1 ;;; GNU Guix --- Functional package management for GNU
2 ;;; Copyright © 2014, 2015, 2016, 2017, 2018, 2019, 2020 Ricardo Wurmus <rekado@elephly.net>
3 ;;; Copyright © 2015, 2016, 2017, 2018 Ben Woodcroft <donttrustben@gmail.com>
4 ;;; Copyright © 2015, 2016 Pjotr Prins <pjotr.guix@thebird.nl>
5 ;;; Copyright © 2015 Andreas Enge <andreas@enge.fr>
6 ;;; Copyright © 2016, 2020 Roel Janssen <roel@gnu.org>
7 ;;; Copyright © 2016, 2017, 2018, 2019, 2020 Efraim Flashner <efraim@flashner.co.il>
8 ;;; Copyright © 2016, 2020 Marius Bakke <mbakke@fastmail.com>
9 ;;; Copyright © 2016, 2018 Raoul Bonnal <ilpuccio.febo@gmail.com>
10 ;;; Copyright © 2017, 2018 Tobias Geerinckx-Rice <me@tobias.gr>
11 ;;; Copyright © 2017 Arun Isaac <arunisaac@systemreboot.net>
12 ;;; Copyright © 2018 Joshua Sierles, Nextjournal <joshua@nextjournal.com>
13 ;;; Copyright © 2018 Gábor Boskovits <boskovits@gmail.com>
14 ;;; Copyright © 2018, 2019 Mădălin Ionel Patrașcu <madalinionel.patrascu@mdc-berlin.de>
15 ;;; Copyright © 2019 Maxim Cournoyer <maxim.cournoyer@gmail.com>
16 ;;; Copyright © 2019 Brian Leung <bkleung89@gmail.com>
17 ;;; Copyright © 2019 Brett Gilio <brettg@gnu.org>
18 ;;; Copyright © 2020 Björn Höfling <bjoern.hoefling@bjoernhoefling.de>
19 ;;; Copyright © 2020 Jakub Kądziołka <kuba@kadziolka.net>
21 ;;; This file is part of GNU Guix.
23 ;;; GNU Guix is free software; you can redistribute it and/or modify it
24 ;;; under the terms of the GNU General Public License as published by
25 ;;; the Free Software Foundation; either version 3 of the License, or (at
26 ;;; your option) any later version.
28 ;;; GNU Guix is distributed in the hope that it will be useful, but
29 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
30 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
31 ;;; GNU General Public License for more details.
33 ;;; You should have received a copy of the GNU General Public License
34 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
36 (define-module (gnu packages bioinformatics)
37 #:use-module ((guix licenses) #:prefix license:)
38 #:use-module (guix packages)
39 #:use-module (guix utils)
40 #:use-module (guix download)
41 #:use-module (guix git-download)
42 #:use-module (guix hg-download)
43 #:use-module (guix build-system ant)
44 #:use-module (guix build-system gnu)
45 #:use-module (guix build-system cmake)
46 #:use-module (guix build-system go)
47 #:use-module (guix build-system haskell)
48 #:use-module (guix build-system meson)
49 #:use-module (guix build-system ocaml)
50 #:use-module (guix build-system perl)
51 #:use-module (guix build-system python)
52 #:use-module (guix build-system r)
53 #:use-module (guix build-system ruby)
54 #:use-module (guix build-system scons)
55 #:use-module (guix build-system trivial)
56 #:use-module (gnu packages)
57 #:use-module (gnu packages autotools)
58 #:use-module (gnu packages algebra)
59 #:use-module (gnu packages base)
60 #:use-module (gnu packages bash)
61 #:use-module (gnu packages bison)
62 #:use-module (gnu packages bioconductor)
63 #:use-module (gnu packages boost)
64 #:use-module (gnu packages check)
65 #:use-module (gnu packages code)
66 #:use-module (gnu packages compression)
67 #:use-module (gnu packages cpio)
68 #:use-module (gnu packages cran)
69 #:use-module (gnu packages curl)
70 #:use-module (gnu packages documentation)
71 #:use-module (gnu packages databases)
72 #:use-module (gnu packages datastructures)
73 #:use-module (gnu packages dlang)
74 #:use-module (gnu packages file)
75 #:use-module (gnu packages flex)
76 #:use-module (gnu packages gawk)
77 #:use-module (gnu packages gcc)
78 #:use-module (gnu packages gd)
79 #:use-module (gnu packages golang)
80 #:use-module (gnu packages glib)
81 #:use-module (gnu packages graph)
82 #:use-module (gnu packages graphviz)
83 #:use-module (gnu packages groff)
84 #:use-module (gnu packages gtk)
85 #:use-module (gnu packages guile)
86 #:use-module (gnu packages guile-xyz)
87 #:use-module (gnu packages haskell-check)
88 #:use-module (gnu packages haskell-web)
89 #:use-module (gnu packages haskell-xyz)
90 #:use-module (gnu packages image)
91 #:use-module (gnu packages imagemagick)
92 #:use-module (gnu packages java)
93 #:use-module (gnu packages java-compression)
94 #:use-module (gnu packages jemalloc)
95 #:use-module (gnu packages linux)
96 #:use-module (gnu packages lisp-xyz)
97 #:use-module (gnu packages logging)
98 #:use-module (gnu packages machine-learning)
99 #:use-module (gnu packages man)
100 #:use-module (gnu packages maths)
101 #:use-module (gnu packages mpi)
102 #:use-module (gnu packages ncurses)
103 #:use-module (gnu packages ocaml)
104 #:use-module (gnu packages pcre)
105 #:use-module (gnu packages parallel)
106 #:use-module (gnu packages pdf)
107 #:use-module (gnu packages perl)
108 #:use-module (gnu packages perl-check)
109 #:use-module (gnu packages pkg-config)
110 #:use-module (gnu packages popt)
111 #:use-module (gnu packages protobuf)
112 #:use-module (gnu packages python)
113 #:use-module (gnu packages python-compression)
114 #:use-module (gnu packages python-science)
115 #:use-module (gnu packages python-web)
116 #:use-module (gnu packages python-xyz)
117 #:use-module (gnu packages readline)
118 #:use-module (gnu packages ruby)
119 #:use-module (gnu packages serialization)
120 #:use-module (gnu packages shells)
121 #:use-module (gnu packages sphinx)
122 #:use-module (gnu packages statistics)
123 #:use-module (gnu packages swig)
124 #:use-module (gnu packages tbb)
125 #:use-module (gnu packages tex)
126 #:use-module (gnu packages texinfo)
127 #:use-module (gnu packages textutils)
128 #:use-module (gnu packages time)
129 #:use-module (gnu packages tls)
130 #:use-module (gnu packages vim)
131 #:use-module (gnu packages web)
132 #:use-module (gnu packages xml)
133 #:use-module (gnu packages xorg)
134 #:use-module (srfi srfi-1)
135 #:use-module (ice-9 match))
137 (define-public aragorn
144 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
148 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
149 (build-system gnu-build-system)
151 `(#:tests? #f ; there are no tests
153 (modify-phases %standard-phases
163 (string-append "aragorn" ,version ".c"))
166 (lambda* (#:key outputs #:allow-other-keys)
167 (let* ((out (assoc-ref outputs "out"))
168 (bin (string-append out "/bin"))
169 (man (string-append out "/share/man/man1")))
170 (install-file "aragorn" bin)
171 (install-file "aragorn.1" man))
173 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
174 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
176 "Aragorn identifies transfer RNA, mitochondrial RNA and
177 transfer-messenger RNA from nucleotide sequences, based on homology to known
178 tRNA consensus sequences and RNA structure. It also outputs the secondary
179 structure of the predicted RNA.")
180 (license license:gpl2)))
188 ;; BamM is not available on pypi.
190 (url "https://github.com/Ecogenomics/BamM.git")
193 (file-name (git-file-name name version))
196 "1p83ahi984ipslxlg4yqy1gdnya9rkn1v71z8djgxkm9d2chw4c5"))
197 (modules '((guix build utils)))
200 ;; Delete bundled htslib.
201 (delete-file-recursively "c/htslib-1.3.1")
203 (build-system python-build-system)
205 `(#:python ,python-2 ; BamM is Python 2 only.
206 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
207 ;; been modified from its original form.
209 (let ((htslib (assoc-ref %build-inputs "htslib")))
210 (list "--with-libhts-lib" (string-append htslib "/lib")
211 "--with-libhts-inc" (string-append htslib "/include/htslib")))
213 (modify-phases %standard-phases
214 (add-after 'unpack 'autogen
216 (with-directory-excursion "c"
217 (let ((sh (which "sh")))
218 (for-each make-file-writable (find-files "." ".*"))
219 ;; Use autogen so that 'configure' works.
220 (substitute* "autogen.sh" (("/bin/sh") sh))
221 (setenv "CONFIG_SHELL" sh)
222 (invoke "./autogen.sh")))
225 ;; Run tests after installation so compilation only happens once.
227 (add-after 'install 'wrap-executable
228 (lambda* (#:key outputs #:allow-other-keys)
229 (let* ((out (assoc-ref outputs "out"))
230 (path (getenv "PATH")))
231 (wrap-program (string-append out "/bin/bamm")
232 `("PATH" ":" prefix (,path))))
234 (add-after 'wrap-executable 'post-install-check
235 (lambda* (#:key inputs outputs #:allow-other-keys)
237 (string-append (assoc-ref outputs "out")
242 (assoc-ref outputs "out")
244 (string-take (string-take-right
245 (assoc-ref inputs "python") 5) 3)
247 (getenv "PYTHONPATH")))
248 ;; There are 2 errors printed, but they are safe to ignore:
249 ;; 1) [E::hts_open_format] fail to open file ...
250 ;; 2) samtools view: failed to open ...
254 `(("autoconf" ,autoconf)
255 ("automake" ,automake)
258 ("python-nose" ,python2-nose)
259 ("python-pysam" ,python2-pysam)))
261 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
262 ("samtools" ,samtools)
266 ("coreutils" ,coreutils)))
268 `(("python-numpy" ,python2-numpy)))
269 (home-page "https://ecogenomics.github.io/BamM/")
270 (synopsis "Metagenomics-focused BAM file manipulator")
272 "BamM is a C library, wrapped in python, to efficiently generate and
273 parse BAM files, specifically for the analysis of metagenomic data. For
274 instance, it implements several methods to assess contig-wise read coverage.")
275 (license license:lgpl3+)))
277 (define-public bamtools
284 (url "https://github.com/pezmaster31/bamtools.git")
285 (commit (string-append "v" version))))
286 (file-name (git-file-name name version))
289 "0nfb2ypcx9959xnbz6wxh6py3xfizgmg8nrknxl95c507m9hmq8b"))))
290 (build-system cmake-build-system)
292 `(#:tests? #f ;no "check" target
294 (modify-phases %standard-phases
296 'configure 'set-ldflags
297 (lambda* (#:key outputs #:allow-other-keys)
301 (assoc-ref outputs "out") "/lib/bamtools"))
303 (inputs `(("zlib" ,zlib)))
304 (home-page "https://github.com/pezmaster31/bamtools")
305 (synopsis "C++ API and command-line toolkit for working with BAM data")
307 "BamTools provides both a C++ API and a command-line toolkit for handling
309 (license license:expat)))
311 (define-public bcftools
317 (uri (string-append "https://github.com/samtools/bcftools/"
319 version "/bcftools-" version ".tar.bz2"))
322 "1j3h638i8kgihzyrlnpj82xg1b23sijibys9hvwari3fy7kd0dkg"))
323 (modules '((guix build utils)))
325 ;; Delete bundled htslib.
326 (delete-file-recursively "htslib-1.9")
328 (build-system gnu-build-system)
331 (list "--enable-libgsl")
334 (modify-phases %standard-phases
335 (add-before 'check 'patch-tests
337 (substitute* "test/test.pl"
338 (("/bin/bash") (which "bash")))
346 (home-page "https://samtools.github.io/bcftools/")
347 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
349 "BCFtools is a set of utilities that manipulate variant calls in the
350 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
351 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
352 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
353 (license (list license:gpl3+ license:expat))))
355 (define-public bedops
362 (url "https://github.com/bedops/bedops.git")
363 (commit (string-append "v" version))))
364 (file-name (git-file-name name version))
367 "0mmgsgwz5r9w76hzgxkxc9s9lkdhhaf7vr6i02b09vbswvs1fyqx"))))
368 (build-system gnu-build-system)
371 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
373 (modify-phases %standard-phases
374 (add-after 'unpack 'unpack-tarballs
376 ;; FIXME: Bedops includes tarballs of minimally patched upstream
377 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
378 ;; libraries because at least one of the libraries (zlib) is
379 ;; patched to add a C++ function definition (deflateInit2cpp).
380 ;; Until the Bedops developers offer a way to link against system
381 ;; libraries we have to build the in-tree copies of these three
384 ;; See upstream discussion:
385 ;; https://github.com/bedops/bedops/issues/124
387 ;; Unpack the tarballs to benefit from shebang patching.
388 (with-directory-excursion "third-party"
389 (invoke "tar" "xvf" "jansson-2.6.tar.bz2")
390 (invoke "tar" "xvf" "zlib-1.2.7.tar.bz2")
391 (invoke "tar" "xvf" "bzip2-1.0.6.tar.bz2"))
392 ;; Disable unpacking of tarballs in Makefile.
393 (substitute* "system.mk/Makefile.linux"
394 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
395 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
396 (substitute* "third-party/zlib-1.2.7/Makefile.in"
397 (("^SHELL=.*$") "SHELL=bash\n"))
399 (delete 'configure))))
400 (home-page "https://github.com/bedops/bedops")
401 (synopsis "Tools for high-performance genomic feature operations")
403 "BEDOPS is a suite of tools to address common questions raised in genomic
404 studies---mostly with regard to overlap and proximity relationships between
405 data sets. It aims to be scalable and flexible, facilitating the efficient
406 and accurate analysis and management of large-scale genomic data.
408 BEDOPS provides tools that perform highly efficient and scalable Boolean and
409 other set operations, statistical calculations, archiving, conversion and
410 other management of genomic data of arbitrary scale. Tasks can be easily
411 split by chromosome for distributing whole-genome analyses across a
412 computational cluster.")
413 (license license:gpl2+)))
415 (define-public bedtools
421 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
422 "download/v" version "/"
423 "bedtools-" version ".tar.gz"))
426 "0m3hk6548846w83a9s5drsczvy67n2azx41kj71n03klb2gbzwg3"))))
427 (build-system gnu-build-system)
429 '(#:test-target "test"
431 (list (string-append "prefix=" (assoc-ref %outputs "out")))
433 (modify-phases %standard-phases
434 (delete 'configure))))
436 `(("python" ,python-wrapper)))
438 `(("samtools" ,samtools)
440 (home-page "https://github.com/arq5x/bedtools2")
441 (synopsis "Tools for genome analysis and arithmetic")
443 "Collectively, the bedtools utilities are a swiss-army knife of tools for
444 a wide-range of genomics analysis tasks. The most widely-used tools enable
445 genome arithmetic: that is, set theory on the genome. For example, bedtools
446 allows one to intersect, merge, count, complement, and shuffle genomic
447 intervals from multiple files in widely-used genomic file formats such as BAM,
449 (license license:expat)))
451 ;; Later releases of bedtools produce files with more columns than
452 ;; what Ribotaper expects.
453 (define-public bedtools-2.18
454 (package (inherit bedtools)
459 (uri (string-append "https://github.com/arq5x/bedtools2/"
460 "releases/download/v" version
461 "/bedtools-" version ".tar.gz"))
464 "11rvca19ncg03kxd0wzlfx5ws7r3nisd0z8s9j9n182d8ksp2pxz"))))
466 '(#:test-target "test"
468 (modify-phases %standard-phases
471 (lambda* (#:key outputs #:allow-other-keys)
472 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
473 (for-each (lambda (file)
474 (install-file file bin))
475 (find-files "bin" ".*")))
485 (url "https://github.com/PacificBiosciences/pbbam.git")
487 (file-name (git-file-name name version))
490 "0h9gkrpf2lrxklxp72xfl5bi3h5zcm5hprrya9gf0hr3xwlbpp0x"))))
491 (build-system meson-build-system)
494 (modify-phases %standard-phases
495 (add-after 'unpack 'find-googletest
496 (lambda* (#:key inputs #:allow-other-keys)
497 ;; It doesn't find gtest_main because there's no pkg-config file
498 ;; for it. Find it another way.
499 (substitute* "tests/meson.build"
500 (("pbbam_gtest_dep = dependency\\('gtest_main'.*")
501 (format #f "cpp = meson.get_compiler('cpp')
502 pbbam_gtest_dep = cpp.find_library('gtest_main', dirs : '~a')\n"
503 (assoc-ref inputs "googletest"))))
505 ;; TODO: tests/pbbam_test cannot be linked
506 ;; ld: tests/59830eb@@pbbam_test@exe/src_test_Accuracy.cpp.o:
507 ;; undefined reference to symbol '_ZTIN7testing4TestE'
508 ;; ld: /gnu/store/...-googletest-1.8.0/lib/libgtest.so:
509 ;; error adding symbols: DSO missing from command line
511 #:configure-flags '("-Dtests=false")))
512 ;; These libraries are listed as "Required" in the pkg-config file.
518 ("samtools" ,samtools)))
520 `(("googletest" ,googletest)
521 ("pkg-config" ,pkg-config)
522 ("python" ,python-wrapper))) ; for tests
523 (home-page "https://github.com/PacificBiosciences/pbbam")
524 (synopsis "Work with PacBio BAM files")
526 "The pbbam software package provides components to create, query, and
527 edit PacBio BAM files and associated indices. These components include a core
528 C++ library, bindings for additional languages, and command-line utilities.
529 This library is not intended to be used as a general-purpose BAM utility - all
530 input and output BAMs must adhere to the PacBio BAM format specification.
531 Non-PacBio BAMs will cause exceptions to be thrown.")
532 (license license:bsd-3)))
534 (define-public blasr-libcpp
536 (name "blasr-libcpp")
541 (url "https://github.com/PacificBiosciences/blasr_libcpp.git")
543 (file-name (git-file-name name version))
546 "0cn5l42zyq67sj0g2imqkhayz2iqvv0a1pgpbmlq0qynjmsrbfd2"))))
547 (build-system meson-build-system)
550 (modify-phases %standard-phases
551 (add-after 'unpack 'link-with-hdf5
552 (lambda* (#:key inputs #:allow-other-keys)
553 (let ((hdf5 (assoc-ref inputs "hdf5")))
554 (substitute* "meson.build"
555 (("libblasr_deps = \\[" m)
558 (format #f "cpp.find_library('hdf5', dirs : '~a'), \
559 cpp.find_library('hdf5_cpp', dirs : '~a'), "
562 (add-after 'unpack 'find-googletest
563 (lambda* (#:key inputs #:allow-other-keys)
564 ;; It doesn't find gtest_main because there's no pkg-config file
565 ;; for it. Find it another way.
566 (substitute* "unittest/meson.build"
567 (("libblasr_gtest_dep = dependency\\('gtest_main'.*")
568 (format #f "cpp = meson.get_compiler('cpp')
569 libblasr_gtest_dep = cpp.find_library('gtest_main', dirs : '~a')\n"
570 (assoc-ref inputs "googletest"))))
572 ;; TODO: unittest/libblasr_unittest cannot be linked
573 ;; ld: ;; unittest/df08227@@libblasr_unittest@exe/alignment_utils_FileUtils_gtest.cpp.o:
574 ;; undefined reference to symbol
575 ;; '_ZN7testing8internal9DeathTest6CreateEPKcPKNS0_2REES3_iPPS1_'
576 ;; ld: /gnu/store/...-googletest-1.8.0/lib/libgtest.so:
577 ;; error adding symbols: DSO missing from command line
579 #:configure-flags '("-Dtests=false")))
586 `(("googletest" ,googletest)
587 ("pkg-config" ,pkg-config)))
588 (home-page "https://github.com/PacificBiosciences/blasr_libcpp")
589 (synopsis "Library for analyzing PacBio genomic sequences")
591 "This package provides three libraries used by applications for analyzing
592 PacBio genomic sequences. This library contains three sub-libraries: pbdata,
594 (license license:bsd-3)))
603 (url "https://github.com/PacificBiosciences/blasr.git")
605 (file-name (git-file-name name version))
608 "1skgy2mvz8gsgfh1gc2nfgwvpyzb1hpmp2cf2773h5wsj8nw22kl"))))
609 (build-system meson-build-system)
612 (modify-phases %standard-phases
613 (add-after 'unpack 'link-with-hdf5
614 (lambda* (#:key inputs #:allow-other-keys)
615 (let ((hdf5 (assoc-ref inputs "hdf5")))
616 (substitute* "meson.build"
617 (("blasr_deps = \\[" m)
620 (format #f "cpp.find_library('hdf5', dirs : '~a'), \
621 cpp.find_library('hdf5_cpp', dirs : '~a'), "
624 ;; Tests require "cram" executable, which is not packaged.
626 #:configure-flags '("-Dtests=false")))
629 ("blasr-libcpp" ,blasr-libcpp)
634 `(("pkg-config" ,pkg-config)))
635 (home-page "https://github.com/PacificBiosciences/blasr")
636 (synopsis "PacBio long read aligner")
638 "Blasr is a genomic sequence aligner for processing PacBio long reads.")
639 (license license:bsd-3)))
641 (define-public ribotaper
647 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
648 "files/RiboTaper/RiboTaper_Version_"
652 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
653 (build-system gnu-build-system)
656 (modify-phases %standard-phases
657 (add-after 'install 'wrap-executables
658 (lambda* (#:key inputs outputs #:allow-other-keys)
659 (let* ((out (assoc-ref outputs "out")))
662 (wrap-program (string-append out "/bin/" script)
663 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
664 '("create_annotations_files.bash"
665 "create_metaplots.bash"
666 "Ribotaper_ORF_find.sh"
670 `(("bedtools" ,bedtools-2.18)
671 ("samtools" ,samtools-0.1)
672 ("r-minimal" ,r-minimal)
673 ("r-foreach" ,r-foreach)
674 ("r-xnomial" ,r-xnomial)
676 ("r-multitaper" ,r-multitaper)
677 ("r-seqinr" ,r-seqinr)))
678 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
679 (synopsis "Define translated ORFs using ribosome profiling data")
681 "Ribotaper is a method for defining translated @dfn{open reading
682 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
683 provides the Ribotaper pipeline.")
684 (license license:gpl3+)))
686 (define-public ribodiff
694 (url "https://github.com/ratschlab/RiboDiff.git")
695 (commit (string-append "v" version))))
696 (file-name (git-file-name name version))
699 "0x75nlp7qnmm64jasbi6l21f2cy99r2cjyl6b4hr8zf2bq22drnz"))))
700 (build-system python-build-system)
704 (modify-phases %standard-phases
705 ;; Generate an installable executable script wrapper.
706 (add-after 'unpack 'patch-setup.py
708 (substitute* "setup.py"
709 (("^(.*)packages=.*" line prefix)
710 (string-append line "\n"
711 prefix "scripts=['scripts/TE.py'],\n")))
714 `(("python-numpy" ,python2-numpy)
715 ("python-matplotlib" ,python2-matplotlib)
716 ("python-scipy" ,python2-scipy)
717 ("python-statsmodels" ,python2-statsmodels)))
719 `(("python-mock" ,python2-mock)
720 ("python-nose" ,python2-nose)))
721 (home-page "https://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
722 (synopsis "Detect translation efficiency changes from ribosome footprints")
723 (description "RiboDiff is a statistical tool that detects the protein
724 translational efficiency change from Ribo-Seq (ribosome footprinting) and
725 RNA-Seq data. It uses a generalized linear model to detect genes showing
726 difference in translational profile taking mRNA abundance into account. It
727 facilitates us to decipher the translational regulation that behave
728 independently with transcriptional regulation.")
729 (license license:gpl3+)))
731 (define-public bioawk
738 (url "https://github.com/lh3/bioawk.git")
739 (commit (string-append "v" version))))
740 (file-name (git-file-name name version))
743 "1pxc3zdnirxbf9a0az698hd8xdik7qkhypm7v6hn922x8y9qmspm"))))
744 (build-system gnu-build-system)
750 `(#:tests? #f ; There are no tests to run.
751 ;; Bison must generate files, before other targets can build.
754 (modify-phases %standard-phases
755 (delete 'configure) ; There is no configure phase.
757 (lambda* (#:key outputs #:allow-other-keys)
758 (let* ((out (assoc-ref outputs "out"))
759 (bin (string-append out "/bin"))
760 (man (string-append out "/share/man/man1")))
762 (copy-file "awk.1" (string-append man "/bioawk.1"))
763 (install-file "bioawk" bin))
765 (home-page "https://github.com/lh3/bioawk")
766 (synopsis "AWK with bioinformatics extensions")
767 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
768 support of several common biological data formats, including optionally gzip'ed
769 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
770 also adds a few built-in functions and a command line option to use TAB as the
771 input/output delimiter. When the new functionality is not used, bioawk is
772 intended to behave exactly the same as the original BWK awk.")
773 (license license:x11)))
775 (define-public python-pybedtools
777 (name "python-pybedtools")
781 (uri (pypi-uri "pybedtools" version))
784 "14w5i40gi25clrr7h4wa2pcpnyipya8hrqi7nq77553zc5wf0df0"))))
785 (build-system python-build-system)
787 `(#:modules ((ice-9 ftw)
791 (guix build python-build-system))
792 ;; See https://github.com/daler/pybedtools/issues/192
794 (modify-phases %standard-phases
795 (add-after 'unpack 'disable-broken-tests
797 (substitute* "pybedtools/test/test_scripts.py"
798 ;; This test freezes.
799 (("def test_intron_exon_reads")
800 "def _do_not_test_intron_exon_reads")
801 ;; This test fails in the Python 2 build.
802 (("def test_venn_mpl")
803 "def _do_not_test_venn_mpl"))
804 (substitute* "pybedtools/test/test_helpers.py"
805 ;; Requires internet access.
806 (("def test_chromsizes")
807 "def _do_not_test_chromsizes")
808 ;; Broken as a result of the workaround used in the check phase
809 ;; (see: https://github.com/daler/pybedtools/issues/192).
810 (("def test_getting_example_beds")
811 "def _do_not_test_getting_example_beds"))
812 ;; This issue still occurs on python2
813 (substitute* "pybedtools/test/test_issues.py"
814 (("def test_issue_303")
815 "def _test_issue_303"))
817 ;; TODO: Remove phase after it's part of PYTHON-BUILD-SYSTEM.
819 ;; Force the Cythonization of C++ files to guard against compilation
821 (add-after 'unpack 'remove-cython-generated-files
823 (let ((cython-sources (map (cut string-drop-right <> 4)
824 (find-files "." "\\.pyx$")))
825 (c/c++-files (find-files "." "\\.(c|cpp|cxx)$")))
826 (define (strip-extension filename)
827 (string-take filename (string-index-right filename #\.)))
828 (define (cythonized? c/c++-file)
829 (member (strip-extension c/c++-file) cython-sources))
830 (for-each delete-file (filter cythonized? c/c++-files))
832 (add-after 'remove-cython-generated-files 'generate-cython-extensions
834 (invoke "python" "setup.py" "cythonize")))
837 (let* ((cwd (getcwd))
838 (build-root-directory (string-append cwd "/build/"))
839 (build (string-append
841 (find (cut string-prefix? "lib" <>)
842 (scandir (string-append
843 build-root-directory)))))
844 (scripts (string-append
846 (find (cut string-prefix? "scripts" <>)
847 (scandir build-root-directory)))))
849 (string-append build ":" (getenv "PYTHONPATH")))
850 ;; Executable scripts such as 'intron_exon_reads.py' must be
851 ;; available in the PATH.
853 (string-append scripts ":" (getenv "PATH"))))
854 ;; The tests need to be run from elsewhere...
855 (mkdir-p "/tmp/test")
856 (copy-recursively "pybedtools/test" "/tmp/test")
857 (with-directory-excursion "/tmp/test"
858 (invoke "pytest" "-v" "--doctest-modules")))))))
860 `(("bedtools" ,bedtools)
861 ("samtools" ,samtools)
862 ("python-matplotlib" ,python-matplotlib)
863 ("python-pysam" ,python-pysam)
864 ("python-pyyaml" ,python-pyyaml)))
866 `(("python-numpy" ,python-numpy)
867 ("python-pandas" ,python-pandas)
868 ("python-cython" ,python-cython)
869 ("kentutils" ,kentutils) ; for bedGraphToBigWig
870 ("python-six" ,python-six)
871 ;; For the test suite.
872 ("python-pytest" ,python-pytest)
873 ("python-psutil" ,python-psutil)))
874 (home-page "https://pythonhosted.org/pybedtools/")
875 (synopsis "Python wrapper for BEDtools programs")
877 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
878 which are widely used for genomic interval manipulation or \"genome algebra\".
879 pybedtools extends BEDTools by offering feature-level manipulations from with
881 (license license:gpl2+)))
883 (define-public python2-pybedtools
884 (let ((pybedtools (package-with-python2 python-pybedtools)))
888 `(("python2-pathlib" ,python2-pathlib)
889 ,@(package-native-inputs pybedtools))))))
891 (define-public python-biom-format
893 (name "python-biom-format")
898 ;; Use GitHub as source because PyPI distribution does not contain
899 ;; test data: https://github.com/biocore/biom-format/issues/693
901 (url "https://github.com/biocore/biom-format.git")
903 (file-name (git-file-name name version))
906 "1rna16lyk5aqhnv0dp77wwaplias93f1vw28ad3jmyw6hwkai05v"))
907 (modules '((guix build utils)))
909 ;; Delete generated C files.
910 (for-each delete-file (find-files "." "\\.c"))
912 (build-system python-build-system)
915 (modify-phases %standard-phases
916 (add-after 'unpack 'use-cython
917 (lambda _ (setenv "USE_CYTHON" "1") #t))
918 (add-after 'unpack 'disable-broken-tests
920 (substitute* "biom/tests/test_cli/test_validate_table.py"
921 (("^(.+)def test_invalid_hdf5" m indent)
922 (string-append indent
923 "@npt.dec.skipif(True, msg='Guix')\n"
925 (substitute* "biom/tests/test_table.py"
926 (("^(.+)def test_from_hdf5_issue_731" m indent)
927 (string-append indent
928 "@npt.dec.skipif(True, msg='Guix')\n"
931 (add-before 'reset-gzip-timestamps 'make-files-writable
932 (lambda* (#:key outputs #:allow-other-keys)
933 (let ((out (assoc-ref outputs "out")))
934 (for-each (lambda (file) (chmod file #o644))
935 (find-files out "\\.gz"))
938 `(("python-numpy" ,python-numpy)
939 ("python-scipy" ,python-scipy)
940 ("python-flake8" ,python-flake8)
941 ("python-future" ,python-future)
942 ("python-click" ,python-click)
943 ("python-h5py" ,python-h5py)
944 ("python-pandas" ,python-pandas)))
946 `(("python-cython" ,python-cython)
947 ("python-pytest" ,python-pytest)
948 ("python-pytest-cov" ,python-pytest-cov)
949 ("python-nose" ,python-nose)))
950 (home-page "http://www.biom-format.org")
951 (synopsis "Biological Observation Matrix (BIOM) format utilities")
953 "The BIOM file format is designed to be a general-use format for
954 representing counts of observations e.g. operational taxonomic units, KEGG
955 orthology groups or lipid types, in one or more biological samples
956 e.g. microbiome samples, genomes, metagenomes.")
957 (license license:bsd-3)
958 (properties `((python2-variant . ,(delay python2-biom-format))))))
960 (define-public python2-biom-format
961 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
965 (substitute-keyword-arguments (package-arguments base)
967 `(modify-phases ,phases
968 ;; Do not require the unmaintained pyqi library.
969 (add-after 'unpack 'remove-pyqi
971 (substitute* "setup.py"
972 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
975 (define-public python-pairtools
977 (name "python-pairtools")
982 (url "https://github.com/mirnylab/pairtools")
983 (commit (string-append "v" version))))
984 (file-name (git-file-name name version))
987 "0gr8y13q7sd6yai6df4aavl2470n1f9s3cib6r473z4hr8hcbwmc"))))
988 (build-system python-build-system)
991 (modify-phases %standard-phases
992 (add-after 'unpack 'fix-references
994 (substitute* '("pairtools/pairtools_merge.py"
995 "pairtools/pairtools_sort.py")
996 (("/bin/bash") (which "bash")))
999 (lambda* (#:key inputs outputs #:allow-other-keys)
1000 (add-installed-pythonpath inputs outputs)
1001 (with-directory-excursion "/tmp"
1002 (invoke "pytest" "-v")))))))
1004 `(("python-cython" ,python-cython)
1005 ("python-nose" ,python-nose)
1006 ("python-pytest" ,python-pytest)))
1008 `(("python" ,python-wrapper)))
1010 `(("htslib" ,htslib) ; for bgzip, looked up in PATH
1011 ("samtools" ,samtools) ; looked up in PATH
1012 ("lz4" ,lz4) ; for lz4c
1013 ("python-click" ,python-click)
1014 ("python-numpy" ,python-numpy)))
1015 (home-page "https://github.com/mirnylab/pairtools")
1016 (synopsis "Process mapped Hi-C data")
1017 (description "Pairtools is a simple and fast command-line framework to
1018 process sequencing data from a Hi-C experiment. Process pair-end sequence
1019 alignments and perform the following operations:
1022 @item detect ligation junctions (a.k.a. Hi-C pairs) in aligned paired-end
1023 sequences of Hi-C DNA molecules
1024 @item sort @code{.pairs} files for downstream analyses
1025 @item detect, tag and remove PCR/optical duplicates
1026 @item generate extensive statistics of Hi-C datasets
1027 @item select Hi-C pairs given flexibly defined criteria
1028 @item restore @code{.sam} alignments from Hi-C pairs.
1031 (license license:expat)))
1033 (define-public bioperl-minimal
1034 (let* ((inputs `(("perl-module-build" ,perl-module-build)
1035 ("perl-data-stag" ,perl-data-stag)
1036 ("perl-libwww" ,perl-libwww)
1037 ("perl-uri" ,perl-uri)))
1039 (map (compose package-name cadr)
1042 (map (compose package-transitive-target-inputs cadr) inputs))))))
1044 (name "bioperl-minimal")
1050 (url "https://github.com/bioperl/bioperl-live")
1051 (commit (string-append "release-"
1052 (string-map (lambda (c)
1054 #\- c)) version)))))
1055 (file-name (git-file-name name version))
1058 "0wl8yvzcls59pwwk6m8ahy87pwg6nnibzy5cldbvmcwg2x2w7783"))))
1059 (build-system perl-build-system)
1062 (modify-phases %standard-phases
1064 'install 'wrap-programs
1065 (lambda* (#:key outputs #:allow-other-keys)
1066 ;; Make sure all executables in "bin" find the required Perl
1067 ;; modules at runtime. As the PERL5LIB variable contains also
1068 ;; the paths of native inputs, we pick the transitive target
1069 ;; inputs from %build-inputs.
1070 (let* ((out (assoc-ref outputs "out"))
1071 (bin (string-append out "/bin/"))
1073 (cons (string-append out "/lib/perl5/site_perl")
1075 (assoc-ref %build-inputs name))
1076 ',transitive-inputs))
1078 (for-each (lambda (file)
1080 `("PERL5LIB" ":" prefix (,path))))
1081 (find-files bin "\\.pl$"))
1085 `(("perl-test-most" ,perl-test-most)))
1086 (home-page "https://metacpan.org/release/BioPerl")
1087 (synopsis "Bioinformatics toolkit")
1089 "BioPerl is the product of a community effort to produce Perl code which
1090 is useful in biology. Examples include Sequence objects, Alignment objects
1091 and database searching objects. These objects not only do what they are
1092 advertised to do in the documentation, but they also interact - Alignment
1093 objects are made from the Sequence objects, Sequence objects have access to
1094 Annotation and SeqFeature objects and databases, Blast objects can be
1095 converted to Alignment objects, and so on. This means that the objects
1096 provide a coordinated and extensible framework to do computational biology.")
1097 (license license:perl-license))))
1099 (define-public python-biopython
1101 (name "python-biopython")
1105 ;; use PyPi rather than biopython.org to ease updating
1106 (uri (pypi-uri "biopython" version))
1109 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
1110 (build-system python-build-system)
1113 (modify-phases %standard-phases
1114 (add-before 'check 'set-home
1115 ;; Some tests require a home directory to be set.
1116 (lambda _ (setenv "HOME" "/tmp") #t)))))
1118 `(("python-numpy" ,python-numpy)))
1119 (home-page "https://biopython.org/")
1120 (synopsis "Tools for biological computation in Python")
1122 "Biopython is a set of tools for biological computation including parsers
1123 for bioinformatics files into Python data structures; interfaces to common
1124 bioinformatics programs; a standard sequence class and tools for performing
1125 common operations on them; code to perform data classification; code for
1126 dealing with alignments; code making it easy to split up parallelizable tasks
1127 into separate processes; and more.")
1128 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
1130 (define-public python2-biopython
1131 (package-with-python2 python-biopython))
1133 (define-public python-fastalite
1135 (name "python-fastalite")
1140 (uri (pypi-uri "fastalite" version))
1143 "1qli6pxp77i9xn2wfciq2zaxhl82bdxb33cpzqzj1z25yd036wqj"))))
1144 (build-system python-build-system)
1146 `(#:tests? #f)) ; Test data is not distributed.
1147 (home-page "https://github.com/nhoffman/fastalite")
1148 (synopsis "Simplest possible FASTA parser")
1149 (description "This library implements a FASTA and a FASTQ parser without
1150 relying on a complex dependency tree.")
1151 (license license:expat)))
1153 (define-public python2-fastalite
1154 (package-with-python2 python-fastalite))
1156 (define-public bpp-core
1157 ;; The last release was in 2014 and the recommended way to install from source
1158 ;; is to clone the git repository, so we do this.
1159 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1160 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
1163 (version (string-append "2.2.0-1." (string-take commit 7)))
1167 (url "http://biopp.univ-montp2.fr/git/bpp-core")
1169 (file-name (string-append name "-" version "-checkout"))
1172 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
1173 (build-system cmake-build-system)
1175 `(#:parallel-build? #f))
1176 (home-page "http://biopp.univ-montp2.fr")
1177 (synopsis "C++ libraries for Bioinformatics")
1179 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1180 analysis, phylogenetics, molecular evolution and population genetics. It is
1181 Object Oriented and is designed to be both easy to use and computer efficient.
1182 Bio++ intends to help programmers to write computer expensive programs, by
1183 providing them a set of re-usable tools.")
1184 (license license:cecill-c))))
1186 (define-public bpp-phyl
1187 ;; The last release was in 2014 and the recommended way to install from source
1188 ;; is to clone the git repository, so we do this.
1189 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1190 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
1193 (version (string-append "2.2.0-1." (string-take commit 7)))
1197 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
1199 (file-name (string-append name "-" version "-checkout"))
1202 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
1203 (build-system cmake-build-system)
1205 `(#:parallel-build? #f
1206 ;; If out-of-source, test data is not copied into the build directory
1207 ;; so the tests fail.
1208 #:out-of-source? #f))
1210 `(("bpp-core" ,bpp-core)
1211 ("bpp-seq" ,bpp-seq)))
1212 (home-page "http://biopp.univ-montp2.fr")
1213 (synopsis "Bio++ phylogenetic Library")
1215 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1216 analysis, phylogenetics, molecular evolution and population genetics. This
1217 library provides phylogenetics-related modules.")
1218 (license license:cecill-c))))
1220 (define-public bpp-popgen
1221 ;; The last release was in 2014 and the recommended way to install from source
1222 ;; is to clone the git repository, so we do this.
1223 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1224 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
1227 (version (string-append "2.2.0-1." (string-take commit 7)))
1231 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
1233 (file-name (string-append name "-" version "-checkout"))
1236 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
1237 (build-system cmake-build-system)
1239 `(#:parallel-build? #f
1240 #:tests? #f)) ; There are no tests.
1242 `(("bpp-core" ,bpp-core)
1243 ("bpp-seq" ,bpp-seq)))
1244 (home-page "http://biopp.univ-montp2.fr")
1245 (synopsis "Bio++ population genetics library")
1247 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1248 analysis, phylogenetics, molecular evolution and population genetics. This
1249 library provides population genetics-related modules.")
1250 (license license:cecill-c))))
1252 (define-public bpp-seq
1253 ;; The last release was in 2014 and the recommended way to install from source
1254 ;; is to clone the git repository, so we do this.
1255 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1256 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
1259 (version (string-append "2.2.0-1." (string-take commit 7)))
1263 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
1265 (file-name (string-append name "-" version "-checkout"))
1268 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
1269 (build-system cmake-build-system)
1271 `(#:parallel-build? #f
1272 ;; If out-of-source, test data is not copied into the build directory
1273 ;; so the tests fail.
1274 #:out-of-source? #f))
1276 `(("bpp-core" ,bpp-core)))
1277 (home-page "http://biopp.univ-montp2.fr")
1278 (synopsis "Bio++ sequence library")
1280 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1281 analysis, phylogenetics, molecular evolution and population genetics. This
1282 library provides sequence-related modules.")
1283 (license license:cecill-c))))
1285 (define-public bppsuite
1286 ;; The last release was in 2014 and the recommended way to install from source
1287 ;; is to clone the git repository, so we do this.
1288 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1289 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
1292 (version (string-append "2.2.0-1." (string-take commit 7)))
1296 (url "http://biopp.univ-montp2.fr/git/bppsuite")
1298 (file-name (string-append name "-" version "-checkout"))
1301 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
1302 (build-system cmake-build-system)
1304 `(#:parallel-build? #f
1305 #:tests? #f)) ; There are no tests.
1309 ("texinfo" ,texinfo)))
1311 `(("bpp-core" ,bpp-core)
1312 ("bpp-seq" ,bpp-seq)
1313 ("bpp-phyl" ,bpp-phyl)
1314 ("bpp-phyl" ,bpp-popgen)))
1315 (home-page "http://biopp.univ-montp2.fr")
1316 (synopsis "Bioinformatics tools written with the Bio++ libraries")
1318 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1319 analysis, phylogenetics, molecular evolution and population genetics. This
1320 package provides command line tools using the Bio++ library.")
1321 (license license:cecill-c))))
1323 (define-public blast+
1330 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
1331 version "/ncbi-blast-" version "+-src.tar.gz"))
1334 "1jlq0afxxgczpp35k6mxh8mn4jzq7vqcnaixk166sfj10wq8v9qh"))
1335 (modules '((guix build utils)))
1338 ;; Remove bundled bzip2, zlib and pcre.
1339 (delete-file-recursively "c++/src/util/compress/bzip2")
1340 (delete-file-recursively "c++/src/util/compress/zlib")
1341 (delete-file-recursively "c++/src/util/regexp")
1342 (substitute* "c++/src/util/compress/Makefile.in"
1343 (("bzip2 zlib api") "api"))
1344 ;; Remove useless msbuild directory
1345 (delete-file-recursively
1346 "c++/src/build-system/project_tree_builder/msbuild")
1348 (build-system gnu-build-system)
1350 `(;; There are two(!) tests for this massive library, and both fail with
1351 ;; "unparsable timing stats".
1352 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
1353 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
1356 #:parallel-build? #f ; not supported
1358 (modify-phases %standard-phases
1359 (add-before 'configure 'set-HOME
1360 ;; $HOME needs to be set at some point during the configure phase
1361 (lambda _ (setenv "HOME" "/tmp") #t))
1362 (add-after 'unpack 'enter-dir
1363 (lambda _ (chdir "c++") #t))
1364 (add-after 'enter-dir 'fix-build-system
1366 (define (which* cmd)
1367 (cond ((string=? cmd "date")
1368 ;; make call to "date" deterministic
1373 (format (current-error-port)
1374 "WARNING: Unable to find absolute path for ~s~%"
1378 ;; Rewrite hardcoded paths to various tools
1379 (substitute* (append '("src/build-system/configure.ac"
1380 "src/build-system/configure"
1381 "src/build-system/helpers/run_with_lock.c"
1382 "scripts/common/impl/if_diff.sh"
1383 "scripts/common/impl/run_with_lock.sh"
1384 "src/build-system/Makefile.configurables.real"
1385 "src/build-system/Makefile.in.top"
1386 "src/build-system/Makefile.meta.gmake=no"
1387 "src/build-system/Makefile.meta.in"
1388 "src/build-system/Makefile.meta_l"
1389 "src/build-system/Makefile.meta_p"
1390 "src/build-system/Makefile.meta_r"
1391 "src/build-system/Makefile.mk.in"
1392 "src/build-system/Makefile.requirements"
1393 "src/build-system/Makefile.rules_with_autodep.in")
1394 (find-files "scripts/common/check" "\\.sh$"))
1395 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1396 (or (which* cmd) all)))
1398 (substitute* (find-files "src/build-system" "^config.*")
1399 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1402 ;; rewrite "/var/tmp" in check script
1403 (substitute* "scripts/common/check/check_make_unix.sh"
1404 (("/var/tmp") "/tmp"))
1406 ;; do not reset PATH
1407 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1409 (("action=/bin/") "action=")
1410 (("export PATH") ":"))
1413 (lambda* (#:key inputs outputs #:allow-other-keys)
1414 (let ((out (assoc-ref outputs "out"))
1415 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1416 (include (string-append (assoc-ref outputs "include")
1417 "/include/ncbi-tools++")))
1418 ;; The 'configure' script doesn't recognize things like
1419 ;; '--enable-fast-install'.
1420 (invoke "./configure.orig"
1421 (string-append "--with-build-root=" (getcwd) "/build")
1422 (string-append "--prefix=" out)
1423 (string-append "--libdir=" lib)
1424 (string-append "--includedir=" include)
1425 (string-append "--with-bz2="
1426 (assoc-ref inputs "bzip2"))
1427 (string-append "--with-z="
1428 (assoc-ref inputs "zlib"))
1429 (string-append "--with-pcre="
1430 (assoc-ref inputs "pcre"))
1431 ;; Each library is built twice by default, once
1432 ;; with "-static" in its name, and again
1437 (outputs '("out" ; 21 MB
1446 ("python" ,python-wrapper)))
1449 (home-page "https://blast.ncbi.nlm.nih.gov")
1450 (synopsis "Basic local alignment search tool")
1452 "BLAST is a popular method of performing a DNA or protein sequence
1453 similarity search, using heuristics to produce results quickly. It also
1454 calculates an “expect value” that estimates how many matches would have
1455 occurred at a given score by chance, which can aid a user in judging how much
1456 confidence to have in an alignment.")
1457 ;; Most of the sources are in the public domain, with the following
1460 ;; * ./c++/include/util/bitset/
1461 ;; * ./c++/src/html/ncbi_menu*.js
1463 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1465 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1467 ;; * ./c++/src/corelib/teamcity_*
1468 (license (list license:public-domain
1474 (define-public bless
1480 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1484 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1485 (modules '((guix build utils)))
1488 ;; Remove bundled boost, pigz, zlib, and .git directory
1489 ;; FIXME: also remove bundled sources for murmurhash3 and
1490 ;; kmc once packaged.
1491 (delete-file-recursively "boost")
1492 (delete-file-recursively "pigz")
1493 (delete-file-recursively "google-sparsehash")
1494 (delete-file-recursively "zlib")
1495 (delete-file-recursively ".git")
1497 (build-system gnu-build-system)
1499 '(#:tests? #f ;no "check" target
1501 (list (string-append "ZLIB="
1502 (assoc-ref %build-inputs "zlib:static")
1504 (string-append "LDFLAGS="
1505 (string-join '("-lboost_filesystem"
1511 (modify-phases %standard-phases
1512 (add-after 'unpack 'do-not-build-bundled-pigz
1513 (lambda* (#:key inputs outputs #:allow-other-keys)
1514 (substitute* "Makefile"
1515 (("cd pigz/pigz-2.3.3; make") ""))
1517 (add-after 'unpack 'patch-paths-to-executables
1518 (lambda* (#:key inputs outputs #:allow-other-keys)
1519 (substitute* "parse_args.cpp"
1520 (("kmc_binary = .*")
1521 (string-append "kmc_binary = \""
1522 (assoc-ref outputs "out")
1524 (("pigz_binary = .*")
1525 (string-append "pigz_binary = \""
1526 (assoc-ref inputs "pigz")
1530 (lambda* (#:key outputs #:allow-other-keys)
1531 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1532 (for-each (lambda (file)
1533 (install-file file bin))
1534 '("bless" "kmc/bin/kmc"))
1536 (delete 'configure))))
1540 `(("openmpi" ,openmpi)
1542 ("sparsehash" ,sparsehash)
1544 ("zlib:static" ,zlib "static")
1546 (supported-systems '("x86_64-linux"))
1547 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1548 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1550 "@dfn{Bloom-filter-based error correction solution for high-throughput
1551 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1552 correction tool for genomic reads produced by @dfn{Next-generation
1553 sequencing} (NGS). BLESS produces accurate correction results with much less
1554 memory compared with previous solutions and is also able to tolerate a higher
1555 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1556 errors at the end of reads.")
1557 (license license:gpl3+)))
1559 (define-public bowtie
1566 (url "https://github.com/BenLangmead/bowtie2.git")
1567 (commit (string-append "v" version))))
1568 (file-name (git-file-name name version))
1571 "1zl3cf327y2p7p03cavymbh7b00djc7lncfaqih33n96iy9q8ibp"))
1572 (modules '((guix build utils)))
1575 (substitute* "Makefile"
1576 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1577 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1578 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
1580 (build-system gnu-build-system)
1585 (string-append "prefix=" (assoc-ref %outputs "out")))
1587 (modify-phases %standard-phases
1592 "scripts/test/simple_tests.pl"
1593 "--bowtie2=./bowtie2"
1594 "--bowtie2-build=./bowtie2-build")
1599 ("python" ,python-wrapper)))
1602 ("perl-clone" ,perl-clone)
1603 ("perl-test-deep" ,perl-test-deep)
1604 ("perl-test-simple" ,perl-test-simple)))
1605 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1606 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1608 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1609 reads to long reference sequences. It is particularly good at aligning reads
1610 of about 50 up to 100s or 1,000s of characters, and particularly good at
1611 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1612 genome with an FM Index to keep its memory footprint small: for the human
1613 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1614 gapped, local, and paired-end alignment modes.")
1615 (supported-systems '("x86_64-linux"))
1616 (license license:gpl3+)))
1618 (define-public bowtie1
1624 (uri (string-append "mirror://sourceforge/bowtie-bio/bowtie/"
1625 version "/bowtie-src-x86_64.zip"))
1628 "0vmiqdhc9dzyfy9sh6vgi7k9xy2hiw8g87vbamnc6cgpm179zsa4"))
1629 (modules '((guix build utils)))
1631 '(substitute* "Makefile"
1632 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1633 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1634 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1635 (build-system gnu-build-system)
1637 '(#:tests? #f ; no "check" target
1640 (string-append "prefix=" (assoc-ref %outputs "out")))
1642 (modify-phases %standard-phases
1643 (delete 'configure))))
1647 (supported-systems '("x86_64-linux"))
1648 (home-page "http://bowtie-bio.sourceforge.net/index.shtml")
1649 (synopsis "Fast aligner for short nucleotide sequence reads")
1651 "Bowtie is a fast, memory-efficient short read aligner. It aligns short
1652 DNA sequences (reads) to the human genome at a rate of over 25 million 35-bp
1653 reads per hour. Bowtie indexes the genome with a Burrows-Wheeler index to
1654 keep its memory footprint small: typically about 2.2 GB for the human
1655 genome (2.9 GB for paired-end).")
1656 (license license:artistic2.0)))
1658 (define-public tophat
1665 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1669 "19add02kv2xhd6ihd779dr7x35ggym3jqr0m5c4315i1yfb0p11p"))
1670 (modules '((guix build utils)))
1673 ;; Remove bundled SeqAn and samtools
1674 (delete-file-recursively "src/SeqAn-1.4.2")
1675 (delete-file-recursively "src/samtools-0.1.18")
1677 (build-system gnu-build-system)
1679 '(#:parallel-build? #f ; not supported
1681 (modify-phases %standard-phases
1682 (add-after 'unpack 'use-system-samtools
1683 (lambda* (#:key inputs #:allow-other-keys)
1684 (substitute* "src/Makefile.in"
1685 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1686 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1687 (("SAMPROG = samtools_0\\.1\\.18") "")
1688 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1689 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1690 (substitute* '("src/common.cpp"
1692 (("samtools_0.1.18") (which "samtools")))
1693 (substitute* '("src/common.h"
1694 "src/bam2fastx.cpp")
1695 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1696 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1697 (substitute* '("src/bwt_map.h"
1699 "src/align_status.h")
1700 (("#include <bam.h>") "#include <samtools/bam.h>")
1701 (("#include <sam.h>") "#include <samtools/sam.h>"))
1704 `(("gcc" ,gcc-5))) ;; doesn't build with later versions
1708 ("ncurses" ,ncurses)
1710 ("python" ,python-2)
1711 ("samtools" ,samtools-0.1)
1714 (home-page "https://ccb.jhu.edu/software/tophat/index.shtml")
1715 (synopsis "Spliced read mapper for RNA-Seq data")
1717 "TopHat is a fast splice junction mapper for nucleotide sequence
1718 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1719 mammalian-sized genomes using the ultra high-throughput short read
1720 aligner Bowtie, and then analyzes the mapping results to identify
1721 splice junctions between exons.")
1722 ;; TopHat is released under the Boost Software License, Version 1.0
1723 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1724 (license license:boost1.0)))
1733 "https://github.com/lh3/bwa/releases/download/v"
1734 version "/bwa-" version ".tar.bz2"))
1737 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1738 (build-system gnu-build-system)
1740 '(#:tests? #f ;no "check" target
1742 (modify-phases %standard-phases
1744 (lambda* (#:key outputs #:allow-other-keys)
1745 (let* ((out (assoc-ref outputs "out"))
1746 (bin (string-append out "/bin"))
1747 (lib (string-append out "/lib"))
1748 (doc (string-append out "/share/doc/bwa"))
1749 (man (string-append out "/share/man/man1")))
1750 (install-file "bwa" bin)
1751 (install-file "libbwa.a" lib)
1752 (install-file "README.md" doc)
1753 (install-file "bwa.1" man))
1755 ;; no "configure" script
1756 (delete 'configure))))
1757 (inputs `(("zlib" ,zlib)))
1758 ;; Non-portable SSE instructions are used so building fails on platforms
1759 ;; other than x86_64.
1760 (supported-systems '("x86_64-linux"))
1761 (home-page "http://bio-bwa.sourceforge.net/")
1762 (synopsis "Burrows-Wheeler sequence aligner")
1764 "BWA is a software package for mapping low-divergent sequences against a
1765 large reference genome, such as the human genome. It consists of three
1766 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1767 designed for Illumina sequence reads up to 100bp, while the rest two for
1768 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1769 features such as long-read support and split alignment, but BWA-MEM, which is
1770 the latest, is generally recommended for high-quality queries as it is faster
1771 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1772 70-100bp Illumina reads.")
1773 (license license:gpl3+)))
1775 (define-public bwa-pssm
1776 (package (inherit bwa)
1782 (url "https://github.com/pkerpedjiev/bwa-pssm.git")
1784 (file-name (git-file-name name version))
1787 "076c4q0cdqz8jgylb067y9zmvxglppnzi3qiscn0xiypgc6lgb5r"))))
1788 (build-system gnu-build-system)
1793 (home-page "http://bwa-pssm.binf.ku.dk/")
1794 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1796 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1797 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1798 existing aligners it is fast and sensitive. Unlike most other aligners,
1799 however, it is also adaptible in the sense that one can direct the alignment
1800 based on known biases within the data set. It is coded as a modification of
1801 the original BWA alignment program and shares the genome index structure as
1802 well as many of the command line options.")
1803 (license license:gpl3+)))
1805 (define-public bwa-meth
1812 (url "https://github.com/brentp/bwa-meth.git")
1813 (commit (string-append "v" version))))
1814 (file-name (git-file-name name version))
1817 "17j31i7zws5j7mhsq9x3qgkxly6mlmrgwhfq0qbflgxrmx04yaiz"))))
1818 (build-system python-build-system)
1821 (modify-phases %standard-phases
1822 (add-after 'unpack 'keep-references-to-bwa
1823 (lambda* (#:key inputs #:allow-other-keys)
1824 (substitute* "bwameth.py"
1825 (("bwa (mem|index)" _ command)
1826 (string-append (which "bwa") " " command))
1827 ;; There's an ill-advised check for "samtools" on PATH.
1833 `(("python-toolshed" ,python-toolshed)))
1834 (home-page "https://github.com/brentp/bwa-meth")
1835 (synopsis "Fast and accurante alignment of BS-Seq reads")
1837 "BWA-Meth works for single-end reads and for paired-end reads from the
1838 directional protocol (most common). It uses the method employed by
1839 methylcoder and Bismark of in silico conversion of all C's to T's in both
1840 reference and reads. It recovers the original read (needed to tabulate
1841 methylation) by attaching it as a comment which BWA appends as a tag to the
1842 read. It performs favorably to existing aligners gauged by number of on and
1843 off-target reads for a capture method that targets CpG-rich region.")
1844 (license license:expat)))
1846 (define-public python-bx-python
1848 (name "python-bx-python")
1852 (uri (pypi-uri "bx-python" version))
1855 "11kksg2rbzihpmcid823xvg42xi88m7sz58rzk29abybkxy0rszs"))))
1856 (build-system python-build-system)
1857 ;; Tests fail because test data are not included
1858 (arguments '(#:tests? #f))
1860 `(("python-numpy" ,python-numpy)
1861 ("python-six" ,python-six)))
1865 `(("python-lzo" ,python-lzo)
1866 ("python-nose" ,python-nose)
1867 ("python-cython" ,python-cython)))
1868 (home-page "https://github.com/bxlab/bx-python")
1869 (synopsis "Tools for manipulating biological data")
1871 "bx-python provides tools for manipulating biological data, particularly
1872 multiple sequence alignments.")
1873 (license license:expat)))
1875 (define-public python2-bx-python
1876 (package-with-python2 python-bx-python))
1878 (define-public python-pysam
1880 (name "python-pysam")
1884 ;; Test data is missing on PyPi.
1886 (url "https://github.com/pysam-developers/pysam.git")
1887 (commit (string-append "v" version))))
1888 (file-name (git-file-name name version))
1891 "1vj367w6xbn9bpmksm162l1aipf7cj97h1q83y7jcpm33ihwpf7x"))
1892 (modules '((guix build utils)))
1894 ;; Drop bundled htslib. TODO: Also remove samtools
1896 (delete-file-recursively "htslib")
1898 (build-system python-build-system)
1900 `(#:modules ((ice-9 ftw)
1902 (guix build python-build-system)
1905 (modify-phases %standard-phases
1906 (add-before 'build 'set-flags
1907 (lambda* (#:key inputs #:allow-other-keys)
1908 (setenv "HTSLIB_MODE" "external")
1909 (setenv "HTSLIB_LIBRARY_DIR"
1910 (string-append (assoc-ref inputs "htslib") "/lib"))
1911 (setenv "HTSLIB_INCLUDE_DIR"
1912 (string-append (assoc-ref inputs "htslib") "/include"))
1913 (setenv "LDFLAGS" "-lncurses")
1914 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1917 (lambda* (#:key inputs outputs #:allow-other-keys)
1918 ;; This file contains tests that require a connection to the
1920 (delete-file "tests/tabix_test.py")
1921 ;; FIXME: This test fails
1922 (delete-file "tests/AlignmentFile_test.py")
1923 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1924 (setenv "PYTHONPATH"
1926 (getenv "PYTHONPATH")
1927 ":" (getcwd) "/build/"
1928 (car (scandir "build"
1929 (negate (cut string-prefix? "." <>))))))
1930 ;; Step out of source dir so python does not import from CWD.
1931 (with-directory-excursion "tests"
1932 (setenv "HOME" "/tmp")
1933 (invoke "make" "-C" "pysam_data")
1934 (invoke "make" "-C" "cbcf_data")
1935 ;; Running nosetests without explicitly asking for a single
1936 ;; process leads to a crash. Running with multiple processes
1937 ;; fails because the tests are not designed to run in parallel.
1939 ;; FIXME: tests keep timing out on some systems.
1940 (invoke "nosetests" "-v" "--processes" "1")))))))
1942 `(("htslib" ,htslib))) ; Included from installed header files.
1944 `(("ncurses" ,ncurses)
1948 `(("python-cython" ,python-cython)
1949 ;; Dependencies below are are for tests only.
1950 ("samtools" ,samtools)
1951 ("bcftools" ,bcftools)
1952 ("python-nose" ,python-nose)))
1953 (home-page "https://github.com/pysam-developers/pysam")
1954 (synopsis "Python bindings to the SAMtools C API")
1956 "Pysam is a Python module for reading and manipulating files in the
1957 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1958 also includes an interface for tabix.")
1959 (license license:expat)))
1961 (define-public python2-pysam
1962 (package-with-python2 python-pysam))
1964 (define-public python-twobitreader
1966 (name "python-twobitreader")
1971 (url "https://github.com/benjschiller/twobitreader")
1973 (file-name (git-file-name name version))
1976 "1qbxvv1h58cismbk1anpjrkpghsaiy64a11ir3lhy6qch6xf8n62"))))
1977 (build-system python-build-system)
1978 ;; Tests are not included
1979 (arguments '(#:tests? #f))
1981 `(("python-sphinx" ,python-sphinx)))
1982 (home-page "https://github.com/benjschiller/twobitreader")
1983 (synopsis "Python library for reading .2bit files")
1985 "twobitreader is a Python library for reading .2bit files as used by the
1986 UCSC genome browser.")
1987 (license license:artistic2.0)))
1989 (define-public python2-twobitreader
1990 (package-with-python2 python-twobitreader))
1992 (define-public python-plastid
1994 (name "python-plastid")
1998 (uri (pypi-uri "plastid" version))
2001 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
2002 (build-system python-build-system)
2004 ;; Some test files are not included.
2007 `(("python-numpy" ,python-numpy)
2008 ("python-scipy" ,python-scipy)
2009 ("python-pandas" ,python-pandas)
2010 ("python-pysam" ,python-pysam)
2011 ("python-matplotlib" ,python-matplotlib)
2012 ("python-biopython" ,python-biopython)
2013 ("python-twobitreader" ,python-twobitreader)
2014 ("python-termcolor" ,python-termcolor)))
2016 `(("python-cython" ,python-cython)
2017 ("python-nose" ,python-nose)))
2018 (home-page "https://github.com/joshuagryphon/plastid")
2019 (synopsis "Python library for genomic analysis")
2021 "plastid is a Python library for genomic analysis – in particular,
2022 high-throughput sequencing data – with an emphasis on simplicity.")
2023 (license license:bsd-3)))
2025 (define-public python2-plastid
2026 (package-with-python2 python-plastid))
2028 (define-public tetoolkit
2035 (url "https://github.com/mhammell-laboratory/tetoolkit.git")
2037 (file-name (git-file-name name version))
2040 "1yzi0kfpzip8zpjb82x1ik6h22yzfyjiz2dv85v6as2awwqvk807"))))
2041 (build-system python-build-system)
2043 `(#:python ,python-2 ; not guaranteed to work with Python 3
2045 (modify-phases %standard-phases
2046 (add-after 'unpack 'make-writable
2048 (for-each make-file-writable (find-files "."))
2050 (add-after 'unpack 'patch-invocations
2051 (lambda* (#:key inputs #:allow-other-keys)
2052 (substitute* '("bin/TEtranscripts"
2055 (string-append "'" (which "sort") " "))
2057 (string-append "'" (which "rm") " -f "))
2058 (("'Rscript'") (string-append "'" (which "Rscript") "'")))
2059 (substitute* "TEToolkit/IO/ReadInputs.py"
2060 (("BamToBED") (which "bamToBed")))
2061 (substitute* "TEToolkit/Normalization.py"
2063 (string-append "\"" (which "Rscript") "\"")))
2065 (add-after 'install 'wrap-program
2066 (lambda* (#:key outputs #:allow-other-keys)
2067 ;; Make sure the executables find R packages.
2068 (let ((out (assoc-ref outputs "out")))
2071 (wrap-program (string-append out "/bin/" script)
2072 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
2077 `(("coreutils" ,coreutils)
2078 ("bedtools" ,bedtools)
2079 ("python-argparse" ,python2-argparse)
2080 ("python-pysam" ,python2-pysam)
2081 ("r-minimal" ,r-minimal)
2082 ("r-deseq2" ,r-deseq2)))
2083 (home-page "https://github.com/mhammell-laboratory/tetoolkit")
2084 (synopsis "Transposable elements in differential enrichment analysis")
2086 "This is package for including transposable elements in differential
2087 enrichment analysis of sequencing datasets. TEtranscripts and TEcount take
2088 RNA-seq (and similar data) and annotates reads to both genes and transposable
2089 elements. TEtranscripts then performs differential analysis using DESeq2.
2090 Note that TEtranscripts and TEcount rely on specially curated GTF files, which
2091 are not included due to their size.")
2092 (license license:gpl3+)))
2094 (define-public cd-hit
2100 (uri (string-append "https://github.com/weizhongli/cdhit"
2101 "/releases/download/V" version
2103 "-2017-0621-source.tar.gz"))
2106 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
2107 (build-system gnu-build-system)
2109 `(#:tests? #f ; there are no tests
2111 ;; Executables are copied directly to the PREFIX.
2112 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin")
2113 ;; Support longer sequences (e.g. Pacbio sequences)
2116 (modify-phases %standard-phases
2117 ;; No "configure" script
2119 ;; Remove sources of non-determinism
2120 (add-after 'unpack 'be-timeless
2122 (substitute* "cdhit-utility.c++"
2123 ((" \\(built on \" __DATE__ \"\\)") ""))
2124 (substitute* "cdhit-common.c++"
2125 (("__DATE__") "\"0\"")
2126 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
2128 ;; The "install" target does not create the target directory.
2129 (add-before 'install 'create-target-dir
2130 (lambda* (#:key outputs #:allow-other-keys)
2131 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
2135 (home-page "http://weizhongli-lab.org/cd-hit/")
2136 (synopsis "Cluster and compare protein or nucleotide sequences")
2138 "CD-HIT is a program for clustering and comparing protein or nucleotide
2139 sequences. CD-HIT is designed to be fast and handle extremely large
2141 ;; The manual says: "It can be copied under the GNU General Public License
2142 ;; version 2 (GPLv2)."
2143 (license license:gpl2)))
2145 (define-public clipper
2152 (url "https://github.com/YeoLab/clipper.git")
2154 (file-name (git-file-name name version))
2157 "0fja1rj84wp9vpj8rxpj3n8zqzcqq454m904yp9as1w4phccirjb"))
2158 (modules '((guix build utils)))
2161 ;; remove unnecessary setup dependency
2162 (substitute* "setup.py"
2163 (("setup_requires = .*") ""))
2165 (build-system python-build-system)
2167 `(#:python ,python-2 ; only Python 2 is supported
2169 (modify-phases %standard-phases
2170 ;; This is fixed in upstream commit
2171 ;; f6c2990198f906bf97730d95695b4bd5a6d01ddb.
2172 (add-after 'unpack 'fix-typo
2174 (substitute* "clipper/src/readsToWiggle.pyx"
2178 `(("htseq" ,python2-htseq)
2179 ("python-pybedtools" ,python2-pybedtools)
2180 ("python-cython" ,python2-cython)
2181 ("python-scikit-learn" ,python2-scikit-learn)
2182 ("python-matplotlib" ,python2-matplotlib)
2183 ("python-pandas" ,python2-pandas)
2184 ("python-pysam" ,python2-pysam)
2185 ("python-numpy" ,python2-numpy)
2186 ("python-scipy" ,python2-scipy)))
2188 `(("python-mock" ,python2-mock) ; for tests
2189 ("python-nose" ,python2-nose) ; for tests
2190 ("python-pytz" ,python2-pytz))) ; for tests
2191 (home-page "https://github.com/YeoLab/clipper")
2192 (synopsis "CLIP peak enrichment recognition")
2194 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
2195 (license license:gpl2)))
2197 (define-public codingquarry
2199 (name "codingquarry")
2204 "mirror://sourceforge/codingquarry/CodingQuarry_v"
2208 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
2209 (build-system gnu-build-system)
2211 '(#:tests? #f ; no "check" target
2213 (modify-phases %standard-phases
2216 (lambda* (#:key outputs #:allow-other-keys)
2217 (let* ((out (assoc-ref outputs "out"))
2218 (bin (string-append out "/bin"))
2219 (doc (string-append out "/share/doc/codingquarry")))
2220 (install-file "INSTRUCTIONS.pdf" doc)
2221 (copy-recursively "QuarryFiles"
2222 (string-append out "/QuarryFiles"))
2223 (install-file "CodingQuarry" bin)
2224 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin))
2226 (inputs `(("openmpi" ,openmpi)))
2227 (native-search-paths
2228 (list (search-path-specification
2229 (variable "QUARRY_PATH")
2230 (files '("QuarryFiles")))))
2231 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
2232 (synopsis "Fungal gene predictor")
2233 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
2234 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
2235 (home-page "https://sourceforge.net/projects/codingquarry/")
2236 (license license:gpl3+)))
2238 (define-public couger
2245 "http://couger.oit.duke.edu/static/assets/COUGER"
2249 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
2250 (build-system gnu-build-system)
2254 (modify-phases %standard-phases
2259 (lambda* (#:key outputs #:allow-other-keys)
2260 (let* ((out (assoc-ref outputs "out"))
2261 (bin (string-append out "/bin")))
2262 (copy-recursively "src" (string-append out "/src"))
2264 ;; Add "src" directory to module lookup path.
2265 (substitute* "couger"
2267 (string-append "import sys\nsys.path.append(\""
2268 out "\")\nfrom argparse")))
2269 (install-file "couger" bin))
2272 'install 'wrap-program
2273 (lambda* (#:key inputs outputs #:allow-other-keys)
2274 ;; Make sure 'couger' runs with the correct PYTHONPATH.
2275 (let* ((out (assoc-ref outputs "out"))
2276 (path (getenv "PYTHONPATH")))
2277 (wrap-program (string-append out "/bin/couger")
2278 `("PYTHONPATH" ":" prefix (,path))))
2281 `(("python" ,python-2)
2282 ("python2-pillow" ,python2-pillow)
2283 ("python2-numpy" ,python2-numpy)
2284 ("python2-scipy" ,python2-scipy)
2285 ("python2-matplotlib" ,python2-matplotlib)))
2287 `(("r-minimal" ,r-minimal)
2289 ("randomjungle" ,randomjungle)))
2291 `(("unzip" ,unzip)))
2292 (home-page "http://couger.oit.duke.edu")
2293 (synopsis "Identify co-factors in sets of genomic regions")
2295 "COUGER can be applied to any two sets of genomic regions bound by
2296 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
2297 putative co-factors that provide specificity to each TF. The framework
2298 determines the genomic targets uniquely-bound by each TF, and identifies a
2299 small set of co-factors that best explain the in vivo binding differences
2300 between the two TFs.
2302 COUGER uses classification algorithms (support vector machines and random
2303 forests) with features that reflect the DNA binding specificities of putative
2304 co-factors. The features are generated either from high-throughput TF-DNA
2305 binding data (from protein binding microarray experiments), or from large
2306 collections of DNA motifs.")
2307 (license license:gpl3+)))
2309 (define-public clustal-omega
2311 (name "clustal-omega")
2315 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
2319 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
2320 (build-system gnu-build-system)
2322 `(("argtable" ,argtable)))
2323 (home-page "http://www.clustal.org/omega/")
2324 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
2326 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
2327 program for protein and DNA/RNA. It produces high quality MSAs and is capable
2328 of handling data-sets of hundreds of thousands of sequences in reasonable
2330 (license license:gpl2+)))
2332 (define-public crossmap
2338 (uri (pypi-uri "CrossMap" version))
2341 "1sb2f2qbxya4fzw3yjl09vbrs8vfmw22zrygrvz004sf9gb1vkan"))))
2342 (build-system python-build-system)
2344 `(("python-bx-python" ,python-bx-python)
2345 ("python-numpy" ,python-numpy)
2346 ("python-pybigwig" ,python-pybigwig)
2347 ("python-pysam" ,python-pysam)
2350 `(("python-cython" ,python-cython)
2351 ("python-nose" ,python-nose)))
2352 (home-page "http://crossmap.sourceforge.net/")
2353 (synopsis "Convert genome coordinates between assemblies")
2355 "CrossMap is a program for conversion of genome coordinates or annotation
2356 files between different genome assemblies. It supports most commonly used
2357 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
2358 (license license:gpl2+)))
2360 (define-public python-dnaio
2362 (name "python-dnaio")
2367 (uri (pypi-uri "dnaio" version))
2370 "0f16m7hdlm0fz1n7y5asy0v9ghyrq17ni1p9iybq22ddzyd49r27"))))
2371 (build-system python-build-system)
2373 `(("python-cython" ,python-cython)
2374 ("python-pytest" ,python-pytest)
2375 ("python-xopen" ,python-xopen)))
2376 (home-page "https://github.com/marcelm/dnaio/")
2377 (synopsis "Read FASTA and FASTQ files efficiently")
2379 "dnaio is a Python library for fast parsing of FASTQ and also FASTA
2380 files. The code was previously part of the cutadapt tool.")
2381 (license license:expat)))
2383 (define-public python-deeptoolsintervals
2385 (name "python-deeptoolsintervals")
2389 (uri (pypi-uri "deeptoolsintervals" version))
2392 "1xnl80nblysj6dylj4683wgrfa425rkx4dp5k65hvwdns9pw753x"))))
2393 (build-system python-build-system)
2396 (home-page "https://github.com/deeptools/deeptools_intervals")
2397 (synopsis "Create GTF-based interval trees with associated meta-data")
2399 "This package provides a Python module creating/accessing GTF-based
2400 interval trees with associated meta-data. It is primarily used by the
2401 @code{deeptools} package.")
2402 (license license:expat)))
2404 (define-public python-deeptools
2406 (name "python-deeptools")
2410 (uri (pypi-uri "deepTools" version))
2413 "1azgjniss5ff6a90nicdjkxyjwqmi3gzfn09gra42hwlz19hipxb"))))
2414 (build-system python-build-system)
2416 `(("python-matplotlib" ,python-matplotlib)
2417 ("python-numpy" ,python-numpy)
2418 ("python-numpydoc" ,python-numpydoc)
2419 ("python-py2bit" ,python-py2bit)
2420 ("python-pybigwig" ,python-pybigwig)
2421 ("python-pysam" ,python-pysam)
2422 ("python-scipy" ,python-scipy)
2423 ("python-deeptoolsintervals" ,python-deeptoolsintervals)
2424 ("python-plotly" ,python-plotly)))
2425 (home-page "https://pypi.org/project/deepTools/")
2426 (synopsis "Useful tools for exploring deep sequencing data")
2427 (description "This package addresses the challenge of handling large amounts
2428 of data that are now routinely generated from DNA sequencing centers.
2429 @code{deepTools} contains useful modules to process the mapped reads data for
2430 multiple quality checks, creating normalized coverage files in standard bedGraph
2431 and bigWig file formats, that allow comparison between different files. Finally,
2432 using such normalized and standardized files, deepTools can create many
2433 publication-ready visualizations to identify enrichments and for functional
2434 annotations of the genome.")
2435 ;; The file deeptools/cm.py is licensed under the BSD license. The
2436 ;; remainder of the code is licensed under the MIT license.
2437 (license (list license:bsd-3 license:expat))))
2439 (define-public cutadapt
2445 (uri (pypi-uri "cutadapt" version))
2448 "1vqmsfkm6llxzmsz9wcfcvzx9a9f8iabvwik2rbyn7nc4wm25z89"))))
2449 (build-system python-build-system)
2451 `(("python-dnaio" ,python-dnaio)
2452 ("python-xopen" ,python-xopen)))
2454 `(("python-cython" ,python-cython)
2455 ("python-pytest" ,python-pytest)
2456 ("python-setuptools-scm" ,python-setuptools-scm)))
2457 (home-page "https://cutadapt.readthedocs.io/en/stable/")
2458 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
2460 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
2461 other types of unwanted sequence from high-throughput sequencing reads.")
2462 (license license:expat)))
2464 (define-public libbigwig
2471 (url "https://github.com/dpryan79/libBigWig.git")
2473 (file-name (git-file-name name version))
2476 "09693dmf1scdac5pyq6qyn8b4mcipvnmc370k9a5z41z81m3dcsj"))))
2477 (build-system gnu-build-system)
2479 `(#:test-target "test"
2480 #:tests? #f ; tests require access to the web
2483 (string-append "prefix=" (assoc-ref %outputs "out")))
2485 (modify-phases %standard-phases
2486 (delete 'configure))))
2491 `(("doxygen" ,doxygen)
2493 ("python" ,python-2)))
2494 (home-page "https://github.com/dpryan79/libBigWig")
2495 (synopsis "C library for handling bigWig files")
2497 "This package provides a C library for parsing local and remote BigWig
2499 (license license:expat)))
2501 (define-public python-pybigwig
2503 (name "python-pybigwig")
2507 (uri (pypi-uri "pyBigWig" version))
2510 "157x6v48y299zm382krf1dw08fdxg95im8lnabhp5vc94s04zxj1"))
2511 (modules '((guix build utils)))
2514 ;; Delete bundled libBigWig sources
2515 (delete-file-recursively "libBigWig")
2517 (build-system python-build-system)
2520 (modify-phases %standard-phases
2521 (add-after 'unpack 'link-with-libBigWig
2522 (lambda* (#:key inputs #:allow-other-keys)
2523 (substitute* "setup.py"
2524 (("libs=\\[") "libs=[\"BigWig\", "))
2527 `(("python-numpy" ,python-numpy)))
2529 `(("libbigwig" ,libbigwig)
2532 (home-page "https://github.com/dpryan79/pyBigWig")
2533 (synopsis "Access bigWig files in Python using libBigWig")
2535 "This package provides Python bindings to the libBigWig library for
2536 accessing bigWig files.")
2537 (license license:expat)))
2539 (define-public python2-pybigwig
2540 (package-with-python2 python-pybigwig))
2542 (define-public python-dendropy
2544 (name "python-dendropy")
2549 ;; Source from GitHub so that tests are included.
2551 (url "https://github.com/jeetsukumaran/DendroPy.git")
2552 (commit (string-append "v" version))))
2553 (file-name (git-file-name name version))
2556 "097hfyv2kaf4x92i4rjx0paw2cncxap48qivv8zxng4z7nhid0x9"))))
2557 (build-system python-build-system)
2558 (home-page "https://dendropy.org/")
2559 (synopsis "Library for phylogenetics and phylogenetic computing")
2561 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
2562 writing, simulation, processing and manipulation of phylogenetic
2563 trees (phylogenies) and characters.")
2564 (license license:bsd-3)))
2566 (define-public python2-dendropy
2567 (let ((base (package-with-python2 python-dendropy)))
2572 (modify-phases %standard-phases
2573 (add-after 'unpack 'remove-failing-test
2575 ;; This test fails when the full test suite is run, as documented
2576 ;; at https://github.com/jeetsukumaran/DendroPy/issues/74
2577 (substitute* "tests/test_dataio_nexml_reader_tree_list.py"
2578 (("test_collection_comments_and_annotations")
2579 "do_not_test_collection_comments_and_annotations"))
2581 ,@(package-arguments base))))))
2583 (define-public python-py2bit
2585 (name "python-py2bit")
2590 (uri (pypi-uri "py2bit" version))
2593 "1vw2nvw1yrl7ikkqsqs1pg239yr5nspvd969r1x9arms1k25a1a5"))))
2594 (build-system python-build-system)
2595 (home-page "https://github.com/dpryan79/py2bit")
2596 (synopsis "Access 2bit files using lib2bit")
2598 "This package provides Python bindings for lib2bit to access 2bit files
2600 (license license:expat)))
2602 (define-public deeptools
2609 (url "https://github.com/deeptools/deepTools.git")
2611 (file-name (git-file-name name version))
2614 "1vggnf52g6q2vifdl4cyi7s2fnfqq0ky2zrkj5zv2qfzsc3p3siw"))))
2615 (build-system python-build-system)
2618 (modify-phases %standard-phases
2619 ;; This phase fails, but it's not needed.
2620 (delete 'reset-gzip-timestamps))))
2622 `(("python-plotly" ,python-plotly)
2623 ("python-scipy" ,python-scipy)
2624 ("python-numpy" ,python-numpy)
2625 ("python-numpydoc" ,python-numpydoc)
2626 ("python-matplotlib" ,python-matplotlib)
2627 ("python-pysam" ,python-pysam)
2628 ("python-py2bit" ,python-py2bit)
2629 ("python-pybigwig" ,python-pybigwig)))
2631 `(("python-mock" ,python-mock) ;for tests
2632 ("python-nose" ,python-nose) ;for tests
2633 ("python-pytz" ,python-pytz))) ;for tests
2634 (home-page "https://github.com/deeptools/deepTools")
2635 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2637 "DeepTools addresses the challenge of handling the large amounts of data
2638 that are now routinely generated from DNA sequencing centers. To do so,
2639 deepTools contains useful modules to process the mapped reads data to create
2640 coverage files in standard bedGraph and bigWig file formats. By doing so,
2641 deepTools allows the creation of normalized coverage files or the comparison
2642 between two files (for example, treatment and control). Finally, using such
2643 normalized and standardized files, multiple visualizations can be created to
2644 identify enrichments with functional annotations of the genome.")
2645 (license license:gpl3+)))
2647 (define-public delly
2654 (url "https://github.com/dellytools/delly.git")
2655 (commit (string-append "v" version))))
2656 (file-name (git-file-name name version))
2658 (base32 "034jqsxswy9gqdh2zkgc1js99qkv75ks4xvzgmh0284sraagv61z"))
2659 (modules '((guix build utils)))
2662 (delete-file-recursively "src/htslib")
2664 (build-system gnu-build-system)
2666 `(#:tests? #f ; There are no tests to run.
2668 (list "PARALLEL=1" ; Allow parallel execution at run-time.
2669 (string-append "prefix=" (assoc-ref %outputs "out")))
2671 (modify-phases %standard-phases
2672 (delete 'configure) ; There is no configure phase.
2673 (add-after 'install 'install-templates
2674 (lambda* (#:key outputs #:allow-other-keys)
2675 (let ((templates (string-append (assoc-ref outputs "out")
2676 "/share/delly/templates")))
2678 (copy-recursively "excludeTemplates" templates)
2685 (home-page "https://github.com/dellytools/delly")
2686 (synopsis "Integrated structural variant prediction method")
2687 (description "Delly is an integrated structural variant prediction method
2688 that can discover and genotype deletions, tandem duplications, inversions and
2689 translocations at single-nucleotide resolution in short-read massively parallel
2690 sequencing data. It uses paired-ends and split-reads to sensitively and
2691 accurately delineate genomic rearrangements throughout the genome.")
2692 (license license:gpl3+)))
2694 (define-public diamond
2701 (url "https://github.com/bbuchfink/diamond.git")
2702 (commit (string-append "v" version))))
2703 (file-name (git-file-name name version))
2706 "0k6f3kb6cniw11xw6763kkbs1sl0yack7xsy7q5fl5v170ssphq4"))))
2707 (build-system cmake-build-system)
2709 '(#:tests? #f ; no "check" target
2711 (modify-phases %standard-phases
2712 (add-after 'unpack 'remove-native-compilation
2714 (substitute* "CMakeLists.txt" (("-march=native") ""))
2718 (home-page "https://github.com/bbuchfink/diamond")
2719 (synopsis "Accelerated BLAST compatible local sequence aligner")
2721 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2722 translated DNA query sequences against a protein reference database (BLASTP
2723 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2724 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2725 data and settings.")
2726 (license license:agpl3+)))
2728 (define-public discrover
2736 (url "https://github.com/maaskola/discrover.git")
2738 (file-name (git-file-name name version))
2741 "173fwi2vb6a5kp406hm3jj6j7v4whww796f2qcygp4rpvamh307y"))))
2742 (build-system cmake-build-system)
2744 `(#:tests? #f ; there are no tests
2746 (modify-phases %standard-phases
2747 (add-after 'unpack 'fix-latex-errors
2749 (with-fluids ((%default-port-encoding #f))
2750 (substitute* "doc/references.bib"
2751 (("\\{S\\}illanp[^,]+,")
2752 "{S}illanp{\\\"a}{\\\"a},")))
2753 ;; XXX: I just can't get pdflatex to not complain about these
2754 ;; characters. They end up in the manual via the generated
2755 ;; discrover-cli-help.txt.
2756 (substitute* "src/hmm/cli.cpp"
2760 ;; This seems to be a syntax error.
2761 (substitute* "doc/discrover-manual.tex"
2762 (("theverbbox\\[t\\]") "theverbbox"))
2764 (add-after 'unpack 'add-missing-includes
2766 (substitute* "src/executioninformation.hpp"
2767 (("#define EXECUTIONINFORMATION_HPP" line)
2768 (string-append line "\n#include <random>")))
2769 (substitute* "src/plasma/fasta.hpp"
2770 (("#define FASTA_HPP" line)
2771 (string-append line "\n#include <random>")))
2773 ;; FIXME: this is needed because we're using texlive-union, which
2774 ;; doesn't handle fonts correctly. It expects to be able to generate
2775 ;; fonts in the home directory.
2776 (add-before 'build 'setenv-HOME
2777 (lambda _ (setenv "HOME" "/tmp") #t)))))
2781 ("rmath-standalone" ,rmath-standalone)))
2783 `(("texlive" ,(texlive-union (list texlive-fonts-cm
2784 texlive-fonts-amsfonts
2787 texlive-latex-examplep
2788 texlive-latex-hyperref
2790 texlive-latex-natbib
2791 texlive-bibtex ; style files used by natbib
2792 texlive-latex-pgf ; tikz
2793 texlive-latex-verbatimbox)))
2794 ("imagemagick" ,imagemagick)))
2795 (home-page "https://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2796 (synopsis "Discover discriminative nucleotide sequence motifs")
2797 (description "Discrover is a motif discovery method to find binding sites
2798 of nucleic acid binding proteins.")
2799 (license license:gpl3+)))
2801 (define-public eigensoft
2809 (url "https://github.com/DReichLab/EIG.git")
2810 (commit (string-append "v" version))))
2811 (file-name (git-file-name name version))
2814 "1c141fqvhnzibmnf22sv23vbmzm20kjjyrib44cfh75wyndp2d9k"))
2815 (modules '((guix build utils)))
2816 ;; Remove pre-built binaries.
2818 (delete-file-recursively "bin")
2821 (build-system gnu-build-system)
2823 `(#:tests? #f ; There are no tests.
2824 #:make-flags '("CC=gcc")
2826 (modify-phases %standard-phases
2827 ;; There is no configure phase, but the Makefile is in a
2830 (lambda _ (chdir "src") #t))
2831 ;; The provided install target only copies executables to
2832 ;; the "bin" directory in the build root.
2833 (add-after 'install 'actually-install
2834 (lambda* (#:key outputs #:allow-other-keys)
2835 (let* ((out (assoc-ref outputs "out"))
2836 (bin (string-append out "/bin")))
2837 (for-each (lambda (file)
2838 (install-file file bin))
2839 (find-files "../bin" ".*"))
2844 ("openblas" ,openblas)
2846 ("gfortran" ,gfortran "lib")))
2847 (home-page "https://github.com/DReichLab/EIG")
2848 (synopsis "Tools for population genetics")
2849 (description "The EIGENSOFT package provides tools for population
2850 genetics and stratification correction. EIGENSOFT implements methods commonly
2851 used in population genetics analyses such as PCA, computation of Tracy-Widom
2852 statistics, and finding related individuals in structured populations. It
2853 comes with a built-in plotting script and supports multiple file formats and
2854 quantitative phenotypes.")
2855 ;; The license of the eigensoft tools is Expat, but since it's
2856 ;; linking with the GNU Scientific Library (GSL) the effective
2857 ;; license is the GPL.
2858 (license license:gpl3+)))
2860 (define-public edirect
2863 (version "13.3.20200128")
2866 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect"
2867 "/versions/" version
2868 "/edirect-" version ".tar.gz"))
2871 "093zp7klv81ph0y8mm8d78a9hnpfxbv2kdym70gzdf3vz176rw33"))
2872 (modules '((guix build utils)))
2874 '(begin (delete-file "Mozilla-CA.tar.gz")
2875 (substitute* "rchive.go"
2876 ;; This go library does not have any license.
2877 (("github.com/fiam/gounidecode/unidecode")
2878 "golang.org/rainycape/unidecode"))
2880 (build-system perl-build-system)
2883 (modify-phases %standard-phases
2886 (delete 'check) ; simple check after install
2887 (add-after 'unpack 'patch-programs
2888 (lambda* (#:key inputs #:allow-other-keys)
2889 ;; Ignore errors about missing xtract.Linux and rchive.Linux.
2890 (substitute* "pm-refresh"
2891 (("cat \\\"\\$target")
2892 "grep ^[[:digit:]] \"$target"))
2895 (lambda* (#:key inputs outputs #:allow-other-keys)
2896 (let ((bin (string-append (assoc-ref outputs "out") "/bin"))
2897 (edirect-go (assoc-ref inputs "edirect-go-programs")))
2900 (install-file file bin))
2901 '("archive-pubmed" "asp-cp" "asp-ls" "download-ncbi-data"
2902 "download-pubmed" "edirect.pl" "efetch" "epost" "esearch"
2903 "fetch-pubmed" "ftp-cp" "ftp-ls" "has-asp" "index-pubmed"
2904 "pm-prepare" "pm-refresh" "pm-stash" "pm-collect"
2905 "pm-index" "pm-invert" "pm-merge" "pm-promote"))
2906 (symlink (string-append edirect-go "/bin/xtract.Linux")
2907 (string-append bin "/xtract"))
2908 (symlink (string-append edirect-go "/bin/rchive.Linux")
2909 (string-append bin "/rchive")))
2911 (add-after 'install 'wrap-program
2912 (lambda* (#:key outputs #:allow-other-keys)
2913 ;; Make sure everything can run in a pure environment.
2914 (let ((out (assoc-ref outputs "out"))
2915 (path (getenv "PERL5LIB")))
2919 `("PERL5LIB" ":" prefix (,path)))
2921 `("PATH" ":" prefix (,(string-append out "/bin")
2922 ,(dirname (which "sed"))
2923 ,(dirname (which "gzip"))
2924 ,(dirname (which "grep"))
2925 ,(dirname (which "perl"))
2926 ,(dirname (which "uname"))))))
2927 (find-files out ".")))
2929 (add-after 'wrap-program 'check
2930 (lambda* (#:key outputs #:allow-other-keys)
2931 (invoke (string-append (assoc-ref outputs "out")
2936 `(("edirect-go-programs" ,edirect-go-programs)
2937 ("perl-html-parser" ,perl-html-parser)
2938 ("perl-encode-locale" ,perl-encode-locale)
2939 ("perl-file-listing" ,perl-file-listing)
2940 ("perl-html-tagset" ,perl-html-tagset)
2941 ("perl-html-tree" ,perl-html-tree)
2942 ("perl-http-cookies" ,perl-http-cookies)
2943 ("perl-http-date" ,perl-http-date)
2944 ("perl-http-message" ,perl-http-message)
2945 ("perl-http-negotiate" ,perl-http-negotiate)
2946 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2947 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2948 ("perl-net-http" ,perl-net-http)
2949 ("perl-uri" ,perl-uri)
2950 ("perl-www-robotrules" ,perl-www-robotrules)
2951 ("perl-xml-simple" ,perl-xml-simple)
2953 (home-page "https://www.ncbi.nlm.nih.gov/books/NBK179288/")
2954 (synopsis "Tools for accessing the NCBI's set of databases")
2956 "Entrez Direct (EDirect) is a method for accessing the National Center
2957 for Biotechnology Information's (NCBI) set of interconnected
2958 databases (publication, sequence, structure, gene, variation, expression,
2959 etc.) from a terminal. Functions take search terms from command-line
2960 arguments. Individual operations are combined to build multi-step queries.
2961 Record retrieval and formatting normally complete the process.
2963 EDirect also provides an argument-driven function that simplifies the
2964 extraction of data from document summaries or other results that are returned
2965 in structured XML format. This can eliminate the need for writing custom
2966 software to answer ad hoc questions.")
2967 (native-search-paths
2968 ;; Ideally this should be set for LWP somewhere.
2969 (list (search-path-specification
2970 (variable "PERL_LWP_SSL_CA_FILE")
2971 (file-type 'regular)
2973 (files '("/etc/ssl/certs/ca-certificates.crt")))))
2974 (license license:public-domain)))
2976 (define-public edirect-go-programs
2979 (name "edirect-go-programs")
2980 (build-system go-build-system)
2982 `(#:install-source? #f
2983 #:tests? #f ; No tests.
2984 #:import-path "ncbi.nlm.nih.gov/entrez/edirect"
2986 (modify-phases %standard-phases
2988 (lambda* (#:key import-path #:allow-other-keys)
2989 (with-directory-excursion (string-append "src/" import-path)
2990 (invoke "go" "build" "-v" "-x" "j2x.go")
2991 (invoke "go" "build" "-v" "-x" "t2x.go")
2992 (invoke "go" "build" "-v" "-x" "-o"
2993 "xtract.Linux" "xtract.go" "common.go")
2994 (invoke "go" "build" "-v" "-x" "-o"
2995 "rchive.Linux" "rchive.go" "common.go")
2996 (invoke "go" "build" "-v" "-x" "-o" "symbols.Linux" "s2p.go"))))
2998 (lambda* (#:key outputs import-path #:allow-other-keys)
2999 (let ((dest (string-append (assoc-ref outputs "out") "/bin"))
3000 (source (string-append "src/" import-path "/")))
3001 (for-each (lambda (file)
3002 (format #t "installing ~a~%" file)
3003 (install-file (string-append source file) dest))
3004 '("j2x" "t2x" "symbols.Linux" "xtract.Linux" "rchive.Linux"))
3007 (propagated-inputs '())
3009 `(("go-github-com-fatih-color" ,go-github-com-fatih-color)
3010 ("go-github-com-fogleman-gg" ,go-github-com-fogleman-gg)
3011 ("go-github-com-gedex-inflector" ,go-github-com-gedex-inflector)
3012 ("go-github-com-golang-freetype" ,go-github-com-golang-freetype)
3013 ("go-github-com-klauspost-cpuid" ,go-github-com-klauspost-cpuid)
3014 ("go-github-com-pbnjay-memory" ,go-github-com-pbnjay-memory)
3015 ("go-github-com-surgebase-porter2" ,go-github-com-surgebase-porter2)
3016 ("go-golang-org-rainycape-unidecode" ,go-golang-org-rainycape-unidecode)
3017 ("go-golang-org-x-image" ,go-golang-org-x-image)
3018 ("go-golang-org-x-text" ,go-golang-org-x-text)))))
3020 (define-public exonerate
3029 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
3030 "exonerate-" version ".tar.gz"))
3033 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
3034 (build-system gnu-build-system)
3036 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
3038 `(("pkg-config" ,pkg-config)))
3042 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
3043 (synopsis "Generic tool for biological sequence alignment")
3045 "Exonerate is a generic tool for pairwise sequence comparison. It allows
3046 the alignment of sequences using a many alignment models, either exhaustive
3047 dynamic programming or a variety of heuristics.")
3048 (license license:gpl3)))
3050 (define-public express
3058 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
3059 version "/express-" version "-src.tgz"))
3062 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
3063 (build-system cmake-build-system)
3065 `(#:tests? #f ;no "check" target
3067 (modify-phases %standard-phases
3068 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
3069 (lambda* (#:key inputs #:allow-other-keys)
3070 (substitute* "CMakeLists.txt"
3071 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
3072 "set(Boost_USE_STATIC_LIBS OFF)")
3073 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
3074 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
3075 (substitute* "src/CMakeLists.txt"
3076 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
3077 (string-append (assoc-ref inputs "bamtools") "/lib"))
3078 (("libprotobuf.a") "libprotobuf.so"))
3082 ("bamtools" ,bamtools)
3083 ("protobuf" ,protobuf)
3085 (home-page "http://bio.math.berkeley.edu/eXpress")
3086 (synopsis "Streaming quantification for high-throughput genomic sequencing")
3088 "eXpress is a streaming tool for quantifying the abundances of a set of
3089 target sequences from sampled subsequences. Example applications include
3090 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
3091 analysis (from RNA-Seq), transcription factor binding quantification in
3092 ChIP-Seq, and analysis of metagenomic data.")
3093 (license license:artistic2.0)))
3095 (define-public express-beta-diversity
3097 (name "express-beta-diversity")
3102 (url "https://github.com/dparks1134/ExpressBetaDiversity.git")
3103 (commit (string-append "v" version))))
3104 (file-name (git-file-name name version))
3107 "0s0yzg5c21349rh7x4w9266jsvnp7j1hp9cf8sk32hz8nvrj745x"))))
3108 (build-system gnu-build-system)
3111 (modify-phases %standard-phases
3113 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
3115 (lambda _ (invoke "../bin/ExpressBetaDiversity" "-u") #t))
3117 (lambda* (#:key outputs #:allow-other-keys)
3118 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3119 (install-file "../scripts/convertToEBD.py" bin)
3120 (install-file "../bin/ExpressBetaDiversity" bin)
3123 `(("python" ,python-2)))
3124 (home-page "https://github.com/dparks1134/ExpressBetaDiversity")
3125 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
3127 "Express Beta Diversity (EBD) calculates ecological beta diversity
3128 (dissimilarity) measures between biological communities. EBD implements a
3129 variety of diversity measures including those that make use of phylogenetic
3130 similarity of community members.")
3131 (license license:gpl3+)))
3133 (define-public fasttree
3140 "http://www.microbesonline.org/fasttree/FastTree-"
3144 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
3145 (build-system gnu-build-system)
3147 `(#:tests? #f ; no "check" target
3149 (modify-phases %standard-phases
3153 (lambda* (#:key source #:allow-other-keys)
3156 "-finline-functions"
3167 "-finline-functions"
3176 (lambda* (#:key outputs #:allow-other-keys)
3177 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3178 (install-file "FastTree" bin)
3179 (install-file "FastTreeMP" bin)
3181 (home-page "http://www.microbesonline.org/fasttree")
3182 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
3184 "FastTree can handle alignments with up to a million of sequences in a
3185 reasonable amount of time and memory. For large alignments, FastTree is
3186 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
3187 (license license:gpl2+)))
3189 (define-public fastx-toolkit
3191 (name "fastx-toolkit")
3197 "https://github.com/agordon/fastx_toolkit/releases/download/"
3198 version "/fastx_toolkit-" version ".tar.bz2"))
3201 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
3202 (build-system gnu-build-system)
3204 `(("libgtextutils" ,libgtextutils)))
3206 `(("gcc" ,gcc-6) ;; doesn't build with later versions
3207 ("pkg-config" ,pkg-config)))
3208 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
3209 (synopsis "Tools for FASTA/FASTQ file preprocessing")
3211 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
3212 FASTA/FASTQ files preprocessing.
3214 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
3215 containing multiple short-reads sequences. The main processing of such
3216 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
3217 is sometimes more productive to preprocess the files before mapping the
3218 sequences to the genome---manipulating the sequences to produce better mapping
3219 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
3220 (license license:agpl3+)))
3222 (define-public flexbar
3229 (url "https://github.com/seqan/flexbar.git")
3230 (commit (string-append "v" version))))
3231 (file-name (git-file-name name version))
3234 "1pq9sxvdnldl14libk234m72dqhwgzs3acgl943wchwdqlcsi5r2"))))
3235 (build-system cmake-build-system)
3238 (modify-phases %standard-phases
3239 (add-after 'unpack 'do-not-tune-to-CPU
3241 (substitute* "src/CMakeLists.txt"
3242 ((" -march=native") ""))
3245 (lambda* (#:key outputs #:allow-other-keys)
3246 (setenv "PATH" (string-append (getcwd) ":" (getenv "PATH")))
3247 (with-directory-excursion "../source/test"
3248 (invoke "bash" "flexbar_test.sh"))
3251 (lambda* (#:key outputs #:allow-other-keys)
3252 (let* ((out (string-append (assoc-ref outputs "out")))
3253 (bin (string-append out "/bin/")))
3254 (install-file "flexbar" bin))
3260 `(("pkg-config" ,pkg-config)
3262 (home-page "https://github.com/seqan/flexbar")
3263 (synopsis "Barcode and adapter removal tool for sequencing platforms")
3265 "Flexbar preprocesses high-throughput nucleotide sequencing data
3266 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
3267 Moreover, trimming and filtering features are provided. Flexbar increases
3268 read mapping rates and improves genome and transcriptome assemblies. It
3269 supports next-generation sequencing data in fasta/q and csfasta/q format from
3270 Illumina, Roche 454, and the SOLiD platform.")
3271 (license license:bsd-3)))
3273 (define-public fraggenescan
3275 (name "fraggenescan")
3281 (string-append "mirror://sourceforge/fraggenescan/"
3282 "FragGeneScan" version ".tar.gz"))
3284 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
3285 (build-system gnu-build-system)
3288 (modify-phases %standard-phases
3290 (add-before 'build 'patch-paths
3291 (lambda* (#:key outputs #:allow-other-keys)
3292 (let* ((out (string-append (assoc-ref outputs "out")))
3293 (share (string-append out "/share/fraggenescan/")))
3294 (substitute* "run_FragGeneScan.pl"
3296 (string-append "system(\"" (which "rm")))
3298 (string-append "system(\"" (which "mv")))
3299 (("\\\"awk") (string-append "\"" (which "awk")))
3300 ;; This script and other programs expect the training files
3301 ;; to be in the non-standard location bin/train/XXX. Change
3302 ;; this to be share/fraggenescan/train/XXX instead.
3303 (("^\\$train.file = \\$dir.*")
3304 (string-append "$train_file = \""
3306 "train/\".$FGS_train_file;")))
3307 (substitute* "run_hmm.c"
3308 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
3309 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
3313 (invoke "make" "clean")
3314 (invoke "make" "fgs")
3317 (lambda* (#:key outputs #:allow-other-keys)
3318 (let* ((out (string-append (assoc-ref outputs "out")))
3319 (bin (string-append out "/bin/"))
3320 (share (string-append out "/share/fraggenescan/train")))
3321 (install-file "run_FragGeneScan.pl" bin)
3322 (install-file "FragGeneScan" bin)
3323 (copy-recursively "train" share))
3326 (add-after 'install 'post-install-check
3327 ;; In lieu of 'make check', run one of the examples and check the
3328 ;; output files gets created.
3329 (lambda* (#:key outputs #:allow-other-keys)
3330 (let* ((out (string-append (assoc-ref outputs "out")))
3331 (bin (string-append out "/bin/"))
3332 (frag (string-append bin "run_FragGeneScan.pl")))
3333 ;; Test complete genome.
3335 "-genome=./example/NC_000913.fna"
3339 (unless (and (file-exists? "test2.faa")
3340 (file-exists? "test2.ffn")
3341 (file-exists? "test2.gff")
3342 (file-exists? "test2.out"))
3343 (error "Expected files do not exist."))
3344 ;; Test incomplete sequences.
3346 "-genome=./example/NC_000913-fgs.ffn"
3353 ("python" ,python-2))) ;not compatible with python 3.
3354 (home-page "https://sourceforge.net/projects/fraggenescan/")
3355 (synopsis "Finds potentially fragmented genes in short reads")
3357 "FragGeneScan is a program for predicting bacterial and archaeal genes in
3358 short and error-prone DNA sequencing reads. It can also be applied to predict
3359 genes in incomplete assemblies or complete genomes.")
3360 ;; GPL3+ according to private correspondense with the authors.
3361 (license license:gpl3+)))
3363 (define-public fxtract
3364 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
3372 (url "https://github.com/ctSkennerton/fxtract.git")
3374 (file-name (git-file-name name version))
3377 "0hab3gpwf4w9s87qlbswq6ws1qqybh4dcqk79q1ahyldzai5fgp5"))))
3378 (build-system gnu-build-system)
3380 `(#:make-flags (list
3381 (string-append "PREFIX=" (assoc-ref %outputs "out"))
3383 #:test-target "fxtract_test"
3385 (modify-phases %standard-phases
3387 (add-before 'build 'copy-util
3388 (lambda* (#:key inputs #:allow-other-keys)
3390 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
3392 ;; Do not use make install as this requires additional dependencies.
3394 (lambda* (#:key outputs #:allow-other-keys)
3395 (let* ((out (assoc-ref outputs "out"))
3396 (bin (string-append out"/bin")))
3397 (install-file "fxtract" bin)
3403 ;; ctskennerton-util is licensed under GPL2.
3404 `(("ctskennerton-util"
3408 (url "https://github.com/ctSkennerton/util.git")
3409 (commit util-commit)))
3410 (file-name (string-append
3411 "ctstennerton-util-" util-commit "-checkout"))
3414 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
3415 (home-page "https://github.com/ctSkennerton/fxtract")
3416 (synopsis "Extract sequences from FASTA and FASTQ files")
3418 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
3419 or FASTQ) file given a subsequence. It uses a simple substring search for
3420 basic tasks but can change to using POSIX regular expressions, PCRE, hash
3421 lookups or multi-pattern searching as required. By default fxtract looks in
3422 the sequence of each record but can also be told to look in the header,
3423 comment or quality sections.")
3424 ;; 'util' requires SSE instructions.
3425 (supported-systems '("x86_64-linux"))
3426 (license license:expat))))
3428 (define-public gemma
3435 (url "https://github.com/xiangzhou/GEMMA.git")
3436 (commit (string-append "v" version))))
3437 (file-name (git-file-name name version))
3440 "1s3ncnbn45r2hh1cvrqky1kbqq6546biypr4f5mkw1kqlrgyh0yg"))))
3443 ("gfortran" ,gfortran "lib")
3446 ("openblas" ,openblas)
3448 (build-system gnu-build-system)
3451 '(,@(match (%current-system)
3453 '("FORCE_DYNAMIC=1"))
3455 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
3457 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
3459 (modify-phases %standard-phases
3461 (add-after 'unpack 'find-eigen
3462 (lambda* (#:key inputs #:allow-other-keys)
3463 ;; Ensure that Eigen headers can be found
3464 (setenv "CPLUS_INCLUDE_PATH"
3465 (string-append (assoc-ref inputs "eigen")
3468 (add-before 'build 'bin-mkdir
3473 (lambda* (#:key outputs #:allow-other-keys)
3474 (let ((out (assoc-ref outputs "out")))
3475 (install-file "bin/gemma"
3479 #:tests? #f)) ; no tests included yet
3480 (home-page "https://github.com/xiangzhou/GEMMA")
3481 (synopsis "Tool for genome-wide efficient mixed model association")
3483 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
3484 standard linear mixed model resolver with application in genome-wide
3485 association studies (GWAS).")
3486 (license license:gpl3)))
3495 (url "https://github.com/nboley/grit.git")
3497 (file-name (git-file-name name version))
3500 "1l5v8vfvfbrpmgnrvbrbv40d0arhxcnmxgv2f1mlcqfa3q6bkqm9"))))
3501 (build-system python-build-system)
3503 `(#:python ,python-2
3505 (modify-phases %standard-phases
3506 (add-after 'unpack 'generate-from-cython-sources
3507 (lambda* (#:key inputs outputs #:allow-other-keys)
3508 ;; Delete these C files to force fresh generation from pyx sources.
3509 (delete-file "grit/sparsify_support_fns.c")
3510 (delete-file "grit/call_peaks_support_fns.c")
3511 (substitute* "setup.py"
3512 (("Cython.Setup") "Cython.Build"))
3515 `(("python-scipy" ,python2-scipy)
3516 ("python-numpy" ,python2-numpy)
3517 ("python-pysam" ,python2-pysam)
3518 ("python-networkx" ,python2-networkx)))
3520 `(("python-cython" ,python2-cython)))
3521 ;; The canonical <http://grit-bio.org> home page times out as of 2020-01-21.
3522 (home-page "https://github.com/nboley/grit")
3523 (synopsis "Tool for integrative analysis of RNA-seq type assays")
3525 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
3526 full length transcript models. When none of these data sources are available,
3527 GRIT can be run by providing a candidate set of TES or TSS sites. In
3528 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
3529 also be run in quantification mode, where it uses a provided GTF file and just
3530 estimates transcript expression.")
3531 (license license:gpl3+)))
3533 (define-public hisat
3540 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
3541 version "-beta-source.zip"))
3544 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
3545 (build-system gnu-build-system)
3547 `(#:tests? #f ;no check target
3548 #:make-flags '("allall"
3549 ;; Disable unsupported `popcnt' instructions on
3550 ;; architectures other than x86_64
3551 ,@(if (string-prefix? "x86_64"
3552 (or (%current-target-system)
3555 '("POPCNT_CAPABILITY=0")))
3557 (modify-phases %standard-phases
3558 (add-after 'unpack 'patch-sources
3560 ;; XXX Cannot use snippet because zip files are not supported
3561 (substitute* "Makefile"
3562 (("^CC = .*$") "CC = gcc")
3563 (("^CPP = .*$") "CPP = g++")
3564 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
3565 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
3566 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
3567 (substitute* '("hisat-build" "hisat-inspect")
3568 (("/usr/bin/env") (which "env")))
3571 (lambda* (#:key outputs #:allow-other-keys)
3572 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
3573 (for-each (lambda (file)
3574 (install-file file bin))
3577 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
3579 (delete 'configure))))
3581 `(("unzip" ,unzip)))
3586 ;; Non-portable SSE instructions are used so building fails on platforms
3587 ;; other than x86_64.
3588 (supported-systems '("x86_64-linux"))
3589 (home-page "https://ccb.jhu.edu/software/hisat/index.shtml")
3590 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
3592 "HISAT is a fast and sensitive spliced alignment program for mapping
3593 RNA-seq reads. In addition to one global FM index that represents a whole
3594 genome, HISAT uses a large set of small FM indexes that collectively cover the
3595 whole genome. These small indexes (called local indexes) combined with
3596 several alignment strategies enable effective alignment of RNA-seq reads, in
3597 particular, reads spanning multiple exons.")
3598 (license license:gpl3+)))
3600 (define-public hisat2
3607 (uri (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
3608 "/downloads/hisat2-" version "-source.zip"))
3611 "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"))))
3612 (build-system gnu-build-system)
3614 `(#:tests? #f ; no check target
3615 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
3616 #:modules ((guix build gnu-build-system)
3620 (modify-phases %standard-phases
3621 (add-after 'unpack 'make-deterministic
3623 (substitute* "Makefile"
3628 (lambda* (#:key outputs #:allow-other-keys)
3629 (let* ((out (assoc-ref outputs "out"))
3630 (bin (string-append out "/bin/"))
3631 (doc (string-append out "/share/doc/hisat2/")))
3633 (cut install-file <> bin)
3635 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
3637 (install-file "doc/manual.inc.html" doc))
3640 `(("unzip" ,unzip) ; needed for archive from ftp
3642 ("pandoc" ,ghc-pandoc))) ; for documentation
3643 (home-page "https://ccb.jhu.edu/software/hisat2/index.shtml")
3644 (synopsis "Graph-based alignment of genomic sequencing reads")
3645 (description "HISAT2 is a fast and sensitive alignment program for mapping
3646 next-generation sequencing reads (both DNA and RNA) to a population of human
3647 genomes (as well as to a single reference genome). In addition to using one
3648 global @dfn{graph FM} (GFM) index that represents a population of human
3649 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
3650 the whole genome. These small indexes, combined with several alignment
3651 strategies, enable rapid and accurate alignment of sequencing reads. This new
3652 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
3653 ;; HISAT2 contains files from Bowtie2, which is released under
3654 ;; GPLv2 or later. The HISAT2 source files are released under
3656 (license license:gpl3+)))
3658 (define-public hmmer
3666 "http://eddylab.org/software/hmmer/hmmer-" version ".tar.gz"))
3669 "171bivy6xhgjsz5nv53n81pc3frnwz29ylblawk2bv46szwjjqd5"))))
3670 (build-system gnu-build-system)
3671 (native-inputs `(("perl" ,perl)))
3672 (home-page "http://hmmer.org/")
3673 (synopsis "Biosequence analysis using profile hidden Markov models")
3675 "HMMER is used for searching sequence databases for homologs of protein
3676 sequences, and for making protein sequence alignments. It implements methods
3677 using probabilistic models called profile hidden Markov models (profile
3679 ;; hmmer uses non-portable SSE intrinsics so building fails on other
3681 (supported-systems '("x86_64-linux" "i686-linux"))
3682 (license license:bsd-3)))
3684 (define-public htseq
3690 (uri (pypi-uri "HTSeq" version))
3693 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
3694 (build-system python-build-system)
3696 `(("python-cython" ,python-cython)))
3697 ;; Numpy needs to be propagated when htseq is used as a Python library.
3699 `(("python-numpy" ,python-numpy)))
3701 `(("python-pysam" ,python-pysam)
3702 ("python-matplotlib" ,python-matplotlib)))
3703 (home-page "https://htseq.readthedocs.io/")
3704 (synopsis "Analysing high-throughput sequencing data with Python")
3706 "HTSeq is a Python package that provides infrastructure to process data
3707 from high-throughput sequencing assays.")
3708 (license license:gpl3+)))
3710 (define-public python2-htseq
3711 (package-with-python2 htseq))
3713 (define-public java-htsjdk
3715 (name "java-htsjdk")
3716 (version "2.3.0") ; last version without build dependency on gradle
3720 (url "https://github.com/samtools/htsjdk.git")
3722 (file-name (git-file-name name version))
3725 "1b178ixcabanm834ydjl3jiakpyxdmki32hqfv2abrzn3rcwa28i"))
3726 (modules '((guix build utils)))
3728 ;; Delete pre-built binaries
3730 (delete-file-recursively "lib")
3733 (build-system ant-build-system)
3735 `(#:tests? #f ; test require Internet access
3738 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3739 "/share/java/htsjdk/"))
3740 #:build-target "all"
3742 (modify-phases %standard-phases
3743 ;; The build phase also installs the jars
3744 (delete 'install))))
3746 `(("java-ngs" ,java-ngs)
3747 ("java-snappy-1" ,java-snappy-1)
3748 ("java-commons-compress" ,java-commons-compress)
3749 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3750 ("java-commons-jexl-2" ,java-commons-jexl-2)
3751 ("java-xz" ,java-xz)))
3753 `(("java-testng" ,java-testng)))
3754 (home-page "http://samtools.github.io/htsjdk/")
3755 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3757 "HTSJDK is an implementation of a unified Java library for accessing
3758 common file formats, such as SAM and VCF, used for high-throughput
3759 sequencing (HTS) data. There are also an number of useful utilities for
3760 manipulating HTS data.")
3761 (license license:expat)))
3763 (define-public java-htsjdk-latest
3765 (name "java-htsjdk")
3770 (url "https://github.com/samtools/htsjdk.git")
3772 (file-name (string-append name "-" version "-checkout"))
3775 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
3776 (build-system ant-build-system)
3778 `(#:tests? #f ; test require Scala
3780 #:jar-name "htsjdk.jar"
3782 (modify-phases %standard-phases
3783 (add-after 'unpack 'remove-useless-build.xml
3784 (lambda _ (delete-file "build.xml") #t))
3785 ;; The tests require the scalatest package.
3786 (add-after 'unpack 'remove-tests
3787 (lambda _ (delete-file-recursively "src/test") #t)))))
3789 `(("java-ngs" ,java-ngs)
3790 ("java-snappy-1" ,java-snappy-1)
3791 ("java-commons-compress" ,java-commons-compress)
3792 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3793 ("java-commons-jexl-2" ,java-commons-jexl-2)
3794 ("java-xz" ,java-xz)))
3796 `(("java-junit" ,java-junit)))
3797 (home-page "http://samtools.github.io/htsjdk/")
3798 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3800 "HTSJDK is an implementation of a unified Java library for accessing
3801 common file formats, such as SAM and VCF, used for high-throughput
3802 sequencing (HTS) data. There are also an number of useful utilities for
3803 manipulating HTS data.")
3804 (license license:expat)))
3806 ;; This is needed for picard 2.10.3
3807 (define-public java-htsjdk-2.10.1
3808 (package (inherit java-htsjdk-latest)
3809 (name "java-htsjdk")
3814 (url "https://github.com/samtools/htsjdk.git")
3816 (file-name (string-append name "-" version "-checkout"))
3819 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
3820 (build-system ant-build-system)
3822 `(#:tests? #f ; tests require Scala
3824 #:jar-name "htsjdk.jar"
3826 (modify-phases %standard-phases
3827 (add-after 'unpack 'remove-useless-build.xml
3828 (lambda _ (delete-file "build.xml") #t))
3829 ;; The tests require the scalatest package.
3830 (add-after 'unpack 'remove-tests
3831 (lambda _ (delete-file-recursively "src/test") #t)))))))
3833 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3834 ;; recent version of java-htsjdk, which depends on gradle.
3835 (define-public java-picard
3837 (name "java-picard")
3842 (url "https://github.com/broadinstitute/picard.git")
3844 (file-name (string-append "java-picard-" version "-checkout"))
3847 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3848 (modules '((guix build utils)))
3851 ;; Delete pre-built binaries.
3852 (delete-file-recursively "lib")
3854 (substitute* "build.xml"
3855 ;; Remove build-time dependency on git.
3856 (("failifexecutionfails=\"true\"")
3857 "failifexecutionfails=\"false\"")
3859 (("depends=\"compile-htsjdk, ")
3861 (("depends=\"compile-htsjdk-tests, ")
3863 ;; Build picard-lib.jar before building picard.jar
3864 (("name=\"picard-jar\" depends=\"" line)
3865 (string-append line "picard-lib-jar, ")))
3867 (build-system ant-build-system)
3869 `(#:build-target "picard-jar"
3870 #:test-target "test"
3871 ;; Tests require jacoco:coverage.
3874 (list (string-append "-Dhtsjdk_lib_dir="
3875 (assoc-ref %build-inputs "java-htsjdk")
3876 "/share/java/htsjdk/")
3877 "-Dhtsjdk-classes=dist/tmp"
3878 (string-append "-Dhtsjdk-version="
3879 ,(package-version java-htsjdk)))
3882 (modify-phases %standard-phases
3883 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3884 (delete 'generate-jar-indices)
3885 (add-after 'unpack 'use-our-htsjdk
3886 (lambda* (#:key inputs #:allow-other-keys)
3887 (substitute* "build.xml"
3888 (("\\$\\{htsjdk\\}/lib")
3889 (string-append (assoc-ref inputs "java-htsjdk")
3890 "/share/java/htsjdk/")))
3892 (add-after 'unpack 'make-test-target-independent
3893 (lambda* (#:key inputs #:allow-other-keys)
3894 (substitute* "build.xml"
3895 (("name=\"test\" depends=\"compile, ")
3896 "name=\"test\" depends=\""))
3898 (replace 'install (install-jars "dist")))))
3900 `(("java-htsjdk" ,java-htsjdk)
3901 ("java-guava" ,java-guava)))
3903 `(("java-testng" ,java-testng)))
3904 (home-page "http://broadinstitute.github.io/picard/")
3905 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3906 (description "Picard is a set of Java command line tools for manipulating
3907 high-throughput sequencing (HTS) data and formats. Picard is implemented
3908 using the HTSJDK Java library to support accessing file formats that are
3909 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3911 (license license:expat)))
3913 ;; This is needed for dropseq-tools
3914 (define-public java-picard-2.10.3
3916 (name "java-picard")
3921 (url "https://github.com/broadinstitute/picard.git")
3923 (file-name (string-append "java-picard-" version "-checkout"))
3926 "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi"))))
3927 (build-system ant-build-system)
3929 `(#:jar-name "picard.jar"
3930 ;; Tests require jacoco:coverage.
3933 #:main-class "picard.cmdline.PicardCommandLine"
3934 #:modules ((guix build ant-build-system)
3936 (guix build java-utils)
3941 (modify-phases %standard-phases
3942 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3943 (delete 'generate-jar-indices)
3944 (add-after 'unpack 'remove-useless-build.xml
3945 (lambda _ (delete-file "build.xml") #t))
3946 ;; This is necessary to ensure that htsjdk is found when using
3947 ;; picard.jar as an executable.
3948 (add-before 'build 'edit-classpath-in-manifest
3949 (lambda* (#:key inputs #:allow-other-keys)
3950 (chmod "build.xml" #o664)
3951 (call-with-output-file "build.xml.new"
3955 (with-input-from-file "build.xml"
3956 (lambda _ (xml->sxml #:trim-whitespace? #t)))
3957 `((target . ,(lambda (tag . kids)
3958 (let ((name ((sxpath '(name *text*))
3960 ;; FIXME: We're breaking the line
3961 ;; early with a dummy path to
3962 ;; ensure that the store reference
3963 ;; isn't broken apart and can still
3964 ;; be found by the reference
3969 ~a/share/java/htsjdk.jar${line.separator}${line.separator}"
3970 ;; maximum line length is 70
3971 (string-tabulate (const #\b) 57)
3972 (assoc-ref inputs "java-htsjdk"))))
3973 (if (member "manifest" name)
3976 (@ (file "${manifest.file}")
3977 (match "\\r\\n\\r\\n")
3978 (replace "${line.separator}")))
3981 (file "${manifest.file}")
3984 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
3985 (*text* . ,(lambda (_ txt) txt))))
3987 (rename-file "build.xml.new" "build.xml")
3990 `(("java-htsjdk" ,java-htsjdk-2.10.1)))
3992 `(("java-testng" ,java-testng)
3993 ("java-guava" ,java-guava)))
3994 (home-page "http://broadinstitute.github.io/picard/")
3995 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3996 (description "Picard is a set of Java command line tools for manipulating
3997 high-throughput sequencing (HTS) data and formats. Picard is implemented
3998 using the HTSJDK Java library to support accessing file formats that are
3999 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
4001 (license license:expat)))
4003 ;; This is the last version of Picard to provide net.sf.samtools
4004 (define-public java-picard-1.113
4005 (package (inherit java-picard)
4006 (name "java-picard")
4011 (url "https://github.com/broadinstitute/picard.git")
4013 (file-name (string-append "java-picard-" version "-checkout"))
4016 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
4017 (modules '((guix build utils)))
4020 ;; Delete pre-built binaries.
4021 (delete-file-recursively "lib")
4024 (build-system ant-build-system)
4026 `(#:build-target "picard-jar"
4027 #:test-target "test"
4028 ;; FIXME: the class path at test time is wrong.
4029 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
4030 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
4033 ;; This is only used for tests.
4035 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
4037 (modify-phases %standard-phases
4038 ;; FIXME: This phase fails.
4039 (delete 'generate-jar-indices)
4040 ;; Do not use bundled ant bzip2.
4041 (add-after 'unpack 'use-ant-bzip
4042 (lambda* (#:key inputs #:allow-other-keys)
4043 (substitute* "build.xml"
4044 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
4045 (string-append (assoc-ref inputs "ant")
4048 (add-after 'unpack 'make-test-target-independent
4049 (lambda* (#:key inputs #:allow-other-keys)
4050 (substitute* "build.xml"
4051 (("name=\"test\" depends=\"compile, ")
4052 "name=\"test\" depends=\"compile-tests, ")
4053 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
4054 "name=\"compile\" depends=\"compile-src\""))
4056 (add-after 'unpack 'fix-deflater-path
4057 (lambda* (#:key outputs #:allow-other-keys)
4058 (substitute* "src/java/net/sf/samtools/Defaults.java"
4059 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
4060 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
4061 (assoc-ref outputs "out")
4062 "/lib/jni/libIntelDeflater.so"
4065 ;; Build the deflater library, because we've previously deleted the
4066 ;; pre-built one. This can only be built with access to the JDK
4068 (add-after 'build 'build-jni
4069 (lambda* (#:key inputs #:allow-other-keys)
4072 (invoke "tar" "--strip-components=1" "-C" "jdk-src"
4073 "-xf" (assoc-ref inputs "jdk-src"))
4074 (invoke "javah" "-jni"
4075 "-classpath" "classes"
4077 "net.sf.samtools.util.zip.IntelDeflater")
4078 (with-directory-excursion "src/c/inteldeflater"
4079 (invoke "gcc" "-I../../../lib" "-I."
4080 (string-append "-I" (assoc-ref inputs "jdk")
4082 "-I../../../jdk-src/src/share/native/common/"
4083 "-I../../../jdk-src/src/solaris/native/common/"
4084 "-c" "-O3" "-fPIC" "IntelDeflater.c")
4085 (invoke "gcc" "-shared"
4086 "-o" "../../../lib/jni/libIntelDeflater.so"
4087 "IntelDeflater.o" "-lz" "-lstdc++"))
4089 ;; We can only build everything else after building the JNI library.
4090 (add-after 'build-jni 'build-rest
4091 (lambda* (#:key make-flags #:allow-other-keys)
4092 (apply invoke `("ant" "all" ,@make-flags))
4094 (add-before 'build 'set-JAVA6_HOME
4096 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
4098 (replace 'install (install-jars "dist"))
4099 (add-after 'install 'install-jni-lib
4100 (lambda* (#:key outputs #:allow-other-keys)
4101 (let ((jni (string-append (assoc-ref outputs "out")
4104 (install-file "lib/jni/libIntelDeflater.so" jni)
4107 `(("java-snappy-1" ,java-snappy-1)
4108 ("java-commons-jexl-2" ,java-commons-jexl-2)
4109 ("java-cofoja" ,java-cofoja)
4110 ("ant" ,ant) ; for bzip2 support at runtime
4113 `(("ant-apache-bcel" ,ant-apache-bcel)
4114 ("ant-junit" ,ant-junit)
4115 ("java-testng" ,java-testng)
4116 ("java-commons-bcel" ,java-commons-bcel)
4117 ("java-jcommander" ,java-jcommander)
4118 ("jdk" ,icedtea-8 "jdk")
4119 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
4121 (define-public fastqc
4128 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
4129 "projects/fastqc/fastqc_v"
4130 version "_source.zip"))
4133 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
4134 (build-system ant-build-system)
4136 `(#:tests? #f ; there are no tests
4137 #:build-target "build"
4139 (modify-phases %standard-phases
4140 (add-after 'unpack 'fix-dependencies
4141 (lambda* (#:key inputs #:allow-other-keys)
4142 (substitute* "build.xml"
4144 (string-append (assoc-ref inputs "java-jbzip2")
4145 "/share/java/jbzip2.jar"))
4147 (string-append (assoc-ref inputs "java-picard-1.113")
4148 "/share/java/sam-1.112.jar"))
4150 (string-append (assoc-ref inputs "java-cisd-jhdf5")
4151 "/share/java/sis-jhdf5.jar")))
4153 ;; There is no installation target
4155 (lambda* (#:key inputs outputs #:allow-other-keys)
4156 (let* ((out (assoc-ref outputs "out"))
4157 (bin (string-append out "/bin"))
4158 (share (string-append out "/share/fastqc/"))
4159 (exe (string-append share "/fastqc")))
4160 (for-each mkdir-p (list bin share))
4161 (copy-recursively "bin" share)
4163 (("my \\$java_bin = 'java';")
4164 (string-append "my $java_bin = '"
4165 (assoc-ref inputs "java")
4168 (symlink exe (string-append bin "/fastqc"))
4172 ("perl" ,perl) ; needed for the wrapper script
4173 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
4174 ("java-picard-1.113" ,java-picard-1.113)
4175 ("java-jbzip2" ,java-jbzip2)))
4177 `(("unzip" ,unzip)))
4178 (home-page "https://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
4179 (synopsis "Quality control tool for high throughput sequence data")
4181 "FastQC aims to provide a simple way to do some quality control
4182 checks on raw sequence data coming from high throughput sequencing
4183 pipelines. It provides a modular set of analyses which you can use to
4184 give a quick impression of whether your data has any problems of which
4185 you should be aware before doing any further analysis.
4187 The main functions of FastQC are:
4190 @item Import of data from BAM, SAM or FastQ files (any variant);
4191 @item Providing a quick overview to tell you in which areas there may
4193 @item Summary graphs and tables to quickly assess your data;
4194 @item Export of results to an HTML based permanent report;
4195 @item Offline operation to allow automated generation of reports
4196 without running the interactive application.
4198 (license license:gpl3+)))
4200 (define-public fastp
4208 (url "https://github.com/OpenGene/fastp.git")
4209 (commit (string-append "v" version))))
4210 (file-name (git-file-name name version))
4213 "1r6ms5zbf5rps4rgp4z73nczadl00b5rqylw8f684isfz27dp0xh"))))
4214 (build-system gnu-build-system)
4216 `(#:tests? #f ; there are none
4218 (list (string-append "BINDIR=" (assoc-ref %outputs "out") "/bin"))
4220 (modify-phases %standard-phases
4222 (add-before 'install 'create-target-dir
4223 (lambda* (#:key outputs #:allow-other-keys)
4224 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4228 (home-page "https://github.com/OpenGene/fastp/")
4229 (synopsis "All-in-one FastQ preprocessor")
4231 "Fastp is a tool designed to provide fast all-in-one preprocessing for
4232 FastQ files. This tool has multi-threading support to afford high
4234 (license license:expat)))
4236 (define-public htslib
4243 "https://github.com/samtools/htslib/releases/download/"
4244 version "/htslib-" version ".tar.bz2"))
4247 "16ljv43sc3fxmv63w7b2ff8m1s7h89xhazwmbm1bicz8axq8fjz0"))))
4248 (build-system gnu-build-system)
4251 ("openssl" ,openssl)))
4252 ;; This is referred to in the pkg-config file as a required library.
4257 (home-page "https://www.htslib.org")
4258 (synopsis "C library for reading/writing high-throughput sequencing data")
4260 "HTSlib is a C library for reading/writing high-throughput sequencing
4261 data. It also provides the @command{bgzip}, @command{htsfile}, and
4262 @command{tabix} utilities.")
4263 ;; Files under cram/ are released under the modified BSD license;
4264 ;; the rest is released under the Expat license
4265 (license (list license:expat license:bsd-3))))
4267 ;; This package should be removed once no packages rely upon it.
4275 "https://github.com/samtools/htslib/releases/download/"
4276 version "/htslib-" version ".tar.bz2"))
4279 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
4288 (url "https://github.com/nboley/idr.git")
4290 (file-name (git-file-name name version))
4293 "04j876h6z444v2q79drxx283d3k5snd72kj895wbalnl42206x9g"))
4294 ;; Delete generated C code.
4296 '(begin (delete-file "idr/inv_cdf.c") #t))))
4297 (build-system python-build-system)
4298 ;; There is only one test ("test_inv_cdf.py") and it tests features that
4299 ;; are no longer part of this package. It also asserts False, which
4300 ;; causes the tests to always fail.
4301 (arguments `(#:tests? #f))
4303 `(("python-scipy" ,python-scipy)
4304 ("python-sympy" ,python-sympy)
4305 ("python-numpy" ,python-numpy)
4306 ("python-matplotlib" ,python-matplotlib)))
4308 `(("python-cython" ,python-cython)))
4309 (home-page "https://github.com/nboley/idr")
4310 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
4312 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
4313 to measure the reproducibility of findings identified from replicate
4314 experiments and provide highly stable thresholds based on reproducibility.")
4315 (license license:gpl2+)))
4317 (define-public jellyfish
4323 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
4324 "releases/download/v" version
4325 "/jellyfish-" version ".tar.gz"))
4328 "1k4pc3fvv6w1km2yph4m5sd78fbxp21d6xyzgmy0gjihzc6mb249"))))
4329 (build-system gnu-build-system)
4330 (outputs '("out" ;for library
4331 "ruby" ;for Ruby bindings
4332 "python")) ;for Python bindings
4335 (list (string-append "--enable-ruby-binding="
4336 (assoc-ref %outputs "ruby"))
4337 (string-append "--enable-python-binding="
4338 (assoc-ref %outputs "python")))
4340 (modify-phases %standard-phases
4341 (add-before 'check 'set-SHELL-variable
4343 ;; generator_manager.hpp either uses /bin/sh or $SHELL
4345 (setenv "SHELL" (which "bash"))
4351 ("python" ,python-2)
4352 ("pkg-config" ,pkg-config)))
4354 `(("htslib" ,htslib)))
4355 (synopsis "Tool for fast counting of k-mers in DNA")
4357 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
4358 DNA. A k-mer is a substring of length k, and counting the occurrences of all
4359 such substrings is a central step in many analyses of DNA sequence. Jellyfish
4360 is a command-line program that reads FASTA and multi-FASTA files containing
4361 DNA sequences. It outputs its k-mer counts in a binary format, which can be
4362 translated into a human-readable text format using the @code{jellyfish dump}
4363 command, or queried for specific k-mers with @code{jellyfish query}.")
4364 (home-page "http://www.genome.umd.edu/jellyfish.html")
4365 ;; JELLYFISH seems to be 64-bit only.
4366 (supported-systems '("x86_64-linux" "aarch64-linux" "mips64el-linux"))
4367 ;; The combined work is published under the GPLv3 or later. Individual
4368 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
4369 (license (list license:gpl3+ license:expat))))
4371 (define-public khmer
4379 (url "https://github.com/dib-lab/khmer.git")
4380 (commit (string-append "v" version))))
4381 (file-name (git-file-name name version))
4384 "01l4jczglkl7yfhgvzx8j0df7k54bk1r8sli9ll16i1mis0d8f37"))
4385 (modules '((guix build utils)))
4388 ;; Delete bundled libraries. We do not replace the bundled seqan
4389 ;; as it is a modified subset of the old version 1.4.1.
4391 ;; We do not replace the bundled MurmurHash as the canonical
4392 ;; repository for this code 'SMHasher' is unsuitable for providing
4394 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
4395 (delete-file-recursively "third-party/zlib")
4396 (delete-file-recursively "third-party/bzip2")
4397 (delete-file-recursively "third-party/seqan")
4398 (substitute* "setup.cfg"
4399 (("# libraries = z,bz2")
4400 "libraries = z,bz2")
4401 (("include:third-party/zlib:third-party/bzip2")
4404 (build-system python-build-system)
4407 (modify-phases %standard-phases
4408 (add-after 'unpack 'set-cc
4409 (lambda _ (setenv "CC" "gcc") #t))
4411 (add-before 'reset-gzip-timestamps 'make-files-writable
4412 (lambda* (#:key outputs #:allow-other-keys)
4413 ;; Make sure .gz files are writable so that the
4414 ;; 'reset-gzip-timestamps' phase can do its work.
4415 (let ((out (assoc-ref outputs "out")))
4416 (for-each make-file-writable
4417 (find-files out "\\.gz$"))
4420 `(("python-cython" ,python-cython)
4421 ("python-pytest" ,python-pytest)
4422 ("python-pytest-runner" ,python-pytest-runner)))
4427 ("python-screed" ,python-screed)
4428 ("python-bz2file" ,python-bz2file)))
4429 (home-page "https://khmer.readthedocs.org/")
4430 (synopsis "K-mer counting, filtering and graph traversal library")
4431 (description "The khmer software is a set of command-line tools for
4432 working with DNA shotgun sequencing data from genomes, transcriptomes,
4433 metagenomes and single cells. Khmer can make de novo assemblies faster, and
4434 sometimes better. Khmer can also identify and fix problems with shotgun
4436 ;; When building on i686, armhf and mips64el, we get the following error:
4437 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
4438 (supported-systems '("x86_64-linux" "aarch64-linux"))
4439 (license license:bsd-3)))
4441 (define-public kaiju
4448 (url "https://github.com/bioinformatics-centre/kaiju")
4449 (commit (string-append "v" version))))
4450 (file-name (git-file-name name version))
4453 "119pzi0ddzv9mjg4wwa6han0cwr3k3ssn7kirvsjfcq05mi5ka0x"))))
4454 (build-system gnu-build-system)
4456 `(#:tests? #f ; There are no tests.
4458 (modify-phases %standard-phases
4460 (add-before 'build 'move-to-src-dir
4461 (lambda _ (chdir "src") #t))
4463 (lambda* (#:key inputs outputs #:allow-other-keys)
4464 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
4467 (copy-recursively "bin" bin))
4472 (home-page "http://kaiju.binf.ku.dk/")
4473 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
4474 (description "Kaiju is a program for sensitive taxonomic classification
4475 of high-throughput sequencing reads from metagenomic whole genome sequencing
4477 (license license:gpl3+)))
4484 ;; The PyPi tarball does not contain tests.
4487 (url "https://github.com/taoliu/MACS.git")
4488 (commit (string-append "v" version))))
4489 (file-name (git-file-name name version))
4492 "1c5gxr0mk6hkd4vclf0k00wvyvzw2vrmk52c85338p7aqjwg6n15"))))
4493 (build-system python-build-system)
4496 (modify-phases %standard-phases
4498 (add-after 'install 'check
4499 (lambda* (#:key inputs outputs #:allow-other-keys)
4500 (add-installed-pythonpath inputs outputs)
4501 (invoke "pytest" "-v"))))))
4503 `(("python-numpy" ,python-numpy)))
4505 `(("python-pytest" ,python-pytest)))
4506 (home-page "https://github.com/taoliu/MACS/")
4507 (synopsis "Model based analysis for ChIP-Seq data")
4509 "MACS is an implementation of a ChIP-Seq analysis algorithm for
4510 identifying transcript factor binding sites named Model-based Analysis of
4511 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
4512 the significance of enriched ChIP regions and it improves the spatial
4513 resolution of binding sites through combining the information of both
4514 sequencing tag position and orientation.")
4515 (license license:bsd-3)))
4517 (define-public mafft
4524 "https://mafft.cbrc.jp/alignment/software/mafft-" version
4525 "-without-extensions-src.tgz"))
4526 (file-name (string-append name "-" version ".tgz"))
4529 "0bacjkxfg944p5khhyh5rd4y7wkjc9qk4v2jjj442sqlq0f8ar7b"))))
4530 (build-system gnu-build-system)
4532 `(#:tests? #f ; no automated tests, though there are tests in the read me
4533 #:make-flags (let ((out (assoc-ref %outputs "out")))
4534 (list (string-append "PREFIX=" out)
4535 (string-append "BINDIR="
4536 (string-append out "/bin"))))
4538 (modify-phases %standard-phases
4539 (add-after 'unpack 'enter-dir
4540 (lambda _ (chdir "core") #t))
4541 (add-after 'enter-dir 'patch-makefile
4543 ;; on advice from the MAFFT authors, there is no need to
4544 ;; distribute mafft-profile, mafft-distance, or
4545 ;; mafft-homologs.rb as they are too "specialised".
4546 (substitute* "Makefile"
4547 ;; remove mafft-homologs.rb from SCRIPTS
4548 (("^SCRIPTS = mafft mafft-homologs.rb")
4550 ;; remove mafft-homologs from MANPAGES
4551 (("^MANPAGES = mafft.1 mafft-homologs.1")
4552 "MANPAGES = mafft.1")
4553 ;; remove mafft-distance from PROGS
4554 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
4555 "PROGS = dvtditr dndfast7 dndblast sextet5")
4556 ;; remove mafft-profile from PROGS
4557 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
4558 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
4559 (("^rm -f mafft-profile mafft-profile.exe") "#")
4560 (("^rm -f mafft-distance mafft-distance.exe") ")#")
4561 ;; do not install MAN pages in libexec folder
4562 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
4563 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
4565 (add-after 'enter-dir 'patch-paths
4566 (lambda* (#:key inputs #:allow-other-keys)
4567 (substitute* '("pairash.c"
4569 (("perl") (which "perl"))
4570 (("([\"`| ])awk" _ prefix)
4571 (string-append prefix (which "awk")))
4572 (("grep") (which "grep")))
4575 (add-after 'install 'wrap-programs
4576 (lambda* (#:key outputs #:allow-other-keys)
4577 (let* ((out (assoc-ref outputs "out"))
4578 (bin (string-append out "/bin"))
4579 (path (string-append
4580 (assoc-ref %build-inputs "coreutils") "/bin:")))
4581 (for-each (lambda (file)
4583 `("PATH" ":" prefix (,path))))
4591 ("coreutils" ,coreutils)))
4592 (home-page "http://mafft.cbrc.jp/alignment/software/")
4593 (synopsis "Multiple sequence alignment program")
4595 "MAFFT offers a range of multiple alignment methods for nucleotide and
4596 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
4597 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
4599 (license (license:non-copyleft
4600 "http://mafft.cbrc.jp/alignment/software/license.txt"
4601 "BSD-3 with different formatting"))))
4610 (url "https://github.com/marbl/mash.git")
4611 (commit (string-append "v" version))))
4612 (file-name (git-file-name name version))
4615 "049hwcc059p2fd9vwndn63laifvvsi0wmv84i6y1fr79k15dxwy6"))
4616 (modules '((guix build utils)))
4619 ;; Delete bundled kseq.
4620 ;; TODO: Also delete bundled murmurhash and open bloom filter.
4621 (delete-file "src/mash/kseq.h")
4623 (build-system gnu-build-system)
4625 `(#:tests? #f ; No tests.
4628 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
4629 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
4630 #:make-flags (list "CC=gcc")
4632 (modify-phases %standard-phases
4633 (add-after 'unpack 'fix-includes
4635 (substitute* '("src/mash/Sketch.cpp"
4636 "src/mash/CommandFind.cpp"
4637 "src/mash/CommandScreen.cpp")
4638 (("^#include \"kseq\\.h\"")
4639 "#include \"htslib/kseq.h\""))
4641 (add-after 'fix-includes 'use-c++14
4643 ;; capnproto 0.7 requires c++14 to build
4644 (substitute* "configure.ac"
4645 (("c\\+\\+11") "c++14"))
4646 (substitute* "Makefile.in"
4647 (("c\\+\\+11") "c++14"))
4650 `(("autoconf" ,autoconf)
4651 ;; Capnproto and htslib are statically embedded in the final
4652 ;; application. Therefore we also list their licenses, below.
4653 ("capnproto" ,capnproto)
4654 ("htslib" ,htslib)))
4658 (supported-systems '("x86_64-linux"))
4659 (home-page "https://mash.readthedocs.io")
4660 (synopsis "Fast genome and metagenome distance estimation using MinHash")
4661 (description "Mash is a fast sequence distance estimator that uses the
4662 MinHash algorithm and is designed to work with genomes and metagenomes in the
4663 form of assemblies or reads.")
4664 (license (list license:bsd-3 ; Mash
4665 license:expat ; HTSlib and capnproto
4666 license:public-domain ; MurmurHash 3
4667 license:cpl1.0)))) ; Open Bloom Filter
4669 (define-public metabat
4677 (url "https://bitbucket.org/berkeleylab/metabat.git")
4678 (commit (string-append "v" version))))
4679 (file-name (git-file-name name version))
4682 "0hyg2smw1nz69mfvjpk45xyyychmda92c80a0cv7baji84ri4iyn"))
4683 (patches (search-patches "metabat-fix-compilation.patch"))))
4684 (build-system scons-build-system)
4686 `(#:scons ,scons-python2
4688 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
4689 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
4690 #:tests? #f ;; Tests are run during the build phase.
4692 (modify-phases %standard-phases
4693 (add-after 'unpack 'fix-includes
4695 (substitute* "src/BamUtils.h"
4696 (("^#include \"bam/bam\\.h\"")
4697 "#include \"samtools/bam.h\"")
4698 (("^#include \"bam/sam\\.h\"")
4699 "#include \"samtools/sam.h\""))
4700 (substitute* "src/KseqReader.h"
4701 (("^#include \"bam/kseq\\.h\"")
4702 "#include \"htslib/kseq.h\""))
4704 (add-after 'unpack 'fix-scons
4705 (lambda* (#:key inputs #:allow-other-keys)
4706 (substitute* "SConstruct"
4707 (("^htslib_dir += 'samtools'")
4708 (string-append "htslib_dir = '"
4709 (assoc-ref inputs "htslib")
4711 (("^samtools_dir = 'samtools'")
4712 (string-append "samtools_dir = '"
4713 (assoc-ref inputs "samtools")
4715 (("^findStaticOrShared\\('bam', hts_lib")
4716 (string-append "findStaticOrShared('bam', '"
4717 (assoc-ref inputs "samtools")
4719 ;; Do not distribute README.
4720 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
4725 ("samtools" ,samtools)
4728 (home-page "https://bitbucket.org/berkeleylab/metabat")
4730 "Reconstruction of single genomes from complex microbial communities")
4732 "Grouping large genomic fragments assembled from shotgun metagenomic
4733 sequences to deconvolute complex microbial communities, or metagenome binning,
4734 enables the study of individual organisms and their interactions. MetaBAT is
4735 an automated metagenome binning software, which integrates empirical
4736 probabilistic distances of genome abundance and tetranucleotide frequency.")
4737 ;; The source code contains inline assembly.
4738 (supported-systems '("x86_64-linux" "i686-linux"))
4739 (license (license:non-copyleft "file://license.txt"
4740 "See license.txt in the distribution."))))
4742 (define-public minced
4749 (url "https://github.com/ctSkennerton/minced.git")
4751 (file-name (git-file-name name version))
4754 "1f5h9him0gd355cnx7p6pnxpknhckd4g0v62mg8zyhfbx9as25fv"))))
4755 (build-system gnu-build-system)
4757 `(#:test-target "test"
4759 (modify-phases %standard-phases
4761 (add-before 'check 'fix-test
4763 ;; Fix test for latest version.
4764 (substitute* "t/Aquifex_aeolicus_VF5.expected"
4765 (("minced:0.1.6") "minced:0.2.0"))
4767 (replace 'install ; No install target.
4768 (lambda* (#:key inputs outputs #:allow-other-keys)
4769 (let* ((out (assoc-ref outputs "out"))
4770 (bin (string-append out "/bin"))
4771 (wrapper (string-append bin "/minced")))
4772 ;; Minced comes with a wrapper script that tries to figure out where
4773 ;; it is located before running the JAR. Since these paths are known
4774 ;; to us, we build our own wrapper to avoid coreutils dependency.
4775 (install-file "minced.jar" bin)
4776 (with-output-to-file wrapper
4780 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
4781 (assoc-ref inputs "jre") "/bin/java -jar "
4782 bin "/minced.jar \"$@\"\n"))))
4783 (chmod wrapper #o555))
4786 `(("jdk" ,icedtea "jdk")))
4789 ("jre" ,icedtea "out")))
4790 (home-page "https://github.com/ctSkennerton/minced")
4791 (synopsis "Mining CRISPRs in Environmental Datasets")
4793 "MinCED is a program to find Clustered Regularly Interspaced Short
4794 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
4795 unassembled metagenomic reads, but is mainly designed for full genomes and
4796 assembled metagenomic sequence.")
4797 (license license:gpl3+)))
4805 (uri (pypi-uri "misopy" version))
4808 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
4809 (modules '((guix build utils)))
4811 (substitute* "setup.py"
4812 ;; Use setuptools, or else the executables are not
4814 (("distutils.core") "setuptools")
4815 ;; Use "gcc" instead of "cc" for compilation.
4817 "cc.set_executables(
4821 linker_so='gcc -shared'); defines"))
4823 (build-system python-build-system)
4825 `(#:python ,python-2 ; only Python 2 is supported
4826 #:tests? #f)) ; no "test" target
4828 `(("samtools" ,samtools)
4829 ("python-numpy" ,python2-numpy)
4830 ("python-pysam" ,python2-pysam)
4831 ("python-scipy" ,python2-scipy)
4832 ("python-matplotlib" ,python2-matplotlib)))
4834 `(("python-mock" ,python2-mock) ; for tests
4835 ("python-pytz" ,python2-pytz))) ; for tests
4836 (home-page "https://www.genes.mit.edu/burgelab/miso/index.html")
4837 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
4839 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
4840 the expression level of alternatively spliced genes from RNA-Seq data, and
4841 identifies differentially regulated isoforms or exons across samples. By
4842 modeling the generative process by which reads are produced from isoforms in
4843 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
4844 that a read originated from a particular isoform.")
4845 (license license:gpl2)))
4847 (define-public muscle
4850 (version "3.8.1551")
4852 (method url-fetch/tarbomb)
4854 "http://www.drive5.com/muscle/muscle_src_"
4858 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
4859 (build-system gnu-build-system)
4861 `(#:make-flags (list "LDLIBS = -lm")
4863 (modify-phases %standard-phases
4866 ;; There are no tests, so just test if it runs.
4867 (lambda _ (invoke "./muscle" "-version") #t))
4869 (lambda* (#:key outputs #:allow-other-keys)
4870 (let* ((out (assoc-ref outputs "out"))
4871 (bin (string-append out "/bin")))
4872 (install-file "muscle" bin)
4874 (home-page "http://www.drive5.com/muscle")
4875 (synopsis "Multiple sequence alignment program")
4877 "MUSCLE aims to be a fast and accurate multiple sequence alignment
4878 program for nucleotide and protein sequences.")
4879 ;; License information found in 'muscle -h' and usage.cpp.
4880 (license license:public-domain)))
4882 (define-public newick-utils
4883 ;; There are no recent releases so we package from git.
4884 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
4886 (name "newick-utils")
4887 (version (string-append "1.6-1." (string-take commit 8)))
4891 (url "https://github.com/tjunier/newick_utils.git")
4893 (file-name (string-append name "-" version "-checkout"))
4896 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4897 (build-system gnu-build-system)
4899 ;; XXX: TODO: Enable Lua and Guile bindings.
4900 ;; https://github.com/tjunier/newick_utils/issues/13
4901 `(("libxml2" ,libxml2)
4905 `(("autoconf" ,autoconf)
4906 ("automake" ,automake)
4907 ("libtool" ,libtool)))
4908 (synopsis "Programs for working with newick format phylogenetic trees")
4910 "Newick-utils is a suite of utilities for processing phylogenetic trees
4911 in Newick format. Functions include re-rooting, extracting subtrees,
4912 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4913 (home-page "https://github.com/tjunier/newick_utils")
4914 (license license:bsd-3))))
4923 "https://github.com/wwood/OrfM/releases/download/v"
4924 version "/orfm-" version ".tar.gz"))
4927 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4928 (build-system gnu-build-system)
4929 (inputs `(("zlib" ,zlib)))
4931 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4932 ("ruby-rspec" ,ruby-rspec)
4934 (synopsis "Simple and not slow open reading frame (ORF) caller")
4936 "An ORF caller finds stretches of DNA that, when translated, are not
4937 interrupted by stop codons. OrfM finds and prints these ORFs.")
4938 (home-page "https://github.com/wwood/OrfM")
4939 (license license:lgpl3+)))
4941 (define-public python2-pbcore
4943 (name "python2-pbcore")
4947 (uri (pypi-uri "pbcore" version))
4950 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4951 (build-system python-build-system)
4953 `(#:python ,python-2 ;pbcore < 2.0 requires Python 2.7
4954 #:phases (modify-phases %standard-phases
4955 (add-after 'unpack 'remove-sphinx-dependency
4957 ;; Sphinx is only required for documentation tests, which
4958 ;; we do not run; furthermore it depends on python2-sphinx
4959 ;; which is no longer maintained.
4960 (substitute* "requirements-dev.txt"
4964 `(("python-cython" ,python2-cython)
4965 ("python-numpy" ,python2-numpy)
4966 ("python-pysam" ,python2-pysam)
4967 ("python-h5py" ,python2-h5py)))
4969 `(("python-nose" ,python2-nose)
4970 ("python-pyxb" ,python2-pyxb)))
4971 (home-page "https://pacificbiosciences.github.io/pbcore/")
4972 (synopsis "Library for reading and writing PacBio data files")
4974 "The pbcore package provides Python APIs for interacting with PacBio data
4975 files and writing bioinformatics applications.")
4976 (license license:bsd-3)))
4978 (define-public python2-warpedlmm
4980 (name "python2-warpedlmm")
4985 (uri (pypi-uri "WarpedLMM" version ".zip"))
4988 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4989 (build-system python-build-system)
4991 `(#:python ,python-2 ; requires Python 2.7
4992 #:tests? #f ; test data are not included
4994 (modify-phases %standard-phases
4995 (add-after 'unpack 'use-weave
4997 (substitute* "warpedlmm/util/linalg.py"
4998 (("from scipy import linalg, weave")
4999 "from scipy import linalg\nimport weave"))
5002 `(("python-scipy" ,python2-scipy)
5003 ("python-numpy" ,python2-numpy)
5004 ("python-matplotlib" ,python2-matplotlib)
5005 ("python-fastlmm" ,python2-fastlmm)
5006 ("python-pandas" ,python2-pandas)
5007 ("python-pysnptools" ,python2-pysnptools)
5008 ("python-weave" ,python2-weave)))
5010 `(("python-mock" ,python2-mock)
5011 ("python-nose" ,python2-nose)
5013 (home-page "https://github.com/PMBio/warpedLMM")
5014 (synopsis "Implementation of warped linear mixed models")
5016 "WarpedLMM is a Python implementation of the warped linear mixed model,
5017 which automatically learns an optimal warping function (or transformation) for
5018 the phenotype as it models the data.")
5019 (license license:asl2.0)))
5021 (define-public pbtranscript-tofu
5022 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
5024 (name "pbtranscript-tofu")
5025 (version (string-append "2.2.3." (string-take commit 7)))
5029 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
5031 (file-name (string-append name "-" version "-checkout"))
5034 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
5035 (modules '((guix build utils)))
5038 ;; remove bundled Cython sources
5039 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
5041 (build-system python-build-system)
5043 `(#:python ,python-2
5044 ;; FIXME: Tests fail with "No such file or directory:
5045 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
5048 (modify-phases %standard-phases
5049 (add-after 'unpack 'enter-directory
5051 (chdir "pbtranscript-tofu/pbtranscript/")
5053 ;; With setuptools version 18.0 and later this setup.py hack causes
5054 ;; a build error, so we disable it.
5055 (add-after 'enter-directory 'patch-setuppy
5057 (substitute* "setup.py"
5058 (("if 'setuptools.extension' in sys.modules:")
5062 `(("python-numpy" ,python2-numpy)
5063 ("python-bx-python" ,python2-bx-python)
5064 ("python-networkx" ,python2-networkx)
5065 ("python-scipy" ,python2-scipy)
5066 ("python-pbcore" ,python2-pbcore)
5067 ("python-h5py" ,python2-h5py)))
5069 `(("python-cython" ,python2-cython)
5070 ("python-nose" ,python2-nose)))
5071 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
5072 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
5074 "pbtranscript-tofu contains scripts to analyze transcriptome data
5075 generated using the PacBio Iso-Seq protocol.")
5076 (license license:bsd-3))))
5078 (define-public prank
5085 "http://wasabiapp.org/download/prank/prank.source."
5089 "0nc8g9c5rkdxcir46s0in9ci1sxwzbjibxrvkksf22ybnplvagk2"))))
5090 (build-system gnu-build-system)
5093 (modify-phases %standard-phases
5094 (add-after 'unpack 'enter-src-dir
5098 (add-after 'unpack 'remove-m64-flag
5099 ;; Prank will build with the correct 'bit-ness' without this flag
5100 ;; and this allows building on 32-bit machines.
5101 (lambda _ (substitute* "src/Makefile"
5106 (lambda* (#:key outputs #:allow-other-keys)
5107 (let* ((out (assoc-ref outputs "out"))
5108 (bin (string-append out "/bin"))
5109 (man (string-append out "/share/man/man1"))
5110 (path (string-append
5111 (assoc-ref %build-inputs "mafft") "/bin:"
5112 (assoc-ref %build-inputs "exonerate") "/bin:"
5113 (assoc-ref %build-inputs "bppsuite") "/bin")))
5114 (install-file "prank" bin)
5115 (wrap-program (string-append bin "/prank")
5116 `("PATH" ":" prefix (,path)))
5117 (install-file "prank.1" man))
5121 ("exonerate" ,exonerate)
5122 ("bppsuite" ,bppsuite)))
5123 (home-page "http://wasabiapp.org/software/prank/")
5124 (synopsis "Probabilistic multiple sequence alignment program")
5126 "PRANK is a probabilistic multiple sequence alignment program for DNA,
5127 codon and amino-acid sequences. It is based on a novel algorithm that treats
5128 insertions correctly and avoids over-estimation of the number of deletion
5129 events. In addition, PRANK borrows ideas from maximum likelihood methods used
5130 in phylogenetics and correctly takes into account the evolutionary distances
5131 between sequences. Lastly, PRANK allows for defining a potential structure
5132 for sequences to be aligned and then, simultaneously with the alignment,
5133 predicts the locations of structural units in the sequences.")
5134 (license license:gpl2+)))
5136 (define-public proteinortho
5138 (name "proteinortho")
5143 (url "https://gitlab.com/paulklemm_PHD/proteinortho.git")
5144 (commit (string-append "v" version))))
5145 (file-name (git-file-name name version))
5148 "0pmy617zy2z2w6hjqxjhf3rzikf5n3mpia80ysq8233vfr7wrzff"))
5149 (modules '((guix build utils)))
5152 ;; remove pre-built scripts
5153 (delete-file-recursively "src/BUILD/")
5155 (build-system gnu-build-system)
5157 `(#:test-target "test"
5158 #:make-flags '("CC=gcc")
5160 (modify-phases %standard-phases
5162 ;; There is no configure script, so we modify the Makefile directly.
5163 (lambda* (#:key outputs #:allow-other-keys)
5164 (substitute* "Makefile"
5167 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
5169 (add-before 'install 'make-install-directory
5170 ;; The install directory is not created during 'make install'.
5171 (lambda* (#:key outputs #:allow-other-keys)
5172 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
5174 (add-after 'install 'wrap-programs
5175 (lambda* (#:key inputs outputs #:allow-other-keys)
5176 (let ((path (getenv "PATH"))
5177 (out (assoc-ref outputs "out")))
5178 (for-each (lambda (script)
5179 (wrap-script script `("PATH" ":" prefix (,path))))
5180 (cons (string-append out "/bin/proteinortho")
5181 (find-files out "\\.(pl|py)$"))))
5184 `(("guile" ,guile-3.0) ; for wrap-script
5185 ("diamond" ,diamond)
5187 ("python" ,python-wrapper)
5190 ("openblas" ,openblas)))
5192 `(("which" ,which)))
5193 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
5194 (synopsis "Detect orthologous genes across species")
5196 "Proteinortho is a tool to detect orthologous genes across different
5197 species. For doing so, it compares similarities of given gene sequences and
5198 clusters them to find significant groups. The algorithm was designed to handle
5199 large-scale data and can be applied to hundreds of species at once.")
5200 (license license:gpl3+)))
5202 (define-public pyicoteo
5210 (url "https://bitbucket.org/regulatorygenomicsupf/pyicoteo.git")
5211 (commit (string-append "v" version))))
5212 (file-name (git-file-name name version))
5215 "0hz5g8d25lbjy1wpscr490l0lmyvaix893hhax4fxnh1h9w34w8p"))))
5216 (build-system python-build-system)
5218 `(#:python ,python-2 ; does not work with Python 3
5219 #:tests? #f)) ; there are no tests
5221 `(("python2-matplotlib" ,python2-matplotlib)))
5222 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
5223 (synopsis "Analyze high-throughput genetic sequencing data")
5225 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
5226 sequencing data. It works with genomic coordinates. There are currently six
5227 different command-line tools:
5230 @item pyicoregion: for generating exploratory regions automatically;
5231 @item pyicoenrich: for differential enrichment between two conditions;
5232 @item pyicoclip: for calling CLIP-Seq peaks without a control;
5233 @item pyicos: for genomic coordinates manipulation;
5234 @item pyicoller: for peak calling on punctuated ChIP-Seq;
5235 @item pyicount: to count how many reads from N experiment files overlap in a
5237 @item pyicotrocol: to combine operations from pyicoteo.
5239 (license license:gpl3+)))
5241 (define-public prodigal
5244 ;; Check for a new home page when updating this package:
5245 ;; https://github.com/hyattpd/Prodigal/issues/36#issuecomment-536617588
5250 (url "https://github.com/hyattpd/Prodigal.git")
5251 (commit (string-append "v" version))))
5252 (file-name (git-file-name name version))
5255 "1fs1hqk83qjbjhrvhw6ni75zakx5ki1ayy3v6wwkn3xvahc9hi5s"))))
5256 (build-system gnu-build-system)
5258 `(#:tests? #f ; no check target
5259 #:make-flags (list (string-append "INSTALLDIR="
5260 (assoc-ref %outputs "out")
5263 (modify-phases %standard-phases
5264 (delete 'configure))))
5265 (home-page "https://github.com/hyattpd/Prodigal")
5266 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
5268 "Prodigal runs smoothly on finished genomes, draft genomes, and
5269 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
5270 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
5271 partial genes, and identifies translation initiation sites.")
5272 (license license:gpl3+)))
5274 (define-public roary
5282 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
5286 "0qxrds9wx7cfhlkihrp6697kx0flhhxymap9fwan0b3rbdhcnmff"))))
5287 (build-system perl-build-system)
5290 (modify-phases %standard-phases
5295 ;; The tests are not run by default, so we run each test file
5297 (setenv "PATH" (string-append (getcwd) "/bin" ":"
5299 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
5300 (getenv "PERL5LIB")))
5301 (for-each (lambda (file)
5302 (display file)(display "\n")
5303 (invoke "perl" file))
5304 (find-files "t" ".*\\.t$"))
5307 ;; There is no 'install' target in the Makefile.
5308 (lambda* (#:key outputs #:allow-other-keys)
5309 (let* ((out (assoc-ref outputs "out"))
5310 (bin (string-append out "/bin"))
5311 (perl (string-append out "/lib/perl5/site_perl"))
5312 (roary-plots "contrib/roary_plots"))
5315 (copy-recursively "bin" bin)
5316 (copy-recursively "lib" perl)
5318 (add-after 'install 'wrap-programs
5319 (lambda* (#:key inputs outputs #:allow-other-keys)
5320 (let* ((out (assoc-ref outputs "out"))
5321 (perl5lib (getenv "PERL5LIB"))
5322 (path (getenv "PATH")))
5323 (for-each (lambda (prog)
5324 (let ((binary (string-append out "/" prog)))
5325 (wrap-program binary
5326 `("PERL5LIB" ":" prefix
5327 (,(string-append perl5lib ":" out
5328 "/lib/perl5/site_perl"))))
5329 (wrap-program binary
5331 (,(string-append path ":" out "/bin"))))))
5332 (find-files "bin" ".*[^R]$"))
5334 (string-append out "/bin/roary-create_pan_genome_plots.R"))
5335 (r-site-lib (getenv "R_LIBS_SITE"))
5337 (string-append (assoc-ref inputs "coreutils") "/bin")))
5339 `("R_LIBS_SITE" ":" prefix
5340 (,(string-append r-site-lib ":" out "/site-library/"))))
5343 (,(string-append coreutils-path ":" out "/bin"))))))
5346 `(("perl-env-path" ,perl-env-path)
5347 ("perl-test-files" ,perl-test-files)
5348 ("perl-test-most" ,perl-test-most)
5349 ("perl-test-output" ,perl-test-output)))
5351 `(("perl-array-utils" ,perl-array-utils)
5352 ("bioperl" ,bioperl-minimal)
5353 ("perl-digest-md5-file" ,perl-digest-md5-file)
5354 ("perl-exception-class" ,perl-exception-class)
5355 ("perl-file-find-rule" ,perl-file-find-rule)
5356 ("perl-file-grep" ,perl-file-grep)
5357 ("perl-file-slurper" ,perl-file-slurper)
5358 ("perl-file-which" ,perl-file-which)
5359 ("perl-graph" ,perl-graph)
5360 ("perl-graph-readwrite" ,perl-graph-readwrite)
5361 ("perl-log-log4perl" ,perl-log-log4perl)
5362 ("perl-moose" ,perl-moose)
5363 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
5364 ("perl-text-csv" ,perl-text-csv)
5365 ("bedtools" ,bedtools)
5369 ("parallel" ,parallel)
5372 ("fasttree" ,fasttree)
5376 ("r-minimal" ,r-minimal)
5377 ("r-ggplot2" ,r-ggplot2)
5378 ("coreutils" ,coreutils)))
5379 (home-page "https://sanger-pathogens.github.io/Roary/")
5380 (synopsis "High speed stand-alone pan genome pipeline")
5382 "Roary is a high speed stand alone pan genome pipeline, which takes
5383 annotated assemblies in GFF3 format (produced by the Prokka program) and
5384 calculates the pan genome. Using a standard desktop PC, it can analyse
5385 datasets with thousands of samples, without compromising the quality of the
5386 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
5387 single processor. Roary is not intended for metagenomics or for comparing
5388 extremely diverse sets of genomes.")
5389 (license license:gpl3)))
5391 (define-public raxml
5399 (url "https://github.com/stamatak/standard-RAxML.git")
5400 (commit (string-append "v" version))))
5401 (file-name (git-file-name name version))
5404 "1jqjzhch0rips0vp04prvb8vmc20c5pdmsqn8knadcf91yy859fh"))))
5405 (build-system gnu-build-system)
5407 `(#:tests? #f ; There are no tests.
5408 ;; Use 'standard' Makefile rather than SSE or AVX ones.
5409 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
5411 (modify-phases %standard-phases
5414 (lambda* (#:key outputs #:allow-other-keys)
5415 (let* ((out (assoc-ref outputs "out"))
5416 (bin (string-append out "/bin"))
5417 (executable "raxmlHPC-HYBRID"))
5418 (install-file executable bin)
5419 (symlink (string-append bin "/" executable) "raxml"))
5422 `(("openmpi" ,openmpi)))
5423 (home-page "https://cme.h-its.org/exelixis/web/software/raxml/index.html")
5424 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
5426 "RAxML is a tool for phylogenetic analysis and post-analysis of large
5428 ;; The source includes x86 specific code
5429 (supported-systems '("x86_64-linux" "i686-linux"))
5430 (license license:gpl2+)))
5440 (url "https://github.com/deweylab/RSEM.git")
5441 (commit (string-append "v" version))))
5443 (base32 "1jlq11d1p8qp64w75yj8cnbbd1a93viq10pzsbwal7vdn8fg13j1"))
5444 (file-name (git-file-name name version))
5445 (modules '((guix build utils)))
5448 ;; remove bundled copy of boost and samtools
5449 (delete-file-recursively "boost")
5450 (delete-file-recursively "samtools-1.3")
5452 (build-system gnu-build-system)
5454 `(#:tests? #f ;no "check" target
5456 (list (string-append "BOOST="
5457 (assoc-ref %build-inputs "boost")
5459 (string-append "SAMHEADERS="
5460 (assoc-ref %build-inputs "htslib")
5461 "/include/htslib/sam.h")
5462 (string-append "SAMLIBS="
5463 (assoc-ref %build-inputs "htslib")
5466 (modify-phases %standard-phases
5467 ;; No "configure" script.
5468 ;; Do not build bundled samtools library.
5471 (substitute* "Makefile"
5472 (("^all : \\$\\(PROGRAMS\\).*") "all: $(PROGRAMS)\n")
5473 (("^\\$\\(SAMLIBS\\).*") ""))
5476 (lambda* (#:key outputs #:allow-other-keys)
5477 (let* ((out (string-append (assoc-ref outputs "out")))
5478 (bin (string-append out "/bin/"))
5479 (perl (string-append out "/lib/perl5/site_perl")))
5482 (for-each (lambda (file)
5483 (install-file file bin))
5484 (find-files "." "rsem-.*"))
5485 (install-file "rsem_perl_utils.pm" perl))
5487 (add-after 'install 'wrap-program
5488 (lambda* (#:key outputs #:allow-other-keys)
5489 (let ((out (assoc-ref outputs "out")))
5490 (for-each (lambda (prog)
5491 (wrap-program (string-append out "/bin/" prog)
5492 `("PERL5LIB" ":" prefix
5493 (,(string-append out "/lib/perl5/site_perl")))))
5494 '("rsem-calculate-expression"
5496 "rsem-generate-data-matrix"
5497 "rsem-generate-ngvector"
5498 "rsem-plot-transcript-wiggles"
5499 "rsem-prepare-reference"
5501 "rsem-run-prsem-testing-procedure")))
5505 ("r-minimal" ,r-minimal)
5507 ("htslib" ,htslib-1.3)
5509 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
5510 (synopsis "Estimate gene expression levels from RNA-Seq data")
5512 "RSEM is a software package for estimating gene and isoform expression
5513 levels from RNA-Seq data. The RSEM package provides a user-friendly
5514 interface, supports threads for parallel computation of the EM algorithm,
5515 single-end and paired-end read data, quality scores, variable-length reads and
5516 RSPD estimation. In addition, it provides posterior mean and 95% credibility
5517 interval estimates for expression levels. For visualization, it can generate
5518 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
5519 (license license:gpl3+)))
5521 (define-public rseqc
5529 (string-append "mirror://sourceforge/rseqc/"
5530 "RSeQC-" version ".tar.gz"))
5533 "0gbb9iyb7swiv5455fm5rg98r7l6qn27v564yllqjd574hncpx6m"))))
5534 (build-system python-build-system)
5536 `(("python-cython" ,python-cython)
5537 ("python-bx-python" ,python-bx-python)
5538 ("python-pybigwig" ,python-pybigwig)
5539 ("python-pysam" ,python-pysam)
5540 ("python-numpy" ,python-numpy)
5543 `(("python-nose" ,python-nose)))
5544 (home-page "http://rseqc.sourceforge.net/")
5545 (synopsis "RNA-seq quality control package")
5547 "RSeQC provides a number of modules that can comprehensively evaluate
5548 high throughput sequence data, especially RNA-seq data. Some basic modules
5549 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
5550 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
5551 distribution, coverage uniformity, strand specificity, etc.")
5552 (license license:gpl3+)))
5555 ;; There are no release tarballs. According to the installation
5556 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
5557 ;; stable release is identified by this changeset ID.
5558 (let ((changeset "2329130")
5562 (version (string-append "0-" revision "." changeset))
5566 (url "https://bitbucket.org/libsleipnir/sleipnir")
5567 (changeset changeset)))
5568 (file-name (string-append name "-" version "-checkout"))
5571 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
5572 (build-system gnu-build-system)
5574 `(#:modules ((srfi srfi-1)
5575 (guix build gnu-build-system)
5578 (let ((dirs '("SeekMiner"
5584 (modify-phases %standard-phases
5587 (substitute* "gen_tools_am"
5588 (("/usr/bin/env.*") (which "perl")))
5589 (invoke "bash" "gen_auto")
5591 (add-after 'build 'build-additional-tools
5592 (lambda* (#:key make-flags #:allow-other-keys)
5593 (for-each (lambda (dir)
5594 (with-directory-excursion (string-append "tools/" dir)
5595 (apply invoke "make" make-flags)))
5598 (add-after 'install 'install-additional-tools
5599 (lambda* (#:key make-flags #:allow-other-keys)
5600 (for-each (lambda (dir)
5601 (with-directory-excursion (string-append "tools/" dir)
5602 (apply invoke `("make" ,@make-flags "install"))))
5609 ("readline" ,readline)
5610 ("gengetopt" ,gengetopt)
5611 ("log4cpp" ,log4cpp)))
5613 `(("autoconf" ,autoconf)
5614 ("automake" ,automake)
5616 (home-page "http://seek.princeton.edu")
5617 (synopsis "Gene co-expression search engine")
5619 "SEEK is a computational gene co-expression search engine. SEEK provides
5620 biologists with a way to navigate the massive human expression compendium that
5621 now contains thousands of expression datasets. SEEK returns a robust ranking
5622 of co-expressed genes in the biological area of interest defined by the user's
5623 query genes. It also prioritizes thousands of expression datasets according
5624 to the user's query of interest.")
5625 (license license:cc-by3.0))))
5627 (define-public samtools
5635 (string-append "mirror://sourceforge/samtools/samtools/"
5636 version "/samtools-" version ".tar.bz2"))
5639 "10ilqbmm7ri8z431sn90lvbjwizd0hhkf9rcqw8j823hf26nhgq8"))
5640 (modules '((guix build utils)))
5642 ;; Delete bundled htslib.
5643 (delete-file-recursively "htslib-1.9")
5645 (build-system gnu-build-system)
5647 `(#:modules ((ice-9 ftw)
5649 (guix build gnu-build-system)
5651 #:configure-flags (list "--with-ncurses")
5653 (modify-phases %standard-phases
5654 (add-after 'unpack 'patch-tests
5656 (substitute* "test/test.pl"
5657 ;; The test script calls out to /bin/bash
5658 (("/bin/bash") (which "bash")))
5660 (add-after 'install 'install-library
5661 (lambda* (#:key outputs #:allow-other-keys)
5662 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
5663 (install-file "libbam.a" lib)
5665 (add-after 'install 'install-headers
5666 (lambda* (#:key outputs #:allow-other-keys)
5667 (let ((include (string-append (assoc-ref outputs "out")
5668 "/include/samtools/")))
5669 (for-each (lambda (file)
5670 (install-file file include))
5671 (scandir "." (lambda (name) (string-match "\\.h$" name))))
5673 (native-inputs `(("pkg-config" ,pkg-config)))
5675 `(("htslib" ,htslib)
5676 ("ncurses" ,ncurses)
5680 (home-page "http://samtools.sourceforge.net")
5681 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
5683 "Samtools implements various utilities for post-processing nucleotide
5684 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
5685 variant calling (in conjunction with bcftools), and a simple alignment
5687 (license license:expat)))
5689 (define-public samtools-0.1
5690 ;; This is the most recent version of the 0.1 line of samtools. The input
5691 ;; and output formats differ greatly from that used and produced by samtools
5692 ;; 1.x and is still used in many bioinformatics pipelines.
5693 (package (inherit samtools)
5699 (string-append "mirror://sourceforge/samtools/samtools/"
5700 version "/samtools-" version ".tar.bz2"))
5702 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
5704 `(#:tests? #f ;no "check" target
5706 (list "LIBCURSES=-lncurses")
5707 ,@(substitute-keyword-arguments (package-arguments samtools)
5709 `(modify-phases ,phases
5711 (lambda* (#:key outputs #:allow-other-keys)
5712 (let ((bin (string-append
5713 (assoc-ref outputs "out") "/bin")))
5715 (install-file "samtools" bin)
5717 (delete 'patch-tests)
5718 (delete 'configure))))))))
5720 (define-public mosaik
5721 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
5726 ;; There are no release tarballs nor tags.
5729 (url "https://github.com/wanpinglee/MOSAIK.git")
5731 (file-name (string-append name "-" version))
5734 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
5735 (build-system gnu-build-system)
5737 `(#:tests? #f ; no tests
5738 #:make-flags (list "CC=gcc")
5740 (modify-phases %standard-phases
5742 (lambda _ (chdir "src") #t))
5744 (lambda* (#:key outputs #:allow-other-keys)
5745 (let ((bin (string-append (assoc-ref outputs "out")
5748 (copy-recursively "../bin" bin)
5752 ("zlib:static" ,zlib "static")
5754 (supported-systems '("x86_64-linux"))
5755 (home-page "https://github.com/wanpinglee/MOSAIK")
5756 (synopsis "Map nucleotide sequence reads to reference genomes")
5758 "MOSAIK is a program for mapping second and third-generation sequencing
5759 reads to a reference genome. MOSAIK can align reads generated by all the
5760 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
5761 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
5762 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
5763 ;; code released into the public domain:
5764 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
5765 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
5766 (license (list license:gpl2+ license:public-domain)))))
5768 (define-public ngs-sdk
5775 (url "https://github.com/ncbi/ngs.git")
5777 (file-name (git-file-name name version))
5780 "1ix51c25hjn57w93qmwzw80xh2i34wx8j2hn7szh8p6w8i3az5qa"))))
5781 (build-system gnu-build-system)
5783 `(#:parallel-build? #f ; not supported
5784 #:tests? #f ; no "check" target
5786 (modify-phases %standard-phases
5788 (lambda* (#:key outputs #:allow-other-keys)
5789 (let ((out (assoc-ref outputs "out")))
5790 ;; Allow 'konfigure.perl' to find 'package.prl'.
5792 (string-append ".:" (getenv "PERL5LIB")))
5794 ;; The 'configure' script doesn't recognize things like
5795 ;; '--enable-fast-install'.
5796 (invoke "./configure"
5797 (string-append "--build-prefix=" (getcwd) "/build")
5798 (string-append "--prefix=" out))
5800 (add-after 'unpack 'enter-dir
5801 (lambda _ (chdir "ngs-sdk") #t)))))
5802 (native-inputs `(("perl" ,perl)))
5803 ;; According to the test
5804 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
5805 ;; in ngs-sdk/setup/konfigure.perl
5806 (supported-systems '("i686-linux" "x86_64-linux"))
5807 (home-page "https://github.com/ncbi/ngs")
5808 (synopsis "API for accessing Next Generation Sequencing data")
5810 "NGS is a domain-specific API for accessing reads, alignments and pileups
5811 produced from Next Generation Sequencing. The API itself is independent from
5812 any particular back-end implementation, and supports use of multiple back-ends
5814 (license license:public-domain)))
5816 (define-public java-ngs
5817 (package (inherit ngs-sdk)
5820 `(,@(substitute-keyword-arguments
5821 `(#:modules ((guix build gnu-build-system)
5825 ,@(package-arguments ngs-sdk))
5827 `(modify-phases ,phases
5828 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5830 `(("jdk" ,icedtea "jdk")
5831 ("ngs-sdk" ,ngs-sdk)))
5832 (synopsis "Java bindings for NGS SDK")))
5834 (define-public ncbi-vdb
5841 (url "https://github.com/ncbi/ncbi-vdb.git")
5843 (file-name (git-file-name name version))
5846 "0m8hlxscidsfqm9x9fyi62q6lpf1dv5115kgjjgnrkl49q9c27m6"))))
5847 (build-system gnu-build-system)
5849 `(#:parallel-build? #f ; not supported
5850 #:tests? #f ; no "check" target
5851 #:make-flags '("HAVE_HDF5=1")
5853 (modify-phases %standard-phases
5854 (add-after 'unpack 'make-files-writable
5855 (lambda _ (for-each make-file-writable (find-files "." ".*")) #t))
5856 (add-before 'configure 'set-perl-search-path
5858 ;; Work around "dotless @INC" build failure.
5860 (string-append (getcwd) "/setup:"
5861 (getenv "PERL5LIB")))
5863 ;; See https://github.com/ncbi/ncbi-vdb/issues/14
5864 (add-after 'unpack 'patch-krypto-flags
5866 (substitute* "libs/krypto/Makefile"
5867 (("-Wa,-march=generic64\\+aes") "")
5868 (("-Wa,-march=generic64\\+sse4") ""))
5871 (lambda* (#:key inputs outputs #:allow-other-keys)
5872 (let ((out (assoc-ref outputs "out")))
5873 ;; Override include path for libmagic
5874 (substitute* "setup/package.prl"
5875 (("name => 'magic', Include => '/usr/include'")
5876 (string-append "name=> 'magic', Include => '"
5877 (assoc-ref inputs "libmagic")
5880 ;; Install kdf5 library (needed by sra-tools)
5881 (substitute* "build/Makefile.install"
5882 (("LIBRARIES_TO_INSTALL =")
5883 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5885 (substitute* "build/Makefile.env"
5886 (("CFLAGS =" prefix)
5887 (string-append prefix "-msse2 ")))
5889 ;; Override search path for ngs-java
5890 (substitute* "setup/package.prl"
5891 (("/usr/local/ngs/ngs-java")
5892 (assoc-ref inputs "java-ngs")))
5894 ;; The 'configure' script doesn't recognize things like
5895 ;; '--enable-fast-install'.
5896 (invoke "./configure"
5897 (string-append "--build-prefix=" (getcwd) "/build")
5898 (string-append "--prefix=" (assoc-ref outputs "out"))
5899 (string-append "--debug")
5900 (string-append "--with-xml2-prefix="
5901 (assoc-ref inputs "libxml2"))
5902 (string-append "--with-ngs-sdk-prefix="
5903 (assoc-ref inputs "ngs-sdk"))
5904 (string-append "--with-hdf5-prefix="
5905 (assoc-ref inputs "hdf5")))
5907 (add-after 'install 'install-interfaces
5908 (lambda* (#:key outputs #:allow-other-keys)
5909 ;; Install interface libraries. On i686 the interface libraries
5910 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5911 ;; architecture name ("i386") instead of the target system prefix
5913 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5914 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5915 ,(system->linux-architecture
5916 (or (%current-target-system)
5919 (string-append (assoc-ref outputs "out")
5921 ;; Install interface headers
5922 (copy-recursively "interfaces"
5923 (string-append (assoc-ref outputs "out")
5926 ;; These files are needed by sra-tools.
5927 (add-after 'install 'install-configuration-files
5928 (lambda* (#:key outputs #:allow-other-keys)
5929 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5931 (install-file "libs/kfg/default.kfg" target)
5932 (install-file "libs/kfg/certs.kfg" target))
5935 `(("libxml2" ,libxml2)
5936 ("ngs-sdk" ,ngs-sdk)
5937 ("java-ngs" ,java-ngs)
5940 (native-inputs `(("perl" ,perl)))
5941 ;; NCBI-VDB requires SSE capability.
5942 (supported-systems '("i686-linux" "x86_64-linux"))
5943 (home-page "https://github.com/ncbi/ncbi-vdb")
5944 (synopsis "Database engine for genetic information")
5946 "The NCBI-VDB library implements a highly compressed columnar data
5947 warehousing engine that is most often used to store genetic information.
5948 Databases are stored in a portable image within the file system, and can be
5949 accessed/downloaded on demand across HTTP.")
5950 (license license:public-domain)))
5952 (define-public plink
5960 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5961 version "-src.zip"))
5963 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5964 (patches (search-patches "plink-1.07-unclobber-i.patch"
5965 "plink-endian-detection.patch"))))
5966 (build-system gnu-build-system)
5968 '(#:tests? #f ;no "check" target
5969 #:make-flags (list (string-append "LIB_LAPACK="
5970 (assoc-ref %build-inputs "lapack")
5971 "/lib/liblapack.so")
5974 ;; disable phoning home
5977 (modify-phases %standard-phases
5978 ;; no "configure" script
5981 (lambda* (#:key outputs #:allow-other-keys)
5982 (let ((bin (string-append (assoc-ref outputs "out")
5984 (install-file "plink" bin)
5988 ("lapack" ,lapack)))
5990 `(("unzip" ,unzip)))
5991 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5992 (synopsis "Whole genome association analysis toolset")
5994 "PLINK is a whole genome association analysis toolset, designed to
5995 perform a range of basic, large-scale analyses in a computationally efficient
5996 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5997 so there is no support for steps prior to this (e.g. study design and
5998 planning, generating genotype or CNV calls from raw data). Through
5999 integration with gPLINK and Haploview, there is some support for the
6000 subsequent visualization, annotation and storage of results.")
6001 ;; Code is released under GPLv2, except for fisher.h, which is under
6003 (license (list license:gpl2 license:lgpl2.1+))))
6005 (define-public plink-ng
6006 (package (inherit plink)
6013 (url "https://github.com/chrchang/plink-ng.git")
6014 (commit (string-append "v" version))))
6015 (file-name (git-file-name name version))
6017 (base32 "02npdwgkpfkdnhw819rhj5kw02a5k5m90b14zq9zzya4hyg929c0"))))
6018 (build-system gnu-build-system)
6020 '(#:tests? #f ;no "check" target
6021 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
6022 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
6024 "-f" "Makefile.std")
6026 (modify-phases %standard-phases
6027 (add-after 'unpack 'chdir
6028 (lambda _ (chdir "1.9") #t))
6029 (delete 'configure) ; no "configure" script
6031 (lambda* (#:key outputs #:allow-other-keys)
6032 (let ((bin (string-append (assoc-ref outputs "out")
6034 (install-file "plink" bin)
6039 ("openblas" ,openblas)))
6040 (home-page "https://www.cog-genomics.org/plink/")
6041 (license license:gpl3+)))
6043 (define-public smithlab-cpp
6044 (let ((revision "1")
6045 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
6047 (name "smithlab-cpp")
6048 (version (string-append "0." revision "." (string-take commit 7)))
6052 (url "https://github.com/smithlabcode/smithlab_cpp.git")
6054 (file-name (string-append name "-" version "-checkout"))
6057 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
6058 (build-system gnu-build-system)
6060 `(#:modules ((guix build gnu-build-system)
6063 #:tests? #f ;no "check" target
6065 (modify-phases %standard-phases
6066 (add-after 'unpack 'use-samtools-headers
6068 (substitute* '("SAM.cpp"
6070 (("sam.h") "samtools/sam.h"))
6073 (lambda* (#:key outputs #:allow-other-keys)
6074 (let* ((out (assoc-ref outputs "out"))
6075 (lib (string-append out "/lib"))
6076 (include (string-append out "/include/smithlab-cpp")))
6079 (for-each (cut install-file <> lib)
6080 (find-files "." "\\.o$"))
6081 (for-each (cut install-file <> include)
6082 (find-files "." "\\.hpp$")))
6084 (delete 'configure))))
6086 `(("samtools" ,samtools-0.1)
6088 (home-page "https://github.com/smithlabcode/smithlab_cpp")
6089 (synopsis "C++ helper library for functions used in Smith lab projects")
6091 "Smithlab CPP is a C++ library that includes functions used in many of
6092 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
6093 structures, classes for genomic regions, mapped sequencing reads, etc.")
6094 (license license:gpl3+))))
6096 (define-public preseq
6102 (uri (string-append "https://github.com/smithlabcode/preseq/"
6103 "releases/download/v" version
6104 "/preseq_v" version ".tar.bz2"))
6106 (base32 "149x9xmk1wy1gff85325yfzqc0qk4sgp1w6gbyj9cnji4x1dszbl"))
6107 (modules '((guix build utils)))
6109 ;; Remove bundled samtools.
6110 (delete-file-recursively "samtools")
6112 (build-system gnu-build-system)
6114 `(#:tests? #f ;no "check" target
6116 (modify-phases %standard-phases
6117 (delete 'configure))
6119 (list (string-append "PREFIX="
6120 (assoc-ref %outputs "out"))
6121 (string-append "LIBBAM="
6122 (assoc-ref %build-inputs "samtools")
6124 (string-append "SMITHLAB_CPP="
6125 (assoc-ref %build-inputs "smithlab-cpp")
6128 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
6131 ("samtools" ,samtools-0.1)
6132 ("smithlab-cpp" ,smithlab-cpp)
6134 (home-page "http://smithlabresearch.org/software/preseq/")
6135 (synopsis "Program for analyzing library complexity")
6137 "The preseq package is aimed at predicting and estimating the complexity
6138 of a genomic sequencing library, equivalent to predicting and estimating the
6139 number of redundant reads from a given sequencing depth and how many will be
6140 expected from additional sequencing using an initial sequencing experiment.
6141 The estimates can then be used to examine the utility of further sequencing,
6142 optimize the sequencing depth, or to screen multiple libraries to avoid low
6143 complexity samples.")
6144 (license license:gpl3+)))
6146 (define-public python-screed
6148 (name "python-screed")
6153 (uri (pypi-uri "screed" version))
6156 "148vcb7w2wr6a4w6vs2bsxanbqibxfk490zbcbg4m61s8669zdjx"))))
6157 (build-system python-build-system)
6160 (modify-phases %standard-phases
6161 ;; Tests must be run after installation, as the "screed" command does
6162 ;; not exist right after building.
6164 (add-after 'install 'check
6165 (lambda* (#:key inputs outputs #:allow-other-keys)
6166 (let ((out (assoc-ref outputs "out")))
6167 (setenv "PYTHONPATH"
6168 (string-append out "/lib/python"
6169 (string-take (string-take-right
6170 (assoc-ref inputs "python")
6173 (getenv "PYTHONPATH")))
6174 (setenv "PATH" (string-append out "/bin:" (getenv "PATH"))))
6175 (invoke "python" "setup.py" "test")
6178 `(("python-pytest" ,python-pytest)
6179 ("python-pytest-cov" ,python-pytest-cov)
6180 ("python-pytest-runner" ,python-pytest-runner)))
6182 `(("python-bz2file" ,python-bz2file)))
6183 (home-page "https://github.com/dib-lab/screed/")
6184 (synopsis "Short read sequence database utilities")
6185 (description "Screed parses FASTA and FASTQ files and generates databases.
6186 Values such as sequence name, sequence description, sequence quality and the
6187 sequence itself can be retrieved from these databases.")
6188 (license license:bsd-3)))
6190 (define-public python2-screed
6191 (package-with-python2 python-screed))
6193 (define-public sra-tools
6201 (url "https://github.com/ncbi/sra-tools.git")
6203 (file-name (git-file-name name version))
6206 "1cr2mijkfs5sm35ffjs6861qsd1qkgnhnbavdv65zg5d655abbjf"))))
6207 (build-system gnu-build-system)
6209 `(#:parallel-build? #f ; not supported
6210 #:tests? #f ; no "check" target
6212 (list (string-append "DEFAULT_CRT="
6213 (assoc-ref %build-inputs "ncbi-vdb")
6215 (string-append "DEFAULT_KFG="
6216 (assoc-ref %build-inputs "ncbi-vdb")
6218 (string-append "VDB_LIBDIR="
6219 (assoc-ref %build-inputs "ncbi-vdb")
6220 ,(if (string-prefix? "x86_64"
6221 (or (%current-target-system)
6226 (modify-phases %standard-phases
6227 (add-before 'configure 'set-perl-search-path
6229 ;; Work around "dotless @INC" build failure.
6231 (string-append (getcwd) "/setup:"
6232 (getenv "PERL5LIB")))
6235 (lambda* (#:key inputs outputs #:allow-other-keys)
6236 ;; The build system expects a directory containing the sources and
6237 ;; raw build output of ncbi-vdb, including files that are not
6238 ;; installed. Since we are building against an installed version of
6239 ;; ncbi-vdb, the following modifications are needed.
6240 (substitute* "setup/konfigure.perl"
6241 ;; Make the configure script look for the "ilib" directory of
6242 ;; "ncbi-vdb" without first checking for the existence of a
6243 ;; matching library in its "lib" directory.
6244 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
6245 "my $f = File::Spec->catdir($ilibdir, $ilib);")
6246 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
6247 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
6248 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
6251 (substitute* "tools/copycat/Makefile"
6252 (("smagic-static") "lmagic"))
6253 (substitute* "tools/driver-tool/utf8proc/Makefile"
6254 (("CC\\?=gcc") "myCC=gcc")
6255 (("\\(CC\\)") "(myCC)"))
6257 ;; The 'configure' script doesn't recognize things like
6258 ;; '--enable-fast-install'.
6259 (invoke "./configure"
6260 (string-append "--build-prefix=" (getcwd) "/build")
6261 (string-append "--prefix=" (assoc-ref outputs "out"))
6262 (string-append "--debug")
6263 (string-append "--with-fuse-prefix="
6264 (assoc-ref inputs "fuse"))
6265 (string-append "--with-magic-prefix="
6266 (assoc-ref inputs "libmagic"))
6267 ;; TODO: building with libxml2 fails with linker errors
6269 (string-append "--with-xml2-prefix="
6270 (assoc-ref inputs "libxml2"))
6271 (string-append "--with-ncbi-vdb-sources="
6272 (assoc-ref inputs "ncbi-vdb"))
6273 (string-append "--with-ncbi-vdb-build="
6274 (assoc-ref inputs "ncbi-vdb"))
6275 (string-append "--with-ngs-sdk-prefix="
6276 (assoc-ref inputs "ngs-sdk"))
6277 (string-append "--with-hdf5-prefix="
6278 (assoc-ref inputs "hdf5")))
6280 (native-inputs `(("perl" ,perl)))
6282 `(("ngs-sdk" ,ngs-sdk)
6283 ("ncbi-vdb" ,ncbi-vdb)
6288 ("python" ,python-wrapper)))
6290 "https://trace.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
6291 (synopsis "Tools and libraries for reading and writing sequencing data")
6293 "The SRA Toolkit from NCBI is a collection of tools and libraries for
6294 reading of sequencing files from the Sequence Read Archive (SRA) database and
6295 writing files into the .sra format.")
6296 (license license:public-domain)))
6298 (define-public seqan
6304 (uri (string-append "https://github.com/seqan/seqan/releases/"
6305 "download/seqan-v" version
6306 "/seqan-library-" version ".tar.xz"))
6309 "19a1rlxx03qy1i1iriicly68w64yjxbv24g9gdywnfmq998v35yx"))))
6310 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6311 ;; makes sense to split the outputs.
6312 (outputs '("out" "doc"))
6313 (build-system trivial-build-system)
6315 `(#:modules ((guix build utils))
6318 (use-modules (guix build utils))
6319 (let ((tar (assoc-ref %build-inputs "tar"))
6320 (xz (assoc-ref %build-inputs "xz"))
6321 (out (assoc-ref %outputs "out"))
6322 (doc (assoc-ref %outputs "doc")))
6323 (setenv "PATH" (string-append tar "/bin:" xz "/bin"))
6324 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6325 (chdir (string-append "seqan-library-" ,version))
6326 (copy-recursively "include" (string-append out "/include"))
6327 (copy-recursively "share" (string-append doc "/share"))
6330 `(("source" ,source)
6333 (home-page "http://www.seqan.de")
6334 (synopsis "Library for nucleotide sequence analysis")
6336 "SeqAn is a C++ library of efficient algorithms and data structures for
6337 the analysis of sequences with the focus on biological data. It contains
6338 algorithms and data structures for string representation and their
6339 manipulation, online and indexed string search, efficient I/O of
6340 bioinformatics file formats, sequence alignment, and more.")
6341 (license license:bsd-3)))
6343 (define-public seqan-1
6344 (package (inherit seqan)
6349 (uri (string-append "http://packages.seqan.de/seqan-library/"
6350 "seqan-library-" version ".tar.bz2"))
6353 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
6354 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6355 ;; makes sense to split the outputs.
6356 (outputs '("out" "doc"))
6357 (build-system trivial-build-system)
6359 `(#:modules ((guix build utils))
6362 (use-modules (guix build utils))
6363 (let ((tar (assoc-ref %build-inputs "tar"))
6364 (bzip (assoc-ref %build-inputs "bzip2"))
6365 (out (assoc-ref %outputs "out"))
6366 (doc (assoc-ref %outputs "doc")))
6367 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
6368 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6369 (chdir (string-append "seqan-library-" ,version))
6370 (copy-recursively "include" (string-append out "/include"))
6371 (copy-recursively "share" (string-append doc "/share"))
6374 `(("source" ,source)
6376 ("bzip2" ,bzip2)))))
6378 (define-public seqmagick
6385 (uri (pypi-uri "seqmagick" version))
6388 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
6389 (build-system python-build-system)
6391 `(("python-biopython" ,python-biopython)))
6393 `(("python-nose" ,python-nose)))
6394 (home-page "https://github.com/fhcrc/seqmagick")
6395 (synopsis "Tools for converting and modifying sequence files")
6397 "Bioinformaticians often have to convert sequence files between formats
6398 and do little manipulations on them, and it's not worth writing scripts for
6399 that. Seqmagick is a utility to expose the file format conversion in
6400 BioPython in a convenient way. Instead of having a big mess of scripts, there
6401 is one that takes arguments.")
6402 (license license:gpl3)))
6404 (define-public seqtk
6411 (url "https://github.com/lh3/seqtk.git")
6412 (commit (string-append "v" version))))
6413 (file-name (git-file-name name version))
6416 "1bfzlqa84b5s1qi22blmmw2s8xdyp9h9ydcq22pfjhh5gab3yz6l"))))
6417 (build-system gnu-build-system)
6420 (modify-phases %standard-phases
6423 ;; There are no tests, so we just run a sanity check.
6424 (lambda _ (invoke "./seqtk" "seq") #t))
6426 (lambda* (#:key outputs #:allow-other-keys)
6427 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6428 (install-file "seqtk" bin)
6432 (home-page "https://github.com/lh3/seqtk")
6433 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
6435 "Seqtk is a fast and lightweight tool for processing sequences in the
6436 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
6437 optionally compressed by gzip.")
6438 (license license:expat)))
6440 (define-public snap-aligner
6442 (name "snap-aligner")
6443 (version "1.0beta.18")
6447 (url "https://github.com/amplab/snap.git")
6448 (commit (string-append "v" version))))
6449 (file-name (git-file-name name version))
6452 "01w3qq4wm07z73vky0cfwlmrbf50n3w722cxrlzxfi99mnb808d8"))))
6453 (build-system gnu-build-system)
6456 (modify-phases %standard-phases
6458 (replace 'check (lambda _ (invoke "./unit_tests") #t))
6460 (lambda* (#:key outputs #:allow-other-keys)
6461 (let* ((out (assoc-ref outputs "out"))
6462 (bin (string-append out "/bin")))
6463 (install-file "snap-aligner" bin)
6464 (install-file "SNAPCommand" bin)
6468 (home-page "http://snap.cs.berkeley.edu/")
6469 (synopsis "Short read DNA sequence aligner")
6471 "SNAP is a fast and accurate aligner for short DNA reads. It is
6472 optimized for modern read lengths of 100 bases or higher, and takes advantage
6473 of these reads to align data quickly through a hash-based indexing scheme.")
6474 ;; 32-bit systems are not supported by the unpatched code.
6475 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
6476 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
6477 ;; systems without a lot of memory cannot make good use of this program.
6478 (supported-systems '("x86_64-linux"))
6479 (license license:asl2.0)))
6481 (define-public sortmerna
6489 (url "https://github.com/biocore/sortmerna.git")
6491 (file-name (git-file-name name version))
6494 "0j3mbz4n25738yijmjbr5r4fyvkgm8v5vn3sshyfvmyqf5q9byqf"))))
6495 (build-system gnu-build-system)
6496 (outputs '("out" ;for binaries
6497 "db")) ;for sequence databases
6500 (modify-phases %standard-phases
6502 (lambda* (#:key outputs #:allow-other-keys)
6503 (let* ((out (assoc-ref outputs "out"))
6504 (bin (string-append out "/bin"))
6505 (db (assoc-ref outputs "db"))
6507 (string-append db "/share/sortmerna/rRNA_databases")))
6508 (install-file "sortmerna" bin)
6509 (install-file "indexdb_rna" bin)
6510 (for-each (lambda (file)
6511 (install-file file share))
6512 (find-files "rRNA_databases" ".*fasta"))
6516 (home-page "https://bioinfo.lifl.fr/RNA/sortmerna/")
6517 (synopsis "Biological sequence analysis tool for NGS reads")
6519 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
6520 and operational taxonomic unit (OTU) picking of next generation
6521 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
6522 allows for fast and sensitive analyses of nucleotide sequences. The main
6523 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
6524 ;; The source includes x86 specific code
6525 (supported-systems '("x86_64-linux" "i686-linux"))
6526 (license license:lgpl3)))
6535 (url "https://github.com/alexdobin/STAR.git")
6537 (file-name (git-file-name name version))
6540 "1hgiqw5qhs0pc1xazzihcfd92na02xyq2kb469z04y1v51kpvvjq"))
6541 (modules '((guix build utils)))
6544 (substitute* "source/Makefile"
6546 ;; Remove pre-built binaries and bundled htslib sources.
6547 (delete-file-recursively "bin/MacOSX_x86_64")
6548 (delete-file-recursively "bin/Linux_x86_64")
6549 (delete-file-recursively "bin/Linux_x86_64_static")
6550 (delete-file-recursively "source/htslib")
6552 (build-system gnu-build-system)
6554 '(#:tests? #f ;no check target
6555 #:make-flags '("STAR")
6557 (modify-phases %standard-phases
6558 (add-after 'unpack 'enter-source-dir
6559 (lambda _ (chdir "source") #t))
6560 (add-after 'enter-source-dir 'make-reproducible
6562 (substitute* "Makefile"
6563 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
6564 (string-append pre "Built with Guix" post)))
6566 ;; See https://github.com/alexdobin/STAR/pull/562
6567 (add-after 'enter-source-dir 'add-missing-header
6569 (substitute* "SoloReadFeature_inputRecords.cpp"
6570 (("#include \"binarySearch2.h\"" h)
6571 (string-append h "\n#include <math.h>")))
6573 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
6575 (substitute* "Makefile"
6576 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
6578 (substitute* '("BAMfunctions.cpp"
6583 "bamRemoveDuplicates.cpp")
6584 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
6585 (string-append "#include <" header ">")))
6586 (substitute* "IncludeDefine.h"
6587 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
6588 (string-append "<" header ">")))
6591 (lambda* (#:key outputs #:allow-other-keys)
6592 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6593 (install-file "STAR" bin))
6595 (delete 'configure))))
6599 `(("htslib" ,htslib)
6601 (home-page "https://github.com/alexdobin/STAR")
6602 (synopsis "Universal RNA-seq aligner")
6604 "The Spliced Transcripts Alignment to a Reference (STAR) software is
6605 based on a previously undescribed RNA-seq alignment algorithm that uses
6606 sequential maximum mappable seed search in uncompressed suffix arrays followed
6607 by seed clustering and stitching procedure. In addition to unbiased de novo
6608 detection of canonical junctions, STAR can discover non-canonical splices and
6609 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
6611 ;; Only 64-bit systems are supported according to the README.
6612 (supported-systems '("x86_64-linux" "mips64el-linux"))
6613 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
6614 (license license:gpl3+)))
6616 (define-public starlong
6617 (package (inherit star)
6620 (substitute-keyword-arguments (package-arguments star)
6621 ((#:make-flags flags)
6624 `(modify-phases ,phases
6625 ;; Allow extra long sequence reads.
6626 (add-after 'unpack 'make-extra-long
6628 (substitute* "source/IncludeDefine.h"
6629 (("(#define DEF_readNameLengthMax ).*" _ match)
6630 (string-append match "900000\n")))
6633 (lambda* (#:key outputs #:allow-other-keys)
6634 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6635 (install-file "STARlong" bin))
6638 (define-public subread
6644 (uri (string-append "mirror://sourceforge/subread/subread-"
6645 version "/subread-" version "-source.tar.gz"))
6648 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
6649 (build-system gnu-build-system)
6651 `(#:tests? #f ;no "check" target
6652 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
6653 ;; optimizations by default, so we override these flags such that x86_64
6654 ;; flags are only added when the build target is an x86_64 system.
6656 (list (let ((system ,(or (%current-target-system)
6658 (flags '("-ggdb" "-fomit-frame-pointer"
6659 "-ffast-math" "-funroll-loops"
6660 "-fmessage-length=0"
6661 "-O9" "-Wall" "-DMAKE_FOR_EXON"
6663 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
6664 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
6665 (if (string-prefix? "x86_64" system)
6666 (string-append "CCFLAGS=" (string-join (append flags flags64)))
6667 (string-append "CCFLAGS=" (string-join flags))))
6668 "-f" "Makefile.Linux"
6669 "CC=gcc ${CCFLAGS}")
6671 (modify-phases %standard-phases
6672 (add-after 'unpack 'enter-dir
6673 (lambda _ (chdir "src") #t))
6675 (lambda* (#:key outputs #:allow-other-keys)
6676 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6678 (copy-recursively "../bin" bin))
6680 ;; no "configure" script
6681 (delete 'configure))))
6682 (inputs `(("zlib" ,zlib)))
6683 (home-page "http://bioinf.wehi.edu.au/subread-package/")
6684 (synopsis "Tool kit for processing next-gen sequencing data")
6686 "The subread package contains the following tools: subread aligner, a
6687 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
6688 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
6689 features; exactSNP: a SNP caller that discovers SNPs by testing signals
6690 against local background noises.")
6691 (license license:gpl3+)))
6693 (define-public stringtie
6699 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
6700 "stringtie-" version ".tar.gz"))
6703 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
6704 (modules '((guix build utils)))
6707 (delete-file-recursively "samtools-0.1.18")
6709 (build-system gnu-build-system)
6711 `(#:tests? #f ;no test suite
6713 (modify-phases %standard-phases
6714 ;; no configure script
6716 (add-before 'build 'use-system-samtools
6718 (substitute* "Makefile"
6719 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
6721 (substitute* '("gclib/GBam.h"
6723 (("#include \"(bam|sam|kstring).h\"" _ header)
6724 (string-append "#include <samtools/" header ".h>")))
6726 (add-after 'unpack 'remove-duplicate-typedef
6728 ;; This typedef conflicts with the typedef in
6729 ;; glibc-2.25/include/bits/types.h
6730 (substitute* "gclib/GThreads.h"
6731 (("typedef long long __intmax_t;") ""))
6734 (lambda* (#:key outputs #:allow-other-keys)
6735 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6736 (install-file "stringtie" bin)
6739 `(("samtools" ,samtools-0.1)
6741 (home-page "http://ccb.jhu.edu/software/stringtie/")
6742 (synopsis "Transcript assembly and quantification for RNA-Seq data")
6744 "StringTie is a fast and efficient assembler of RNA-Seq sequence
6745 alignments into potential transcripts. It uses a novel network flow algorithm
6746 as well as an optional de novo assembly step to assemble and quantitate
6747 full-length transcripts representing multiple splice variants for each gene
6748 locus. Its input can include not only the alignments of raw reads used by
6749 other transcript assemblers, but also alignments of longer sequences that have
6750 been assembled from those reads. To identify differentially expressed genes
6751 between experiments, StringTie's output can be processed either by the
6752 Cuffdiff or Ballgown programs.")
6753 (license license:artistic2.0)))
6755 (define-public taxtastic
6760 ;; The Pypi version does not include tests.
6763 (url "https://github.com/fhcrc/taxtastic.git")
6764 (commit (string-append "v" version))))
6765 (file-name (git-file-name name version))
6768 "1sv8mkg64jn7zdwf1jj71c16686yrwxk0apb1l8sjszy9p166g0p"))))
6769 (build-system python-build-system)
6772 (modify-phases %standard-phases
6773 (add-after 'unpack 'prepare-directory
6775 ;; The git checkout must be writable for tests.
6776 (for-each make-file-writable (find-files "."))
6777 ;; This test fails, but the error is not caught by the test
6778 ;; framework, so the tests fail...
6779 (substitute* "tests/test_taxit.py"
6780 (("self.cmd_fails\\(''\\)")
6781 "self.cmd_fails('nothing')"))
6782 ;; This version file is expected to be created with git describe.
6783 (mkdir-p "taxtastic/data")
6784 (with-output-to-file "taxtastic/data/ver"
6785 (lambda () (display ,version)))
6787 (add-after 'unpack 'python37-compatibility
6789 (substitute* "taxtastic/utils.py"
6790 (("import csv") "import csv, errno")
6791 (("os.errno") "errno"))
6794 ;; Note, this fails to run with "-v" as it tries to write to a
6795 ;; closed output stream.
6796 (lambda _ (invoke "python" "-m" "unittest") #t)))))
6798 `(("python-sqlalchemy" ,python-sqlalchemy)
6799 ("python-decorator" ,python-decorator)
6800 ("python-biopython" ,python-biopython)
6801 ("python-pandas" ,python-pandas)
6802 ("python-psycopg2" ,python-psycopg2)
6803 ("python-fastalite" ,python-fastalite)
6804 ("python-pyyaml" ,python-pyyaml)
6805 ("python-six" ,python-six)
6806 ("python-jinja2" ,python-jinja2)
6807 ("python-dendropy" ,python-dendropy)))
6808 (home-page "https://github.com/fhcrc/taxtastic")
6809 (synopsis "Tools for taxonomic naming and annotation")
6811 "Taxtastic is software written in python used to build and maintain
6812 reference packages i.e. collections of reference trees, reference alignments,
6813 profiles, and associated taxonomic information.")
6814 (license license:gpl3+)))
6816 (define-public vcftools
6823 "https://github.com/vcftools/vcftools/releases/download/v"
6824 version "/vcftools-" version ".tar.gz"))
6827 "1qqlx7flfv7axrjwkaz6njkscsl1d0jw98ns8d8bh1n1hd1pgz6v"))))
6828 (build-system gnu-build-system)
6830 `(#:tests? #f ; no "check" target
6832 "CFLAGS=-O2" ; override "-m64" flag
6833 (string-append "PREFIX=" (assoc-ref %outputs "out"))
6834 (string-append "MANDIR=" (assoc-ref %outputs "out")
6835 "/share/man/man1"))))
6837 `(("pkg-config" ,pkg-config)))
6841 (home-page "https://vcftools.github.io/")
6842 (synopsis "Tools for working with VCF files")
6844 "VCFtools is a program package designed for working with VCF files, such
6845 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
6846 provide easily accessible methods for working with complex genetic variation
6847 data in the form of VCF files.")
6848 ;; The license is declared as LGPLv3 in the README and
6849 ;; at https://vcftools.github.io/license.html
6850 (license license:lgpl3)))
6852 (define-public infernal
6858 (uri (string-append "http://eddylab.org/software/infernal/"
6859 "infernal-" version ".tar.gz"))
6862 "0pm8bm3s6nfa0av4x6m6h27lsg12b3lz3jm0fyh1mc77l2isd61v"))))
6863 (build-system gnu-build-system)
6866 ("python" ,python))) ; for tests
6867 (home-page "http://eddylab.org/infernal/")
6868 (synopsis "Inference of RNA alignments")
6869 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
6870 searching DNA sequence databases for RNA structure and sequence similarities.
6871 It is an implementation of a special case of profile stochastic context-free
6872 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
6873 profile, but it scores a combination of sequence consensus and RNA secondary
6874 structure consensus, so in many cases, it is more capable of identifying RNA
6875 homologs that conserve their secondary structure more than their primary
6877 ;; Infernal 1.1.3 requires VMX or SSE capability for parallel instructions.
6878 (supported-systems '("i686-linux" "x86_64-linux"))
6879 (license license:bsd-3)))
6881 (define-public r-scde
6888 (url "https://github.com/hms-dbmi/scde.git")
6890 (file-name (git-file-name name version))
6893 "10na2gyka24mszdxf92wz9h2c13hdf1ww30c68gfsw53lvvhhhxb"))))
6894 (build-system r-build-system)
6896 `(("r-rcpp" ,r-rcpp)
6897 ("r-rcpparmadillo" ,r-rcpparmadillo)
6900 ("r-rjson" ,r-rjson)
6901 ("r-cairo" ,r-cairo)
6902 ("r-rcolorbrewer" ,r-rcolorbrewer)
6903 ("r-edger" ,r-edger)
6904 ("r-quantreg" ,r-quantreg)
6906 ("r-rmtstat" ,r-rmtstat)
6907 ("r-extremes" ,r-extremes)
6908 ("r-pcamethods" ,r-pcamethods)
6909 ("r-biocparallel" ,r-biocparallel)
6910 ("r-flexmix" ,r-flexmix)))
6911 (home-page "https://hms-dbmi.github.io/scde/")
6912 (synopsis "R package for analyzing single-cell RNA-seq data")
6913 (description "The SCDE package implements a set of statistical methods for
6914 analyzing single-cell RNA-seq data. SCDE fits individual error models for
6915 single-cell RNA-seq measurements. These models can then be used for
6916 assessment of differential expression between groups of cells, as well as
6917 other types of analysis. The SCDE package also contains the pagoda framework
6918 which applies pathway and gene set overdispersion analysis to identify aspects
6919 of transcriptional heterogeneity among single cells.")
6920 ;; See https://github.com/hms-dbmi/scde/issues/38
6921 (license license:gpl2)))
6923 (define-public r-centipede
6925 (name "r-centipede")
6929 (uri (string-append "http://download.r-forge.r-project.org/"
6930 "src/contrib/CENTIPEDE_" version ".tar.gz"))
6933 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
6934 (build-system r-build-system)
6935 (home-page "http://centipede.uchicago.edu/")
6936 (synopsis "Predict transcription factor binding sites")
6938 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
6939 of the genome that are bound by particular transcription factors. It starts
6940 by identifying a set of candidate binding sites, and then aims to classify the
6941 sites according to whether each site is bound or not bound by a transcription
6942 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
6943 between two different types of motif instances using as much relevant
6944 information as possible.")
6945 (license (list license:gpl2+ license:gpl3+))))
6947 (define-public r-genefilter
6949 (name "r-genefilter")
6954 (uri (bioconductor-uri "genefilter" version))
6957 "1sbbrnq6p90fri0ik6aq2zw26kasw63nyiy7xkzrj6vgyq7x258g"))))
6958 (build-system r-build-system)
6960 `(("gfortran" ,gfortran)
6961 ("r-knitr" ,r-knitr)))
6963 `(("r-annotate" ,r-annotate)
6964 ("r-annotationdbi" ,r-annotationdbi)
6965 ("r-biobase" ,r-biobase)
6966 ("r-biocgenerics" ,r-biocgenerics)
6967 ("r-survival" ,r-survival)))
6968 (home-page "https://bioconductor.org/packages/genefilter")
6969 (synopsis "Filter genes from high-throughput experiments")
6971 "This package provides basic functions for filtering genes from
6972 high-throughput sequencing experiments.")
6973 (license license:artistic2.0)))
6975 (define-public r-deseq2
6982 (uri (bioconductor-uri "DESeq2" version))
6985 "0xh12c2skr0bbv893p05gvbismkcnqw8zwh7yz4wmycgajfzg2pp"))))
6986 (properties `((upstream-name . "DESeq2")))
6987 (build-system r-build-system)
6989 `(("r-biobase" ,r-biobase)
6990 ("r-biocgenerics" ,r-biocgenerics)
6991 ("r-biocparallel" ,r-biocparallel)
6992 ("r-genefilter" ,r-genefilter)
6993 ("r-geneplotter" ,r-geneplotter)
6994 ("r-genomicranges" ,r-genomicranges)
6995 ("r-ggplot2" ,r-ggplot2)
6996 ("r-iranges" ,r-iranges)
6997 ("r-locfit" ,r-locfit)
6999 ("r-rcpparmadillo" ,r-rcpparmadillo)
7000 ("r-s4vectors" ,r-s4vectors)
7001 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7003 `(("r-knitr" ,r-knitr)))
7004 (home-page "https://bioconductor.org/packages/DESeq2")
7005 (synopsis "Differential gene expression analysis")
7007 "This package provides functions to estimate variance-mean dependence in
7008 count data from high-throughput nucleotide sequencing assays and test for
7009 differential expression based on a model using the negative binomial
7011 (license license:lgpl3+)))
7013 (define-public r-dexseq
7020 (uri (bioconductor-uri "DEXSeq" version))
7023 "1inyxb89hd5bn0sl7a9qbv9d1g40z4v1s9qwxkcsx5c79fl04n1h"))))
7024 (properties `((upstream-name . "DEXSeq")))
7025 (build-system r-build-system)
7027 `(("r-annotationdbi" ,r-annotationdbi)
7028 ("r-biobase" ,r-biobase)
7029 ("r-biocgenerics" ,r-biocgenerics)
7030 ("r-biocparallel" ,r-biocparallel)
7031 ("r-biomart" ,r-biomart)
7032 ("r-deseq2" ,r-deseq2)
7033 ("r-genefilter" ,r-genefilter)
7034 ("r-geneplotter" ,r-geneplotter)
7035 ("r-genomicranges" ,r-genomicranges)
7036 ("r-hwriter" ,r-hwriter)
7037 ("r-iranges" ,r-iranges)
7038 ("r-rcolorbrewer" ,r-rcolorbrewer)
7039 ("r-rsamtools" ,r-rsamtools)
7040 ("r-s4vectors" ,r-s4vectors)
7041 ("r-statmod" ,r-statmod)
7042 ("r-stringr" ,r-stringr)
7043 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7045 `(("r-knitr" ,r-knitr)))
7046 (home-page "https://bioconductor.org/packages/DEXSeq")
7047 (synopsis "Inference of differential exon usage in RNA-Seq")
7049 "This package is focused on finding differential exon usage using RNA-seq
7050 exon counts between samples with different experimental designs. It provides
7051 functions that allows the user to make the necessary statistical tests based
7052 on a model that uses the negative binomial distribution to estimate the
7053 variance between biological replicates and generalized linear models for
7054 testing. The package also provides functions for the visualization and
7055 exploration of the results.")
7056 (license license:gpl3+)))
7058 (define-public r-annotationforge
7060 (name "r-annotationforge")
7065 (uri (bioconductor-uri "AnnotationForge" version))
7068 "1a2155jxbwc6qr3dcyvp850grhdr7czc7bs3s87ff4sgdl0jp3jw"))))
7070 `((upstream-name . "AnnotationForge")))
7071 (build-system r-build-system)
7073 `(("r-annotationdbi" ,r-annotationdbi)
7074 ("r-biobase" ,r-biobase)
7075 ("r-biocgenerics" ,r-biocgenerics)
7077 ("r-rcurl" ,r-rcurl)
7078 ("r-rsqlite" ,r-rsqlite)
7079 ("r-s4vectors" ,r-s4vectors)
7082 `(("r-knitr" ,r-knitr)))
7083 (home-page "https://bioconductor.org/packages/AnnotationForge")
7084 (synopsis "Code for building annotation database packages")
7086 "This package provides code for generating Annotation packages and their
7087 databases. Packages produced are intended to be used with AnnotationDbi.")
7088 (license license:artistic2.0)))
7090 (define-public r-rbgl
7097 (uri (bioconductor-uri "RBGL" version))
7100 "079599a6xn2i7snfn2vgshkw0c00rrfhj44pvi03ap8id29bkayy"))))
7101 (properties `((upstream-name . "RBGL")))
7102 (build-system r-build-system)
7105 ("r-graph" ,r-graph)))
7106 (home-page "https://www.bioconductor.org/packages/RBGL")
7107 (synopsis "Interface to the Boost graph library")
7109 "This package provides a fairly extensive and comprehensive interface to
7110 the graph algorithms contained in the Boost library.")
7111 (license license:artistic2.0)))
7113 (define-public r-gseabase
7120 (uri (bioconductor-uri "GSEABase" version))
7123 "1k4faj53cwvqijad8cf7fcghzxcv9shlbpl8n73bsncc8k192y2j"))))
7124 (properties `((upstream-name . "GSEABase")))
7125 (build-system r-build-system)
7127 `(("r-annotate" ,r-annotate)
7128 ("r-annotationdbi" ,r-annotationdbi)
7129 ("r-biobase" ,r-biobase)
7130 ("r-biocgenerics" ,r-biocgenerics)
7131 ("r-graph" ,r-graph)
7134 `(("r-knitr" ,r-knitr)))
7135 (home-page "https://bioconductor.org/packages/GSEABase")
7136 (synopsis "Gene set enrichment data structures and methods")
7138 "This package provides classes and methods to support @dfn{Gene Set
7139 Enrichment Analysis} (GSEA).")
7140 (license license:artistic2.0)))
7142 (define-public r-category
7149 (uri (bioconductor-uri "Category" version))
7152 "1grspdzk5a4vidnxwcd1jmy1vcn494aydsp3vydx235yv7iqac1b"))))
7153 (properties `((upstream-name . "Category")))
7154 (build-system r-build-system)
7156 `(("r-annotate" ,r-annotate)
7157 ("r-annotationdbi" ,r-annotationdbi)
7158 ("r-biobase" ,r-biobase)
7159 ("r-biocgenerics" ,r-biocgenerics)
7160 ("r-genefilter" ,r-genefilter)
7161 ("r-graph" ,r-graph)
7162 ("r-gseabase" ,r-gseabase)
7163 ("r-matrix" ,r-matrix)
7166 (home-page "https://bioconductor.org/packages/Category")
7167 (synopsis "Category analysis")
7169 "This package provides a collection of tools for performing category
7171 (license license:artistic2.0)))
7173 (define-public r-gostats
7180 (uri (bioconductor-uri "GOstats" version))
7183 "00q39cyv4l28r6s9gjnd0qhl7h80vmwp4lpmchisqzj44xzyics9"))))
7184 (properties `((upstream-name . "GOstats")))
7185 (build-system r-build-system)
7187 `(("r-annotate" ,r-annotate)
7188 ("r-annotationdbi" ,r-annotationdbi)
7189 ("r-annotationforge" ,r-annotationforge)
7190 ("r-biobase" ,r-biobase)
7191 ("r-category" ,r-category)
7192 ("r-go-db" ,r-go-db)
7193 ("r-graph" ,r-graph)
7194 ("r-rgraphviz" ,r-rgraphviz)
7195 ("r-rbgl" ,r-rbgl)))
7196 (home-page "https://bioconductor.org/packages/GOstats")
7197 (synopsis "Tools for manipulating GO and microarrays")
7199 "This package provides a set of tools for interacting with GO and
7200 microarray data. A variety of basic manipulation tools for graphs, hypothesis
7201 testing and other simple calculations.")
7202 (license license:artistic2.0)))
7204 (define-public r-shortread
7206 (name "r-shortread")
7211 (uri (bioconductor-uri "ShortRead" version))
7214 "0l4kdln69y6yhln0xiv2jmpxg05fjcglln406p43a2bqvk2lr03d"))))
7215 (properties `((upstream-name . "ShortRead")))
7216 (build-system r-build-system)
7220 `(("r-biobase" ,r-biobase)
7221 ("r-biocgenerics" ,r-biocgenerics)
7222 ("r-biocparallel" ,r-biocparallel)
7223 ("r-biostrings" ,r-biostrings)
7224 ("r-genomeinfodb" ,r-genomeinfodb)
7225 ("r-genomicalignments" ,r-genomicalignments)
7226 ("r-genomicranges" ,r-genomicranges)
7227 ("r-hwriter" ,r-hwriter)
7228 ("r-iranges" ,r-iranges)
7229 ("r-lattice" ,r-lattice)
7230 ("r-latticeextra" ,r-latticeextra)
7231 ("r-rsamtools" ,r-rsamtools)
7232 ("r-s4vectors" ,r-s4vectors)
7233 ("r-xvector" ,r-xvector)
7234 ("r-zlibbioc" ,r-zlibbioc)))
7235 (home-page "https://bioconductor.org/packages/ShortRead")
7236 (synopsis "FASTQ input and manipulation tools")
7238 "This package implements sampling, iteration, and input of FASTQ files.
7239 It includes functions for filtering and trimming reads, and for generating a
7240 quality assessment report. Data are represented as
7241 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
7242 purposes. The package also contains legacy support for early single-end,
7243 ungapped alignment formats.")
7244 (license license:artistic2.0)))
7246 (define-public r-systempiper
7248 (name "r-systempiper")
7253 (uri (bioconductor-uri "systemPipeR" version))
7256 "01ilhlrvy28jfdyxjria4024yryj5zgympgqznw17g3y3az78kk2"))))
7257 (properties `((upstream-name . "systemPipeR")))
7258 (build-system r-build-system)
7260 `(("r-annotate" ,r-annotate)
7261 ("r-assertthat" ,r-assertthat)
7262 ("r-batchtools" ,r-batchtools)
7263 ("r-biostrings" ,r-biostrings)
7264 ("r-deseq2" ,r-deseq2)
7266 ("r-edger" ,r-edger)
7267 ("r-genomicfeatures" ,r-genomicfeatures)
7268 ("r-genomicranges" ,r-genomicranges)
7269 ("r-ggplot2" ,r-ggplot2)
7270 ("r-go-db" ,r-go-db)
7271 ("r-gostats" ,r-gostats)
7272 ("r-limma" ,r-limma)
7273 ("r-magrittr" ,r-magrittr)
7274 ("r-pheatmap" ,r-pheatmap)
7275 ("r-rjson" ,r-rjson)
7276 ("r-rsamtools" ,r-rsamtools)
7278 ("r-shortread" ,r-shortread)
7279 ("r-stringr" ,r-stringr)
7280 ("r-summarizedexperiment" ,r-summarizedexperiment)
7282 ("r-variantannotation" ,r-variantannotation)))
7284 `(("r-knitr" ,r-knitr)))
7285 (home-page "https://github.com/tgirke/systemPipeR")
7286 (synopsis "Next generation sequencing workflow and reporting environment")
7288 "This R package provides tools for building and running automated
7289 end-to-end analysis workflows for a wide range of @dfn{next generation
7290 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
7291 Important features include a uniform workflow interface across different NGS
7292 applications, automated report generation, and support for running both R and
7293 command-line software, such as NGS aligners or peak/variant callers, on local
7294 computers or compute clusters. Efficient handling of complex sample sets and
7295 experimental designs is facilitated by a consistently implemented sample
7296 annotation infrastructure.")
7297 (license license:artistic2.0)))
7299 (define-public r-grohmm
7306 (uri (bioconductor-uri "groHMM" version))
7309 "04z9qq1xwdsaxbqhyld37w0ybvzly9pc1hcyrnwdbyjwd7n1fncb"))))
7310 (properties `((upstream-name . "groHMM")))
7311 (build-system r-build-system)
7313 `(("r-genomeinfodb" ,r-genomeinfodb)
7314 ("r-genomicalignments" ,r-genomicalignments)
7315 ("r-genomicranges" ,r-genomicranges)
7316 ("r-iranges" ,r-iranges)
7318 ("r-rtracklayer" ,r-rtracklayer)
7319 ("r-s4vectors" ,r-s4vectors)))
7320 (home-page "https://github.com/Kraus-Lab/groHMM")
7321 (synopsis "GRO-seq analysis pipeline")
7323 "This package provides a pipeline for the analysis of GRO-seq data.")
7324 (license license:gpl3+)))
7326 (define-public vsearch
7334 (url "https://github.com/torognes/vsearch.git")
7335 (commit (string-append "v" version))))
7336 (file-name (git-file-name name version))
7339 "0vhrpjfdf75ba04b24xknp41790cvcgwl0vgpy7qbzj5xh2521ss"))
7340 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
7343 ;; Remove bundled cityhash sources. The vsearch source is adjusted
7344 ;; for this in the patch.
7345 (delete-file "src/city.h")
7346 (delete-file "src/citycrc.h")
7347 (delete-file "src/city.cc")
7349 (build-system gnu-build-system)
7353 ("cityhash" ,cityhash)))
7355 `(("autoconf" ,autoconf)
7356 ("automake" ,automake)))
7357 (synopsis "Sequence search tools for metagenomics")
7359 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
7360 dereplication, pairwise alignment, shuffling, subsampling, sorting and
7361 masking. The tool takes advantage of parallelism in the form of SIMD
7362 vectorization as well as multiple threads to perform accurate alignments at
7363 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
7364 Needleman-Wunsch).")
7365 (home-page "https://github.com/torognes/vsearch")
7366 ;; vsearch uses non-portable SSE intrinsics so building fails on other
7368 (supported-systems '("x86_64-linux"))
7369 ;; Dual licensed; also includes public domain source.
7370 (license (list license:gpl3 license:bsd-2))))
7372 (define-public pardre
7375 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
7380 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
7384 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
7385 (build-system gnu-build-system)
7387 `(#:tests? #f ; no tests included
7389 (modify-phases %standard-phases
7392 (lambda* (#:key outputs #:allow-other-keys)
7393 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
7394 (install-file "ParDRe" bin)
7397 `(("openmpi" ,openmpi)
7399 (synopsis "Parallel tool to remove duplicate DNA reads")
7401 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
7402 Duplicate reads can be seen as identical or nearly identical sequences with
7403 some mismatches. This tool lets users avoid the analysis of unnecessary
7404 reads, reducing the time of subsequent procedures with the
7405 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
7406 in order to exploit the parallel capabilities of multicore clusters. It is
7407 faster than multithreaded counterparts (end of 2015) for the same number of
7408 cores and, thanks to the message-passing technology, it can be executed on
7410 (home-page "https://sourceforge.net/projects/pardre/")
7411 (license license:gpl3+)))
7413 (define-public ruby-bio-kseq
7415 (name "ruby-bio-kseq")
7420 (uri (rubygems-uri "bio-kseq" version))
7423 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
7424 (build-system ruby-build-system)
7426 `(#:test-target "spec"))
7428 `(("bundler" ,bundler)
7429 ("ruby-rspec" ,ruby-rspec)
7430 ("ruby-rake-compiler" ,ruby-rake-compiler)))
7433 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
7435 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
7436 FASTQ parsing code. It provides a fast iterator over sequences and their
7438 (home-page "https://github.com/gusevfe/bio-kseq")
7439 (license license:expat)))
7441 (define-public bio-locus
7448 (uri (rubygems-uri "bio-locus" version))
7451 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
7452 (build-system ruby-build-system)
7454 `(("ruby-rspec" ,ruby-rspec)))
7455 (synopsis "Tool for fast querying of genome locations")
7457 "Bio-locus is a tabix-like tool for fast querying of genome
7458 locations. Many file formats in bioinformatics contain records that
7459 start with a chromosome name and a position for a SNP, or a start-end
7460 position for indels. Bio-locus allows users to store this chr+pos or
7461 chr+pos+alt information in a database.")
7462 (home-page "https://github.com/pjotrp/bio-locus")
7463 (license license:expat)))
7465 (define-public bio-blastxmlparser
7467 (name "bio-blastxmlparser")
7471 (uri (rubygems-uri "bio-blastxmlparser" version))
7474 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
7475 (build-system ruby-build-system)
7477 `(("ruby-bio-logger" ,ruby-bio-logger)
7478 ("ruby-nokogiri" ,ruby-nokogiri)))
7480 `(("ruby-rspec" ,ruby-rspec)))
7481 (synopsis "Fast big data BLAST XML parser and library")
7483 "Very fast parallel big-data BLAST XML file parser which can be used as
7484 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
7485 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
7486 (home-page "https://github.com/pjotrp/blastxmlparser")
7487 (license license:expat)))
7489 (define-public bioruby
7496 (uri (rubygems-uri "bio" version))
7499 "1d56amdsjv1mag7m6gv2w0xij8hqx1v5xbdjsix8sp3yp36m7938"))))
7500 (build-system ruby-build-system)
7502 `(("ruby-libxml" ,ruby-libxml)))
7504 `(("which" ,which))) ; required for test phase
7507 (modify-phases %standard-phases
7508 (add-before 'build 'patch-test-command
7510 (substitute* '("test/functional/bio/test_command.rb")
7511 (("/bin/sh") (which "sh")))
7512 (substitute* '("test/functional/bio/test_command.rb")
7513 (("/bin/ls") (which "ls")))
7514 (substitute* '("test/functional/bio/test_command.rb")
7515 (("which") (which "which")))
7516 (substitute* '("test/functional/bio/test_command.rb",
7517 "test/data/command/echoarg2.sh")
7518 (("/bin/echo") (which "echo")))
7520 (synopsis "Ruby library, shell and utilities for bioinformatics")
7521 (description "BioRuby comes with a comprehensive set of Ruby development
7522 tools and libraries for bioinformatics and molecular biology. BioRuby has
7523 components for sequence analysis, pathway analysis, protein modelling and
7524 phylogenetic analysis; it supports many widely used data formats and provides
7525 easy access to databases, external programs and public web services, including
7526 BLAST, KEGG, GenBank, MEDLINE and GO.")
7527 (home-page "http://bioruby.org/")
7528 ;; Code is released under Ruby license, except for setup
7529 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
7530 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
7532 (define-public r-biocviews
7534 (name "r-biocviews")
7538 (uri (bioconductor-uri "biocViews" version))
7541 "1h4cmfbff79v9xrh271dp3rv0877ris06lmkvc39kqzj7yjsh7c2"))))
7543 `((upstream-name . "biocViews")))
7544 (build-system r-build-system)
7546 `(("r-biobase" ,r-biobase)
7547 ("r-biocmanager" ,r-biocmanager)
7548 ("r-graph" ,r-graph)
7550 ("r-rcurl" ,r-rcurl)
7552 ("r-runit" ,r-runit)))
7553 (home-page "https://bioconductor.org/packages/biocViews")
7554 (synopsis "Bioconductor package categorization helper")
7555 (description "The purpose of biocViews is to create HTML pages that
7556 categorize packages in a Bioconductor package repository according to keywords,
7557 also known as views, in a controlled vocabulary.")
7558 (license license:artistic2.0)))
7560 (define-public r-biocstyle
7562 (name "r-biocstyle")
7566 (uri (bioconductor-uri "BiocStyle" version))
7569 "07rjl2n4sazdg581zh7w3yykzphgr2gpz41ba4ryqs7347vh9nbf"))))
7571 `((upstream-name . "BiocStyle")))
7572 (build-system r-build-system)
7574 `(("r-biocmanager" ,r-biocmanager)
7575 ("r-bookdown" ,r-bookdown)
7576 ("r-knitr" ,r-knitr)
7577 ("r-rmarkdown" ,r-rmarkdown)
7578 ("r-yaml" ,r-yaml)))
7580 `(("r-knitr" ,r-knitr)))
7581 (home-page "https://bioconductor.org/packages/BiocStyle")
7582 (synopsis "Bioconductor formatting styles")
7583 (description "This package provides standard formatting styles for
7584 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
7586 (license license:artistic2.0)))
7588 (define-public r-bioccheck
7590 (name "r-bioccheck")
7594 (uri (bioconductor-uri "BiocCheck" version))
7597 "1p9ys18sn1crxw1iac2jdgqvwpb5hjd9nfxx0qn0ncrv0b550mny"))))
7599 `((upstream-name . "BiocCheck")))
7600 (build-system r-build-system)
7603 (modify-phases %standard-phases
7604 ;; This package can be used by calling BiocCheck(<package>) from
7605 ;; within R, or by running R CMD BiocCheck <package>. This phase
7606 ;; makes sure the latter works. For this to work, the BiocCheck
7607 ;; script must be somewhere on the PATH (not the R bin directory).
7608 (add-after 'install 'install-bioccheck-subcommand
7609 (lambda* (#:key outputs #:allow-other-keys)
7610 (let* ((out (assoc-ref outputs "out"))
7611 (dest-dir (string-append out "/bin"))
7613 (string-append out "/site-library/BiocCheck/script/")))
7615 (symlink (string-append script-dir "/checkBadDeps.R")
7616 (string-append dest-dir "/checkBadDeps.R"))
7617 (symlink (string-append script-dir "/BiocCheck")
7618 (string-append dest-dir "/BiocCheck")))
7621 `(("r-codetools" ,r-codetools)
7622 ("r-graph" ,r-graph)
7624 ("r-knitr" ,r-knitr)
7625 ("r-optparse" ,r-optparse)
7626 ("r-biocmanager" ,r-biocmanager)
7627 ("r-biocviews" ,r-biocviews)
7628 ("r-stringdist" ,r-stringdist)))
7630 `(("r-knitr" ,r-knitr)))
7631 (home-page "https://bioconductor.org/packages/BiocCheck")
7632 (synopsis "Executes Bioconductor-specific package checks")
7633 (description "This package contains tools to perform additional quality
7634 checks on R packages that are to be submitted to the Bioconductor repository.")
7635 (license license:artistic2.0)))
7637 (define-public r-s4vectors
7639 (name "r-s4vectors")
7643 (uri (bioconductor-uri "S4Vectors" version))
7646 "1ddr3ngyczx332zw9ai1a6h7442lgrbfcj8vrhvbkdkzqwj14xmb"))))
7648 `((upstream-name . "S4Vectors")))
7649 (build-system r-build-system)
7651 `(("r-biocgenerics" ,r-biocgenerics)))
7652 (home-page "https://bioconductor.org/packages/S4Vectors")
7653 (synopsis "S4 implementation of vectors and lists")
7655 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7656 classes and a set of generic functions that extend the semantic of ordinary
7657 vectors and lists in R. Package developers can easily implement vector-like
7658 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7659 In addition, a few low-level concrete subclasses of general interest (e.g.
7660 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7661 S4Vectors package itself.")
7662 (license license:artistic2.0)))
7664 (define-public r-iranges
7670 (uri (bioconductor-uri "IRanges" version))
7673 "1y24jw62806wp2afiyj1x6n00gj7d3323klqdypra9q43pg1w49d"))))
7675 `((upstream-name . "IRanges")))
7676 (build-system r-build-system)
7678 `(("r-biocgenerics" ,r-biocgenerics)
7679 ("r-s4vectors" ,r-s4vectors)))
7680 (home-page "https://bioconductor.org/packages/IRanges")
7681 (synopsis "Infrastructure for manipulating intervals on sequences")
7683 "This package provides efficient low-level and highly reusable S4 classes
7684 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7685 generally, data that can be organized sequentially (formally defined as
7686 @code{Vector} objects), as well as views on these @code{Vector} objects.
7687 Efficient list-like classes are also provided for storing big collections of
7688 instances of the basic classes. All classes in the package use consistent
7689 naming and share the same rich and consistent \"Vector API\" as much as
7691 (license license:artistic2.0)))
7693 (define-public r-genomeinfodbdata
7695 (name "r-genomeinfodbdata")
7699 ;; We cannot use bioconductor-uri here because this tarball is
7700 ;; located under "data/annotation/" instead of "bioc/".
7701 (uri (string-append "https://bioconductor.org/packages/release/"
7702 "data/annotation/src/contrib/GenomeInfoDbData_"
7706 "0di6nlqpsyqf693k2na65ayqldih563x3zfrczpqc5q2hl5kg35c"))))
7708 `((upstream-name . "GenomeInfoDbData")))
7709 (build-system r-build-system)
7710 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7711 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7712 (description "This package contains data for mapping between NCBI taxonomy
7713 ID and species. It is used by functions in the GenomeInfoDb package.")
7714 (license license:artistic2.0)))
7716 (define-public r-genomeinfodb
7718 (name "r-genomeinfodb")
7722 (uri (bioconductor-uri "GenomeInfoDb" version))
7725 "0ab92nq7lvhvhgp512qhiiphpby0b17c666qska6p8a636zzmqiv"))))
7727 `((upstream-name . "GenomeInfoDb")))
7728 (build-system r-build-system)
7730 `(("r-biocgenerics" ,r-biocgenerics)
7731 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7732 ("r-iranges" ,r-iranges)
7733 ("r-rcurl" ,r-rcurl)
7734 ("r-s4vectors" ,r-s4vectors)))
7736 `(("r-knitr" ,r-knitr)))
7737 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7738 (synopsis "Utilities for manipulating chromosome identifiers")
7740 "This package contains data and functions that define and allow
7741 translation between different chromosome sequence naming conventions (e.g.,
7742 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7743 names in their natural, rather than lexicographic, order.")
7744 (license license:artistic2.0)))
7746 (define-public r-edger
7752 (uri (bioconductor-uri "edgeR" version))
7755 "1z9bkg08rgqn3jm2s4ndbj641w33wl8jd3j6m5if6h2nnw6011ic"))))
7756 (properties `((upstream-name . "edgeR")))
7757 (build-system r-build-system)
7759 `(("r-limma" ,r-limma)
7760 ("r-locfit" ,r-locfit)
7762 ("r-statmod" ,r-statmod))) ;for estimateDisp
7763 (home-page "http://bioinf.wehi.edu.au/edgeR")
7764 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7765 (description "This package can do differential expression analysis of
7766 RNA-seq expression profiles with biological replication. It implements a range
7767 of statistical methodology based on the negative binomial distributions,
7768 including empirical Bayes estimation, exact tests, generalized linear models
7769 and quasi-likelihood tests. It be applied to differential signal analysis of
7770 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7772 (license license:gpl2+)))
7774 (define-public r-variantannotation
7776 (name "r-variantannotation")
7780 (uri (bioconductor-uri "VariantAnnotation" version))
7783 "09y6ymwky839nb0y7y93w810hk9mvwqn7595q1276c28dkddiqvw"))))
7785 `((upstream-name . "VariantAnnotation")))
7789 `(("r-annotationdbi" ,r-annotationdbi)
7790 ("r-biobase" ,r-biobase)
7791 ("r-biocgenerics" ,r-biocgenerics)
7792 ("r-biostrings" ,r-biostrings)
7793 ("r-bsgenome" ,r-bsgenome)
7795 ("r-genomeinfodb" ,r-genomeinfodb)
7796 ("r-genomicfeatures" ,r-genomicfeatures)
7797 ("r-genomicranges" ,r-genomicranges)
7798 ("r-iranges" ,r-iranges)
7799 ("r-summarizedexperiment" ,r-summarizedexperiment)
7800 ("r-rhtslib" ,r-rhtslib)
7801 ("r-rsamtools" ,r-rsamtools)
7802 ("r-rtracklayer" ,r-rtracklayer)
7803 ("r-s4vectors" ,r-s4vectors)
7804 ("r-xvector" ,r-xvector)
7805 ("r-zlibbioc" ,r-zlibbioc)))
7806 (build-system r-build-system)
7807 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7808 (synopsis "Package for annotation of genetic variants")
7809 (description "This R package can annotate variants, compute amino acid
7810 coding changes and predict coding outcomes.")
7811 (license license:artistic2.0)))
7813 (define-public r-limma
7819 (uri (bioconductor-uri "limma" version))
7822 "0l6f6lz1rghj8c5s14ljbnmsrwz27fi6a7g42n15n3d3msvflw36"))))
7823 (build-system r-build-system)
7824 (home-page "http://bioinf.wehi.edu.au/limma")
7825 (synopsis "Package for linear models for microarray and RNA-seq data")
7826 (description "This package can be used for the analysis of gene expression
7827 studies, especially the use of linear models for analysing designed experiments
7828 and the assessment of differential expression. The analysis methods apply to
7829 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7830 (license license:gpl2+)))
7832 (define-public r-xvector
7838 (uri (bioconductor-uri "XVector" version))
7841 "11h1hszv4798q1gbx8r6zf8vlaqx4v9ql0lbh2xaxybp66a03pvc"))))
7843 `((upstream-name . "XVector")))
7844 (build-system r-build-system)
7847 (modify-phases %standard-phases
7848 (add-after 'unpack 'use-system-zlib
7850 (substitute* "DESCRIPTION"
7851 (("zlibbioc, ") ""))
7852 (substitute* "NAMESPACE"
7853 (("import\\(zlibbioc\\)") ""))
7858 `(("r-biocgenerics" ,r-biocgenerics)
7859 ("r-iranges" ,r-iranges)
7860 ("r-s4vectors" ,r-s4vectors)))
7861 (home-page "https://bioconductor.org/packages/XVector")
7862 (synopsis "Representation and manpulation of external sequences")
7864 "This package provides memory efficient S4 classes for storing sequences
7865 \"externally\" (behind an R external pointer, or on disk).")
7866 (license license:artistic2.0)))
7868 (define-public r-genomicranges
7870 (name "r-genomicranges")
7874 (uri (bioconductor-uri "GenomicRanges" version))
7877 "0wn1zr2qq0rpv9z2wialgizn6xzdlcjg1w2kif67n53svz6vk2x1"))))
7879 `((upstream-name . "GenomicRanges")))
7880 (build-system r-build-system)
7882 `(("r-biocgenerics" ,r-biocgenerics)
7883 ("r-genomeinfodb" ,r-genomeinfodb)
7884 ("r-iranges" ,r-iranges)
7885 ("r-s4vectors" ,r-s4vectors)
7886 ("r-xvector" ,r-xvector)))
7888 `(("r-knitr" ,r-knitr)))
7889 (home-page "https://bioconductor.org/packages/GenomicRanges")
7890 (synopsis "Representation and manipulation of genomic intervals")
7892 "This package provides tools to efficiently represent and manipulate
7893 genomic annotations and alignments is playing a central role when it comes to
7894 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7895 GenomicRanges package defines general purpose containers for storing and
7896 manipulating genomic intervals and variables defined along a genome.")
7897 (license license:artistic2.0)))
7899 (define-public r-biobase
7905 (uri (bioconductor-uri "Biobase" version))
7908 "13p3kgnxm7hbn8cy289kbhaiyfa6rxx7l1pbvajwqzbay3cxznqp"))))
7910 `((upstream-name . "Biobase")))
7911 (build-system r-build-system)
7913 `(("r-biocgenerics" ,r-biocgenerics)))
7914 (home-page "https://bioconductor.org/packages/Biobase")
7915 (synopsis "Base functions for Bioconductor")
7917 "This package provides functions that are needed by many other packages
7918 on Bioconductor or which replace R functions.")
7919 (license license:artistic2.0)))
7921 (define-public r-annotationdbi
7923 (name "r-annotationdbi")
7927 (uri (bioconductor-uri "AnnotationDbi" version))
7930 "10gplxal0qphcn29azv0i6hiim9q45lmhzvhhhsnwfhwpgja7p05"))))
7932 `((upstream-name . "AnnotationDbi")))
7933 (build-system r-build-system)
7935 `(("r-biobase" ,r-biobase)
7936 ("r-biocgenerics" ,r-biocgenerics)
7938 ("r-iranges" ,r-iranges)
7939 ("r-rsqlite" ,r-rsqlite)
7940 ("r-s4vectors" ,r-s4vectors)))
7942 `(("r-knitr" ,r-knitr)))
7943 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7944 (synopsis "Annotation database interface")
7946 "This package provides user interface and database connection code for
7947 annotation data packages using SQLite data storage.")
7948 (license license:artistic2.0)))
7950 (define-public r-biomart
7956 (uri (bioconductor-uri "biomaRt" version))
7959 "0ag26q9283p9mfz4zx8qnx1w7b7ilmsb8wyx737z9cqy9a0i57wj"))))
7961 `((upstream-name . "biomaRt")))
7962 (build-system r-build-system)
7964 `(("r-annotationdbi" ,r-annotationdbi)
7965 ("r-biocfilecache" ,r-biocfilecache)
7967 ("r-openssl" ,r-openssl)
7968 ("r-progress" ,r-progress)
7969 ("r-rappdirs" ,r-rappdirs)
7970 ("r-stringr" ,r-stringr)
7973 `(("r-knitr" ,r-knitr)))
7974 (home-page "https://bioconductor.org/packages/biomaRt")
7975 (synopsis "Interface to BioMart databases")
7977 "biomaRt provides an interface to a growing collection of databases
7978 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7979 package enables retrieval of large amounts of data in a uniform way without
7980 the need to know the underlying database schemas or write complex SQL queries.
7981 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7982 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7983 users direct access to a diverse set of data and enable a wide range of
7984 powerful online queries from gene annotation to database mining.")
7985 (license license:artistic2.0)))
7987 (define-public r-biocparallel
7989 (name "r-biocparallel")
7993 (uri (bioconductor-uri "BiocParallel" version))
7996 "1lsg5xm5j3ly5k60fidzhkgqc9jgscyfkqngjvd9qp6yfzvsb82g"))))
7998 `((upstream-name . "BiocParallel")))
7999 (build-system r-build-system)
8001 `(("r-futile-logger" ,r-futile-logger)
8005 `(("r-knitr" ,r-knitr)))
8006 (home-page "https://bioconductor.org/packages/BiocParallel")
8007 (synopsis "Bioconductor facilities for parallel evaluation")
8009 "This package provides modified versions and novel implementation of
8010 functions for parallel evaluation, tailored to use with Bioconductor
8012 (license (list license:gpl2+ license:gpl3+))))
8014 (define-public r-biostrings
8016 (name "r-biostrings")
8020 (uri (bioconductor-uri "Biostrings" version))
8023 "0imhfz7dg8b3l5qzipjranqqshdsg2x6zc49drlhn8sc7j40cvi8"))))
8025 `((upstream-name . "Biostrings")))
8026 (build-system r-build-system)
8028 `(("r-biocgenerics" ,r-biocgenerics)
8029 ("r-crayon" ,r-crayon)
8030 ("r-iranges" ,r-iranges)
8031 ("r-s4vectors" ,r-s4vectors)
8032 ("r-xvector" ,r-xvector)))
8033 (home-page "https://bioconductor.org/packages/Biostrings")
8034 (synopsis "String objects and algorithms for biological sequences")
8036 "This package provides memory efficient string containers, string
8037 matching algorithms, and other utilities, for fast manipulation of large
8038 biological sequences or sets of sequences.")
8039 (license license:artistic2.0)))
8041 (define-public r-rsamtools
8043 (name "r-rsamtools")
8047 (uri (bioconductor-uri "Rsamtools" version))
8050 "0z01z0s71f941k7sns46nyabps28c69d6jxx6sppjpc6h4vrw0vq"))))
8052 `((upstream-name . "Rsamtools")))
8053 (build-system r-build-system)
8056 (modify-phases %standard-phases
8057 (add-after 'unpack 'use-system-zlib
8059 (substitute* "DESCRIPTION"
8060 (("zlibbioc, ") ""))
8061 (substitute* "NAMESPACE"
8062 (("import\\(zlibbioc\\)") ""))
8067 `(("r-biocgenerics" ,r-biocgenerics)
8068 ("r-biocparallel" ,r-biocparallel)
8069 ("r-biostrings" ,r-biostrings)
8070 ("r-bitops" ,r-bitops)
8071 ("r-genomeinfodb" ,r-genomeinfodb)
8072 ("r-genomicranges" ,r-genomicranges)
8073 ("r-iranges" ,r-iranges)
8074 ("r-rhtslib" ,r-rhtslib)
8075 ("r-s4vectors" ,r-s4vectors)
8076 ("r-xvector" ,r-xvector)))
8077 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
8078 (synopsis "Interface to samtools, bcftools, and tabix")
8080 "This package provides an interface to the @code{samtools},
8081 @code{bcftools}, and @code{tabix} utilities for manipulating SAM (Sequence
8082 Alignment / Map), FASTA, binary variant call (BCF) and compressed indexed
8083 tab-delimited (tabix) files.")
8084 (license license:expat)))
8086 (define-public r-delayedarray
8088 (name "r-delayedarray")
8092 (uri (bioconductor-uri "DelayedArray" version))
8095 "1lz7a0rrlfv3w44n073mk8pw39z7lfs0njdxp5vpp0rdsmvdf1qk"))))
8097 `((upstream-name . "DelayedArray")))
8098 (build-system r-build-system)
8100 `(("r-biocgenerics" ,r-biocgenerics)
8101 ("r-s4vectors" ,r-s4vectors)
8102 ("r-iranges" ,r-iranges)
8103 ("r-matrix" ,r-matrix)
8104 ("r-matrixstats" ,r-matrixstats)))
8106 `(("r-knitr" ,r-knitr)))
8107 (home-page "https://bioconductor.org/packages/DelayedArray")
8108 (synopsis "Delayed operations on array-like objects")
8110 "Wrapping an array-like object (typically an on-disk object) in a
8111 @code{DelayedArray} object allows one to perform common array operations on it
8112 without loading the object in memory. In order to reduce memory usage and
8113 optimize performance, operations on the object are either delayed or executed
8114 using a block processing mechanism. Note that this also works on in-memory
8115 array-like objects like @code{DataFrame} objects (typically with Rle columns),
8116 @code{Matrix} objects, and ordinary arrays and data frames.")
8117 (license license:artistic2.0)))
8119 (define-public r-summarizedexperiment
8121 (name "r-summarizedexperiment")
8125 (uri (bioconductor-uri "SummarizedExperiment" version))
8128 "07rc79k5dp0dnf4dvsxif995aa9cgfkf13yf84qnwl64k9pf3c2c"))))
8130 `((upstream-name . "SummarizedExperiment")))
8131 (build-system r-build-system)
8133 `(("r-biobase" ,r-biobase)
8134 ("r-biocgenerics" ,r-biocgenerics)
8135 ("r-delayedarray" ,r-delayedarray)
8136 ("r-genomeinfodb" ,r-genomeinfodb)
8137 ("r-genomicranges" ,r-genomicranges)
8138 ("r-iranges" ,r-iranges)
8139 ("r-matrix" ,r-matrix)
8140 ("r-s4vectors" ,r-s4vectors)))
8142 `(("r-knitr" ,r-knitr)))
8143 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
8144 (synopsis "Container for representing genomic ranges by sample")
8146 "The SummarizedExperiment container contains one or more assays, each
8147 represented by a matrix-like object of numeric or other mode. The rows
8148 typically represent genomic ranges of interest and the columns represent
8150 (license license:artistic2.0)))
8152 (define-public r-genomicalignments
8154 (name "r-genomicalignments")
8158 (uri (bioconductor-uri "GenomicAlignments" version))
8161 "0v8k6d7frm5p48cmk4zik78cw9abz4inx0zhl4zrmmx31ifyvk8d"))))
8163 `((upstream-name . "GenomicAlignments")))
8164 (build-system r-build-system)
8166 `(("r-biocgenerics" ,r-biocgenerics)
8167 ("r-biocparallel" ,r-biocparallel)
8168 ("r-biostrings" ,r-biostrings)
8169 ("r-genomeinfodb" ,r-genomeinfodb)
8170 ("r-genomicranges" ,r-genomicranges)
8171 ("r-iranges" ,r-iranges)
8172 ("r-rsamtools" ,r-rsamtools)
8173 ("r-s4vectors" ,r-s4vectors)
8174 ("r-summarizedexperiment" ,r-summarizedexperiment)))
8175 (home-page "https://bioconductor.org/packages/GenomicAlignments")
8176 (synopsis "Representation and manipulation of short genomic alignments")
8178 "This package provides efficient containers for storing and manipulating
8179 short genomic alignments (typically obtained by aligning short reads to a
8180 reference genome). This includes read counting, computing the coverage,
8181 junction detection, and working with the nucleotide content of the
8183 (license license:artistic2.0)))
8185 (define-public r-rtracklayer
8187 (name "r-rtracklayer")
8191 (uri (bioconductor-uri "rtracklayer" version))
8194 "1zcgk92sidhy4y7ws9ms4nkkh2hnccfhfh53qgna0kma9jy4v5xf"))))
8195 (build-system r-build-system)
8198 (modify-phases %standard-phases
8199 (add-after 'unpack 'use-system-zlib
8201 (substitute* "DESCRIPTION"
8202 ((" zlibbioc,") ""))
8203 (substitute* "NAMESPACE"
8204 (("import\\(zlibbioc\\)") ""))
8207 `(("pkg-config" ,pkg-config)))
8211 `(("r-biocgenerics" ,r-biocgenerics)
8212 ("r-biostrings" ,r-biostrings)
8213 ("r-genomeinfodb" ,r-genomeinfodb)
8214 ("r-genomicalignments" ,r-genomicalignments)
8215 ("r-genomicranges" ,r-genomicranges)
8216 ("r-iranges" ,r-iranges)
8217 ("r-rcurl" ,r-rcurl)
8218 ("r-rsamtools" ,r-rsamtools)
8219 ("r-s4vectors" ,r-s4vectors)
8221 ("r-xvector" ,r-xvector)))
8222 (home-page "https://bioconductor.org/packages/rtracklayer")
8223 (synopsis "R interface to genome browsers and their annotation tracks")
8225 "rtracklayer is an extensible framework for interacting with multiple
8226 genome browsers (currently UCSC built-in) and manipulating annotation tracks
8227 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
8228 built-in). The user may export/import tracks to/from the supported browsers,
8229 as well as query and modify the browser state, such as the current viewport.")
8230 (license license:artistic2.0)))
8232 (define-public r-genomicfeatures
8234 (name "r-genomicfeatures")
8238 (uri (bioconductor-uri "GenomicFeatures" version))
8241 "09ffsflk2yhhj9ivm028y3qdkvv8idgxpm4il3y9rym7shc8b3f8"))))
8243 `((upstream-name . "GenomicFeatures")))
8244 (build-system r-build-system)
8246 `(("r-annotationdbi" ,r-annotationdbi)
8247 ("r-biobase" ,r-biobase)
8248 ("r-biocgenerics" ,r-biocgenerics)
8249 ("r-biomart" ,r-biomart)
8250 ("r-biostrings" ,r-biostrings)
8252 ("r-genomeinfodb" ,r-genomeinfodb)
8253 ("r-genomicranges" ,r-genomicranges)
8254 ("r-iranges" ,r-iranges)
8255 ("r-rcurl" ,r-rcurl)
8256 ("r-rsqlite" ,r-rsqlite)
8257 ("r-rtracklayer" ,r-rtracklayer)
8258 ("r-s4vectors" ,r-s4vectors)
8259 ("r-xvector" ,r-xvector)))
8261 `(("r-knitr" ,r-knitr)))
8262 (home-page "https://bioconductor.org/packages/GenomicFeatures")
8263 (synopsis "Tools for working with transcript centric annotations")
8265 "This package provides a set of tools and methods for making and
8266 manipulating transcript centric annotations. With these tools the user can
8267 easily download the genomic locations of the transcripts, exons and cds of a
8268 given organism, from either the UCSC Genome Browser or a BioMart
8269 database (more sources will be supported in the future). This information is
8270 then stored in a local database that keeps track of the relationship between
8271 transcripts, exons, cds and genes. Flexible methods are provided for
8272 extracting the desired features in a convenient format.")
8273 (license license:artistic2.0)))
8275 (define-public r-go-db
8281 (uri (string-append "https://www.bioconductor.org/packages/"
8282 "release/data/annotation/src/contrib/GO.db_"
8286 "0i3wcf5h3n0dawzc1hy0kv74f06j80c47n4p3g3fmrcxlhi3jpa5"))))
8288 `((upstream-name . "GO.db")))
8289 (build-system r-build-system)
8291 `(("r-annotationdbi" ,r-annotationdbi)))
8292 (home-page "https://bioconductor.org/packages/GO.db")
8293 (synopsis "Annotation maps describing the entire Gene Ontology")
8295 "The purpose of this GO.db annotation package is to provide detailed
8296 information about the latest version of the Gene Ontologies.")
8297 (license license:artistic2.0)))
8299 (define-public r-topgo
8305 (uri (bioconductor-uri "topGO" version))
8308 "13rhbvn27sj75fklf1cnjaazacx8yyjlhqlnbp5zk157q6y5cwdr"))))
8310 `((upstream-name . "topGO")))
8311 (build-system r-build-system)
8313 `(("r-annotationdbi" ,r-annotationdbi)
8315 ("r-biobase" ,r-biobase)
8316 ("r-biocgenerics" ,r-biocgenerics)
8317 ("r-go-db" ,r-go-db)
8318 ("r-graph" ,r-graph)
8319 ("r-lattice" ,r-lattice)
8320 ("r-matrixstats" ,r-matrixstats)
8321 ("r-sparsem" ,r-sparsem)))
8322 (home-page "https://bioconductor.org/packages/topGO")
8323 (synopsis "Enrichment analysis for gene ontology")
8325 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
8326 terms while accounting for the topology of the GO graph. Different test
8327 statistics and different methods for eliminating local similarities and
8328 dependencies between GO terms can be implemented and applied.")
8329 ;; Any version of the LGPL applies.
8330 (license license:lgpl2.1+)))
8332 (define-public r-bsgenome
8338 (uri (bioconductor-uri "BSgenome" version))
8341 "1jw8r1qm9fpg2s1cw2y4np243jjxm65j2xdy2785h8fc1b02msf6"))))
8343 `((upstream-name . "BSgenome")))
8344 (build-system r-build-system)
8346 `(("r-biocgenerics" ,r-biocgenerics)
8347 ("r-biostrings" ,r-biostrings)
8348 ("r-genomeinfodb" ,r-genomeinfodb)
8349 ("r-genomicranges" ,r-genomicranges)
8350 ("r-iranges" ,r-iranges)
8351 ("r-matrixstats" ,r-matrixstats)
8352 ("r-rsamtools" ,r-rsamtools)
8353 ("r-rtracklayer" ,r-rtracklayer)
8354 ("r-s4vectors" ,r-s4vectors)
8355 ("r-xvector" ,r-xvector)))
8356 (home-page "https://bioconductor.org/packages/BSgenome")
8357 (synopsis "Infrastructure for Biostrings-based genome data packages")
8359 "This package provides infrastructure shared by all Biostrings-based
8360 genome data packages and support for efficient SNP representation.")
8361 (license license:artistic2.0)))
8363 (define-public r-impute
8369 (uri (bioconductor-uri "impute" version))
8372 "161p6l1cp3wwdynkxwvg0yhrh6yv20brdlplw5w5mavn4hf1nm0h"))))
8374 `(("gfortran" ,gfortran)))
8375 (build-system r-build-system)
8376 (home-page "https://bioconductor.org/packages/impute")
8377 (synopsis "Imputation for microarray data")
8379 "This package provides a function to impute missing gene expression
8380 microarray data, using nearest neighbor averaging.")
8381 (license license:gpl2+)))
8383 (define-public r-seqpattern
8385 (name "r-seqpattern")
8389 (uri (bioconductor-uri "seqPattern" version))
8392 "0f1yvx2ri1557rzjx08q5bgml1cvkm8hjl8xn1qi4rjs64sy6mci"))))
8394 `((upstream-name . "seqPattern")))
8395 (build-system r-build-system)
8397 `(("r-biostrings" ,r-biostrings)
8398 ("r-genomicranges" ,r-genomicranges)
8399 ("r-iranges" ,r-iranges)
8400 ("r-kernsmooth" ,r-kernsmooth)
8401 ("r-plotrix" ,r-plotrix)))
8402 (home-page "https://bioconductor.org/packages/seqPattern")
8403 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
8405 "This package provides tools to visualize oligonucleotide patterns and
8406 sequence motif occurrences across a large set of sequences centred at a common
8407 reference point and sorted by a user defined feature.")
8408 (license license:gpl3+)))
8410 (define-public r-genomation
8412 (name "r-genomation")
8416 (uri (bioconductor-uri "genomation" version))
8419 "1cy8kqwddiha5jy6nda1al956i4wncbgjkrxwijdb08cmka2sfwh"))))
8420 (build-system r-build-system)
8422 `(("r-biostrings" ,r-biostrings)
8423 ("r-bsgenome" ,r-bsgenome)
8424 ("r-data-table" ,r-data-table)
8425 ("r-genomeinfodb" ,r-genomeinfodb)
8426 ("r-genomicalignments" ,r-genomicalignments)
8427 ("r-genomicranges" ,r-genomicranges)
8428 ("r-ggplot2" ,r-ggplot2)
8429 ("r-gridbase" ,r-gridbase)
8430 ("r-impute" ,r-impute)
8431 ("r-iranges" ,r-iranges)
8432 ("r-matrixstats" ,r-matrixstats)
8433 ("r-plotrix" ,r-plotrix)
8436 ("r-readr" ,r-readr)
8437 ("r-reshape2" ,r-reshape2)
8438 ("r-rsamtools" ,r-rsamtools)
8439 ("r-rtracklayer" ,r-rtracklayer)
8440 ("r-runit" ,r-runit)
8441 ("r-s4vectors" ,r-s4vectors)
8442 ("r-seqpattern" ,r-seqpattern)))
8444 `(("r-knitr" ,r-knitr)))
8445 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8446 (synopsis "Summary, annotation and visualization of genomic data")
8448 "This package provides a package for summary and annotation of genomic
8449 intervals. Users can visualize and quantify genomic intervals over
8450 pre-defined functional regions, such as promoters, exons, introns, etc. The
8451 genomic intervals represent regions with a defined chromosome position, which
8452 may be associated with a score, such as aligned reads from HT-seq experiments,
8453 TF binding sites, methylation scores, etc. The package can use any tabular
8454 genomic feature data as long as it has minimal information on the locations of
8455 genomic intervals. In addition, it can use BAM or BigWig files as input.")
8456 (license license:artistic2.0)))
8458 (define-public r-genomationdata
8460 (name "r-genomationdata")
8464 ;; We cannot use bioconductor-uri here because this tarball is
8465 ;; located under "data/annotation/" instead of "bioc/".
8466 (uri (string-append "https://bioconductor.org/packages/"
8467 "release/data/experiment/src/contrib/"
8468 "genomationData_" version ".tar.gz"))
8471 "10xyb8akjrhmak2i0mnv1agny2ipy364q9nlibyplpzc7vdb6bw7"))))
8472 (build-system r-build-system)
8473 ;; As this package provides little more than large data files, it doesn't
8474 ;; make sense to build substitutes.
8475 (arguments `(#:substitutable? #f))
8477 `(("r-knitr" ,r-knitr)))
8478 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8479 (synopsis "Experimental data for use with the genomation package")
8481 "This package contains experimental genetic data for use with the
8482 genomation package. Included are Chip Seq, Methylation and Cage data,
8483 downloaded from Encode.")
8484 (license license:gpl3+)))
8486 (define-public r-seqlogo
8493 (uri (bioconductor-uri "seqLogo" version))
8496 "09kkxir305fv8z2yyihvspkrzclxbw1cx5mvhfkrhl10rap6662j"))))
8497 (properties `((upstream-name . "seqLogo")))
8498 (build-system r-build-system)
8499 (home-page "https://bioconductor.org/packages/seqLogo")
8500 (synopsis "Sequence logos for DNA sequence alignments")
8502 "seqLogo takes the position weight matrix of a DNA sequence motif and
8503 plots the corresponding sequence logo as introduced by Schneider and
8505 (license license:lgpl2.0+)))
8507 (define-public r-motifrg
8514 (uri (bioconductor-uri "motifRG" version))
8517 "1ml6zyzlk8yjbnfhga2qnw8nl43rankvka0kc1yljxr2b66aqbhn"))))
8518 (properties `((upstream-name . "motifRG")))
8519 (build-system r-build-system)
8521 `(("r-biostrings" ,r-biostrings)
8522 ("r-bsgenome" ,r-bsgenome)
8523 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8524 ("r-iranges" ,r-iranges)
8525 ("r-seqlogo" ,r-seqlogo)
8526 ("r-xvector" ,r-xvector)))
8527 (home-page "https://bioconductor.org/packages/motifRG")
8528 (synopsis "Discover motifs in high throughput sequencing data")
8530 "This package provides tools for discriminative motif discovery in high
8531 throughput genetic sequencing data sets using regression methods.")
8532 (license license:artistic2.0)))
8534 (define-public r-qtl
8541 (uri (string-append "mirror://cran/src/contrib/qtl_"
8545 "0rbwcnvyy96gq1dsgpxx03pv423qya26h6ws5y0blj3blfdmj83a"))))
8546 (build-system r-build-system)
8547 (home-page "https://rqtl.org/")
8548 (synopsis "R package for analyzing QTL experiments in genetics")
8549 (description "R/qtl is an extension library for the R statistics
8550 system. It is used to analyze experimental crosses for identifying
8551 genes contributing to variation in quantitative traits (so-called
8552 quantitative trait loci, QTLs).
8554 Using a hidden Markov model, R/qtl estimates genetic maps, to
8555 identify genotyping errors, and to perform single-QTL and two-QTL,
8556 two-dimensional genome scans.")
8557 (license license:gpl3)))
8559 (define-public r-qtl2
8565 ;; Not yet available in cran.
8567 (url "https://github.com/rqtl/qtl2.git")
8569 (file-name (git-file-name name version))
8571 (base32 "0l1asr28q25jzbwrbg5490962sg3y4sjrd0qf09p78ws1aq8vfs0"))))
8572 (build-system r-build-system)
8574 `(("r-data-table" ,r-data-table)
8575 ("r-jsonlite" ,r-jsonlite)
8577 ("r-rcppeigen" ,r-rcppeigen)
8578 ("r-rsqlite" ,r-rsqlite)
8579 ("r-yaml" ,r-yaml)))
8580 (home-page "https://kbroman.org/qtl2/")
8582 "QTL analysis software for high-dimensional data and complex cross designs")
8584 "R/qtl2 (aka qtl2) is a reimplementation of the QTL analysis software
8585 R/qtl, to better handle high-dimensional data and complex cross designs.")
8586 (license license:gpl3)))
8588 (define-public r-zlibbioc
8594 (uri (bioconductor-uri "zlibbioc" version))
8597 "0j1l052jb2cwc1nifxzwknc9csagf4f2d092zs0i95dz0rma89l0"))))
8599 `((upstream-name . "zlibbioc")))
8600 (build-system r-build-system)
8601 (home-page "https://bioconductor.org/packages/zlibbioc")
8602 (synopsis "Provider for zlib-1.2.5 to R packages")
8603 (description "This package uses the source code of zlib-1.2.5 to create
8604 libraries for systems that do not have these available via other means.")
8605 (license license:artistic2.0)))
8607 (define-public r-r4rna
8614 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8618 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8619 (build-system r-build-system)
8621 `(("r-optparse" ,r-optparse)
8622 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8623 (home-page "https://www.e-rna.org/r-chie/index.cgi")
8624 (synopsis "Analysis framework for RNA secondary structure")
8626 "The R4RNA package aims to be a general framework for the analysis of RNA
8627 secondary structure and comparative analysis in R.")
8628 (license license:gpl3+)))
8630 (define-public r-rhtslib
8637 (uri (bioconductor-uri "Rhtslib" version))
8640 "186r7icrkzrni1c4n33ip7dlsfgys7hnqf0simvxrpl3yhh3ygdi"))))
8641 (properties `((upstream-name . "Rhtslib")))
8642 (build-system r-build-system)
8643 ;; Without this a temporary directory ends up in the Rhtslib.so binary,
8644 ;; which makes R abort the build.
8645 (arguments '(#:configure-flags '("--no-staged-install")))
8648 ("r-zlibbioc" ,r-zlibbioc)))
8652 `(("pkg-config" ,pkg-config)
8653 ("r-knitr" ,r-knitr)))
8654 (home-page "https://github.com/nhayden/Rhtslib")
8655 (synopsis "High-throughput sequencing library as an R package")
8657 "This package provides the HTSlib C library for high-throughput
8658 nucleotide sequence analysis. The package is primarily useful to developers
8659 of other R packages who wish to make use of HTSlib.")
8660 (license license:lgpl2.0+)))
8662 (define-public r-bamsignals
8664 (name "r-bamsignals")
8669 (uri (bioconductor-uri "bamsignals" version))
8672 "0p858xxfv79yc8b3lq58zl9f00irvbn3czsd8wdi5040xg42m402"))))
8673 (build-system r-build-system)
8675 `(("r-biocgenerics" ,r-biocgenerics)
8676 ("r-genomicranges" ,r-genomicranges)
8677 ("r-iranges" ,r-iranges)
8679 ("r-rhtslib" ,r-rhtslib)
8680 ("r-zlibbioc" ,r-zlibbioc)))
8684 `(("r-knitr" ,r-knitr)))
8685 (home-page "https://bioconductor.org/packages/bamsignals")
8686 (synopsis "Extract read count signals from bam files")
8688 "This package efficiently obtains count vectors from indexed bam
8689 files. It counts the number of nucleotide sequence reads in given genomic
8690 ranges and it computes reads profiles and coverage profiles. It also handles
8692 (license license:gpl2+)))
8694 (define-public r-rcas
8700 (uri (bioconductor-uri "RCAS" version))
8703 "0f812pgv3ys1zv4n9sqkgm01hj4cdd0i0h85dqbhkwd94zl6cavl"))))
8704 (properties `((upstream-name . "RCAS")))
8705 (build-system r-build-system)
8707 `(("r-biocgenerics" ,r-biocgenerics)
8708 ("r-biostrings" ,r-biostrings)
8709 ("r-bsgenome" ,r-bsgenome)
8710 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8711 ("r-cowplot" ,r-cowplot)
8712 ("r-data-table" ,r-data-table)
8714 ("r-genomation" ,r-genomation)
8715 ("r-genomeinfodb" ,r-genomeinfodb)
8716 ("r-genomicfeatures" ,r-genomicfeatures)
8717 ("r-genomicranges" ,r-genomicranges)
8718 ("r-ggplot2" ,r-ggplot2)
8719 ("r-ggseqlogo" ,r-ggseqlogo)
8720 ("r-gprofiler2" ,r-gprofiler2)
8721 ("r-iranges" ,r-iranges)
8722 ("r-pbapply" ,r-pbapply)
8723 ("r-pheatmap" ,r-pheatmap)
8724 ("r-plotly" ,r-plotly)
8725 ("r-plotrix" ,r-plotrix)
8726 ("r-proxy" ,r-proxy)
8727 ("r-ranger" ,r-ranger)
8728 ("r-rsqlite" ,r-rsqlite)
8729 ("r-rtracklayer" ,r-rtracklayer)
8730 ("r-rmarkdown" ,r-rmarkdown)
8731 ("r-s4vectors" ,r-s4vectors)
8732 ("pandoc" ,ghc-pandoc)))
8734 `(("r-knitr" ,r-knitr)))
8735 (synopsis "RNA-centric annotation system")
8737 "RCAS aims to be a standalone RNA-centric annotation system that provides
8738 intuitive reports and publication-ready graphics. This package provides the R
8739 library implementing most of the pipeline's features.")
8740 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8741 (license license:artistic2.0)))
8743 (define-public rcas-web
8750 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8751 "releases/download/v" version
8752 "/rcas-web-" version ".tar.gz"))
8755 "0wq951aj45gqki1bickg876i993lmawkp8x24agg264br5x716db"))))
8756 (build-system gnu-build-system)
8759 (modify-phases %standard-phases
8760 (add-before 'configure 'find-RCAS
8761 ;; The configure script can't find non-1.3.x versions of RCAS because
8762 ;; its R expression ‘1.10.1 >= 1.3.4’ evaluates to false.
8764 (substitute* "configure"
8765 (("1\\.3\\.4") "0.0.0"))
8767 (add-after 'install 'wrap-executable
8768 (lambda* (#:key inputs outputs #:allow-other-keys)
8769 (let* ((out (assoc-ref outputs "out"))
8770 (json (assoc-ref inputs "guile-json"))
8771 (redis (assoc-ref inputs "guile-redis"))
8772 (path (string-append
8773 json "/share/guile/site/2.2:"
8774 redis "/share/guile/site/2.2")))
8775 (wrap-program (string-append out "/bin/rcas-web")
8776 `("GUILE_LOAD_PATH" ":" = (,path))
8777 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8778 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8781 `(("r-minimal" ,r-minimal)
8783 ("guile" ,guile-2.2)
8784 ("guile-json" ,guile-json-1)
8785 ("guile-redis" ,guile2.2-redis)))
8787 `(("pkg-config" ,pkg-config)))
8788 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8789 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8790 (description "This package provides a simple web interface for the
8791 @dfn{RNA-centric annotation system} (RCAS).")
8792 (license license:agpl3+)))
8794 (define-public r-mutationalpatterns
8796 (name "r-mutationalpatterns")
8801 (uri (bioconductor-uri "MutationalPatterns" version))
8804 "02lyjiabyhmifycksvpcx29a0pb7z9xjw0hgg8n0sd0dy3afqhcm"))))
8805 (build-system r-build-system)
8807 `(("r-biocgenerics" ,r-biocgenerics)
8808 ("r-biostrings" ,r-biostrings)
8809 ;; These two packages are suggested packages
8810 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8811 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8812 ("r-genomicranges" ,r-genomicranges)
8813 ("r-genomeinfodb" ,r-genomeinfodb)
8814 ("r-ggplot2" ,r-ggplot2)
8815 ("r-iranges" ,r-iranges)
8818 ("r-pracma" ,r-pracma)
8819 ("r-reshape2" ,r-reshape2)
8820 ("r-cowplot" ,r-cowplot)
8821 ("r-ggdendro" ,r-ggdendro)
8822 ("r-s4vectors" ,r-s4vectors)
8823 ("r-summarizedexperiment" ,r-summarizedexperiment)
8824 ("r-variantannotation" ,r-variantannotation)))
8825 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8826 (synopsis "Extract and visualize mutational patterns in genomic data")
8827 (description "This package provides an extensive toolset for the
8828 characterization and visualization of a wide range of mutational patterns
8829 in SNV base substitution data.")
8830 (license license:expat)))
8832 (define-public r-chipkernels
8833 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8836 (name "r-chipkernels")
8837 (version (string-append "1.1-" revision "." (string-take commit 9)))
8842 (url "https://github.com/ManuSetty/ChIPKernels.git")
8844 (file-name (string-append name "-" version))
8847 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8848 (build-system r-build-system)
8850 `(("r-iranges" ,r-iranges)
8851 ("r-xvector" ,r-xvector)
8852 ("r-biostrings" ,r-biostrings)
8853 ("r-bsgenome" ,r-bsgenome)
8854 ("r-gtools" ,r-gtools)
8855 ("r-genomicranges" ,r-genomicranges)
8856 ("r-sfsmisc" ,r-sfsmisc)
8857 ("r-kernlab" ,r-kernlab)
8858 ("r-s4vectors" ,r-s4vectors)
8859 ("r-biocgenerics" ,r-biocgenerics)))
8860 (home-page "https://github.com/ManuSetty/ChIPKernels")
8861 (synopsis "Build string kernels for DNA Sequence analysis")
8862 (description "ChIPKernels is an R package for building different string
8863 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8864 must be built and this dictionary can be used for determining kernels for DNA
8866 (license license:gpl2+))))
8868 (define-public r-seqgl
8876 (url "https://github.com/ManuSetty/SeqGL.git")
8878 (file-name (git-file-name name version))
8881 "1r6ywvhxl3ffv48lgj7sbd582mcc6dha3ksgc2qjlvjrnkbj3799"))))
8882 (build-system r-build-system)
8884 `(("r-biostrings" ,r-biostrings)
8885 ("r-chipkernels" ,r-chipkernels)
8886 ("r-genomicranges" ,r-genomicranges)
8887 ("r-spams" ,r-spams)
8888 ("r-wgcna" ,r-wgcna)
8889 ("r-fastcluster" ,r-fastcluster)))
8890 (home-page "https://github.com/ManuSetty/SeqGL")
8891 (synopsis "Group lasso for Dnase/ChIP-seq data")
8892 (description "SeqGL is a group lasso based algorithm to extract
8893 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8894 This package presents a method which uses group lasso to discriminate between
8895 bound and non bound genomic regions to accurately identify transcription
8896 factors bound at the specific regions.")
8897 (license license:gpl2+)))
8899 (define-public r-tximport
8905 (uri (bioconductor-uri "tximport" version))
8908 "1x9959lkjl2h869rgd1b30q1idxzjkr1fyqbpndqk3kbi4q2gr40"))))
8909 (build-system r-build-system)
8911 `(("r-knitr" ,r-knitr)))
8912 (home-page "https://bioconductor.org/packages/tximport")
8913 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8915 "This package provides tools to import transcript-level abundance,
8916 estimated counts and transcript lengths, and to summarize them into matrices
8917 for use with downstream gene-level analysis packages. Average transcript
8918 length, weighted by sample-specific transcript abundance estimates, is
8919 provided as a matrix which can be used as an offset for different expression
8920 of gene-level counts.")
8921 (license license:gpl2+)))
8923 (define-public r-rhdf5
8929 (uri (bioconductor-uri "rhdf5" version))
8932 "097znwl95y2vd6asyqxs62m7binwxqmna7ss0302yl3b0s72skcy"))))
8933 (build-system r-build-system)
8935 `(("r-rhdf5lib" ,r-rhdf5lib)))
8939 `(("r-knitr" ,r-knitr)))
8940 (home-page "https://bioconductor.org/packages/rhdf5")
8941 (synopsis "HDF5 interface to R")
8943 "This R/Bioconductor package provides an interface between HDF5 and R.
8944 HDF5's main features are the ability to store and access very large and/or
8945 complex datasets and a wide variety of metadata on mass storage (disk) through
8946 a completely portable file format. The rhdf5 package is thus suited for the
8947 exchange of large and/or complex datasets between R and other software
8948 package, and for letting R applications work on datasets that are larger than
8949 the available RAM.")
8950 (license license:artistic2.0)))
8952 (define-public r-annotationfilter
8954 (name "r-annotationfilter")
8958 (uri (bioconductor-uri "AnnotationFilter" version))
8961 "18kh1xrhpwb48s1qj4f1v8af3jmw49pnbp5afi2myn9894hxg0cs"))))
8963 `((upstream-name . "AnnotationFilter")))
8964 (build-system r-build-system)
8966 `(("r-genomicranges" ,r-genomicranges)
8967 ("r-lazyeval" ,r-lazyeval)))
8969 `(("r-knitr" ,r-knitr)))
8970 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8971 (synopsis "Facilities for filtering Bioconductor annotation resources")
8973 "This package provides classes and other infrastructure to implement
8974 filters for manipulating Bioconductor annotation resources. The filters are
8975 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8976 (license license:artistic2.0)))
8978 (define-public emboss
8984 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8985 (version-major+minor version) ".0/"
8986 "EMBOSS-" version ".tar.gz"))
8989 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8990 (build-system gnu-build-system)
8993 (list (string-append "--with-hpdf="
8994 (assoc-ref %build-inputs "libharu")))
8996 (modify-phases %standard-phases
8997 (add-after 'unpack 'fix-checks
8999 ;; The PNGDRIVER tests check for the presence of libgd, libpng
9000 ;; and zlib, but assume that they are all found at the same
9002 (substitute* "configure.in"
9003 (("CHECK_PNGDRIVER")
9004 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
9005 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
9006 AM_CONDITIONAL(AMPNG, true)"))
9008 (add-after 'fix-checks 'disable-update-check
9010 ;; At build time there is no connection to the Internet, so
9011 ;; looking for updates will not work.
9012 (substitute* "Makefile.am"
9013 (("\\$\\(bindir\\)/embossupdate") ""))
9015 (add-after 'disable-update-check 'autogen
9016 (lambda _ (invoke "autoreconf" "-vif") #t)))))
9022 ("libharu" ,libharu)
9025 `(("autoconf" ,autoconf)
9026 ("automake" ,automake)
9027 ("libtool" ,libtool)
9028 ("pkg-config" ,pkg-config)))
9029 (home-page "http://emboss.sourceforge.net")
9030 (synopsis "Molecular biology analysis suite")
9031 (description "EMBOSS is the \"European Molecular Biology Open Software
9032 Suite\". EMBOSS is an analysis package specially developed for the needs of
9033 the molecular biology (e.g. EMBnet) user community. The software
9034 automatically copes with data in a variety of formats and even allows
9035 transparent retrieval of sequence data from the web. It also provides a
9036 number of libraries for the development of software in the field of molecular
9037 biology. EMBOSS also integrates a range of currently available packages and
9038 tools for sequence analysis into a seamless whole.")
9039 (license license:gpl2+)))
9042 (let ((revision "1")
9043 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
9046 ;; The version is 2.13.0 even though no release archives have been
9047 ;; published as yet.
9048 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
9052 (url "https://github.com/arq5x/bits.git")
9054 (file-name (string-append name "-" version "-checkout"))
9057 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
9058 (build-system gnu-build-system)
9060 `(#:tests? #f ;no tests included
9062 (modify-phases %standard-phases
9064 (add-after 'unpack 'remove-cuda
9066 (substitute* "Makefile"
9068 (("(bits_test_intersections) \\\\" _ match) match))
9071 (lambda* (#:key outputs #:allow-other-keys)
9073 "bin" (string-append (assoc-ref outputs "out") "/bin"))
9078 (home-page "https://github.com/arq5x/bits")
9079 (synopsis "Implementation of binary interval search algorithm")
9080 (description "This package provides an implementation of the
9081 BITS (Binary Interval Search) algorithm, an approach to interval set
9082 intersection. It is especially suited for the comparison of diverse genomic
9083 datasets and the exploration of large datasets of genome
9084 intervals (e.g. genes, sequence alignments).")
9085 (license license:gpl2))))
9087 (define-public piranha
9088 ;; There is no release tarball for the latest version. The latest commit is
9089 ;; older than one year at the time of this writing.
9090 (let ((revision "1")
9091 (commit "0466d364b71117d01e4471b74c514436cc281233"))
9094 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
9098 (url "https://github.com/smithlabcode/piranha.git")
9100 (file-name (git-file-name name version))
9103 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
9104 (build-system gnu-build-system)
9106 `(#:test-target "test"
9108 (modify-phases %standard-phases
9109 (add-after 'unpack 'copy-smithlab-cpp
9110 (lambda* (#:key inputs #:allow-other-keys)
9111 (for-each (lambda (file)
9112 (install-file file "./src/smithlab_cpp/"))
9113 (find-files (assoc-ref inputs "smithlab-cpp")))
9115 (add-after 'install 'install-to-store
9116 (lambda* (#:key outputs #:allow-other-keys)
9117 (let* ((out (assoc-ref outputs "out"))
9118 (bin (string-append out "/bin")))
9119 (for-each (lambda (file)
9120 (install-file file bin))
9121 (find-files "bin" ".*")))
9124 (list (string-append "--with-bam_tools_headers="
9125 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
9126 (string-append "--with-bam_tools_library="
9127 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
9129 `(("bamtools" ,bamtools)
9130 ("samtools" ,samtools-0.1)
9133 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
9137 (url "https://github.com/smithlabcode/smithlab_cpp.git")
9139 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
9142 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
9144 `(("python" ,python-2)))
9145 (home-page "https://github.com/smithlabcode/piranha")
9146 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
9148 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
9149 RIP-seq experiments. It takes input in BED or BAM format and identifies
9150 regions of statistically significant read enrichment. Additional covariates
9151 may optionally be provided to further inform the peak-calling process.")
9152 (license license:gpl3+))))
9160 (uri (pypi-uri "PePr" version))
9163 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
9164 (build-system python-build-system)
9166 `(#:python ,python-2 ; python2 only
9167 #:tests? #f)) ; no tests included
9169 `(("python2-numpy" ,python2-numpy)
9170 ("python2-scipy" ,python2-scipy)
9171 ("python2-pysam" ,python2-pysam)))
9172 (home-page "https://github.com/shawnzhangyx/PePr")
9173 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
9175 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
9176 that is primarily designed for data with biological replicates. It uses a
9177 negative binomial distribution to model the read counts among the samples in
9178 the same group, and look for consistent differences between ChIP and control
9179 group or two ChIP groups run under different conditions.")
9180 (license license:gpl3+)))
9182 (define-public filevercmp
9183 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
9186 (version (string-append "0-1." (string-take commit 7)))
9190 (url "https://github.com/ekg/filevercmp.git")
9192 (file-name (git-file-name name commit))
9195 "1j9vxsy0y050v59h0q1d6501fcw1kjvj0d18l1xk2zyg0jzj247c"))))
9196 (build-system gnu-build-system)
9198 `(#:tests? #f ; There are no tests to run.
9200 (modify-phases %standard-phases
9201 (delete 'configure) ; There is no configure phase.
9203 (lambda* (#:key outputs #:allow-other-keys)
9204 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
9205 (install-file "filevercmp" bin)
9207 (home-page "https://github.com/ekg/filevercmp")
9208 (synopsis "This program compares version strings")
9209 (description "This program compares version strings. It intends to be a
9210 replacement for strverscmp.")
9211 (license license:gpl3+))))
9213 (define-public multiqc
9220 (uri (pypi-uri "multiqc" version))
9223 "02iihfl0w0hpnr4pa0sbd1y9qxrg3ycyhjp5lidkcrqh1lmzs3zy"))))
9224 (build-system python-build-system)
9226 `(("python-jinja2" ,python-jinja2)
9227 ("python-simplejson" ,python-simplejson)
9228 ("python-pyyaml" ,python-pyyaml)
9229 ("python-click" ,python-click)
9230 ("python-spectra" ,python-spectra)
9231 ("python-requests" ,python-requests)
9232 ("python-markdown" ,python-markdown)
9233 ("python-lzstring" ,python-lzstring)
9234 ("python-matplotlib" ,python-matplotlib)
9235 ("python-numpy" ,python-numpy)
9236 ;; MultQC checks for the presence of nose at runtime.
9237 ("python-nose" ,python-nose)))
9240 (modify-phases %standard-phases
9241 (add-after 'unpack 'relax-requirements
9243 (substitute* "setup.py"
9244 ;; MultiQC 1.5 ‘requires’ a version of python-matplotlib older
9245 ;; than the one in Guix, but should work fine with 2.2.2.
9246 ;; See <https://github.com/ewels/MultiQC/issues/725> and
9247 ;; <https://github.com/ewels/MultiQC/issues/732> for details.
9248 (("['\"]matplotlib.*?['\"]")
9251 (home-page "https://multiqc.info")
9252 (synopsis "Aggregate bioinformatics analysis reports")
9254 "MultiQC is a tool to aggregate bioinformatics results across many
9255 samples into a single report. It contains modules for a large number of
9256 common bioinformatics tools.")
9257 (license license:gpl3+)))
9259 (define-public variant-tools
9261 (name "variant-tools")
9267 (url "https://github.com/vatlab/varianttools.git")
9268 ;; There is no tag corresponding to version 3.1.2
9269 (commit "813ae4a90d25b69abc8a40f4f70441fe09015249")))
9270 (file-name (git-file-name name version))
9273 "12ibdmksj7icyqhks4xyvd61bygk4pjmxn618kp6vgk1af01y34g"))))
9274 (build-system python-build-system)
9277 ("c-blosc" ,c-blosc)
9280 ("hdf5-blosc" ,hdf5-blosc)
9281 ("python-cython" ,python-cython)
9284 `(("python-numpy" ,python-numpy)
9285 ("python-pycurl" ,python-pycurl)
9286 ("python-pyzmq" ,python-pyzmq)
9287 ("python-scipy" ,python-scipy)
9288 ("python-tables" ,python-tables)))
9289 (home-page "https://vatlab.github.io/vat-docs/")
9290 (synopsis "Analyze genetic variants from Next-Gen sequencing studies")
9292 "Variant tools is a tool for the manipulation, annotation,
9293 selection, simulation, and analysis of variants in the context of next-gen
9294 sequencing analysis. Unlike some other tools used for next-gen sequencing
9295 analysis, variant tools is project based and provides a whole set of tools to
9296 manipulate and analyze genetic variants.")
9297 (license license:gpl3+)))
9299 (define-public r-chipseq
9306 (uri (bioconductor-uri "chipseq" version))
9309 "0lh859s0aq73vac1phcgagf6n000qgq2xsk0bmfr61n5swifml2a"))))
9310 (build-system r-build-system)
9312 `(("r-biocgenerics" ,r-biocgenerics)
9313 ("r-genomicranges" ,r-genomicranges)
9314 ("r-iranges" ,r-iranges)
9315 ("r-lattice" ,r-lattice)
9316 ("r-s4vectors" ,r-s4vectors)
9317 ("r-shortread" ,r-shortread)))
9318 (home-page "https://bioconductor.org/packages/chipseq")
9319 (synopsis "Package for analyzing ChIPseq data")
9321 "This package provides tools for processing short read data from ChIPseq
9323 (license license:artistic2.0)))
9325 (define-public r-copyhelper
9327 (name "r-copyhelper")
9332 (uri (string-append "https://bioconductor.org/packages/release/"
9333 "data/experiment/src/contrib/CopyhelpeR_"
9337 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
9338 (properties `((upstream-name . "CopyhelpeR")))
9339 (build-system r-build-system)
9340 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
9341 (synopsis "Helper files for CopywriteR")
9343 "This package contains the helper files that are required to run the
9344 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
9345 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
9346 mm10. In addition, it contains a blacklist filter to remove regions that
9347 display copy number variation. Files are stored as GRanges objects from the
9348 GenomicRanges Bioconductor package.")
9349 (license license:gpl2)))
9351 (define-public r-copywriter
9353 (name "r-copywriter")
9358 (uri (bioconductor-uri "CopywriteR" version))
9361 "0c36wpv0rygkbqpf3dwh5xmc3lr7p8lrdzsq2fbbpw04skl6i7m2"))))
9362 (properties `((upstream-name . "CopywriteR")))
9363 (build-system r-build-system)
9365 `(("r-biocparallel" ,r-biocparallel)
9366 ("r-chipseq" ,r-chipseq)
9367 ("r-copyhelper" ,r-copyhelper)
9368 ("r-data-table" ,r-data-table)
9369 ("r-dnacopy" ,r-dnacopy)
9370 ("r-futile-logger" ,r-futile-logger)
9371 ("r-genomeinfodb" ,r-genomeinfodb)
9372 ("r-genomicalignments" ,r-genomicalignments)
9373 ("r-genomicranges" ,r-genomicranges)
9374 ("r-gtools" ,r-gtools)
9375 ("r-iranges" ,r-iranges)
9376 ("r-matrixstats" ,r-matrixstats)
9377 ("r-rsamtools" ,r-rsamtools)
9378 ("r-s4vectors" ,r-s4vectors)))
9379 (home-page "https://github.com/PeeperLab/CopywriteR")
9380 (synopsis "Copy number information from targeted sequencing")
9382 "CopywriteR extracts DNA copy number information from targeted sequencing
9383 by utilizing off-target reads. It allows for extracting uniformly distributed
9384 copy number information, can be used without reference, and can be applied to
9385 sequencing data obtained from various techniques including chromatin
9386 immunoprecipitation and target enrichment on small gene panels. Thereby,
9387 CopywriteR constitutes a widely applicable alternative to available copy
9388 number detection tools.")
9389 (license license:gpl2)))
9391 (define-public r-methylkit
9393 (name "r-methylkit")
9397 (uri (bioconductor-uri "methylKit" version))
9400 "1qr13d2712ypbn96ijic2z5adr5dsd61kzscx7shw6vyj360rlm5"))))
9401 (properties `((upstream-name . "methylKit")))
9402 (build-system r-build-system)
9404 `(("r-data-table" ,r-data-table)
9405 ("r-emdbook" ,r-emdbook)
9406 ("r-fastseg" ,r-fastseg)
9407 ("r-genomeinfodb" ,r-genomeinfodb)
9408 ("r-genomicranges" ,r-genomicranges)
9409 ("r-gtools" ,r-gtools)
9410 ("r-iranges" ,r-iranges)
9411 ("r-kernsmooth" ,r-kernsmooth)
9412 ("r-limma" ,r-limma)
9413 ("r-mclust" ,r-mclust)
9415 ("r-qvalue" ,r-qvalue)
9416 ("r-r-utils" ,r-r-utils)
9418 ("r-rhtslib" ,r-rhtslib)
9419 ("r-rsamtools" ,r-rsamtools)
9420 ("r-rtracklayer" ,r-rtracklayer)
9421 ("r-s4vectors" ,r-s4vectors)
9422 ("r-zlibbioc" ,r-zlibbioc)))
9424 `(("r-knitr" ,r-knitr))) ; for vignettes
9427 (home-page "https://github.com/al2na/methylKit")
9429 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9431 "MethylKit is an R package for DNA methylation analysis and annotation
9432 from high-throughput bisulfite sequencing. The package is designed to deal
9433 with sequencing data from @dfn{Reduced representation bisulfite
9434 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9435 genome bisulfite sequencing. It also has functions to analyze base-pair
9436 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9438 (license license:artistic2.0)))
9440 (define-public r-sva
9447 (uri (bioconductor-uri "sva" version))
9450 "0xa1lm0k1a6nig90mab6xh4gln88rbs5l1cdr6ik6agg7jhs7ji4"))))
9451 (build-system r-build-system)
9453 `(("r-edger" ,r-edger)
9454 ("r-genefilter" ,r-genefilter)
9456 ("r-biocparallel" ,r-biocparallel)
9457 ("r-matrixstats" ,r-matrixstats)
9458 ("r-limma" ,r-limma)))
9459 (home-page "https://bioconductor.org/packages/sva")
9460 (synopsis "Surrogate variable analysis")
9462 "This package contains functions for removing batch effects and other
9463 unwanted variation in high-throughput experiment. It also contains functions
9464 for identifying and building surrogate variables for high-dimensional data
9465 sets. Surrogate variables are covariates constructed directly from
9466 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9467 imaging data that can be used in subsequent analyses to adjust for unknown,
9468 unmodeled, or latent sources of noise.")
9469 (license license:artistic2.0)))
9471 (define-public r-seqminer
9478 (uri (cran-uri "seqminer" version))
9481 "00jzj8mwb0zaiwlifd41b26mrq9mzigj18nc29dydi0r42hxg16i"))))
9482 (build-system r-build-system)
9485 (home-page "http://seqminer.genomic.codes")
9486 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9488 "This package provides tools to integrate nucleotide sequencing
9489 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9490 ;; Any version of the GPL is acceptable
9491 (license (list license:gpl2+ license:gpl3+))))
9493 (define-public r-raremetals2
9495 (name "r-raremetals2")
9500 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9501 "b/b7/RareMETALS2_" version ".tar.gz"))
9504 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9505 (properties `((upstream-name . "RareMETALS2")))
9506 (build-system r-build-system)
9508 `(("r-seqminer" ,r-seqminer)
9509 ("r-mvtnorm" ,r-mvtnorm)
9511 ("r-compquadform" ,r-compquadform)
9512 ("r-getopt" ,r-getopt)))
9513 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9514 (synopsis "Analyze gene-level association tests for binary trait")
9516 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9517 It was designed to meta-analyze gene-level association tests for binary trait.
9518 While rareMETALS offers a near-complete solution for meta-analysis of
9519 gene-level tests for quantitative trait, it does not offer the optimal
9520 solution for binary trait. The package rareMETALS2 offers improved features
9521 for analyzing gene-level association tests in meta-analyses for binary
9523 (license license:gpl3)))
9525 (define-public r-maldiquant
9527 (name "r-maldiquant")
9532 (uri (cran-uri "MALDIquant" version))
9535 "0b7kdz3x4sdq413h1q09l1qhcvdnnwv6fqsqwllks1cd3xy34c57"))))
9536 (properties `((upstream-name . "MALDIquant")))
9537 (build-system r-build-system)
9538 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9539 (synopsis "Quantitative analysis of mass spectrometry data")
9541 "This package provides a complete analysis pipeline for matrix-assisted
9542 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9543 two-dimensional mass spectrometry data. In addition to commonly used plotting
9544 and processing methods it includes distinctive features, namely baseline
9545 subtraction methods such as morphological filters (TopHat) or the
9546 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9547 alignment using warping functions, handling of replicated measurements as well
9548 as allowing spectra with different resolutions.")
9549 (license license:gpl3+)))
9551 (define-public r-protgenerics
9553 (name "r-protgenerics")
9558 (uri (bioconductor-uri "ProtGenerics" version))
9561 "14xzdh7vxss8vmrw91hcwrszdn3ikm71mah8875b2lkrkrfzbl73"))))
9562 (properties `((upstream-name . "ProtGenerics")))
9563 (build-system r-build-system)
9564 (home-page "https://github.com/lgatto/ProtGenerics")
9565 (synopsis "S4 generic functions for proteomics infrastructure")
9567 "This package provides S4 generic functions needed by Bioconductor
9568 proteomics packages.")
9569 (license license:artistic2.0)))
9571 (define-public r-mzr
9578 (uri (bioconductor-uri "mzR" version))
9581 "1cwd7phlc5jbx6r6cznyfbdpvcin5fvsaasbbi65zn0s92a80r13"))
9582 (modules '((guix build utils)))
9585 (delete-file-recursively "src/boost")
9587 (properties `((upstream-name . "mzR")))
9588 (build-system r-build-system)
9591 (modify-phases %standard-phases
9592 (add-after 'unpack 'use-system-boost
9594 (substitute* "src/Makevars"
9595 (("\\./boost/libs.*") "")
9596 (("ARCH_OBJS=" line)
9598 "\nARCH_LIBS=-lboost_system -lboost_regex \
9599 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9602 `(;; Our default boost package won't work here, unfortunately, even with
9603 ;; mzR version 2.20.0.
9604 ("boost" ,boost-for-mysql) ; use this instead of the bundled boost sources
9607 `(("r-biobase" ,r-biobase)
9608 ("r-biocgenerics" ,r-biocgenerics)
9609 ("r-ncdf4" ,r-ncdf4)
9610 ("r-protgenerics" ,r-protgenerics)
9612 ("r-rhdf5lib" ,r-rhdf5lib)
9613 ("r-zlibbioc" ,r-zlibbioc)))
9614 (home-page "https://github.com/sneumann/mzR/")
9615 (synopsis "Parser for mass spectrometry data files")
9617 "The mzR package provides a unified API to the common file formats and
9618 parsers available for mass spectrometry data. It comes with a wrapper for the
9619 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9620 The package contains the original code written by the ISB, and a subset of the
9621 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9622 previously been used in XCMS.")
9623 (license license:artistic2.0)))
9625 (define-public r-affyio
9632 (uri (bioconductor-uri "affyio" version))
9635 "0j1f61409yq6hmkqrpzamfm7dx35rlq33ccs7wb1qcqx3d3nb75q"))))
9636 (build-system r-build-system)
9638 `(("r-zlibbioc" ,r-zlibbioc)))
9641 (home-page "https://github.com/bmbolstad/affyio")
9642 (synopsis "Tools for parsing Affymetrix data files")
9644 "This package provides routines for parsing Affymetrix data files based
9645 upon file format information. The primary focus is on accessing the CEL and
9647 (license license:lgpl2.0+)))
9649 (define-public r-affy
9656 (uri (bioconductor-uri "affy" version))
9659 "0m6hkyjxmsf80n3anhwh9k26csxczv6v92fkb7klnchdski61pyc"))))
9660 (build-system r-build-system)
9662 `(("r-affyio" ,r-affyio)
9663 ("r-biobase" ,r-biobase)
9664 ("r-biocgenerics" ,r-biocgenerics)
9665 ("r-biocmanager" ,r-biocmanager)
9666 ("r-preprocesscore" ,r-preprocesscore)
9667 ("r-zlibbioc" ,r-zlibbioc)))
9670 (home-page "https://bioconductor.org/packages/affy")
9671 (synopsis "Methods for affymetrix oligonucleotide arrays")
9673 "This package contains functions for exploratory oligonucleotide array
9675 (license license:lgpl2.0+)))
9677 (define-public r-vsn
9684 (uri (bioconductor-uri "vsn" version))
9687 "1k82dikrv1gcync5y1131wg7z1kxv2z2jl4nndg20bixc3398h58"))))
9688 (build-system r-build-system)
9690 `(("r-affy" ,r-affy)
9691 ("r-biobase" ,r-biobase)
9692 ("r-ggplot2" ,r-ggplot2)
9693 ("r-lattice" ,r-lattice)
9694 ("r-limma" ,r-limma)))
9696 `(("r-knitr" ,r-knitr))) ; for vignettes
9697 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9698 (synopsis "Variance stabilization and calibration for microarray data")
9700 "The package implements a method for normalising microarray intensities,
9701 and works for single- and multiple-color arrays. It can also be used for data
9702 from other technologies, as long as they have similar format. The method uses
9703 a robust variant of the maximum-likelihood estimator for an
9704 additive-multiplicative error model and affine calibration. The model
9705 incorporates data calibration step (a.k.a. normalization), a model for the
9706 dependence of the variance on the mean intensity and a variance stabilizing
9707 data transformation. Differences between transformed intensities are
9708 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9709 their variance is independent of the mean, and they are usually more sensitive
9710 and specific in detecting differential transcription.")
9711 (license license:artistic2.0)))
9713 (define-public r-mzid
9720 (uri (bioconductor-uri "mzID" version))
9723 "0y50lzkdamkpz67f6r5whp246qsxpbammjil7g8vjprx0c4jk5n5"))))
9724 (properties `((upstream-name . "mzID")))
9725 (build-system r-build-system)
9727 `(("r-doparallel" ,r-doparallel)
9728 ("r-foreach" ,r-foreach)
9729 ("r-iterators" ,r-iterators)
9731 ("r-protgenerics" ,r-protgenerics)
9735 `(("r-knitr" ,r-knitr)))
9736 (home-page "https://bioconductor.org/packages/mzID")
9737 (synopsis "Parser for mzIdentML files")
9739 "This package provides a parser for mzIdentML files implemented using the
9740 XML package. The parser tries to be general and able to handle all types of
9741 mzIdentML files with the drawback of having less pretty output than a vendor
9743 (license license:gpl2+)))
9745 (define-public r-pcamethods
9747 (name "r-pcamethods")
9752 (uri (bioconductor-uri "pcaMethods" version))
9755 "10cww4jxyynkwxbbsx804nwac31j0hh8dgisygld0q663gaxkgni"))))
9756 (properties `((upstream-name . "pcaMethods")))
9757 (build-system r-build-system)
9759 `(("r-biobase" ,r-biobase)
9760 ("r-biocgenerics" ,r-biocgenerics)
9762 ("r-rcpp" ,r-rcpp)))
9763 (home-page "https://github.com/hredestig/pcamethods")
9764 (synopsis "Collection of PCA methods")
9766 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9767 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9768 for missing value estimation is included for comparison. BPCA, PPCA and
9769 NipalsPCA may be used to perform PCA on incomplete data as well as for
9770 accurate missing value estimation. A set of methods for printing and plotting
9771 the results is also provided. All PCA methods make use of the same data
9772 structure (pcaRes) to provide a common interface to the PCA results.")
9773 (license license:gpl3+)))
9775 (define-public r-msnbase
9782 (uri (bioconductor-uri "MSnbase" version))
9785 "17vlv9gh41s1hp043b7j1jfqiw52alh1misjzy1kxl0g90rld00l"))))
9786 (properties `((upstream-name . "MSnbase")))
9787 (build-system r-build-system)
9789 `(("r-affy" ,r-affy)
9790 ("r-biobase" ,r-biobase)
9791 ("r-biocgenerics" ,r-biocgenerics)
9792 ("r-biocparallel" ,r-biocparallel)
9793 ("r-digest" ,r-digest)
9794 ("r-ggplot2" ,r-ggplot2)
9795 ("r-impute" ,r-impute)
9796 ("r-iranges" ,r-iranges)
9797 ("r-lattice" ,r-lattice)
9798 ("r-maldiquant" ,r-maldiquant)
9802 ("r-pcamethods" ,r-pcamethods)
9804 ("r-preprocesscore" ,r-preprocesscore)
9805 ("r-protgenerics" ,r-protgenerics)
9807 ("r-s4vectors" ,r-s4vectors)
9808 ("r-scales" ,r-scales)
9812 `(("r-knitr" ,r-knitr)))
9813 (home-page "https://github.com/lgatto/MSnbase")
9814 (synopsis "Base functions and classes for MS-based proteomics")
9816 "This package provides basic plotting, data manipulation and processing
9817 of mass spectrometry based proteomics data.")
9818 (license license:artistic2.0)))
9820 (define-public r-msnid
9827 (uri (bioconductor-uri "MSnID" version))
9830 "0dwa6j2nqb3223a8g4f453aznjh69wngrpvdi12iy69j1psbbjcc"))))
9831 (properties `((upstream-name . "MSnID")))
9832 (build-system r-build-system)
9834 `(("r-biobase" ,r-biobase)
9835 ("r-data-table" ,r-data-table)
9836 ("r-doparallel" ,r-doparallel)
9837 ("r-dplyr" ,r-dplyr)
9838 ("r-foreach" ,r-foreach)
9839 ("r-iterators" ,r-iterators)
9840 ("r-msnbase" ,r-msnbase)
9843 ("r-protgenerics" ,r-protgenerics)
9844 ("r-r-cache" ,r-r-cache)
9846 ("r-reshape2" ,r-reshape2)))
9847 (home-page "https://bioconductor.org/packages/MSnID")
9848 (synopsis "Utilities for LC-MSn proteomics identifications")
9850 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9851 from mzIdentML (leveraging the mzID package) or text files. After collating
9852 the search results from multiple datasets it assesses their identification
9853 quality and optimize filtering criteria to achieve the maximum number of
9854 identifications while not exceeding a specified false discovery rate. It also
9855 contains a number of utilities to explore the MS/MS results and assess missed
9856 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9857 (license license:artistic2.0)))
9859 (define-public r-seurat
9865 (uri (cran-uri "Seurat" version))
9868 "1lbq2pqhb6ih6iqawlnzdh05zff71pwbw1cpfv2sld3pd7kz0zkm"))))
9869 (properties `((upstream-name . "Seurat")))
9870 (build-system r-build-system)
9873 ("r-cluster" ,r-cluster)
9874 ("r-cowplot" ,r-cowplot)
9875 ("r-fitdistrplus" ,r-fitdistrplus)
9876 ("r-future" ,r-future)
9877 ("r-future-apply" ,r-future-apply)
9878 ("r-ggplot2" ,r-ggplot2)
9879 ("r-ggrepel" ,r-ggrepel)
9880 ("r-ggridges" ,r-ggridges)
9883 ("r-igraph" ,r-igraph)
9884 ("r-irlba" ,r-irlba)
9885 ("r-kernsmooth" ,r-kernsmooth)
9886 ("r-leiden" ,r-leiden)
9887 ("r-lmtest" ,r-lmtest)
9889 ("r-matrix" ,r-matrix)
9890 ("r-patchwork" ,r-patchwork)
9891 ("r-pbapply" ,r-pbapply)
9892 ("r-plotly" ,r-plotly)
9895 ("r-rcolorbrewer" ,r-rcolorbrewer)
9897 ("r-rcppannoy" ,r-rcppannoy)
9898 ("r-rcppeigen" ,r-rcppeigen)
9899 ("r-rcppprogress" ,r-rcppprogress)
9900 ("r-reticulate" ,r-reticulate)
9901 ("r-rlang" ,r-rlang)
9904 ("r-rtsne" ,r-rtsne)
9905 ("r-scales" ,r-scales)
9906 ("r-sctransform" ,r-sctransform)
9908 ("r-uwot" ,r-uwot)))
9909 (home-page "http://www.satijalab.org/seurat")
9910 (synopsis "Seurat is an R toolkit for single cell genomics")
9912 "This package is an R package designed for QC, analysis, and
9913 exploration of single cell RNA-seq data. It easily enables widely-used
9914 analytical techniques, including the identification of highly variable genes,
9915 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9916 algorithms; density clustering, hierarchical clustering, k-means, and the
9917 discovery of differentially expressed genes and markers.")
9918 (license license:gpl3)))
9920 (define-public r-aroma-light
9922 (name "r-aroma-light")
9927 (uri (bioconductor-uri "aroma.light" version))
9930 "19y5f2minx2pp73zdh43v1qkwpkaxygkl8cwlnwja15i46s0bcyc"))))
9931 (properties `((upstream-name . "aroma.light")))
9932 (build-system r-build-system)
9934 `(("r-matrixstats" ,r-matrixstats)
9935 ("r-r-methodss3" ,r-r-methodss3)
9937 ("r-r-utils" ,r-r-utils)))
9938 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9939 (synopsis "Methods for normalization and visualization of microarray data")
9941 "This package provides methods for microarray analysis that take basic
9942 data types such as matrices and lists of vectors. These methods can be used
9943 standalone, be utilized in other packages, or be wrapped up in higher-level
9945 (license license:gpl2+)))
9947 (define-public r-deseq
9954 (uri (bioconductor-uri "DESeq" version))
9957 "047hph5aqmjnz1aqprziw0smdn5lf96hmwpnvqrxv1j2yfvcf3h1"))))
9958 (properties `((upstream-name . "DESeq")))
9959 (build-system r-build-system)
9961 `(("r-biobase" ,r-biobase)
9962 ("r-biocgenerics" ,r-biocgenerics)
9963 ("r-genefilter" ,r-genefilter)
9964 ("r-geneplotter" ,r-geneplotter)
9965 ("r-lattice" ,r-lattice)
9966 ("r-locfit" ,r-locfit)
9968 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9969 (home-page "https://www-huber.embl.de/users/anders/DESeq/")
9970 (synopsis "Differential gene expression analysis")
9972 "This package provides tools for estimating variance-mean dependence in
9973 count data from high-throughput genetic sequencing assays and for testing for
9974 differential expression based on a model using the negative binomial
9976 (license license:gpl3+)))
9978 (define-public r-edaseq
9985 (uri (bioconductor-uri "EDASeq" version))
9988 "12gzxjh73qshlwvsf92lbrf4bi199kxg2snrkprh1z4yqf7bjfm4"))))
9989 (properties `((upstream-name . "EDASeq")))
9990 (build-system r-build-system)
9992 `(("r-annotationdbi" ,r-annotationdbi)
9993 ("r-aroma-light" ,r-aroma-light)
9994 ("r-biobase" ,r-biobase)
9995 ("r-biocgenerics" ,r-biocgenerics)
9996 ("r-biocmanager" ,r-biocmanager)
9997 ("r-biomart" ,r-biomart)
9998 ("r-biostrings" ,r-biostrings)
9999 ("r-deseq" ,r-deseq)
10000 ("r-genomicfeatures" ,r-genomicfeatures)
10001 ("r-genomicranges" ,r-genomicranges)
10002 ("r-iranges" ,r-iranges)
10003 ("r-rsamtools" ,r-rsamtools)
10004 ("r-shortread" ,r-shortread)))
10006 `(("r-knitr" ,r-knitr)))
10007 (home-page "https://github.com/drisso/EDASeq")
10008 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
10010 "This package provides support for numerical and graphical summaries of
10011 RNA-Seq genomic read data. Provided within-lane normalization procedures to
10012 adjust for GC-content effect (or other gene-level effects) on read counts:
10013 loess robust local regression, global-scaling, and full-quantile
10014 normalization. Between-lane normalization procedures to adjust for
10015 distributional differences between lanes (e.g., sequencing depth):
10016 global-scaling and full-quantile normalization.")
10017 (license license:artistic2.0)))
10019 (define-public r-interactivedisplaybase
10021 (name "r-interactivedisplaybase")
10026 (uri (bioconductor-uri "interactiveDisplayBase" version))
10029 "1x5vipqa4pgwpd62c1c58shnlpv3zyzzpf4wdwr00q1swkdb7wv3"))))
10031 `((upstream-name . "interactiveDisplayBase")))
10032 (build-system r-build-system)
10034 `(("r-biocgenerics" ,r-biocgenerics)
10036 ("r-shiny" ,r-shiny)))
10038 `(("r-knitr" ,r-knitr)))
10039 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
10040 (synopsis "Base package for web displays of Bioconductor objects")
10042 "This package contains the basic methods needed to generate interactive
10043 Shiny-based display methods for Bioconductor objects.")
10044 (license license:artistic2.0)))
10046 (define-public r-annotationhub
10048 (name "r-annotationhub")
10053 (uri (bioconductor-uri "AnnotationHub" version))
10056 "0r4xzf93bm9cpys5cg70wg0b8hxli80hvqwgh4hzbd45yyf5c4wz"))))
10057 (properties `((upstream-name . "AnnotationHub")))
10058 (build-system r-build-system)
10060 `(("r-annotationdbi" ,r-annotationdbi)
10061 ("r-biocfilecache" ,r-biocfilecache)
10062 ("r-biocgenerics" ,r-biocgenerics)
10063 ("r-biocmanager" ,r-biocmanager)
10064 ("r-biocversion" ,r-biocversion)
10066 ("r-dplyr" ,r-dplyr)
10068 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
10069 ("r-rappdirs" ,r-rappdirs)
10070 ("r-rsqlite" ,r-rsqlite)
10071 ("r-s4vectors" ,r-s4vectors)
10072 ("r-yaml" ,r-yaml)))
10074 `(("r-knitr" ,r-knitr)))
10075 (home-page "https://bioconductor.org/packages/AnnotationHub")
10076 (synopsis "Client to access AnnotationHub resources")
10078 "This package provides a client for the Bioconductor AnnotationHub web
10079 resource. The AnnotationHub web resource provides a central location where
10080 genomic files (e.g. VCF, bed, wig) and other resources from standard
10081 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
10082 metadata about each resource, e.g., a textual description, tags, and date of
10083 modification. The client creates and manages a local cache of files retrieved
10084 by the user, helping with quick and reproducible access.")
10085 (license license:artistic2.0)))
10087 (define-public r-fastseg
10094 (uri (bioconductor-uri "fastseg" version))
10097 "1d48n245pzmvcpsz93lxb4frqh222gfhpmlvm0sb74skn16way63"))))
10098 (build-system r-build-system)
10100 `(("r-biobase" ,r-biobase)
10101 ("r-biocgenerics" ,r-biocgenerics)
10102 ("r-genomicranges" ,r-genomicranges)
10103 ("r-iranges" ,r-iranges)
10104 ("r-s4vectors" ,r-s4vectors)))
10105 (home-page "https://www.bioinf.jku.at/software/fastseg/index.html")
10106 (synopsis "Fast segmentation algorithm for genetic sequencing data")
10108 "Fastseg implements a very fast and efficient segmentation algorithm.
10109 It can segment data from DNA microarrays and data from next generation
10110 sequencing for example to detect copy number segments. Further it can segment
10111 data from RNA microarrays like tiling arrays to identify transcripts. Most
10112 generally, it can segment data given as a matrix or as a vector. Various data
10113 formats can be used as input to fastseg like expression set objects for
10114 microarrays or GRanges for sequencing data.")
10115 (license license:lgpl2.0+)))
10117 (define-public r-keggrest
10119 (name "r-keggrest")
10124 (uri (bioconductor-uri "KEGGREST" version))
10127 "0q76w17fya2x0z7mvyhkk5kqh07flldgih13ma44vhcy1bdlm6j1"))))
10128 (properties `((upstream-name . "KEGGREST")))
10129 (build-system r-build-system)
10131 `(("r-biostrings" ,r-biostrings)
10135 `(("r-knitr" ,r-knitr)))
10136 (home-page "https://bioconductor.org/packages/KEGGREST")
10137 (synopsis "Client-side REST access to KEGG")
10139 "This package provides a package that provides a client interface to the
10140 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
10141 (license license:artistic2.0)))
10143 (define-public r-gage
10150 (uri (bioconductor-uri "gage" version))
10153 "1zfaas4x6g7wiml6cmxa7b4f43az9s0lrw80k6sf7c96hsh1jijr"))))
10154 (build-system r-build-system)
10156 `(("r-annotationdbi" ,r-annotationdbi)
10157 ("r-graph" ,r-graph)
10158 ("r-keggrest" ,r-keggrest)))
10159 (home-page (string-append "https://bmcbioinformatics.biomedcentral.com/"
10160 "articles/10.1186/1471-2105-10-161"))
10161 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
10163 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
10164 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
10165 data attributes including sample sizes, experimental designs, assay platforms,
10166 and other types of heterogeneity. The gage package provides functions for
10167 basic GAGE analysis, result processing and presentation. In addition, it
10168 provides demo microarray data and commonly used gene set data based on KEGG
10169 pathways and GO terms. These functions and data are also useful for gene set
10170 analysis using other methods.")
10171 (license license:gpl2+)))
10173 (define-public r-genomicfiles
10175 (name "r-genomicfiles")
10180 (uri (bioconductor-uri "GenomicFiles" version))
10183 "1k3824pzf9fdqvcv6cz2742q3mabpmncrc72hwa21ac8wy1b04n4"))))
10184 (properties `((upstream-name . "GenomicFiles")))
10185 (build-system r-build-system)
10187 `(("r-biocgenerics" ,r-biocgenerics)
10188 ("r-biocparallel" ,r-biocparallel)
10189 ("r-genomeinfodb" ,r-genomeinfodb)
10190 ("r-genomicalignments" ,r-genomicalignments)
10191 ("r-genomicranges" ,r-genomicranges)
10192 ("r-iranges" ,r-iranges)
10193 ("r-rsamtools" ,r-rsamtools)
10194 ("r-rtracklayer" ,r-rtracklayer)
10195 ("r-s4vectors" ,r-s4vectors)
10196 ("r-summarizedexperiment" ,r-summarizedexperiment)
10197 ("r-variantannotation" ,r-variantannotation)))
10198 (home-page "https://bioconductor.org/packages/GenomicFiles")
10199 (synopsis "Distributed computing by file or by range")
10201 "This package provides infrastructure for parallel computations
10202 distributed by file or by range. User defined mapper and reducer functions
10203 provide added flexibility for data combination and manipulation.")
10204 (license license:artistic2.0)))
10206 (define-public r-complexheatmap
10208 (name "r-complexheatmap")
10213 (uri (bioconductor-uri "ComplexHeatmap" version))
10216 "01jxxwxhf9n8baxgja4rb592p5210s4ppd7a5b4xby5aalhzkr0l"))))
10218 `((upstream-name . "ComplexHeatmap")))
10219 (build-system r-build-system)
10221 `(("r-circlize" ,r-circlize)
10223 ("r-colorspace" ,r-colorspace)
10224 ("r-getoptlong" ,r-getoptlong)
10225 ("r-globaloptions" ,r-globaloptions)
10227 ("r-rcolorbrewer" ,r-rcolorbrewer)))
10229 `(("r-knitr" ,r-knitr)))
10231 "https://github.com/jokergoo/ComplexHeatmap")
10232 (synopsis "Making Complex Heatmaps")
10234 "Complex heatmaps are efficient to visualize associations between
10235 different sources of data sets and reveal potential structures. This package
10236 provides a highly flexible way to arrange multiple heatmaps and supports
10237 self-defined annotation graphics.")
10238 (license license:gpl2+)))
10240 (define-public r-dirichletmultinomial
10242 (name "r-dirichletmultinomial")
10247 (uri (bioconductor-uri "DirichletMultinomial" version))
10250 "1m9dsrddrllb2i88qzik1867iv9mggrgdkn0dlp8sq7gl69vmalb"))))
10252 `((upstream-name . "DirichletMultinomial")))
10253 (build-system r-build-system)
10257 `(("r-biocgenerics" ,r-biocgenerics)
10258 ("r-iranges" ,r-iranges)
10259 ("r-s4vectors" ,r-s4vectors)))
10260 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
10261 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
10263 "Dirichlet-multinomial mixture models can be used to describe variability
10264 in microbial metagenomic data. This package is an interface to code
10265 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
10267 (license license:lgpl3)))
10269 (define-public r-ensembldb
10271 (name "r-ensembldb")
10276 (uri (bioconductor-uri "ensembldb" version))
10279 "1vvchc04nshxc768fp31rxb603aj3hmq8xlh5qabcwf2c3z9719g"))))
10280 (build-system r-build-system)
10282 `(("r-annotationdbi" ,r-annotationdbi)
10283 ("r-annotationfilter" ,r-annotationfilter)
10284 ("r-biobase" ,r-biobase)
10285 ("r-biocgenerics" ,r-biocgenerics)
10286 ("r-biostrings" ,r-biostrings)
10289 ("r-genomeinfodb" ,r-genomeinfodb)
10290 ("r-genomicfeatures" ,r-genomicfeatures)
10291 ("r-genomicranges" ,r-genomicranges)
10292 ("r-iranges" ,r-iranges)
10293 ("r-protgenerics" ,r-protgenerics)
10294 ("r-rsamtools" ,r-rsamtools)
10295 ("r-rsqlite" ,r-rsqlite)
10296 ("r-rtracklayer" ,r-rtracklayer)
10297 ("r-s4vectors" ,r-s4vectors)))
10299 `(("r-knitr" ,r-knitr)))
10300 (home-page "https://github.com/jotsetung/ensembldb")
10301 (synopsis "Utilities to create and use Ensembl-based annotation databases")
10303 "The package provides functions to create and use transcript-centric
10304 annotation databases/packages. The annotation for the databases are directly
10305 fetched from Ensembl using their Perl API. The functionality and data is
10306 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
10307 but, in addition to retrieve all gene/transcript models and annotations from
10308 the database, the @code{ensembldb} package also provides a filter framework
10309 allowing to retrieve annotations for specific entries like genes encoded on a
10310 chromosome region or transcript models of lincRNA genes.")
10311 ;; No version specified
10312 (license license:lgpl3+)))
10314 (define-public r-organismdbi
10316 (name "r-organismdbi")
10321 (uri (bioconductor-uri "OrganismDbi" version))
10324 "194h5576inq44qr666snzq0ygnc77rk5ljkn9bn8zs6x6gb3cwaw"))))
10325 (properties `((upstream-name . "OrganismDbi")))
10326 (build-system r-build-system)
10328 `(("r-annotationdbi" ,r-annotationdbi)
10329 ("r-biobase" ,r-biobase)
10330 ("r-biocgenerics" ,r-biocgenerics)
10331 ("r-biocmanager" ,r-biocmanager)
10333 ("r-genomicfeatures" ,r-genomicfeatures)
10334 ("r-genomicranges" ,r-genomicranges)
10335 ("r-graph" ,r-graph)
10336 ("r-iranges" ,r-iranges)
10338 ("r-s4vectors" ,r-s4vectors)))
10339 (home-page "https://bioconductor.org/packages/OrganismDbi")
10340 (synopsis "Software to enable the smooth interfacing of database packages")
10341 (description "The package enables a simple unified interface to several
10342 annotation packages each of which has its own schema by taking advantage of
10343 the fact that each of these packages implements a select methods.")
10344 (license license:artistic2.0)))
10346 (define-public r-biovizbase
10348 (name "r-biovizbase")
10353 (uri (bioconductor-uri "biovizBase" version))
10356 "1vq2mxa2jkljgw75zqjdkyml0ppi5dspvwj4cznfhi31cq8ds0qh"))))
10357 (properties `((upstream-name . "biovizBase")))
10358 (build-system r-build-system)
10360 `(("r-annotationdbi" ,r-annotationdbi)
10361 ("r-annotationfilter" ,r-annotationfilter)
10362 ("r-biocgenerics" ,r-biocgenerics)
10363 ("r-biostrings" ,r-biostrings)
10364 ("r-dichromat" ,r-dichromat)
10365 ("r-ensembldb" ,r-ensembldb)
10366 ("r-genomeinfodb" ,r-genomeinfodb)
10367 ("r-genomicalignments" ,r-genomicalignments)
10368 ("r-genomicfeatures" ,r-genomicfeatures)
10369 ("r-genomicranges" ,r-genomicranges)
10370 ("r-hmisc" ,r-hmisc)
10371 ("r-iranges" ,r-iranges)
10372 ("r-rcolorbrewer" ,r-rcolorbrewer)
10373 ("r-rlang" ,r-rlang)
10374 ("r-rsamtools" ,r-rsamtools)
10375 ("r-s4vectors" ,r-s4vectors)
10376 ("r-scales" ,r-scales)
10377 ("r-summarizedexperiment" ,r-summarizedexperiment)
10378 ("r-variantannotation" ,r-variantannotation)))
10379 (home-page "https://bioconductor.org/packages/biovizBase")
10380 (synopsis "Basic graphic utilities for visualization of genomic data")
10382 "The biovizBase package is designed to provide a set of utilities, color
10383 schemes and conventions for genomic data. It serves as the base for various
10384 high-level packages for biological data visualization. This saves development
10385 effort and encourages consistency.")
10386 (license license:artistic2.0)))
10388 (define-public r-ggbio
10395 (uri (bioconductor-uri "ggbio" version))
10398 "11ggnqjq42fi2hm9xlvrrlr2xhy4kglvl1a0mycp1s4v67lxw5h5"))))
10399 (build-system r-build-system)
10402 (modify-phases %standard-phases
10403 ;; See https://github.com/tengfei/ggbio/issues/117
10404 ;; This fix will be included in the next release.
10405 (add-after 'unpack 'fix-typo
10407 (substitute* "R/GGbio-class.R"
10408 (("fechable") "fetchable"))
10411 `(("r-annotationdbi" ,r-annotationdbi)
10412 ("r-annotationfilter" ,r-annotationfilter)
10413 ("r-biobase" ,r-biobase)
10414 ("r-biocgenerics" ,r-biocgenerics)
10415 ("r-biostrings" ,r-biostrings)
10416 ("r-biovizbase" ,r-biovizbase)
10417 ("r-bsgenome" ,r-bsgenome)
10418 ("r-ensembldb" ,r-ensembldb)
10419 ("r-genomeinfodb" ,r-genomeinfodb)
10420 ("r-genomicalignments" ,r-genomicalignments)
10421 ("r-genomicfeatures" ,r-genomicfeatures)
10422 ("r-genomicranges" ,r-genomicranges)
10423 ("r-ggally" ,r-ggally)
10424 ("r-ggplot2" ,r-ggplot2)
10425 ("r-gridextra" ,r-gridextra)
10426 ("r-gtable" ,r-gtable)
10427 ("r-hmisc" ,r-hmisc)
10428 ("r-iranges" ,r-iranges)
10429 ("r-organismdbi" ,r-organismdbi)
10430 ("r-reshape2" ,r-reshape2)
10431 ("r-rlang" ,r-rlang)
10432 ("r-rsamtools" ,r-rsamtools)
10433 ("r-rtracklayer" ,r-rtracklayer)
10434 ("r-s4vectors" ,r-s4vectors)
10435 ("r-scales" ,r-scales)
10436 ("r-summarizedexperiment" ,r-summarizedexperiment)
10437 ("r-variantannotation" ,r-variantannotation)))
10439 `(("r-knitr" ,r-knitr)))
10440 (home-page "http://www.tengfei.name/ggbio/")
10441 (synopsis "Visualization tools for genomic data")
10443 "The ggbio package extends and specializes the grammar of graphics for
10444 biological data. The graphics are designed to answer common scientific
10445 questions, in particular those often asked of high throughput genomics data.
10446 All core Bioconductor data structures are supported, where appropriate. The
10447 package supports detailed views of particular genomic regions, as well as
10448 genome-wide overviews. Supported overviews include ideograms and grand linear
10449 views. High-level plots include sequence fragment length, edge-linked
10450 interval to data view, mismatch pileup, and several splicing summaries.")
10451 (license license:artistic2.0)))
10453 (define-public r-gqtlbase
10455 (name "r-gqtlbase")
10460 (uri (bioconductor-uri "gQTLBase" version))
10463 "06xvzp4fn3qfa46ggg8kxi267gbyd821vvx4040173xkqxpr0g5j"))))
10464 (properties `((upstream-name . "gQTLBase")))
10465 (build-system r-build-system)
10467 `(("r-batchjobs" ,r-batchjobs)
10468 ("r-bbmisc" ,r-bbmisc)
10469 ("r-biocgenerics" ,r-biocgenerics)
10471 ("r-doparallel" ,r-doparallel)
10473 ("r-ffbase" ,r-ffbase)
10474 ("r-foreach" ,r-foreach)
10475 ("r-genomicfiles" ,r-genomicfiles)
10476 ("r-genomicranges" ,r-genomicranges)
10477 ("r-rtracklayer" ,r-rtracklayer)
10478 ("r-s4vectors" ,r-s4vectors)
10479 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10481 `(("r-knitr" ,r-knitr)))
10482 (home-page "https://bioconductor.org/packages/gQTLBase")
10483 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10485 "The purpose of this package is to simplify the storage and interrogation
10486 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10488 (license license:artistic2.0)))
10490 (define-public r-snpstats
10492 (name "r-snpstats")
10497 (uri (bioconductor-uri "snpStats" version))
10500 "1qv3nqqr30d3n66mawqd9dbl95dl89r4bcjvkc5iassy1yrwr8wq"))))
10501 (properties `((upstream-name . "snpStats")))
10502 (build-system r-build-system)
10503 (inputs `(("zlib" ,zlib)))
10505 `(("r-biocgenerics" ,r-biocgenerics)
10506 ("r-matrix" ,r-matrix)
10507 ("r-survival" ,r-survival)
10508 ("r-zlibbioc" ,r-zlibbioc)))
10509 (home-page "https://bioconductor.org/packages/snpStats")
10510 (synopsis "Methods for SNP association studies")
10512 "This package provides classes and statistical methods for large
10513 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10514 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10515 (license license:gpl3)))
10517 (define-public r-homo-sapiens
10519 (name "r-homo-sapiens")
10523 ;; We cannot use bioconductor-uri here because this tarball is
10524 ;; located under "data/annotation/" instead of "bioc/".
10525 (uri (string-append "https://www.bioconductor.org/packages/"
10526 "release/data/annotation/src/contrib/"
10528 version ".tar.gz"))
10531 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10533 `((upstream-name . "Homo.sapiens")))
10534 (build-system r-build-system)
10536 `(("r-genomicfeatures" ,r-genomicfeatures)
10537 ("r-go-db" ,r-go-db)
10538 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10539 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10540 ("r-organismdbi" ,r-organismdbi)
10541 ("r-annotationdbi" ,r-annotationdbi)))
10542 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10543 (synopsis "Annotation package for the Homo.sapiens object")
10545 "This package contains the Homo.sapiens object to access data from
10546 several related annotation packages.")
10547 (license license:artistic2.0)))
10549 (define-public r-erma
10556 (uri (bioconductor-uri "erma" version))
10559 "1ccfbq0r48sr3h8050w8zv8402h7nx09adr0xdyqlg7kwp9vd2l3"))))
10560 (build-system r-build-system)
10562 `(("r-annotationdbi" ,r-annotationdbi)
10563 ("r-biobase" ,r-biobase)
10564 ("r-biocgenerics" ,r-biocgenerics)
10565 ("r-biocparallel" ,r-biocparallel)
10566 ("r-genomeinfodb" ,r-genomeinfodb)
10567 ("r-genomicfiles" ,r-genomicfiles)
10568 ("r-genomicranges" ,r-genomicranges)
10569 ("r-ggplot2" ,r-ggplot2)
10570 ("r-homo-sapiens" ,r-homo-sapiens)
10571 ("r-iranges" ,r-iranges)
10572 ("r-rtracklayer" ,r-rtracklayer)
10573 ("r-s4vectors" ,r-s4vectors)
10574 ("r-shiny" ,r-shiny)
10575 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10577 `(("r-knitr" ,r-knitr)))
10578 (home-page "https://bioconductor.org/packages/erma")
10579 (synopsis "Epigenomic road map adventures")
10581 "The epigenomics road map describes locations of epigenetic marks in DNA
10582 from a variety of cell types. Of interest are locations of histone
10583 modifications, sites of DNA methylation, and regions of accessible chromatin.
10584 This package presents a selection of elements of the road map including
10585 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10586 by Ernst and Kellis.")
10587 (license license:artistic2.0)))
10589 (define-public r-ldblock
10596 (uri (bioconductor-uri "ldblock" version))
10599 "0plw00n2zfgh029ab41dnydzgv2yxrapjp770147rx9pff4dngrv"))))
10600 (build-system r-build-system)
10602 `(("r-biocgenerics" ,r-biocgenerics)
10603 ("r-ensdb-hsapiens-v75" ,r-ensdb-hsapiens-v75)
10604 ("r-ensembldb" ,r-ensembldb)
10605 ("r-genomeinfodb" ,r-genomeinfodb)
10606 ("r-genomicfiles" ,r-genomicfiles)
10608 ("r-matrix" ,r-matrix)
10609 ("r-rsamtools" ,r-rsamtools)
10610 ("r-snpstats" ,r-snpstats)
10611 ("r-variantannotation" ,r-variantannotation)))
10613 `(("r-knitr" ,r-knitr)))
10614 (home-page "https://bioconductor.org/packages/ldblock")
10615 (synopsis "Data structures for linkage disequilibrium measures in populations")
10617 "This package defines data structures for @dfn{linkage
10618 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10619 handling of existing population-level data for the purpose of flexibly
10620 defining LD blocks.")
10621 (license license:artistic2.0)))
10623 (define-public r-gqtlstats
10625 (name "r-gqtlstats")
10630 (uri (bioconductor-uri "gQTLstats" version))
10633 "1jjqfpjp93nmxjn757j5mzcax96bzcqdd1gr3rsdxg7ap008l2w7"))))
10634 (properties `((upstream-name . "gQTLstats")))
10635 (build-system r-build-system)
10637 `(("r-annotationdbi" ,r-annotationdbi)
10638 ("r-batchjobs" ,r-batchjobs)
10639 ("r-bbmisc" ,r-bbmisc)
10640 ("r-beeswarm" ,r-beeswarm)
10641 ("r-biobase" ,r-biobase)
10642 ("r-biocgenerics" ,r-biocgenerics)
10643 ("r-doparallel" ,r-doparallel)
10644 ("r-dplyr" ,r-dplyr)
10646 ("r-ffbase" ,r-ffbase)
10647 ("r-foreach" ,r-foreach)
10648 ("r-genomeinfodb" ,r-genomeinfodb)
10649 ("r-genomicfeatures" ,r-genomicfeatures)
10650 ("r-genomicfiles" ,r-genomicfiles)
10651 ("r-genomicranges" ,r-genomicranges)
10652 ("r-ggbeeswarm" ,r-ggbeeswarm)
10653 ("r-ggplot2" ,r-ggplot2)
10654 ("r-gqtlbase" ,r-gqtlbase)
10655 ("r-hardyweinberg" ,r-hardyweinberg)
10656 ("r-homo-sapiens" ,r-homo-sapiens)
10657 ("r-iranges" ,r-iranges)
10658 ("r-limma" ,r-limma)
10660 ("r-plotly" ,r-plotly)
10661 ("r-reshape2" ,r-reshape2)
10662 ("r-s4vectors" ,r-s4vectors)
10663 ("r-shiny" ,r-shiny)
10664 ("r-snpstats" ,r-snpstats)
10665 ("r-summarizedexperiment" ,r-summarizedexperiment)
10666 ("r-variantannotation" ,r-variantannotation)))
10668 `(("r-knitr" ,r-knitr)))
10669 (home-page "https://bioconductor.org/packages/gQTLstats")
10670 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10672 "This package provides tools for the computationally efficient analysis
10673 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10674 The software in this package aims to support refinements and functional
10675 interpretation of members of a collection of association statistics on a
10676 family of feature/genome hypotheses.")
10677 (license license:artistic2.0)))
10679 (define-public r-gviz
10686 (uri (bioconductor-uri "Gviz" version))
10689 "0cgkp0ciyy2qykqgh3vzp5mx9b4vsvacjh2jnsj3wldiapzlz08a"))))
10690 (properties `((upstream-name . "Gviz")))
10691 (build-system r-build-system)
10693 `(("r-annotationdbi" ,r-annotationdbi)
10694 ("r-biobase" ,r-biobase)
10695 ("r-biocgenerics" ,r-biocgenerics)
10696 ("r-biomart" ,r-biomart)
10697 ("r-biostrings" ,r-biostrings)
10698 ("r-biovizbase" ,r-biovizbase)
10699 ("r-bsgenome" ,r-bsgenome)
10700 ("r-digest" ,r-digest)
10701 ("r-ensembldb" ,r-ensembldb)
10702 ("r-genomeinfodb" ,r-genomeinfodb)
10703 ("r-genomicalignments" ,r-genomicalignments)
10704 ("r-genomicfeatures" ,r-genomicfeatures)
10705 ("r-genomicranges" ,r-genomicranges)
10706 ("r-iranges" ,r-iranges)
10707 ("r-lattice" ,r-lattice)
10708 ("r-latticeextra" ,r-latticeextra)
10709 ("r-matrixstats" ,r-matrixstats)
10710 ("r-rcolorbrewer" ,r-rcolorbrewer)
10711 ("r-rsamtools" ,r-rsamtools)
10712 ("r-rtracklayer" ,r-rtracklayer)
10713 ("r-s4vectors" ,r-s4vectors)
10714 ("r-xvector" ,r-xvector)))
10716 `(("r-knitr" ,r-knitr)))
10717 (home-page "https://bioconductor.org/packages/Gviz")
10718 (synopsis "Plotting data and annotation information along genomic coordinates")
10720 "Genomic data analyses requires integrated visualization of known genomic
10721 information and new experimental data. Gviz uses the biomaRt and the
10722 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10723 and translates this to e.g. gene/transcript structures in viewports of the
10724 grid graphics package. This results in genomic information plotted together
10726 (license license:artistic2.0)))
10728 (define-public r-gwascat
10735 (uri (bioconductor-uri "gwascat" version))
10738 "1cq5cmdrf0a0arr841yvkh6d8drc15p7mif1afr215l1s3y2dwd4"))))
10739 (build-system r-build-system)
10741 `(("r-annotationdbi" ,r-annotationdbi)
10742 ("r-biocgenerics" ,r-biocgenerics)
10743 ("r-biostrings" ,r-biostrings)
10744 ("r-genomeinfodb" ,r-genomeinfodb)
10745 ("r-genomicfeatures" ,r-genomicfeatures)
10746 ("r-genomicranges" ,r-genomicranges)
10747 ("r-ggplot2" ,r-ggplot2)
10748 ("r-iranges" ,r-iranges)
10749 ("r-rsamtools" ,r-rsamtools)
10750 ("r-rtracklayer" ,r-rtracklayer)
10751 ("r-s4vectors" ,r-s4vectors)))
10753 `(("r-knitr" ,r-knitr)))
10754 (home-page "https://bioconductor.org/packages/gwascat")
10755 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10757 "This package provides tools for representing and modeling data in the
10758 EMBL-EBI GWAS catalog.")
10759 (license license:artistic2.0)))
10761 (define-public r-sushi
10767 (uri (bioconductor-uri "Sushi" version))
10770 "17j3d5qjq5nbv99by5mq8rwr0jgh2jyyfn2nwxmwgzlmk3lgi1rb"))))
10771 (properties `((upstream-name . "Sushi")))
10772 (build-system r-build-system)
10774 `(("r-biomart" ,r-biomart)
10776 (home-page "https://bioconductor.org/packages/Sushi")
10777 (synopsis "Tools for visualizing genomics data")
10779 "This package provides flexible, quantitative, and integrative genomic
10780 visualizations for publication-quality multi-panel figures.")
10781 (license license:gpl2+)))
10783 (define-public r-fithic
10789 (uri (bioconductor-uri "FitHiC" version))
10792 "1dffkdxm08wq4kjd9j2v2625x3p6vbrk33a2zx94pwpgkghr72yp"))))
10793 (properties `((upstream-name . "FitHiC")))
10794 (build-system r-build-system)
10796 `(("r-data-table" ,r-data-table)
10797 ("r-fdrtool" ,r-fdrtool)
10798 ("r-rcpp" ,r-rcpp)))
10800 `(("r-knitr" ,r-knitr)))
10801 (home-page "https://bioconductor.org/packages/FitHiC")
10802 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10804 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10805 intra-chromosomal contact maps produced by genome-wide genome architecture
10806 assays such as Hi-C.")
10807 (license license:gpl2+)))
10809 (define-public r-hitc
10815 (uri (bioconductor-uri "HiTC" version))
10818 "1jx2pfa7sbdz7xi466lz1h5xv126g56z73n0a5l2wrq28k47qaxy"))))
10819 (properties `((upstream-name . "HiTC")))
10820 (build-system r-build-system)
10822 `(("r-biostrings" ,r-biostrings)
10823 ("r-genomeinfodb" ,r-genomeinfodb)
10824 ("r-genomicranges" ,r-genomicranges)
10825 ("r-iranges" ,r-iranges)
10826 ("r-matrix" ,r-matrix)
10827 ("r-rcolorbrewer" ,r-rcolorbrewer)
10828 ("r-rtracklayer" ,r-rtracklayer)))
10829 (home-page "https://bioconductor.org/packages/HiTC")
10830 (synopsis "High throughput chromosome conformation capture analysis")
10832 "The HiTC package was developed to explore high-throughput \"C\" data
10833 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10834 quality controls, normalization, visualization, and further analysis are also
10836 (license license:artistic2.0)))
10838 (define-public r-hdf5array
10840 (name "r-hdf5array")
10845 (uri (bioconductor-uri "HDF5Array" version))
10848 "1g848s0qc6i4ipd7y2s5pk8k1xggk2kfy0gnr8wjjs2gq3914aw4"))))
10849 (properties `((upstream-name . "HDF5Array")))
10850 (build-system r-build-system)
10854 `(("r-biocgenerics" ,r-biocgenerics)
10855 ("r-delayedarray" ,r-delayedarray)
10856 ("r-iranges" ,r-iranges)
10857 ("r-matrix" ,r-matrix)
10858 ("r-rhdf5" ,r-rhdf5)
10859 ("r-rhdf5lib" ,r-rhdf5lib)
10860 ("r-s4vectors" ,r-s4vectors)))
10861 (home-page "https://bioconductor.org/packages/HDF5Array")
10862 (synopsis "HDF5 back end for DelayedArray objects")
10863 (description "This package provides an array-like container for convenient
10864 access and manipulation of HDF5 datasets. It supports delayed operations and
10865 block processing.")
10866 (license license:artistic2.0)))
10868 (define-public r-rhdf5lib
10870 (name "r-rhdf5lib")
10875 (uri (bioconductor-uri "Rhdf5lib" version))
10878 "09ylwyk6a8sdrmi1mx7vpycpykqlqylmwa973g6jrcmk0h0qfa4w"))
10879 (modules '((guix build utils)))
10882 ;; Delete bundled binaries
10883 (delete-file-recursively "src/wininclude/")
10884 (delete-file-recursively "src/winlib-4.9.3/")
10885 (delete-file-recursively "src/winlib-8.3.0/")
10886 (delete-file "src/hdf5small_cxx_hl_1.10.6.tar.gz")
10888 (properties `((upstream-name . "Rhdf5lib")))
10889 (build-system r-build-system)
10892 (modify-phases %standard-phases
10893 (add-after 'unpack 'do-not-use-bundled-hdf5
10894 (lambda* (#:key inputs #:allow-other-keys)
10895 (for-each delete-file '("configure" "configure.ac"))
10896 ;; Do not make other packages link with the proprietary libsz.
10897 (substitute* "R/zzz.R"
10898 (("'\"%s/libhdf5.a\" \"%s/libsz.a\" -lz'")
10899 "'\"%s/libhdf5.a\" \"%s/libhdf5.a\" -lz'")
10900 (("'\"%s/libhdf5_cpp.a\" \"%s/libhdf5.a\" \"%s/libsz.a\" -lz'")
10901 "'\"%s/libhdf5_cpp.a\" \"%s/libhdf5.a\" \"%s/libhdf5.a\" -lz'")
10902 (("'%s/libhdf5_hl.a %s/libhdf5.a %s/libsz.a -lz'")
10903 "'%s/libhdf5_hl.a %s/libhdf5.a %s/libhdf5.a -lz'")
10904 (("'%s/libhdf5_hl_cpp.a %s/libhdf5_hl.a %s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a -lz'")
10905 "'%s/libhdf5_hl_cpp.a %s/libhdf5_hl.a %s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a -lz'"))
10906 (with-directory-excursion "src"
10907 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10908 (rename-file (string-append "hdf5-" ,(package-version hdf5-1.10))
10910 ;; Remove timestamp and host system information to make
10911 ;; the build reproducible.
10912 (substitute* "hdf5/src/libhdf5.settings.in"
10913 (("Configured on: @CONFIG_DATE@")
10914 "Configured on: Guix")
10915 (("Uname information:.*")
10916 "Uname information: Linux\n")
10917 ;; Remove unnecessary store reference.
10919 "C Compiler: GCC\n"))
10920 (rename-file "Makevars.in" "Makevars")
10921 (substitute* "Makevars"
10922 (("@ZLIB_LIB@") "-lz")
10923 (("@ZLIB_INCLUDE@") "")
10924 (("HDF5_CXX_LIB=.*")
10925 (string-append "HDF5_CXX_LIB="
10926 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10928 (string-append "HDF5_LIB="
10929 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10930 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10931 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10932 (("HDF5_HL_INCLUDE=.*") "HDF5_HL_INCLUDE=./hdf5/hl/src\n")
10933 (("HDF5_HL_CXX_INCLUDE=.*") "HDF5_HL_CXX_INCLUDE=./hdf5/hl/c++/src\n")
10934 (("HDF5_HL_LIB=.*")
10935 (string-append "HDF5_HL_LIB="
10936 (assoc-ref inputs "hdf5") "/lib/libhdf5_hl.a\n"))
10937 (("HDF5_HL_CXX_LIB=.*")
10938 (string-append "HDF5_HL_CXX_LIB="
10939 (assoc-ref inputs "hdf5") "/lib/libhdf5_hl_cpp.a\n"))
10940 ;; szip is non-free software
10941 (("cp \"\\$\\{SZIP_LIB\\}.*") "")
10942 (("PKG_LIBS =.*") "PKG_LIBS = -lz -lhdf5\n")))
10947 `(("hdf5" ,hdf5-1.10)))
10949 `(("hdf5-source" ,(package-source hdf5-1.10))
10950 ("r-knitr" ,r-knitr)))
10951 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10952 (synopsis "HDF5 library as an R package")
10953 (description "This package provides C and C++ HDF5 libraries for use in R
10955 (license license:artistic2.0)))
10957 (define-public r-beachmat
10959 (name "r-beachmat")
10964 (uri (bioconductor-uri "beachmat" version))
10967 "1vl6jbf9ia78cm4ikdb8vz04jv4b46zhvg5i006c63a9pzw7zhxi"))))
10968 (build-system r-build-system)
10970 `(("r-biocgenerics" ,r-biocgenerics)
10971 ("r-delayedarray" ,r-delayedarray)
10972 ("r-matrix" ,r-matrix)))
10974 `(("r-knitr" ,r-knitr)))
10975 (home-page "https://bioconductor.org/packages/beachmat")
10976 (synopsis "Compiling Bioconductor to handle each matrix type")
10977 (description "This package provides a consistent C++ class interface for a
10978 variety of commonly used matrix types, including sparse and HDF5-backed
10980 (license license:gpl3)))
10982 (define-public r-singlecellexperiment
10984 (name "r-singlecellexperiment")
10989 (uri (bioconductor-uri "SingleCellExperiment" version))
10992 "092wvk11n7pa234vlwhxm3gdi4k3sbnz1splhxalbdhz3jf02zfp"))))
10994 `((upstream-name . "SingleCellExperiment")))
10995 (build-system r-build-system)
10997 `(("r-biocgenerics" ,r-biocgenerics)
10998 ("r-s4vectors" ,r-s4vectors)
10999 ("r-summarizedexperiment" ,r-summarizedexperiment)))
11001 `(("r-knitr" ,r-knitr)))
11002 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
11003 (synopsis "S4 classes for single cell data")
11004 (description "This package defines an S4 class for storing data from
11005 single-cell experiments. This includes specialized methods to store and
11006 retrieve spike-in information, dimensionality reduction coordinates and size
11007 factors for each cell, along with the usual metadata for genes and
11009 (license license:gpl3)))
11011 (define-public r-scater
11017 (uri (bioconductor-uri "scater" version))
11020 "0sxd1s8wdlj9926bagq4crjrk1nnmh3j3bhgrw160zfgc3y8pzck"))))
11021 (build-system r-build-system)
11023 `(("r-beachmat" ,r-beachmat)
11024 ("r-biocgenerics" ,r-biocgenerics)
11025 ("r-biocneighbors" ,r-biocneighbors)
11026 ("r-biocparallel" ,r-biocparallel)
11027 ("r-biocsingular" ,r-biocsingular)
11028 ("r-delayedarray" ,r-delayedarray)
11029 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
11030 ("r-ggbeeswarm" ,r-ggbeeswarm)
11031 ("r-ggplot2" ,r-ggplot2)
11032 ("r-matrix" ,r-matrix)
11034 ("r-s4vectors" ,r-s4vectors)
11035 ("r-singlecellexperiment" ,r-singlecellexperiment)
11036 ("r-summarizedexperiment" ,r-summarizedexperiment)
11037 ("r-viridis" ,r-viridis)))
11038 (home-page "https://github.com/davismcc/scater")
11039 (synopsis "Single-cell analysis toolkit for gene expression data in R")
11040 (description "This package provides a collection of tools for doing
11041 various analyses of single-cell RNA-seq gene expression data, with a focus on
11043 (license license:gpl2+)))
11045 (define-public r-scran
11052 (uri (bioconductor-uri "scran" version))
11055 "1y8wlgk5zbv7c7gcp0ahfpbh9lifab7y3zwf0093fzaw7vr1y6cr"))))
11056 (build-system r-build-system)
11058 `(("r-beachmat" ,r-beachmat)
11060 ("r-biocgenerics" ,r-biocgenerics)
11061 ("r-biocneighbors" ,r-biocneighbors)
11062 ("r-biocparallel" ,r-biocparallel)
11063 ("r-biocsingular" ,r-biocsingular)
11064 ("r-delayedarray" ,r-delayedarray)
11065 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
11066 ("r-dqrng" ,r-dqrng)
11067 ("r-edger" ,r-edger)
11068 ("r-igraph" ,r-igraph)
11069 ("r-limma" ,r-limma)
11070 ("r-matrix" ,r-matrix)
11072 ("r-s4vectors" ,r-s4vectors)
11073 ("r-scater" ,r-scater)
11074 ("r-singlecellexperiment" ,r-singlecellexperiment)
11075 ("r-statmod" ,r-statmod)
11076 ("r-summarizedexperiment" ,r-summarizedexperiment)))
11077 (home-page "https://bioconductor.org/packages/scran")
11078 (synopsis "Methods for single-cell RNA-Seq data analysis")
11079 (description "This package implements a variety of low-level analyses of
11080 single-cell RNA-seq data. Methods are provided for normalization of
11081 cell-specific biases, assignment of cell cycle phase, and detection of highly
11082 variable and significantly correlated genes.")
11083 (license license:gpl3)))
11085 (define-public r-delayedmatrixstats
11087 (name "r-delayedmatrixstats")
11092 (uri (bioconductor-uri "DelayedMatrixStats" version))
11095 "0mv2rl6a6l404piabcazxz1s6ars016pxhjf5v40hhr6y1r0wbqy"))))
11097 `((upstream-name . "DelayedMatrixStats")))
11098 (build-system r-build-system)
11100 `(("r-biocparallel" ,r-biocparallel)
11101 ("r-delayedarray" ,r-delayedarray)
11102 ("r-hdf5array" ,r-hdf5array)
11103 ("r-iranges" ,r-iranges)
11104 ("r-matrix" ,r-matrix)
11105 ("r-matrixstats" ,r-matrixstats)
11106 ("r-s4vectors" ,r-s4vectors)))
11107 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
11108 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
11110 "This package provides a port of the @code{matrixStats} API for use with
11111 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
11112 contains high-performing functions operating on rows and columns of
11113 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
11114 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
11115 are optimized per data type and for subsetted calculations such that both
11116 memory usage and processing time is minimized.")
11117 (license license:expat)))
11119 (define-public r-phangorn
11121 (name "r-phangorn")
11126 (uri (cran-uri "phangorn" version))
11129 "0ihkaykqjmf80d8wrk3saphxvnv58zma6pd13633bd3cwanc33f5"))))
11130 (build-system r-build-system)
11133 ("r-fastmatch" ,r-fastmatch)
11134 ("r-igraph" ,r-igraph)
11135 ("r-magrittr" ,r-magrittr)
11136 ("r-matrix" ,r-matrix)
11137 ("r-quadprog" ,r-quadprog)
11138 ("r-rcpp" ,r-rcpp)))
11139 (home-page "https://github.com/KlausVigo/phangorn")
11140 (synopsis "Phylogenetic analysis in R")
11142 "Phangorn is a package for phylogenetic analysis in R. It supports
11143 estimation of phylogenetic trees and networks using Maximum Likelihood,
11144 Maximum Parsimony, distance methods and Hadamard conjugation.")
11145 (license license:gpl2+)))
11147 (define-public r-dropbead
11148 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
11151 (name "r-dropbead")
11152 (version (string-append "0-" revision "." (string-take commit 7)))
11156 (uri (git-reference
11157 (url "https://github.com/rajewsky-lab/dropbead.git")
11159 (file-name (git-file-name name version))
11162 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
11163 (build-system r-build-system)
11165 `(("r-ggplot2" ,r-ggplot2)
11166 ("r-rcolorbrewer" ,r-rcolorbrewer)
11167 ("r-gridextra" ,r-gridextra)
11168 ("r-gplots" ,r-gplots)
11169 ("r-plyr" ,r-plyr)))
11170 (home-page "https://github.com/rajewsky-lab/dropbead")
11171 (synopsis "Basic exploration and analysis of Drop-seq data")
11172 (description "This package offers a quick and straight-forward way to
11173 explore and perform basic analysis of single cell sequencing data coming from
11174 droplet sequencing. It has been particularly tailored for Drop-seq.")
11175 (license license:gpl3))))
11177 (define htslib-for-sambamba
11178 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
11181 (name "htslib-for-sambamba")
11182 (version (string-append "1.3.1-1." (string-take commit 9)))
11186 (uri (git-reference
11187 (url "https://github.com/lomereiter/htslib.git")
11189 (file-name (string-append "htslib-" version "-checkout"))
11192 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
11194 `(("autoconf" ,autoconf)
11195 ("automake" ,automake)
11196 ,@(package-native-inputs htslib))))))
11198 (define-public sambamba
11205 (uri (git-reference
11206 (url "https://github.com/lomereiter/sambamba.git")
11207 (commit (string-append "v" version))))
11208 (file-name (string-append name "-" version "-checkout"))
11211 "111h05b60pj8dxbidiamy4imc92x2962b3lmb7wgysl6lx064qis"))))
11212 (build-system gnu-build-system)
11214 `(#:tests? #f ; there is no test target
11215 #:parallel-build? #f ; not supported
11217 (modify-phases %standard-phases
11218 (delete 'configure)
11219 (add-after 'unpack 'fix-ldc-version
11221 (substitute* "gen_ldc_version_info.py"
11222 (("/usr/bin/env.*") (which "python3")))
11223 (substitute* "Makefile"
11224 ;; We use ldc2 instead of ldmd2 to compile sambamba.
11225 (("\\$\\(shell which ldmd2\\)") (which "ldc2")))
11227 (add-after 'unpack 'place-biod-and-undead
11228 (lambda* (#:key inputs #:allow-other-keys)
11229 (copy-recursively (assoc-ref inputs "biod") "BioD")
11231 (add-after 'unpack 'unbundle-prerequisites
11233 (substitute* "Makefile"
11234 (("htslib/libhts.a lz4/lib/liblz4.a")
11236 ((" lz4-static htslib-static") ""))
11239 (lambda* (#:key outputs #:allow-other-keys)
11240 (let* ((out (assoc-ref outputs "out"))
11241 (bin (string-append out "/bin")))
11243 (copy-file (string-append "bin/sambamba-" ,version)
11244 (string-append bin "/sambamba"))
11251 ,(let ((commit "7969eb0a847b05874e83ffddead26e193ece8101"))
11254 (uri (git-reference
11255 (url "https://github.com/biod/BioD.git")
11257 (file-name (string-append "biod-"
11258 (string-take commit 9)
11262 "0mjxsmbmv0jxl3pq21p8j5r829d648if8q58ka50b2956lc6qkpm")))))))
11265 ("htslib" ,htslib-for-sambamba)))
11266 (home-page "https://lomereiter.github.io/sambamba/")
11267 (synopsis "Tools for working with SAM/BAM data")
11268 (description "Sambamba is a high performance modern robust and
11269 fast tool (and library), written in the D programming language, for
11270 working with SAM and BAM files. Current parallelised functionality is
11271 an important subset of samtools functionality, including view, index,
11272 sort, markdup, and depth.")
11273 (license license:gpl2+)))
11275 (define-public ritornello
11277 (name "ritornello")
11281 (uri (git-reference
11282 (url "https://github.com/KlugerLab/Ritornello.git")
11283 (commit (string-append "v" version))))
11284 (file-name (git-file-name name version))
11287 "1xahvq215qld7x1w8vpa5zbrsj6p9crb9shqa2x89sb0aaxa02jk"))))
11288 (build-system gnu-build-system)
11290 `(#:tests? #f ; there are no tests
11292 (modify-phases %standard-phases
11293 (add-after 'unpack 'patch-samtools-references
11294 (lambda* (#:key inputs #:allow-other-keys)
11295 (substitute* '("src/SamStream.h"
11297 (("<sam.h>") "<samtools/sam.h>"))
11299 (delete 'configure)
11301 (lambda* (#:key inputs outputs #:allow-other-keys)
11302 (let* ((out (assoc-ref outputs "out"))
11303 (bin (string-append out "/bin/")))
11305 (install-file "bin/Ritornello" bin)
11308 `(("samtools" ,samtools-0.1)
11312 (home-page "https://github.com/KlugerLab/Ritornello")
11313 (synopsis "Control-free peak caller for ChIP-seq data")
11314 (description "Ritornello is a ChIP-seq peak calling algorithm based on
11315 signal processing that can accurately call binding events without the need to
11316 do a pair total DNA input or IgG control sample. It has been tested for use
11317 with narrow binding events such as transcription factor ChIP-seq.")
11318 (license license:gpl3+)))
11320 (define-public trim-galore
11322 (name "trim-galore")
11327 (uri (git-reference
11328 (url "https://github.com/FelixKrueger/TrimGalore.git")
11330 (file-name (git-file-name name version))
11333 "1y31wbxwkm9xqzr5zv1pk5q418whnmlmgmfyxxpnl12h83m2i9iv"))))
11334 (build-system gnu-build-system)
11336 `(#:tests? #f ; no tests
11338 (modify-phases %standard-phases
11339 (replace 'configure
11341 ;; Trim Galore tries to figure out what version of Python
11342 ;; cutadapt is using by looking at the shebang. Of course that
11343 ;; doesn't work, because cutadapt is wrapped in a shell script.
11344 (substitute* "trim_galore"
11345 (("my \\$python_return.*")
11346 "my $python_return = \"Python 3.999\";\n"))
11349 (add-after 'unpack 'hardcode-tool-references
11350 (lambda* (#:key inputs #:allow-other-keys)
11351 (substitute* "trim_galore"
11352 (("\\$path_to_cutadapt = 'cutadapt'")
11353 (string-append "$path_to_cutadapt = '"
11354 (assoc-ref inputs "cutadapt")
11356 (("\\$compression_path = \"gzip\"")
11357 (string-append "$compression_path = \""
11358 (assoc-ref inputs "gzip")
11361 (string-append "\""
11362 (assoc-ref inputs "gzip")
11365 (string-append "\""
11366 (assoc-ref inputs "pigz")
11370 (lambda* (#:key outputs #:allow-other-keys)
11371 (let ((bin (string-append (assoc-ref outputs "out")
11374 (install-file "trim_galore" bin)
11380 ("cutadapt" ,cutadapt)))
11382 `(("unzip" ,unzip)))
11383 (home-page "https://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
11384 (synopsis "Wrapper around Cutadapt and FastQC")
11385 (description "Trim Galore! is a wrapper script to automate quality and
11386 adapter trimming as well as quality control, with some added functionality to
11387 remove biased methylation positions for RRBS sequence files.")
11388 (license license:gpl3+)))
11390 (define-public gess
11396 (uri (string-append "http://compbio.uthscsa.edu/"
11398 "gess-" version ".src.tar.gz"))
11401 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
11402 (build-system gnu-build-system)
11404 `(#:tests? #f ; no tests
11406 (modify-phases %standard-phases
11407 (delete 'configure)
11410 (lambda* (#:key inputs outputs #:allow-other-keys)
11411 (let* ((python (assoc-ref inputs "python"))
11412 (out (assoc-ref outputs "out"))
11413 (bin (string-append out "/bin/"))
11414 (target (string-append
11416 ,(version-major+minor
11417 (package-version python))
11418 "/site-packages/gess/")))
11420 (copy-recursively "." target)
11421 ;; Make GESS.py executable
11422 (chmod (string-append target "GESS.py") #o555)
11423 ;; Add Python shebang to the top and make Matplotlib
11425 (substitute* (string-append target "GESS.py")
11426 (("\"\"\"Description:" line)
11427 (string-append "#!" (which "python") "
11429 matplotlib.use('Agg')
11431 ;; Make sure GESS has all modules in its path
11432 (wrap-script (string-append target "GESS.py")
11433 `("PYTHONPATH" ":" = (,target ,(getenv "PYTHONPATH"))))
11435 (symlink (string-append target "GESS.py")
11436 (string-append bin "GESS.py"))
11439 `(("python" ,python-2)
11440 ("python2-pysam" ,python2-pysam)
11441 ("python2-scipy" ,python2-scipy)
11442 ("python2-numpy" ,python2-numpy)
11443 ("python2-networkx" ,python2-networkx)
11444 ("python2-biopython" ,python2-biopython)
11445 ("guile" ,guile-3.0))) ; for the script wrapper
11446 (home-page "https://compbio.uthscsa.edu/GESS_Web/")
11447 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11449 "GESS is an implementation of a novel computational method to detect de
11450 novo exon-skipping events directly from raw RNA-seq data without the prior
11451 knowledge of gene annotation information. GESS stands for the graph-based
11452 exon-skipping scanner detection scheme.")
11453 (license license:bsd-3)))
11455 (define-public phylip
11462 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11463 "download/phylip-" version ".tar.gz"))
11466 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11467 (build-system gnu-build-system)
11469 `(#:tests? #f ; no check target
11470 #:make-flags (list "-f" "Makefile.unx" "install")
11471 #:parallel-build? #f ; not supported
11473 (modify-phases %standard-phases
11474 (add-after 'unpack 'enter-dir
11475 (lambda _ (chdir "src") #t))
11476 (delete 'configure)
11478 (lambda* (#:key inputs outputs #:allow-other-keys)
11479 (let ((target (string-append (assoc-ref outputs "out")
11482 (for-each (lambda (file)
11483 (install-file file target))
11484 (find-files "../exe" ".*")))
11486 (home-page "http://evolution.genetics.washington.edu/phylip/")
11487 (synopsis "Tools for inferring phylogenies")
11488 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11489 programs for inferring phylogenies (evolutionary trees).")
11490 (license license:bsd-2)))
11499 (uri (string-append "https://integrativemodeling.org/"
11500 version "/download/imp-" version ".tar.gz"))
11503 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
11504 (build-system cmake-build-system)
11506 `(;; FIXME: Some tests fail because they produce warnings, others fail
11507 ;; because the PYTHONPATH does not include the modeller's directory.
11515 ("python" ,python-2)))
11517 `(("python2-numpy" ,python2-numpy)
11518 ("python2-scipy" ,python2-scipy)
11519 ("python2-pandas" ,python2-pandas)
11520 ("python2-scikit-learn" ,python2-scikit-learn)
11521 ("python2-networkx" ,python2-networkx)))
11522 (home-page "https://integrativemodeling.org")
11523 (synopsis "Integrative modeling platform")
11524 (description "IMP's broad goal is to contribute to a comprehensive
11525 structural characterization of biomolecules ranging in size and complexity
11526 from small peptides to large macromolecular assemblies, by integrating data
11527 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11528 Python toolbox for solving complex modeling problems, and a number of
11529 applications for tackling some common problems in a user-friendly way.")
11530 ;; IMP is largely available under the GNU Lesser GPL; see the file
11531 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11532 ;; available under the GNU GPL (see the file COPYING.GPL).
11533 (license (list license:lgpl2.1+
11536 (define-public tadbit
11542 (uri (git-reference
11543 (url "https://github.com/3DGenomes/TADbit.git")
11544 (commit (string-append "v" version))))
11545 (file-name (git-file-name name version))
11548 "07g3aj648prmsvxp9caz5yl41k0y0647vxh0f5p3w8376mfiljd0"))))
11549 (build-system python-build-system)
11551 `(;; Tests are included and must be run after installation, but
11552 ;; they are incomplete and thus cannot be run.
11556 (modify-phases %standard-phases
11557 (add-after 'unpack 'fix-problems-with-setup.py
11558 (lambda* (#:key outputs #:allow-other-keys)
11559 ;; setup.py opens these files for writing
11560 (chmod "_pytadbit/_version.py" #o664)
11561 (chmod "README.rst" #o664)
11563 ;; Don't attempt to install the bash completions to
11564 ;; the home directory.
11565 (rename-file "extras/.bash_completion"
11567 (substitute* "setup.py"
11568 (("\\(path.expanduser\\('~'\\)")
11569 (string-append "(\""
11570 (assoc-ref outputs "out")
11571 "/etc/bash_completion.d\""))
11572 (("extras/\\.bash_completion")
11576 ;; TODO: add Chimera for visualization
11579 ("python2-scipy" ,python2-scipy)
11580 ("python2-numpy" ,python2-numpy)
11581 ("python2-matplotlib" ,python2-matplotlib)
11582 ("python2-pysam" ,python2-pysam)))
11583 (home-page "https://3dgenomes.github.io/TADbit/")
11584 (synopsis "Analyze, model, and explore 3C-based data")
11586 "TADbit is a complete Python library to deal with all steps to analyze,
11587 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11588 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11589 correct interaction matrices, identify and compare the so-called
11590 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11591 interaction matrices, and finally, extract structural properties from the
11592 models. TADbit is complemented by TADkit for visualizing 3D models.")
11593 (license license:gpl3+)))
11595 (define-public kentutils
11598 ;; 302.1.0 is out, but the only difference is the inclusion of
11599 ;; pre-built binaries.
11600 (version "302.0.0")
11604 (uri (git-reference
11605 (url "https://github.com/ENCODE-DCC/kentUtils.git")
11606 (commit (string-append "v" version))))
11607 (file-name (git-file-name name version))
11610 "0n1wbyjpzii2b9qhyp9r1q76j623cggpg3y8fmw78ld3z4y7ivha"))
11611 (modules '((guix build utils)
11616 ;; Only the contents of the specified directories are free
11617 ;; for all uses, so we remove the rest. "hg/autoSql" and
11618 ;; "hg/autoXml" are nominally free, but they depend on a
11619 ;; library that is built from the sources in "hg/lib",
11620 ;; which is nonfree.
11621 (let ((free (list "." ".."
11622 "utils" "lib" "inc" "tagStorm"
11623 "parasol" "htslib"))
11624 (directory? (lambda (file)
11625 (eq? 'directory (stat:type (stat file))))))
11626 (for-each (lambda (file)
11627 (and (directory? file)
11628 (delete-file-recursively file)))
11629 (map (cut string-append "src/" <>)
11632 (not (member file free)))))))
11633 ;; Only make the utils target, not the userApps target,
11634 ;; because that requires libraries we won't build.
11635 (substitute* "Makefile"
11636 ((" userApps") " utils"))
11637 ;; Only build libraries that are free.
11638 (substitute* "src/makefile"
11639 (("DIRS =.*") "DIRS =\n")
11640 (("cd jkOwnLib.*") "")
11643 (substitute* "src/utils/makefile"
11644 ;; These tools depend on "jkhgap.a", which is part of the
11645 ;; nonfree "src/hg/lib" directory.
11646 (("raSqlQuery") "")
11647 (("pslLiftSubrangeBlat") "")
11649 ;; Do not build UCSC tools, which may require nonfree
11651 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11653 (build-system gnu-build-system)
11655 `( ;; There is no global test target and the test target for
11656 ;; individual tools depends on input files that are not
11660 (modify-phases %standard-phases
11661 (add-after 'unpack 'fix-permissions
11662 (lambda _ (make-file-writable "src/inc/localEnvironment.mk") #t))
11663 (add-after 'unpack 'fix-paths
11665 (substitute* "Makefile"
11666 (("/bin/echo") (which "echo")))
11668 (add-after 'unpack 'prepare-samtabix
11669 (lambda* (#:key inputs #:allow-other-keys)
11670 (copy-recursively (assoc-ref inputs "samtabix")
11673 (delete 'configure)
11675 (lambda* (#:key outputs #:allow-other-keys)
11676 (let ((bin (string-append (assoc-ref outputs "out")
11678 (copy-recursively "bin" bin))
11684 (uri (git-reference
11685 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11686 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11689 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11695 ("mariadb" ,mariadb "lib")
11696 ("mariadb-dev" ,mariadb "dev")
11697 ("openssl" ,openssl-1.0)))
11698 (home-page "https://genome.cse.ucsc.edu/index.html")
11699 (synopsis "Assorted bioinformatics utilities")
11700 (description "This package provides the kentUtils, a selection of
11701 bioinformatics utilities used in combination with the UCSC genome
11703 ;; Only a subset of the sources are released under a non-copyleft
11704 ;; free software license. All other sources are removed in a
11705 ;; snippet. See this bug report for an explanation of how the
11706 ;; license statements apply:
11707 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11708 (license (license:non-copyleft
11709 "http://genome.ucsc.edu/license/"
11710 "The contents of this package are free for all uses."))))
11712 (define-public f-seq
11713 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11717 (version (string-append "1.1-" revision "." (string-take commit 7)))
11720 (uri (git-reference
11721 (url "https://github.com/aboyle/F-seq.git")
11723 (file-name (string-append name "-" version))
11726 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11727 (modules '((guix build utils)))
11728 ;; Remove bundled Java library archives.
11731 (for-each delete-file (find-files "lib" ".*"))
11733 (build-system ant-build-system)
11735 `(#:tests? #f ; no tests included
11737 (modify-phases %standard-phases
11739 (lambda* (#:key inputs outputs #:allow-other-keys)
11740 (let* ((target (assoc-ref outputs "out"))
11741 (bin (string-append target "/bin"))
11742 (doc (string-append target "/share/doc/f-seq"))
11743 (lib (string-append target "/lib")))
11746 (substitute* "bin/linux/fseq"
11747 (("java") (which "java"))
11748 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11749 (string-append (assoc-ref inputs "java-commons-cli")
11750 "/share/java/commons-cli.jar"))
11752 (string-append "REALDIR=" bin "\n")))
11753 (install-file "README.txt" doc)
11754 (install-file "bin/linux/fseq" bin)
11755 (install-file "build~/fseq.jar" lib)
11756 (copy-recursively "lib" lib)
11760 ("java-commons-cli" ,java-commons-cli)))
11761 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11762 (synopsis "Feature density estimator for high-throughput sequence tags")
11764 "F-Seq is a software package that generates a continuous tag sequence
11765 density estimation allowing identification of biologically meaningful sites
11766 such as transcription factor binding sites (ChIP-seq) or regions of open
11767 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11769 (license license:gpl3+))))
11771 (define-public bismark
11778 (uri (git-reference
11779 (url "https://github.com/FelixKrueger/Bismark.git")
11781 (file-name (string-append name "-" version "-checkout"))
11784 "0xchm3rgilj6vfjnyzfzzymfd7djr64sbrmrvs3njbwi66jqbzw9"))))
11785 (build-system perl-build-system)
11787 `(#:tests? #f ; there are no tests
11788 #:modules ((guix build utils)
11791 (guix build perl-build-system))
11793 (modify-phases %standard-phases
11794 ;; The bundled plotly.js is minified.
11795 (add-after 'unpack 'replace-plotly.js
11796 (lambda* (#:key inputs #:allow-other-keys)
11797 (let* ((file (assoc-ref inputs "plotly.js"))
11798 (installed "plotly/plotly.js"))
11799 (let ((minified (open-pipe* OPEN_READ "uglify-js" file)))
11800 (call-with-output-file installed
11801 (cut dump-port minified <>))))
11803 (delete 'configure)
11806 (lambda* (#:key inputs outputs #:allow-other-keys)
11807 (let* ((out (assoc-ref outputs "out"))
11808 (bin (string-append out "/bin"))
11809 (share (string-append out "/share/bismark"))
11810 (docdir (string-append out "/share/doc/bismark"))
11811 (docs '("Docs/Bismark_User_Guide.html"))
11812 (scripts '("bismark"
11813 "bismark_genome_preparation"
11814 "bismark_methylation_extractor"
11817 "coverage2cytosine"
11818 "deduplicate_bismark"
11819 "filter_non_conversion"
11822 "NOMe_filtering")))
11823 (substitute* "bismark2report"
11824 (("\\$RealBin/plotly")
11825 (string-append share "/plotly")))
11829 (for-each (lambda (file) (install-file file bin))
11831 (for-each (lambda (file) (install-file file docdir))
11833 (copy-recursively "Docs/Images" (string-append docdir "/Images"))
11834 (copy-recursively "plotly"
11835 (string-append share "/plotly"))
11837 ;; Fix references to gunzip
11838 (substitute* (map (lambda (file)
11839 (string-append bin "/" file))
11842 (string-append "\"" (assoc-ref inputs "gzip")
11843 "/bin/gunzip -c")))
11847 ("perl-carp" ,perl-carp)
11848 ("perl-getopt-long" ,perl-getopt-long)))
11853 (uri (string-append "https://raw.githubusercontent.com/plotly/plotly.js/"
11854 "v1.39.4/dist/plotly.js"))
11856 (base32 "138mwsr4nf5qif4mrxx286mpnagxd1xwl6k8aidrjgknaqg88zyr"))))
11857 ("uglify-js" ,uglify-js)))
11858 (home-page "https://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11859 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11860 (description "Bismark is a program to map bisulfite treated sequencing
11861 reads to a genome of interest and perform methylation calls in a single step.
11862 The output can be easily imported into a genome viewer, such as SeqMonk, and
11863 enables a researcher to analyse the methylation levels of their samples
11864 straight away. Its main features are:
11867 @item Bisulfite mapping and methylation calling in one single step
11868 @item Supports single-end and paired-end read alignments
11869 @item Supports ungapped and gapped alignments
11870 @item Alignment seed length, number of mismatches etc are adjustable
11871 @item Output discriminates between cytosine methylation in CpG, CHG
11874 (license license:gpl3+)))
11876 (define-public paml
11882 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11883 "paml" version ".tgz"))
11886 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11887 (modules '((guix build utils)))
11888 ;; Remove Windows binaries
11891 (for-each delete-file (find-files "." "\\.exe$"))
11893 (build-system gnu-build-system)
11895 `(#:tests? #f ; there are no tests
11896 #:make-flags '("CC=gcc")
11898 (modify-phases %standard-phases
11899 (replace 'configure
11901 (substitute* "src/BFdriver.c"
11902 (("/bin/bash") (which "bash")))
11906 (lambda* (#:key outputs #:allow-other-keys)
11907 (let ((tools '("baseml" "basemlg" "codeml"
11908 "pamp" "evolver" "yn00" "chi2"))
11909 (bin (string-append (assoc-ref outputs "out") "/bin"))
11910 (docdir (string-append (assoc-ref outputs "out")
11911 "/share/doc/paml")))
11913 (for-each (lambda (file) (install-file file bin)) tools)
11914 (copy-recursively "../doc" docdir)
11916 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11917 (synopsis "Phylogentic analysis by maximum likelihood")
11918 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11919 contains a few programs for model fitting and phylogenetic tree reconstruction
11920 using nucleotide or amino-acid sequence data.")
11922 (license license:gpl3)))
11924 (define-public kallisto
11930 (uri (git-reference
11931 (url "https://github.com/pachterlab/kallisto.git")
11932 (commit (string-append "v" version))))
11933 (file-name (git-file-name name version))
11936 "0nj382jiywqnpgvyhichajpkkh5r0bapn43f4dx40zdaq5v4m40m"))))
11937 (build-system cmake-build-system)
11939 `(#:tests? #f ; no "check" target
11941 (modify-phases %standard-phases
11942 (add-after 'unpack 'do-not-use-bundled-htslib
11944 (substitute* "CMakeLists.txt"
11945 (("^ExternalProject_Add" m)
11946 (string-append "if (NEVER)\n" m))
11948 (string-append ")\nendif(NEVER)"))
11949 (("include_directories\\(\\$\\{htslib_PREFIX.*" m)
11950 (string-append "# " m)))
11951 (substitute* "src/CMakeLists.txt"
11952 (("target_link_libraries\\(kallisto kallisto_core pthread \
11953 \\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/../ext/htslib/libhts.a\\)")
11954 "target_link_libraries(kallisto kallisto_core pthread hts)")
11955 (("include_directories\\(\\.\\./ext/htslib\\)") ""))
11961 (home-page "https://pachterlab.github.io/kallisto/")
11962 (synopsis "Near-optimal RNA-Seq quantification")
11964 "Kallisto is a program for quantifying abundances of transcripts from
11965 RNA-Seq data, or more generally of target sequences using high-throughput
11966 sequencing reads. It is based on the novel idea of pseudoalignment for
11967 rapidly determining the compatibility of reads with targets, without the need
11968 for alignment. Pseudoalignment of reads preserves the key information needed
11969 for quantification, and kallisto is therefore not only fast, but also as
11970 accurate as existing quantification tools.")
11971 (license license:bsd-2)))
11973 (define-public libgff
11979 (uri (git-reference
11980 (url "https://github.com/Kingsford-Group/libgff.git")
11981 (commit (string-append "v" version))))
11982 (file-name (git-file-name name version))
11985 "0n6vfjnq7a2mianipscbshrvbncss8z4zkgkbjw754p9043nfkps"))))
11986 (build-system cmake-build-system)
11987 (arguments `(#:tests? #f)) ; no tests included
11988 (home-page "https://github.com/Kingsford-Group/libgff")
11989 (synopsis "Parser library for reading/writing GFF files")
11990 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11991 code that is used in the Cufflinks codebase. The goal of this library is to
11992 provide this functionality without the necessity of drawing in a heavy-weight
11993 dependency like SeqAn.")
11994 (license (license:x11-style "https://www.boost.org/LICENSE_1_0.txt"))))
11996 (define-public sailfish
12002 (uri (git-reference
12003 (url "https://github.com/kingsfordgroup/sailfish.git")
12004 (commit (string-append "v" version))))
12005 (file-name (git-file-name name version))
12008 "1amcc5hqvsl42hg4x19bi9vy47cl874s0lw1fmi0hwsdk9i8c03v"))
12009 (modules '((guix build utils)))
12012 ;; Delete bundled headers for eigen3.
12013 (delete-file-recursively "include/eigen3/")
12015 (build-system cmake-build-system)
12017 `(#:configure-flags
12018 (list (string-append "-DBOOST_INCLUDEDIR="
12019 (assoc-ref %build-inputs "boost")
12021 (string-append "-DBOOST_LIBRARYDIR="
12022 (assoc-ref %build-inputs "boost")
12024 (string-append "-DBoost_LIBRARIES="
12025 "-lboost_iostreams "
12026 "-lboost_filesystem "
12031 "-lboost_program_options")
12032 "-DBoost_FOUND=TRUE"
12033 ;; Don't download RapMap---we already have it!
12034 "-DFETCHED_RAPMAP=1")
12035 ;; Tests must be run after installation and the location of the test
12036 ;; data file must be overridden. But the tests fail. It looks like
12037 ;; they are not really meant to be run.
12040 (modify-phases %standard-phases
12041 ;; Boost cannot be found, even though it's right there.
12042 (add-after 'unpack 'do-not-look-for-boost
12043 (lambda* (#:key inputs #:allow-other-keys)
12044 (substitute* "CMakeLists.txt"
12045 (("find_package\\(Boost 1\\.53\\.0") "#"))
12047 (add-after 'unpack 'do-not-assign-to-macro
12049 (substitute* "include/spdlog/details/format.cc"
12050 (("const unsigned CHAR_WIDTH = 1;") ""))
12052 (add-after 'unpack 'prepare-rapmap
12053 (lambda* (#:key inputs #:allow-other-keys)
12054 (let ((src "external/install/src/rapmap/")
12055 (include "external/install/include/rapmap/")
12056 (rapmap (assoc-ref inputs "rapmap")))
12057 (mkdir-p "/tmp/rapmap")
12059 (assoc-ref inputs "rapmap")
12061 "--strip-components=1")
12064 (for-each (lambda (file)
12065 (install-file file src))
12066 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
12067 (copy-recursively "/tmp/rapmap/include" include))
12069 (add-after 'unpack 'use-system-libraries
12070 (lambda* (#:key inputs #:allow-other-keys)
12071 (substitute* '("src/SailfishIndexer.cpp"
12072 "src/SailfishUtils.cpp"
12073 "src/SailfishQuantify.cpp"
12074 "src/FASTAParser.cpp"
12076 "include/SailfishUtils.hpp"
12077 "include/SailfishIndex.hpp"
12078 "include/CollapsedEMOptimizer.hpp"
12079 "src/CollapsedEMOptimizer.cpp")
12080 (("#include \"jellyfish/config.h\"") ""))
12081 (substitute* "src/CMakeLists.txt"
12082 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
12083 (string-append (assoc-ref inputs "jellyfish")
12084 "/include/jellyfish-" ,(package-version jellyfish)))
12085 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
12086 (string-append (assoc-ref inputs "jellyfish")
12087 "/lib/libjellyfish-2.0.a"))
12088 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12089 (string-append (assoc-ref inputs "libdivsufsort")
12090 "/lib/libdivsufsort.so"))
12091 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12092 (string-append (assoc-ref inputs "libdivsufsort")
12093 "/lib/libdivsufsort64.so")))
12094 (substitute* "CMakeLists.txt"
12095 ;; Don't prefer static libs
12096 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12097 (("find_package\\(Jellyfish.*") "")
12098 (("ExternalProject_Add\\(libjellyfish") "message(")
12099 (("ExternalProject_Add\\(libgff") "message(")
12100 (("ExternalProject_Add\\(libsparsehash") "message(")
12101 (("ExternalProject_Add\\(libdivsufsort") "message("))
12103 ;; Ensure that Eigen headers can be found
12104 (setenv "CPLUS_INCLUDE_PATH"
12105 (string-append (assoc-ref inputs "eigen")
12107 (or (getenv "CPLUS_INCLUDE_PATH") "")))
12112 ("jemalloc" ,jemalloc)
12113 ("jellyfish" ,jellyfish)
12114 ("sparsehash" ,sparsehash)
12117 (uri (git-reference
12118 (url "https://github.com/COMBINE-lab/RapMap.git")
12119 (commit (string-append "sf-v" version))))
12120 (file-name (string-append "rapmap-sf-v" version "-checkout"))
12123 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
12124 (modules '((guix build utils)))
12125 ;; These files are expected to be excluded.
12127 '(begin (delete-file-recursively "include/spdlog")
12128 (for-each delete-file '("include/xxhash.h"
12131 ("libdivsufsort" ,libdivsufsort)
12136 `(("pkg-config" ,pkg-config)))
12137 (home-page "https://www.cs.cmu.edu/~ckingsf/software/sailfish/")
12138 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
12139 (description "Sailfish is a tool for genomic transcript quantification
12140 from RNA-seq data. It requires a set of target transcripts (either from a
12141 reference or de-novo assembly) to quantify. All you need to run sailfish is a
12142 fasta file containing your reference transcripts and a (set of) fasta/fastq
12143 file(s) containing your reads.")
12144 (license license:gpl3+)))
12146 (define libstadenio-for-salmon
12148 (name "libstadenio")
12152 (uri (git-reference
12153 (url "https://github.com/COMBINE-lab/staden-io_lib.git")
12154 (commit (string-append "v" version))))
12155 (file-name (string-append name "-" version "-checkout"))
12158 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
12159 (build-system gnu-build-system)
12160 (arguments '(#:parallel-tests? #f)) ; not supported
12164 `(("perl" ,perl))) ; for tests
12165 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
12166 (synopsis "General purpose trace and experiment file library")
12167 (description "This package provides a library of file reading and writing
12168 code to provide a general purpose Trace file (and Experiment File) reading
12171 The following file formats are supported:
12174 @item SCF trace files
12175 @item ABI trace files
12176 @item ALF trace files
12177 @item ZTR trace files
12178 @item SFF trace archives
12179 @item SRF trace archives
12180 @item Experiment files
12181 @item Plain text files
12182 @item SAM/BAM sequence files
12183 @item CRAM sequence files
12185 (license license:bsd-3)))
12187 (define-public salmon
12193 (uri (git-reference
12194 (url "https://github.com/COMBINE-lab/salmon.git")
12195 (commit (string-append "v" version))))
12196 (file-name (git-file-name name version))
12199 "1i2z4aivicmiixdz9bxalp7vmfzi3k92fxa63iqa8kgvfw5a4aq5"))
12200 (modules '((guix build utils)))
12203 ;; Delete bundled headers for eigen3.
12204 (delete-file-recursively "include/eigen3/")
12206 (build-system cmake-build-system)
12208 `(#:configure-flags
12209 (list (string-append "-DBOOST_INCLUDEDIR="
12210 (assoc-ref %build-inputs "boost")
12212 (string-append "-DBOOST_LIBRARYDIR="
12213 (assoc-ref %build-inputs "boost")
12215 (string-append "-DBoost_LIBRARIES="
12216 "-lboost_iostreams "
12217 "-lboost_filesystem "
12222 "-lboost_program_options")
12223 "-DBoost_FOUND=TRUE"
12224 "-DTBB_LIBRARIES=tbb tbbmalloc"
12225 ;; Don't download RapMap---we already have it!
12226 "-DFETCHED_RAPMAP=1")
12228 (modify-phases %standard-phases
12229 ;; Boost cannot be found, even though it's right there.
12230 (add-after 'unpack 'do-not-look-for-boost
12231 (lambda* (#:key inputs #:allow-other-keys)
12232 (substitute* "CMakeLists.txt"
12233 (("find_package\\(Boost 1\\.59\\.0") "#"))
12235 (add-after 'unpack 'do-not-phone-home
12237 (substitute* "src/Salmon.cpp"
12238 (("getVersionMessage\\(\\)") "\"\""))
12240 (add-after 'unpack 'prepare-rapmap
12241 (lambda* (#:key inputs #:allow-other-keys)
12242 (let ((src "external/install/src/rapmap/")
12243 (include "external/install/include/rapmap/")
12244 (rapmap (assoc-ref inputs "rapmap")))
12247 (copy-recursively (string-append rapmap "/src") src)
12248 (copy-recursively (string-append rapmap "/include") include)
12249 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
12250 "external/install/include/rapmap/FastxParser.hpp"
12251 "external/install/include/rapmap/concurrentqueue.h"
12252 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
12253 "external/install/src/rapmap/FastxParser.cpp"
12254 "external/install/src/rapmap/xxhash.c"))
12255 (delete-file-recursively "external/install/include/rapmap/spdlog"))
12257 (add-after 'unpack 'use-system-libraries
12258 (lambda* (#:key inputs #:allow-other-keys)
12259 (substitute* "CMakeLists.txt"
12260 ;; Don't prefer static libs
12261 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12262 (("set\\(TBB_LIBRARIES") "message(")
12263 ;; Don't download anything
12264 (("DOWNLOAD_COMMAND") "DOWNLOAD_COMMAND echo")
12265 (("externalproject_add\\(libcereal") "message(")
12266 (("externalproject_add\\(libgff") "message(")
12267 (("externalproject_add\\(libtbb") "message(")
12268 (("externalproject_add\\(libdivsufsort") "message(")
12269 (("externalproject_add\\(libstadenio") "message(")
12270 (("externalproject_add_step\\(") "message("))
12271 (substitute* "src/CMakeLists.txt"
12272 (("add_dependencies") "#")
12273 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
12274 (string-append (assoc-ref inputs "libstadenio-for-salmon")
12275 "/lib/libstaden-read.so"))
12276 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12277 (string-append (assoc-ref inputs "libdivsufsort")
12278 "/lib/libdivsufsort.so"))
12279 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12280 (string-append (assoc-ref inputs "libdivsufsort")
12281 "/lib/libdivsufsort64.so"))
12282 (("lib/libdivsufsort.a") "/lib/libdivsufsort.so"))
12284 ;; Ensure that all headers can be found
12285 (setenv "CPLUS_INCLUDE_PATH"
12286 (string-append (or (getenv "CPLUS_INCLUDE_PATH") "")
12288 (assoc-ref inputs "eigen")
12289 "/include/eigen3"))
12291 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
12292 ;; run. It only exists after the install phase.
12293 (add-after 'unpack 'fix-tests
12295 (substitute* "src/CMakeLists.txt"
12296 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
12297 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
12306 (uri (git-reference
12307 (url "https://github.com/COMBINE-lab/RapMap.git")
12308 (commit (string-append "salmon-v" version))))
12309 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
12312 "1biplxf0csc7a8h1wf219b0vmjkvw6wk2zylhdklb577kgmihdms"))))
12313 ("jemalloc" ,jemalloc)
12316 ("libdivsufsort" ,libdivsufsort)
12317 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
12321 `(("pkg-config" ,pkg-config)))
12322 (home-page "https://github.com/COMBINE-lab/salmon")
12323 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
12324 (description "Salmon is a program to produce highly-accurate,
12325 transcript-level quantification estimates from RNA-seq data. Salmon achieves
12326 its accuracy and speed via a number of different innovations, including the
12327 use of lightweight alignments (accurate but fast-to-compute proxies for
12328 traditional read alignments) and massively-parallel stochastic collapsed
12329 variational inference.")
12330 (license license:gpl3+)))
12332 (define-public python-loompy
12334 (name "python-loompy")
12336 ;; The tarball on Pypi does not include the tests.
12339 (uri (git-reference
12340 (url "https://github.com/linnarsson-lab/loompy.git")
12342 (file-name (git-file-name name version))
12345 "12a5kjgiikapv93wahfw0frszx1lblnppyz3vs5gy8fgmgngra07"))))
12346 (build-system python-build-system)
12349 (modify-phases %standard-phases
12352 (setenv "PYTHONPATH"
12353 (string-append (getcwd) ":"
12354 (getenv "PYTHONPATH")))
12355 (invoke "pytest" "tests")
12358 `(("python-h5py" ,python-h5py)
12359 ("python-numpy" ,python-numpy)
12360 ("python-pandas" ,python-pandas)
12361 ("python-scipy" ,python-scipy)))
12363 `(("python-pytest" ,python-pytest)))
12364 (home-page "https://github.com/linnarsson-lab/loompy")
12365 (synopsis "Work with .loom files for single-cell RNA-seq data")
12366 (description "The loom file format is an efficient format for very large
12367 omics datasets, consisting of a main matrix, optional additional layers, a
12368 variable number of row and column annotations. Loom also supports sparse
12369 graphs. This library makes it easy to work with @file{.loom} files for
12370 single-cell RNA-seq data.")
12371 (license license:bsd-3)))
12373 ;; We cannot use the latest commit because it requires Java 9.
12374 (define-public java-forester
12375 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
12378 (name "java-forester")
12379 (version (string-append "0-" revision "." (string-take commit 7)))
12382 (uri (git-reference
12383 (url "https://github.com/cmzmasek/forester.git")
12385 (file-name (string-append name "-" version "-checkout"))
12388 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12389 (modules '((guix build utils)))
12392 ;; Delete bundled jars and pre-built classes
12393 (delete-file-recursively "forester/java/resources")
12394 (delete-file-recursively "forester/java/classes")
12395 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12396 ;; Delete bundled applications
12397 (delete-file-recursively "forester_applications")
12399 (build-system ant-build-system)
12401 `(#:tests? #f ; there are none
12403 #:modules ((guix build ant-build-system)
12405 (guix build java-utils)
12409 (modify-phases %standard-phases
12410 (add-after 'unpack 'chdir
12411 (lambda _ (chdir "forester/java") #t))
12412 (add-after 'chdir 'fix-dependencies
12414 (chmod "build.xml" #o664)
12415 (call-with-output-file "build.xml.new"
12419 (with-input-from-file "build.xml"
12420 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12421 `(;; Remove all unjar tags to avoid repacking classes.
12422 (unjar . ,(lambda _ '()))
12423 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12424 (*text* . ,(lambda (_ txt) txt))))
12426 (rename-file "build.xml.new" "build.xml")
12428 ;; FIXME: itext is difficult to package as it depends on a few
12429 ;; unpackaged libraries.
12430 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12432 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12433 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12434 (("pdf_written_to = PdfExporter.*")
12435 "throw new IOException(\"PDF export is not available.\");"))
12437 ;; There is no install target
12438 (replace 'install (install-jars ".")))))
12440 `(("java-commons-codec" ,java-commons-codec)
12441 ("java-openchart2" ,java-openchart2)))
12442 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12443 (synopsis "Phylogenomics libraries for Java")
12444 (description "Forester is a collection of Java libraries for
12445 phylogenomics and evolutionary biology research. It includes support for
12446 reading, writing, and exporting phylogenetic trees.")
12447 (license license:lgpl2.1+))))
12449 (define-public java-forester-1.005
12451 (name "java-forester")
12455 (uri (string-append "https://repo1.maven.org/maven2/"
12456 "org/biojava/thirdparty/forester/"
12457 version "/forester-" version "-sources.jar"))
12458 (file-name (string-append name "-" version ".jar"))
12461 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12462 (build-system ant-build-system)
12464 `(#:tests? #f ; there are none
12466 #:modules ((guix build ant-build-system)
12468 (guix build java-utils)
12472 (modify-phases %standard-phases
12473 (add-after 'unpack 'fix-dependencies
12474 (lambda* (#:key inputs #:allow-other-keys)
12475 (call-with-output-file "build.xml"
12479 (with-input-from-file "src/build.xml"
12480 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12481 `(;; Remove all unjar tags to avoid repacking classes.
12482 (unjar . ,(lambda _ '()))
12483 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12484 (*text* . ,(lambda (_ txt) txt))))
12486 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12487 "synth_look_and_feel_1.xml")
12488 (copy-file (assoc-ref inputs "phyloxml.xsd")
12490 (substitute* "build.xml"
12491 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12492 "synth_look_and_feel_1.xml")
12493 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12496 ;; FIXME: itext is difficult to package as it depends on a few
12497 ;; unpackaged libraries.
12498 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12500 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12501 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12502 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12503 (("pdf_written_to = PdfExporter.*")
12504 "throw new IOException(\"PDF export is not available.\"); /*")
12505 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12506 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12508 (add-after 'unpack 'delete-pre-built-classes
12509 (lambda _ (delete-file-recursively "src/classes") #t))
12510 ;; There is no install target
12511 (replace 'install (install-jars ".")))))
12513 `(("java-commons-codec" ,java-commons-codec)
12514 ("java-openchart2" ,java-openchart2)))
12515 ;; The source archive does not contain the resources.
12520 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12521 "b61cc2dcede0bede317db362472333115756b8c6/"
12522 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12523 (file-name (string-append name "-phyloxml-" version ".xsd"))
12526 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12527 ("synth_look_and_feel_1.xml"
12530 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12531 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12532 "forester/java/classes/resources/"
12533 "synth_look_and_feel_1.xml"))
12534 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12537 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12538 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12539 (synopsis "Phylogenomics libraries for Java")
12540 (description "Forester is a collection of Java libraries for
12541 phylogenomics and evolutionary biology research. It includes support for
12542 reading, writing, and exporting phylogenetic trees.")
12543 (license license:lgpl2.1+)))
12545 (define-public java-biojava-core
12547 (name "java-biojava-core")
12551 (uri (git-reference
12552 (url "https://github.com/biojava/biojava")
12553 (commit (string-append "biojava-" version))))
12554 (file-name (string-append name "-" version "-checkout"))
12557 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12558 (build-system ant-build-system)
12561 #:jar-name "biojava-core.jar"
12562 #:source-dir "biojava-core/src/main/java/"
12563 #:test-dir "biojava-core/src/test"
12564 ;; These tests seem to require internet access.
12565 #:test-exclude (list "**/SearchIOTest.java"
12566 "**/BlastXMLParserTest.java"
12567 "**/GenbankCookbookTest.java"
12568 "**/GenbankProxySequenceReaderTest.java")
12570 (modify-phases %standard-phases
12571 (add-before 'build 'copy-resources
12573 (copy-recursively "biojava-core/src/main/resources"
12576 (add-before 'check 'copy-test-resources
12578 (copy-recursively "biojava-core/src/test/resources"
12579 "build/test-classes")
12582 `(("java-log4j-api" ,java-log4j-api)
12583 ("java-log4j-core" ,java-log4j-core)
12584 ("java-slf4j-api" ,java-slf4j-api)
12585 ("java-slf4j-simple" ,java-slf4j-simple)))
12587 `(("java-junit" ,java-junit)
12588 ("java-hamcrest-core" ,java-hamcrest-core)))
12589 (home-page "http://biojava.org")
12590 (synopsis "Core libraries of Java framework for processing biological data")
12591 (description "BioJava is a project dedicated to providing a Java framework
12592 for processing biological data. It provides analytical and statistical
12593 routines, parsers for common file formats, reference implementations of
12594 popular algorithms, and allows the manipulation of sequences and 3D
12595 structures. The goal of the biojava project is to facilitate rapid
12596 application development for bioinformatics.
12598 This package provides the core libraries.")
12599 (license license:lgpl2.1+)))
12601 (define-public java-biojava-phylo
12602 (package (inherit java-biojava-core)
12603 (name "java-biojava-phylo")
12604 (build-system ant-build-system)
12607 #:jar-name "biojava-phylo.jar"
12608 #:source-dir "biojava-phylo/src/main/java/"
12609 #:test-dir "biojava-phylo/src/test"
12611 (modify-phases %standard-phases
12612 (add-before 'build 'copy-resources
12614 (copy-recursively "biojava-phylo/src/main/resources"
12617 (add-before 'check 'copy-test-resources
12619 (copy-recursively "biojava-phylo/src/test/resources"
12620 "build/test-classes")
12623 `(("java-log4j-api" ,java-log4j-api)
12624 ("java-log4j-core" ,java-log4j-core)
12625 ("java-slf4j-api" ,java-slf4j-api)
12626 ("java-slf4j-simple" ,java-slf4j-simple)
12627 ("java-biojava-core" ,java-biojava-core)
12628 ("java-forester" ,java-forester)))
12630 `(("java-junit" ,java-junit)
12631 ("java-hamcrest-core" ,java-hamcrest-core)))
12632 (home-page "http://biojava.org")
12633 (synopsis "Biojava interface to the forester phylogenomics library")
12634 (description "The phylo module provides a biojava interface layer to the
12635 forester phylogenomics library for constructing phylogenetic trees.")))
12637 (define-public java-biojava-alignment
12638 (package (inherit java-biojava-core)
12639 (name "java-biojava-alignment")
12640 (build-system ant-build-system)
12643 #:jar-name "biojava-alignment.jar"
12644 #:source-dir "biojava-alignment/src/main/java/"
12645 #:test-dir "biojava-alignment/src/test"
12647 (modify-phases %standard-phases
12648 (add-before 'build 'copy-resources
12650 (copy-recursively "biojava-alignment/src/main/resources"
12653 (add-before 'check 'copy-test-resources
12655 (copy-recursively "biojava-alignment/src/test/resources"
12656 "build/test-classes")
12659 `(("java-log4j-api" ,java-log4j-api)
12660 ("java-log4j-core" ,java-log4j-core)
12661 ("java-slf4j-api" ,java-slf4j-api)
12662 ("java-slf4j-simple" ,java-slf4j-simple)
12663 ("java-biojava-core" ,java-biojava-core)
12664 ("java-biojava-phylo" ,java-biojava-phylo)
12665 ("java-forester" ,java-forester)))
12667 `(("java-junit" ,java-junit)
12668 ("java-hamcrest-core" ,java-hamcrest-core)))
12669 (home-page "http://biojava.org")
12670 (synopsis "Biojava API for genetic sequence alignment")
12671 (description "The alignment module of BioJava provides an API that
12675 @item implementations of dynamic programming algorithms for sequence
12677 @item reading and writing of popular alignment file formats;
12678 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12681 (define-public java-biojava-core-4.0
12682 (package (inherit java-biojava-core)
12683 (name "java-biojava-core")
12687 (uri (git-reference
12688 (url "https://github.com/biojava/biojava")
12689 (commit (string-append "biojava-" version))))
12690 (file-name (string-append name "-" version "-checkout"))
12693 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12695 (define-public java-biojava-phylo-4.0
12696 (package (inherit java-biojava-core-4.0)
12697 (name "java-biojava-phylo")
12698 (build-system ant-build-system)
12701 #:jar-name "biojava-phylo.jar"
12702 #:source-dir "biojava-phylo/src/main/java/"
12703 #:test-dir "biojava-phylo/src/test"
12705 (modify-phases %standard-phases
12706 (add-before 'build 'copy-resources
12708 (copy-recursively "biojava-phylo/src/main/resources"
12711 (add-before 'check 'copy-test-resources
12713 (copy-recursively "biojava-phylo/src/test/resources"
12714 "build/test-classes")
12717 `(("java-log4j-api" ,java-log4j-api)
12718 ("java-log4j-core" ,java-log4j-core)
12719 ("java-slf4j-api" ,java-slf4j-api)
12720 ("java-slf4j-simple" ,java-slf4j-simple)
12721 ("java-biojava-core" ,java-biojava-core-4.0)
12722 ("java-forester" ,java-forester-1.005)))
12724 `(("java-junit" ,java-junit)
12725 ("java-hamcrest-core" ,java-hamcrest-core)))
12726 (home-page "http://biojava.org")
12727 (synopsis "Biojava interface to the forester phylogenomics library")
12728 (description "The phylo module provides a biojava interface layer to the
12729 forester phylogenomics library for constructing phylogenetic trees.")))
12731 (define-public java-biojava-alignment-4.0
12732 (package (inherit java-biojava-core-4.0)
12733 (name "java-biojava-alignment")
12734 (build-system ant-build-system)
12737 #:jar-name "biojava-alignment.jar"
12738 #:source-dir "biojava-alignment/src/main/java/"
12739 #:test-dir "biojava-alignment/src/test"
12741 (modify-phases %standard-phases
12742 (add-before 'build 'copy-resources
12744 (copy-recursively "biojava-alignment/src/main/resources"
12747 (add-before 'check 'copy-test-resources
12749 (copy-recursively "biojava-alignment/src/test/resources"
12750 "build/test-classes")
12753 `(("java-log4j-api" ,java-log4j-api)
12754 ("java-log4j-core" ,java-log4j-core)
12755 ("java-slf4j-api" ,java-slf4j-api)
12756 ("java-slf4j-simple" ,java-slf4j-simple)
12757 ("java-biojava-core" ,java-biojava-core-4.0)
12758 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12759 ("java-forester" ,java-forester-1.005)))
12761 `(("java-junit" ,java-junit)
12762 ("java-hamcrest-core" ,java-hamcrest-core)))
12763 (home-page "http://biojava.org")
12764 (synopsis "Biojava API for genetic sequence alignment")
12765 (description "The alignment module of BioJava provides an API that
12769 @item implementations of dynamic programming algorithms for sequence
12771 @item reading and writing of popular alignment file formats;
12772 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12775 (define-public dropseq-tools
12777 (name "dropseq-tools")
12782 (uri "http://mccarrolllab.com/download/1276/")
12783 (file-name (string-append "dropseq-tools-" version ".zip"))
12786 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12787 ;; Delete bundled libraries
12788 (modules '((guix build utils)))
12791 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12792 (delete-file-recursively "3rdParty")
12794 (build-system ant-build-system)
12796 `(#:tests? #f ; test data are not included
12797 #:test-target "test"
12798 #:build-target "all"
12799 #:source-dir "public/src/"
12802 (list (string-append "-Dpicard.executable.dir="
12803 (assoc-ref %build-inputs "java-picard")
12805 #:modules ((ice-9 match)
12808 (guix build java-utils)
12809 (guix build ant-build-system))
12811 (modify-phases %standard-phases
12812 ;; FIXME: fails with "java.io.FileNotFoundException:
12813 ;; /gnu/store/…-dropseq-tools-1.13/share/java/lib/biojava-alignment.jar"
12814 (delete 'generate-jar-indices)
12815 ;; All dependencies must be linked to "lib", because that's where
12816 ;; they will be searched for when the Class-Path property of the
12817 ;; manifest is computed.
12818 (add-after 'unpack 'record-references
12819 (lambda* (#:key inputs #:allow-other-keys)
12820 (mkdir-p "jar/lib")
12821 (let ((dirs (filter-map (match-lambda
12823 (if (and (string-prefix? "java-" name)
12824 (not (string=? name "java-testng")))
12827 (for-each (lambda (jar)
12828 (symlink jar (string-append "jar/lib/" (basename jar))))
12829 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12832 ;; There is no installation target
12834 (lambda* (#:key inputs outputs #:allow-other-keys)
12835 (let* ((out (assoc-ref outputs "out"))
12836 (bin (string-append out "/bin"))
12837 (share (string-append out "/share/java/"))
12838 (lib (string-append share "/lib/"))
12839 (scripts (list "BAMTagHistogram"
12840 "BAMTagofTagCounts"
12841 "BaseDistributionAtReadPosition"
12842 "CollapseBarcodesInPlace"
12843 "CollapseTagWithContext"
12845 "CreateIntervalsFiles"
12846 "DetectBeadSynthesisErrors"
12847 "DigitalExpression"
12848 "Drop-seq_alignment.sh"
12851 "GatherGeneGCLength"
12852 "GatherMolecularBarcodeDistributionByGene"
12853 "GatherReadQualityMetrics"
12856 "SelectCellsByNumTranscripts"
12857 "SingleCellRnaSeqMetricsCollector"
12858 "TagBamWithReadSequenceExtended"
12859 "TagReadWithGeneExon"
12860 "TagReadWithInterval"
12861 "TrimStartingSequence"
12862 "ValidateReference")))
12863 (for-each mkdir-p (list bin share lib))
12864 (install-file "dist/dropseq.jar" share)
12865 (for-each (lambda (script)
12866 (chmod script #o555)
12867 (install-file script bin))
12869 (substitute* (map (lambda (script)
12870 (string-append bin "/" script))
12872 (("^java") (which "java"))
12873 (("jar_deploy_dir=.*")
12874 (string-append "jar_deploy_dir=" share "\n"))))
12876 ;; FIXME: We do this after stripping jars because we don't want it to
12877 ;; copy all these jars and strip them. We only want to install
12878 ;; links. Arguably, this is a problem with the ant-build-system.
12879 (add-after 'strip-jar-timestamps 'install-links
12880 (lambda* (#:key outputs #:allow-other-keys)
12881 (let* ((out (assoc-ref outputs "out"))
12882 (share (string-append out "/share/java/"))
12883 (lib (string-append share "/lib/")))
12884 (for-each (lambda (jar)
12885 (symlink (readlink jar)
12886 (string-append lib (basename jar))))
12887 (find-files "jar/lib" "\\.jar$")))
12890 `(("jdk" ,icedtea-8)
12891 ("java-picard" ,java-picard-2.10.3)
12892 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12893 ("java-commons-math3" ,java-commons-math3)
12894 ("java-commons-jexl2" ,java-commons-jexl-2)
12895 ("java-commons-collections4" ,java-commons-collections4)
12896 ("java-commons-lang2" ,java-commons-lang)
12897 ("java-commons-io" ,java-commons-io)
12898 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12899 ("java-guava" ,java-guava)
12900 ("java-la4j" ,java-la4j)
12901 ("java-biojava-core" ,java-biojava-core-4.0)
12902 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12903 ("java-jdistlib" ,java-jdistlib)
12904 ("java-simple-xml" ,java-simple-xml)
12905 ("java-snakeyaml" ,java-snakeyaml)))
12908 ("java-testng" ,java-testng)))
12909 (home-page "http://mccarrolllab.com/dropseq/")
12910 (synopsis "Tools for Drop-seq analyses")
12911 (description "Drop-seq is a technology to enable biologists to
12912 analyze RNA expression genome-wide in thousands of individual cells at
12913 once. This package provides tools to perform Drop-seq analyses.")
12914 (license license:expat)))
12916 (define-public pigx-rnaseq
12918 (name "pigx-rnaseq")
12922 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12923 "releases/download/v" version
12924 "/pigx_rnaseq-" version ".tar.gz"))
12927 "0z3hr120wk2vrlmlpz1vp3n9wy3rq4y2mnzh2vf08qgqn2xfdwcw"))))
12928 (build-system gnu-build-system)
12930 `(#:parallel-tests? #f ; not supported
12932 (modify-phases %standard-phases
12933 ;; "test.sh" runs STAR, which requires excessive amounts of memory.
12934 (add-after 'unpack 'disable-resource-intensive-test
12936 (substitute* "Makefile.in"
12937 (("(^ tests/test_trim_galore/test.sh).*" _ m) m)
12938 (("^ tests/test_multiqc/test.sh") "")
12939 (("^ test.sh") ""))
12942 `(("coreutils" ,coreutils)
12945 ("snakemake" ,snakemake)
12947 ("multiqc" ,multiqc)
12949 ("trim-galore" ,trim-galore)
12951 ("samtools" ,samtools)
12952 ("r-minimal" ,r-minimal)
12953 ("r-rmarkdown" ,r-rmarkdown)
12954 ("r-ggplot2" ,r-ggplot2)
12955 ("r-ggrepel" ,r-ggrepel)
12956 ("r-gprofiler" ,r-gprofiler)
12957 ("r-deseq2" ,r-deseq2)
12959 ("r-knitr" ,r-knitr)
12960 ("r-pheatmap" ,r-pheatmap)
12961 ("r-corrplot" ,r-corrplot)
12962 ("r-reshape2" ,r-reshape2)
12963 ("r-plotly" ,r-plotly)
12964 ("r-scales" ,r-scales)
12965 ("r-summarizedexperiment" ,r-summarizedexperiment)
12966 ("r-crosstalk" ,r-crosstalk)
12967 ("r-tximport" ,r-tximport)
12968 ("r-rtracklayer" ,r-rtracklayer)
12969 ("r-rjson" ,r-rjson)
12971 ("ghc-pandoc" ,ghc-pandoc)
12972 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12973 ("python-wrapper" ,python-wrapper)
12974 ("python-pyyaml" ,python-pyyaml)))
12975 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12976 (synopsis "Analysis pipeline for RNA sequencing experiments")
12977 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
12978 reporting for RNA sequencing experiments. It is easy to use and produces high
12979 quality reports. The inputs are reads files from the sequencing experiment,
12980 and a configuration file which describes the experiment. In addition to
12981 quality control of the experiment, the pipeline produces a differential
12982 expression report comparing samples in an easily configurable manner.")
12983 (license license:gpl3+)))
12985 (define-public pigx-chipseq
12987 (name "pigx-chipseq")
12991 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
12992 "releases/download/v" version
12993 "/pigx_chipseq-" version ".tar.gz"))
12996 "0xbvgqpk32a8iczhvac56cacr46rdkqb0allhhpvmj940idf72bi"))))
12997 (build-system gnu-build-system)
12998 ;; parts of the tests rely on access to the network
12999 (arguments '(#:tests? #f))
13002 ("coreutils" ,coreutils)
13003 ("r-minimal" ,r-minimal)
13004 ("r-argparser" ,r-argparser)
13005 ("r-biocparallel" ,r-biocparallel)
13006 ("r-biostrings" ,r-biostrings)
13007 ("r-chipseq" ,r-chipseq)
13008 ("r-data-table" ,r-data-table)
13009 ("r-dplyr" ,r-dplyr)
13010 ("r-genomation" ,r-genomation)
13011 ("r-genomicalignments" ,r-genomicalignments)
13012 ("r-genomicranges" ,r-genomicranges)
13013 ("r-rsamtools" ,r-rsamtools)
13014 ("r-rtracklayer" ,r-rtracklayer)
13015 ("r-s4vectors" ,r-s4vectors)
13016 ("r-stringr" ,r-stringr)
13017 ("r-tibble" ,r-tibble)
13018 ("r-tidyr" ,r-tidyr)
13019 ("r-jsonlite" ,r-jsonlite)
13020 ("r-heatmaply" ,r-heatmaply)
13021 ("r-htmlwidgets" ,r-htmlwidgets)
13022 ("r-ggplot2" ,r-ggplot2)
13023 ("r-plotly" ,r-plotly)
13024 ("r-rmarkdown" ,r-rmarkdown)
13025 ("python-wrapper" ,python-wrapper)
13026 ("python-pyyaml" ,python-pyyaml)
13027 ("python-magic" ,python-magic)
13028 ("python-xlrd" ,python-xlrd)
13029 ("trim-galore" ,trim-galore)
13031 ("multiqc" ,multiqc)
13033 ("ghc-pandoc" ,ghc-pandoc)
13034 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
13038 ("snakemake" ,snakemake)
13039 ("samtools" ,samtools)
13040 ("bedtools" ,bedtools)
13041 ("kentutils" ,kentutils)))
13043 `(("python-pytest" ,python-pytest)))
13044 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13045 (synopsis "Analysis pipeline for ChIP sequencing experiments")
13046 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
13047 calling and reporting for ChIP sequencing experiments. It is easy to use and
13048 produces high quality reports. The inputs are reads files from the sequencing
13049 experiment, and a configuration file which describes the experiment. In
13050 addition to quality control of the experiment, the pipeline enables to set up
13051 multiple peak calling analysis and allows the generation of a UCSC track hub
13052 in an easily configurable manner.")
13053 (license license:gpl3+)))
13055 (define-public pigx-bsseq
13057 (name "pigx-bsseq")
13061 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
13062 "releases/download/v" version
13063 "/pigx_bsseq-" version ".tar.gz"))
13066 "0l97wvkq4diq8lcarraj33bby1zzf0w804jwi8mlc5qddp8idwhy"))))
13067 (build-system gnu-build-system)
13070 (modify-phases %standard-phases
13071 (add-before 'check 'set-timezone
13072 ;; The readr package is picky about timezones.
13073 (lambda* (#:key inputs #:allow-other-keys)
13074 (setenv "TZ" "UTC+1")
13076 (string-append (assoc-ref inputs "tzdata")
13077 "/share/zoneinfo"))
13080 `(("tzdata" ,tzdata)))
13082 `(("coreutils" ,coreutils)
13085 ("r-minimal" ,r-minimal)
13086 ("r-annotationhub" ,r-annotationhub)
13088 ("r-genomation" ,r-genomation)
13089 ("r-methylkit" ,r-methylkit)
13090 ("r-rtracklayer" ,r-rtracklayer)
13091 ("r-rmarkdown" ,r-rmarkdown)
13092 ("r-bookdown" ,r-bookdown)
13093 ("r-ggplot2" ,r-ggplot2)
13094 ("r-ggbio" ,r-ggbio)
13095 ("ghc-pandoc" ,ghc-pandoc)
13096 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
13097 ("python-wrapper" ,python-wrapper)
13098 ("python-pyyaml" ,python-pyyaml)
13099 ("snakemake" ,snakemake)
13100 ("bismark" ,bismark)
13103 ("trim-galore" ,trim-galore)
13104 ("cutadapt" ,cutadapt)
13105 ("samtools" ,samtools)))
13106 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13107 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
13108 (description "PiGx BSseq is a data processing pipeline for raw fastq read
13109 data of bisulfite experiments; it produces reports on aggregate methylation
13110 and coverage and can be used to produce information on differential
13111 methylation and segmentation.")
13112 (license license:gpl3+)))
13114 (define-public pigx-scrnaseq
13116 (name "pigx-scrnaseq")
13120 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/"
13121 "releases/download/v" version
13122 "/pigx_scrnaseq-" version ".tar.gz"))
13125 "1d5l3gywypi67yz9advxq5xkgfhr4733gj0bwnngm723i3hdf5w9"))))
13126 (build-system gnu-build-system)
13128 `(("coreutils" ,coreutils)
13131 ("flexbar" ,flexbar)
13132 ("java" ,icedtea-8)
13133 ("jellyfish" ,jellyfish)
13134 ("python-wrapper" ,python-wrapper)
13135 ("python-pyyaml" ,python-pyyaml)
13136 ("python-pandas" ,python-pandas)
13137 ("python-magic" ,python-magic)
13138 ("python-numpy" ,python-numpy)
13139 ("python-loompy" ,python-loompy)
13140 ("ghc-pandoc" ,ghc-pandoc)
13141 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
13142 ("samtools" ,samtools)
13143 ("snakemake" ,snakemake)
13145 ("r-minimal" ,r-minimal)
13146 ("r-argparser" ,r-argparser)
13147 ("r-cowplot" ,r-cowplot)
13148 ("r-data-table" ,r-data-table)
13149 ("r-delayedarray" ,r-delayedarray)
13150 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
13151 ("r-dplyr" ,r-dplyr)
13152 ("r-dropbead" ,r-dropbead)
13154 ("r-genomicalignments" ,r-genomicalignments)
13155 ("r-genomicfiles" ,r-genomicfiles)
13156 ("r-genomicranges" ,r-genomicranges)
13157 ("r-ggplot2" ,r-ggplot2)
13158 ("r-hdf5array" ,r-hdf5array)
13159 ("r-pheatmap" ,r-pheatmap)
13160 ("r-rmarkdown" ,r-rmarkdown)
13161 ("r-rsamtools" ,r-rsamtools)
13162 ("r-rtracklayer" ,r-rtracklayer)
13163 ("r-rtsne" ,r-rtsne)
13164 ("r-scater" ,r-scater)
13165 ("r-scran" ,r-scran)
13166 ("r-seurat" ,r-seurat)
13167 ("r-singlecellexperiment" ,r-singlecellexperiment)
13168 ("r-stringr" ,r-stringr)
13169 ("r-yaml" ,r-yaml)))
13170 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13171 (synopsis "Analysis pipeline for single-cell RNA sequencing experiments")
13172 (description "PiGX scRNAseq is an analysis pipeline for preprocessing and
13173 quality control for single cell RNA sequencing experiments. The inputs are
13174 read files from the sequencing experiment, and a configuration file which
13175 describes the experiment. It produces processed files for downstream analysis
13176 and interactive quality reports. The pipeline is designed to work with UMI
13178 (license license:gpl3+)))
13180 (define-public pigx
13186 (uri (string-append "https://github.com/BIMSBbioinfo/pigx/"
13187 "releases/download/v" version
13188 "/pigx-" version ".tar.gz"))
13191 "1i5njdy1clj5ncw45d16p7mwmqvb1ilikl9n797pxklc3f4s7mq7"))))
13192 (build-system gnu-build-system)
13194 `(("python" ,python)
13195 ("pigx-bsseq" ,pigx-bsseq)
13196 ("pigx-chipseq" ,pigx-chipseq)
13197 ("pigx-rnaseq" ,pigx-rnaseq)
13198 ("pigx-scrnaseq" ,pigx-scrnaseq)))
13199 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13200 (synopsis "Analysis pipelines for genomics")
13201 (description "PiGx is a collection of genomics pipelines. It includes the
13202 following pipelines:
13205 @item PiGx BSseq for raw fastq read data of bisulfite experiments
13206 @item PiGx RNAseq for RNAseq samples
13207 @item PiGx scRNAseq for single cell dropseq analysis
13208 @item PiGx ChIPseq for reads from ChIPseq experiments
13211 All pipelines are easily configured with a simple sample sheet and a
13212 descriptive settings file. The result is a set of comprehensive, interactive
13213 HTML reports with interesting findings about your samples.")
13214 (license license:gpl3+)))
13216 (define-public genrich
13222 (uri (git-reference
13223 (url "https://github.com/jsh58/Genrich.git")
13224 (commit (string-append "v" version))))
13225 (file-name (git-file-name name version))
13228 "0x0q6z0208n3cxzqjla4rgjqpyqgwpmz27852lcvzkzaigymq4zp"))))
13229 (build-system gnu-build-system)
13231 `(#:tests? #f ; there are none
13233 (modify-phases %standard-phases
13234 (delete 'configure)
13236 (lambda* (#:key outputs #:allow-other-keys)
13237 (install-file "Genrich" (string-append (assoc-ref outputs "out") "/bin"))
13241 (home-page "https://github.com/jsh58/Genrich")
13242 (synopsis "Detecting sites of genomic enrichment")
13243 (description "Genrich is a peak-caller for genomic enrichment
13244 assays (e.g. ChIP-seq, ATAC-seq). It analyzes alignment files generated
13245 following the assay and produces a file detailing peaks of significant
13247 (license license:expat)))
13249 (define-public mantis
13250 (let ((commit "4ffd171632c2cb0056a86d709dfd2bf21bc69b84")
13254 (version (git-version "0" revision commit))
13257 (uri (git-reference
13258 (url "https://github.com/splatlab/mantis.git")
13260 (file-name (git-file-name name version))
13263 "0iqbr0dhmlc8mzpirmm2s4pkzkwdgrcx50yx6cv3wlr2qi064p55"))))
13264 (build-system cmake-build-system)
13265 (arguments '(#:tests? #f)) ; there are none
13267 `(("sdsl-lite" ,sdsl-lite)
13268 ("openssl" ,openssl)
13270 (home-page "https://github.com/splatlab/mantis")
13271 (synopsis "Large-scale sequence-search index data structure")
13272 (description "Mantis is a space-efficient data structure that can be
13273 used to index thousands of raw-read genomics experiments and facilitate
13274 large-scale sequence searches on those experiments. Mantis uses counting
13275 quotient filters instead of Bloom filters, enabling rapid index builds and
13276 queries, small indexes, and exact results, i.e., no false positives or
13277 negatives. Furthermore, Mantis is also a colored de Bruijn graph
13278 representation, so it supports fast graph traversal and other topological
13279 analyses in addition to large-scale sequence-level searches.")
13280 ;; uses __uint128_t and inline assembly
13281 (supported-systems '("x86_64-linux"))
13282 (license license:bsd-3))))
13284 (define-public r-diversitree
13286 (name "r-diversitree")
13291 (uri (cran-uri "diversitree" version))
13294 "00vi4klywi35hd170ksjv3xja3hqqbkcidcnrrlpgv4179k0azix"))))
13295 (build-system r-build-system)
13297 `(("gfortran" ,gfortran)))
13298 (inputs `(("fftw" ,fftw) ("gsl" ,gsl)))
13301 ("r-desolve" ,r-desolve)
13303 ("r-subplex" ,r-subplex)))
13304 (home-page "https://www.zoology.ubc.ca/prog/diversitree")
13305 (synopsis "Comparative 'phylogenetic' analyses of diversification")
13306 (description "This package contains a number of comparative \"phylogenetic\"
13307 methods, mostly focusing on analysing diversification and character evolution.
13308 Contains implementations of \"BiSSE\" (Binary State Speciation and Extinction)
13309 and its unresolved tree extensions, \"MuSSE\" (Multiple State Speciation and
13310 Extinction), \"QuaSSE\", \"GeoSSE\", and \"BiSSE-ness\" Other included methods
13311 include Markov models of discrete and continuous trait evolution and constant
13312 rate speciation and extinction.")
13313 (license license:gpl2+)))
13315 (define-public sjcount
13316 ;; There is no tag for version 3.2, nor is there a release archive.
13317 (let ((commit "292d3917cadb3f6834c81e509c30e61cd7ead6e5")
13321 (version (git-version "3.2" revision commit))
13324 (uri (git-reference
13325 (url "https://github.com/pervouchine/sjcount-full.git")
13327 (file-name (string-append name "-" version "-checkout"))
13330 "0gdgj35j249f04rqgq8ymcc1xg1vi9kzbajnjqpaq2wpbh8bl234"))))
13331 (build-system gnu-build-system)
13333 `(#:tests? #f ; requires a 1.4G test file
13335 (list (string-append "SAMTOOLS_DIR="
13336 (assoc-ref %build-inputs "samtools")
13339 (modify-phases %standard-phases
13340 (replace 'configure
13341 (lambda* (#:key inputs #:allow-other-keys)
13342 (substitute* "makefile"
13343 (("-I \\$\\{SAMTOOLS_DIR\\}")
13344 (string-append "-I" (assoc-ref inputs "samtools")
13345 "/include/samtools"))
13346 (("-lz ") "-lz -lpthread "))
13349 (lambda* (#:key outputs #:allow-other-keys)
13350 (for-each (lambda (tool)
13352 (string-append (assoc-ref outputs "out")
13354 '("j_count" "b_count" "sjcount"))
13357 `(("samtools" ,samtools-0.1)
13359 (home-page "https://github.com/pervouchine/sjcount-full/")
13360 (synopsis "Annotation-agnostic splice junction counting pipeline")
13361 (description "Sjcount is a utility for fast quantification of splice
13362 junctions in RNA-seq data. It is annotation-agnostic and offset-aware. This
13363 version does count multisplits.")
13364 (license license:gpl3+))))
13366 (define-public minimap2
13373 (uri (string-append "https://github.com/lh3/minimap2/"
13374 "releases/download/v" version "/"
13375 "minimap2-" version ".tar.bz2"))
13378 "0hi7i9pzxhvjj44khzzzj1lrn5gb5837arr4wgln7k1k5n4ci2mn"))))
13379 (build-system gnu-build-system)
13381 `(#:tests? #f ; there are none
13384 (let ((system ,(or (%current-target-system)
13385 (%current-system))))
13387 ((string-prefix? "x86_64" system)
13389 ((or (string-prefix? "armhf" system)
13390 (string-prefix? "aarch64" system))
13392 (else "sse2only=1"))))
13394 (modify-phases %standard-phases
13395 (delete 'configure)
13397 (lambda* (#:key outputs #:allow-other-keys)
13398 (let* ((out (assoc-ref outputs "out"))
13399 (bin (string-append out "/bin"))
13400 (man (string-append out "/share/man/man1")))
13401 (install-file "minimap2" bin)
13403 (install-file "minimap2.1" man))
13407 (home-page "https://lh3.github.io/minimap2/")
13408 (synopsis "Pairwise aligner for genomic and spliced nucleotide sequences")
13409 (description "Minimap2 is a versatile sequence alignment program that
13410 aligns DNA or mRNA sequences against a large reference database. Typical use
13414 @item mapping PacBio or Oxford Nanopore genomic reads to the human genome;
13415 @item finding overlaps between long reads with error rate up to ~15%;
13416 @item splice-aware alignment of PacBio Iso-Seq or Nanopore cDNA or Direct RNA
13417 reads against a reference genome;
13418 @item aligning Illumina single- or paired-end reads;
13419 @item assembly-to-assembly alignment;
13420 @item full-genome alignment between two closely related species with
13421 divergence below ~15%.
13423 (license license:expat)))
13425 (define-public miniasm
13431 (uri (string-append
13432 "https://github.com/lh3/miniasm/archive/v"
13433 version ".tar.gz"))
13434 (file-name (string-append name "-" version ".tar.gz"))
13437 "0g89pa98dvh34idv7w1zv12bsbyr3a11c4qb1cdcz68gyda88s4v"))))
13438 (build-system gnu-build-system)
13442 `(#:tests? #f ; There are no tests.
13444 (modify-phases %standard-phases
13445 (delete 'configure)
13447 (lambda* (#:key inputs outputs #:allow-other-keys)
13448 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
13449 (install-file "miniasm" bin)
13450 (install-file "minidot" bin)))))))
13451 (home-page "https://github.com/lh3/miniasm")
13452 (synopsis "Ultrafast de novo assembly for long noisy reads")
13453 (description "Miniasm is a very fast OLC-based de novo assembler for noisy
13454 long reads. It takes all-vs-all read self-mappings (typically by minimap) as
13455 input and outputs an assembly graph in the GFA format. Different from
13456 mainstream assemblers, miniasm does not have a consensus step. It simply
13457 concatenates pieces of read sequences to generate the final unitig sequences.
13458 Thus the per-base error rate is similar to the raw input reads.")
13459 (license license:expat)))
13461 (define-public r-circus
13468 (uri (git-reference
13469 (url "https://github.com/BIMSBbioinfo/ciRcus.git")
13470 (commit (string-append "v" version))))
13471 (file-name (git-file-name name version))
13474 "0jhjn3ilb057hbf6yzrihj13ifxxs32y7nkby8l3lkm28dg4p97h"))))
13475 (build-system r-build-system)
13477 `(("r-annotationdbi" ,r-annotationdbi)
13478 ("r-annotationhub" ,r-annotationhub)
13479 ("r-biomart" ,r-biomart)
13480 ("r-data-table" ,r-data-table)
13482 ("r-genomicfeatures" ,r-genomicfeatures)
13483 ("r-genomicranges" ,r-genomicranges)
13484 ("r-ggplot2" ,r-ggplot2)
13486 ("r-iranges" ,r-iranges)
13487 ("r-rcolorbrewer" ,r-rcolorbrewer)
13488 ("r-rmysql" ,r-rmysql)
13489 ("r-s4vectors" ,r-s4vectors)
13490 ("r-stringr" ,r-stringr)
13491 ("r-summarizedexperiment" ,r-summarizedexperiment)))
13493 `(("r-knitr" ,r-knitr)))
13494 (home-page "https://github.com/BIMSBbioinfo/ciRcus")
13495 (synopsis "Annotation, analysis and visualization of circRNA data")
13496 (description "Circus is an R package for annotation, analysis and
13497 visualization of circRNA data. Users can annotate their circRNA candidates
13498 with host genes, gene featrues they are spliced from, and discriminate between
13499 known and yet unknown splice junctions. Circular-to-linear ratios of circRNAs
13500 can be calculated, and a number of descriptive plots easily generated.")
13501 (license license:artistic2.0)))
13503 (define-public gffread
13504 ;; We cannot use the tagged release because it is not in sync with gclib.
13505 ;; See https://github.com/gpertea/gffread/issues/26
13506 (let ((commit "ba7535fcb3cea55a6e5a491d916e93b454e87fd0")
13510 (version (git-version "0.9.12" revision commit))
13514 (uri (git-reference
13515 (url "https://github.com/gpertea/gffread.git")
13517 (file-name (git-file-name name version))
13520 "1dl2nbcg96lxpd0drg48ssa8343nf7pw9s9mkrc4mjjmfwsin3ki"))))
13521 (build-system gnu-build-system)
13523 `(#:tests? #f ; no check target
13525 (list "GCLDIR=gclib")
13527 (modify-phases %standard-phases
13528 (delete 'configure)
13529 (add-after 'unpack 'copy-gclib-source
13530 (lambda* (#:key inputs #:allow-other-keys)
13532 (copy-recursively (assoc-ref inputs "gclib-source") "gclib")
13534 ;; There is no install target
13536 (lambda* (#:key outputs #:allow-other-keys)
13537 (let* ((out (assoc-ref outputs "out"))
13538 (bin (string-append out "/bin")))
13539 (install-file "gffread" bin))
13543 ,(let ((version "0.10.3")
13544 (commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13548 (uri (git-reference
13549 (url "https://github.com/gpertea/gclib.git")
13551 (file-name (git-file-name "gclib" version))
13554 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13555 (home-page "https://github.com/gpertea/gffread/")
13556 (synopsis "Parse and convert GFF/GTF files")
13558 "This package provides a GFF/GTF file parsing utility providing format
13559 conversions, region filtering, FASTA sequence extraction and more.")
13560 ;; gffread is under Expat, but gclib is under Artistic 2.0
13561 (license (list license:expat
13562 license:artistic2.0)))))
13564 (define-public find-circ
13565 ;; The last release was in 2015. The license was clarified in 2017, so we
13566 ;; take the latest commit.
13567 (let ((commit "8655dca54970fcf7e92e22fbf57e1188724dda7d")
13571 (version (git-version "1.2" revision commit))
13575 (uri (git-reference
13576 (url "https://github.com/marvin-jens/find_circ.git")
13578 (file-name (git-file-name name version))
13581 "0p77pbqbclqr4srms34y1b9b4njybfpjiknc11ki84f3p8skb3cg"))))
13582 (build-system gnu-build-system)
13584 `(#:tests? #f ; there are none
13586 ;; There is no actual build system.
13587 (modify-phases %standard-phases
13588 (delete 'configure)
13591 (lambda* (#:key outputs #:allow-other-keys)
13592 (let* ((out (assoc-ref outputs "out"))
13593 (bin (string-append out "/bin"))
13594 (path (getenv "PYTHONPATH")))
13595 (for-each (lambda (script)
13596 (install-file script bin)
13597 (wrap-program (string-append bin "/" script)
13598 `("PYTHONPATH" ":" prefix (,path))))
13603 "unmapped2anchors.py")))
13606 `(("python2" ,python-2)
13607 ("python2-pysam" ,python2-pysam)
13608 ("python2-numpy" ,python2-numpy)))
13609 (home-page "https://github.com/marvin-jens/find_circ")
13610 (synopsis "circRNA detection from RNA-seq reads")
13611 (description "This package provides tools to detect head-to-tail
13612 spliced (back-spliced) sequencing reads, indicative of circular RNA (circRNA)
13614 (license license:gpl3))))
13616 (define-public python-scanpy
13618 (name "python-scanpy")
13623 (uri (pypi-uri "scanpy" version))
13626 "0s2b6cvaigx4wzw3850qb93sjwwxbzh22kpbp498zklc5rjpbz4l"))))
13627 (build-system python-build-system)
13630 (modify-phases %standard-phases
13632 (lambda* (#:key inputs #:allow-other-keys)
13633 ;; These tests require Internet access.
13634 (delete-file-recursively "scanpy/tests/notebooks")
13635 (delete-file "scanpy/tests/test_clustering.py")
13636 (delete-file "scanpy/tests/test_datasets.py")
13638 ;; TODO: I can't get the plotting tests to work, even with Xvfb.
13639 (delete-file "scanpy/tests/test_plotting.py")
13640 (delete-file "scanpy/tests/test_preprocessing.py")
13641 (delete-file "scanpy/tests/test_read_10x.py")
13643 (setenv "PYTHONPATH"
13644 (string-append (getcwd) ":"
13645 (getenv "PYTHONPATH")))
13649 `(("python-anndata" ,python-anndata)
13650 ("python-h5py" ,python-h5py)
13651 ("python-igraph" ,python-igraph)
13652 ("python-joblib" ,python-joblib)
13653 ("python-legacy-api-wrap" ,python-legacy-api-wrap)
13654 ("python-louvain" ,python-louvain)
13655 ("python-matplotlib" ,python-matplotlib)
13656 ("python-natsort" ,python-natsort)
13657 ("python-networkx" ,python-networkx)
13658 ("python-numba" ,python-numba)
13659 ("python-packaging" ,python-packaging)
13660 ("python-pandas" ,python-pandas)
13661 ("python-patsy" ,python-patsy)
13662 ("python-scikit-learn" ,python-scikit-learn)
13663 ("python-scipy" ,python-scipy)
13664 ("python-seaborn" ,python-seaborn)
13665 ("python-statsmodels" ,python-statsmodels)
13666 ("python-tables" ,python-tables)
13667 ("python-tqdm" ,python-tqdm)
13668 ("python-umap-learn" ,python-umap-learn)))
13670 `(("python-pytest" ,python-pytest)
13671 ("python-setuptools-scm" ,python-setuptools-scm)))
13672 (home-page "https://github.com/theislab/scanpy")
13673 (synopsis "Single-Cell Analysis in Python.")
13674 (description "Scanpy is a scalable toolkit for analyzing single-cell gene
13675 expression data. It includes preprocessing, visualization, clustering,
13676 pseudotime and trajectory inference and differential expression testing. The
13677 Python-based implementation efficiently deals with datasets of more than one
13679 (license license:bsd-3)))
13681 (define-public python-bbknn
13683 (name "python-bbknn")
13688 (uri (pypi-uri "bbknn" version))
13691 "1jbsh01f57zj4bhvjr3jh4532zznqd6nccmgrl3qi9gnhkf7c4y0"))))
13692 (build-system python-build-system)
13694 `(#:tests? #f)) ; TODO: Enable after migration to scikit-learn.
13696 `(("python-annoy" ,python-annoy)
13697 ("python-cython" ,python-cython)
13698 ("python-numpy" ,python-numpy)
13699 ("python-scipy" ,python-scipy)
13700 ("python-umap-learn" ,python-umap-learn)))
13701 (home-page "https://github.com/Teichlab/bbknn")
13702 (synopsis "Batch balanced KNN")
13703 (description "BBKNN is a batch effect removal tool that can be directly
13704 used in the Scanpy workflow. It serves as an alternative to
13705 @code{scanpy.api.pp.neighbors()}, with both functions creating a neighbour
13706 graph for subsequent use in clustering, pseudotime and UMAP visualisation. If
13707 technical artifacts are present in the data, they will make it challenging to
13708 link corresponding cell types across different batches. BBKNN actively
13709 combats this effect by splitting your data into batches and finding a smaller
13710 number of neighbours for each cell within each of the groups. This helps
13711 create connections between analogous cells in different batches without
13712 altering the counts or PCA space.")
13713 (license license:expat)))
13715 (define-public gffcompare
13716 (let ((commit "be56ef4349ea3966c12c6397f85e49e047361c41")
13719 (name "gffcompare")
13720 (version (git-version "0.10.15" revision commit))
13724 (uri (git-reference
13725 (url "https://github.com/gpertea/gffcompare/")
13727 (file-name (git-file-name name version))
13729 (base32 "0cp5qpxdhw4mxpya5dld8wi3jk00zyklm6rcri426wydinrnfmkg"))))
13730 (build-system gnu-build-system)
13732 `(#:tests? #f ; no check target
13734 (modify-phases %standard-phases
13735 (delete 'configure)
13736 (add-before 'build 'copy-gclib-source
13737 (lambda* (#:key inputs #:allow-other-keys)
13740 (assoc-ref inputs "gclib-source") "../gclib")
13743 (lambda* (#:key outputs #:allow-other-keys)
13744 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
13745 (install-file "gffcompare" bin)
13748 `(("gclib-source" ; see 'README.md' of gffcompare
13749 ,(let ((commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13752 (version (git-version "0.10.3" revision commit)))
13755 (uri (git-reference
13756 (url "https://github.com/gpertea/gclib/")
13758 (file-name (git-file-name name version))
13760 (base32 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13761 (home-page "https://github.com/gpertea/gffcompare/")
13762 (synopsis "Tool for comparing or classifing transcripts of RNA-Seq")
13764 "@code{gffcompare} is a tool that can:
13766 @item compare and evaluate the accuracy of RNA-Seq transcript assemblers
13767 (Cufflinks, Stringtie);
13768 @item collapse (merge) duplicate transcripts from multiple GTF/GFF3 files (e.g.
13769 resulted from assembly of different samples);
13770 @item classify transcripts from one or multiple GTF/GFF3 files as they relate to
13771 reference transcripts provided in a annotation file (also in GTF/GFF3 format).
13775 license:expat ;license for gffcompare
13776 license:artistic2.0))))) ;license for gclib
13778 (define-public intervaltree
13779 (let ((commit "b90527f9e6d51cd36ecbb50429e4524d3a418ea5"))
13781 (name "intervaltree")
13782 (version (git-version "0.0.0" "1" commit))
13786 (uri (git-reference
13787 (url "https://github.com/ekg/intervaltree/")
13789 (file-name (git-file-name name version))
13791 (base32 "0rgv6q5fl4x5d74n6p5wvdna6zmbdbqpb4jqqh6vq3670gn08xad"))))
13792 (build-system gnu-build-system)
13794 '(#:tests? #f ; No tests.
13795 #:make-flags (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
13798 (modify-phases %standard-phases
13799 (delete 'configure)))) ; There is no configure phase.
13800 (home-page "https://github.com/ekg/intervaltree")
13801 (synopsis "Minimal C++ interval tree implementation")
13802 (description "An interval tree can be used to efficiently find a set of
13803 numeric intervals overlapping or containing another interval. This library
13804 provides a basic implementation of an interval tree using C++ templates,
13805 allowing the insertion of arbitrary types into the tree.")
13806 (license license:expat))))
13808 (define-public python-intervaltree
13810 (name "python-intervaltree")
13815 (uri (pypi-uri "intervaltree" version))
13818 "0wz234g6irlm4hivs2qzmnywk0ss06ckagwh15nflkyb3p462kyb"))))
13819 (build-system python-build-system)
13822 (modify-phases %standard-phases
13823 ;; pytest seems to have a check to make sure the user is testing
13824 ;; their checked-out code and not an installed, potentially
13825 ;; out-of-date copy. This is harmless here, since we just installed
13826 ;; the package, so we disable the check to avoid skipping tests
13828 (add-before 'check 'import-mismatch-error-workaround
13830 (setenv "PY_IGNORE_IMPORTMISMATCH" "1")
13833 `(("python-sortedcontainers" ,python-sortedcontainers)))
13835 `(("python-pytest" ,python-pytest)))
13836 (home-page "https://github.com/chaimleib/intervaltree")
13837 (synopsis "Editable interval tree data structure")
13839 "This package provides a mutable, self-balancing interval tree
13840 implementation for Python. Queries may be by point, by range overlap, or by
13841 range envelopment. This library was designed to allow tagging text and time
13842 intervals, where the intervals include the lower bound but not the upper
13844 (license license:asl2.0)))
13846 (define-public python-pypairix
13848 (name "python-pypairix")
13850 ;; The tarball on pypi does not include the makefile to build the
13855 (uri (git-reference
13856 (url "https://github.com/4dn-dcic/pairix.git")
13858 (file-name (git-file-name name version))
13861 "1snr3lrmsld8sy77ng6ba6wcmd33xjccf1l2f3m6pi29xis9nd6p"))))
13862 (build-system python-build-system)
13865 (modify-phases %standard-phases
13866 (add-before 'build 'build-programs
13867 (lambda _ (invoke "make")))
13868 (add-after 'install 'install-programs
13869 (lambda* (#:key outputs #:allow-other-keys)
13870 (copy-recursively "bin" (string-append
13871 (assoc-ref outputs "out")
13876 (home-page "https://github.com/4dn-dcic/pairix")
13877 (synopsis "Support for querying pairix-indexed bgzipped text files")
13879 "Pypairix is a Python module for fast querying on a pairix-indexed
13880 bgzipped text file that contains a pair of genomic coordinates per line.")
13881 (license license:expat)))
13883 (define-public python-pyfaidx
13885 (name "python-pyfaidx")
13890 (uri (pypi-uri "pyfaidx" version))
13893 "038xi3a6zvrxbyyfpp64ka8pcjgsdq4fgw9cl5lpxbvmm1bzzw2q"))))
13894 (build-system python-build-system)
13896 `(("python-six" ,python-six)))
13897 (home-page "http://mattshirley.com")
13898 (synopsis "Random access to fasta subsequences")
13900 "This package provides procedures for efficient pythonic random access to
13901 fasta subsequences.")
13902 (license license:bsd-3)))
13904 (define-public python2-pyfaidx
13905 (package-with-python2 python-pyfaidx))
13907 (define-public python-cooler
13909 (name "python-cooler")
13914 (uri (pypi-uri "cooler" version))
13917 "01g6gqix9ba27sappz6nfyiwabzrlf8i5fn8kwcz8ra356cq9crp"))))
13918 (build-system python-build-system)
13920 `(("python-asciitree" ,python-asciitree)
13921 ("python-biopython" ,python-biopython)
13922 ("python-click" ,python-click)
13923 ("python-cytoolz" ,python-cytoolz)
13924 ("python-dask" ,python-dask)
13925 ("python-h5py" ,python-h5py)
13926 ("python-multiprocess" ,python-multiprocess)
13927 ("python-numpy" ,python-numpy)
13928 ("python-pandas" ,python-pandas)
13929 ("python-pyfaidx" ,python-pyfaidx)
13930 ("python-pypairix" ,python-pypairix)
13931 ("python-pysam" ,python-pysam)
13932 ("python-pyyaml" ,python-pyyaml)
13933 ("python-scipy" ,python-scipy)
13934 ("python-simplejson" ,python-simplejson)))
13936 `(("python-mock" ,python-mock)
13937 ("python-pytest" ,python-pytest)))
13938 (home-page "https://github.com/mirnylab/cooler")
13939 (synopsis "Sparse binary format for genomic interaction matrices")
13941 "Cooler is a support library for a sparse, compressed, binary persistent
13942 storage format, called @code{cool}, used to store genomic interaction data,
13943 such as Hi-C contact matrices.")
13944 (license license:bsd-3)))
13946 (define-public python-hicmatrix
13948 (name "python-hicmatrix")
13952 ;; Version 12 is not available on pypi.
13954 (uri (git-reference
13955 (url "https://github.com/deeptools/HiCMatrix.git")
13957 (file-name (git-file-name name version))
13960 "1xhdyx16f3brgxgxybixdi64ki8nbbkq5vk4h9ahi11pzpjfn1pj"))))
13961 (build-system python-build-system)
13964 (modify-phases %standard-phases
13965 (add-after 'unpack 'relax-requirements
13967 (substitute* '("requirements.txt"
13969 (("cooler *=+ *0.8.5")
13973 `(("python-cooler" ,python-cooler)
13974 ("python-intervaltree" ,python-intervaltree)
13975 ("python-numpy" ,python-numpy)
13976 ("python-pandas" ,python-pandas)
13977 ("python-scipy" ,python-scipy)
13978 ("python-tables" ,python-tables)))
13979 (home-page "https://github.com/deeptools/HiCMatrix/")
13980 (synopsis "HiCMatrix class for HiCExplorer and pyGenomeTracks")
13982 "This helper package implements the @code{HiCMatrix} class for
13983 the HiCExplorer and pyGenomeTracks packages.")
13984 (license license:gpl3+)))
13986 (define-public python-hicexplorer
13988 (name "python-hicexplorer")
13992 ;; The latest version is not available on Pypi.
13994 (uri (git-reference
13995 (url "https://github.com/deeptools/HiCExplorer.git")
13997 (file-name (git-file-name name version))
14000 "0q5gpbzmrkvygqgw524q36b4nrivcmyi5v194vsx0qw7b3gcmq08"))))
14001 (build-system python-build-system)
14004 (modify-phases %standard-phases
14005 (add-after 'unpack 'loosen-up-requirements
14007 (substitute* "setup.py"
14011 `(("python-biopython" ,python-biopython)
14012 ("python-configparser" ,python-configparser)
14013 ("python-cooler" ,python-cooler)
14014 ("python-future" ,python-future)
14015 ("python-intervaltree" ,python-intervaltree)
14016 ("python-jinja2" ,python-jinja2)
14017 ("python-matplotlib" ,python-matplotlib)
14018 ("python-numpy" ,python-numpy)
14019 ("python-pandas" ,python-pandas)
14020 ("python-pybigwig" ,python-pybigwig)
14021 ("python-pysam" ,python-pysam)
14022 ("python-scipy" ,python-scipy)
14023 ("python-six" ,python-six)
14024 ("python-tables" ,python-tables)
14025 ("python-unidecode" ,python-unidecode)))
14026 (home-page "https://hicexplorer.readthedocs.io")
14027 (synopsis "Process, analyze and visualize Hi-C data")
14029 "HiCExplorer is a powerful and easy to use set of tools to process,
14030 normalize and visualize Hi-C data. HiCExplorer facilitates the creation of
14031 contact matrices, correction of contacts, TAD detection, A/B compartments,
14032 merging, reordering or chromosomes, conversion from different formats
14033 including cooler and detection of long-range contacts. Moreover, it allows
14034 the visualization of multiple contact matrices along with other types of data
14035 like genes, compartments, ChIP-seq coverage tracks (and in general any type of
14036 genomic scores), long range contacts and the visualization of viewpoints.")
14037 (license license:gpl3)))
14039 (define-public python-pygenometracks
14041 (name "python-pygenometracks")
14046 (uri (pypi-uri "pyGenomeTracks" version))
14049 "16laa0wnf4qn9fb9ych4w1vqhqwjss70v0y0f6wp4gwqfrlgac0f"))))
14050 (build-system python-build-system)
14052 `(#:tests? #f ; there are none
14054 (modify-phases %standard-phases
14055 (add-after 'unpack 'relax-requirements
14057 (substitute* "setup.py"
14058 (("matplotlib ==3.1.1")
14059 "matplotlib >=3.1.1"))
14062 `(("python-future" ,python-future)
14063 ("python-gffutils" ,python-gffutils)
14064 ("python-hicmatrix" ,python-hicmatrix)
14065 ("python-intervaltree" ,python-intervaltree)
14066 ("python-matplotlib" ,python-matplotlib)
14067 ("python-numpy" ,python-numpy)
14068 ("python-pybigwig" ,python-pybigwig)
14069 ("python-pysam" ,python-pysam)
14070 ("python-tqdm" ,python-tqdm)))
14072 `(("python-pytest" ,python-pytest)))
14073 (home-page "https://pygenometracks.readthedocs.io")
14074 (synopsis "Program and library to plot beautiful genome browser tracks")
14076 "This package aims to produce high-quality genome browser tracks that
14077 are highly customizable. Currently, it is possible to plot: bigwig, bed (many
14078 options), bedgraph, links (represented as arcs), and Hi-C matrices.
14079 pyGenomeTracks can make plots with or without Hi-C data.")
14080 (license license:gpl3+)))
14082 (define-public python-hic2cool
14084 (name "python-hic2cool")
14089 (uri (pypi-uri "hic2cool" version))
14092 "0xy6mhfns2lzib1kcr6419jjp6pmh0qx8z8na55lmiwn0ds8q9cl"))))
14093 (build-system python-build-system)
14094 (arguments '(#:tests? #f)) ; no tests included
14096 `(("python-cooler" ,python-cooler)))
14097 (home-page "https://github.com/4dn-dcic/hic2cool")
14098 (synopsis "Converter for .hic and .cool files")
14100 "This package provides a converter between @code{.hic} files (from
14101 juicer) and single-resolution or multi-resolution @code{.cool} files (for
14102 cooler). Both @code{hic} and @code{cool} files describe Hi-C contact
14104 (license license:expat)))
14106 (define-public r-pore
14114 (string-append "mirror://sourceforge/rpore/" version
14115 "/poRe_" version ".tar.gz"))
14117 (base32 "0pih9nljbv8g4x8rkk29i7aqq681b782r5s5ynp4nw9yzqnmmksv"))))
14118 (properties `((upstream-name . "poRe")))
14119 (build-system r-build-system)
14121 `(("r-bit64" ,r-bit64)
14122 ("r-data-table" ,r-data-table)
14123 ("r-rhdf5" ,r-rhdf5)
14124 ("r-shiny" ,r-shiny)
14125 ("r-svdialogs" ,r-svdialogs)))
14126 (home-page "https://sourceforge.net/projects/rpore/")
14127 (synopsis "Visualize Nanopore sequencing data")
14129 "This package provides graphical user interfaces to organize and visualize Nanopore
14131 ;; This is free software but the license variant is unclear:
14132 ;; <https://github.com/mw55309/poRe_docs/issues/10>.
14133 (license license:bsd-3)))
14135 (define-public r-xbioc
14136 (let ((revision "1")
14137 (commit "6ff0670a37ab3036aaf1d94aa4b208310946b0b5"))
14140 (version (git-version "0.1.16" revision commit))
14143 (uri (git-reference
14144 (url "https://github.com/renozao/xbioc.git")
14146 (file-name (git-file-name name version))
14149 "0w8bsq5myiwkfhh83nm6is5ichiyvwa1axx2szvxnzq39x6knf66"))))
14150 (build-system r-build-system)
14152 `(("r-annotationdbi" ,r-annotationdbi)
14153 ("r-assertthat" ,r-assertthat)
14154 ("r-biobase" ,r-biobase)
14155 ("r-biocmanager" ,r-biocmanager)
14156 ("r-digest" ,r-digest)
14157 ("r-pkgmaker" ,r-pkgmaker)
14159 ("r-reshape2" ,r-reshape2)
14160 ("r-stringr" ,r-stringr)))
14161 (home-page "https://github.com/renozao/xbioc/")
14162 (synopsis "Extra base functions for Bioconductor")
14163 (description "This package provides extra utility functions to perform
14164 common tasks in the analysis of omics data, leveraging and enhancing features
14165 provided by Bioconductor packages.")
14166 (license license:gpl3+))))
14168 (define-public r-cssam
14169 (let ((revision "1")
14170 (commit "9ec58c982fa551af0d80b1a266890d92954833f2"))
14173 (version (git-version "1.4" revision commit))
14176 (uri (git-reference
14177 (url "https://github.com/shenorrLab/csSAM.git")
14179 (file-name (git-file-name name version))
14182 "128syf9v39gk0z3ip000qpsjbg6l1siyq6c8b0hz41dzg5achyb3"))))
14183 (build-system r-build-system)
14185 `(("r-formula" ,r-formula)
14186 ("r-ggplot2" ,r-ggplot2)
14187 ("r-pkgmaker" ,r-pkgmaker)
14189 ("r-rngtools" ,r-rngtools)
14190 ("r-scales" ,r-scales)))
14191 (home-page "https://github.com/shenorrLab/csSAM/")
14192 (synopsis "Cell type-specific statistical analysis of microarray")
14193 (description "This package implements the method csSAM that computes
14194 cell-specific differential expression from measured cell proportions using
14197 (license license:lgpl2.1+))))
14199 (define-public r-bseqsc
14200 (let ((revision "1")
14201 (commit "fef3f3e38dcf3df37103348b5780937982b43b98"))
14204 (version (git-version "1.0" revision commit))
14207 (uri (git-reference
14208 (url "https://github.com/shenorrLab/bseqsc.git")
14210 (file-name (git-file-name name version))
14213 "1prw13wa20f7wlc3gkkls66n1kxz8d28qrb8icfqdwdnnv8w5qg8"))))
14214 (build-system r-build-system)
14216 `(("r-abind" ,r-abind)
14217 ("r-annotationdbi" ,r-annotationdbi)
14218 ("r-biobase" ,r-biobase)
14219 ("r-cssam" ,r-cssam)
14220 ("r-dplyr" ,r-dplyr)
14221 ("r-e1071" ,r-e1071)
14222 ("r-edger" ,r-edger)
14223 ("r-ggplot2" ,r-ggplot2)
14225 ("r-openxlsx" ,r-openxlsx)
14226 ("r-pkgmaker" ,r-pkgmaker)
14228 ("r-preprocesscore" ,r-preprocesscore)
14229 ("r-rngtools" ,r-rngtools)
14230 ("r-scales" ,r-scales)
14231 ("r-stringr" ,r-stringr)
14232 ("r-xbioc" ,r-xbioc)))
14233 (home-page "https://github.com/shenorrLab/bseqsc")
14234 (synopsis "Deconvolution of bulk sequencing experiments using single cell data")
14235 (description "BSeq-sc is a bioinformatics analysis pipeline that
14236 leverages single-cell sequencing data to estimate cell type proportion and
14237 cell type-specific gene expression differences from RNA-seq data from bulk
14238 tissue samples. This is a companion package to the publication \"A
14239 single-cell transcriptomic map of the human and mouse pancreas reveals inter-
14240 and intra-cell population structure.\" Baron et al. Cell Systems (2016)
14241 @url{https://www.ncbi.nlm.nih.gov/pubmed/27667365}.")
14242 (license license:gpl2+))))
14244 (define-public porechop
14245 ;; The recommended way to install is to clone the git repository
14246 ;; https://github.com/rrwick/Porechop#installation
14247 (let ((commit "289d5dca4a5fc327f97b3f8cecb68ecaf1014861")
14251 (version (git-version "0.2.3" revision commit))
14255 (uri (git-reference
14256 (url "https://github.com/rrwick/Porechop.git")
14258 (file-name (git-file-name name version))
14260 (base32 "05ps43gig0d3ia9x5lj84lb00hbsl6ba9n7y7jz927npxbr2ym23"))))
14261 (build-system python-build-system)
14262 (home-page "https://github.com/rrwick/porechop")
14263 (synopsis "Finding, trimming or splitting adapters, in Oxford Nanopore reads")
14265 "The porechop package is a tool for finding and removing adapters from Oxford
14266 Nanopore reads. Adapters on the ends of reads are trimmed off, and when a read
14267 has an adapter in its middle, it is treated as chimeric and chopped into
14268 separate reads. Porechop performs thorough alignments to effectively find
14269 adapters, even at low sequence identity. Porechop also supports demultiplexing
14270 of Nanopore reads that were barcoded with the Native Barcoding Kit, PCR
14271 Barcoding Kit or Rapid Barcoding Kit.")
14272 (license license:gpl3+))))
14274 (define-public poretools
14275 ;; The latest release was in 2016 and the latest commit is from 2017
14276 ;; the recommended way to install is to clone the git repository
14277 ;; https://poretools.readthedocs.io/en/latest/content/installation.html
14278 (let ((commit "e426b1f09e86ac259a00c261c79df91510777407")
14282 (version (git-version "0.6.0" revision commit))
14286 (uri (git-reference
14287 (url "https://github.com/arq5x/poretools.git")
14289 (file-name (git-file-name name version))
14291 (base32 "0bglj833wxpp3cq430p1d3xp085ls221js2y90w7ir2x5ay8l7am"))))
14292 (build-system python-build-system)
14293 ;; requires python >=2.7, <3.0, and the same for python dependencies
14294 (arguments `(#:python ,python-2))
14298 `(("python-dateutil" ,python2-dateutil)
14299 ("python-h5py" ,python2-h5py)
14300 ("python-matplotlib" ,python2-matplotlib)
14301 ("python-pandas" ,python2-pandas)
14302 ("python-seaborn" ,python2-seaborn)))
14303 (home-page "https://poretools.readthedocs.io")
14304 (synopsis "Toolkit for working with nanopore sequencing data")
14306 "The MinION from Oxford Nanopore Technologies is a nanopore sequencer.
14307 This @code{poretools} package is a flexible toolkit for exploring datasets
14308 generated by nanopore sequencing devices for the purposes of quality control and
14309 downstream analysis. Poretools operates directly on the native FAST5, a variant
14310 of the Hierarchical Data Format (HDF5) standard.")
14311 (license license:expat))))
14313 (define-public r-absfiltergsea
14315 (name "r-absfiltergsea")
14320 (uri (cran-uri "AbsFilterGSEA" version))
14322 (base32 "15srxkxsvn38kd5frdrwfdf0ad8gskrd0h01wmdf9hglq8fjrp7w"))))
14323 (properties `((upstream-name . "AbsFilterGSEA")))
14324 (build-system r-build-system)
14326 `(("r-biobase" ,r-biobase)
14327 ("r-deseq" ,r-deseq)
14328 ("r-limma" ,r-limma)
14330 ("r-rcpparmadillo" ,r-rcpparmadillo)))
14331 (home-page "https://cran.r-project.org/web/packages/AbsFilterGSEA/")
14332 (synopsis "Improved false positive control of gene-permuting with absolute filtering")
14334 "This package provides a function that performs gene-permuting of a gene-set
14335 enrichment analysis (GSEA) calculation with or without the absolute filtering.
14336 Without filtering, users can perform (original) two-tailed or one-tailed
14338 (license license:gpl2)))
14340 (define-public jamm
14343 (version "1.0.7.6")
14347 (uri (git-reference
14348 (url "https://github.com/mahmoudibrahim/JAMM.git")
14349 (commit (string-append "JAMMv" version))))
14350 (file-name (git-file-name name version))
14353 "0bsa5mf9n9q5jz7mmacrra41l7r8rac5vgsn6wv1fb52ya58b970"))))
14354 (build-system gnu-build-system)
14356 `(#:tests? #f ; there are none
14358 (modify-phases %standard-phases
14359 (delete 'configure)
14362 (lambda* (#:key inputs outputs #:allow-other-keys)
14363 (let* ((out (assoc-ref outputs "out"))
14364 (libexec (string-append out "/libexec/jamm"))
14365 (bin (string-append out "/bin")))
14366 (substitute* '("JAMM.sh"
14367 "SignalGenerator.sh")
14369 (string-append "sPath=\"" libexec "\"\n")))
14370 (for-each (lambda (file)
14371 (install-file file libexec))
14372 (list "bincalculator.r"
14384 (chmod script #o555)
14385 (install-file script bin)
14386 (wrap-program (string-append bin "/" script)
14387 `("PATH" ":" prefix
14388 (,(string-append (assoc-ref inputs "coreutils") "/bin")
14389 ,(string-append (assoc-ref inputs "gawk") "/bin")
14390 ,(string-append (assoc-ref inputs "perl") "/bin")
14391 ,(string-append (assoc-ref inputs "r-minimal") "/bin")))
14392 `("PERL5LIB" ":" prefix (,(getenv "PERL5LIB")))
14393 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
14394 (list "JAMM.sh" "SignalGenerator.sh")))
14398 ("coreutils" ,coreutils)
14401 ("r-minimal" ,r-minimal)
14402 ;;("r-parallel" ,r-parallel)
14403 ("r-signal" ,r-signal)
14404 ("r-mclust" ,r-mclust)))
14405 (home-page "https://github.com/mahmoudibrahim/JAMM")
14406 (synopsis "Peak finder for NGS datasets")
14408 "JAMM is a peak finder for next generation sequencing datasets (ChIP-Seq,
14409 ATAC-Seq, DNase-Seq, etc.) that can integrate replicates and assign peak
14410 boundaries accurately. JAMM is applicable to both broad and narrow
14412 (license license:gpl3+)))
14414 (define-public ngless
14421 (uri (git-reference
14422 (url "https://gitlab.com/ngless/ngless.git")
14423 (commit (string-append "v" version))))
14424 (file-name (git-file-name name version))
14427 "1wim8wpqyff080dfcazynrmjwqas38m24m0v350w245mmhrapdma"))))
14428 (build-system haskell-build-system)
14430 `(#:haddock? #f ; The haddock phase fails with: NGLess/CmdArgs.hs:20:1:
14431 ; error: parse error on input import
14432 ; import Options.Applicative
14434 (modify-phases %standard-phases
14435 (add-after 'unpack 'create-Versions.hs
14437 (substitute* "Makefile"
14438 (("BWA_VERSION = .*")
14439 (string-append "BWA_VERSION = "
14440 ,(package-version bwa) "\n"))
14441 (("SAM_VERSION = .*")
14442 (string-append "SAM_VERSION = "
14443 ,(package-version samtools) "\n"))
14444 (("PRODIGAL_VERSION = .*")
14445 (string-append "PRODIGAL_VERSION = "
14446 ,(package-version prodigal) "\n"))
14447 (("MINIMAP2_VERSION = .*")
14448 (string-append "MINIMAP2_VERSION = "
14449 ,(package-version minimap2) "\n")))
14450 (invoke "make" "NGLess/Dependencies/Versions.hs")
14452 (add-after 'create-Versions.hs 'create-cabal-file
14453 (lambda _ (invoke "hpack") #t))
14454 ;; These tools are expected to be installed alongside ngless.
14455 (add-after 'install 'link-tools
14456 (lambda* (#:key inputs outputs #:allow-other-keys)
14457 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
14458 (symlink (string-append (assoc-ref inputs "prodigal")
14460 (string-append bin "ngless-" ,version "-prodigal"))
14461 (symlink (string-append (assoc-ref inputs "minimap2")
14463 (string-append bin "ngless-" ,version "-minimap2"))
14464 (symlink (string-append (assoc-ref inputs "samtools")
14466 (string-append bin "ngless-" ,version "-samtools"))
14467 (symlink (string-append (assoc-ref inputs "bwa")
14469 (string-append bin "ngless-" ,version "-bwa"))
14472 `(("prodigal" ,prodigal)
14474 ("samtools" ,samtools)
14475 ("minimap2" ,minimap2)
14476 ("ghc-aeson" ,ghc-aeson)
14477 ("ghc-ansi-terminal" ,ghc-ansi-terminal)
14478 ("ghc-async" ,ghc-async)
14479 ("ghc-atomic-write" ,ghc-atomic-write)
14480 ("ghc-bytestring-lexing" ,ghc-bytestring-lexing)
14481 ("ghc-conduit" ,ghc-conduit)
14482 ("ghc-conduit-algorithms" ,ghc-conduit-algorithms)
14483 ("ghc-conduit-extra" ,ghc-conduit-extra)
14484 ("ghc-configurator" ,ghc-configurator)
14485 ("ghc-convertible" ,ghc-convertible)
14486 ("ghc-data-default" ,ghc-data-default)
14487 ("ghc-diagrams-core" ,ghc-diagrams-core)
14488 ("ghc-diagrams-lib" ,ghc-diagrams-lib)
14489 ("ghc-diagrams-svg" ,ghc-diagrams-svg)
14490 ("ghc-double-conversion" ,ghc-double-conversion)
14491 ("ghc-edit-distance" ,ghc-edit-distance)
14492 ("ghc-either" ,ghc-either)
14493 ("ghc-errors" ,ghc-errors)
14494 ("ghc-extra" ,ghc-extra)
14495 ("ghc-filemanip" ,ghc-filemanip)
14496 ("ghc-file-embed" ,ghc-file-embed)
14497 ("ghc-gitrev" ,ghc-gitrev)
14498 ("ghc-hashtables" ,ghc-hashtables)
14499 ("ghc-http-conduit" ,ghc-http-conduit)
14500 ("ghc-inline-c" ,ghc-inline-c)
14501 ("ghc-inline-c-cpp" ,ghc-inline-c-cpp)
14502 ("ghc-intervalmap" ,ghc-intervalmap)
14503 ("ghc-missingh" ,ghc-missingh)
14504 ("ghc-optparse-applicative" ,ghc-optparse-applicative)
14505 ("ghc-regex" ,ghc-regex)
14506 ("ghc-safe" ,ghc-safe)
14507 ("ghc-safeio" ,ghc-safeio)
14508 ("ghc-strict" ,ghc-strict)
14509 ("ghc-tar" ,ghc-tar)
14510 ("ghc-tar-conduit" ,ghc-tar-conduit)
14511 ("ghc-unliftio" ,ghc-unliftio)
14512 ("ghc-unliftio-core" ,ghc-unliftio-core)
14513 ("ghc-vector" ,ghc-vector)
14514 ("ghc-yaml" ,ghc-yaml)
14515 ("ghc-zlib" ,ghc-zlib)))
14518 ("r-hdf5r" ,r-hdf5r)
14519 ("r-iterators" ,r-iterators)
14520 ("r-itertools" ,r-itertools)
14521 ("r-matrix" ,r-matrix)))
14523 `(("ghc-hpack" ,ghc-hpack)
14524 ("ghc-quickcheck" ,ghc-quickcheck)
14525 ("ghc-test-framework" ,ghc-test-framework)
14526 ("ghc-test-framework-hunit",ghc-test-framework-hunit)
14527 ("ghc-test-framework-quickcheck2" ,ghc-test-framework-quickcheck2)
14528 ("ghc-test-framework-th" ,ghc-test-framework-th)))
14529 (home-page "https://gitlab.com/ngless/ngless")
14530 (synopsis "DSL for processing next-generation sequencing data")
14531 (description "Ngless is a domain-specific language for
14532 @dfn{next-generation sequencing} (NGS) data processing.")
14533 (license license:expat)))
14535 (define-public filtlong
14536 ;; The recommended way to install is to clone the git repository
14537 ;; https://github.com/rrwick/Filtlong#installation
14538 ;; and the lastest release is more than nine months old
14539 (let ((commit "d1bb46dfe8bc7efe6257b5ce222c04bfe8aedaab")
14543 (version (git-version "0.2.0" revision commit))
14547 (uri (git-reference
14548 (url "https://github.com/rrwick/Filtlong.git")
14550 (file-name (git-file-name name version))
14552 (base32 "1xr92r820x8qlkcr3b57iw223yq8vjgyi42jr79w2xgw47qzr575"))))
14553 (build-system gnu-build-system)
14555 `(#:tests? #f ; no check target
14557 (modify-phases %standard-phases
14558 (delete 'configure)
14560 (lambda* (#:key outputs #:allow-other-keys)
14561 (let* ((out (assoc-ref outputs "out"))
14562 (bin (string-append out "/bin"))
14563 (scripts (string-append out "/share/filtlong/scripts")))
14564 (install-file "bin/filtlong" bin)
14565 (install-file "scripts/histogram.py" scripts)
14566 (install-file "scripts/read_info_histograms.sh" scripts))
14568 (add-after 'install 'wrap-program
14569 (lambda* (#:key inputs outputs #:allow-other-keys)
14570 (let* ((out (assoc-ref outputs "out"))
14571 (path (getenv "PYTHONPATH")))
14572 (wrap-program (string-append out
14573 "/share/filtlong/scripts/histogram.py")
14574 `("PYTHONPATH" ":" prefix (,path))))
14576 (add-before 'check 'patch-tests
14578 (substitute* "scripts/read_info_histograms.sh"
14579 (("awk") (which "gawk")))
14582 `(("gawk" ,gawk) ;for read_info_histograms.sh
14583 ("python" ,python-2) ;required for histogram.py
14585 (home-page "https://github.com/rrwick/Filtlong/")
14586 (synopsis "Tool for quality filtering of Nanopore and PacBio data")
14588 "The Filtlong package is a tool for filtering long reads by quality.
14589 It can take a set of long reads and produce a smaller, better subset. It uses
14590 both read length (longer is better) and read identity (higher is better) when
14591 choosing which reads pass the filter.")
14592 (license (list license:gpl3 ;filtlong
14593 license:asl2.0))))) ;histogram.py
14595 (define-public nanopolish
14596 ;; The recommended way to install is to clone the git repository
14597 ;; <https://github.com/jts/nanopolish#installing-a-particular-release>.
14598 ;; Also, the differences between release and current version seem to be
14600 (let ((commit "6331dc4f15b9dfabb954ba3fae9d76b6c3ca6377")
14603 (name "nanopolish")
14604 (version (git-version "0.11.1" revision commit))
14608 (uri (git-reference
14609 (url "https://github.com/jts/nanopolish.git")
14612 (file-name (git-file-name name version))
14614 (base32 "15ikl3d37y49pwd7vx36xksgsqajhf24q7qqsnpl15dqqyy5qgbc"))
14615 (modules '((guix build utils)))
14618 (delete-file-recursively "htslib")
14620 (build-system gnu-build-system)
14623 `("HDF5=noinstall" "EIGEN=noinstall" "HTS=noinstall" "CC=gcc")
14624 #:tests? #f ; no check target
14626 (modify-phases %standard-phases
14627 (add-after 'unpack 'find-eigen
14628 (lambda* (#:key inputs #:allow-other-keys)
14630 (string-append (assoc-ref inputs "eigen")
14632 (or (getenv "CPATH") "")))
14634 (delete 'configure)
14636 (lambda* (#:key outputs #:allow-other-keys)
14637 (let* ((out (assoc-ref outputs "out"))
14638 (bin (string-append out "/bin"))
14639 (scripts (string-append out "/share/nanopolish/scripts")))
14641 (install-file "nanopolish" bin)
14642 (for-each (lambda (file) (install-file file scripts))
14643 (find-files "scripts" ".*"))
14645 (add-after 'install 'wrap-programs
14646 (lambda* (#:key outputs #:allow-other-keys)
14647 (for-each (lambda (file)
14648 (wrap-program file `("PYTHONPATH" ":" prefix (,path))))
14649 (find-files "/share/nanopolish/scripts" "\\.py"))
14650 (for-each (lambda (file)
14651 (wrap-program file `("PERL5LIB" ":" prefix (,path))))
14652 (find-files "/share/nanopolish/scripts" "\\.pl"))
14659 ("python" ,python-wrapper)
14660 ("python-biopython" ,python-biopython)
14661 ("python-numpy" ,python-numpy)
14662 ("python-pysam" ,python-pysam)
14663 ("python-scikit-learn" , python-scikit-learn)
14664 ("python-scipy" ,python-scipy)
14666 (home-page "https://github.com/jts/nanopolish")
14667 (synopsis "Signal-level analysis of Oxford Nanopore sequencing data")
14669 "This package analyses the Oxford Nanopore sequencing data at signal-level.
14670 Nanopolish can calculate an improved consensus sequence for a draft genome
14671 assembly, detect base modifications, call SNPs (Single nucleotide
14672 polymorphisms) and indels with respect to a reference genome and more.")
14673 (license license:expat))))
14675 (define-public cnvkit
14682 (uri (git-reference
14683 (url "https://github.com/etal/cnvkit.git")
14684 (commit (string-append "v" version))))
14685 (file-name (git-file-name name version))
14687 (base32 "0g2f78k68yglmj4fsfmgs8idqv3di9aj53fg0ld0hqljg8chhh82"))))
14688 (build-system python-build-system)
14690 `(("python-biopython" ,python-biopython)
14691 ("python-future" ,python-future)
14692 ("python-matplotlib" ,python-matplotlib)
14693 ("python-numpy" ,python-numpy)
14694 ("python-reportlab" ,python-reportlab)
14695 ("python-pandas" ,python-pandas)
14696 ("python-pysam" ,python-pysam)
14697 ("python-pyfaidx" ,python-pyfaidx)
14698 ("python-scipy" ,python-scipy)
14700 ("r-dnacopy" ,r-dnacopy)))
14701 (home-page "https://cnvkit.readthedocs.org/")
14702 (synopsis "Copy number variant detection from targeted DNA sequencing")
14704 "CNVkit is a Python library and command-line software toolkit to infer
14705 and visualize copy number from high-throughput DNA sequencing data. It is
14706 designed for use with hybrid capture, including both whole-exome and custom
14707 target panels, and short-read sequencing platforms such as Illumina and Ion
14709 (license license:asl2.0)))
14711 (define-public python-pyfit-sne
14713 (name "python-pyfit-sne")
14718 (uri (git-reference
14719 (url "https://github.com/KlugerLab/pyFIt-SNE.git")
14721 (file-name (git-file-name name version))
14723 (base32 "13wh3qkzs56azmmgnxib6xfr29g7xh09sxylzjpni5j0pp0rc5qw"))))
14724 (build-system python-build-system)
14726 `(("python-numpy" ,python-numpy)))
14730 `(("python-cython" ,python-cython)))
14731 (home-page "https://github.com/KlugerLab/pyFIt-SNE")
14732 (synopsis "FFT-accelerated Interpolation-based t-SNE")
14734 "t-Stochastic Neighborhood Embedding (t-SNE) is a highly successful
14735 method for dimensionality reduction and visualization of high dimensional
14736 datasets. A popular implementation of t-SNE uses the Barnes-Hut algorithm to
14737 approximate the gradient at each iteration of gradient descent. This package
14738 is a Cython wrapper for FIt-SNE.")
14739 (license license:bsd-4)))
14741 (define-public bbmap
14747 (uri (string-append
14748 "mirror://sourceforge/bbmap/BBMap_" version ".tar.gz"))
14751 "1q4rfhxcb6z3gm8zg2davjz98w22lkf4hm9ikxz9kdl93pil3wkd"))))
14752 (build-system ant-build-system)
14754 `(#:build-target "dist"
14755 #:tests? #f ; there are none
14757 (list (string-append "-Dmpijar="
14758 (assoc-ref %build-inputs "java-openmpi")
14760 #:modules ((guix build ant-build-system)
14762 (guix build java-utils))
14764 (modify-phases %standard-phases
14765 (add-after 'build 'build-jni-library
14767 (with-directory-excursion "jni"
14768 (invoke "make" "-f" "makefile.linux"))))
14769 ;; There is no install target
14770 (replace 'install (install-jars "dist"))
14771 (add-after 'install 'install-scripts-and-documentation
14772 (lambda* (#:key outputs #:allow-other-keys)
14773 (substitute* "calcmem.sh"
14774 (("\\| awk ") (string-append "| " (which "awk") " ")))
14775 (let* ((scripts (find-files "." "\\.sh$"))
14776 (out (assoc-ref outputs "out"))
14777 (bin (string-append out "/bin"))
14778 (doc (string-append out "/share/doc/bbmap"))
14779 (jni (string-append out "/lib/jni")))
14780 (substitute* scripts
14781 (("\\$DIR\"\"docs") doc)
14783 (string-append "CP=" out "/share/java/BBTools.jar\n"))
14784 (("^NATIVELIBDIR.*")
14785 (string-append "NATIVELIBDIR=" jni "\n"))
14787 (string-append "CMD=\"" (which "java"))))
14788 (for-each (lambda (script) (install-file script bin)) scripts)
14790 ;; Install JNI library
14791 (install-file "jni/libbbtoolsjni.so" jni)
14793 ;; Install documentation
14794 (install-file "docs/readme.txt" doc)
14795 (copy-recursively "docs/guides" doc))
14800 ("java-eclipse-jdt-core" ,java-eclipse-jdt-core)
14801 ("java-eclipse-jdt-compiler-apt" ,java-eclipse-jdt-compiler-apt)
14802 ("java-openmpi" ,java-openmpi)))
14803 (home-page "https://sourceforge.net/projects/bbmap/")
14804 (synopsis "Aligner and other tools for short sequencing reads")
14806 "This package provides bioinformatic tools to align, deduplicate,
14807 reformat, filter and normalize DNA and RNA-seq data. It includes the
14808 following tools: BBMap, a short read aligner for DNA and RNA-seq data; BBNorm,
14809 a kmer-based error-correction and normalization tool; Dedupe, a tool to
14810 simplify assemblies by removing duplicate or contained subsequences that share
14811 a target percent identity; Reformat, to convert reads between
14812 fasta/fastq/scarf/fasta+qual/sam, interleaved/paired, and ASCII-33/64, at over
14813 500 MB/s; and BBDuk, a tool to filter, trim, or mask reads with kmer matches
14814 to an artifact/contaminant file.")
14815 (license license:bsd-3)))
14817 (define-public velvet
14823 (uri (string-append "https://www.ebi.ac.uk/~zerbino/velvet/"
14824 "velvet_" version ".tgz"))
14827 "0h3njwy66p6bx14r3ar1byb0ccaxmxka4c65rn4iybyiqa4d8kc8"))
14828 ;; Delete bundled libraries
14829 (modules '((guix build utils)))
14832 (delete-file "Manual.pdf")
14833 (delete-file-recursively "third-party")
14835 (build-system gnu-build-system)
14837 `(#:make-flags '("OPENMP=t")
14838 #:test-target "test"
14840 (modify-phases %standard-phases
14841 (delete 'configure)
14842 (add-after 'unpack 'fix-zlib-include
14844 (substitute* "src/binarySequences.c"
14845 (("../third-party/zlib-1.2.3/zlib.h") "zlib.h"))
14848 (lambda* (#:key outputs #:allow-other-keys)
14849 (let* ((out (assoc-ref outputs "out"))
14850 (bin (string-append out "/bin"))
14851 (doc (string-append out "/share/doc/velvet")))
14854 (install-file "velveth" bin)
14855 (install-file "velvetg" bin)
14856 (install-file "Manual.pdf" doc)
14857 (install-file "Columbus_manual.pdf" doc)
14860 `(("openmpi" ,openmpi)
14863 `(("texlive" ,(texlive-union (list texlive-latex-graphics
14864 texlive-latex-hyperref)))))
14865 (home-page "https://www.ebi.ac.uk/~zerbino/velvet/")
14866 (synopsis "Nucleic acid sequence assembler for very short reads")
14868 "Velvet is a de novo genomic assembler specially designed for short read
14869 sequencing technologies, such as Solexa or 454. Velvet currently takes in
14870 short read sequences, removes errors then produces high quality unique
14871 contigs. It then uses paired read information, if available, to retrieve the
14872 repeated areas between contigs.")
14873 (license license:gpl2+)))
14875 (define-public python-velocyto
14877 (name "python-velocyto")
14878 (version "0.17.17")
14882 (uri (pypi-uri "velocyto" version))
14885 "0fgygyzqgrq32dv6a00biq1p1cwi6kbl5iqblxq1kklj6b2mzmhs"))))
14886 (build-system python-build-system)
14888 `(("python-joblib" ,python-joblib)))
14890 `(("python-click" ,python-click)
14891 ("python-cython" ,python-cython)
14892 ("python-h5py" ,python-h5py)
14893 ("python-loompy" ,python-loompy)
14894 ("python-matplotlib" ,python-matplotlib)
14895 ("python-numba" ,python-numba)
14896 ("python-numpy" ,python-numpy)
14897 ("python-pandas" ,python-pandas)
14898 ("python-pysam" ,python-pysam)
14899 ("python-scikit-learn" ,python-scikit-learn)
14900 ("python-scipy" ,python-scipy)))
14901 (home-page "https://github.com/velocyto-team/velocyto.py")
14902 (synopsis "RNA velocity analysis for single cell RNA-seq data")
14904 "Velocyto is a library for the analysis of RNA velocity. Velocyto
14905 includes a command line tool and an analysis pipeline.")
14906 (license license:bsd-2)))
14908 (define-public arriba
14915 (uri (string-append "https://github.com/suhrig/arriba/releases/"
14916 "download/v" version "/arriba_v" version ".tar.gz"))
14919 "0jx9656ry766vb8z08m1c3im87b0c82qpnjby9wz4kcz8vn87dx2"))))
14920 (build-system gnu-build-system)
14922 `(#:tests? #f ; there are none
14924 (modify-phases %standard-phases
14925 (replace 'configure
14926 (lambda* (#:key inputs #:allow-other-keys)
14927 (let ((htslib (assoc-ref inputs "htslib")))
14928 (substitute* "Makefile"
14929 (("-I\\$\\(HTSLIB\\)/htslib")
14930 (string-append "-I" htslib "/include/htslib"))
14931 ((" \\$\\(HTSLIB\\)/libhts.a")
14932 (string-append " " htslib "/lib/libhts.so"))))
14933 (substitute* "run_arriba.sh"
14934 (("^STAR ") (string-append (which "STAR") " "))
14935 (("samtools --version-only")
14936 (string-append (which "samtools") " --version-only"))
14937 (("samtools index")
14938 (string-append (which "samtools") " index"))
14940 (string-append (which "samtools") " sort")))
14943 (lambda* (#:key outputs #:allow-other-keys)
14944 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
14945 (install-file "arriba" bin)
14946 (install-file "run_arriba.sh" bin)
14947 (install-file "draw_fusions.R" bin)
14948 (wrap-program (string-append bin "/draw_fusions.R")
14949 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
14952 `(("htslib" ,htslib)
14953 ("r-minimal" ,r-minimal)
14954 ("r-circlize" ,r-circlize)
14955 ("r-genomicalignments" ,r-genomicalignments)
14956 ("r-genomicranges" ,r-genomicranges)
14957 ("samtools" ,samtools)
14960 (home-page "https://github.com/suhrig/arriba")
14961 (synopsis "Gene fusion detection from RNA-Seq data ")
14963 "Arriba is a command-line tool for the detection of gene fusions from
14964 RNA-Seq data. It was developed for the use in a clinical research setting.
14965 Therefore, short runtimes and high sensitivity were important design criteria.
14966 It is based on the fast STAR aligner and the post-alignment runtime is
14967 typically just around two minutes. In contrast to many other fusion detection
14968 tools which build on STAR, Arriba does not require to reduce the
14969 @code{alignIntronMax} parameter of STAR to detect small deletions.")
14970 ;; All code is under the Expat license with the exception of
14971 ;; "draw_fusions.R", which is under GPLv3.
14972 (license (list license:expat license:gpl3))))
14974 (define-public adapterremoval
14976 (name "adapterremoval")
14981 (uri (git-reference
14982 (url "https://github.com/MikkelSchubert/adapterremoval.git")
14983 (commit (string-append "v" version))))
14984 (file-name (git-file-name name version))
14987 "1nf3ki5pfzalhrx2fr1y6pfqfi133yj2m7q4fj9irf5fb94bapwr"))))
14988 (build-system gnu-build-system)
14990 `(#:make-flags (list "COLOR_BUILD=no"
14991 (string-append "PREFIX="
14992 (assoc-ref %outputs "out")))
14993 #:test-target "test"
14995 (modify-phases %standard-phases
14996 (delete 'configure))))
14999 (home-page "https://adapterremoval.readthedocs.io/")
15000 (synopsis "Rapid sequence adapter trimming, identification, and read merging")
15002 "This program searches for and removes remnant adapter sequences from
15003 @dfn{High-Throughput Sequencing} (HTS) data and (optionally) trims low quality
15004 bases from the 3' end of reads following adapter removal. AdapterRemoval can
15005 analyze both single end and paired end data, and can be used to merge
15006 overlapping paired-ended reads into (longer) consensus sequences.
15007 Additionally, the AdapterRemoval may be used to recover a consensus adapter
15008 sequence for paired-ended data, for which this information is not available.")
15009 (license license:gpl3+)))
15011 (define-public pplacer
15012 (let ((commit "807f6f3"))
15015 ;; The commit should be updated with each version change.
15016 (version "1.1.alpha19")
15020 (uri (git-reference
15021 (url "https://github.com/matsen/pplacer.git")
15022 (commit (string-append "v" version))))
15023 (file-name (git-file-name name version))
15025 (base32 "11ppbbbx20p2g9wj3ff64dhnarb12q79v7qh4rk0gj6lkbz4n7cn"))))
15026 (build-system ocaml-build-system)
15028 `(#:modules ((guix build ocaml-build-system)
15032 (modify-phases %standard-phases
15033 (delete 'configure)
15034 (add-after 'unpack 'fix-build-with-latest-ocaml
15036 (substitute* "myocamlbuild.ml"
15037 (("dep \\[\"c_pam\"\\]" m)
15038 (string-append "flag [\"ocaml\"; \"compile\"] (A \"-unsafe-string\");\n"
15040 (("let run_and_read" m)
15045 let pos = String.index s ch in
15046 x := (String.before s pos)::!x;
15047 go (String.after s (pos + 1))
15050 with Not_found -> !x
15051 let split_nl s = split s '\\n'
15052 let before_space s =
15053 try String.before s (String.index s ' ')
15054 with Not_found -> s
15057 (("run_and_read \"ocamlfind list \\| cut -d' ' -f1\"" m)
15058 (string-append "List.map before_space (split_nl & " m ")"))
15059 ((" blank_sep_strings &") "")
15060 ((" Lexing.from_string &") ""))
15062 (add-after 'unpack 'replace-bundled-cddlib
15063 (lambda* (#:key inputs #:allow-other-keys)
15064 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
15065 (local-dir "cddlib_guix"))
15067 (with-directory-excursion local-dir
15068 (invoke "tar" "xvf" cddlib-src))
15069 (let ((cddlib-src-folder
15070 (string-append local-dir "/"
15071 (list-ref (scandir local-dir) 2)
15073 (for-each make-file-writable (find-files "cdd_src" ".*"))
15077 (string-append "cdd_src/" (basename file))))
15078 (find-files cddlib-src-folder ".*[ch]$")))
15080 (add-after 'unpack 'fix-makefile
15082 ;; Remove system calls to 'git'.
15083 (substitute* "Makefile"
15084 (("^DESCRIPT:=pplacer-.*")
15086 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
15087 (substitute* "myocamlbuild.ml"
15088 (("git describe --tags --long .*\\\" with")
15090 "echo -n v" ,version "-" ,commit "\" with")))
15093 (lambda* (#:key outputs #:allow-other-keys)
15094 (let* ((out (assoc-ref outputs "out"))
15095 (bin (string-append out "/bin")))
15096 (copy-recursively "bin" bin))
15098 #:ocaml ,ocaml-4.07
15099 #:findlib ,ocaml4.07-findlib))
15101 `(("zlib" ,zlib "static")
15103 ("ocaml-ounit" ,(package-with-ocaml4.07 ocaml-ounit))
15104 ("ocaml-batteries" ,(package-with-ocaml4.07 ocaml-batteries))
15105 ("ocaml-camlzip" ,(package-with-ocaml4.07 camlzip))
15106 ("ocaml-csv" ,(package-with-ocaml4.07 ocaml-csv))
15107 ("ocaml-sqlite3" ,ocaml4.07-sqlite3)
15108 ("ocaml-xmlm" ,(package-with-ocaml4.07 ocaml-xmlm))
15109 ("ocaml-mcl" ,(package-with-ocaml4.07 ocaml-mcl))
15110 ("ocaml-gsl" ,ocaml4.07-gsl-1)))
15112 `(("cddlib-src" ,(package-source cddlib))
15113 ("ocamlbuild" ,(package-with-ocaml4.07 ocamlbuild))
15114 ("pkg-config" ,pkg-config)))
15116 `(("pplacer-scripts" ,pplacer-scripts)))
15117 (synopsis "Phylogenetic placement of biological sequences")
15119 "Pplacer places query sequences on a fixed reference phylogenetic tree
15120 to maximize phylogenetic likelihood or posterior probability according to a
15121 reference alignment. Pplacer is designed to be fast, to give useful
15122 information about uncertainty, and to offer advanced visualization and
15123 downstream analysis.")
15124 (home-page "https://matsen.fhcrc.org/pplacer/")
15125 (license license:gpl3))))
15127 ;; This package is installed alongside 'pplacer'. It is a separate package so
15128 ;; that it can use the python-build-system for the scripts that are
15129 ;; distributed alongside the main OCaml binaries.
15130 (define pplacer-scripts
15133 (name "pplacer-scripts")
15134 (build-system python-build-system)
15136 `(#:python ,python-2
15138 (modify-phases %standard-phases
15139 (add-after 'unpack 'enter-scripts-dir
15140 (lambda _ (chdir "scripts") #t))
15142 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t))
15143 (add-after 'install 'wrap-executables
15144 (lambda* (#:key inputs outputs #:allow-other-keys)
15145 (let* ((out (assoc-ref outputs "out"))
15146 (bin (string-append out "/bin")))
15147 (let ((path (string-append
15148 (assoc-ref inputs "hmmer") "/bin:"
15149 (assoc-ref inputs "infernal") "/bin")))
15151 (wrap-program (string-append bin "/refpkg_align.py")
15152 `("PATH" ":" prefix (,path))))
15153 (let ((path (string-append
15154 (assoc-ref inputs "hmmer") "/bin")))
15155 (wrap-program (string-append bin "/hrefpkg_query.py")
15156 `("PATH" ":" prefix (,path)))))
15159 `(("infernal" ,infernal)
15162 `(("python-biopython" ,python2-biopython)
15163 ("taxtastic" ,taxtastic)))
15164 (synopsis "Pplacer Python scripts")))
15166 (define-public python2-checkm-genome
15168 (name "python2-checkm-genome")
15173 (uri (pypi-uri "checkm-genome" version))
15176 "0bm8gpxjmzxsxxl8lzwqhgx8g1dlnmp6znz7wv3hgb0gdjbf9dzz"))))
15177 (build-system python-build-system)
15179 `(#:python ,python-2
15180 #:tests? #f)) ; some tests are interactive
15182 `(("python-dendropy" ,python2-dendropy)
15183 ("python-matplotlib" ,python2-matplotlib)
15184 ("python-numpy" ,python2-numpy)
15185 ("python-pysam" ,python2-pysam)
15186 ("python-scipy" ,python2-scipy)))
15187 (home-page "https://pypi.org/project/Checkm/")
15188 (synopsis "Assess the quality of putative genome bins")
15190 "CheckM provides a set of tools for assessing the quality of genomes
15191 recovered from isolates, single cells, or metagenomes. It provides robust
15192 estimates of genome completeness and contamination by using collocated sets of
15193 genes that are ubiquitous and single-copy within a phylogenetic lineage.
15194 Assessment of genome quality can also be examined using plots depicting key
15195 genomic characteristics (e.g., GC, coding density) which highlight sequences
15196 outside the expected distributions of a typical genome. CheckM also provides
15197 tools for identifying genome bins that are likely candidates for merging based
15198 on marker set compatibility, similarity in genomic characteristics, and
15199 proximity within a reference genome.")
15200 (license license:gpl3+)))
15202 (define-public umi-tools
15209 (uri (pypi-uri "umi_tools" version))
15212 "08y3vz1vcx09whmbsn722lcs6jl9wyrh9i4p3k8j4cb1i32bij4a"))))
15213 (build-system python-build-system)
15215 `(("python-pandas" ,python-pandas)
15216 ("python-future" ,python-future)
15217 ("python-scipy" ,python-scipy)
15218 ("python-matplotlib" ,python-matplotlib)
15219 ("python-regex" ,python-regex)
15220 ("python-pysam" ,python-pysam)))
15222 `(("python-cython" ,python-cython)))
15223 (home-page "https://github.com/CGATOxford/UMI-tools")
15224 (synopsis "Tools for analyzing unique modular identifiers")
15225 (description "This package provides tools for dealing with @dfn{Unique
15226 Molecular Identifiers} (UMIs) and @dfn{Random Molecular Tags} (RMTs) in
15227 genetic sequences. There are six tools: the @code{extract} and
15228 @code{whitelist} commands are used to prepare a fastq containing UMIs @code{+/-}
15229 cell barcodes for alignment. The remaining commands, @code{group},
15230 @code{dedup}, and @{count}/@code{count_tab}, are used to identify PCR
15231 duplicates using the UMIs and perform different levels of analysis depending
15232 on the needs of the user.")
15233 (license license:expat)))
15235 (define-public ataqv
15242 (uri (git-reference
15243 (url "https://github.com/ParkerLab/ataqv.git")
15245 (file-name (git-file-name name version))
15248 "031xr6jx1aprh26y5b1lv3gzrlmzg4alfl73vvshymx8cq8asrqi"))))
15249 (build-system gnu-build-system)
15252 (list (string-append "prefix=" (assoc-ref %outputs "out"))
15253 (string-append "BOOST_ROOT="
15254 (assoc-ref %build-inputs "boost"))
15255 (string-append "HTSLIB_ROOT="
15256 (assoc-ref %build-inputs "htslib")))
15257 #:test-target "test"
15259 (modify-phases %standard-phases
15260 (delete 'configure))))
15264 ("ncurses" ,ncurses)
15268 (home-page "https://github.com/ParkerLab/ataqv")
15269 (synopsis "Toolkit for quality control and visualization of ATAC-seq data")
15270 (description "This package provides a toolkit for measuring and comparing
15271 ATAC-seq results. It was written to make it easier to spot differences that
15272 might be caused by ATAC-seq library prep or sequencing. The main program,
15273 @code{ataqv}, examines aligned reads and reports some basic metrics.")
15274 (license license:gpl3+)))
15276 (define-public r-psiplot
15283 (uri (git-reference
15284 (url "https://github.com/kcha/psiplot.git")
15285 (commit (string-append "v" version))))
15286 (file-name (git-file-name name version))
15288 (base32 "08438h16cfry5kqh3y9hs8q1b1a8bxhblsm75knviz5r6q0n1jxh"))))
15289 (build-system r-build-system)
15291 `(("r-mass" ,r-mass)
15292 ("r-dplyr" ,r-dplyr)
15293 ("r-tidyr" ,r-tidyr)
15294 ("r-purrr" ,r-purrr)
15295 ("r-readr" ,r-readr)
15296 ("r-magrittr" ,r-magrittr)
15297 ("r-ggplot2" ,r-ggplot2)))
15298 (home-page "https://github.com/kcha/psiplot")
15299 (synopsis "Plot percent spliced-in values of alternatively-spliced exons")
15301 "PSIplot is an R package for generating plots of @dfn{percent
15302 spliced-in} (PSI) values of alternatively-spliced exons that were computed by
15303 vast-tools, an RNA-Seq pipeline for alternative splicing analysis. The plots
15304 are generated using @code{ggplot2}.")
15305 (license license:expat)))
15307 (define-public python-ont-fast5-api
15309 (name "python-ont-fast5-api")
15314 (uri (git-reference
15315 (url "https://github.com/nanoporetech/ont_fast5_api.git")
15316 (commit (string-append "release_" version))))
15317 (file-name (git-file-name name version))
15320 "03cbq4zbbwhll8ml2m9k8sa31mirsvcbjkrq1yna0kkzz9fad5fm"))))
15321 (build-system python-build-system)
15323 `(("python-numpy" ,python-numpy)
15324 ("python-six" ,python-six)
15325 ("python-h5py" ,python-h5py)
15326 ("python-progressbar33" ,python-progressbar33)))
15327 (home-page "https://github.com/nanoporetech/ont_fast5_api")
15328 (synopsis "Interface to HDF5 files of the Oxford Nanopore fast5 file format")
15330 "This package provides a concrete implementation of the fast5 file schema
15331 using the generic @code{h5py} library, plain-named methods to interact with
15332 and reflect the fast5 file schema, and tools to convert between
15333 @code{multi_read} and @code{single_read} formats.")
15334 (license license:mpl2.0)))
15336 (define-public tbsp
15337 (let ((commit "ec8fff4410cfb13a677dbbb95cbbc60217e64907")
15341 (version (git-version "1.0.0" revision commit))
15345 (uri (git-reference
15346 (url "https://github.com/phoenixding/tbsp.git")
15348 (file-name (git-file-name name version))
15351 "025ym14x8gbd6hb55lsinqj6f5qzw36i10klgs7ldzxxd7s39ki1"))))
15352 (build-system python-build-system)
15353 (arguments '(#:tests? #f)) ; no tests included
15355 `(("python-matplotlib" ,python-matplotlib)
15356 ("python-networkx" ,python-networkx)
15357 ("python-numpy" ,python-numpy)
15358 ("python-pybigwig" ,python-pybigwig)
15359 ("python-biopython" ,python-biopython)
15360 ("python-scikit-learn" ,python-scikit-learn)
15361 ("python-scipy" ,python-scipy)))
15362 (home-page "https://github.com/phoenixding/tbsp/")
15363 (synopsis "SNP-based trajectory inference")
15365 "Several studies focus on the inference of developmental and response
15366 trajectories from single cell RNA-Seq (scRNA-Seq) data. A number of
15367 computational methods, often referred to as pseudo-time ordering, have been
15368 developed for this task. CRISPR has also been used to reconstruct lineage
15369 trees by inserting random mutations. The tbsp package implements an
15370 alternative method to detect significant, cell type specific sequence
15371 mutations from scRNA-Seq data.")
15372 (license license:expat))))
15374 (define-public tabixpp
15380 (uri (git-reference
15381 (url "https://github.com/ekg/tabixpp")
15382 (commit (string-append "v" version))))
15383 (file-name (git-file-name name version))
15385 (base32 "1k2a3vbq96ic4lw72iwp5s3mwwc4xhdffjj584yn6l9637q9j1yd"))
15386 (modules '((guix build utils)))
15389 (delete-file-recursively "htslib") #t))))
15390 (build-system gnu-build-system)
15392 `(("htslib" ,htslib)
15395 `(#:tests? #f ; There are no tests to run.
15397 (modify-phases %standard-phases
15398 (delete 'configure) ; There is no configure phase.
15399 ;; The build phase needs overriding the location of htslib.
15401 (lambda* (#:key inputs #:allow-other-keys)
15402 (let ((htslib-ref (assoc-ref inputs "htslib")))
15404 (string-append "HTS_LIB=" htslib-ref "/lib/libhts.a")
15405 (string-append "INCLUDES= -I" htslib-ref "/include/htslib")
15406 "HTS_HEADERS=" ; No need to check for headers here.
15407 (string-append "LIBPATH=-L. -L" htslib-ref "/include")))))
15409 (lambda* (#:key outputs #:allow-other-keys)
15410 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15411 (install-file "tabix++" bin))
15413 (home-page "https://github.com/ekg/tabixpp")
15414 (synopsis "C++ wrapper around tabix project")
15415 (description "This is a C++ wrapper around the Tabix project which abstracts
15416 some of the details of opening and jumping in tabix-indexed files.")
15417 (license license:expat)))
15419 (define-public smithwaterman
15420 (let ((commit "2610e259611ae4cde8f03c72499d28f03f6d38a7"))
15422 (name "smithwaterman")
15423 (version (git-version "0.0.0" "2" commit))
15426 (uri (git-reference
15427 (url "https://github.com/ekg/smithwaterman/")
15429 (file-name (git-file-name name version))
15431 (base32 "0i9d8zrxpiracw3mxzd9siybpy62p06rqz9mc2w93arajgbk45bs"))))
15432 (build-system gnu-build-system)
15434 `(#:tests? #f ; There are no tests to run.
15435 #:make-flags '("libsw.a" "all")
15437 (modify-phases %standard-phases
15438 (delete 'configure) ; There is no configure phase.
15440 (lambda* (#:key outputs #:allow-other-keys)
15441 (let* ((out (assoc-ref outputs "out"))
15442 (bin (string-append out "/bin"))
15443 (lib (string-append out "/lib")))
15444 (install-file "smithwaterman" bin)
15445 (install-file "libsw.a" lib))
15447 (home-page "https://github.com/ekg/smithwaterman")
15448 (synopsis "Implementation of the Smith-Waterman algorithm")
15449 (description "Implementation of the Smith-Waterman algorithm.")
15450 ;; The licensing terms are unclear: https://github.com/ekg/smithwaterman/issues/9.
15451 (license (list license:gpl2 license:expat)))))
15453 (define-public multichoose
15455 (name "multichoose")
15459 (uri (git-reference
15460 (url "https://github.com/ekg/multichoose/")
15461 (commit (string-append "v" version))))
15462 (file-name (git-file-name name version))
15464 (base32 "0ci5fqvmpamwgxvmyd79ygj6n3bnbl3vc7b6h1sxz58186sm3pfs"))))
15465 (build-system gnu-build-system)
15467 `(#:tests? #f ; Tests require node.
15469 (modify-phases %standard-phases
15470 (delete 'configure) ; There is no configure phase.
15472 (lambda* (#:key outputs #:allow-other-keys)
15473 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15474 ;; TODO: There are Python modules for these programs too.
15475 (install-file "multichoose" bin)
15476 (install-file "multipermute" bin))
15478 (home-page "https://github.com/ekg/multichoose")
15479 (synopsis "Efficient loopless multiset combination generation algorithm")
15480 (description "This library implements an efficient loopless multiset
15481 combination generation algorithm which is (approximately) described in
15482 \"Loopless algorithms for generating permutations, combinations, and other
15483 combinatorial configurations.\", G. Ehrlich - Journal of the ACM (JACM),
15484 1973. (Algorithm 7.)")
15485 (license license:expat)))
15487 (define-public fsom
15488 (let ((commit "a6ef318fbd347c53189384aef7f670c0e6ce89a3"))
15491 (version (git-version "0.0.0" "1" commit))
15494 (uri (git-reference
15495 (url "https://github.com/ekg/fsom/")
15497 (file-name (git-file-name name version))
15499 (base32 "0gw1lpvr812pywg9y546x0h1hhj261xwls41r6kqhddjlrcjc0pi"))))
15500 (build-system gnu-build-system)
15502 `(#:tests? #f ; There are no tests to run.
15504 (modify-phases %standard-phases
15505 (delete 'configure) ; There is no configure phase.
15507 (lambda* (#:key outputs #:allow-other-keys)
15508 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15509 (install-file "fsom" bin))
15511 (home-page "https://github.com/ekg/fsom")
15512 (synopsis "Manage SOM (Self-Organizing Maps) neural networks")
15513 (description "A tiny C library for managing SOM (Self-Organizing Maps)
15515 (license license:gpl3))))
15517 (define-public fastahack
15523 (uri (git-reference
15524 (url "https://github.com/ekg/fastahack/")
15525 (commit (string-append "v" version))))
15526 (file-name (git-file-name name version))
15528 (base32 "0rp1blskhzxf7vbh253ibpxbgl9wwgyzf1wbkxndi08d3j4vcss9"))))
15529 (build-system gnu-build-system)
15531 `(#:tests? #f ; Unclear how to run tests: https://github.com/ekg/fastahack/issues/15
15533 (modify-phases %standard-phases
15534 (delete 'configure) ; There is no configure phase.
15536 (lambda* (#:key outputs #:allow-other-keys)
15537 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15538 (install-file "fastahack" bin))
15540 (home-page "https://github.com/ekg/fastahack")
15541 (synopsis "Indexing and sequence extraction from FASTA files")
15542 (description "Fastahack is a small application for indexing and
15543 extracting sequences and subsequences from FASTA files. The included library
15544 provides a FASTA reader and indexer that can be embedded into applications
15545 which would benefit from directly reading subsequences from FASTA files. The
15546 library automatically handles index file generation and use.")
15547 (license (list license:expat license:gpl2))))
15549 (define-public vcflib
15556 (uri (string-append "https://github.com/vcflib/vcflib/releases/"
15557 "download/v" version
15558 "/vcflib-" version "-src.tar.gz"))
15560 (base32 "14zzrg8hg8cq9cvq2wdvp21j7nmxxkjrbagw2apd2yqv2kyx42lm"))
15561 (modules '((guix build utils)))
15564 (for-each delete-file-recursively
15565 '("fastahack" "filevercmp" "fsom" "googletest" "intervaltree"
15566 "libVCFH" "multichoose" "smithwaterman" "tabixpp"))
15568 (build-system gnu-build-system)
15570 `(("htslib" ,htslib)
15576 ;; This package builds against the .o files so we need to extract the source.
15577 ("fastahack-src" ,(package-source fastahack))
15578 ("filevercmp-src" ,(package-source filevercmp))
15579 ("fsom-src" ,(package-source fsom))
15580 ("intervaltree-src" ,(package-source intervaltree))
15581 ("multichoose-src" ,(package-source multichoose))
15582 ("smithwaterman-src" ,(package-source smithwaterman))
15583 ("tabixpp-src" ,(package-source tabixpp))))
15585 `(#:tests? #f ; no tests
15586 #:make-flags (list (string-append "HTS_LIB="
15587 (assoc-ref %build-inputs "htslib")
15589 (string-append "HTS_INCLUDES= -I"
15590 (assoc-ref %build-inputs "htslib")
15592 (string-append "HTS_LDFLAGS= -L"
15593 (assoc-ref %build-inputs "htslib")
15594 "/include/htslib" " -lhts"))
15596 (modify-phases %standard-phases
15597 (delete 'configure)
15599 (add-after 'unpack 'unpack-submodule-sources
15600 (lambda* (#:key inputs #:allow-other-keys)
15601 (let ((unpack (lambda (source target)
15603 (with-directory-excursion target
15604 (if (file-is-directory? (assoc-ref inputs source))
15605 (copy-recursively (assoc-ref inputs source) ".")
15606 (invoke "tar" "xvf"
15607 (assoc-ref inputs source)
15608 "--strip-components=1"))))))
15610 (unpack "fastahack-src" "fastahack")
15611 (unpack "filevercmp-src" "filevercmp")
15612 (unpack "fsom-src" "fsom")
15613 (unpack "intervaltree-src" "intervaltree")
15614 (unpack "multichoose-src" "multichoose")
15615 (unpack "smithwaterman-src" "smithwaterman")
15616 (unpack "tabixpp-src" "tabixpp")))))
15618 (lambda* (#:key inputs make-flags #:allow-other-keys)
15619 (let ((htslib (assoc-ref inputs "htslib")))
15620 (with-directory-excursion "tabixpp"
15621 (substitute* "Makefile"
15622 (("-Ihtslib") (string-append "-I" htslib "/include/htslib"))
15623 (("-Lhtslib") (string-append "-L" htslib "/lib/htslib"))
15624 (("htslib/htslib") (string-append htslib "/include/htslib")))
15626 (string-append "HTS_LIB=" htslib "/lib/libhts.a")))
15627 (apply invoke "make" "CC=gcc" "CFLAGS=-Itabixpp" make-flags))))
15629 (lambda* (#:key outputs #:allow-other-keys)
15630 (let ((bin (string-append (assoc-ref outputs "out") "/bin"))
15631 (lib (string-append (assoc-ref outputs "out") "/lib")))
15632 (for-each (lambda (file)
15633 (install-file file bin))
15634 (find-files "bin" ".*"))
15635 ;; The header files in src/ do not interface libvcflib,
15636 ;; therefore they are left out.
15637 (install-file "libvcflib.a" lib))
15639 (home-page "https://github.com/vcflib/vcflib/")
15640 (synopsis "Library for parsing and manipulating VCF files")
15641 (description "Vcflib provides methods to manipulate and interpret
15642 sequence variation as it can be described by VCF. It is both an API for parsing
15643 and operating on records of genomic variation as it can be described by the VCF
15644 format, and a collection of command-line utilities for executing complex
15645 manipulations on VCF files.")
15646 (license license:expat)))
15648 (define-public freebayes
15649 (let ((commit "3ce827d8ebf89bb3bdc097ee0fe7f46f9f30d5fb")
15654 (version (git-version version revision commit))
15657 (uri (git-reference
15658 (url "https://github.com/ekg/freebayes.git")
15660 (file-name (git-file-name name version))
15662 (base32 "1sbzwmcbn78ybymjnhwk7qc5r912azy5vqz2y7y81616yc3ba2a2"))))
15663 (build-system gnu-build-system)
15665 `(("bamtools" ,bamtools)
15669 `(("bc" ,bc) ; Needed for running tests.
15670 ("samtools" ,samtools) ; Needed for running tests.
15671 ("parallel" ,parallel) ; Needed for running tests.
15672 ("perl" ,perl) ; Needed for running tests.
15673 ("procps" ,procps) ; Needed for running tests.
15674 ("python" ,python-2) ; Needed for running tests.
15675 ("vcflib-src" ,(package-source vcflib))
15676 ;; These are submodules for the vcflib version used in freebayes.
15677 ;; This package builds against the .o files so we need to extract the source.
15678 ("tabixpp-src" ,(package-source tabixpp))
15679 ("smithwaterman-src" ,(package-source smithwaterman))
15680 ("multichoose-src" ,(package-source multichoose))
15681 ("fsom-src" ,(package-source fsom))
15682 ("filevercmp-src" ,(package-source filevercmp))
15683 ("fastahack-src" ,(package-source fastahack))
15684 ("intervaltree-src" ,(package-source intervaltree))
15685 ;; These submodules are needed to run the tests.
15686 ("bash-tap-src" ,(package-source bash-tap))
15687 ("test-simple-bash-src"
15690 (uri (git-reference
15691 (url "https://github.com/ingydotnet/test-simple-bash/")
15692 (commit "124673ff204b01c8e96b7fc9f9b32ee35d898acc")))
15693 (file-name "test-simple-bash-src-checkout")
15695 (base32 "043plp6z0x9yf7mdpky1fw7zcpwn1p47px95w9mh16603zqqqpga"))))))
15699 (string-append "BAMTOOLS_ROOT="
15700 (assoc-ref %build-inputs "bamtools")))
15701 #:test-target "test"
15703 (modify-phases %standard-phases
15704 (delete 'configure)
15705 (add-after 'unpack 'fix-tests
15707 (substitute* "test/t/01_call_variants.t"
15708 (("grep -P \"\\(\\\\t500\\$\\|\\\\t11000\\$\\|\\\\t1000\\$\\)\"")
15709 "grep -E ' (500|11000|1000)$'"))
15711 (add-after 'unpack 'unpack-submodule-sources
15712 (lambda* (#:key inputs #:allow-other-keys)
15713 (let ((unpack (lambda (source target)
15714 (with-directory-excursion target
15715 (if (file-is-directory? (assoc-ref inputs source))
15716 (copy-recursively (assoc-ref inputs source) ".")
15717 (invoke "tar" "xvf"
15718 (assoc-ref inputs source)
15719 "--strip-components=1"))))))
15721 (unpack "vcflib-src" "vcflib")
15722 (unpack "fastahack-src" "vcflib/fastahack")
15723 (unpack "filevercmp-src" "vcflib/filevercmp")
15724 (unpack "fsom-src" "vcflib/fsom")
15725 (unpack "intervaltree-src" "vcflib/intervaltree")
15726 (unpack "multichoose-src" "vcflib/multichoose")
15727 (unpack "smithwaterman-src" "vcflib/smithwaterman")
15728 (unpack "tabixpp-src" "vcflib/tabixpp")
15729 (unpack "test-simple-bash-src" "test/test-simple-bash")
15730 (unpack "bash-tap-src" "test/bash-tap")))))
15731 (add-after 'unpack-submodule-sources 'fix-makefiles
15733 ;; We don't have the .git folder to get the version tag from.
15734 (substitute* "vcflib/Makefile"
15735 (("^GIT_VERSION.*")
15736 (string-append "GIT_VERSION = v" ,version)))
15737 (substitute* "src/Makefile"
15738 (("-I\\$\\(BAMTOOLS_ROOT\\)/src")
15739 "-I$(BAMTOOLS_ROOT)/include/bamtools"))
15741 (add-before 'build 'build-tabixpp-and-vcflib
15742 (lambda* (#:key inputs make-flags #:allow-other-keys)
15743 (with-directory-excursion "vcflib"
15744 (with-directory-excursion "tabixpp"
15745 (apply invoke "make"
15746 (string-append "HTS_LIB="
15747 (assoc-ref inputs "htslib")
15750 (apply invoke "make"
15751 (string-append "CFLAGS=-Itabixpp")
15755 (lambda* (#:key outputs #:allow-other-keys)
15756 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15757 (install-file "bin/freebayes" bin)
15758 (install-file "bin/bamleftalign" bin))
15760 (home-page "https://github.com/ekg/freebayes")
15761 (synopsis "Haplotype-based variant detector")
15762 (description "FreeBayes is a Bayesian genetic variant detector designed to
15763 find small polymorphisms, specifically SNPs (single-nucleotide polymorphisms),
15764 indels (insertions and deletions), MNPs (multi-nucleotide polymorphisms), and
15765 complex events (composite insertion and substitution events) smaller than the
15766 length of a short-read sequencing alignment.")
15767 (license license:expat))))
15769 (define-public samblaster
15771 (name "samblaster")
15775 (uri (git-reference
15776 (url "https://github.com/GregoryFaust/samblaster.git")
15777 (commit (string-append "v." version))))
15778 (file-name (git-file-name name version))
15781 "0iv2ddfw8363vb2x8gr3p8g88whb6mb9m0pf71i2cqsbv6jghap7"))))
15782 (build-system gnu-build-system)
15784 `(#:tests? #f ; there are none
15786 (modify-phases %standard-phases
15787 (delete 'configure) ; There is no configure phase.
15789 (lambda* (#:key outputs #:allow-other-keys)
15790 (install-file "samblaster"
15791 (string-append (assoc-ref outputs "out") "/bin"))
15793 (home-page "https://github.com/GregoryFaust/samblaster")
15794 (synopsis "Mark duplicates in paired-end SAM files")
15795 (description "Samblaster is a fast and flexible program for marking
15796 duplicates in read-id grouped paired-end SAM files. It can also optionally
15797 output discordant read pairs and/or split read mappings to separate SAM files,
15798 and/or unmapped/clipped reads to a separate FASTQ file. When marking
15799 duplicates, samblaster will require approximately 20MB of memory per 1M read
15801 (license license:expat)))
15803 (define-public r-velocyto
15804 (let ((commit "d7790346cb99f49ab9c2b23ba70dcf9d2c9fc350")
15807 (name "r-velocyto")
15808 (version (git-version "0.6" revision commit))
15812 (uri (git-reference
15813 (url "https://github.com/velocyto-team/velocyto.R.git")
15815 (file-name (git-file-name name version))
15818 "16wqf70j7rd7pay2q513iyz12i8n9vrpg1bisah4lddbcpx5dz1n"))))
15819 (build-system r-build-system)
15821 `(("boost" ,boost)))
15823 `(("r-hdf5r" ,r-hdf5r)
15826 ("r-pcamethods" ,r-pcamethods)
15828 ("r-rcpparmadillo" ,r-rcpparmadillo)
15829 ;; Suggested packages
15830 ("r-rtsne" ,r-rtsne)
15831 ("r-cluster" ,r-cluster)
15832 ("r-abind" ,r-abind)
15834 ("r-biocgenerics" ,r-biocgenerics)
15835 ("r-genomicalignments" ,r-genomicalignments)
15836 ("r-rsamtools" ,r-rsamtools)
15837 ("r-edger" ,r-edger)
15838 ("r-igraph" ,r-igraph)))
15839 (home-page "https://velocyto.org")
15840 (synopsis "RNA velocity estimation in R")
15842 "This package provides basic routines for estimation of gene-specific
15843 transcriptional derivatives and visualization of the resulting velocity
15845 (license license:gpl3))))
15847 (define-public methyldackel
15849 (name "methyldackel")
15853 (uri (git-reference
15854 (url "https://github.com/dpryan79/MethylDackel.git")
15856 (file-name (git-file-name name version))
15859 "10gh8k0ca92kywnrw5pkacq3g6r8s976s12k8jhp8g3g49q9a97g"))))
15860 (build-system gnu-build-system)
15862 `(#:test-target "test"
15865 (string-append "prefix="
15866 (assoc-ref %outputs "out") "/bin/"))
15868 (modify-phases %standard-phases
15869 (replace 'configure
15870 (lambda* (#:key outputs #:allow-other-keys)
15871 (substitute* "Makefile"
15872 (("install MethylDackel \\$\\(prefix\\)" match)
15873 (string-append "install -d $(prefix); " match)))
15876 `(("htslib" ,htslib)
15878 ;; Needed for tests
15880 `(("python" ,python-wrapper)))
15881 (home-page "https://github.com/dpryan79/MethylDackel")
15882 (synopsis "Universal methylation extractor for BS-seq experiments")
15884 "MethylDackel will process a coordinate-sorted and indexed BAM or CRAM
15885 file containing some form of BS-seq alignments and extract per-base
15886 methylation metrics from them. MethylDackel requires an indexed fasta file
15887 containing the reference genome as well.")
15888 ;; See https://github.com/dpryan79/MethylDackel/issues/85
15889 (license license:expat)))
15891 (define-public python-gffutils
15892 ;; The latest release is older more than a year than the latest commit
15893 (let ((commit "4034c54600813b1402945e12faa91b3a53162cf1")
15896 (name "python-gffutils")
15897 (version (git-version "0.9" revision commit))
15901 (uri (git-reference
15902 (url "https://github.com/daler/gffutils.git")
15904 (file-name (git-file-name name version))
15907 "1rwafjdnbir5wnk0ap06ww4lra3p5frhy7mfs03rlldgfnwxymsn"))))
15908 (build-system python-build-system)
15911 (modify-phases %standard-phases
15914 ;; Tests need to access the HOME directory
15915 (setenv "HOME" "/tmp")
15916 (invoke "nosetests" "-a" "!slow")))
15917 (add-after 'unpack 'make-gz-files-writable
15919 (for-each make-file-writable
15920 (find-files "." "\\.gz"))
15923 `(("python-argcomplete" ,python-argcomplete)
15924 ("python-argh" ,python-argh)
15925 ("python-biopython" ,python-biopython)
15926 ("python-pybedtools" ,python-pybedtools)
15927 ("python-pyfaidx" ,python-pyfaidx)
15928 ("python-simplejson" ,python-simplejson)
15929 ("python-six" ,python-six)))
15931 `(("python-nose" , python-nose)))
15932 (home-page "https://github.com/daler/gffutils")
15933 (synopsis "Tool for manipulation of GFF and GTF files")
15935 "python-gffutils is a Python package for working with and manipulating
15936 the GFF and GTF format files typically used for genomic annotations. The
15937 files are loaded into a SQLite database, allowing much more complex
15938 manipulation of hierarchical features (e.g., genes, transcripts, and exons)
15939 than is possible with plain-text methods alone.")
15940 (license license:expat))))
15942 (define-public libsbml
15948 (uri (string-append "mirror://sourceforge/sbml/libsbml/"
15949 version "/stable/libSBML-"
15950 version "-core-src.tar.gz"))
15953 "0slkagrk3nfi2qsksv6b1brj6zhx4bj4bkib2sdycvrcd10ql2lh"))))
15954 (build-system cmake-build-system)
15956 `(#:test-target "test"
15958 (list "-DWITH_CHECK=ON"
15959 (string-append "-DLIBXML_LIBRARY="
15960 (assoc-ref %build-inputs "libxml2")
15962 (string-append "-DLIBXML_INCLUDE_DIR="
15963 (assoc-ref %build-inputs "libxml2")
15964 "/include/libxml2"))))
15966 `(("libxml2" ,libxml2)))
15970 (home-page "http://sbml.org/Software/libSBML")
15971 (synopsis "Process SBML files and data streams")
15972 (description "LibSBML is a library to help you read, write, manipulate,
15973 translate, and validate SBML files and data streams. The @dfn{Systems Biology
15974 Markup Language} (SBML) is an interchange format for computer models of
15975 biological processes. SBML is useful for models of metabolism, cell
15976 signaling, and more. It continues to be evolved and expanded by an
15977 international community.")
15978 (license license:lgpl2.1+)))
15980 (define-public grocsvs
15981 ;; The last release is out of date and new features have been added.
15982 (let ((commit "ecd956a65093a0b2c41849050e4512d46fecea5d")
15986 (version (git-version "0.2.6.1" revision commit))
15989 (uri (git-reference
15990 (url "https://github.com/grocsvs/grocsvs")
15992 (file-name (git-file-name name version))
15994 (base32 "14505725gr7qxc17cxxf0k6lzcwmgi64pija4mwf29aw70qn35cc"))
15995 (patches (search-patches "grocsvs-dont-use-admiral.patch"))))
15996 (build-system python-build-system)
15998 `(#:tests? #f ; No test suite.
15999 #:python ,python-2)) ; Only python-2 supported.
16001 `(("python2-h5py" ,python2-h5py)
16002 ("python2-ipython-cluster-helper" ,python2-ipython-cluster-helper)
16003 ("python2-networkx" ,python2-networkx)
16004 ("python2-psutil" ,python2-psutil)
16005 ("python2-pandas" ,python2-pandas)
16006 ("python2-pybedtools" ,python2-pybedtools)
16007 ("python2-pyfaidx" ,python2-pyfaidx)
16008 ("python2-pygraphviz" ,python2-pygraphviz)
16009 ("python2-pysam" ,python2-pysam)
16010 ("python2-scipy" ,python2-scipy)))
16011 (home-page "https://github.com/grocsvs/grocsvs")
16012 (synopsis "Genome-wide reconstruction of complex structural variants")
16014 "@dfn{Genome-wide Reconstruction of Complex Structural Variants}
16015 (GROC-SVs) is a software pipeline for identifying large-scale structural
16016 variants, performing sequence assembly at the breakpoints, and reconstructing
16017 the complex structural variants using the long-fragment information from the
16018 10x Genomics platform.")
16019 (license license:expat))))