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" ".*")))
478 ;; Needed for pybedtools.
479 (define-public bedtools-2.26
480 (package (inherit bedtools)
485 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
486 "download/v" version "/"
487 "bedtools-" version ".tar.gz"))
490 "0jhavwifnf7lmkb11h9y7dynr8d699h0rd2l52j1pfgircr2zwv5"))))))
499 (url "https://github.com/PacificBiosciences/pbbam.git")
501 (file-name (git-file-name name version))
504 "0h9gkrpf2lrxklxp72xfl5bi3h5zcm5hprrya9gf0hr3xwlbpp0x"))))
505 (build-system meson-build-system)
508 (modify-phases %standard-phases
509 (add-after 'unpack 'find-googletest
510 (lambda* (#:key inputs #:allow-other-keys)
511 ;; It doesn't find gtest_main because there's no pkg-config file
512 ;; for it. Find it another way.
513 (substitute* "tests/meson.build"
514 (("pbbam_gtest_dep = dependency\\('gtest_main'.*")
515 (format #f "cpp = meson.get_compiler('cpp')
516 pbbam_gtest_dep = cpp.find_library('gtest_main', dirs : '~a')\n"
517 (assoc-ref inputs "googletest"))))
519 ;; TODO: tests/pbbam_test cannot be linked
520 ;; ld: tests/59830eb@@pbbam_test@exe/src_test_Accuracy.cpp.o:
521 ;; undefined reference to symbol '_ZTIN7testing4TestE'
522 ;; ld: /gnu/store/...-googletest-1.8.0/lib/libgtest.so:
523 ;; error adding symbols: DSO missing from command line
525 #:configure-flags '("-Dtests=false")))
526 ;; These libraries are listed as "Required" in the pkg-config file.
532 ("samtools" ,samtools)))
534 `(("googletest" ,googletest)
535 ("pkg-config" ,pkg-config)
536 ("python" ,python-wrapper))) ; for tests
537 (home-page "https://github.com/PacificBiosciences/pbbam")
538 (synopsis "Work with PacBio BAM files")
540 "The pbbam software package provides components to create, query, and
541 edit PacBio BAM files and associated indices. These components include a core
542 C++ library, bindings for additional languages, and command-line utilities.
543 This library is not intended to be used as a general-purpose BAM utility - all
544 input and output BAMs must adhere to the PacBio BAM format specification.
545 Non-PacBio BAMs will cause exceptions to be thrown.")
546 (license license:bsd-3)))
548 (define-public blasr-libcpp
550 (name "blasr-libcpp")
555 (url "https://github.com/PacificBiosciences/blasr_libcpp.git")
557 (file-name (git-file-name name version))
560 "0cn5l42zyq67sj0g2imqkhayz2iqvv0a1pgpbmlq0qynjmsrbfd2"))))
561 (build-system meson-build-system)
564 (modify-phases %standard-phases
565 (add-after 'unpack 'link-with-hdf5
566 (lambda* (#:key inputs #:allow-other-keys)
567 (let ((hdf5 (assoc-ref inputs "hdf5")))
568 (substitute* "meson.build"
569 (("libblasr_deps = \\[" m)
572 (format #f "cpp.find_library('hdf5', dirs : '~a'), \
573 cpp.find_library('hdf5_cpp', dirs : '~a'), "
576 (add-after 'unpack 'find-googletest
577 (lambda* (#:key inputs #:allow-other-keys)
578 ;; It doesn't find gtest_main because there's no pkg-config file
579 ;; for it. Find it another way.
580 (substitute* "unittest/meson.build"
581 (("libblasr_gtest_dep = dependency\\('gtest_main'.*")
582 (format #f "cpp = meson.get_compiler('cpp')
583 libblasr_gtest_dep = cpp.find_library('gtest_main', dirs : '~a')\n"
584 (assoc-ref inputs "googletest"))))
586 ;; TODO: unittest/libblasr_unittest cannot be linked
587 ;; ld: ;; unittest/df08227@@libblasr_unittest@exe/alignment_utils_FileUtils_gtest.cpp.o:
588 ;; undefined reference to symbol
589 ;; '_ZN7testing8internal9DeathTest6CreateEPKcPKNS0_2REES3_iPPS1_'
590 ;; ld: /gnu/store/...-googletest-1.8.0/lib/libgtest.so:
591 ;; error adding symbols: DSO missing from command line
593 #:configure-flags '("-Dtests=false")))
600 `(("googletest" ,googletest)
601 ("pkg-config" ,pkg-config)))
602 (home-page "https://github.com/PacificBiosciences/blasr_libcpp")
603 (synopsis "Library for analyzing PacBio genomic sequences")
605 "This package provides three libraries used by applications for analyzing
606 PacBio genomic sequences. This library contains three sub-libraries: pbdata,
608 (license license:bsd-3)))
617 (url "https://github.com/PacificBiosciences/blasr.git")
619 (file-name (git-file-name name version))
622 "1skgy2mvz8gsgfh1gc2nfgwvpyzb1hpmp2cf2773h5wsj8nw22kl"))))
623 (build-system meson-build-system)
626 (modify-phases %standard-phases
627 (add-after 'unpack 'link-with-hdf5
628 (lambda* (#:key inputs #:allow-other-keys)
629 (let ((hdf5 (assoc-ref inputs "hdf5")))
630 (substitute* "meson.build"
631 (("blasr_deps = \\[" m)
634 (format #f "cpp.find_library('hdf5', dirs : '~a'), \
635 cpp.find_library('hdf5_cpp', dirs : '~a'), "
638 ;; Tests require "cram" executable, which is not packaged.
640 #:configure-flags '("-Dtests=false")))
643 ("blasr-libcpp" ,blasr-libcpp)
648 `(("pkg-config" ,pkg-config)))
649 (home-page "https://github.com/PacificBiosciences/blasr")
650 (synopsis "PacBio long read aligner")
652 "Blasr is a genomic sequence aligner for processing PacBio long reads.")
653 (license license:bsd-3)))
655 (define-public ribotaper
661 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
662 "files/RiboTaper/RiboTaper_Version_"
666 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
667 (build-system gnu-build-system)
670 (modify-phases %standard-phases
671 (add-after 'install 'wrap-executables
672 (lambda* (#:key inputs outputs #:allow-other-keys)
673 (let* ((out (assoc-ref outputs "out")))
676 (wrap-program (string-append out "/bin/" script)
677 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
678 '("create_annotations_files.bash"
679 "create_metaplots.bash"
680 "Ribotaper_ORF_find.sh"
684 `(("bedtools" ,bedtools-2.18)
685 ("samtools" ,samtools-0.1)
686 ("r-minimal" ,r-minimal)
687 ("r-foreach" ,r-foreach)
688 ("r-xnomial" ,r-xnomial)
690 ("r-multitaper" ,r-multitaper)
691 ("r-seqinr" ,r-seqinr)))
692 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
693 (synopsis "Define translated ORFs using ribosome profiling data")
695 "Ribotaper is a method for defining translated @dfn{open reading
696 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
697 provides the Ribotaper pipeline.")
698 (license license:gpl3+)))
700 (define-public ribodiff
708 (url "https://github.com/ratschlab/RiboDiff.git")
709 (commit (string-append "v" version))))
710 (file-name (git-file-name name version))
713 "0x75nlp7qnmm64jasbi6l21f2cy99r2cjyl6b4hr8zf2bq22drnz"))))
714 (build-system python-build-system)
718 (modify-phases %standard-phases
719 ;; Generate an installable executable script wrapper.
720 (add-after 'unpack 'patch-setup.py
722 (substitute* "setup.py"
723 (("^(.*)packages=.*" line prefix)
724 (string-append line "\n"
725 prefix "scripts=['scripts/TE.py'],\n")))
728 `(("python-numpy" ,python2-numpy)
729 ("python-matplotlib" ,python2-matplotlib)
730 ("python-scipy" ,python2-scipy)
731 ("python-statsmodels" ,python2-statsmodels)))
733 `(("python-mock" ,python2-mock)
734 ("python-nose" ,python2-nose)))
735 (home-page "https://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
736 (synopsis "Detect translation efficiency changes from ribosome footprints")
737 (description "RiboDiff is a statistical tool that detects the protein
738 translational efficiency change from Ribo-Seq (ribosome footprinting) and
739 RNA-Seq data. It uses a generalized linear model to detect genes showing
740 difference in translational profile taking mRNA abundance into account. It
741 facilitates us to decipher the translational regulation that behave
742 independently with transcriptional regulation.")
743 (license license:gpl3+)))
745 (define-public bioawk
752 (url "https://github.com/lh3/bioawk.git")
753 (commit (string-append "v" version))))
754 (file-name (git-file-name name version))
757 "1pxc3zdnirxbf9a0az698hd8xdik7qkhypm7v6hn922x8y9qmspm"))))
758 (build-system gnu-build-system)
764 `(#:tests? #f ; There are no tests to run.
765 ;; Bison must generate files, before other targets can build.
768 (modify-phases %standard-phases
769 (delete 'configure) ; There is no configure phase.
771 (lambda* (#:key outputs #:allow-other-keys)
772 (let* ((out (assoc-ref outputs "out"))
773 (bin (string-append out "/bin"))
774 (man (string-append out "/share/man/man1")))
776 (copy-file "awk.1" (string-append man "/bioawk.1"))
777 (install-file "bioawk" bin))
779 (home-page "https://github.com/lh3/bioawk")
780 (synopsis "AWK with bioinformatics extensions")
781 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
782 support of several common biological data formats, including optionally gzip'ed
783 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
784 also adds a few built-in functions and a command line option to use TAB as the
785 input/output delimiter. When the new functionality is not used, bioawk is
786 intended to behave exactly the same as the original BWK awk.")
787 (license license:x11)))
789 (define-public python-pybedtools
791 (name "python-pybedtools")
795 (uri (pypi-uri "pybedtools" version))
798 "14w5i40gi25clrr7h4wa2pcpnyipya8hrqi7nq77553zc5wf0df0"))))
799 (build-system python-build-system)
801 `(#:modules ((ice-9 ftw)
805 (guix build python-build-system))
806 ;; See https://github.com/daler/pybedtools/issues/192
808 (modify-phases %standard-phases
809 ;; See https://github.com/daler/pybedtools/issues/261
810 (add-after 'unpack 'disable-broken-tests
812 ;; This test (pybedtools.test.test_scripts.test_venn_mpl) needs a
813 ;; graphical environment.
814 (substitute* "pybedtools/test/test_scripts.py"
815 (("def test_venn_mpl")
816 "def _do_not_test_venn_mpl"))
817 (substitute* "pybedtools/test/test_helpers.py"
818 ;; Requires internet access.
819 (("def test_chromsizes")
820 "def _do_not_test_chromsizes")
821 ;; Broken as a result of the workaround used in the check phase
822 ;; (see: https://github.com/daler/pybedtools/issues/192).
823 (("def test_getting_example_beds")
824 "def _do_not_test_getting_example_beds"))
825 ;; This issue still occurs on python2
826 (substitute* "pybedtools/test/test_issues.py"
827 (("def test_issue_303")
828 "def _test_issue_303"))
830 ;; TODO: Remove phase after it's part of PYTHON-BUILD-SYSTEM.
832 ;; Force the Cythonization of C++ files to guard against compilation
834 (add-after 'unpack 'remove-cython-generated-files
836 (let ((cython-sources (map (cut string-drop-right <> 4)
837 (find-files "." "\\.pyx$")))
838 (c/c++-files (find-files "." "\\.(c|cpp|cxx)$")))
839 (define (strip-extension filename)
840 (string-take filename (string-index-right filename #\.)))
841 (define (cythonized? c/c++-file)
842 (member (strip-extension c/c++-file) cython-sources))
843 (for-each delete-file (filter cythonized? c/c++-files))
845 (add-after 'remove-cython-generated-files 'generate-cython-extensions
847 (invoke "python" "setup.py" "cythonize")))
850 (let* ((cwd (getcwd))
851 (build-root-directory (string-append cwd "/build/"))
852 (build (string-append
854 (find (cut string-prefix? "lib" <>)
855 (scandir (string-append
856 build-root-directory)))))
857 (scripts (string-append
859 (find (cut string-prefix? "scripts" <>)
860 (scandir build-root-directory)))))
862 (string-append build ":" (getenv "PYTHONPATH")))
863 ;; Executable scripts such as 'intron_exon_reads.py' must be
864 ;; available in the PATH.
866 (string-append scripts ":" (getenv "PATH"))))
867 ;; The tests need to be run from elsewhere...
868 (mkdir-p "/tmp/test")
869 (copy-recursively "pybedtools/test" "/tmp/test")
870 (with-directory-excursion "/tmp/test"
871 (invoke "pytest")))))))
873 `(("bedtools" ,bedtools)
874 ("samtools" ,samtools)
875 ("python-matplotlib" ,python-matplotlib)
876 ("python-pysam" ,python-pysam)
877 ("python-pyyaml" ,python-pyyaml)))
879 `(("python-numpy" ,python-numpy)
880 ("python-pandas" ,python-pandas)
881 ("python-cython" ,python-cython)
882 ("kentutils" ,kentutils) ; for bedGraphToBigWig
883 ("python-six" ,python-six)
884 ;; For the test suite.
885 ("python-pytest" ,python-pytest)
886 ("python-psutil" ,python-psutil)))
887 (home-page "https://pythonhosted.org/pybedtools/")
888 (synopsis "Python wrapper for BEDtools programs")
890 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
891 which are widely used for genomic interval manipulation or \"genome algebra\".
892 pybedtools extends BEDTools by offering feature-level manipulations from with
894 (license license:gpl2+)))
896 (define-public python2-pybedtools
897 (let ((pybedtools (package-with-python2 python-pybedtools)))
901 `(("python2-pathlib" ,python2-pathlib)
902 ,@(package-native-inputs pybedtools))))))
904 (define-public python-biom-format
906 (name "python-biom-format")
911 ;; Use GitHub as source because PyPI distribution does not contain
912 ;; test data: https://github.com/biocore/biom-format/issues/693
914 (url "https://github.com/biocore/biom-format.git")
916 (file-name (git-file-name name version))
919 "1rna16lyk5aqhnv0dp77wwaplias93f1vw28ad3jmyw6hwkai05v"))
920 (modules '((guix build utils)))
922 ;; Delete generated C files.
923 (for-each delete-file (find-files "." "\\.c"))
925 (build-system python-build-system)
928 (modify-phases %standard-phases
929 (add-after 'unpack 'use-cython
930 (lambda _ (setenv "USE_CYTHON" "1") #t))
931 (add-after 'unpack 'disable-broken-tests
933 (substitute* "biom/tests/test_cli/test_validate_table.py"
934 (("^(.+)def test_invalid_hdf5" m indent)
935 (string-append indent
936 "@npt.dec.skipif(True, msg='Guix')\n"
938 (substitute* "biom/tests/test_table.py"
939 (("^(.+)def test_from_hdf5_issue_731" m indent)
940 (string-append indent
941 "@npt.dec.skipif(True, msg='Guix')\n"
944 (add-before 'reset-gzip-timestamps 'make-files-writable
945 (lambda* (#:key outputs #:allow-other-keys)
946 (let ((out (assoc-ref outputs "out")))
947 (for-each (lambda (file) (chmod file #o644))
948 (find-files out "\\.gz"))
951 `(("python-numpy" ,python-numpy)
952 ("python-scipy" ,python-scipy)
953 ("python-flake8" ,python-flake8)
954 ("python-future" ,python-future)
955 ("python-click" ,python-click)
956 ("python-h5py" ,python-h5py)
957 ("python-pandas" ,python-pandas)))
959 `(("python-cython" ,python-cython)
960 ("python-pytest" ,python-pytest)
961 ("python-pytest-cov" ,python-pytest-cov)
962 ("python-nose" ,python-nose)))
963 (home-page "http://www.biom-format.org")
964 (synopsis "Biological Observation Matrix (BIOM) format utilities")
966 "The BIOM file format is designed to be a general-use format for
967 representing counts of observations e.g. operational taxonomic units, KEGG
968 orthology groups or lipid types, in one or more biological samples
969 e.g. microbiome samples, genomes, metagenomes.")
970 (license license:bsd-3)
971 (properties `((python2-variant . ,(delay python2-biom-format))))))
973 (define-public python2-biom-format
974 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
978 (substitute-keyword-arguments (package-arguments base)
980 `(modify-phases ,phases
981 ;; Do not require the unmaintained pyqi library.
982 (add-after 'unpack 'remove-pyqi
984 (substitute* "setup.py"
985 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
988 (define-public bioperl-minimal
989 (let* ((inputs `(("perl-module-build" ,perl-module-build)
990 ("perl-data-stag" ,perl-data-stag)
991 ("perl-libwww" ,perl-libwww)
992 ("perl-uri" ,perl-uri)))
994 (map (compose package-name cadr)
997 (map (compose package-transitive-target-inputs cadr) inputs))))))
999 (name "bioperl-minimal")
1005 (url "https://github.com/bioperl/bioperl-live")
1006 (commit (string-append "release-"
1007 (string-map (lambda (c)
1009 #\- c)) version)))))
1010 (file-name (git-file-name name version))
1013 "0wl8yvzcls59pwwk6m8ahy87pwg6nnibzy5cldbvmcwg2x2w7783"))))
1014 (build-system perl-build-system)
1017 (modify-phases %standard-phases
1019 'install 'wrap-programs
1020 (lambda* (#:key outputs #:allow-other-keys)
1021 ;; Make sure all executables in "bin" find the required Perl
1022 ;; modules at runtime. As the PERL5LIB variable contains also
1023 ;; the paths of native inputs, we pick the transitive target
1024 ;; inputs from %build-inputs.
1025 (let* ((out (assoc-ref outputs "out"))
1026 (bin (string-append out "/bin/"))
1028 (cons (string-append out "/lib/perl5/site_perl")
1030 (assoc-ref %build-inputs name))
1031 ',transitive-inputs))
1033 (for-each (lambda (file)
1035 `("PERL5LIB" ":" prefix (,path))))
1036 (find-files bin "\\.pl$"))
1040 `(("perl-test-most" ,perl-test-most)))
1041 (home-page "https://metacpan.org/release/BioPerl")
1042 (synopsis "Bioinformatics toolkit")
1044 "BioPerl is the product of a community effort to produce Perl code which
1045 is useful in biology. Examples include Sequence objects, Alignment objects
1046 and database searching objects. These objects not only do what they are
1047 advertised to do in the documentation, but they also interact - Alignment
1048 objects are made from the Sequence objects, Sequence objects have access to
1049 Annotation and SeqFeature objects and databases, Blast objects can be
1050 converted to Alignment objects, and so on. This means that the objects
1051 provide a coordinated and extensible framework to do computational biology.")
1052 (license license:perl-license))))
1054 (define-public python-biopython
1056 (name "python-biopython")
1060 ;; use PyPi rather than biopython.org to ease updating
1061 (uri (pypi-uri "biopython" version))
1064 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
1065 (build-system python-build-system)
1068 (modify-phases %standard-phases
1069 (add-before 'check 'set-home
1070 ;; Some tests require a home directory to be set.
1071 (lambda _ (setenv "HOME" "/tmp") #t)))))
1073 `(("python-numpy" ,python-numpy)))
1074 (home-page "https://biopython.org/")
1075 (synopsis "Tools for biological computation in Python")
1077 "Biopython is a set of tools for biological computation including parsers
1078 for bioinformatics files into Python data structures; interfaces to common
1079 bioinformatics programs; a standard sequence class and tools for performing
1080 common operations on them; code to perform data classification; code for
1081 dealing with alignments; code making it easy to split up parallelizable tasks
1082 into separate processes; and more.")
1083 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
1085 (define-public python2-biopython
1086 (package-with-python2 python-biopython))
1088 (define-public python-fastalite
1090 (name "python-fastalite")
1095 (uri (pypi-uri "fastalite" version))
1098 "1qli6pxp77i9xn2wfciq2zaxhl82bdxb33cpzqzj1z25yd036wqj"))))
1099 (build-system python-build-system)
1101 `(#:tests? #f)) ; Test data is not distributed.
1102 (home-page "https://github.com/nhoffman/fastalite")
1103 (synopsis "Simplest possible FASTA parser")
1104 (description "This library implements a FASTA and a FASTQ parser without
1105 relying on a complex dependency tree.")
1106 (license license:expat)))
1108 (define-public python2-fastalite
1109 (package-with-python2 python-fastalite))
1111 (define-public bpp-core
1112 ;; The last release was in 2014 and the recommended way to install from source
1113 ;; is to clone the git repository, so we do this.
1114 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1115 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
1118 (version (string-append "2.2.0-1." (string-take commit 7)))
1122 (url "http://biopp.univ-montp2.fr/git/bpp-core")
1124 (file-name (string-append name "-" version "-checkout"))
1127 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
1128 (build-system cmake-build-system)
1130 `(#:parallel-build? #f))
1131 (home-page "http://biopp.univ-montp2.fr")
1132 (synopsis "C++ libraries for Bioinformatics")
1134 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1135 analysis, phylogenetics, molecular evolution and population genetics. It is
1136 Object Oriented and is designed to be both easy to use and computer efficient.
1137 Bio++ intends to help programmers to write computer expensive programs, by
1138 providing them a set of re-usable tools.")
1139 (license license:cecill-c))))
1141 (define-public bpp-phyl
1142 ;; The last release was in 2014 and the recommended way to install from source
1143 ;; is to clone the git repository, so we do this.
1144 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1145 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
1148 (version (string-append "2.2.0-1." (string-take commit 7)))
1152 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
1154 (file-name (string-append name "-" version "-checkout"))
1157 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
1158 (build-system cmake-build-system)
1160 `(#:parallel-build? #f
1161 ;; If out-of-source, test data is not copied into the build directory
1162 ;; so the tests fail.
1163 #:out-of-source? #f))
1165 `(("bpp-core" ,bpp-core)
1166 ("bpp-seq" ,bpp-seq)))
1167 (home-page "http://biopp.univ-montp2.fr")
1168 (synopsis "Bio++ phylogenetic Library")
1170 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1171 analysis, phylogenetics, molecular evolution and population genetics. This
1172 library provides phylogenetics-related modules.")
1173 (license license:cecill-c))))
1175 (define-public bpp-popgen
1176 ;; The last release was in 2014 and the recommended way to install from source
1177 ;; is to clone the git repository, so we do this.
1178 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1179 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
1182 (version (string-append "2.2.0-1." (string-take commit 7)))
1186 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
1188 (file-name (string-append name "-" version "-checkout"))
1191 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
1192 (build-system cmake-build-system)
1194 `(#:parallel-build? #f
1195 #:tests? #f)) ; There are no tests.
1197 `(("bpp-core" ,bpp-core)
1198 ("bpp-seq" ,bpp-seq)))
1199 (home-page "http://biopp.univ-montp2.fr")
1200 (synopsis "Bio++ population genetics library")
1202 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1203 analysis, phylogenetics, molecular evolution and population genetics. This
1204 library provides population genetics-related modules.")
1205 (license license:cecill-c))))
1207 (define-public bpp-seq
1208 ;; The last release was in 2014 and the recommended way to install from source
1209 ;; is to clone the git repository, so we do this.
1210 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1211 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
1214 (version (string-append "2.2.0-1." (string-take commit 7)))
1218 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
1220 (file-name (string-append name "-" version "-checkout"))
1223 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
1224 (build-system cmake-build-system)
1226 `(#:parallel-build? #f
1227 ;; If out-of-source, test data is not copied into the build directory
1228 ;; so the tests fail.
1229 #:out-of-source? #f))
1231 `(("bpp-core" ,bpp-core)))
1232 (home-page "http://biopp.univ-montp2.fr")
1233 (synopsis "Bio++ sequence library")
1235 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1236 analysis, phylogenetics, molecular evolution and population genetics. This
1237 library provides sequence-related modules.")
1238 (license license:cecill-c))))
1240 (define-public bppsuite
1241 ;; The last release was in 2014 and the recommended way to install from source
1242 ;; is to clone the git repository, so we do this.
1243 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1244 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
1247 (version (string-append "2.2.0-1." (string-take commit 7)))
1251 (url "http://biopp.univ-montp2.fr/git/bppsuite")
1253 (file-name (string-append name "-" version "-checkout"))
1256 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
1257 (build-system cmake-build-system)
1259 `(#:parallel-build? #f
1260 #:tests? #f)) ; There are no tests.
1264 ("texinfo" ,texinfo)))
1266 `(("bpp-core" ,bpp-core)
1267 ("bpp-seq" ,bpp-seq)
1268 ("bpp-phyl" ,bpp-phyl)
1269 ("bpp-phyl" ,bpp-popgen)))
1270 (home-page "http://biopp.univ-montp2.fr")
1271 (synopsis "Bioinformatics tools written with the Bio++ libraries")
1273 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1274 analysis, phylogenetics, molecular evolution and population genetics. This
1275 package provides command line tools using the Bio++ library.")
1276 (license license:cecill-c))))
1278 (define-public blast+
1285 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
1286 version "/ncbi-blast-" version "+-src.tar.gz"))
1289 "1jlq0afxxgczpp35k6mxh8mn4jzq7vqcnaixk166sfj10wq8v9qh"))
1290 (modules '((guix build utils)))
1293 ;; Remove bundled bzip2, zlib and pcre.
1294 (delete-file-recursively "c++/src/util/compress/bzip2")
1295 (delete-file-recursively "c++/src/util/compress/zlib")
1296 (delete-file-recursively "c++/src/util/regexp")
1297 (substitute* "c++/src/util/compress/Makefile.in"
1298 (("bzip2 zlib api") "api"))
1299 ;; Remove useless msbuild directory
1300 (delete-file-recursively
1301 "c++/src/build-system/project_tree_builder/msbuild")
1303 (build-system gnu-build-system)
1305 `(;; There are two(!) tests for this massive library, and both fail with
1306 ;; "unparsable timing stats".
1307 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
1308 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
1311 #:parallel-build? #f ; not supported
1313 (modify-phases %standard-phases
1314 (add-before 'configure 'set-HOME
1315 ;; $HOME needs to be set at some point during the configure phase
1316 (lambda _ (setenv "HOME" "/tmp") #t))
1317 (add-after 'unpack 'enter-dir
1318 (lambda _ (chdir "c++") #t))
1319 (add-after 'enter-dir 'fix-build-system
1321 (define (which* cmd)
1322 (cond ((string=? cmd "date")
1323 ;; make call to "date" deterministic
1328 (format (current-error-port)
1329 "WARNING: Unable to find absolute path for ~s~%"
1333 ;; Rewrite hardcoded paths to various tools
1334 (substitute* (append '("src/build-system/configure.ac"
1335 "src/build-system/configure"
1336 "src/build-system/helpers/run_with_lock.c"
1337 "scripts/common/impl/if_diff.sh"
1338 "scripts/common/impl/run_with_lock.sh"
1339 "src/build-system/Makefile.configurables.real"
1340 "src/build-system/Makefile.in.top"
1341 "src/build-system/Makefile.meta.gmake=no"
1342 "src/build-system/Makefile.meta.in"
1343 "src/build-system/Makefile.meta_l"
1344 "src/build-system/Makefile.meta_p"
1345 "src/build-system/Makefile.meta_r"
1346 "src/build-system/Makefile.mk.in"
1347 "src/build-system/Makefile.requirements"
1348 "src/build-system/Makefile.rules_with_autodep.in")
1349 (find-files "scripts/common/check" "\\.sh$"))
1350 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1351 (or (which* cmd) all)))
1353 (substitute* (find-files "src/build-system" "^config.*")
1354 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1357 ;; rewrite "/var/tmp" in check script
1358 (substitute* "scripts/common/check/check_make_unix.sh"
1359 (("/var/tmp") "/tmp"))
1361 ;; do not reset PATH
1362 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1364 (("action=/bin/") "action=")
1365 (("export PATH") ":"))
1368 (lambda* (#:key inputs outputs #:allow-other-keys)
1369 (let ((out (assoc-ref outputs "out"))
1370 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1371 (include (string-append (assoc-ref outputs "include")
1372 "/include/ncbi-tools++")))
1373 ;; The 'configure' script doesn't recognize things like
1374 ;; '--enable-fast-install'.
1375 (invoke "./configure.orig"
1376 (string-append "--with-build-root=" (getcwd) "/build")
1377 (string-append "--prefix=" out)
1378 (string-append "--libdir=" lib)
1379 (string-append "--includedir=" include)
1380 (string-append "--with-bz2="
1381 (assoc-ref inputs "bzip2"))
1382 (string-append "--with-z="
1383 (assoc-ref inputs "zlib"))
1384 (string-append "--with-pcre="
1385 (assoc-ref inputs "pcre"))
1386 ;; Each library is built twice by default, once
1387 ;; with "-static" in its name, and again
1392 (outputs '("out" ; 21 MB
1401 ("python" ,python-wrapper)))
1404 (home-page "http://blast.ncbi.nlm.nih.gov")
1405 (synopsis "Basic local alignment search tool")
1407 "BLAST is a popular method of performing a DNA or protein sequence
1408 similarity search, using heuristics to produce results quickly. It also
1409 calculates an “expect value” that estimates how many matches would have
1410 occurred at a given score by chance, which can aid a user in judging how much
1411 confidence to have in an alignment.")
1412 ;; Most of the sources are in the public domain, with the following
1415 ;; * ./c++/include/util/bitset/
1416 ;; * ./c++/src/html/ncbi_menu*.js
1418 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1420 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1422 ;; * ./c++/src/corelib/teamcity_*
1423 (license (list license:public-domain
1429 (define-public bless
1435 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1439 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1440 (modules '((guix build utils)))
1443 ;; Remove bundled boost, pigz, zlib, and .git directory
1444 ;; FIXME: also remove bundled sources for murmurhash3 and
1445 ;; kmc once packaged.
1446 (delete-file-recursively "boost")
1447 (delete-file-recursively "pigz")
1448 (delete-file-recursively "google-sparsehash")
1449 (delete-file-recursively "zlib")
1450 (delete-file-recursively ".git")
1452 (build-system gnu-build-system)
1454 '(#:tests? #f ;no "check" target
1456 (list (string-append "ZLIB="
1457 (assoc-ref %build-inputs "zlib:static")
1459 (string-append "LDFLAGS="
1460 (string-join '("-lboost_filesystem"
1466 (modify-phases %standard-phases
1467 (add-after 'unpack 'do-not-build-bundled-pigz
1468 (lambda* (#:key inputs outputs #:allow-other-keys)
1469 (substitute* "Makefile"
1470 (("cd pigz/pigz-2.3.3; make") ""))
1472 (add-after 'unpack 'patch-paths-to-executables
1473 (lambda* (#:key inputs outputs #:allow-other-keys)
1474 (substitute* "parse_args.cpp"
1475 (("kmc_binary = .*")
1476 (string-append "kmc_binary = \""
1477 (assoc-ref outputs "out")
1479 (("pigz_binary = .*")
1480 (string-append "pigz_binary = \""
1481 (assoc-ref inputs "pigz")
1485 (lambda* (#:key outputs #:allow-other-keys)
1486 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1487 (for-each (lambda (file)
1488 (install-file file bin))
1489 '("bless" "kmc/bin/kmc"))
1491 (delete 'configure))))
1495 `(("openmpi" ,openmpi)
1497 ("sparsehash" ,sparsehash)
1499 ("zlib:static" ,zlib "static")
1501 (supported-systems '("x86_64-linux"))
1502 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1503 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1505 "@dfn{Bloom-filter-based error correction solution for high-throughput
1506 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1507 correction tool for genomic reads produced by @dfn{Next-generation
1508 sequencing} (NGS). BLESS produces accurate correction results with much less
1509 memory compared with previous solutions and is also able to tolerate a higher
1510 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1511 errors at the end of reads.")
1512 (license license:gpl3+)))
1514 (define-public bowtie
1521 (url "https://github.com/BenLangmead/bowtie2.git")
1522 (commit (string-append "v" version))))
1523 (file-name (git-file-name name version))
1526 "1zl3cf327y2p7p03cavymbh7b00djc7lncfaqih33n96iy9q8ibp"))
1527 (modules '((guix build utils)))
1530 (substitute* "Makefile"
1531 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1532 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1533 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
1535 (build-system gnu-build-system)
1540 (string-append "prefix=" (assoc-ref %outputs "out")))
1542 (modify-phases %standard-phases
1547 "scripts/test/simple_tests.pl"
1548 "--bowtie2=./bowtie2"
1549 "--bowtie2-build=./bowtie2-build")
1554 ("python" ,python-wrapper)))
1557 ("perl-clone" ,perl-clone)
1558 ("perl-test-deep" ,perl-test-deep)
1559 ("perl-test-simple" ,perl-test-simple)))
1560 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1561 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1563 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1564 reads to long reference sequences. It is particularly good at aligning reads
1565 of about 50 up to 100s or 1,000s of characters, and particularly good at
1566 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1567 genome with an FM Index to keep its memory footprint small: for the human
1568 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1569 gapped, local, and paired-end alignment modes.")
1570 (supported-systems '("x86_64-linux"))
1571 (license license:gpl3+)))
1573 (define-public bowtie1
1579 (uri (string-append "mirror://sourceforge/bowtie-bio/bowtie/"
1580 version "/bowtie-src-x86_64.zip"))
1583 "0vmiqdhc9dzyfy9sh6vgi7k9xy2hiw8g87vbamnc6cgpm179zsa4"))
1584 (modules '((guix build utils)))
1586 '(substitute* "Makefile"
1587 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1588 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1589 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1590 (build-system gnu-build-system)
1592 '(#:tests? #f ; no "check" target
1595 (string-append "prefix=" (assoc-ref %outputs "out")))
1597 (modify-phases %standard-phases
1598 (delete 'configure))))
1602 (supported-systems '("x86_64-linux"))
1603 (home-page "http://bowtie-bio.sourceforge.net/index.shtml")
1604 (synopsis "Fast aligner for short nucleotide sequence reads")
1606 "Bowtie is a fast, memory-efficient short read aligner. It aligns short
1607 DNA sequences (reads) to the human genome at a rate of over 25 million 35-bp
1608 reads per hour. Bowtie indexes the genome with a Burrows-Wheeler index to
1609 keep its memory footprint small: typically about 2.2 GB for the human
1610 genome (2.9 GB for paired-end).")
1611 (license license:artistic2.0)))
1613 (define-public tophat
1620 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1624 "19add02kv2xhd6ihd779dr7x35ggym3jqr0m5c4315i1yfb0p11p"))
1625 (modules '((guix build utils)))
1628 ;; Remove bundled SeqAn and samtools
1629 (delete-file-recursively "src/SeqAn-1.4.2")
1630 (delete-file-recursively "src/samtools-0.1.18")
1632 (build-system gnu-build-system)
1634 '(#:parallel-build? #f ; not supported
1636 (modify-phases %standard-phases
1637 (add-after 'unpack 'use-system-samtools
1638 (lambda* (#:key inputs #:allow-other-keys)
1639 (substitute* "src/Makefile.in"
1640 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1641 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1642 (("SAMPROG = samtools_0\\.1\\.18") "")
1643 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1644 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1645 (substitute* '("src/common.cpp"
1647 (("samtools_0.1.18") (which "samtools")))
1648 (substitute* '("src/common.h"
1649 "src/bam2fastx.cpp")
1650 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1651 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1652 (substitute* '("src/bwt_map.h"
1654 "src/align_status.h")
1655 (("#include <bam.h>") "#include <samtools/bam.h>")
1656 (("#include <sam.h>") "#include <samtools/sam.h>"))
1659 `(("gcc" ,gcc-5))) ;; doesn't build with later versions
1663 ("ncurses" ,ncurses)
1665 ("python" ,python-2)
1666 ("samtools" ,samtools-0.1)
1669 (home-page "https://ccb.jhu.edu/software/tophat/index.shtml")
1670 (synopsis "Spliced read mapper for RNA-Seq data")
1672 "TopHat is a fast splice junction mapper for nucleotide sequence
1673 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1674 mammalian-sized genomes using the ultra high-throughput short read
1675 aligner Bowtie, and then analyzes the mapping results to identify
1676 splice junctions between exons.")
1677 ;; TopHat is released under the Boost Software License, Version 1.0
1678 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1679 (license license:boost1.0)))
1688 "https://github.com/lh3/bwa/releases/download/v"
1689 version "/bwa-" version ".tar.bz2"))
1692 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1693 (build-system gnu-build-system)
1695 '(#:tests? #f ;no "check" target
1697 (modify-phases %standard-phases
1699 (lambda* (#:key outputs #:allow-other-keys)
1700 (let* ((out (assoc-ref outputs "out"))
1701 (bin (string-append out "/bin"))
1702 (lib (string-append out "/lib"))
1703 (doc (string-append out "/share/doc/bwa"))
1704 (man (string-append out "/share/man/man1")))
1705 (install-file "bwa" bin)
1706 (install-file "libbwa.a" lib)
1707 (install-file "README.md" doc)
1708 (install-file "bwa.1" man))
1710 ;; no "configure" script
1711 (delete 'configure))))
1712 (inputs `(("zlib" ,zlib)))
1713 ;; Non-portable SSE instructions are used so building fails on platforms
1714 ;; other than x86_64.
1715 (supported-systems '("x86_64-linux"))
1716 (home-page "http://bio-bwa.sourceforge.net/")
1717 (synopsis "Burrows-Wheeler sequence aligner")
1719 "BWA is a software package for mapping low-divergent sequences against a
1720 large reference genome, such as the human genome. It consists of three
1721 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1722 designed for Illumina sequence reads up to 100bp, while the rest two for
1723 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1724 features such as long-read support and split alignment, but BWA-MEM, which is
1725 the latest, is generally recommended for high-quality queries as it is faster
1726 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1727 70-100bp Illumina reads.")
1728 (license license:gpl3+)))
1730 (define-public bwa-pssm
1731 (package (inherit bwa)
1737 (url "https://github.com/pkerpedjiev/bwa-pssm.git")
1739 (file-name (git-file-name name version))
1742 "076c4q0cdqz8jgylb067y9zmvxglppnzi3qiscn0xiypgc6lgb5r"))))
1743 (build-system gnu-build-system)
1748 (home-page "http://bwa-pssm.binf.ku.dk/")
1749 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1751 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1752 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1753 existing aligners it is fast and sensitive. Unlike most other aligners,
1754 however, it is also adaptible in the sense that one can direct the alignment
1755 based on known biases within the data set. It is coded as a modification of
1756 the original BWA alignment program and shares the genome index structure as
1757 well as many of the command line options.")
1758 (license license:gpl3+)))
1760 (define-public bwa-meth
1767 (url "https://github.com/brentp/bwa-meth.git")
1768 (commit (string-append "v" version))))
1769 (file-name (git-file-name name version))
1772 "17j31i7zws5j7mhsq9x3qgkxly6mlmrgwhfq0qbflgxrmx04yaiz"))))
1773 (build-system python-build-system)
1776 (modify-phases %standard-phases
1777 (add-after 'unpack 'keep-references-to-bwa
1778 (lambda* (#:key inputs #:allow-other-keys)
1779 (substitute* "bwameth.py"
1780 (("bwa (mem|index)" _ command)
1781 (string-append (which "bwa") " " command))
1782 ;; There's an ill-advised check for "samtools" on PATH.
1788 `(("python-toolshed" ,python-toolshed)))
1789 (home-page "https://github.com/brentp/bwa-meth")
1790 (synopsis "Fast and accurante alignment of BS-Seq reads")
1792 "BWA-Meth works for single-end reads and for paired-end reads from the
1793 directional protocol (most common). It uses the method employed by
1794 methylcoder and Bismark of in silico conversion of all C's to T's in both
1795 reference and reads. It recovers the original read (needed to tabulate
1796 methylation) by attaching it as a comment which BWA appends as a tag to the
1797 read. It performs favorably to existing aligners gauged by number of on and
1798 off-target reads for a capture method that targets CpG-rich region.")
1799 (license license:expat)))
1801 (define-public python-bx-python
1803 (name "python-bx-python")
1807 (uri (pypi-uri "bx-python" version))
1810 "11kksg2rbzihpmcid823xvg42xi88m7sz58rzk29abybkxy0rszs"))))
1811 (build-system python-build-system)
1812 ;; Tests fail because test data are not included
1813 (arguments '(#:tests? #f))
1815 `(("python-numpy" ,python-numpy)
1816 ("python-six" ,python-six)))
1820 `(("python-lzo" ,python-lzo)
1821 ("python-nose" ,python-nose)
1822 ("python-cython" ,python-cython)))
1823 (home-page "https://github.com/bxlab/bx-python")
1824 (synopsis "Tools for manipulating biological data")
1826 "bx-python provides tools for manipulating biological data, particularly
1827 multiple sequence alignments.")
1828 (license license:expat)))
1830 (define-public python2-bx-python
1831 (package-with-python2 python-bx-python))
1833 (define-public python-pysam
1835 (name "python-pysam")
1839 ;; Test data is missing on PyPi.
1841 (url "https://github.com/pysam-developers/pysam.git")
1842 (commit (string-append "v" version))))
1843 (file-name (git-file-name name version))
1846 "1vj367w6xbn9bpmksm162l1aipf7cj97h1q83y7jcpm33ihwpf7x"))
1847 (modules '((guix build utils)))
1849 ;; Drop bundled htslib. TODO: Also remove samtools
1851 (delete-file-recursively "htslib")
1853 (build-system python-build-system)
1855 `(#:modules ((ice-9 ftw)
1857 (guix build python-build-system)
1860 (modify-phases %standard-phases
1861 (add-before 'build 'set-flags
1862 (lambda* (#:key inputs #:allow-other-keys)
1863 (setenv "HTSLIB_MODE" "external")
1864 (setenv "HTSLIB_LIBRARY_DIR"
1865 (string-append (assoc-ref inputs "htslib") "/lib"))
1866 (setenv "HTSLIB_INCLUDE_DIR"
1867 (string-append (assoc-ref inputs "htslib") "/include"))
1868 (setenv "LDFLAGS" "-lncurses")
1869 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1872 (lambda* (#:key inputs outputs #:allow-other-keys)
1873 ;; This file contains tests that require a connection to the
1875 (delete-file "tests/tabix_test.py")
1876 ;; FIXME: This test fails
1877 (delete-file "tests/AlignmentFile_test.py")
1878 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1879 (setenv "PYTHONPATH"
1881 (getenv "PYTHONPATH")
1882 ":" (getcwd) "/build/"
1883 (car (scandir "build"
1884 (negate (cut string-prefix? "." <>))))))
1885 ;; Step out of source dir so python does not import from CWD.
1886 (with-directory-excursion "tests"
1887 (setenv "HOME" "/tmp")
1888 (invoke "make" "-C" "pysam_data")
1889 (invoke "make" "-C" "cbcf_data")
1890 ;; Running nosetests without explicitly asking for a single
1891 ;; process leads to a crash. Running with multiple processes
1892 ;; fails because the tests are not designed to run in parallel.
1894 ;; FIXME: tests keep timing out on some systems.
1895 (invoke "nosetests" "-v" "--processes" "1")))))))
1897 `(("htslib" ,htslib))) ; Included from installed header files.
1899 `(("ncurses" ,ncurses)
1903 `(("python-cython" ,python-cython)
1904 ;; Dependencies below are are for tests only.
1905 ("samtools" ,samtools)
1906 ("bcftools" ,bcftools)
1907 ("python-nose" ,python-nose)))
1908 (home-page "https://github.com/pysam-developers/pysam")
1909 (synopsis "Python bindings to the SAMtools C API")
1911 "Pysam is a Python module for reading and manipulating files in the
1912 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1913 also includes an interface for tabix.")
1914 (license license:expat)))
1916 (define-public python2-pysam
1917 (package-with-python2 python-pysam))
1919 (define-public python-twobitreader
1921 (name "python-twobitreader")
1926 (url "https://github.com/benjschiller/twobitreader")
1928 (file-name (git-file-name name version))
1931 "1qbxvv1h58cismbk1anpjrkpghsaiy64a11ir3lhy6qch6xf8n62"))))
1932 (build-system python-build-system)
1933 ;; Tests are not included
1934 (arguments '(#:tests? #f))
1936 `(("python-sphinx" ,python-sphinx)))
1937 (home-page "https://github.com/benjschiller/twobitreader")
1938 (synopsis "Python library for reading .2bit files")
1940 "twobitreader is a Python library for reading .2bit files as used by the
1941 UCSC genome browser.")
1942 (license license:artistic2.0)))
1944 (define-public python2-twobitreader
1945 (package-with-python2 python-twobitreader))
1947 (define-public python-plastid
1949 (name "python-plastid")
1953 (uri (pypi-uri "plastid" version))
1956 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1957 (build-system python-build-system)
1959 ;; Some test files are not included.
1962 `(("python-numpy" ,python-numpy)
1963 ("python-scipy" ,python-scipy)
1964 ("python-pandas" ,python-pandas)
1965 ("python-pysam" ,python-pysam)
1966 ("python-matplotlib" ,python-matplotlib)
1967 ("python-biopython" ,python-biopython)
1968 ("python-twobitreader" ,python-twobitreader)
1969 ("python-termcolor" ,python-termcolor)))
1971 `(("python-cython" ,python-cython)
1972 ("python-nose" ,python-nose)))
1973 (home-page "https://github.com/joshuagryphon/plastid")
1974 (synopsis "Python library for genomic analysis")
1976 "plastid is a Python library for genomic analysis – in particular,
1977 high-throughput sequencing data – with an emphasis on simplicity.")
1978 (license license:bsd-3)))
1980 (define-public python2-plastid
1981 (package-with-python2 python-plastid))
1983 (define-public tetoolkit
1990 (url "https://github.com/mhammell-laboratory/tetoolkit.git")
1992 (file-name (git-file-name name version))
1995 "1yzi0kfpzip8zpjb82x1ik6h22yzfyjiz2dv85v6as2awwqvk807"))))
1996 (build-system python-build-system)
1998 `(#:python ,python-2 ; not guaranteed to work with Python 3
2000 (modify-phases %standard-phases
2001 (add-after 'unpack 'make-writable
2003 (for-each make-file-writable (find-files "."))
2005 (add-after 'unpack 'patch-invocations
2006 (lambda* (#:key inputs #:allow-other-keys)
2007 (substitute* '("bin/TEtranscripts"
2010 (string-append "'" (which "sort") " "))
2012 (string-append "'" (which "rm") " -f "))
2013 (("'Rscript'") (string-append "'" (which "Rscript") "'")))
2014 (substitute* "TEToolkit/IO/ReadInputs.py"
2015 (("BamToBED") (which "bamToBed")))
2016 (substitute* "TEToolkit/Normalization.py"
2018 (string-append "\"" (which "Rscript") "\"")))
2020 (add-after 'install 'wrap-program
2021 (lambda* (#:key outputs #:allow-other-keys)
2022 ;; Make sure the executables find R packages.
2023 (let ((out (assoc-ref outputs "out")))
2026 (wrap-program (string-append out "/bin/" script)
2027 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
2032 `(("coreutils" ,coreutils)
2033 ("bedtools" ,bedtools)
2034 ("python-argparse" ,python2-argparse)
2035 ("python-pysam" ,python2-pysam)
2036 ("r-minimal" ,r-minimal)
2037 ("r-deseq2" ,r-deseq2)))
2038 (home-page "https://github.com/mhammell-laboratory/tetoolkit")
2039 (synopsis "Transposable elements in differential enrichment analysis")
2041 "This is package for including transposable elements in differential
2042 enrichment analysis of sequencing datasets. TEtranscripts and TEcount take
2043 RNA-seq (and similar data) and annotates reads to both genes and transposable
2044 elements. TEtranscripts then performs differential analysis using DESeq2.
2045 Note that TEtranscripts and TEcount rely on specially curated GTF files, which
2046 are not included due to their size.")
2047 (license license:gpl3+)))
2049 (define-public cd-hit
2055 (uri (string-append "https://github.com/weizhongli/cdhit"
2056 "/releases/download/V" version
2058 "-2017-0621-source.tar.gz"))
2061 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
2062 (build-system gnu-build-system)
2064 `(#:tests? #f ; there are no tests
2066 ;; Executables are copied directly to the PREFIX.
2067 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin")
2068 ;; Support longer sequences (e.g. Pacbio sequences)
2071 (modify-phases %standard-phases
2072 ;; No "configure" script
2074 ;; Remove sources of non-determinism
2075 (add-after 'unpack 'be-timeless
2077 (substitute* "cdhit-utility.c++"
2078 ((" \\(built on \" __DATE__ \"\\)") ""))
2079 (substitute* "cdhit-common.c++"
2080 (("__DATE__") "\"0\"")
2081 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
2083 ;; The "install" target does not create the target directory.
2084 (add-before 'install 'create-target-dir
2085 (lambda* (#:key outputs #:allow-other-keys)
2086 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
2090 (home-page "http://weizhongli-lab.org/cd-hit/")
2091 (synopsis "Cluster and compare protein or nucleotide sequences")
2093 "CD-HIT is a program for clustering and comparing protein or nucleotide
2094 sequences. CD-HIT is designed to be fast and handle extremely large
2096 ;; The manual says: "It can be copied under the GNU General Public License
2097 ;; version 2 (GPLv2)."
2098 (license license:gpl2)))
2100 (define-public clipper
2107 (url "https://github.com/YeoLab/clipper.git")
2109 (file-name (git-file-name name version))
2112 "0fja1rj84wp9vpj8rxpj3n8zqzcqq454m904yp9as1w4phccirjb"))
2113 (modules '((guix build utils)))
2116 ;; remove unnecessary setup dependency
2117 (substitute* "setup.py"
2118 (("setup_requires = .*") ""))
2120 (build-system python-build-system)
2122 `(#:python ,python-2 ; only Python 2 is supported
2124 (modify-phases %standard-phases
2125 ;; This is fixed in upstream commit
2126 ;; f6c2990198f906bf97730d95695b4bd5a6d01ddb.
2127 (add-after 'unpack 'fix-typo
2129 (substitute* "clipper/src/readsToWiggle.pyx"
2133 `(("htseq" ,python2-htseq)
2134 ("python-pybedtools" ,python2-pybedtools)
2135 ("python-cython" ,python2-cython)
2136 ("python-scikit-learn" ,python2-scikit-learn)
2137 ("python-matplotlib" ,python2-matplotlib)
2138 ("python-pandas" ,python2-pandas)
2139 ("python-pysam" ,python2-pysam)
2140 ("python-numpy" ,python2-numpy)
2141 ("python-scipy" ,python2-scipy)))
2143 `(("python-mock" ,python2-mock) ; for tests
2144 ("python-nose" ,python2-nose) ; for tests
2145 ("python-pytz" ,python2-pytz))) ; for tests
2146 (home-page "https://github.com/YeoLab/clipper")
2147 (synopsis "CLIP peak enrichment recognition")
2149 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
2150 (license license:gpl2)))
2152 (define-public codingquarry
2154 (name "codingquarry")
2159 "mirror://sourceforge/codingquarry/CodingQuarry_v"
2163 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
2164 (build-system gnu-build-system)
2166 '(#:tests? #f ; no "check" target
2168 (modify-phases %standard-phases
2171 (lambda* (#:key outputs #:allow-other-keys)
2172 (let* ((out (assoc-ref outputs "out"))
2173 (bin (string-append out "/bin"))
2174 (doc (string-append out "/share/doc/codingquarry")))
2175 (install-file "INSTRUCTIONS.pdf" doc)
2176 (copy-recursively "QuarryFiles"
2177 (string-append out "/QuarryFiles"))
2178 (install-file "CodingQuarry" bin)
2179 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin))
2181 (inputs `(("openmpi" ,openmpi)))
2182 (native-search-paths
2183 (list (search-path-specification
2184 (variable "QUARRY_PATH")
2185 (files '("QuarryFiles")))))
2186 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
2187 (synopsis "Fungal gene predictor")
2188 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
2189 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
2190 (home-page "https://sourceforge.net/projects/codingquarry/")
2191 (license license:gpl3+)))
2193 (define-public couger
2200 "http://couger.oit.duke.edu/static/assets/COUGER"
2204 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
2205 (build-system gnu-build-system)
2209 (modify-phases %standard-phases
2214 (lambda* (#:key outputs #:allow-other-keys)
2215 (let* ((out (assoc-ref outputs "out"))
2216 (bin (string-append out "/bin")))
2217 (copy-recursively "src" (string-append out "/src"))
2219 ;; Add "src" directory to module lookup path.
2220 (substitute* "couger"
2222 (string-append "import sys\nsys.path.append(\""
2223 out "\")\nfrom argparse")))
2224 (install-file "couger" bin))
2227 'install 'wrap-program
2228 (lambda* (#:key inputs outputs #:allow-other-keys)
2229 ;; Make sure 'couger' runs with the correct PYTHONPATH.
2230 (let* ((out (assoc-ref outputs "out"))
2231 (path (getenv "PYTHONPATH")))
2232 (wrap-program (string-append out "/bin/couger")
2233 `("PYTHONPATH" ":" prefix (,path))))
2236 `(("python" ,python-2)
2237 ("python2-pillow" ,python2-pillow)
2238 ("python2-numpy" ,python2-numpy)
2239 ("python2-scipy" ,python2-scipy)
2240 ("python2-matplotlib" ,python2-matplotlib)))
2242 `(("r-minimal" ,r-minimal)
2244 ("randomjungle" ,randomjungle)))
2246 `(("unzip" ,unzip)))
2247 (home-page "http://couger.oit.duke.edu")
2248 (synopsis "Identify co-factors in sets of genomic regions")
2250 "COUGER can be applied to any two sets of genomic regions bound by
2251 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
2252 putative co-factors that provide specificity to each TF. The framework
2253 determines the genomic targets uniquely-bound by each TF, and identifies a
2254 small set of co-factors that best explain the in vivo binding differences
2255 between the two TFs.
2257 COUGER uses classification algorithms (support vector machines and random
2258 forests) with features that reflect the DNA binding specificities of putative
2259 co-factors. The features are generated either from high-throughput TF-DNA
2260 binding data (from protein binding microarray experiments), or from large
2261 collections of DNA motifs.")
2262 (license license:gpl3+)))
2264 (define-public clustal-omega
2266 (name "clustal-omega")
2270 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
2274 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
2275 (build-system gnu-build-system)
2277 `(("argtable" ,argtable)))
2278 (home-page "http://www.clustal.org/omega/")
2279 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
2281 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
2282 program for protein and DNA/RNA. It produces high quality MSAs and is capable
2283 of handling data-sets of hundreds of thousands of sequences in reasonable
2285 (license license:gpl2+)))
2287 (define-public crossmap
2293 (uri (pypi-uri "CrossMap" version))
2296 "1sb2f2qbxya4fzw3yjl09vbrs8vfmw22zrygrvz004sf9gb1vkan"))))
2297 (build-system python-build-system)
2299 `(("python-bx-python" ,python-bx-python)
2300 ("python-numpy" ,python-numpy)
2301 ("python-pybigwig" ,python-pybigwig)
2302 ("python-pysam" ,python-pysam)
2305 `(("python-cython" ,python-cython)
2306 ("python-nose" ,python-nose)))
2307 (home-page "http://crossmap.sourceforge.net/")
2308 (synopsis "Convert genome coordinates between assemblies")
2310 "CrossMap is a program for conversion of genome coordinates or annotation
2311 files between different genome assemblies. It supports most commonly used
2312 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
2313 (license license:gpl2+)))
2315 (define-public python-dnaio
2317 (name "python-dnaio")
2322 (uri (pypi-uri "dnaio" version))
2325 "0f16m7hdlm0fz1n7y5asy0v9ghyrq17ni1p9iybq22ddzyd49r27"))))
2326 (build-system python-build-system)
2328 `(("python-cython" ,python-cython)
2329 ("python-pytest" ,python-pytest)
2330 ("python-xopen" ,python-xopen)))
2331 (home-page "https://github.com/marcelm/dnaio/")
2332 (synopsis "Read FASTA and FASTQ files efficiently")
2334 "dnaio is a Python library for fast parsing of FASTQ and also FASTA
2335 files. The code was previously part of the cutadapt tool.")
2336 (license license:expat)))
2338 (define-public python-deeptoolsintervals
2340 (name "python-deeptoolsintervals")
2344 (uri (pypi-uri "deeptoolsintervals" version))
2347 "1xnl80nblysj6dylj4683wgrfa425rkx4dp5k65hvwdns9pw753x"))))
2348 (build-system python-build-system)
2351 (home-page "https://github.com/deeptools/deeptools_intervals")
2352 (synopsis "Create GTF-based interval trees with associated meta-data")
2354 "This package provides a Python module creating/accessing GTF-based
2355 interval trees with associated meta-data. It is primarily used by the
2356 @code{deeptools} package.")
2357 (license license:expat)))
2359 (define-public python-deeptools
2361 (name "python-deeptools")
2365 (uri (pypi-uri "deepTools" version))
2368 "1azgjniss5ff6a90nicdjkxyjwqmi3gzfn09gra42hwlz19hipxb"))))
2369 (build-system python-build-system)
2371 `(("python-matplotlib" ,python-matplotlib)
2372 ("python-numpy" ,python-numpy)
2373 ("python-numpydoc" ,python-numpydoc)
2374 ("python-py2bit" ,python-py2bit)
2375 ("python-pybigwig" ,python-pybigwig)
2376 ("python-pysam" ,python-pysam)
2377 ("python-scipy" ,python-scipy)
2378 ("python-deeptoolsintervals" ,python-deeptoolsintervals)
2379 ("python-plotly" ,python-plotly)))
2380 (home-page "https://pypi.org/project/deepTools/")
2381 (synopsis "Useful tools for exploring deep sequencing data")
2382 (description "This package addresses the challenge of handling large amounts
2383 of data that are now routinely generated from DNA sequencing centers.
2384 @code{deepTools} contains useful modules to process the mapped reads data for
2385 multiple quality checks, creating normalized coverage files in standard bedGraph
2386 and bigWig file formats, that allow comparison between different files. Finally,
2387 using such normalized and standardized files, deepTools can create many
2388 publication-ready visualizations to identify enrichments and for functional
2389 annotations of the genome.")
2390 ;; The file deeptools/cm.py is licensed under the BSD license. The
2391 ;; remainder of the code is licensed under the MIT license.
2392 (license (list license:bsd-3 license:expat))))
2394 (define-public cutadapt
2400 (uri (pypi-uri "cutadapt" version))
2403 "1vqmsfkm6llxzmsz9wcfcvzx9a9f8iabvwik2rbyn7nc4wm25z89"))))
2404 (build-system python-build-system)
2406 `(("python-dnaio" ,python-dnaio)
2407 ("python-xopen" ,python-xopen)))
2409 `(("python-cython" ,python-cython)
2410 ("python-pytest" ,python-pytest)
2411 ("python-setuptools-scm" ,python-setuptools-scm)))
2412 (home-page "https://cutadapt.readthedocs.io/en/stable/")
2413 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
2415 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
2416 other types of unwanted sequence from high-throughput sequencing reads.")
2417 (license license:expat)))
2419 (define-public libbigwig
2426 (url "https://github.com/dpryan79/libBigWig.git")
2428 (file-name (git-file-name name version))
2431 "09693dmf1scdac5pyq6qyn8b4mcipvnmc370k9a5z41z81m3dcsj"))))
2432 (build-system gnu-build-system)
2434 `(#:test-target "test"
2435 #:tests? #f ; tests require access to the web
2438 (string-append "prefix=" (assoc-ref %outputs "out")))
2440 (modify-phases %standard-phases
2441 (delete 'configure))))
2446 `(("doxygen" ,doxygen)
2448 ("python" ,python-2)))
2449 (home-page "https://github.com/dpryan79/libBigWig")
2450 (synopsis "C library for handling bigWig files")
2452 "This package provides a C library for parsing local and remote BigWig
2454 (license license:expat)))
2456 (define-public python-pybigwig
2458 (name "python-pybigwig")
2462 (uri (pypi-uri "pyBigWig" version))
2465 "157x6v48y299zm382krf1dw08fdxg95im8lnabhp5vc94s04zxj1"))
2466 (modules '((guix build utils)))
2469 ;; Delete bundled libBigWig sources
2470 (delete-file-recursively "libBigWig")
2472 (build-system python-build-system)
2475 (modify-phases %standard-phases
2476 (add-after 'unpack 'link-with-libBigWig
2477 (lambda* (#:key inputs #:allow-other-keys)
2478 (substitute* "setup.py"
2479 (("libs=\\[") "libs=[\"BigWig\", "))
2482 `(("python-numpy" ,python-numpy)))
2484 `(("libbigwig" ,libbigwig)
2487 (home-page "https://github.com/dpryan79/pyBigWig")
2488 (synopsis "Access bigWig files in Python using libBigWig")
2490 "This package provides Python bindings to the libBigWig library for
2491 accessing bigWig files.")
2492 (license license:expat)))
2494 (define-public python2-pybigwig
2495 (package-with-python2 python-pybigwig))
2497 (define-public python-dendropy
2499 (name "python-dendropy")
2504 ;; Source from GitHub so that tests are included.
2506 (url "https://github.com/jeetsukumaran/DendroPy.git")
2507 (commit (string-append "v" version))))
2508 (file-name (git-file-name name version))
2511 "097hfyv2kaf4x92i4rjx0paw2cncxap48qivv8zxng4z7nhid0x9"))))
2512 (build-system python-build-system)
2513 (home-page "https://dendropy.org/")
2514 (synopsis "Library for phylogenetics and phylogenetic computing")
2516 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
2517 writing, simulation, processing and manipulation of phylogenetic
2518 trees (phylogenies) and characters.")
2519 (license license:bsd-3)))
2521 (define-public python2-dendropy
2522 (let ((base (package-with-python2 python-dendropy)))
2527 (modify-phases %standard-phases
2528 (add-after 'unpack 'remove-failing-test
2530 ;; This test fails when the full test suite is run, as documented
2531 ;; at https://github.com/jeetsukumaran/DendroPy/issues/74
2532 (substitute* "tests/test_dataio_nexml_reader_tree_list.py"
2533 (("test_collection_comments_and_annotations")
2534 "do_not_test_collection_comments_and_annotations"))
2536 ,@(package-arguments base))))))
2538 (define-public python-py2bit
2540 (name "python-py2bit")
2545 (uri (pypi-uri "py2bit" version))
2548 "1vw2nvw1yrl7ikkqsqs1pg239yr5nspvd969r1x9arms1k25a1a5"))))
2549 (build-system python-build-system)
2550 (home-page "https://github.com/dpryan79/py2bit")
2551 (synopsis "Access 2bit files using lib2bit")
2553 "This package provides Python bindings for lib2bit to access 2bit files
2555 (license license:expat)))
2557 (define-public deeptools
2564 (url "https://github.com/deeptools/deepTools.git")
2566 (file-name (git-file-name name version))
2569 "1vggnf52g6q2vifdl4cyi7s2fnfqq0ky2zrkj5zv2qfzsc3p3siw"))))
2570 (build-system python-build-system)
2573 (modify-phases %standard-phases
2574 ;; This phase fails, but it's not needed.
2575 (delete 'reset-gzip-timestamps))))
2577 `(("python-plotly" ,python-plotly)
2578 ("python-scipy" ,python-scipy)
2579 ("python-numpy" ,python-numpy)
2580 ("python-numpydoc" ,python-numpydoc)
2581 ("python-matplotlib" ,python-matplotlib)
2582 ("python-pysam" ,python-pysam)
2583 ("python-py2bit" ,python-py2bit)
2584 ("python-pybigwig" ,python-pybigwig)))
2586 `(("python-mock" ,python-mock) ;for tests
2587 ("python-nose" ,python-nose) ;for tests
2588 ("python-pytz" ,python-pytz))) ;for tests
2589 (home-page "https://github.com/deeptools/deepTools")
2590 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2592 "DeepTools addresses the challenge of handling the large amounts of data
2593 that are now routinely generated from DNA sequencing centers. To do so,
2594 deepTools contains useful modules to process the mapped reads data to create
2595 coverage files in standard bedGraph and bigWig file formats. By doing so,
2596 deepTools allows the creation of normalized coverage files or the comparison
2597 between two files (for example, treatment and control). Finally, using such
2598 normalized and standardized files, multiple visualizations can be created to
2599 identify enrichments with functional annotations of the genome.")
2600 (license license:gpl3+)))
2602 (define-public delly
2609 (url "https://github.com/dellytools/delly.git")
2610 (commit (string-append "v" version))))
2611 (file-name (git-file-name name version))
2613 (base32 "034jqsxswy9gqdh2zkgc1js99qkv75ks4xvzgmh0284sraagv61z"))
2614 (modules '((guix build utils)))
2617 (delete-file-recursively "src/htslib")
2619 (build-system gnu-build-system)
2621 `(#:tests? #f ; There are no tests to run.
2623 (list "PARALLEL=1" ; Allow parallel execution at run-time.
2624 (string-append "prefix=" (assoc-ref %outputs "out")))
2626 (modify-phases %standard-phases
2627 (delete 'configure) ; There is no configure phase.
2628 (add-after 'install 'install-templates
2629 (lambda* (#:key outputs #:allow-other-keys)
2630 (let ((templates (string-append (assoc-ref outputs "out")
2631 "/share/delly/templates")))
2633 (copy-recursively "excludeTemplates" templates)
2640 (home-page "https://github.com/dellytools/delly")
2641 (synopsis "Integrated structural variant prediction method")
2642 (description "Delly is an integrated structural variant prediction method
2643 that can discover and genotype deletions, tandem duplications, inversions and
2644 translocations at single-nucleotide resolution in short-read massively parallel
2645 sequencing data. It uses paired-ends and split-reads to sensitively and
2646 accurately delineate genomic rearrangements throughout the genome.")
2647 (license license:gpl3+)))
2649 (define-public diamond
2656 (url "https://github.com/bbuchfink/diamond.git")
2657 (commit (string-append "v" version))))
2658 (file-name (git-file-name name version))
2661 "0k6f3kb6cniw11xw6763kkbs1sl0yack7xsy7q5fl5v170ssphq4"))))
2662 (build-system cmake-build-system)
2664 '(#:tests? #f ; no "check" target
2666 (modify-phases %standard-phases
2667 (add-after 'unpack 'remove-native-compilation
2669 (substitute* "CMakeLists.txt" (("-march=native") ""))
2673 (home-page "https://github.com/bbuchfink/diamond")
2674 (synopsis "Accelerated BLAST compatible local sequence aligner")
2676 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2677 translated DNA query sequences against a protein reference database (BLASTP
2678 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2679 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2680 data and settings.")
2681 (license license:agpl3+)))
2683 (define-public discrover
2691 (url "https://github.com/maaskola/discrover.git")
2693 (file-name (git-file-name name version))
2696 "173fwi2vb6a5kp406hm3jj6j7v4whww796f2qcygp4rpvamh307y"))))
2697 (build-system cmake-build-system)
2699 `(#:tests? #f ; there are no tests
2701 (modify-phases %standard-phases
2702 (add-after 'unpack 'fix-latex-errors
2704 (with-fluids ((%default-port-encoding #f))
2705 (substitute* "doc/references.bib"
2706 (("\\{S\\}illanp[^,]+,")
2707 "{S}illanp{\\\"a}{\\\"a},")))
2708 ;; XXX: I just can't get pdflatex to not complain about these
2709 ;; characters. They end up in the manual via the generated
2710 ;; discrover-cli-help.txt.
2711 (substitute* "src/hmm/cli.cpp"
2715 ;; This seems to be a syntax error.
2716 (substitute* "doc/discrover-manual.tex"
2717 (("theverbbox\\[t\\]") "theverbbox"))
2719 (add-after 'unpack 'add-missing-includes
2721 (substitute* "src/executioninformation.hpp"
2722 (("#define EXECUTIONINFORMATION_HPP" line)
2723 (string-append line "\n#include <random>")))
2724 (substitute* "src/plasma/fasta.hpp"
2725 (("#define FASTA_HPP" line)
2726 (string-append line "\n#include <random>")))
2728 ;; FIXME: this is needed because we're using texlive-union, which
2729 ;; doesn't handle fonts correctly. It expects to be able to generate
2730 ;; fonts in the home directory.
2731 (add-before 'build 'setenv-HOME
2732 (lambda _ (setenv "HOME" "/tmp") #t)))))
2736 ("rmath-standalone" ,rmath-standalone)))
2738 `(("texlive" ,(texlive-union (list texlive-fonts-cm
2739 texlive-fonts-amsfonts
2742 texlive-latex-examplep
2743 texlive-latex-hyperref
2745 texlive-latex-natbib
2746 texlive-bibtex ; style files used by natbib
2747 texlive-latex-pgf ; tikz
2748 texlive-latex-verbatimbox)))
2749 ("imagemagick" ,imagemagick)))
2750 (home-page "https://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2751 (synopsis "Discover discriminative nucleotide sequence motifs")
2752 (description "Discrover is a motif discovery method to find binding sites
2753 of nucleic acid binding proteins.")
2754 (license license:gpl3+)))
2756 (define-public eigensoft
2764 (url "https://github.com/DReichLab/EIG.git")
2765 (commit (string-append "v" version))))
2766 (file-name (git-file-name name version))
2769 "1c141fqvhnzibmnf22sv23vbmzm20kjjyrib44cfh75wyndp2d9k"))
2770 (modules '((guix build utils)))
2771 ;; Remove pre-built binaries.
2773 (delete-file-recursively "bin")
2776 (build-system gnu-build-system)
2778 `(#:tests? #f ; There are no tests.
2779 #:make-flags '("CC=gcc")
2781 (modify-phases %standard-phases
2782 ;; There is no configure phase, but the Makefile is in a
2785 (lambda _ (chdir "src") #t))
2786 ;; The provided install target only copies executables to
2787 ;; the "bin" directory in the build root.
2788 (add-after 'install 'actually-install
2789 (lambda* (#:key outputs #:allow-other-keys)
2790 (let* ((out (assoc-ref outputs "out"))
2791 (bin (string-append out "/bin")))
2792 (for-each (lambda (file)
2793 (install-file file bin))
2794 (find-files "../bin" ".*"))
2799 ("openblas" ,openblas)
2801 ("gfortran" ,gfortran "lib")))
2802 (home-page "https://github.com/DReichLab/EIG")
2803 (synopsis "Tools for population genetics")
2804 (description "The EIGENSOFT package provides tools for population
2805 genetics and stratification correction. EIGENSOFT implements methods commonly
2806 used in population genetics analyses such as PCA, computation of Tracy-Widom
2807 statistics, and finding related individuals in structured populations. It
2808 comes with a built-in plotting script and supports multiple file formats and
2809 quantitative phenotypes.")
2810 ;; The license of the eigensoft tools is Expat, but since it's
2811 ;; linking with the GNU Scientific Library (GSL) the effective
2812 ;; license is the GPL.
2813 (license license:gpl3+)))
2815 (define-public edirect
2818 (version "13.3.20200128")
2821 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect"
2822 "/versions/" version
2823 "/edirect-" version ".tar.gz"))
2826 "093zp7klv81ph0y8mm8d78a9hnpfxbv2kdym70gzdf3vz176rw33"))
2827 (modules '((guix build utils)))
2829 '(begin (delete-file "Mozilla-CA.tar.gz")
2830 (substitute* "rchive.go"
2831 ;; This go library does not have any license.
2832 (("github.com/fiam/gounidecode/unidecode")
2833 "golang.org/rainycape/unidecode"))
2835 (build-system perl-build-system)
2838 (modify-phases %standard-phases
2841 (delete 'check) ; simple check after install
2842 (add-after 'unpack 'patch-programs
2843 (lambda* (#:key inputs #:allow-other-keys)
2844 ;; Ignore errors about missing xtract.Linux and rchive.Linux.
2845 (substitute* "pm-refresh"
2846 (("cat \\\"\\$target")
2847 "grep ^[[:digit:]] \"$target"))
2850 (lambda* (#:key inputs outputs #:allow-other-keys)
2851 (let ((bin (string-append (assoc-ref outputs "out") "/bin"))
2852 (edirect-go (assoc-ref inputs "edirect-go-programs")))
2855 (install-file file bin))
2856 '("archive-pubmed" "asp-cp" "asp-ls" "download-ncbi-data"
2857 "download-pubmed" "edirect.pl" "efetch" "epost" "esearch"
2858 "fetch-pubmed" "ftp-cp" "ftp-ls" "has-asp" "index-pubmed"
2859 "pm-prepare" "pm-refresh" "pm-stash" "pm-collect"
2860 "pm-index" "pm-invert" "pm-merge" "pm-promote"))
2861 (symlink (string-append edirect-go "/bin/xtract.Linux")
2862 (string-append bin "/xtract"))
2863 (symlink (string-append edirect-go "/bin/rchive.Linux")
2864 (string-append bin "/rchive")))
2866 (add-after 'install 'wrap-program
2867 (lambda* (#:key outputs #:allow-other-keys)
2868 ;; Make sure everything can run in a pure environment.
2869 (let ((out (assoc-ref outputs "out"))
2870 (path (getenv "PERL5LIB")))
2874 `("PERL5LIB" ":" prefix (,path)))
2876 `("PATH" ":" prefix (,(string-append out "/bin")
2877 ,(dirname (which "sed"))
2878 ,(dirname (which "gzip"))
2879 ,(dirname (which "grep"))
2880 ,(dirname (which "perl"))
2881 ,(dirname (which "uname"))))))
2882 (find-files out ".")))
2884 (add-after 'wrap-program 'check
2885 (lambda* (#:key outputs #:allow-other-keys)
2886 (invoke (string-append (assoc-ref outputs "out")
2891 `(("edirect-go-programs" ,edirect-go-programs)
2892 ("perl-html-parser" ,perl-html-parser)
2893 ("perl-encode-locale" ,perl-encode-locale)
2894 ("perl-file-listing" ,perl-file-listing)
2895 ("perl-html-tagset" ,perl-html-tagset)
2896 ("perl-html-tree" ,perl-html-tree)
2897 ("perl-http-cookies" ,perl-http-cookies)
2898 ("perl-http-date" ,perl-http-date)
2899 ("perl-http-message" ,perl-http-message)
2900 ("perl-http-negotiate" ,perl-http-negotiate)
2901 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2902 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2903 ("perl-net-http" ,perl-net-http)
2904 ("perl-uri" ,perl-uri)
2905 ("perl-www-robotrules" ,perl-www-robotrules)
2906 ("perl-xml-simple" ,perl-xml-simple)
2908 (home-page "https://www.ncbi.nlm.nih.gov/books/NBK179288/")
2909 (synopsis "Tools for accessing the NCBI's set of databases")
2911 "Entrez Direct (EDirect) is a method for accessing the National Center
2912 for Biotechnology Information's (NCBI) set of interconnected
2913 databases (publication, sequence, structure, gene, variation, expression,
2914 etc.) from a terminal. Functions take search terms from command-line
2915 arguments. Individual operations are combined to build multi-step queries.
2916 Record retrieval and formatting normally complete the process.
2918 EDirect also provides an argument-driven function that simplifies the
2919 extraction of data from document summaries or other results that are returned
2920 in structured XML format. This can eliminate the need for writing custom
2921 software to answer ad hoc questions.")
2922 (native-search-paths
2923 ;; Ideally this should be set for LWP somewhere.
2924 (list (search-path-specification
2925 (variable "PERL_LWP_SSL_CA_FILE")
2926 (file-type 'regular)
2928 (files '("/etc/ssl/certs/ca-certificates.crt")))))
2929 (license license:public-domain)))
2931 (define-public edirect-go-programs
2934 (name "edirect-go-programs")
2935 (build-system go-build-system)
2937 `(#:install-source? #f
2938 #:tests? #f ; No tests.
2939 #:import-path "ncbi.nlm.nih.gov/entrez/edirect"
2941 (modify-phases %standard-phases
2943 (lambda* (#:key import-path #:allow-other-keys)
2944 (with-directory-excursion (string-append "src/" import-path)
2945 (invoke "go" "build" "-v" "-x" "j2x.go")
2946 (invoke "go" "build" "-v" "-x" "t2x.go")
2947 (invoke "go" "build" "-v" "-x" "-o"
2948 "xtract.Linux" "xtract.go" "common.go")
2949 (invoke "go" "build" "-v" "-x" "-o"
2950 "rchive.Linux" "rchive.go" "common.go")
2951 (invoke "go" "build" "-v" "-x" "-o" "symbols.Linux" "s2p.go"))))
2953 (lambda* (#:key outputs import-path #:allow-other-keys)
2954 (let ((dest (string-append (assoc-ref outputs "out") "/bin"))
2955 (source (string-append "src/" import-path "/")))
2956 (for-each (lambda (file)
2957 (format #t "installing ~a~%" file)
2958 (install-file (string-append source file) dest))
2959 '("j2x" "t2x" "symbols.Linux" "xtract.Linux" "rchive.Linux"))
2962 (propagated-inputs '())
2964 `(("go-github-com-fatih-color" ,go-github-com-fatih-color)
2965 ("go-github-com-fogleman-gg" ,go-github-com-fogleman-gg)
2966 ("go-github-com-gedex-inflector" ,go-github-com-gedex-inflector)
2967 ("go-github-com-golang-freetype" ,go-github-com-golang-freetype)
2968 ("go-github-com-klauspost-cpuid" ,go-github-com-klauspost-cpuid)
2969 ("go-github-com-pbnjay-memory" ,go-github-com-pbnjay-memory)
2970 ("go-github-com-surgebase-porter2" ,go-github-com-surgebase-porter2)
2971 ("go-golang-org-rainycape-unidecode" ,go-golang-org-rainycape-unidecode)
2972 ("go-golang-org-x-image" ,go-golang-org-x-image)
2973 ("go-golang-org-x-text" ,go-golang-org-x-text)))))
2975 (define-public exonerate
2984 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2985 "exonerate-" version ".tar.gz"))
2988 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2989 (build-system gnu-build-system)
2991 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2993 `(("pkg-config" ,pkg-config)))
2997 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2998 (synopsis "Generic tool for biological sequence alignment")
3000 "Exonerate is a generic tool for pairwise sequence comparison. It allows
3001 the alignment of sequences using a many alignment models, either exhaustive
3002 dynamic programming or a variety of heuristics.")
3003 (license license:gpl3)))
3005 (define-public express
3013 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
3014 version "/express-" version "-src.tgz"))
3017 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
3018 (build-system cmake-build-system)
3020 `(#:tests? #f ;no "check" target
3022 (modify-phases %standard-phases
3023 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
3024 (lambda* (#:key inputs #:allow-other-keys)
3025 (substitute* "CMakeLists.txt"
3026 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
3027 "set(Boost_USE_STATIC_LIBS OFF)")
3028 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
3029 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
3030 (substitute* "src/CMakeLists.txt"
3031 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
3032 (string-append (assoc-ref inputs "bamtools") "/lib"))
3033 (("libprotobuf.a") "libprotobuf.so"))
3037 ("bamtools" ,bamtools)
3038 ("protobuf" ,protobuf)
3040 (home-page "http://bio.math.berkeley.edu/eXpress")
3041 (synopsis "Streaming quantification for high-throughput genomic sequencing")
3043 "eXpress is a streaming tool for quantifying the abundances of a set of
3044 target sequences from sampled subsequences. Example applications include
3045 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
3046 analysis (from RNA-Seq), transcription factor binding quantification in
3047 ChIP-Seq, and analysis of metagenomic data.")
3048 (license license:artistic2.0)))
3050 (define-public express-beta-diversity
3052 (name "express-beta-diversity")
3057 (url "https://github.com/dparks1134/ExpressBetaDiversity.git")
3058 (commit (string-append "v" version))))
3059 (file-name (git-file-name name version))
3062 "0s0yzg5c21349rh7x4w9266jsvnp7j1hp9cf8sk32hz8nvrj745x"))))
3063 (build-system gnu-build-system)
3066 (modify-phases %standard-phases
3068 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
3070 (lambda _ (invoke "../bin/ExpressBetaDiversity" "-u") #t))
3072 (lambda* (#:key outputs #:allow-other-keys)
3073 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3074 (install-file "../scripts/convertToEBD.py" bin)
3075 (install-file "../bin/ExpressBetaDiversity" bin)
3078 `(("python" ,python-2)))
3079 (home-page "https://github.com/dparks1134/ExpressBetaDiversity")
3080 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
3082 "Express Beta Diversity (EBD) calculates ecological beta diversity
3083 (dissimilarity) measures between biological communities. EBD implements a
3084 variety of diversity measures including those that make use of phylogenetic
3085 similarity of community members.")
3086 (license license:gpl3+)))
3088 (define-public fasttree
3095 "http://www.microbesonline.org/fasttree/FastTree-"
3099 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
3100 (build-system gnu-build-system)
3102 `(#:tests? #f ; no "check" target
3104 (modify-phases %standard-phases
3108 (lambda* (#:key source #:allow-other-keys)
3111 "-finline-functions"
3122 "-finline-functions"
3131 (lambda* (#:key outputs #:allow-other-keys)
3132 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3133 (install-file "FastTree" bin)
3134 (install-file "FastTreeMP" bin)
3136 (home-page "http://www.microbesonline.org/fasttree")
3137 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
3139 "FastTree can handle alignments with up to a million of sequences in a
3140 reasonable amount of time and memory. For large alignments, FastTree is
3141 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
3142 (license license:gpl2+)))
3144 (define-public fastx-toolkit
3146 (name "fastx-toolkit")
3152 "https://github.com/agordon/fastx_toolkit/releases/download/"
3153 version "/fastx_toolkit-" version ".tar.bz2"))
3156 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
3157 (build-system gnu-build-system)
3159 `(("libgtextutils" ,libgtextutils)))
3161 `(("gcc" ,gcc-6) ;; doesn't build with later versions
3162 ("pkg-config" ,pkg-config)))
3163 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
3164 (synopsis "Tools for FASTA/FASTQ file preprocessing")
3166 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
3167 FASTA/FASTQ files preprocessing.
3169 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
3170 containing multiple short-reads sequences. The main processing of such
3171 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
3172 is sometimes more productive to preprocess the files before mapping the
3173 sequences to the genome---manipulating the sequences to produce better mapping
3174 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
3175 (license license:agpl3+)))
3177 (define-public flexbar
3184 (url "https://github.com/seqan/flexbar.git")
3185 (commit (string-append "v" version))))
3186 (file-name (git-file-name name version))
3189 "1pq9sxvdnldl14libk234m72dqhwgzs3acgl943wchwdqlcsi5r2"))))
3190 (build-system cmake-build-system)
3193 (modify-phases %standard-phases
3194 (add-after 'unpack 'do-not-tune-to-CPU
3196 (substitute* "src/CMakeLists.txt"
3197 ((" -march=native") ""))
3200 (lambda* (#:key outputs #:allow-other-keys)
3201 (setenv "PATH" (string-append (getcwd) ":" (getenv "PATH")))
3202 (with-directory-excursion "../source/test"
3203 (invoke "bash" "flexbar_test.sh"))
3206 (lambda* (#:key outputs #:allow-other-keys)
3207 (let* ((out (string-append (assoc-ref outputs "out")))
3208 (bin (string-append out "/bin/")))
3209 (install-file "flexbar" bin))
3215 `(("pkg-config" ,pkg-config)
3217 (home-page "https://github.com/seqan/flexbar")
3218 (synopsis "Barcode and adapter removal tool for sequencing platforms")
3220 "Flexbar preprocesses high-throughput nucleotide sequencing data
3221 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
3222 Moreover, trimming and filtering features are provided. Flexbar increases
3223 read mapping rates and improves genome and transcriptome assemblies. It
3224 supports next-generation sequencing data in fasta/q and csfasta/q format from
3225 Illumina, Roche 454, and the SOLiD platform.")
3226 (license license:bsd-3)))
3228 (define-public fraggenescan
3230 (name "fraggenescan")
3236 (string-append "mirror://sourceforge/fraggenescan/"
3237 "FragGeneScan" version ".tar.gz"))
3239 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
3240 (build-system gnu-build-system)
3243 (modify-phases %standard-phases
3245 (add-before 'build 'patch-paths
3246 (lambda* (#:key outputs #:allow-other-keys)
3247 (let* ((out (string-append (assoc-ref outputs "out")))
3248 (share (string-append out "/share/fraggenescan/")))
3249 (substitute* "run_FragGeneScan.pl"
3251 (string-append "system(\"" (which "rm")))
3253 (string-append "system(\"" (which "mv")))
3254 (("\\\"awk") (string-append "\"" (which "awk")))
3255 ;; This script and other programs expect the training files
3256 ;; to be in the non-standard location bin/train/XXX. Change
3257 ;; this to be share/fraggenescan/train/XXX instead.
3258 (("^\\$train.file = \\$dir.*")
3259 (string-append "$train_file = \""
3261 "train/\".$FGS_train_file;")))
3262 (substitute* "run_hmm.c"
3263 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
3264 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
3268 (invoke "make" "clean")
3269 (invoke "make" "fgs")
3272 (lambda* (#:key outputs #:allow-other-keys)
3273 (let* ((out (string-append (assoc-ref outputs "out")))
3274 (bin (string-append out "/bin/"))
3275 (share (string-append out "/share/fraggenescan/train")))
3276 (install-file "run_FragGeneScan.pl" bin)
3277 (install-file "FragGeneScan" bin)
3278 (copy-recursively "train" share))
3281 (add-after 'install 'post-install-check
3282 ;; In lieu of 'make check', run one of the examples and check the
3283 ;; output files gets created.
3284 (lambda* (#:key outputs #:allow-other-keys)
3285 (let* ((out (string-append (assoc-ref outputs "out")))
3286 (bin (string-append out "/bin/"))
3287 (frag (string-append bin "run_FragGeneScan.pl")))
3288 ;; Test complete genome.
3290 "-genome=./example/NC_000913.fna"
3294 (unless (and (file-exists? "test2.faa")
3295 (file-exists? "test2.ffn")
3296 (file-exists? "test2.gff")
3297 (file-exists? "test2.out"))
3298 (error "Expected files do not exist."))
3299 ;; Test incomplete sequences.
3301 "-genome=./example/NC_000913-fgs.ffn"
3308 ("python" ,python-2))) ;not compatible with python 3.
3309 (home-page "https://sourceforge.net/projects/fraggenescan/")
3310 (synopsis "Finds potentially fragmented genes in short reads")
3312 "FragGeneScan is a program for predicting bacterial and archaeal genes in
3313 short and error-prone DNA sequencing reads. It can also be applied to predict
3314 genes in incomplete assemblies or complete genomes.")
3315 ;; GPL3+ according to private correspondense with the authors.
3316 (license license:gpl3+)))
3318 (define-public fxtract
3319 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
3327 (url "https://github.com/ctSkennerton/fxtract.git")
3329 (file-name (git-file-name name version))
3332 "0hab3gpwf4w9s87qlbswq6ws1qqybh4dcqk79q1ahyldzai5fgp5"))))
3333 (build-system gnu-build-system)
3335 `(#:make-flags (list
3336 (string-append "PREFIX=" (assoc-ref %outputs "out"))
3338 #:test-target "fxtract_test"
3340 (modify-phases %standard-phases
3342 (add-before 'build 'copy-util
3343 (lambda* (#:key inputs #:allow-other-keys)
3345 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
3347 ;; Do not use make install as this requires additional dependencies.
3349 (lambda* (#:key outputs #:allow-other-keys)
3350 (let* ((out (assoc-ref outputs "out"))
3351 (bin (string-append out"/bin")))
3352 (install-file "fxtract" bin)
3358 ;; ctskennerton-util is licensed under GPL2.
3359 `(("ctskennerton-util"
3363 (url "https://github.com/ctSkennerton/util.git")
3364 (commit util-commit)))
3365 (file-name (string-append
3366 "ctstennerton-util-" util-commit "-checkout"))
3369 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
3370 (home-page "https://github.com/ctSkennerton/fxtract")
3371 (synopsis "Extract sequences from FASTA and FASTQ files")
3373 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
3374 or FASTQ) file given a subsequence. It uses a simple substring search for
3375 basic tasks but can change to using POSIX regular expressions, PCRE, hash
3376 lookups or multi-pattern searching as required. By default fxtract looks in
3377 the sequence of each record but can also be told to look in the header,
3378 comment or quality sections.")
3379 ;; 'util' requires SSE instructions.
3380 (supported-systems '("x86_64-linux"))
3381 (license license:expat))))
3383 (define-public gemma
3390 (url "https://github.com/xiangzhou/GEMMA.git")
3391 (commit (string-append "v" version))))
3392 (file-name (git-file-name name version))
3395 "1s3ncnbn45r2hh1cvrqky1kbqq6546biypr4f5mkw1kqlrgyh0yg"))))
3398 ("gfortran" ,gfortran "lib")
3401 ("openblas" ,openblas)
3403 (build-system gnu-build-system)
3406 '(,@(match (%current-system)
3408 '("FORCE_DYNAMIC=1"))
3410 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
3412 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
3414 (modify-phases %standard-phases
3416 (add-after 'unpack 'find-eigen
3417 (lambda* (#:key inputs #:allow-other-keys)
3418 ;; Ensure that Eigen headers can be found
3419 (setenv "CPLUS_INCLUDE_PATH"
3420 (string-append (assoc-ref inputs "eigen")
3423 (add-before 'build 'bin-mkdir
3428 (lambda* (#:key outputs #:allow-other-keys)
3429 (let ((out (assoc-ref outputs "out")))
3430 (install-file "bin/gemma"
3434 #:tests? #f)) ; no tests included yet
3435 (home-page "https://github.com/xiangzhou/GEMMA")
3436 (synopsis "Tool for genome-wide efficient mixed model association")
3438 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
3439 standard linear mixed model resolver with application in genome-wide
3440 association studies (GWAS).")
3441 (license license:gpl3)))
3450 (url "https://github.com/nboley/grit.git")
3452 (file-name (git-file-name name version))
3455 "1l5v8vfvfbrpmgnrvbrbv40d0arhxcnmxgv2f1mlcqfa3q6bkqm9"))))
3456 (build-system python-build-system)
3458 `(#:python ,python-2
3460 (modify-phases %standard-phases
3461 (add-after 'unpack 'generate-from-cython-sources
3462 (lambda* (#:key inputs outputs #:allow-other-keys)
3463 ;; Delete these C files to force fresh generation from pyx sources.
3464 (delete-file "grit/sparsify_support_fns.c")
3465 (delete-file "grit/call_peaks_support_fns.c")
3466 (substitute* "setup.py"
3467 (("Cython.Setup") "Cython.Build"))
3470 `(("python-scipy" ,python2-scipy)
3471 ("python-numpy" ,python2-numpy)
3472 ("python-pysam" ,python2-pysam)
3473 ("python-networkx" ,python2-networkx)))
3475 `(("python-cython" ,python2-cython)))
3476 ;; The canonical <http://grit-bio.org> home page times out as of 2020-01-21.
3477 (home-page "https://github.com/nboley/grit")
3478 (synopsis "Tool for integrative analysis of RNA-seq type assays")
3480 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
3481 full length transcript models. When none of these data sources are available,
3482 GRIT can be run by providing a candidate set of TES or TSS sites. In
3483 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
3484 also be run in quantification mode, where it uses a provided GTF file and just
3485 estimates transcript expression.")
3486 (license license:gpl3+)))
3488 (define-public hisat
3495 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
3496 version "-beta-source.zip"))
3499 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
3500 (build-system gnu-build-system)
3502 `(#:tests? #f ;no check target
3503 #:make-flags '("allall"
3504 ;; Disable unsupported `popcnt' instructions on
3505 ;; architectures other than x86_64
3506 ,@(if (string-prefix? "x86_64"
3507 (or (%current-target-system)
3510 '("POPCNT_CAPABILITY=0")))
3512 (modify-phases %standard-phases
3513 (add-after 'unpack 'patch-sources
3515 ;; XXX Cannot use snippet because zip files are not supported
3516 (substitute* "Makefile"
3517 (("^CC = .*$") "CC = gcc")
3518 (("^CPP = .*$") "CPP = g++")
3519 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
3520 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
3521 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
3522 (substitute* '("hisat-build" "hisat-inspect")
3523 (("/usr/bin/env") (which "env")))
3526 (lambda* (#:key outputs #:allow-other-keys)
3527 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
3528 (for-each (lambda (file)
3529 (install-file file bin))
3532 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
3534 (delete 'configure))))
3536 `(("unzip" ,unzip)))
3541 ;; Non-portable SSE instructions are used so building fails on platforms
3542 ;; other than x86_64.
3543 (supported-systems '("x86_64-linux"))
3544 (home-page "https://ccb.jhu.edu/software/hisat/index.shtml")
3545 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
3547 "HISAT is a fast and sensitive spliced alignment program for mapping
3548 RNA-seq reads. In addition to one global FM index that represents a whole
3549 genome, HISAT uses a large set of small FM indexes that collectively cover the
3550 whole genome. These small indexes (called local indexes) combined with
3551 several alignment strategies enable effective alignment of RNA-seq reads, in
3552 particular, reads spanning multiple exons.")
3553 (license license:gpl3+)))
3555 (define-public hisat2
3562 (uri (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
3563 "/downloads/hisat2-" version "-source.zip"))
3566 "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"))))
3567 (build-system gnu-build-system)
3569 `(#:tests? #f ; no check target
3570 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
3571 #:modules ((guix build gnu-build-system)
3575 (modify-phases %standard-phases
3576 (add-after 'unpack 'make-deterministic
3578 (substitute* "Makefile"
3583 (lambda* (#:key outputs #:allow-other-keys)
3584 (let* ((out (assoc-ref outputs "out"))
3585 (bin (string-append out "/bin/"))
3586 (doc (string-append out "/share/doc/hisat2/")))
3588 (cut install-file <> bin)
3590 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
3592 (install-file "doc/manual.inc.html" doc))
3595 `(("unzip" ,unzip) ; needed for archive from ftp
3597 ("pandoc" ,ghc-pandoc))) ; for documentation
3598 (home-page "https://ccb.jhu.edu/software/hisat2/index.shtml")
3599 (synopsis "Graph-based alignment of genomic sequencing reads")
3600 (description "HISAT2 is a fast and sensitive alignment program for mapping
3601 next-generation sequencing reads (both DNA and RNA) to a population of human
3602 genomes (as well as to a single reference genome). In addition to using one
3603 global @dfn{graph FM} (GFM) index that represents a population of human
3604 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
3605 the whole genome. These small indexes, combined with several alignment
3606 strategies, enable rapid and accurate alignment of sequencing reads. This new
3607 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
3608 ;; HISAT2 contains files from Bowtie2, which is released under
3609 ;; GPLv2 or later. The HISAT2 source files are released under
3611 (license license:gpl3+)))
3613 (define-public hmmer
3621 "http://eddylab.org/software/hmmer/hmmer-" version ".tar.gz"))
3624 "171bivy6xhgjsz5nv53n81pc3frnwz29ylblawk2bv46szwjjqd5"))))
3625 (build-system gnu-build-system)
3626 (native-inputs `(("perl" ,perl)))
3627 (home-page "http://hmmer.org/")
3628 (synopsis "Biosequence analysis using profile hidden Markov models")
3630 "HMMER is used for searching sequence databases for homologs of protein
3631 sequences, and for making protein sequence alignments. It implements methods
3632 using probabilistic models called profile hidden Markov models (profile
3634 ;; hmmer uses non-portable SSE intrinsics so building fails on other
3636 (supported-systems '("x86_64-linux" "i686-linux"))
3637 (license license:bsd-3)))
3639 (define-public htseq
3645 (uri (pypi-uri "HTSeq" version))
3648 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
3649 (build-system python-build-system)
3651 `(("python-cython" ,python-cython)))
3652 ;; Numpy needs to be propagated when htseq is used as a Python library.
3654 `(("python-numpy" ,python-numpy)))
3656 `(("python-pysam" ,python-pysam)
3657 ("python-matplotlib" ,python-matplotlib)))
3658 (home-page "https://htseq.readthedocs.io/")
3659 (synopsis "Analysing high-throughput sequencing data with Python")
3661 "HTSeq is a Python package that provides infrastructure to process data
3662 from high-throughput sequencing assays.")
3663 (license license:gpl3+)))
3665 (define-public python2-htseq
3666 (package-with-python2 htseq))
3668 (define-public java-htsjdk
3670 (name "java-htsjdk")
3671 (version "2.3.0") ; last version without build dependency on gradle
3675 (url "https://github.com/samtools/htsjdk.git")
3677 (file-name (git-file-name name version))
3680 "1b178ixcabanm834ydjl3jiakpyxdmki32hqfv2abrzn3rcwa28i"))
3681 (modules '((guix build utils)))
3683 ;; Delete pre-built binaries
3685 (delete-file-recursively "lib")
3688 (build-system ant-build-system)
3690 `(#:tests? #f ; test require Internet access
3693 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3694 "/share/java/htsjdk/"))
3695 #:build-target "all"
3697 (modify-phases %standard-phases
3698 ;; The build phase also installs the jars
3699 (delete 'install))))
3701 `(("java-ngs" ,java-ngs)
3702 ("java-snappy-1" ,java-snappy-1)
3703 ("java-commons-compress" ,java-commons-compress)
3704 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3705 ("java-commons-jexl-2" ,java-commons-jexl-2)
3706 ("java-xz" ,java-xz)))
3708 `(("java-testng" ,java-testng)))
3709 (home-page "http://samtools.github.io/htsjdk/")
3710 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3712 "HTSJDK is an implementation of a unified Java library for accessing
3713 common file formats, such as SAM and VCF, used for high-throughput
3714 sequencing (HTS) data. There are also an number of useful utilities for
3715 manipulating HTS data.")
3716 (license license:expat)))
3718 (define-public java-htsjdk-latest
3720 (name "java-htsjdk")
3725 (url "https://github.com/samtools/htsjdk.git")
3727 (file-name (string-append name "-" version "-checkout"))
3730 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
3731 (build-system ant-build-system)
3733 `(#:tests? #f ; test require Scala
3735 #:jar-name "htsjdk.jar"
3737 (modify-phases %standard-phases
3738 (add-after 'unpack 'remove-useless-build.xml
3739 (lambda _ (delete-file "build.xml") #t))
3740 ;; The tests require the scalatest package.
3741 (add-after 'unpack 'remove-tests
3742 (lambda _ (delete-file-recursively "src/test") #t)))))
3744 `(("java-ngs" ,java-ngs)
3745 ("java-snappy-1" ,java-snappy-1)
3746 ("java-commons-compress" ,java-commons-compress)
3747 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3748 ("java-commons-jexl-2" ,java-commons-jexl-2)
3749 ("java-xz" ,java-xz)))
3751 `(("java-junit" ,java-junit)))
3752 (home-page "http://samtools.github.io/htsjdk/")
3753 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3755 "HTSJDK is an implementation of a unified Java library for accessing
3756 common file formats, such as SAM and VCF, used for high-throughput
3757 sequencing (HTS) data. There are also an number of useful utilities for
3758 manipulating HTS data.")
3759 (license license:expat)))
3761 ;; This is needed for picard 2.10.3
3762 (define-public java-htsjdk-2.10.1
3763 (package (inherit java-htsjdk-latest)
3764 (name "java-htsjdk")
3769 (url "https://github.com/samtools/htsjdk.git")
3771 (file-name (string-append name "-" version "-checkout"))
3774 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
3775 (build-system ant-build-system)
3777 `(#:tests? #f ; tests require Scala
3779 #:jar-name "htsjdk.jar"
3781 (modify-phases %standard-phases
3782 (add-after 'unpack 'remove-useless-build.xml
3783 (lambda _ (delete-file "build.xml") #t))
3784 ;; The tests require the scalatest package.
3785 (add-after 'unpack 'remove-tests
3786 (lambda _ (delete-file-recursively "src/test") #t)))))))
3788 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3789 ;; recent version of java-htsjdk, which depends on gradle.
3790 (define-public java-picard
3792 (name "java-picard")
3797 (url "https://github.com/broadinstitute/picard.git")
3799 (file-name (string-append "java-picard-" version "-checkout"))
3802 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3803 (modules '((guix build utils)))
3806 ;; Delete pre-built binaries.
3807 (delete-file-recursively "lib")
3809 (substitute* "build.xml"
3810 ;; Remove build-time dependency on git.
3811 (("failifexecutionfails=\"true\"")
3812 "failifexecutionfails=\"false\"")
3814 (("depends=\"compile-htsjdk, ")
3816 (("depends=\"compile-htsjdk-tests, ")
3818 ;; Build picard-lib.jar before building picard.jar
3819 (("name=\"picard-jar\" depends=\"" line)
3820 (string-append line "picard-lib-jar, ")))
3822 (build-system ant-build-system)
3824 `(#:build-target "picard-jar"
3825 #:test-target "test"
3826 ;; Tests require jacoco:coverage.
3829 (list (string-append "-Dhtsjdk_lib_dir="
3830 (assoc-ref %build-inputs "java-htsjdk")
3831 "/share/java/htsjdk/")
3832 "-Dhtsjdk-classes=dist/tmp"
3833 (string-append "-Dhtsjdk-version="
3834 ,(package-version java-htsjdk)))
3837 (modify-phases %standard-phases
3838 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3839 (delete 'generate-jar-indices)
3840 (add-after 'unpack 'use-our-htsjdk
3841 (lambda* (#:key inputs #:allow-other-keys)
3842 (substitute* "build.xml"
3843 (("\\$\\{htsjdk\\}/lib")
3844 (string-append (assoc-ref inputs "java-htsjdk")
3845 "/share/java/htsjdk/")))
3847 (add-after 'unpack 'make-test-target-independent
3848 (lambda* (#:key inputs #:allow-other-keys)
3849 (substitute* "build.xml"
3850 (("name=\"test\" depends=\"compile, ")
3851 "name=\"test\" depends=\""))
3853 (replace 'install (install-jars "dist")))))
3855 `(("java-htsjdk" ,java-htsjdk)
3856 ("java-guava" ,java-guava)))
3858 `(("java-testng" ,java-testng)))
3859 (home-page "http://broadinstitute.github.io/picard/")
3860 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3861 (description "Picard is a set of Java command line tools for manipulating
3862 high-throughput sequencing (HTS) data and formats. Picard is implemented
3863 using the HTSJDK Java library to support accessing file formats that are
3864 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3866 (license license:expat)))
3868 ;; This is needed for dropseq-tools
3869 (define-public java-picard-2.10.3
3871 (name "java-picard")
3876 (url "https://github.com/broadinstitute/picard.git")
3878 (file-name (string-append "java-picard-" version "-checkout"))
3881 "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi"))))
3882 (build-system ant-build-system)
3884 `(#:jar-name "picard.jar"
3885 ;; Tests require jacoco:coverage.
3888 #:main-class "picard.cmdline.PicardCommandLine"
3889 #:modules ((guix build ant-build-system)
3891 (guix build java-utils)
3896 (modify-phases %standard-phases
3897 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3898 (delete 'generate-jar-indices)
3899 (add-after 'unpack 'remove-useless-build.xml
3900 (lambda _ (delete-file "build.xml") #t))
3901 ;; This is necessary to ensure that htsjdk is found when using
3902 ;; picard.jar as an executable.
3903 (add-before 'build 'edit-classpath-in-manifest
3904 (lambda* (#:key inputs #:allow-other-keys)
3905 (chmod "build.xml" #o664)
3906 (call-with-output-file "build.xml.new"
3910 (with-input-from-file "build.xml"
3911 (lambda _ (xml->sxml #:trim-whitespace? #t)))
3912 `((target . ,(lambda (tag . kids)
3913 (let ((name ((sxpath '(name *text*))
3915 ;; FIXME: We're breaking the line
3916 ;; early with a dummy path to
3917 ;; ensure that the store reference
3918 ;; isn't broken apart and can still
3919 ;; be found by the reference
3924 ~a/share/java/htsjdk.jar${line.separator}${line.separator}"
3925 ;; maximum line length is 70
3926 (string-tabulate (const #\b) 57)
3927 (assoc-ref inputs "java-htsjdk"))))
3928 (if (member "manifest" name)
3931 (@ (file "${manifest.file}")
3932 (match "\\r\\n\\r\\n")
3933 (replace "${line.separator}")))
3936 (file "${manifest.file}")
3939 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
3940 (*text* . ,(lambda (_ txt) txt))))
3942 (rename-file "build.xml.new" "build.xml")
3945 `(("java-htsjdk" ,java-htsjdk-2.10.1)))
3947 `(("java-testng" ,java-testng)
3948 ("java-guava" ,java-guava)))
3949 (home-page "http://broadinstitute.github.io/picard/")
3950 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3951 (description "Picard is a set of Java command line tools for manipulating
3952 high-throughput sequencing (HTS) data and formats. Picard is implemented
3953 using the HTSJDK Java library to support accessing file formats that are
3954 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3956 (license license:expat)))
3958 ;; This is the last version of Picard to provide net.sf.samtools
3959 (define-public java-picard-1.113
3960 (package (inherit java-picard)
3961 (name "java-picard")
3966 (url "https://github.com/broadinstitute/picard.git")
3968 (file-name (string-append "java-picard-" version "-checkout"))
3971 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
3972 (modules '((guix build utils)))
3975 ;; Delete pre-built binaries.
3976 (delete-file-recursively "lib")
3979 (build-system ant-build-system)
3981 `(#:build-target "picard-jar"
3982 #:test-target "test"
3983 ;; FIXME: the class path at test time is wrong.
3984 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
3985 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
3988 ;; This is only used for tests.
3990 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
3992 (modify-phases %standard-phases
3993 ;; FIXME: This phase fails.
3994 (delete 'generate-jar-indices)
3995 ;; Do not use bundled ant bzip2.
3996 (add-after 'unpack 'use-ant-bzip
3997 (lambda* (#:key inputs #:allow-other-keys)
3998 (substitute* "build.xml"
3999 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
4000 (string-append (assoc-ref inputs "ant")
4003 (add-after 'unpack 'make-test-target-independent
4004 (lambda* (#:key inputs #:allow-other-keys)
4005 (substitute* "build.xml"
4006 (("name=\"test\" depends=\"compile, ")
4007 "name=\"test\" depends=\"compile-tests, ")
4008 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
4009 "name=\"compile\" depends=\"compile-src\""))
4011 (add-after 'unpack 'fix-deflater-path
4012 (lambda* (#:key outputs #:allow-other-keys)
4013 (substitute* "src/java/net/sf/samtools/Defaults.java"
4014 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
4015 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
4016 (assoc-ref outputs "out")
4017 "/lib/jni/libIntelDeflater.so"
4020 ;; Build the deflater library, because we've previously deleted the
4021 ;; pre-built one. This can only be built with access to the JDK
4023 (add-after 'build 'build-jni
4024 (lambda* (#:key inputs #:allow-other-keys)
4027 (invoke "tar" "--strip-components=1" "-C" "jdk-src"
4028 "-xf" (assoc-ref inputs "jdk-src"))
4029 (invoke "javah" "-jni"
4030 "-classpath" "classes"
4032 "net.sf.samtools.util.zip.IntelDeflater")
4033 (with-directory-excursion "src/c/inteldeflater"
4034 (invoke "gcc" "-I../../../lib" "-I."
4035 (string-append "-I" (assoc-ref inputs "jdk")
4037 "-I../../../jdk-src/src/share/native/common/"
4038 "-I../../../jdk-src/src/solaris/native/common/"
4039 "-c" "-O3" "-fPIC" "IntelDeflater.c")
4040 (invoke "gcc" "-shared"
4041 "-o" "../../../lib/jni/libIntelDeflater.so"
4042 "IntelDeflater.o" "-lz" "-lstdc++"))
4044 ;; We can only build everything else after building the JNI library.
4045 (add-after 'build-jni 'build-rest
4046 (lambda* (#:key make-flags #:allow-other-keys)
4047 (apply invoke `("ant" "all" ,@make-flags))
4049 (add-before 'build 'set-JAVA6_HOME
4051 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
4053 (replace 'install (install-jars "dist"))
4054 (add-after 'install 'install-jni-lib
4055 (lambda* (#:key outputs #:allow-other-keys)
4056 (let ((jni (string-append (assoc-ref outputs "out")
4059 (install-file "lib/jni/libIntelDeflater.so" jni)
4062 `(("java-snappy-1" ,java-snappy-1)
4063 ("java-commons-jexl-2" ,java-commons-jexl-2)
4064 ("java-cofoja" ,java-cofoja)
4065 ("ant" ,ant) ; for bzip2 support at runtime
4068 `(("ant-apache-bcel" ,ant-apache-bcel)
4069 ("ant-junit" ,ant-junit)
4070 ("java-testng" ,java-testng)
4071 ("java-commons-bcel" ,java-commons-bcel)
4072 ("java-jcommander" ,java-jcommander)
4073 ("jdk" ,icedtea-8 "jdk")
4074 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
4076 (define-public fastqc
4083 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
4084 "projects/fastqc/fastqc_v"
4085 version "_source.zip"))
4088 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
4089 (build-system ant-build-system)
4091 `(#:tests? #f ; there are no tests
4092 #:build-target "build"
4094 (modify-phases %standard-phases
4095 (add-after 'unpack 'fix-dependencies
4096 (lambda* (#:key inputs #:allow-other-keys)
4097 (substitute* "build.xml"
4099 (string-append (assoc-ref inputs "java-jbzip2")
4100 "/share/java/jbzip2.jar"))
4102 (string-append (assoc-ref inputs "java-picard-1.113")
4103 "/share/java/sam-1.112.jar"))
4105 (string-append (assoc-ref inputs "java-cisd-jhdf5")
4106 "/share/java/sis-jhdf5.jar")))
4108 ;; There is no installation target
4110 (lambda* (#:key inputs outputs #:allow-other-keys)
4111 (let* ((out (assoc-ref outputs "out"))
4112 (bin (string-append out "/bin"))
4113 (share (string-append out "/share/fastqc/"))
4114 (exe (string-append share "/fastqc")))
4115 (for-each mkdir-p (list bin share))
4116 (copy-recursively "bin" share)
4118 (("my \\$java_bin = 'java';")
4119 (string-append "my $java_bin = '"
4120 (assoc-ref inputs "java")
4123 (symlink exe (string-append bin "/fastqc"))
4127 ("perl" ,perl) ; needed for the wrapper script
4128 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
4129 ("java-picard-1.113" ,java-picard-1.113)
4130 ("java-jbzip2" ,java-jbzip2)))
4132 `(("unzip" ,unzip)))
4133 (home-page "https://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
4134 (synopsis "Quality control tool for high throughput sequence data")
4136 "FastQC aims to provide a simple way to do some quality control
4137 checks on raw sequence data coming from high throughput sequencing
4138 pipelines. It provides a modular set of analyses which you can use to
4139 give a quick impression of whether your data has any problems of which
4140 you should be aware before doing any further analysis.
4142 The main functions of FastQC are:
4145 @item Import of data from BAM, SAM or FastQ files (any variant);
4146 @item Providing a quick overview to tell you in which areas there may
4148 @item Summary graphs and tables to quickly assess your data;
4149 @item Export of results to an HTML based permanent report;
4150 @item Offline operation to allow automated generation of reports
4151 without running the interactive application.
4153 (license license:gpl3+)))
4155 (define-public fastp
4163 (url "https://github.com/OpenGene/fastp.git")
4164 (commit (string-append "v" version))))
4165 (file-name (git-file-name name version))
4168 "1r6ms5zbf5rps4rgp4z73nczadl00b5rqylw8f684isfz27dp0xh"))))
4169 (build-system gnu-build-system)
4171 `(#:tests? #f ; there are none
4173 (list (string-append "BINDIR=" (assoc-ref %outputs "out") "/bin"))
4175 (modify-phases %standard-phases
4177 (add-before 'install 'create-target-dir
4178 (lambda* (#:key outputs #:allow-other-keys)
4179 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4183 (home-page "https://github.com/OpenGene/fastp/")
4184 (synopsis "All-in-one FastQ preprocessor")
4186 "Fastp is a tool designed to provide fast all-in-one preprocessing for
4187 FastQ files. This tool has multi-threading support to afford high
4189 (license license:expat)))
4191 (define-public htslib
4198 "https://github.com/samtools/htslib/releases/download/"
4199 version "/htslib-" version ".tar.bz2"))
4202 "16ljv43sc3fxmv63w7b2ff8m1s7h89xhazwmbm1bicz8axq8fjz0"))))
4203 (build-system gnu-build-system)
4206 ("openssl" ,openssl)))
4207 ;; This is referred to in the pkg-config file as a required library.
4212 (home-page "https://www.htslib.org")
4213 (synopsis "C library for reading/writing high-throughput sequencing data")
4215 "HTSlib is a C library for reading/writing high-throughput sequencing
4216 data. It also provides the @command{bgzip}, @command{htsfile}, and
4217 @command{tabix} utilities.")
4218 ;; Files under cram/ are released under the modified BSD license;
4219 ;; the rest is released under the Expat license
4220 (license (list license:expat license:bsd-3))))
4222 ;; This package should be removed once no packages rely upon it.
4230 "https://github.com/samtools/htslib/releases/download/"
4231 version "/htslib-" version ".tar.bz2"))
4234 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
4243 (url "https://github.com/nboley/idr.git")
4245 (file-name (git-file-name name version))
4248 "04j876h6z444v2q79drxx283d3k5snd72kj895wbalnl42206x9g"))
4249 ;; Delete generated C code.
4251 '(begin (delete-file "idr/inv_cdf.c") #t))))
4252 (build-system python-build-system)
4253 ;; There is only one test ("test_inv_cdf.py") and it tests features that
4254 ;; are no longer part of this package. It also asserts False, which
4255 ;; causes the tests to always fail.
4256 (arguments `(#:tests? #f))
4258 `(("python-scipy" ,python-scipy)
4259 ("python-sympy" ,python-sympy)
4260 ("python-numpy" ,python-numpy)
4261 ("python-matplotlib" ,python-matplotlib)))
4263 `(("python-cython" ,python-cython)))
4264 (home-page "https://github.com/nboley/idr")
4265 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
4267 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
4268 to measure the reproducibility of findings identified from replicate
4269 experiments and provide highly stable thresholds based on reproducibility.")
4270 (license license:gpl2+)))
4272 (define-public jellyfish
4278 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
4279 "releases/download/v" version
4280 "/jellyfish-" version ".tar.gz"))
4283 "1k4pc3fvv6w1km2yph4m5sd78fbxp21d6xyzgmy0gjihzc6mb249"))))
4284 (build-system gnu-build-system)
4285 (outputs '("out" ;for library
4286 "ruby" ;for Ruby bindings
4287 "python")) ;for Python bindings
4290 (list (string-append "--enable-ruby-binding="
4291 (assoc-ref %outputs "ruby"))
4292 (string-append "--enable-python-binding="
4293 (assoc-ref %outputs "python")))
4295 (modify-phases %standard-phases
4296 (add-before 'check 'set-SHELL-variable
4298 ;; generator_manager.hpp either uses /bin/sh or $SHELL
4300 (setenv "SHELL" (which "bash"))
4306 ("python" ,python-2)
4307 ("pkg-config" ,pkg-config)))
4309 `(("htslib" ,htslib)))
4310 (synopsis "Tool for fast counting of k-mers in DNA")
4312 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
4313 DNA. A k-mer is a substring of length k, and counting the occurrences of all
4314 such substrings is a central step in many analyses of DNA sequence. Jellyfish
4315 is a command-line program that reads FASTA and multi-FASTA files containing
4316 DNA sequences. It outputs its k-mer counts in a binary format, which can be
4317 translated into a human-readable text format using the @code{jellyfish dump}
4318 command, or queried for specific k-mers with @code{jellyfish query}.")
4319 (home-page "http://www.genome.umd.edu/jellyfish.html")
4320 ;; JELLYFISH seems to be 64-bit only.
4321 (supported-systems '("x86_64-linux" "aarch64-linux" "mips64el-linux"))
4322 ;; The combined work is published under the GPLv3 or later. Individual
4323 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
4324 (license (list license:gpl3+ license:expat))))
4326 (define-public khmer
4334 (url "https://github.com/dib-lab/khmer.git")
4335 (commit (string-append "v" version))))
4336 (file-name (git-file-name name version))
4339 "01l4jczglkl7yfhgvzx8j0df7k54bk1r8sli9ll16i1mis0d8f37"))
4340 (modules '((guix build utils)))
4343 ;; Delete bundled libraries. We do not replace the bundled seqan
4344 ;; as it is a modified subset of the old version 1.4.1.
4346 ;; We do not replace the bundled MurmurHash as the canonical
4347 ;; repository for this code 'SMHasher' is unsuitable for providing
4349 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
4350 (delete-file-recursively "third-party/zlib")
4351 (delete-file-recursively "third-party/bzip2")
4352 (delete-file-recursively "third-party/seqan")
4353 (substitute* "setup.cfg"
4354 (("# libraries = z,bz2")
4355 "libraries = z,bz2")
4356 (("include:third-party/zlib:third-party/bzip2")
4359 (build-system python-build-system)
4362 (modify-phases %standard-phases
4363 (add-after 'unpack 'set-cc
4364 (lambda _ (setenv "CC" "gcc") #t))
4366 (add-before 'reset-gzip-timestamps 'make-files-writable
4367 (lambda* (#:key outputs #:allow-other-keys)
4368 ;; Make sure .gz files are writable so that the
4369 ;; 'reset-gzip-timestamps' phase can do its work.
4370 (let ((out (assoc-ref outputs "out")))
4371 (for-each make-file-writable
4372 (find-files out "\\.gz$"))
4375 `(("python-cython" ,python-cython)
4376 ("python-pytest" ,python-pytest)
4377 ("python-pytest-runner" ,python-pytest-runner)))
4382 ("python-screed" ,python-screed)
4383 ("python-bz2file" ,python-bz2file)))
4384 (home-page "https://khmer.readthedocs.org/")
4385 (synopsis "K-mer counting, filtering and graph traversal library")
4386 (description "The khmer software is a set of command-line tools for
4387 working with DNA shotgun sequencing data from genomes, transcriptomes,
4388 metagenomes and single cells. Khmer can make de novo assemblies faster, and
4389 sometimes better. Khmer can also identify and fix problems with shotgun
4391 ;; When building on i686, armhf and mips64el, we get the following error:
4392 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
4393 (supported-systems '("x86_64-linux" "aarch64-linux"))
4394 (license license:bsd-3)))
4396 (define-public kaiju
4403 (url "https://github.com/bioinformatics-centre/kaiju")
4404 (commit (string-append "v" version))))
4405 (file-name (git-file-name name version))
4408 "119pzi0ddzv9mjg4wwa6han0cwr3k3ssn7kirvsjfcq05mi5ka0x"))))
4409 (build-system gnu-build-system)
4411 `(#:tests? #f ; There are no tests.
4413 (modify-phases %standard-phases
4415 (add-before 'build 'move-to-src-dir
4416 (lambda _ (chdir "src") #t))
4418 (lambda* (#:key inputs outputs #:allow-other-keys)
4419 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
4422 (copy-recursively "bin" bin))
4427 (home-page "http://kaiju.binf.ku.dk/")
4428 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
4429 (description "Kaiju is a program for sensitive taxonomic classification
4430 of high-throughput sequencing reads from metagenomic whole genome sequencing
4432 (license license:gpl3+)))
4439 ;; The PyPi tarball does not contain tests.
4442 (url "https://github.com/taoliu/MACS.git")
4443 (commit (string-append "v" version))))
4444 (file-name (git-file-name name version))
4447 "1c5gxr0mk6hkd4vclf0k00wvyvzw2vrmk52c85338p7aqjwg6n15"))))
4448 (build-system python-build-system)
4451 (modify-phases %standard-phases
4453 (add-after 'install 'check
4454 (lambda* (#:key inputs outputs #:allow-other-keys)
4455 (add-installed-pythonpath inputs outputs)
4456 (invoke "pytest" "-v"))))))
4458 `(("python-numpy" ,python-numpy)))
4460 `(("python-pytest" ,python-pytest)))
4461 (home-page "https://github.com/taoliu/MACS/")
4462 (synopsis "Model based analysis for ChIP-Seq data")
4464 "MACS is an implementation of a ChIP-Seq analysis algorithm for
4465 identifying transcript factor binding sites named Model-based Analysis of
4466 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
4467 the significance of enriched ChIP regions and it improves the spatial
4468 resolution of binding sites through combining the information of both
4469 sequencing tag position and orientation.")
4470 (license license:bsd-3)))
4472 (define-public mafft
4479 "https://mafft.cbrc.jp/alignment/software/mafft-" version
4480 "-without-extensions-src.tgz"))
4481 (file-name (string-append name "-" version ".tgz"))
4484 "0bacjkxfg944p5khhyh5rd4y7wkjc9qk4v2jjj442sqlq0f8ar7b"))))
4485 (build-system gnu-build-system)
4487 `(#:tests? #f ; no automated tests, though there are tests in the read me
4488 #:make-flags (let ((out (assoc-ref %outputs "out")))
4489 (list (string-append "PREFIX=" out)
4490 (string-append "BINDIR="
4491 (string-append out "/bin"))))
4493 (modify-phases %standard-phases
4494 (add-after 'unpack 'enter-dir
4495 (lambda _ (chdir "core") #t))
4496 (add-after 'enter-dir 'patch-makefile
4498 ;; on advice from the MAFFT authors, there is no need to
4499 ;; distribute mafft-profile, mafft-distance, or
4500 ;; mafft-homologs.rb as they are too "specialised".
4501 (substitute* "Makefile"
4502 ;; remove mafft-homologs.rb from SCRIPTS
4503 (("^SCRIPTS = mafft mafft-homologs.rb")
4505 ;; remove mafft-homologs from MANPAGES
4506 (("^MANPAGES = mafft.1 mafft-homologs.1")
4507 "MANPAGES = mafft.1")
4508 ;; remove mafft-distance from PROGS
4509 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
4510 "PROGS = dvtditr dndfast7 dndblast sextet5")
4511 ;; remove mafft-profile from PROGS
4512 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
4513 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
4514 (("^rm -f mafft-profile mafft-profile.exe") "#")
4515 (("^rm -f mafft-distance mafft-distance.exe") ")#")
4516 ;; do not install MAN pages in libexec folder
4517 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
4518 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
4520 (add-after 'enter-dir 'patch-paths
4521 (lambda* (#:key inputs #:allow-other-keys)
4522 (substitute* '("pairash.c"
4524 (("perl") (which "perl"))
4525 (("([\"`| ])awk" _ prefix)
4526 (string-append prefix (which "awk")))
4527 (("grep") (which "grep")))
4530 (add-after 'install 'wrap-programs
4531 (lambda* (#:key outputs #:allow-other-keys)
4532 (let* ((out (assoc-ref outputs "out"))
4533 (bin (string-append out "/bin"))
4534 (path (string-append
4535 (assoc-ref %build-inputs "coreutils") "/bin:")))
4536 (for-each (lambda (file)
4538 `("PATH" ":" prefix (,path))))
4546 ("coreutils" ,coreutils)))
4547 (home-page "http://mafft.cbrc.jp/alignment/software/")
4548 (synopsis "Multiple sequence alignment program")
4550 "MAFFT offers a range of multiple alignment methods for nucleotide and
4551 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
4552 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
4554 (license (license:non-copyleft
4555 "http://mafft.cbrc.jp/alignment/software/license.txt"
4556 "BSD-3 with different formatting"))))
4565 (url "https://github.com/marbl/mash.git")
4566 (commit (string-append "v" version))))
4567 (file-name (git-file-name name version))
4570 "049hwcc059p2fd9vwndn63laifvvsi0wmv84i6y1fr79k15dxwy6"))
4571 (modules '((guix build utils)))
4574 ;; Delete bundled kseq.
4575 ;; TODO: Also delete bundled murmurhash and open bloom filter.
4576 (delete-file "src/mash/kseq.h")
4578 (build-system gnu-build-system)
4580 `(#:tests? #f ; No tests.
4583 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
4584 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
4585 #:make-flags (list "CC=gcc")
4587 (modify-phases %standard-phases
4588 (add-after 'unpack 'fix-includes
4590 (substitute* '("src/mash/Sketch.cpp"
4591 "src/mash/CommandFind.cpp"
4592 "src/mash/CommandScreen.cpp")
4593 (("^#include \"kseq\\.h\"")
4594 "#include \"htslib/kseq.h\""))
4596 (add-after 'fix-includes 'use-c++14
4598 ;; capnproto 0.7 requires c++14 to build
4599 (substitute* "configure.ac"
4600 (("c\\+\\+11") "c++14"))
4601 (substitute* "Makefile.in"
4602 (("c\\+\\+11") "c++14"))
4605 `(("autoconf" ,autoconf)
4606 ;; Capnproto and htslib are statically embedded in the final
4607 ;; application. Therefore we also list their licenses, below.
4608 ("capnproto" ,capnproto)
4609 ("htslib" ,htslib)))
4613 (supported-systems '("x86_64-linux"))
4614 (home-page "https://mash.readthedocs.io")
4615 (synopsis "Fast genome and metagenome distance estimation using MinHash")
4616 (description "Mash is a fast sequence distance estimator that uses the
4617 MinHash algorithm and is designed to work with genomes and metagenomes in the
4618 form of assemblies or reads.")
4619 (license (list license:bsd-3 ; Mash
4620 license:expat ; HTSlib and capnproto
4621 license:public-domain ; MurmurHash 3
4622 license:cpl1.0)))) ; Open Bloom Filter
4624 (define-public metabat
4632 (url "https://bitbucket.org/berkeleylab/metabat.git")
4633 (commit (string-append "v" version))))
4634 (file-name (git-file-name name version))
4637 "0hyg2smw1nz69mfvjpk45xyyychmda92c80a0cv7baji84ri4iyn"))
4638 (patches (search-patches "metabat-fix-compilation.patch"))))
4639 (build-system scons-build-system)
4641 `(#:scons ,scons-python2
4643 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
4644 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
4645 #:tests? #f ;; Tests are run during the build phase.
4647 (modify-phases %standard-phases
4648 (add-after 'unpack 'fix-includes
4650 (substitute* "src/BamUtils.h"
4651 (("^#include \"bam/bam\\.h\"")
4652 "#include \"samtools/bam.h\"")
4653 (("^#include \"bam/sam\\.h\"")
4654 "#include \"samtools/sam.h\""))
4655 (substitute* "src/KseqReader.h"
4656 (("^#include \"bam/kseq\\.h\"")
4657 "#include \"htslib/kseq.h\""))
4659 (add-after 'unpack 'fix-scons
4660 (lambda* (#:key inputs #:allow-other-keys)
4661 (substitute* "SConstruct"
4662 (("^htslib_dir += 'samtools'")
4663 (string-append "htslib_dir = '"
4664 (assoc-ref inputs "htslib")
4666 (("^samtools_dir = 'samtools'")
4667 (string-append "samtools_dir = '"
4668 (assoc-ref inputs "samtools")
4670 (("^findStaticOrShared\\('bam', hts_lib")
4671 (string-append "findStaticOrShared('bam', '"
4672 (assoc-ref inputs "samtools")
4674 ;; Do not distribute README.
4675 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
4680 ("samtools" ,samtools)
4683 (home-page "https://bitbucket.org/berkeleylab/metabat")
4685 "Reconstruction of single genomes from complex microbial communities")
4687 "Grouping large genomic fragments assembled from shotgun metagenomic
4688 sequences to deconvolute complex microbial communities, or metagenome binning,
4689 enables the study of individual organisms and their interactions. MetaBAT is
4690 an automated metagenome binning software, which integrates empirical
4691 probabilistic distances of genome abundance and tetranucleotide frequency.")
4692 ;; The source code contains inline assembly.
4693 (supported-systems '("x86_64-linux" "i686-linux"))
4694 (license (license:non-copyleft "file://license.txt"
4695 "See license.txt in the distribution."))))
4697 (define-public minced
4704 (url "https://github.com/ctSkennerton/minced.git")
4706 (file-name (git-file-name name version))
4709 "1f5h9him0gd355cnx7p6pnxpknhckd4g0v62mg8zyhfbx9as25fv"))))
4710 (build-system gnu-build-system)
4712 `(#:test-target "test"
4714 (modify-phases %standard-phases
4716 (add-before 'check 'fix-test
4718 ;; Fix test for latest version.
4719 (substitute* "t/Aquifex_aeolicus_VF5.expected"
4720 (("minced:0.1.6") "minced:0.2.0"))
4722 (replace 'install ; No install target.
4723 (lambda* (#:key inputs outputs #:allow-other-keys)
4724 (let* ((out (assoc-ref outputs "out"))
4725 (bin (string-append out "/bin"))
4726 (wrapper (string-append bin "/minced")))
4727 ;; Minced comes with a wrapper script that tries to figure out where
4728 ;; it is located before running the JAR. Since these paths are known
4729 ;; to us, we build our own wrapper to avoid coreutils dependency.
4730 (install-file "minced.jar" bin)
4731 (with-output-to-file wrapper
4735 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
4736 (assoc-ref inputs "jre") "/bin/java -jar "
4737 bin "/minced.jar \"$@\"\n"))))
4738 (chmod wrapper #o555))
4741 `(("jdk" ,icedtea "jdk")))
4744 ("jre" ,icedtea "out")))
4745 (home-page "https://github.com/ctSkennerton/minced")
4746 (synopsis "Mining CRISPRs in Environmental Datasets")
4748 "MinCED is a program to find Clustered Regularly Interspaced Short
4749 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
4750 unassembled metagenomic reads, but is mainly designed for full genomes and
4751 assembled metagenomic sequence.")
4752 (license license:gpl3+)))
4760 (uri (pypi-uri "misopy" version))
4763 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
4764 (modules '((guix build utils)))
4766 (substitute* "setup.py"
4767 ;; Use setuptools, or else the executables are not
4769 (("distutils.core") "setuptools")
4770 ;; Use "gcc" instead of "cc" for compilation.
4772 "cc.set_executables(
4776 linker_so='gcc -shared'); defines"))
4778 (build-system python-build-system)
4780 `(#:python ,python-2 ; only Python 2 is supported
4781 #:tests? #f)) ; no "test" target
4783 `(("samtools" ,samtools)
4784 ("python-numpy" ,python2-numpy)
4785 ("python-pysam" ,python2-pysam)
4786 ("python-scipy" ,python2-scipy)
4787 ("python-matplotlib" ,python2-matplotlib)))
4789 `(("python-mock" ,python2-mock) ; for tests
4790 ("python-pytz" ,python2-pytz))) ; for tests
4791 (home-page "https://www.genes.mit.edu/burgelab/miso/index.html")
4792 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
4794 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
4795 the expression level of alternatively spliced genes from RNA-Seq data, and
4796 identifies differentially regulated isoforms or exons across samples. By
4797 modeling the generative process by which reads are produced from isoforms in
4798 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
4799 that a read originated from a particular isoform.")
4800 (license license:gpl2)))
4802 (define-public muscle
4805 (version "3.8.1551")
4807 (method url-fetch/tarbomb)
4809 "http://www.drive5.com/muscle/muscle_src_"
4813 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
4814 (build-system gnu-build-system)
4816 `(#:make-flags (list "LDLIBS = -lm")
4818 (modify-phases %standard-phases
4821 ;; There are no tests, so just test if it runs.
4822 (lambda _ (invoke "./muscle" "-version") #t))
4824 (lambda* (#:key outputs #:allow-other-keys)
4825 (let* ((out (assoc-ref outputs "out"))
4826 (bin (string-append out "/bin")))
4827 (install-file "muscle" bin)
4829 (home-page "http://www.drive5.com/muscle")
4830 (synopsis "Multiple sequence alignment program")
4832 "MUSCLE aims to be a fast and accurate multiple sequence alignment
4833 program for nucleotide and protein sequences.")
4834 ;; License information found in 'muscle -h' and usage.cpp.
4835 (license license:public-domain)))
4837 (define-public newick-utils
4838 ;; There are no recent releases so we package from git.
4839 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
4841 (name "newick-utils")
4842 (version (string-append "1.6-1." (string-take commit 8)))
4846 (url "https://github.com/tjunier/newick_utils.git")
4848 (file-name (string-append name "-" version "-checkout"))
4851 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4852 (build-system gnu-build-system)
4854 ;; XXX: TODO: Enable Lua and Guile bindings.
4855 ;; https://github.com/tjunier/newick_utils/issues/13
4856 `(("libxml2" ,libxml2)
4860 `(("autoconf" ,autoconf)
4861 ("automake" ,automake)
4862 ("libtool" ,libtool)))
4863 (synopsis "Programs for working with newick format phylogenetic trees")
4865 "Newick-utils is a suite of utilities for processing phylogenetic trees
4866 in Newick format. Functions include re-rooting, extracting subtrees,
4867 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4868 (home-page "https://github.com/tjunier/newick_utils")
4869 (license license:bsd-3))))
4878 "https://github.com/wwood/OrfM/releases/download/v"
4879 version "/orfm-" version ".tar.gz"))
4882 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4883 (build-system gnu-build-system)
4884 (inputs `(("zlib" ,zlib)))
4886 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4887 ("ruby-rspec" ,ruby-rspec)
4889 (synopsis "Simple and not slow open reading frame (ORF) caller")
4891 "An ORF caller finds stretches of DNA that, when translated, are not
4892 interrupted by stop codons. OrfM finds and prints these ORFs.")
4893 (home-page "https://github.com/wwood/OrfM")
4894 (license license:lgpl3+)))
4896 (define-public python2-pbcore
4898 (name "python2-pbcore")
4902 (uri (pypi-uri "pbcore" version))
4905 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4906 (build-system python-build-system)
4908 `(#:python ,python-2 ;pbcore < 2.0 requires Python 2.7
4909 #:phases (modify-phases %standard-phases
4910 (add-after 'unpack 'remove-sphinx-dependency
4912 ;; Sphinx is only required for documentation tests, which
4913 ;; we do not run; furthermore it depends on python2-sphinx
4914 ;; which is no longer maintained.
4915 (substitute* "requirements-dev.txt"
4919 `(("python-cython" ,python2-cython)
4920 ("python-numpy" ,python2-numpy)
4921 ("python-pysam" ,python2-pysam)
4922 ("python-h5py" ,python2-h5py)))
4924 `(("python-nose" ,python2-nose)
4925 ("python-pyxb" ,python2-pyxb)))
4926 (home-page "https://pacificbiosciences.github.io/pbcore/")
4927 (synopsis "Library for reading and writing PacBio data files")
4929 "The pbcore package provides Python APIs for interacting with PacBio data
4930 files and writing bioinformatics applications.")
4931 (license license:bsd-3)))
4933 (define-public python2-warpedlmm
4935 (name "python2-warpedlmm")
4940 (uri (pypi-uri "WarpedLMM" version ".zip"))
4943 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4944 (build-system python-build-system)
4946 `(#:python ,python-2 ; requires Python 2.7
4947 #:tests? #f ; test data are not included
4949 (modify-phases %standard-phases
4950 (add-after 'unpack 'use-weave
4952 (substitute* "warpedlmm/util/linalg.py"
4953 (("from scipy import linalg, weave")
4954 "from scipy import linalg\nimport weave"))
4957 `(("python-scipy" ,python2-scipy)
4958 ("python-numpy" ,python2-numpy)
4959 ("python-matplotlib" ,python2-matplotlib)
4960 ("python-fastlmm" ,python2-fastlmm)
4961 ("python-pandas" ,python2-pandas)
4962 ("python-pysnptools" ,python2-pysnptools)
4963 ("python-weave" ,python2-weave)))
4965 `(("python-mock" ,python2-mock)
4966 ("python-nose" ,python2-nose)
4968 (home-page "https://github.com/PMBio/warpedLMM")
4969 (synopsis "Implementation of warped linear mixed models")
4971 "WarpedLMM is a Python implementation of the warped linear mixed model,
4972 which automatically learns an optimal warping function (or transformation) for
4973 the phenotype as it models the data.")
4974 (license license:asl2.0)))
4976 (define-public pbtranscript-tofu
4977 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
4979 (name "pbtranscript-tofu")
4980 (version (string-append "2.2.3." (string-take commit 7)))
4984 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
4986 (file-name (string-append name "-" version "-checkout"))
4989 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
4990 (modules '((guix build utils)))
4993 ;; remove bundled Cython sources
4994 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
4996 (build-system python-build-system)
4998 `(#:python ,python-2
4999 ;; FIXME: Tests fail with "No such file or directory:
5000 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
5003 (modify-phases %standard-phases
5004 (add-after 'unpack 'enter-directory
5006 (chdir "pbtranscript-tofu/pbtranscript/")
5008 ;; With setuptools version 18.0 and later this setup.py hack causes
5009 ;; a build error, so we disable it.
5010 (add-after 'enter-directory 'patch-setuppy
5012 (substitute* "setup.py"
5013 (("if 'setuptools.extension' in sys.modules:")
5017 `(("python-numpy" ,python2-numpy)
5018 ("python-bx-python" ,python2-bx-python)
5019 ("python-networkx" ,python2-networkx)
5020 ("python-scipy" ,python2-scipy)
5021 ("python-pbcore" ,python2-pbcore)
5022 ("python-h5py" ,python2-h5py)))
5024 `(("python-cython" ,python2-cython)
5025 ("python-nose" ,python2-nose)))
5026 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
5027 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
5029 "pbtranscript-tofu contains scripts to analyze transcriptome data
5030 generated using the PacBio Iso-Seq protocol.")
5031 (license license:bsd-3))))
5033 (define-public prank
5040 "http://wasabiapp.org/download/prank/prank.source."
5044 "0nc8g9c5rkdxcir46s0in9ci1sxwzbjibxrvkksf22ybnplvagk2"))))
5045 (build-system gnu-build-system)
5048 (modify-phases %standard-phases
5049 (add-after 'unpack 'enter-src-dir
5053 (add-after 'unpack 'remove-m64-flag
5054 ;; Prank will build with the correct 'bit-ness' without this flag
5055 ;; and this allows building on 32-bit machines.
5056 (lambda _ (substitute* "src/Makefile"
5061 (lambda* (#:key outputs #:allow-other-keys)
5062 (let* ((out (assoc-ref outputs "out"))
5063 (bin (string-append out "/bin"))
5064 (man (string-append out "/share/man/man1"))
5065 (path (string-append
5066 (assoc-ref %build-inputs "mafft") "/bin:"
5067 (assoc-ref %build-inputs "exonerate") "/bin:"
5068 (assoc-ref %build-inputs "bppsuite") "/bin")))
5069 (install-file "prank" bin)
5070 (wrap-program (string-append bin "/prank")
5071 `("PATH" ":" prefix (,path)))
5072 (install-file "prank.1" man))
5076 ("exonerate" ,exonerate)
5077 ("bppsuite" ,bppsuite)))
5078 (home-page "http://wasabiapp.org/software/prank/")
5079 (synopsis "Probabilistic multiple sequence alignment program")
5081 "PRANK is a probabilistic multiple sequence alignment program for DNA,
5082 codon and amino-acid sequences. It is based on a novel algorithm that treats
5083 insertions correctly and avoids over-estimation of the number of deletion
5084 events. In addition, PRANK borrows ideas from maximum likelihood methods used
5085 in phylogenetics and correctly takes into account the evolutionary distances
5086 between sequences. Lastly, PRANK allows for defining a potential structure
5087 for sequences to be aligned and then, simultaneously with the alignment,
5088 predicts the locations of structural units in the sequences.")
5089 (license license:gpl2+)))
5091 (define-public proteinortho
5093 (name "proteinortho")
5098 (url "https://gitlab.com/paulklemm_PHD/proteinortho.git")
5099 (commit (string-append "v" version))))
5100 (file-name (git-file-name name version))
5103 "0pmy617zy2z2w6hjqxjhf3rzikf5n3mpia80ysq8233vfr7wrzff"))
5104 (modules '((guix build utils)))
5107 ;; remove pre-built scripts
5108 (delete-file-recursively "src/BUILD/")
5110 (build-system gnu-build-system)
5112 `(#:test-target "test"
5113 #:make-flags '("CC=gcc")
5115 (modify-phases %standard-phases
5117 ;; There is no configure script, so we modify the Makefile directly.
5118 (lambda* (#:key outputs #:allow-other-keys)
5119 (substitute* "Makefile"
5122 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
5124 (add-before 'install 'make-install-directory
5125 ;; The install directory is not created during 'make install'.
5126 (lambda* (#:key outputs #:allow-other-keys)
5127 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
5129 (add-after 'install 'wrap-programs
5130 (lambda* (#:key inputs outputs #:allow-other-keys)
5131 (let ((path (getenv "PATH"))
5132 (out (assoc-ref outputs "out")))
5133 (for-each (lambda (script)
5134 (wrap-script script `("PATH" ":" prefix (,path))))
5135 (cons (string-append out "/bin/proteinortho")
5136 (find-files out "\\.(pl|py)$"))))
5139 `(("guile" ,guile-3.0) ; for wrap-script
5140 ("diamond" ,diamond)
5142 ("python" ,python-wrapper)
5145 ("openblas" ,openblas)))
5147 `(("which" ,which)))
5148 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
5149 (synopsis "Detect orthologous genes across species")
5151 "Proteinortho is a tool to detect orthologous genes across different
5152 species. For doing so, it compares similarities of given gene sequences and
5153 clusters them to find significant groups. The algorithm was designed to handle
5154 large-scale data and can be applied to hundreds of species at once.")
5155 (license license:gpl3+)))
5157 (define-public pyicoteo
5165 (url "https://bitbucket.org/regulatorygenomicsupf/pyicoteo.git")
5166 (commit (string-append "v" version))))
5167 (file-name (git-file-name name version))
5170 "0hz5g8d25lbjy1wpscr490l0lmyvaix893hhax4fxnh1h9w34w8p"))))
5171 (build-system python-build-system)
5173 `(#:python ,python-2 ; does not work with Python 3
5174 #:tests? #f)) ; there are no tests
5176 `(("python2-matplotlib" ,python2-matplotlib)))
5177 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
5178 (synopsis "Analyze high-throughput genetic sequencing data")
5180 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
5181 sequencing data. It works with genomic coordinates. There are currently six
5182 different command-line tools:
5185 @item pyicoregion: for generating exploratory regions automatically;
5186 @item pyicoenrich: for differential enrichment between two conditions;
5187 @item pyicoclip: for calling CLIP-Seq peaks without a control;
5188 @item pyicos: for genomic coordinates manipulation;
5189 @item pyicoller: for peak calling on punctuated ChIP-Seq;
5190 @item pyicount: to count how many reads from N experiment files overlap in a
5192 @item pyicotrocol: to combine operations from pyicoteo.
5194 (license license:gpl3+)))
5196 (define-public prodigal
5199 ;; Check for a new home page when updating this package:
5200 ;; https://github.com/hyattpd/Prodigal/issues/36#issuecomment-536617588
5205 (url "https://github.com/hyattpd/Prodigal.git")
5206 (commit (string-append "v" version))))
5207 (file-name (git-file-name name version))
5210 "1fs1hqk83qjbjhrvhw6ni75zakx5ki1ayy3v6wwkn3xvahc9hi5s"))))
5211 (build-system gnu-build-system)
5213 `(#:tests? #f ; no check target
5214 #:make-flags (list (string-append "INSTALLDIR="
5215 (assoc-ref %outputs "out")
5218 (modify-phases %standard-phases
5219 (delete 'configure))))
5220 (home-page "https://github.com/hyattpd/Prodigal")
5221 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
5223 "Prodigal runs smoothly on finished genomes, draft genomes, and
5224 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
5225 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
5226 partial genes, and identifies translation initiation sites.")
5227 (license license:gpl3+)))
5229 (define-public roary
5237 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
5241 "0qxrds9wx7cfhlkihrp6697kx0flhhxymap9fwan0b3rbdhcnmff"))))
5242 (build-system perl-build-system)
5245 (modify-phases %standard-phases
5250 ;; The tests are not run by default, so we run each test file
5252 (setenv "PATH" (string-append (getcwd) "/bin" ":"
5254 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
5255 (getenv "PERL5LIB")))
5256 (for-each (lambda (file)
5257 (display file)(display "\n")
5258 (invoke "perl" file))
5259 (find-files "t" ".*\\.t$"))
5262 ;; There is no 'install' target in the Makefile.
5263 (lambda* (#:key outputs #:allow-other-keys)
5264 (let* ((out (assoc-ref outputs "out"))
5265 (bin (string-append out "/bin"))
5266 (perl (string-append out "/lib/perl5/site_perl"))
5267 (roary-plots "contrib/roary_plots"))
5270 (copy-recursively "bin" bin)
5271 (copy-recursively "lib" perl)
5273 (add-after 'install 'wrap-programs
5274 (lambda* (#:key inputs outputs #:allow-other-keys)
5275 (let* ((out (assoc-ref outputs "out"))
5276 (perl5lib (getenv "PERL5LIB"))
5277 (path (getenv "PATH")))
5278 (for-each (lambda (prog)
5279 (let ((binary (string-append out "/" prog)))
5280 (wrap-program binary
5281 `("PERL5LIB" ":" prefix
5282 (,(string-append perl5lib ":" out
5283 "/lib/perl5/site_perl"))))
5284 (wrap-program binary
5286 (,(string-append path ":" out "/bin"))))))
5287 (find-files "bin" ".*[^R]$"))
5289 (string-append out "/bin/roary-create_pan_genome_plots.R"))
5290 (r-site-lib (getenv "R_LIBS_SITE"))
5292 (string-append (assoc-ref inputs "coreutils") "/bin")))
5294 `("R_LIBS_SITE" ":" prefix
5295 (,(string-append r-site-lib ":" out "/site-library/"))))
5298 (,(string-append coreutils-path ":" out "/bin"))))))
5301 `(("perl-env-path" ,perl-env-path)
5302 ("perl-test-files" ,perl-test-files)
5303 ("perl-test-most" ,perl-test-most)
5304 ("perl-test-output" ,perl-test-output)))
5306 `(("perl-array-utils" ,perl-array-utils)
5307 ("bioperl" ,bioperl-minimal)
5308 ("perl-digest-md5-file" ,perl-digest-md5-file)
5309 ("perl-exception-class" ,perl-exception-class)
5310 ("perl-file-find-rule" ,perl-file-find-rule)
5311 ("perl-file-grep" ,perl-file-grep)
5312 ("perl-file-slurper" ,perl-file-slurper)
5313 ("perl-file-which" ,perl-file-which)
5314 ("perl-graph" ,perl-graph)
5315 ("perl-graph-readwrite" ,perl-graph-readwrite)
5316 ("perl-log-log4perl" ,perl-log-log4perl)
5317 ("perl-moose" ,perl-moose)
5318 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
5319 ("perl-text-csv" ,perl-text-csv)
5320 ("bedtools" ,bedtools)
5324 ("parallel" ,parallel)
5327 ("fasttree" ,fasttree)
5331 ("r-minimal" ,r-minimal)
5332 ("r-ggplot2" ,r-ggplot2)
5333 ("coreutils" ,coreutils)))
5334 (home-page "https://sanger-pathogens.github.io/Roary/")
5335 (synopsis "High speed stand-alone pan genome pipeline")
5337 "Roary is a high speed stand alone pan genome pipeline, which takes
5338 annotated assemblies in GFF3 format (produced by the Prokka program) and
5339 calculates the pan genome. Using a standard desktop PC, it can analyse
5340 datasets with thousands of samples, without compromising the quality of the
5341 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
5342 single processor. Roary is not intended for metagenomics or for comparing
5343 extremely diverse sets of genomes.")
5344 (license license:gpl3)))
5346 (define-public raxml
5354 (url "https://github.com/stamatak/standard-RAxML.git")
5355 (commit (string-append "v" version))))
5356 (file-name (git-file-name name version))
5359 "1jqjzhch0rips0vp04prvb8vmc20c5pdmsqn8knadcf91yy859fh"))))
5360 (build-system gnu-build-system)
5362 `(#:tests? #f ; There are no tests.
5363 ;; Use 'standard' Makefile rather than SSE or AVX ones.
5364 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
5366 (modify-phases %standard-phases
5369 (lambda* (#:key outputs #:allow-other-keys)
5370 (let* ((out (assoc-ref outputs "out"))
5371 (bin (string-append out "/bin"))
5372 (executable "raxmlHPC-HYBRID"))
5373 (install-file executable bin)
5374 (symlink (string-append bin "/" executable) "raxml"))
5377 `(("openmpi" ,openmpi)))
5378 (home-page "https://cme.h-its.org/exelixis/web/software/raxml/index.html")
5379 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
5381 "RAxML is a tool for phylogenetic analysis and post-analysis of large
5383 ;; The source includes x86 specific code
5384 (supported-systems '("x86_64-linux" "i686-linux"))
5385 (license license:gpl2+)))
5395 (url "https://github.com/deweylab/RSEM.git")
5396 (commit (string-append "v" version))))
5398 (base32 "1jlq11d1p8qp64w75yj8cnbbd1a93viq10pzsbwal7vdn8fg13j1"))
5399 (file-name (git-file-name name version))
5400 (modules '((guix build utils)))
5403 ;; remove bundled copy of boost and samtools
5404 (delete-file-recursively "boost")
5405 (delete-file-recursively "samtools-1.3")
5407 (build-system gnu-build-system)
5409 `(#:tests? #f ;no "check" target
5411 (list (string-append "BOOST="
5412 (assoc-ref %build-inputs "boost")
5414 (string-append "SAMHEADERS="
5415 (assoc-ref %build-inputs "htslib")
5416 "/include/htslib/sam.h")
5417 (string-append "SAMLIBS="
5418 (assoc-ref %build-inputs "htslib")
5421 (modify-phases %standard-phases
5422 ;; No "configure" script.
5423 ;; Do not build bundled samtools library.
5426 (substitute* "Makefile"
5427 (("^all : \\$\\(PROGRAMS\\).*") "all: $(PROGRAMS)\n")
5428 (("^\\$\\(SAMLIBS\\).*") ""))
5431 (lambda* (#:key outputs #:allow-other-keys)
5432 (let* ((out (string-append (assoc-ref outputs "out")))
5433 (bin (string-append out "/bin/"))
5434 (perl (string-append out "/lib/perl5/site_perl")))
5437 (for-each (lambda (file)
5438 (install-file file bin))
5439 (find-files "." "rsem-.*"))
5440 (install-file "rsem_perl_utils.pm" perl))
5442 (add-after 'install 'wrap-program
5443 (lambda* (#:key outputs #:allow-other-keys)
5444 (let ((out (assoc-ref outputs "out")))
5445 (for-each (lambda (prog)
5446 (wrap-program (string-append out "/bin/" prog)
5447 `("PERL5LIB" ":" prefix
5448 (,(string-append out "/lib/perl5/site_perl")))))
5449 '("rsem-calculate-expression"
5451 "rsem-generate-data-matrix"
5452 "rsem-generate-ngvector"
5453 "rsem-plot-transcript-wiggles"
5454 "rsem-prepare-reference"
5456 "rsem-run-prsem-testing-procedure")))
5460 ("r-minimal" ,r-minimal)
5462 ("htslib" ,htslib-1.3)
5464 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
5465 (synopsis "Estimate gene expression levels from RNA-Seq data")
5467 "RSEM is a software package for estimating gene and isoform expression
5468 levels from RNA-Seq data. The RSEM package provides a user-friendly
5469 interface, supports threads for parallel computation of the EM algorithm,
5470 single-end and paired-end read data, quality scores, variable-length reads and
5471 RSPD estimation. In addition, it provides posterior mean and 95% credibility
5472 interval estimates for expression levels. For visualization, it can generate
5473 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
5474 (license license:gpl3+)))
5476 (define-public rseqc
5484 (string-append "mirror://sourceforge/rseqc/"
5485 "RSeQC-" version ".tar.gz"))
5488 "0gbb9iyb7swiv5455fm5rg98r7l6qn27v564yllqjd574hncpx6m"))))
5489 (build-system python-build-system)
5491 `(("python-cython" ,python-cython)
5492 ("python-bx-python" ,python-bx-python)
5493 ("python-pybigwig" ,python-pybigwig)
5494 ("python-pysam" ,python-pysam)
5495 ("python-numpy" ,python-numpy)
5498 `(("python-nose" ,python-nose)))
5499 (home-page "http://rseqc.sourceforge.net/")
5500 (synopsis "RNA-seq quality control package")
5502 "RSeQC provides a number of modules that can comprehensively evaluate
5503 high throughput sequence data, especially RNA-seq data. Some basic modules
5504 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
5505 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
5506 distribution, coverage uniformity, strand specificity, etc.")
5507 (license license:gpl3+)))
5510 ;; There are no release tarballs. According to the installation
5511 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
5512 ;; stable release is identified by this changeset ID.
5513 (let ((changeset "2329130")
5517 (version (string-append "0-" revision "." changeset))
5521 (url "https://bitbucket.org/libsleipnir/sleipnir")
5522 (changeset changeset)))
5523 (file-name (string-append name "-" version "-checkout"))
5526 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
5527 (build-system gnu-build-system)
5529 `(#:modules ((srfi srfi-1)
5530 (guix build gnu-build-system)
5533 (let ((dirs '("SeekMiner"
5539 (modify-phases %standard-phases
5542 (substitute* "gen_tools_am"
5543 (("/usr/bin/env.*") (which "perl")))
5544 (invoke "bash" "gen_auto")
5546 (add-after 'build 'build-additional-tools
5547 (lambda* (#:key make-flags #:allow-other-keys)
5548 (for-each (lambda (dir)
5549 (with-directory-excursion (string-append "tools/" dir)
5550 (apply invoke "make" make-flags)))
5553 (add-after 'install 'install-additional-tools
5554 (lambda* (#:key make-flags #:allow-other-keys)
5555 (for-each (lambda (dir)
5556 (with-directory-excursion (string-append "tools/" dir)
5557 (apply invoke `("make" ,@make-flags "install"))))
5564 ("readline" ,readline)
5565 ("gengetopt" ,gengetopt)
5566 ("log4cpp" ,log4cpp)))
5568 `(("autoconf" ,autoconf)
5569 ("automake" ,automake)
5571 (home-page "http://seek.princeton.edu")
5572 (synopsis "Gene co-expression search engine")
5574 "SEEK is a computational gene co-expression search engine. SEEK provides
5575 biologists with a way to navigate the massive human expression compendium that
5576 now contains thousands of expression datasets. SEEK returns a robust ranking
5577 of co-expressed genes in the biological area of interest defined by the user's
5578 query genes. It also prioritizes thousands of expression datasets according
5579 to the user's query of interest.")
5580 (license license:cc-by3.0))))
5582 (define-public samtools
5590 (string-append "mirror://sourceforge/samtools/samtools/"
5591 version "/samtools-" version ".tar.bz2"))
5594 "10ilqbmm7ri8z431sn90lvbjwizd0hhkf9rcqw8j823hf26nhgq8"))
5595 (modules '((guix build utils)))
5597 ;; Delete bundled htslib.
5598 (delete-file-recursively "htslib-1.9")
5600 (build-system gnu-build-system)
5602 `(#:modules ((ice-9 ftw)
5604 (guix build gnu-build-system)
5606 #:configure-flags (list "--with-ncurses")
5608 (modify-phases %standard-phases
5609 (add-after 'unpack 'patch-tests
5611 (substitute* "test/test.pl"
5612 ;; The test script calls out to /bin/bash
5613 (("/bin/bash") (which "bash")))
5615 (add-after 'install 'install-library
5616 (lambda* (#:key outputs #:allow-other-keys)
5617 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
5618 (install-file "libbam.a" lib)
5620 (add-after 'install 'install-headers
5621 (lambda* (#:key outputs #:allow-other-keys)
5622 (let ((include (string-append (assoc-ref outputs "out")
5623 "/include/samtools/")))
5624 (for-each (lambda (file)
5625 (install-file file include))
5626 (scandir "." (lambda (name) (string-match "\\.h$" name))))
5628 (native-inputs `(("pkg-config" ,pkg-config)))
5630 `(("htslib" ,htslib)
5631 ("ncurses" ,ncurses)
5635 (home-page "http://samtools.sourceforge.net")
5636 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
5638 "Samtools implements various utilities for post-processing nucleotide
5639 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
5640 variant calling (in conjunction with bcftools), and a simple alignment
5642 (license license:expat)))
5644 (define-public samtools-0.1
5645 ;; This is the most recent version of the 0.1 line of samtools. The input
5646 ;; and output formats differ greatly from that used and produced by samtools
5647 ;; 1.x and is still used in many bioinformatics pipelines.
5648 (package (inherit samtools)
5654 (string-append "mirror://sourceforge/samtools/samtools/"
5655 version "/samtools-" version ".tar.bz2"))
5657 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
5659 `(#:tests? #f ;no "check" target
5661 (list "LIBCURSES=-lncurses")
5662 ,@(substitute-keyword-arguments (package-arguments samtools)
5664 `(modify-phases ,phases
5666 (lambda* (#:key outputs #:allow-other-keys)
5667 (let ((bin (string-append
5668 (assoc-ref outputs "out") "/bin")))
5670 (install-file "samtools" bin)
5672 (delete 'patch-tests)
5673 (delete 'configure))))))))
5675 (define-public mosaik
5676 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
5681 ;; There are no release tarballs nor tags.
5684 (url "https://github.com/wanpinglee/MOSAIK.git")
5686 (file-name (string-append name "-" version))
5689 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
5690 (build-system gnu-build-system)
5692 `(#:tests? #f ; no tests
5693 #:make-flags (list "CC=gcc")
5695 (modify-phases %standard-phases
5697 (lambda _ (chdir "src") #t))
5699 (lambda* (#:key outputs #:allow-other-keys)
5700 (let ((bin (string-append (assoc-ref outputs "out")
5703 (copy-recursively "../bin" bin)
5707 ("zlib:static" ,zlib "static")
5709 (supported-systems '("x86_64-linux"))
5710 (home-page "https://github.com/wanpinglee/MOSAIK")
5711 (synopsis "Map nucleotide sequence reads to reference genomes")
5713 "MOSAIK is a program for mapping second and third-generation sequencing
5714 reads to a reference genome. MOSAIK can align reads generated by all the
5715 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
5716 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
5717 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
5718 ;; code released into the public domain:
5719 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
5720 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
5721 (license (list license:gpl2+ license:public-domain)))))
5723 (define-public ngs-sdk
5730 (url "https://github.com/ncbi/ngs.git")
5732 (file-name (git-file-name name version))
5735 "1ix51c25hjn57w93qmwzw80xh2i34wx8j2hn7szh8p6w8i3az5qa"))))
5736 (build-system gnu-build-system)
5738 `(#:parallel-build? #f ; not supported
5739 #:tests? #f ; no "check" target
5741 (modify-phases %standard-phases
5743 (lambda* (#:key outputs #:allow-other-keys)
5744 (let ((out (assoc-ref outputs "out")))
5745 ;; Allow 'konfigure.perl' to find 'package.prl'.
5747 (string-append ".:" (getenv "PERL5LIB")))
5749 ;; The 'configure' script doesn't recognize things like
5750 ;; '--enable-fast-install'.
5751 (invoke "./configure"
5752 (string-append "--build-prefix=" (getcwd) "/build")
5753 (string-append "--prefix=" out))
5755 (add-after 'unpack 'enter-dir
5756 (lambda _ (chdir "ngs-sdk") #t)))))
5757 (native-inputs `(("perl" ,perl)))
5758 ;; According to the test
5759 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
5760 ;; in ngs-sdk/setup/konfigure.perl
5761 (supported-systems '("i686-linux" "x86_64-linux"))
5762 (home-page "https://github.com/ncbi/ngs")
5763 (synopsis "API for accessing Next Generation Sequencing data")
5765 "NGS is a domain-specific API for accessing reads, alignments and pileups
5766 produced from Next Generation Sequencing. The API itself is independent from
5767 any particular back-end implementation, and supports use of multiple back-ends
5769 (license license:public-domain)))
5771 (define-public java-ngs
5772 (package (inherit ngs-sdk)
5775 `(,@(substitute-keyword-arguments
5776 `(#:modules ((guix build gnu-build-system)
5780 ,@(package-arguments ngs-sdk))
5782 `(modify-phases ,phases
5783 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5785 `(("jdk" ,icedtea "jdk")
5786 ("ngs-sdk" ,ngs-sdk)))
5787 (synopsis "Java bindings for NGS SDK")))
5789 (define-public ncbi-vdb
5796 (url "https://github.com/ncbi/ncbi-vdb.git")
5798 (file-name (git-file-name name version))
5801 "0m8hlxscidsfqm9x9fyi62q6lpf1dv5115kgjjgnrkl49q9c27m6"))))
5802 (build-system gnu-build-system)
5804 `(#:parallel-build? #f ; not supported
5805 #:tests? #f ; no "check" target
5806 #:make-flags '("HAVE_HDF5=1")
5808 (modify-phases %standard-phases
5809 (add-after 'unpack 'make-files-writable
5810 (lambda _ (for-each make-file-writable (find-files "." ".*")) #t))
5811 (add-before 'configure 'set-perl-search-path
5813 ;; Work around "dotless @INC" build failure.
5815 (string-append (getcwd) "/setup:"
5816 (getenv "PERL5LIB")))
5818 ;; See https://github.com/ncbi/ncbi-vdb/issues/14
5819 (add-after 'unpack 'patch-krypto-flags
5821 (substitute* "libs/krypto/Makefile"
5822 (("-Wa,-march=generic64\\+aes") "")
5823 (("-Wa,-march=generic64\\+sse4") ""))
5826 (lambda* (#:key inputs outputs #:allow-other-keys)
5827 (let ((out (assoc-ref outputs "out")))
5828 ;; Override include path for libmagic
5829 (substitute* "setup/package.prl"
5830 (("name => 'magic', Include => '/usr/include'")
5831 (string-append "name=> 'magic', Include => '"
5832 (assoc-ref inputs "libmagic")
5835 ;; Install kdf5 library (needed by sra-tools)
5836 (substitute* "build/Makefile.install"
5837 (("LIBRARIES_TO_INSTALL =")
5838 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5840 (substitute* "build/Makefile.env"
5841 (("CFLAGS =" prefix)
5842 (string-append prefix "-msse2 ")))
5844 ;; Override search path for ngs-java
5845 (substitute* "setup/package.prl"
5846 (("/usr/local/ngs/ngs-java")
5847 (assoc-ref inputs "java-ngs")))
5849 ;; The 'configure' script doesn't recognize things like
5850 ;; '--enable-fast-install'.
5851 (invoke "./configure"
5852 (string-append "--build-prefix=" (getcwd) "/build")
5853 (string-append "--prefix=" (assoc-ref outputs "out"))
5854 (string-append "--debug")
5855 (string-append "--with-xml2-prefix="
5856 (assoc-ref inputs "libxml2"))
5857 (string-append "--with-ngs-sdk-prefix="
5858 (assoc-ref inputs "ngs-sdk"))
5859 (string-append "--with-hdf5-prefix="
5860 (assoc-ref inputs "hdf5")))
5862 (add-after 'install 'install-interfaces
5863 (lambda* (#:key outputs #:allow-other-keys)
5864 ;; Install interface libraries. On i686 the interface libraries
5865 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5866 ;; architecture name ("i386") instead of the target system prefix
5868 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5869 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5870 ,(system->linux-architecture
5871 (or (%current-target-system)
5874 (string-append (assoc-ref outputs "out")
5876 ;; Install interface headers
5877 (copy-recursively "interfaces"
5878 (string-append (assoc-ref outputs "out")
5881 ;; These files are needed by sra-tools.
5882 (add-after 'install 'install-configuration-files
5883 (lambda* (#:key outputs #:allow-other-keys)
5884 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5886 (install-file "libs/kfg/default.kfg" target)
5887 (install-file "libs/kfg/certs.kfg" target))
5890 `(("libxml2" ,libxml2)
5891 ("ngs-sdk" ,ngs-sdk)
5892 ("java-ngs" ,java-ngs)
5895 (native-inputs `(("perl" ,perl)))
5896 ;; NCBI-VDB requires SSE capability.
5897 (supported-systems '("i686-linux" "x86_64-linux"))
5898 (home-page "https://github.com/ncbi/ncbi-vdb")
5899 (synopsis "Database engine for genetic information")
5901 "The NCBI-VDB library implements a highly compressed columnar data
5902 warehousing engine that is most often used to store genetic information.
5903 Databases are stored in a portable image within the file system, and can be
5904 accessed/downloaded on demand across HTTP.")
5905 (license license:public-domain)))
5907 (define-public plink
5915 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5916 version "-src.zip"))
5918 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5919 (patches (search-patches "plink-1.07-unclobber-i.patch"
5920 "plink-endian-detection.patch"))))
5921 (build-system gnu-build-system)
5923 '(#:tests? #f ;no "check" target
5924 #:make-flags (list (string-append "LIB_LAPACK="
5925 (assoc-ref %build-inputs "lapack")
5926 "/lib/liblapack.so")
5929 ;; disable phoning home
5932 (modify-phases %standard-phases
5933 ;; no "configure" script
5936 (lambda* (#:key outputs #:allow-other-keys)
5937 (let ((bin (string-append (assoc-ref outputs "out")
5939 (install-file "plink" bin)
5943 ("lapack" ,lapack)))
5945 `(("unzip" ,unzip)))
5946 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5947 (synopsis "Whole genome association analysis toolset")
5949 "PLINK is a whole genome association analysis toolset, designed to
5950 perform a range of basic, large-scale analyses in a computationally efficient
5951 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5952 so there is no support for steps prior to this (e.g. study design and
5953 planning, generating genotype or CNV calls from raw data). Through
5954 integration with gPLINK and Haploview, there is some support for the
5955 subsequent visualization, annotation and storage of results.")
5956 ;; Code is released under GPLv2, except for fisher.h, which is under
5958 (license (list license:gpl2 license:lgpl2.1+))))
5960 (define-public plink-ng
5961 (package (inherit plink)
5968 (url "https://github.com/chrchang/plink-ng.git")
5969 (commit (string-append "v" version))))
5970 (file-name (git-file-name name version))
5972 (base32 "02npdwgkpfkdnhw819rhj5kw02a5k5m90b14zq9zzya4hyg929c0"))))
5973 (build-system gnu-build-system)
5975 '(#:tests? #f ;no "check" target
5976 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5977 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5979 "-f" "Makefile.std")
5981 (modify-phases %standard-phases
5982 (add-after 'unpack 'chdir
5983 (lambda _ (chdir "1.9") #t))
5984 (delete 'configure) ; no "configure" script
5986 (lambda* (#:key outputs #:allow-other-keys)
5987 (let ((bin (string-append (assoc-ref outputs "out")
5989 (install-file "plink" bin)
5994 ("openblas" ,openblas)))
5995 (home-page "https://www.cog-genomics.org/plink/")
5996 (license license:gpl3+)))
5998 (define-public smithlab-cpp
5999 (let ((revision "1")
6000 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
6002 (name "smithlab-cpp")
6003 (version (string-append "0." revision "." (string-take commit 7)))
6007 (url "https://github.com/smithlabcode/smithlab_cpp.git")
6009 (file-name (string-append name "-" version "-checkout"))
6012 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
6013 (build-system gnu-build-system)
6015 `(#:modules ((guix build gnu-build-system)
6018 #:tests? #f ;no "check" target
6020 (modify-phases %standard-phases
6021 (add-after 'unpack 'use-samtools-headers
6023 (substitute* '("SAM.cpp"
6025 (("sam.h") "samtools/sam.h"))
6028 (lambda* (#:key outputs #:allow-other-keys)
6029 (let* ((out (assoc-ref outputs "out"))
6030 (lib (string-append out "/lib"))
6031 (include (string-append out "/include/smithlab-cpp")))
6034 (for-each (cut install-file <> lib)
6035 (find-files "." "\\.o$"))
6036 (for-each (cut install-file <> include)
6037 (find-files "." "\\.hpp$")))
6039 (delete 'configure))))
6041 `(("samtools" ,samtools-0.1)
6043 (home-page "https://github.com/smithlabcode/smithlab_cpp")
6044 (synopsis "C++ helper library for functions used in Smith lab projects")
6046 "Smithlab CPP is a C++ library that includes functions used in many of
6047 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
6048 structures, classes for genomic regions, mapped sequencing reads, etc.")
6049 (license license:gpl3+))))
6051 (define-public preseq
6057 (uri (string-append "https://github.com/smithlabcode/preseq/"
6058 "releases/download/v" version
6059 "/preseq_v" version ".tar.bz2"))
6061 (base32 "149x9xmk1wy1gff85325yfzqc0qk4sgp1w6gbyj9cnji4x1dszbl"))
6062 (modules '((guix build utils)))
6064 ;; Remove bundled samtools.
6065 (delete-file-recursively "samtools")
6067 (build-system gnu-build-system)
6069 `(#:tests? #f ;no "check" target
6071 (modify-phases %standard-phases
6072 (delete 'configure))
6074 (list (string-append "PREFIX="
6075 (assoc-ref %outputs "out"))
6076 (string-append "LIBBAM="
6077 (assoc-ref %build-inputs "samtools")
6079 (string-append "SMITHLAB_CPP="
6080 (assoc-ref %build-inputs "smithlab-cpp")
6083 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
6086 ("samtools" ,samtools-0.1)
6087 ("smithlab-cpp" ,smithlab-cpp)
6089 (home-page "http://smithlabresearch.org/software/preseq/")
6090 (synopsis "Program for analyzing library complexity")
6092 "The preseq package is aimed at predicting and estimating the complexity
6093 of a genomic sequencing library, equivalent to predicting and estimating the
6094 number of redundant reads from a given sequencing depth and how many will be
6095 expected from additional sequencing using an initial sequencing experiment.
6096 The estimates can then be used to examine the utility of further sequencing,
6097 optimize the sequencing depth, or to screen multiple libraries to avoid low
6098 complexity samples.")
6099 (license license:gpl3+)))
6101 (define-public python-screed
6103 (name "python-screed")
6108 (uri (pypi-uri "screed" version))
6111 "148vcb7w2wr6a4w6vs2bsxanbqibxfk490zbcbg4m61s8669zdjx"))))
6112 (build-system python-build-system)
6115 (modify-phases %standard-phases
6116 ;; Tests must be run after installation, as the "screed" command does
6117 ;; not exist right after building.
6119 (add-after 'install 'check
6120 (lambda* (#:key inputs outputs #:allow-other-keys)
6121 (let ((out (assoc-ref outputs "out")))
6122 (setenv "PYTHONPATH"
6123 (string-append out "/lib/python"
6124 (string-take (string-take-right
6125 (assoc-ref inputs "python")
6128 (getenv "PYTHONPATH")))
6129 (setenv "PATH" (string-append out "/bin:" (getenv "PATH"))))
6130 (invoke "python" "setup.py" "test")
6133 `(("python-pytest" ,python-pytest)
6134 ("python-pytest-cov" ,python-pytest-cov)
6135 ("python-pytest-runner" ,python-pytest-runner)))
6137 `(("python-bz2file" ,python-bz2file)))
6138 (home-page "https://github.com/dib-lab/screed/")
6139 (synopsis "Short read sequence database utilities")
6140 (description "Screed parses FASTA and FASTQ files and generates databases.
6141 Values such as sequence name, sequence description, sequence quality and the
6142 sequence itself can be retrieved from these databases.")
6143 (license license:bsd-3)))
6145 (define-public python2-screed
6146 (package-with-python2 python-screed))
6148 (define-public sra-tools
6156 (url "https://github.com/ncbi/sra-tools.git")
6158 (file-name (git-file-name name version))
6161 "1cr2mijkfs5sm35ffjs6861qsd1qkgnhnbavdv65zg5d655abbjf"))))
6162 (build-system gnu-build-system)
6164 `(#:parallel-build? #f ; not supported
6165 #:tests? #f ; no "check" target
6167 (list (string-append "DEFAULT_CRT="
6168 (assoc-ref %build-inputs "ncbi-vdb")
6170 (string-append "DEFAULT_KFG="
6171 (assoc-ref %build-inputs "ncbi-vdb")
6173 (string-append "VDB_LIBDIR="
6174 (assoc-ref %build-inputs "ncbi-vdb")
6175 ,(if (string-prefix? "x86_64"
6176 (or (%current-target-system)
6181 (modify-phases %standard-phases
6182 (add-before 'configure 'set-perl-search-path
6184 ;; Work around "dotless @INC" build failure.
6186 (string-append (getcwd) "/setup:"
6187 (getenv "PERL5LIB")))
6190 (lambda* (#:key inputs outputs #:allow-other-keys)
6191 ;; The build system expects a directory containing the sources and
6192 ;; raw build output of ncbi-vdb, including files that are not
6193 ;; installed. Since we are building against an installed version of
6194 ;; ncbi-vdb, the following modifications are needed.
6195 (substitute* "setup/konfigure.perl"
6196 ;; Make the configure script look for the "ilib" directory of
6197 ;; "ncbi-vdb" without first checking for the existence of a
6198 ;; matching library in its "lib" directory.
6199 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
6200 "my $f = File::Spec->catdir($ilibdir, $ilib);")
6201 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
6202 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
6203 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
6206 (substitute* "tools/copycat/Makefile"
6207 (("smagic-static") "lmagic"))
6208 (substitute* "tools/driver-tool/utf8proc/Makefile"
6209 (("CC\\?=gcc") "myCC=gcc")
6210 (("\\(CC\\)") "(myCC)"))
6212 ;; The 'configure' script doesn't recognize things like
6213 ;; '--enable-fast-install'.
6214 (invoke "./configure"
6215 (string-append "--build-prefix=" (getcwd) "/build")
6216 (string-append "--prefix=" (assoc-ref outputs "out"))
6217 (string-append "--debug")
6218 (string-append "--with-fuse-prefix="
6219 (assoc-ref inputs "fuse"))
6220 (string-append "--with-magic-prefix="
6221 (assoc-ref inputs "libmagic"))
6222 ;; TODO: building with libxml2 fails with linker errors
6224 (string-append "--with-xml2-prefix="
6225 (assoc-ref inputs "libxml2"))
6226 (string-append "--with-ncbi-vdb-sources="
6227 (assoc-ref inputs "ncbi-vdb"))
6228 (string-append "--with-ncbi-vdb-build="
6229 (assoc-ref inputs "ncbi-vdb"))
6230 (string-append "--with-ngs-sdk-prefix="
6231 (assoc-ref inputs "ngs-sdk"))
6232 (string-append "--with-hdf5-prefix="
6233 (assoc-ref inputs "hdf5")))
6235 (native-inputs `(("perl" ,perl)))
6237 `(("ngs-sdk" ,ngs-sdk)
6238 ("ncbi-vdb" ,ncbi-vdb)
6243 ("python" ,python-wrapper)))
6245 "https://trace.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
6246 (synopsis "Tools and libraries for reading and writing sequencing data")
6248 "The SRA Toolkit from NCBI is a collection of tools and libraries for
6249 reading of sequencing files from the Sequence Read Archive (SRA) database and
6250 writing files into the .sra format.")
6251 (license license:public-domain)))
6253 (define-public seqan
6259 (uri (string-append "https://github.com/seqan/seqan/releases/"
6260 "download/seqan-v" version
6261 "/seqan-library-" version ".tar.xz"))
6264 "19a1rlxx03qy1i1iriicly68w64yjxbv24g9gdywnfmq998v35yx"))))
6265 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6266 ;; makes sense to split the outputs.
6267 (outputs '("out" "doc"))
6268 (build-system trivial-build-system)
6270 `(#:modules ((guix build utils))
6273 (use-modules (guix build utils))
6274 (let ((tar (assoc-ref %build-inputs "tar"))
6275 (xz (assoc-ref %build-inputs "xz"))
6276 (out (assoc-ref %outputs "out"))
6277 (doc (assoc-ref %outputs "doc")))
6278 (setenv "PATH" (string-append tar "/bin:" xz "/bin"))
6279 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6280 (chdir (string-append "seqan-library-" ,version))
6281 (copy-recursively "include" (string-append out "/include"))
6282 (copy-recursively "share" (string-append doc "/share"))
6285 `(("source" ,source)
6288 (home-page "http://www.seqan.de")
6289 (synopsis "Library for nucleotide sequence analysis")
6291 "SeqAn is a C++ library of efficient algorithms and data structures for
6292 the analysis of sequences with the focus on biological data. It contains
6293 algorithms and data structures for string representation and their
6294 manipulation, online and indexed string search, efficient I/O of
6295 bioinformatics file formats, sequence alignment, and more.")
6296 (license license:bsd-3)))
6298 (define-public seqan-1
6299 (package (inherit seqan)
6304 (uri (string-append "http://packages.seqan.de/seqan-library/"
6305 "seqan-library-" version ".tar.bz2"))
6308 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
6309 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6310 ;; makes sense to split the outputs.
6311 (outputs '("out" "doc"))
6312 (build-system trivial-build-system)
6314 `(#:modules ((guix build utils))
6317 (use-modules (guix build utils))
6318 (let ((tar (assoc-ref %build-inputs "tar"))
6319 (bzip (assoc-ref %build-inputs "bzip2"))
6320 (out (assoc-ref %outputs "out"))
6321 (doc (assoc-ref %outputs "doc")))
6322 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
6323 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6324 (chdir (string-append "seqan-library-" ,version))
6325 (copy-recursively "include" (string-append out "/include"))
6326 (copy-recursively "share" (string-append doc "/share"))
6329 `(("source" ,source)
6331 ("bzip2" ,bzip2)))))
6333 (define-public seqmagick
6340 (uri (pypi-uri "seqmagick" version))
6343 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
6344 (build-system python-build-system)
6346 `(("python-biopython" ,python-biopython)))
6348 `(("python-nose" ,python-nose)))
6349 (home-page "https://github.com/fhcrc/seqmagick")
6350 (synopsis "Tools for converting and modifying sequence files")
6352 "Bioinformaticians often have to convert sequence files between formats
6353 and do little manipulations on them, and it's not worth writing scripts for
6354 that. Seqmagick is a utility to expose the file format conversion in
6355 BioPython in a convenient way. Instead of having a big mess of scripts, there
6356 is one that takes arguments.")
6357 (license license:gpl3)))
6359 (define-public seqtk
6366 (url "https://github.com/lh3/seqtk.git")
6367 (commit (string-append "v" version))))
6368 (file-name (git-file-name name version))
6371 "1bfzlqa84b5s1qi22blmmw2s8xdyp9h9ydcq22pfjhh5gab3yz6l"))))
6372 (build-system gnu-build-system)
6375 (modify-phases %standard-phases
6378 ;; There are no tests, so we just run a sanity check.
6379 (lambda _ (invoke "./seqtk" "seq") #t))
6381 (lambda* (#:key outputs #:allow-other-keys)
6382 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6383 (install-file "seqtk" bin)
6387 (home-page "https://github.com/lh3/seqtk")
6388 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
6390 "Seqtk is a fast and lightweight tool for processing sequences in the
6391 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
6392 optionally compressed by gzip.")
6393 (license license:expat)))
6395 (define-public snap-aligner
6397 (name "snap-aligner")
6398 (version "1.0beta.18")
6402 (url "https://github.com/amplab/snap.git")
6403 (commit (string-append "v" version))))
6404 (file-name (git-file-name name version))
6407 "01w3qq4wm07z73vky0cfwlmrbf50n3w722cxrlzxfi99mnb808d8"))))
6408 (build-system gnu-build-system)
6411 (modify-phases %standard-phases
6413 (replace 'check (lambda _ (invoke "./unit_tests") #t))
6415 (lambda* (#:key outputs #:allow-other-keys)
6416 (let* ((out (assoc-ref outputs "out"))
6417 (bin (string-append out "/bin")))
6418 (install-file "snap-aligner" bin)
6419 (install-file "SNAPCommand" bin)
6423 (home-page "http://snap.cs.berkeley.edu/")
6424 (synopsis "Short read DNA sequence aligner")
6426 "SNAP is a fast and accurate aligner for short DNA reads. It is
6427 optimized for modern read lengths of 100 bases or higher, and takes advantage
6428 of these reads to align data quickly through a hash-based indexing scheme.")
6429 ;; 32-bit systems are not supported by the unpatched code.
6430 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
6431 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
6432 ;; systems without a lot of memory cannot make good use of this program.
6433 (supported-systems '("x86_64-linux"))
6434 (license license:asl2.0)))
6436 (define-public sortmerna
6444 (url "https://github.com/biocore/sortmerna.git")
6446 (file-name (git-file-name name version))
6449 "0j3mbz4n25738yijmjbr5r4fyvkgm8v5vn3sshyfvmyqf5q9byqf"))))
6450 (build-system gnu-build-system)
6451 (outputs '("out" ;for binaries
6452 "db")) ;for sequence databases
6455 (modify-phases %standard-phases
6457 (lambda* (#:key outputs #:allow-other-keys)
6458 (let* ((out (assoc-ref outputs "out"))
6459 (bin (string-append out "/bin"))
6460 (db (assoc-ref outputs "db"))
6462 (string-append db "/share/sortmerna/rRNA_databases")))
6463 (install-file "sortmerna" bin)
6464 (install-file "indexdb_rna" bin)
6465 (for-each (lambda (file)
6466 (install-file file share))
6467 (find-files "rRNA_databases" ".*fasta"))
6471 (home-page "https://bioinfo.lifl.fr/RNA/sortmerna/")
6472 (synopsis "Biological sequence analysis tool for NGS reads")
6474 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
6475 and operational taxonomic unit (OTU) picking of next generation
6476 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
6477 allows for fast and sensitive analyses of nucleotide sequences. The main
6478 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
6479 ;; The source includes x86 specific code
6480 (supported-systems '("x86_64-linux" "i686-linux"))
6481 (license license:lgpl3)))
6490 (url "https://github.com/alexdobin/STAR.git")
6492 (file-name (git-file-name name version))
6495 "1hgiqw5qhs0pc1xazzihcfd92na02xyq2kb469z04y1v51kpvvjq"))
6496 (modules '((guix build utils)))
6499 (substitute* "source/Makefile"
6501 ;; Remove pre-built binaries and bundled htslib sources.
6502 (delete-file-recursively "bin/MacOSX_x86_64")
6503 (delete-file-recursively "bin/Linux_x86_64")
6504 (delete-file-recursively "bin/Linux_x86_64_static")
6505 (delete-file-recursively "source/htslib")
6507 (build-system gnu-build-system)
6509 '(#:tests? #f ;no check target
6510 #:make-flags '("STAR")
6512 (modify-phases %standard-phases
6513 (add-after 'unpack 'enter-source-dir
6514 (lambda _ (chdir "source") #t))
6515 (add-after 'enter-source-dir 'make-reproducible
6517 (substitute* "Makefile"
6518 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
6519 (string-append pre "Built with Guix" post)))
6521 ;; See https://github.com/alexdobin/STAR/pull/562
6522 (add-after 'enter-source-dir 'add-missing-header
6524 (substitute* "SoloReadFeature_inputRecords.cpp"
6525 (("#include \"binarySearch2.h\"" h)
6526 (string-append h "\n#include <math.h>")))
6528 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
6530 (substitute* "Makefile"
6531 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
6533 (substitute* '("BAMfunctions.cpp"
6538 "bamRemoveDuplicates.cpp")
6539 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
6540 (string-append "#include <" header ">")))
6541 (substitute* "IncludeDefine.h"
6542 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
6543 (string-append "<" header ">")))
6546 (lambda* (#:key outputs #:allow-other-keys)
6547 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6548 (install-file "STAR" bin))
6550 (delete 'configure))))
6554 `(("htslib" ,htslib)
6556 (home-page "https://github.com/alexdobin/STAR")
6557 (synopsis "Universal RNA-seq aligner")
6559 "The Spliced Transcripts Alignment to a Reference (STAR) software is
6560 based on a previously undescribed RNA-seq alignment algorithm that uses
6561 sequential maximum mappable seed search in uncompressed suffix arrays followed
6562 by seed clustering and stitching procedure. In addition to unbiased de novo
6563 detection of canonical junctions, STAR can discover non-canonical splices and
6564 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
6566 ;; Only 64-bit systems are supported according to the README.
6567 (supported-systems '("x86_64-linux" "mips64el-linux"))
6568 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
6569 (license license:gpl3+)))
6571 (define-public starlong
6572 (package (inherit star)
6575 (substitute-keyword-arguments (package-arguments star)
6576 ((#:make-flags flags)
6579 `(modify-phases ,phases
6580 ;; Allow extra long sequence reads.
6581 (add-after 'unpack 'make-extra-long
6583 (substitute* "source/IncludeDefine.h"
6584 (("(#define DEF_readNameLengthMax ).*" _ match)
6585 (string-append match "900000\n")))
6588 (lambda* (#:key outputs #:allow-other-keys)
6589 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6590 (install-file "STARlong" bin))
6593 (define-public subread
6599 (uri (string-append "mirror://sourceforge/subread/subread-"
6600 version "/subread-" version "-source.tar.gz"))
6603 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
6604 (build-system gnu-build-system)
6606 `(#:tests? #f ;no "check" target
6607 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
6608 ;; optimizations by default, so we override these flags such that x86_64
6609 ;; flags are only added when the build target is an x86_64 system.
6611 (list (let ((system ,(or (%current-target-system)
6613 (flags '("-ggdb" "-fomit-frame-pointer"
6614 "-ffast-math" "-funroll-loops"
6615 "-fmessage-length=0"
6616 "-O9" "-Wall" "-DMAKE_FOR_EXON"
6618 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
6619 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
6620 (if (string-prefix? "x86_64" system)
6621 (string-append "CCFLAGS=" (string-join (append flags flags64)))
6622 (string-append "CCFLAGS=" (string-join flags))))
6623 "-f" "Makefile.Linux"
6624 "CC=gcc ${CCFLAGS}")
6626 (modify-phases %standard-phases
6627 (add-after 'unpack 'enter-dir
6628 (lambda _ (chdir "src") #t))
6630 (lambda* (#:key outputs #:allow-other-keys)
6631 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6633 (copy-recursively "../bin" bin))
6635 ;; no "configure" script
6636 (delete 'configure))))
6637 (inputs `(("zlib" ,zlib)))
6638 (home-page "http://bioinf.wehi.edu.au/subread-package/")
6639 (synopsis "Tool kit for processing next-gen sequencing data")
6641 "The subread package contains the following tools: subread aligner, a
6642 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
6643 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
6644 features; exactSNP: a SNP caller that discovers SNPs by testing signals
6645 against local background noises.")
6646 (license license:gpl3+)))
6648 (define-public stringtie
6654 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
6655 "stringtie-" version ".tar.gz"))
6658 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
6659 (modules '((guix build utils)))
6662 (delete-file-recursively "samtools-0.1.18")
6664 (build-system gnu-build-system)
6666 `(#:tests? #f ;no test suite
6668 (modify-phases %standard-phases
6669 ;; no configure script
6671 (add-before 'build 'use-system-samtools
6673 (substitute* "Makefile"
6674 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
6676 (substitute* '("gclib/GBam.h"
6678 (("#include \"(bam|sam|kstring).h\"" _ header)
6679 (string-append "#include <samtools/" header ".h>")))
6681 (add-after 'unpack 'remove-duplicate-typedef
6683 ;; This typedef conflicts with the typedef in
6684 ;; glibc-2.25/include/bits/types.h
6685 (substitute* "gclib/GThreads.h"
6686 (("typedef long long __intmax_t;") ""))
6689 (lambda* (#:key outputs #:allow-other-keys)
6690 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6691 (install-file "stringtie" bin)
6694 `(("samtools" ,samtools-0.1)
6696 (home-page "http://ccb.jhu.edu/software/stringtie/")
6697 (synopsis "Transcript assembly and quantification for RNA-Seq data")
6699 "StringTie is a fast and efficient assembler of RNA-Seq sequence
6700 alignments into potential transcripts. It uses a novel network flow algorithm
6701 as well as an optional de novo assembly step to assemble and quantitate
6702 full-length transcripts representing multiple splice variants for each gene
6703 locus. Its input can include not only the alignments of raw reads used by
6704 other transcript assemblers, but also alignments of longer sequences that have
6705 been assembled from those reads. To identify differentially expressed genes
6706 between experiments, StringTie's output can be processed either by the
6707 Cuffdiff or Ballgown programs.")
6708 (license license:artistic2.0)))
6710 (define-public taxtastic
6715 ;; The Pypi version does not include tests.
6718 (url "https://github.com/fhcrc/taxtastic.git")
6719 (commit (string-append "v" version))))
6720 (file-name (git-file-name name version))
6723 "1sv8mkg64jn7zdwf1jj71c16686yrwxk0apb1l8sjszy9p166g0p"))))
6724 (build-system python-build-system)
6727 (modify-phases %standard-phases
6728 (add-after 'unpack 'prepare-directory
6730 ;; The git checkout must be writable for tests.
6731 (for-each make-file-writable (find-files "."))
6732 ;; This test fails, but the error is not caught by the test
6733 ;; framework, so the tests fail...
6734 (substitute* "tests/test_taxit.py"
6735 (("self.cmd_fails\\(''\\)")
6736 "self.cmd_fails('nothing')"))
6737 ;; This version file is expected to be created with git describe.
6738 (mkdir-p "taxtastic/data")
6739 (with-output-to-file "taxtastic/data/ver"
6740 (lambda () (display ,version)))
6742 (add-after 'unpack 'python37-compatibility
6744 (substitute* "taxtastic/utils.py"
6745 (("import csv") "import csv, errno")
6746 (("os.errno") "errno"))
6749 ;; Note, this fails to run with "-v" as it tries to write to a
6750 ;; closed output stream.
6751 (lambda _ (invoke "python" "-m" "unittest") #t)))))
6753 `(("python-sqlalchemy" ,python-sqlalchemy)
6754 ("python-decorator" ,python-decorator)
6755 ("python-biopython" ,python-biopython)
6756 ("python-pandas" ,python-pandas)
6757 ("python-psycopg2" ,python-psycopg2)
6758 ("python-fastalite" ,python-fastalite)
6759 ("python-pyyaml" ,python-pyyaml)
6760 ("python-six" ,python-six)
6761 ("python-jinja2" ,python-jinja2)
6762 ("python-dendropy" ,python-dendropy)))
6763 (home-page "https://github.com/fhcrc/taxtastic")
6764 (synopsis "Tools for taxonomic naming and annotation")
6766 "Taxtastic is software written in python used to build and maintain
6767 reference packages i.e. collections of reference trees, reference alignments,
6768 profiles, and associated taxonomic information.")
6769 (license license:gpl3+)))
6771 (define-public vcftools
6778 "https://github.com/vcftools/vcftools/releases/download/v"
6779 version "/vcftools-" version ".tar.gz"))
6782 "1qqlx7flfv7axrjwkaz6njkscsl1d0jw98ns8d8bh1n1hd1pgz6v"))))
6783 (build-system gnu-build-system)
6785 `(#:tests? #f ; no "check" target
6787 "CFLAGS=-O2" ; override "-m64" flag
6788 (string-append "PREFIX=" (assoc-ref %outputs "out"))
6789 (string-append "MANDIR=" (assoc-ref %outputs "out")
6790 "/share/man/man1"))))
6792 `(("pkg-config" ,pkg-config)))
6796 (home-page "https://vcftools.github.io/")
6797 (synopsis "Tools for working with VCF files")
6799 "VCFtools is a program package designed for working with VCF files, such
6800 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
6801 provide easily accessible methods for working with complex genetic variation
6802 data in the form of VCF files.")
6803 ;; The license is declared as LGPLv3 in the README and
6804 ;; at https://vcftools.github.io/license.html
6805 (license license:lgpl3)))
6807 (define-public infernal
6813 (uri (string-append "http://eddylab.org/software/infernal/"
6814 "infernal-" version ".tar.gz"))
6817 "0pm8bm3s6nfa0av4x6m6h27lsg12b3lz3jm0fyh1mc77l2isd61v"))))
6818 (build-system gnu-build-system)
6821 ("python" ,python))) ; for tests
6822 (home-page "http://eddylab.org/infernal/")
6823 (synopsis "Inference of RNA alignments")
6824 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
6825 searching DNA sequence databases for RNA structure and sequence similarities.
6826 It is an implementation of a special case of profile stochastic context-free
6827 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
6828 profile, but it scores a combination of sequence consensus and RNA secondary
6829 structure consensus, so in many cases, it is more capable of identifying RNA
6830 homologs that conserve their secondary structure more than their primary
6832 ;; Infernal 1.1.3 requires VMX or SSE capability for parallel instructions.
6833 (supported-systems '("i686-linux" "x86_64-linux"))
6834 (license license:bsd-3)))
6836 (define-public r-scde
6843 (url "https://github.com/hms-dbmi/scde.git")
6845 (file-name (git-file-name name version))
6848 "10na2gyka24mszdxf92wz9h2c13hdf1ww30c68gfsw53lvvhhhxb"))))
6849 (build-system r-build-system)
6851 `(("r-rcpp" ,r-rcpp)
6852 ("r-rcpparmadillo" ,r-rcpparmadillo)
6855 ("r-rjson" ,r-rjson)
6856 ("r-cairo" ,r-cairo)
6857 ("r-rcolorbrewer" ,r-rcolorbrewer)
6858 ("r-edger" ,r-edger)
6859 ("r-quantreg" ,r-quantreg)
6861 ("r-rmtstat" ,r-rmtstat)
6862 ("r-extremes" ,r-extremes)
6863 ("r-pcamethods" ,r-pcamethods)
6864 ("r-biocparallel" ,r-biocparallel)
6865 ("r-flexmix" ,r-flexmix)))
6866 (home-page "https://hms-dbmi.github.io/scde/")
6867 (synopsis "R package for analyzing single-cell RNA-seq data")
6868 (description "The SCDE package implements a set of statistical methods for
6869 analyzing single-cell RNA-seq data. SCDE fits individual error models for
6870 single-cell RNA-seq measurements. These models can then be used for
6871 assessment of differential expression between groups of cells, as well as
6872 other types of analysis. The SCDE package also contains the pagoda framework
6873 which applies pathway and gene set overdispersion analysis to identify aspects
6874 of transcriptional heterogeneity among single cells.")
6875 ;; See https://github.com/hms-dbmi/scde/issues/38
6876 (license license:gpl2)))
6878 (define-public r-centipede
6880 (name "r-centipede")
6884 (uri (string-append "http://download.r-forge.r-project.org/"
6885 "src/contrib/CENTIPEDE_" version ".tar.gz"))
6888 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
6889 (build-system r-build-system)
6890 (home-page "http://centipede.uchicago.edu/")
6891 (synopsis "Predict transcription factor binding sites")
6893 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
6894 of the genome that are bound by particular transcription factors. It starts
6895 by identifying a set of candidate binding sites, and then aims to classify the
6896 sites according to whether each site is bound or not bound by a transcription
6897 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
6898 between two different types of motif instances using as much relevant
6899 information as possible.")
6900 (license (list license:gpl2+ license:gpl3+))))
6902 (define-public r-genefilter
6904 (name "r-genefilter")
6909 (uri (bioconductor-uri "genefilter" version))
6912 "1xjr02qhldspjwd6y374wgik18fgywb6408wsz471i8b4ik98ckc"))))
6913 (build-system r-build-system)
6915 `(("gfortran" ,gfortran)))
6917 `(("r-annotate" ,r-annotate)
6918 ("r-annotationdbi" ,r-annotationdbi)
6919 ("r-biobase" ,r-biobase)
6920 ("r-biocgenerics" ,r-biocgenerics)
6921 ("r-survival" ,r-survival)))
6922 (home-page "https://bioconductor.org/packages/genefilter")
6923 (synopsis "Filter genes from high-throughput experiments")
6925 "This package provides basic functions for filtering genes from
6926 high-throughput sequencing experiments.")
6927 (license license:artistic2.0)))
6929 (define-public r-deseq2
6936 (uri (bioconductor-uri "DESeq2" version))
6939 "1lmbhznfs8dz9ipd53z4ccwvwxqwzx1ayw56jlrvlsambaj8fash"))))
6940 (properties `((upstream-name . "DESeq2")))
6941 (build-system r-build-system)
6943 `(("r-biobase" ,r-biobase)
6944 ("r-biocgenerics" ,r-biocgenerics)
6945 ("r-biocparallel" ,r-biocparallel)
6946 ("r-genefilter" ,r-genefilter)
6947 ("r-geneplotter" ,r-geneplotter)
6948 ("r-genomicranges" ,r-genomicranges)
6949 ("r-ggplot2" ,r-ggplot2)
6950 ("r-hmisc" ,r-hmisc)
6951 ("r-iranges" ,r-iranges)
6952 ("r-locfit" ,r-locfit)
6954 ("r-rcpparmadillo" ,r-rcpparmadillo)
6955 ("r-s4vectors" ,r-s4vectors)
6956 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6957 (home-page "https://bioconductor.org/packages/DESeq2")
6958 (synopsis "Differential gene expression analysis")
6960 "This package provides functions to estimate variance-mean dependence in
6961 count data from high-throughput nucleotide sequencing assays and test for
6962 differential expression based on a model using the negative binomial
6964 (license license:lgpl3+)))
6966 (define-public r-dexseq
6973 (uri (bioconductor-uri "DEXSeq" version))
6976 "0sqqb65ckliif2nmvlvc7w49id59z0nvqcdz5gry8l2mn6azrf6a"))))
6977 (properties `((upstream-name . "DEXSeq")))
6978 (build-system r-build-system)
6980 `(("r-annotationdbi" ,r-annotationdbi)
6981 ("r-biobase" ,r-biobase)
6982 ("r-biocgenerics" ,r-biocgenerics)
6983 ("r-biocparallel" ,r-biocparallel)
6984 ("r-biomart" ,r-biomart)
6985 ("r-deseq2" ,r-deseq2)
6986 ("r-genefilter" ,r-genefilter)
6987 ("r-geneplotter" ,r-geneplotter)
6988 ("r-genomicranges" ,r-genomicranges)
6989 ("r-hwriter" ,r-hwriter)
6990 ("r-iranges" ,r-iranges)
6991 ("r-rcolorbrewer" ,r-rcolorbrewer)
6992 ("r-rsamtools" ,r-rsamtools)
6993 ("r-s4vectors" ,r-s4vectors)
6994 ("r-statmod" ,r-statmod)
6995 ("r-stringr" ,r-stringr)
6996 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6997 (home-page "https://bioconductor.org/packages/DEXSeq")
6998 (synopsis "Inference of differential exon usage in RNA-Seq")
7000 "This package is focused on finding differential exon usage using RNA-seq
7001 exon counts between samples with different experimental designs. It provides
7002 functions that allows the user to make the necessary statistical tests based
7003 on a model that uses the negative binomial distribution to estimate the
7004 variance between biological replicates and generalized linear models for
7005 testing. The package also provides functions for the visualization and
7006 exploration of the results.")
7007 (license license:gpl3+)))
7009 (define-public r-annotationforge
7011 (name "r-annotationforge")
7016 (uri (bioconductor-uri "AnnotationForge" version))
7019 "0h2r60v339ajk5r6xq4iwwcpihdvf12fi8255byr2dhglzrd8xl7"))))
7021 `((upstream-name . "AnnotationForge")))
7022 (build-system r-build-system)
7024 `(("r-annotationdbi" ,r-annotationdbi)
7025 ("r-biobase" ,r-biobase)
7026 ("r-biocgenerics" ,r-biocgenerics)
7028 ("r-rcurl" ,r-rcurl)
7029 ("r-rsqlite" ,r-rsqlite)
7030 ("r-s4vectors" ,r-s4vectors)
7032 (home-page "https://bioconductor.org/packages/AnnotationForge")
7033 (synopsis "Code for building annotation database packages")
7035 "This package provides code for generating Annotation packages and their
7036 databases. Packages produced are intended to be used with AnnotationDbi.")
7037 (license license:artistic2.0)))
7039 (define-public r-rbgl
7046 (uri (bioconductor-uri "RBGL" version))
7049 "0ixbkdirf08i400db587r262j52sdwdgk3884nxk5xkbhx2m6vg0"))))
7050 (properties `((upstream-name . "RBGL")))
7051 (build-system r-build-system)
7054 ("r-graph" ,r-graph)))
7055 (home-page "https://www.bioconductor.org/packages/RBGL")
7056 (synopsis "Interface to the Boost graph library")
7058 "This package provides a fairly extensive and comprehensive interface to
7059 the graph algorithms contained in the Boost library.")
7060 (license license:artistic2.0)))
7062 (define-public r-gseabase
7069 (uri (bioconductor-uri "GSEABase" version))
7072 "0kcb90sxlf19d5dxhdbqk9x62svky4262cccl0wxarbq6gf3bd57"))))
7073 (properties `((upstream-name . "GSEABase")))
7074 (build-system r-build-system)
7076 `(("r-annotate" ,r-annotate)
7077 ("r-annotationdbi" ,r-annotationdbi)
7078 ("r-biobase" ,r-biobase)
7079 ("r-biocgenerics" ,r-biocgenerics)
7080 ("r-graph" ,r-graph)
7082 (home-page "https://bioconductor.org/packages/GSEABase")
7083 (synopsis "Gene set enrichment data structures and methods")
7085 "This package provides classes and methods to support @dfn{Gene Set
7086 Enrichment Analysis} (GSEA).")
7087 (license license:artistic2.0)))
7089 (define-public r-category
7096 (uri (bioconductor-uri "Category" version))
7099 "0ga0ij9hyzsxa5pavwmv35i8xggia2wygrk4m4z8an0qcvgy3v5g"))))
7100 (properties `((upstream-name . "Category")))
7101 (build-system r-build-system)
7103 `(("r-annotate" ,r-annotate)
7104 ("r-annotationdbi" ,r-annotationdbi)
7105 ("r-biobase" ,r-biobase)
7106 ("r-biocgenerics" ,r-biocgenerics)
7107 ("r-genefilter" ,r-genefilter)
7108 ("r-graph" ,r-graph)
7109 ("r-gseabase" ,r-gseabase)
7110 ("r-matrix" ,r-matrix)
7113 (home-page "https://bioconductor.org/packages/Category")
7114 (synopsis "Category analysis")
7116 "This package provides a collection of tools for performing category
7118 (license license:artistic2.0)))
7120 (define-public r-gostats
7127 (uri (bioconductor-uri "GOstats" version))
7130 "19f4gxm3sbprqrnwzvskvywv6j4ibm8xkrbgg4h0fvh2b5331nwc"))))
7131 (properties `((upstream-name . "GOstats")))
7132 (build-system r-build-system)
7134 `(("r-annotate" ,r-annotate)
7135 ("r-annotationdbi" ,r-annotationdbi)
7136 ("r-annotationforge" ,r-annotationforge)
7137 ("r-biobase" ,r-biobase)
7138 ("r-category" ,r-category)
7139 ("r-go-db" ,r-go-db)
7140 ("r-graph" ,r-graph)
7141 ("r-rgraphviz" ,r-rgraphviz)
7142 ("r-rbgl" ,r-rbgl)))
7143 (home-page "https://bioconductor.org/packages/GOstats")
7144 (synopsis "Tools for manipulating GO and microarrays")
7146 "This package provides a set of tools for interacting with GO and
7147 microarray data. A variety of basic manipulation tools for graphs, hypothesis
7148 testing and other simple calculations.")
7149 (license license:artistic2.0)))
7151 (define-public r-shortread
7153 (name "r-shortread")
7158 (uri (bioconductor-uri "ShortRead" version))
7161 "0ykyrj4g6vc67d5s46sp4659qvar2iavflzhggm79w4p50hxia4s"))))
7162 (properties `((upstream-name . "ShortRead")))
7163 (build-system r-build-system)
7167 `(("r-biobase" ,r-biobase)
7168 ("r-biocgenerics" ,r-biocgenerics)
7169 ("r-biocparallel" ,r-biocparallel)
7170 ("r-biostrings" ,r-biostrings)
7171 ("r-genomeinfodb" ,r-genomeinfodb)
7172 ("r-genomicalignments" ,r-genomicalignments)
7173 ("r-genomicranges" ,r-genomicranges)
7174 ("r-hwriter" ,r-hwriter)
7175 ("r-iranges" ,r-iranges)
7176 ("r-lattice" ,r-lattice)
7177 ("r-latticeextra" ,r-latticeextra)
7178 ("r-rsamtools" ,r-rsamtools)
7179 ("r-s4vectors" ,r-s4vectors)
7180 ("r-xvector" ,r-xvector)
7181 ("r-zlibbioc" ,r-zlibbioc)))
7182 (home-page "https://bioconductor.org/packages/ShortRead")
7183 (synopsis "FASTQ input and manipulation tools")
7185 "This package implements sampling, iteration, and input of FASTQ files.
7186 It includes functions for filtering and trimming reads, and for generating a
7187 quality assessment report. Data are represented as
7188 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
7189 purposes. The package also contains legacy support for early single-end,
7190 ungapped alignment formats.")
7191 (license license:artistic2.0)))
7193 (define-public r-systempiper
7195 (name "r-systempiper")
7200 (uri (bioconductor-uri "systemPipeR" version))
7203 "17r25v9wcglyma2v1c8fka80dm7fx86saxlsb2aprmwi4h3dhb0j"))))
7204 (properties `((upstream-name . "systemPipeR")))
7205 (build-system r-build-system)
7207 `(("r-annotate" ,r-annotate)
7208 ("r-batchtools" ,r-batchtools)
7209 ("r-biocgenerics" ,r-biocgenerics)
7210 ("r-biostrings" ,r-biostrings)
7211 ("r-deseq2" ,r-deseq2)
7212 ("r-edger" ,r-edger)
7213 ("r-genomicfeatures" ,r-genomicfeatures)
7214 ("r-genomicranges" ,r-genomicranges)
7215 ("r-ggplot2" ,r-ggplot2)
7216 ("r-go-db" ,r-go-db)
7217 ("r-gostats" ,r-gostats)
7218 ("r-limma" ,r-limma)
7219 ("r-pheatmap" ,r-pheatmap)
7220 ("r-rjson" ,r-rjson)
7221 ("r-rsamtools" ,r-rsamtools)
7222 ("r-shortread" ,r-shortread)
7223 ("r-summarizedexperiment" ,r-summarizedexperiment)
7225 ("r-variantannotation" ,r-variantannotation)))
7226 (home-page "https://github.com/tgirke/systemPipeR")
7227 (synopsis "Next generation sequencing workflow and reporting environment")
7229 "This R package provides tools for building and running automated
7230 end-to-end analysis workflows for a wide range of @dfn{next generation
7231 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
7232 Important features include a uniform workflow interface across different NGS
7233 applications, automated report generation, and support for running both R and
7234 command-line software, such as NGS aligners or peak/variant callers, on local
7235 computers or compute clusters. Efficient handling of complex sample sets and
7236 experimental designs is facilitated by a consistently implemented sample
7237 annotation infrastructure.")
7238 (license license:artistic2.0)))
7240 (define-public r-grohmm
7247 (uri (bioconductor-uri "groHMM" version))
7250 "0ywr8f6bfhg2ia3n4rmsxr4v1xqmlyhkwh0rvkgh3yqgnbvihndg"))))
7251 (properties `((upstream-name . "groHMM")))
7252 (build-system r-build-system)
7254 `(("r-genomeinfodb" ,r-genomeinfodb)
7255 ("r-genomicalignments" ,r-genomicalignments)
7256 ("r-genomicranges" ,r-genomicranges)
7257 ("r-iranges" ,r-iranges)
7259 ("r-rtracklayer" ,r-rtracklayer)
7260 ("r-s4vectors" ,r-s4vectors)))
7261 (home-page "https://github.com/Kraus-Lab/groHMM")
7262 (synopsis "GRO-seq analysis pipeline")
7264 "This package provides a pipeline for the analysis of GRO-seq data.")
7265 (license license:gpl3+)))
7267 (define-public vsearch
7275 (url "https://github.com/torognes/vsearch.git")
7276 (commit (string-append "v" version))))
7277 (file-name (git-file-name name version))
7280 "0vhrpjfdf75ba04b24xknp41790cvcgwl0vgpy7qbzj5xh2521ss"))
7281 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
7284 ;; Remove bundled cityhash sources. The vsearch source is adjusted
7285 ;; for this in the patch.
7286 (delete-file "src/city.h")
7287 (delete-file "src/citycrc.h")
7288 (delete-file "src/city.cc")
7290 (build-system gnu-build-system)
7294 ("cityhash" ,cityhash)))
7296 `(("autoconf" ,autoconf)
7297 ("automake" ,automake)))
7298 (synopsis "Sequence search tools for metagenomics")
7300 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
7301 dereplication, pairwise alignment, shuffling, subsampling, sorting and
7302 masking. The tool takes advantage of parallelism in the form of SIMD
7303 vectorization as well as multiple threads to perform accurate alignments at
7304 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
7305 Needleman-Wunsch).")
7306 (home-page "https://github.com/torognes/vsearch")
7307 ;; vsearch uses non-portable SSE intrinsics so building fails on other
7309 (supported-systems '("x86_64-linux"))
7310 ;; Dual licensed; also includes public domain source.
7311 (license (list license:gpl3 license:bsd-2))))
7313 (define-public pardre
7316 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
7321 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
7325 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
7326 (build-system gnu-build-system)
7328 `(#:tests? #f ; no tests included
7330 (modify-phases %standard-phases
7333 (lambda* (#:key outputs #:allow-other-keys)
7334 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
7335 (install-file "ParDRe" bin)
7338 `(("openmpi" ,openmpi)
7340 (synopsis "Parallel tool to remove duplicate DNA reads")
7342 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
7343 Duplicate reads can be seen as identical or nearly identical sequences with
7344 some mismatches. This tool lets users avoid the analysis of unnecessary
7345 reads, reducing the time of subsequent procedures with the
7346 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
7347 in order to exploit the parallel capabilities of multicore clusters. It is
7348 faster than multithreaded counterparts (end of 2015) for the same number of
7349 cores and, thanks to the message-passing technology, it can be executed on
7351 (home-page "https://sourceforge.net/projects/pardre/")
7352 (license license:gpl3+)))
7354 (define-public ruby-bio-kseq
7356 (name "ruby-bio-kseq")
7361 (uri (rubygems-uri "bio-kseq" version))
7364 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
7365 (build-system ruby-build-system)
7367 `(#:test-target "spec"))
7369 `(("bundler" ,bundler)
7370 ("ruby-rspec" ,ruby-rspec)
7371 ("ruby-rake-compiler" ,ruby-rake-compiler)))
7374 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
7376 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
7377 FASTQ parsing code. It provides a fast iterator over sequences and their
7379 (home-page "https://github.com/gusevfe/bio-kseq")
7380 (license license:expat)))
7382 (define-public bio-locus
7389 (uri (rubygems-uri "bio-locus" version))
7392 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
7393 (build-system ruby-build-system)
7395 `(("ruby-rspec" ,ruby-rspec)))
7396 (synopsis "Tool for fast querying of genome locations")
7398 "Bio-locus is a tabix-like tool for fast querying of genome
7399 locations. Many file formats in bioinformatics contain records that
7400 start with a chromosome name and a position for a SNP, or a start-end
7401 position for indels. Bio-locus allows users to store this chr+pos or
7402 chr+pos+alt information in a database.")
7403 (home-page "https://github.com/pjotrp/bio-locus")
7404 (license license:expat)))
7406 (define-public bio-blastxmlparser
7408 (name "bio-blastxmlparser")
7412 (uri (rubygems-uri "bio-blastxmlparser" version))
7415 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
7416 (build-system ruby-build-system)
7418 `(("ruby-bio-logger" ,ruby-bio-logger)
7419 ("ruby-nokogiri" ,ruby-nokogiri)))
7421 `(("ruby-rspec" ,ruby-rspec)))
7422 (synopsis "Fast big data BLAST XML parser and library")
7424 "Very fast parallel big-data BLAST XML file parser which can be used as
7425 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
7426 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
7427 (home-page "https://github.com/pjotrp/blastxmlparser")
7428 (license license:expat)))
7430 (define-public bioruby
7437 (uri (rubygems-uri "bio" version))
7440 "1d56amdsjv1mag7m6gv2w0xij8hqx1v5xbdjsix8sp3yp36m7938"))))
7441 (build-system ruby-build-system)
7443 `(("ruby-libxml" ,ruby-libxml)))
7445 `(("which" ,which))) ; required for test phase
7448 (modify-phases %standard-phases
7449 (add-before 'build 'patch-test-command
7451 (substitute* '("test/functional/bio/test_command.rb")
7452 (("/bin/sh") (which "sh")))
7453 (substitute* '("test/functional/bio/test_command.rb")
7454 (("/bin/ls") (which "ls")))
7455 (substitute* '("test/functional/bio/test_command.rb")
7456 (("which") (which "which")))
7457 (substitute* '("test/functional/bio/test_command.rb",
7458 "test/data/command/echoarg2.sh")
7459 (("/bin/echo") (which "echo")))
7461 (synopsis "Ruby library, shell and utilities for bioinformatics")
7462 (description "BioRuby comes with a comprehensive set of Ruby development
7463 tools and libraries for bioinformatics and molecular biology. BioRuby has
7464 components for sequence analysis, pathway analysis, protein modelling and
7465 phylogenetic analysis; it supports many widely used data formats and provides
7466 easy access to databases, external programs and public web services, including
7467 BLAST, KEGG, GenBank, MEDLINE and GO.")
7468 (home-page "http://bioruby.org/")
7469 ;; Code is released under Ruby license, except for setup
7470 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
7471 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
7473 (define-public r-biocviews
7475 (name "r-biocviews")
7479 (uri (bioconductor-uri "biocViews" version))
7482 "0yn8jys1900d31haayz0ppqk5y79mwjajwp4alz6pln3dbs70f3g"))))
7484 `((upstream-name . "biocViews")))
7485 (build-system r-build-system)
7487 `(("r-biobase" ,r-biobase)
7488 ("r-biocmanager" ,r-biocmanager)
7489 ("r-graph" ,r-graph)
7491 ("r-rcurl" ,r-rcurl)
7493 ("r-runit" ,r-runit)))
7494 (home-page "https://bioconductor.org/packages/biocViews")
7495 (synopsis "Bioconductor package categorization helper")
7496 (description "The purpose of biocViews is to create HTML pages that
7497 categorize packages in a Bioconductor package repository according to keywords,
7498 also known as views, in a controlled vocabulary.")
7499 (license license:artistic2.0)))
7501 (define-public r-biocstyle
7503 (name "r-biocstyle")
7507 (uri (bioconductor-uri "BiocStyle" version))
7510 "1x71in059zql40f4c87bd1gf96r945kdvwbq61jmch9d3d8nwxbb"))))
7512 `((upstream-name . "BiocStyle")))
7513 (build-system r-build-system)
7515 `(("r-biocmanager" ,r-biocmanager)
7516 ("r-bookdown" ,r-bookdown)
7517 ("r-knitr" ,r-knitr)
7518 ("r-rmarkdown" ,r-rmarkdown)
7519 ("r-yaml" ,r-yaml)))
7520 (home-page "https://bioconductor.org/packages/BiocStyle")
7521 (synopsis "Bioconductor formatting styles")
7522 (description "This package provides standard formatting styles for
7523 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
7525 (license license:artistic2.0)))
7527 (define-public r-bioccheck
7529 (name "r-bioccheck")
7533 (uri (bioconductor-uri "BiocCheck" version))
7536 "1qnvl5yajgh67ijkq6gdsafri1k5hyw5gzn2ccqk9ymx6i2xd80g"))))
7538 `((upstream-name . "BiocCheck")))
7539 (build-system r-build-system)
7542 (modify-phases %standard-phases
7543 ;; This package can be used by calling BiocCheck(<package>) from
7544 ;; within R, or by running R CMD BiocCheck <package>. This phase
7545 ;; makes sure the latter works. For this to work, the BiocCheck
7546 ;; script must be somewhere on the PATH (not the R bin directory).
7547 (add-after 'install 'install-bioccheck-subcommand
7548 (lambda* (#:key outputs #:allow-other-keys)
7549 (let* ((out (assoc-ref outputs "out"))
7550 (dest-dir (string-append out "/bin"))
7552 (string-append out "/site-library/BiocCheck/script/")))
7554 (symlink (string-append script-dir "/checkBadDeps.R")
7555 (string-append dest-dir "/checkBadDeps.R"))
7556 (symlink (string-append script-dir "/BiocCheck")
7557 (string-append dest-dir "/BiocCheck")))
7560 `(("r-codetools" ,r-codetools)
7561 ("r-graph" ,r-graph)
7563 ("r-knitr" ,r-knitr)
7564 ("r-optparse" ,r-optparse)
7565 ("r-biocmanager" ,r-biocmanager)
7566 ("r-biocviews" ,r-biocviews)
7567 ("r-stringdist" ,r-stringdist)))
7568 (home-page "https://bioconductor.org/packages/BiocCheck")
7569 (synopsis "Executes Bioconductor-specific package checks")
7570 (description "This package contains tools to perform additional quality
7571 checks on R packages that are to be submitted to the Bioconductor repository.")
7572 (license license:artistic2.0)))
7574 (define-public r-s4vectors
7576 (name "r-s4vectors")
7580 (uri (bioconductor-uri "S4Vectors" version))
7583 "1fzs8j2d3wwfzm2fq63ywf68a4dbggyl5l098f148yn4jw7jd3bc"))))
7585 `((upstream-name . "S4Vectors")))
7586 (build-system r-build-system)
7588 `(("r-biocgenerics" ,r-biocgenerics)))
7589 (home-page "https://bioconductor.org/packages/S4Vectors")
7590 (synopsis "S4 implementation of vectors and lists")
7592 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7593 classes and a set of generic functions that extend the semantic of ordinary
7594 vectors and lists in R. Package developers can easily implement vector-like
7595 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7596 In addition, a few low-level concrete subclasses of general interest (e.g.
7597 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7598 S4Vectors package itself.")
7599 (license license:artistic2.0)))
7601 (define-public r-iranges
7607 (uri (bioconductor-uri "IRanges" version))
7610 "1jhnxb9yacmj2z82b6992gihjvj1a0gnjwbjiagyyx03fqnv23kg"))))
7612 `((upstream-name . "IRanges")))
7613 (build-system r-build-system)
7615 `(("r-biocgenerics" ,r-biocgenerics)
7616 ("r-s4vectors" ,r-s4vectors)))
7617 (home-page "https://bioconductor.org/packages/IRanges")
7618 (synopsis "Infrastructure for manipulating intervals on sequences")
7620 "This package provides efficient low-level and highly reusable S4 classes
7621 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7622 generally, data that can be organized sequentially (formally defined as
7623 @code{Vector} objects), as well as views on these @code{Vector} objects.
7624 Efficient list-like classes are also provided for storing big collections of
7625 instances of the basic classes. All classes in the package use consistent
7626 naming and share the same rich and consistent \"Vector API\" as much as
7628 (license license:artistic2.0)))
7630 (define-public r-genomeinfodbdata
7632 (name "r-genomeinfodbdata")
7636 ;; We cannot use bioconductor-uri here because this tarball is
7637 ;; located under "data/annotation/" instead of "bioc/".
7638 (uri (string-append "https://bioconductor.org/packages/release/"
7639 "data/annotation/src/contrib/GenomeInfoDbData_"
7643 "0di6nlqpsyqf693k2na65ayqldih563x3zfrczpqc5q2hl5kg35c"))))
7645 `((upstream-name . "GenomeInfoDbData")))
7646 (build-system r-build-system)
7647 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7648 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7649 (description "This package contains data for mapping between NCBI taxonomy
7650 ID and species. It is used by functions in the GenomeInfoDb package.")
7651 (license license:artistic2.0)))
7653 (define-public r-genomeinfodb
7655 (name "r-genomeinfodb")
7659 (uri (bioconductor-uri "GenomeInfoDb" version))
7662 "0phadr67yb4l25x41a9wg4pjy1wbxlk14jhidhz6g5n4z6x45qbm"))))
7664 `((upstream-name . "GenomeInfoDb")))
7665 (build-system r-build-system)
7667 `(("r-biocgenerics" ,r-biocgenerics)
7668 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7669 ("r-iranges" ,r-iranges)
7670 ("r-rcurl" ,r-rcurl)
7671 ("r-s4vectors" ,r-s4vectors)))
7673 `(("r-knitr" ,r-knitr)))
7674 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7675 (synopsis "Utilities for manipulating chromosome identifiers")
7677 "This package contains data and functions that define and allow
7678 translation between different chromosome sequence naming conventions (e.g.,
7679 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7680 names in their natural, rather than lexicographic, order.")
7681 (license license:artistic2.0)))
7683 (define-public r-edger
7689 (uri (bioconductor-uri "edgeR" version))
7692 "07dv99kl7jfa62nzcq705r56gcpb1hq7p4px48j71y2ddi1rqmr6"))))
7693 (properties `((upstream-name . "edgeR")))
7694 (build-system r-build-system)
7696 `(("r-limma" ,r-limma)
7697 ("r-locfit" ,r-locfit)
7699 ("r-statmod" ,r-statmod))) ;for estimateDisp
7700 (home-page "http://bioinf.wehi.edu.au/edgeR")
7701 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7702 (description "This package can do differential expression analysis of
7703 RNA-seq expression profiles with biological replication. It implements a range
7704 of statistical methodology based on the negative binomial distributions,
7705 including empirical Bayes estimation, exact tests, generalized linear models
7706 and quasi-likelihood tests. It be applied to differential signal analysis of
7707 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7709 (license license:gpl2+)))
7711 (define-public r-variantannotation
7713 (name "r-variantannotation")
7717 (uri (bioconductor-uri "VariantAnnotation" version))
7720 "009s7rzp78s2w6iybizina42qx2w8qv3xwjbkpqphmm451maykgs"))))
7722 `((upstream-name . "VariantAnnotation")))
7726 `(("r-annotationdbi" ,r-annotationdbi)
7727 ("r-biobase" ,r-biobase)
7728 ("r-biocgenerics" ,r-biocgenerics)
7729 ("r-biostrings" ,r-biostrings)
7730 ("r-bsgenome" ,r-bsgenome)
7732 ("r-genomeinfodb" ,r-genomeinfodb)
7733 ("r-genomicfeatures" ,r-genomicfeatures)
7734 ("r-genomicranges" ,r-genomicranges)
7735 ("r-iranges" ,r-iranges)
7736 ("r-summarizedexperiment" ,r-summarizedexperiment)
7737 ("r-rhtslib" ,r-rhtslib)
7738 ("r-rsamtools" ,r-rsamtools)
7739 ("r-rtracklayer" ,r-rtracklayer)
7740 ("r-s4vectors" ,r-s4vectors)
7741 ("r-xvector" ,r-xvector)
7742 ("r-zlibbioc" ,r-zlibbioc)))
7743 (build-system r-build-system)
7744 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7745 (synopsis "Package for annotation of genetic variants")
7746 (description "This R package can annotate variants, compute amino acid
7747 coding changes and predict coding outcomes.")
7748 (license license:artistic2.0)))
7750 (define-public r-limma
7756 (uri (bioconductor-uri "limma" version))
7759 "1nd01r7rd7jb5qz84vbgfnyrmgm9wiq7fsdji68537kjgvrzmm9z"))))
7760 (build-system r-build-system)
7761 (home-page "http://bioinf.wehi.edu.au/limma")
7762 (synopsis "Package for linear models for microarray and RNA-seq data")
7763 (description "This package can be used for the analysis of gene expression
7764 studies, especially the use of linear models for analysing designed experiments
7765 and the assessment of differential expression. The analysis methods apply to
7766 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7767 (license license:gpl2+)))
7769 (define-public r-xvector
7775 (uri (bioconductor-uri "XVector" version))
7778 "0s2gg84yzl5ffkzp6n7kh0jjk1vd90z189f5hkfn18rn67cy2nv7"))))
7780 `((upstream-name . "XVector")))
7781 (build-system r-build-system)
7784 (modify-phases %standard-phases
7785 (add-after 'unpack 'use-system-zlib
7787 (substitute* "DESCRIPTION"
7788 (("zlibbioc, ") ""))
7789 (substitute* "NAMESPACE"
7790 (("import\\(zlibbioc\\)") ""))
7795 `(("r-biocgenerics" ,r-biocgenerics)
7796 ("r-iranges" ,r-iranges)
7797 ("r-s4vectors" ,r-s4vectors)))
7798 (home-page "https://bioconductor.org/packages/XVector")
7799 (synopsis "Representation and manpulation of external sequences")
7801 "This package provides memory efficient S4 classes for storing sequences
7802 \"externally\" (behind an R external pointer, or on disk).")
7803 (license license:artistic2.0)))
7805 (define-public r-genomicranges
7807 (name "r-genomicranges")
7811 (uri (bioconductor-uri "GenomicRanges" version))
7814 "0xdds6ws7jjdfy4x3mb0qhy43kpxdmifmpw0jdk4wgw999zabb50"))))
7816 `((upstream-name . "GenomicRanges")))
7817 (build-system r-build-system)
7819 `(("r-biocgenerics" ,r-biocgenerics)
7820 ("r-genomeinfodb" ,r-genomeinfodb)
7821 ("r-iranges" ,r-iranges)
7822 ("r-s4vectors" ,r-s4vectors)
7823 ("r-xvector" ,r-xvector)))
7824 (home-page "https://bioconductor.org/packages/GenomicRanges")
7825 (synopsis "Representation and manipulation of genomic intervals")
7827 "This package provides tools to efficiently represent and manipulate
7828 genomic annotations and alignments is playing a central role when it comes to
7829 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7830 GenomicRanges package defines general purpose containers for storing and
7831 manipulating genomic intervals and variables defined along a genome.")
7832 (license license:artistic2.0)))
7834 (define-public r-biobase
7840 (uri (bioconductor-uri "Biobase" version))
7843 "1gx41083dqlm59vwqdxvc4ny31x91j48mda9n3scg0f2zwasvqgl"))))
7845 `((upstream-name . "Biobase")))
7846 (build-system r-build-system)
7848 `(("r-biocgenerics" ,r-biocgenerics)))
7849 (home-page "https://bioconductor.org/packages/Biobase")
7850 (synopsis "Base functions for Bioconductor")
7852 "This package provides functions that are needed by many other packages
7853 on Bioconductor or which replace R functions.")
7854 (license license:artistic2.0)))
7856 (define-public r-annotationdbi
7858 (name "r-annotationdbi")
7862 (uri (bioconductor-uri "AnnotationDbi" version))
7865 "09piz1f0xpbb4amskx4ilby6lfrn27hhwk75il2c4lq6m3hr4w8s"))))
7867 `((upstream-name . "AnnotationDbi")))
7868 (build-system r-build-system)
7870 `(("r-biobase" ,r-biobase)
7871 ("r-biocgenerics" ,r-biocgenerics)
7873 ("r-iranges" ,r-iranges)
7874 ("r-rsqlite" ,r-rsqlite)
7875 ("r-s4vectors" ,r-s4vectors)))
7876 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7877 (synopsis "Annotation database interface")
7879 "This package provides user interface and database connection code for
7880 annotation data packages using SQLite data storage.")
7881 (license license:artistic2.0)))
7883 (define-public r-biomart
7889 (uri (bioconductor-uri "biomaRt" version))
7892 "0676s8aq9xj2pdrfk28kf5j69fmssn900k4vxrp11ghwjr8z24h7"))))
7894 `((upstream-name . "biomaRt")))
7895 (build-system r-build-system)
7897 `(("r-annotationdbi" ,r-annotationdbi)
7898 ("r-biocfilecache" ,r-biocfilecache)
7900 ("r-openssl" ,r-openssl)
7901 ("r-progress" ,r-progress)
7902 ("r-rappdirs" ,r-rappdirs)
7903 ("r-stringr" ,r-stringr)
7906 `(("r-knitr" ,r-knitr)))
7907 (home-page "https://bioconductor.org/packages/biomaRt")
7908 (synopsis "Interface to BioMart databases")
7910 "biomaRt provides an interface to a growing collection of databases
7911 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7912 package enables retrieval of large amounts of data in a uniform way without
7913 the need to know the underlying database schemas or write complex SQL queries.
7914 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7915 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7916 users direct access to a diverse set of data and enable a wide range of
7917 powerful online queries from gene annotation to database mining.")
7918 (license license:artistic2.0)))
7920 (define-public r-biocparallel
7922 (name "r-biocparallel")
7926 (uri (bioconductor-uri "BiocParallel" version))
7929 "0g0znb4whsvb9hpwx9xaasdi5n4vjqw8cpdyqgrdrjm91rls1h21"))))
7931 `((upstream-name . "BiocParallel")))
7932 (build-system r-build-system)
7934 `(("r-futile-logger" ,r-futile-logger)
7937 (home-page "https://bioconductor.org/packages/BiocParallel")
7938 (synopsis "Bioconductor facilities for parallel evaluation")
7940 "This package provides modified versions and novel implementation of
7941 functions for parallel evaluation, tailored to use with Bioconductor
7943 (license (list license:gpl2+ license:gpl3+))))
7945 (define-public r-biostrings
7947 (name "r-biostrings")
7951 (uri (bioconductor-uri "Biostrings" version))
7954 "0pq7g2hflx2cjlpwdj6mscw9hnxvlf5y50dxf48lbrf9r3q9kmyp"))))
7956 `((upstream-name . "Biostrings")))
7957 (build-system r-build-system)
7959 `(("r-biocgenerics" ,r-biocgenerics)
7960 ("r-iranges" ,r-iranges)
7961 ("r-s4vectors" ,r-s4vectors)
7962 ("r-xvector" ,r-xvector)))
7963 (home-page "https://bioconductor.org/packages/Biostrings")
7964 (synopsis "String objects and algorithms for biological sequences")
7966 "This package provides memory efficient string containers, string
7967 matching algorithms, and other utilities, for fast manipulation of large
7968 biological sequences or sets of sequences.")
7969 (license license:artistic2.0)))
7971 (define-public r-rsamtools
7973 (name "r-rsamtools")
7977 (uri (bioconductor-uri "Rsamtools" version))
7980 "1vj43acawqqkf9yval9fzxarpsf04fmn78m2hq4f083w1k0myhyr"))))
7982 `((upstream-name . "Rsamtools")))
7983 (build-system r-build-system)
7986 (modify-phases %standard-phases
7987 (add-after 'unpack 'use-system-zlib
7989 (substitute* "DESCRIPTION"
7990 (("zlibbioc, ") ""))
7991 (substitute* "NAMESPACE"
7992 (("import\\(zlibbioc\\)") ""))
7997 `(("r-biocgenerics" ,r-biocgenerics)
7998 ("r-biocparallel" ,r-biocparallel)
7999 ("r-biostrings" ,r-biostrings)
8000 ("r-bitops" ,r-bitops)
8001 ("r-genomeinfodb" ,r-genomeinfodb)
8002 ("r-genomicranges" ,r-genomicranges)
8003 ("r-iranges" ,r-iranges)
8004 ("r-rhtslib" ,r-rhtslib)
8005 ("r-s4vectors" ,r-s4vectors)
8006 ("r-xvector" ,r-xvector)))
8007 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
8008 (synopsis "Interface to samtools, bcftools, and tabix")
8010 "This package provides an interface to the @code{samtools},
8011 @code{bcftools}, and @code{tabix} utilities for manipulating SAM (Sequence
8012 Alignment / Map), FASTA, binary variant call (BCF) and compressed indexed
8013 tab-delimited (tabix) files.")
8014 (license license:expat)))
8016 (define-public r-delayedarray
8018 (name "r-delayedarray")
8022 (uri (bioconductor-uri "DelayedArray" version))
8025 "02i88ll2d7r83nk0wdj28akvsz3jq19g6ixpaahfy3jy5av4byv6"))))
8027 `((upstream-name . "DelayedArray")))
8028 (build-system r-build-system)
8030 `(("r-biocgenerics" ,r-biocgenerics)
8031 ("r-biocparallel" ,r-biocparallel)
8032 ("r-s4vectors" ,r-s4vectors)
8033 ("r-iranges" ,r-iranges)
8034 ("r-matrix" ,r-matrix)
8035 ("r-matrixstats" ,r-matrixstats)))
8037 `(("r-knitr" ,r-knitr)))
8038 (home-page "https://bioconductor.org/packages/DelayedArray")
8039 (synopsis "Delayed operations on array-like objects")
8041 "Wrapping an array-like object (typically an on-disk object) in a
8042 @code{DelayedArray} object allows one to perform common array operations on it
8043 without loading the object in memory. In order to reduce memory usage and
8044 optimize performance, operations on the object are either delayed or executed
8045 using a block processing mechanism. Note that this also works on in-memory
8046 array-like objects like @code{DataFrame} objects (typically with Rle columns),
8047 @code{Matrix} objects, and ordinary arrays and data frames.")
8048 (license license:artistic2.0)))
8050 (define-public r-summarizedexperiment
8052 (name "r-summarizedexperiment")
8056 (uri (bioconductor-uri "SummarizedExperiment" version))
8059 "1z9bdk49dajafkfvv99nv6zyn6v70iyyy2jgdp5w5z8174a2bnn1"))))
8061 `((upstream-name . "SummarizedExperiment")))
8062 (build-system r-build-system)
8064 `(("r-biobase" ,r-biobase)
8065 ("r-biocgenerics" ,r-biocgenerics)
8066 ("r-delayedarray" ,r-delayedarray)
8067 ("r-genomeinfodb" ,r-genomeinfodb)
8068 ("r-genomicranges" ,r-genomicranges)
8069 ("r-iranges" ,r-iranges)
8070 ("r-matrix" ,r-matrix)
8071 ("r-s4vectors" ,r-s4vectors)))
8072 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
8073 (synopsis "Container for representing genomic ranges by sample")
8075 "The SummarizedExperiment container contains one or more assays, each
8076 represented by a matrix-like object of numeric or other mode. The rows
8077 typically represent genomic ranges of interest and the columns represent
8079 (license license:artistic2.0)))
8081 (define-public r-genomicalignments
8083 (name "r-genomicalignments")
8087 (uri (bioconductor-uri "GenomicAlignments" version))
8090 "065xvy4pkda0ajvl1b75iski95k1pnbhxwdq7vkfl8v55915vqh6"))))
8092 `((upstream-name . "GenomicAlignments")))
8093 (build-system r-build-system)
8095 `(("r-biocgenerics" ,r-biocgenerics)
8096 ("r-biocparallel" ,r-biocparallel)
8097 ("r-biostrings" ,r-biostrings)
8098 ("r-genomeinfodb" ,r-genomeinfodb)
8099 ("r-genomicranges" ,r-genomicranges)
8100 ("r-iranges" ,r-iranges)
8101 ("r-rsamtools" ,r-rsamtools)
8102 ("r-s4vectors" ,r-s4vectors)
8103 ("r-summarizedexperiment" ,r-summarizedexperiment)))
8104 (home-page "https://bioconductor.org/packages/GenomicAlignments")
8105 (synopsis "Representation and manipulation of short genomic alignments")
8107 "This package provides efficient containers for storing and manipulating
8108 short genomic alignments (typically obtained by aligning short reads to a
8109 reference genome). This includes read counting, computing the coverage,
8110 junction detection, and working with the nucleotide content of the
8112 (license license:artistic2.0)))
8114 (define-public r-rtracklayer
8116 (name "r-rtracklayer")
8120 (uri (bioconductor-uri "rtracklayer" version))
8123 "0lp9xsm8kqrgpwgwj7qaqcv1z6qynbz084grlpwp94zsp2ppf0n6"))))
8124 (build-system r-build-system)
8127 (modify-phases %standard-phases
8128 (add-after 'unpack 'use-system-zlib
8130 (substitute* "DESCRIPTION"
8131 ((" zlibbioc,") ""))
8132 (substitute* "NAMESPACE"
8133 (("import\\(zlibbioc\\)") ""))
8136 `(("pkg-config" ,pkg-config)))
8140 `(("r-biocgenerics" ,r-biocgenerics)
8141 ("r-biostrings" ,r-biostrings)
8142 ("r-genomeinfodb" ,r-genomeinfodb)
8143 ("r-genomicalignments" ,r-genomicalignments)
8144 ("r-genomicranges" ,r-genomicranges)
8145 ("r-iranges" ,r-iranges)
8146 ("r-rcurl" ,r-rcurl)
8147 ("r-rsamtools" ,r-rsamtools)
8148 ("r-s4vectors" ,r-s4vectors)
8150 ("r-xvector" ,r-xvector)))
8151 (home-page "https://bioconductor.org/packages/rtracklayer")
8152 (synopsis "R interface to genome browsers and their annotation tracks")
8154 "rtracklayer is an extensible framework for interacting with multiple
8155 genome browsers (currently UCSC built-in) and manipulating annotation tracks
8156 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
8157 built-in). The user may export/import tracks to/from the supported browsers,
8158 as well as query and modify the browser state, such as the current viewport.")
8159 (license license:artistic2.0)))
8161 (define-public r-genomicfeatures
8163 (name "r-genomicfeatures")
8167 (uri (bioconductor-uri "GenomicFeatures" version))
8170 "0dd226kgks50jdx5w35f3wmg95hy8aibi4kcn8p5kmqp5i8j580b"))))
8172 `((upstream-name . "GenomicFeatures")))
8173 (build-system r-build-system)
8175 `(("r-annotationdbi" ,r-annotationdbi)
8176 ("r-biobase" ,r-biobase)
8177 ("r-biocgenerics" ,r-biocgenerics)
8178 ("r-biomart" ,r-biomart)
8179 ("r-biostrings" ,r-biostrings)
8181 ("r-genomeinfodb" ,r-genomeinfodb)
8182 ("r-genomicranges" ,r-genomicranges)
8183 ("r-iranges" ,r-iranges)
8184 ("r-rcurl" ,r-rcurl)
8185 ("r-rsqlite" ,r-rsqlite)
8186 ("r-rtracklayer" ,r-rtracklayer)
8187 ("r-s4vectors" ,r-s4vectors)
8188 ("r-xvector" ,r-xvector)))
8189 (home-page "https://bioconductor.org/packages/GenomicFeatures")
8190 (synopsis "Tools for working with transcript centric annotations")
8192 "This package provides a set of tools and methods for making and
8193 manipulating transcript centric annotations. With these tools the user can
8194 easily download the genomic locations of the transcripts, exons and cds of a
8195 given organism, from either the UCSC Genome Browser or a BioMart
8196 database (more sources will be supported in the future). This information is
8197 then stored in a local database that keeps track of the relationship between
8198 transcripts, exons, cds and genes. Flexible methods are provided for
8199 extracting the desired features in a convenient format.")
8200 (license license:artistic2.0)))
8202 (define-public r-go-db
8208 (uri (string-append "https://www.bioconductor.org/packages/"
8209 "release/data/annotation/src/contrib/GO.db_"
8213 "0i3wcf5h3n0dawzc1hy0kv74f06j80c47n4p3g3fmrcxlhi3jpa5"))))
8215 `((upstream-name . "GO.db")))
8216 (build-system r-build-system)
8218 `(("r-annotationdbi" ,r-annotationdbi)))
8219 (home-page "https://bioconductor.org/packages/GO.db")
8220 (synopsis "Annotation maps describing the entire Gene Ontology")
8222 "The purpose of this GO.db annotation package is to provide detailed
8223 information about the latest version of the Gene Ontologies.")
8224 (license license:artistic2.0)))
8226 (define-public r-topgo
8232 (uri (bioconductor-uri "topGO" version))
8235 "1kw9m2j67895k58lx9msc248pjwblp8clxwgsl01cql7sgi1xzlf"))))
8237 `((upstream-name . "topGO")))
8238 (build-system r-build-system)
8240 `(("r-annotationdbi" ,r-annotationdbi)
8242 ("r-biobase" ,r-biobase)
8243 ("r-biocgenerics" ,r-biocgenerics)
8244 ("r-go-db" ,r-go-db)
8245 ("r-graph" ,r-graph)
8246 ("r-lattice" ,r-lattice)
8247 ("r-matrixstats" ,r-matrixstats)
8248 ("r-sparsem" ,r-sparsem)))
8249 (home-page "https://bioconductor.org/packages/topGO")
8250 (synopsis "Enrichment analysis for gene ontology")
8252 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
8253 terms while accounting for the topology of the GO graph. Different test
8254 statistics and different methods for eliminating local similarities and
8255 dependencies between GO terms can be implemented and applied.")
8256 ;; Any version of the LGPL applies.
8257 (license license:lgpl2.1+)))
8259 (define-public r-bsgenome
8265 (uri (bioconductor-uri "BSgenome" version))
8268 "0nn1b3h4hmnx5whf2cmzmyxdrcf4myj8c38rwr0sw4rc07xfzndy"))))
8270 `((upstream-name . "BSgenome")))
8271 (build-system r-build-system)
8273 `(("r-biocgenerics" ,r-biocgenerics)
8274 ("r-biostrings" ,r-biostrings)
8275 ("r-genomeinfodb" ,r-genomeinfodb)
8276 ("r-genomicranges" ,r-genomicranges)
8277 ("r-iranges" ,r-iranges)
8278 ("r-rsamtools" ,r-rsamtools)
8279 ("r-rtracklayer" ,r-rtracklayer)
8280 ("r-s4vectors" ,r-s4vectors)
8281 ("r-xvector" ,r-xvector)))
8282 (home-page "https://bioconductor.org/packages/BSgenome")
8283 (synopsis "Infrastructure for Biostrings-based genome data packages")
8285 "This package provides infrastructure shared by all Biostrings-based
8286 genome data packages and support for efficient SNP representation.")
8287 (license license:artistic2.0)))
8289 (define-public r-impute
8295 (uri (bioconductor-uri "impute" version))
8298 "0igz1phjd1j9bg9z4kyy7j8v9bxi9sdwz4df26r51i2vavlbrf4q"))))
8300 `(("gfortran" ,gfortran)))
8301 (build-system r-build-system)
8302 (home-page "https://bioconductor.org/packages/impute")
8303 (synopsis "Imputation for microarray data")
8305 "This package provides a function to impute missing gene expression
8306 microarray data, using nearest neighbor averaging.")
8307 (license license:gpl2+)))
8309 (define-public r-seqpattern
8311 (name "r-seqpattern")
8315 (uri (bioconductor-uri "seqPattern" version))
8318 "1gxrq6s2hiyac69idh5r1nbr1s69n0hg4ap2skm4g6857av9pwqf"))))
8320 `((upstream-name . "seqPattern")))
8321 (build-system r-build-system)
8323 `(("r-biostrings" ,r-biostrings)
8324 ("r-genomicranges" ,r-genomicranges)
8325 ("r-iranges" ,r-iranges)
8326 ("r-kernsmooth" ,r-kernsmooth)
8327 ("r-plotrix" ,r-plotrix)))
8328 (home-page "https://bioconductor.org/packages/seqPattern")
8329 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
8331 "This package provides tools to visualize oligonucleotide patterns and
8332 sequence motif occurrences across a large set of sequences centred at a common
8333 reference point and sorted by a user defined feature.")
8334 (license license:gpl3+)))
8336 (define-public r-genomation
8338 (name "r-genomation")
8342 (uri (bioconductor-uri "genomation" version))
8345 "1sba928h23b67gr3i4yj1bg655g24l3bcgsf5gvymzrv5idrss1l"))))
8346 (build-system r-build-system)
8348 `(("r-biostrings" ,r-biostrings)
8349 ("r-bsgenome" ,r-bsgenome)
8350 ("r-data-table" ,r-data-table)
8351 ("r-genomeinfodb" ,r-genomeinfodb)
8352 ("r-genomicalignments" ,r-genomicalignments)
8353 ("r-genomicranges" ,r-genomicranges)
8354 ("r-ggplot2" ,r-ggplot2)
8355 ("r-gridbase" ,r-gridbase)
8356 ("r-impute" ,r-impute)
8357 ("r-iranges" ,r-iranges)
8358 ("r-matrixstats" ,r-matrixstats)
8359 ("r-plotrix" ,r-plotrix)
8362 ("r-readr" ,r-readr)
8363 ("r-reshape2" ,r-reshape2)
8364 ("r-rsamtools" ,r-rsamtools)
8365 ("r-rtracklayer" ,r-rtracklayer)
8366 ("r-runit" ,r-runit)
8367 ("r-s4vectors" ,r-s4vectors)
8368 ("r-seqpattern" ,r-seqpattern)))
8369 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8370 (synopsis "Summary, annotation and visualization of genomic data")
8372 "This package provides a package for summary and annotation of genomic
8373 intervals. Users can visualize and quantify genomic intervals over
8374 pre-defined functional regions, such as promoters, exons, introns, etc. The
8375 genomic intervals represent regions with a defined chromosome position, which
8376 may be associated with a score, such as aligned reads from HT-seq experiments,
8377 TF binding sites, methylation scores, etc. The package can use any tabular
8378 genomic feature data as long as it has minimal information on the locations of
8379 genomic intervals. In addition, it can use BAM or BigWig files as input.")
8380 (license license:artistic2.0)))
8382 (define-public r-genomationdata
8384 (name "r-genomationdata")
8388 ;; We cannot use bioconductor-uri here because this tarball is
8389 ;; located under "data/annotation/" instead of "bioc/".
8390 (uri (string-append "https://bioconductor.org/packages/"
8391 "release/data/experiment/src/contrib/"
8392 "genomationData_" version ".tar.gz"))
8395 "10xyb8akjrhmak2i0mnv1agny2ipy364q9nlibyplpzc7vdb6bw7"))))
8396 (build-system r-build-system)
8397 ;; As this package provides little more than large data files, it doesn't
8398 ;; make sense to build substitutes.
8399 (arguments `(#:substitutable? #f))
8401 `(("r-knitr" ,r-knitr)))
8402 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8403 (synopsis "Experimental data for use with the genomation package")
8405 "This package contains experimental genetic data for use with the
8406 genomation package. Included are Chip Seq, Methylation and Cage data,
8407 downloaded from Encode.")
8408 (license license:gpl3+)))
8410 (define-public r-seqlogo
8417 (uri (bioconductor-uri "seqLogo" version))
8420 "0s94aahp8ma1crmp83dz65ifjwrx6wqi3q6005lmbp8yk2x1rkj4"))))
8421 (properties `((upstream-name . "seqLogo")))
8422 (build-system r-build-system)
8423 (home-page "https://bioconductor.org/packages/seqLogo")
8424 (synopsis "Sequence logos for DNA sequence alignments")
8426 "seqLogo takes the position weight matrix of a DNA sequence motif and
8427 plots the corresponding sequence logo as introduced by Schneider and
8429 (license license:lgpl2.0+)))
8431 (define-public r-motifrg
8438 (uri (bioconductor-uri "motifRG" version))
8441 "0s6wdr036lra9x93r9k8wvicbkgzypjh3jp46h92yacw8d829k0d"))))
8442 (properties `((upstream-name . "motifRG")))
8443 (build-system r-build-system)
8445 `(("r-biostrings" ,r-biostrings)
8446 ("r-bsgenome" ,r-bsgenome)
8447 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8448 ("r-iranges" ,r-iranges)
8449 ("r-seqlogo" ,r-seqlogo)
8450 ("r-xvector" ,r-xvector)))
8451 (home-page "https://bioconductor.org/packages/motifRG")
8452 (synopsis "Discover motifs in high throughput sequencing data")
8454 "This package provides tools for discriminative motif discovery in high
8455 throughput genetic sequencing data sets using regression methods.")
8456 (license license:artistic2.0)))
8458 (define-public r-qtl
8465 (uri (string-append "mirror://cran/src/contrib/qtl_"
8469 "0rbwcnvyy96gq1dsgpxx03pv423qya26h6ws5y0blj3blfdmj83a"))))
8470 (build-system r-build-system)
8471 (home-page "https://rqtl.org/")
8472 (synopsis "R package for analyzing QTL experiments in genetics")
8473 (description "R/qtl is an extension library for the R statistics
8474 system. It is used to analyze experimental crosses for identifying
8475 genes contributing to variation in quantitative traits (so-called
8476 quantitative trait loci, QTLs).
8478 Using a hidden Markov model, R/qtl estimates genetic maps, to
8479 identify genotyping errors, and to perform single-QTL and two-QTL,
8480 two-dimensional genome scans.")
8481 (license license:gpl3)))
8483 (define-public r-qtl2
8489 ;; Not yet available in cran.
8491 (url "https://github.com/rqtl/qtl2.git")
8493 (file-name (git-file-name name version))
8495 (base32 "0l1asr28q25jzbwrbg5490962sg3y4sjrd0qf09p78ws1aq8vfs0"))))
8496 (build-system r-build-system)
8498 `(("r-data-table" ,r-data-table)
8499 ("r-jsonlite" ,r-jsonlite)
8501 ("r-rcppeigen" ,r-rcppeigen)
8502 ("r-rsqlite" ,r-rsqlite)
8503 ("r-yaml" ,r-yaml)))
8504 (home-page "https://kbroman.org/qtl2/")
8506 "QTL analysis software for high-dimensional data and complex cross designs")
8508 "R/qtl2 (aka qtl2) is a reimplementation of the QTL analysis software
8509 R/qtl, to better handle high-dimensional data and complex cross designs.")
8510 (license license:gpl3)))
8512 (define-public r-zlibbioc
8518 (uri (bioconductor-uri "zlibbioc" version))
8521 "1xh7qan0w62mzsmanbx9vcj6ygdfhzw1abaxijkq7f4nh5w87idj"))))
8523 `((upstream-name . "zlibbioc")))
8524 (build-system r-build-system)
8525 (home-page "https://bioconductor.org/packages/zlibbioc")
8526 (synopsis "Provider for zlib-1.2.5 to R packages")
8527 (description "This package uses the source code of zlib-1.2.5 to create
8528 libraries for systems that do not have these available via other means.")
8529 (license license:artistic2.0)))
8531 (define-public r-r4rna
8538 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8542 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8543 (build-system r-build-system)
8545 `(("r-optparse" ,r-optparse)
8546 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8547 (home-page "https://www.e-rna.org/r-chie/index.cgi")
8548 (synopsis "Analysis framework for RNA secondary structure")
8550 "The R4RNA package aims to be a general framework for the analysis of RNA
8551 secondary structure and comparative analysis in R.")
8552 (license license:gpl3+)))
8554 (define-public r-rhtslib
8561 (uri (bioconductor-uri "Rhtslib" version))
8564 "0gkbrmrcg55c9s5166ifljlx0v25rv4ijdyp4wf4c292xd6chy2l"))))
8565 (properties `((upstream-name . "Rhtslib")))
8566 (build-system r-build-system)
8567 ;; Without this a temporary directory ends up in the Rhtslib.so binary,
8568 ;; which makes R abort the build.
8569 (arguments '(#:configure-flags '("--no-staged-install")))
8572 ("r-zlibbioc" ,r-zlibbioc)))
8576 `(("pkg-config" ,pkg-config)))
8577 (home-page "https://github.com/nhayden/Rhtslib")
8578 (synopsis "High-throughput sequencing library as an R package")
8580 "This package provides the HTSlib C library for high-throughput
8581 nucleotide sequence analysis. The package is primarily useful to developers
8582 of other R packages who wish to make use of HTSlib.")
8583 (license license:lgpl2.0+)))
8585 (define-public r-bamsignals
8587 (name "r-bamsignals")
8592 (uri (bioconductor-uri "bamsignals" version))
8595 "0699b0pqbs0dvs91yjibcjc90lxj9mg8rcml4a6wchfr9md7n74w"))))
8596 (build-system r-build-system)
8598 `(("r-biocgenerics" ,r-biocgenerics)
8599 ("r-genomicranges" ,r-genomicranges)
8600 ("r-iranges" ,r-iranges)
8602 ("r-rhtslib" ,r-rhtslib)
8603 ("r-zlibbioc" ,r-zlibbioc)))
8606 (home-page "https://bioconductor.org/packages/bamsignals")
8607 (synopsis "Extract read count signals from bam files")
8609 "This package efficiently obtains count vectors from indexed bam
8610 files. It counts the number of nucleotide sequence reads in given genomic
8611 ranges and it computes reads profiles and coverage profiles. It also handles
8613 (license license:gpl2+)))
8615 (define-public r-rcas
8621 (uri (bioconductor-uri "RCAS" version))
8624 "1s3gvvxi1029d1vfwnjh21nnw3mlx08kcwz63891hml9y850cvsn"))))
8625 (properties `((upstream-name . "RCAS")))
8626 (build-system r-build-system)
8628 `(("r-annotationdbi" ,r-annotationdbi)
8629 ("r-biocgenerics" ,r-biocgenerics)
8630 ("r-biomart" ,r-biomart)
8631 ("r-biostrings" ,r-biostrings)
8632 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8633 ("r-cowplot" ,r-cowplot)
8634 ("r-data-table" ,r-data-table)
8637 ("r-genomation" ,r-genomation)
8638 ("r-genomeinfodb" ,r-genomeinfodb)
8639 ("r-genomicfeatures" ,r-genomicfeatures)
8640 ("r-genomicranges" ,r-genomicranges)
8641 ("r-ggplot2" ,r-ggplot2)
8642 ("r-ggseqlogo" ,r-ggseqlogo)
8643 ("r-knitr" ,r-knitr)
8644 ("r-motifrg" ,r-motifrg)
8645 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8646 ("r-pbapply" ,r-pbapply)
8647 ("r-pheatmap" ,r-pheatmap)
8648 ("r-plotly" ,r-plotly)
8649 ("r-plotrix" ,r-plotrix)
8650 ("r-proxy" ,r-proxy)
8651 ("r-rsqlite" ,r-rsqlite)
8652 ("r-rtracklayer" ,r-rtracklayer)
8653 ("r-rmarkdown" ,r-rmarkdown)
8654 ("r-s4vectors" ,r-s4vectors)
8655 ("r-topgo" ,r-topgo)
8656 ("pandoc" ,ghc-pandoc)))
8657 (synopsis "RNA-centric annotation system")
8659 "RCAS aims to be a standalone RNA-centric annotation system that provides
8660 intuitive reports and publication-ready graphics. This package provides the R
8661 library implementing most of the pipeline's features.")
8662 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8663 (license license:artistic2.0)))
8665 (define-public rcas-web
8672 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8673 "releases/download/v" version
8674 "/rcas-web-" version ".tar.gz"))
8677 "0wq951aj45gqki1bickg876i993lmawkp8x24agg264br5x716db"))))
8678 (build-system gnu-build-system)
8681 (modify-phases %standard-phases
8682 (add-before 'configure 'find-RCAS
8683 ;; The configure script can't find non-1.3.x versions of RCAS because
8684 ;; its R expression ‘1.10.1 >= 1.3.4’ evaluates to false.
8686 (substitute* "configure"
8687 (("1\\.3\\.4") "0.0.0"))
8689 (add-after 'install 'wrap-executable
8690 (lambda* (#:key inputs outputs #:allow-other-keys)
8691 (let* ((out (assoc-ref outputs "out"))
8692 (json (assoc-ref inputs "guile-json"))
8693 (redis (assoc-ref inputs "guile-redis"))
8694 (path (string-append
8695 json "/share/guile/site/2.2:"
8696 redis "/share/guile/site/2.2")))
8697 (wrap-program (string-append out "/bin/rcas-web")
8698 `("GUILE_LOAD_PATH" ":" = (,path))
8699 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8700 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8703 `(("r-minimal" ,r-minimal)
8705 ("guile-next" ,guile-2.2)
8706 ("guile-json" ,guile-json-1)
8707 ("guile-redis" ,guile-redis)))
8709 `(("pkg-config" ,pkg-config)))
8710 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8711 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8712 (description "This package provides a simple web interface for the
8713 @dfn{RNA-centric annotation system} (RCAS).")
8714 (license license:agpl3+)))
8716 (define-public r-mutationalpatterns
8718 (name "r-mutationalpatterns")
8723 (uri (bioconductor-uri "MutationalPatterns" version))
8726 "08715l6swrlccviw7932v5hyrd2x4c6049vy9qnxk0lw3sp1zvsf"))))
8727 (build-system r-build-system)
8729 `(("r-biocgenerics" ,r-biocgenerics)
8730 ("r-biostrings" ,r-biostrings)
8731 ;; These two packages are suggested packages
8732 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8733 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8734 ("r-genomicranges" ,r-genomicranges)
8735 ("r-genomeinfodb" ,r-genomeinfodb)
8736 ("r-ggplot2" ,r-ggplot2)
8737 ("r-iranges" ,r-iranges)
8740 ("r-pracma" ,r-pracma)
8741 ("r-reshape2" ,r-reshape2)
8742 ("r-cowplot" ,r-cowplot)
8743 ("r-ggdendro" ,r-ggdendro)
8744 ("r-s4vectors" ,r-s4vectors)
8745 ("r-summarizedexperiment" ,r-summarizedexperiment)
8746 ("r-variantannotation" ,r-variantannotation)))
8747 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8748 (synopsis "Extract and visualize mutational patterns in genomic data")
8749 (description "This package provides an extensive toolset for the
8750 characterization and visualization of a wide range of mutational patterns
8751 in SNV base substitution data.")
8752 (license license:expat)))
8754 (define-public r-chipkernels
8755 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8758 (name "r-chipkernels")
8759 (version (string-append "1.1-" revision "." (string-take commit 9)))
8764 (url "https://github.com/ManuSetty/ChIPKernels.git")
8766 (file-name (string-append name "-" version))
8769 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8770 (build-system r-build-system)
8772 `(("r-iranges" ,r-iranges)
8773 ("r-xvector" ,r-xvector)
8774 ("r-biostrings" ,r-biostrings)
8775 ("r-bsgenome" ,r-bsgenome)
8776 ("r-gtools" ,r-gtools)
8777 ("r-genomicranges" ,r-genomicranges)
8778 ("r-sfsmisc" ,r-sfsmisc)
8779 ("r-kernlab" ,r-kernlab)
8780 ("r-s4vectors" ,r-s4vectors)
8781 ("r-biocgenerics" ,r-biocgenerics)))
8782 (home-page "https://github.com/ManuSetty/ChIPKernels")
8783 (synopsis "Build string kernels for DNA Sequence analysis")
8784 (description "ChIPKernels is an R package for building different string
8785 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8786 must be built and this dictionary can be used for determining kernels for DNA
8788 (license license:gpl2+))))
8790 (define-public r-seqgl
8798 (url "https://github.com/ManuSetty/SeqGL.git")
8800 (file-name (git-file-name name version))
8803 "1r6ywvhxl3ffv48lgj7sbd582mcc6dha3ksgc2qjlvjrnkbj3799"))))
8804 (build-system r-build-system)
8806 `(("r-biostrings" ,r-biostrings)
8807 ("r-chipkernels" ,r-chipkernels)
8808 ("r-genomicranges" ,r-genomicranges)
8809 ("r-spams" ,r-spams)
8810 ("r-wgcna" ,r-wgcna)
8811 ("r-fastcluster" ,r-fastcluster)))
8812 (home-page "https://github.com/ManuSetty/SeqGL")
8813 (synopsis "Group lasso for Dnase/ChIP-seq data")
8814 (description "SeqGL is a group lasso based algorithm to extract
8815 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8816 This package presents a method which uses group lasso to discriminate between
8817 bound and non bound genomic regions to accurately identify transcription
8818 factors bound at the specific regions.")
8819 (license license:gpl2+)))
8821 (define-public r-tximport
8827 (uri (bioconductor-uri "tximport" version))
8830 "1avy0zhgnszmg0dr9w74yq9ml10kwdrrgcni2wysrd48zzskc1n0"))))
8831 (build-system r-build-system)
8833 `(("r-knitr" ,r-knitr)))
8834 (home-page "https://bioconductor.org/packages/tximport")
8835 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8837 "This package provides tools to import transcript-level abundance,
8838 estimated counts and transcript lengths, and to summarize them into matrices
8839 for use with downstream gene-level analysis packages. Average transcript
8840 length, weighted by sample-specific transcript abundance estimates, is
8841 provided as a matrix which can be used as an offset for different expression
8842 of gene-level counts.")
8843 (license license:gpl2+)))
8845 (define-public r-rhdf5
8851 (uri (bioconductor-uri "rhdf5" version))
8854 "18pv74jj4wr1981r92ss10qkgf5g1b09dsbz3im3j70a4l5l0df0"))))
8855 (build-system r-build-system)
8857 `(("r-rhdf5lib" ,r-rhdf5lib)))
8860 (home-page "https://bioconductor.org/packages/rhdf5")
8861 (synopsis "HDF5 interface to R")
8863 "This R/Bioconductor package provides an interface between HDF5 and R.
8864 HDF5's main features are the ability to store and access very large and/or
8865 complex datasets and a wide variety of metadata on mass storage (disk) through
8866 a completely portable file format. The rhdf5 package is thus suited for the
8867 exchange of large and/or complex datasets between R and other software
8868 package, and for letting R applications work on datasets that are larger than
8869 the available RAM.")
8870 (license license:artistic2.0)))
8872 (define-public r-annotationfilter
8874 (name "r-annotationfilter")
8878 (uri (bioconductor-uri "AnnotationFilter" version))
8881 "1l9sxhlvnwn6327vgg02h11ppmqr2zr07ff8wmcng0i1jbqwa8q5"))))
8883 `((upstream-name . "AnnotationFilter")))
8884 (build-system r-build-system)
8886 `(("r-genomicranges" ,r-genomicranges)
8887 ("r-lazyeval" ,r-lazyeval)))
8888 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8889 (synopsis "Facilities for filtering Bioconductor annotation resources")
8891 "This package provides classes and other infrastructure to implement
8892 filters for manipulating Bioconductor annotation resources. The filters are
8893 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8894 (license license:artistic2.0)))
8896 (define-public emboss
8902 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8903 (version-major+minor version) ".0/"
8904 "EMBOSS-" version ".tar.gz"))
8907 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8908 (build-system gnu-build-system)
8911 (list (string-append "--with-hpdf="
8912 (assoc-ref %build-inputs "libharu")))
8914 (modify-phases %standard-phases
8915 (add-after 'unpack 'fix-checks
8917 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8918 ;; and zlib, but assume that they are all found at the same
8920 (substitute* "configure.in"
8921 (("CHECK_PNGDRIVER")
8922 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8923 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8924 AM_CONDITIONAL(AMPNG, true)"))
8926 (add-after 'fix-checks 'disable-update-check
8928 ;; At build time there is no connection to the Internet, so
8929 ;; looking for updates will not work.
8930 (substitute* "Makefile.am"
8931 (("\\$\\(bindir\\)/embossupdate") ""))
8933 (add-after 'disable-update-check 'autogen
8934 (lambda _ (invoke "autoreconf" "-vif") #t)))))
8940 ("libharu" ,libharu)
8943 `(("autoconf" ,autoconf)
8944 ("automake" ,automake)
8945 ("libtool" ,libtool)
8946 ("pkg-config" ,pkg-config)))
8947 (home-page "http://emboss.sourceforge.net")
8948 (synopsis "Molecular biology analysis suite")
8949 (description "EMBOSS is the \"European Molecular Biology Open Software
8950 Suite\". EMBOSS is an analysis package specially developed for the needs of
8951 the molecular biology (e.g. EMBnet) user community. The software
8952 automatically copes with data in a variety of formats and even allows
8953 transparent retrieval of sequence data from the web. It also provides a
8954 number of libraries for the development of software in the field of molecular
8955 biology. EMBOSS also integrates a range of currently available packages and
8956 tools for sequence analysis into a seamless whole.")
8957 (license license:gpl2+)))
8960 (let ((revision "1")
8961 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8964 ;; The version is 2.13.0 even though no release archives have been
8965 ;; published as yet.
8966 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8970 (url "https://github.com/arq5x/bits.git")
8972 (file-name (string-append name "-" version "-checkout"))
8975 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8976 (build-system gnu-build-system)
8978 `(#:tests? #f ;no tests included
8980 (modify-phases %standard-phases
8982 (add-after 'unpack 'remove-cuda
8984 (substitute* "Makefile"
8986 (("(bits_test_intersections) \\\\" _ match) match))
8989 (lambda* (#:key outputs #:allow-other-keys)
8991 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8996 (home-page "https://github.com/arq5x/bits")
8997 (synopsis "Implementation of binary interval search algorithm")
8998 (description "This package provides an implementation of the
8999 BITS (Binary Interval Search) algorithm, an approach to interval set
9000 intersection. It is especially suited for the comparison of diverse genomic
9001 datasets and the exploration of large datasets of genome
9002 intervals (e.g. genes, sequence alignments).")
9003 (license license:gpl2))))
9005 (define-public piranha
9006 ;; There is no release tarball for the latest version. The latest commit is
9007 ;; older than one year at the time of this writing.
9008 (let ((revision "1")
9009 (commit "0466d364b71117d01e4471b74c514436cc281233"))
9012 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
9016 (url "https://github.com/smithlabcode/piranha.git")
9018 (file-name (git-file-name name version))
9021 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
9022 (build-system gnu-build-system)
9024 `(#:test-target "test"
9026 (modify-phases %standard-phases
9027 (add-after 'unpack 'copy-smithlab-cpp
9028 (lambda* (#:key inputs #:allow-other-keys)
9029 (for-each (lambda (file)
9030 (install-file file "./src/smithlab_cpp/"))
9031 (find-files (assoc-ref inputs "smithlab-cpp")))
9033 (add-after 'install 'install-to-store
9034 (lambda* (#:key outputs #:allow-other-keys)
9035 (let* ((out (assoc-ref outputs "out"))
9036 (bin (string-append out "/bin")))
9037 (for-each (lambda (file)
9038 (install-file file bin))
9039 (find-files "bin" ".*")))
9042 (list (string-append "--with-bam_tools_headers="
9043 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
9044 (string-append "--with-bam_tools_library="
9045 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
9047 `(("bamtools" ,bamtools)
9048 ("samtools" ,samtools-0.1)
9051 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
9055 (url "https://github.com/smithlabcode/smithlab_cpp.git")
9057 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
9060 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
9062 `(("python" ,python-2)))
9063 (home-page "https://github.com/smithlabcode/piranha")
9064 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
9066 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
9067 RIP-seq experiments. It takes input in BED or BAM format and identifies
9068 regions of statistically significant read enrichment. Additional covariates
9069 may optionally be provided to further inform the peak-calling process.")
9070 (license license:gpl3+))))
9078 (uri (pypi-uri "PePr" version))
9081 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
9082 (build-system python-build-system)
9084 `(#:python ,python-2 ; python2 only
9085 #:tests? #f)) ; no tests included
9087 `(("python2-numpy" ,python2-numpy)
9088 ("python2-scipy" ,python2-scipy)
9089 ("python2-pysam" ,python2-pysam)))
9090 (home-page "https://github.com/shawnzhangyx/PePr")
9091 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
9093 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
9094 that is primarily designed for data with biological replicates. It uses a
9095 negative binomial distribution to model the read counts among the samples in
9096 the same group, and look for consistent differences between ChIP and control
9097 group or two ChIP groups run under different conditions.")
9098 (license license:gpl3+)))
9100 (define-public filevercmp
9101 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
9104 (version (string-append "0-1." (string-take commit 7)))
9108 (url "https://github.com/ekg/filevercmp.git")
9110 (file-name (git-file-name name commit))
9113 "1j9vxsy0y050v59h0q1d6501fcw1kjvj0d18l1xk2zyg0jzj247c"))))
9114 (build-system gnu-build-system)
9116 `(#:tests? #f ; There are no tests to run.
9118 (modify-phases %standard-phases
9119 (delete 'configure) ; There is no configure phase.
9121 (lambda* (#:key outputs #:allow-other-keys)
9122 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
9123 (install-file "filevercmp" bin)
9125 (home-page "https://github.com/ekg/filevercmp")
9126 (synopsis "This program compares version strings")
9127 (description "This program compares version strings. It intends to be a
9128 replacement for strverscmp.")
9129 (license license:gpl3+))))
9131 (define-public multiqc
9138 (uri (pypi-uri "multiqc" version))
9141 "02iihfl0w0hpnr4pa0sbd1y9qxrg3ycyhjp5lidkcrqh1lmzs3zy"))))
9142 (build-system python-build-system)
9144 `(("python-jinja2" ,python-jinja2)
9145 ("python-simplejson" ,python-simplejson)
9146 ("python-pyyaml" ,python-pyyaml)
9147 ("python-click" ,python-click)
9148 ("python-spectra" ,python-spectra)
9149 ("python-requests" ,python-requests)
9150 ("python-markdown" ,python-markdown)
9151 ("python-lzstring" ,python-lzstring)
9152 ("python-matplotlib" ,python-matplotlib)
9153 ("python-numpy" ,python-numpy)
9154 ;; MultQC checks for the presence of nose at runtime.
9155 ("python-nose" ,python-nose)))
9158 (modify-phases %standard-phases
9159 (add-after 'unpack 'relax-requirements
9161 (substitute* "setup.py"
9162 ;; MultiQC 1.5 ‘requires’ a version of python-matplotlib older
9163 ;; than the one in Guix, but should work fine with 2.2.2.
9164 ;; See <https://github.com/ewels/MultiQC/issues/725> and
9165 ;; <https://github.com/ewels/MultiQC/issues/732> for details.
9166 (("['\"]matplotlib.*?['\"]")
9169 (home-page "https://multiqc.info")
9170 (synopsis "Aggregate bioinformatics analysis reports")
9172 "MultiQC is a tool to aggregate bioinformatics results across many
9173 samples into a single report. It contains modules for a large number of
9174 common bioinformatics tools.")
9175 (license license:gpl3+)))
9177 (define-public variant-tools
9179 (name "variant-tools")
9185 (url "https://github.com/vatlab/varianttools.git")
9186 ;; There is no tag corresponding to version 3.1.2
9187 (commit "813ae4a90d25b69abc8a40f4f70441fe09015249")))
9188 (file-name (git-file-name name version))
9191 "12ibdmksj7icyqhks4xyvd61bygk4pjmxn618kp6vgk1af01y34g"))))
9192 (build-system python-build-system)
9195 ("c-blosc" ,c-blosc)
9198 ("hdf5-blosc" ,hdf5-blosc)
9199 ("python-cython" ,python-cython)
9202 `(("python-numpy" ,python-numpy)
9203 ("python-pycurl" ,python-pycurl)
9204 ("python-pyzmq" ,python-pyzmq)
9205 ("python-scipy" ,python-scipy)
9206 ("python-tables" ,python-tables)))
9207 (home-page "https://vatlab.github.io/vat-docs/")
9208 (synopsis "Analyze genetic variants from Next-Gen sequencing studies")
9210 "Variant tools is a tool for the manipulation, annotation,
9211 selection, simulation, and analysis of variants in the context of next-gen
9212 sequencing analysis. Unlike some other tools used for next-gen sequencing
9213 analysis, variant tools is project based and provides a whole set of tools to
9214 manipulate and analyze genetic variants.")
9215 (license license:gpl3+)))
9217 (define-public r-chipseq
9224 (uri (bioconductor-uri "chipseq" version))
9227 "1ln6bn08xig3j6ryak1xfkjhvpnlm2vf1czz9hlj6f02299nbs6l"))))
9228 (build-system r-build-system)
9230 `(("r-biocgenerics" ,r-biocgenerics)
9231 ("r-genomicranges" ,r-genomicranges)
9232 ("r-iranges" ,r-iranges)
9233 ("r-lattice" ,r-lattice)
9234 ("r-s4vectors" ,r-s4vectors)
9235 ("r-shortread" ,r-shortread)))
9236 (home-page "https://bioconductor.org/packages/chipseq")
9237 (synopsis "Package for analyzing ChIPseq data")
9239 "This package provides tools for processing short read data from ChIPseq
9241 (license license:artistic2.0)))
9243 (define-public r-copyhelper
9245 (name "r-copyhelper")
9250 (uri (string-append "https://bioconductor.org/packages/release/"
9251 "data/experiment/src/contrib/CopyhelpeR_"
9255 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
9256 (properties `((upstream-name . "CopyhelpeR")))
9257 (build-system r-build-system)
9258 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
9259 (synopsis "Helper files for CopywriteR")
9261 "This package contains the helper files that are required to run the
9262 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
9263 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
9264 mm10. In addition, it contains a blacklist filter to remove regions that
9265 display copy number variation. Files are stored as GRanges objects from the
9266 GenomicRanges Bioconductor package.")
9267 (license license:gpl2)))
9269 (define-public r-copywriter
9271 (name "r-copywriter")
9276 (uri (bioconductor-uri "CopywriteR" version))
9279 "0llg1zpxg7qnvja5f5w1z1xic0jdg6zc4mfn97h2sm44skxxcyl1"))))
9280 (properties `((upstream-name . "CopywriteR")))
9281 (build-system r-build-system)
9283 `(("r-biocparallel" ,r-biocparallel)
9284 ("r-chipseq" ,r-chipseq)
9285 ("r-copyhelper" ,r-copyhelper)
9286 ("r-data-table" ,r-data-table)
9287 ("r-dnacopy" ,r-dnacopy)
9288 ("r-futile-logger" ,r-futile-logger)
9289 ("r-genomeinfodb" ,r-genomeinfodb)
9290 ("r-genomicalignments" ,r-genomicalignments)
9291 ("r-genomicranges" ,r-genomicranges)
9292 ("r-gtools" ,r-gtools)
9293 ("r-iranges" ,r-iranges)
9294 ("r-matrixstats" ,r-matrixstats)
9295 ("r-rsamtools" ,r-rsamtools)
9296 ("r-s4vectors" ,r-s4vectors)))
9297 (home-page "https://github.com/PeeperLab/CopywriteR")
9298 (synopsis "Copy number information from targeted sequencing")
9300 "CopywriteR extracts DNA copy number information from targeted sequencing
9301 by utilizing off-target reads. It allows for extracting uniformly distributed
9302 copy number information, can be used without reference, and can be applied to
9303 sequencing data obtained from various techniques including chromatin
9304 immunoprecipitation and target enrichment on small gene panels. Thereby,
9305 CopywriteR constitutes a widely applicable alternative to available copy
9306 number detection tools.")
9307 (license license:gpl2)))
9309 (define-public r-methylkit
9311 (name "r-methylkit")
9315 (uri (bioconductor-uri "methylKit" version))
9318 "0klwc0sbmrxj1lxbz16pl39rxjm0pi57gjw547hlgnac1p9fspzy"))))
9319 (properties `((upstream-name . "methylKit")))
9320 (build-system r-build-system)
9322 `(("r-data-table" ,r-data-table)
9323 ("r-emdbook" ,r-emdbook)
9324 ("r-fastseg" ,r-fastseg)
9325 ("r-genomeinfodb" ,r-genomeinfodb)
9326 ("r-genomicranges" ,r-genomicranges)
9327 ("r-gtools" ,r-gtools)
9328 ("r-iranges" ,r-iranges)
9329 ("r-kernsmooth" ,r-kernsmooth)
9330 ("r-limma" ,r-limma)
9331 ("r-mclust" ,r-mclust)
9333 ("r-qvalue" ,r-qvalue)
9334 ("r-r-utils" ,r-r-utils)
9336 ("r-rhtslib" ,r-rhtslib)
9337 ("r-rsamtools" ,r-rsamtools)
9338 ("r-rtracklayer" ,r-rtracklayer)
9339 ("r-s4vectors" ,r-s4vectors)
9340 ("r-zlibbioc" ,r-zlibbioc)))
9342 `(("r-knitr" ,r-knitr))) ; for vignettes
9345 (home-page "https://github.com/al2na/methylKit")
9347 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9349 "MethylKit is an R package for DNA methylation analysis and annotation
9350 from high-throughput bisulfite sequencing. The package is designed to deal
9351 with sequencing data from @dfn{Reduced representation bisulfite
9352 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9353 genome bisulfite sequencing. It also has functions to analyze base-pair
9354 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9356 (license license:artistic2.0)))
9358 (define-public r-sva
9365 (uri (bioconductor-uri "sva" version))
9368 "1bzms6idx30s4nxl610zwa8rjxsyxb5pf3vxsdfmxg8j4pab9gh1"))))
9369 (build-system r-build-system)
9371 `(("r-genefilter" ,r-genefilter)
9373 ("r-biocparallel" ,r-biocparallel)
9374 ("r-matrixstats" ,r-matrixstats)
9375 ("r-limma" ,r-limma)))
9376 (home-page "https://bioconductor.org/packages/sva")
9377 (synopsis "Surrogate variable analysis")
9379 "This package contains functions for removing batch effects and other
9380 unwanted variation in high-throughput experiment. It also contains functions
9381 for identifying and building surrogate variables for high-dimensional data
9382 sets. Surrogate variables are covariates constructed directly from
9383 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9384 imaging data that can be used in subsequent analyses to adjust for unknown,
9385 unmodeled, or latent sources of noise.")
9386 (license license:artistic2.0)))
9388 (define-public r-seqminer
9395 (uri (cran-uri "seqminer" version))
9398 "00jzj8mwb0zaiwlifd41b26mrq9mzigj18nc29dydi0r42hxg16i"))))
9399 (build-system r-build-system)
9402 (home-page "http://seqminer.genomic.codes")
9403 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9405 "This package provides tools to integrate nucleotide sequencing
9406 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9407 ;; Any version of the GPL is acceptable
9408 (license (list license:gpl2+ license:gpl3+))))
9410 (define-public r-raremetals2
9412 (name "r-raremetals2")
9417 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9418 "b/b7/RareMETALS2_" version ".tar.gz"))
9421 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9422 (properties `((upstream-name . "RareMETALS2")))
9423 (build-system r-build-system)
9425 `(("r-seqminer" ,r-seqminer)
9426 ("r-mvtnorm" ,r-mvtnorm)
9428 ("r-compquadform" ,r-compquadform)
9429 ("r-getopt" ,r-getopt)))
9430 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9431 (synopsis "Analyze gene-level association tests for binary trait")
9433 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9434 It was designed to meta-analyze gene-level association tests for binary trait.
9435 While rareMETALS offers a near-complete solution for meta-analysis of
9436 gene-level tests for quantitative trait, it does not offer the optimal
9437 solution for binary trait. The package rareMETALS2 offers improved features
9438 for analyzing gene-level association tests in meta-analyses for binary
9440 (license license:gpl3)))
9442 (define-public r-maldiquant
9444 (name "r-maldiquant")
9449 (uri (cran-uri "MALDIquant" version))
9452 "0b7kdz3x4sdq413h1q09l1qhcvdnnwv6fqsqwllks1cd3xy34c57"))))
9453 (properties `((upstream-name . "MALDIquant")))
9454 (build-system r-build-system)
9455 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9456 (synopsis "Quantitative analysis of mass spectrometry data")
9458 "This package provides a complete analysis pipeline for matrix-assisted
9459 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9460 two-dimensional mass spectrometry data. In addition to commonly used plotting
9461 and processing methods it includes distinctive features, namely baseline
9462 subtraction methods such as morphological filters (TopHat) or the
9463 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9464 alignment using warping functions, handling of replicated measurements as well
9465 as allowing spectra with different resolutions.")
9466 (license license:gpl3+)))
9468 (define-public r-protgenerics
9470 (name "r-protgenerics")
9475 (uri (bioconductor-uri "ProtGenerics" version))
9478 "1k1ggjgx2la8b21841a4ngkp6xfxwz0czv7x960r7i1jqif8y48z"))))
9479 (properties `((upstream-name . "ProtGenerics")))
9480 (build-system r-build-system)
9481 (home-page "https://github.com/lgatto/ProtGenerics")
9482 (synopsis "S4 generic functions for proteomics infrastructure")
9484 "This package provides S4 generic functions needed by Bioconductor
9485 proteomics packages.")
9486 (license license:artistic2.0)))
9488 (define-public r-mzr
9495 (uri (bioconductor-uri "mzR" version))
9498 "1cwd7phlc5jbx6r6cznyfbdpvcin5fvsaasbbi65zn0s92a80r13"))
9499 (modules '((guix build utils)))
9502 (delete-file-recursively "src/boost")
9504 (properties `((upstream-name . "mzR")))
9505 (build-system r-build-system)
9508 (modify-phases %standard-phases
9509 (add-after 'unpack 'use-system-boost
9511 (substitute* "src/Makevars"
9512 (("\\./boost/libs.*") "")
9513 (("ARCH_OBJS=" line)
9515 "\nARCH_LIBS=-lboost_system -lboost_regex \
9516 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9519 `(;; Our default boost package won't work here, unfortunately, even with
9520 ;; mzR version 2.20.0.
9521 ("boost" ,boost-for-mysql) ; use this instead of the bundled boost sources
9524 `(("r-biobase" ,r-biobase)
9525 ("r-biocgenerics" ,r-biocgenerics)
9526 ("r-ncdf4" ,r-ncdf4)
9527 ("r-protgenerics" ,r-protgenerics)
9529 ("r-rhdf5lib" ,r-rhdf5lib)
9530 ("r-zlibbioc" ,r-zlibbioc)))
9531 (home-page "https://github.com/sneumann/mzR/")
9532 (synopsis "Parser for mass spectrometry data files")
9534 "The mzR package provides a unified API to the common file formats and
9535 parsers available for mass spectrometry data. It comes with a wrapper for the
9536 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9537 The package contains the original code written by the ISB, and a subset of the
9538 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9539 previously been used in XCMS.")
9540 (license license:artistic2.0)))
9542 (define-public r-affyio
9549 (uri (bioconductor-uri "affyio" version))
9552 "0sbkadxdlx7qzxc8z8iv90y6j9b2f62mk3i54dijjh56x3hjy3hb"))))
9553 (build-system r-build-system)
9555 `(("r-zlibbioc" ,r-zlibbioc)))
9558 (home-page "https://github.com/bmbolstad/affyio")
9559 (synopsis "Tools for parsing Affymetrix data files")
9561 "This package provides routines for parsing Affymetrix data files based
9562 upon file format information. The primary focus is on accessing the CEL and
9564 (license license:lgpl2.0+)))
9566 (define-public r-affy
9573 (uri (bioconductor-uri "affy" version))
9576 "131za66wbaz9y86gvjqcc2yd1f2ngl2b796xw726g75djhdgxgap"))))
9577 (build-system r-build-system)
9579 `(("r-affyio" ,r-affyio)
9580 ("r-biobase" ,r-biobase)
9581 ("r-biocgenerics" ,r-biocgenerics)
9582 ("r-biocmanager" ,r-biocmanager)
9583 ("r-preprocesscore" ,r-preprocesscore)
9584 ("r-zlibbioc" ,r-zlibbioc)))
9587 (home-page "https://bioconductor.org/packages/affy")
9588 (synopsis "Methods for affymetrix oligonucleotide arrays")
9590 "This package contains functions for exploratory oligonucleotide array
9592 (license license:lgpl2.0+)))
9594 (define-public r-vsn
9601 (uri (bioconductor-uri "vsn" version))
9604 "1naqzb2m0km8fzr6chf9z71sisrwviy1fdi9b3hn4i8p18b4kqzh"))))
9605 (build-system r-build-system)
9607 `(("r-affy" ,r-affy)
9608 ("r-biobase" ,r-biobase)
9609 ("r-ggplot2" ,r-ggplot2)
9610 ("r-lattice" ,r-lattice)
9611 ("r-limma" ,r-limma)))
9613 `(("r-knitr" ,r-knitr))) ; for vignettes
9614 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9615 (synopsis "Variance stabilization and calibration for microarray data")
9617 "The package implements a method for normalising microarray intensities,
9618 and works for single- and multiple-color arrays. It can also be used for data
9619 from other technologies, as long as they have similar format. The method uses
9620 a robust variant of the maximum-likelihood estimator for an
9621 additive-multiplicative error model and affine calibration. The model
9622 incorporates data calibration step (a.k.a. normalization), a model for the
9623 dependence of the variance on the mean intensity and a variance stabilizing
9624 data transformation. Differences between transformed intensities are
9625 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9626 their variance is independent of the mean, and they are usually more sensitive
9627 and specific in detecting differential transcription.")
9628 (license license:artistic2.0)))
9630 (define-public r-mzid
9637 (uri (bioconductor-uri "mzID" version))
9640 "1glcv096bn6pxlw89dlij1nzpwnjvrbxysvw2gm6qgm7rhxlaxrw"))))
9641 (properties `((upstream-name . "mzID")))
9642 (build-system r-build-system)
9644 `(("r-doparallel" ,r-doparallel)
9645 ("r-foreach" ,r-foreach)
9646 ("r-iterators" ,r-iterators)
9648 ("r-protgenerics" ,r-protgenerics)
9651 (home-page "https://bioconductor.org/packages/mzID")
9652 (synopsis "Parser for mzIdentML files")
9654 "This package provides a parser for mzIdentML files implemented using the
9655 XML package. The parser tries to be general and able to handle all types of
9656 mzIdentML files with the drawback of having less pretty output than a vendor
9658 (license license:gpl2+)))
9660 (define-public r-pcamethods
9662 (name "r-pcamethods")
9667 (uri (bioconductor-uri "pcaMethods" version))
9670 "1wir67kfjm0m9gf0ki8qmvh45n4gx2k0wfl9pd1hp4g62fbrj1pj"))))
9671 (properties `((upstream-name . "pcaMethods")))
9672 (build-system r-build-system)
9674 `(("r-biobase" ,r-biobase)
9675 ("r-biocgenerics" ,r-biocgenerics)
9677 ("r-rcpp" ,r-rcpp)))
9678 (home-page "https://github.com/hredestig/pcamethods")
9679 (synopsis "Collection of PCA methods")
9681 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9682 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9683 for missing value estimation is included for comparison. BPCA, PPCA and
9684 NipalsPCA may be used to perform PCA on incomplete data as well as for
9685 accurate missing value estimation. A set of methods for printing and plotting
9686 the results is also provided. All PCA methods make use of the same data
9687 structure (pcaRes) to provide a common interface to the PCA results.")
9688 (license license:gpl3+)))
9690 (define-public r-msnbase
9697 (uri (bioconductor-uri "MSnbase" version))
9700 "1z889xkfphqqmv31i8hh5xqyclv660ic26rfck5bjpgk3s2zzwi6"))))
9701 (properties `((upstream-name . "MSnbase")))
9702 (build-system r-build-system)
9704 `(("r-affy" ,r-affy)
9705 ("r-biobase" ,r-biobase)
9706 ("r-biocgenerics" ,r-biocgenerics)
9707 ("r-biocparallel" ,r-biocparallel)
9708 ("r-digest" ,r-digest)
9709 ("r-ggplot2" ,r-ggplot2)
9710 ("r-impute" ,r-impute)
9711 ("r-iranges" ,r-iranges)
9712 ("r-lattice" ,r-lattice)
9713 ("r-maldiquant" ,r-maldiquant)
9717 ("r-pcamethods" ,r-pcamethods)
9719 ("r-preprocesscore" ,r-preprocesscore)
9720 ("r-protgenerics" ,r-protgenerics)
9722 ("r-s4vectors" ,r-s4vectors)
9723 ("r-scales" ,r-scales)
9726 (home-page "https://github.com/lgatto/MSnbase")
9727 (synopsis "Base functions and classes for MS-based proteomics")
9729 "This package provides basic plotting, data manipulation and processing
9730 of mass spectrometry based proteomics data.")
9731 (license license:artistic2.0)))
9733 (define-public r-msnid
9740 (uri (bioconductor-uri "MSnID" version))
9743 "0m71f2y12hmwvng45kzz4r4qrgc2jbd7j9gprmw8y5laawpdaifg"))))
9744 (properties `((upstream-name . "MSnID")))
9745 (build-system r-build-system)
9747 `(("r-biobase" ,r-biobase)
9748 ("r-data-table" ,r-data-table)
9749 ("r-doparallel" ,r-doparallel)
9750 ("r-dplyr" ,r-dplyr)
9751 ("r-foreach" ,r-foreach)
9752 ("r-iterators" ,r-iterators)
9753 ("r-msnbase" ,r-msnbase)
9756 ("r-protgenerics" ,r-protgenerics)
9757 ("r-r-cache" ,r-r-cache)
9759 ("r-reshape2" ,r-reshape2)))
9760 (home-page "https://bioconductor.org/packages/MSnID")
9761 (synopsis "Utilities for LC-MSn proteomics identifications")
9763 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9764 from mzIdentML (leveraging the mzID package) or text files. After collating
9765 the search results from multiple datasets it assesses their identification
9766 quality and optimize filtering criteria to achieve the maximum number of
9767 identifications while not exceeding a specified false discovery rate. It also
9768 contains a number of utilities to explore the MS/MS results and assess missed
9769 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9770 (license license:artistic2.0)))
9772 (define-public r-seurat
9778 (uri (cran-uri "Seurat" version))
9781 "1lbq2pqhb6ih6iqawlnzdh05zff71pwbw1cpfv2sld3pd7kz0zkm"))))
9782 (properties `((upstream-name . "Seurat")))
9783 (build-system r-build-system)
9786 ("r-cluster" ,r-cluster)
9787 ("r-cowplot" ,r-cowplot)
9788 ("r-fitdistrplus" ,r-fitdistrplus)
9789 ("r-future" ,r-future)
9790 ("r-future-apply" ,r-future-apply)
9791 ("r-ggplot2" ,r-ggplot2)
9792 ("r-ggrepel" ,r-ggrepel)
9793 ("r-ggridges" ,r-ggridges)
9796 ("r-igraph" ,r-igraph)
9797 ("r-irlba" ,r-irlba)
9798 ("r-kernsmooth" ,r-kernsmooth)
9799 ("r-leiden" ,r-leiden)
9800 ("r-lmtest" ,r-lmtest)
9802 ("r-matrix" ,r-matrix)
9803 ("r-patchwork" ,r-patchwork)
9804 ("r-pbapply" ,r-pbapply)
9805 ("r-plotly" ,r-plotly)
9808 ("r-rcolorbrewer" ,r-rcolorbrewer)
9810 ("r-rcppannoy" ,r-rcppannoy)
9811 ("r-rcppeigen" ,r-rcppeigen)
9812 ("r-rcppprogress" ,r-rcppprogress)
9813 ("r-reticulate" ,r-reticulate)
9814 ("r-rlang" ,r-rlang)
9817 ("r-rtsne" ,r-rtsne)
9818 ("r-scales" ,r-scales)
9819 ("r-sctransform" ,r-sctransform)
9821 ("r-uwot" ,r-uwot)))
9822 (home-page "http://www.satijalab.org/seurat")
9823 (synopsis "Seurat is an R toolkit for single cell genomics")
9825 "This package is an R package designed for QC, analysis, and
9826 exploration of single cell RNA-seq data. It easily enables widely-used
9827 analytical techniques, including the identification of highly variable genes,
9828 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9829 algorithms; density clustering, hierarchical clustering, k-means, and the
9830 discovery of differentially expressed genes and markers.")
9831 (license license:gpl3)))
9833 (define-public r-aroma-light
9835 (name "r-aroma-light")
9840 (uri (bioconductor-uri "aroma.light" version))
9843 "0cgdg650j4dl0b45pwaw49ib97dwjazrv9sqzkygrjmcnnfxry8x"))))
9844 (properties `((upstream-name . "aroma.light")))
9845 (build-system r-build-system)
9847 `(("r-matrixstats" ,r-matrixstats)
9848 ("r-r-methodss3" ,r-r-methodss3)
9850 ("r-r-utils" ,r-r-utils)))
9851 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9852 (synopsis "Methods for normalization and visualization of microarray data")
9854 "This package provides methods for microarray analysis that take basic
9855 data types such as matrices and lists of vectors. These methods can be used
9856 standalone, be utilized in other packages, or be wrapped up in higher-level
9858 (license license:gpl2+)))
9860 (define-public r-deseq
9867 (uri (bioconductor-uri "DESeq" version))
9870 "14pys93gsl50xmq5pc7pp1g20v3ywlg0yzkkhwb3kiy8573xn9nc"))))
9871 (properties `((upstream-name . "DESeq")))
9872 (build-system r-build-system)
9874 `(("r-biobase" ,r-biobase)
9875 ("r-biocgenerics" ,r-biocgenerics)
9876 ("r-genefilter" ,r-genefilter)
9877 ("r-geneplotter" ,r-geneplotter)
9878 ("r-lattice" ,r-lattice)
9879 ("r-locfit" ,r-locfit)
9881 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9882 (home-page "https://www-huber.embl.de/users/anders/DESeq/")
9883 (synopsis "Differential gene expression analysis")
9885 "This package provides tools for estimating variance-mean dependence in
9886 count data from high-throughput genetic sequencing assays and for testing for
9887 differential expression based on a model using the negative binomial
9889 (license license:gpl3+)))
9891 (define-public r-edaseq
9898 (uri (bioconductor-uri "EDASeq" version))
9901 "19mgzbv8yxgvw86wpq401l27q55ygawlngl775yavwccz1zbhjnj"))))
9902 (properties `((upstream-name . "EDASeq")))
9903 (build-system r-build-system)
9905 `(("r-annotationdbi" ,r-annotationdbi)
9906 ("r-aroma-light" ,r-aroma-light)
9907 ("r-biobase" ,r-biobase)
9908 ("r-biocgenerics" ,r-biocgenerics)
9909 ("r-biocmanager" ,r-biocmanager)
9910 ("r-biomart" ,r-biomart)
9911 ("r-biostrings" ,r-biostrings)
9912 ("r-deseq" ,r-deseq)
9913 ("r-genomicfeatures" ,r-genomicfeatures)
9914 ("r-genomicranges" ,r-genomicranges)
9915 ("r-iranges" ,r-iranges)
9916 ("r-rsamtools" ,r-rsamtools)
9917 ("r-shortread" ,r-shortread)))
9918 (home-page "https://github.com/drisso/EDASeq")
9919 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9921 "This package provides support for numerical and graphical summaries of
9922 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9923 adjust for GC-content effect (or other gene-level effects) on read counts:
9924 loess robust local regression, global-scaling, and full-quantile
9925 normalization. Between-lane normalization procedures to adjust for
9926 distributional differences between lanes (e.g., sequencing depth):
9927 global-scaling and full-quantile normalization.")
9928 (license license:artistic2.0)))
9930 (define-public r-interactivedisplaybase
9932 (name "r-interactivedisplaybase")
9937 (uri (bioconductor-uri "interactiveDisplayBase" version))
9940 "0zwf3ma6wf4zypl6bgjp0n72k2hmp0g16gzl4v3y4157rxcbpl0n"))))
9942 `((upstream-name . "interactiveDisplayBase")))
9943 (build-system r-build-system)
9945 `(("r-biocgenerics" ,r-biocgenerics)
9946 ("r-shiny" ,r-shiny)))
9947 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9948 (synopsis "Base package for web displays of Bioconductor objects")
9950 "This package contains the basic methods needed to generate interactive
9951 Shiny-based display methods for Bioconductor objects.")
9952 (license license:artistic2.0)))
9954 (define-public r-annotationhub
9956 (name "r-annotationhub")
9961 (uri (bioconductor-uri "AnnotationHub" version))
9964 "19vj3bk8jz68q84g3j8xs1s9bqz90lbwbciig1h45zvn2zc6087m"))))
9965 (properties `((upstream-name . "AnnotationHub")))
9966 (build-system r-build-system)
9968 `(("r-annotationdbi" ,r-annotationdbi)
9969 ("r-biocfilecache" ,r-biocfilecache)
9970 ("r-biocgenerics" ,r-biocgenerics)
9971 ("r-biocmanager" ,r-biocmanager)
9972 ("r-biocversion" ,r-biocversion)
9974 ("r-dplyr" ,r-dplyr)
9976 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9977 ("r-rappdirs" ,r-rappdirs)
9978 ("r-rsqlite" ,r-rsqlite)
9979 ("r-s4vectors" ,r-s4vectors)
9980 ("r-yaml" ,r-yaml)))
9981 (home-page "https://bioconductor.org/packages/AnnotationHub")
9982 (synopsis "Client to access AnnotationHub resources")
9984 "This package provides a client for the Bioconductor AnnotationHub web
9985 resource. The AnnotationHub web resource provides a central location where
9986 genomic files (e.g. VCF, bed, wig) and other resources from standard
9987 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9988 metadata about each resource, e.g., a textual description, tags, and date of
9989 modification. The client creates and manages a local cache of files retrieved
9990 by the user, helping with quick and reproducible access.")
9991 (license license:artistic2.0)))
9993 (define-public r-fastseg
10000 (uri (bioconductor-uri "fastseg" version))
10003 "1cys6frmbizc8bf933mwvvnr31sfya9ahcc0wm66pbd1x3mygkmk"))))
10004 (build-system r-build-system)
10006 `(("r-biobase" ,r-biobase)
10007 ("r-biocgenerics" ,r-biocgenerics)
10008 ("r-genomicranges" ,r-genomicranges)
10009 ("r-iranges" ,r-iranges)
10010 ("r-s4vectors" ,r-s4vectors)))
10011 (home-page "https://www.bioinf.jku.at/software/fastseg/index.html")
10012 (synopsis "Fast segmentation algorithm for genetic sequencing data")
10014 "Fastseg implements a very fast and efficient segmentation algorithm.
10015 It can segment data from DNA microarrays and data from next generation
10016 sequencing for example to detect copy number segments. Further it can segment
10017 data from RNA microarrays like tiling arrays to identify transcripts. Most
10018 generally, it can segment data given as a matrix or as a vector. Various data
10019 formats can be used as input to fastseg like expression set objects for
10020 microarrays or GRanges for sequencing data.")
10021 (license license:lgpl2.0+)))
10023 (define-public r-keggrest
10025 (name "r-keggrest")
10030 (uri (bioconductor-uri "KEGGREST" version))
10033 "1cgjvv9n88y3ah21356mh8z2l08vjn42hjy8hcljsibknzc4v247"))))
10034 (properties `((upstream-name . "KEGGREST")))
10035 (build-system r-build-system)
10037 `(("r-biostrings" ,r-biostrings)
10040 (home-page "https://bioconductor.org/packages/KEGGREST")
10041 (synopsis "Client-side REST access to KEGG")
10043 "This package provides a package that provides a client interface to the
10044 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
10045 (license license:artistic2.0)))
10047 (define-public r-gage
10054 (uri (bioconductor-uri "gage" version))
10057 "1qxfmg0id19iy3ia8h5nrvk3d1azqb28kl7m08i23654wb6b45c6"))))
10058 (build-system r-build-system)
10060 `(("r-annotationdbi" ,r-annotationdbi)
10061 ("r-graph" ,r-graph)
10062 ("r-keggrest" ,r-keggrest)))
10063 (home-page (string-append "https://bmcbioinformatics.biomedcentral.com/"
10064 "articles/10.1186/1471-2105-10-161"))
10065 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
10067 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
10068 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
10069 data attributes including sample sizes, experimental designs, assay platforms,
10070 and other types of heterogeneity. The gage package provides functions for
10071 basic GAGE analysis, result processing and presentation. In addition, it
10072 provides demo microarray data and commonly used gene set data based on KEGG
10073 pathways and GO terms. These functions and data are also useful for gene set
10074 analysis using other methods.")
10075 (license license:gpl2+)))
10077 (define-public r-genomicfiles
10079 (name "r-genomicfiles")
10084 (uri (bioconductor-uri "GenomicFiles" version))
10087 "1x6q827ms2l5lwzha1vsgfrshh35n9f19jq57xagrqlafxgpz86s"))))
10088 (properties `((upstream-name . "GenomicFiles")))
10089 (build-system r-build-system)
10091 `(("r-biocgenerics" ,r-biocgenerics)
10092 ("r-biocparallel" ,r-biocparallel)
10093 ("r-genomeinfodb" ,r-genomeinfodb)
10094 ("r-genomicalignments" ,r-genomicalignments)
10095 ("r-genomicranges" ,r-genomicranges)
10096 ("r-iranges" ,r-iranges)
10097 ("r-rsamtools" ,r-rsamtools)
10098 ("r-rtracklayer" ,r-rtracklayer)
10099 ("r-s4vectors" ,r-s4vectors)
10100 ("r-summarizedexperiment" ,r-summarizedexperiment)
10101 ("r-variantannotation" ,r-variantannotation)))
10102 (home-page "https://bioconductor.org/packages/GenomicFiles")
10103 (synopsis "Distributed computing by file or by range")
10105 "This package provides infrastructure for parallel computations
10106 distributed by file or by range. User defined mapper and reducer functions
10107 provide added flexibility for data combination and manipulation.")
10108 (license license:artistic2.0)))
10110 (define-public r-complexheatmap
10112 (name "r-complexheatmap")
10117 (uri (bioconductor-uri "ComplexHeatmap" version))
10120 "1pj6a6rmqckk033pkklk6hr4066rzavamy6w194rfdhind90rk0p"))))
10122 `((upstream-name . "ComplexHeatmap")))
10123 (build-system r-build-system)
10125 `(("r-circlize" ,r-circlize)
10127 ("r-colorspace" ,r-colorspace)
10128 ("r-getoptlong" ,r-getoptlong)
10129 ("r-globaloptions" ,r-globaloptions)
10131 ("r-rcolorbrewer" ,r-rcolorbrewer)))
10133 "https://github.com/jokergoo/ComplexHeatmap")
10134 (synopsis "Making Complex Heatmaps")
10136 "Complex heatmaps are efficient to visualize associations between
10137 different sources of data sets and reveal potential structures. This package
10138 provides a highly flexible way to arrange multiple heatmaps and supports
10139 self-defined annotation graphics.")
10140 (license license:gpl2+)))
10142 (define-public r-dirichletmultinomial
10144 (name "r-dirichletmultinomial")
10149 (uri (bioconductor-uri "DirichletMultinomial" version))
10152 "0knmncmkkf2ypyqfcl5s8nmyyf9nrzkqprzn9w3w8182c0v49r0s"))))
10154 `((upstream-name . "DirichletMultinomial")))
10155 (build-system r-build-system)
10159 `(("r-biocgenerics" ,r-biocgenerics)
10160 ("r-iranges" ,r-iranges)
10161 ("r-s4vectors" ,r-s4vectors)))
10162 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
10163 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
10165 "Dirichlet-multinomial mixture models can be used to describe variability
10166 in microbial metagenomic data. This package is an interface to code
10167 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
10169 (license license:lgpl3)))
10171 (define-public r-ensembldb
10173 (name "r-ensembldb")
10178 (uri (bioconductor-uri "ensembldb" version))
10181 "02lnpyp85zchmz404hr5381zmihvq4x9zgxdrbn2afi352vg0vab"))))
10182 (build-system r-build-system)
10184 `(("r-annotationdbi" ,r-annotationdbi)
10185 ("r-annotationfilter" ,r-annotationfilter)
10186 ("r-biobase" ,r-biobase)
10187 ("r-biocgenerics" ,r-biocgenerics)
10188 ("r-biostrings" ,r-biostrings)
10191 ("r-genomeinfodb" ,r-genomeinfodb)
10192 ("r-genomicfeatures" ,r-genomicfeatures)
10193 ("r-genomicranges" ,r-genomicranges)
10194 ("r-iranges" ,r-iranges)
10195 ("r-protgenerics" ,r-protgenerics)
10196 ("r-rsamtools" ,r-rsamtools)
10197 ("r-rsqlite" ,r-rsqlite)
10198 ("r-rtracklayer" ,r-rtracklayer)
10199 ("r-s4vectors" ,r-s4vectors)))
10200 (home-page "https://github.com/jotsetung/ensembldb")
10201 (synopsis "Utilities to create and use Ensembl-based annotation databases")
10203 "The package provides functions to create and use transcript-centric
10204 annotation databases/packages. The annotation for the databases are directly
10205 fetched from Ensembl using their Perl API. The functionality and data is
10206 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
10207 but, in addition to retrieve all gene/transcript models and annotations from
10208 the database, the @code{ensembldb} package also provides a filter framework
10209 allowing to retrieve annotations for specific entries like genes encoded on a
10210 chromosome region or transcript models of lincRNA genes.")
10211 ;; No version specified
10212 (license license:lgpl3+)))
10214 (define-public r-organismdbi
10216 (name "r-organismdbi")
10221 (uri (bioconductor-uri "OrganismDbi" version))
10224 "1bvfyh733mhka9zd00hrzpalgjs255c2blnxyf60ipzk5jg7yllb"))))
10225 (properties `((upstream-name . "OrganismDbi")))
10226 (build-system r-build-system)
10228 `(("r-annotationdbi" ,r-annotationdbi)
10229 ("r-biobase" ,r-biobase)
10230 ("r-biocgenerics" ,r-biocgenerics)
10231 ("r-biocmanager" ,r-biocmanager)
10233 ("r-genomicfeatures" ,r-genomicfeatures)
10234 ("r-genomicranges" ,r-genomicranges)
10235 ("r-graph" ,r-graph)
10236 ("r-iranges" ,r-iranges)
10238 ("r-s4vectors" ,r-s4vectors)))
10239 (home-page "https://bioconductor.org/packages/OrganismDbi")
10240 (synopsis "Software to enable the smooth interfacing of database packages")
10241 (description "The package enables a simple unified interface to several
10242 annotation packages each of which has its own schema by taking advantage of
10243 the fact that each of these packages implements a select methods.")
10244 (license license:artistic2.0)))
10246 (define-public r-biovizbase
10248 (name "r-biovizbase")
10253 (uri (bioconductor-uri "biovizBase" version))
10256 "04vvj907bgs67w8rb7n1haf80p6cd0qj5fdxw0dwryb455y35vir"))))
10257 (properties `((upstream-name . "biovizBase")))
10258 (build-system r-build-system)
10260 `(("r-annotationdbi" ,r-annotationdbi)
10261 ("r-annotationfilter" ,r-annotationfilter)
10262 ("r-biocgenerics" ,r-biocgenerics)
10263 ("r-biostrings" ,r-biostrings)
10264 ("r-dichromat" ,r-dichromat)
10265 ("r-ensembldb" ,r-ensembldb)
10266 ("r-genomeinfodb" ,r-genomeinfodb)
10267 ("r-genomicalignments" ,r-genomicalignments)
10268 ("r-genomicfeatures" ,r-genomicfeatures)
10269 ("r-genomicranges" ,r-genomicranges)
10270 ("r-hmisc" ,r-hmisc)
10271 ("r-iranges" ,r-iranges)
10272 ("r-rcolorbrewer" ,r-rcolorbrewer)
10273 ("r-rlang" ,r-rlang)
10274 ("r-rsamtools" ,r-rsamtools)
10275 ("r-s4vectors" ,r-s4vectors)
10276 ("r-scales" ,r-scales)
10277 ("r-summarizedexperiment" ,r-summarizedexperiment)
10278 ("r-variantannotation" ,r-variantannotation)))
10279 (home-page "https://bioconductor.org/packages/biovizBase")
10280 (synopsis "Basic graphic utilities for visualization of genomic data")
10282 "The biovizBase package is designed to provide a set of utilities, color
10283 schemes and conventions for genomic data. It serves as the base for various
10284 high-level packages for biological data visualization. This saves development
10285 effort and encourages consistency.")
10286 (license license:artistic2.0)))
10288 (define-public r-ggbio
10295 (uri (bioconductor-uri "ggbio" version))
10298 "13wzwh40anh8l53yp19bg4w5cpxykcaf228dc8cxvjndyib711qb"))))
10299 (build-system r-build-system)
10302 (modify-phases %standard-phases
10303 ;; See https://github.com/tengfei/ggbio/issues/117
10304 ;; This fix will be included in the next release.
10305 (add-after 'unpack 'fix-typo
10307 (substitute* "R/GGbio-class.R"
10308 (("fechable") "fetchable"))
10311 `(("r-annotationdbi" ,r-annotationdbi)
10312 ("r-annotationfilter" ,r-annotationfilter)
10313 ("r-biobase" ,r-biobase)
10314 ("r-biocgenerics" ,r-biocgenerics)
10315 ("r-biostrings" ,r-biostrings)
10316 ("r-biovizbase" ,r-biovizbase)
10317 ("r-bsgenome" ,r-bsgenome)
10318 ("r-ensembldb" ,r-ensembldb)
10319 ("r-genomeinfodb" ,r-genomeinfodb)
10320 ("r-genomicalignments" ,r-genomicalignments)
10321 ("r-genomicfeatures" ,r-genomicfeatures)
10322 ("r-genomicranges" ,r-genomicranges)
10323 ("r-ggally" ,r-ggally)
10324 ("r-ggplot2" ,r-ggplot2)
10325 ("r-gridextra" ,r-gridextra)
10326 ("r-gtable" ,r-gtable)
10327 ("r-hmisc" ,r-hmisc)
10328 ("r-iranges" ,r-iranges)
10329 ("r-organismdbi" ,r-organismdbi)
10330 ("r-reshape2" ,r-reshape2)
10331 ("r-rlang" ,r-rlang)
10332 ("r-rsamtools" ,r-rsamtools)
10333 ("r-rtracklayer" ,r-rtracklayer)
10334 ("r-s4vectors" ,r-s4vectors)
10335 ("r-scales" ,r-scales)
10336 ("r-summarizedexperiment" ,r-summarizedexperiment)
10337 ("r-variantannotation" ,r-variantannotation)))
10338 (home-page "http://www.tengfei.name/ggbio/")
10339 (synopsis "Visualization tools for genomic data")
10341 "The ggbio package extends and specializes the grammar of graphics for
10342 biological data. The graphics are designed to answer common scientific
10343 questions, in particular those often asked of high throughput genomics data.
10344 All core Bioconductor data structures are supported, where appropriate. The
10345 package supports detailed views of particular genomic regions, as well as
10346 genome-wide overviews. Supported overviews include ideograms and grand linear
10347 views. High-level plots include sequence fragment length, edge-linked
10348 interval to data view, mismatch pileup, and several splicing summaries.")
10349 (license license:artistic2.0)))
10351 (define-public r-gprofiler
10353 (name "r-gprofiler")
10358 (uri (cran-uri "gProfileR" version))
10361 "1h1v0kgpsn04ald2izznh7fr2riwisj5hcgz4k7h3qc931rf0r4k"))))
10362 (properties `((upstream-name . "gProfileR")))
10363 (build-system r-build-system)
10365 `(("r-plyr" ,r-plyr)
10366 ("r-rcurl" ,r-rcurl)))
10367 (home-page "https://cran.r-project.org/web/packages/gProfileR/")
10368 (synopsis "Interface to the g:Profiler toolkit")
10370 "This package provides tools for functional enrichment analysis,
10371 gene identifier conversion and mapping homologous genes across related
10372 organisms via the @code{g:Profiler} toolkit.")
10373 (license license:gpl2+)))
10375 (define-public r-gqtlbase
10377 (name "r-gqtlbase")
10382 (uri (bioconductor-uri "gQTLBase" version))
10385 "1qr8dqjbmj1mdjbzbnxwzfrm8f02wqfsgic8ws5kv7pmsby63y4x"))))
10386 (properties `((upstream-name . "gQTLBase")))
10387 (build-system r-build-system)
10389 `(("r-batchjobs" ,r-batchjobs)
10390 ("r-bbmisc" ,r-bbmisc)
10391 ("r-biocgenerics" ,r-biocgenerics)
10393 ("r-doparallel" ,r-doparallel)
10395 ("r-ffbase" ,r-ffbase)
10396 ("r-foreach" ,r-foreach)
10397 ("r-genomicfiles" ,r-genomicfiles)
10398 ("r-genomicranges" ,r-genomicranges)
10399 ("r-rtracklayer" ,r-rtracklayer)
10400 ("r-s4vectors" ,r-s4vectors)
10401 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10402 (home-page "https://bioconductor.org/packages/gQTLBase")
10403 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10405 "The purpose of this package is to simplify the storage and interrogation
10406 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10408 (license license:artistic2.0)))
10410 (define-public r-snpstats
10412 (name "r-snpstats")
10417 (uri (bioconductor-uri "snpStats" version))
10420 "1xq1rjljg70h5mshdza56dis0iv1a20sivs6dav3w5jbdd1l5qkh"))))
10421 (properties `((upstream-name . "snpStats")))
10422 (build-system r-build-system)
10423 (inputs `(("zlib" ,zlib)))
10425 `(("r-biocgenerics" ,r-biocgenerics)
10426 ("r-matrix" ,r-matrix)
10427 ("r-survival" ,r-survival)
10428 ("r-zlibbioc" ,r-zlibbioc)))
10429 (home-page "https://bioconductor.org/packages/snpStats")
10430 (synopsis "Methods for SNP association studies")
10432 "This package provides classes and statistical methods for large
10433 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10434 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10435 (license license:gpl3)))
10437 (define-public r-homo-sapiens
10439 (name "r-homo-sapiens")
10443 ;; We cannot use bioconductor-uri here because this tarball is
10444 ;; located under "data/annotation/" instead of "bioc/".
10445 (uri (string-append "https://www.bioconductor.org/packages/"
10446 "release/data/annotation/src/contrib/"
10448 version ".tar.gz"))
10451 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10453 `((upstream-name . "Homo.sapiens")))
10454 (build-system r-build-system)
10456 `(("r-genomicfeatures" ,r-genomicfeatures)
10457 ("r-go-db" ,r-go-db)
10458 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10459 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10460 ("r-organismdbi" ,r-organismdbi)
10461 ("r-annotationdbi" ,r-annotationdbi)))
10462 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10463 (synopsis "Annotation package for the Homo.sapiens object")
10465 "This package contains the Homo.sapiens object to access data from
10466 several related annotation packages.")
10467 (license license:artistic2.0)))
10469 (define-public r-erma
10476 (uri (bioconductor-uri "erma" version))
10479 "085qsr73p8nyp435f15l4l1jkfd64bfd9gl4z496nfxdnqn95srz"))))
10480 (build-system r-build-system)
10482 `(("r-annotationdbi" ,r-annotationdbi)
10483 ("r-biobase" ,r-biobase)
10484 ("r-biocgenerics" ,r-biocgenerics)
10485 ("r-biocparallel" ,r-biocparallel)
10486 ("r-genomeinfodb" ,r-genomeinfodb)
10487 ("r-genomicfiles" ,r-genomicfiles)
10488 ("r-genomicranges" ,r-genomicranges)
10489 ("r-ggplot2" ,r-ggplot2)
10490 ("r-homo-sapiens" ,r-homo-sapiens)
10491 ("r-iranges" ,r-iranges)
10492 ("r-rtracklayer" ,r-rtracklayer)
10493 ("r-s4vectors" ,r-s4vectors)
10494 ("r-shiny" ,r-shiny)
10495 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10496 (home-page "https://bioconductor.org/packages/erma")
10497 (synopsis "Epigenomic road map adventures")
10499 "The epigenomics road map describes locations of epigenetic marks in DNA
10500 from a variety of cell types. Of interest are locations of histone
10501 modifications, sites of DNA methylation, and regions of accessible chromatin.
10502 This package presents a selection of elements of the road map including
10503 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10504 by Ernst and Kellis.")
10505 (license license:artistic2.0)))
10507 (define-public r-ldblock
10514 (uri (bioconductor-uri "ldblock" version))
10517 "0xpigfidmylfawy6vzshqnsw1lzjs4qms8q7zffij6bkvkv7920x"))))
10518 (build-system r-build-system)
10520 `(("r-biocgenerics" ,r-biocgenerics)
10521 ("r-ensdb-hsapiens-v75" ,r-ensdb-hsapiens-v75)
10522 ("r-ensembldb" ,r-ensembldb)
10523 ("r-genomeinfodb" ,r-genomeinfodb)
10524 ("r-genomicfiles" ,r-genomicfiles)
10526 ("r-matrix" ,r-matrix)
10527 ("r-rsamtools" ,r-rsamtools)
10528 ("r-snpstats" ,r-snpstats)
10529 ("r-variantannotation" ,r-variantannotation)))
10530 (home-page "https://bioconductor.org/packages/ldblock")
10531 (synopsis "Data structures for linkage disequilibrium measures in populations")
10533 "This package defines data structures for @dfn{linkage
10534 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10535 handling of existing population-level data for the purpose of flexibly
10536 defining LD blocks.")
10537 (license license:artistic2.0)))
10539 (define-public r-gqtlstats
10541 (name "r-gqtlstats")
10546 (uri (bioconductor-uri "gQTLstats" version))
10549 "1dly4p9r4231hf31xg1nzqiyvjbcfjljfmhb88ic1jxwnvniyv2f"))))
10550 (properties `((upstream-name . "gQTLstats")))
10551 (build-system r-build-system)
10553 `(("r-annotationdbi" ,r-annotationdbi)
10554 ("r-batchjobs" ,r-batchjobs)
10555 ("r-bbmisc" ,r-bbmisc)
10556 ("r-beeswarm" ,r-beeswarm)
10557 ("r-biobase" ,r-biobase)
10558 ("r-biocgenerics" ,r-biocgenerics)
10559 ("r-doparallel" ,r-doparallel)
10560 ("r-dplyr" ,r-dplyr)
10562 ("r-ffbase" ,r-ffbase)
10563 ("r-foreach" ,r-foreach)
10564 ("r-genomeinfodb" ,r-genomeinfodb)
10565 ("r-genomicfeatures" ,r-genomicfeatures)
10566 ("r-genomicfiles" ,r-genomicfiles)
10567 ("r-genomicranges" ,r-genomicranges)
10568 ("r-ggbeeswarm" ,r-ggbeeswarm)
10569 ("r-ggplot2" ,r-ggplot2)
10570 ("r-gqtlbase" ,r-gqtlbase)
10571 ("r-hardyweinberg" ,r-hardyweinberg)
10572 ("r-homo-sapiens" ,r-homo-sapiens)
10573 ("r-iranges" ,r-iranges)
10574 ("r-limma" ,r-limma)
10576 ("r-plotly" ,r-plotly)
10577 ("r-reshape2" ,r-reshape2)
10578 ("r-s4vectors" ,r-s4vectors)
10579 ("r-shiny" ,r-shiny)
10580 ("r-snpstats" ,r-snpstats)
10581 ("r-summarizedexperiment" ,r-summarizedexperiment)
10582 ("r-variantannotation" ,r-variantannotation)))
10583 (home-page "https://bioconductor.org/packages/gQTLstats")
10584 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10586 "This package provides tools for the computationally efficient analysis
10587 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10588 The software in this package aims to support refinements and functional
10589 interpretation of members of a collection of association statistics on a
10590 family of feature/genome hypotheses.")
10591 (license license:artistic2.0)))
10593 (define-public r-gviz
10600 (uri (bioconductor-uri "Gviz" version))
10603 "0c9i26h5czm60n1bxzmdxxpywcj0sig6wcj913pb41mr83bbgra3"))))
10604 (properties `((upstream-name . "Gviz")))
10605 (build-system r-build-system)
10607 `(("r-annotationdbi" ,r-annotationdbi)
10608 ("r-biobase" ,r-biobase)
10609 ("r-biocgenerics" ,r-biocgenerics)
10610 ("r-biomart" ,r-biomart)
10611 ("r-biostrings" ,r-biostrings)
10612 ("r-biovizbase" ,r-biovizbase)
10613 ("r-bsgenome" ,r-bsgenome)
10614 ("r-digest" ,r-digest)
10615 ("r-genomeinfodb" ,r-genomeinfodb)
10616 ("r-genomicalignments" ,r-genomicalignments)
10617 ("r-genomicfeatures" ,r-genomicfeatures)
10618 ("r-genomicranges" ,r-genomicranges)
10619 ("r-iranges" ,r-iranges)
10620 ("r-lattice" ,r-lattice)
10621 ("r-latticeextra" ,r-latticeextra)
10622 ("r-matrixstats" ,r-matrixstats)
10623 ("r-rcolorbrewer" ,r-rcolorbrewer)
10624 ("r-rsamtools" ,r-rsamtools)
10625 ("r-rtracklayer" ,r-rtracklayer)
10626 ("r-s4vectors" ,r-s4vectors)
10627 ("r-xvector" ,r-xvector)))
10628 (home-page "https://bioconductor.org/packages/Gviz")
10629 (synopsis "Plotting data and annotation information along genomic coordinates")
10631 "Genomic data analyses requires integrated visualization of known genomic
10632 information and new experimental data. Gviz uses the biomaRt and the
10633 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10634 and translates this to e.g. gene/transcript structures in viewports of the
10635 grid graphics package. This results in genomic information plotted together
10637 (license license:artistic2.0)))
10639 (define-public r-gwascat
10646 (uri (bioconductor-uri "gwascat" version))
10649 "038vhfsk2vs7inn5di093cmjbb81k7j0af385sg7l01jj70bdqq1"))))
10650 (build-system r-build-system)
10652 `(("r-annotationdbi" ,r-annotationdbi)
10653 ("r-biocgenerics" ,r-biocgenerics)
10654 ("r-biostrings" ,r-biostrings)
10655 ("r-genomeinfodb" ,r-genomeinfodb)
10656 ("r-genomicfeatures" ,r-genomicfeatures)
10657 ("r-genomicranges" ,r-genomicranges)
10658 ("r-homo-sapiens" ,r-homo-sapiens)
10659 ("r-iranges" ,r-iranges)
10660 ("r-rsamtools" ,r-rsamtools)
10661 ("r-rtracklayer" ,r-rtracklayer)
10662 ("r-s4vectors" ,r-s4vectors)))
10663 (home-page "https://bioconductor.org/packages/gwascat")
10664 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10666 "This package provides tools for representing and modeling data in the
10667 EMBL-EBI GWAS catalog.")
10668 (license license:artistic2.0)))
10670 (define-public r-sushi
10676 (uri (bioconductor-uri "Sushi" version))
10679 "15xng21hd09fb234ravrry3b872zg82w8x9lijxab9n96xihcpz5"))))
10680 (properties `((upstream-name . "Sushi")))
10681 (build-system r-build-system)
10683 `(("r-biomart" ,r-biomart)
10685 (home-page "https://bioconductor.org/packages/Sushi")
10686 (synopsis "Tools for visualizing genomics data")
10688 "This package provides flexible, quantitative, and integrative genomic
10689 visualizations for publication-quality multi-panel figures.")
10690 (license license:gpl2+)))
10692 (define-public r-fithic
10698 (uri (bioconductor-uri "FitHiC" version))
10701 "1irwkwi4afdj395134k31mvx7c2vpdd0rv8zrblnldascdsb04kc"))))
10702 (properties `((upstream-name . "FitHiC")))
10703 (build-system r-build-system)
10705 `(("r-data-table" ,r-data-table)
10706 ("r-fdrtool" ,r-fdrtool)
10707 ("r-rcpp" ,r-rcpp)))
10708 (home-page "https://bioconductor.org/packages/FitHiC")
10709 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10711 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10712 intra-chromosomal contact maps produced by genome-wide genome architecture
10713 assays such as Hi-C.")
10714 (license license:gpl2+)))
10716 (define-public r-hitc
10722 (uri (bioconductor-uri "HiTC" version))
10725 "0byahi0fz0dzjyklz8v9whax9ygg7gwb4pl1j3zbl6z8a9qx8pps"))))
10726 (properties `((upstream-name . "HiTC")))
10727 (build-system r-build-system)
10729 `(("r-biostrings" ,r-biostrings)
10730 ("r-genomeinfodb" ,r-genomeinfodb)
10731 ("r-genomicranges" ,r-genomicranges)
10732 ("r-iranges" ,r-iranges)
10733 ("r-matrix" ,r-matrix)
10734 ("r-rcolorbrewer" ,r-rcolorbrewer)
10735 ("r-rtracklayer" ,r-rtracklayer)))
10736 (home-page "https://bioconductor.org/packages/HiTC")
10737 (synopsis "High throughput chromosome conformation capture analysis")
10739 "The HiTC package was developed to explore high-throughput \"C\" data
10740 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10741 quality controls, normalization, visualization, and further analysis are also
10743 (license license:artistic2.0)))
10745 (define-public r-hdf5array
10747 (name "r-hdf5array")
10752 (uri (bioconductor-uri "HDF5Array" version))
10755 "0ib0grhd9zbrn0dkrm4aa7qj7h0y6z1dvyx1ab3w6vczw7xghsfb"))))
10756 (properties `((upstream-name . "HDF5Array")))
10757 (build-system r-build-system)
10761 `(("r-biocgenerics" ,r-biocgenerics)
10762 ("r-delayedarray" ,r-delayedarray)
10763 ("r-iranges" ,r-iranges)
10764 ("r-matrix" ,r-matrix)
10765 ("r-rhdf5" ,r-rhdf5)
10766 ("r-rhdf5lib" ,r-rhdf5lib)
10767 ("r-s4vectors" ,r-s4vectors)))
10768 (home-page "https://bioconductor.org/packages/HDF5Array")
10769 (synopsis "HDF5 back end for DelayedArray objects")
10770 (description "This package provides an array-like container for convenient
10771 access and manipulation of HDF5 datasets. It supports delayed operations and
10772 block processing.")
10773 (license license:artistic2.0)))
10775 (define-public r-rhdf5lib
10777 (name "r-rhdf5lib")
10782 (uri (bioconductor-uri "Rhdf5lib" version))
10785 "17lhwnm9rqsvbqkvwp0m07vjrk63a4389p2y39zffv8fgznxqzd7"))
10786 (modules '((guix build utils)))
10789 ;; Delete bundled binaries
10790 (delete-file-recursively "src/winlib/")
10792 (properties `((upstream-name . "Rhdf5lib")))
10793 (build-system r-build-system)
10796 (modify-phases %standard-phases
10797 (add-after 'unpack 'do-not-use-bundled-hdf5
10798 (lambda* (#:key inputs #:allow-other-keys)
10799 (for-each delete-file '("configure" "configure.ac"))
10800 ;; Do not make other packages link with the proprietary libsz.
10801 (substitute* "R/zzz.R"
10802 (("'\"%s/libhdf5.a\" \"%s/libsz.a\" -lz'")
10803 "'\"%s/libhdf5.a\" \"%s/libhdf5.a\" -lz'")
10804 (("'\"%s/libhdf5_cpp.a\" \"%s/libhdf5.a\" \"%s/libsz.a\" -lz'")
10805 "'\"%s/libhdf5_cpp.a\" \"%s/libhdf5.a\" \"%s/libhdf5.a\" -lz'")
10806 (("'%s/libhdf5_hl.a %s/libhdf5.a %s/libsz.a -lz'")
10807 "'%s/libhdf5_hl.a %s/libhdf5.a %s/libhdf5.a -lz'")
10808 (("'%s/libhdf5_hl_cpp.a %s/libhdf5_hl.a %s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a -lz'")
10809 "'%s/libhdf5_hl_cpp.a %s/libhdf5_hl.a %s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a -lz'"))
10810 (with-directory-excursion "src"
10811 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10812 (rename-file (string-append "hdf5-" ,(package-version hdf5-1.10))
10814 ;; Remove timestamp and host system information to make
10815 ;; the build reproducible.
10816 (substitute* "hdf5/src/libhdf5.settings.in"
10817 (("Configured on: @CONFIG_DATE@")
10818 "Configured on: Guix")
10819 (("Uname information:.*")
10820 "Uname information: Linux\n")
10821 ;; Remove unnecessary store reference.
10823 "C Compiler: GCC\n"))
10824 (rename-file "Makevars.in" "Makevars")
10825 (substitute* "Makevars"
10826 (("HDF5_CXX_LIB=.*")
10827 (string-append "HDF5_CXX_LIB="
10828 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10830 (string-append "HDF5_LIB="
10831 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10832 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10833 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10834 (("HDF5_HL_INCLUDE=.*") "HDF5_HL_INCLUDE=./hdf5/hl/src\n")
10835 (("HDF5_HL_CXX_INCLUDE=.*") "HDF5_HL_CXX_INCLUDE=./hdf5/hl/c++/src\n")
10836 (("HDF5_HL_LIB=.*")
10837 (string-append "HDF5_HL_LIB="
10838 (assoc-ref inputs "hdf5") "/lib/libhdf5_hl.a\n"))
10839 (("HDF5_HL_CXX_LIB=.*")
10840 (string-append "HDF5_HL_CXX_LIB="
10841 (assoc-ref inputs "hdf5") "/lib/libhdf5_hl_cpp.a\n"))
10842 ;; szip is non-free software
10843 (("cp \"\\$\\{SZIP_LIB\\}.*") "")
10844 (("PKG_LIBS =.*") "PKG_LIBS = -lz -lhdf5\n")))
10849 `(("hdf5" ,hdf5-1.10)))
10851 `(("hdf5-source" ,(package-source hdf5-1.10))))
10852 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10853 (synopsis "HDF5 library as an R package")
10854 (description "This package provides C and C++ HDF5 libraries for use in R
10856 (license license:artistic2.0)))
10858 (define-public r-beachmat
10860 (name "r-beachmat")
10865 (uri (bioconductor-uri "beachmat" version))
10868 "1bpnlw2kdy9yc2vq948k980r0j25ipb80llhvn0j3kxjiwyfgs3i"))))
10869 (build-system r-build-system)
10871 `(("r-biocgenerics" ,r-biocgenerics)
10872 ("r-delayedarray" ,r-delayedarray)
10873 ("r-matrix" ,r-matrix)))
10874 (home-page "https://bioconductor.org/packages/beachmat")
10875 (synopsis "Compiling Bioconductor to handle each matrix type")
10876 (description "This package provides a consistent C++ class interface for a
10877 variety of commonly used matrix types, including sparse and HDF5-backed
10879 (license license:gpl3)))
10881 (define-public r-singlecellexperiment
10883 (name "r-singlecellexperiment")
10888 (uri (bioconductor-uri "SingleCellExperiment" version))
10891 "11pqb3cigi9xbhxq2k3n7z23v1ibd03ws1lcrh5c5ffgb33nlyw5"))))
10893 `((upstream-name . "SingleCellExperiment")))
10894 (build-system r-build-system)
10896 `(("r-biocgenerics" ,r-biocgenerics)
10897 ("r-s4vectors" ,r-s4vectors)
10898 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10899 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10900 (synopsis "S4 classes for single cell data")
10901 (description "This package defines an S4 class for storing data from
10902 single-cell experiments. This includes specialized methods to store and
10903 retrieve spike-in information, dimensionality reduction coordinates and size
10904 factors for each cell, along with the usual metadata for genes and
10906 (license license:gpl3)))
10908 (define-public r-scater
10914 (uri (bioconductor-uri "scater" version))
10917 "0sxd1s8wdlj9926bagq4crjrk1nnmh3j3bhgrw160zfgc3y8pzck"))))
10918 (build-system r-build-system)
10920 `(("r-beachmat" ,r-beachmat)
10921 ("r-biocgenerics" ,r-biocgenerics)
10922 ("r-biocneighbors" ,r-biocneighbors)
10923 ("r-biocparallel" ,r-biocparallel)
10924 ("r-biocsingular" ,r-biocsingular)
10925 ("r-delayedarray" ,r-delayedarray)
10926 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10927 ("r-ggbeeswarm" ,r-ggbeeswarm)
10928 ("r-ggplot2" ,r-ggplot2)
10929 ("r-matrix" ,r-matrix)
10931 ("r-s4vectors" ,r-s4vectors)
10932 ("r-singlecellexperiment" ,r-singlecellexperiment)
10933 ("r-summarizedexperiment" ,r-summarizedexperiment)
10934 ("r-viridis" ,r-viridis)))
10935 (home-page "https://github.com/davismcc/scater")
10936 (synopsis "Single-cell analysis toolkit for gene expression data in R")
10937 (description "This package provides a collection of tools for doing
10938 various analyses of single-cell RNA-seq gene expression data, with a focus on
10940 (license license:gpl2+)))
10942 (define-public r-scran
10949 (uri (bioconductor-uri "scran" version))
10952 "1y8wlgk5zbv7c7gcp0ahfpbh9lifab7y3zwf0093fzaw7vr1y6cr"))))
10953 (build-system r-build-system)
10955 `(("r-beachmat" ,r-beachmat)
10957 ("r-biocgenerics" ,r-biocgenerics)
10958 ("r-biocneighbors" ,r-biocneighbors)
10959 ("r-biocparallel" ,r-biocparallel)
10960 ("r-biocsingular" ,r-biocsingular)
10961 ("r-delayedarray" ,r-delayedarray)
10962 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10963 ("r-dqrng" ,r-dqrng)
10964 ("r-edger" ,r-edger)
10965 ("r-igraph" ,r-igraph)
10966 ("r-limma" ,r-limma)
10967 ("r-matrix" ,r-matrix)
10969 ("r-s4vectors" ,r-s4vectors)
10970 ("r-scater" ,r-scater)
10971 ("r-singlecellexperiment" ,r-singlecellexperiment)
10972 ("r-statmod" ,r-statmod)
10973 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10974 (home-page "https://bioconductor.org/packages/scran")
10975 (synopsis "Methods for single-cell RNA-Seq data analysis")
10976 (description "This package implements a variety of low-level analyses of
10977 single-cell RNA-seq data. Methods are provided for normalization of
10978 cell-specific biases, assignment of cell cycle phase, and detection of highly
10979 variable and significantly correlated genes.")
10980 (license license:gpl3)))
10982 (define-public r-delayedmatrixstats
10984 (name "r-delayedmatrixstats")
10989 (uri (bioconductor-uri "DelayedMatrixStats" version))
10992 "0mv2rl6a6l404piabcazxz1s6ars016pxhjf5v40hhr6y1r0wbqy"))))
10994 `((upstream-name . "DelayedMatrixStats")))
10995 (build-system r-build-system)
10997 `(("r-biocparallel" ,r-biocparallel)
10998 ("r-delayedarray" ,r-delayedarray)
10999 ("r-hdf5array" ,r-hdf5array)
11000 ("r-iranges" ,r-iranges)
11001 ("r-matrix" ,r-matrix)
11002 ("r-matrixstats" ,r-matrixstats)
11003 ("r-s4vectors" ,r-s4vectors)))
11004 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
11005 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
11007 "This package provides a port of the @code{matrixStats} API for use with
11008 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
11009 contains high-performing functions operating on rows and columns of
11010 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
11011 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
11012 are optimized per data type and for subsetted calculations such that both
11013 memory usage and processing time is minimized.")
11014 (license license:expat)))
11016 (define-public r-phangorn
11018 (name "r-phangorn")
11023 (uri (cran-uri "phangorn" version))
11026 "0ihkaykqjmf80d8wrk3saphxvnv58zma6pd13633bd3cwanc33f5"))))
11027 (build-system r-build-system)
11030 ("r-fastmatch" ,r-fastmatch)
11031 ("r-igraph" ,r-igraph)
11032 ("r-magrittr" ,r-magrittr)
11033 ("r-matrix" ,r-matrix)
11034 ("r-quadprog" ,r-quadprog)
11035 ("r-rcpp" ,r-rcpp)))
11036 (home-page "https://github.com/KlausVigo/phangorn")
11037 (synopsis "Phylogenetic analysis in R")
11039 "Phangorn is a package for phylogenetic analysis in R. It supports
11040 estimation of phylogenetic trees and networks using Maximum Likelihood,
11041 Maximum Parsimony, distance methods and Hadamard conjugation.")
11042 (license license:gpl2+)))
11044 (define-public r-dropbead
11045 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
11048 (name "r-dropbead")
11049 (version (string-append "0-" revision "." (string-take commit 7)))
11053 (uri (git-reference
11054 (url "https://github.com/rajewsky-lab/dropbead.git")
11056 (file-name (git-file-name name version))
11059 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
11060 (build-system r-build-system)
11062 `(("r-ggplot2" ,r-ggplot2)
11063 ("r-rcolorbrewer" ,r-rcolorbrewer)
11064 ("r-gridextra" ,r-gridextra)
11065 ("r-gplots" ,r-gplots)
11066 ("r-plyr" ,r-plyr)))
11067 (home-page "https://github.com/rajewsky-lab/dropbead")
11068 (synopsis "Basic exploration and analysis of Drop-seq data")
11069 (description "This package offers a quick and straight-forward way to
11070 explore and perform basic analysis of single cell sequencing data coming from
11071 droplet sequencing. It has been particularly tailored for Drop-seq.")
11072 (license license:gpl3))))
11074 (define htslib-for-sambamba
11075 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
11078 (name "htslib-for-sambamba")
11079 (version (string-append "1.3.1-1." (string-take commit 9)))
11083 (uri (git-reference
11084 (url "https://github.com/lomereiter/htslib.git")
11086 (file-name (string-append "htslib-" version "-checkout"))
11089 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
11091 `(("autoconf" ,autoconf)
11092 ("automake" ,automake)
11093 ,@(package-native-inputs htslib))))))
11095 (define-public sambamba
11102 (uri (git-reference
11103 (url "https://github.com/lomereiter/sambamba.git")
11104 (commit (string-append "v" version))))
11105 (file-name (string-append name "-" version "-checkout"))
11108 "111h05b60pj8dxbidiamy4imc92x2962b3lmb7wgysl6lx064qis"))))
11109 (build-system gnu-build-system)
11111 `(#:tests? #f ; there is no test target
11112 #:parallel-build? #f ; not supported
11114 (modify-phases %standard-phases
11115 (delete 'configure)
11116 (add-after 'unpack 'fix-ldc-version
11118 (substitute* "gen_ldc_version_info.py"
11119 (("/usr/bin/env.*") (which "python3")))
11120 (substitute* "Makefile"
11121 ;; We use ldc2 instead of ldmd2 to compile sambamba.
11122 (("\\$\\(shell which ldmd2\\)") (which "ldc2")))
11124 (add-after 'unpack 'place-biod-and-undead
11125 (lambda* (#:key inputs #:allow-other-keys)
11126 (copy-recursively (assoc-ref inputs "biod") "BioD")
11128 (add-after 'unpack 'unbundle-prerequisites
11130 (substitute* "Makefile"
11131 (("htslib/libhts.a lz4/lib/liblz4.a")
11133 ((" lz4-static htslib-static") ""))
11136 (lambda* (#:key outputs #:allow-other-keys)
11137 (let* ((out (assoc-ref outputs "out"))
11138 (bin (string-append out "/bin")))
11140 (copy-file (string-append "bin/sambamba-" ,version)
11141 (string-append bin "/sambamba"))
11148 ,(let ((commit "7969eb0a847b05874e83ffddead26e193ece8101"))
11151 (uri (git-reference
11152 (url "https://github.com/biod/BioD.git")
11154 (file-name (string-append "biod-"
11155 (string-take commit 9)
11159 "0mjxsmbmv0jxl3pq21p8j5r829d648if8q58ka50b2956lc6qkpm")))))))
11162 ("htslib" ,htslib-for-sambamba)))
11163 (home-page "https://lomereiter.github.io/sambamba/")
11164 (synopsis "Tools for working with SAM/BAM data")
11165 (description "Sambamba is a high performance modern robust and
11166 fast tool (and library), written in the D programming language, for
11167 working with SAM and BAM files. Current parallelised functionality is
11168 an important subset of samtools functionality, including view, index,
11169 sort, markdup, and depth.")
11170 (license license:gpl2+)))
11172 (define-public ritornello
11174 (name "ritornello")
11178 (uri (git-reference
11179 (url "https://github.com/KlugerLab/Ritornello.git")
11180 (commit (string-append "v" version))))
11181 (file-name (git-file-name name version))
11184 "1xahvq215qld7x1w8vpa5zbrsj6p9crb9shqa2x89sb0aaxa02jk"))))
11185 (build-system gnu-build-system)
11187 `(#:tests? #f ; there are no tests
11189 (modify-phases %standard-phases
11190 (add-after 'unpack 'patch-samtools-references
11191 (lambda* (#:key inputs #:allow-other-keys)
11192 (substitute* '("src/SamStream.h"
11194 (("<sam.h>") "<samtools/sam.h>"))
11196 (delete 'configure)
11198 (lambda* (#:key inputs outputs #:allow-other-keys)
11199 (let* ((out (assoc-ref outputs "out"))
11200 (bin (string-append out "/bin/")))
11202 (install-file "bin/Ritornello" bin)
11205 `(("samtools" ,samtools-0.1)
11209 (home-page "https://github.com/KlugerLab/Ritornello")
11210 (synopsis "Control-free peak caller for ChIP-seq data")
11211 (description "Ritornello is a ChIP-seq peak calling algorithm based on
11212 signal processing that can accurately call binding events without the need to
11213 do a pair total DNA input or IgG control sample. It has been tested for use
11214 with narrow binding events such as transcription factor ChIP-seq.")
11215 (license license:gpl3+)))
11217 (define-public trim-galore
11219 (name "trim-galore")
11224 (uri (git-reference
11225 (url "https://github.com/FelixKrueger/TrimGalore.git")
11227 (file-name (git-file-name name version))
11230 "1y31wbxwkm9xqzr5zv1pk5q418whnmlmgmfyxxpnl12h83m2i9iv"))))
11231 (build-system gnu-build-system)
11233 `(#:tests? #f ; no tests
11235 (modify-phases %standard-phases
11236 (replace 'configure
11238 ;; Trim Galore tries to figure out what version of Python
11239 ;; cutadapt is using by looking at the shebang. Of course that
11240 ;; doesn't work, because cutadapt is wrapped in a shell script.
11241 (substitute* "trim_galore"
11242 (("my \\$python_return.*")
11243 "my $python_return = \"Python 3.999\";\n"))
11246 (add-after 'unpack 'hardcode-tool-references
11247 (lambda* (#:key inputs #:allow-other-keys)
11248 (substitute* "trim_galore"
11249 (("\\$path_to_cutadapt = 'cutadapt'")
11250 (string-append "$path_to_cutadapt = '"
11251 (assoc-ref inputs "cutadapt")
11253 (("\\$compression_path = \"gzip\"")
11254 (string-append "$compression_path = \""
11255 (assoc-ref inputs "gzip")
11258 (string-append "\""
11259 (assoc-ref inputs "gzip")
11262 (string-append "\""
11263 (assoc-ref inputs "pigz")
11267 (lambda* (#:key outputs #:allow-other-keys)
11268 (let ((bin (string-append (assoc-ref outputs "out")
11271 (install-file "trim_galore" bin)
11277 ("cutadapt" ,cutadapt)))
11279 `(("unzip" ,unzip)))
11280 (home-page "https://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
11281 (synopsis "Wrapper around Cutadapt and FastQC")
11282 (description "Trim Galore! is a wrapper script to automate quality and
11283 adapter trimming as well as quality control, with some added functionality to
11284 remove biased methylation positions for RRBS sequence files.")
11285 (license license:gpl3+)))
11287 (define-public gess
11293 (uri (string-append "http://compbio.uthscsa.edu/"
11295 "gess-" version ".src.tar.gz"))
11298 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
11299 (build-system gnu-build-system)
11301 `(#:tests? #f ; no tests
11303 (modify-phases %standard-phases
11304 (delete 'configure)
11307 (lambda* (#:key inputs outputs #:allow-other-keys)
11308 (let* ((python (assoc-ref inputs "python"))
11309 (out (assoc-ref outputs "out"))
11310 (bin (string-append out "/bin/"))
11311 (target (string-append
11313 ,(version-major+minor
11314 (package-version python))
11315 "/site-packages/gess/")))
11317 (copy-recursively "." target)
11318 ;; Make GESS.py executable
11319 (chmod (string-append target "GESS.py") #o555)
11320 ;; Add Python shebang to the top and make Matplotlib
11322 (substitute* (string-append target "GESS.py")
11323 (("\"\"\"Description:" line)
11324 (string-append "#!" (which "python") "
11326 matplotlib.use('Agg')
11328 ;; Make sure GESS has all modules in its path
11329 (wrap-script (string-append target "GESS.py")
11330 `("PYTHONPATH" ":" = (,target ,(getenv "PYTHONPATH"))))
11332 (symlink (string-append target "GESS.py")
11333 (string-append bin "GESS.py"))
11336 `(("python" ,python-2)
11337 ("python2-pysam" ,python2-pysam)
11338 ("python2-scipy" ,python2-scipy)
11339 ("python2-numpy" ,python2-numpy)
11340 ("python2-networkx" ,python2-networkx)
11341 ("python2-biopython" ,python2-biopython)
11342 ("guile" ,guile-3.0))) ; for the script wrapper
11343 (home-page "https://compbio.uthscsa.edu/GESS_Web/")
11344 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11346 "GESS is an implementation of a novel computational method to detect de
11347 novo exon-skipping events directly from raw RNA-seq data without the prior
11348 knowledge of gene annotation information. GESS stands for the graph-based
11349 exon-skipping scanner detection scheme.")
11350 (license license:bsd-3)))
11352 (define-public phylip
11359 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11360 "download/phylip-" version ".tar.gz"))
11363 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11364 (build-system gnu-build-system)
11366 `(#:tests? #f ; no check target
11367 #:make-flags (list "-f" "Makefile.unx" "install")
11368 #:parallel-build? #f ; not supported
11370 (modify-phases %standard-phases
11371 (add-after 'unpack 'enter-dir
11372 (lambda _ (chdir "src") #t))
11373 (delete 'configure)
11375 (lambda* (#:key inputs outputs #:allow-other-keys)
11376 (let ((target (string-append (assoc-ref outputs "out")
11379 (for-each (lambda (file)
11380 (install-file file target))
11381 (find-files "../exe" ".*")))
11383 (home-page "http://evolution.genetics.washington.edu/phylip/")
11384 (synopsis "Tools for inferring phylogenies")
11385 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11386 programs for inferring phylogenies (evolutionary trees).")
11387 (license license:bsd-2)))
11396 (uri (string-append "https://integrativemodeling.org/"
11397 version "/download/imp-" version ".tar.gz"))
11400 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
11401 (build-system cmake-build-system)
11403 `(;; FIXME: Some tests fail because they produce warnings, others fail
11404 ;; because the PYTHONPATH does not include the modeller's directory.
11412 ("python" ,python-2)))
11414 `(("python2-numpy" ,python2-numpy)
11415 ("python2-scipy" ,python2-scipy)
11416 ("python2-pandas" ,python2-pandas)
11417 ("python2-scikit-learn" ,python2-scikit-learn)
11418 ("python2-networkx" ,python2-networkx)))
11419 (home-page "https://integrativemodeling.org")
11420 (synopsis "Integrative modeling platform")
11421 (description "IMP's broad goal is to contribute to a comprehensive
11422 structural characterization of biomolecules ranging in size and complexity
11423 from small peptides to large macromolecular assemblies, by integrating data
11424 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11425 Python toolbox for solving complex modeling problems, and a number of
11426 applications for tackling some common problems in a user-friendly way.")
11427 ;; IMP is largely available under the GNU Lesser GPL; see the file
11428 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11429 ;; available under the GNU GPL (see the file COPYING.GPL).
11430 (license (list license:lgpl2.1+
11433 (define-public tadbit
11439 (uri (git-reference
11440 (url "https://github.com/3DGenomes/TADbit.git")
11441 (commit (string-append "v" version))))
11442 (file-name (git-file-name name version))
11445 "07g3aj648prmsvxp9caz5yl41k0y0647vxh0f5p3w8376mfiljd0"))))
11446 (build-system python-build-system)
11448 `(;; Tests are included and must be run after installation, but
11449 ;; they are incomplete and thus cannot be run.
11453 (modify-phases %standard-phases
11454 (add-after 'unpack 'fix-problems-with-setup.py
11455 (lambda* (#:key outputs #:allow-other-keys)
11456 ;; setup.py opens these files for writing
11457 (chmod "_pytadbit/_version.py" #o664)
11458 (chmod "README.rst" #o664)
11460 ;; Don't attempt to install the bash completions to
11461 ;; the home directory.
11462 (rename-file "extras/.bash_completion"
11464 (substitute* "setup.py"
11465 (("\\(path.expanduser\\('~'\\)")
11466 (string-append "(\""
11467 (assoc-ref outputs "out")
11468 "/etc/bash_completion.d\""))
11469 (("extras/\\.bash_completion")
11473 ;; TODO: add Chimera for visualization
11476 ("python2-scipy" ,python2-scipy)
11477 ("python2-numpy" ,python2-numpy)
11478 ("python2-matplotlib" ,python2-matplotlib)
11479 ("python2-pysam" ,python2-pysam)))
11480 (home-page "https://3dgenomes.github.io/TADbit/")
11481 (synopsis "Analyze, model, and explore 3C-based data")
11483 "TADbit is a complete Python library to deal with all steps to analyze,
11484 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11485 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11486 correct interaction matrices, identify and compare the so-called
11487 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11488 interaction matrices, and finally, extract structural properties from the
11489 models. TADbit is complemented by TADkit for visualizing 3D models.")
11490 (license license:gpl3+)))
11492 (define-public kentutils
11495 ;; 302.1.0 is out, but the only difference is the inclusion of
11496 ;; pre-built binaries.
11497 (version "302.0.0")
11501 (uri (git-reference
11502 (url "https://github.com/ENCODE-DCC/kentUtils.git")
11503 (commit (string-append "v" version))))
11504 (file-name (git-file-name name version))
11507 "0n1wbyjpzii2b9qhyp9r1q76j623cggpg3y8fmw78ld3z4y7ivha"))
11508 (modules '((guix build utils)
11513 ;; Only the contents of the specified directories are free
11514 ;; for all uses, so we remove the rest. "hg/autoSql" and
11515 ;; "hg/autoXml" are nominally free, but they depend on a
11516 ;; library that is built from the sources in "hg/lib",
11517 ;; which is nonfree.
11518 (let ((free (list "." ".."
11519 "utils" "lib" "inc" "tagStorm"
11520 "parasol" "htslib"))
11521 (directory? (lambda (file)
11522 (eq? 'directory (stat:type (stat file))))))
11523 (for-each (lambda (file)
11524 (and (directory? file)
11525 (delete-file-recursively file)))
11526 (map (cut string-append "src/" <>)
11529 (not (member file free)))))))
11530 ;; Only make the utils target, not the userApps target,
11531 ;; because that requires libraries we won't build.
11532 (substitute* "Makefile"
11533 ((" userApps") " utils"))
11534 ;; Only build libraries that are free.
11535 (substitute* "src/makefile"
11536 (("DIRS =.*") "DIRS =\n")
11537 (("cd jkOwnLib.*") "")
11540 (substitute* "src/utils/makefile"
11541 ;; These tools depend on "jkhgap.a", which is part of the
11542 ;; nonfree "src/hg/lib" directory.
11543 (("raSqlQuery") "")
11544 (("pslLiftSubrangeBlat") "")
11546 ;; Do not build UCSC tools, which may require nonfree
11548 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11550 (build-system gnu-build-system)
11552 `( ;; There is no global test target and the test target for
11553 ;; individual tools depends on input files that are not
11557 (modify-phases %standard-phases
11558 (add-after 'unpack 'fix-permissions
11559 (lambda _ (make-file-writable "src/inc/localEnvironment.mk") #t))
11560 (add-after 'unpack 'fix-paths
11562 (substitute* "Makefile"
11563 (("/bin/echo") (which "echo")))
11565 (add-after 'unpack 'prepare-samtabix
11566 (lambda* (#:key inputs #:allow-other-keys)
11567 (copy-recursively (assoc-ref inputs "samtabix")
11570 (delete 'configure)
11572 (lambda* (#:key outputs #:allow-other-keys)
11573 (let ((bin (string-append (assoc-ref outputs "out")
11575 (copy-recursively "bin" bin))
11581 (uri (git-reference
11582 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11583 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11586 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11592 ("mariadb" ,mariadb "lib")
11593 ("mariadb-dev" ,mariadb "dev")
11594 ("openssl" ,openssl-1.0)))
11595 (home-page "https://genome.cse.ucsc.edu/index.html")
11596 (synopsis "Assorted bioinformatics utilities")
11597 (description "This package provides the kentUtils, a selection of
11598 bioinformatics utilities used in combination with the UCSC genome
11600 ;; Only a subset of the sources are released under a non-copyleft
11601 ;; free software license. All other sources are removed in a
11602 ;; snippet. See this bug report for an explanation of how the
11603 ;; license statements apply:
11604 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11605 (license (license:non-copyleft
11606 "http://genome.ucsc.edu/license/"
11607 "The contents of this package are free for all uses."))))
11609 (define-public f-seq
11610 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11614 (version (string-append "1.1-" revision "." (string-take commit 7)))
11617 (uri (git-reference
11618 (url "https://github.com/aboyle/F-seq.git")
11620 (file-name (string-append name "-" version))
11623 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11624 (modules '((guix build utils)))
11625 ;; Remove bundled Java library archives.
11628 (for-each delete-file (find-files "lib" ".*"))
11630 (build-system ant-build-system)
11632 `(#:tests? #f ; no tests included
11634 (modify-phases %standard-phases
11636 (lambda* (#:key inputs outputs #:allow-other-keys)
11637 (let* ((target (assoc-ref outputs "out"))
11638 (bin (string-append target "/bin"))
11639 (doc (string-append target "/share/doc/f-seq"))
11640 (lib (string-append target "/lib")))
11643 (substitute* "bin/linux/fseq"
11644 (("java") (which "java"))
11645 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11646 (string-append (assoc-ref inputs "java-commons-cli")
11647 "/share/java/commons-cli.jar"))
11649 (string-append "REALDIR=" bin "\n")))
11650 (install-file "README.txt" doc)
11651 (install-file "bin/linux/fseq" bin)
11652 (install-file "build~/fseq.jar" lib)
11653 (copy-recursively "lib" lib)
11657 ("java-commons-cli" ,java-commons-cli)))
11658 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11659 (synopsis "Feature density estimator for high-throughput sequence tags")
11661 "F-Seq is a software package that generates a continuous tag sequence
11662 density estimation allowing identification of biologically meaningful sites
11663 such as transcription factor binding sites (ChIP-seq) or regions of open
11664 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11666 (license license:gpl3+))))
11668 (define-public bismark
11675 (uri (git-reference
11676 (url "https://github.com/FelixKrueger/Bismark.git")
11678 (file-name (string-append name "-" version "-checkout"))
11681 "0xchm3rgilj6vfjnyzfzzymfd7djr64sbrmrvs3njbwi66jqbzw9"))))
11682 (build-system perl-build-system)
11684 `(#:tests? #f ; there are no tests
11685 #:modules ((guix build utils)
11688 (guix build perl-build-system))
11690 (modify-phases %standard-phases
11691 ;; The bundled plotly.js is minified.
11692 (add-after 'unpack 'replace-plotly.js
11693 (lambda* (#:key inputs #:allow-other-keys)
11694 (let* ((file (assoc-ref inputs "plotly.js"))
11695 (installed "plotly/plotly.js"))
11696 (let ((minified (open-pipe* OPEN_READ "uglify-js" file)))
11697 (call-with-output-file installed
11698 (cut dump-port minified <>))))
11700 (delete 'configure)
11703 (lambda* (#:key inputs outputs #:allow-other-keys)
11704 (let* ((out (assoc-ref outputs "out"))
11705 (bin (string-append out "/bin"))
11706 (share (string-append out "/share/bismark"))
11707 (docdir (string-append out "/share/doc/bismark"))
11708 (docs '("Docs/Bismark_User_Guide.html"))
11709 (scripts '("bismark"
11710 "bismark_genome_preparation"
11711 "bismark_methylation_extractor"
11714 "coverage2cytosine"
11715 "deduplicate_bismark"
11716 "filter_non_conversion"
11719 "NOMe_filtering")))
11720 (substitute* "bismark2report"
11721 (("\\$RealBin/plotly")
11722 (string-append share "/plotly")))
11726 (for-each (lambda (file) (install-file file bin))
11728 (for-each (lambda (file) (install-file file docdir))
11730 (copy-recursively "Docs/Images" (string-append docdir "/Images"))
11731 (copy-recursively "plotly"
11732 (string-append share "/plotly"))
11734 ;; Fix references to gunzip
11735 (substitute* (map (lambda (file)
11736 (string-append bin "/" file))
11739 (string-append "\"" (assoc-ref inputs "gzip")
11740 "/bin/gunzip -c")))
11744 ("perl-carp" ,perl-carp)
11745 ("perl-getopt-long" ,perl-getopt-long)))
11750 (uri (string-append "https://raw.githubusercontent.com/plotly/plotly.js/"
11751 "v1.39.4/dist/plotly.js"))
11753 (base32 "138mwsr4nf5qif4mrxx286mpnagxd1xwl6k8aidrjgknaqg88zyr"))))
11754 ("uglify-js" ,uglify-js)))
11755 (home-page "https://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11756 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11757 (description "Bismark is a program to map bisulfite treated sequencing
11758 reads to a genome of interest and perform methylation calls in a single step.
11759 The output can be easily imported into a genome viewer, such as SeqMonk, and
11760 enables a researcher to analyse the methylation levels of their samples
11761 straight away. Its main features are:
11764 @item Bisulfite mapping and methylation calling in one single step
11765 @item Supports single-end and paired-end read alignments
11766 @item Supports ungapped and gapped alignments
11767 @item Alignment seed length, number of mismatches etc are adjustable
11768 @item Output discriminates between cytosine methylation in CpG, CHG
11771 (license license:gpl3+)))
11773 (define-public paml
11779 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11780 "paml" version ".tgz"))
11783 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11784 (modules '((guix build utils)))
11785 ;; Remove Windows binaries
11788 (for-each delete-file (find-files "." "\\.exe$"))
11790 (build-system gnu-build-system)
11792 `(#:tests? #f ; there are no tests
11793 #:make-flags '("CC=gcc")
11795 (modify-phases %standard-phases
11796 (replace 'configure
11798 (substitute* "src/BFdriver.c"
11799 (("/bin/bash") (which "bash")))
11803 (lambda* (#:key outputs #:allow-other-keys)
11804 (let ((tools '("baseml" "basemlg" "codeml"
11805 "pamp" "evolver" "yn00" "chi2"))
11806 (bin (string-append (assoc-ref outputs "out") "/bin"))
11807 (docdir (string-append (assoc-ref outputs "out")
11808 "/share/doc/paml")))
11810 (for-each (lambda (file) (install-file file bin)) tools)
11811 (copy-recursively "../doc" docdir)
11813 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11814 (synopsis "Phylogentic analysis by maximum likelihood")
11815 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11816 contains a few programs for model fitting and phylogenetic tree reconstruction
11817 using nucleotide or amino-acid sequence data.")
11819 (license license:gpl3)))
11821 (define-public kallisto
11827 (uri (git-reference
11828 (url "https://github.com/pachterlab/kallisto.git")
11829 (commit (string-append "v" version))))
11830 (file-name (git-file-name name version))
11833 "0nj382jiywqnpgvyhichajpkkh5r0bapn43f4dx40zdaq5v4m40m"))))
11834 (build-system cmake-build-system)
11836 `(#:tests? #f ; no "check" target
11838 (modify-phases %standard-phases
11839 (add-after 'unpack 'do-not-use-bundled-htslib
11841 (substitute* "CMakeLists.txt"
11842 (("^ExternalProject_Add" m)
11843 (string-append "if (NEVER)\n" m))
11845 (string-append ")\nendif(NEVER)"))
11846 (("include_directories\\(\\$\\{htslib_PREFIX.*" m)
11847 (string-append "# " m)))
11848 (substitute* "src/CMakeLists.txt"
11849 (("target_link_libraries\\(kallisto kallisto_core pthread \
11850 \\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/../ext/htslib/libhts.a\\)")
11851 "target_link_libraries(kallisto kallisto_core pthread hts)")
11852 (("include_directories\\(\\.\\./ext/htslib\\)") ""))
11858 (home-page "https://pachterlab.github.io/kallisto/")
11859 (synopsis "Near-optimal RNA-Seq quantification")
11861 "Kallisto is a program for quantifying abundances of transcripts from
11862 RNA-Seq data, or more generally of target sequences using high-throughput
11863 sequencing reads. It is based on the novel idea of pseudoalignment for
11864 rapidly determining the compatibility of reads with targets, without the need
11865 for alignment. Pseudoalignment of reads preserves the key information needed
11866 for quantification, and kallisto is therefore not only fast, but also as
11867 accurate as existing quantification tools.")
11868 (license license:bsd-2)))
11870 (define-public libgff
11876 (uri (git-reference
11877 (url "https://github.com/Kingsford-Group/libgff.git")
11878 (commit (string-append "v" version))))
11879 (file-name (git-file-name name version))
11882 "0n6vfjnq7a2mianipscbshrvbncss8z4zkgkbjw754p9043nfkps"))))
11883 (build-system cmake-build-system)
11884 (arguments `(#:tests? #f)) ; no tests included
11885 (home-page "https://github.com/Kingsford-Group/libgff")
11886 (synopsis "Parser library for reading/writing GFF files")
11887 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11888 code that is used in the Cufflinks codebase. The goal of this library is to
11889 provide this functionality without the necessity of drawing in a heavy-weight
11890 dependency like SeqAn.")
11891 (license (license:x11-style "https://www.boost.org/LICENSE_1_0.txt"))))
11893 (define-public sailfish
11899 (uri (git-reference
11900 (url "https://github.com/kingsfordgroup/sailfish.git")
11901 (commit (string-append "v" version))))
11902 (file-name (git-file-name name version))
11905 "1amcc5hqvsl42hg4x19bi9vy47cl874s0lw1fmi0hwsdk9i8c03v"))
11906 (modules '((guix build utils)))
11909 ;; Delete bundled headers for eigen3.
11910 (delete-file-recursively "include/eigen3/")
11912 (build-system cmake-build-system)
11914 `(#:configure-flags
11915 (list (string-append "-DBOOST_INCLUDEDIR="
11916 (assoc-ref %build-inputs "boost")
11918 (string-append "-DBOOST_LIBRARYDIR="
11919 (assoc-ref %build-inputs "boost")
11921 (string-append "-DBoost_LIBRARIES="
11922 "-lboost_iostreams "
11923 "-lboost_filesystem "
11928 "-lboost_program_options")
11929 "-DBoost_FOUND=TRUE"
11930 ;; Don't download RapMap---we already have it!
11931 "-DFETCHED_RAPMAP=1")
11932 ;; Tests must be run after installation and the location of the test
11933 ;; data file must be overridden. But the tests fail. It looks like
11934 ;; they are not really meant to be run.
11937 (modify-phases %standard-phases
11938 ;; Boost cannot be found, even though it's right there.
11939 (add-after 'unpack 'do-not-look-for-boost
11940 (lambda* (#:key inputs #:allow-other-keys)
11941 (substitute* "CMakeLists.txt"
11942 (("find_package\\(Boost 1\\.53\\.0") "#"))
11944 (add-after 'unpack 'do-not-assign-to-macro
11946 (substitute* "include/spdlog/details/format.cc"
11947 (("const unsigned CHAR_WIDTH = 1;") ""))
11949 (add-after 'unpack 'prepare-rapmap
11950 (lambda* (#:key inputs #:allow-other-keys)
11951 (let ((src "external/install/src/rapmap/")
11952 (include "external/install/include/rapmap/")
11953 (rapmap (assoc-ref inputs "rapmap")))
11954 (mkdir-p "/tmp/rapmap")
11956 (assoc-ref inputs "rapmap")
11958 "--strip-components=1")
11961 (for-each (lambda (file)
11962 (install-file file src))
11963 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
11964 (copy-recursively "/tmp/rapmap/include" include))
11966 (add-after 'unpack 'use-system-libraries
11967 (lambda* (#:key inputs #:allow-other-keys)
11968 (substitute* '("src/SailfishIndexer.cpp"
11969 "src/SailfishUtils.cpp"
11970 "src/SailfishQuantify.cpp"
11971 "src/FASTAParser.cpp"
11973 "include/SailfishUtils.hpp"
11974 "include/SailfishIndex.hpp"
11975 "include/CollapsedEMOptimizer.hpp"
11976 "src/CollapsedEMOptimizer.cpp")
11977 (("#include \"jellyfish/config.h\"") ""))
11978 (substitute* "src/CMakeLists.txt"
11979 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11980 (string-append (assoc-ref inputs "jellyfish")
11981 "/include/jellyfish-" ,(package-version jellyfish)))
11982 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11983 (string-append (assoc-ref inputs "jellyfish")
11984 "/lib/libjellyfish-2.0.a"))
11985 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11986 (string-append (assoc-ref inputs "libdivsufsort")
11987 "/lib/libdivsufsort.so"))
11988 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11989 (string-append (assoc-ref inputs "libdivsufsort")
11990 "/lib/libdivsufsort64.so")))
11991 (substitute* "CMakeLists.txt"
11992 ;; Don't prefer static libs
11993 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11994 (("find_package\\(Jellyfish.*") "")
11995 (("ExternalProject_Add\\(libjellyfish") "message(")
11996 (("ExternalProject_Add\\(libgff") "message(")
11997 (("ExternalProject_Add\\(libsparsehash") "message(")
11998 (("ExternalProject_Add\\(libdivsufsort") "message("))
12000 ;; Ensure that Eigen headers can be found
12001 (setenv "CPLUS_INCLUDE_PATH"
12002 (string-append (assoc-ref inputs "eigen")
12004 (or (getenv "CPLUS_INCLUDE_PATH") "")))
12009 ("jemalloc" ,jemalloc)
12010 ("jellyfish" ,jellyfish)
12011 ("sparsehash" ,sparsehash)
12014 (uri (git-reference
12015 (url "https://github.com/COMBINE-lab/RapMap.git")
12016 (commit (string-append "sf-v" version))))
12017 (file-name (string-append "rapmap-sf-v" version "-checkout"))
12020 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
12021 (modules '((guix build utils)))
12022 ;; These files are expected to be excluded.
12024 '(begin (delete-file-recursively "include/spdlog")
12025 (for-each delete-file '("include/xxhash.h"
12028 ("libdivsufsort" ,libdivsufsort)
12033 `(("pkg-config" ,pkg-config)))
12034 (home-page "https://www.cs.cmu.edu/~ckingsf/software/sailfish/")
12035 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
12036 (description "Sailfish is a tool for genomic transcript quantification
12037 from RNA-seq data. It requires a set of target transcripts (either from a
12038 reference or de-novo assembly) to quantify. All you need to run sailfish is a
12039 fasta file containing your reference transcripts and a (set of) fasta/fastq
12040 file(s) containing your reads.")
12041 (license license:gpl3+)))
12043 (define libstadenio-for-salmon
12045 (name "libstadenio")
12049 (uri (git-reference
12050 (url "https://github.com/COMBINE-lab/staden-io_lib.git")
12051 (commit (string-append "v" version))))
12052 (file-name (string-append name "-" version "-checkout"))
12055 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
12056 (build-system gnu-build-system)
12057 (arguments '(#:parallel-tests? #f)) ; not supported
12061 `(("perl" ,perl))) ; for tests
12062 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
12063 (synopsis "General purpose trace and experiment file library")
12064 (description "This package provides a library of file reading and writing
12065 code to provide a general purpose Trace file (and Experiment File) reading
12068 The following file formats are supported:
12071 @item SCF trace files
12072 @item ABI trace files
12073 @item ALF trace files
12074 @item ZTR trace files
12075 @item SFF trace archives
12076 @item SRF trace archives
12077 @item Experiment files
12078 @item Plain text files
12079 @item SAM/BAM sequence files
12080 @item CRAM sequence files
12082 (license license:bsd-3)))
12084 (define-public salmon
12090 (uri (git-reference
12091 (url "https://github.com/COMBINE-lab/salmon.git")
12092 (commit (string-append "v" version))))
12093 (file-name (git-file-name name version))
12096 "1i2z4aivicmiixdz9bxalp7vmfzi3k92fxa63iqa8kgvfw5a4aq5"))
12097 (modules '((guix build utils)))
12100 ;; Delete bundled headers for eigen3.
12101 (delete-file-recursively "include/eigen3/")
12103 (build-system cmake-build-system)
12105 `(#:configure-flags
12106 (list (string-append "-DBOOST_INCLUDEDIR="
12107 (assoc-ref %build-inputs "boost")
12109 (string-append "-DBOOST_LIBRARYDIR="
12110 (assoc-ref %build-inputs "boost")
12112 (string-append "-DBoost_LIBRARIES="
12113 "-lboost_iostreams "
12114 "-lboost_filesystem "
12119 "-lboost_program_options")
12120 "-DBoost_FOUND=TRUE"
12121 "-DTBB_LIBRARIES=tbb tbbmalloc"
12122 ;; Don't download RapMap---we already have it!
12123 "-DFETCHED_RAPMAP=1")
12125 (modify-phases %standard-phases
12126 ;; Boost cannot be found, even though it's right there.
12127 (add-after 'unpack 'do-not-look-for-boost
12128 (lambda* (#:key inputs #:allow-other-keys)
12129 (substitute* "CMakeLists.txt"
12130 (("find_package\\(Boost 1\\.59\\.0") "#"))
12132 (add-after 'unpack 'do-not-phone-home
12134 (substitute* "src/Salmon.cpp"
12135 (("getVersionMessage\\(\\)") "\"\""))
12137 (add-after 'unpack 'prepare-rapmap
12138 (lambda* (#:key inputs #:allow-other-keys)
12139 (let ((src "external/install/src/rapmap/")
12140 (include "external/install/include/rapmap/")
12141 (rapmap (assoc-ref inputs "rapmap")))
12144 (copy-recursively (string-append rapmap "/src") src)
12145 (copy-recursively (string-append rapmap "/include") include)
12146 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
12147 "external/install/include/rapmap/FastxParser.hpp"
12148 "external/install/include/rapmap/concurrentqueue.h"
12149 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
12150 "external/install/src/rapmap/FastxParser.cpp"
12151 "external/install/src/rapmap/xxhash.c"))
12152 (delete-file-recursively "external/install/include/rapmap/spdlog"))
12154 (add-after 'unpack 'use-system-libraries
12155 (lambda* (#:key inputs #:allow-other-keys)
12156 (substitute* "CMakeLists.txt"
12157 ;; Don't prefer static libs
12158 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12159 (("set\\(TBB_LIBRARIES") "message(")
12160 ;; Don't download anything
12161 (("DOWNLOAD_COMMAND") "DOWNLOAD_COMMAND echo")
12162 (("externalproject_add\\(libcereal") "message(")
12163 (("externalproject_add\\(libgff") "message(")
12164 (("externalproject_add\\(libtbb") "message(")
12165 (("externalproject_add\\(libdivsufsort") "message(")
12166 (("externalproject_add\\(libstadenio") "message(")
12167 (("externalproject_add_step\\(") "message("))
12168 (substitute* "src/CMakeLists.txt"
12169 (("add_dependencies") "#")
12170 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
12171 (string-append (assoc-ref inputs "libstadenio-for-salmon")
12172 "/lib/libstaden-read.so"))
12173 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12174 (string-append (assoc-ref inputs "libdivsufsort")
12175 "/lib/libdivsufsort.so"))
12176 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12177 (string-append (assoc-ref inputs "libdivsufsort")
12178 "/lib/libdivsufsort64.so"))
12179 (("lib/libdivsufsort.a") "/lib/libdivsufsort.so"))
12181 ;; Ensure that all headers can be found
12182 (setenv "CPLUS_INCLUDE_PATH"
12183 (string-append (or (getenv "CPLUS_INCLUDE_PATH") "")
12185 (assoc-ref inputs "eigen")
12186 "/include/eigen3"))
12188 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
12189 ;; run. It only exists after the install phase.
12190 (add-after 'unpack 'fix-tests
12192 (substitute* "src/CMakeLists.txt"
12193 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
12194 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
12203 (uri (git-reference
12204 (url "https://github.com/COMBINE-lab/RapMap.git")
12205 (commit (string-append "salmon-v" version))))
12206 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
12209 "1biplxf0csc7a8h1wf219b0vmjkvw6wk2zylhdklb577kgmihdms"))))
12210 ("jemalloc" ,jemalloc)
12213 ("libdivsufsort" ,libdivsufsort)
12214 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
12218 `(("pkg-config" ,pkg-config)))
12219 (home-page "https://github.com/COMBINE-lab/salmon")
12220 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
12221 (description "Salmon is a program to produce highly-accurate,
12222 transcript-level quantification estimates from RNA-seq data. Salmon achieves
12223 its accuracy and speed via a number of different innovations, including the
12224 use of lightweight alignments (accurate but fast-to-compute proxies for
12225 traditional read alignments) and massively-parallel stochastic collapsed
12226 variational inference.")
12227 (license license:gpl3+)))
12229 (define-public python-loompy
12231 (name "python-loompy")
12233 ;; The tarball on Pypi does not include the tests.
12236 (uri (git-reference
12237 (url "https://github.com/linnarsson-lab/loompy.git")
12239 (file-name (git-file-name name version))
12242 "12a5kjgiikapv93wahfw0frszx1lblnppyz3vs5gy8fgmgngra07"))))
12243 (build-system python-build-system)
12246 (modify-phases %standard-phases
12249 (setenv "PYTHONPATH"
12250 (string-append (getcwd) ":"
12251 (getenv "PYTHONPATH")))
12252 (invoke "pytest" "tests")
12255 `(("python-h5py" ,python-h5py)
12256 ("python-numpy" ,python-numpy)
12257 ("python-pandas" ,python-pandas)
12258 ("python-scipy" ,python-scipy)))
12260 `(("python-pytest" ,python-pytest)))
12261 (home-page "https://github.com/linnarsson-lab/loompy")
12262 (synopsis "Work with .loom files for single-cell RNA-seq data")
12263 (description "The loom file format is an efficient format for very large
12264 omics datasets, consisting of a main matrix, optional additional layers, a
12265 variable number of row and column annotations. Loom also supports sparse
12266 graphs. This library makes it easy to work with @file{.loom} files for
12267 single-cell RNA-seq data.")
12268 (license license:bsd-3)))
12270 ;; We cannot use the latest commit because it requires Java 9.
12271 (define-public java-forester
12272 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
12275 (name "java-forester")
12276 (version (string-append "0-" revision "." (string-take commit 7)))
12279 (uri (git-reference
12280 (url "https://github.com/cmzmasek/forester.git")
12282 (file-name (string-append name "-" version "-checkout"))
12285 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12286 (modules '((guix build utils)))
12289 ;; Delete bundled jars and pre-built classes
12290 (delete-file-recursively "forester/java/resources")
12291 (delete-file-recursively "forester/java/classes")
12292 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12293 ;; Delete bundled applications
12294 (delete-file-recursively "forester_applications")
12296 (build-system ant-build-system)
12298 `(#:tests? #f ; there are none
12300 #:modules ((guix build ant-build-system)
12302 (guix build java-utils)
12306 (modify-phases %standard-phases
12307 (add-after 'unpack 'chdir
12308 (lambda _ (chdir "forester/java") #t))
12309 (add-after 'chdir 'fix-dependencies
12311 (chmod "build.xml" #o664)
12312 (call-with-output-file "build.xml.new"
12316 (with-input-from-file "build.xml"
12317 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12318 `(;; Remove all unjar tags to avoid repacking classes.
12319 (unjar . ,(lambda _ '()))
12320 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12321 (*text* . ,(lambda (_ txt) txt))))
12323 (rename-file "build.xml.new" "build.xml")
12325 ;; FIXME: itext is difficult to package as it depends on a few
12326 ;; unpackaged libraries.
12327 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12329 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12330 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12331 (("pdf_written_to = PdfExporter.*")
12332 "throw new IOException(\"PDF export is not available.\");"))
12334 ;; There is no install target
12335 (replace 'install (install-jars ".")))))
12337 `(("java-commons-codec" ,java-commons-codec)
12338 ("java-openchart2" ,java-openchart2)))
12339 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12340 (synopsis "Phylogenomics libraries for Java")
12341 (description "Forester is a collection of Java libraries for
12342 phylogenomics and evolutionary biology research. It includes support for
12343 reading, writing, and exporting phylogenetic trees.")
12344 (license license:lgpl2.1+))))
12346 (define-public java-forester-1.005
12348 (name "java-forester")
12352 (uri (string-append "https://repo1.maven.org/maven2/"
12353 "org/biojava/thirdparty/forester/"
12354 version "/forester-" version "-sources.jar"))
12355 (file-name (string-append name "-" version ".jar"))
12358 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12359 (build-system ant-build-system)
12361 `(#:tests? #f ; there are none
12363 #:modules ((guix build ant-build-system)
12365 (guix build java-utils)
12369 (modify-phases %standard-phases
12370 (add-after 'unpack 'fix-dependencies
12371 (lambda* (#:key inputs #:allow-other-keys)
12372 (call-with-output-file "build.xml"
12376 (with-input-from-file "src/build.xml"
12377 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12378 `(;; Remove all unjar tags to avoid repacking classes.
12379 (unjar . ,(lambda _ '()))
12380 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12381 (*text* . ,(lambda (_ txt) txt))))
12383 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12384 "synth_look_and_feel_1.xml")
12385 (copy-file (assoc-ref inputs "phyloxml.xsd")
12387 (substitute* "build.xml"
12388 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12389 "synth_look_and_feel_1.xml")
12390 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12393 ;; FIXME: itext is difficult to package as it depends on a few
12394 ;; unpackaged libraries.
12395 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12397 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12398 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12399 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12400 (("pdf_written_to = PdfExporter.*")
12401 "throw new IOException(\"PDF export is not available.\"); /*")
12402 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12403 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12405 (add-after 'unpack 'delete-pre-built-classes
12406 (lambda _ (delete-file-recursively "src/classes") #t))
12407 ;; There is no install target
12408 (replace 'install (install-jars ".")))))
12410 `(("java-commons-codec" ,java-commons-codec)
12411 ("java-openchart2" ,java-openchart2)))
12412 ;; The source archive does not contain the resources.
12417 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12418 "b61cc2dcede0bede317db362472333115756b8c6/"
12419 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12420 (file-name (string-append name "-phyloxml-" version ".xsd"))
12423 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12424 ("synth_look_and_feel_1.xml"
12427 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12428 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12429 "forester/java/classes/resources/"
12430 "synth_look_and_feel_1.xml"))
12431 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12434 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12435 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12436 (synopsis "Phylogenomics libraries for Java")
12437 (description "Forester is a collection of Java libraries for
12438 phylogenomics and evolutionary biology research. It includes support for
12439 reading, writing, and exporting phylogenetic trees.")
12440 (license license:lgpl2.1+)))
12442 (define-public java-biojava-core
12444 (name "java-biojava-core")
12448 (uri (git-reference
12449 (url "https://github.com/biojava/biojava")
12450 (commit (string-append "biojava-" version))))
12451 (file-name (string-append name "-" version "-checkout"))
12454 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12455 (build-system ant-build-system)
12458 #:jar-name "biojava-core.jar"
12459 #:source-dir "biojava-core/src/main/java/"
12460 #:test-dir "biojava-core/src/test"
12461 ;; These tests seem to require internet access.
12462 #:test-exclude (list "**/SearchIOTest.java"
12463 "**/BlastXMLParserTest.java"
12464 "**/GenbankCookbookTest.java"
12465 "**/GenbankProxySequenceReaderTest.java")
12467 (modify-phases %standard-phases
12468 (add-before 'build 'copy-resources
12470 (copy-recursively "biojava-core/src/main/resources"
12473 (add-before 'check 'copy-test-resources
12475 (copy-recursively "biojava-core/src/test/resources"
12476 "build/test-classes")
12479 `(("java-log4j-api" ,java-log4j-api)
12480 ("java-log4j-core" ,java-log4j-core)
12481 ("java-slf4j-api" ,java-slf4j-api)
12482 ("java-slf4j-simple" ,java-slf4j-simple)))
12484 `(("java-junit" ,java-junit)
12485 ("java-hamcrest-core" ,java-hamcrest-core)))
12486 (home-page "http://biojava.org")
12487 (synopsis "Core libraries of Java framework for processing biological data")
12488 (description "BioJava is a project dedicated to providing a Java framework
12489 for processing biological data. It provides analytical and statistical
12490 routines, parsers for common file formats, reference implementations of
12491 popular algorithms, and allows the manipulation of sequences and 3D
12492 structures. The goal of the biojava project is to facilitate rapid
12493 application development for bioinformatics.
12495 This package provides the core libraries.")
12496 (license license:lgpl2.1+)))
12498 (define-public java-biojava-phylo
12499 (package (inherit java-biojava-core)
12500 (name "java-biojava-phylo")
12501 (build-system ant-build-system)
12504 #:jar-name "biojava-phylo.jar"
12505 #:source-dir "biojava-phylo/src/main/java/"
12506 #:test-dir "biojava-phylo/src/test"
12508 (modify-phases %standard-phases
12509 (add-before 'build 'copy-resources
12511 (copy-recursively "biojava-phylo/src/main/resources"
12514 (add-before 'check 'copy-test-resources
12516 (copy-recursively "biojava-phylo/src/test/resources"
12517 "build/test-classes")
12520 `(("java-log4j-api" ,java-log4j-api)
12521 ("java-log4j-core" ,java-log4j-core)
12522 ("java-slf4j-api" ,java-slf4j-api)
12523 ("java-slf4j-simple" ,java-slf4j-simple)
12524 ("java-biojava-core" ,java-biojava-core)
12525 ("java-forester" ,java-forester)))
12527 `(("java-junit" ,java-junit)
12528 ("java-hamcrest-core" ,java-hamcrest-core)))
12529 (home-page "http://biojava.org")
12530 (synopsis "Biojava interface to the forester phylogenomics library")
12531 (description "The phylo module provides a biojava interface layer to the
12532 forester phylogenomics library for constructing phylogenetic trees.")))
12534 (define-public java-biojava-alignment
12535 (package (inherit java-biojava-core)
12536 (name "java-biojava-alignment")
12537 (build-system ant-build-system)
12540 #:jar-name "biojava-alignment.jar"
12541 #:source-dir "biojava-alignment/src/main/java/"
12542 #:test-dir "biojava-alignment/src/test"
12544 (modify-phases %standard-phases
12545 (add-before 'build 'copy-resources
12547 (copy-recursively "biojava-alignment/src/main/resources"
12550 (add-before 'check 'copy-test-resources
12552 (copy-recursively "biojava-alignment/src/test/resources"
12553 "build/test-classes")
12556 `(("java-log4j-api" ,java-log4j-api)
12557 ("java-log4j-core" ,java-log4j-core)
12558 ("java-slf4j-api" ,java-slf4j-api)
12559 ("java-slf4j-simple" ,java-slf4j-simple)
12560 ("java-biojava-core" ,java-biojava-core)
12561 ("java-biojava-phylo" ,java-biojava-phylo)
12562 ("java-forester" ,java-forester)))
12564 `(("java-junit" ,java-junit)
12565 ("java-hamcrest-core" ,java-hamcrest-core)))
12566 (home-page "http://biojava.org")
12567 (synopsis "Biojava API for genetic sequence alignment")
12568 (description "The alignment module of BioJava provides an API that
12572 @item implementations of dynamic programming algorithms for sequence
12574 @item reading and writing of popular alignment file formats;
12575 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12578 (define-public java-biojava-core-4.0
12579 (package (inherit java-biojava-core)
12580 (name "java-biojava-core")
12584 (uri (git-reference
12585 (url "https://github.com/biojava/biojava")
12586 (commit (string-append "biojava-" version))))
12587 (file-name (string-append name "-" version "-checkout"))
12590 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12592 (define-public java-biojava-phylo-4.0
12593 (package (inherit java-biojava-core-4.0)
12594 (name "java-biojava-phylo")
12595 (build-system ant-build-system)
12598 #:jar-name "biojava-phylo.jar"
12599 #:source-dir "biojava-phylo/src/main/java/"
12600 #:test-dir "biojava-phylo/src/test"
12602 (modify-phases %standard-phases
12603 (add-before 'build 'copy-resources
12605 (copy-recursively "biojava-phylo/src/main/resources"
12608 (add-before 'check 'copy-test-resources
12610 (copy-recursively "biojava-phylo/src/test/resources"
12611 "build/test-classes")
12614 `(("java-log4j-api" ,java-log4j-api)
12615 ("java-log4j-core" ,java-log4j-core)
12616 ("java-slf4j-api" ,java-slf4j-api)
12617 ("java-slf4j-simple" ,java-slf4j-simple)
12618 ("java-biojava-core" ,java-biojava-core-4.0)
12619 ("java-forester" ,java-forester-1.005)))
12621 `(("java-junit" ,java-junit)
12622 ("java-hamcrest-core" ,java-hamcrest-core)))
12623 (home-page "http://biojava.org")
12624 (synopsis "Biojava interface to the forester phylogenomics library")
12625 (description "The phylo module provides a biojava interface layer to the
12626 forester phylogenomics library for constructing phylogenetic trees.")))
12628 (define-public java-biojava-alignment-4.0
12629 (package (inherit java-biojava-core-4.0)
12630 (name "java-biojava-alignment")
12631 (build-system ant-build-system)
12634 #:jar-name "biojava-alignment.jar"
12635 #:source-dir "biojava-alignment/src/main/java/"
12636 #:test-dir "biojava-alignment/src/test"
12638 (modify-phases %standard-phases
12639 (add-before 'build 'copy-resources
12641 (copy-recursively "biojava-alignment/src/main/resources"
12644 (add-before 'check 'copy-test-resources
12646 (copy-recursively "biojava-alignment/src/test/resources"
12647 "build/test-classes")
12650 `(("java-log4j-api" ,java-log4j-api)
12651 ("java-log4j-core" ,java-log4j-core)
12652 ("java-slf4j-api" ,java-slf4j-api)
12653 ("java-slf4j-simple" ,java-slf4j-simple)
12654 ("java-biojava-core" ,java-biojava-core-4.0)
12655 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12656 ("java-forester" ,java-forester-1.005)))
12658 `(("java-junit" ,java-junit)
12659 ("java-hamcrest-core" ,java-hamcrest-core)))
12660 (home-page "http://biojava.org")
12661 (synopsis "Biojava API for genetic sequence alignment")
12662 (description "The alignment module of BioJava provides an API that
12666 @item implementations of dynamic programming algorithms for sequence
12668 @item reading and writing of popular alignment file formats;
12669 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12672 (define-public dropseq-tools
12674 (name "dropseq-tools")
12679 (uri "http://mccarrolllab.com/download/1276/")
12680 (file-name (string-append "dropseq-tools-" version ".zip"))
12683 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12684 ;; Delete bundled libraries
12685 (modules '((guix build utils)))
12688 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12689 (delete-file-recursively "3rdParty")
12691 (build-system ant-build-system)
12693 `(#:tests? #f ; test data are not included
12694 #:test-target "test"
12695 #:build-target "all"
12696 #:source-dir "public/src/"
12699 (list (string-append "-Dpicard.executable.dir="
12700 (assoc-ref %build-inputs "java-picard")
12702 #:modules ((ice-9 match)
12705 (guix build java-utils)
12706 (guix build ant-build-system))
12708 (modify-phases %standard-phases
12709 ;; FIXME: fails with "java.io.FileNotFoundException:
12710 ;; /gnu/store/…-dropseq-tools-1.13/share/java/lib/biojava-alignment.jar"
12711 (delete 'generate-jar-indices)
12712 ;; All dependencies must be linked to "lib", because that's where
12713 ;; they will be searched for when the Class-Path property of the
12714 ;; manifest is computed.
12715 (add-after 'unpack 'record-references
12716 (lambda* (#:key inputs #:allow-other-keys)
12717 (mkdir-p "jar/lib")
12718 (let ((dirs (filter-map (match-lambda
12720 (if (and (string-prefix? "java-" name)
12721 (not (string=? name "java-testng")))
12724 (for-each (lambda (jar)
12725 (symlink jar (string-append "jar/lib/" (basename jar))))
12726 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12729 ;; There is no installation target
12731 (lambda* (#:key inputs outputs #:allow-other-keys)
12732 (let* ((out (assoc-ref outputs "out"))
12733 (bin (string-append out "/bin"))
12734 (share (string-append out "/share/java/"))
12735 (lib (string-append share "/lib/"))
12736 (scripts (list "BAMTagHistogram"
12737 "BAMTagofTagCounts"
12738 "BaseDistributionAtReadPosition"
12739 "CollapseBarcodesInPlace"
12740 "CollapseTagWithContext"
12742 "CreateIntervalsFiles"
12743 "DetectBeadSynthesisErrors"
12744 "DigitalExpression"
12745 "Drop-seq_alignment.sh"
12748 "GatherGeneGCLength"
12749 "GatherMolecularBarcodeDistributionByGene"
12750 "GatherReadQualityMetrics"
12753 "SelectCellsByNumTranscripts"
12754 "SingleCellRnaSeqMetricsCollector"
12755 "TagBamWithReadSequenceExtended"
12756 "TagReadWithGeneExon"
12757 "TagReadWithInterval"
12758 "TrimStartingSequence"
12759 "ValidateReference")))
12760 (for-each mkdir-p (list bin share lib))
12761 (install-file "dist/dropseq.jar" share)
12762 (for-each (lambda (script)
12763 (chmod script #o555)
12764 (install-file script bin))
12766 (substitute* (map (lambda (script)
12767 (string-append bin "/" script))
12769 (("^java") (which "java"))
12770 (("jar_deploy_dir=.*")
12771 (string-append "jar_deploy_dir=" share "\n"))))
12773 ;; FIXME: We do this after stripping jars because we don't want it to
12774 ;; copy all these jars and strip them. We only want to install
12775 ;; links. Arguably, this is a problem with the ant-build-system.
12776 (add-after 'strip-jar-timestamps 'install-links
12777 (lambda* (#:key outputs #:allow-other-keys)
12778 (let* ((out (assoc-ref outputs "out"))
12779 (share (string-append out "/share/java/"))
12780 (lib (string-append share "/lib/")))
12781 (for-each (lambda (jar)
12782 (symlink (readlink jar)
12783 (string-append lib (basename jar))))
12784 (find-files "jar/lib" "\\.jar$")))
12787 `(("jdk" ,icedtea-8)
12788 ("java-picard" ,java-picard-2.10.3)
12789 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12790 ("java-commons-math3" ,java-commons-math3)
12791 ("java-commons-jexl2" ,java-commons-jexl-2)
12792 ("java-commons-collections4" ,java-commons-collections4)
12793 ("java-commons-lang2" ,java-commons-lang)
12794 ("java-commons-io" ,java-commons-io)
12795 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12796 ("java-guava" ,java-guava)
12797 ("java-la4j" ,java-la4j)
12798 ("java-biojava-core" ,java-biojava-core-4.0)
12799 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12800 ("java-jdistlib" ,java-jdistlib)
12801 ("java-simple-xml" ,java-simple-xml)
12802 ("java-snakeyaml" ,java-snakeyaml)))
12805 ("java-testng" ,java-testng)))
12806 (home-page "http://mccarrolllab.com/dropseq/")
12807 (synopsis "Tools for Drop-seq analyses")
12808 (description "Drop-seq is a technology to enable biologists to
12809 analyze RNA expression genome-wide in thousands of individual cells at
12810 once. This package provides tools to perform Drop-seq analyses.")
12811 (license license:expat)))
12813 (define-public pigx-rnaseq
12815 (name "pigx-rnaseq")
12819 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12820 "releases/download/v" version
12821 "/pigx_rnaseq-" version ".tar.gz"))
12824 "0z3hr120wk2vrlmlpz1vp3n9wy3rq4y2mnzh2vf08qgqn2xfdwcw"))))
12825 (build-system gnu-build-system)
12827 `(#:parallel-tests? #f ; not supported
12829 (modify-phases %standard-phases
12830 ;; "test.sh" runs STAR, which requires excessive amounts of memory.
12831 (add-after 'unpack 'disable-resource-intensive-test
12833 (substitute* "Makefile.in"
12834 (("(^ tests/test_trim_galore/test.sh).*" _ m) m)
12835 (("^ tests/test_multiqc/test.sh") "")
12836 (("^ test.sh") ""))
12839 `(("coreutils" ,coreutils)
12842 ("snakemake" ,snakemake)
12844 ("multiqc" ,multiqc)
12846 ("trim-galore" ,trim-galore)
12848 ("samtools" ,samtools)
12849 ("r-minimal" ,r-minimal)
12850 ("r-rmarkdown" ,r-rmarkdown)
12851 ("r-ggplot2" ,r-ggplot2)
12852 ("r-ggrepel" ,r-ggrepel)
12853 ("r-gprofiler" ,r-gprofiler)
12854 ("r-deseq2" ,r-deseq2)
12856 ("r-knitr" ,r-knitr)
12857 ("r-pheatmap" ,r-pheatmap)
12858 ("r-corrplot" ,r-corrplot)
12859 ("r-reshape2" ,r-reshape2)
12860 ("r-plotly" ,r-plotly)
12861 ("r-scales" ,r-scales)
12862 ("r-summarizedexperiment" ,r-summarizedexperiment)
12863 ("r-crosstalk" ,r-crosstalk)
12864 ("r-tximport" ,r-tximport)
12865 ("r-rtracklayer" ,r-rtracklayer)
12866 ("r-rjson" ,r-rjson)
12868 ("ghc-pandoc" ,ghc-pandoc)
12869 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12870 ("python-wrapper" ,python-wrapper)
12871 ("python-pyyaml" ,python-pyyaml)))
12872 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12873 (synopsis "Analysis pipeline for RNA sequencing experiments")
12874 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
12875 reporting for RNA sequencing experiments. It is easy to use and produces high
12876 quality reports. The inputs are reads files from the sequencing experiment,
12877 and a configuration file which describes the experiment. In addition to
12878 quality control of the experiment, the pipeline produces a differential
12879 expression report comparing samples in an easily configurable manner.")
12880 (license license:gpl3+)))
12882 (define-public pigx-chipseq
12884 (name "pigx-chipseq")
12888 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
12889 "releases/download/v" version
12890 "/pigx_chipseq-" version ".tar.gz"))
12893 "0xbvgqpk32a8iczhvac56cacr46rdkqb0allhhpvmj940idf72bi"))))
12894 (build-system gnu-build-system)
12895 ;; parts of the tests rely on access to the network
12896 (arguments '(#:tests? #f))
12899 ("coreutils" ,coreutils)
12900 ("r-minimal" ,r-minimal)
12901 ("r-argparser" ,r-argparser)
12902 ("r-biocparallel" ,r-biocparallel)
12903 ("r-biostrings" ,r-biostrings)
12904 ("r-chipseq" ,r-chipseq)
12905 ("r-data-table" ,r-data-table)
12906 ("r-dplyr" ,r-dplyr)
12907 ("r-genomation" ,r-genomation)
12908 ("r-genomicalignments" ,r-genomicalignments)
12909 ("r-genomicranges" ,r-genomicranges)
12910 ("r-rsamtools" ,r-rsamtools)
12911 ("r-rtracklayer" ,r-rtracklayer)
12912 ("r-s4vectors" ,r-s4vectors)
12913 ("r-stringr" ,r-stringr)
12914 ("r-tibble" ,r-tibble)
12915 ("r-tidyr" ,r-tidyr)
12916 ("r-jsonlite" ,r-jsonlite)
12917 ("r-heatmaply" ,r-heatmaply)
12918 ("r-htmlwidgets" ,r-htmlwidgets)
12919 ("r-ggplot2" ,r-ggplot2)
12920 ("r-plotly" ,r-plotly)
12921 ("r-rmarkdown" ,r-rmarkdown)
12922 ("python-wrapper" ,python-wrapper)
12923 ("python-pyyaml" ,python-pyyaml)
12924 ("python-magic" ,python-magic)
12925 ("python-xlrd" ,python-xlrd)
12926 ("trim-galore" ,trim-galore)
12928 ("multiqc" ,multiqc)
12930 ("ghc-pandoc" ,ghc-pandoc)
12931 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12935 ("snakemake" ,snakemake)
12936 ("samtools" ,samtools)
12937 ("bedtools" ,bedtools)
12938 ("kentutils" ,kentutils)))
12940 `(("python-pytest" ,python-pytest)))
12941 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12942 (synopsis "Analysis pipeline for ChIP sequencing experiments")
12943 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
12944 calling and reporting for ChIP sequencing experiments. It is easy to use and
12945 produces high quality reports. The inputs are reads files from the sequencing
12946 experiment, and a configuration file which describes the experiment. In
12947 addition to quality control of the experiment, the pipeline enables to set up
12948 multiple peak calling analysis and allows the generation of a UCSC track hub
12949 in an easily configurable manner.")
12950 (license license:gpl3+)))
12952 (define-public pigx-bsseq
12954 (name "pigx-bsseq")
12958 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
12959 "releases/download/v" version
12960 "/pigx_bsseq-" version ".tar.gz"))
12963 "0l97wvkq4diq8lcarraj33bby1zzf0w804jwi8mlc5qddp8idwhy"))))
12964 (build-system gnu-build-system)
12967 (modify-phases %standard-phases
12968 (add-before 'check 'set-timezone
12969 ;; The readr package is picky about timezones.
12970 (lambda* (#:key inputs #:allow-other-keys)
12971 (setenv "TZ" "UTC+1")
12973 (string-append (assoc-ref inputs "tzdata")
12974 "/share/zoneinfo"))
12977 `(("tzdata" ,tzdata)))
12979 `(("coreutils" ,coreutils)
12982 ("r-minimal" ,r-minimal)
12983 ("r-annotationhub" ,r-annotationhub)
12985 ("r-genomation" ,r-genomation)
12986 ("r-methylkit" ,r-methylkit)
12987 ("r-rtracklayer" ,r-rtracklayer)
12988 ("r-rmarkdown" ,r-rmarkdown)
12989 ("r-bookdown" ,r-bookdown)
12990 ("r-ggplot2" ,r-ggplot2)
12991 ("r-ggbio" ,r-ggbio)
12992 ("ghc-pandoc" ,ghc-pandoc)
12993 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12994 ("python-wrapper" ,python-wrapper)
12995 ("python-pyyaml" ,python-pyyaml)
12996 ("snakemake" ,snakemake)
12997 ("bismark" ,bismark)
13000 ("trim-galore" ,trim-galore)
13001 ("cutadapt" ,cutadapt)
13002 ("samtools" ,samtools)))
13003 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13004 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
13005 (description "PiGx BSseq is a data processing pipeline for raw fastq read
13006 data of bisulfite experiments; it produces reports on aggregate methylation
13007 and coverage and can be used to produce information on differential
13008 methylation and segmentation.")
13009 (license license:gpl3+)))
13011 (define-public pigx-scrnaseq
13013 (name "pigx-scrnaseq")
13017 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/"
13018 "releases/download/v" version
13019 "/pigx_scrnaseq-" version ".tar.gz"))
13022 "1d5l3gywypi67yz9advxq5xkgfhr4733gj0bwnngm723i3hdf5w9"))))
13023 (build-system gnu-build-system)
13025 `(("coreutils" ,coreutils)
13028 ("flexbar" ,flexbar)
13029 ("java" ,icedtea-8)
13030 ("jellyfish" ,jellyfish)
13031 ("python-wrapper" ,python-wrapper)
13032 ("python-pyyaml" ,python-pyyaml)
13033 ("python-pandas" ,python-pandas)
13034 ("python-magic" ,python-magic)
13035 ("python-numpy" ,python-numpy)
13036 ("python-loompy" ,python-loompy)
13037 ("ghc-pandoc" ,ghc-pandoc)
13038 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
13039 ("samtools" ,samtools)
13040 ("snakemake" ,snakemake)
13042 ("r-minimal" ,r-minimal)
13043 ("r-argparser" ,r-argparser)
13044 ("r-cowplot" ,r-cowplot)
13045 ("r-data-table" ,r-data-table)
13046 ("r-delayedarray" ,r-delayedarray)
13047 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
13048 ("r-dplyr" ,r-dplyr)
13049 ("r-dropbead" ,r-dropbead)
13051 ("r-genomicalignments" ,r-genomicalignments)
13052 ("r-genomicfiles" ,r-genomicfiles)
13053 ("r-genomicranges" ,r-genomicranges)
13054 ("r-ggplot2" ,r-ggplot2)
13055 ("r-hdf5array" ,r-hdf5array)
13056 ("r-pheatmap" ,r-pheatmap)
13057 ("r-rmarkdown" ,r-rmarkdown)
13058 ("r-rsamtools" ,r-rsamtools)
13059 ("r-rtracklayer" ,r-rtracklayer)
13060 ("r-rtsne" ,r-rtsne)
13061 ("r-scater" ,r-scater)
13062 ("r-scran" ,r-scran)
13063 ("r-seurat" ,r-seurat)
13064 ("r-singlecellexperiment" ,r-singlecellexperiment)
13065 ("r-stringr" ,r-stringr)
13066 ("r-yaml" ,r-yaml)))
13067 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13068 (synopsis "Analysis pipeline for single-cell RNA sequencing experiments")
13069 (description "PiGX scRNAseq is an analysis pipeline for preprocessing and
13070 quality control for single cell RNA sequencing experiments. The inputs are
13071 read files from the sequencing experiment, and a configuration file which
13072 describes the experiment. It produces processed files for downstream analysis
13073 and interactive quality reports. The pipeline is designed to work with UMI
13075 (license license:gpl3+)))
13077 (define-public pigx
13083 (uri (string-append "https://github.com/BIMSBbioinfo/pigx/"
13084 "releases/download/v" version
13085 "/pigx-" version ".tar.gz"))
13088 "1i5njdy1clj5ncw45d16p7mwmqvb1ilikl9n797pxklc3f4s7mq7"))))
13089 (build-system gnu-build-system)
13091 `(("python" ,python)
13092 ("pigx-bsseq" ,pigx-bsseq)
13093 ("pigx-chipseq" ,pigx-chipseq)
13094 ("pigx-rnaseq" ,pigx-rnaseq)
13095 ("pigx-scrnaseq" ,pigx-scrnaseq)))
13096 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13097 (synopsis "Analysis pipelines for genomics")
13098 (description "PiGx is a collection of genomics pipelines. It includes the
13099 following pipelines:
13102 @item PiGx BSseq for raw fastq read data of bisulfite experiments
13103 @item PiGx RNAseq for RNAseq samples
13104 @item PiGx scRNAseq for single cell dropseq analysis
13105 @item PiGx ChIPseq for reads from ChIPseq experiments
13108 All pipelines are easily configured with a simple sample sheet and a
13109 descriptive settings file. The result is a set of comprehensive, interactive
13110 HTML reports with interesting findings about your samples.")
13111 (license license:gpl3+)))
13113 (define-public genrich
13119 (uri (git-reference
13120 (url "https://github.com/jsh58/Genrich.git")
13121 (commit (string-append "v" version))))
13122 (file-name (git-file-name name version))
13125 "0x0q6z0208n3cxzqjla4rgjqpyqgwpmz27852lcvzkzaigymq4zp"))))
13126 (build-system gnu-build-system)
13128 `(#:tests? #f ; there are none
13130 (modify-phases %standard-phases
13131 (delete 'configure)
13133 (lambda* (#:key outputs #:allow-other-keys)
13134 (install-file "Genrich" (string-append (assoc-ref outputs "out") "/bin"))
13138 (home-page "https://github.com/jsh58/Genrich")
13139 (synopsis "Detecting sites of genomic enrichment")
13140 (description "Genrich is a peak-caller for genomic enrichment
13141 assays (e.g. ChIP-seq, ATAC-seq). It analyzes alignment files generated
13142 following the assay and produces a file detailing peaks of significant
13144 (license license:expat)))
13146 (define-public mantis
13147 (let ((commit "4ffd171632c2cb0056a86d709dfd2bf21bc69b84")
13151 (version (git-version "0" revision commit))
13154 (uri (git-reference
13155 (url "https://github.com/splatlab/mantis.git")
13157 (file-name (git-file-name name version))
13160 "0iqbr0dhmlc8mzpirmm2s4pkzkwdgrcx50yx6cv3wlr2qi064p55"))))
13161 (build-system cmake-build-system)
13162 (arguments '(#:tests? #f)) ; there are none
13164 `(("sdsl-lite" ,sdsl-lite)
13165 ("openssl" ,openssl)
13167 (home-page "https://github.com/splatlab/mantis")
13168 (synopsis "Large-scale sequence-search index data structure")
13169 (description "Mantis is a space-efficient data structure that can be
13170 used to index thousands of raw-read genomics experiments and facilitate
13171 large-scale sequence searches on those experiments. Mantis uses counting
13172 quotient filters instead of Bloom filters, enabling rapid index builds and
13173 queries, small indexes, and exact results, i.e., no false positives or
13174 negatives. Furthermore, Mantis is also a colored de Bruijn graph
13175 representation, so it supports fast graph traversal and other topological
13176 analyses in addition to large-scale sequence-level searches.")
13177 ;; uses __uint128_t and inline assembly
13178 (supported-systems '("x86_64-linux"))
13179 (license license:bsd-3))))
13181 (define-public r-diversitree
13183 (name "r-diversitree")
13188 (uri (cran-uri "diversitree" version))
13191 "00vi4klywi35hd170ksjv3xja3hqqbkcidcnrrlpgv4179k0azix"))))
13192 (build-system r-build-system)
13194 `(("gfortran" ,gfortran)))
13195 (inputs `(("fftw" ,fftw) ("gsl" ,gsl)))
13198 ("r-desolve" ,r-desolve)
13200 ("r-subplex" ,r-subplex)))
13201 (home-page "https://www.zoology.ubc.ca/prog/diversitree")
13202 (synopsis "Comparative 'phylogenetic' analyses of diversification")
13203 (description "This package contains a number of comparative \"phylogenetic\"
13204 methods, mostly focusing on analysing diversification and character evolution.
13205 Contains implementations of \"BiSSE\" (Binary State Speciation and Extinction)
13206 and its unresolved tree extensions, \"MuSSE\" (Multiple State Speciation and
13207 Extinction), \"QuaSSE\", \"GeoSSE\", and \"BiSSE-ness\" Other included methods
13208 include Markov models of discrete and continuous trait evolution and constant
13209 rate speciation and extinction.")
13210 (license license:gpl2+)))
13212 (define-public sjcount
13213 ;; There is no tag for version 3.2, nor is there a release archive.
13214 (let ((commit "292d3917cadb3f6834c81e509c30e61cd7ead6e5")
13218 (version (git-version "3.2" revision commit))
13221 (uri (git-reference
13222 (url "https://github.com/pervouchine/sjcount-full.git")
13224 (file-name (string-append name "-" version "-checkout"))
13227 "0gdgj35j249f04rqgq8ymcc1xg1vi9kzbajnjqpaq2wpbh8bl234"))))
13228 (build-system gnu-build-system)
13230 `(#:tests? #f ; requires a 1.4G test file
13232 (list (string-append "SAMTOOLS_DIR="
13233 (assoc-ref %build-inputs "samtools")
13236 (modify-phases %standard-phases
13237 (replace 'configure
13238 (lambda* (#:key inputs #:allow-other-keys)
13239 (substitute* "makefile"
13240 (("-I \\$\\{SAMTOOLS_DIR\\}")
13241 (string-append "-I" (assoc-ref inputs "samtools")
13242 "/include/samtools"))
13243 (("-lz ") "-lz -lpthread "))
13246 (lambda* (#:key outputs #:allow-other-keys)
13247 (for-each (lambda (tool)
13249 (string-append (assoc-ref outputs "out")
13251 '("j_count" "b_count" "sjcount"))
13254 `(("samtools" ,samtools-0.1)
13256 (home-page "https://github.com/pervouchine/sjcount-full/")
13257 (synopsis "Annotation-agnostic splice junction counting pipeline")
13258 (description "Sjcount is a utility for fast quantification of splice
13259 junctions in RNA-seq data. It is annotation-agnostic and offset-aware. This
13260 version does count multisplits.")
13261 (license license:gpl3+))))
13263 (define-public minimap2
13270 (uri (string-append "https://github.com/lh3/minimap2/"
13271 "releases/download/v" version "/"
13272 "minimap2-" version ".tar.bz2"))
13275 "0hi7i9pzxhvjj44khzzzj1lrn5gb5837arr4wgln7k1k5n4ci2mn"))))
13276 (build-system gnu-build-system)
13278 `(#:tests? #f ; there are none
13281 (let ((system ,(or (%current-target-system)
13282 (%current-system))))
13284 ((string-prefix? "x86_64" system)
13286 ((or (string-prefix? "armhf" system)
13287 (string-prefix? "aarch64" system))
13289 (else "sse2only=1"))))
13291 (modify-phases %standard-phases
13292 (delete 'configure)
13294 (lambda* (#:key outputs #:allow-other-keys)
13295 (let* ((out (assoc-ref outputs "out"))
13296 (bin (string-append out "/bin"))
13297 (man (string-append out "/share/man/man1")))
13298 (install-file "minimap2" bin)
13300 (install-file "minimap2.1" man))
13304 (home-page "https://lh3.github.io/minimap2/")
13305 (synopsis "Pairwise aligner for genomic and spliced nucleotide sequences")
13306 (description "Minimap2 is a versatile sequence alignment program that
13307 aligns DNA or mRNA sequences against a large reference database. Typical use
13311 @item mapping PacBio or Oxford Nanopore genomic reads to the human genome;
13312 @item finding overlaps between long reads with error rate up to ~15%;
13313 @item splice-aware alignment of PacBio Iso-Seq or Nanopore cDNA or Direct RNA
13314 reads against a reference genome;
13315 @item aligning Illumina single- or paired-end reads;
13316 @item assembly-to-assembly alignment;
13317 @item full-genome alignment between two closely related species with
13318 divergence below ~15%.
13320 (license license:expat)))
13322 (define-public miniasm
13328 (uri (string-append
13329 "https://github.com/lh3/miniasm/archive/v"
13330 version ".tar.gz"))
13331 (file-name (string-append name "-" version ".tar.gz"))
13334 "0g89pa98dvh34idv7w1zv12bsbyr3a11c4qb1cdcz68gyda88s4v"))))
13335 (build-system gnu-build-system)
13339 `(#:tests? #f ; There are no tests.
13341 (modify-phases %standard-phases
13342 (delete 'configure)
13344 (lambda* (#:key inputs outputs #:allow-other-keys)
13345 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
13346 (install-file "miniasm" bin)
13347 (install-file "minidot" bin)))))))
13348 (home-page "https://github.com/lh3/miniasm")
13349 (synopsis "Ultrafast de novo assembly for long noisy reads")
13350 (description "Miniasm is a very fast OLC-based de novo assembler for noisy
13351 long reads. It takes all-vs-all read self-mappings (typically by minimap) as
13352 input and outputs an assembly graph in the GFA format. Different from
13353 mainstream assemblers, miniasm does not have a consensus step. It simply
13354 concatenates pieces of read sequences to generate the final unitig sequences.
13355 Thus the per-base error rate is similar to the raw input reads.")
13356 (license license:expat)))
13358 (define-public r-circus
13365 (uri (git-reference
13366 (url "https://github.com/BIMSBbioinfo/ciRcus.git")
13367 (commit (string-append "v" version))))
13368 (file-name (git-file-name name version))
13371 "0jhjn3ilb057hbf6yzrihj13ifxxs32y7nkby8l3lkm28dg4p97h"))))
13372 (build-system r-build-system)
13374 `(("r-annotationdbi" ,r-annotationdbi)
13375 ("r-annotationhub" ,r-annotationhub)
13376 ("r-biomart" ,r-biomart)
13377 ("r-data-table" ,r-data-table)
13379 ("r-genomicfeatures" ,r-genomicfeatures)
13380 ("r-genomicranges" ,r-genomicranges)
13381 ("r-ggplot2" ,r-ggplot2)
13383 ("r-iranges" ,r-iranges)
13384 ("r-rcolorbrewer" ,r-rcolorbrewer)
13385 ("r-rmysql" ,r-rmysql)
13386 ("r-s4vectors" ,r-s4vectors)
13387 ("r-stringr" ,r-stringr)
13388 ("r-summarizedexperiment" ,r-summarizedexperiment)))
13390 `(("r-knitr" ,r-knitr)))
13391 (home-page "https://github.com/BIMSBbioinfo/ciRcus")
13392 (synopsis "Annotation, analysis and visualization of circRNA data")
13393 (description "Circus is an R package for annotation, analysis and
13394 visualization of circRNA data. Users can annotate their circRNA candidates
13395 with host genes, gene featrues they are spliced from, and discriminate between
13396 known and yet unknown splice junctions. Circular-to-linear ratios of circRNAs
13397 can be calculated, and a number of descriptive plots easily generated.")
13398 (license license:artistic2.0)))
13400 (define-public gffread
13401 ;; We cannot use the tagged release because it is not in sync with gclib.
13402 ;; See https://github.com/gpertea/gffread/issues/26
13403 (let ((commit "ba7535fcb3cea55a6e5a491d916e93b454e87fd0")
13407 (version (git-version "0.9.12" revision commit))
13411 (uri (git-reference
13412 (url "https://github.com/gpertea/gffread.git")
13414 (file-name (git-file-name name version))
13417 "1dl2nbcg96lxpd0drg48ssa8343nf7pw9s9mkrc4mjjmfwsin3ki"))))
13418 (build-system gnu-build-system)
13420 `(#:tests? #f ; no check target
13422 (list "GCLDIR=gclib")
13424 (modify-phases %standard-phases
13425 (delete 'configure)
13426 (add-after 'unpack 'copy-gclib-source
13427 (lambda* (#:key inputs #:allow-other-keys)
13429 (copy-recursively (assoc-ref inputs "gclib-source") "gclib")
13431 ;; There is no install target
13433 (lambda* (#:key outputs #:allow-other-keys)
13434 (let* ((out (assoc-ref outputs "out"))
13435 (bin (string-append out "/bin")))
13436 (install-file "gffread" bin))
13440 ,(let ((version "0.10.3")
13441 (commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13445 (uri (git-reference
13446 (url "https://github.com/gpertea/gclib.git")
13448 (file-name (git-file-name "gclib" version))
13451 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13452 (home-page "https://github.com/gpertea/gffread/")
13453 (synopsis "Parse and convert GFF/GTF files")
13455 "This package provides a GFF/GTF file parsing utility providing format
13456 conversions, region filtering, FASTA sequence extraction and more.")
13457 ;; gffread is under Expat, but gclib is under Artistic 2.0
13458 (license (list license:expat
13459 license:artistic2.0)))))
13461 (define-public find-circ
13462 ;; The last release was in 2015. The license was clarified in 2017, so we
13463 ;; take the latest commit.
13464 (let ((commit "8655dca54970fcf7e92e22fbf57e1188724dda7d")
13468 (version (git-version "1.2" revision commit))
13472 (uri (git-reference
13473 (url "https://github.com/marvin-jens/find_circ.git")
13475 (file-name (git-file-name name version))
13478 "0p77pbqbclqr4srms34y1b9b4njybfpjiknc11ki84f3p8skb3cg"))))
13479 (build-system gnu-build-system)
13481 `(#:tests? #f ; there are none
13483 ;; There is no actual build system.
13484 (modify-phases %standard-phases
13485 (delete 'configure)
13488 (lambda* (#:key outputs #:allow-other-keys)
13489 (let* ((out (assoc-ref outputs "out"))
13490 (bin (string-append out "/bin"))
13491 (path (getenv "PYTHONPATH")))
13492 (for-each (lambda (script)
13493 (install-file script bin)
13494 (wrap-program (string-append bin "/" script)
13495 `("PYTHONPATH" ":" prefix (,path))))
13500 "unmapped2anchors.py")))
13503 `(("python2" ,python-2)
13504 ("python2-pysam" ,python2-pysam)
13505 ("python2-numpy" ,python2-numpy)))
13506 (home-page "https://github.com/marvin-jens/find_circ")
13507 (synopsis "circRNA detection from RNA-seq reads")
13508 (description "This package provides tools to detect head-to-tail
13509 spliced (back-spliced) sequencing reads, indicative of circular RNA (circRNA)
13511 (license license:gpl3))))
13513 (define-public python-scanpy
13515 (name "python-scanpy")
13520 (uri (pypi-uri "scanpy" version))
13523 "0s2b6cvaigx4wzw3850qb93sjwwxbzh22kpbp498zklc5rjpbz4l"))))
13524 (build-system python-build-system)
13527 (modify-phases %standard-phases
13529 (lambda* (#:key inputs #:allow-other-keys)
13530 ;; These tests require Internet access.
13531 (delete-file-recursively "scanpy/tests/notebooks")
13532 (delete-file "scanpy/tests/test_clustering.py")
13533 (delete-file "scanpy/tests/test_datasets.py")
13535 ;; TODO: I can't get the plotting tests to work, even with Xvfb.
13536 (delete-file "scanpy/tests/test_plotting.py")
13537 (delete-file "scanpy/tests/test_preprocessing.py")
13538 (delete-file "scanpy/tests/test_read_10x.py")
13540 (setenv "PYTHONPATH"
13541 (string-append (getcwd) ":"
13542 (getenv "PYTHONPATH")))
13546 `(("python-anndata" ,python-anndata)
13547 ("python-h5py" ,python-h5py)
13548 ("python-igraph" ,python-igraph)
13549 ("python-joblib" ,python-joblib)
13550 ("python-legacy-api-wrap" ,python-legacy-api-wrap)
13551 ("python-louvain" ,python-louvain)
13552 ("python-matplotlib" ,python-matplotlib)
13553 ("python-natsort" ,python-natsort)
13554 ("python-networkx" ,python-networkx)
13555 ("python-numba" ,python-numba)
13556 ("python-packaging" ,python-packaging)
13557 ("python-pandas" ,python-pandas)
13558 ("python-patsy" ,python-patsy)
13559 ("python-scikit-learn" ,python-scikit-learn)
13560 ("python-scipy" ,python-scipy)
13561 ("python-seaborn" ,python-seaborn)
13562 ("python-statsmodels" ,python-statsmodels)
13563 ("python-tables" ,python-tables)
13564 ("python-tqdm" ,python-tqdm)
13565 ("python-umap-learn" ,python-umap-learn)))
13567 `(("python-pytest" ,python-pytest)
13568 ("python-setuptools-scm" ,python-setuptools-scm)))
13569 (home-page "https://github.com/theislab/scanpy")
13570 (synopsis "Single-Cell Analysis in Python.")
13571 (description "Scanpy is a scalable toolkit for analyzing single-cell gene
13572 expression data. It includes preprocessing, visualization, clustering,
13573 pseudotime and trajectory inference and differential expression testing. The
13574 Python-based implementation efficiently deals with datasets of more than one
13576 (license license:bsd-3)))
13578 (define-public python-bbknn
13580 (name "python-bbknn")
13585 (uri (pypi-uri "bbknn" version))
13588 "1jbsh01f57zj4bhvjr3jh4532zznqd6nccmgrl3qi9gnhkf7c4y0"))))
13589 (build-system python-build-system)
13591 `(#:tests? #f)) ; TODO: Enable after migration to scikit-learn.
13593 `(("python-annoy" ,python-annoy)
13594 ("python-cython" ,python-cython)
13595 ("python-numpy" ,python-numpy)
13596 ("python-scipy" ,python-scipy)
13597 ("python-umap-learn" ,python-umap-learn)))
13598 (home-page "https://github.com/Teichlab/bbknn")
13599 (synopsis "Batch balanced KNN")
13600 (description "BBKNN is a batch effect removal tool that can be directly
13601 used in the Scanpy workflow. It serves as an alternative to
13602 @code{scanpy.api.pp.neighbors()}, with both functions creating a neighbour
13603 graph for subsequent use in clustering, pseudotime and UMAP visualisation. If
13604 technical artifacts are present in the data, they will make it challenging to
13605 link corresponding cell types across different batches. BBKNN actively
13606 combats this effect by splitting your data into batches and finding a smaller
13607 number of neighbours for each cell within each of the groups. This helps
13608 create connections between analogous cells in different batches without
13609 altering the counts or PCA space.")
13610 (license license:expat)))
13612 (define-public gffcompare
13613 (let ((commit "be56ef4349ea3966c12c6397f85e49e047361c41")
13616 (name "gffcompare")
13617 (version (git-version "0.10.15" revision commit))
13621 (uri (git-reference
13622 (url "https://github.com/gpertea/gffcompare/")
13624 (file-name (git-file-name name version))
13626 (base32 "0cp5qpxdhw4mxpya5dld8wi3jk00zyklm6rcri426wydinrnfmkg"))))
13627 (build-system gnu-build-system)
13629 `(#:tests? #f ; no check target
13631 (modify-phases %standard-phases
13632 (delete 'configure)
13633 (add-before 'build 'copy-gclib-source
13634 (lambda* (#:key inputs #:allow-other-keys)
13637 (assoc-ref inputs "gclib-source") "../gclib")
13640 (lambda* (#:key outputs #:allow-other-keys)
13641 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
13642 (install-file "gffcompare" bin)
13645 `(("gclib-source" ; see 'README.md' of gffcompare
13646 ,(let ((commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13649 (version (git-version "0.10.3" revision commit)))
13652 (uri (git-reference
13653 (url "https://github.com/gpertea/gclib/")
13655 (file-name (git-file-name name version))
13657 (base32 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13658 (home-page "https://github.com/gpertea/gffcompare/")
13659 (synopsis "Tool for comparing or classifing transcripts of RNA-Seq")
13661 "@code{gffcompare} is a tool that can:
13663 @item compare and evaluate the accuracy of RNA-Seq transcript assemblers
13664 (Cufflinks, Stringtie);
13665 @item collapse (merge) duplicate transcripts from multiple GTF/GFF3 files (e.g.
13666 resulted from assembly of different samples);
13667 @item classify transcripts from one or multiple GTF/GFF3 files as they relate to
13668 reference transcripts provided in a annotation file (also in GTF/GFF3 format).
13672 license:expat ;license for gffcompare
13673 license:artistic2.0))))) ;license for gclib
13675 (define-public intervaltree
13676 (let ((commit "b90527f9e6d51cd36ecbb50429e4524d3a418ea5"))
13678 (name "intervaltree")
13679 (version (git-version "0.0.0" "1" commit))
13683 (uri (git-reference
13684 (url "https://github.com/ekg/intervaltree/")
13686 (file-name (git-file-name name version))
13688 (base32 "0rgv6q5fl4x5d74n6p5wvdna6zmbdbqpb4jqqh6vq3670gn08xad"))))
13689 (build-system gnu-build-system)
13691 '(#:tests? #f ; No tests.
13692 #:make-flags (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
13695 (modify-phases %standard-phases
13696 (delete 'configure)))) ; There is no configure phase.
13697 (home-page "https://github.com/ekg/intervaltree")
13698 (synopsis "Minimal C++ interval tree implementation")
13699 (description "An interval tree can be used to efficiently find a set of
13700 numeric intervals overlapping or containing another interval. This library
13701 provides a basic implementation of an interval tree using C++ templates,
13702 allowing the insertion of arbitrary types into the tree.")
13703 (license license:expat))))
13705 (define-public python-intervaltree
13707 (name "python-intervaltree")
13712 (uri (pypi-uri "intervaltree" version))
13715 "0wz234g6irlm4hivs2qzmnywk0ss06ckagwh15nflkyb3p462kyb"))))
13716 (build-system python-build-system)
13719 (modify-phases %standard-phases
13720 ;; pytest seems to have a check to make sure the user is testing
13721 ;; their checked-out code and not an installed, potentially
13722 ;; out-of-date copy. This is harmless here, since we just installed
13723 ;; the package, so we disable the check to avoid skipping tests
13725 (add-before 'check 'import-mismatch-error-workaround
13727 (setenv "PY_IGNORE_IMPORTMISMATCH" "1")
13730 `(("python-sortedcontainers" ,python-sortedcontainers)))
13732 `(("python-pytest" ,python-pytest)))
13733 (home-page "https://github.com/chaimleib/intervaltree")
13734 (synopsis "Editable interval tree data structure")
13736 "This package provides a mutable, self-balancing interval tree
13737 implementation for Python. Queries may be by point, by range overlap, or by
13738 range envelopment. This library was designed to allow tagging text and time
13739 intervals, where the intervals include the lower bound but not the upper
13741 (license license:asl2.0)))
13743 (define-public python-pypairix
13745 (name "python-pypairix")
13750 (uri (pypi-uri "pypairix" version))
13753 "0zs92b74s5v4xy2h16s15f3z6l4nnbw8x8zyif7xx5xpafjn0xss"))))
13754 (build-system python-build-system)
13755 ;; FIXME: the tests fail because test.support cannot be loaded:
13756 ;; ImportError: cannot import name 'support'
13757 (arguments '(#:tests? #f))
13760 (home-page "https://github.com/4dn-dcic/pairix")
13761 (synopsis "Support for querying pairix-indexed bgzipped text files")
13763 "Pypairix is a Python module for fast querying on a pairix-indexed
13764 bgzipped text file that contains a pair of genomic coordinates per line.")
13765 (license license:expat)))
13767 (define-public python-pyfaidx
13769 (name "python-pyfaidx")
13774 (uri (pypi-uri "pyfaidx" version))
13777 "038xi3a6zvrxbyyfpp64ka8pcjgsdq4fgw9cl5lpxbvmm1bzzw2q"))))
13778 (build-system python-build-system)
13780 `(("python-six" ,python-six)))
13781 (home-page "http://mattshirley.com")
13782 (synopsis "Random access to fasta subsequences")
13784 "This package provides procedures for efficient pythonic random access to
13785 fasta subsequences.")
13786 (license license:bsd-3)))
13788 (define-public python2-pyfaidx
13789 (package-with-python2 python-pyfaidx))
13791 (define-public python-cooler
13793 (name "python-cooler")
13798 (uri (pypi-uri "cooler" version))
13801 "01g6gqix9ba27sappz6nfyiwabzrlf8i5fn8kwcz8ra356cq9crp"))))
13802 (build-system python-build-system)
13804 `(("python-asciitree" ,python-asciitree)
13805 ("python-biopython" ,python-biopython)
13806 ("python-click" ,python-click)
13807 ("python-cytoolz" ,python-cytoolz)
13808 ("python-dask" ,python-dask)
13809 ("python-h5py" ,python-h5py)
13810 ("python-multiprocess" ,python-multiprocess)
13811 ("python-numpy" ,python-numpy)
13812 ("python-pandas" ,python-pandas)
13813 ("python-pyfaidx" ,python-pyfaidx)
13814 ("python-pypairix" ,python-pypairix)
13815 ("python-pysam" ,python-pysam)
13816 ("python-pyyaml" ,python-pyyaml)
13817 ("python-scipy" ,python-scipy)
13818 ("python-simplejson" ,python-simplejson)))
13820 `(("python-mock" ,python-mock)
13821 ("python-pytest" ,python-pytest)))
13822 (home-page "https://github.com/mirnylab/cooler")
13823 (synopsis "Sparse binary format for genomic interaction matrices")
13825 "Cooler is a support library for a sparse, compressed, binary persistent
13826 storage format, called @code{cool}, used to store genomic interaction data,
13827 such as Hi-C contact matrices.")
13828 (license license:bsd-3)))
13830 (define-public python-hicmatrix
13832 (name "python-hicmatrix")
13836 ;; Version 12 is not available on pypi.
13838 (uri (git-reference
13839 (url "https://github.com/deeptools/HiCMatrix.git")
13841 (file-name (git-file-name name version))
13844 "1xhdyx16f3brgxgxybixdi64ki8nbbkq5vk4h9ahi11pzpjfn1pj"))))
13845 (build-system python-build-system)
13848 (modify-phases %standard-phases
13849 (add-after 'unpack 'relax-requirements
13851 (substitute* '("requirements.txt"
13853 (("cooler *=+ *0.8.5")
13857 `(("python-cooler" ,python-cooler)
13858 ("python-intervaltree" ,python-intervaltree)
13859 ("python-numpy" ,python-numpy)
13860 ("python-pandas" ,python-pandas)
13861 ("python-scipy" ,python-scipy)
13862 ("python-tables" ,python-tables)))
13863 (home-page "https://github.com/deeptools/HiCMatrix/")
13864 (synopsis "HiCMatrix class for HiCExplorer and pyGenomeTracks")
13866 "This helper package implements the @code{HiCMatrix} class for
13867 the HiCExplorer and pyGenomeTracks packages.")
13868 (license license:gpl3+)))
13870 (define-public python-hicexplorer
13872 (name "python-hicexplorer")
13876 ;; The latest version is not available on Pypi.
13878 (uri (git-reference
13879 (url "https://github.com/deeptools/HiCExplorer.git")
13881 (file-name (git-file-name name version))
13884 "0q5gpbzmrkvygqgw524q36b4nrivcmyi5v194vsx0qw7b3gcmq08"))))
13885 (build-system python-build-system)
13888 (modify-phases %standard-phases
13889 (add-after 'unpack 'loosen-up-requirements
13891 (substitute* "setup.py"
13895 `(("python-biopython" ,python-biopython)
13896 ("python-configparser" ,python-configparser)
13897 ("python-cooler" ,python-cooler)
13898 ("python-future" ,python-future)
13899 ("python-intervaltree" ,python-intervaltree)
13900 ("python-jinja2" ,python-jinja2)
13901 ("python-matplotlib" ,python-matplotlib)
13902 ("python-numpy" ,python-numpy)
13903 ("python-pandas" ,python-pandas)
13904 ("python-pybigwig" ,python-pybigwig)
13905 ("python-pysam" ,python-pysam)
13906 ("python-scipy" ,python-scipy)
13907 ("python-six" ,python-six)
13908 ("python-tables" ,python-tables)
13909 ("python-unidecode" ,python-unidecode)))
13910 (home-page "https://hicexplorer.readthedocs.io")
13911 (synopsis "Process, analyze and visualize Hi-C data")
13913 "HiCExplorer is a powerful and easy to use set of tools to process,
13914 normalize and visualize Hi-C data. HiCExplorer facilitates the creation of
13915 contact matrices, correction of contacts, TAD detection, A/B compartments,
13916 merging, reordering or chromosomes, conversion from different formats
13917 including cooler and detection of long-range contacts. Moreover, it allows
13918 the visualization of multiple contact matrices along with other types of data
13919 like genes, compartments, ChIP-seq coverage tracks (and in general any type of
13920 genomic scores), long range contacts and the visualization of viewpoints.")
13921 (license license:gpl3)))
13923 (define-public python-pygenometracks
13925 (name "python-pygenometracks")
13930 (uri (pypi-uri "pyGenomeTracks" version))
13933 "16laa0wnf4qn9fb9ych4w1vqhqwjss70v0y0f6wp4gwqfrlgac0f"))))
13934 (build-system python-build-system)
13936 `(#:tests? #f ; there are none
13938 (modify-phases %standard-phases
13939 (add-after 'unpack 'relax-requirements
13941 (substitute* "setup.py"
13942 (("matplotlib ==3.1.1")
13943 "matplotlib >=3.1.1"))
13946 `(("python-future" ,python-future)
13947 ("python-gffutils" ,python-gffutils)
13948 ("python-hicmatrix" ,python-hicmatrix)
13949 ("python-intervaltree" ,python-intervaltree)
13950 ("python-matplotlib" ,python-matplotlib)
13951 ("python-numpy" ,python-numpy)
13952 ("python-pybigwig" ,python-pybigwig)
13953 ("python-pysam" ,python-pysam)
13954 ("python-tqdm" ,python-tqdm)))
13956 `(("python-pytest" ,python-pytest)))
13957 (home-page "https://pygenometracks.readthedocs.io")
13958 (synopsis "Program and library to plot beautiful genome browser tracks")
13960 "This package aims to produce high-quality genome browser tracks that
13961 are highly customizable. Currently, it is possible to plot: bigwig, bed (many
13962 options), bedgraph, links (represented as arcs), and Hi-C matrices.
13963 pyGenomeTracks can make plots with or without Hi-C data.")
13964 (license license:gpl3+)))
13966 (define-public python-hic2cool
13968 (name "python-hic2cool")
13973 (uri (pypi-uri "hic2cool" version))
13976 "0xy6mhfns2lzib1kcr6419jjp6pmh0qx8z8na55lmiwn0ds8q9cl"))))
13977 (build-system python-build-system)
13978 (arguments '(#:tests? #f)) ; no tests included
13980 `(("python-cooler" ,python-cooler)))
13981 (home-page "https://github.com/4dn-dcic/hic2cool")
13982 (synopsis "Converter for .hic and .cool files")
13984 "This package provides a converter between @code{.hic} files (from
13985 juicer) and single-resolution or multi-resolution @code{.cool} files (for
13986 cooler). Both @code{hic} and @code{cool} files describe Hi-C contact
13988 (license license:expat)))
13990 (define-public r-pore
13998 (string-append "mirror://sourceforge/rpore/" version
13999 "/poRe_" version ".tar.gz"))
14001 (base32 "0pih9nljbv8g4x8rkk29i7aqq681b782r5s5ynp4nw9yzqnmmksv"))))
14002 (properties `((upstream-name . "poRe")))
14003 (build-system r-build-system)
14005 `(("r-bit64" ,r-bit64)
14006 ("r-data-table" ,r-data-table)
14007 ("r-rhdf5" ,r-rhdf5)
14008 ("r-shiny" ,r-shiny)
14009 ("r-svdialogs" ,r-svdialogs)))
14010 (home-page "https://sourceforge.net/projects/rpore/")
14011 (synopsis "Visualize Nanopore sequencing data")
14013 "This package provides graphical user interfaces to organize and visualize Nanopore
14015 ;; This is free software but the license variant is unclear:
14016 ;; <https://github.com/mw55309/poRe_docs/issues/10>.
14017 (license license:bsd-3)))
14019 (define-public r-xbioc
14020 (let ((revision "1")
14021 (commit "6ff0670a37ab3036aaf1d94aa4b208310946b0b5"))
14024 (version (git-version "0.1.16" revision commit))
14027 (uri (git-reference
14028 (url "https://github.com/renozao/xbioc.git")
14030 (file-name (git-file-name name version))
14033 "0w8bsq5myiwkfhh83nm6is5ichiyvwa1axx2szvxnzq39x6knf66"))))
14034 (build-system r-build-system)
14036 `(("r-annotationdbi" ,r-annotationdbi)
14037 ("r-assertthat" ,r-assertthat)
14038 ("r-biobase" ,r-biobase)
14039 ("r-biocmanager" ,r-biocmanager)
14040 ("r-digest" ,r-digest)
14041 ("r-pkgmaker" ,r-pkgmaker)
14043 ("r-reshape2" ,r-reshape2)
14044 ("r-stringr" ,r-stringr)))
14045 (home-page "https://github.com/renozao/xbioc/")
14046 (synopsis "Extra base functions for Bioconductor")
14047 (description "This package provides extra utility functions to perform
14048 common tasks in the analysis of omics data, leveraging and enhancing features
14049 provided by Bioconductor packages.")
14050 (license license:gpl3+))))
14052 (define-public r-cssam
14053 (let ((revision "1")
14054 (commit "9ec58c982fa551af0d80b1a266890d92954833f2"))
14057 (version (git-version "1.4" revision commit))
14060 (uri (git-reference
14061 (url "https://github.com/shenorrLab/csSAM.git")
14063 (file-name (git-file-name name version))
14066 "128syf9v39gk0z3ip000qpsjbg6l1siyq6c8b0hz41dzg5achyb3"))))
14067 (build-system r-build-system)
14069 `(("r-formula" ,r-formula)
14070 ("r-ggplot2" ,r-ggplot2)
14071 ("r-pkgmaker" ,r-pkgmaker)
14073 ("r-rngtools" ,r-rngtools)
14074 ("r-scales" ,r-scales)))
14075 (home-page "https://github.com/shenorrLab/csSAM/")
14076 (synopsis "Cell type-specific statistical analysis of microarray")
14077 (description "This package implements the method csSAM that computes
14078 cell-specific differential expression from measured cell proportions using
14081 (license license:lgpl2.1+))))
14083 (define-public r-bseqsc
14084 (let ((revision "1")
14085 (commit "fef3f3e38dcf3df37103348b5780937982b43b98"))
14088 (version (git-version "1.0" revision commit))
14091 (uri (git-reference
14092 (url "https://github.com/shenorrLab/bseqsc.git")
14094 (file-name (git-file-name name version))
14097 "1prw13wa20f7wlc3gkkls66n1kxz8d28qrb8icfqdwdnnv8w5qg8"))))
14098 (build-system r-build-system)
14100 `(("r-abind" ,r-abind)
14101 ("r-annotationdbi" ,r-annotationdbi)
14102 ("r-biobase" ,r-biobase)
14103 ("r-cssam" ,r-cssam)
14104 ("r-dplyr" ,r-dplyr)
14105 ("r-e1071" ,r-e1071)
14106 ("r-edger" ,r-edger)
14107 ("r-ggplot2" ,r-ggplot2)
14109 ("r-openxlsx" ,r-openxlsx)
14110 ("r-pkgmaker" ,r-pkgmaker)
14112 ("r-preprocesscore" ,r-preprocesscore)
14113 ("r-rngtools" ,r-rngtools)
14114 ("r-scales" ,r-scales)
14115 ("r-stringr" ,r-stringr)
14116 ("r-xbioc" ,r-xbioc)))
14117 (home-page "https://github.com/shenorrLab/bseqsc")
14118 (synopsis "Deconvolution of bulk sequencing experiments using single cell data")
14119 (description "BSeq-sc is a bioinformatics analysis pipeline that
14120 leverages single-cell sequencing data to estimate cell type proportion and
14121 cell type-specific gene expression differences from RNA-seq data from bulk
14122 tissue samples. This is a companion package to the publication \"A
14123 single-cell transcriptomic map of the human and mouse pancreas reveals inter-
14124 and intra-cell population structure.\" Baron et al. Cell Systems (2016)
14125 @url{https://www.ncbi.nlm.nih.gov/pubmed/27667365}.")
14126 (license license:gpl2+))))
14128 (define-public porechop
14129 ;; The recommended way to install is to clone the git repository
14130 ;; https://github.com/rrwick/Porechop#installation
14131 (let ((commit "289d5dca4a5fc327f97b3f8cecb68ecaf1014861")
14135 (version (git-version "0.2.3" revision commit))
14139 (uri (git-reference
14140 (url "https://github.com/rrwick/Porechop.git")
14142 (file-name (git-file-name name version))
14144 (base32 "05ps43gig0d3ia9x5lj84lb00hbsl6ba9n7y7jz927npxbr2ym23"))))
14145 (build-system python-build-system)
14146 (home-page "https://github.com/rrwick/porechop")
14147 (synopsis "Finding, trimming or splitting adapters, in Oxford Nanopore reads")
14149 "The porechop package is a tool for finding and removing adapters from Oxford
14150 Nanopore reads. Adapters on the ends of reads are trimmed off, and when a read
14151 has an adapter in its middle, it is treated as chimeric and chopped into
14152 separate reads. Porechop performs thorough alignments to effectively find
14153 adapters, even at low sequence identity. Porechop also supports demultiplexing
14154 of Nanopore reads that were barcoded with the Native Barcoding Kit, PCR
14155 Barcoding Kit or Rapid Barcoding Kit.")
14156 (license license:gpl3+))))
14158 (define-public poretools
14159 ;; The latest release was in 2016 and the latest commit is from 2017
14160 ;; the recommended way to install is to clone the git repository
14161 ;; https://poretools.readthedocs.io/en/latest/content/installation.html
14162 (let ((commit "e426b1f09e86ac259a00c261c79df91510777407")
14166 (version (git-version "0.6.0" revision commit))
14170 (uri (git-reference
14171 (url "https://github.com/arq5x/poretools.git")
14173 (file-name (git-file-name name version))
14175 (base32 "0bglj833wxpp3cq430p1d3xp085ls221js2y90w7ir2x5ay8l7am"))))
14176 (build-system python-build-system)
14177 ;; requires python >=2.7, <3.0, and the same for python dependencies
14178 (arguments `(#:python ,python-2))
14182 `(("python-dateutil" ,python2-dateutil)
14183 ("python-h5py" ,python2-h5py)
14184 ("python-matplotlib" ,python2-matplotlib)
14185 ("python-pandas" ,python2-pandas)
14186 ("python-seaborn" ,python2-seaborn)))
14187 (home-page "https://poretools.readthedocs.io")
14188 (synopsis "Toolkit for working with nanopore sequencing data")
14190 "The MinION from Oxford Nanopore Technologies is a nanopore sequencer.
14191 This @code{poretools} package is a flexible toolkit for exploring datasets
14192 generated by nanopore sequencing devices for the purposes of quality control and
14193 downstream analysis. Poretools operates directly on the native FAST5, a variant
14194 of the Hierarchical Data Format (HDF5) standard.")
14195 (license license:expat))))
14197 (define-public r-absfiltergsea
14199 (name "r-absfiltergsea")
14204 (uri (cran-uri "AbsFilterGSEA" version))
14206 (base32 "15srxkxsvn38kd5frdrwfdf0ad8gskrd0h01wmdf9hglq8fjrp7w"))))
14207 (properties `((upstream-name . "AbsFilterGSEA")))
14208 (build-system r-build-system)
14210 `(("r-biobase" ,r-biobase)
14211 ("r-deseq" ,r-deseq)
14212 ("r-limma" ,r-limma)
14214 ("r-rcpparmadillo" ,r-rcpparmadillo)))
14215 (home-page "https://cran.r-project.org/web/packages/AbsFilterGSEA/")
14216 (synopsis "Improved false positive control of gene-permuting with absolute filtering")
14218 "This package provides a function that performs gene-permuting of a gene-set
14219 enrichment analysis (GSEA) calculation with or without the absolute filtering.
14220 Without filtering, users can perform (original) two-tailed or one-tailed
14222 (license license:gpl2)))
14224 (define-public jamm
14227 (version "1.0.7.6")
14231 (uri (git-reference
14232 (url "https://github.com/mahmoudibrahim/JAMM.git")
14233 (commit (string-append "JAMMv" version))))
14234 (file-name (git-file-name name version))
14237 "0bsa5mf9n9q5jz7mmacrra41l7r8rac5vgsn6wv1fb52ya58b970"))))
14238 (build-system gnu-build-system)
14240 `(#:tests? #f ; there are none
14242 (modify-phases %standard-phases
14243 (delete 'configure)
14246 (lambda* (#:key inputs outputs #:allow-other-keys)
14247 (let* ((out (assoc-ref outputs "out"))
14248 (libexec (string-append out "/libexec/jamm"))
14249 (bin (string-append out "/bin")))
14250 (substitute* '("JAMM.sh"
14251 "SignalGenerator.sh")
14253 (string-append "sPath=\"" libexec "\"\n")))
14254 (for-each (lambda (file)
14255 (install-file file libexec))
14256 (list "bincalculator.r"
14268 (chmod script #o555)
14269 (install-file script bin)
14270 (wrap-program (string-append bin "/" script)
14271 `("PATH" ":" prefix
14272 (,(string-append (assoc-ref inputs "coreutils") "/bin")
14273 ,(string-append (assoc-ref inputs "gawk") "/bin")
14274 ,(string-append (assoc-ref inputs "perl") "/bin")
14275 ,(string-append (assoc-ref inputs "r-minimal") "/bin")))
14276 `("PERL5LIB" ":" prefix (,(getenv "PERL5LIB")))
14277 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
14278 (list "JAMM.sh" "SignalGenerator.sh")))
14282 ("coreutils" ,coreutils)
14285 ("r-minimal" ,r-minimal)
14286 ;;("r-parallel" ,r-parallel)
14287 ("r-signal" ,r-signal)
14288 ("r-mclust" ,r-mclust)))
14289 (home-page "https://github.com/mahmoudibrahim/JAMM")
14290 (synopsis "Peak finder for NGS datasets")
14292 "JAMM is a peak finder for next generation sequencing datasets (ChIP-Seq,
14293 ATAC-Seq, DNase-Seq, etc.) that can integrate replicates and assign peak
14294 boundaries accurately. JAMM is applicable to both broad and narrow
14296 (license license:gpl3+)))
14298 (define-public ngless
14305 (uri (git-reference
14306 (url "https://gitlab.com/ngless/ngless.git")
14307 (commit (string-append "v" version))))
14308 (file-name (git-file-name name version))
14311 "1wim8wpqyff080dfcazynrmjwqas38m24m0v350w245mmhrapdma"))))
14312 (build-system haskell-build-system)
14314 `(#:haddock? #f ; The haddock phase fails with: NGLess/CmdArgs.hs:20:1:
14315 ; error: parse error on input import
14316 ; import Options.Applicative
14318 (modify-phases %standard-phases
14319 (add-after 'unpack 'create-Versions.hs
14321 (substitute* "Makefile"
14322 (("BWA_VERSION = .*")
14323 (string-append "BWA_VERSION = "
14324 ,(package-version bwa) "\n"))
14325 (("SAM_VERSION = .*")
14326 (string-append "SAM_VERSION = "
14327 ,(package-version samtools) "\n"))
14328 (("PRODIGAL_VERSION = .*")
14329 (string-append "PRODIGAL_VERSION = "
14330 ,(package-version prodigal) "\n"))
14331 (("MINIMAP2_VERSION = .*")
14332 (string-append "MINIMAP2_VERSION = "
14333 ,(package-version minimap2) "\n")))
14334 (invoke "make" "NGLess/Dependencies/Versions.hs")
14336 (add-after 'create-Versions.hs 'create-cabal-file
14337 (lambda _ (invoke "hpack") #t))
14338 ;; These tools are expected to be installed alongside ngless.
14339 (add-after 'install 'link-tools
14340 (lambda* (#:key inputs outputs #:allow-other-keys)
14341 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
14342 (symlink (string-append (assoc-ref inputs "prodigal")
14344 (string-append bin "ngless-" ,version "-prodigal"))
14345 (symlink (string-append (assoc-ref inputs "minimap2")
14347 (string-append bin "ngless-" ,version "-minimap2"))
14348 (symlink (string-append (assoc-ref inputs "samtools")
14350 (string-append bin "ngless-" ,version "-samtools"))
14351 (symlink (string-append (assoc-ref inputs "bwa")
14353 (string-append bin "ngless-" ,version "-bwa"))
14356 `(("prodigal" ,prodigal)
14358 ("samtools" ,samtools)
14359 ("minimap2" ,minimap2)
14360 ("ghc-aeson" ,ghc-aeson)
14361 ("ghc-ansi-terminal" ,ghc-ansi-terminal)
14362 ("ghc-async" ,ghc-async)
14363 ("ghc-atomic-write" ,ghc-atomic-write)
14364 ("ghc-bytestring-lexing" ,ghc-bytestring-lexing)
14365 ("ghc-conduit" ,ghc-conduit)
14366 ("ghc-conduit-algorithms" ,ghc-conduit-algorithms)
14367 ("ghc-conduit-extra" ,ghc-conduit-extra)
14368 ("ghc-configurator" ,ghc-configurator)
14369 ("ghc-convertible" ,ghc-convertible)
14370 ("ghc-data-default" ,ghc-data-default)
14371 ("ghc-diagrams-core" ,ghc-diagrams-core)
14372 ("ghc-diagrams-lib" ,ghc-diagrams-lib)
14373 ("ghc-diagrams-svg" ,ghc-diagrams-svg)
14374 ("ghc-double-conversion" ,ghc-double-conversion)
14375 ("ghc-edit-distance" ,ghc-edit-distance)
14376 ("ghc-either" ,ghc-either)
14377 ("ghc-errors" ,ghc-errors)
14378 ("ghc-extra" ,ghc-extra)
14379 ("ghc-filemanip" ,ghc-filemanip)
14380 ("ghc-file-embed" ,ghc-file-embed)
14381 ("ghc-gitrev" ,ghc-gitrev)
14382 ("ghc-hashtables" ,ghc-hashtables)
14383 ("ghc-http-conduit" ,ghc-http-conduit)
14384 ("ghc-inline-c" ,ghc-inline-c)
14385 ("ghc-inline-c-cpp" ,ghc-inline-c-cpp)
14386 ("ghc-intervalmap" ,ghc-intervalmap)
14387 ("ghc-missingh" ,ghc-missingh)
14388 ("ghc-optparse-applicative" ,ghc-optparse-applicative)
14389 ("ghc-regex" ,ghc-regex)
14390 ("ghc-safe" ,ghc-safe)
14391 ("ghc-safeio" ,ghc-safeio)
14392 ("ghc-strict" ,ghc-strict)
14393 ("ghc-tar" ,ghc-tar)
14394 ("ghc-tar-conduit" ,ghc-tar-conduit)
14395 ("ghc-unliftio" ,ghc-unliftio)
14396 ("ghc-unliftio-core" ,ghc-unliftio-core)
14397 ("ghc-vector" ,ghc-vector)
14398 ("ghc-yaml" ,ghc-yaml)
14399 ("ghc-zlib" ,ghc-zlib)))
14402 ("r-hdf5r" ,r-hdf5r)
14403 ("r-iterators" ,r-iterators)
14404 ("r-itertools" ,r-itertools)
14405 ("r-matrix" ,r-matrix)))
14407 `(("ghc-hpack" ,ghc-hpack)
14408 ("ghc-quickcheck" ,ghc-quickcheck)
14409 ("ghc-test-framework" ,ghc-test-framework)
14410 ("ghc-test-framework-hunit",ghc-test-framework-hunit)
14411 ("ghc-test-framework-quickcheck2" ,ghc-test-framework-quickcheck2)
14412 ("ghc-test-framework-th" ,ghc-test-framework-th)))
14413 (home-page "https://gitlab.com/ngless/ngless")
14414 (synopsis "DSL for processing next-generation sequencing data")
14415 (description "Ngless is a domain-specific language for
14416 @dfn{next-generation sequencing} (NGS) data processing.")
14417 (license license:expat)))
14419 (define-public filtlong
14420 ;; The recommended way to install is to clone the git repository
14421 ;; https://github.com/rrwick/Filtlong#installation
14422 ;; and the lastest release is more than nine months old
14423 (let ((commit "d1bb46dfe8bc7efe6257b5ce222c04bfe8aedaab")
14427 (version (git-version "0.2.0" revision commit))
14431 (uri (git-reference
14432 (url "https://github.com/rrwick/Filtlong.git")
14434 (file-name (git-file-name name version))
14436 (base32 "1xr92r820x8qlkcr3b57iw223yq8vjgyi42jr79w2xgw47qzr575"))))
14437 (build-system gnu-build-system)
14439 `(#:tests? #f ; no check target
14441 (modify-phases %standard-phases
14442 (delete 'configure)
14444 (lambda* (#:key outputs #:allow-other-keys)
14445 (let* ((out (assoc-ref outputs "out"))
14446 (bin (string-append out "/bin"))
14447 (scripts (string-append out "/share/filtlong/scripts")))
14448 (install-file "bin/filtlong" bin)
14449 (install-file "scripts/histogram.py" scripts)
14450 (install-file "scripts/read_info_histograms.sh" scripts))
14452 (add-after 'install 'wrap-program
14453 (lambda* (#:key inputs outputs #:allow-other-keys)
14454 (let* ((out (assoc-ref outputs "out"))
14455 (path (getenv "PYTHONPATH")))
14456 (wrap-program (string-append out
14457 "/share/filtlong/scripts/histogram.py")
14458 `("PYTHONPATH" ":" prefix (,path))))
14460 (add-before 'check 'patch-tests
14462 (substitute* "scripts/read_info_histograms.sh"
14463 (("awk") (which "gawk")))
14466 `(("gawk" ,gawk) ;for read_info_histograms.sh
14467 ("python" ,python-2) ;required for histogram.py
14469 (home-page "https://github.com/rrwick/Filtlong/")
14470 (synopsis "Tool for quality filtering of Nanopore and PacBio data")
14472 "The Filtlong package is a tool for filtering long reads by quality.
14473 It can take a set of long reads and produce a smaller, better subset. It uses
14474 both read length (longer is better) and read identity (higher is better) when
14475 choosing which reads pass the filter.")
14476 (license (list license:gpl3 ;filtlong
14477 license:asl2.0))))) ;histogram.py
14479 (define-public nanopolish
14480 ;; The recommended way to install is to clone the git repository
14481 ;; <https://github.com/jts/nanopolish#installing-a-particular-release>.
14482 ;; Also, the differences between release and current version seem to be
14484 (let ((commit "6331dc4f15b9dfabb954ba3fae9d76b6c3ca6377")
14487 (name "nanopolish")
14488 (version (git-version "0.11.1" revision commit))
14492 (uri (git-reference
14493 (url "https://github.com/jts/nanopolish.git")
14496 (file-name (git-file-name name version))
14498 (base32 "15ikl3d37y49pwd7vx36xksgsqajhf24q7qqsnpl15dqqyy5qgbc"))
14499 (modules '((guix build utils)))
14502 (delete-file-recursively "htslib")
14504 (build-system gnu-build-system)
14507 `("HDF5=noinstall" "EIGEN=noinstall" "HTS=noinstall" "CC=gcc")
14508 #:tests? #f ; no check target
14510 (modify-phases %standard-phases
14511 (add-after 'unpack 'find-eigen
14512 (lambda* (#:key inputs #:allow-other-keys)
14514 (string-append (assoc-ref inputs "eigen")
14516 (or (getenv "CPATH") "")))
14518 (delete 'configure)
14520 (lambda* (#:key outputs #:allow-other-keys)
14521 (let* ((out (assoc-ref outputs "out"))
14522 (bin (string-append out "/bin"))
14523 (scripts (string-append out "/share/nanopolish/scripts")))
14525 (install-file "nanopolish" bin)
14526 (for-each (lambda (file) (install-file file scripts))
14527 (find-files "scripts" ".*"))
14529 (add-after 'install 'wrap-programs
14530 (lambda* (#:key outputs #:allow-other-keys)
14531 (for-each (lambda (file)
14532 (wrap-program file `("PYTHONPATH" ":" prefix (,path))))
14533 (find-files "/share/nanopolish/scripts" "\\.py"))
14534 (for-each (lambda (file)
14535 (wrap-program file `("PERL5LIB" ":" prefix (,path))))
14536 (find-files "/share/nanopolish/scripts" "\\.pl"))
14543 ("python" ,python-wrapper)
14544 ("python-biopython" ,python-biopython)
14545 ("python-numpy" ,python-numpy)
14546 ("python-pysam" ,python-pysam)
14547 ("python-scikit-learn" , python-scikit-learn)
14548 ("python-scipy" ,python-scipy)
14550 (home-page "https://github.com/jts/nanopolish")
14551 (synopsis "Signal-level analysis of Oxford Nanopore sequencing data")
14553 "This package analyses the Oxford Nanopore sequencing data at signal-level.
14554 Nanopolish can calculate an improved consensus sequence for a draft genome
14555 assembly, detect base modifications, call SNPs (Single nucleotide
14556 polymorphisms) and indels with respect to a reference genome and more.")
14557 (license license:expat))))
14559 (define-public cnvkit
14566 (uri (git-reference
14567 (url "https://github.com/etal/cnvkit.git")
14568 (commit (string-append "v" version))))
14569 (file-name (git-file-name name version))
14571 (base32 "0g2f78k68yglmj4fsfmgs8idqv3di9aj53fg0ld0hqljg8chhh82"))))
14572 (build-system python-build-system)
14574 `(("python-biopython" ,python-biopython)
14575 ("python-future" ,python-future)
14576 ("python-matplotlib" ,python-matplotlib)
14577 ("python-numpy" ,python-numpy)
14578 ("python-reportlab" ,python-reportlab)
14579 ("python-pandas" ,python-pandas)
14580 ("python-pysam" ,python-pysam)
14581 ("python-pyfaidx" ,python-pyfaidx)
14582 ("python-scipy" ,python-scipy)
14584 ("r-dnacopy" ,r-dnacopy)))
14585 (home-page "https://cnvkit.readthedocs.org/")
14586 (synopsis "Copy number variant detection from targeted DNA sequencing")
14588 "CNVkit is a Python library and command-line software toolkit to infer
14589 and visualize copy number from high-throughput DNA sequencing data. It is
14590 designed for use with hybrid capture, including both whole-exome and custom
14591 target panels, and short-read sequencing platforms such as Illumina and Ion
14593 (license license:asl2.0)))
14595 (define-public python-pyfit-sne
14597 (name "python-pyfit-sne")
14602 (uri (git-reference
14603 (url "https://github.com/KlugerLab/pyFIt-SNE.git")
14605 (file-name (git-file-name name version))
14607 (base32 "13wh3qkzs56azmmgnxib6xfr29g7xh09sxylzjpni5j0pp0rc5qw"))))
14608 (build-system python-build-system)
14610 `(("python-numpy" ,python-numpy)))
14614 `(("python-cython" ,python-cython)))
14615 (home-page "https://github.com/KlugerLab/pyFIt-SNE")
14616 (synopsis "FFT-accelerated Interpolation-based t-SNE")
14618 "t-Stochastic Neighborhood Embedding (t-SNE) is a highly successful
14619 method for dimensionality reduction and visualization of high dimensional
14620 datasets. A popular implementation of t-SNE uses the Barnes-Hut algorithm to
14621 approximate the gradient at each iteration of gradient descent. This package
14622 is a Cython wrapper for FIt-SNE.")
14623 (license license:bsd-4)))
14625 (define-public bbmap
14631 (uri (string-append
14632 "mirror://sourceforge/bbmap/BBMap_" version ".tar.gz"))
14635 "1q4rfhxcb6z3gm8zg2davjz98w22lkf4hm9ikxz9kdl93pil3wkd"))))
14636 (build-system ant-build-system)
14638 `(#:build-target "dist"
14639 #:tests? #f ; there are none
14641 (list (string-append "-Dmpijar="
14642 (assoc-ref %build-inputs "java-openmpi")
14644 #:modules ((guix build ant-build-system)
14646 (guix build java-utils))
14648 (modify-phases %standard-phases
14649 (add-after 'build 'build-jni-library
14651 (with-directory-excursion "jni"
14652 (invoke "make" "-f" "makefile.linux"))))
14653 ;; There is no install target
14654 (replace 'install (install-jars "dist"))
14655 (add-after 'install 'install-scripts-and-documentation
14656 (lambda* (#:key outputs #:allow-other-keys)
14657 (substitute* "calcmem.sh"
14658 (("\\| awk ") (string-append "| " (which "awk") " ")))
14659 (let* ((scripts (find-files "." "\\.sh$"))
14660 (out (assoc-ref outputs "out"))
14661 (bin (string-append out "/bin"))
14662 (doc (string-append out "/share/doc/bbmap"))
14663 (jni (string-append out "/lib/jni")))
14664 (substitute* scripts
14665 (("\\$DIR\"\"docs") doc)
14667 (string-append "CP=" out "/share/java/BBTools.jar\n"))
14668 (("^NATIVELIBDIR.*")
14669 (string-append "NATIVELIBDIR=" jni "\n"))
14671 (string-append "CMD=\"" (which "java"))))
14672 (for-each (lambda (script) (install-file script bin)) scripts)
14674 ;; Install JNI library
14675 (install-file "jni/libbbtoolsjni.so" jni)
14677 ;; Install documentation
14678 (install-file "docs/readme.txt" doc)
14679 (copy-recursively "docs/guides" doc))
14684 ("java-eclipse-jdt-core" ,java-eclipse-jdt-core)
14685 ("java-eclipse-jdt-compiler-apt" ,java-eclipse-jdt-compiler-apt)
14686 ("java-openmpi" ,java-openmpi)))
14687 (home-page "http://sourceforge.net/projects/bbmap/")
14688 (synopsis "Aligner and other tools for short sequencing reads")
14690 "This package provides bioinformatic tools to align, deduplicate,
14691 reformat, filter and normalize DNA and RNA-seq data. It includes the
14692 following tools: BBMap, a short read aligner for DNA and RNA-seq data; BBNorm,
14693 a kmer-based error-correction and normalization tool; Dedupe, a tool to
14694 simplify assemblies by removing duplicate or contained subsequences that share
14695 a target percent identity; Reformat, to convert reads between
14696 fasta/fastq/scarf/fasta+qual/sam, interleaved/paired, and ASCII-33/64, at over
14697 500 MB/s; and BBDuk, a tool to filter, trim, or mask reads with kmer matches
14698 to an artifact/contaminant file.")
14699 (license license:bsd-3)))
14701 (define-public velvet
14707 (uri (string-append "https://www.ebi.ac.uk/~zerbino/velvet/"
14708 "velvet_" version ".tgz"))
14711 "0h3njwy66p6bx14r3ar1byb0ccaxmxka4c65rn4iybyiqa4d8kc8"))
14712 ;; Delete bundled libraries
14713 (modules '((guix build utils)))
14716 (delete-file "Manual.pdf")
14717 (delete-file-recursively "third-party")
14719 (build-system gnu-build-system)
14721 `(#:make-flags '("OPENMP=t")
14722 #:test-target "test"
14724 (modify-phases %standard-phases
14725 (delete 'configure)
14726 (add-after 'unpack 'fix-zlib-include
14728 (substitute* "src/binarySequences.c"
14729 (("../third-party/zlib-1.2.3/zlib.h") "zlib.h"))
14732 (lambda* (#:key outputs #:allow-other-keys)
14733 (let* ((out (assoc-ref outputs "out"))
14734 (bin (string-append out "/bin"))
14735 (doc (string-append out "/share/doc/velvet")))
14738 (install-file "velveth" bin)
14739 (install-file "velvetg" bin)
14740 (install-file "Manual.pdf" doc)
14741 (install-file "Columbus_manual.pdf" doc)
14744 `(("openmpi" ,openmpi)
14747 `(("texlive" ,(texlive-union (list texlive-latex-graphics
14748 texlive-latex-hyperref)))))
14749 (home-page "https://www.ebi.ac.uk/~zerbino/velvet/")
14750 (synopsis "Nucleic acid sequence assembler for very short reads")
14752 "Velvet is a de novo genomic assembler specially designed for short read
14753 sequencing technologies, such as Solexa or 454. Velvet currently takes in
14754 short read sequences, removes errors then produces high quality unique
14755 contigs. It then uses paired read information, if available, to retrieve the
14756 repeated areas between contigs.")
14757 (license license:gpl2+)))
14759 (define-public python-velocyto
14761 (name "python-velocyto")
14762 (version "0.17.17")
14766 (uri (pypi-uri "velocyto" version))
14769 "0fgygyzqgrq32dv6a00biq1p1cwi6kbl5iqblxq1kklj6b2mzmhs"))))
14770 (build-system python-build-system)
14772 `(("python-joblib" ,python-joblib)))
14774 `(("python-click" ,python-click)
14775 ("python-cython" ,python-cython)
14776 ("python-h5py" ,python-h5py)
14777 ("python-loompy" ,python-loompy)
14778 ("python-matplotlib" ,python-matplotlib)
14779 ("python-numba" ,python-numba)
14780 ("python-numpy" ,python-numpy)
14781 ("python-pandas" ,python-pandas)
14782 ("python-pysam" ,python-pysam)
14783 ("python-scikit-learn" ,python-scikit-learn)
14784 ("python-scipy" ,python-scipy)))
14785 (home-page "https://github.com/velocyto-team/velocyto.py")
14786 (synopsis "RNA velocity analysis for single cell RNA-seq data")
14788 "Velocyto is a library for the analysis of RNA velocity. Velocyto
14789 includes a command line tool and an analysis pipeline.")
14790 (license license:bsd-2)))
14792 (define-public arriba
14799 (uri (string-append "https://github.com/suhrig/arriba/releases/"
14800 "download/v" version "/arriba_v" version ".tar.gz"))
14803 "0jx9656ry766vb8z08m1c3im87b0c82qpnjby9wz4kcz8vn87dx2"))))
14804 (build-system gnu-build-system)
14806 `(#:tests? #f ; there are none
14808 (modify-phases %standard-phases
14809 (replace 'configure
14810 (lambda* (#:key inputs #:allow-other-keys)
14811 (let ((htslib (assoc-ref inputs "htslib")))
14812 (substitute* "Makefile"
14813 (("-I\\$\\(HTSLIB\\)/htslib")
14814 (string-append "-I" htslib "/include/htslib"))
14815 ((" \\$\\(HTSLIB\\)/libhts.a")
14816 (string-append " " htslib "/lib/libhts.so"))))
14817 (substitute* "run_arriba.sh"
14818 (("^STAR ") (string-append (which "STAR") " "))
14819 (("samtools --version-only")
14820 (string-append (which "samtools") " --version-only"))
14821 (("samtools index")
14822 (string-append (which "samtools") " index"))
14824 (string-append (which "samtools") " sort")))
14827 (lambda* (#:key outputs #:allow-other-keys)
14828 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
14829 (install-file "arriba" bin)
14830 (install-file "run_arriba.sh" bin)
14831 (install-file "draw_fusions.R" bin)
14832 (wrap-program (string-append bin "/draw_fusions.R")
14833 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
14836 `(("htslib" ,htslib)
14837 ("r-minimal" ,r-minimal)
14838 ("r-circlize" ,r-circlize)
14839 ("r-genomicalignments" ,r-genomicalignments)
14840 ("r-genomicranges" ,r-genomicranges)
14841 ("samtools" ,samtools)
14844 (home-page "https://github.com/suhrig/arriba")
14845 (synopsis "Gene fusion detection from RNA-Seq data ")
14847 "Arriba is a command-line tool for the detection of gene fusions from
14848 RNA-Seq data. It was developed for the use in a clinical research setting.
14849 Therefore, short runtimes and high sensitivity were important design criteria.
14850 It is based on the fast STAR aligner and the post-alignment runtime is
14851 typically just around two minutes. In contrast to many other fusion detection
14852 tools which build on STAR, Arriba does not require to reduce the
14853 @code{alignIntronMax} parameter of STAR to detect small deletions.")
14854 ;; All code is under the Expat license with the exception of
14855 ;; "draw_fusions.R", which is under GPLv3.
14856 (license (list license:expat license:gpl3))))
14858 (define-public adapterremoval
14860 (name "adapterremoval")
14865 (uri (git-reference
14866 (url "https://github.com/MikkelSchubert/adapterremoval.git")
14867 (commit (string-append "v" version))))
14868 (file-name (git-file-name name version))
14871 "1nf3ki5pfzalhrx2fr1y6pfqfi133yj2m7q4fj9irf5fb94bapwr"))))
14872 (build-system gnu-build-system)
14874 `(#:make-flags (list "COLOR_BUILD=no"
14875 (string-append "PREFIX="
14876 (assoc-ref %outputs "out")))
14877 #:test-target "test"
14879 (modify-phases %standard-phases
14880 (delete 'configure))))
14883 (home-page "https://adapterremoval.readthedocs.io/")
14884 (synopsis "Rapid sequence adapter trimming, identification, and read merging")
14886 "This program searches for and removes remnant adapter sequences from
14887 @dfn{High-Throughput Sequencing} (HTS) data and (optionally) trims low quality
14888 bases from the 3' end of reads following adapter removal. AdapterRemoval can
14889 analyze both single end and paired end data, and can be used to merge
14890 overlapping paired-ended reads into (longer) consensus sequences.
14891 Additionally, the AdapterRemoval may be used to recover a consensus adapter
14892 sequence for paired-ended data, for which this information is not available.")
14893 (license license:gpl3+)))
14895 (define-public pplacer
14896 (let ((commit "807f6f3"))
14899 ;; The commit should be updated with each version change.
14900 (version "1.1.alpha19")
14904 (uri (git-reference
14905 (url "https://github.com/matsen/pplacer.git")
14906 (commit (string-append "v" version))))
14907 (file-name (git-file-name name version))
14909 (base32 "11ppbbbx20p2g9wj3ff64dhnarb12q79v7qh4rk0gj6lkbz4n7cn"))))
14910 (build-system ocaml-build-system)
14912 `(#:modules ((guix build ocaml-build-system)
14916 (modify-phases %standard-phases
14917 (delete 'configure)
14918 (add-after 'unpack 'fix-build-with-latest-ocaml
14920 (substitute* "myocamlbuild.ml"
14921 (("dep \\[\"c_pam\"\\]" m)
14922 (string-append "flag [\"ocaml\"; \"compile\"] (A \"-unsafe-string\");\n"
14924 (("let run_and_read" m)
14929 let pos = String.index s ch in
14930 x := (String.before s pos)::!x;
14931 go (String.after s (pos + 1))
14934 with Not_found -> !x
14935 let split_nl s = split s '\\n'
14936 let before_space s =
14937 try String.before s (String.index s ' ')
14938 with Not_found -> s
14941 (("run_and_read \"ocamlfind list \\| cut -d' ' -f1\"" m)
14942 (string-append "List.map before_space (split_nl & " m ")"))
14943 ((" blank_sep_strings &") "")
14944 ((" Lexing.from_string &") ""))
14946 (add-after 'unpack 'replace-bundled-cddlib
14947 (lambda* (#:key inputs #:allow-other-keys)
14948 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
14949 (local-dir "cddlib_guix"))
14951 (with-directory-excursion local-dir
14952 (invoke "tar" "xvf" cddlib-src))
14953 (let ((cddlib-src-folder
14954 (string-append local-dir "/"
14955 (list-ref (scandir local-dir) 2)
14957 (for-each make-file-writable (find-files "cdd_src" ".*"))
14961 (string-append "cdd_src/" (basename file))))
14962 (find-files cddlib-src-folder ".*[ch]$")))
14964 (add-after 'unpack 'fix-makefile
14966 ;; Remove system calls to 'git'.
14967 (substitute* "Makefile"
14968 (("^DESCRIPT:=pplacer-.*")
14970 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
14971 (substitute* "myocamlbuild.ml"
14972 (("git describe --tags --long .*\\\" with")
14974 "echo -n v" ,version "-" ,commit "\" with")))
14977 (lambda* (#:key outputs #:allow-other-keys)
14978 (let* ((out (assoc-ref outputs "out"))
14979 (bin (string-append out "/bin")))
14980 (copy-recursively "bin" bin))
14982 #:ocaml ,ocaml-4.07
14983 #:findlib ,ocaml4.07-findlib))
14985 `(("zlib" ,zlib "static")
14987 ("ocaml-ounit" ,(package-with-ocaml4.07 ocaml-ounit))
14988 ("ocaml-batteries" ,(package-with-ocaml4.07 ocaml-batteries))
14989 ("ocaml-camlzip" ,(package-with-ocaml4.07 camlzip))
14990 ("ocaml-csv" ,(package-with-ocaml4.07 ocaml-csv))
14991 ("ocaml-sqlite3" ,ocaml4.07-sqlite3)
14992 ("ocaml-xmlm" ,(package-with-ocaml4.07 ocaml-xmlm))
14993 ("ocaml-mcl" ,(package-with-ocaml4.07 ocaml-mcl))
14994 ("ocaml-gsl" ,ocaml4.07-gsl-1)))
14996 `(("cddlib-src" ,(package-source cddlib))
14997 ("ocamlbuild" ,(package-with-ocaml4.07 ocamlbuild))
14998 ("pkg-config" ,pkg-config)))
15000 `(("pplacer-scripts" ,pplacer-scripts)))
15001 (synopsis "Phylogenetic placement of biological sequences")
15003 "Pplacer places query sequences on a fixed reference phylogenetic tree
15004 to maximize phylogenetic likelihood or posterior probability according to a
15005 reference alignment. Pplacer is designed to be fast, to give useful
15006 information about uncertainty, and to offer advanced visualization and
15007 downstream analysis.")
15008 (home-page "https://matsen.fhcrc.org/pplacer/")
15009 (license license:gpl3))))
15011 ;; This package is installed alongside 'pplacer'. It is a separate package so
15012 ;; that it can use the python-build-system for the scripts that are
15013 ;; distributed alongside the main OCaml binaries.
15014 (define pplacer-scripts
15017 (name "pplacer-scripts")
15018 (build-system python-build-system)
15020 `(#:python ,python-2
15022 (modify-phases %standard-phases
15023 (add-after 'unpack 'enter-scripts-dir
15024 (lambda _ (chdir "scripts") #t))
15026 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t))
15027 (add-after 'install 'wrap-executables
15028 (lambda* (#:key inputs outputs #:allow-other-keys)
15029 (let* ((out (assoc-ref outputs "out"))
15030 (bin (string-append out "/bin")))
15031 (let ((path (string-append
15032 (assoc-ref inputs "hmmer") "/bin:"
15033 (assoc-ref inputs "infernal") "/bin")))
15035 (wrap-program (string-append bin "/refpkg_align.py")
15036 `("PATH" ":" prefix (,path))))
15037 (let ((path (string-append
15038 (assoc-ref inputs "hmmer") "/bin")))
15039 (wrap-program (string-append bin "/hrefpkg_query.py")
15040 `("PATH" ":" prefix (,path)))))
15043 `(("infernal" ,infernal)
15046 `(("python-biopython" ,python2-biopython)
15047 ("taxtastic" ,taxtastic)))
15048 (synopsis "Pplacer Python scripts")))
15050 (define-public python2-checkm-genome
15052 (name "python2-checkm-genome")
15057 (uri (pypi-uri "checkm-genome" version))
15060 "0bm8gpxjmzxsxxl8lzwqhgx8g1dlnmp6znz7wv3hgb0gdjbf9dzz"))))
15061 (build-system python-build-system)
15063 `(#:python ,python-2
15064 #:tests? #f)) ; some tests are interactive
15066 `(("python-dendropy" ,python2-dendropy)
15067 ("python-matplotlib" ,python2-matplotlib)
15068 ("python-numpy" ,python2-numpy)
15069 ("python-pysam" ,python2-pysam)
15070 ("python-scipy" ,python2-scipy)))
15071 (home-page "https://pypi.org/project/Checkm/")
15072 (synopsis "Assess the quality of putative genome bins")
15074 "CheckM provides a set of tools for assessing the quality of genomes
15075 recovered from isolates, single cells, or metagenomes. It provides robust
15076 estimates of genome completeness and contamination by using collocated sets of
15077 genes that are ubiquitous and single-copy within a phylogenetic lineage.
15078 Assessment of genome quality can also be examined using plots depicting key
15079 genomic characteristics (e.g., GC, coding density) which highlight sequences
15080 outside the expected distributions of a typical genome. CheckM also provides
15081 tools for identifying genome bins that are likely candidates for merging based
15082 on marker set compatibility, similarity in genomic characteristics, and
15083 proximity within a reference genome.")
15084 (license license:gpl3+)))
15086 (define-public umi-tools
15093 (uri (pypi-uri "umi_tools" version))
15096 "08y3vz1vcx09whmbsn722lcs6jl9wyrh9i4p3k8j4cb1i32bij4a"))))
15097 (build-system python-build-system)
15099 `(("python-pandas" ,python-pandas)
15100 ("python-future" ,python-future)
15101 ("python-scipy" ,python-scipy)
15102 ("python-matplotlib" ,python-matplotlib)
15103 ("python-regex" ,python-regex)
15104 ("python-pysam" ,python-pysam)))
15106 `(("python-cython" ,python-cython)))
15107 (home-page "https://github.com/CGATOxford/UMI-tools")
15108 (synopsis "Tools for analyzing unique modular identifiers")
15109 (description "This package provides tools for dealing with @dfn{Unique
15110 Molecular Identifiers} (UMIs) and @dfn{Random Molecular Tags} (RMTs) in
15111 genetic sequences. There are six tools: the @code{extract} and
15112 @code{whitelist} commands are used to prepare a fastq containing UMIs @code{+/-}
15113 cell barcodes for alignment. The remaining commands, @code{group},
15114 @code{dedup}, and @{count}/@code{count_tab}, are used to identify PCR
15115 duplicates using the UMIs and perform different levels of analysis depending
15116 on the needs of the user.")
15117 (license license:expat)))
15119 (define-public ataqv
15126 (uri (git-reference
15127 (url "https://github.com/ParkerLab/ataqv.git")
15129 (file-name (git-file-name name version))
15132 "031xr6jx1aprh26y5b1lv3gzrlmzg4alfl73vvshymx8cq8asrqi"))))
15133 (build-system gnu-build-system)
15136 (list (string-append "prefix=" (assoc-ref %outputs "out"))
15137 (string-append "BOOST_ROOT="
15138 (assoc-ref %build-inputs "boost"))
15139 (string-append "HTSLIB_ROOT="
15140 (assoc-ref %build-inputs "htslib")))
15141 #:test-target "test"
15143 (modify-phases %standard-phases
15144 (delete 'configure))))
15148 ("ncurses" ,ncurses)
15152 (home-page "https://github.com/ParkerLab/ataqv")
15153 (synopsis "Toolkit for quality control and visualization of ATAC-seq data")
15154 (description "This package provides a toolkit for measuring and comparing
15155 ATAC-seq results. It was written to make it easier to spot differences that
15156 might be caused by ATAC-seq library prep or sequencing. The main program,
15157 @code{ataqv}, examines aligned reads and reports some basic metrics.")
15158 (license license:gpl3+)))
15160 (define-public r-psiplot
15167 (uri (git-reference
15168 (url "https://github.com/kcha/psiplot.git")
15169 (commit (string-append "v" version))))
15170 (file-name (git-file-name name version))
15172 (base32 "08438h16cfry5kqh3y9hs8q1b1a8bxhblsm75knviz5r6q0n1jxh"))))
15173 (build-system r-build-system)
15175 `(("r-mass" ,r-mass)
15176 ("r-dplyr" ,r-dplyr)
15177 ("r-tidyr" ,r-tidyr)
15178 ("r-purrr" ,r-purrr)
15179 ("r-readr" ,r-readr)
15180 ("r-magrittr" ,r-magrittr)
15181 ("r-ggplot2" ,r-ggplot2)))
15182 (home-page "https://github.com/kcha/psiplot")
15183 (synopsis "Plot percent spliced-in values of alternatively-spliced exons")
15185 "PSIplot is an R package for generating plots of @dfn{percent
15186 spliced-in} (PSI) values of alternatively-spliced exons that were computed by
15187 vast-tools, an RNA-Seq pipeline for alternative splicing analysis. The plots
15188 are generated using @code{ggplot2}.")
15189 (license license:expat)))
15191 (define-public python-ont-fast5-api
15193 (name "python-ont-fast5-api")
15198 (uri (git-reference
15199 (url "https://github.com/nanoporetech/ont_fast5_api.git")
15200 (commit (string-append "release_" version))))
15201 (file-name (git-file-name name version))
15204 "03cbq4zbbwhll8ml2m9k8sa31mirsvcbjkrq1yna0kkzz9fad5fm"))))
15205 (build-system python-build-system)
15207 `(("python-numpy" ,python-numpy)
15208 ("python-six" ,python-six)
15209 ("python-h5py" ,python-h5py)
15210 ("python-progressbar33" ,python-progressbar33)))
15211 (home-page "https://github.com/nanoporetech/ont_fast5_api")
15212 (synopsis "Interface to HDF5 files of the Oxford Nanopore fast5 file format")
15214 "This package provides a concrete implementation of the fast5 file schema
15215 using the generic @code{h5py} library, plain-named methods to interact with
15216 and reflect the fast5 file schema, and tools to convert between
15217 @code{multi_read} and @code{single_read} formats.")
15218 (license license:mpl2.0)))
15220 (define-public tbsp
15221 (let ((commit "ec8fff4410cfb13a677dbbb95cbbc60217e64907")
15225 (version (git-version "1.0.0" revision commit))
15229 (uri (git-reference
15230 (url "https://github.com/phoenixding/tbsp.git")
15232 (file-name (git-file-name name version))
15235 "025ym14x8gbd6hb55lsinqj6f5qzw36i10klgs7ldzxxd7s39ki1"))))
15236 (build-system python-build-system)
15237 (arguments '(#:tests? #f)) ; no tests included
15239 `(("python-matplotlib" ,python-matplotlib)
15240 ("python-networkx" ,python-networkx)
15241 ("python-numpy" ,python-numpy)
15242 ("python-pybigwig" ,python-pybigwig)
15243 ("python-biopython" ,python-biopython)
15244 ("python-scikit-learn" ,python-scikit-learn)
15245 ("python-scipy" ,python-scipy)))
15246 (home-page "https://github.com/phoenixding/tbsp/")
15247 (synopsis "SNP-based trajectory inference")
15249 "Several studies focus on the inference of developmental and response
15250 trajectories from single cell RNA-Seq (scRNA-Seq) data. A number of
15251 computational methods, often referred to as pseudo-time ordering, have been
15252 developed for this task. CRISPR has also been used to reconstruct lineage
15253 trees by inserting random mutations. The tbsp package implements an
15254 alternative method to detect significant, cell type specific sequence
15255 mutations from scRNA-Seq data.")
15256 (license license:expat))))
15258 (define-public tabixpp
15264 (uri (git-reference
15265 (url "https://github.com/ekg/tabixpp")
15266 (commit (string-append "v" version))))
15267 (file-name (git-file-name name version))
15269 (base32 "1k2a3vbq96ic4lw72iwp5s3mwwc4xhdffjj584yn6l9637q9j1yd"))
15270 (modules '((guix build utils)))
15273 (delete-file-recursively "htslib") #t))))
15274 (build-system gnu-build-system)
15276 `(("htslib" ,htslib)
15279 `(#:tests? #f ; There are no tests to run.
15281 (modify-phases %standard-phases
15282 (delete 'configure) ; There is no configure phase.
15283 ;; The build phase needs overriding the location of htslib.
15285 (lambda* (#:key inputs #:allow-other-keys)
15286 (let ((htslib-ref (assoc-ref inputs "htslib")))
15288 (string-append "HTS_LIB=" htslib-ref "/lib/libhts.a")
15289 (string-append "INCLUDES= -I" htslib-ref "/include/htslib")
15290 "HTS_HEADERS=" ; No need to check for headers here.
15291 (string-append "LIBPATH=-L. -L" htslib-ref "/include")))))
15293 (lambda* (#:key outputs #:allow-other-keys)
15294 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15295 (install-file "tabix++" bin))
15297 (home-page "https://github.com/ekg/tabixpp")
15298 (synopsis "C++ wrapper around tabix project")
15299 (description "This is a C++ wrapper around the Tabix project which abstracts
15300 some of the details of opening and jumping in tabix-indexed files.")
15301 (license license:expat)))
15303 (define-public smithwaterman
15304 (let ((commit "2610e259611ae4cde8f03c72499d28f03f6d38a7"))
15306 (name "smithwaterman")
15307 (version (git-version "0.0.0" "2" commit))
15310 (uri (git-reference
15311 (url "https://github.com/ekg/smithwaterman/")
15313 (file-name (git-file-name name version))
15315 (base32 "0i9d8zrxpiracw3mxzd9siybpy62p06rqz9mc2w93arajgbk45bs"))))
15316 (build-system gnu-build-system)
15318 `(#:tests? #f ; There are no tests to run.
15319 #:make-flags '("libsw.a" "all")
15321 (modify-phases %standard-phases
15322 (delete 'configure) ; There is no configure phase.
15324 (lambda* (#:key outputs #:allow-other-keys)
15325 (let* ((out (assoc-ref outputs "out"))
15326 (bin (string-append out "/bin"))
15327 (lib (string-append out "/lib")))
15328 (install-file "smithwaterman" bin)
15329 (install-file "libsw.a" lib))
15331 (home-page "https://github.com/ekg/smithwaterman")
15332 (synopsis "Implementation of the Smith-Waterman algorithm")
15333 (description "Implementation of the Smith-Waterman algorithm.")
15334 ;; The licensing terms are unclear: https://github.com/ekg/smithwaterman/issues/9.
15335 (license (list license:gpl2 license:expat)))))
15337 (define-public multichoose
15339 (name "multichoose")
15343 (uri (git-reference
15344 (url "https://github.com/ekg/multichoose/")
15345 (commit (string-append "v" version))))
15346 (file-name (git-file-name name version))
15348 (base32 "0ci5fqvmpamwgxvmyd79ygj6n3bnbl3vc7b6h1sxz58186sm3pfs"))))
15349 (build-system gnu-build-system)
15351 `(#:tests? #f ; Tests require node.
15353 (modify-phases %standard-phases
15354 (delete 'configure) ; There is no configure phase.
15356 (lambda* (#:key outputs #:allow-other-keys)
15357 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15358 ;; TODO: There are Python modules for these programs too.
15359 (install-file "multichoose" bin)
15360 (install-file "multipermute" bin))
15362 (home-page "https://github.com/ekg/multichoose")
15363 (synopsis "Efficient loopless multiset combination generation algorithm")
15364 (description "This library implements an efficient loopless multiset
15365 combination generation algorithm which is (approximately) described in
15366 \"Loopless algorithms for generating permutations, combinations, and other
15367 combinatorial configurations.\", G. Ehrlich - Journal of the ACM (JACM),
15368 1973. (Algorithm 7.)")
15369 (license license:expat)))
15371 (define-public fsom
15372 (let ((commit "a6ef318fbd347c53189384aef7f670c0e6ce89a3"))
15375 (version (git-version "0.0.0" "1" commit))
15378 (uri (git-reference
15379 (url "https://github.com/ekg/fsom/")
15381 (file-name (git-file-name name version))
15383 (base32 "0gw1lpvr812pywg9y546x0h1hhj261xwls41r6kqhddjlrcjc0pi"))))
15384 (build-system gnu-build-system)
15386 `(#:tests? #f ; There are no tests to run.
15388 (modify-phases %standard-phases
15389 (delete 'configure) ; There is no configure phase.
15391 (lambda* (#:key outputs #:allow-other-keys)
15392 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15393 (install-file "fsom" bin))
15395 (home-page "https://github.com/ekg/fsom")
15396 (synopsis "Manage SOM (Self-Organizing Maps) neural networks")
15397 (description "A tiny C library for managing SOM (Self-Organizing Maps)
15399 (license license:gpl3))))
15401 (define-public fastahack
15407 (uri (git-reference
15408 (url "https://github.com/ekg/fastahack/")
15409 (commit (string-append "v" version))))
15410 (file-name (git-file-name name version))
15412 (base32 "0rp1blskhzxf7vbh253ibpxbgl9wwgyzf1wbkxndi08d3j4vcss9"))))
15413 (build-system gnu-build-system)
15415 `(#:tests? #f ; Unclear how to run tests: https://github.com/ekg/fastahack/issues/15
15417 (modify-phases %standard-phases
15418 (delete 'configure) ; There is no configure phase.
15420 (lambda* (#:key outputs #:allow-other-keys)
15421 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15422 (install-file "fastahack" bin))
15424 (home-page "https://github.com/ekg/fastahack")
15425 (synopsis "Indexing and sequence extraction from FASTA files")
15426 (description "Fastahack is a small application for indexing and
15427 extracting sequences and subsequences from FASTA files. The included library
15428 provides a FASTA reader and indexer that can be embedded into applications
15429 which would benefit from directly reading subsequences from FASTA files. The
15430 library automatically handles index file generation and use.")
15431 (license (list license:expat license:gpl2))))
15433 (define-public vcflib
15440 (uri (string-append "https://github.com/vcflib/vcflib/releases/"
15441 "download/v" version
15442 "/vcflib-" version "-src.tar.gz"))
15444 (base32 "14zzrg8hg8cq9cvq2wdvp21j7nmxxkjrbagw2apd2yqv2kyx42lm"))
15445 (modules '((guix build utils)))
15448 (for-each delete-file-recursively
15449 '("fastahack" "filevercmp" "fsom" "googletest" "intervaltree"
15450 "libVCFH" "multichoose" "smithwaterman" "tabixpp"))
15452 (build-system gnu-build-system)
15454 `(("htslib" ,htslib)
15460 ;; This package builds against the .o files so we need to extract the source.
15461 ("fastahack-src" ,(package-source fastahack))
15462 ("filevercmp-src" ,(package-source filevercmp))
15463 ("fsom-src" ,(package-source fsom))
15464 ("intervaltree-src" ,(package-source intervaltree))
15465 ("multichoose-src" ,(package-source multichoose))
15466 ("smithwaterman-src" ,(package-source smithwaterman))
15467 ("tabixpp-src" ,(package-source tabixpp))))
15469 `(#:tests? #f ; no tests
15470 #:make-flags (list (string-append "HTS_LIB="
15471 (assoc-ref %build-inputs "htslib")
15473 (string-append "HTS_INCLUDES= -I"
15474 (assoc-ref %build-inputs "htslib")
15476 (string-append "HTS_LDFLAGS= -L"
15477 (assoc-ref %build-inputs "htslib")
15478 "/include/htslib" " -lhts"))
15480 (modify-phases %standard-phases
15481 (delete 'configure)
15483 (add-after 'unpack 'unpack-submodule-sources
15484 (lambda* (#:key inputs #:allow-other-keys)
15485 (let ((unpack (lambda (source target)
15487 (with-directory-excursion target
15488 (if (file-is-directory? (assoc-ref inputs source))
15489 (copy-recursively (assoc-ref inputs source) ".")
15490 (invoke "tar" "xvf"
15491 (assoc-ref inputs source)
15492 "--strip-components=1"))))))
15494 (unpack "fastahack-src" "fastahack")
15495 (unpack "filevercmp-src" "filevercmp")
15496 (unpack "fsom-src" "fsom")
15497 (unpack "intervaltree-src" "intervaltree")
15498 (unpack "multichoose-src" "multichoose")
15499 (unpack "smithwaterman-src" "smithwaterman")
15500 (unpack "tabixpp-src" "tabixpp")))))
15502 (lambda* (#:key inputs make-flags #:allow-other-keys)
15503 (let ((htslib (assoc-ref inputs "htslib")))
15504 (with-directory-excursion "tabixpp"
15505 (substitute* "Makefile"
15506 (("-Ihtslib") (string-append "-I" htslib "/include/htslib"))
15507 (("-Lhtslib") (string-append "-L" htslib "/lib/htslib"))
15508 (("htslib/htslib") (string-append htslib "/include/htslib")))
15510 (string-append "HTS_LIB=" htslib "/lib/libhts.a")))
15511 (apply invoke "make" "CC=gcc" "CFLAGS=-Itabixpp" make-flags))))
15513 (lambda* (#:key outputs #:allow-other-keys)
15514 (let ((bin (string-append (assoc-ref outputs "out") "/bin"))
15515 (lib (string-append (assoc-ref outputs "out") "/lib")))
15516 (for-each (lambda (file)
15517 (install-file file bin))
15518 (find-files "bin" ".*"))
15519 ;; The header files in src/ do not interface libvcflib,
15520 ;; therefore they are left out.
15521 (install-file "libvcflib.a" lib))
15523 (home-page "https://github.com/vcflib/vcflib/")
15524 (synopsis "Library for parsing and manipulating VCF files")
15525 (description "Vcflib provides methods to manipulate and interpret
15526 sequence variation as it can be described by VCF. It is both an API for parsing
15527 and operating on records of genomic variation as it can be described by the VCF
15528 format, and a collection of command-line utilities for executing complex
15529 manipulations on VCF files.")
15530 (license license:expat)))
15532 (define-public freebayes
15533 (let ((commit "3ce827d8ebf89bb3bdc097ee0fe7f46f9f30d5fb")
15538 (version (git-version version revision commit))
15541 (uri (git-reference
15542 (url "https://github.com/ekg/freebayes.git")
15544 (file-name (git-file-name name version))
15546 (base32 "1sbzwmcbn78ybymjnhwk7qc5r912azy5vqz2y7y81616yc3ba2a2"))))
15547 (build-system gnu-build-system)
15549 `(("bamtools" ,bamtools)
15553 `(("bc" ,bc) ; Needed for running tests.
15554 ("samtools" ,samtools) ; Needed for running tests.
15555 ("parallel" ,parallel) ; Needed for running tests.
15556 ("perl" ,perl) ; Needed for running tests.
15557 ("procps" ,procps) ; Needed for running tests.
15558 ("python" ,python-2) ; Needed for running tests.
15559 ("vcflib-src" ,(package-source vcflib))
15560 ;; These are submodules for the vcflib version used in freebayes.
15561 ;; This package builds against the .o files so we need to extract the source.
15562 ("tabixpp-src" ,(package-source tabixpp))
15563 ("smithwaterman-src" ,(package-source smithwaterman))
15564 ("multichoose-src" ,(package-source multichoose))
15565 ("fsom-src" ,(package-source fsom))
15566 ("filevercmp-src" ,(package-source filevercmp))
15567 ("fastahack-src" ,(package-source fastahack))
15568 ("intervaltree-src" ,(package-source intervaltree))
15569 ;; These submodules are needed to run the tests.
15570 ("bash-tap-src" ,(package-source bash-tap))
15571 ("test-simple-bash-src"
15574 (uri (git-reference
15575 (url "https://github.com/ingydotnet/test-simple-bash/")
15576 (commit "124673ff204b01c8e96b7fc9f9b32ee35d898acc")))
15577 (file-name "test-simple-bash-src-checkout")
15579 (base32 "043plp6z0x9yf7mdpky1fw7zcpwn1p47px95w9mh16603zqqqpga"))))))
15583 (string-append "BAMTOOLS_ROOT="
15584 (assoc-ref %build-inputs "bamtools")))
15585 #:test-target "test"
15587 (modify-phases %standard-phases
15588 (delete 'configure)
15589 (add-after 'unpack 'fix-tests
15591 (substitute* "test/t/01_call_variants.t"
15592 (("grep -P \"\\(\\\\t500\\$\\|\\\\t11000\\$\\|\\\\t1000\\$\\)\"")
15593 "grep -E ' (500|11000|1000)$'"))
15595 (add-after 'unpack 'unpack-submodule-sources
15596 (lambda* (#:key inputs #:allow-other-keys)
15597 (let ((unpack (lambda (source target)
15598 (with-directory-excursion target
15599 (if (file-is-directory? (assoc-ref inputs source))
15600 (copy-recursively (assoc-ref inputs source) ".")
15601 (invoke "tar" "xvf"
15602 (assoc-ref inputs source)
15603 "--strip-components=1"))))))
15605 (unpack "vcflib-src" "vcflib")
15606 (unpack "fastahack-src" "vcflib/fastahack")
15607 (unpack "filevercmp-src" "vcflib/filevercmp")
15608 (unpack "fsom-src" "vcflib/fsom")
15609 (unpack "intervaltree-src" "vcflib/intervaltree")
15610 (unpack "multichoose-src" "vcflib/multichoose")
15611 (unpack "smithwaterman-src" "vcflib/smithwaterman")
15612 (unpack "tabixpp-src" "vcflib/tabixpp")
15613 (unpack "test-simple-bash-src" "test/test-simple-bash")
15614 (unpack "bash-tap-src" "test/bash-tap")))))
15615 (add-after 'unpack-submodule-sources 'fix-makefiles
15617 ;; We don't have the .git folder to get the version tag from.
15618 (substitute* "vcflib/Makefile"
15619 (("^GIT_VERSION.*")
15620 (string-append "GIT_VERSION = v" ,version)))
15621 (substitute* "src/Makefile"
15622 (("-I\\$\\(BAMTOOLS_ROOT\\)/src")
15623 "-I$(BAMTOOLS_ROOT)/include/bamtools"))
15625 (add-before 'build 'build-tabixpp-and-vcflib
15626 (lambda* (#:key inputs make-flags #:allow-other-keys)
15627 (with-directory-excursion "vcflib"
15628 (with-directory-excursion "tabixpp"
15629 (apply invoke "make"
15630 (string-append "HTS_LIB="
15631 (assoc-ref inputs "htslib")
15634 (apply invoke "make"
15635 (string-append "CFLAGS=-Itabixpp")
15639 (lambda* (#:key outputs #:allow-other-keys)
15640 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15641 (install-file "bin/freebayes" bin)
15642 (install-file "bin/bamleftalign" bin))
15644 (home-page "https://github.com/ekg/freebayes")
15645 (synopsis "Haplotype-based variant detector")
15646 (description "FreeBayes is a Bayesian genetic variant detector designed to
15647 find small polymorphisms, specifically SNPs (single-nucleotide polymorphisms),
15648 indels (insertions and deletions), MNPs (multi-nucleotide polymorphisms), and
15649 complex events (composite insertion and substitution events) smaller than the
15650 length of a short-read sequencing alignment.")
15651 (license license:expat))))
15653 (define-public samblaster
15655 (name "samblaster")
15659 (uri (git-reference
15660 (url "https://github.com/GregoryFaust/samblaster.git")
15661 (commit (string-append "v." version))))
15662 (file-name (git-file-name name version))
15665 "0iv2ddfw8363vb2x8gr3p8g88whb6mb9m0pf71i2cqsbv6jghap7"))))
15666 (build-system gnu-build-system)
15668 `(#:tests? #f ; there are none
15670 (modify-phases %standard-phases
15671 (delete 'configure) ; There is no configure phase.
15673 (lambda* (#:key outputs #:allow-other-keys)
15674 (install-file "samblaster"
15675 (string-append (assoc-ref outputs "out") "/bin"))
15677 (home-page "https://github.com/GregoryFaust/samblaster")
15678 (synopsis "Mark duplicates in paired-end SAM files")
15679 (description "Samblaster is a fast and flexible program for marking
15680 duplicates in read-id grouped paired-end SAM files. It can also optionally
15681 output discordant read pairs and/or split read mappings to separate SAM files,
15682 and/or unmapped/clipped reads to a separate FASTQ file. When marking
15683 duplicates, samblaster will require approximately 20MB of memory per 1M read
15685 (license license:expat)))
15687 (define-public r-velocyto
15688 (let ((commit "d7790346cb99f49ab9c2b23ba70dcf9d2c9fc350")
15691 (name "r-velocyto")
15692 (version (git-version "0.6" revision commit))
15696 (uri (git-reference
15697 (url "https://github.com/velocyto-team/velocyto.R.git")
15699 (file-name (git-file-name name version))
15702 "16wqf70j7rd7pay2q513iyz12i8n9vrpg1bisah4lddbcpx5dz1n"))))
15703 (build-system r-build-system)
15705 `(("boost" ,boost)))
15707 `(("r-hdf5r" ,r-hdf5r)
15710 ("r-pcamethods" ,r-pcamethods)
15712 ("r-rcpparmadillo" ,r-rcpparmadillo)
15713 ;; Suggested packages
15714 ("r-rtsne" ,r-rtsne)
15715 ("r-cluster" ,r-cluster)
15716 ("r-abind" ,r-abind)
15718 ("r-biocgenerics" ,r-biocgenerics)
15719 ("r-genomicalignments" ,r-genomicalignments)
15720 ("r-rsamtools" ,r-rsamtools)
15721 ("r-edger" ,r-edger)
15722 ("r-igraph" ,r-igraph)))
15723 (home-page "https://velocyto.org")
15724 (synopsis "RNA velocity estimation in R")
15726 "This package provides basic routines for estimation of gene-specific
15727 transcriptional derivatives and visualization of the resulting velocity
15729 (license license:gpl3))))
15731 (define-public methyldackel
15733 (name "methyldackel")
15737 (uri (git-reference
15738 (url "https://github.com/dpryan79/MethylDackel.git")
15740 (file-name (git-file-name name version))
15743 "10gh8k0ca92kywnrw5pkacq3g6r8s976s12k8jhp8g3g49q9a97g"))))
15744 (build-system gnu-build-system)
15746 `(#:test-target "test"
15749 (string-append "prefix="
15750 (assoc-ref %outputs "out") "/bin/"))
15752 (modify-phases %standard-phases
15753 (replace 'configure
15754 (lambda* (#:key outputs #:allow-other-keys)
15755 (substitute* "Makefile"
15756 (("install MethylDackel \\$\\(prefix\\)" match)
15757 (string-append "install -d $(prefix); " match)))
15760 `(("htslib" ,htslib)
15762 ;; Needed for tests
15764 `(("python" ,python-wrapper)))
15765 (home-page "https://github.com/dpryan79/MethylDackel")
15766 (synopsis "Universal methylation extractor for BS-seq experiments")
15768 "MethylDackel will process a coordinate-sorted and indexed BAM or CRAM
15769 file containing some form of BS-seq alignments and extract per-base
15770 methylation metrics from them. MethylDackel requires an indexed fasta file
15771 containing the reference genome as well.")
15772 ;; See https://github.com/dpryan79/MethylDackel/issues/85
15773 (license license:expat)))
15775 (define-public python-gffutils
15776 ;; The latest release is older more than a year than the latest commit
15777 (let ((commit "4034c54600813b1402945e12faa91b3a53162cf1")
15780 (name "python-gffutils")
15781 (version (git-version "0.9" revision commit))
15785 (uri (git-reference
15786 (url "https://github.com/daler/gffutils.git")
15788 (file-name (git-file-name name version))
15791 "1rwafjdnbir5wnk0ap06ww4lra3p5frhy7mfs03rlldgfnwxymsn"))))
15792 (build-system python-build-system)
15795 (modify-phases %standard-phases
15798 ;; Tests need to access the HOME directory
15799 (setenv "HOME" "/tmp")
15800 (invoke "nosetests" "-a" "!slow")))
15801 (add-after 'unpack 'make-gz-files-writable
15803 (for-each make-file-writable
15804 (find-files "." "\\.gz"))
15807 `(("python-argcomplete" ,python-argcomplete)
15808 ("python-argh" ,python-argh)
15809 ("python-biopython" ,python-biopython)
15810 ("python-pybedtools" ,python-pybedtools)
15811 ("python-pyfaidx" ,python-pyfaidx)
15812 ("python-simplejson" ,python-simplejson)
15813 ("python-six" ,python-six)))
15815 `(("python-nose" , python-nose)))
15816 (home-page "https://github.com/daler/gffutils")
15817 (synopsis "Tool for manipulation of GFF and GTF files")
15819 "python-gffutils is a Python package for working with and manipulating
15820 the GFF and GTF format files typically used for genomic annotations. The
15821 files are loaded into a SQLite database, allowing much more complex
15822 manipulation of hierarchical features (e.g., genes, transcripts, and exons)
15823 than is possible with plain-text methods alone.")
15824 (license license:expat))))
15826 (define-public libsbml
15832 (uri (string-append "mirror://sourceforge/sbml/libsbml/"
15833 version "/stable/libSBML-"
15834 version "-core-src.tar.gz"))
15837 "0slkagrk3nfi2qsksv6b1brj6zhx4bj4bkib2sdycvrcd10ql2lh"))))
15838 (build-system cmake-build-system)
15840 `(#:test-target "test"
15842 (list "-DWITH_CHECK=ON"
15843 (string-append "-DLIBXML_LIBRARY="
15844 (assoc-ref %build-inputs "libxml2")
15846 (string-append "-DLIBXML_INCLUDE_DIR="
15847 (assoc-ref %build-inputs "libxml2")
15848 "/include/libxml2"))))
15850 `(("libxml2" ,libxml2)))
15854 (home-page "http://sbml.org/Software/libSBML")
15855 (synopsis "Process SBML files and data streams")
15856 (description "LibSBML is a library to help you read, write, manipulate,
15857 translate, and validate SBML files and data streams. The @dfn{Systems Biology
15858 Markup Language} (SBML) is an interchange format for computer models of
15859 biological processes. SBML is useful for models of metabolism, cell
15860 signaling, and more. It continues to be evolved and expanded by an
15861 international community.")
15862 (license license:lgpl2.1+)))
15864 (define-public grocsvs
15865 ;; The last release is out of date and new features have been added.
15866 (let ((commit "ecd956a65093a0b2c41849050e4512d46fecea5d")
15870 (version (git-version "0.2.6.1" revision commit))
15873 (uri (git-reference
15874 (url "https://github.com/grocsvs/grocsvs")
15876 (file-name (git-file-name name version))
15878 (base32 "14505725gr7qxc17cxxf0k6lzcwmgi64pija4mwf29aw70qn35cc"))
15879 (patches (search-patches "grocsvs-dont-use-admiral.patch"))))
15880 (build-system python-build-system)
15882 `(#:tests? #f ; No test suite.
15883 #:python ,python-2)) ; Only python-2 supported.
15885 `(("python2-h5py" ,python2-h5py)
15886 ("python2-ipython-cluster-helper" ,python2-ipython-cluster-helper)
15887 ("python2-networkx" ,python2-networkx)
15888 ("python2-psutil" ,python2-psutil)
15889 ("python2-pandas" ,python2-pandas)
15890 ("python2-pybedtools" ,python2-pybedtools)
15891 ("python2-pyfaidx" ,python2-pyfaidx)
15892 ("python2-pygraphviz" ,python2-pygraphviz)
15893 ("python2-pysam" ,python2-pysam)
15894 ("python2-scipy" ,python2-scipy)))
15895 (home-page "https://github.com/grocsvs/grocsvs")
15896 (synopsis "Genome-wide reconstruction of complex structural variants")
15898 "@dfn{Genome-wide Reconstruction of Complex Structural Variants}
15899 (GROC-SVs) is a software pipeline for identifying large-scale structural
15900 variants, performing sequence assembly at the breakpoints, and reconstructing
15901 the complex structural variants using the long-fragment information from the
15902 10x Genomics platform.")
15903 (license license:expat))))