gjihzc6mb249"))))
4570 (build-system gnu-build-system)
4571 (outputs '("out" ;for library
4572 "ruby" ;for Ruby bindings
4573 "python")) ;for Python bindings
4576 (list (string-append "--enable-ruby-binding="
4577 (assoc-ref %outputs "ruby"))
4578 (string-append "--enable-python-binding="
4579 (assoc-ref %outputs "python")))
4581 (modify-phases %standard-phases
4582 (add-before 'check 'set-SHELL-variable
4584 ;; generator_manager.hpp either uses /bin/sh or $SHELL
4586 (setenv "SHELL" (which "bash"))
4592 ("python" ,python-2)
4593 ("pkg-config" ,pkg-config)))
4595 `(("htslib" ,htslib)))
4596 (synopsis "Tool for fast counting of k-mers in DNA")
4598 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
4599 DNA. A k-mer is a substring of length k, and counting the occurrences of all
4600 such substrings is a central step in many analyses of DNA sequence. Jellyfish
4601 is a command-line program that reads FASTA and multi-FASTA files containing
4602 DNA sequences. It outputs its k-mer counts in a binary format, which can be
4603 translated into a human-readable text format using the @code{jellyfish dump}
4604 command, or queried for specific k-mers with @code{jellyfish query}.")
4605 (home-page "http://www.genome.umd.edu/jellyfish.html")
4606 ;; JELLYFISH seems to be 64-bit only.
4607 (supported-systems '("x86_64-linux" "aarch64-linux" "mips64el-linux"))
4608 ;; The combined work is published under the GPLv3 or later. Individual
4609 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
4610 (license (list license:gpl3+ license:expat))))
4612 (define-public khmer
4620 (url "https://github.com/dib-lab/khmer")
4621 (commit (string-append "v" version))))
4622 (file-name (git-file-name name version))
4625 "01l4jczglkl7yfhgvzx8j0df7k54bk1r8sli9ll16i1mis0d8f37"))
4626 (modules '((guix build utils)))
4629 ;; Delete bundled libraries. We do not replace the bundled seqan
4630 ;; as it is a modified subset of the old version 1.4.1.
4632 ;; We do not replace the bundled MurmurHash as the canonical
4633 ;; repository for this code 'SMHasher' is unsuitable for providing
4635 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
4636 (delete-file-recursively "third-party/zlib")
4637 (delete-file-recursively "third-party/bzip2")
4638 (delete-file-recursively "third-party/seqan")
4639 (substitute* "setup.cfg"
4640 (("# libraries = z,bz2")
4641 "libraries = z,bz2")
4642 (("include:third-party/zlib:third-party/bzip2")
4645 (build-system python-build-system)
4648 (modify-phases %standard-phases
4649 (add-after 'unpack 'set-cc
4650 (lambda _ (setenv "CC" "gcc") #t))
4652 (add-before 'reset-gzip-timestamps 'make-files-writable
4653 (lambda* (#:key outputs #:allow-other-keys)
4654 ;; Make sure .gz files are writable so that the
4655 ;; 'reset-gzip-timestamps' phase can do its work.
4656 (let ((out (assoc-ref outputs "out")))
4657 (for-each make-file-writable
4658 (find-files out "\\.gz$"))
4661 `(("python-cython" ,python-cython)
4662 ("python-pytest" ,python-pytest)
4663 ("python-pytest-runner" ,python-pytest-runner)))
4668 ("python-screed" ,python-screed)
4669 ("python-bz2file" ,python-bz2file)))
4670 (home-page "https://khmer.readthedocs.org/")
4671 (synopsis "K-mer counting, filtering and graph traversal library")
4672 (description "The khmer software is a set of command-line tools for
4673 working with DNA shotgun sequencing data from genomes, transcriptomes,
4674 metagenomes and single cells. Khmer can make de novo assemblies faster, and
4675 sometimes better. Khmer can also identify and fix problems with shotgun
4677 ;; When building on i686, armhf and mips64el, we get the following error:
4678 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
4679 (supported-systems '("x86_64-linux" "aarch64-linux"))
4680 (license license:bsd-3)))
4682 (define-public kaiju
4689 (url "https://github.com/bioinformatics-centre/kaiju")
4690 (commit (string-append "v" version))))
4691 (file-name (git-file-name name version))
4694 "119pzi0ddzv9mjg4wwa6han0cwr3k3ssn7kirvsjfcq05mi5ka0x"))))
4695 (build-system gnu-build-system)
4697 `(#:tests? #f ; There are no tests.
4699 (modify-phases %standard-phases
4701 (add-before 'build 'move-to-src-dir
4702 (lambda _ (chdir "src") #t))
4704 (lambda* (#:key inputs outputs #:allow-other-keys)
4705 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
4708 (copy-recursively "bin" bin))
4713 (home-page "http://kaiju.binf.ku.dk/")
4714 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
4715 (description "Kaiju is a program for sensitive taxonomic classification
4716 of high-throughput sequencing reads from metagenomic whole genome sequencing
4718 (license license:gpl3+)))
4725 ;; The PyPi tarball does not contain tests.
4728 (url "https://github.com/macs3-project/MACS")
4729 (commit (string-append "v" version))))
4730 (file-name (git-file-name name version))
4733 "1c5gxr0mk6hkd4vclf0k00wvyvzw2vrmk52c85338p7aqjwg6n15"))
4734 (modules '((guix build utils)))
4735 ;; Remove files generated by Cython
4738 (for-each (lambda (file)
4739 (let ((generated-file
4740 (string-append (string-drop-right file 3) "c")))
4741 (when (file-exists? generated-file)
4742 (delete-file generated-file))))
4743 (find-files "." "\\.pyx$"))
4744 (delete-file "MACS2/IO/CallPeakUnitPrecompiled.c")
4746 (build-system python-build-system)
4749 (modify-phases %standard-phases
4751 (lambda* (#:key tests? inputs outputs #:allow-other-keys)
4753 (add-installed-pythonpath inputs outputs)
4754 (invoke "pytest" "-v"))
4757 `(("python-numpy" ,python-numpy)))
4759 `(("python-cython" ,python-cython)
4760 ("python-pytest" ,python-pytest)))
4761 (home-page "https://github.com/macs3-project/MACS")
4762 (synopsis "Model based analysis for ChIP-Seq data")
4764 "MACS is an implementation of a ChIP-Seq analysis algorithm for
4765 identifying transcript factor binding sites named Model-based Analysis of
4766 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
4767 the significance of enriched ChIP regions and it improves the spatial
4768 resolution of binding sites through combining the information of both
4769 sequencing tag position and orientation.")
4770 (license license:bsd-3)))
4772 (define-public mafft
4779 "https://mafft.cbrc.jp/alignment/software/mafft-" version
4780 "-without-extensions-src.tgz"))
4781 (file-name (string-append name "-" version ".tgz"))
4784 "0i2i2m3blh2xkbkdk48hxfssks30ny0v381gdl7zwhcvp0axs26r"))))
4785 (build-system gnu-build-system)
4787 `(#:tests? #f ; no automated tests, though there are tests in the read me
4788 #:make-flags (let ((out (assoc-ref %outputs "out")))
4789 (list (string-append "PREFIX=" out)
4790 (string-append "BINDIR="
4791 (string-append out "/bin"))))
4793 (modify-phases %standard-phases
4794 (add-after 'unpack 'enter-dir
4795 (lambda _ (chdir "core") #t))
4796 (add-after 'enter-dir 'patch-makefile
4798 ;; on advice from the MAFFT authors, there is no need to
4799 ;; distribute mafft-profile, mafft-distance, or
4800 ;; mafft-homologs.rb as they are too "specialised".
4801 (substitute* "Makefile"
4802 ;; remove mafft-homologs.rb from SCRIPTS
4803 (("^SCRIPTS = mafft mafft-homologs.rb")
4805 ;; remove mafft-homologs from MANPAGES
4806 (("^MANPAGES = mafft.1 mafft-homologs.1")
4807 "MANPAGES = mafft.1")
4808 ;; remove mafft-distance from PROGS
4809 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
4810 "PROGS = dvtditr dndfast7 dndblast sextet5")
4811 ;; remove mafft-profile from PROGS
4812 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
4813 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
4814 (("^rm -f mafft-profile mafft-profile.exe") "#")
4815 (("^rm -f mafft-distance mafft-distance.exe") ")#")
4816 ;; do not install MAN pages in libexec folder
4817 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
4818 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
4820 (add-after 'enter-dir 'patch-paths
4821 (lambda* (#:key inputs #:allow-other-keys)
4822 (substitute* '("pairash.c"
4824 (("perl") (which "perl"))
4825 (("([\"`| ])awk" _ prefix)
4826 (string-append prefix (which "awk")))
4827 (("grep") (which "grep")))
4830 (add-after 'install 'wrap-programs
4831 (lambda* (#:key outputs #:allow-other-keys)
4832 (let* ((out (assoc-ref outputs "out"))
4833 (bin (string-append out "/bin"))
4834 (path (string-append
4835 (assoc-ref %build-inputs "coreutils") "/bin:")))
4836 (for-each (lambda (file)
4838 `("PATH" ":" prefix (,path))))
4846 ("coreutils" ,coreutils)))
4847 (home-page "https://mafft.cbrc.jp/alignment/software/")
4848 (synopsis "Multiple sequence alignment program")
4850 "MAFFT offers a range of multiple alignment methods for nucleotide and
4851 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
4852 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
4854 (license (license:non-copyleft
4855 "https://mafft.cbrc.jp/alignment/software/license.txt"
4856 "BSD-3 with different formatting"))))
4865 (url "https://github.com/marbl/mash")
4866 (commit (string-append "v" version))))
4867 (file-name (git-file-name name version))
4870 "049hwcc059p2fd9vwndn63laifvvsi0wmv84i6y1fr79k15dxwy6"))
4871 (modules '((guix build utils)))
4874 ;; Delete bundled kseq.
4875 ;; TODO: Also delete bundled murmurhash and open bloom filter.
4876 (delete-file "src/mash/kseq.h")
4878 (build-system gnu-build-system)
4880 `(#:tests? #f ; No tests.
4883 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
4884 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
4885 #:make-flags (list "CC=gcc")
4887 (modify-phases %standard-phases
4888 (add-after 'unpack 'fix-includes
4890 (substitute* '("src/mash/Sketch.cpp"
4891 "src/mash/CommandFind.cpp"
4892 "src/mash/CommandScreen.cpp")
4893 (("^#include \"kseq\\.h\"")
4894 "#include \"htslib/kseq.h\""))
4896 (add-after 'fix-includes 'use-c++14
4898 ;; capnproto 0.7 requires c++14 to build
4899 (substitute* "configure.ac"
4900 (("c\\+\\+11") "c++14"))
4901 (substitute* "Makefile.in"
4902 (("c\\+\\+11") "c++14"))
4905 `(("autoconf" ,autoconf)
4906 ;; Capnproto and htslib are statically embedded in the final
4907 ;; application. Therefore we also list their licenses, below.
4908 ("capnproto" ,capnproto)
4909 ("htslib" ,htslib)))
4913 (supported-systems '("x86_64-linux"))
4914 (home-page "https://mash.readthedocs.io")
4915 (synopsis "Fast genome and metagenome distance estimation using MinHash")
4916 (description "Mash is a fast sequence distance estimator that uses the
4917 MinHash algorithm and is designed to work with genomes and metagenomes in the
4918 form of assemblies or reads.")
4919 (license (list license:bsd-3 ; Mash
4920 license:expat ; HTSlib and capnproto
4921 license:public-domain ; MurmurHash 3
4922 license:cpl1.0)))) ; Open Bloom Filter
4924 (define-public metabat
4932 (url "https://bitbucket.org/berkeleylab/metabat.git")
4933 (commit (string-append "v" version))))
4934 (file-name (git-file-name name version))
4937 "0hyg2smw1nz69mfvjpk45xyyychmda92c80a0cv7baji84ri4iyn"))
4938 (patches (search-patches "metabat-fix-compilation.patch"))))
4939 (build-system scons-build-system)
4941 `(#:scons ,scons-python2
4943 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
4944 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
4945 #:tests? #f ;; Tests are run during the build phase.
4947 (modify-phases %standard-phases
4948 (add-after 'unpack 'fix-includes
4950 (substitute* "src/BamUtils.h"
4951 (("^#include \"bam/bam\\.h\"")
4952 "#include \"samtools/bam.h\"")
4953 (("^#include \"bam/sam\\.h\"")
4954 "#include \"samtools/sam.h\""))
4955 (substitute* "src/KseqReader.h"
4956 (("^#include \"bam/kseq\\.h\"")
4957 "#include \"htslib/kseq.h\""))
4959 (add-after 'unpack 'fix-scons
4960 (lambda* (#:key inputs #:allow-other-keys)
4961 (substitute* "SConstruct"
4962 (("^htslib_dir += 'samtools'")
4963 (string-append "htslib_dir = '"
4964 (assoc-ref inputs "htslib")
4966 (("^samtools_dir = 'samtools'")
4967 (string-append "samtools_dir = '"
4968 (assoc-ref inputs "samtools")
4970 (("^findStaticOrShared\\('bam', hts_lib")
4971 (string-append "findStaticOrShared('bam', '"
4972 (assoc-ref inputs "samtools")
4974 ;; Do not distribute README.
4975 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
4980 ("samtools" ,samtools)
4983 (home-page "https://bitbucket.org/berkeleylab/metabat")
4985 "Reconstruction of single genomes from complex microbial communities")
4987 "Grouping large genomic fragments assembled from shotgun metagenomic
4988 sequences to deconvolute complex microbial communities, or metagenome binning,
4989 enables the study of individual organisms and their interactions. MetaBAT is
4990 an automated metagenome binning software, which integrates empirical
4991 probabilistic distances of genome abundance and tetranucleotide frequency.")
4992 ;; The source code contains inline assembly.
4993 (supported-systems '("x86_64-linux" "i686-linux"))
4994 (license (license:non-copyleft "file://license.txt"
4995 "See license.txt in the distribution."))))
4997 (define-public minced
5004 (url "https://github.com/ctSkennerton/minced")
5006 (file-name (git-file-name name version))
5009 "1f5h9him0gd355cnx7p6pnxpknhckd4g0v62mg8zyhfbx9as25fv"))))
5010 (build-system gnu-build-system)
5012 `(#:test-target "test"
5014 (modify-phases %standard-phases
5016 (add-before 'check 'fix-test
5018 ;; Fix test for latest version.
5019 (substitute* "t/Aquifex_aeolicus_VF5.expected"
5020 (("minced:0.1.6") "minced:0.2.0"))
5022 (replace 'install ; No install target.
5023 (lambda* (#:key inputs outputs #:allow-other-keys)
5024 (let* ((out (assoc-ref outputs "out"))
5025 (bin (string-append out "/bin"))
5026 (wrapper (string-append bin "/minced")))
5027 ;; Minced comes with a wrapper script that tries to figure out where
5028 ;; it is located before running the JAR. Since these paths are known
5029 ;; to us, we build our own wrapper to avoid coreutils dependency.
5030 (install-file "minced.jar" bin)
5031 (with-output-to-file wrapper
5035 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
5036 (assoc-ref inputs "jre") "/bin/java -jar "
5037 bin "/minced.jar \"$@\"\n"))))
5038 (chmod wrapper #o555))
5041 `(("jdk" ,icedtea "jdk")))
5044 ("jre" ,icedtea "out")))
5045 (home-page "https://github.com/ctSkennerton/minced")
5046 (synopsis "Mining CRISPRs in Environmental Datasets")
5048 "MinCED is a program to find Clustered Regularly Interspaced Short
5049 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
5050 unassembled metagenomic reads, but is mainly designed for full genomes and
5051 assembled metagenomic sequence.")
5052 (license license:gpl3+)))
5060 (uri (pypi-uri "misopy" version))
5063 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
5064 (modules '((guix build utils)))
5066 (substitute* "setup.py"
5067 ;; Use setuptools, or else the executables are not
5069 (("distutils.core") "setuptools")
5070 ;; Use "gcc" instead of "cc" for compilation.
5072 "cc.set_executables(
5076 linker_so='gcc -shared'); defines"))
5078 (build-system python-build-system)
5080 `(#:python ,python-2 ; only Python 2 is supported
5081 #:tests? #f)) ; no "test" target
5083 `(("samtools" ,samtools)
5084 ("python-numpy" ,python2-numpy)
5085 ("python-pysam" ,python2-pysam)
5086 ("python-scipy" ,python2-scipy)
5087 ("python-matplotlib" ,python2-matplotlib)))
5089 `(("python-mock" ,python2-mock) ; for tests
5090 ("python-pytz" ,python2-pytz))) ; for tests
5091 (home-page "https://www.genes.mit.edu/burgelab/miso/index.html")
5092 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
5094 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
5095 the expression level of alternatively spliced genes from RNA-Seq data, and
5096 identifies differentially regulated isoforms or exons across samples. By
5097 modeling the generative process by which reads are produced from isoforms in
5098 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
5099 that a read originated from a particular isoform.")
5100 (license license:gpl2)))
5102 (define-public muscle
5105 (version "3.8.1551")
5107 (method url-fetch/tarbomb)
5109 "http://www.drive5.com/muscle/muscle_src_"
5113 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
5114 (build-system gnu-build-system)
5116 `(#:make-flags (list "LDLIBS = -lm")
5118 (modify-phases %standard-phases
5121 ;; There are no tests, so just test if it runs.
5122 (lambda _ (invoke "./muscle" "-version") #t))
5124 (lambda* (#:key outputs #:allow-other-keys)
5125 (let* ((out (assoc-ref outputs "out"))
5126 (bin (string-append out "/bin")))
5127 (install-file "muscle" bin)
5129 (home-page "http://www.drive5.com/muscle")
5130 (synopsis "Multiple sequence alignment program")
5132 "MUSCLE aims to be a fast and accurate multiple sequence alignment
5133 program for nucleotide and protein sequences.")
5134 ;; License information found in 'muscle -h' and usage.cpp.
5135 (license license:public-domain)))
5137 (define-public newick-utils
5138 ;; There are no recent releases so we package from git.
5139 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
5141 (name "newick-utils")
5142 (version (string-append "1.6-1." (string-take commit 8)))
5146 (url "https://github.com/tjunier/newick_utils")
5148 (file-name (string-append name "-" version "-checkout"))
5151 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
5152 (build-system gnu-build-system)
5154 ;; XXX: TODO: Enable Lua and Guile bindings.
5155 ;; https://github.com/tjunier/newick_utils/issues/13
5156 `(("libxml2" ,libxml2)
5160 `(("autoconf" ,autoconf)
5161 ("automake" ,automake)
5162 ("libtool" ,libtool)))
5163 (synopsis "Programs for working with newick format phylogenetic trees")
5165 "Newick-utils is a suite of utilities for processing phylogenetic trees
5166 in Newick format. Functions include re-rooting, extracting subtrees,
5167 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
5168 (home-page "https://github.com/tjunier/newick_utils")
5169 (license license:bsd-3))))
5178 "https://github.com/wwood/OrfM/releases/download/v"
5179 version "/orfm-" version ".tar.gz"))
5182 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
5183 (build-system gnu-build-system)
5184 (inputs `(("zlib" ,zlib)))
5186 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
5187 ("ruby-rspec" ,ruby-rspec)
5189 (synopsis "Simple and not slow open reading frame (ORF) caller")
5191 "An ORF caller finds stretches of DNA that, when translated, are not
5192 interrupted by stop codons. OrfM finds and prints these ORFs.")
5193 (home-page "https://github.com/wwood/OrfM")
5194 (license license:lgpl3+)))
5196 (define-public python2-pbcore
5198 (name "python2-pbcore")
5202 (uri (pypi-uri "pbcore" version))
5205 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
5206 (build-system python-build-system)
5208 `(#:python ,python-2 ;pbcore < 2.0 requires Python 2.7
5209 #:phases (modify-phases %standard-phases
5210 (add-after 'unpack 'remove-sphinx-dependency
5212 ;; Sphinx is only required for documentation tests, which
5213 ;; we do not run; furthermore it depends on python2-sphinx
5214 ;; which is no longer maintained.
5215 (substitute* "requirements-dev.txt"
5219 `(("python-cython" ,python2-cython)
5220 ("python-numpy" ,python2-numpy)
5221 ("python-pysam" ,python2-pysam)
5222 ("python-h5py" ,python2-h5py)))
5224 `(("python-nose" ,python2-nose)
5225 ("python-pyxb" ,python2-pyxb)))
5226 (home-page "https://pacificbiosciences.github.io/pbcore/")
5227 (synopsis "Library for reading and writing PacBio data files")
5229 "The pbcore package provides Python APIs for interacting with PacBio data
5230 files and writing bioinformatics applications.")
5231 (license license:bsd-3)))
5233 (define-public python2-warpedlmm
5235 (name "python2-warpedlmm")
5240 (uri (pypi-uri "WarpedLMM" version ".zip"))
5243 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
5244 (build-system python-build-system)
5246 `(#:python ,python-2 ; requires Python 2.7
5247 #:tests? #f ; test data are not included
5249 (modify-phases %standard-phases
5250 (add-after 'unpack 'use-weave
5252 (substitute* "warpedlmm/util/linalg.py"
5253 (("from scipy import linalg, weave")
5254 "from scipy import linalg\nimport weave"))
5257 `(("python-scipy" ,python2-scipy)
5258 ("python-numpy" ,python2-numpy)
5259 ("python-matplotlib" ,python2-matplotlib)
5260 ("python-fastlmm" ,python2-fastlmm)
5261 ("python-pandas" ,python2-pandas)
5262 ("python-pysnptools" ,python2-pysnptools)
5263 ("python-weave" ,python2-weave)))
5265 `(("python-mock" ,python2-mock)
5266 ("python-nose" ,python2-nose)
5268 (home-page "https://github.com/PMBio/warpedLMM")
5269 (synopsis "Implementation of warped linear mixed models")
5271 "WarpedLMM is a Python implementation of the warped linear mixed model,
5272 which automatically learns an optimal warping function (or transformation) for
5273 the phenotype as it models the data.")
5274 (license license:asl2.0)))
5276 (define-public pbtranscript-tofu
5277 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
5279 (name "pbtranscript-tofu")
5280 (version (string-append "2.2.3." (string-take commit 7)))
5284 (url "https://github.com/PacificBiosciences/cDNA_primer")
5286 (file-name (string-append name "-" version "-checkout"))
5289 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
5290 (modules '((guix build utils)))
5293 ;; remove bundled Cython sources
5294 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
5296 (build-system python-build-system)
5298 `(#:python ,python-2
5299 ;; FIXME: Tests fail with "No such file or directory:
5300 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
5303 (modify-phases %standard-phases
5304 (add-after 'unpack 'enter-directory
5306 (chdir "pbtranscript-tofu/pbtranscript/")
5308 ;; With setuptools version 18.0 and later this setup.py hack causes
5309 ;; a build error, so we disable it.
5310 (add-after 'enter-directory 'patch-setuppy
5312 (substitute* "setup.py"
5313 (("if 'setuptools.extension' in sys.modules:")
5317 `(("python-numpy" ,python2-numpy)
5318 ("python-bx-python" ,python2-bx-python)
5319 ("python-networkx" ,python2-networkx)
5320 ("python-scipy" ,python2-scipy)
5321 ("python-pbcore" ,python2-pbcore)
5322 ("python-h5py" ,python2-h5py)))
5324 `(("python-cython" ,python2-cython)
5325 ("python-nose" ,python2-nose)))
5326 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
5327 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
5329 "pbtranscript-tofu contains scripts to analyze transcriptome data
5330 generated using the PacBio Iso-Seq protocol.")
5331 (license license:bsd-3))))
5333 (define-public prank
5340 "http://wasabiapp.org/download/prank/prank.source."
5344 "0nc8g9c5rkdxcir46s0in9ci1sxwzbjibxrvkksf22ybnplvagk2"))))
5345 (build-system gnu-build-system)
5348 (modify-phases %standard-phases
5349 (add-after 'unpack 'enter-src-dir
5353 (add-after 'unpack 'remove-m64-flag
5354 ;; Prank will build with the correct 'bit-ness' without this flag
5355 ;; and this allows building on 32-bit machines.
5356 (lambda _ (substitute* "src/Makefile"
5361 (lambda* (#:key outputs #:allow-other-keys)
5362 (let* ((out (assoc-ref outputs "out"))
5363 (bin (string-append out "/bin"))
5364 (man (string-append out "/share/man/man1"))
5365 (path (string-append
5366 (assoc-ref %build-inputs "mafft") "/bin:"
5367 (assoc-ref %build-inputs "exonerate") "/bin:"
5368 (assoc-ref %build-inputs "bppsuite") "/bin")))
5369 (install-file "prank" bin)
5370 (wrap-program (string-append bin "/prank")
5371 `("PATH" ":" prefix (,path)))
5372 (install-file "prank.1" man))
5376 ("exonerate" ,exonerate)
5377 ("bppsuite" ,bppsuite)))
5378 (home-page "http://wasabiapp.org/software/prank/")
5379 (synopsis "Probabilistic multiple sequence alignment program")
5381 "PRANK is a probabilistic multiple sequence alignment program for DNA,
5382 codon and amino-acid sequences. It is based on a novel algorithm that treats
5383 insertions correctly and avoids over-estimation of the number of deletion
5384 events. In addition, PRANK borrows ideas from maximum likelihood methods used
5385 in phylogenetics and correctly takes into account the evolutionary distances
5386 between sequences. Lastly, PRANK allows for defining a potential structure
5387 for sequences to be aligned and then, simultaneously with the alignment,
5388 predicts the locations of structural units in the sequences.")
5389 (license license:gpl2+)))
5391 (define-public proteinortho
5393 (name "proteinortho")
5398 (url "https://gitlab.com/paulklemm_PHD/proteinortho.git")
5399 (commit (string-append "v" version))))
5400 (file-name (git-file-name name version))
5403 "0pmy617zy2z2w6hjqxjhf3rzikf5n3mpia80ysq8233vfr7wrzff"))
5404 (modules '((guix build utils)))
5407 ;; remove pre-built scripts
5408 (delete-file-recursively "src/BUILD/")
5410 (build-system gnu-build-system)
5412 `(#:test-target "test"
5413 #:make-flags '("CC=gcc")
5415 (modify-phases %standard-phases
5417 ;; There is no configure script, so we modify the Makefile directly.
5418 (lambda* (#:key outputs #:allow-other-keys)
5419 (substitute* "Makefile"
5422 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
5424 (add-before 'install 'make-install-directory
5425 ;; The install directory is not created during 'make install'.
5426 (lambda* (#:key outputs #:allow-other-keys)
5427 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
5429 (add-after 'install 'wrap-programs
5430 (lambda* (#:key inputs outputs #:allow-other-keys)
5431 (let ((path (getenv "PATH"))
5432 (out (assoc-ref outputs "out")))
5433 (for-each (lambda (script)
5434 (wrap-script script `("PATH" ":" prefix (,path))))
5435 (cons (string-append out "/bin/proteinortho")
5436 (find-files out "\\.(pl|py)$"))))
5439 `(("guile" ,guile-3.0) ; for wrap-script
5440 ("diamond" ,diamond)
5442 ("python" ,python-wrapper)
5445 ("openblas" ,openblas)))
5447 `(("which" ,which)))
5448 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
5449 (synopsis "Detect orthologous genes across species")
5451 "Proteinortho is a tool to detect orthologous genes across different
5452 species. For doing so, it compares similarities of given gene sequences and
5453 clusters them to find significant groups. The algorithm was designed to handle
5454 large-scale data and can be applied to hundreds of species at once.")
5455 (license license:gpl3+)))
5457 (define-public pyicoteo
5465 (url "https://bitbucket.org/regulatorygenomicsupf/pyicoteo.git")
5466 (commit (string-append "v" version))))
5467 (file-name (git-file-name name version))
5470 "0hz5g8d25lbjy1wpscr490l0lmyvaix893hhax4fxnh1h9w34w8p"))))
5471 (build-system python-build-system)
5473 `(#:python ,python-2 ; does not work with Python 3
5474 #:tests? #f)) ; there are no tests
5476 `(("python2-matplotlib" ,python2-matplotlib)))
5477 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
5478 (synopsis "Analyze high-throughput genetic sequencing data")
5480 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
5481 sequencing data. It works with genomic coordinates. There are currently six
5482 different command-line tools:
5485 @item pyicoregion: for generating exploratory regions automatically;
5486 @item pyicoenrich: for differential enrichment between two conditions;
5487 @item pyicoclip: for calling CLIP-Seq peaks without a control;
5488 @item pyicos: for genomic coordinates manipulation;
5489 @item pyicoller: for peak calling on punctuated ChIP-Seq;
5490 @item pyicount: to count how many reads from N experiment files overlap in a
5492 @item pyicotrocol: to combine operations from pyicoteo.
5494 (license license:gpl3+)))
5496 (define-public prodigal
5499 ;; Check for a new home page when updating this package:
5500 ;; https://github.com/hyattpd/Prodigal/issues/36#issuecomment-536617588
5505 (url "https://github.com/hyattpd/Prodigal")
5506 (commit (string-append "v" version))))
5507 (file-name (git-file-name name version))
5510 "1fs1hqk83qjbjhrvhw6ni75zakx5ki1ayy3v6wwkn3xvahc9hi5s"))))
5511 (build-system gnu-build-system)
5513 `(#:tests? #f ; no check target
5514 #:make-flags (list (string-append "INSTALLDIR="
5515 (assoc-ref %outputs "out")
5518 (modify-phases %standard-phases
5519 (delete 'configure))))
5520 (home-page "https://github.com/hyattpd/Prodigal")
5521 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
5523 "Prodigal runs smoothly on finished genomes, draft genomes, and
5524 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
5525 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
5526 partial genes, and identifies translation initiation sites.")
5527 (license license:gpl3+)))
5529 (define-public roary
5537 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
5541 "0qxrds9wx7cfhlkihrp6697kx0flhhxymap9fwan0b3rbdhcnmff"))))
5542 (build-system perl-build-system)
5545 (modify-phases %standard-phases
5550 ;; The tests are not run by default, so we run each test file
5552 (setenv "PATH" (string-append (getcwd) "/bin" ":"
5554 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
5555 (getenv "PERL5LIB")))
5556 (for-each (lambda (file)
5557 (display file)(display "\n")
5558 (invoke "perl" file))
5559 (find-files "t" ".*\\.t$"))
5562 ;; There is no 'install' target in the Makefile.
5563 (lambda* (#:key outputs #:allow-other-keys)
5564 (let* ((out (assoc-ref outputs "out"))
5565 (bin (string-append out "/bin"))
5566 (perl (string-append out "/lib/perl5/site_perl"))
5567 (roary-plots "contrib/roary_plots"))
5570 (copy-recursively "bin" bin)
5571 (copy-recursively "lib" perl)
5573 (add-after 'install 'wrap-programs
5574 (lambda* (#:key inputs outputs #:allow-other-keys)
5575 (let* ((out (assoc-ref outputs "out"))
5576 (perl5lib (getenv "PERL5LIB"))
5577 (path (getenv "PATH")))
5578 (for-each (lambda (prog)
5579 (let ((binary (string-append out "/" prog)))
5580 (wrap-program binary
5581 `("PERL5LIB" ":" prefix
5582 (,(string-append perl5lib ":" out
5583 "/lib/perl5/site_perl"))))
5584 (wrap-program binary
5586 (,(string-append path ":" out "/bin"))))))
5587 (find-files "bin" ".*[^R]$"))
5589 (string-append out "/bin/roary-create_pan_genome_plots.R"))
5590 (r-site-lib (getenv "R_LIBS_SITE"))
5592 (string-append (assoc-ref inputs "coreutils") "/bin")))
5594 `("R_LIBS_SITE" ":" prefix
5595 (,(string-append r-site-lib ":" out "/site-library/"))))
5598 (,(string-append coreutils-path ":" out "/bin"))))))
5601 `(("perl-env-path" ,perl-env-path)
5602 ("perl-test-files" ,perl-test-files)
5603 ("perl-test-most" ,perl-test-most)
5604 ("perl-test-output" ,perl-test-output)))
5606 `(("perl-array-utils" ,perl-array-utils)
5607 ("bioperl" ,bioperl-minimal)
5608 ("perl-digest-md5-file" ,perl-digest-md5-file)
5609 ("perl-exception-class" ,perl-exception-class)
5610 ("perl-file-find-rule" ,perl-file-find-rule)
5611 ("perl-file-grep" ,perl-file-grep)
5612 ("perl-file-slurper" ,perl-file-slurper)
5613 ("perl-file-which" ,perl-file-which)
5614 ("perl-graph" ,perl-graph)
5615 ("perl-graph-readwrite" ,perl-graph-readwrite)
5616 ("perl-log-log4perl" ,perl-log-log4perl)
5617 ("perl-moose" ,perl-moose)
5618 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
5619 ("perl-text-csv" ,perl-text-csv)
5620 ("bedtools" ,bedtools)
5624 ("parallel" ,parallel)
5627 ("fasttree" ,fasttree)
5631 ("r-minimal" ,r-minimal)
5632 ("r-ggplot2" ,r-ggplot2)
5633 ("coreutils" ,coreutils)))
5634 (home-page "https://sanger-pathogens.github.io/Roary/")
5635 (synopsis "High speed stand-alone pan genome pipeline")
5637 "Roary is a high speed stand alone pan genome pipeline, which takes
5638 annotated assemblies in GFF3 format (produced by the Prokka program) and
5639 calculates the pan genome. Using a standard desktop PC, it can analyse
5640 datasets with thousands of samples, without compromising the quality of the
5641 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
5642 single processor. Roary is not intended for metagenomics or for comparing
5643 extremely diverse sets of genomes.")
5644 (license license:gpl3)))
5646 (define-public raxml
5654 (url "https://github.com/stamatak/standard-RAxML")
5655 (commit (string-append "v" version))))
5656 (file-name (git-file-name name version))
5659 "1jqjzhch0rips0vp04prvb8vmc20c5pdmsqn8knadcf91yy859fh"))))
5660 (build-system gnu-build-system)
5662 `(#:tests? #f ; There are no tests.
5663 ;; Use 'standard' Makefile rather than SSE or AVX ones.
5664 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
5666 (modify-phases %standard-phases
5669 (lambda* (#:key outputs #:allow-other-keys)
5670 (let* ((out (assoc-ref outputs "out"))
5671 (bin (string-append out "/bin"))
5672 (executable "raxmlHPC-HYBRID"))
5673 (install-file executable bin)
5674 (symlink (string-append bin "/" executable) "raxml"))
5677 `(("openmpi" ,openmpi)))
5678 (home-page "https://cme.h-its.org/exelixis/web/software/raxml/index.html")
5679 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
5681 "RAxML is a tool for phylogenetic analysis and post-analysis of large
5683 ;; The source includes x86 specific code
5684 (supported-systems '("x86_64-linux" "i686-linux"))
5685 (license license:gpl2+)))
5695 (url "https://github.com/deweylab/RSEM")
5696 (commit (string-append "v" version))))
5698 (base32 "1jlq11d1p8qp64w75yj8cnbbd1a93viq10pzsbwal7vdn8fg13j1"))
5699 (file-name (git-file-name name version))
5700 (modules '((guix build utils)))
5703 ;; remove bundled copy of boost and samtools
5704 (delete-file-recursively "boost")
5705 (delete-file-recursively "samtools-1.3")
5707 (build-system gnu-build-system)
5709 `(#:tests? #f ;no "check" target
5711 (list (string-append "BOOST="
5712 (assoc-ref %build-inputs "boost")
5714 (string-append "SAMHEADERS="
5715 (assoc-ref %build-inputs "htslib")
5716 "/include/htslib/sam.h")
5717 (string-append "SAMLIBS="
5718 (assoc-ref %build-inputs "htslib")
5721 (modify-phases %standard-phases
5722 ;; No "configure" script.
5723 ;; Do not build bundled samtools library.
5726 (substitute* "Makefile"
5727 (("^all : \\$\\(PROGRAMS\\).*") "all: $(PROGRAMS)\n")
5728 (("^\\$\\(SAMLIBS\\).*") ""))
5731 (lambda* (#:key outputs #:allow-other-keys)
5732 (let* ((out (string-append (assoc-ref outputs "out")))
5733 (bin (string-append out "/bin/"))
5734 (perl (string-append out "/lib/perl5/site_perl")))
5737 (for-each (lambda (file)
5738 (install-file file bin))
5739 (find-files "." "rsem-.*"))
5740 (install-file "rsem_perl_utils.pm" perl))
5742 (add-after 'install 'wrap-program
5743 (lambda* (#:key outputs #:allow-other-keys)
5744 (let ((out (assoc-ref outputs "out")))
5745 (for-each (lambda (prog)
5746 (wrap-program (string-append out "/bin/" prog)
5747 `("PERL5LIB" ":" prefix
5748 (,(string-append out "/lib/perl5/site_perl")))))
5749 '("rsem-calculate-expression"
5751 "rsem-generate-data-matrix"
5752 "rsem-generate-ngvector"
5753 "rsem-plot-transcript-wiggles"
5754 "rsem-prepare-reference"
5756 "rsem-run-prsem-testing-procedure")))
5760 ("r-minimal" ,r-minimal)
5762 ("htslib" ,htslib-1.3)
5764 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
5765 (synopsis "Estimate gene expression levels from RNA-Seq data")
5767 "RSEM is a software package for estimating gene and isoform expression
5768 levels from RNA-Seq data. The RSEM package provides a user-friendly
5769 interface, supports threads for parallel computation of the EM algorithm,
5770 single-end and paired-end read data, quality scores, variable-length reads and
5771 RSPD estimation. In addition, it provides posterior mean and 95% credibility
5772 interval estimates for expression levels. For visualization, it can generate
5773 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
5774 (license license:gpl3+)))
5776 (define-public rseqc
5784 (string-append "mirror://sourceforge/rseqc/"
5785 "RSeQC-" version ".tar.gz"))
5788 "0gbb9iyb7swiv5455fm5rg98r7l6qn27v564yllqjd574hncpx6m"))))
5789 (build-system python-build-system)
5791 `(("python-cython" ,python-cython)
5792 ("python-bx-python" ,python-bx-python)
5793 ("python-pybigwig" ,python-pybigwig)
5794 ("python-pysam" ,python-pysam)
5795 ("python-numpy" ,python-numpy)
5798 `(("python-nose" ,python-nose)))
5799 (home-page "http://rseqc.sourceforge.net/")
5800 (synopsis "RNA-seq quality control package")
5802 "RSeQC provides a number of modules that can comprehensively evaluate
5803 high throughput sequence data, especially RNA-seq data. Some basic modules
5804 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
5805 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
5806 distribution, coverage uniformity, strand specificity, etc.")
5807 (license license:gpl3+)))
5810 ;; There are no release tarballs. According to the installation
5811 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
5812 ;; stable release is identified by this changeset ID.
5813 (let ((changeset "2329130")
5817 (version (string-append "0-" revision "." changeset))
5821 (url "https://bitbucket.org/libsleipnir/sleipnir")
5822 (changeset changeset)))
5823 (file-name (string-append name "-" version "-checkout"))
5826 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
5827 (build-system gnu-build-system)
5829 `(#:modules ((srfi srfi-1)
5830 (guix build gnu-build-system)
5833 (let ((dirs '("SeekMiner"
5839 (modify-phases %standard-phases
5842 (substitute* "gen_tools_am"
5843 (("/usr/bin/env.*") (which "perl")))
5844 (invoke "bash" "gen_auto")
5846 (add-after 'build 'build-additional-tools
5847 (lambda* (#:key make-flags #:allow-other-keys)
5848 (for-each (lambda (dir)
5849 (with-directory-excursion (string-append "tools/" dir)
5850 (apply invoke "make" make-flags)))
5853 (add-after 'install 'install-additional-tools
5854 (lambda* (#:key make-flags #:allow-other-keys)
5855 (for-each (lambda (dir)
5856 (with-directory-excursion (string-append "tools/" dir)
5857 (apply invoke `("make" ,@make-flags "install"))))
5864 ("readline" ,readline)
5865 ("gengetopt" ,gengetopt)
5866 ("log4cpp" ,log4cpp)))
5868 `(("autoconf" ,autoconf)
5869 ("automake" ,automake)
5871 (home-page "http://seek.princeton.edu")
5872 (synopsis "Gene co-expression search engine")
5874 "SEEK is a computational gene co-expression search engine. SEEK provides
5875 biologists with a way to navigate the massive human expression compendium that
5876 now contains thousands of expression datasets. SEEK returns a robust ranking
5877 of co-expressed genes in the biological area of interest defined by the user's
5878 query genes. It also prioritizes thousands of expression datasets according
5879 to the user's query of interest.")
5880 (license license:cc-by3.0))))
5882 (define-public samtools
5890 (string-append "mirror://sourceforge/samtools/samtools/"
5891 version "/samtools-" version ".tar.bz2"))
5894 "1dp5wknak4arnw5ghhif9mmljlfnw5bgm91wib7z0j8wdjywx0z2"))
5895 (modules '((guix build utils)))
5897 ;; Delete bundled htslib.
5898 (delete-file-recursively "htslib-1.11")
5900 (build-system gnu-build-system)
5902 `(#:modules ((ice-9 ftw)
5904 (guix build gnu-build-system)
5906 #:configure-flags (list "--with-ncurses")
5908 (modify-phases %standard-phases
5909 (add-after 'unpack 'patch-tests
5911 (substitute* "test/test.pl"
5912 ;; The test script calls out to /bin/bash
5913 (("/bin/bash") (which "bash")))
5915 (add-after 'install 'install-library
5916 (lambda* (#:key outputs #:allow-other-keys)
5917 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
5918 (install-file "libbam.a" lib)
5920 (add-after 'install 'install-headers
5921 (lambda* (#:key outputs #:allow-other-keys)
5922 (let ((include (string-append (assoc-ref outputs "out")
5923 "/include/samtools/")))
5924 (for-each (lambda (file)
5925 (install-file file include))
5926 (scandir "." (lambda (name) (string-match "\\.h$" name))))
5928 (native-inputs `(("pkg-config" ,pkg-config)))
5930 `(("htslib" ,htslib)
5931 ("ncurses" ,ncurses)
5935 (home-page "http://samtools.sourceforge.net")
5936 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
5938 "Samtools implements various utilities for post-processing nucleotide
5939 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
5940 variant calling (in conjunction with bcftools), and a simple alignment
5942 (license license:expat)))
5944 (define-public samtools-1.9
5945 (package (inherit samtools)
5952 (string-append "mirror://sourceforge/samtools/samtools/"
5953 version "/samtools-" version ".tar.bz2"))
5956 "10ilqbmm7ri8z431sn90lvbjwizd0hhkf9rcqw8j823hf26nhgq8"))
5957 (modules '((guix build utils)))
5959 ;; Delete bundled htslib.
5960 (delete-file-recursively "htslib-1.9")
5963 `(("htslib" ,htslib-1.9)
5964 ("ncurses" ,ncurses)
5969 (define-public samtools-0.1
5970 ;; This is the most recent version of the 0.1 line of samtools. The input
5971 ;; and output formats differ greatly from that used and produced by samtools
5972 ;; 1.x and is still used in many bioinformatics pipelines.
5973 (package (inherit samtools)
5979 (string-append "mirror://sourceforge/samtools/samtools/"
5980 version "/samtools-" version ".tar.bz2"))
5982 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
5984 `(#:tests? #f ;no "check" target
5986 (list "LIBCURSES=-lncurses")
5987 ,@(substitute-keyword-arguments (package-arguments samtools)
5989 `(modify-phases ,phases
5991 (lambda* (#:key outputs #:allow-other-keys)
5992 (let ((bin (string-append
5993 (assoc-ref outputs "out") "/bin")))
5995 (install-file "samtools" bin)
5997 (delete 'patch-tests)
5998 (delete 'configure))))))))
6000 (define-public mosaik
6001 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
6006 ;; There are no release tarballs nor tags.
6009 (url "https://github.com/wanpinglee/MOSAIK")
6011 (file-name (string-append name "-" version))
6014 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
6015 (build-system gnu-build-system)
6017 `(#:tests? #f ; no tests
6018 #:make-flags (list "CC=gcc")
6020 (modify-phases %standard-phases
6022 (lambda _ (chdir "src") #t))
6024 (lambda* (#:key outputs #:allow-other-keys)
6025 (let ((bin (string-append (assoc-ref outputs "out")
6028 (copy-recursively "../bin" bin)
6032 ("zlib:static" ,zlib "static")
6034 (supported-systems '("x86_64-linux"))
6035 (home-page "https://github.com/wanpinglee/MOSAIK")
6036 (synopsis "Map nucleotide sequence reads to reference genomes")
6038 "MOSAIK is a program for mapping second and third-generation sequencing
6039 reads to a reference genome. MOSAIK can align reads generated by all the
6040 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
6041 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
6042 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
6043 ;; code released into the public domain:
6044 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
6045 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
6046 (license (list license:gpl2+ license:public-domain)))))
6048 (define-public ngs-sdk
6055 (url "https://github.com/ncbi/ngs")
6057 (file-name (git-file-name name version))
6060 "1ix51c25hjn57w93qmwzw80xh2i34wx8j2hn7szh8p6w8i3az5qa"))))
6061 (build-system gnu-build-system)
6063 `(#:parallel-build? #f ; not supported
6064 #:tests? #f ; no "check" target
6066 (modify-phases %standard-phases
6068 (lambda* (#:key outputs #:allow-other-keys)
6069 (let ((out (assoc-ref outputs "out")))
6070 ;; Allow 'konfigure.perl' to find 'package.prl'.
6072 (string-append ".:" (getenv "PERL5LIB")))
6074 ;; The 'configure' script doesn't recognize things like
6075 ;; '--enable-fast-install'.
6076 (invoke "./configure"
6077 (string-append "--build-prefix=" (getcwd) "/build")
6078 (string-append "--prefix=" out))
6080 (add-after 'unpack 'enter-dir
6081 (lambda _ (chdir "ngs-sdk") #t)))))
6082 (native-inputs `(("perl" ,perl)))
6083 ;; According to the test
6084 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
6085 ;; in ngs-sdk/setup/konfigure.perl
6086 (supported-systems '("i686-linux" "x86_64-linux"))
6087 (home-page "https://github.com/ncbi/ngs")
6088 (synopsis "API for accessing Next Generation Sequencing data")
6090 "NGS is a domain-specific API for accessing reads, alignments and pileups
6091 produced from Next Generation Sequencing. The API itself is independent from
6092 any particular back-end implementation, and supports use of multiple back-ends
6094 (license license:public-domain)))
6096 (define-public java-ngs
6097 (package (inherit ngs-sdk)
6100 `(,@(substitute-keyword-arguments
6101 `(#:modules ((guix build gnu-build-system)
6105 ,@(package-arguments ngs-sdk))
6107 `(modify-phases ,phases
6108 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
6110 `(("jdk" ,icedtea "jdk")
6111 ("ngs-sdk" ,ngs-sdk)))
6112 (synopsis "Java bindings for NGS SDK")))
6114 (define-public ncbi-vdb
6121 (url "https://github.com/ncbi/ncbi-vdb")
6123 (file-name (git-file-name name version))
6126 "0m8hlxscidsfqm9x9fyi62q6lpf1dv5115kgjjgnrkl49q9c27m6"))))
6127 (build-system gnu-build-system)
6129 `(#:parallel-build? #f ; not supported
6130 #:tests? #f ; no "check" target
6131 #:make-flags '("HAVE_HDF5=1")
6133 (modify-phases %standard-phases
6134 (add-after 'unpack 'make-files-writable
6135 (lambda _ (for-each make-file-writable (find-files "." ".*")) #t))
6136 (add-before 'configure 'set-perl-search-path
6138 ;; Work around "dotless @INC" build failure.
6140 (string-append (getcwd) "/setup:"
6141 (getenv "PERL5LIB")))
6143 ;; See https://github.com/ncbi/ncbi-vdb/issues/14
6144 (add-after 'unpack 'patch-krypto-flags
6146 (substitute* "libs/krypto/Makefile"
6147 (("-Wa,-march=generic64\\+aes") "")
6148 (("-Wa,-march=generic64\\+sse4") ""))
6151 (lambda* (#:key inputs outputs #:allow-other-keys)
6152 (let ((out (assoc-ref outputs "out")))
6153 ;; Override include path for libmagic
6154 (substitute* "setup/package.prl"
6155 (("name => 'magic', Include => '/usr/include'")
6156 (string-append "name=> 'magic', Include => '"
6157 (assoc-ref inputs "libmagic")
6160 ;; Install kdf5 library (needed by sra-tools)
6161 (substitute* "build/Makefile.install"
6162 (("LIBRARIES_TO_INSTALL =")
6163 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
6165 (substitute* "build/Makefile.env"
6166 (("CFLAGS =" prefix)
6167 (string-append prefix "-msse2 ")))
6169 ;; Override search path for ngs-java
6170 (substitute* "setup/package.prl"
6171 (("/usr/local/ngs/ngs-java")
6172 (assoc-ref inputs "java-ngs")))
6174 ;; The 'configure' script doesn't recognize things like
6175 ;; '--enable-fast-install'.
6176 (invoke "./configure"
6177 (string-append "--build-prefix=" (getcwd) "/build")
6178 (string-append "--prefix=" (assoc-ref outputs "out"))
6179 (string-append "--debug")
6180 (string-append "--with-xml2-prefix="
6181 (assoc-ref inputs "libxml2"))
6182 (string-append "--with-ngs-sdk-prefix="
6183 (assoc-ref inputs "ngs-sdk"))
6184 (string-append "--with-hdf5-prefix="
6185 (assoc-ref inputs "hdf5")))
6187 (add-after 'install 'install-interfaces
6188 (lambda* (#:key outputs #:allow-other-keys)
6189 ;; Install interface libraries. On i686 the interface libraries
6190 ;; are installed to "linux/gcc/i386", so we need to use the Linux
6191 ;; architecture name ("i386") instead of the target system prefix
6193 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
6194 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
6195 ,(system->linux-architecture
6196 (or (%current-target-system)
6199 (string-append (assoc-ref outputs "out")
6201 ;; Install interface headers
6202 (copy-recursively "interfaces"
6203 (string-append (assoc-ref outputs "out")
6206 ;; These files are needed by sra-tools.
6207 (add-after 'install 'install-configuration-files
6208 (lambda* (#:key outputs #:allow-other-keys)
6209 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
6211 (install-file "libs/kfg/default.kfg" target)
6212 (install-file "libs/kfg/certs.kfg" target))
6215 `(("libxml2" ,libxml2)
6216 ("ngs-sdk" ,ngs-sdk)
6217 ("java-ngs" ,java-ngs)
6220 (native-inputs `(("perl" ,perl)))
6221 ;; NCBI-VDB requires SSE capability.
6222 (supported-systems '("i686-linux" "x86_64-linux"))
6223 (home-page "https://github.com/ncbi/ncbi-vdb")
6224 (synopsis "Database engine for genetic information")
6226 "The NCBI-VDB library implements a highly compressed columnar data
6227 warehousing engine that is most often used to store genetic information.
6228 Databases are stored in a portable image within the file system, and can be
6229 accessed/downloaded on demand across HTTP.")
6230 (license license:public-domain)))
6232 (define-public plink
6240 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
6241 version "-src.zip"))
6243 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
6244 (patches (search-patches "plink-1.07-unclobber-i.patch"
6245 "plink-endian-detection.patch"))))
6246 (build-system gnu-build-system)
6248 '(#:tests? #f ;no "check" target
6249 #:make-flags (list (string-append "LIB_LAPACK="
6250 (assoc-ref %build-inputs "lapack")
6251 "/lib/liblapack.so")
6254 ;; disable phoning home
6257 (modify-phases %standard-phases
6258 ;; no "configure" script
6261 (lambda* (#:key outputs #:allow-other-keys)
6262 (let ((bin (string-append (assoc-ref outputs "out")
6264 (install-file "plink" bin)
6268 ("lapack" ,lapack)))
6270 `(("unzip" ,unzip)))
6271 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
6272 (synopsis "Whole genome association analysis toolset")
6274 "PLINK is a whole genome association analysis toolset, designed to
6275 perform a range of basic, large-scale analyses in a computationally efficient
6276 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
6277 so there is no support for steps prior to this (e.g. study design and
6278 planning, generating genotype or CNV calls from raw data). Through
6279 integration with gPLINK and Haploview, there is some support for the
6280 subsequent visualization, annotation and storage of results.")
6281 ;; Code is released under GPLv2, except for fisher.h, which is under
6283 (license (list license:gpl2 license:lgpl2.1+))))
6285 (define-public plink-ng
6286 (package (inherit plink)
6293 (url "https://github.com/chrchang/plink-ng")
6294 (commit (string-append "v" version))))
6295 (file-name (git-file-name name version))
6297 (base32 "02npdwgkpfkdnhw819rhj5kw02a5k5m90b14zq9zzya4hyg929c0"))))
6298 (build-system gnu-build-system)
6300 '(#:tests? #f ;no "check" target
6301 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
6302 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
6304 "-f" "Makefile.std")
6306 (modify-phases %standard-phases
6307 (add-after 'unpack 'chdir
6308 (lambda _ (chdir "1.9") #t))
6309 (delete 'configure) ; no "configure" script
6311 (lambda* (#:key outputs #:allow-other-keys)
6312 (let ((bin (string-append (assoc-ref outputs "out")
6314 (install-file "plink" bin)
6319 ("openblas" ,openblas)))
6320 (home-page "https://www.cog-genomics.org/plink/")
6321 (license license:gpl3+)))
6323 (define-public smithlab-cpp
6324 (let ((revision "1")
6325 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
6327 (name "smithlab-cpp")
6328 (version (string-append "0." revision "." (string-take commit 7)))
6332 (url "https://github.com/smithlabcode/smithlab_cpp")
6334 (file-name (string-append name "-" version "-checkout"))
6337 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
6338 (build-system gnu-build-system)
6340 `(#:modules ((guix build gnu-build-system)
6343 #:tests? #f ;no "check" target
6345 (modify-phases %standard-phases
6346 (add-after 'unpack 'use-samtools-headers
6348 (substitute* '("SAM.cpp"
6350 (("sam.h") "samtools/sam.h"))
6353 (lambda* (#:key outputs #:allow-other-keys)
6354 (let* ((out (assoc-ref outputs "out"))
6355 (lib (string-append out "/lib"))
6356 (include (string-append out "/include/smithlab-cpp")))
6359 (for-each (cut install-file <> lib)
6360 (find-files "." "\\.o$"))
6361 (for-each (cut install-file <> include)
6362 (find-files "." "\\.hpp$")))
6364 (delete 'configure))))
6366 `(("samtools" ,samtools-0.1)
6368 (home-page "https://github.com/smithlabcode/smithlab_cpp")
6369 (synopsis "C++ helper library for functions used in Smith lab projects")
6371 "Smithlab CPP is a C++ library that includes functions used in many of
6372 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
6373 structures, classes for genomic regions, mapped sequencing reads, etc.")
6374 (license license:gpl3+))))
6376 (define-public preseq
6382 (uri (string-append "https://github.com/smithlabcode/preseq/"
6383 "releases/download/v" version
6384 "/preseq_v" version ".tar.bz2"))
6386 (base32 "149x9xmk1wy1gff85325yfzqc0qk4sgp1w6gbyj9cnji4x1dszbl"))
6387 (modules '((guix build utils)))
6389 ;; Remove bundled samtools.
6390 (delete-file-recursively "samtools")
6392 (build-system gnu-build-system)
6394 `(#:tests? #f ;no "check" target
6396 (modify-phases %standard-phases
6397 (delete 'configure))
6399 (list (string-append "PREFIX="
6400 (assoc-ref %outputs "out"))
6401 (string-append "LIBBAM="
6402 (assoc-ref %build-inputs "samtools")
6404 (string-append "SMITHLAB_CPP="
6405 (assoc-ref %build-inputs "smithlab-cpp")
6408 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
6411 ("samtools" ,samtools-0.1)
6412 ("smithlab-cpp" ,smithlab-cpp)
6414 (home-page "http://smithlabresearch.org/software/preseq/")
6415 (synopsis "Program for analyzing library complexity")
6417 "The preseq package is aimed at predicting and estimating the complexity
6418 of a genomic sequencing library, equivalent to predicting and estimating the
6419 number of redundant reads from a given sequencing depth and how many will be
6420 expected from additional sequencing using an initial sequencing experiment.
6421 The estimates can then be used to examine the utility of further sequencing,
6422 optimize the sequencing depth, or to screen multiple libraries to avoid low
6423 complexity samples.")
6424 (license license:gpl3+)))
6426 (define-public python-screed
6428 (name "python-screed")
6433 (uri (pypi-uri "screed" version))
6436 "148vcb7w2wr6a4w6vs2bsxanbqibxfk490zbcbg4m61s8669zdjx"))))
6437 (build-system python-build-system)
6440 (modify-phases %standard-phases
6441 ;; Tests must be run after installation, as the "screed" command does
6442 ;; not exist right after building.
6444 (add-after 'install 'check
6445 (lambda* (#:key inputs outputs #:allow-other-keys)
6446 (let ((out (assoc-ref outputs "out")))
6447 (setenv "PYTHONPATH"
6448 (string-append out "/lib/python"
6449 (string-take (string-take-right
6450 (assoc-ref inputs "python")
6453 (getenv "PYTHONPATH")))
6454 (setenv "PATH" (string-append out "/bin:" (getenv "PATH"))))
6455 (invoke "python" "setup.py" "test")
6458 `(("python-pytest" ,python-pytest)
6459 ("python-pytest-cov" ,python-pytest-cov)
6460 ("python-pytest-runner" ,python-pytest-runner)))
6462 `(("python-bz2file" ,python-bz2file)))
6463 (home-page "https://github.com/dib-lab/screed/")
6464 (synopsis "Short read sequence database utilities")
6465 (description "Screed parses FASTA and FASTQ files and generates databases.
6466 Values such as sequence name, sequence description, sequence quality and the
6467 sequence itself can be retrieved from these databases.")
6468 (license license:bsd-3)))
6470 (define-public python2-screed
6471 (package-with-python2 python-screed))
6473 (define-public sra-tools
6481 (url "https://github.com/ncbi/sra-tools")
6483 (file-name (git-file-name name version))
6486 "1cr2mijkfs5sm35ffjs6861qsd1qkgnhnbavdv65zg5d655abbjf"))))
6487 (build-system gnu-build-system)
6489 `(#:parallel-build? #f ; not supported
6490 #:tests? #f ; no "check" target
6492 (list (string-append "DEFAULT_CRT="
6493 (assoc-ref %build-inputs "ncbi-vdb")
6495 (string-append "DEFAULT_KFG="
6496 (assoc-ref %build-inputs "ncbi-vdb")
6498 (string-append "VDB_LIBDIR="
6499 (assoc-ref %build-inputs "ncbi-vdb")
6500 ,(if (string-prefix? "x86_64"
6501 (or (%current-target-system)
6506 (modify-phases %standard-phases
6507 (add-before 'configure 'set-perl-search-path
6509 ;; Work around "dotless @INC" build failure.
6511 (string-append (getcwd) "/setup:"
6512 (getenv "PERL5LIB")))
6515 (lambda* (#:key inputs outputs #:allow-other-keys)
6516 ;; The build system expects a directory containing the sources and
6517 ;; raw build output of ncbi-vdb, including files that are not
6518 ;; installed. Since we are building against an installed version of
6519 ;; ncbi-vdb, the following modifications are needed.
6520 (substitute* "setup/konfigure.perl"
6521 ;; Make the configure script look for the "ilib" directory of
6522 ;; "ncbi-vdb" without first checking for the existence of a
6523 ;; matching library in its "lib" directory.
6524 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
6525 "my $f = File::Spec->catdir($ilibdir, $ilib);")
6526 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
6527 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
6528 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
6531 (substitute* "tools/copycat/Makefile"
6532 (("smagic-static") "lmagic"))
6533 (substitute* "tools/driver-tool/utf8proc/Makefile"
6534 (("CC\\?=gcc") "myCC=gcc")
6535 (("\\(CC\\)") "(myCC)"))
6537 ;; The 'configure' script doesn't recognize things like
6538 ;; '--enable-fast-install'.
6539 (invoke "./configure"
6540 (string-append "--build-prefix=" (getcwd) "/build")
6541 (string-append "--prefix=" (assoc-ref outputs "out"))
6542 (string-append "--debug")
6543 (string-append "--with-fuse-prefix="
6544 (assoc-ref inputs "fuse"))
6545 (string-append "--with-magic-prefix="
6546 (assoc-ref inputs "libmagic"))
6547 ;; TODO: building with libxml2 fails with linker errors
6549 (string-append "--with-xml2-prefix="
6550 (assoc-ref inputs "libxml2"))
6551 (string-append "--with-ncbi-vdb-sources="
6552 (assoc-ref inputs "ncbi-vdb"))
6553 (string-append "--with-ncbi-vdb-build="
6554 (assoc-ref inputs "ncbi-vdb"))
6555 (string-append "--with-ngs-sdk-prefix="
6556 (assoc-ref inputs "ngs-sdk"))
6557 (string-append "--with-hdf5-prefix="
6558 (assoc-ref inputs "hdf5")))
6560 (native-inputs `(("perl" ,perl)))
6562 `(("ngs-sdk" ,ngs-sdk)
6563 ("ncbi-vdb" ,ncbi-vdb)
6568 ("python" ,python-wrapper)))
6570 "https://trace.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
6571 (synopsis "Tools and libraries for reading and writing sequencing data")
6573 "The SRA Toolkit from NCBI is a collection of tools and libraries for
6574 reading of sequencing files from the Sequence Read Archive (SRA) database and
6575 writing files into the .sra format.")
6576 (license license:public-domain)))
6578 (define-public seqan
6584 (uri (string-append "https://github.com/seqan/seqan/releases/"
6585 "download/seqan-v" version
6586 "/seqan-library-" version ".tar.xz"))
6589 "19a1rlxx03qy1i1iriicly68w64yjxbv24g9gdywnfmq998v35yx"))))
6590 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6591 ;; makes sense to split the outputs.
6592 (outputs '("out" "doc"))
6593 (build-system trivial-build-system)
6595 `(#:modules ((guix build utils))
6598 (use-modules (guix build utils))
6599 (let ((tar (assoc-ref %build-inputs "tar"))
6600 (xz (assoc-ref %build-inputs "xz"))
6601 (out (assoc-ref %outputs "out"))
6602 (doc (assoc-ref %outputs "doc")))
6603 (setenv "PATH" (string-append tar "/bin:" xz "/bin"))
6604 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6605 (chdir (string-append "seqan-library-" ,version))
6606 (copy-recursively "include" (string-append out "/include"))
6607 (copy-recursively "share" (string-append doc "/share"))
6610 `(("source" ,source)
6613 (home-page "https://www.seqan.de")
6614 (synopsis "Library for nucleotide sequence analysis")
6616 "SeqAn is a C++ library of efficient algorithms and data structures for
6617 the analysis of sequences with the focus on biological data. It contains
6618 algorithms and data structures for string representation and their
6619 manipulation, online and indexed string search, efficient I/O of
6620 bioinformatics file formats, sequence alignment, and more.")
6621 (license license:bsd-3)))
6623 (define-public seqan-1
6624 (package (inherit seqan)
6629 (uri (string-append "https://packages.seqan.de/seqan-library/"
6630 "seqan-library-" version ".tar.bz2"))
6633 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
6634 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6635 ;; makes sense to split the outputs.
6636 (outputs '("out" "doc"))
6637 (build-system trivial-build-system)
6639 `(#:modules ((guix build utils))
6642 (use-modules (guix build utils))
6643 (let ((tar (assoc-ref %build-inputs "tar"))
6644 (bzip (assoc-ref %build-inputs "bzip2"))
6645 (out (assoc-ref %outputs "out"))
6646 (doc (assoc-ref %outputs "doc")))
6647 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
6648 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6649 (chdir (string-append "seqan-library-" ,version))
6650 (copy-recursively "include" (string-append out "/include"))
6651 (copy-recursively "share" (string-append doc "/share"))
6654 `(("source" ,source)
6656 ("bzip2" ,bzip2)))))
6658 (define-public seqmagick
6665 (uri (pypi-uri "seqmagick" version))
6668 "0pf98da7i59q47gwrbx0wjk6xlvbybiwphw80w7h4ydjj0579a2b"))))
6669 (build-system python-build-system)
6671 `(("python-biopython" ,python-biopython)))
6673 `(("python-nose" ,python-nose)))
6674 (home-page "https://github.com/fhcrc/seqmagick")
6675 (synopsis "Tools for converting and modifying sequence files")
6677 "Bioinformaticians often have to convert sequence files between formats
6678 and do little manipulations on them, and it's not worth writing scripts for
6679 that. Seqmagick is a utility to expose the file format conversion in
6680 BioPython in a convenient way. Instead of having a big mess of scripts, there
6681 is one that takes arguments.")
6682 (license license:gpl3)))
6684 (define-public seqtk
6691 (url "https://github.com/lh3/seqtk")
6692 (commit (string-append "v" version))))
6693 (file-name (git-file-name name version))
6696 "1bfzlqa84b5s1qi22blmmw2s8xdyp9h9ydcq22pfjhh5gab3yz6l"))))
6697 (build-system gnu-build-system)
6700 (modify-phases %standard-phases
6703 ;; There are no tests, so we just run a sanity check.
6704 (lambda _ (invoke "./seqtk" "seq") #t))
6706 (lambda* (#:key outputs #:allow-other-keys)
6707 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6708 (install-file "seqtk" bin)
6712 (home-page "https://github.com/lh3/seqtk")
6713 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
6715 "Seqtk is a fast and lightweight tool for processing sequences in the
6716 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
6717 optionally compressed by gzip.")
6718 (license license:expat)))
6720 (define-public snap-aligner
6722 (name "snap-aligner")
6723 (version "1.0beta.18")
6727 (url "https://github.com/amplab/snap")
6728 (commit (string-append "v" version))))
6729 (file-name (git-file-name name version))
6732 "01w3qq4wm07z73vky0cfwlmrbf50n3w722cxrlzxfi99mnb808d8"))))
6733 (build-system gnu-build-system)
6736 (modify-phases %standard-phases
6738 (replace 'check (lambda _ (invoke "./unit_tests") #t))
6740 (lambda* (#:key outputs #:allow-other-keys)
6741 (let* ((out (assoc-ref outputs "out"))
6742 (bin (string-append out "/bin")))
6743 (install-file "snap-aligner" bin)
6744 (install-file "SNAPCommand" bin)
6748 (home-page "http://snap.cs.berkeley.edu/")
6749 (synopsis "Short read DNA sequence aligner")
6751 "SNAP is a fast and accurate aligner for short DNA reads. It is
6752 optimized for modern read lengths of 100 bases or higher, and takes advantage
6753 of these reads to align data quickly through a hash-based indexing scheme.")
6754 ;; 32-bit systems are not supported by the unpatched code.
6755 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
6756 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
6757 ;; systems without a lot of memory cannot make good use of this program.
6758 (supported-systems '("x86_64-linux"))
6759 (license license:asl2.0)))
6761 (define-public sortmerna
6769 (url "https://github.com/biocore/sortmerna")
6771 (file-name (git-file-name name version))
6774 "0j3mbz4n25738yijmjbr5r4fyvkgm8v5vn3sshyfvmyqf5q9byqf"))))
6775 (build-system gnu-build-system)
6776 (outputs '("out" ;for binaries
6777 "db")) ;for sequence databases
6780 (modify-phases %standard-phases
6782 (lambda* (#:key outputs #:allow-other-keys)
6783 (let* ((out (assoc-ref outputs "out"))
6784 (bin (string-append out "/bin"))
6785 (db (assoc-ref outputs "db"))
6787 (string-append db "/share/sortmerna/rRNA_databases")))
6788 (install-file "sortmerna" bin)
6789 (install-file "indexdb_rna" bin)
6790 (for-each (lambda (file)
6791 (install-file file share))
6792 (find-files "rRNA_databases" ".*fasta"))
6796 (home-page "https://bioinfo.lifl.fr/RNA/sortmerna/")
6797 (synopsis "Biological sequence analysis tool for NGS reads")
6799 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
6800 and operational taxonomic unit (OTU) picking of next generation
6801 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
6802 allows for fast and sensitive analyses of nucleotide sequences. The main
6803 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
6804 ;; The source includes x86 specific code
6805 (supported-systems '("x86_64-linux" "i686-linux"))
6806 (license license:lgpl3)))
6815 (url "https://github.com/alexdobin/STAR")
6817 (file-name (git-file-name name version))
6820 "0zc5biymja9zml9yizcj1h68fq9c6sxfcav8a0lbgvgsm44rvans"))
6821 (modules '((guix build utils)))
6824 (substitute* "source/Makefile"
6826 ;; Remove pre-built binaries and bundled htslib sources.
6827 (delete-file-recursively "bin/MacOSX_x86_64")
6828 (delete-file-recursively "bin/Linux_x86_64")
6829 (delete-file-recursively "bin/Linux_x86_64_static")
6830 (delete-file-recursively "source/htslib")
6832 (build-system gnu-build-system)
6834 '(#:tests? #f ;no check target
6835 #:make-flags '("STAR")
6837 (modify-phases %standard-phases
6838 (add-after 'unpack 'enter-source-dir
6839 (lambda _ (chdir "source") #t))
6840 (add-after 'enter-source-dir 'make-reproducible
6842 (substitute* "Makefile"
6843 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
6844 (string-append pre "Built with Guix" post)))
6846 ;; See https://github.com/alexdobin/STAR/pull/562
6847 (add-after 'enter-source-dir 'add-missing-header
6849 (substitute* "SoloReadFeature_inputRecords.cpp"
6850 (("#include \"binarySearch2.h\"" h)
6851 (string-append h "\n#include <math.h>")))
6853 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
6855 (substitute* "Makefile"
6856 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
6858 (substitute* '("BAMfunctions.cpp"
6863 "bamRemoveDuplicates.cpp")
6864 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
6865 (string-append "#include <" header ">")))
6866 (substitute* "IncludeDefine.h"
6867 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
6868 (string-append "<" header ">")))
6871 (lambda* (#:key outputs #:allow-other-keys)
6872 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6873 (install-file "STAR" bin))
6875 (delete 'configure))))
6879 `(("htslib" ,htslib)
6881 (home-page "https://github.com/alexdobin/STAR")
6882 (synopsis "Universal RNA-seq aligner")
6884 "The Spliced Transcripts Alignment to a Reference (STAR) software is
6885 based on a previously undescribed RNA-seq alignment algorithm that uses
6886 sequential maximum mappable seed search in uncompressed suffix arrays followed
6887 by seed clustering and stitching procedure. In addition to unbiased de novo
6888 detection of canonical junctions, STAR can discover non-canonical splices and
6889 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
6891 ;; Only 64-bit systems are supported according to the README.
6892 (supported-systems '("x86_64-linux" "mips64el-linux"))
6893 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
6894 (license license:gpl3+)))
6896 (define-public star-for-pigx
6904 (url "https://github.com/alexdobin/STAR")
6906 (file-name (git-file-name name version))
6909 "1hgiqw5qhs0pc1xazzihcfd92na02xyq2kb469z04y1v51kpvvjq"))
6910 (modules '((guix build utils)))
6913 (substitute* "source/Makefile"
6915 ;; Remove pre-built binaries and bundled htslib sources.
6916 (delete-file-recursively "bin/MacOSX_x86_64")
6917 (delete-file-recursively "bin/Linux_x86_64")
6918 (delete-file-recursively "bin/Linux_x86_64_static")
6919 (delete-file-recursively "source/htslib")
6922 (define-public starlong
6923 (package (inherit star)
6926 (substitute-keyword-arguments (package-arguments star)
6927 ((#:make-flags flags)
6930 `(modify-phases ,phases
6931 ;; Allow extra long sequence reads.
6932 (add-after 'unpack 'make-extra-long
6934 (substitute* "source/IncludeDefine.h"
6935 (("(#define DEF_readNameLengthMax ).*" _ match)
6936 (string-append match "900000\n")))
6939 (lambda* (#:key outputs #:allow-other-keys)
6940 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6941 (install-file "STARlong" bin))
6944 (define-public subread
6950 (uri (string-append "mirror://sourceforge/subread/subread-"
6951 version "/subread-" version "-source.tar.gz"))
6954 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
6955 (build-system gnu-build-system)
6957 `(#:tests? #f ;no "check" target
6958 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
6959 ;; optimizations by default, so we override these flags such that x86_64
6960 ;; flags are only added when the build target is an x86_64 system.
6962 (list (let ((system ,(or (%current-target-system)
6964 (flags '("-ggdb" "-fomit-frame-pointer"
6965 "-ffast-math" "-funroll-loops"
6966 "-fmessage-length=0"
6967 "-O9" "-Wall" "-DMAKE_FOR_EXON"
6969 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
6970 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
6971 (if (string-prefix? "x86_64" system)
6972 (string-append "CCFLAGS=" (string-join (append flags flags64)))
6973 (string-append "CCFLAGS=" (string-join flags))))
6974 "-f" "Makefile.Linux"
6975 "CC=gcc ${CCFLAGS}")
6977 (modify-phases %standard-phases
6978 (add-after 'unpack 'enter-dir
6979 (lambda _ (chdir "src") #t))
6981 (lambda* (#:key outputs #:allow-other-keys)
6982 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6984 (copy-recursively "../bin" bin))
6986 ;; no "configure" script
6987 (delete 'configure))))
6988 (inputs `(("zlib" ,zlib)))
6989 (home-page "http://bioinf.wehi.edu.au/subread-package/")
6990 (synopsis "Tool kit for processing next-gen sequencing data")
6992 "The subread package contains the following tools: subread aligner, a
6993 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
6994 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
6995 features; exactSNP: a SNP caller that discovers SNPs by testing signals
6996 against local background noises.")
6997 (license license:gpl3+)))
6999 (define-public stringtie
7005 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
7006 "stringtie-" version ".tar.gz"))
7009 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
7010 (modules '((guix build utils)))
7013 (delete-file-recursively "samtools-0.1.18")
7015 (build-system gnu-build-system)
7017 `(#:tests? #f ;no test suite
7019 (modify-phases %standard-phases
7020 ;; no configure script
7022 (add-before 'build 'use-system-samtools
7024 (substitute* "Makefile"
7025 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
7027 (substitute* '("gclib/GBam.h"
7029 (("#include \"(bam|sam|kstring).h\"" _ header)
7030 (string-append "#include <samtools/" header ".h>")))
7032 (add-after 'unpack 'remove-duplicate-typedef
7034 ;; This typedef conflicts with the typedef in
7035 ;; glibc-2.25/include/bits/types.h
7036 (substitute* "gclib/GThreads.h"
7037 (("typedef long long __intmax_t;") ""))
7040 (lambda* (#:key outputs #:allow-other-keys)
7041 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
7042 (install-file "stringtie" bin)
7045 `(("samtools" ,samtools-0.1)
7047 (home-page "http://ccb.jhu.edu/software/stringtie/")
7048 (synopsis "Transcript assembly and quantification for RNA-Seq data")
7050 "StringTie is a fast and efficient assembler of RNA-Seq sequence
7051 alignments into potential transcripts. It uses a novel network flow algorithm
7052 as well as an optional de novo assembly step to assemble and quantitate
7053 full-length transcripts representing multiple splice variants for each gene
7054 locus. Its input can include not only the alignments of raw reads used by
7055 other transcript assemblers, but also alignments of longer sequences that have
7056 been assembled from those reads. To identify differentially expressed genes
7057 between experiments, StringTie's output can be processed either by the
7058 Cuffdiff or Ballgown programs.")
7059 (license license:artistic2.0)))
7061 (define-public taxtastic
7066 ;; The Pypi version does not include tests.
7069 (url "https://github.com/fhcrc/taxtastic")
7070 (commit (string-append "v" version))))
7071 (file-name (git-file-name name version))
7074 "1sv8mkg64jn7zdwf1jj71c16686yrwxk0apb1l8sjszy9p166g0p"))))
7075 (build-system python-build-system)
7078 (modify-phases %standard-phases
7079 (add-after 'unpack 'prepare-directory
7081 ;; The git checkout must be writable for tests.
7082 (for-each make-file-writable (find-files "."))
7083 ;; This test fails, but the error is not caught by the test
7084 ;; framework, so the tests fail...
7085 (substitute* "tests/test_taxit.py"
7086 (("self.cmd_fails\\(''\\)")
7087 "self.cmd_fails('nothing')"))
7088 ;; This version file is expected to be created with git describe.
7089 (mkdir-p "taxtastic/data")
7090 (with-output-to-file "taxtastic/data/ver"
7091 (lambda () (display ,version)))
7093 (add-after 'unpack 'python37-compatibility
7095 (substitute* "taxtastic/utils.py"
7096 (("import csv") "import csv, errno")
7097 (("os.errno") "errno"))
7100 ;; Note, this fails to run with "-v" as it tries to write to a
7101 ;; closed output stream.
7102 (lambda _ (invoke "python" "-m" "unittest") #t)))))
7104 `(("python-sqlalchemy" ,python-sqlalchemy)
7105 ("python-decorator" ,python-decorator)
7106 ("python-biopython" ,python-biopython)
7107 ("python-pandas" ,python-pandas)
7108 ("python-psycopg2" ,python-psycopg2)
7109 ("python-fastalite" ,python-fastalite)
7110 ("python-pyyaml" ,python-pyyaml)
7111 ("python-six" ,python-six)
7112 ("python-jinja2" ,python-jinja2)
7113 ("python-dendropy" ,python-dendropy)))
7114 (home-page "https://github.com/fhcrc/taxtastic")
7115 (synopsis "Tools for taxonomic naming and annotation")
7117 "Taxtastic is software written in python used to build and maintain
7118 reference packages i.e. collections of reference trees, reference alignments,
7119 profiles, and associated taxonomic information.")
7120 (license license:gpl3+)))
7122 (define-public vcftools
7129 "https://github.com/vcftools/vcftools/releases/download/v"
7130 version "/vcftools-" version ".tar.gz"))
7133 "1qqlx7flfv7axrjwkaz6njkscsl1d0jw98ns8d8bh1n1hd1pgz6v"))))
7134 (build-system gnu-build-system)
7136 `(#:tests? #f ; no "check" target
7138 "CFLAGS=-O2" ; override "-m64" flag
7139 (string-append "PREFIX=" (assoc-ref %outputs "out"))
7140 (string-append "MANDIR=" (assoc-ref %outputs "out")
7141 "/share/man/man1"))))
7143 `(("pkg-config" ,pkg-config)))
7147 (home-page "https://vcftools.github.io/")
7148 (synopsis "Tools for working with VCF files")
7150 "VCFtools is a program package designed for working with VCF files, such
7151 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
7152 provide easily accessible methods for working with complex genetic variation
7153 data in the form of VCF files.")
7154 ;; The license is declared as LGPLv3 in the README and
7155 ;; at https://vcftools.github.io/license.html
7156 (license license:lgpl3)))
7158 (define-public infernal
7164 (uri (string-append "http://eddylab.org/software/infernal/"
7165 "infernal-" version ".tar.gz"))
7168 "1z4mgwqg1j4n5ika08ai8mg9yjyjhf4821jp83v2bgwzxrykqjgr"))))
7169 (build-system gnu-build-system)
7172 ("python" ,python))) ; for tests
7173 (home-page "http://eddylab.org/infernal/")
7174 (synopsis "Inference of RNA alignments")
7175 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
7176 searching DNA sequence databases for RNA structure and sequence similarities.
7177 It is an implementation of a special case of profile stochastic context-free
7178 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
7179 profile, but it scores a combination of sequence consensus and RNA secondary
7180 structure consensus, so in many cases, it is more capable of identifying RNA
7181 homologs that conserve their secondary structure more than their primary
7183 ;; Infernal 1.1.3 requires VMX or SSE capability for parallel instructions.
7184 (supported-systems '("i686-linux" "x86_64-linux"))
7185 (license license:bsd-3)))
7187 (define-public r-snapatac
7195 (url "https://github.com/r3fang/SnapATAC")
7196 (commit (string-append "v" version))))
7197 (file-name (git-file-name name version))
7199 (base32 "037jzlbl436fi7lkpq7d83i2vd1crnrik3vac2x6xj75dbikb2av"))))
7200 (properties `((upstream-name . "SnapATAC")))
7201 (build-system r-build-system)
7203 `(("r-bigmemory" ,r-bigmemory)
7204 ("r-doparallel" ,r-doparallel)
7205 ("r-dosnow" ,r-dosnow)
7206 ("r-edger" ,r-edger)
7207 ("r-foreach" ,r-foreach)
7208 ("r-genomicranges" ,r-genomicranges)
7209 ("r-igraph" ,r-igraph)
7210 ("r-iranges" ,r-iranges)
7211 ("r-irlba" ,r-irlba)
7212 ("r-matrix" ,r-matrix)
7214 ("r-plot3d" ,r-plot3d)
7216 ("r-raster" ,r-raster)
7217 ("r-rcolorbrewer" ,r-rcolorbrewer)
7218 ("r-rhdf5" ,r-rhdf5)
7219 ("r-rtsne" ,r-rtsne)
7220 ("r-scales" ,r-scales)
7221 ("r-viridis" ,r-viridis)))
7222 (home-page "https://github.com/r3fang/SnapATAC")
7223 (synopsis "Single nucleus analysis package for ATAC-Seq")
7225 "This package provides a fast and accurate analysis toolkit for single
7226 cell ATAC-seq (Assay for transposase-accessible chromatin using sequencing).
7227 Single cell ATAC-seq can resolve the heterogeneity of a complex tissue and
7228 reveal cell-type specific regulatory landscapes. However, the exceeding data
7229 sparsity has posed unique challenges for the data analysis. This package
7230 @code{r-snapatac} is an end-to-end bioinformatics pipeline for analyzing large-
7231 scale single cell ATAC-seq data which includes quality control, normalization,
7232 clustering analysis, differential analysis, motif inference and exploration of
7233 single cell ATAC-seq sequencing data.")
7234 (license license:gpl3)))
7236 (define-public r-archr
7237 (let ((commit "46b519ffb6f73edf132497ac31650d19ef055dc1")
7241 (version (git-version "1.0.0" revision commit))
7246 (url "https://github.com/GreenleafLab/ArchR")
7248 (file-name (git-file-name name version))
7251 "1zj3sdfhgn2q2256fmz61a92vw1wylyck632d7842d6knd0v92v8"))))
7252 (properties `((upstream-name . "ArchR")))
7253 (build-system r-build-system)
7255 `(("r-biocgenerics" ,r-biocgenerics)
7256 ("r-biostrings" ,r-biostrings)
7257 ("r-chromvar" ,r-chromvar)
7258 ("r-complexheatmap" ,r-complexheatmap)
7259 ("r-data-table" ,r-data-table)
7260 ("r-genomicranges" ,r-genomicranges)
7261 ("r-ggplot2" ,r-ggplot2)
7262 ("r-ggrepel" ,r-ggrepel)
7263 ("r-gridextra" ,r-gridextra)
7264 ("r-gtable" ,r-gtable)
7265 ("r-gtools" ,r-gtools)
7266 ("r-magrittr" ,r-magrittr)
7267 ("r-matrix" ,r-matrix)
7268 ("r-matrixstats" ,r-matrixstats)
7269 ("r-motifmatchr" ,r-motifmatchr)
7270 ("r-nabor" ,r-nabor)
7273 ("r-rhdf5" ,r-rhdf5)
7274 ("r-rsamtools" ,r-rsamtools)
7275 ("r-s4vectors" ,r-s4vectors)
7276 ("r-stringr" ,r-stringr)
7277 ("r-summarizedexperiment" ,r-summarizedexperiment)
7278 ("r-uwot" ,r-uwot)))
7279 (home-page "https://github.com/GreenleafLab/ArchR")
7280 (synopsis "Analyze single-cell regulatory chromatin in R")
7282 "This package is designed to streamline scATAC analyses in R.")
7283 (license license:gpl2+))))
7285 (define-public r-scde
7292 (url "https://github.com/hms-dbmi/scde")
7294 (file-name (git-file-name name version))
7297 "10na2gyka24mszdxf92wz9h2c13hdf1ww30c68gfsw53lvvhhhxb"))))
7298 (build-system r-build-system)
7300 `(("r-rcpp" ,r-rcpp)
7301 ("r-rcpparmadillo" ,r-rcpparmadillo)
7304 ("r-rjson" ,r-rjson)
7305 ("r-cairo" ,r-cairo)
7306 ("r-rcolorbrewer" ,r-rcolorbrewer)
7307 ("r-edger" ,r-edger)
7308 ("r-quantreg" ,r-quantreg)
7310 ("r-rmtstat" ,r-rmtstat)
7311 ("r-extremes" ,r-extremes)
7312 ("r-pcamethods" ,r-pcamethods)
7313 ("r-biocparallel" ,r-biocparallel)
7314 ("r-flexmix" ,r-flexmix)))
7315 (home-page "https://hms-dbmi.github.io/scde/")
7316 (synopsis "R package for analyzing single-cell RNA-seq data")
7317 (description "The SCDE package implements a set of statistical methods for
7318 analyzing single-cell RNA-seq data. SCDE fits individual error models for
7319 single-cell RNA-seq measurements. These models can then be used for
7320 assessment of differential expression between groups of cells, as well as
7321 other types of analysis. The SCDE package also contains the pagoda framework
7322 which applies pathway and gene set overdispersion analysis to identify aspects
7323 of transcriptional heterogeneity among single cells.")
7324 ;; See https://github.com/hms-dbmi/scde/issues/38
7325 (license license:gpl2)))
7327 (define-public r-centipede
7329 (name "r-centipede")
7333 (uri (string-append "http://download.r-forge.r-project.org/"
7334 "src/contrib/CENTIPEDE_" version ".tar.gz"))
7337 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
7338 (build-system r-build-system)
7339 (home-page "http://centipede.uchicago.edu/")
7340 (synopsis "Predict transcription factor binding sites")
7342 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
7343 of the genome that are bound by particular transcription factors. It starts
7344 by identifying a set of candidate binding sites, and then aims to classify the
7345 sites according to whether each site is bound or not bound by a transcription
7346 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
7347 between two different types of motif instances using as much relevant
7348 information as possible.")
7349 (license (list license:gpl2+ license:gpl3+))))
7351 (define-public r-demultiplex
7352 (let ((commit "6e2a1422c8e6f418cfb271997eebc91f9195f299")
7355 (name "r-demultiplex")
7356 (version (git-version "1.0.2" revision commit))
7361 (url "https://github.com/chris-mcginnis-ucsf/MULTI-seq")
7363 (file-name (git-file-name name version))
7366 "01kv88wp8vdaq07sjk0d3d1cb553mq1xqg0war81pgmg63bgi38w"))))
7367 (properties `((upstream-name . "deMULTIplex")))
7368 (build-system r-build-system)
7370 `(("r-kernsmooth" ,r-kernsmooth)
7371 ("r-reshape2" ,r-reshape2)
7372 ("r-rtsne" ,r-rtsne)
7373 ("r-shortread" ,r-shortread)
7374 ("r-stringdist" ,r-stringdist)))
7375 (home-page "https://github.com/chris-mcginnis-ucsf/MULTI-seq")
7376 (synopsis "MULTI-seq pre-processing and classification tools")
7378 "deMULTIplex is an R package for analyzing single-cell RNA sequencing
7379 data generated with the MULTI-seq sample multiplexing method. The package
7380 includes software to
7383 @item Convert raw MULTI-seq sample barcode library FASTQs into a sample
7384 barcode UMI count matrix, and
7385 @item Classify cell barcodes into sample barcode groups.
7388 (license license:cc0))))
7390 (define-public vsearch
7398 (url "https://github.com/torognes/vsearch")
7399 (commit (string-append "v" version))))
7400 (file-name (git-file-name name version))
7403 "0vhrpjfdf75ba04b24xknp41790cvcgwl0vgpy7qbzj5xh2521ss"))
7404 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
7407 ;; Remove bundled cityhash sources. The vsearch source is adjusted
7408 ;; for this in the patch.
7409 (delete-file "src/city.h")
7410 (delete-file "src/citycrc.h")
7411 (delete-file "src/city.cc")
7413 (build-system gnu-build-system)
7417 ("cityhash" ,cityhash)))
7419 `(("autoconf" ,autoconf)
7420 ("automake" ,automake)))
7421 (synopsis "Sequence search tools for metagenomics")
7423 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
7424 dereplication, pairwise alignment, shuffling, subsampling, sorting and
7425 masking. The tool takes advantage of parallelism in the form of SIMD
7426 vectorization as well as multiple threads to perform accurate alignments at
7427 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
7428 Needleman-Wunsch).")
7429 (home-page "https://github.com/torognes/vsearch")
7430 ;; vsearch uses non-portable SSE intrinsics so building fails on other
7432 (supported-systems '("x86_64-linux"))
7433 ;; Dual licensed; also includes public domain source.
7434 (license (list license:gpl3 license:bsd-2))))
7436 (define-public pardre
7439 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
7444 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
7448 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
7449 (build-system gnu-build-system)
7451 `(#:tests? #f ; no tests included
7453 (modify-phases %standard-phases
7456 (lambda* (#:key outputs #:allow-other-keys)
7457 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
7458 (install-file "ParDRe" bin)
7461 `(("openmpi" ,openmpi)
7463 (synopsis "Parallel tool to remove duplicate DNA reads")
7465 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
7466 Duplicate reads can be seen as identical or nearly identical sequences with
7467 some mismatches. This tool lets users avoid the analysis of unnecessary
7468 reads, reducing the time of subsequent procedures with the
7469 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
7470 in order to exploit the parallel capabilities of multicore clusters. It is
7471 faster than multithreaded counterparts (end of 2015) for the same number of
7472 cores and, thanks to the message-passing technology, it can be executed on
7474 (home-page "https://sourceforge.net/projects/pardre/")
7475 (license license:gpl3+)))
7477 (define-public ngshmmalign
7479 (name "ngshmmalign")
7484 (uri (string-append "https://github.com/cbg-ethz/ngshmmalign/"
7485 "releases/download/" version
7486 "/ngshmmalign-" version ".tar.bz2"))
7489 "0jryvlssi2r2ii1dxnx39yk6bh4yqgq010fnxrgfgbaj3ykijlzv"))))
7490 (build-system cmake-build-system)
7491 (arguments '(#:tests? #false)) ; there are none
7493 `(("boost" ,boost)))
7494 (home-page "https://github.com/cbg-ethz/ngshmmalign/")
7495 (synopsis "Profile HMM aligner for NGS reads")
7497 "ngshmmalign is a profile HMM aligner for NGS reads designed particularly
7498 for small genomes (such as those of RNA viruses like HIV-1 and HCV) that
7499 experience substantial biological insertions and deletions.")
7500 (license license:gpl2+)))
7502 (define-public prinseq
7509 (uri (string-append "mirror://sourceforge/prinseq/standalone/"
7510 "prinseq-lite-" version ".tar.gz"))
7513 "0vxmzvmm67whxrqdaaamwgjk7cf0fzfs5s673jgg00kz7g70splv"))))
7514 (build-system gnu-build-system)
7516 `(#:tests? #false ; no check target
7518 (modify-phases %standard-phases
7522 (lambda* (#:key outputs #:allow-other-keys)
7523 (let* ((out (assoc-ref outputs "out"))
7524 (bin (string-append out "/bin")))
7525 (for-each (lambda (file)
7527 (install-file file bin)
7528 (wrap-script (string-append bin "/" (basename file))
7529 `("PERL5LIB" ":" prefix
7530 (,(getenv "PERL5LIB")))))
7531 (find-files "." "prinseq.*.pl"))))))))
7533 `(("guile" ,guile-3.0) ; for wrapper scripts
7535 ("perl-cairo" ,perl-cairo)
7536 ("perl-data-dumper" ,perl-data-dumper)
7537 ("perl-digest-md5" ,perl-digest-md5)
7538 ("perl-getopt-long" ,perl-getopt-long)
7539 ("perl-json" ,perl-json)
7540 ("perl-statistics-pca" ,perl-statistics-pca)))
7541 (home-page "http://prinseq.sourceforge.net/")
7542 (synopsis "Preprocess sequence data in FASTA or FASTQ formats")
7544 "PRINSEQ is a bioinformatics tool to help you preprocess your genomic or
7545 metagenomic sequence data in FASTA or FASTQ formats. The tool is written in
7546 Perl and can be helpful if you want to filter, reformat, or trim your sequence
7547 data. It also generates basic statistics for your sequences.")
7548 (license license:gpl3+)))
7550 (define-public ruby-bio-kseq
7552 (name "ruby-bio-kseq")
7557 (uri (rubygems-uri "bio-kseq" version))
7560 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
7561 (build-system ruby-build-system)
7563 `(#:test-target "spec"))
7565 `(("bundler" ,bundler)
7566 ("ruby-rspec" ,ruby-rspec)
7567 ("ruby-rake-compiler" ,ruby-rake-compiler)))
7570 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
7572 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
7573 FASTQ parsing code. It provides a fast iterator over sequences and their
7575 (home-page "https://github.com/gusevfe/bio-kseq")
7576 (license license:expat)))
7578 (define-public bio-locus
7585 (uri (rubygems-uri "bio-locus" version))
7588 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
7589 (build-system ruby-build-system)
7591 `(("ruby-rspec" ,ruby-rspec)))
7592 (synopsis "Tool for fast querying of genome locations")
7594 "Bio-locus is a tabix-like tool for fast querying of genome
7595 locations. Many file formats in bioinformatics contain records that
7596 start with a chromosome name and a position for a SNP, or a start-end
7597 position for indels. Bio-locus allows users to store this chr+pos or
7598 chr+pos+alt information in a database.")
7599 (home-page "https://github.com/pjotrp/bio-locus")
7600 (license license:expat)))
7602 (define-public bio-blastxmlparser
7604 (name "bio-blastxmlparser")
7608 (uri (rubygems-uri "bio-blastxmlparser" version))
7611 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
7612 (build-system ruby-build-system)
7614 `(("ruby-bio-logger" ,ruby-bio-logger)
7615 ("ruby-nokogiri" ,ruby-nokogiri)))
7617 `(("ruby-rspec" ,ruby-rspec)))
7618 (synopsis "Fast big data BLAST XML parser and library")
7620 "Very fast parallel big-data BLAST XML file parser which can be used as
7621 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
7622 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
7623 (home-page "https://github.com/pjotrp/blastxmlparser")
7624 (license license:expat)))
7626 (define-public bioruby
7633 (uri (rubygems-uri "bio" version))
7636 "1d56amdsjv1mag7m6gv2w0xij8hqx1v5xbdjsix8sp3yp36m7938"))))
7637 (build-system ruby-build-system)
7639 `(("ruby-libxml" ,ruby-libxml)))
7641 `(("which" ,which))) ; required for test phase
7644 (modify-phases %standard-phases
7645 (add-before 'build 'patch-test-command
7647 (substitute* '("test/functional/bio/test_command.rb")
7648 (("/bin/sh") (which "sh")))
7649 (substitute* '("test/functional/bio/test_command.rb")
7650 (("/bin/ls") (which "ls")))
7651 (substitute* '("test/functional/bio/test_command.rb")
7652 (("which") (which "which")))
7653 (substitute* '("test/functional/bio/test_command.rb",
7654 "test/data/command/echoarg2.sh")
7655 (("/bin/echo") (which "echo")))
7657 (synopsis "Ruby library, shell and utilities for bioinformatics")
7658 (description "BioRuby comes with a comprehensive set of Ruby development
7659 tools and libraries for bioinformatics and molecular biology. BioRuby has
7660 components for sequence analysis, pathway analysis, protein modelling and
7661 phylogenetic analysis; it supports many widely used data formats and provides
7662 easy access to databases, external programs and public web services, including
7663 BLAST, KEGG, GenBank, MEDLINE and GO.")
7664 (home-page "http://bioruby.org/")
7665 ;; Code is released under Ruby license, except for setup
7666 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
7667 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
7669 (define-public bio-vcf
7676 (uri (rubygems-uri "bio-vcf" version))
7679 "1glw5pn9s8z13spxk6yyfqaz80n9lga67f33w35nkpq9dwi2vg6g"))))
7680 (build-system ruby-build-system)
7682 `(("ruby-cucumber" ,ruby-cucumber)))
7683 (synopsis "Smart VCF parser DSL")
7685 "Bio-vcf provides a @acronym{DSL, domain specific language} for processing
7686 the VCF format. Record named fields can be queried with regular expressions.
7687 Bio-vcf is a new generation VCF parser, filter and converter. Bio-vcf is not
7688 only very fast for genome-wide (WGS) data, it also comes with a filtering,
7689 evaluation and rewrite language and can output any type of textual data,
7690 including VCF header and contents in RDF and JSON.")
7691 (home-page "https://github.com/vcflib/bio-vcf")
7692 (license license:expat)))
7694 (define-public r-edger
7700 (uri (bioconductor-uri "edgeR" version))
7703 "1gaic8qf6a6sy0bmydh1xzf52w0wnq31aanpvw3a30pfsi218bcp"))))
7704 (properties `((upstream-name . "edgeR")))
7705 (build-system r-build-system)
7707 `(("r-limma" ,r-limma)
7708 ("r-locfit" ,r-locfit)
7710 ("r-statmod" ,r-statmod))) ;for estimateDisp
7711 (home-page "http://bioinf.wehi.edu.au/edgeR")
7712 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7713 (description "This package can do differential expression analysis of
7714 RNA-seq expression profiles with biological replication. It implements a range
7715 of statistical methodology based on the negative binomial distributions,
7716 including empirical Bayes estimation, exact tests, generalized linear models
7717 and quasi-likelihood tests. It be applied to differential signal analysis of
7718 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7720 (license license:gpl2+)))
7722 (define-public r-variantannotation
7724 (name "r-variantannotation")
7728 (uri (bioconductor-uri "VariantAnnotation" version))
7731 "1sl0l6v05lfglj281nszma0h5k234md7rn2pdah8vs2d4iq3kimw"))))
7733 `((upstream-name . "VariantAnnotation")))
7735 `(("r-annotationdbi" ,r-annotationdbi)
7736 ("r-biobase" ,r-biobase)
7737 ("r-biocgenerics" ,r-biocgenerics)
7738 ("r-biostrings" ,r-biostrings)
7739 ("r-bsgenome" ,r-bsgenome)
7741 ("r-genomeinfodb" ,r-genomeinfodb)
7742 ("r-genomicfeatures" ,r-genomicfeatures)
7743 ("r-genomicranges" ,r-genomicranges)
7744 ("r-iranges" ,r-iranges)
7745 ("r-matrixgenerics" ,r-matrixgenerics)
7746 ("r-summarizedexperiment" ,r-summarizedexperiment)
7747 ("r-rhtslib" ,r-rhtslib)
7748 ("r-rsamtools" ,r-rsamtools)
7749 ("r-rtracklayer" ,r-rtracklayer)
7750 ("r-s4vectors" ,r-s4vectors)
7751 ("r-xvector" ,r-xvector)
7752 ("r-zlibbioc" ,r-zlibbioc)))
7753 (build-system r-build-system)
7754 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7755 (synopsis "Package for annotation of genetic variants")
7756 (description "This R package can annotate variants, compute amino acid
7757 coding changes and predict coding outcomes.")
7758 (license license:artistic2.0)))
7760 (define-public r-limma
7766 (uri (bioconductor-uri "limma" version))
7769 "1xxv493q1kip9bjfv7v7k5dnq7hz7gvl80i983v4mvwavhgnbxfz"))))
7770 (build-system r-build-system)
7771 (home-page "http://bioinf.wehi.edu.au/limma")
7772 (synopsis "Package for linear models for microarray and RNA-seq data")
7773 (description "This package can be used for the analysis of gene expression
7774 studies, especially the use of linear models for analysing designed experiments
7775 and the assessment of differential expression. The analysis methods apply to
7776 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7777 (license license:gpl2+)))
7779 (define-public r-xvector
7785 (uri (bioconductor-uri "XVector" version))
7788 "1pqljikg4f6jb7wgm5537zwgq5b013nyz1agjrwfq2cljb0ym6lq"))))
7790 `((upstream-name . "XVector")))
7791 (build-system r-build-system)
7794 (modify-phases %standard-phases
7795 (add-after 'unpack 'use-system-zlib
7797 (substitute* "DESCRIPTION"
7798 (("zlibbioc, ") ""))
7799 (substitute* "NAMESPACE"
7800 (("import\\(zlibbioc\\)") ""))
7805 `(("r-biocgenerics" ,r-biocgenerics)
7806 ("r-iranges" ,r-iranges)
7807 ("r-s4vectors" ,r-s4vectors)))
7808 (home-page "https://bioconductor.org/packages/XVector")
7809 (synopsis "Representation and manpulation of external sequences")
7811 "This package provides memory efficient S4 classes for storing sequences
7812 \"externally\" (behind an R external pointer, or on disk).")
7813 (license license:artistic2.0)))
7815 (define-public r-genomicranges
7817 (name "r-genomicranges")
7821 (uri (bioconductor-uri "GenomicRanges" version))
7824 "0j4py5g6pdj35xhlaqhxxhg55j9l4mcdk3yck4dgyavv5f2dh24i"))))
7826 `((upstream-name . "GenomicRanges")))
7827 (build-system r-build-system)
7829 `(("r-biocgenerics" ,r-biocgenerics)
7830 ("r-genomeinfodb" ,r-genomeinfodb)
7831 ("r-iranges" ,r-iranges)
7832 ("r-s4vectors" ,r-s4vectors)
7833 ("r-xvector" ,r-xvector)))
7835 `(("r-knitr" ,r-knitr)))
7836 (home-page "https://bioconductor.org/packages/GenomicRanges")
7837 (synopsis "Representation and manipulation of genomic intervals")
7839 "This package provides tools to efficiently represent and manipulate
7840 genomic annotations and alignments is playing a central role when it comes to
7841 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7842 GenomicRanges package defines general purpose containers for storing and
7843 manipulating genomic intervals and variables defined along a genome.")
7844 (license license:artistic2.0)))
7846 (define-public r-biobase
7852 (uri (bioconductor-uri "Biobase" version))
7855 "11kgc4flywlm3i18603558l8ksv91c24vkc5fnnbcd375i2dhhd4"))))
7857 `((upstream-name . "Biobase")))
7858 (build-system r-build-system)
7860 `(("r-biocgenerics" ,r-biocgenerics)))
7861 (home-page "https://bioconductor.org/packages/Biobase")
7862 (synopsis "Base functions for Bioconductor")
7864 "This package provides functions that are needed by many other packages
7865 on Bioconductor or which replace R functions.")
7866 (license license:artistic2.0)))
7868 (define-public r-annotationdbi
7870 (name "r-annotationdbi")
7874 (uri (bioconductor-uri "AnnotationDbi" version))
7877 "0zqxgh3nx6y8ry12s2vss2f4axz5vpqxha1y4ifhhcx4zhpzsglr"))))
7879 `((upstream-name . "AnnotationDbi")))
7880 (build-system r-build-system)
7882 `(("r-biobase" ,r-biobase)
7883 ("r-biocgenerics" ,r-biocgenerics)
7885 ("r-iranges" ,r-iranges)
7886 ("r-rsqlite" ,r-rsqlite)
7887 ("r-s4vectors" ,r-s4vectors)))
7889 `(("r-knitr" ,r-knitr)))
7890 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7891 (synopsis "Annotation database interface")
7893 "This package provides user interface and database connection code for
7894 annotation data packages using SQLite data storage.")
7895 (license license:artistic2.0)))
7897 (define-public r-biomart
7903 (uri (bioconductor-uri "biomaRt" version))
7906 "0gwmd0ykpv0gyh34c56g5m12lil20fvig49f3ih1jxrxf3q4wmq7"))))
7908 `((upstream-name . "biomaRt")))
7909 (build-system r-build-system)
7911 `(("r-annotationdbi" ,r-annotationdbi)
7912 ("r-biocfilecache" ,r-biocfilecache)
7914 ("r-openssl" ,r-openssl)
7915 ("r-progress" ,r-progress)
7916 ("r-rappdirs" ,r-rappdirs)
7917 ("r-stringr" ,r-stringr)
7919 ("r-xml2" ,r-xml2)))
7921 `(("r-knitr" ,r-knitr)))
7922 (home-page "https://bioconductor.org/packages/biomaRt")
7923 (synopsis "Interface to BioMart databases")
7925 "biomaRt provides an interface to a growing collection of databases
7926 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7927 package enables retrieval of large amounts of data in a uniform way without
7928 the need to know the underlying database schemas or write complex SQL queries.
7929 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7930 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7931 users direct access to a diverse set of data and enable a wide range of
7932 powerful online queries from gene annotation to database mining.")
7933 (license license:artistic2.0)))
7935 (define-public r-biocparallel
7937 (name "r-biocparallel")
7941 (uri (bioconductor-uri "BiocParallel" version))
7944 "1iryicvmcagcrj29kp49mqhiq2kn72j4idj380hi9illmdrg9ism"))))
7946 `((upstream-name . "BiocParallel")))
7947 (build-system r-build-system)
7949 `(("r-futile-logger" ,r-futile-logger)
7953 `(("r-knitr" ,r-knitr)))
7954 (home-page "https://bioconductor.org/packages/BiocParallel")
7955 (synopsis "Bioconductor facilities for parallel evaluation")
7957 "This package provides modified versions and novel implementation of
7958 functions for parallel evaluation, tailored to use with Bioconductor
7960 (license (list license:gpl2+ license:gpl3+))))
7962 (define-public r-biostrings
7964 (name "r-biostrings")
7968 (uri (bioconductor-uri "Biostrings" version))
7971 "1rbqhs73mhfr1gi0rx28jiyan7i3hb45ai3jpl1656fnrhgjfxq5"))))
7973 `((upstream-name . "Biostrings")))
7974 (build-system r-build-system)
7976 `(("r-biocgenerics" ,r-biocgenerics)
7977 ("r-crayon" ,r-crayon)
7978 ("r-iranges" ,r-iranges)
7979 ("r-s4vectors" ,r-s4vectors)
7980 ("r-xvector" ,r-xvector)))
7981 (home-page "https://bioconductor.org/packages/Biostrings")
7982 (synopsis "String objects and algorithms for biological sequences")
7984 "This package provides memory efficient string containers, string
7985 matching algorithms, and other utilities, for fast manipulation of large
7986 biological sequences or sets of sequences.")
7987 (license license:artistic2.0)))
7989 (define-public r-rsamtools
7991 (name "r-rsamtools")
7995 (uri (bioconductor-uri "Rsamtools" version))
7998 "040pggkwglc6wy90qnc7xcdnaj0v3iqlykvvsl74241409qly554"))))
8000 `((upstream-name . "Rsamtools")))
8001 (build-system r-build-system)
8004 (modify-phases %standard-phases
8005 (add-after 'unpack 'use-system-zlib
8007 (substitute* "DESCRIPTION"
8008 (("zlibbioc, ") ""))
8009 (substitute* "NAMESPACE"
8010 (("import\\(zlibbioc\\)") ""))
8013 `(("r-biocgenerics" ,r-biocgenerics)
8014 ("r-biocparallel" ,r-biocparallel)
8015 ("r-biostrings" ,r-biostrings)
8016 ("r-bitops" ,r-bitops)
8017 ("r-genomeinfodb" ,r-genomeinfodb)
8018 ("r-genomicranges" ,r-genomicranges)
8019 ("r-iranges" ,r-iranges)
8020 ("r-rhtslib" ,r-rhtslib)
8021 ("r-s4vectors" ,r-s4vectors)
8022 ("r-xvector" ,r-xvector)))
8023 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
8024 (synopsis "Interface to samtools, bcftools, and tabix")
8026 "This package provides an interface to the @code{samtools},
8027 @code{bcftools}, and @code{tabix} utilities for manipulating SAM (Sequence
8028 Alignment / Map), FASTA, binary variant call (BCF) and compressed indexed
8029 tab-delimited (tabix) files.")
8030 (license license:expat)))
8032 (define-public r-delayedarray
8034 (name "r-delayedarray")
8038 (uri (bioconductor-uri "DelayedArray" version))
8041 "1d75zrhha1v7dhbvjp6a4iap441l5k268w0jjxklpqywbqns7l3d"))))
8043 `((upstream-name . "DelayedArray")))
8044 (build-system r-build-system)
8046 `(("r-biocgenerics" ,r-biocgenerics)
8047 ("r-s4vectors" ,r-s4vectors)
8048 ("r-iranges" ,r-iranges)
8049 ("r-matrix" ,r-matrix)
8050 ("r-matrixgenerics" ,r-matrixgenerics)))
8052 `(("r-knitr" ,r-knitr)))
8053 (home-page "https://bioconductor.org/packages/DelayedArray")
8054 (synopsis "Delayed operations on array-like objects")
8056 "Wrapping an array-like object (typically an on-disk object) in a
8057 @code{DelayedArray} object allows one to perform common array operations on it
8058 without loading the object in memory. In order to reduce memory usage and
8059 optimize performance, operations on the object are either delayed or executed
8060 using a block processing mechanism. Note that this also works on in-memory
8061 array-like objects like @code{DataFrame} objects (typically with Rle columns),
8062 @code{Matrix} objects, and ordinary arrays and data frames.")
8063 (license license:artistic2.0)))
8065 (define-public r-summarizedexperiment
8067 (name "r-summarizedexperiment")
8071 (uri (bioconductor-uri "SummarizedExperiment" version))
8074 "04x6d4mcsnvz6glkmf6k2cv3fs8zk03i9rvv0ahpl793n8l411ps"))))
8076 `((upstream-name . "SummarizedExperiment")))
8077 (build-system r-build-system)
8079 `(("r-biobase" ,r-biobase)
8080 ("r-biocgenerics" ,r-biocgenerics)
8081 ("r-delayedarray" ,r-delayedarray)
8082 ("r-genomeinfodb" ,r-genomeinfodb)
8083 ("r-genomicranges" ,r-genomicranges)
8084 ("r-iranges" ,r-iranges)
8085 ("r-matrix" ,r-matrix)
8086 ("r-matrixgenerics" ,r-matrixgenerics)
8087 ("r-s4vectors" ,r-s4vectors)))
8089 `(("r-knitr" ,r-knitr)))
8090 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
8091 (synopsis "Container for representing genomic ranges by sample")
8093 "The SummarizedExperiment container contains one or more assays, each
8094 represented by a matrix-like object of numeric or other mode. The rows
8095 typically represent genomic ranges of interest and the columns represent
8097 (license license:artistic2.0)))
8099 (define-public r-genomicalignments
8101 (name "r-genomicalignments")
8105 (uri (bioconductor-uri "GenomicAlignments" version))
8108 "1q95px6s6snsax4ax955zzpdlrwp5liwf70wqq0lrk9mp6lq0hbr"))))
8110 `((upstream-name . "GenomicAlignments")))
8111 (build-system r-build-system)
8113 `(("r-biocgenerics" ,r-biocgenerics)
8114 ("r-biocparallel" ,r-biocparallel)
8115 ("r-biostrings" ,r-biostrings)
8116 ("r-genomeinfodb" ,r-genomeinfodb)
8117 ("r-genomicranges" ,r-genomicranges)
8118 ("r-iranges" ,r-iranges)
8119 ("r-rsamtools" ,r-rsamtools)
8120 ("r-s4vectors" ,r-s4vectors)
8121 ("r-summarizedexperiment" ,r-summarizedexperiment)))
8122 (home-page "https://bioconductor.org/packages/GenomicAlignments")
8123 (synopsis "Representation and manipulation of short genomic alignments")
8125 "This package provides efficient containers for storing and manipulating
8126 short genomic alignments (typically obtained by aligning short reads to a
8127 reference genome). This includes read counting, computing the coverage,
8128 junction detection, and working with the nucleotide content of the
8130 (license license:artistic2.0)))
8132 (define-public r-rtracklayer
8134 (name "r-rtracklayer")
8138 (uri (bioconductor-uri "rtracklayer" version))
8141 "12zimhpdzjyzd81wrzz5hdbzvlgzcs22x1nnaf2jq4cba3ch5px8"))))
8142 (build-system r-build-system)
8145 (modify-phases %standard-phases
8146 (add-after 'unpack 'use-system-zlib
8148 (substitute* "DESCRIPTION"
8149 ((" zlibbioc,") ""))
8150 (substitute* "NAMESPACE"
8151 (("import\\(zlibbioc\\)") ""))
8154 `(("pkg-config" ,pkg-config)))
8158 `(("r-biocgenerics" ,r-biocgenerics)
8159 ("r-biostrings" ,r-biostrings)
8160 ("r-genomeinfodb" ,r-genomeinfodb)
8161 ("r-genomicalignments" ,r-genomicalignments)
8162 ("r-genomicranges" ,r-genomicranges)
8163 ("r-iranges" ,r-iranges)
8164 ("r-rcurl" ,r-rcurl)
8165 ("r-rsamtools" ,r-rsamtools)
8166 ("r-s4vectors" ,r-s4vectors)
8168 ("r-xvector" ,r-xvector)
8169 ("r-zlibbioc" ,r-zlibbioc)))
8170 (home-page "https://bioconductor.org/packages/rtracklayer")
8171 (synopsis "R interface to genome browsers and their annotation tracks")
8173 "rtracklayer is an extensible framework for interacting with multiple
8174 genome browsers (currently UCSC built-in) and manipulating annotation tracks
8175 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
8176 built-in). The user may export/import tracks to/from the supported browsers,
8177 as well as query and modify the browser state, such as the current viewport.")
8178 (license license:artistic2.0)))
8180 (define-public r-genomicfeatures
8182 (name "r-genomicfeatures")
8186 (uri (bioconductor-uri "GenomicFeatures" version))
8189 "17dyd9hcw6pw16y353dh55wfhxmkxka99lbsxsp9xyrhffwrxi0s"))))
8191 `((upstream-name . "GenomicFeatures")))
8192 (build-system r-build-system)
8194 `(("r-annotationdbi" ,r-annotationdbi)
8195 ("r-biobase" ,r-biobase)
8196 ("r-biocgenerics" ,r-biocgenerics)
8197 ("r-biomart" ,r-biomart)
8198 ("r-biostrings" ,r-biostrings)
8200 ("r-genomeinfodb" ,r-genomeinfodb)
8201 ("r-genomicranges" ,r-genomicranges)
8202 ("r-iranges" ,r-iranges)
8203 ("r-rcurl" ,r-rcurl)
8204 ("r-rsqlite" ,r-rsqlite)
8205 ("r-rtracklayer" ,r-rtracklayer)
8206 ("r-s4vectors" ,r-s4vectors)
8207 ("r-xvector" ,r-xvector)))
8209 `(("r-knitr" ,r-knitr)))
8210 (home-page "https://bioconductor.org/packages/GenomicFeatures")
8211 (synopsis "Tools for working with transcript centric annotations")
8213 "This package provides a set of tools and methods for making and
8214 manipulating transcript centric annotations. With these tools the user can
8215 easily download the genomic locations of the transcripts, exons and cds of a
8216 given organism, from either the UCSC Genome Browser or a BioMart
8217 database (more sources will be supported in the future). This information is
8218 then stored in a local database that keeps track of the relationship between
8219 transcripts, exons, cds and genes. Flexible methods are provided for
8220 extracting the desired features in a convenient format.")
8221 (license license:artistic2.0)))
8223 (define-public r-go-db
8229 (uri (string-append "https://www.bioconductor.org/packages/"
8230 "release/data/annotation/src/contrib/GO.db_"
8234 "0i3wcf5h3n0dawzc1hy0kv74f06j80c47n4p3g3fmrcxlhi3jpa5"))))
8236 `((upstream-name . "GO.db")))
8237 (build-system r-build-system)
8239 `(("r-annotationdbi" ,r-annotationdbi)))
8240 (home-page "https://bioconductor.org/packages/GO.db")
8241 (synopsis "Annotation maps describing the entire Gene Ontology")
8243 "The purpose of this GO.db annotation package is to provide detailed
8244 information about the latest version of the Gene Ontologies.")
8245 (license license:artistic2.0)))
8247 (define-public r-topgo
8253 (uri (bioconductor-uri "topGO" version))
8256 "0vr3l9gvd3dhy446k3fkj6rm7z1abxi56rbnrs64297yzxaz1ngl"))))
8258 `((upstream-name . "topGO")))
8259 (build-system r-build-system)
8261 `(("r-annotationdbi" ,r-annotationdbi)
8263 ("r-biobase" ,r-biobase)
8264 ("r-biocgenerics" ,r-biocgenerics)
8265 ("r-go-db" ,r-go-db)
8266 ("r-graph" ,r-graph)
8267 ("r-lattice" ,r-lattice)
8268 ("r-matrixstats" ,r-matrixstats)
8269 ("r-sparsem" ,r-sparsem)))
8270 (home-page "https://bioconductor.org/packages/topGO")
8271 (synopsis "Enrichment analysis for gene ontology")
8273 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
8274 terms while accounting for the topology of the GO graph. Different test
8275 statistics and different methods for eliminating local similarities and
8276 dependencies between GO terms can be implemented and applied.")
8277 ;; Any version of the LGPL applies.
8278 (license license:lgpl2.1+)))
8280 (define-public r-bsgenome
8286 (uri (bioconductor-uri "BSgenome" version))
8289 "1gbvmxr6r57smgvhqgwspbcnwyk4hsfkxkpzzcs6470q03zfb4wq"))))
8291 `((upstream-name . "BSgenome")))
8292 (build-system r-build-system)
8294 `(("r-biocgenerics" ,r-biocgenerics)
8295 ("r-biostrings" ,r-biostrings)
8296 ("r-genomeinfodb" ,r-genomeinfodb)
8297 ("r-genomicranges" ,r-genomicranges)
8298 ("r-iranges" ,r-iranges)
8299 ("r-matrixstats" ,r-matrixstats)
8300 ("r-rsamtools" ,r-rsamtools)
8301 ("r-rtracklayer" ,r-rtracklayer)
8302 ("r-s4vectors" ,r-s4vectors)
8303 ("r-xvector" ,r-xvector)))
8304 (home-page "https://bioconductor.org/packages/BSgenome")
8305 (synopsis "Infrastructure for Biostrings-based genome data packages")
8307 "This package provides infrastructure shared by all Biostrings-based
8308 genome data packages and support for efficient SNP representation.")
8309 (license license:artistic2.0)))
8311 (define-public r-impute
8317 (uri (bioconductor-uri "impute" version))
8320 "1pnjasw9i19nmxwjzrd9jbln31yc5jilfvwk414ya5zbqfsazvxa"))))
8322 `(("gfortran" ,gfortran)))
8323 (build-system r-build-system)
8324 (home-page "https://bioconductor.org/packages/impute")
8325 (synopsis "Imputation for microarray data")
8327 "This package provides a function to impute missing gene expression
8328 microarray data, using nearest neighbor averaging.")
8329 (license license:gpl2+)))
8331 (define-public r-seqpattern
8333 (name "r-seqpattern")
8337 (uri (bioconductor-uri "seqPattern" version))
8340 "0j68n6fwycxjpl2va5fw7ajb123n758s2pq997d76dysxghmrlzq"))))
8342 `((upstream-name . "seqPattern")))
8343 (build-system r-build-system)
8345 `(("r-biostrings" ,r-biostrings)
8346 ("r-genomicranges" ,r-genomicranges)
8347 ("r-iranges" ,r-iranges)
8348 ("r-kernsmooth" ,r-kernsmooth)
8349 ("r-plotrix" ,r-plotrix)))
8350 (home-page "https://bioconductor.org/packages/seqPattern")
8351 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
8353 "This package provides tools to visualize oligonucleotide patterns and
8354 sequence motif occurrences across a large set of sequences centred at a common
8355 reference point and sorted by a user defined feature.")
8356 (license license:gpl3+)))
8358 (define-public r-genomation
8360 (name "r-genomation")
8364 (uri (bioconductor-uri "genomation" version))
8367 "1ana06irlpdgnmk8mb329nws9sm8n6max4qargf1xdcdf3rnk45g"))))
8368 (build-system r-build-system)
8370 `(("r-biostrings" ,r-biostrings)
8371 ("r-bsgenome" ,r-bsgenome)
8372 ("r-data-table" ,r-data-table)
8373 ("r-genomeinfodb" ,r-genomeinfodb)
8374 ("r-genomicalignments" ,r-genomicalignments)
8375 ("r-genomicranges" ,r-genomicranges)
8376 ("r-ggplot2" ,r-ggplot2)
8377 ("r-gridbase" ,r-gridbase)
8378 ("r-impute" ,r-impute)
8379 ("r-iranges" ,r-iranges)
8380 ("r-matrixstats" ,r-matrixstats)
8381 ("r-plotrix" ,r-plotrix)
8384 ("r-readr" ,r-readr)
8385 ("r-reshape2" ,r-reshape2)
8386 ("r-rsamtools" ,r-rsamtools)
8387 ("r-rtracklayer" ,r-rtracklayer)
8388 ("r-runit" ,r-runit)
8389 ("r-s4vectors" ,r-s4vectors)
8390 ("r-seqpattern" ,r-seqpattern)))
8392 `(("r-knitr" ,r-knitr)))
8393 (home-page "https://bioinformatics.mdc-berlin.de/genomation/")
8394 (synopsis "Summary, annotation and visualization of genomic data")
8396 "This package provides a package for summary and annotation of genomic
8397 intervals. Users can visualize and quantify genomic intervals over
8398 pre-defined functional regions, such as promoters, exons, introns, etc. The
8399 genomic intervals represent regions with a defined chromosome position, which
8400 may be associated with a score, such as aligned reads from HT-seq experiments,
8401 TF binding sites, methylation scores, etc. The package can use any tabular
8402 genomic feature data as long as it has minimal information on the locations of
8403 genomic intervals. In addition, it can use BAM or BigWig files as input.")
8404 (license license:artistic2.0)))
8406 (define-public r-genomationdata
8408 (name "r-genomationdata")
8412 ;; We cannot use bioconductor-uri here because this tarball is
8413 ;; located under "data/annotation/" instead of "bioc/".
8414 (uri (string-append "https://bioconductor.org/packages/"
8415 "release/data/experiment/src/contrib/"
8416 "genomationData_" version ".tar.gz"))
8419 "0igjsvfnws3498j65ifniw0kbxfqpfr59rcjddqvq4zsj453fx1g"))))
8420 (build-system r-build-system)
8421 ;; As this package provides little more than large data files, it doesn't
8422 ;; make sense to build substitutes.
8423 (arguments `(#:substitutable? #f))
8425 `(("r-knitr" ,r-knitr)))
8426 (home-page "https://bioinformatics.mdc-berlin.de/genomation/")
8427 (synopsis "Experimental data for use with the genomation package")
8429 "This package contains experimental genetic data for use with the
8430 genomation package. Included are Chip Seq, Methylation and Cage data,
8431 downloaded from Encode.")
8432 (license license:gpl3+)))
8434 (define-public r-seqlogo
8441 (uri (bioconductor-uri "seqLogo" version))
8444 "02rpzjjfg5chlwwfbvv72cm78cg2vfmdwzars0cin9hz1hd7rnq1"))))
8445 (properties `((upstream-name . "seqLogo")))
8446 (build-system r-build-system)
8448 `(("r-knitr" ,r-knitr)))
8449 (home-page "https://bioconductor.org/packages/seqLogo")
8450 (synopsis "Sequence logos for DNA sequence alignments")
8452 "seqLogo takes the position weight matrix of a DNA sequence motif and
8453 plots the corresponding sequence logo as introduced by Schneider and
8455 (license license:lgpl2.0+)))
8457 (define-public r-motifrg
8464 (uri (bioconductor-uri "motifRG" version))
8467 "1ml6zyzlk8yjbnfhga2qnw8nl43rankvka0kc1yljxr2b66aqbhn"))))
8468 (properties `((upstream-name . "motifRG")))
8469 (build-system r-build-system)
8471 `(("r-biostrings" ,r-biostrings)
8472 ("r-bsgenome" ,r-bsgenome)
8473 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8474 ("r-iranges" ,r-iranges)
8475 ("r-seqlogo" ,r-seqlogo)
8476 ("r-xvector" ,r-xvector)))
8477 (home-page "https://bioconductor.org/packages/motifRG")
8478 (synopsis "Discover motifs in high throughput sequencing data")
8480 "This package provides tools for discriminative motif discovery in high
8481 throughput genetic sequencing data sets using regression methods.")
8482 (license license:artistic2.0)))
8484 (define-public r-zlibbioc
8490 (uri (bioconductor-uri "zlibbioc" version))
8493 "0m36ddss0znvm19dhnxcclxjhgjplw8ajk8v419h20ab8an6khxg"))))
8495 `((upstream-name . "zlibbioc")))
8496 (build-system r-build-system)
8497 (home-page "https://bioconductor.org/packages/zlibbioc")
8498 (synopsis "Provider for zlib-1.2.5 to R packages")
8499 (description "This package uses the source code of zlib-1.2.5 to create
8500 libraries for systems that do not have these available via other means.")
8501 (license license:artistic2.0)))
8503 (define-public r-r4rna
8510 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8514 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8515 (build-system r-build-system)
8517 `(("r-optparse" ,r-optparse)
8518 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8519 (home-page "https://www.e-rna.org/r-chie/index.cgi")
8520 (synopsis "Analysis framework for RNA secondary structure")
8522 "The R4RNA package aims to be a general framework for the analysis of RNA
8523 secondary structure and comparative analysis in R.")
8524 (license license:gpl3+)))
8526 (define-public r-rhtslib
8533 (uri (bioconductor-uri "Rhtslib" version))
8536 "18wag2jnpda6078xjkpfdvar1gkb2myhw83gg03l39sabh35qya4"))))
8537 (properties `((upstream-name . "Rhtslib")))
8538 (build-system r-build-system)
8539 ;; Without this a temporary directory ends up in the Rhtslib.so binary,
8540 ;; which makes R abort the build.
8541 (arguments '(#:configure-flags '("--no-staged-install")))
8544 ("zlib" ,zlib) ; packages using rhtslib need to link with zlib
8545 ("r-zlibbioc" ,r-zlibbioc)))
8547 `(("pkg-config" ,pkg-config)
8548 ("r-knitr" ,r-knitr)))
8549 (home-page "https://github.com/nhayden/Rhtslib")
8550 (synopsis "High-throughput sequencing library as an R package")
8552 "This package provides the HTSlib C library for high-throughput
8553 nucleotide sequence analysis. The package is primarily useful to developers
8554 of other R packages who wish to make use of HTSlib.")
8555 (license license:lgpl2.0+)))
8557 (define-public r-bamsignals
8559 (name "r-bamsignals")
8564 (uri (bioconductor-uri "bamsignals" version))
8567 "0p3r9z9z5sfkd0b951cgr751k4z0yviyn1jfw9d4fcnyld7g1jxv"))))
8568 (build-system r-build-system)
8570 `(("r-biocgenerics" ,r-biocgenerics)
8571 ("r-genomicranges" ,r-genomicranges)
8572 ("r-iranges" ,r-iranges)
8574 ("r-rhtslib" ,r-rhtslib)
8575 ("r-zlibbioc" ,r-zlibbioc)))
8577 `(("r-knitr" ,r-knitr)))
8578 (home-page "https://bioconductor.org/packages/bamsignals")
8579 (synopsis "Extract read count signals from bam files")
8581 "This package efficiently obtains count vectors from indexed bam
8582 files. It counts the number of nucleotide sequence reads in given genomic
8583 ranges and it computes reads profiles and coverage profiles. It also handles
8585 (license license:gpl2+)))
8587 (define-public r-rcas
8593 (uri (bioconductor-uri "RCAS" version))
8596 "0vdxml618vqvf8xyh0zxs307p9zby0cj9dqyiiz625ilyq1hkw2m"))))
8597 (properties `((upstream-name . "RCAS")))
8598 (build-system r-build-system)
8600 `(("r-biocgenerics" ,r-biocgenerics)
8601 ("r-biostrings" ,r-biostrings)
8602 ("r-bsgenome" ,r-bsgenome)
8603 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8604 ("r-cowplot" ,r-cowplot)
8605 ("r-data-table" ,r-data-table)
8607 ("r-genomation" ,r-genomation)
8608 ("r-genomeinfodb" ,r-genomeinfodb)
8609 ("r-genomicfeatures" ,r-genomicfeatures)
8610 ("r-genomicranges" ,r-genomicranges)
8611 ("r-ggplot2" ,r-ggplot2)
8612 ("r-ggseqlogo" ,r-ggseqlogo)
8613 ("r-gprofiler2" ,r-gprofiler2)
8614 ("r-iranges" ,r-iranges)
8615 ("r-pbapply" ,r-pbapply)
8616 ("r-pheatmap" ,r-pheatmap)
8617 ("r-plotly" ,r-plotly)
8618 ("r-plotrix" ,r-plotrix)
8619 ("r-proxy" ,r-proxy)
8620 ("r-ranger" ,r-ranger)
8621 ("r-rsqlite" ,r-rsqlite)
8622 ("r-rtracklayer" ,r-rtracklayer)
8623 ("r-rmarkdown" ,r-rmarkdown)
8624 ("r-s4vectors" ,r-s4vectors)
8625 ("pandoc" ,pandoc)))
8627 `(("r-knitr" ,r-knitr)))
8628 (synopsis "RNA-centric annotation system")
8630 "RCAS aims to be a standalone RNA-centric annotation system that provides
8631 intuitive reports and publication-ready graphics. This package provides the R
8632 library implementing most of the pipeline's features.")
8633 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8634 (license license:artistic2.0)))
8636 (define-public rcas-web
8643 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8644 "releases/download/v" version
8645 "/rcas-web-" version ".tar.gz"))
8648 "0wq951aj45gqki1bickg876i993lmawkp8x24agg264br5x716db"))))
8649 (build-system gnu-build-system)
8652 (modify-phases %standard-phases
8653 (add-before 'configure 'find-RCAS
8654 ;; The configure script can't find non-1.3.x versions of RCAS because
8655 ;; its R expression ‘1.10.1 >= 1.3.4’ evaluates to false.
8657 (substitute* "configure"
8658 (("1\\.3\\.4") "0.0.0"))
8660 (add-after 'install 'wrap-executable
8661 (lambda* (#:key inputs outputs #:allow-other-keys)
8662 (let* ((out (assoc-ref outputs "out"))
8663 (json (assoc-ref inputs "guile-json"))
8664 (redis (assoc-ref inputs "guile-redis"))
8665 (path (string-append
8666 json "/share/guile/site/2.2:"
8667 redis "/share/guile/site/2.2")))
8668 (wrap-program (string-append out "/bin/rcas-web")
8669 `("GUILE_LOAD_PATH" ":" = (,path))
8670 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8671 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8674 `(("r-minimal" ,r-minimal)
8676 ("guile" ,guile-2.2)
8677 ("guile-json" ,guile-json-1)
8678 ("guile-redis" ,guile2.2-redis)))
8680 `(("pkg-config" ,pkg-config)))
8681 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8682 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8683 (description "This package provides a simple web interface for the
8684 @dfn{RNA-centric annotation system} (RCAS).")
8685 (license license:agpl3+)))
8687 (define-public r-mutationalpatterns
8689 (name "r-mutationalpatterns")
8694 (uri (bioconductor-uri "MutationalPatterns" version))
8697 "1988kjjgq8af0hj7chhpxi88717wwmzs9qgrwapjh0hm2hjwhn35"))))
8698 (build-system r-build-system)
8700 `(("r-knitr" ,r-knitr)))
8702 `(("r-biocgenerics" ,r-biocgenerics)
8703 ("r-biostrings" ,r-biostrings)
8704 ("r-bsgenome" ,r-bsgenome)
8705 ;; These two packages are suggested packages
8706 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8707 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8708 ("r-cowplot" ,r-cowplot)
8709 ("r-dplyr" ,r-dplyr)
8710 ("r-genomeinfodb" ,r-genomeinfodb)
8711 ("r-genomicranges" ,r-genomicranges)
8712 ("r-ggalluvial" ,r-ggalluvial)
8713 ("r-ggdendro" ,r-ggdendro)
8714 ("r-ggplot2" ,r-ggplot2)
8715 ("r-iranges" ,r-iranges)
8716 ("r-magrittr" ,r-magrittr)
8718 ("r-pracma" ,r-pracma)
8719 ("r-purrr" ,r-purrr)
8720 ("r-s4vectors" ,r-s4vectors)
8721 ("r-stringr" ,r-stringr)
8722 ("r-tibble" ,r-tibble)
8723 ("r-tidyr" ,r-tidyr)
8724 ("r-variantannotation" ,r-variantannotation)))
8725 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8726 (synopsis "Extract and visualize mutational patterns in genomic data")
8727 (description "This package provides an extensive toolset for the
8728 characterization and visualization of a wide range of mutational patterns
8729 in SNV base substitution data.")
8730 (license license:expat)))
8732 (define-public r-chipkernels
8733 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8736 (name "r-chipkernels")
8737 (version (string-append "1.1-" revision "." (string-take commit 9)))
8742 (url "https://github.com/ManuSetty/ChIPKernels")
8744 (file-name (string-append name "-" version))
8747 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8748 (build-system r-build-system)
8750 `(("r-iranges" ,r-iranges)
8751 ("r-xvector" ,r-xvector)
8752 ("r-biostrings" ,r-biostrings)
8753 ("r-bsgenome" ,r-bsgenome)
8754 ("r-gtools" ,r-gtools)
8755 ("r-genomicranges" ,r-genomicranges)
8756 ("r-sfsmisc" ,r-sfsmisc)
8757 ("r-kernlab" ,r-kernlab)
8758 ("r-s4vectors" ,r-s4vectors)
8759 ("r-biocgenerics" ,r-biocgenerics)))
8760 (home-page "https://github.com/ManuSetty/ChIPKernels")
8761 (synopsis "Build string kernels for DNA Sequence analysis")
8762 (description "ChIPKernels is an R package for building different string
8763 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8764 must be built and this dictionary can be used for determining kernels for DNA
8766 (license license:gpl2+))))
8768 (define-public r-seqgl
8776 (url "https://github.com/ManuSetty/SeqGL")
8778 (file-name (git-file-name name version))
8781 "1r6ywvhxl3ffv48lgj7sbd582mcc6dha3ksgc2qjlvjrnkbj3799"))))
8782 (build-system r-build-system)
8784 `(("r-biostrings" ,r-biostrings)
8785 ("r-chipkernels" ,r-chipkernels)
8786 ("r-genomicranges" ,r-genomicranges)
8787 ("r-spams" ,r-spams)
8788 ("r-wgcna" ,r-wgcna)
8789 ("r-fastcluster" ,r-fastcluster)))
8790 (home-page "https://github.com/ManuSetty/SeqGL")
8791 (synopsis "Group lasso for Dnase/ChIP-seq data")
8792 (description "SeqGL is a group lasso based algorithm to extract
8793 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8794 This package presents a method which uses group lasso to discriminate between
8795 bound and non bound genomic regions to accurately identify transcription
8796 factors bound at the specific regions.")
8797 (license license:gpl2+)))
8799 (define-public r-tximport
8805 (uri (bioconductor-uri "tximport" version))
8808 "1nxnlvl4iv2392xa72j0lzy2xnb3vrvyhfrdj9l54znwkrryyq34"))))
8809 (build-system r-build-system)
8811 `(("r-knitr" ,r-knitr)))
8812 (home-page "https://bioconductor.org/packages/tximport")
8813 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8815 "This package provides tools to import transcript-level abundance,
8816 estimated counts and transcript lengths, and to summarize them into matrices
8817 for use with downstream gene-level analysis packages. Average transcript
8818 length, weighted by sample-specific transcript abundance estimates, is
8819 provided as a matrix which can be used as an offset for different expression
8820 of gene-level counts.")
8821 (license license:gpl2+)))
8823 (define-public r-rhdf5filters
8825 (name "r-rhdf5filters")
8830 (uri (bioconductor-uri "rhdf5filters" version))
8833 "1jvnss44liapbc6hk93yg1gknv0ahd5x86dydqiwq9l65jd03psq"))))
8834 (properties `((upstream-name . "rhdf5filters")))
8835 (build-system r-build-system)
8837 `(("r-rhdf5lib" ,r-rhdf5lib)))
8841 `(("r-knitr" ,r-knitr)))
8842 (home-page "https://github.com/grimbough/rhdf5filters")
8843 (synopsis "HDF5 compression filters")
8845 "This package provides a collection of compression filters for use with
8847 (license license:bsd-2)))
8849 (define-public r-rhdf5
8855 (uri (bioconductor-uri "rhdf5" version))
8858 "0almr1vscrgj5g4dyrags131wia2pmdbdidlpskbgm44ha6hpmqi"))))
8859 (build-system r-build-system)
8862 (modify-phases %standard-phases
8863 (add-after 'unpack 'fix-linking
8865 (substitute* "src/Makevars"
8866 ;; This is to avoid having a plain directory on the list of
8867 ;; libraries to link.
8868 (("\\(RHDF5_LIBS\\)" match)
8869 (string-append match "/libhdf5.a")))
8872 `(("r-rhdf5filters" ,r-rhdf5filters)
8873 ("r-rhdf5lib" ,r-rhdf5lib)))
8875 `(("r-knitr" ,r-knitr)))
8876 (home-page "https://bioconductor.org/packages/rhdf5")
8877 (synopsis "HDF5 interface to R")
8879 "This R/Bioconductor package provides an interface between HDF5 and R.
8880 HDF5's main features are the ability to store and access very large and/or
8881 complex datasets and a wide variety of metadata on mass storage (disk) through
8882 a completely portable file format. The rhdf5 package is thus suited for the
8883 exchange of large and/or complex datasets between R and other software
8884 package, and for letting R applications work on datasets that are larger than
8885 the available RAM.")
8886 (license license:artistic2.0)))
8888 (define-public r-annotationfilter
8890 (name "r-annotationfilter")
8894 (uri (bioconductor-uri "AnnotationFilter" version))
8897 "0npk0laa2rc93rsh6yikj886zf2fl53a050j07fj9w67j0q0h3s9"))))
8899 `((upstream-name . "AnnotationFilter")))
8900 (build-system r-build-system)
8902 `(("r-genomicranges" ,r-genomicranges)
8903 ("r-lazyeval" ,r-lazyeval)))
8905 `(("r-knitr" ,r-knitr)))
8906 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8907 (synopsis "Facilities for filtering Bioconductor annotation resources")
8909 "This package provides classes and other infrastructure to implement
8910 filters for manipulating Bioconductor annotation resources. The filters are
8911 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8912 (license license:artistic2.0)))
8914 (define-public emboss
8920 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8921 (version-major+minor version) ".0/"
8922 "EMBOSS-" version ".tar.gz"))
8925 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8926 (build-system gnu-build-system)
8929 (list (string-append "--with-hpdf="
8930 (assoc-ref %build-inputs "libharu")))
8932 (modify-phases %standard-phases
8933 (add-after 'unpack 'fix-checks
8935 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8936 ;; and zlib, but assume that they are all found at the same
8938 (substitute* "configure.in"
8939 (("CHECK_PNGDRIVER")
8940 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8941 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8942 AM_CONDITIONAL(AMPNG, true)"))
8944 (add-after 'fix-checks 'disable-update-check
8946 ;; At build time there is no connection to the Internet, so
8947 ;; looking for updates will not work.
8948 (substitute* "Makefile.am"
8949 (("\\$\\(bindir\\)/embossupdate") ""))
8951 (add-after 'disable-update-check 'autogen
8952 (lambda _ (invoke "autoreconf" "-vif") #t)))))
8958 ("libharu" ,libharu)
8961 `(("autoconf" ,autoconf)
8962 ("automake" ,automake)
8963 ("libtool" ,libtool)
8964 ("pkg-config" ,pkg-config)))
8965 (home-page "http://emboss.sourceforge.net")
8966 (synopsis "Molecular biology analysis suite")
8967 (description "EMBOSS is the \"European Molecular Biology Open Software
8968 Suite\". EMBOSS is an analysis package specially developed for the needs of
8969 the molecular biology (e.g. EMBnet) user community. The software
8970 automatically copes with data in a variety of formats and even allows
8971 transparent retrieval of sequence data from the web. It also provides a
8972 number of libraries for the development of software in the field of molecular
8973 biology. EMBOSS also integrates a range of currently available packages and
8974 tools for sequence analysis into a seamless whole.")
8975 (license license:gpl2+)))
8978 (let ((revision "1")
8979 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8982 ;; The version is 2.13.0 even though no release archives have been
8983 ;; published as yet.
8984 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8988 (url "https://github.com/arq5x/bits")
8990 (file-name (string-append name "-" version "-checkout"))
8993 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8994 (build-system gnu-build-system)
8996 `(#:tests? #f ;no tests included
8998 (modify-phases %standard-phases
9000 (add-after 'unpack 'remove-cuda
9002 (substitute* "Makefile"
9004 (("(bits_test_intersections) \\\\" _ match) match))
9007 (lambda* (#:key outputs #:allow-other-keys)
9009 "bin" (string-append (assoc-ref outputs "out") "/bin"))
9014 (home-page "https://github.com/arq5x/bits")
9015 (synopsis "Implementation of binary interval search algorithm")
9016 (description "This package provides an implementation of the
9017 BITS (Binary Interval Search) algorithm, an approach to interval set
9018 intersection. It is especially suited for the comparison of diverse genomic
9019 datasets and the exploration of large datasets of genome
9020 intervals (e.g. genes, sequence alignments).")
9021 (license license:gpl2))))
9023 (define-public piranha
9024 ;; There is no release tarball for the latest version. The latest commit is
9025 ;; older than one year at the time of this writing.
9026 (let ((revision "1")
9027 (commit "0466d364b71117d01e4471b74c514436cc281233"))
9030 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
9034 (url "https://github.com/smithlabcode/piranha")
9036 (file-name (git-file-name name version))
9039 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
9040 (build-system gnu-build-system)
9042 `(#:test-target "test"
9044 (modify-phases %standard-phases
9045 (add-after 'unpack 'copy-smithlab-cpp
9046 (lambda* (#:key inputs #:allow-other-keys)
9047 (for-each (lambda (file)
9048 (install-file file "./src/smithlab_cpp/"))
9049 (find-files (assoc-ref inputs "smithlab-cpp")))
9051 (add-after 'install 'install-to-store
9052 (lambda* (#:key outputs #:allow-other-keys)
9053 (let* ((out (assoc-ref outputs "out"))
9054 (bin (string-append out "/bin")))
9055 (for-each (lambda (file)
9056 (install-file file bin))
9057 (find-files "bin" ".*")))
9060 (list (string-append "--with-bam_tools_headers="
9061 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
9062 (string-append "--with-bam_tools_library="
9063 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
9065 `(("bamtools" ,bamtools)
9066 ("samtools" ,samtools-0.1)
9069 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
9073 (url "https://github.com/smithlabcode/smithlab_cpp")
9075 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
9078 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
9080 `(("python" ,python-2)))
9081 (home-page "https://github.com/smithlabcode/piranha")
9082 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
9084 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
9085 RIP-seq experiments. It takes input in BED or BAM format and identifies
9086 regions of statistically significant read enrichment. Additional covariates
9087 may optionally be provided to further inform the peak-calling process.")
9088 (license license:gpl3+))))
9096 (uri (pypi-uri "PePr" version))
9099 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
9100 (build-system python-build-system)
9102 `(#:python ,python-2 ; python2 only
9103 #:tests? #f)) ; no tests included
9105 `(("python2-numpy" ,python2-numpy)
9106 ("python2-scipy" ,python2-scipy)
9107 ("python2-pysam" ,python2-pysam)))
9108 (home-page "https://github.com/shawnzhangyx/PePr")
9109 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
9111 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
9112 that is primarily designed for data with biological replicates. It uses a
9113 negative binomial distribution to model the read counts among the samples in
9114 the same group, and look for consistent differences between ChIP and control
9115 group or two ChIP groups run under different conditions.")
9116 (license license:gpl3+)))
9118 (define-public filevercmp
9119 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
9122 (version (string-append "0-1." (string-take commit 7)))
9126 (url "https://github.com/ekg/filevercmp")
9128 (file-name (git-file-name name commit))
9131 "1j9vxsy0y050v59h0q1d6501fcw1kjvj0d18l1xk2zyg0jzj247c"))))
9132 (build-system gnu-build-system)
9134 `(#:tests? #f ; There are no tests to run.
9136 (modify-phases %standard-phases
9137 (delete 'configure) ; There is no configure phase.
9139 (lambda* (#:key outputs #:allow-other-keys)
9140 (let ((out (assoc-ref outputs "out")))
9141 (install-file "filevercmp" (string-append out "/bin"))
9142 (install-file "filevercmp.h" (string-append out "/include"))
9144 (home-page "https://github.com/ekg/filevercmp")
9145 (synopsis "This program compares version strings")
9146 (description "This program compares version strings. It intends to be a
9147 replacement for strverscmp.")
9148 (license license:gpl3+))))
9150 (define-public multiqc
9157 (uri (pypi-uri "multiqc" version))
9160 "02iihfl0w0hpnr4pa0sbd1y9qxrg3ycyhjp5lidkcrqh1lmzs3zy"))))
9161 (build-system python-build-system)
9163 `(("python-jinja2" ,python-jinja2)
9164 ("python-simplejson" ,python-simplejson)
9165 ("python-pyyaml" ,python-pyyaml)
9166 ("python-click" ,python-click)
9167 ("python-spectra" ,python-spectra)
9168 ("python-requests" ,python-requests)
9169 ("python-markdown" ,python-markdown)
9170 ("python-lzstring" ,python-lzstring)
9171 ("python-matplotlib" ,python-matplotlib)
9172 ("python-numpy" ,python-numpy)
9173 ;; MultQC checks for the presence of nose at runtime.
9174 ("python-nose" ,python-nose)))
9177 (modify-phases %standard-phases
9178 (add-after 'unpack 'relax-requirements
9180 (substitute* "setup.py"
9181 ;; MultiQC 1.5 ‘requires’ a version of python-matplotlib older
9182 ;; than the one in Guix, but should work fine with 2.2.2.
9183 ;; See <https://github.com/ewels/MultiQC/issues/725> and
9184 ;; <https://github.com/ewels/MultiQC/issues/732> for details.
9185 (("['\"]matplotlib.*?['\"]")
9188 (home-page "https://multiqc.info")
9189 (synopsis "Aggregate bioinformatics analysis reports")
9191 "MultiQC is a tool to aggregate bioinformatics results across many
9192 samples into a single report. It contains modules for a large number of
9193 common bioinformatics tools.")
9194 (license license:gpl3+)))
9196 (define-public variant-tools
9198 (name "variant-tools")
9204 (url "https://github.com/vatlab/varianttools")
9205 ;; There is no tag corresponding to version 3.1.2
9206 (commit "813ae4a90d25b69abc8a40f4f70441fe09015249")))
9207 (file-name (git-file-name name version))
9210 "12ibdmksj7icyqhks4xyvd61bygk4pjmxn618kp6vgk1af01y34g"))))
9211 (build-system python-build-system)
9214 ("c-blosc" ,c-blosc)
9217 ("hdf5-blosc" ,hdf5-blosc)
9218 ("python-cython" ,python-cython)
9221 `(("python-numpy" ,python-numpy)
9222 ("python-pycurl" ,python-pycurl)
9223 ("python-pyzmq" ,python-pyzmq)
9224 ("python-scipy" ,python-scipy)
9225 ("python-tables" ,python-tables)))
9226 (home-page "https://vatlab.github.io/vat-docs/")
9227 (synopsis "Analyze genetic variants from Next-Gen sequencing studies")
9229 "Variant tools is a tool for the manipulation, annotation,
9230 selection, simulation, and analysis of variants in the context of next-gen
9231 sequencing analysis. Unlike some other tools used for next-gen sequencing
9232 analysis, variant tools is project based and provides a whole set of tools to
9233 manipulate and analyze genetic variants.")
9234 (license license:gpl3+)))
9236 (define-public r-chipseq
9243 (uri (bioconductor-uri "chipseq" version))
9246 "12pzq24aarvgxfmhcad0l5g951xqdvvi7bspgbsvlvmfkqd74j2v"))))
9247 (build-system r-build-system)
9249 `(("r-biocgenerics" ,r-biocgenerics)
9250 ("r-genomicranges" ,r-genomicranges)
9251 ("r-iranges" ,r-iranges)
9252 ("r-lattice" ,r-lattice)
9253 ("r-s4vectors" ,r-s4vectors)
9254 ("r-shortread" ,r-shortread)))
9255 (home-page "https://bioconductor.org/packages/chipseq")
9256 (synopsis "Package for analyzing ChIPseq data")
9258 "This package provides tools for processing short read data from ChIPseq
9260 (license license:artistic2.0)))
9262 (define-public r-copyhelper
9264 (name "r-copyhelper")
9269 (uri (string-append "https://bioconductor.org/packages/release/"
9270 "data/experiment/src/contrib/CopyhelpeR_"
9274 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
9275 (properties `((upstream-name . "CopyhelpeR")))
9276 (build-system r-build-system)
9277 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
9278 (synopsis "Helper files for CopywriteR")
9280 "This package contains the helper files that are required to run the
9281 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
9282 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
9283 mm10. In addition, it contains a blacklist filter to remove regions that
9284 display copy number variation. Files are stored as GRanges objects from the
9285 GenomicRanges Bioconductor package.")
9286 (license license:gpl2)))
9288 (define-public r-copywriter
9290 (name "r-copywriter")
9295 (uri (bioconductor-uri "CopywriteR" version))
9298 "060p6l6l8i6b15hyyz5v5kkxih3h4wcciixii51m9mn82z23xr2f"))))
9299 (properties `((upstream-name . "CopywriteR")))
9300 (build-system r-build-system)
9302 `(("r-biocparallel" ,r-biocparallel)
9303 ("r-chipseq" ,r-chipseq)
9304 ("r-copyhelper" ,r-copyhelper)
9305 ("r-data-table" ,r-data-table)
9306 ("r-dnacopy" ,r-dnacopy)
9307 ("r-futile-logger" ,r-futile-logger)
9308 ("r-genomeinfodb" ,r-genomeinfodb)
9309 ("r-genomicalignments" ,r-genomicalignments)
9310 ("r-genomicranges" ,r-genomicranges)
9311 ("r-gtools" ,r-gtools)
9312 ("r-iranges" ,r-iranges)
9313 ("r-matrixstats" ,r-matrixstats)
9314 ("r-rsamtools" ,r-rsamtools)
9315 ("r-s4vectors" ,r-s4vectors)))
9316 (home-page "https://github.com/PeeperLab/CopywriteR")
9317 (synopsis "Copy number information from targeted sequencing")
9319 "CopywriteR extracts DNA copy number information from targeted sequencing
9320 by utilizing off-target reads. It allows for extracting uniformly distributed
9321 copy number information, can be used without reference, and can be applied to
9322 sequencing data obtained from various techniques including chromatin
9323 immunoprecipitation and target enrichment on small gene panels. Thereby,
9324 CopywriteR constitutes a widely applicable alternative to available copy
9325 number detection tools.")
9326 (license license:gpl2)))
9328 (define-public r-methylkit
9330 (name "r-methylkit")
9334 (uri (bioconductor-uri "methylKit" version))
9337 "1c9b11gfh3cc37iwym9rgsba3mh2xkp78a1gvnjqhzlkiz667mn3"))))
9338 (properties `((upstream-name . "methylKit")))
9339 (build-system r-build-system)
9341 `(("r-data-table" ,r-data-table)
9342 ("r-emdbook" ,r-emdbook)
9343 ("r-fastseg" ,r-fastseg)
9344 ("r-genomeinfodb" ,r-genomeinfodb)
9345 ("r-genomicranges" ,r-genomicranges)
9346 ("r-gtools" ,r-gtools)
9347 ("r-iranges" ,r-iranges)
9348 ("r-kernsmooth" ,r-kernsmooth)
9349 ("r-limma" ,r-limma)
9350 ("r-mclust" ,r-mclust)
9352 ("r-qvalue" ,r-qvalue)
9353 ("r-r-utils" ,r-r-utils)
9355 ("r-rhtslib" ,r-rhtslib)
9356 ("r-rsamtools" ,r-rsamtools)
9357 ("r-rtracklayer" ,r-rtracklayer)
9358 ("r-s4vectors" ,r-s4vectors)
9359 ("r-zlibbioc" ,r-zlibbioc)))
9361 `(("r-knitr" ,r-knitr))) ; for vignettes
9362 (home-page "https://github.com/al2na/methylKit")
9364 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9366 "MethylKit is an R package for DNA methylation analysis and annotation
9367 from high-throughput bisulfite sequencing. The package is designed to deal
9368 with sequencing data from @dfn{Reduced representation bisulfite
9369 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9370 genome bisulfite sequencing. It also has functions to analyze base-pair
9371 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9373 (license license:artistic2.0)))
9375 (define-public r-sva
9382 (uri (bioconductor-uri "sva" version))
9385 "1hpzzg3qrgkd8kwg1m5gq94cikjgk9j4l1wk58fxl49s6fmd13zy"))))
9386 (build-system r-build-system)
9388 `(("r-edger" ,r-edger)
9389 ("r-genefilter" ,r-genefilter)
9391 ("r-biocparallel" ,r-biocparallel)
9392 ("r-matrixstats" ,r-matrixstats)
9393 ("r-limma" ,r-limma)))
9394 (home-page "https://bioconductor.org/packages/sva")
9395 (synopsis "Surrogate variable analysis")
9397 "This package contains functions for removing batch effects and other
9398 unwanted variation in high-throughput experiment. It also contains functions
9399 for identifying and building surrogate variables for high-dimensional data
9400 sets. Surrogate variables are covariates constructed directly from
9401 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9402 imaging data that can be used in subsequent analyses to adjust for unknown,
9403 unmodeled, or latent sources of noise.")
9404 (license license:artistic2.0)))
9406 (define-public r-raremetals2
9408 (name "r-raremetals2")
9413 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9414 "b/b7/RareMETALS2_" version ".tar.gz"))
9417 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9418 (properties `((upstream-name . "RareMETALS2")))
9419 (build-system r-build-system)
9421 `(("r-seqminer" ,r-seqminer)
9422 ("r-mvtnorm" ,r-mvtnorm)
9424 ("r-compquadform" ,r-compquadform)
9425 ("r-getopt" ,r-getopt)))
9426 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9427 (synopsis "Analyze gene-level association tests for binary trait")
9429 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9430 It was designed to meta-analyze gene-level association tests for binary trait.
9431 While rareMETALS offers a near-complete solution for meta-analysis of
9432 gene-level tests for quantitative trait, it does not offer the optimal
9433 solution for binary trait. The package rareMETALS2 offers improved features
9434 for analyzing gene-level association tests in meta-analyses for binary
9436 (license license:gpl3)))
9438 (define-public r-protgenerics
9440 (name "r-protgenerics")
9445 (uri (bioconductor-uri "ProtGenerics" version))
9448 "0yihxphgkshvfv1sn67wc4zvr2zlzws2j7ki3zabm6vyfkfdkfiz"))))
9449 (properties `((upstream-name . "ProtGenerics")))
9450 (build-system r-build-system)
9451 (home-page "https://github.com/lgatto/ProtGenerics")
9452 (synopsis "S4 generic functions for proteomics infrastructure")
9454 "This package provides S4 generic functions needed by Bioconductor
9455 proteomics packages.")
9456 (license license:artistic2.0)))
9458 (define-public r-mzr
9465 (uri (bioconductor-uri "mzR" version))
9468 "0ik0yrjhvk8r5pm990chn2aadp0gqzzkkm0027682ky34xp142sg"))
9469 (modules '((guix build utils)))
9472 (delete-file-recursively "src/boost")
9474 (properties `((upstream-name . "mzR")))
9475 (build-system r-build-system)
9478 (modify-phases %standard-phases
9479 (add-after 'unpack 'use-system-boost
9481 (substitute* "src/Makevars"
9482 (("\\./boost/libs.*") "")
9483 ;; This is to avoid having a plain directory on the list of
9484 ;; libraries to link.
9485 (("\\(RHDF5_LIBS\\)" match)
9486 (string-append match "/libhdf5.a"))
9487 (("PKG_LIBS=") "PKG_LIBS=$(BOOST_LIBS) ")
9488 (("\\ARCH_OBJS=" line)
9490 "\nBOOST_LIBS=-lboost_system -lboost_regex \
9491 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9494 `(;; Our default boost package won't work here, unfortunately, even with
9495 ;; mzR version 2.24.1.
9496 ("boost" ,boost-for-mysql) ; use this instead of the bundled boost sources
9499 `(("r-biobase" ,r-biobase)
9500 ("r-biocgenerics" ,r-biocgenerics)
9501 ("r-ncdf4" ,r-ncdf4)
9502 ("r-protgenerics" ,r-protgenerics)
9504 ("r-rhdf5lib" ,r-rhdf5lib)
9505 ("r-zlibbioc" ,r-zlibbioc)))
9507 `(("r-knitr" ,r-knitr)))
9508 (home-page "https://github.com/sneumann/mzR/")
9509 (synopsis "Parser for mass spectrometry data files")
9511 "The mzR package provides a unified API to the common file formats and
9512 parsers available for mass spectrometry data. It comes with a wrapper for the
9513 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9514 The package contains the original code written by the ISB, and a subset of the
9515 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9516 previously been used in XCMS.")
9517 (license license:artistic2.0)))
9519 (define-public r-affyio
9526 (uri (bioconductor-uri "affyio" version))
9529 "14xnzrxrvgxgixjhq5a9fdgcmrxam2j74hwidkc9if92ffv6s83h"))))
9530 (build-system r-build-system)
9532 `(("r-zlibbioc" ,r-zlibbioc)))
9535 (home-page "https://github.com/bmbolstad/affyio")
9536 (synopsis "Tools for parsing Affymetrix data files")
9538 "This package provides routines for parsing Affymetrix data files based
9539 upon file format information. The primary focus is on accessing the CEL and
9541 (license license:lgpl2.0+)))
9543 (define-public r-affy
9550 (uri (bioconductor-uri "affy" version))
9553 "0ywz548cbzk2k1njnxhlk5ydzvz2dk78ka8kx53gwrmdc4sc2b06"))))
9554 (build-system r-build-system)
9556 `(("r-affyio" ,r-affyio)
9557 ("r-biobase" ,r-biobase)
9558 ("r-biocgenerics" ,r-biocgenerics)
9559 ("r-biocmanager" ,r-biocmanager)
9560 ("r-preprocesscore" ,r-preprocesscore)
9561 ("r-zlibbioc" ,r-zlibbioc)))
9564 (home-page "https://bioconductor.org/packages/affy")
9565 (synopsis "Methods for affymetrix oligonucleotide arrays")
9567 "This package contains functions for exploratory oligonucleotide array
9569 (license license:lgpl2.0+)))
9571 (define-public r-vsn
9578 (uri (bioconductor-uri "vsn" version))
9581 "0dfrfflidpnphwyqzmmfiz9blfqv6qa09xlwgfabhpfsf3ml2rlb"))))
9582 (build-system r-build-system)
9584 `(("r-affy" ,r-affy)
9585 ("r-biobase" ,r-biobase)
9586 ("r-ggplot2" ,r-ggplot2)
9587 ("r-lattice" ,r-lattice)
9588 ("r-limma" ,r-limma)))
9590 `(("r-knitr" ,r-knitr))) ; for vignettes
9591 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9592 (synopsis "Variance stabilization and calibration for microarray data")
9594 "The package implements a method for normalising microarray intensities,
9595 and works for single- and multiple-color arrays. It can also be used for data
9596 from other technologies, as long as they have similar format. The method uses
9597 a robust variant of the maximum-likelihood estimator for an
9598 additive-multiplicative error model and affine calibration. The model
9599 incorporates data calibration step (a.k.a. normalization), a model for the
9600 dependence of the variance on the mean intensity and a variance stabilizing
9601 data transformation. Differences between transformed intensities are
9602 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9603 their variance is independent of the mean, and they are usually more sensitive
9604 and specific in detecting differential transcription.")
9605 (license license:artistic2.0)))
9607 (define-public r-mzid
9614 (uri (bioconductor-uri "mzID" version))
9617 "0s7d6cz1li7v3ni6n6hrdspl93yiyr283kmbbd3hhkfgzgx6kpq2"))))
9618 (properties `((upstream-name . "mzID")))
9619 (build-system r-build-system)
9621 `(("r-doparallel" ,r-doparallel)
9622 ("r-foreach" ,r-foreach)
9623 ("r-iterators" ,r-iterators)
9625 ("r-protgenerics" ,r-protgenerics)
9628 `(("r-knitr" ,r-knitr)))
9629 (home-page "https://bioconductor.org/packages/mzID")
9630 (synopsis "Parser for mzIdentML files")
9632 "This package provides a parser for mzIdentML files implemented using the
9633 XML package. The parser tries to be general and able to handle all types of
9634 mzIdentML files with the drawback of having less pretty output than a vendor
9636 (license license:gpl2+)))
9638 (define-public r-pcamethods
9640 (name "r-pcamethods")
9645 (uri (bioconductor-uri "pcaMethods" version))
9648 "04xb4vjky6hq58l30i1iq9rv5gzjdxnidjxpnzg7pvg67vz8pgf0"))))
9649 (properties `((upstream-name . "pcaMethods")))
9650 (build-system r-build-system)
9652 `(("r-biobase" ,r-biobase)
9653 ("r-biocgenerics" ,r-biocgenerics)
9655 ("r-rcpp" ,r-rcpp)))
9656 (home-page "https://github.com/hredestig/pcamethods")
9657 (synopsis "Collection of PCA methods")
9659 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9660 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9661 for missing value estimation is included for comparison. BPCA, PPCA and
9662 NipalsPCA may be used to perform PCA on incomplete data as well as for
9663 accurate missing value estimation. A set of methods for printing and plotting
9664 the results is also provided. All PCA methods make use of the same data
9665 structure (pcaRes) to provide a common interface to the PCA results.")
9666 (license license:gpl3+)))
9668 (define-public r-msnbase
9675 (uri (bioconductor-uri "MSnbase" version))
9678 "0hxzs9zzljywqxr7q388hshpy1pdryhl0zkwffqbxpf5pcf92d3h"))))
9679 (properties `((upstream-name . "MSnbase")))
9680 (build-system r-build-system)
9682 `(("r-affy" ,r-affy)
9683 ("r-biobase" ,r-biobase)
9684 ("r-biocgenerics" ,r-biocgenerics)
9685 ("r-biocparallel" ,r-biocparallel)
9686 ("r-digest" ,r-digest)
9687 ("r-ggplot2" ,r-ggplot2)
9688 ("r-impute" ,r-impute)
9689 ("r-iranges" ,r-iranges)
9690 ("r-lattice" ,r-lattice)
9691 ("r-maldiquant" ,r-maldiquant)
9695 ("r-pcamethods" ,r-pcamethods)
9697 ("r-preprocesscore" ,r-preprocesscore)
9698 ("r-protgenerics" ,r-protgenerics)
9700 ("r-s4vectors" ,r-s4vectors)
9701 ("r-scales" ,r-scales)
9705 `(("r-knitr" ,r-knitr)))
9706 (home-page "https://github.com/lgatto/MSnbase")
9707 (synopsis "Base functions and classes for MS-based proteomics")
9709 "This package provides basic plotting, data manipulation and processing
9710 of mass spectrometry based proteomics data.")
9711 (license license:artistic2.0)))
9713 (define-public r-msnid
9720 (uri (bioconductor-uri "MSnID" version))
9723 "05bncy7lw2a3h8xgnavjiz56pc6mk8q7l6qdd81197nawxs3j02d"))))
9724 (properties `((upstream-name . "MSnID")))
9725 (build-system r-build-system)
9727 `(("r-annotationdbi" ,r-annotationdbi)
9728 ("r-annotationhub" ,r-annotationhub)
9729 ("r-biobase" ,r-biobase)
9730 ("r-biocgenerics" ,r-biocgenerics)
9731 ("r-biocstyle" ,r-biocstyle)
9732 ("r-biostrings" ,r-biostrings)
9733 ("r-data-table" ,r-data-table)
9734 ("r-doparallel" ,r-doparallel)
9735 ("r-dplyr" ,r-dplyr)
9736 ("r-foreach" ,r-foreach)
9737 ("r-ggplot2" ,r-ggplot2)
9738 ("r-iterators" ,r-iterators)
9739 ("r-msnbase" ,r-msnbase)
9740 ("r-msmstests" ,r-msmstests)
9743 ("r-protgenerics" ,r-protgenerics)
9744 ("r-purrr" ,r-purrr)
9745 ("r-r-cache" ,r-r-cache)
9747 ("r-reshape2" ,r-reshape2)
9748 ("r-rlang" ,r-rlang)
9749 ("r-runit" ,r-runit)
9750 ("r-stringr" ,r-stringr)
9751 ("r-tibble" ,r-tibble)
9752 ("r-xtable" ,r-xtable)))
9753 (home-page "https://bioconductor.org/packages/MSnID")
9754 (synopsis "Utilities for LC-MSn proteomics identifications")
9756 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9757 from mzIdentML (leveraging the mzID package) or text files. After collating
9758 the search results from multiple datasets it assesses their identification
9759 quality and optimize filtering criteria to achieve the maximum number of
9760 identifications while not exceeding a specified false discovery rate. It also
9761 contains a number of utilities to explore the MS/MS results and assess missed
9762 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9763 (license license:artistic2.0)))
9765 (define-public r-aroma-light
9767 (name "r-aroma-light")
9772 (uri (bioconductor-uri "aroma.light" version))
9775 "0pi37rlfqh24p9wd7l1xb3f7c7938xdscgcc5agp8c9qhajq25a0"))))
9776 (properties `((upstream-name . "aroma.light")))
9777 (build-system r-build-system)
9779 `(("r-matrixstats" ,r-matrixstats)
9780 ("r-r-methodss3" ,r-r-methodss3)
9782 ("r-r-utils" ,r-r-utils)))
9783 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9784 (synopsis "Methods for normalization and visualization of microarray data")
9786 "This package provides methods for microarray analysis that take basic
9787 data types such as matrices and lists of vectors. These methods can be used
9788 standalone, be utilized in other packages, or be wrapped up in higher-level
9790 (license license:gpl2+)))
9792 (define-public r-deseq
9799 (uri (bioconductor-uri "DESeq" version))
9802 "047hph5aqmjnz1aqprziw0smdn5lf96hmwpnvqrxv1j2yfvcf3h1"))))
9803 (properties `((upstream-name . "DESeq")))
9804 (build-system r-build-system)
9806 `(("r-biobase" ,r-biobase)
9807 ("r-biocgenerics" ,r-biocgenerics)
9808 ("r-genefilter" ,r-genefilter)
9809 ("r-geneplotter" ,r-geneplotter)
9810 ("r-lattice" ,r-lattice)
9811 ("r-locfit" ,r-locfit)
9813 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9814 (home-page "https://www-huber.embl.de/users/anders/DESeq/")
9815 (synopsis "Differential gene expression analysis")
9817 "This package provides tools for estimating variance-mean dependence in
9818 count data from high-throughput genetic sequencing assays and for testing for
9819 differential expression based on a model using the negative binomial
9821 (license license:gpl3+)))
9823 (define-public r-edaseq
9830 (uri (bioconductor-uri "EDASeq" version))
9833 "0fznj7lsgkss1svv4rq8g87s1gmnbd7hccim41dv1c2w2nl0n2ip"))))
9834 (properties `((upstream-name . "EDASeq")))
9835 (build-system r-build-system)
9837 `(("r-annotationdbi" ,r-annotationdbi)
9838 ("r-aroma-light" ,r-aroma-light)
9839 ("r-biobase" ,r-biobase)
9840 ("r-biocgenerics" ,r-biocgenerics)
9841 ("r-biocmanager" ,r-biocmanager)
9842 ("r-biomart" ,r-biomart)
9843 ("r-biostrings" ,r-biostrings)
9844 ("r-genomicfeatures" ,r-genomicfeatures)
9845 ("r-genomicranges" ,r-genomicranges)
9846 ("r-iranges" ,r-iranges)
9847 ("r-rsamtools" ,r-rsamtools)
9848 ("r-shortread" ,r-shortread)))
9850 `(("r-knitr" ,r-knitr)))
9851 (home-page "https://github.com/drisso/EDASeq")
9852 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9854 "This package provides support for numerical and graphical summaries of
9855 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9856 adjust for GC-content effect (or other gene-level effects) on read counts:
9857 loess robust local regression, global-scaling, and full-quantile
9858 normalization. Between-lane normalization procedures to adjust for
9859 distributional differences between lanes (e.g., sequencing depth):
9860 global-scaling and full-quantile normalization.")
9861 (license license:artistic2.0)))
9863 (define-public r-interactivedisplaybase
9865 (name "r-interactivedisplaybase")
9870 (uri (bioconductor-uri "interactiveDisplayBase" version))
9873 "08id2hkx4ssxj34dildx00a4j3z0nv171b7b0wl6xjks7wk6lv01"))))
9875 `((upstream-name . "interactiveDisplayBase")))
9876 (build-system r-build-system)
9878 `(("r-biocgenerics" ,r-biocgenerics)
9880 ("r-shiny" ,r-shiny)))
9882 `(("r-knitr" ,r-knitr)))
9883 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9884 (synopsis "Base package for web displays of Bioconductor objects")
9886 "This package contains the basic methods needed to generate interactive
9887 Shiny-based display methods for Bioconductor objects.")
9888 (license license:artistic2.0)))
9890 (define-public r-annotationhub
9892 (name "r-annotationhub")
9897 (uri (bioconductor-uri "AnnotationHub" version))
9900 "1950x654ffqx53b154kbph808zdh2xm5vmj9vzmc5nxc28fi2z5g"))))
9901 (properties `((upstream-name . "AnnotationHub")))
9902 (build-system r-build-system)
9904 `(("r-annotationdbi" ,r-annotationdbi)
9905 ("r-biocfilecache" ,r-biocfilecache)
9906 ("r-biocgenerics" ,r-biocgenerics)
9907 ("r-biocmanager" ,r-biocmanager)
9908 ("r-biocversion" ,r-biocversion)
9910 ("r-dplyr" ,r-dplyr)
9912 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9913 ("r-rappdirs" ,r-rappdirs)
9914 ("r-rsqlite" ,r-rsqlite)
9915 ("r-s4vectors" ,r-s4vectors)
9916 ("r-yaml" ,r-yaml)))
9918 `(("r-knitr" ,r-knitr)))
9919 (home-page "https://bioconductor.org/packages/AnnotationHub")
9920 (synopsis "Client to access AnnotationHub resources")
9922 "This package provides a client for the Bioconductor AnnotationHub web
9923 resource. The AnnotationHub web resource provides a central location where
9924 genomic files (e.g. VCF, bed, wig) and other resources from standard
9925 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9926 metadata about each resource, e.g., a textual description, tags, and date of
9927 modification. The client creates and manages a local cache of files retrieved
9928 by the user, helping with quick and reproducible access.")
9929 (license license:artistic2.0)))
9931 (define-public r-fastseg
9938 (uri (bioconductor-uri "fastseg" version))
9941 "1ln6w93ag4wanp0nrm0pqngbfc88w95zq2kcj583hbxy885dkg4f"))))
9942 (build-system r-build-system)
9944 `(("r-biobase" ,r-biobase)
9945 ("r-biocgenerics" ,r-biocgenerics)
9946 ("r-genomicranges" ,r-genomicranges)
9947 ("r-iranges" ,r-iranges)
9948 ("r-s4vectors" ,r-s4vectors)))
9949 (home-page "https://www.bioinf.jku.at/software/fastseg/index.html")
9950 (synopsis "Fast segmentation algorithm for genetic sequencing data")
9952 "Fastseg implements a very fast and efficient segmentation algorithm.
9953 It can segment data from DNA microarrays and data from next generation
9954 sequencing for example to detect copy number segments. Further it can segment
9955 data from RNA microarrays like tiling arrays to identify transcripts. Most
9956 generally, it can segment data given as a matrix or as a vector. Various data
9957 formats can be used as input to fastseg like expression set objects for
9958 microarrays or GRanges for sequencing data.")
9959 (license license:lgpl2.0+)))
9961 (define-public r-keggrest
9968 (uri (bioconductor-uri "KEGGREST" version))
9971 "0k9z85xf9la2y98xqmdmjb8mci9fh2fdybkl77x1yl26hyalip0s"))))
9972 (properties `((upstream-name . "KEGGREST")))
9973 (build-system r-build-system)
9975 `(("r-biostrings" ,r-biostrings)
9979 `(("r-knitr" ,r-knitr)))
9980 (home-page "https://bioconductor.org/packages/KEGGREST")
9981 (synopsis "Client-side REST access to KEGG")
9983 "This package provides a package that provides a client interface to the
9984 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
9985 (license license:artistic2.0)))
9987 (define-public r-gage
9994 (uri (bioconductor-uri "gage" version))
9997 "1iawa03dy4bl333my69d4sk7d74cjzfg5dpcxga6q5dglan4sp8r"))))
9998 (build-system r-build-system)
10000 `(("r-annotationdbi" ,r-annotationdbi)
10001 ("r-go-db" ,r-go-db)
10002 ("r-graph" ,r-graph)
10003 ("r-keggrest" ,r-keggrest)))
10004 (home-page (string-append "https://bmcbioinformatics.biomedcentral.com/"
10005 "articles/10.1186/1471-2105-10-161"))
10006 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
10008 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
10009 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
10010 data attributes including sample sizes, experimental designs, assay platforms,
10011 and other types of heterogeneity. The gage package provides functions for
10012 basic GAGE analysis, result processing and presentation. In addition, it
10013 provides demo microarray data and commonly used gene set data based on KEGG
10014 pathways and GO terms. These functions and data are also useful for gene set
10015 analysis using other methods.")
10016 (license license:gpl2+)))
10018 (define-public r-genomicfiles
10020 (name "r-genomicfiles")
10025 (uri (bioconductor-uri "GenomicFiles" version))
10028 "0awnf0m1pz7cw9wvh9cfxz9k7xm6wnvjm7xbxf139lrhd4nlyqjz"))))
10029 (properties `((upstream-name . "GenomicFiles")))
10030 (build-system r-build-system)
10032 `(("r-biocgenerics" ,r-biocgenerics)
10033 ("r-biocparallel" ,r-biocparallel)
10034 ("r-genomeinfodb" ,r-genomeinfodb)
10035 ("r-genomicalignments" ,r-genomicalignments)
10036 ("r-genomicranges" ,r-genomicranges)
10037 ("r-iranges" ,r-iranges)
10038 ("r-matrixgenerics" ,r-matrixgenerics)
10039 ("r-rsamtools" ,r-rsamtools)
10040 ("r-rtracklayer" ,r-rtracklayer)
10041 ("r-s4vectors" ,r-s4vectors)
10042 ("r-summarizedexperiment" ,r-summarizedexperiment)
10043 ("r-variantannotation" ,r-variantannotation)))
10044 (home-page "https://bioconductor.org/packages/GenomicFiles")
10045 (synopsis "Distributed computing by file or by range")
10047 "This package provides infrastructure for parallel computations
10048 distributed by file or by range. User defined mapper and reducer functions
10049 provide added flexibility for data combination and manipulation.")
10050 (license license:artistic2.0)))
10052 (define-public r-complexheatmap
10054 (name "r-complexheatmap")
10059 (uri (bioconductor-uri "ComplexHeatmap" version))
10062 "1nx1xxpq8zrvi990v9fmvx3msl85pdz5dp1gp6m78q6i4s2alg5x"))))
10064 `((upstream-name . "ComplexHeatmap")))
10065 (build-system r-build-system)
10067 `(("r-cairo" ,r-cairo)
10068 ("r-circlize" ,r-circlize)
10070 ("r-colorspace" ,r-colorspace)
10071 ("r-digest" ,r-digest)
10072 ("r-getoptlong" ,r-getoptlong)
10073 ("r-globaloptions" ,r-globaloptions)
10074 ("r-iranges" ,r-iranges)
10075 ("r-matrixstats" ,r-matrixstats)
10077 ("r-rcolorbrewer" ,r-rcolorbrewer)
10078 ("r-s4vectors" ,r-s4vectors)))
10080 `(("r-knitr" ,r-knitr)))
10082 "https://github.com/jokergoo/ComplexHeatmap")
10083 (synopsis "Making Complex Heatmaps")
10085 "Complex heatmaps are efficient to visualize associations between
10086 different sources of data sets and reveal potential structures. This package
10087 provides a highly flexible way to arrange multiple heatmaps and supports
10088 self-defined annotation graphics.")
10089 (license license:gpl2+)))
10091 (define-public r-dirichletmultinomial
10093 (name "r-dirichletmultinomial")
10098 (uri (bioconductor-uri "DirichletMultinomial" version))
10101 "098zql6ryd1b0gkq4cjybblyh0x8xidxxfygqq5a5x9asl8y4vsk"))))
10103 `((upstream-name . "DirichletMultinomial")))
10104 (build-system r-build-system)
10108 `(("r-biocgenerics" ,r-biocgenerics)
10109 ("r-iranges" ,r-iranges)
10110 ("r-s4vectors" ,r-s4vectors)))
10111 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
10112 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
10114 "Dirichlet-multinomial mixture models can be used to describe variability
10115 in microbial metagenomic data. This package is an interface to code
10116 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
10118 (license license:lgpl3)))
10120 (define-public r-ensembldb
10122 (name "r-ensembldb")
10127 (uri (bioconductor-uri "ensembldb" version))
10130 "04il99gcrqzakvc0bxchdp9gghkn1sp9lpiian0iz4y7r67z3wpy"))))
10131 (build-system r-build-system)
10133 `(("r-annotationdbi" ,r-annotationdbi)
10134 ("r-annotationfilter" ,r-annotationfilter)
10135 ("r-biobase" ,r-biobase)
10136 ("r-biocgenerics" ,r-biocgenerics)
10137 ("r-biostrings" ,r-biostrings)
10140 ("r-genomeinfodb" ,r-genomeinfodb)
10141 ("r-genomicfeatures" ,r-genomicfeatures)
10142 ("r-genomicranges" ,r-genomicranges)
10143 ("r-iranges" ,r-iranges)
10144 ("r-protgenerics" ,r-protgenerics)
10145 ("r-rsamtools" ,r-rsamtools)
10146 ("r-rsqlite" ,r-rsqlite)
10147 ("r-rtracklayer" ,r-rtracklayer)
10148 ("r-s4vectors" ,r-s4vectors)))
10150 `(("r-knitr" ,r-knitr)))
10151 (home-page "https://github.com/jotsetung/ensembldb")
10152 (synopsis "Utilities to create and use Ensembl-based annotation databases")
10154 "The package provides functions to create and use transcript-centric
10155 annotation databases/packages. The annotation for the databases are directly
10156 fetched from Ensembl using their Perl API. The functionality and data is
10157 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
10158 but, in addition to retrieve all gene/transcript models and annotations from
10159 the database, the @code{ensembldb} package also provides a filter framework
10160 allowing to retrieve annotations for specific entries like genes encoded on a
10161 chromosome region or transcript models of lincRNA genes.")
10162 ;; No version specified
10163 (license license:lgpl3+)))
10165 (define-public r-organismdbi
10167 (name "r-organismdbi")
10172 (uri (bioconductor-uri "OrganismDbi" version))
10175 "1mklnzs0d0ygcdibwfnk5xqr8ln6wpa00qcaw9c68m342kql0jqw"))))
10176 (properties `((upstream-name . "OrganismDbi")))
10177 (build-system r-build-system)
10179 `(("r-annotationdbi" ,r-annotationdbi)
10180 ("r-biobase" ,r-biobase)
10181 ("r-biocgenerics" ,r-biocgenerics)
10182 ("r-biocmanager" ,r-biocmanager)
10184 ("r-genomicfeatures" ,r-genomicfeatures)
10185 ("r-genomicranges" ,r-genomicranges)
10186 ("r-graph" ,r-graph)
10187 ("r-iranges" ,r-iranges)
10189 ("r-s4vectors" ,r-s4vectors)))
10190 (home-page "https://bioconductor.org/packages/OrganismDbi")
10191 (synopsis "Software to enable the smooth interfacing of database packages")
10192 (description "The package enables a simple unified interface to several
10193 annotation packages each of which has its own schema by taking advantage of
10194 the fact that each of these packages implements a select methods.")
10195 (license license:artistic2.0)))
10197 (define-public r-biovizbase
10199 (name "r-biovizbase")
10204 (uri (bioconductor-uri "biovizBase" version))
10207 "10jflvadfcgxq2jnfxkpn417xd8ibh3zllz9rsqnq5w3wgfr4fhq"))))
10208 (properties `((upstream-name . "biovizBase")))
10209 (build-system r-build-system)
10211 `(("r-annotationdbi" ,r-annotationdbi)
10212 ("r-annotationfilter" ,r-annotationfilter)
10213 ("r-biocgenerics" ,r-biocgenerics)
10214 ("r-biostrings" ,r-biostrings)
10215 ("r-dichromat" ,r-dichromat)
10216 ("r-ensembldb" ,r-ensembldb)
10217 ("r-genomeinfodb" ,r-genomeinfodb)
10218 ("r-genomicalignments" ,r-genomicalignments)
10219 ("r-genomicfeatures" ,r-genomicfeatures)
10220 ("r-genomicranges" ,r-genomicranges)
10221 ("r-hmisc" ,r-hmisc)
10222 ("r-iranges" ,r-iranges)
10223 ("r-rcolorbrewer" ,r-rcolorbrewer)
10224 ("r-rlang" ,r-rlang)
10225 ("r-rsamtools" ,r-rsamtools)
10226 ("r-s4vectors" ,r-s4vectors)
10227 ("r-scales" ,r-scales)
10228 ("r-summarizedexperiment" ,r-summarizedexperiment)
10229 ("r-variantannotation" ,r-variantannotation)))
10230 (home-page "https://bioconductor.org/packages/biovizBase")
10231 (synopsis "Basic graphic utilities for visualization of genomic data")
10233 "The biovizBase package is designed to provide a set of utilities, color
10234 schemes and conventions for genomic data. It serves as the base for various
10235 high-level packages for biological data visualization. This saves development
10236 effort and encourages consistency.")
10237 (license license:artistic2.0)))
10239 (define-public r-dropbead
10240 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
10243 (name "r-dropbead")
10244 (version (string-append "0-" revision "." (string-take commit 7)))
10248 (uri (git-reference
10249 (url "https://github.com/rajewsky-lab/dropbead")
10251 (file-name (git-file-name name version))
10254 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
10255 (build-system r-build-system)
10257 `(("r-ggplot2" ,r-ggplot2)
10258 ("r-rcolorbrewer" ,r-rcolorbrewer)
10259 ("r-gridextra" ,r-gridextra)
10260 ("r-gplots" ,r-gplots)
10261 ("r-plyr" ,r-plyr)))
10262 (home-page "https://github.com/rajewsky-lab/dropbead")
10263 (synopsis "Basic exploration and analysis of Drop-seq data")
10264 (description "This package offers a quick and straight-forward way to
10265 explore and perform basic analysis of single cell sequencing data coming from
10266 droplet sequencing. It has been particularly tailored for Drop-seq.")
10267 (license license:gpl3))))
10269 (define-public r-cellchat
10271 "21edd226ca408e4c413408f98562d71ee0b54e5d")
10274 (name "r-cellchat")
10275 (version (git-version "1.0.0" revision commit))
10279 (uri (git-reference
10280 (url "https://github.com/sqjin/CellChat")
10282 (file-name (git-file-name name version))
10285 "0cvzl9mi8jjznpql2gv67swnk1dndn3a2h22z5l84h7lwpwjmh53"))
10287 '(for-each delete-file '("src/CellChat.so"
10288 "src/CellChat_Rcpp.o"
10289 "src/RcppExports.o")))))
10290 (properties `((upstream-name . "CellChat")))
10291 (build-system r-build-system)
10293 `(("r-biocgenerics" ,r-biocgenerics)
10294 ("r-circlize" ,r-circlize)
10295 ("r-colorspace" ,r-colorspace)
10296 ("r-complexheatmap" ,r-complexheatmap)
10297 ("r-cowplot" ,r-cowplot)
10298 ("r-dplyr" ,r-dplyr)
10301 ("r-forcats" ,r-forcats)
10302 ("r-future" ,r-future)
10303 ("r-future-apply" ,r-future-apply)
10304 ("r-gg-gap" ,r-gg-gap)
10305 ("r-ggalluvial" ,r-ggalluvial)
10306 ("r-ggplot2" ,r-ggplot2)
10307 ("r-ggrepel" ,r-ggrepel)
10308 ("r-igraph" ,r-igraph)
10309 ("r-irlba" ,r-irlba)
10310 ("r-magrittr" ,r-magrittr)
10311 ("r-matrix" ,r-matrix)
10313 ("r-patchwork" ,r-patchwork)
10314 ("r-pbapply" ,r-pbapply)
10315 ("r-rcolorbrewer" ,r-rcolorbrewer)
10317 ("r-rcppeigen" ,r-rcppeigen)
10318 ("r-reshape2" ,r-reshape2)
10319 ("r-reticulate" ,r-reticulate)
10320 ("r-rspectra" ,r-rspectra)
10321 ("r-rtsne" ,r-rtsne)
10322 ("r-scales" ,r-scales)
10323 ("r-shape" ,r-shape)
10325 ("r-stringr" ,r-stringr)
10326 ("r-svglite" ,r-svglite)))
10327 (native-inputs `(("r-knitr" ,r-knitr)))
10328 (home-page "https://github.com/sqjin/CellChat")
10329 (synopsis "Analysis of cell-cell communication from single-cell transcriptomics data")
10331 "This package infers, visualizes and analyzes the cell-cell
10332 communication networks from scRNA-seq data.")
10333 (license license:gpl3))))
10335 (define-public sambamba
10342 (uri (git-reference
10343 (url "https://github.com/biod/sambamba")
10344 (commit (string-append "v" version))))
10345 (file-name (git-file-name name version))
10348 "07dznzl6m8k7sw84jxw2kx6i3ymrapbmcmyh0fxz8wrybhw8fmwc"))))
10349 (build-system gnu-build-system)
10351 `(#:tests? #f ; there is no test target
10352 #:parallel-build? #f ; not supported
10354 (modify-phases %standard-phases
10355 (delete 'configure)
10356 (add-after 'unpack 'fix-ldc-version
10358 (substitute* "Makefile"
10359 ;; We use ldc2 instead of ldmd2 to compile sambamba.
10360 (("\\$\\(shell which ldmd2\\)") (which "ldc2")))
10362 (add-after 'unpack 'unbundle-prerequisites
10364 (substitute* "Makefile"
10365 (("= lz4/lib/liblz4.a") "= -L-llz4")
10366 (("ldc_version_info lz4-static") "ldc_version_info"))
10369 (lambda* (#:key outputs #:allow-other-keys)
10370 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
10372 (copy-file (string-append "bin/sambamba-" ,version)
10373 (string-append bin "/sambamba"))
10376 `(("python" ,python)))
10381 (home-page "https://github.com/biod/sambamba")
10382 (synopsis "Tools for working with SAM/BAM data")
10383 (description "Sambamba is a high performance modern robust and
10384 fast tool (and library), written in the D programming language, for
10385 working with SAM and BAM files. Current parallelised functionality is
10386 an important subset of samtools functionality, including view, index,
10387 sort, markdup, and depth.")
10388 (license license:gpl2+)))
10390 (define-public ritornello
10392 (name "ritornello")
10396 (uri (git-reference
10397 (url "https://github.com/KlugerLab/Ritornello")
10398 (commit (string-append "v" version))))
10399 (file-name (git-file-name name version))
10402 "1xahvq215qld7x1w8vpa5zbrsj6p9crb9shqa2x89sb0aaxa02jk"))))
10403 (build-system gnu-build-system)
10405 `(#:tests? #f ; there are no tests
10407 (modify-phases %standard-phases
10408 (add-after 'unpack 'patch-samtools-references
10409 (lambda* (#:key inputs #:allow-other-keys)
10410 (substitute* '("src/SamStream.h"
10412 (("<sam.h>") "<samtools/sam.h>"))
10414 (delete 'configure)
10416 (lambda* (#:key inputs outputs #:allow-other-keys)
10417 (let* ((out (assoc-ref outputs "out"))
10418 (bin (string-append out "/bin/")))
10420 (install-file "bin/Ritornello" bin)
10423 `(("samtools" ,samtools-0.1)
10427 (home-page "https://github.com/KlugerLab/Ritornello")
10428 (synopsis "Control-free peak caller for ChIP-seq data")
10429 (description "Ritornello is a ChIP-seq peak calling algorithm based on
10430 signal processing that can accurately call binding events without the need to
10431 do a pair total DNA input or IgG control sample. It has been tested for use
10432 with narrow binding events such as transcription factor ChIP-seq.")
10433 (license license:gpl3+)))
10435 (define-public trim-galore
10437 (name "trim-galore")
10442 (uri (git-reference
10443 (url "https://github.com/FelixKrueger/TrimGalore")
10445 (file-name (git-file-name name version))
10448 "0yrwg6325j4sb9vnplvl3jplzab0qdhp92wl480qjinpfq88j4rs"))))
10449 (build-system gnu-build-system)
10451 `(#:tests? #f ; no tests
10453 (modify-phases %standard-phases
10454 (replace 'configure
10456 ;; Trim Galore tries to figure out what version of Python
10457 ;; cutadapt is using by looking at the shebang. Of course that
10458 ;; doesn't work, because cutadapt is wrapped in a shell script.
10459 (substitute* "trim_galore"
10460 (("my \\$python_return.*")
10461 "my $python_return = \"Python 3.999\";\n"))
10464 (add-after 'unpack 'hardcode-tool-references
10465 (lambda* (#:key inputs #:allow-other-keys)
10466 (substitute* "trim_galore"
10467 (("\\$path_to_cutadapt = 'cutadapt'")
10468 (string-append "$path_to_cutadapt = '"
10469 (assoc-ref inputs "cutadapt")
10471 (("\\$compression_path = \"gzip\"")
10472 (string-append "$compression_path = \""
10473 (assoc-ref inputs "gzip")
10476 (string-append "\""
10477 (assoc-ref inputs "gzip")
10480 (string-append "\""
10481 (assoc-ref inputs "pigz")
10485 (lambda* (#:key outputs #:allow-other-keys)
10486 (let ((bin (string-append (assoc-ref outputs "out")
10489 (install-file "trim_galore" bin)
10495 ("cutadapt" ,cutadapt)))
10497 `(("unzip" ,unzip)))
10498 (home-page "https://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
10499 (synopsis "Wrapper around Cutadapt and FastQC")
10500 (description "Trim Galore! is a wrapper script to automate quality and
10501 adapter trimming as well as quality control, with some added functionality to
10502 remove biased methylation positions for RRBS sequence files.")
10503 (license license:gpl3+)))
10505 (define-public gess
10511 (uri (string-append "http://compbio.uthscsa.edu/"
10513 "gess-" version ".src.tar.gz"))
10516 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
10517 (build-system gnu-build-system)
10519 `(#:tests? #f ; no tests
10521 (modify-phases %standard-phases
10522 (delete 'configure)
10525 (lambda* (#:key inputs outputs #:allow-other-keys)
10526 (let* ((python (assoc-ref inputs "python"))
10527 (out (assoc-ref outputs "out"))
10528 (bin (string-append out "/bin/"))
10529 (target (string-append
10531 ,(version-major+minor
10532 (package-version python))
10533 "/site-packages/gess/")))
10535 (copy-recursively "." target)
10536 ;; Make GESS.py executable
10537 (chmod (string-append target "GESS.py") #o555)
10538 ;; Add Python shebang to the top and make Matplotlib
10540 (substitute* (string-append target "GESS.py")
10541 (("\"\"\"Description:" line)
10542 (string-append "#!" (which "python") "
10544 matplotlib.use('Agg')
10546 ;; Make sure GESS has all modules in its path
10547 (wrap-script (string-append target "GESS.py")
10548 `("PYTHONPATH" ":" = (,target ,(getenv "PYTHONPATH"))))
10550 (symlink (string-append target "GESS.py")
10551 (string-append bin "GESS.py"))
10554 `(("python" ,python-2)
10555 ("python2-pysam" ,python2-pysam)
10556 ("python2-scipy" ,python2-scipy)
10557 ("python2-numpy" ,python2-numpy)
10558 ("python2-networkx" ,python2-networkx)
10559 ("python2-biopython" ,python2-biopython)
10560 ("guile" ,guile-3.0))) ; for the script wrapper
10561 (home-page "https://compbio.uthscsa.edu/GESS_Web/")
10562 (synopsis "Detect exon-skipping events from raw RNA-seq data")
10564 "GESS is an implementation of a novel computational method to detect de
10565 novo exon-skipping events directly from raw RNA-seq data without the prior
10566 knowledge of gene annotation information. GESS stands for the graph-based
10567 exon-skipping scanner detection scheme.")
10568 (license license:bsd-3)))
10570 (define-public phylip
10577 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
10578 "download/phylip-" version ".tar.gz"))
10581 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
10582 (build-system gnu-build-system)
10584 `(#:tests? #f ; no check target
10585 #:make-flags (list "-f" "Makefile.unx" "install")
10586 #:parallel-build? #f ; not supported
10588 (modify-phases %standard-phases
10589 (add-after 'unpack 'enter-dir
10590 (lambda _ (chdir "src") #t))
10591 (delete 'configure)
10593 (lambda* (#:key inputs outputs #:allow-other-keys)
10594 (let ((target (string-append (assoc-ref outputs "out")
10597 (for-each (lambda (file)
10598 (install-file file target))
10599 (find-files "../exe" ".*")))
10601 (home-page "http://evolution.genetics.washington.edu/phylip/")
10602 (synopsis "Tools for inferring phylogenies")
10603 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
10604 programs for inferring phylogenies (evolutionary trees).")
10605 (license license:bsd-2)))
10614 (uri (string-append "https://integrativemodeling.org/"
10615 version "/download/imp-" version ".tar.gz"))
10618 "1z1vcpwbylixk0zywngg5iw0jv083jj1bqphi817jpg3fb9fx2jj"))))
10619 (build-system cmake-build-system)
10621 `( ;; CMake 3.17 or newer is required for the CMAKE_TEST_ARGUMENTS used
10622 ;; below to have an effect.
10625 (let ((disabled-tests
10626 '("expensive" ;exclude expensive tests
10627 "IMP.modeller" ;fail to import its own modules
10628 "IMP.parallel-test_sge.py" ;fail in build container
10629 ;; The following test fails non-reproducibly on
10630 ;; an inexact numbers assertion.
10631 "IMP.em-medium_test_local_fitting.py")))
10634 "-DCMAKE_CTEST_ARGUMENTS="
10636 (list "-L" "-tests?-" ;select only tests
10637 "-E" (format #f "'(~a)'" (string-join disabled-tests "|")))
10640 `(("python" ,python-wrapper)
10649 ;; Enabling MPI causes the build to use all the available memory and
10650 ;; fail (tested on a machine with 32 GiB of RAM).
10652 ("opencv" ,opencv)))
10654 `(("python-numpy" ,python-numpy)
10655 ("python-scipy" ,python-scipy)
10656 ("python-pandas" ,python-pandas)
10657 ("python-scikit-learn" ,python-scikit-learn)
10658 ("python-networkx" ,python-networkx)))
10659 (home-page "https://integrativemodeling.org")
10660 (synopsis "Integrative modeling platform")
10661 (description "IMP's broad goal is to contribute to a comprehensive
10662 structural characterization of biomolecules ranging in size and complexity
10663 from small peptides to large macromolecular assemblies, by integrating data
10664 from diverse biochemical and biophysical experiments. IMP provides a C++ and
10665 Python toolbox for solving complex modeling problems, and a number of
10666 applications for tackling some common problems in a user-friendly way.")
10667 ;; IMP is largely available under the GNU Lesser GPL; see the file
10668 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
10669 ;; available under the GNU GPL (see the file COPYING.GPL).
10670 (license (list license:lgpl2.1+
10673 (define-public tadbit
10679 (uri (git-reference
10680 (url "https://github.com/3DGenomes/TADbit")
10681 (commit (string-append "v" version))))
10682 (file-name (git-file-name name version))
10685 "0hqrlymh2a2bimcfdvlssy1x5h1lp3h1c5a7jj11hmcqczzqn3ni"))))
10686 (build-system python-build-system)
10689 (modify-phases %standard-phases
10690 (add-after 'unpack 'fix-problems-with-setup.py
10691 (lambda* (#:key outputs #:allow-other-keys)
10692 ;; Don't attempt to install the bash completions to
10693 ;; the home directory.
10694 (rename-file "extras/.bash_completion"
10696 (substitute* "setup.py"
10697 (("\\(path.expanduser\\('~'\\)")
10698 (string-append "(\""
10699 (assoc-ref outputs "out")
10700 "/etc/bash_completion.d\""))
10701 (("extras/\\.bash_completion")
10705 (lambda* (#:key inputs outputs #:allow-other-keys)
10706 (add-installed-pythonpath inputs outputs)
10707 (invoke "python3" "test/test_all.py")
10710 `(("glib" ,glib "bin") ;for gtester
10711 ("pkg-config" ,pkg-config)))
10713 ;; TODO: add Chimera for visualization
10716 ("python-future" ,python-future)
10717 ("python-h5py" ,python-h5py)
10718 ("python-scipy" ,python-scipy)
10719 ("python-numpy" ,python-numpy)
10720 ("python-matplotlib" ,python-matplotlib)
10721 ("python-pysam" ,python-pysam)))
10722 (home-page "https://3dgenomes.github.io/TADbit/")
10723 (synopsis "Analyze, model, and explore 3C-based data")
10725 "TADbit is a complete Python library to deal with all steps to analyze,
10726 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
10727 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
10728 correct interaction matrices, identify and compare the so-called
10729 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
10730 interaction matrices, and finally, extract structural properties from the
10731 models. TADbit is complemented by TADkit for visualizing 3D models.")
10732 (license license:gpl3+)))
10734 (define-public kentutils
10737 ;; 302.1.0 is out, but the only difference is the inclusion of
10738 ;; pre-built binaries.
10739 (version "302.0.0")
10743 (uri (git-reference
10744 (url "https://github.com/ENCODE-DCC/kentUtils")
10745 (commit (string-append "v" version))))
10746 (file-name (git-file-name name version))
10749 "0n1wbyjpzii2b9qhyp9r1q76j623cggpg3y8fmw78ld3z4y7ivha"))
10750 (modules '((guix build utils)
10755 ;; Only the contents of the specified directories are free
10756 ;; for all uses, so we remove the rest. "hg/autoSql" and
10757 ;; "hg/autoXml" are nominally free, but they depend on a
10758 ;; library that is built from the sources in "hg/lib",
10759 ;; which is nonfree.
10760 (let ((free (list "." ".."
10761 "utils" "lib" "inc" "tagStorm"
10762 "parasol" "htslib"))
10763 (directory? (lambda (file)
10764 (eq? 'directory (stat:type (stat file))))))
10765 (for-each (lambda (file)
10766 (and (directory? file)
10767 (delete-file-recursively file)))
10768 (map (cut string-append "src/" <>)
10771 (not (member file free)))))))
10772 ;; Only make the utils target, not the userApps target,
10773 ;; because that requires libraries we won't build.
10774 (substitute* "Makefile"
10775 ((" userApps") " utils"))
10776 ;; Only build libraries that are free.
10777 (substitute* "src/makefile"
10778 (("DIRS =.*") "DIRS =\n")
10779 (("cd jkOwnLib.*") "")
10782 (substitute* "src/utils/makefile"
10783 ;; These tools depend on "jkhgap.a", which is part of the
10784 ;; nonfree "src/hg/lib" directory.
10785 (("raSqlQuery") "")
10786 (("pslLiftSubrangeBlat") "")
10788 ;; Do not build UCSC tools, which may require nonfree
10790 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
10792 (build-system gnu-build-system)
10794 `( ;; There is no global test target and the test target for
10795 ;; individual tools depends on input files that are not
10799 (modify-phases %standard-phases
10800 (add-after 'unpack 'fix-permissions
10801 (lambda _ (make-file-writable "src/inc/localEnvironment.mk") #t))
10802 (add-after 'unpack 'fix-paths
10804 (substitute* "Makefile"
10805 (("/bin/echo") (which "echo")))
10807 (add-after 'unpack 'prepare-samtabix
10808 (lambda* (#:key inputs #:allow-other-keys)
10809 (copy-recursively (assoc-ref inputs "samtabix")
10812 (delete 'configure)
10814 (lambda* (#:key outputs #:allow-other-keys)
10815 (let ((bin (string-append (assoc-ref outputs "out")
10817 (copy-recursively "bin" bin))
10821 ,(let ((commit "10fd107909c1ac4d679299908be4262a012965ba"))
10824 (uri (git-reference
10825 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
10827 (file-name (git-file-name "samtabix" (string-take commit 7)))
10830 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma")))))))
10836 ("mariadb-dev" ,mariadb "dev")
10837 ("openssl" ,openssl)))
10838 (home-page "https://genome.cse.ucsc.edu/index.html")
10839 (synopsis "Assorted bioinformatics utilities")
10840 (description "This package provides the kentUtils, a selection of
10841 bioinformatics utilities used in combination with the UCSC genome
10843 ;; Only a subset of the sources are released under a non-copyleft
10844 ;; free software license. All other sources are removed in a
10845 ;; snippet. See this bug report for an explanation of how the
10846 ;; license statements apply:
10847 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
10848 (license (license:non-copyleft
10849 "http://genome.ucsc.edu/license/"
10850 "The contents of this package are free for all uses."))))
10852 (define-public f-seq
10853 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
10857 (version (string-append "1.1-" revision "." (string-take commit 7)))
10860 (uri (git-reference
10861 (url "https://github.com/aboyle/F-seq")
10863 (file-name (string-append name "-" version))
10866 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
10867 (modules '((guix build utils)))
10868 ;; Remove bundled Java library archives.
10871 (for-each delete-file (find-files "lib" ".*"))
10873 (build-system ant-build-system)
10875 `(#:tests? #f ; no tests included
10877 (modify-phases %standard-phases
10879 (lambda* (#:key inputs outputs #:allow-other-keys)
10880 (let* ((target (assoc-ref outputs "out"))
10881 (bin (string-append target "/bin"))
10882 (doc (string-append target "/share/doc/f-seq"))
10883 (lib (string-append target "/lib")))
10886 (substitute* "bin/linux/fseq"
10887 (("java") (which "java"))
10888 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
10889 (string-append (assoc-ref inputs "java-commons-cli")
10890 "/share/java/commons-cli.jar"))
10892 (string-append "REALDIR=" bin "\n")))
10893 (install-file "README.txt" doc)
10894 (install-file "bin/linux/fseq" bin)
10895 (install-file "build~/fseq.jar" lib)
10896 (copy-recursively "lib" lib)
10900 ("java-commons-cli" ,java-commons-cli)))
10901 (home-page "https://fureylab.web.unc.edu/software/fseq/")
10902 (synopsis "Feature density estimator for high-throughput sequence tags")
10904 "F-Seq is a software package that generates a continuous tag sequence
10905 density estimation allowing identification of biologically meaningful sites
10906 such as transcription factor binding sites (ChIP-seq) or regions of open
10907 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
10909 (license license:gpl3+))))
10911 (define-public bismark
10918 (uri (git-reference
10919 (url "https://github.com/FelixKrueger/Bismark")
10921 (file-name (string-append name "-" version "-checkout"))
10924 "0xchm3rgilj6vfjnyzfzzymfd7djr64sbrmrvs3njbwi66jqbzw9"))))
10925 (build-system perl-build-system)
10927 `(#:tests? #f ; there are no tests
10928 #:modules ((guix build utils)
10931 (guix build perl-build-system))
10933 (modify-phases %standard-phases
10934 ;; The bundled plotly.js is minified.
10935 (add-after 'unpack 'replace-plotly.js
10936 (lambda* (#:key inputs #:allow-other-keys)
10937 (let* ((file (assoc-ref inputs "plotly.js"))
10938 (installed "plotly/plotly.js"))
10939 (let ((minified (open-pipe* OPEN_READ "uglify-js" file)))
10940 (call-with-output-file installed
10941 (cut dump-port minified <>))))
10943 (delete 'configure)
10946 (lambda* (#:key inputs outputs #:allow-other-keys)
10947 (let* ((out (assoc-ref outputs "out"))
10948 (bin (string-append out "/bin"))
10949 (share (string-append out "/share/bismark"))
10950 (docdir (string-append out "/share/doc/bismark"))
10951 (docs '("Docs/Bismark_User_Guide.html"))
10952 (scripts '("bismark"
10953 "bismark_genome_preparation"
10954 "bismark_methylation_extractor"
10957 "coverage2cytosine"
10958 "deduplicate_bismark"
10959 "filter_non_conversion"
10962 "NOMe_filtering")))
10963 (substitute* "bismark2report"
10964 (("\\$RealBin/plotly")
10965 (string-append share "/plotly")))
10969 (for-each (lambda (file) (install-file file bin))
10971 (for-each (lambda (file) (install-file file docdir))
10973 (copy-recursively "Docs/Images" (string-append docdir "/Images"))
10974 (copy-recursively "plotly"
10975 (string-append share "/plotly"))
10977 ;; Fix references to gunzip
10978 (substitute* (map (lambda (file)
10979 (string-append bin "/" file))
10982 (string-append "\"" (assoc-ref inputs "gzip")
10983 "/bin/gunzip -c")))
10987 ("perl-carp" ,perl-carp)
10988 ("perl-getopt-long" ,perl-getopt-long)))
10993 (uri (string-append "https://raw.githubusercontent.com/plotly/plotly.js/"
10994 "v1.39.4/dist/plotly.js"))
10996 (base32 "138mwsr4nf5qif4mrxx286mpnagxd1xwl6k8aidrjgknaqg88zyr"))))
10997 ("uglify-js" ,uglify-js)))
10998 (home-page "https://www.bioinformatics.babraham.ac.uk/projects/bismark/")
10999 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11000 (description "Bismark is a program to map bisulfite treated sequencing
11001 reads to a genome of interest and perform methylation calls in a single step.
11002 The output can be easily imported into a genome viewer, such as SeqMonk, and
11003 enables a researcher to analyse the methylation levels of their samples
11004 straight away. Its main features are:
11007 @item Bisulfite mapping and methylation calling in one single step
11008 @item Supports single-end and paired-end read alignments
11009 @item Supports ungapped and gapped alignments
11010 @item Alignment seed length, number of mismatches etc are adjustable
11011 @item Output discriminates between cytosine methylation in CpG, CHG
11014 (license license:gpl3+)))
11016 (define-public paml
11022 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11023 "paml" version ".tgz"))
11026 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11027 (modules '((guix build utils)))
11028 ;; Remove Windows binaries
11031 (for-each delete-file (find-files "." "\\.exe$"))
11032 ;; Some files in the original tarball have restrictive
11033 ;; permissions, which makes repackaging fail
11034 (for-each (lambda (file) (chmod file #o644)) (find-files "."))
11036 (build-system gnu-build-system)
11038 `(#:tests? #f ; there are no tests
11039 #:make-flags '("CC=gcc")
11041 (modify-phases %standard-phases
11042 (replace 'configure
11044 (substitute* "src/BFdriver.c"
11045 (("/bin/bash") (which "bash")))
11049 (lambda* (#:key outputs #:allow-other-keys)
11050 (let ((tools '("baseml" "basemlg" "codeml"
11051 "pamp" "evolver" "yn00" "chi2"))
11052 (bin (string-append (assoc-ref outputs "out") "/bin"))
11053 (docdir (string-append (assoc-ref outputs "out")
11054 "/share/doc/paml")))
11056 (for-each (lambda (file) (install-file file bin)) tools)
11057 (copy-recursively "../doc" docdir)
11059 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11060 (synopsis "Phylogentic analysis by maximum likelihood")
11061 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11062 contains a few programs for model fitting and phylogenetic tree reconstruction
11063 using nucleotide or amino-acid sequence data.")
11065 (license license:gpl3)))
11067 (define-public kallisto
11073 (uri (git-reference
11074 (url "https://github.com/pachterlab/kallisto")
11075 (commit (string-append "v" version))))
11076 (file-name (git-file-name name version))
11079 "0ij5n7v3m90jdfi7sn8nvglfyf58abp1f5xq42r4k73l0lfds6xi"))
11080 (modules '((guix build utils)))
11082 '(delete-file-recursively "ext/htslib/"))))
11083 (build-system cmake-build-system)
11085 `(#:tests? #f ; no "check" target
11087 (modify-phases %standard-phases
11088 (add-after 'unpack 'do-not-use-bundled-htslib
11090 (substitute* "CMakeLists.txt"
11091 (("^ExternalProject_Add" m)
11092 (string-append "if (NEVER)\n" m))
11094 (string-append ")\nendif(NEVER)"))
11095 (("include_directories\\(\\$\\{htslib_PREFIX.*" m)
11096 (string-append "# " m)))
11097 (substitute* "src/CMakeLists.txt"
11098 (("target_link_libraries\\(kallisto kallisto_core pthread \
11099 \\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/../ext/htslib/libhts.a\\)")
11100 "target_link_libraries(kallisto kallisto_core pthread hts)")
11101 (("include_directories\\(\\.\\./ext/htslib\\)") ""))
11105 ("htslib" ,htslib-1.9)
11107 (home-page "https://pachterlab.github.io/kallisto/")
11108 (synopsis "Near-optimal RNA-Seq quantification")
11110 "Kallisto is a program for quantifying abundances of transcripts from
11111 RNA-Seq data, or more generally of target sequences using high-throughput
11112 sequencing reads. It is based on the novel idea of pseudoalignment for
11113 rapidly determining the compatibility of reads with targets, without the need
11114 for alignment. Pseudoalignment of reads preserves the key information needed
11115 for quantification, and kallisto is therefore not only fast, but also as
11116 accurate as existing quantification tools.")
11117 (license license:bsd-2)))
11119 (define-public libgff
11125 (uri (git-reference
11126 (url "https://github.com/Kingsford-Group/libgff")
11127 (commit (string-append "v" version))))
11128 (file-name (git-file-name name version))
11131 "0n6vfjnq7a2mianipscbshrvbncss8z4zkgkbjw754p9043nfkps"))))
11132 (build-system cmake-build-system)
11133 (arguments `(#:tests? #f)) ; no tests included
11134 (home-page "https://github.com/Kingsford-Group/libgff")
11135 (synopsis "Parser library for reading/writing GFF files")
11136 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11137 code that is used in the Cufflinks codebase. The goal of this library is to
11138 provide this functionality without the necessity of drawing in a heavy-weight
11139 dependency like SeqAn.")
11140 (license (license:x11-style "https://www.boost.org/LICENSE_1_0.txt"))))
11142 (define-public sailfish
11148 (uri (git-reference
11149 (url "https://github.com/kingsfordgroup/sailfish")
11150 (commit (string-append "v" version))))
11151 (file-name (git-file-name name version))
11154 "1amcc5hqvsl42hg4x19bi9vy47cl874s0lw1fmi0hwsdk9i8c03v"))
11155 (modules '((guix build utils)))
11158 ;; Delete bundled headers for eigen3.
11159 (delete-file-recursively "include/eigen3/")
11161 (build-system cmake-build-system)
11163 `(#:configure-flags
11164 (list (string-append "-DBOOST_INCLUDEDIR="
11165 (assoc-ref %build-inputs "boost")
11167 (string-append "-DBOOST_LIBRARYDIR="
11168 (assoc-ref %build-inputs "boost")
11170 (string-append "-DBoost_LIBRARIES="
11171 "-lboost_iostreams "
11172 "-lboost_filesystem "
11177 "-lboost_program_options")
11178 "-DBoost_FOUND=TRUE"
11179 ;; Don't download RapMap---we already have it!
11180 "-DFETCHED_RAPMAP=1")
11181 ;; Tests must be run after installation and the location of the test
11182 ;; data file must be overridden. But the tests fail. It looks like
11183 ;; they are not really meant to be run.
11186 (modify-phases %standard-phases
11187 ;; Boost cannot be found, even though it's right there.
11188 (add-after 'unpack 'do-not-look-for-boost
11189 (lambda* (#:key inputs #:allow-other-keys)
11190 (substitute* "CMakeLists.txt"
11191 (("find_package\\(Boost 1\\.53\\.0") "#"))
11193 (add-after 'unpack 'do-not-assign-to-macro
11195 (substitute* "include/spdlog/details/format.cc"
11196 (("const unsigned CHAR_WIDTH = 1;") ""))
11198 (add-after 'unpack 'prepare-rapmap
11199 (lambda* (#:key inputs #:allow-other-keys)
11200 (let ((src "external/install/src/rapmap/")
11201 (include "external/install/include/rapmap/")
11202 (rapmap (assoc-ref inputs "rapmap")))
11203 (mkdir-p "/tmp/rapmap")
11205 (assoc-ref inputs "rapmap")
11207 "--strip-components=1")
11210 (for-each (lambda (file)
11211 (install-file file src))
11212 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
11213 (copy-recursively "/tmp/rapmap/include" include))
11215 (add-after 'unpack 'use-system-libraries
11216 (lambda* (#:key inputs #:allow-other-keys)
11217 (substitute* '("src/SailfishIndexer.cpp"
11218 "src/SailfishUtils.cpp"
11219 "src/SailfishQuantify.cpp"
11220 "src/FASTAParser.cpp"
11222 "include/SailfishUtils.hpp"
11223 "include/SailfishIndex.hpp"
11224 "include/CollapsedEMOptimizer.hpp"
11225 "src/CollapsedEMOptimizer.cpp")
11226 (("#include \"jellyfish/config.h\"") ""))
11227 (substitute* "src/CMakeLists.txt"
11228 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11229 (string-append (assoc-ref inputs "jellyfish")
11230 "/include/jellyfish-" ,(package-version jellyfish)))
11231 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11232 (string-append (assoc-ref inputs "jellyfish")
11233 "/lib/libjellyfish-2.0.a"))
11234 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11235 (string-append (assoc-ref inputs "libdivsufsort")
11236 "/lib/libdivsufsort.so"))
11237 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11238 (string-append (assoc-ref inputs "libdivsufsort")
11239 "/lib/libdivsufsort64.so")))
11240 (substitute* "CMakeLists.txt"
11241 ;; Don't prefer static libs
11242 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11243 (("find_package\\(Jellyfish.*") "")
11244 (("ExternalProject_Add\\(libjellyfish") "message(")
11245 (("ExternalProject_Add\\(libgff") "message(")
11246 (("ExternalProject_Add\\(libsparsehash") "message(")
11247 (("ExternalProject_Add\\(libdivsufsort") "message("))
11249 ;; Ensure that Eigen headers can be found
11250 (setenv "CPLUS_INCLUDE_PATH"
11251 (string-append (assoc-ref inputs "eigen")
11253 (or (getenv "CPLUS_INCLUDE_PATH") "")))
11258 ("jemalloc" ,jemalloc)
11259 ("jellyfish" ,jellyfish)
11260 ("sparsehash" ,sparsehash)
11263 (uri (git-reference
11264 (url "https://github.com/COMBINE-lab/RapMap")
11265 (commit (string-append "sf-v" version))))
11266 (file-name (string-append "rapmap-sf-v" version "-checkout"))
11269 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
11270 (modules '((guix build utils)))
11271 ;; These files are expected to be excluded.
11273 '(begin (delete-file-recursively "include/spdlog")
11274 (for-each delete-file '("include/xxhash.h"
11277 ("libdivsufsort" ,libdivsufsort)
11282 `(("pkg-config" ,pkg-config)))
11283 (home-page "https://www.cs.cmu.edu/~ckingsf/software/sailfish/")
11284 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
11285 (description "Sailfish is a tool for genomic transcript quantification
11286 from RNA-seq data. It requires a set of target transcripts (either from a
11287 reference or de-novo assembly) to quantify. All you need to run sailfish is a
11288 fasta file containing your reference transcripts and a (set of) fasta/fastq
11289 file(s) containing your reads.")
11290 (license license:gpl3+)))
11292 (define libstadenio-for-salmon
11294 (name "libstadenio")
11298 (uri (git-reference
11299 (url "https://github.com/COMBINE-lab/staden-io_lib")
11300 (commit (string-append "v" version))))
11301 (file-name (string-append name "-" version "-checkout"))
11304 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
11305 (build-system gnu-build-system)
11306 (arguments '(#:parallel-tests? #f)) ; not supported
11310 `(("perl" ,perl))) ; for tests
11311 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
11312 (synopsis "General purpose trace and experiment file library")
11313 (description "This package provides a library of file reading and writing
11314 code to provide a general purpose Trace file (and Experiment File) reading
11317 The following file formats are supported:
11320 @item SCF trace files
11321 @item ABI trace files
11322 @item ALF trace files
11323 @item ZTR trace files
11324 @item SFF trace archives
11325 @item SRF trace archives
11326 @item Experiment files
11327 @item Plain text files
11328 @item SAM/BAM sequence files
11329 @item CRAM sequence files
11331 (license license:bsd-3)))
11333 (define-public salmon
11339 (uri (git-reference
11340 (url "https://github.com/COMBINE-lab/salmon")
11341 (commit (string-append "v" version))))
11342 (file-name (git-file-name name version))
11345 "1i2z4aivicmiixdz9bxalp7vmfzi3k92fxa63iqa8kgvfw5a4aq5"))
11346 (modules '((guix build utils)))
11349 ;; Delete bundled headers for eigen3.
11350 (delete-file-recursively "include/eigen3/")
11352 (build-system cmake-build-system)
11354 `(#:configure-flags
11355 (list (string-append "-DBOOST_INCLUDEDIR="
11356 (assoc-ref %build-inputs "boost")
11358 (string-append "-DBOOST_LIBRARYDIR="
11359 (assoc-ref %build-inputs "boost")
11361 (string-append "-DBoost_LIBRARIES="
11362 "-lboost_iostreams "
11363 "-lboost_filesystem "
11368 "-lboost_program_options")
11369 "-DBoost_FOUND=TRUE"
11370 "-DTBB_LIBRARIES=tbb tbbmalloc"
11371 ;; Don't download RapMap---we already have it!
11372 "-DFETCHED_RAPMAP=1")
11374 (modify-phases %standard-phases
11375 ;; Boost cannot be found, even though it's right there.
11376 (add-after 'unpack 'do-not-look-for-boost
11377 (lambda* (#:key inputs #:allow-other-keys)
11378 (substitute* "CMakeLists.txt"
11379 (("find_package\\(Boost 1\\.59\\.0") "#"))
11381 (add-after 'unpack 'do-not-phone-home
11383 (substitute* "src/Salmon.cpp"
11384 (("getVersionMessage\\(\\)") "\"\""))
11386 (add-after 'unpack 'prepare-rapmap
11387 (lambda* (#:key inputs #:allow-other-keys)
11388 (let ((src "external/install/src/rapmap/")
11389 (include "external/install/include/rapmap/")
11390 (rapmap (assoc-ref inputs "rapmap")))
11393 (copy-recursively (string-append rapmap "/src") src)
11394 (copy-recursively (string-append rapmap "/include") include)
11395 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
11396 "external/install/include/rapmap/FastxParser.hpp"
11397 "external/install/include/rapmap/concurrentqueue.h"
11398 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
11399 "external/install/src/rapmap/FastxParser.cpp"
11400 "external/install/src/rapmap/xxhash.c"))
11401 (delete-file-recursively "external/install/include/rapmap/spdlog"))
11403 (add-after 'unpack 'use-system-libraries
11404 (lambda* (#:key inputs #:allow-other-keys)
11405 (substitute* "CMakeLists.txt"
11406 ;; Don't prefer static libs
11407 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11408 (("set\\(TBB_LIBRARIES") "message(")
11409 ;; Don't download anything
11410 (("DOWNLOAD_COMMAND") "DOWNLOAD_COMMAND echo")
11411 (("externalproject_add\\(libcereal") "message(")
11412 (("externalproject_add\\(libgff") "message(")
11413 (("externalproject_add\\(libtbb") "message(")
11414 (("externalproject_add\\(libdivsufsort") "message(")
11415 (("externalproject_add\\(libstadenio") "message(")
11416 (("externalproject_add_step\\(") "message("))
11417 (substitute* "src/CMakeLists.txt"
11418 (("add_dependencies") "#")
11419 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
11420 (string-append (assoc-ref inputs "libstadenio-for-salmon")
11421 "/lib/libstaden-read.so"))
11422 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11423 (string-append (assoc-ref inputs "libdivsufsort")
11424 "/lib/libdivsufsort.so"))
11425 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11426 (string-append (assoc-ref inputs "libdivsufsort")
11427 "/lib/libdivsufsort64.so"))
11428 (("lib/libdivsufsort.a") "/lib/libdivsufsort.so"))
11430 ;; Ensure that all headers can be found
11431 (setenv "CPLUS_INCLUDE_PATH"
11432 (string-append (or (getenv "CPLUS_INCLUDE_PATH") "")
11434 (assoc-ref inputs "eigen")
11435 "/include/eigen3"))
11437 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
11438 ;; run. It only exists after the install phase.
11439 (add-after 'unpack 'fix-tests
11441 (substitute* "src/CMakeLists.txt"
11442 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
11443 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
11452 (uri (git-reference
11453 (url "https://github.com/COMBINE-lab/RapMap")
11454 (commit (string-append "salmon-v" version))))
11455 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
11458 "1biplxf0csc7a8h1wf219b0vmjkvw6wk2zylhdklb577kgmihdms"))))
11459 ("jemalloc" ,jemalloc)
11462 ("libdivsufsort" ,libdivsufsort)
11463 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
11467 `(("pkg-config" ,pkg-config)))
11468 (home-page "https://github.com/COMBINE-lab/salmon")
11469 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
11470 (description "Salmon is a program to produce highly-accurate,
11471 transcript-level quantification estimates from RNA-seq data. Salmon achieves
11472 its accuracy and speed via a number of different innovations, including the
11473 use of lightweight alignments (accurate but fast-to-compute proxies for
11474 traditional read alignments) and massively-parallel stochastic collapsed
11475 variational inference.")
11476 (license license:gpl3+)))
11478 (define-public python-loompy
11480 (name "python-loompy")
11482 ;; The tarball on Pypi does not include the tests.
11485 (uri (git-reference
11486 (url "https://github.com/linnarsson-lab/loompy")
11488 (file-name (git-file-name name version))
11491 "12a5kjgiikapv93wahfw0frszx1lblnppyz3vs5gy8fgmgngra07"))))
11492 (build-system python-build-system)
11495 (modify-phases %standard-phases
11498 (setenv "PYTHONPATH"
11499 (string-append (getcwd) ":"
11500 (getenv "PYTHONPATH")))
11501 (invoke "pytest" "tests")
11504 `(("python-h5py" ,python-h5py)
11505 ("python-numpy" ,python-numpy)
11506 ("python-pandas" ,python-pandas)
11507 ("python-scipy" ,python-scipy)))
11509 `(("python-pytest" ,python-pytest)))
11510 (home-page "https://github.com/linnarsson-lab/loompy")
11511 (synopsis "Work with .loom files for single-cell RNA-seq data")
11512 (description "The loom file format is an efficient format for very large
11513 omics datasets, consisting of a main matrix, optional additional layers, a
11514 variable number of row and column annotations. Loom also supports sparse
11515 graphs. This library makes it easy to work with @file{.loom} files for
11516 single-cell RNA-seq data.")
11517 (license license:bsd-3)))
11519 ;; We cannot use the latest commit because it requires Java 9.
11520 (define-public java-forester
11521 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
11524 (name "java-forester")
11525 (version (string-append "0-" revision "." (string-take commit 7)))
11528 (uri (git-reference
11529 (url "https://github.com/cmzmasek/forester")
11531 (file-name (string-append name "-" version "-checkout"))
11534 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
11535 (modules '((guix build utils)))
11538 ;; Delete bundled jars and pre-built classes
11539 (delete-file-recursively "forester/java/resources")
11540 (delete-file-recursively "forester/java/classes")
11541 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
11542 ;; Delete bundled applications
11543 (delete-file-recursively "forester_applications")
11545 (build-system ant-build-system)
11547 `(#:tests? #f ; there are none
11549 #:modules ((guix build ant-build-system)
11551 (guix build java-utils)
11555 (modify-phases %standard-phases
11556 (add-after 'unpack 'chdir
11557 (lambda _ (chdir "forester/java") #t))
11558 (add-after 'chdir 'fix-dependencies
11560 (chmod "build.xml" #o664)
11561 (call-with-output-file "build.xml.new"
11565 (with-input-from-file "build.xml"
11566 (lambda _ (xml->sxml #:trim-whitespace? #t)))
11567 `(;; Remove all unjar tags to avoid repacking classes.
11568 (unjar . ,(lambda _ '()))
11569 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
11570 (*text* . ,(lambda (_ txt) txt))))
11572 (rename-file "build.xml.new" "build.xml")
11574 ;; FIXME: itext is difficult to package as it depends on a few
11575 ;; unpackaged libraries.
11576 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
11578 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
11579 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
11580 (("pdf_written_to = PdfExporter.*")
11581 "throw new IOException(\"PDF export is not available.\");"))
11583 ;; There is no install target
11584 (replace 'install (install-jars ".")))))
11586 `(("java-commons-codec" ,java-commons-codec)
11587 ("java-openchart2" ,java-openchart2)))
11588 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
11589 (synopsis "Phylogenomics libraries for Java")
11590 (description "Forester is a collection of Java libraries for
11591 phylogenomics and evolutionary biology research. It includes support for
11592 reading, writing, and exporting phylogenetic trees.")
11593 (license license:lgpl2.1+))))
11595 (define-public java-forester-1.005
11597 (name "java-forester")
11601 (uri (string-append "https://repo1.maven.org/maven2/"
11602 "org/biojava/thirdparty/forester/"
11603 version "/forester-" version "-sources.jar"))
11604 (file-name (string-append name "-" version ".jar"))
11607 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
11608 (build-system ant-build-system)
11610 `(#:tests? #f ; there are none
11612 #:modules ((guix build ant-build-system)
11614 (guix build java-utils)
11618 (modify-phases %standard-phases
11619 (add-after 'unpack 'fix-dependencies
11620 (lambda* (#:key inputs #:allow-other-keys)
11621 (call-with-output-file "build.xml"
11625 (with-input-from-file "src/build.xml"
11626 (lambda _ (xml->sxml #:trim-whitespace? #t)))
11627 `(;; Remove all unjar tags to avoid repacking classes.
11628 (unjar . ,(lambda _ '()))
11629 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
11630 (*text* . ,(lambda (_ txt) txt))))
11632 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
11633 "synth_look_and_feel_1.xml")
11634 (copy-file (assoc-ref inputs "phyloxml.xsd")
11636 (substitute* "build.xml"
11637 (("../resources/synth_laf/synth_look_and_feel_1.xml")
11638 "synth_look_and_feel_1.xml")
11639 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
11642 ;; FIXME: itext is difficult to package as it depends on a few
11643 ;; unpackaged libraries.
11644 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
11646 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
11647 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
11648 "src/org/forester/archaeopteryx/MainFrameApplication.java")
11649 (("pdf_written_to = PdfExporter.*")
11650 "throw new IOException(\"PDF export is not available.\"); /*")
11651 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
11652 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
11654 (add-after 'unpack 'delete-pre-built-classes
11655 (lambda _ (delete-file-recursively "src/classes") #t))
11656 ;; There is no install target
11657 (replace 'install (install-jars ".")))))
11659 `(("java-commons-codec" ,java-commons-codec)
11660 ("java-openchart2" ,java-openchart2)))
11661 ;; The source archive does not contain the resources.
11666 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
11667 "b61cc2dcede0bede317db362472333115756b8c6/"
11668 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
11669 (file-name (string-append name "-phyloxml-" version ".xsd"))
11672 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
11673 ("synth_look_and_feel_1.xml"
11676 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
11677 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
11678 "forester/java/classes/resources/"
11679 "synth_look_and_feel_1.xml"))
11680 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
11683 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
11684 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
11685 (synopsis "Phylogenomics libraries for Java")
11686 (description "Forester is a collection of Java libraries for
11687 phylogenomics and evolutionary biology research. It includes support for
11688 reading, writing, and exporting phylogenetic trees.")
11689 (license license:lgpl2.1+)))
11691 (define-public java-biojava-core
11693 (name "java-biojava-core")
11697 (uri (git-reference
11698 (url "https://github.com/biojava/biojava")
11699 (commit (string-append "biojava-" version))))
11700 (file-name (string-append name "-" version "-checkout"))
11703 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
11704 (build-system ant-build-system)
11707 #:jar-name "biojava-core.jar"
11708 #:source-dir "biojava-core/src/main/java/"
11709 #:test-dir "biojava-core/src/test"
11710 ;; These tests seem to require internet access.
11711 #:test-exclude (list "**/SearchIOTest.java"
11712 "**/BlastXMLParserTest.java"
11713 "**/GenbankCookbookTest.java"
11714 "**/GenbankProxySequenceReaderTest.java")
11716 (modify-phases %standard-phases
11717 (add-before 'build 'copy-resources
11719 (copy-recursively "biojava-core/src/main/resources"
11722 (add-before 'check 'copy-test-resources
11724 (copy-recursively "biojava-core/src/test/resources"
11725 "build/test-classes")
11728 `(("java-log4j-api" ,java-log4j-api)
11729 ("java-log4j-core" ,java-log4j-core)
11730 ("java-slf4j-api" ,java-slf4j-api)
11731 ("java-slf4j-simple" ,java-slf4j-simple)))
11733 `(("java-junit" ,java-junit)
11734 ("java-hamcrest-core" ,java-hamcrest-core)))
11735 (home-page "https://biojava.org")
11736 (synopsis "Core libraries of Java framework for processing biological data")
11737 (description "BioJava is a project dedicated to providing a Java framework
11738 for processing biological data. It provides analytical and statistical
11739 routines, parsers for common file formats, reference implementations of
11740 popular algorithms, and allows the manipulation of sequences and 3D
11741 structures. The goal of the biojava project is to facilitate rapid
11742 application development for bioinformatics.
11744 This package provides the core libraries.")
11745 (license license:lgpl2.1+)))
11747 (define-public java-biojava-phylo
11748 (package (inherit java-biojava-core)
11749 (name "java-biojava-phylo")
11750 (build-system ant-build-system)
11753 #:jar-name "biojava-phylo.jar"
11754 #:source-dir "biojava-phylo/src/main/java/"
11755 #:test-dir "biojava-phylo/src/test"
11757 (modify-phases %standard-phases
11758 (add-before 'build 'copy-resources
11760 (copy-recursively "biojava-phylo/src/main/resources"
11763 (add-before 'check 'copy-test-resources
11765 (copy-recursively "biojava-phylo/src/test/resources"
11766 "build/test-classes")
11769 `(("java-log4j-api" ,java-log4j-api)
11770 ("java-log4j-core" ,java-log4j-core)
11771 ("java-slf4j-api" ,java-slf4j-api)
11772 ("java-slf4j-simple" ,java-slf4j-simple)
11773 ("java-biojava-core" ,java-biojava-core)
11774 ("java-forester" ,java-forester)))
11776 `(("java-junit" ,java-junit)
11777 ("java-hamcrest-core" ,java-hamcrest-core)))
11778 (home-page "https://biojava.org")
11779 (synopsis "Biojava interface to the forester phylogenomics library")
11780 (description "The phylo module provides a biojava interface layer to the
11781 forester phylogenomics library for constructing phylogenetic trees.")))
11783 (define-public java-biojava-alignment
11784 (package (inherit java-biojava-core)
11785 (name "java-biojava-alignment")
11786 (build-system ant-build-system)
11789 #:jar-name "biojava-alignment.jar"
11790 #:source-dir "biojava-alignment/src/main/java/"
11791 #:test-dir "biojava-alignment/src/test"
11793 (modify-phases %standard-phases
11794 (add-before 'build 'copy-resources
11796 (copy-recursively "biojava-alignment/src/main/resources"
11799 (add-before 'check 'copy-test-resources
11801 (copy-recursively "biojava-alignment/src/test/resources"
11802 "build/test-classes")
11805 `(("java-log4j-api" ,java-log4j-api)
11806 ("java-log4j-core" ,java-log4j-core)
11807 ("java-slf4j-api" ,java-slf4j-api)
11808 ("java-slf4j-simple" ,java-slf4j-simple)
11809 ("java-biojava-core" ,java-biojava-core)
11810 ("java-biojava-phylo" ,java-biojava-phylo)
11811 ("java-forester" ,java-forester)))
11813 `(("java-junit" ,java-junit)
11814 ("java-hamcrest-core" ,java-hamcrest-core)))
11815 (home-page "https://biojava.org")
11816 (synopsis "Biojava API for genetic sequence alignment")
11817 (description "The alignment module of BioJava provides an API that
11821 @item implementations of dynamic programming algorithms for sequence
11823 @item reading and writing of popular alignment file formats;
11824 @item a single-, or multi- threaded multiple sequence alignment algorithm.
11827 (define-public java-biojava-core-4.0
11828 (package (inherit java-biojava-core)
11829 (name "java-biojava-core")
11833 (uri (git-reference
11834 (url "https://github.com/biojava/biojava")
11835 (commit (string-append "biojava-" version))))
11836 (file-name (string-append name "-" version "-checkout"))
11839 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
11841 (define-public java-biojava-phylo-4.0
11842 (package (inherit java-biojava-core-4.0)
11843 (name "java-biojava-phylo")
11844 (build-system ant-build-system)
11847 #:jar-name "biojava-phylo.jar"
11848 #:source-dir "biojava-phylo/src/main/java/"
11849 #:test-dir "biojava-phylo/src/test"
11851 (modify-phases %standard-phases
11852 (add-before 'build 'copy-resources
11854 (copy-recursively "biojava-phylo/src/main/resources"
11857 (add-before 'check 'copy-test-resources
11859 (copy-recursively "biojava-phylo/src/test/resources"
11860 "build/test-classes")
11863 `(("java-log4j-api" ,java-log4j-api)
11864 ("java-log4j-core" ,java-log4j-core)
11865 ("java-slf4j-api" ,java-slf4j-api)
11866 ("java-slf4j-simple" ,java-slf4j-simple)
11867 ("java-biojava-core" ,java-biojava-core-4.0)
11868 ("java-forester" ,java-forester-1.005)))
11870 `(("java-junit" ,java-junit)
11871 ("java-hamcrest-core" ,java-hamcrest-core)))
11872 (home-page "https://biojava.org")
11873 (synopsis "Biojava interface to the forester phylogenomics library")
11874 (description "The phylo module provides a biojava interface layer to the
11875 forester phylogenomics library for constructing phylogenetic trees.")))
11877 (define-public java-biojava-alignment-4.0
11878 (package (inherit java-biojava-core-4.0)
11879 (name "java-biojava-alignment")
11880 (build-system ant-build-system)
11883 #:jar-name "biojava-alignment.jar"
11884 #:source-dir "biojava-alignment/src/main/java/"
11885 #:test-dir "biojava-alignment/src/test"
11887 (modify-phases %standard-phases
11888 (add-before 'build 'copy-resources
11890 (copy-recursively "biojava-alignment/src/main/resources"
11893 (add-before 'check 'copy-test-resources
11895 (copy-recursively "biojava-alignment/src/test/resources"
11896 "build/test-classes")
11899 `(("java-log4j-api" ,java-log4j-api)
11900 ("java-log4j-core" ,java-log4j-core)
11901 ("java-slf4j-api" ,java-slf4j-api)
11902 ("java-slf4j-simple" ,java-slf4j-simple)
11903 ("java-biojava-core" ,java-biojava-core-4.0)
11904 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
11905 ("java-forester" ,java-forester-1.005)))
11907 `(("java-junit" ,java-junit)
11908 ("java-hamcrest-core" ,java-hamcrest-core)))
11909 (home-page "https://biojava.org")
11910 (synopsis "Biojava API for genetic sequence alignment")
11911 (description "The alignment module of BioJava provides an API that
11915 @item implementations of dynamic programming algorithms for sequence
11917 @item reading and writing of popular alignment file formats;
11918 @item a single-, or multi- threaded multiple sequence alignment algorithm.
11921 (define-public dropseq-tools
11923 (name "dropseq-tools")
11928 (uri "http://mccarrolllab.com/download/1276/")
11929 (file-name (string-append "dropseq-tools-" version ".zip"))
11932 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
11933 ;; Delete bundled libraries
11934 (modules '((guix build utils)))
11937 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
11938 (delete-file-recursively "3rdParty")
11940 (build-system ant-build-system)
11942 `(#:tests? #f ; test data are not included
11943 #:test-target "test"
11944 #:build-target "all"
11945 #:source-dir "public/src/"
11948 (list (string-append "-Dpicard.executable.dir="
11949 (assoc-ref %build-inputs "java-picard")
11951 #:modules ((ice-9 match)
11954 (guix build java-utils)
11955 (guix build ant-build-system))
11957 (modify-phases %standard-phases
11958 ;; FIXME: fails with "java.io.FileNotFoundException:
11959 ;; /gnu/store/…-dropseq-tools-1.13/share/java/lib/biojava-alignment.jar"
11960 (delete 'generate-jar-indices)
11961 ;; All dependencies must be linked to "lib", because that's where
11962 ;; they will be searched for when the Class-Path property of the
11963 ;; manifest is computed.
11964 (add-after 'unpack 'record-references
11965 (lambda* (#:key inputs #:allow-other-keys)
11966 (mkdir-p "jar/lib")
11967 (let ((dirs (filter-map (match-lambda
11969 (if (and (string-prefix? "java-" name)
11970 (not (string=? name "java-testng")))
11973 (for-each (lambda (jar)
11974 (symlink jar (string-append "jar/lib/" (basename jar))))
11975 (append-map (lambda (dir) (find-files dir "\\.jar$"))
11978 ;; There is no installation target
11980 (lambda* (#:key inputs outputs #:allow-other-keys)
11981 (let* ((out (assoc-ref outputs "out"))
11982 (bin (string-append out "/bin"))
11983 (share (string-append out "/share/java/"))
11984 (lib (string-append share "/lib/"))
11985 (scripts (list "BAMTagHistogram"
11986 "BAMTagofTagCounts"
11987 "BaseDistributionAtReadPosition"
11988 "CollapseBarcodesInPlace"
11989 "CollapseTagWithContext"
11991 "CreateIntervalsFiles"
11992 "DetectBeadSynthesisErrors"
11993 "DigitalExpression"
11994 "Drop-seq_alignment.sh"
11997 "GatherGeneGCLength"
11998 "GatherMolecularBarcodeDistributionByGene"
11999 "GatherReadQualityMetrics"
12002 "SelectCellsByNumTranscripts"
12003 "SingleCellRnaSeqMetricsCollector"
12004 "TagBamWithReadSequenceExtended"
12005 "TagReadWithGeneExon"
12006 "TagReadWithInterval"
12007 "TrimStartingSequence"
12008 "ValidateReference")))
12009 (for-each mkdir-p (list bin share lib))
12010 (install-file "dist/dropseq.jar" share)
12011 (for-each (lambda (script)
12012 (chmod script #o555)
12013 (install-file script bin))
12015 (substitute* (map (lambda (script)
12016 (string-append bin "/" script))
12018 (("^java") (which "java"))
12019 (("jar_deploy_dir=.*")
12020 (string-append "jar_deploy_dir=" share "\n"))))
12022 ;; FIXME: We do this after stripping jars because we don't want it to
12023 ;; copy all these jars and strip them. We only want to install
12024 ;; links. Arguably, this is a problem with the ant-build-system.
12025 (add-after 'strip-jar-timestamps 'install-links
12026 (lambda* (#:key outputs #:allow-other-keys)
12027 (let* ((out (assoc-ref outputs "out"))
12028 (share (string-append out "/share/java/"))
12029 (lib (string-append share "/lib/")))
12030 (for-each (lambda (jar)
12031 (symlink (readlink jar)
12032 (string-append lib (basename jar))))
12033 (find-files "jar/lib" "\\.jar$")))
12036 `(("jdk" ,icedtea-8)
12037 ("java-picard" ,java-picard-2.10.3)
12038 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12039 ("java-commons-math3" ,java-commons-math3)
12040 ("java-commons-jexl2" ,java-commons-jexl-2)
12041 ("java-commons-collections4" ,java-commons-collections4)
12042 ("java-commons-lang2" ,java-commons-lang)
12043 ("java-commons-io" ,java-commons-io)
12044 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12045 ("java-guava" ,java-guava)
12046 ("java-la4j" ,java-la4j)
12047 ("java-biojava-core" ,java-biojava-core-4.0)
12048 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12049 ("java-jdistlib" ,java-jdistlib)
12050 ("java-simple-xml" ,java-simple-xml)
12051 ("java-snakeyaml" ,java-snakeyaml)))
12054 ("java-testng" ,java-testng)))
12055 (home-page "http://mccarrolllab.com/dropseq/")
12056 (synopsis "Tools for Drop-seq analyses")
12057 (description "Drop-seq is a technology to enable biologists to
12058 analyze RNA expression genome-wide in thousands of individual cells at
12059 once. This package provides tools to perform Drop-seq analyses.")
12060 (license license:expat)))
12062 (define-public pigx-rnaseq
12064 (name "pigx-rnaseq")
12068 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12069 "releases/download/v" version
12070 "/pigx_rnaseq-" version ".tar.gz"))
12073 "0z3hr120wk2vrlmlpz1vp3n9wy3rq4y2mnzh2vf08qgqn2xfdwcw"))))
12074 (build-system gnu-build-system)
12076 `(#:parallel-tests? #f ; not supported
12078 (modify-phases %standard-phases
12079 ;; "test.sh" runs STAR, which requires excessive amounts of memory.
12080 (add-after 'unpack 'disable-resource-intensive-test
12082 (substitute* "Makefile.in"
12083 (("(^ tests/test_trim_galore/test.sh).*" _ m) m)
12084 (("^ tests/test_multiqc/test.sh") "")
12085 (("^ test.sh") ""))
12088 `(("coreutils" ,coreutils)
12091 ("snakemake" ,snakemake)
12093 ("multiqc" ,multiqc)
12094 ("star" ,star-for-pigx)
12095 ("trim-galore" ,trim-galore)
12097 ("samtools" ,samtools)
12098 ("r-minimal" ,r-minimal)
12099 ("r-rmarkdown" ,r-rmarkdown)
12100 ("r-ggplot2" ,r-ggplot2)
12101 ("r-ggrepel" ,r-ggrepel)
12102 ("r-gprofiler" ,r-gprofiler)
12103 ("r-deseq2" ,r-deseq2)
12105 ("r-knitr" ,r-knitr)
12106 ("r-pheatmap" ,r-pheatmap)
12107 ("r-corrplot" ,r-corrplot)
12108 ("r-reshape2" ,r-reshape2)
12109 ("r-plotly" ,r-plotly)
12110 ("r-scales" ,r-scales)
12111 ("r-summarizedexperiment" ,r-summarizedexperiment)
12112 ("r-crosstalk" ,r-crosstalk)
12113 ("r-tximport" ,r-tximport)
12114 ("r-rtracklayer" ,r-rtracklayer)
12115 ("r-rjson" ,r-rjson)
12118 ("pandoc-citeproc" ,pandoc-citeproc)
12119 ("python-wrapper" ,python-wrapper)
12120 ("python-pyyaml" ,python-pyyaml)))
12121 (home-page "https://bioinformatics.mdc-berlin.de/pigx/")
12122 (synopsis "Analysis pipeline for RNA sequencing experiments")
12123 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
12124 reporting for RNA sequencing experiments. It is easy to use and produces high
12125 quality reports. The inputs are reads files from the sequencing experiment,
12126 and a configuration file which describes the experiment. In addition to
12127 quality control of the experiment, the pipeline produces a differential
12128 expression report comparing samples in an easily configurable manner.")
12129 (license license:gpl3+)))
12131 (define-public pigx-chipseq
12133 (name "pigx-chipseq")
12137 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
12138 "releases/download/v" version
12139 "/pigx_chipseq-" version ".tar.gz"))
12142 "0bb6hzpl0qq0jd57pgd1m5ns547rfipr6071a4m12vxlm4nlpi5q"))))
12143 (build-system gnu-build-system)
12144 ;; parts of the tests rely on access to the network
12145 (arguments '(#:tests? #f))
12148 ("coreutils" ,coreutils)
12149 ("r-minimal" ,r-minimal)
12150 ("r-argparser" ,r-argparser)
12151 ("r-biocparallel" ,r-biocparallel)
12152 ("r-biostrings" ,r-biostrings)
12153 ("r-chipseq" ,r-chipseq)
12154 ("r-corrplot" ,r-corrplot)
12155 ("r-data-table" ,r-data-table)
12156 ("r-deseq2" ,r-deseq2)
12157 ("r-dplyr" ,r-dplyr)
12159 ("r-genomation" ,r-genomation)
12160 ("r-genomicalignments" ,r-genomicalignments)
12161 ("r-genomicranges" ,r-genomicranges)
12162 ("r-ggplot2" ,r-ggplot2)
12163 ("r-ggrepel" ,r-ggrepel)
12164 ("r-gprofiler2" ,r-gprofiler2)
12165 ("r-heatmaply" ,r-heatmaply)
12166 ("r-htmlwidgets" ,r-htmlwidgets)
12167 ("r-jsonlite" ,r-jsonlite)
12168 ("r-pheatmap" ,r-pheatmap)
12169 ("r-plotly" ,r-plotly)
12170 ("r-rmarkdown" ,r-rmarkdown)
12171 ("r-rsamtools" ,r-rsamtools)
12172 ("r-rsubread" ,r-rsubread)
12173 ("r-rtracklayer" ,r-rtracklayer)
12174 ("r-s4vectors" ,r-s4vectors)
12175 ("r-stringr" ,r-stringr)
12176 ("r-tibble" ,r-tibble)
12177 ("r-tidyr" ,r-tidyr)
12178 ("python-wrapper" ,python-wrapper)
12179 ("python-pyyaml" ,python-pyyaml)
12180 ("python-magic" ,python-magic)
12181 ("python-xlrd" ,python-xlrd)
12182 ("trim-galore" ,trim-galore)
12184 ("multiqc" ,multiqc)
12187 ("pandoc-citeproc" ,pandoc-citeproc)
12191 ("snakemake" ,snakemake)
12192 ("samtools" ,samtools)
12193 ("bedtools" ,bedtools)
12194 ("kentutils" ,kentutils)))
12196 `(("python-pytest" ,python-pytest)))
12197 (home-page "https://bioinformatics.mdc-berlin.de/pigx/")
12198 (synopsis "Analysis pipeline for ChIP sequencing experiments")
12199 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
12200 calling and reporting for ChIP sequencing experiments. It is easy to use and
12201 produces high quality reports. The inputs are reads files from the sequencing
12202 experiment, and a configuration file which describes the experiment. In
12203 addition to quality control of the experiment, the pipeline enables to set up
12204 multiple peak calling analysis and allows the generation of a UCSC track hub
12205 in an easily configurable manner.")
12206 (license license:gpl3+)))
12208 (define-public pigx-bsseq
12210 (name "pigx-bsseq")
12214 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
12215 "releases/download/v" version
12216 "/pigx_bsseq-" version ".tar.gz"))
12219 "0mpzlay2d5cjpmrcp7knff6rg1c2mqszd638n7lw0mc0cycbp9f8"))))
12220 (build-system gnu-build-system)
12222 `(;; TODO: tests currently require 12+GB of RAM. See
12223 ;; https://github.com/BIMSBbioinfo/pigx_bsseq/issues/164
12226 (modify-phases %standard-phases
12227 (add-before 'check 'set-timezone
12228 ;; The readr package is picky about timezones.
12229 (lambda* (#:key inputs #:allow-other-keys)
12230 (setenv "TZ" "UTC+1")
12232 (string-append (assoc-ref inputs "tzdata")
12233 "/share/zoneinfo"))
12236 `(("tzdata" ,tzdata)))
12238 `(("coreutils" ,coreutils)
12241 ("r-minimal" ,r-minimal)
12242 ("r-annotationhub" ,r-annotationhub)
12244 ("r-genomation" ,r-genomation)
12245 ("r-ggrepel" ,r-ggrepel)
12246 ("r-methylkit" ,r-methylkit)
12247 ("r-rtracklayer" ,r-rtracklayer)
12248 ("r-rmarkdown" ,r-rmarkdown)
12249 ("r-bookdown" ,r-bookdown)
12250 ("r-ggplot2" ,r-ggplot2)
12251 ("r-ggbio" ,r-ggbio)
12253 ("pandoc-citeproc" ,pandoc-citeproc)
12254 ("python-wrapper" ,python-wrapper)
12255 ("python-pyyaml" ,python-pyyaml)
12256 ("snakemake" ,snakemake)
12257 ("bismark" ,bismark)
12259 ("bwa-meth" ,bwa-meth)
12261 ("methyldackel" ,methyldackel)
12262 ("multiqc" ,multiqc)
12263 ("trim-galore" ,trim-galore)
12264 ("cutadapt" ,cutadapt)
12265 ("samblaster" ,samblaster)
12266 ("samtools" ,samtools)))
12267 (home-page "https://bioinformatics.mdc-berlin.de/pigx/")
12268 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
12269 (description "PiGx BSseq is a data processing pipeline for raw fastq read
12270 data of bisulfite experiments; it produces reports on aggregate methylation
12271 and coverage and can be used to produce information on differential
12272 methylation and segmentation.")
12273 (license license:gpl3+)))
12275 (define-public pigx-scrnaseq
12277 (name "pigx-scrnaseq")
12281 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/"
12282 "releases/download/v" version
12283 "/pigx_scrnaseq-" version ".tar.gz"))
12286 "1h5mcxzwj3cidlkvy9ly5wmi48vwfsjf8dxjfirknqxr9a92hwlx"))))
12287 (build-system gnu-build-system)
12289 `(("coreutils" ,coreutils)
12292 ("flexbar" ,flexbar)
12293 ("java" ,icedtea-8)
12294 ("jellyfish" ,jellyfish)
12295 ("python-wrapper" ,python-wrapper)
12296 ("python-pyyaml" ,python-pyyaml)
12297 ("python-pandas" ,python-pandas)
12298 ("python-magic" ,python-magic)
12299 ("python-numpy" ,python-numpy)
12300 ("python-loompy" ,python-loompy)
12302 ("pandoc-citeproc" ,pandoc-citeproc)
12303 ("samtools" ,samtools)
12304 ("snakemake" ,snakemake)
12305 ("star" ,star-for-pigx)
12306 ("r-minimal" ,r-minimal)
12307 ("r-argparser" ,r-argparser)
12308 ("r-cowplot" ,r-cowplot)
12309 ("r-data-table" ,r-data-table)
12310 ("r-delayedarray" ,r-delayedarray)
12311 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
12312 ("r-dplyr" ,r-dplyr)
12313 ("r-dropbead" ,r-dropbead)
12315 ("r-genomicalignments" ,r-genomicalignments)
12316 ("r-genomicfiles" ,r-genomicfiles)
12317 ("r-genomicranges" ,r-genomicranges)
12318 ("r-ggplot2" ,r-ggplot2)
12319 ("r-hdf5array" ,r-hdf5array)
12320 ("r-pheatmap" ,r-pheatmap)
12321 ("r-rmarkdown" ,r-rmarkdown)
12322 ("r-rsamtools" ,r-rsamtools)
12323 ("r-rtracklayer" ,r-rtracklayer)
12324 ("r-rtsne" ,r-rtsne)
12325 ("r-scater" ,r-scater)
12326 ("r-scran" ,r-scran)
12327 ("r-seurat" ,r-seurat)
12328 ("r-singlecellexperiment" ,r-singlecellexperiment)
12329 ("r-stringr" ,r-stringr)
12330 ("r-yaml" ,r-yaml)))
12331 (home-page "https://bioinformatics.mdc-berlin.de/pigx/")
12332 (synopsis "Analysis pipeline for single-cell RNA sequencing experiments")
12333 (description "PiGX scRNAseq is an analysis pipeline for preprocessing and
12334 quality control for single cell RNA sequencing experiments. The inputs are
12335 read files from the sequencing experiment, and a configuration file which
12336 describes the experiment. It produces processed files for downstream analysis
12337 and interactive quality reports. The pipeline is designed to work with UMI
12339 (license license:gpl3+)))
12341 (define-public pigx
12347 (uri (string-append "https://github.com/BIMSBbioinfo/pigx/"
12348 "releases/download/v" version
12349 "/pigx-" version ".tar.gz"))
12352 "1i5njdy1clj5ncw45d16p7mwmqvb1ilikl9n797pxklc3f4s7mq7"))))
12353 (build-system gnu-build-system)
12355 `(("python" ,python)
12356 ("pigx-bsseq" ,pigx-bsseq)
12357 ("pigx-chipseq" ,pigx-chipseq)
12358 ("pigx-rnaseq" ,pigx-rnaseq)
12359 ("pigx-scrnaseq" ,pigx-scrnaseq)))
12360 (home-page "https://bioinformatics.mdc-berlin.de/pigx/")
12361 (synopsis "Analysis pipelines for genomics")
12362 (description "PiGx is a collection of genomics pipelines. It includes the
12363 following pipelines:
12366 @item PiGx BSseq for raw fastq read data of bisulfite experiments
12367 @item PiGx RNAseq for RNAseq samples
12368 @item PiGx scRNAseq for single cell dropseq analysis
12369 @item PiGx ChIPseq for reads from ChIPseq experiments
12372 All pipelines are easily configured with a simple sample sheet and a
12373 descriptive settings file. The result is a set of comprehensive, interactive
12374 HTML reports with interesting findings about your samples.")
12375 (license license:gpl3+)))
12377 (define-public genrich
12383 (uri (git-reference
12384 (url "https://github.com/jsh58/Genrich")
12385 (commit (string-append "v" version))))
12386 (file-name (git-file-name name version))
12389 "0x0q6z0208n3cxzqjla4rgjqpyqgwpmz27852lcvzkzaigymq4zp"))))
12390 (build-system gnu-build-system)
12392 `(#:tests? #f ; there are none
12394 (modify-phases %standard-phases
12395 (delete 'configure)
12397 (lambda* (#:key outputs #:allow-other-keys)
12398 (install-file "Genrich" (string-append (assoc-ref outputs "out") "/bin"))
12402 (home-page "https://github.com/jsh58/Genrich")
12403 (synopsis "Detecting sites of genomic enrichment")
12404 (description "Genrich is a peak-caller for genomic enrichment
12405 assays (e.g. ChIP-seq, ATAC-seq). It analyzes alignment files generated
12406 following the assay and produces a file detailing peaks of significant
12408 (license license:expat)))
12410 (define-public mantis
12411 (let ((commit "4ffd171632c2cb0056a86d709dfd2bf21bc69b84")
12415 (version (git-version "0" revision commit))
12418 (uri (git-reference
12419 (url "https://github.com/splatlab/mantis")
12421 (file-name (git-file-name name version))
12424 "0iqbr0dhmlc8mzpirmm2s4pkzkwdgrcx50yx6cv3wlr2qi064p55"))))
12425 (build-system cmake-build-system)
12426 (arguments '(#:tests? #f)) ; there are none
12428 `(("sdsl-lite" ,sdsl-lite)
12429 ("openssl" ,openssl)
12431 (home-page "https://github.com/splatlab/mantis")
12432 (synopsis "Large-scale sequence-search index data structure")
12433 (description "Mantis is a space-efficient data structure that can be
12434 used to index thousands of raw-read genomics experiments and facilitate
12435 large-scale sequence searches on those experiments. Mantis uses counting
12436 quotient filters instead of Bloom filters, enabling rapid index builds and
12437 queries, small indexes, and exact results, i.e., no false positives or
12438 negatives. Furthermore, Mantis is also a colored de Bruijn graph
12439 representation, so it supports fast graph traversal and other topological
12440 analyses in addition to large-scale sequence-level searches.")
12441 ;; uses __uint128_t and inline assembly
12442 (supported-systems '("x86_64-linux"))
12443 (license license:bsd-3))))
12445 (define-public sjcount
12446 ;; There is no tag for version 3.2, nor is there a release archive.
12447 (let ((commit "292d3917cadb3f6834c81e509c30e61cd7ead6e5")
12451 (version (git-version "3.2" revision commit))
12454 (uri (git-reference
12455 (url "https://github.com/pervouchine/sjcount-full")
12457 (file-name (string-append name "-" version "-checkout"))
12460 "0gdgj35j249f04rqgq8ymcc1xg1vi9kzbajnjqpaq2wpbh8bl234"))))
12461 (build-system gnu-build-system)
12463 `(#:tests? #f ; requires a 1.4G test file
12465 (list (string-append "SAMTOOLS_DIR="
12466 (assoc-ref %build-inputs "samtools")
12469 (modify-phases %standard-phases
12470 (replace 'configure
12471 (lambda* (#:key inputs #:allow-other-keys)
12472 (substitute* "makefile"
12473 (("-I \\$\\{SAMTOOLS_DIR\\}")
12474 (string-append "-I" (assoc-ref inputs "samtools")
12475 "/include/samtools"))
12476 (("-lz ") "-lz -lpthread "))
12479 (lambda* (#:key outputs #:allow-other-keys)
12480 (for-each (lambda (tool)
12482 (string-append (assoc-ref outputs "out")
12484 '("j_count" "b_count" "sjcount"))
12487 `(("samtools" ,samtools-0.1)
12489 (home-page "https://github.com/pervouchine/sjcount-full/")
12490 (synopsis "Annotation-agnostic splice junction counting pipeline")
12491 (description "Sjcount is a utility for fast quantification of splice
12492 junctions in RNA-seq data. It is annotation-agnostic and offset-aware. This
12493 version does count multisplits.")
12494 (license license:gpl3+))))
12496 (define-public minimap2
12503 (uri (string-append "https://github.com/lh3/minimap2/"
12504 "releases/download/v" version "/"
12505 "minimap2-" version ".tar.bz2"))
12508 "0hi7i9pzxhvjj44khzzzj1lrn5gb5837arr4wgln7k1k5n4ci2mn"))
12509 (patches (search-patches "minimap2-aarch64-support.patch"))))
12510 (build-system gnu-build-system)
12512 `(#:tests? #f ; there are none
12514 (list (string-append "CC=" ,(cc-for-target))
12515 (let ((system ,(or (%current-target-system)
12516 (%current-system))))
12518 ((string-prefix? "x86_64" system)
12520 ((or (string-prefix? "i586" system)
12521 (string-prefix? "i686" system))
12523 ((string-prefix? "armhf" system)
12525 ((string-prefix? "aarch64" system)
12529 (modify-phases %standard-phases
12530 (delete 'configure)
12532 (lambda* (#:key outputs #:allow-other-keys)
12533 (let* ((out (assoc-ref outputs "out"))
12534 (bin (string-append out "/bin"))
12535 (man (string-append out "/share/man/man1")))
12536 (install-file "minimap2" bin)
12538 (install-file "minimap2.1" man))
12542 (home-page "https://lh3.github.io/minimap2/")
12543 (synopsis "Pairwise aligner for genomic and spliced nucleotide sequences")
12544 (description "Minimap2 is a versatile sequence alignment program that
12545 aligns DNA or mRNA sequences against a large reference database. Typical use
12549 @item mapping PacBio or Oxford Nanopore genomic reads to the human genome;
12550 @item finding overlaps between long reads with error rate up to ~15%;
12551 @item splice-aware alignment of PacBio Iso-Seq or Nanopore cDNA or Direct RNA
12552 reads against a reference genome;
12553 @item aligning Illumina single- or paired-end reads;
12554 @item assembly-to-assembly alignment;
12555 @item full-genome alignment between two closely related species with
12556 divergence below ~15%.
12558 (license license:expat)))
12560 (define-public miniasm
12566 (uri (git-reference
12567 (url "https://github.com/lh3/miniasm")
12568 (commit (string-append "v" version))))
12569 (file-name (git-file-name name version))
12572 "04dv5wv8bhsw1imxwyd438bnn9kby7svp44nbcz8lsadzjjci5gs"))))
12573 (build-system gnu-build-system)
12577 `(#:tests? #f ; There are no tests.
12579 (modify-phases %standard-phases
12580 (delete 'configure)
12582 (lambda* (#:key inputs outputs #:allow-other-keys)
12583 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
12584 (install-file "miniasm" bin)
12585 (install-file "minidot" bin)
12587 (home-page "https://github.com/lh3/miniasm")
12588 (synopsis "Ultrafast de novo assembly for long noisy reads")
12589 (description "Miniasm is a very fast OLC-based de novo assembler for noisy
12590 long reads. It takes all-vs-all read self-mappings (typically by minimap) as
12591 input and outputs an assembly graph in the GFA format. Different from
12592 mainstream assemblers, miniasm does not have a consensus step. It simply
12593 concatenates pieces of read sequences to generate the final unitig sequences.
12594 Thus the per-base error rate is similar to the raw input reads.")
12595 (license license:expat)))
12597 (define-public bandage
12604 (uri (git-reference
12605 (url "https://github.com/rrwick/Bandage")
12606 (commit (string-append "v" version))))
12607 (file-name (git-file-name name version))
12609 (base32 "1bbsn5f5x8wlspg4pbibqz6m5vin8c19nl224f3z3km0pkc97rwv"))))
12610 (build-system qt-build-system)
12613 (modify-phases %standard-phases
12614 (replace 'configure
12616 (invoke "qmake" "Bandage.pro")))
12618 (lambda* (#:key tests? #:allow-other-keys)
12620 (substitute* "tests/bandage_command_line_tests.sh"
12621 (("^bandagepath=.*")
12622 (string-append "bandagepath=" (getcwd) "/Bandage\n")))
12623 (with-directory-excursion "tests"
12624 (setenv "XDG_RUNTIME_DIR" (getcwd))
12625 (invoke "./bandage_command_line_tests.sh")))
12628 (lambda* (#:key outputs #:allow-other-keys)
12629 (let ((out (assoc-ref outputs "out")))
12630 (install-file "Bandage" (string-append out "/bin"))
12633 `(("qtbase" ,qtbase)
12636 `(("imagemagick" ,imagemagick)))
12637 (home-page "https://rrwick.github.io/Bandage/")
12639 "Bioinformatics Application for Navigating De novo Assembly Graphs Easily")
12640 (description "Bandage is a program for visualising de novo assembly graphs.
12641 It allows users to interact with the assembly graphs made by de novo assemblers
12642 such as Velvet, SPAdes, MEGAHIT and others. De novo assembly graphs contain not
12643 only assembled contigs but also the connections between those contigs, which
12644 were previously not easily accessible. Bandage visualises assembly graphs, with
12645 connections, using graph layout algorithms. Nodes in the drawn graph, which
12646 represent contigs, can be automatically labelled with their ID, length or depth.
12647 Users can interact with the graph by moving, labelling and colouring nodes.
12648 Sequence information can also be extracted directly from the graph viewer. By
12649 displaying connections between contigs, Bandage opens up new possibilities for
12650 analysing and improving de novo assemblies that are not possible by looking at
12652 (license (list license:gpl2+ ; bundled ogdf
12655 (define-public r-circus
12662 (uri (git-reference
12663 (url "https://github.com/BIMSBbioinfo/ciRcus")
12664 (commit (string-append "v" version))))
12665 (file-name (git-file-name name version))
12668 "0jhjn3ilb057hbf6yzrihj13ifxxs32y7nkby8l3lkm28dg4p97h"))))
12669 (build-system r-build-system)
12671 `(("r-annotationdbi" ,r-annotationdbi)
12672 ("r-annotationhub" ,r-annotationhub)
12673 ("r-biomart" ,r-biomart)
12674 ("r-data-table" ,r-data-table)
12676 ("r-genomicfeatures" ,r-genomicfeatures)
12677 ("r-genomicranges" ,r-genomicranges)
12678 ("r-ggplot2" ,r-ggplot2)
12680 ("r-iranges" ,r-iranges)
12681 ("r-rcolorbrewer" ,r-rcolorbrewer)
12682 ("r-rmysql" ,r-rmysql)
12683 ("r-s4vectors" ,r-s4vectors)
12684 ("r-stringr" ,r-stringr)
12685 ("r-summarizedexperiment" ,r-summarizedexperiment)))
12687 `(("r-knitr" ,r-knitr)))
12688 (home-page "https://github.com/BIMSBbioinfo/ciRcus")
12689 (synopsis "Annotation, analysis and visualization of circRNA data")
12690 (description "Circus is an R package for annotation, analysis and
12691 visualization of circRNA data. Users can annotate their circRNA candidates
12692 with host genes, gene featrues they are spliced from, and discriminate between
12693 known and yet unknown splice junctions. Circular-to-linear ratios of circRNAs
12694 can be calculated, and a number of descriptive plots easily generated.")
12695 (license license:artistic2.0)))
12697 (define-public gffread
12698 ;; We cannot use the tagged release because it is not in sync with gclib.
12699 ;; See https://github.com/gpertea/gffread/issues/26
12700 (let ((commit "ba7535fcb3cea55a6e5a491d916e93b454e87fd0")
12704 (version (git-version "0.9.12" revision commit))
12708 (uri (git-reference
12709 (url "https://github.com/gpertea/gffread")
12711 (file-name (git-file-name name version))
12714 "1dl2nbcg96lxpd0drg48ssa8343nf7pw9s9mkrc4mjjmfwsin3ki"))))
12715 (build-system gnu-build-system)
12717 `(#:tests? #f ; no check target
12719 (list "GCLDIR=gclib")
12721 (modify-phases %standard-phases
12722 (delete 'configure)
12723 (add-after 'unpack 'copy-gclib-source
12724 (lambda* (#:key inputs #:allow-other-keys)
12726 (copy-recursively (assoc-ref inputs "gclib-source") "gclib")
12728 ;; There is no install target
12730 (lambda* (#:key outputs #:allow-other-keys)
12731 (let* ((out (assoc-ref outputs "out"))
12732 (bin (string-append out "/bin")))
12733 (install-file "gffread" bin))
12737 ,(let ((version "0.10.3")
12738 (commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
12742 (uri (git-reference
12743 (url "https://github.com/gpertea/gclib")
12745 (file-name (git-file-name "gclib" version))
12748 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
12749 (home-page "https://github.com/gpertea/gffread/")
12750 (synopsis "Parse and convert GFF/GTF files")
12752 "This package provides a GFF/GTF file parsing utility providing format
12753 conversions, region filtering, FASTA sequence extraction and more.")
12754 ;; gffread is under Expat, but gclib is under Artistic 2.0
12755 (license (list license:expat
12756 license:artistic2.0)))))
12758 (define-public find-circ
12759 ;; The last release was in 2015. The license was clarified in 2017, so we
12760 ;; take the latest commit.
12761 (let ((commit "8655dca54970fcf7e92e22fbf57e1188724dda7d")
12765 (version (git-version "1.2" revision commit))
12769 (uri (git-reference
12770 (url "https://github.com/marvin-jens/find_circ")
12772 (file-name (git-file-name name version))
12775 "0p77pbqbclqr4srms34y1b9b4njybfpjiknc11ki84f3p8skb3cg"))))
12776 (build-system gnu-build-system)
12778 `(#:tests? #f ; there are none
12780 ;; There is no actual build system.
12781 (modify-phases %standard-phases
12782 (delete 'configure)
12785 (lambda* (#:key outputs #:allow-other-keys)
12786 (let* ((out (assoc-ref outputs "out"))
12787 (bin (string-append out "/bin"))
12788 (path (getenv "PYTHONPATH")))
12789 (for-each (lambda (script)
12790 (install-file script bin)
12791 (wrap-program (string-append bin "/" script)
12792 `("PYTHONPATH" ":" prefix (,path))))
12797 "unmapped2anchors.py")))
12800 `(("python2" ,python-2)
12801 ("python2-pysam" ,python2-pysam)
12802 ("python2-numpy" ,python2-numpy)))
12803 (home-page "https://github.com/marvin-jens/find_circ")
12804 (synopsis "circRNA detection from RNA-seq reads")
12805 (description "This package provides tools to detect head-to-tail
12806 spliced (back-spliced) sequencing reads, indicative of circular RNA (circRNA)
12808 (license license:gpl3))))
12810 (define-public python-scanpy
12812 (name "python-scanpy")
12817 (uri (pypi-uri "scanpy" version))
12820 "0s2b6cvaigx4wzw3850qb93sjwwxbzh22kpbp498zklc5rjpbz4l"))))
12821 (build-system python-build-system)
12824 (modify-phases %standard-phases
12826 (lambda* (#:key inputs #:allow-other-keys)
12827 ;; These tests require Internet access.
12828 (delete-file-recursively "scanpy/tests/notebooks")
12829 (delete-file "scanpy/tests/test_clustering.py")
12830 (delete-file "scanpy/tests/test_datasets.py")
12832 ;; TODO: I can't get the plotting tests to work, even with Xvfb.
12833 (delete-file "scanpy/tests/test_plotting.py")
12834 (delete-file "scanpy/tests/test_preprocessing.py")
12835 (delete-file "scanpy/tests/test_read_10x.py")
12837 (setenv "PYTHONPATH"
12838 (string-append (getcwd) ":"
12839 (getenv "PYTHONPATH")))
12843 `(("python-anndata" ,python-anndata)
12844 ("python-h5py" ,python-h5py)
12845 ("python-igraph" ,python-igraph)
12846 ("python-joblib" ,python-joblib)
12847 ("python-legacy-api-wrap" ,python-legacy-api-wrap)
12848 ("python-louvain" ,python-louvain)
12849 ("python-matplotlib" ,python-matplotlib)
12850 ("python-natsort" ,python-natsort)
12851 ("python-networkx" ,python-networkx)
12852 ("python-numba" ,python-numba)
12853 ("python-packaging" ,python-packaging)
12854 ("python-pandas" ,python-pandas)
12855 ("python-patsy" ,python-patsy)
12856 ("python-scikit-learn" ,python-scikit-learn)
12857 ("python-scipy" ,python-scipy)
12858 ("python-seaborn" ,python-seaborn)
12859 ("python-statsmodels" ,python-statsmodels)
12860 ("python-tables" ,python-tables)
12861 ("python-tqdm" ,python-tqdm)
12862 ("python-umap-learn" ,python-umap-learn)))
12864 `(("python-pytest" ,python-pytest)
12865 ("python-setuptools-scm" ,python-setuptools-scm)))
12866 (home-page "https://github.com/theislab/scanpy")
12867 (synopsis "Single-Cell Analysis in Python.")
12868 (description "Scanpy is a scalable toolkit for analyzing single-cell gene
12869 expression data. It includes preprocessing, visualization, clustering,
12870 pseudotime and trajectory inference and differential expression testing. The
12871 Python-based implementation efficiently deals with datasets of more than one
12873 (license license:bsd-3)))
12875 (define-public python-bbknn
12877 (name "python-bbknn")
12882 (uri (pypi-uri "bbknn" version))
12885 "1jbsh01f57zj4bhvjr3jh4532zznqd6nccmgrl3qi9gnhkf7c4y0"))))
12886 (build-system python-build-system)
12888 `(#:tests? #f)) ; TODO: Enable after migration to scikit-learn.
12890 `(("python-annoy" ,python-annoy)
12891 ("python-cython" ,python-cython)
12892 ("python-numpy" ,python-numpy)
12893 ("python-scipy" ,python-scipy)
12894 ("python-umap-learn" ,python-umap-learn)))
12895 (home-page "https://github.com/Teichlab/bbknn")
12896 (synopsis "Batch balanced KNN")
12897 (description "BBKNN is a batch effect removal tool that can be directly
12898 used in the Scanpy workflow. It serves as an alternative to
12899 @code{scanpy.api.pp.neighbors()}, with both functions creating a neighbour
12900 graph for subsequent use in clustering, pseudotime and UMAP visualisation. If
12901 technical artifacts are present in the data, they will make it challenging to
12902 link corresponding cell types across different batches. BBKNN actively
12903 combats this effect by splitting your data into batches and finding a smaller
12904 number of neighbours for each cell within each of the groups. This helps
12905 create connections between analogous cells in different batches without
12906 altering the counts or PCA space.")
12907 (license license:expat)))
12909 (define-public python-drep
12911 (name "python-drep")
12916 (uri (pypi-uri "drep" version))
12919 "08vk0x6v5c5n7afgd5pcjhsvb424absypxy22hw1cm1n9kirbi77"))))
12920 (build-system python-build-system)
12922 `(("python-biopython" ,python-biopython)
12923 ("python-matplotlib" ,python-matplotlib)
12924 ("python-numpy" ,python-numpy)
12925 ("python-pandas" ,python-pandas)
12926 ("python-pytest" ,python-pytest)
12927 ("python-scikit-learn" ,python-scikit-learn)
12928 ("python-seaborn" ,python-seaborn)
12929 ("python-tqdm" ,python-tqdm)))
12930 (home-page "https://github.com/MrOlm/drep")
12931 (synopsis "De-replication of microbial genomes assembled from multiple samples")
12933 "dRep is a Python program for rapidly comparing large numbers of genomes.
12934 dRep can also \"de-replicate\" a genome set by identifying groups of highly
12935 similar genomes and choosing the best representative genome for each genome
12937 (license license:expat)))
12939 (define-public instrain
12946 (uri (pypi-uri "inStrain" version))
12949 "0ykqlpf6yz4caihsaz3ys00cyvlr7wdj4s9a8rh56q5r8xf80ic0"))))
12950 (build-system python-build-system)
12953 (modify-phases %standard-phases
12954 (add-after 'unpack 'patch-relative-imports
12956 (substitute* "docker/run_instrain.py"
12959 (("from job_utils")
12960 "from .job_utils")))))))
12962 `(("python-biopython" ,python-biopython)
12963 ("python-boto3" ,python-boto3)
12964 ("python-h5py" ,python-h5py)
12965 ("python-lmfit" ,python-lmfit)
12966 ("python-matplotlib" ,python-matplotlib)
12967 ("python-networkx" ,python-networkx)
12968 ("python-numba" ,python-numba)
12969 ("python-numpy" ,python-numpy)
12970 ("python-pandas" ,python-pandas)
12971 ("python-psutil" ,python-psutil)
12972 ("python-pysam" ,python-pysam)
12973 ("python-scikit-learn" ,python-scikit-learn)
12974 ("python-seaborn" ,python-seaborn)
12975 ("python-tqdm" ,python-tqdm)
12976 ;; drep is needed for deprecated plot utilities
12977 ("python-drep" ,python-drep)))
12979 `(("python-pytest" ,python-pytest)))
12980 (home-page "https://github.com/MrOlm/inStrain")
12981 (synopsis "Calculation of strain-level metrics")
12983 "inStrain is a Python program for analysis of co-occurring genome
12984 populations from metagenomes that allows highly accurate genome comparisons,
12985 analysis of coverage, microdiversity, and linkage, and sensitive SNP detection
12986 with gene localization and synonymous non-synonymous identification.")
12987 ;; The tool itself says that the license is "MIT", but the repository
12988 ;; contains a LICENSE file with the GPLv3.
12989 ;; See https://github.com/MrOlm/inStrain/issues/51
12990 (license license:expat)))
12992 (define-public gffcompare
12993 (let ((commit "be56ef4349ea3966c12c6397f85e49e047361c41")
12996 (name "gffcompare")
12997 (version (git-version "0.10.15" revision commit))
13001 (uri (git-reference
13002 (url "https://github.com/gpertea/gffcompare/")
13004 (file-name (git-file-name name version))
13006 (base32 "0cp5qpxdhw4mxpya5dld8wi3jk00zyklm6rcri426wydinrnfmkg"))))
13007 (build-system gnu-build-system)
13009 `(#:tests? #f ; no check target
13011 (modify-phases %standard-phases
13012 (delete 'configure)
13013 (add-before 'build 'copy-gclib-source
13014 (lambda* (#:key inputs #:allow-other-keys)
13017 (assoc-ref inputs "gclib-source") "../gclib")
13020 (lambda* (#:key outputs #:allow-other-keys)
13021 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
13022 (install-file "gffcompare" bin)
13025 `(("gclib-source" ; see 'README.md' of gffcompare
13026 ,(let ((commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13029 (version (git-version "0.10.3" revision commit)))
13032 (uri (git-reference
13033 (url "https://github.com/gpertea/gclib/")
13035 (file-name (git-file-name name version))
13037 (base32 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13038 (home-page "https://github.com/gpertea/gffcompare/")
13039 (synopsis "Tool for comparing or classifing transcripts of RNA-Seq")
13041 "@code{gffcompare} is a tool that can:
13043 @item compare and evaluate the accuracy of RNA-Seq transcript assemblers
13044 (Cufflinks, Stringtie);
13045 @item collapse (merge) duplicate transcripts from multiple GTF/GFF3 files (e.g.
13046 resulted from assembly of different samples);
13047 @item classify transcripts from one or multiple GTF/GFF3 files as they relate to
13048 reference transcripts provided in a annotation file (also in GTF/GFF3 format).
13052 license:expat ;license for gffcompare
13053 license:artistic2.0))))) ;license for gclib
13055 (define-public intervaltree
13056 (let ((commit "b90527f9e6d51cd36ecbb50429e4524d3a418ea5"))
13058 (name "intervaltree")
13059 (version (git-version "0.0.0" "1" commit))
13063 (uri (git-reference
13064 (url "https://github.com/ekg/intervaltree/")
13066 (file-name (git-file-name name version))
13068 (base32 "0rgv6q5fl4x5d74n6p5wvdna6zmbdbqpb4jqqh6vq3670gn08xad"))))
13069 (build-system gnu-build-system)
13071 '(#:tests? #f ; No tests.
13072 #:make-flags (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
13075 (modify-phases %standard-phases
13076 (delete 'configure)))) ; There is no configure phase.
13077 (home-page "https://github.com/ekg/intervaltree")
13078 (synopsis "Minimal C++ interval tree implementation")
13079 (description "An interval tree can be used to efficiently find a set of
13080 numeric intervals overlapping or containing another interval. This library
13081 provides a basic implementation of an interval tree using C++ templates,
13082 allowing the insertion of arbitrary types into the tree.")
13083 (license license:expat))))
13085 (define-public python-intervaltree
13087 (name "python-intervaltree")
13092 (uri (pypi-uri "intervaltree" version))
13095 "0wz234g6irlm4hivs2qzmnywk0ss06ckagwh15nflkyb3p462kyb"))))
13096 (build-system python-build-system)
13099 (modify-phases %standard-phases
13100 ;; pytest seems to have a check to make sure the user is testing
13101 ;; their checked-out code and not an installed, potentially
13102 ;; out-of-date copy. This is harmless here, since we just installed
13103 ;; the package, so we disable the check to avoid skipping tests
13105 (add-before 'check 'import-mismatch-error-workaround
13107 (setenv "PY_IGNORE_IMPORTMISMATCH" "1")
13110 `(("python-sortedcontainers" ,python-sortedcontainers)))
13112 `(("python-pytest" ,python-pytest)))
13113 (home-page "https://github.com/chaimleib/intervaltree")
13114 (synopsis "Editable interval tree data structure")
13116 "This package provides a mutable, self-balancing interval tree
13117 implementation for Python. Queries may be by point, by range overlap, or by
13118 range envelopment. This library was designed to allow tagging text and time
13119 intervals, where the intervals include the lower bound but not the upper
13121 (license license:asl2.0)))
13123 (define-public python-pypairix
13125 (name "python-pypairix")
13127 ;; The tarball on pypi does not include the makefile to build the
13132 (uri (git-reference
13133 (url "https://github.com/4dn-dcic/pairix")
13135 (file-name (git-file-name name version))
13138 "1snr3lrmsld8sy77ng6ba6wcmd33xjccf1l2f3m6pi29xis9nd6p"))))
13139 (build-system python-build-system)
13142 (modify-phases %standard-phases
13143 (add-before 'build 'build-programs
13144 (lambda _ (invoke "make")))
13145 (add-after 'install 'install-programs
13146 (lambda* (#:key outputs #:allow-other-keys)
13147 (copy-recursively "bin" (string-append
13148 (assoc-ref outputs "out")
13153 (home-page "https://github.com/4dn-dcic/pairix")
13154 (synopsis "Support for querying pairix-indexed bgzipped text files")
13156 "Pypairix is a Python module for fast querying on a pairix-indexed
13157 bgzipped text file that contains a pair of genomic coordinates per line.")
13158 (license license:expat)))
13160 (define-public python-pyfaidx
13162 (name "python-pyfaidx")
13167 (uri (pypi-uri "pyfaidx" version))
13170 "038xi3a6zvrxbyyfpp64ka8pcjgsdq4fgw9cl5lpxbvmm1bzzw2q"))))
13171 (build-system python-build-system)
13173 `(("python-six" ,python-six)))
13174 (home-page "http://mattshirley.com")
13175 (synopsis "Random access to fasta subsequences")
13177 "This package provides procedures for efficient pythonic random access to
13178 fasta subsequences.")
13179 (license license:bsd-3)))
13181 (define-public python2-pyfaidx
13182 (package-with-python2 python-pyfaidx))
13184 (define-public python-cooler
13186 (name "python-cooler")
13191 (uri (pypi-uri "cooler" version))
13194 "01g6gqix9ba27sappz6nfyiwabzrlf8i5fn8kwcz8ra356cq9crp"))))
13195 (build-system python-build-system)
13197 `(("python-asciitree" ,python-asciitree)
13198 ("python-biopython" ,python-biopython)
13199 ("python-click" ,python-click)
13200 ("python-cytoolz" ,python-cytoolz)
13201 ("python-dask" ,python-dask)
13202 ("python-h5py" ,python-h5py)
13203 ("python-multiprocess" ,python-multiprocess)
13204 ("python-numpy" ,python-numpy)
13205 ("python-pandas" ,python-pandas)
13206 ("python-pyfaidx" ,python-pyfaidx)
13207 ("python-pypairix" ,python-pypairix)
13208 ("python-pysam" ,python-pysam)
13209 ("python-pyyaml" ,python-pyyaml)
13210 ("python-scipy" ,python-scipy)
13211 ("python-simplejson" ,python-simplejson)))
13213 `(("python-mock" ,python-mock)
13214 ("python-pytest" ,python-pytest)))
13215 (home-page "https://github.com/mirnylab/cooler")
13216 (synopsis "Sparse binary format for genomic interaction matrices")
13218 "Cooler is a support library for a sparse, compressed, binary persistent
13219 storage format, called @code{cool}, used to store genomic interaction data,
13220 such as Hi-C contact matrices.")
13221 (license license:bsd-3)))
13223 (define-public python-hicmatrix
13225 (name "python-hicmatrix")
13229 ;; Version 12 is not available on pypi.
13231 (uri (git-reference
13232 (url "https://github.com/deeptools/HiCMatrix")
13234 (file-name (git-file-name name version))
13237 "1xhdyx16f3brgxgxybixdi64ki8nbbkq5vk4h9ahi11pzpjfn1pj"))))
13238 (build-system python-build-system)
13241 (modify-phases %standard-phases
13242 (add-after 'unpack 'relax-requirements
13244 (substitute* '("requirements.txt"
13246 (("cooler *=+ *0.8.5")
13250 `(("python-cooler" ,python-cooler)
13251 ("python-intervaltree" ,python-intervaltree)
13252 ("python-numpy" ,python-numpy)
13253 ("python-pandas" ,python-pandas)
13254 ("python-scipy" ,python-scipy)
13255 ("python-tables" ,python-tables)))
13256 (home-page "https://github.com/deeptools/HiCMatrix/")
13257 (synopsis "HiCMatrix class for HiCExplorer and pyGenomeTracks")
13259 "This helper package implements the @code{HiCMatrix} class for
13260 the HiCExplorer and pyGenomeTracks packages.")
13261 (license license:gpl3+)))
13263 (define-public python-hicexplorer
13265 (name "python-hicexplorer")
13269 ;; The latest version is not available on Pypi.
13271 (uri (git-reference
13272 (url "https://github.com/deeptools/HiCExplorer")
13274 (file-name (git-file-name name version))
13277 "0q5gpbzmrkvygqgw524q36b4nrivcmyi5v194vsx0qw7b3gcmq08"))))
13278 (build-system python-build-system)
13281 (modify-phases %standard-phases
13282 (add-after 'unpack 'loosen-up-requirements
13284 (substitute* "setup.py"
13288 `(("python-biopython" ,python-biopython)
13289 ("python-configparser" ,python-configparser)
13290 ("python-cooler" ,python-cooler)
13291 ("python-future" ,python-future)
13292 ("python-intervaltree" ,python-intervaltree)
13293 ("python-jinja2" ,python-jinja2)
13294 ("python-matplotlib" ,python-matplotlib)
13295 ("python-numpy" ,python-numpy)
13296 ("python-pandas" ,python-pandas)
13297 ("python-pybigwig" ,python-pybigwig)
13298 ("python-pysam" ,python-pysam)
13299 ("python-scipy" ,python-scipy)
13300 ("python-six" ,python-six)
13301 ("python-tables" ,python-tables)
13302 ("python-unidecode" ,python-unidecode)))
13303 (home-page "https://hicexplorer.readthedocs.io")
13304 (synopsis "Process, analyze and visualize Hi-C data")
13306 "HiCExplorer is a powerful and easy to use set of tools to process,
13307 normalize and visualize Hi-C data. HiCExplorer facilitates the creation of
13308 contact matrices, correction of contacts, TAD detection, A/B compartments,
13309 merging, reordering or chromosomes, conversion from different formats
13310 including cooler and detection of long-range contacts. Moreover, it allows
13311 the visualization of multiple contact matrices along with other types of data
13312 like genes, compartments, ChIP-seq coverage tracks (and in general any type of
13313 genomic scores), long range contacts and the visualization of viewpoints.")
13314 (license license:gpl3)))
13316 (define-public python-pygenometracks
13318 (name "python-pygenometracks")
13323 (uri (pypi-uri "pyGenomeTracks" version))
13326 "16laa0wnf4qn9fb9ych4w1vqhqwjss70v0y0f6wp4gwqfrlgac0f"))))
13327 (build-system python-build-system)
13329 `(#:tests? #f ; there are none
13331 (modify-phases %standard-phases
13332 (add-after 'unpack 'relax-requirements
13334 (substitute* "setup.py"
13335 (("matplotlib ==3.1.1")
13336 "matplotlib >=3.1.1"))
13339 `(("python-future" ,python-future)
13340 ("python-gffutils" ,python-gffutils)
13341 ("python-hicmatrix" ,python-hicmatrix)
13342 ("python-intervaltree" ,python-intervaltree)
13343 ("python-matplotlib" ,python-matplotlib)
13344 ("python-numpy" ,python-numpy)
13345 ("python-pybigwig" ,python-pybigwig)
13346 ("python-pysam" ,python-pysam)
13347 ("python-tqdm" ,python-tqdm)))
13349 `(("python-pytest" ,python-pytest)))
13350 (home-page "https://pygenometracks.readthedocs.io")
13351 (synopsis "Program and library to plot beautiful genome browser tracks")
13353 "This package aims to produce high-quality genome browser tracks that
13354 are highly customizable. Currently, it is possible to plot: bigwig, bed (many
13355 options), bedgraph, links (represented as arcs), and Hi-C matrices.
13356 pyGenomeTracks can make plots with or without Hi-C data.")
13357 (license license:gpl3+)))
13359 (define-public python-hic2cool
13361 (name "python-hic2cool")
13366 (uri (pypi-uri "hic2cool" version))
13369 "0xy6mhfns2lzib1kcr6419jjp6pmh0qx8z8na55lmiwn0ds8q9cl"))))
13370 (build-system python-build-system)
13371 (arguments '(#:tests? #f)) ; no tests included
13373 `(("python-cooler" ,python-cooler)))
13374 (home-page "https://github.com/4dn-dcic/hic2cool")
13375 (synopsis "Converter for .hic and .cool files")
13377 "This package provides a converter between @code{.hic} files (from
13378 juicer) and single-resolution or multi-resolution @code{.cool} files (for
13379 cooler). Both @code{hic} and @code{cool} files describe Hi-C contact
13381 (license license:expat)))
13383 (define-public r-pore
13391 (string-append "mirror://sourceforge/rpore/" version
13392 "/poRe_" version ".tar.gz"))
13394 (base32 "0pih9nljbv8g4x8rkk29i7aqq681b782r5s5ynp4nw9yzqnmmksv"))))
13395 (properties `((upstream-name . "poRe")))
13396 (build-system r-build-system)
13398 `(("r-bit64" ,r-bit64)
13399 ("r-data-table" ,r-data-table)
13400 ("r-rhdf5" ,r-rhdf5)
13401 ("r-shiny" ,r-shiny)
13402 ("r-svdialogs" ,r-svdialogs)))
13403 (home-page "https://sourceforge.net/projects/rpore/")
13404 (synopsis "Visualize Nanopore sequencing data")
13406 "This package provides graphical user interfaces to organize and visualize Nanopore
13408 ;; This is free software but the license variant is unclear:
13409 ;; <https://github.com/mw55309/poRe_docs/issues/10>.
13410 (license license:bsd-3)))
13412 (define-public r-xbioc
13413 (let ((revision "1")
13414 (commit "6ff0670a37ab3036aaf1d94aa4b208310946b0b5"))
13417 (version (git-version "0.1.16" revision commit))
13420 (uri (git-reference
13421 (url "https://github.com/renozao/xbioc")
13423 (file-name (git-file-name name version))
13426 "0w8bsq5myiwkfhh83nm6is5ichiyvwa1axx2szvxnzq39x6knf66"))))
13427 (build-system r-build-system)
13429 `(("r-annotationdbi" ,r-annotationdbi)
13430 ("r-assertthat" ,r-assertthat)
13431 ("r-biobase" ,r-biobase)
13432 ("r-biocmanager" ,r-biocmanager)
13433 ("r-digest" ,r-digest)
13434 ("r-pkgmaker" ,r-pkgmaker)
13436 ("r-reshape2" ,r-reshape2)
13437 ("r-stringr" ,r-stringr)))
13438 (home-page "https://github.com/renozao/xbioc/")
13439 (synopsis "Extra base functions for Bioconductor")
13440 (description "This package provides extra utility functions to perform
13441 common tasks in the analysis of omics data, leveraging and enhancing features
13442 provided by Bioconductor packages.")
13443 (license license:gpl3+))))
13445 (define-public r-cssam
13446 (let ((revision "1")
13447 (commit "9ec58c982fa551af0d80b1a266890d92954833f2"))
13450 (version (git-version "1.4" revision commit))
13453 (uri (git-reference
13454 (url "https://github.com/shenorrLab/csSAM")
13456 (file-name (git-file-name name version))
13459 "128syf9v39gk0z3ip000qpsjbg6l1siyq6c8b0hz41dzg5achyb3"))))
13460 (build-system r-build-system)
13462 `(("r-formula" ,r-formula)
13463 ("r-ggplot2" ,r-ggplot2)
13464 ("r-pkgmaker" ,r-pkgmaker)
13466 ("r-rngtools" ,r-rngtools)
13467 ("r-scales" ,r-scales)))
13468 (home-page "https://github.com/shenorrLab/csSAM/")
13469 (synopsis "Cell type-specific statistical analysis of microarray")
13470 (description "This package implements the method csSAM that computes
13471 cell-specific differential expression from measured cell proportions using
13474 (license license:lgpl2.1+))))
13476 (define-public r-bseqsc
13477 (let ((revision "1")
13478 (commit "fef3f3e38dcf3df37103348b5780937982b43b98"))
13481 (version (git-version "1.0" revision commit))
13484 (uri (git-reference
13485 (url "https://github.com/shenorrLab/bseqsc")
13487 (file-name (git-file-name name version))
13490 "1prw13wa20f7wlc3gkkls66n1kxz8d28qrb8icfqdwdnnv8w5qg8"))))
13491 (build-system r-build-system)
13493 `(("r-abind" ,r-abind)
13494 ("r-annotationdbi" ,r-annotationdbi)
13495 ("r-biobase" ,r-biobase)
13496 ("r-cssam" ,r-cssam)
13497 ("r-dplyr" ,r-dplyr)
13498 ("r-e1071" ,r-e1071)
13499 ("r-edger" ,r-edger)
13500 ("r-ggplot2" ,r-ggplot2)
13502 ("r-openxlsx" ,r-openxlsx)
13503 ("r-pkgmaker" ,r-pkgmaker)
13505 ("r-preprocesscore" ,r-preprocesscore)
13506 ("r-rngtools" ,r-rngtools)
13507 ("r-scales" ,r-scales)
13508 ("r-stringr" ,r-stringr)
13509 ("r-xbioc" ,r-xbioc)))
13510 (home-page "https://github.com/shenorrLab/bseqsc")
13511 (synopsis "Deconvolution of bulk sequencing experiments using single cell data")
13512 (description "BSeq-sc is a bioinformatics analysis pipeline that
13513 leverages single-cell sequencing data to estimate cell type proportion and
13514 cell type-specific gene expression differences from RNA-seq data from bulk
13515 tissue samples. This is a companion package to the publication \"A
13516 single-cell transcriptomic map of the human and mouse pancreas reveals inter-
13517 and intra-cell population structure.\" Baron et al. Cell Systems (2016)
13518 @url{https://www.ncbi.nlm.nih.gov/pubmed/27667365}.")
13519 (license license:gpl2+))))
13521 (define-public porechop
13522 ;; The recommended way to install is to clone the git repository
13523 ;; https://github.com/rrwick/Porechop#installation
13524 (let ((commit "289d5dca4a5fc327f97b3f8cecb68ecaf1014861")
13528 (version (git-version "0.2.3" revision commit))
13532 (uri (git-reference
13533 (url "https://github.com/rrwick/Porechop")
13535 (file-name (git-file-name name version))
13537 (base32 "05ps43gig0d3ia9x5lj84lb00hbsl6ba9n7y7jz927npxbr2ym23"))))
13538 (build-system python-build-system)
13539 (home-page "https://github.com/rrwick/porechop")
13540 (synopsis "Finding, trimming or splitting adapters, in Oxford Nanopore reads")
13542 "The porechop package is a tool for finding and removing adapters from Oxford
13543 Nanopore reads. Adapters on the ends of reads are trimmed off, and when a read
13544 has an adapter in its middle, it is treated as chimeric and chopped into
13545 separate reads. Porechop performs thorough alignments to effectively find
13546 adapters, even at low sequence identity. Porechop also supports demultiplexing
13547 of Nanopore reads that were barcoded with the Native Barcoding Kit, PCR
13548 Barcoding Kit or Rapid Barcoding Kit.")
13549 (license license:gpl3+))))
13551 (define-public poretools
13552 ;; The latest release was in 2016 and the latest commit is from 2017
13553 ;; the recommended way to install is to clone the git repository
13554 ;; https://poretools.readthedocs.io/en/latest/content/installation.html
13555 (let ((commit "e426b1f09e86ac259a00c261c79df91510777407")
13559 (version (git-version "0.6.0" revision commit))
13563 (uri (git-reference
13564 (url "https://github.com/arq5x/poretools")
13566 (file-name (git-file-name name version))
13568 (base32 "0bglj833wxpp3cq430p1d3xp085ls221js2y90w7ir2x5ay8l7am"))))
13569 (build-system python-build-system)
13570 ;; requires python >=2.7, <3.0, and the same for python dependencies
13571 (arguments `(#:python ,python-2))
13575 `(("python-dateutil" ,python2-dateutil)
13576 ("python-h5py" ,python2-h5py)
13577 ("python-matplotlib" ,python2-matplotlib)
13578 ("python-pandas" ,python2-pandas)
13579 ("python-seaborn" ,python2-seaborn)))
13580 (home-page "https://poretools.readthedocs.io")
13581 (synopsis "Toolkit for working with nanopore sequencing data")
13583 "The MinION from Oxford Nanopore Technologies is a nanopore sequencer.
13584 This @code{poretools} package is a flexible toolkit for exploring datasets
13585 generated by nanopore sequencing devices for the purposes of quality control and
13586 downstream analysis. Poretools operates directly on the native FAST5, a variant
13587 of the Hierarchical Data Format (HDF5) standard.")
13588 (license license:expat))))
13590 (define-public jamm
13593 (version "1.0.7.6")
13597 (uri (git-reference
13598 (url "https://github.com/mahmoudibrahim/JAMM")
13599 (commit (string-append "JAMMv" version))))
13600 (file-name (git-file-name name version))
13603 "0bsa5mf9n9q5jz7mmacrra41l7r8rac5vgsn6wv1fb52ya58b970"))))
13604 (build-system gnu-build-system)
13606 `(#:tests? #f ; there are none
13608 (modify-phases %standard-phases
13609 (delete 'configure)
13612 (lambda* (#:key inputs outputs #:allow-other-keys)
13613 (let* ((out (assoc-ref outputs "out"))
13614 (libexec (string-append out "/libexec/jamm"))
13615 (bin (string-append out "/bin")))
13616 (substitute* '("JAMM.sh"
13617 "SignalGenerator.sh")
13619 (string-append "sPath=\"" libexec "\"\n")))
13620 (for-each (lambda (file)
13621 (install-file file libexec))
13622 (list "bincalculator.r"
13634 (chmod script #o555)
13635 (install-file script bin)
13636 (wrap-program (string-append bin "/" script)
13637 `("PATH" ":" prefix
13638 (,(string-append (assoc-ref inputs "coreutils") "/bin")
13639 ,(string-append (assoc-ref inputs "gawk") "/bin")
13640 ,(string-append (assoc-ref inputs "perl") "/bin")
13641 ,(string-append (assoc-ref inputs "r-minimal") "/bin")))
13642 `("PERL5LIB" ":" prefix (,(getenv "PERL5LIB")))
13643 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
13644 (list "JAMM.sh" "SignalGenerator.sh")))
13648 ("coreutils" ,coreutils)
13651 ("r-minimal" ,r-minimal)
13652 ;;("r-parallel" ,r-parallel)
13653 ("r-signal" ,r-signal)
13654 ("r-mclust" ,r-mclust)))
13655 (home-page "https://github.com/mahmoudibrahim/JAMM")
13656 (synopsis "Peak finder for NGS datasets")
13658 "JAMM is a peak finder for next generation sequencing datasets (ChIP-Seq,
13659 ATAC-Seq, DNase-Seq, etc.) that can integrate replicates and assign peak
13660 boundaries accurately. JAMM is applicable to both broad and narrow
13662 (license license:gpl3+)))
13664 (define-public ngless
13671 (uri (git-reference
13672 (url "https://gitlab.com/ngless/ngless.git")
13673 (commit (string-append "v" version))))
13674 (file-name (git-file-name name version))
13677 "1wim8wpqyff080dfcazynrmjwqas38m24m0v350w245mmhrapdma"))))
13678 (build-system haskell-build-system)
13680 `(#:haddock? #f ; The haddock phase fails with: NGLess/CmdArgs.hs:20:1:
13681 ; error: parse error on input import
13682 ; import Options.Applicative
13684 (modify-phases %standard-phases
13685 (add-after 'unpack 'create-Versions.hs
13687 (substitute* "Makefile"
13688 (("BWA_VERSION = .*")
13689 (string-append "BWA_VERSION = "
13690 ,(package-version bwa) "\n"))
13691 (("SAM_VERSION = .*")
13692 (string-append "SAM_VERSION = "
13693 ,(package-version samtools) "\n"))
13694 (("PRODIGAL_VERSION = .*")
13695 (string-append "PRODIGAL_VERSION = "
13696 ,(package-version prodigal) "\n"))
13697 (("MINIMAP2_VERSION = .*")
13698 (string-append "MINIMAP2_VERSION = "
13699 ,(package-version minimap2) "\n")))
13700 (invoke "make" "NGLess/Dependencies/Versions.hs")
13702 (add-after 'create-Versions.hs 'create-cabal-file
13703 (lambda _ (invoke "hpack") #t))
13704 ;; These tools are expected to be installed alongside ngless.
13705 (add-after 'install 'link-tools
13706 (lambda* (#:key inputs outputs #:allow-other-keys)
13707 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
13708 (symlink (string-append (assoc-ref inputs "prodigal")
13710 (string-append bin "ngless-" ,version "-prodigal"))
13711 (symlink (string-append (assoc-ref inputs "minimap2")
13713 (string-append bin "ngless-" ,version "-minimap2"))
13714 (symlink (string-append (assoc-ref inputs "samtools")
13716 (string-append bin "ngless-" ,version "-samtools"))
13717 (symlink (string-append (assoc-ref inputs "bwa")
13719 (string-append bin "ngless-" ,version "-bwa"))
13722 `(("prodigal" ,prodigal)
13724 ("samtools" ,samtools)
13725 ("minimap2" ,minimap2)
13726 ("ghc-aeson" ,ghc-aeson)
13727 ("ghc-ansi-terminal" ,ghc-ansi-terminal)
13728 ("ghc-async" ,ghc-async)
13729 ("ghc-atomic-write" ,ghc-atomic-write)
13730 ("ghc-bytestring-lexing" ,ghc-bytestring-lexing)
13731 ("ghc-conduit" ,ghc-conduit)
13732 ("ghc-conduit-algorithms" ,ghc-conduit-algorithms)
13733 ("ghc-conduit-extra" ,ghc-conduit-extra)
13734 ("ghc-configurator" ,ghc-configurator)
13735 ("ghc-convertible" ,ghc-convertible)
13736 ("ghc-data-default" ,ghc-data-default)
13737 ("ghc-diagrams-core" ,ghc-diagrams-core)
13738 ("ghc-diagrams-lib" ,ghc-diagrams-lib)
13739 ("ghc-diagrams-svg" ,ghc-diagrams-svg)
13740 ("ghc-double-conversion" ,ghc-double-conversion)
13741 ("ghc-edit-distance" ,ghc-edit-distance)
13742 ("ghc-either" ,ghc-either)
13743 ("ghc-errors" ,ghc-errors)
13744 ("ghc-extra" ,ghc-extra)
13745 ("ghc-filemanip" ,ghc-filemanip)
13746 ("ghc-file-embed" ,ghc-file-embed)
13747 ("ghc-gitrev" ,ghc-gitrev)
13748 ("ghc-hashtables" ,ghc-hashtables)
13749 ("ghc-http-conduit" ,ghc-http-conduit)
13750 ("ghc-inline-c" ,ghc-inline-c)
13751 ("ghc-inline-c-cpp" ,ghc-inline-c-cpp)
13752 ("ghc-intervalmap" ,ghc-intervalmap)
13753 ("ghc-missingh" ,ghc-missingh)
13754 ("ghc-optparse-applicative" ,ghc-optparse-applicative)
13755 ("ghc-regex" ,ghc-regex)
13756 ("ghc-safe" ,ghc-safe)
13757 ("ghc-safeio" ,ghc-safeio)
13758 ("ghc-strict" ,ghc-strict)
13759 ("ghc-tar" ,ghc-tar)
13760 ("ghc-tar-conduit" ,ghc-tar-conduit)
13761 ("ghc-unliftio" ,ghc-unliftio)
13762 ("ghc-unliftio-core" ,ghc-unliftio-core)
13763 ("ghc-vector" ,ghc-vector)
13764 ("ghc-yaml" ,ghc-yaml)
13765 ("ghc-zlib" ,ghc-zlib)))
13768 ("r-hdf5r" ,r-hdf5r)
13769 ("r-iterators" ,r-iterators)
13770 ("r-itertools" ,r-itertools)
13771 ("r-matrix" ,r-matrix)))
13773 `(("ghc-hpack" ,ghc-hpack)
13774 ("ghc-quickcheck" ,ghc-quickcheck)
13775 ("ghc-test-framework" ,ghc-test-framework)
13776 ("ghc-test-framework-hunit",ghc-test-framework-hunit)
13777 ("ghc-test-framework-quickcheck2" ,ghc-test-framework-quickcheck2)
13778 ("ghc-test-framework-th" ,ghc-test-framework-th)))
13779 (home-page "https://gitlab.com/ngless/ngless")
13780 (synopsis "DSL for processing next-generation sequencing data")
13781 (description "Ngless is a domain-specific language for
13782 @dfn{next-generation sequencing} (NGS) data processing.")
13783 (license license:expat)))
13785 (define-public filtlong
13786 ;; The recommended way to install is to clone the git repository
13787 ;; https://github.com/rrwick/Filtlong#installation
13788 ;; and the lastest release is more than nine months old
13789 (let ((commit "d1bb46dfe8bc7efe6257b5ce222c04bfe8aedaab")
13793 (version (git-version "0.2.0" revision commit))
13797 (uri (git-reference
13798 (url "https://github.com/rrwick/Filtlong")
13800 (file-name (git-file-name name version))
13802 (base32 "1xr92r820x8qlkcr3b57iw223yq8vjgyi42jr79w2xgw47qzr575"))))
13803 (build-system gnu-build-system)
13805 `(#:tests? #f ; no check target
13807 (modify-phases %standard-phases
13808 (delete 'configure)
13810 (lambda* (#:key outputs #:allow-other-keys)
13811 (let* ((out (assoc-ref outputs "out"))
13812 (bin (string-append out "/bin"))
13813 (scripts (string-append out "/share/filtlong/scripts")))
13814 (install-file "bin/filtlong" bin)
13815 (install-file "scripts/histogram.py" scripts)
13816 (install-file "scripts/read_info_histograms.sh" scripts))
13818 (add-after 'install 'wrap-program
13819 (lambda* (#:key inputs outputs #:allow-other-keys)
13820 (let* ((out (assoc-ref outputs "out"))
13821 (path (getenv "PYTHONPATH")))
13822 (wrap-program (string-append out
13823 "/share/filtlong/scripts/histogram.py")
13824 `("PYTHONPATH" ":" prefix (,path))))
13826 (add-before 'check 'patch-tests
13828 (substitute* "scripts/read_info_histograms.sh"
13829 (("awk") (which "gawk")))
13832 `(("gawk" ,gawk) ;for read_info_histograms.sh
13833 ("python" ,python-2) ;required for histogram.py
13835 (home-page "https://github.com/rrwick/Filtlong/")
13836 (synopsis "Tool for quality filtering of Nanopore and PacBio data")
13838 "The Filtlong package is a tool for filtering long reads by quality.
13839 It can take a set of long reads and produce a smaller, better subset. It uses
13840 both read length (longer is better) and read identity (higher is better) when
13841 choosing which reads pass the filter.")
13842 (license (list license:gpl3 ;filtlong
13843 license:asl2.0))))) ;histogram.py
13845 (define-public nanopolish
13846 ;; The recommended way to install is to clone the git repository
13847 ;; <https://github.com/jts/nanopolish#installing-a-particular-release>.
13848 ;; Also, the differences between release and current version seem to be
13850 (let ((commit "6331dc4f15b9dfabb954ba3fae9d76b6c3ca6377")
13853 (name "nanopolish")
13854 (version (git-version "0.11.1" revision commit))
13858 (uri (git-reference
13859 (url "https://github.com/jts/nanopolish")
13862 (file-name (git-file-name name version))
13864 (base32 "15ikl3d37y49pwd7vx36xksgsqajhf24q7qqsnpl15dqqyy5qgbc"))
13865 (modules '((guix build utils)))
13868 (delete-file-recursively "htslib")
13870 (build-system gnu-build-system)
13873 `("HDF5=noinstall" "EIGEN=noinstall" "HTS=noinstall" "CC=gcc")
13874 #:tests? #f ; no check target
13876 (modify-phases %standard-phases
13877 (add-after 'unpack 'find-eigen
13878 (lambda* (#:key inputs #:allow-other-keys)
13880 (string-append (assoc-ref inputs "eigen")
13882 (or (getenv "CPATH") "")))
13884 (delete 'configure)
13886 (lambda* (#:key outputs #:allow-other-keys)
13887 (let* ((out (assoc-ref outputs "out"))
13888 (bin (string-append out "/bin"))
13889 (scripts (string-append out "/share/nanopolish/scripts")))
13891 (install-file "nanopolish" bin)
13892 (for-each (lambda (file) (install-file file scripts))
13893 (find-files "scripts" ".*"))
13895 (add-after 'install 'wrap-programs
13896 (lambda* (#:key outputs #:allow-other-keys)
13897 (let ((pythonpath (getenv "PYTHONPATH"))
13898 (perl5lib (getenv "PERL5LIB"))
13899 (scripts (string-append (assoc-ref outputs "out")
13900 "/share/nanopolish/scripts")))
13901 (for-each (lambda (file)
13902 (wrap-program file `("PYTHONPATH" ":" prefix (,pythonpath))))
13903 (find-files scripts "\\.py"))
13904 (for-each (lambda (file)
13905 (wrap-script file `("PERL5LIB" ":" prefix (,perl5lib))))
13906 (find-files scripts "\\.pl"))))))))
13908 `(("guile" ,guile-3.0) ; for wrappers
13913 ("bioperl" ,bioperl-minimal)
13914 ("perl-getopt-long" ,perl-getopt-long)
13915 ("python" ,python-wrapper)
13916 ("python-biopython" ,python-biopython)
13917 ("python-numpy" ,python-numpy)
13918 ("python-pysam" ,python-pysam)
13919 ("python-scikit-learn" , python-scikit-learn)
13920 ("python-scipy" ,python-scipy)
13922 (home-page "https://github.com/jts/nanopolish")
13923 (synopsis "Signal-level analysis of Oxford Nanopore sequencing data")
13925 "This package analyses the Oxford Nanopore sequencing data at signal-level.
13926 Nanopolish can calculate an improved consensus sequence for a draft genome
13927 assembly, detect base modifications, call SNPs (Single nucleotide
13928 polymorphisms) and indels with respect to a reference genome and more.")
13929 (license license:expat))))
13931 (define-public cnvkit
13938 (uri (git-reference
13939 (url "https://github.com/etal/cnvkit")
13940 (commit (string-append "v" version))))
13941 (file-name (git-file-name name version))
13943 (base32 "0g2f78k68yglmj4fsfmgs8idqv3di9aj53fg0ld0hqljg8chhh82"))))
13944 (build-system python-build-system)
13946 `(("python-biopython" ,python-biopython)
13947 ("python-future" ,python-future)
13948 ("python-matplotlib" ,python-matplotlib)
13949 ("python-numpy" ,python-numpy)
13950 ("python-reportlab" ,python-reportlab)
13951 ("python-pandas" ,python-pandas)
13952 ("python-pysam" ,python-pysam)
13953 ("python-pyfaidx" ,python-pyfaidx)
13954 ("python-scipy" ,python-scipy)
13956 ("r-dnacopy" ,r-dnacopy)))
13957 (home-page "https://cnvkit.readthedocs.org/")
13958 (synopsis "Copy number variant detection from targeted DNA sequencing")
13960 "CNVkit is a Python library and command-line software toolkit to infer
13961 and visualize copy number from high-throughput DNA sequencing data. It is
13962 designed for use with hybrid capture, including both whole-exome and custom
13963 target panels, and short-read sequencing platforms such as Illumina and Ion
13965 (license license:asl2.0)))
13967 (define-public python-pyfit-sne
13969 (name "python-pyfit-sne")
13974 (uri (git-reference
13975 (url "https://github.com/KlugerLab/pyFIt-SNE")
13977 (file-name (git-file-name name version))
13979 (base32 "13wh3qkzs56azmmgnxib6xfr29g7xh09sxylzjpni5j0pp0rc5qw"))))
13980 (build-system python-build-system)
13982 `(("python-numpy" ,python-numpy)))
13986 `(("python-cython" ,python-cython)))
13987 (home-page "https://github.com/KlugerLab/pyFIt-SNE")
13988 (synopsis "FFT-accelerated Interpolation-based t-SNE")
13990 "t-Stochastic Neighborhood Embedding (t-SNE) is a highly successful
13991 method for dimensionality reduction and visualization of high dimensional
13992 datasets. A popular implementation of t-SNE uses the Barnes-Hut algorithm to
13993 approximate the gradient at each iteration of gradient descent. This package
13994 is a Cython wrapper for FIt-SNE.")
13995 (license license:bsd-4)))
13997 (define-public bbmap
14003 (uri (string-append
14004 "mirror://sourceforge/bbmap/BBMap_" version ".tar.gz"))
14007 "1wb94bcc006qq86x77z2rz0lc8m9f1kpnw6gdhjfg9bdaqf56rm3"))))
14008 (build-system ant-build-system)
14010 `(#:build-target "dist"
14011 #:tests? #f ; there are none
14013 (list (string-append "-Dmpijar="
14014 (assoc-ref %build-inputs "java-openmpi")
14016 #:modules ((guix build ant-build-system)
14018 (guix build java-utils))
14020 (modify-phases %standard-phases
14021 (add-after 'build 'build-jni-library
14023 (with-directory-excursion "jni"
14024 (invoke "make" "-f" "makefile.linux"))))
14025 ;; There is no install target
14026 (replace 'install (install-jars "dist"))
14027 (add-after 'install 'install-scripts-and-documentation
14028 (lambda* (#:key outputs #:allow-other-keys)
14029 (substitute* "calcmem.sh"
14030 (("\\| awk ") (string-append "| " (which "awk") " ")))
14031 (let* ((scripts (find-files "." "\\.sh$"))
14032 (out (assoc-ref outputs "out"))
14033 (bin (string-append out "/bin"))
14034 (doc (string-append out "/share/doc/bbmap"))
14035 (jni (string-append out "/lib/jni")))
14036 (substitute* scripts
14037 (("\\$DIR\"\"docs") doc)
14039 (string-append "CP=" out "/share/java/BBTools.jar\n"))
14040 (("^NATIVELIBDIR.*")
14041 (string-append "NATIVELIBDIR=" jni "\n"))
14043 (string-append "CMD=\"" (which "java"))))
14044 (for-each (lambda (script) (install-file script bin)) scripts)
14046 ;; Install JNI library
14047 (install-file "jni/libbbtoolsjni.so" jni)
14049 ;; Install documentation
14050 (install-file "docs/readme.txt" doc)
14051 (copy-recursively "docs/guides" doc))
14056 ("java-eclipse-jdt-core" ,java-eclipse-jdt-core)
14057 ("java-eclipse-jdt-compiler-apt" ,java-eclipse-jdt-compiler-apt)
14058 ("java-openmpi" ,java-openmpi)))
14059 (home-page "https://sourceforge.net/projects/bbmap/")
14060 (synopsis "Aligner and other tools for short sequencing reads")
14062 "This package provides bioinformatic tools to align, deduplicate,
14063 reformat, filter and normalize DNA and RNA-seq data. It includes the
14064 following tools: BBMap, a short read aligner for DNA and RNA-seq data; BBNorm,
14065 a kmer-based error-correction and normalization tool; Dedupe, a tool to
14066 simplify assemblies by removing duplicate or contained subsequences that share
14067 a target percent identity; Reformat, to convert reads between
14068 fasta/fastq/scarf/fasta+qual/sam, interleaved/paired, and ASCII-33/64, at over
14069 500 MB/s; and BBDuk, a tool to filter, trim, or mask reads with kmer matches
14070 to an artifact/contaminant file.")
14071 (license license:bsd-3)))
14073 (define-public velvet
14079 (uri (string-append "https://www.ebi.ac.uk/~zerbino/velvet/"
14080 "velvet_" version ".tgz"))
14083 "0h3njwy66p6bx14r3ar1byb0ccaxmxka4c65rn4iybyiqa4d8kc8"))
14084 ;; Delete bundled libraries
14085 (modules '((guix build utils)))
14088 (delete-file "Manual.pdf")
14089 (delete-file-recursively "third-party")
14091 (build-system gnu-build-system)
14093 `(#:make-flags '("OPENMP=t")
14094 #:test-target "test"
14096 (modify-phases %standard-phases
14097 (delete 'configure)
14098 (add-after 'unpack 'fix-zlib-include
14100 (substitute* "src/binarySequences.c"
14101 (("../third-party/zlib-1.2.3/zlib.h") "zlib.h"))
14104 (lambda* (#:key outputs #:allow-other-keys)
14105 (let* ((out (assoc-ref outputs "out"))
14106 (bin (string-append out "/bin"))
14107 (doc (string-append out "/share/doc/velvet")))
14110 (install-file "velveth" bin)
14111 (install-file "velvetg" bin)
14112 (install-file "Manual.pdf" doc)
14113 (install-file "Columbus_manual.pdf" doc)
14116 `(("openmpi" ,openmpi)
14119 `(("texlive" ,(texlive-union (list texlive-latex-graphics
14120 texlive-latex-hyperref)))))
14121 (home-page "https://www.ebi.ac.uk/~zerbino/velvet/")
14122 (synopsis "Nucleic acid sequence assembler for very short reads")
14124 "Velvet is a de novo genomic assembler specially designed for short read
14125 sequencing technologies, such as Solexa or 454. Velvet currently takes in
14126 short read sequences, removes errors then produces high quality unique
14127 contigs. It then uses paired read information, if available, to retrieve the
14128 repeated areas between contigs.")
14129 (license license:gpl2+)))
14131 (define-public python-velocyto
14133 (name "python-velocyto")
14134 (version "0.17.17")
14138 (uri (pypi-uri "velocyto" version))
14141 "0fgygyzqgrq32dv6a00biq1p1cwi6kbl5iqblxq1kklj6b2mzmhs"))))
14142 (build-system python-build-system)
14144 `(("python-joblib" ,python-joblib)))
14146 `(("python-click" ,python-click)
14147 ("python-cython" ,python-cython)
14148 ("python-h5py" ,python-h5py)
14149 ("python-loompy" ,python-loompy)
14150 ("python-matplotlib" ,python-matplotlib)
14151 ("python-numba" ,python-numba)
14152 ("python-numpy" ,python-numpy)
14153 ("python-pandas" ,python-pandas)
14154 ("python-pysam" ,python-pysam)
14155 ("python-scikit-learn" ,python-scikit-learn)
14156 ("python-scipy" ,python-scipy)))
14157 (home-page "https://github.com/velocyto-team/velocyto.py")
14158 (synopsis "RNA velocity analysis for single cell RNA-seq data")
14160 "Velocyto is a library for the analysis of RNA velocity. Velocyto
14161 includes a command line tool and an analysis pipeline.")
14162 (license license:bsd-2)))
14164 (define-public arriba
14171 (uri (string-append "https://github.com/suhrig/arriba/releases/"
14172 "download/v" version "/arriba_v" version ".tar.gz"))
14175 "0jx9656ry766vb8z08m1c3im87b0c82qpnjby9wz4kcz8vn87dx2"))))
14176 (build-system gnu-build-system)
14178 `(#:tests? #f ; there are none
14180 (modify-phases %standard-phases
14181 (replace 'configure
14182 (lambda* (#:key inputs #:allow-other-keys)
14183 (let ((htslib (assoc-ref inputs "htslib")))
14184 (substitute* "Makefile"
14185 (("-I\\$\\(HTSLIB\\)/htslib")
14186 (string-append "-I" htslib "/include/htslib"))
14187 ((" \\$\\(HTSLIB\\)/libhts.a")
14188 (string-append " " htslib "/lib/libhts.so"))))
14189 (substitute* "run_arriba.sh"
14190 (("^STAR ") (string-append (which "STAR") " "))
14191 (("samtools --version-only")
14192 (string-append (which "samtools") " --version-only"))
14193 (("samtools index")
14194 (string-append (which "samtools") " index"))
14196 (string-append (which "samtools") " sort")))
14199 (lambda* (#:key outputs #:allow-other-keys)
14200 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
14201 (install-file "arriba" bin)
14202 (install-file "run_arriba.sh" bin)
14203 (install-file "draw_fusions.R" bin)
14204 (wrap-program (string-append bin "/draw_fusions.R")
14205 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
14208 `(("htslib" ,htslib)
14209 ("r-minimal" ,r-minimal)
14210 ("r-circlize" ,r-circlize)
14211 ("r-genomicalignments" ,r-genomicalignments)
14212 ("r-genomicranges" ,r-genomicranges)
14213 ("samtools" ,samtools)
14216 (home-page "https://github.com/suhrig/arriba")
14217 (synopsis "Gene fusion detection from RNA-Seq data ")
14219 "Arriba is a command-line tool for the detection of gene fusions from
14220 RNA-Seq data. It was developed for the use in a clinical research setting.
14221 Therefore, short runtimes and high sensitivity were important design criteria.
14222 It is based on the fast STAR aligner and the post-alignment runtime is
14223 typically just around two minutes. In contrast to many other fusion detection
14224 tools which build on STAR, Arriba does not require to reduce the
14225 @code{alignIntronMax} parameter of STAR to detect small deletions.")
14226 ;; All code is under the Expat license with the exception of
14227 ;; "draw_fusions.R", which is under GPLv3.
14228 (license (list license:expat license:gpl3))))
14230 (define-public adapterremoval
14232 (name "adapterremoval")
14237 (uri (git-reference
14238 (url "https://github.com/MikkelSchubert/adapterremoval")
14239 (commit (string-append "v" version))))
14240 (file-name (git-file-name name version))
14243 "1nf3ki5pfzalhrx2fr1y6pfqfi133yj2m7q4fj9irf5fb94bapwr"))))
14244 (build-system gnu-build-system)
14246 `(#:make-flags (list "COLOR_BUILD=no"
14247 (string-append "PREFIX="
14248 (assoc-ref %outputs "out")))
14249 #:test-target "test"
14251 (modify-phases %standard-phases
14252 (delete 'configure))))
14255 (home-page "https://adapterremoval.readthedocs.io/")
14256 (synopsis "Rapid sequence adapter trimming, identification, and read merging")
14258 "This program searches for and removes remnant adapter sequences from
14259 @dfn{High-Throughput Sequencing} (HTS) data and (optionally) trims low quality
14260 bases from the 3' end of reads following adapter removal. AdapterRemoval can
14261 analyze both single end and paired end data, and can be used to merge
14262 overlapping paired-ended reads into (longer) consensus sequences.
14263 Additionally, the AdapterRemoval may be used to recover a consensus adapter
14264 sequence for paired-ended data, for which this information is not available.")
14265 (license license:gpl3+)))
14267 (define-public pplacer
14268 (let ((commit "807f6f3"))
14271 ;; The commit should be updated with each version change.
14272 (version "1.1.alpha19")
14276 (uri (git-reference
14277 (url "https://github.com/matsen/pplacer")
14278 (commit (string-append "v" version))))
14279 (file-name (git-file-name name version))
14281 (base32 "11ppbbbx20p2g9wj3ff64dhnarb12q79v7qh4rk0gj6lkbz4n7cn"))))
14282 (build-system ocaml-build-system)
14284 `(#:modules ((guix build ocaml-build-system)
14288 (modify-phases %standard-phases
14289 (delete 'configure)
14290 (add-after 'unpack 'fix-build-with-latest-ocaml
14292 (substitute* "myocamlbuild.ml"
14293 (("dep \\[\"c_pam\"\\]" m)
14294 (string-append "flag [\"ocaml\"; \"compile\"] (A \"-unsafe-string\");\n"
14296 (("let run_and_read" m)
14301 let pos = String.index s ch in
14302 x := (String.before s pos)::!x;
14303 go (String.after s (pos + 1))
14306 with Not_found -> !x
14307 let split_nl s = split s '\\n'
14308 let before_space s =
14309 try String.before s (String.index s ' ')
14310 with Not_found -> s
14313 (("run_and_read \"ocamlfind list \\| cut -d' ' -f1\"" m)
14314 (string-append "List.map before_space (split_nl & " m ")"))
14315 ((" blank_sep_strings &") "")
14316 ((" Lexing.from_string &") ""))
14318 (add-after 'unpack 'replace-bundled-cddlib
14319 (lambda* (#:key inputs #:allow-other-keys)
14320 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
14321 (local-dir "cddlib_guix"))
14323 (with-directory-excursion local-dir
14324 (invoke "tar" "xvf" cddlib-src))
14325 (let ((cddlib-src-folder
14326 (string-append local-dir "/"
14327 (list-ref (scandir local-dir) 2)
14329 (for-each make-file-writable (find-files "cdd_src" ".*"))
14333 (string-append "cdd_src/" (basename file))))
14334 (find-files cddlib-src-folder ".*[ch]$")))
14336 (add-after 'unpack 'fix-makefile
14338 ;; Remove system calls to 'git'.
14339 (substitute* "Makefile"
14340 (("^DESCRIPT:=pplacer-.*")
14342 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
14343 (substitute* "myocamlbuild.ml"
14344 (("git describe --tags --long .*\\\" with")
14346 "echo -n v" ,version "-" ,commit "\" with")))
14349 (lambda* (#:key outputs #:allow-other-keys)
14350 (let* ((out (assoc-ref outputs "out"))
14351 (bin (string-append out "/bin")))
14352 (copy-recursively "bin" bin))
14354 #:ocaml ,ocaml-4.07
14355 #:findlib ,ocaml4.07-findlib))
14357 `(("zlib" ,zlib "static")
14359 ("ocaml-ounit" ,(package-with-ocaml4.07 ocaml-ounit))
14360 ("ocaml-batteries" ,(package-with-ocaml4.07 ocaml-batteries))
14361 ("ocaml-camlzip" ,(package-with-ocaml4.07 camlzip))
14362 ("ocaml-csv" ,(package-with-ocaml4.07 ocaml-csv))
14363 ("ocaml-sqlite3" ,ocaml4.07-sqlite3)
14364 ("ocaml-xmlm" ,(package-with-ocaml4.07 ocaml-xmlm))
14365 ("ocaml-mcl" ,(package-with-ocaml4.07 ocaml-mcl))
14366 ("ocaml-gsl" ,ocaml4.07-gsl-1)))
14368 `(("cddlib-src" ,(package-source cddlib))
14369 ("ocamlbuild" ,(package-with-ocaml4.07 ocamlbuild))
14370 ("pkg-config" ,pkg-config)))
14372 `(("pplacer-scripts" ,pplacer-scripts)))
14373 (synopsis "Phylogenetic placement of biological sequences")
14375 "Pplacer places query sequences on a fixed reference phylogenetic tree
14376 to maximize phylogenetic likelihood or posterior probability according to a
14377 reference alignment. Pplacer is designed to be fast, to give useful
14378 information about uncertainty, and to offer advanced visualization and
14379 downstream analysis.")
14380 (home-page "https://matsen.fhcrc.org/pplacer/")
14381 (license license:gpl3))))
14383 ;; This package is installed alongside 'pplacer'. It is a separate package so
14384 ;; that it can use the python-build-system for the scripts that are
14385 ;; distributed alongside the main OCaml binaries.
14386 (define pplacer-scripts
14389 (name "pplacer-scripts")
14390 (build-system python-build-system)
14392 `(#:python ,python-2
14394 (modify-phases %standard-phases
14395 (add-after 'unpack 'enter-scripts-dir
14396 (lambda _ (chdir "scripts") #t))
14398 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t))
14399 (add-after 'install 'wrap-executables
14400 (lambda* (#:key inputs outputs #:allow-other-keys)
14401 (let* ((out (assoc-ref outputs "out"))
14402 (bin (string-append out "/bin")))
14403 (let ((path (string-append
14404 (assoc-ref inputs "hmmer") "/bin:"
14405 (assoc-ref inputs "infernal") "/bin")))
14407 (wrap-program (string-append bin "/refpkg_align.py")
14408 `("PATH" ":" prefix (,path))))
14409 (let ((path (string-append
14410 (assoc-ref inputs "hmmer") "/bin")))
14411 (wrap-program (string-append bin "/hrefpkg_query.py")
14412 `("PATH" ":" prefix (,path)))))
14415 `(("infernal" ,infernal)
14418 `(("python-biopython" ,python2-biopython)
14419 ("taxtastic" ,taxtastic)))
14420 (synopsis "Pplacer Python scripts")))
14422 (define-public python2-checkm-genome
14424 (name "python2-checkm-genome")
14429 (uri (pypi-uri "checkm-genome" version))
14432 "0bm8gpxjmzxsxxl8lzwqhgx8g1dlnmp6znz7wv3hgb0gdjbf9dzz"))))
14433 (build-system python-build-system)
14435 `(#:python ,python-2
14436 #:tests? #f)) ; some tests are interactive
14438 `(("python-dendropy" ,python2-dendropy)
14439 ("python-matplotlib" ,python2-matplotlib)
14440 ("python-numpy" ,python2-numpy)
14441 ("python-pysam" ,python2-pysam)
14442 ("python-scipy" ,python2-scipy)))
14443 (home-page "https://pypi.org/project/Checkm/")
14444 (synopsis "Assess the quality of putative genome bins")
14446 "CheckM provides a set of tools for assessing the quality of genomes
14447 recovered from isolates, single cells, or metagenomes. It provides robust
14448 estimates of genome completeness and contamination by using collocated sets of
14449 genes that are ubiquitous and single-copy within a phylogenetic lineage.
14450 Assessment of genome quality can also be examined using plots depicting key
14451 genomic characteristics (e.g., GC, coding density) which highlight sequences
14452 outside the expected distributions of a typical genome. CheckM also provides
14453 tools for identifying genome bins that are likely candidates for merging based
14454 on marker set compatibility, similarity in genomic characteristics, and
14455 proximity within a reference genome.")
14456 (license license:gpl3+)))
14458 (define-public umi-tools
14465 (uri (pypi-uri "umi_tools" version))
14468 "08y3vz1vcx09whmbsn722lcs6jl9wyrh9i4p3k8j4cb1i32bij4a"))))
14469 (build-system python-build-system)
14471 `(("python-pandas" ,python-pandas)
14472 ("python-future" ,python-future)
14473 ("python-scipy" ,python-scipy)
14474 ("python-matplotlib" ,python-matplotlib)
14475 ("python-regex" ,python-regex)
14476 ("python-pysam" ,python-pysam)))
14478 `(("python-cython" ,python-cython)))
14479 (home-page "https://github.com/CGATOxford/UMI-tools")
14480 (synopsis "Tools for analyzing unique modular identifiers")
14481 (description "This package provides tools for dealing with @dfn{Unique
14482 Molecular Identifiers} (UMIs) and @dfn{Random Molecular Tags} (RMTs) in
14483 genetic sequences. There are six tools: the @code{extract} and
14484 @code{whitelist} commands are used to prepare a fastq containing UMIs @code{+/-}
14485 cell barcodes for alignment. The remaining commands, @code{group},
14486 @code{dedup}, and @{count}/@code{count_tab}, are used to identify PCR
14487 duplicates using the UMIs and perform different levels of analysis depending
14488 on the needs of the user.")
14489 (license license:expat)))
14491 (define-public ataqv
14498 (uri (git-reference
14499 (url "https://github.com/ParkerLab/ataqv")
14501 (file-name (git-file-name name version))
14504 "031xr6jx1aprh26y5b1lv3gzrlmzg4alfl73vvshymx8cq8asrqi"))))
14505 (build-system gnu-build-system)
14508 (list (string-append "prefix=" (assoc-ref %outputs "out"))
14509 (string-append "BOOST_ROOT="
14510 (assoc-ref %build-inputs "boost"))
14511 (string-append "HTSLIB_ROOT="
14512 (assoc-ref %build-inputs "htslib")))
14513 #:test-target "test"
14515 (modify-phases %standard-phases
14516 (delete 'configure))))
14520 ("ncurses" ,ncurses)
14524 (home-page "https://github.com/ParkerLab/ataqv")
14525 (synopsis "Toolkit for quality control and visualization of ATAC-seq data")
14526 (description "This package provides a toolkit for measuring and comparing
14527 ATAC-seq results. It was written to make it easier to spot differences that
14528 might be caused by ATAC-seq library prep or sequencing. The main program,
14529 @code{ataqv}, examines aligned reads and reports some basic metrics.")
14530 (license license:gpl3+)))
14532 (define-public r-psiplot
14539 (uri (git-reference
14540 (url "https://github.com/kcha/psiplot")
14541 (commit (string-append "v" version))))
14542 (file-name (git-file-name name version))
14544 (base32 "08438h16cfry5kqh3y9hs8q1b1a8bxhblsm75knviz5r6q0n1jxh"))))
14545 (build-system r-build-system)
14547 `(("r-mass" ,r-mass)
14548 ("r-dplyr" ,r-dplyr)
14549 ("r-tidyr" ,r-tidyr)
14550 ("r-purrr" ,r-purrr)
14551 ("r-readr" ,r-readr)
14552 ("r-magrittr" ,r-magrittr)
14553 ("r-ggplot2" ,r-ggplot2)))
14554 (home-page "https://github.com/kcha/psiplot")
14555 (synopsis "Plot percent spliced-in values of alternatively-spliced exons")
14557 "PSIplot is an R package for generating plots of @dfn{percent
14558 spliced-in} (PSI) values of alternatively-spliced exons that were computed by
14559 vast-tools, an RNA-Seq pipeline for alternative splicing analysis. The plots
14560 are generated using @code{ggplot2}.")
14561 (license license:expat)))
14563 (define-public python-ont-fast5-api
14565 (name "python-ont-fast5-api")
14570 (uri (git-reference
14571 (url "https://github.com/nanoporetech/ont_fast5_api")
14572 (commit (string-append "release_" version))))
14573 (file-name (git-file-name name version))
14576 "03cbq4zbbwhll8ml2m9k8sa31mirsvcbjkrq1yna0kkzz9fad5fm"))))
14577 (build-system python-build-system)
14579 `(("python-numpy" ,python-numpy)
14580 ("python-six" ,python-six)
14581 ("python-h5py" ,python-h5py)
14582 ("python-progressbar33" ,python-progressbar33)))
14583 (home-page "https://github.com/nanoporetech/ont_fast5_api")
14584 (synopsis "Interface to HDF5 files of the Oxford Nanopore fast5 file format")
14586 "This package provides a concrete implementation of the fast5 file schema
14587 using the generic @code{h5py} library, plain-named methods to interact with
14588 and reflect the fast5 file schema, and tools to convert between
14589 @code{multi_read} and @code{single_read} formats.")
14590 (license license:mpl2.0)))
14592 (define-public tbsp
14593 (let ((commit "ec8fff4410cfb13a677dbbb95cbbc60217e64907")
14597 (version (git-version "1.0.0" revision commit))
14601 (uri (git-reference
14602 (url "https://github.com/phoenixding/tbsp")
14604 (file-name (git-file-name name version))
14607 "025ym14x8gbd6hb55lsinqj6f5qzw36i10klgs7ldzxxd7s39ki1"))))
14608 (build-system python-build-system)
14609 (arguments '(#:tests? #f)) ; no tests included
14611 `(("python-matplotlib" ,python-matplotlib)
14612 ("python-networkx" ,python-networkx)
14613 ("python-numpy" ,python-numpy)
14614 ("python-pybigwig" ,python-pybigwig)
14615 ("python-biopython" ,python-biopython)
14616 ("python-scikit-learn" ,python-scikit-learn)
14617 ("python-scipy" ,python-scipy)))
14618 (home-page "https://github.com/phoenixding/tbsp/")
14619 (synopsis "SNP-based trajectory inference")
14621 "Several studies focus on the inference of developmental and response
14622 trajectories from single cell RNA-Seq (scRNA-Seq) data. A number of
14623 computational methods, often referred to as pseudo-time ordering, have been
14624 developed for this task. CRISPR has also been used to reconstruct lineage
14625 trees by inserting random mutations. The tbsp package implements an
14626 alternative method to detect significant, cell type specific sequence
14627 mutations from scRNA-Seq data.")
14628 (license license:expat))))
14630 (define-public tabixpp
14636 (uri (git-reference
14637 (url "https://github.com/ekg/tabixpp")
14638 (commit (string-append "v" version))))
14639 (file-name (git-file-name name version))
14641 (base32 "1k2a3vbq96ic4lw72iwp5s3mwwc4xhdffjj584yn6l9637q9j1yd"))
14642 (modules '((guix build utils)))
14645 (delete-file-recursively "htslib") #t))))
14646 (build-system gnu-build-system)
14648 `(("htslib" ,htslib)
14651 `(#:tests? #f ; There are no tests to run.
14653 (modify-phases %standard-phases
14654 (delete 'configure) ; There is no configure phase.
14655 ;; The build phase needs overriding the location of htslib.
14657 (lambda* (#:key inputs #:allow-other-keys)
14658 (let ((htslib-ref (assoc-ref inputs "htslib")))
14660 (string-append "HTS_LIB=" htslib-ref "/lib/libhts.a")
14661 (string-append "INCLUDES= -I" htslib-ref "/include/htslib")
14662 "HTS_HEADERS=" ; No need to check for headers here.
14663 (string-append "LIBPATH=-L. -L" htslib-ref "/include"))
14664 (invoke "g++" "-shared" "-o" "libtabixpp.so" "tabix.o" "-lhts")
14665 (invoke "ar" "rcs" "libtabixpp.a" "tabix.o"))))
14667 (lambda* (#:key outputs #:allow-other-keys)
14668 (let* ((out (assoc-ref outputs "out"))
14669 (lib (string-append out "/lib"))
14670 (bin (string-append out "/bin")))
14671 (install-file "tabix++" bin)
14672 (install-file "libtabixpp.so" lib)
14673 (install-file "libtabixpp.a" lib)
14674 (install-file "tabix.hpp" (string-append out "/include"))
14675 (mkdir-p (string-append lib "/pkgconfig"))
14676 (with-output-to-file (string-append lib "/pkgconfig/tabixpp.pc")
14678 (format #t "prefix=~a~@
14679 exec_prefix=${prefix}~@
14680 libdir=${exec_prefix}/lib~@
14681 includedir=${prefix}/include~@
14686 Description: C++ wrapper around tabix project~@
14687 Libs: -L${libdir} -ltabixpp~@
14688 Cflags: -I${includedir}~%"
14691 (home-page "https://github.com/ekg/tabixpp")
14692 (synopsis "C++ wrapper around tabix project")
14693 (description "This is a C++ wrapper around the Tabix project which abstracts
14694 some of the details of opening and jumping in tabix-indexed files.")
14695 (license license:expat)))
14697 (define-public smithwaterman
14698 (let ((commit "2610e259611ae4cde8f03c72499d28f03f6d38a7"))
14700 (name "smithwaterman")
14701 (version (git-version "0.0.0" "2" commit))
14704 (uri (git-reference
14705 (url "https://github.com/ekg/smithwaterman/")
14707 (file-name (git-file-name name version))
14709 (base32 "0i9d8zrxpiracw3mxzd9siybpy62p06rqz9mc2w93arajgbk45bs"))))
14710 (build-system gnu-build-system)
14712 `(#:tests? #f ; There are no tests to run.
14713 #:make-flags '("libsw.a" "all")
14715 (modify-phases %standard-phases
14716 (delete 'configure) ; There is no configure phase.
14717 (add-after 'unpack 'patch-source
14719 (substitute* "Makefile"
14720 (("-c ") "-c -fPIC "))
14722 (add-after 'build 'build-dynamic
14725 "-shared" "-o" "libsmithwaterman.so"
14726 "smithwaterman.o" "SmithWatermanGotoh.o"
14727 "disorder.o" "BandedSmithWaterman.o"
14728 "LeftAlign.o" "Repeats.o" "IndelAllele.o")))
14730 (lambda* (#:key outputs #:allow-other-keys)
14731 (let* ((out (assoc-ref outputs "out"))
14732 (bin (string-append out "/bin"))
14733 (lib (string-append out "/lib")))
14734 (install-file "smithwaterman" bin)
14737 (install-file file (string-append out "/include/smithwaterman")))
14738 (find-files "." "\\.h$"))
14739 (install-file "libsmithwaterman.so" lib)
14740 (install-file "libsw.a" lib)
14741 (mkdir-p (string-append lib "/pkgconfig"))
14742 (with-output-to-file (string-append lib "/pkgconfig/smithwaterman.pc")
14744 (format #t "prefix=~a~@
14745 exec_prefix=${prefix}~@
14746 libdir=${exec_prefix}/lib~@
14747 includedir=${prefix}/include/smithwaterman~@
14750 Name: smithwaterman~@
14752 Description: smith-waterman-gotoh alignment algorithm~@
14753 Libs: -L${libdir} -lsmithwaterman~@
14754 Cflags: -I${includedir}~%"
14757 (home-page "https://github.com/ekg/smithwaterman")
14758 (synopsis "Implementation of the Smith-Waterman algorithm")
14759 (description "Implementation of the Smith-Waterman algorithm.")
14760 ;; The licensing terms are unclear: https://github.com/ekg/smithwaterman/issues/9.
14761 (license (list license:gpl2 license:expat)))))
14763 (define-public multichoose
14765 (name "multichoose")
14769 (uri (git-reference
14770 (url "https://github.com/ekg/multichoose/")
14771 (commit (string-append "v" version))))
14772 (file-name (git-file-name name version))
14774 (base32 "0ci5fqvmpamwgxvmyd79ygj6n3bnbl3vc7b6h1sxz58186sm3pfs"))))
14775 (build-system gnu-build-system)
14777 `(#:tests? #f ; Tests require node.
14779 (modify-phases %standard-phases
14780 (delete 'configure) ; There is no configure phase.
14782 (lambda* (#:key outputs #:allow-other-keys)
14783 (let* ((out (assoc-ref outputs "out"))
14784 (bin (string-append out "/bin"))
14785 (include (string-append out "/include")))
14786 ;; TODO: There are Python modules for these programs too.
14787 (install-file "multichoose" bin)
14788 (install-file "multipermute" bin)
14789 (install-file "multichoose.h" include)
14790 (install-file "multipermute.h" include))
14792 (home-page "https://github.com/ekg/multichoose")
14793 (synopsis "Efficient loopless multiset combination generation algorithm")
14794 (description "This library implements an efficient loopless multiset
14795 combination generation algorithm which is (approximately) described in
14796 \"Loopless algorithms for generating permutations, combinations, and other
14797 combinatorial configurations.\", G. Ehrlich - Journal of the ACM (JACM),
14798 1973. (Algorithm 7.)")
14799 (license license:expat)))
14801 (define-public fsom
14802 (let ((commit "a6ef318fbd347c53189384aef7f670c0e6ce89a3"))
14805 (version (git-version "0.0.0" "1" commit))
14808 (uri (git-reference
14809 (url "https://github.com/ekg/fsom/")
14811 (file-name (git-file-name name version))
14813 (base32 "0gw1lpvr812pywg9y546x0h1hhj261xwls41r6kqhddjlrcjc0pi"))))
14814 (build-system gnu-build-system)
14816 `(#:tests? #f ; There are no tests to run.
14818 (modify-phases %standard-phases
14819 (delete 'configure) ; There is no configure phase.
14821 (lambda* (#:key outputs #:allow-other-keys)
14822 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
14823 (install-file "fsom" bin))
14825 (home-page "https://github.com/ekg/fsom")
14826 (synopsis "Manage SOM (Self-Organizing Maps) neural networks")
14827 (description "A tiny C library for managing SOM (Self-Organizing Maps)
14829 (license license:gpl3))))
14831 (define-public fastahack
14837 (uri (git-reference
14838 (url "https://github.com/ekg/fastahack/")
14839 (commit (string-append "v" version))))
14840 (file-name (git-file-name name version))
14842 (base32 "0rp1blskhzxf7vbh253ibpxbgl9wwgyzf1wbkxndi08d3j4vcss9"))))
14843 (build-system gnu-build-system)
14845 `(#:tests? #f ; Unclear how to run tests: https://github.com/ekg/fastahack/issues/15
14847 (modify-phases %standard-phases
14848 (delete 'configure) ; There is no configure phase.
14849 (add-after 'unpack 'patch-source
14851 (substitute* "Makefile"
14852 (("-c ") "-c -fPIC "))
14854 (add-after 'build 'build-dynamic
14857 "-shared" "-o" "libfastahack.so"
14858 "Fasta.o" "FastaHack.o" "split.o" "disorder.o")))
14860 (lambda* (#:key outputs #:allow-other-keys)
14861 (let* ((out (assoc-ref outputs "out"))
14862 (lib (string-append out "/lib"))
14863 (bin (string-append out "/bin")))
14864 (mkdir-p (string-append out "/include/fastahack"))
14867 (install-file file (string-append out "/include/fastahack")))
14868 (find-files "." "\\.h$"))
14869 (install-file "fastahack" bin)
14870 (install-file "libfastahack.so" lib)
14871 (mkdir-p (string-append lib "/pkgconfig"))
14872 (with-output-to-file (string-append lib "/pkgconfig/fastahack.pc")
14874 (format #t "prefix=~a~@
14875 exec_prefix=${prefix}~@
14876 libdir=${exec_prefix}/lib~@
14877 includedir=${prefix}/include/fastahack~@
14882 Description: Indexing and sequence extraction from FASTA files~@
14883 Libs: -L${libdir} -lfastahack~@
14884 Cflags: -I${includedir}~%"
14887 (home-page "https://github.com/ekg/fastahack")
14888 (synopsis "Indexing and sequence extraction from FASTA files")
14889 (description "Fastahack is a small application for indexing and
14890 extracting sequences and subsequences from FASTA files. The included library
14891 provides a FASTA reader and indexer that can be embedded into applications
14892 which would benefit from directly reading subsequences from FASTA files. The
14893 library automatically handles index file generation and use.")
14894 (license (list license:expat license:gpl2))))
14896 (define-public vcflib
14903 (uri (git-reference
14904 (url "https://github.com/vcflib/vcflib")
14905 (commit (string-append "v" version))))
14906 (file-name (git-file-name name version))
14908 (base32 "1k1z3876kbzifj1sqfzsf3lgb4rw779hvkg6ryxbyq5bc2paj9kh"))
14909 (modules '((guix build utils)))
14912 (substitute* "CMakeLists.txt"
14913 ((".*fastahack.*") "")
14914 ((".*smithwaterman.*") "")
14915 (("(pkg_check_modules\\(TABIXPP)" text)
14917 "pkg_check_modules(FASTAHACK REQUIRED fastahack)\n"
14918 "pkg_check_modules(SMITHWATERMAN REQUIRED smithwaterman)\n"
14920 (("\\$\\{TABIXPP_LIBRARIES\\}" text)
14921 (string-append "${FASTAHACK_LIBRARIES} "
14922 "${SMITHWATERMAN_LIBRARIES} "
14924 (substitute* (find-files "." "\\.(h|c)(pp)?$")
14925 (("\"SmithWatermanGotoh.h\"") "<smithwaterman/SmithWatermanGotoh.h>")
14926 (("\"convert.h\"") "<smithwaterman/convert.h>")
14927 (("\"disorder.h\"") "<smithwaterman/disorder.h>")
14928 (("Fasta.h") "fastahack/Fasta.h"))
14929 (for-each delete-file-recursively
14930 '("fastahack" "filevercmp" "fsom" "googletest" "intervaltree"
14931 "libVCFH" "multichoose" "smithwaterman"))
14933 (build-system cmake-build-system)
14937 ("fastahack" ,fastahack)
14940 ("smithwaterman" ,smithwaterman)
14941 ("tabixpp" ,tabixpp)
14945 `(("pkg-config" ,pkg-config)
14947 ;; This package builds against the .o files so we need to extract the source.
14948 ("filevercmp-src" ,(package-source filevercmp))
14949 ("fsom-src" ,(package-source fsom))
14950 ("intervaltree-src" ,(package-source intervaltree))
14951 ("multichoose-src" ,(package-source multichoose))))
14953 `(#:tests? #f ; no tests
14955 (modify-phases %standard-phases
14956 (add-after 'unpack 'build-shared-library
14958 (substitute* "CMakeLists.txt"
14959 (("vcflib STATIC") "vcflib SHARED"))
14960 (substitute* "test/Makefile"
14961 (("libvcflib.a") "libvcflib.so"))
14963 (add-after 'unpack 'unpack-submodule-sources
14964 (lambda* (#:key inputs #:allow-other-keys)
14965 (let ((unpack (lambda (source target)
14967 (with-directory-excursion target
14968 (if (file-is-directory? (assoc-ref inputs source))
14969 (copy-recursively (assoc-ref inputs source) ".")
14970 (invoke "tar" "xvf"
14971 (assoc-ref inputs source)
14972 "--strip-components=1"))))))
14974 (unpack "filevercmp-src" "filevercmp")
14975 (unpack "fsom-src" "fsom")
14976 (unpack "intervaltree-src" "intervaltree")
14977 (unpack "multichoose-src" "multichoose"))
14979 ;; This pkg-config file is provided by other distributions.
14980 (add-after 'install 'install-pkg-config-file
14981 (lambda* (#:key outputs #:allow-other-keys)
14982 (let* ((out (assoc-ref outputs "out"))
14983 (pkgconfig (string-append out "/lib/pkgconfig")))
14984 (mkdir-p pkgconfig)
14985 (with-output-to-file (string-append pkgconfig "/vcflib.pc")
14987 (format #t "prefix=~a~@
14988 exec_prefix=${prefix}~@
14989 libdir=${exec_prefix}/lib~@
14990 includedir=${prefix}/include~@
14994 Requires: smithwaterman, fastahack, tabixpp~@
14995 Description: C++ library for parsing and manipulating VCF files~@
14996 Libs: -L${libdir} -lvcflib~@
14997 Cflags: -I${includedir}~%"
15000 (home-page "https://github.com/vcflib/vcflib/")
15001 (synopsis "Library for parsing and manipulating VCF files")
15002 (description "Vcflib provides methods to manipulate and interpret
15003 sequence variation as it can be described by VCF. It is both an API for parsing
15004 and operating on records of genomic variation as it can be described by the VCF
15005 format, and a collection of command-line utilities for executing complex
15006 manipulations on VCF files.")
15007 (license license:expat)))
15009 (define-public freebayes
15015 (uri (git-reference
15016 (url "https://github.com/freebayes/freebayes")
15017 (commit (string-append "v" version))))
15018 (file-name (git-file-name name version))
15020 (base32 "0myz3giad7jqp6ricdfnig9ymlcps2h67mlivadvx97ngagm85z8"))
15021 (patches (search-patches "freebayes-devendor-deps.patch"))
15022 (modules '((guix build utils)))
15025 (delete-file-recursively "contrib/htslib")
15027 (build-system meson-build-system)
15029 `(("fastahack" ,fastahack)
15031 ("smithwaterman" ,smithwaterman)
15032 ("tabixpp" ,tabixpp)
15036 `(("bash-tap" ,bash-tap)
15038 ("grep" ,grep) ; Built with perl support.
15039 ("parallel" ,parallel)
15041 ("pkg-config" ,pkg-config)
15042 ("samtools" ,samtools)
15044 ;; This submodule is needed to run the tests.
15045 ("test-simple-bash-src"
15048 (uri (git-reference
15049 (url "https://github.com/ingydotnet/test-simple-bash/")
15050 (commit "124673ff204b01c8e96b7fc9f9b32ee35d898acc")))
15051 (file-name "test-simple-bash-src-checkout")
15053 (base32 "043plp6z0x9yf7mdpky1fw7zcpwn1p47px95w9mh16603zqqqpga"))))))
15056 (modify-phases %standard-phases
15057 (add-after 'unpack 'patch-source
15058 (lambda* (#:key inputs #:allow-other-keys)
15059 (let ((bash-tap (assoc-ref inputs "bash-tap")))
15060 (substitute* (find-files "test/t")
15061 (("BASH_TAP_ROOT=bash-tap")
15062 (string-append "BASH_TAP_ROOT=" bash-tap "/bin"))
15063 (("bash-tap/bash-tap-bootstrap")
15064 (string-append bash-tap "/bin/bash-tap-bootstrap"))
15065 (("source.*bash-tap-bootstrap")
15066 (string-append "source " bash-tap "/bin/bash-tap-bootstrap")))
15067 (substitute* "meson.build"
15068 ;; Some inputs aren't actually needed.
15069 ((".*bamtools/src.*") "")
15070 ((".*multichoose.*") ""))
15071 (substitute* '("src/BedReader.cpp"
15073 (("../intervaltree/IntervalTree.h") "IntervalTree.h"))
15075 (add-after 'unpack 'unpack-submodule-sources
15076 (lambda* (#:key inputs #:allow-other-keys)
15077 (mkdir-p "test/test-simple-bash")
15078 (copy-recursively (assoc-ref inputs "test-simple-bash-src")
15079 "test/test-simple-bash")
15081 ;; The slow tests take longer than the specified timeout.
15082 ,@(if (any (cute string=? <> (%current-system))
15083 '("armhf-linux" "aarch64-linux"))
15085 (lambda* (#:key tests? #:allow-other-keys)
15087 (invoke "meson" "test" "--timeout-multiplier" "5"))
15090 (home-page "https://github.com/freebayes/freebayes")
15091 (synopsis "Haplotype-based variant detector")
15092 (description "FreeBayes is a Bayesian genetic variant detector designed to
15093 find small polymorphisms, specifically SNPs (single-nucleotide polymorphisms),
15094 indels (insertions and deletions), MNPs (multi-nucleotide polymorphisms), and
15095 complex events (composite insertion and substitution events) smaller than the
15096 length of a short-read sequencing alignment.")
15097 (license license:expat)))
15099 (define-public samblaster
15101 (name "samblaster")
15105 (uri (git-reference
15106 (url "https://github.com/GregoryFaust/samblaster")
15107 (commit (string-append "v." version))))
15108 (file-name (git-file-name name version))
15111 "0iv2ddfw8363vb2x8gr3p8g88whb6mb9m0pf71i2cqsbv6jghap7"))))
15112 (build-system gnu-build-system)
15114 `(#:tests? #f ; there are none
15116 (modify-phases %standard-phases
15117 (delete 'configure) ; There is no configure phase.
15119 (lambda* (#:key outputs #:allow-other-keys)
15120 (install-file "samblaster"
15121 (string-append (assoc-ref outputs "out") "/bin"))
15123 (home-page "https://github.com/GregoryFaust/samblaster")
15124 (synopsis "Mark duplicates in paired-end SAM files")
15125 (description "Samblaster is a fast and flexible program for marking
15126 duplicates in read-id grouped paired-end SAM files. It can also optionally
15127 output discordant read pairs and/or split read mappings to separate SAM files,
15128 and/or unmapped/clipped reads to a separate FASTQ file. When marking
15129 duplicates, samblaster will require approximately 20MB of memory per 1M read
15131 (license license:expat)))
15133 (define-public r-velocyto
15134 (let ((commit "d7790346cb99f49ab9c2b23ba70dcf9d2c9fc350")
15137 (name "r-velocyto")
15138 (version (git-version "0.6" revision commit))
15142 (uri (git-reference
15143 (url "https://github.com/velocyto-team/velocyto.R")
15145 (file-name (git-file-name name version))
15148 "16wqf70j7rd7pay2q513iyz12i8n9vrpg1bisah4lddbcpx5dz1n"))))
15149 (build-system r-build-system)
15151 `(("boost" ,boost)))
15153 `(("r-hdf5r" ,r-hdf5r)
15156 ("r-pcamethods" ,r-pcamethods)
15158 ("r-rcpparmadillo" ,r-rcpparmadillo)
15159 ;; Suggested packages
15160 ("r-rtsne" ,r-rtsne)
15161 ("r-cluster" ,r-cluster)
15162 ("r-abind" ,r-abind)
15164 ("r-biocgenerics" ,r-biocgenerics)
15165 ("r-genomicalignments" ,r-genomicalignments)
15166 ("r-rsamtools" ,r-rsamtools)
15167 ("r-edger" ,r-edger)
15168 ("r-igraph" ,r-igraph)))
15169 (home-page "https://velocyto.org")
15170 (synopsis "RNA velocity estimation in R")
15172 "This package provides basic routines for estimation of gene-specific
15173 transcriptional derivatives and visualization of the resulting velocity
15175 (license license:gpl3))))
15177 (define-public methyldackel
15179 (name "methyldackel")
15183 (uri (git-reference
15184 (url "https://github.com/dpryan79/MethylDackel")
15186 (file-name (git-file-name name version))
15189 "1sfhf2ap75qxpnmy1ifgmxqs18rq8mah9mcgkby73vc6h0sw99ws"))))
15190 (build-system gnu-build-system)
15192 `(#:test-target "test"
15195 (string-append "prefix="
15196 (assoc-ref %outputs "out") "/bin/"))
15198 (modify-phases %standard-phases
15199 (replace 'configure
15200 (lambda* (#:key outputs #:allow-other-keys)
15201 (substitute* "Makefile"
15202 (("-lhts ") "-lhts -lBigWig ")
15203 (("install MethylDackel \\$\\(prefix\\)" match)
15204 (string-append "install -d $(prefix); " match)))
15207 `(("curl" ,curl) ; XXX: needed by libbigwig
15208 ("htslib" ,htslib-1.9)
15209 ("libbigwig" ,libbigwig)
15211 ;; Needed for tests
15213 `(("python" ,python-wrapper)))
15214 (home-page "https://github.com/dpryan79/MethylDackel")
15215 (synopsis "Universal methylation extractor for BS-seq experiments")
15217 "MethylDackel will process a coordinate-sorted and indexed BAM or CRAM
15218 file containing some form of BS-seq alignments and extract per-base
15219 methylation metrics from them. MethylDackel requires an indexed fasta file
15220 containing the reference genome as well.")
15221 ;; See https://github.com/dpryan79/MethylDackel/issues/85
15222 (license license:expat)))
15224 ;; This package bundles PCRE 8.02 and cannot be built with the current
15226 (define-public phast
15232 (uri (git-reference
15233 (url "https://github.com/CshlSiepelLab/phast")
15234 (commit (string-append "v" version))))
15235 (file-name (git-file-name name version))
15238 "10lpbllvny923jjbbyrpxahhd1m5h7sbj9gx7rd123rg10mlidki"))))
15239 (build-system gnu-build-system)
15243 (string-append "DESTDIR=" (assoc-ref %outputs "out")))
15245 (modify-phases %standard-phases
15246 (replace 'configure
15247 (lambda* (#:key inputs outputs #:allow-other-keys)
15249 (substitute* "test/Makefile"
15251 (substitute* "Makefile"
15252 (("CLAPACKPATH=/usr/lib")
15253 (string-append "CLAPACKPATH="
15254 (assoc-ref inputs "clapack") "/lib")))
15255 ;; Renaming the libraries is not necessary with our version of
15257 (substitute* "src/lib/Makefile"
15258 (("ifdef CLAPACKPATH") "ifdef UNNECESSARY"))
15259 (substitute* "src/make-include.mk"
15260 (("-lblaswr") "-lblas")
15261 (("-ltmg") "-ltmglib")
15262 (("liblapack.a") "liblapack.so")
15263 (("libblas.a") "libblas.so")
15264 (("libf2c.a") "libf2c.so"))
15265 (substitute* "src/Makefile"
15266 (("/opt") "/share")
15272 (string-append (getcwd) "/bin:" (getenv "PATH")))
15273 ;; Disable broken test
15274 (substitute* "test/Makefile"
15275 ((".*if.*hmrc_summary" m) (string-append "#" m)))
15276 ;; Only run the msa_view tests because the others fail for
15277 ;; unknown reasons.
15278 (invoke "make" "-C" "test" "msa_view"))))))
15280 `(("clapack" ,clapack)))
15283 (home-page "http://compgen.cshl.edu/phast/")
15284 (synopsis "Phylogenetic analysis with space/time models")
15286 "Phylogenetic Analysis with Space/Time models (PHAST) is a collection of
15287 command-line programs and supporting libraries for comparative and
15288 evolutionary genomics. Best known as the search engine behind the
15289 Conservation tracks in the University of California, Santa Cruz (UCSC) Genome
15290 Browser, PHAST also includes several tools for phylogenetic modeling,
15291 functional element identification, as well as utilities for manipulating
15292 alignments, trees and genomic annotations.")
15293 (license license:bsd-3)))
15295 (define-public python-gffutils
15296 ;; The latest release is older more than a year than the latest commit
15297 (let ((commit "4034c54600813b1402945e12faa91b3a53162cf1")
15300 (name "python-gffutils")
15301 (version (git-version "0.9" revision commit))
15305 (uri (git-reference
15306 (url "https://github.com/daler/gffutils")
15308 (file-name (git-file-name name version))
15311 "1rwafjdnbir5wnk0ap06ww4lra3p5frhy7mfs03rlldgfnwxymsn"))))
15312 (build-system python-build-system)
15315 (modify-phases %standard-phases
15318 ;; Tests need to access the HOME directory
15319 (setenv "HOME" "/tmp")
15320 (invoke "nosetests" "-a" "!slow")))
15321 (add-after 'unpack 'make-gz-files-writable
15323 (for-each make-file-writable
15324 (find-files "." "\\.gz"))
15327 `(("python-argcomplete" ,python-argcomplete)
15328 ("python-argh" ,python-argh)
15329 ("python-biopython" ,python-biopython)
15330 ("python-pybedtools" ,python-pybedtools)
15331 ("python-pyfaidx" ,python-pyfaidx)
15332 ("python-simplejson" ,python-simplejson)
15333 ("python-six" ,python-six)))
15335 `(("python-nose" , python-nose)))
15336 (home-page "https://github.com/daler/gffutils")
15337 (synopsis "Tool for manipulation of GFF and GTF files")
15339 "python-gffutils is a Python package for working with and manipulating
15340 the GFF and GTF format files typically used for genomic annotations. The
15341 files are loaded into a SQLite database, allowing much more complex
15342 manipulation of hierarchical features (e.g., genes, transcripts, and exons)
15343 than is possible with plain-text methods alone.")
15344 (license license:expat))))
15346 (define-public indelfixer
15348 (name "indelfixer")
15352 (uri (git-reference
15353 (url "https://github.com/cbg-ethz/InDelFixer/")
15354 (commit (string-append "v" version))))
15355 (file-name (git-file-name name version))
15358 "10ak05x8i1bx2p7rriv2rglqg1wr7c8wrhjrqlq1wm7ka99w8i79"))))
15359 (build-system ant-build-system)
15361 `(#:jar-name "InDelFixer.jar"
15362 #:source-dir "src/main/java"
15363 #:test-dir "src/test"))
15365 `(("java-commons-lang2" ,java-commons-lang)
15366 ("java-args4j" ,java-args4j)))
15368 `(("java-junit" ,java-junit)))
15369 (home-page "https://github.com/cbg-ethz/InDelFixer/")
15370 (synopsis "Iterative and sensitive NGS sequence aligner")
15371 (description "InDelFixer is a sensitive aligner for 454, Illumina and
15372 PacBio data, employing a full Smith-Waterman alignment against a reference.
15373 This Java command line application aligns Next-Generation Sequencing (NGS) and
15374 third-generation reads to a set of reference sequences, by a prior fast k-mer
15375 matching and removes indels, causing frame shifts. In addition, only a
15376 specific region can be considered. An iterative refinement of the alignment
15377 can be performed, by alignment against the consensus sequence with wobbles.
15378 The output is in SAM format.")
15379 (license license:gpl3+)))
15381 (define-public libsbml
15387 (uri (string-append "mirror://sourceforge/sbml/libsbml/"
15388 version "/stable/libSBML-"
15389 version "-core-src.tar.gz"))
15392 "0slkagrk3nfi2qsksv6b1brj6zhx4bj4bkib2sdycvrcd10ql2lh"))))
15393 (build-system cmake-build-system)
15395 `(#:test-target "test"
15397 (list "-DWITH_CHECK=ON"
15398 (string-append "-DLIBXML_LIBRARY="
15399 (assoc-ref %build-inputs "libxml2")
15401 (string-append "-DLIBXML_INCLUDE_DIR="
15402 (assoc-ref %build-inputs "libxml2")
15403 "/include/libxml2"))))
15405 `(("libxml2" ,libxml2)))
15407 `(("check" ,check-0.14)
15409 (home-page "http://sbml.org/Software/libSBML")
15410 (synopsis "Process SBML files and data streams")
15411 (description "LibSBML is a library to help you read, write, manipulate,
15412 translate, and validate SBML files and data streams. The @dfn{Systems Biology
15413 Markup Language} (SBML) is an interchange format for computer models of
15414 biological processes. SBML is useful for models of metabolism, cell
15415 signaling, and more. It continues to be evolved and expanded by an
15416 international community.")
15417 (license license:lgpl2.1+)))