1 ;;; GNU Guix --- Functional package management for GNU
2 ;;; Copyright © 2014, 2015, 2016, 2017, 2018, 2019 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 Roel Janssen <roel@gnu.org>
7 ;;; Copyright © 2016, 2017, 2018, 2019 Efraim Flashner <efraim@flashner.co.il>
8 ;;; Copyright © 2016 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 Mădălin Ionel Patrașcu <madalinionel.patrascu@mdc-berlin.de>
15 ;;; Copyright © 2019 Maxim Cournoyer <maxim.cournoyer@gmail.com>
17 ;;; This file is part of GNU Guix.
19 ;;; GNU Guix is free software; you can redistribute it and/or modify it
20 ;;; under the terms of the GNU General Public License as published by
21 ;;; the Free Software Foundation; either version 3 of the License, or (at
22 ;;; your option) any later version.
24 ;;; GNU Guix is distributed in the hope that it will be useful, but
25 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
26 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
27 ;;; GNU General Public License for more details.
29 ;;; You should have received a copy of the GNU General Public License
30 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
32 (define-module (gnu packages bioinformatics)
33 #:use-module ((guix licenses) #:prefix license:)
34 #:use-module (guix packages)
35 #:use-module (guix utils)
36 #:use-module (guix download)
37 #:use-module (guix git-download)
38 #:use-module (guix hg-download)
39 #:use-module (guix build-system ant)
40 #:use-module (guix build-system gnu)
41 #:use-module (guix build-system cmake)
42 #:use-module (guix build-system haskell)
43 #:use-module (guix build-system meson)
44 #:use-module (guix build-system ocaml)
45 #:use-module (guix build-system perl)
46 #:use-module (guix build-system python)
47 #:use-module (guix build-system r)
48 #:use-module (guix build-system ruby)
49 #:use-module (guix build-system scons)
50 #:use-module (guix build-system trivial)
51 #:use-module (gnu packages)
52 #:use-module (gnu packages autotools)
53 #:use-module (gnu packages algebra)
54 #:use-module (gnu packages base)
55 #:use-module (gnu packages bash)
56 #:use-module (gnu packages bison)
57 #:use-module (gnu packages bioconductor)
58 #:use-module (gnu packages boost)
59 #:use-module (gnu packages check)
60 #:use-module (gnu packages compression)
61 #:use-module (gnu packages cpio)
62 #:use-module (gnu packages cran)
63 #:use-module (gnu packages curl)
64 #:use-module (gnu packages documentation)
65 #:use-module (gnu packages databases)
66 #:use-module (gnu packages datastructures)
67 #:use-module (gnu packages file)
68 #:use-module (gnu packages flex)
69 #:use-module (gnu packages gawk)
70 #:use-module (gnu packages gcc)
71 #:use-module (gnu packages gd)
72 #:use-module (gnu packages gtk)
73 #:use-module (gnu packages glib)
74 #:use-module (gnu packages graph)
75 #:use-module (gnu packages groff)
76 #:use-module (gnu packages guile)
77 #:use-module (gnu packages guile-xyz)
78 #:use-module (gnu packages haskell)
79 #:use-module (gnu packages haskell-check)
80 #:use-module (gnu packages haskell-web)
81 #:use-module (gnu packages image)
82 #:use-module (gnu packages imagemagick)
83 #:use-module (gnu packages java)
84 #:use-module (gnu packages java-compression)
85 #:use-module (gnu packages jemalloc)
86 #:use-module (gnu packages dlang)
87 #:use-module (gnu packages linux)
88 #:use-module (gnu packages lisp)
89 #:use-module (gnu packages logging)
90 #:use-module (gnu packages machine-learning)
91 #:use-module (gnu packages man)
92 #:use-module (gnu packages maths)
93 #:use-module (gnu packages mpi)
94 #:use-module (gnu packages ncurses)
95 #:use-module (gnu packages ocaml)
96 #:use-module (gnu packages pcre)
97 #:use-module (gnu packages parallel)
98 #:use-module (gnu packages pdf)
99 #:use-module (gnu packages perl)
100 #:use-module (gnu packages perl-check)
101 #:use-module (gnu packages pkg-config)
102 #:use-module (gnu packages popt)
103 #:use-module (gnu packages protobuf)
104 #:use-module (gnu packages python)
105 #:use-module (gnu packages python-compression)
106 #:use-module (gnu packages python-web)
107 #:use-module (gnu packages python-xyz)
108 #:use-module (gnu packages readline)
109 #:use-module (gnu packages ruby)
110 #:use-module (gnu packages serialization)
111 #:use-module (gnu packages shells)
112 #:use-module (gnu packages statistics)
113 #:use-module (gnu packages swig)
114 #:use-module (gnu packages tbb)
115 #:use-module (gnu packages tex)
116 #:use-module (gnu packages texinfo)
117 #:use-module (gnu packages textutils)
118 #:use-module (gnu packages time)
119 #:use-module (gnu packages tls)
120 #:use-module (gnu packages vim)
121 #:use-module (gnu packages web)
122 #:use-module (gnu packages xml)
123 #:use-module (gnu packages xorg)
124 #:use-module (srfi srfi-1)
125 #:use-module (ice-9 match))
127 (define-public aragorn
134 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
138 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
139 (build-system gnu-build-system)
141 `(#:tests? #f ; there are no tests
143 (modify-phases %standard-phases
153 (string-append "aragorn" ,version ".c"))
156 (lambda* (#:key outputs #:allow-other-keys)
157 (let* ((out (assoc-ref outputs "out"))
158 (bin (string-append out "/bin"))
159 (man (string-append out "/share/man/man1")))
160 (install-file "aragorn" bin)
161 (install-file "aragorn.1" man))
163 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
164 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
166 "Aragorn identifies transfer RNA, mitochondrial RNA and
167 transfer-messenger RNA from nucleotide sequences, based on homology to known
168 tRNA consensus sequences and RNA structure. It also outputs the secondary
169 structure of the predicted RNA.")
170 (license license:gpl2)))
178 ;; BamM is not available on pypi.
180 (url "https://github.com/Ecogenomics/BamM.git")
183 (file-name (git-file-name name version))
186 "1p83ahi984ipslxlg4yqy1gdnya9rkn1v71z8djgxkm9d2chw4c5"))
187 (modules '((guix build utils)))
190 ;; Delete bundled htslib.
191 (delete-file-recursively "c/htslib-1.3.1")
193 (build-system python-build-system)
195 `(#:python ,python-2 ; BamM is Python 2 only.
196 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
197 ;; been modified from its original form.
199 (let ((htslib (assoc-ref %build-inputs "htslib")))
200 (list "--with-libhts-lib" (string-append htslib "/lib")
201 "--with-libhts-inc" (string-append htslib "/include/htslib")))
203 (modify-phases %standard-phases
204 (add-after 'unpack 'autogen
206 (with-directory-excursion "c"
207 (let ((sh (which "sh")))
208 (for-each make-file-writable (find-files "." ".*"))
209 ;; Use autogen so that 'configure' works.
210 (substitute* "autogen.sh" (("/bin/sh") sh))
211 (setenv "CONFIG_SHELL" sh)
212 (invoke "./autogen.sh")))
215 ;; Run tests after installation so compilation only happens once.
217 (add-after 'install 'wrap-executable
218 (lambda* (#:key outputs #:allow-other-keys)
219 (let* ((out (assoc-ref outputs "out"))
220 (path (getenv "PATH")))
221 (wrap-program (string-append out "/bin/bamm")
222 `("PATH" ":" prefix (,path))))
224 (add-after 'wrap-executable 'post-install-check
225 (lambda* (#:key inputs outputs #:allow-other-keys)
227 (string-append (assoc-ref outputs "out")
232 (assoc-ref outputs "out")
234 (string-take (string-take-right
235 (assoc-ref inputs "python") 5) 3)
237 (getenv "PYTHONPATH")))
238 ;; There are 2 errors printed, but they are safe to ignore:
239 ;; 1) [E::hts_open_format] fail to open file ...
240 ;; 2) samtools view: failed to open ...
244 `(("autoconf" ,autoconf)
245 ("automake" ,automake)
248 ("python-nose" ,python2-nose)
249 ("python-pysam" ,python2-pysam)))
251 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
252 ("samtools" ,samtools)
256 ("coreutils" ,coreutils)))
258 `(("python-numpy" ,python2-numpy)))
259 (home-page "http://ecogenomics.github.io/BamM/")
260 (synopsis "Metagenomics-focused BAM file manipulator")
262 "BamM is a C library, wrapped in python, to efficiently generate and
263 parse BAM files, specifically for the analysis of metagenomic data. For
264 instance, it implements several methods to assess contig-wise read coverage.")
265 (license license:lgpl3+)))
267 (define-public bamtools
274 (url "https://github.com/pezmaster31/bamtools.git")
275 (commit (string-append "v" version))))
276 (file-name (git-file-name name version))
279 "0nfb2ypcx9959xnbz6wxh6py3xfizgmg8nrknxl95c507m9hmq8b"))))
280 (build-system cmake-build-system)
282 `(#:tests? #f ;no "check" target
284 (modify-phases %standard-phases
286 'configure 'set-ldflags
287 (lambda* (#:key outputs #:allow-other-keys)
291 (assoc-ref outputs "out") "/lib/bamtools"))
293 (inputs `(("zlib" ,zlib)))
294 (home-page "https://github.com/pezmaster31/bamtools")
295 (synopsis "C++ API and command-line toolkit for working with BAM data")
297 "BamTools provides both a C++ API and a command-line toolkit for handling
299 (license license:expat)))
301 (define-public bcftools
307 (uri (string-append "https://github.com/samtools/bcftools/"
309 version "/bcftools-" version ".tar.bz2"))
312 "1j3h638i8kgihzyrlnpj82xg1b23sijibys9hvwari3fy7kd0dkg"))
313 (modules '((guix build utils)))
315 ;; Delete bundled htslib.
316 (delete-file-recursively "htslib-1.9")
318 (build-system gnu-build-system)
321 (list "--enable-libgsl")
324 (modify-phases %standard-phases
325 (add-before 'check 'patch-tests
327 (substitute* "test/test.pl"
328 (("/bin/bash") (which "bash")))
336 (home-page "https://samtools.github.io/bcftools/")
337 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
339 "BCFtools is a set of utilities that manipulate variant calls in the
340 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
341 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
342 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
343 (license (list license:gpl3+ license:expat))))
345 (define-public bedops
352 (url "https://github.com/bedops/bedops.git")
353 (commit (string-append "v" version))))
354 (file-name (git-file-name name version))
357 "0mmgsgwz5r9w76hzgxkxc9s9lkdhhaf7vr6i02b09vbswvs1fyqx"))))
358 (build-system gnu-build-system)
361 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
363 (modify-phases %standard-phases
364 (add-after 'unpack 'unpack-tarballs
366 ;; FIXME: Bedops includes tarballs of minimally patched upstream
367 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
368 ;; libraries because at least one of the libraries (zlib) is
369 ;; patched to add a C++ function definition (deflateInit2cpp).
370 ;; Until the Bedops developers offer a way to link against system
371 ;; libraries we have to build the in-tree copies of these three
374 ;; See upstream discussion:
375 ;; https://github.com/bedops/bedops/issues/124
377 ;; Unpack the tarballs to benefit from shebang patching.
378 (with-directory-excursion "third-party"
379 (invoke "tar" "xvf" "jansson-2.6.tar.bz2")
380 (invoke "tar" "xvf" "zlib-1.2.7.tar.bz2")
381 (invoke "tar" "xvf" "bzip2-1.0.6.tar.bz2"))
382 ;; Disable unpacking of tarballs in Makefile.
383 (substitute* "system.mk/Makefile.linux"
384 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
385 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
386 (substitute* "third-party/zlib-1.2.7/Makefile.in"
387 (("^SHELL=.*$") "SHELL=bash\n"))
389 (delete 'configure))))
390 (home-page "https://github.com/bedops/bedops")
391 (synopsis "Tools for high-performance genomic feature operations")
393 "BEDOPS is a suite of tools to address common questions raised in genomic
394 studies---mostly with regard to overlap and proximity relationships between
395 data sets. It aims to be scalable and flexible, facilitating the efficient
396 and accurate analysis and management of large-scale genomic data.
398 BEDOPS provides tools that perform highly efficient and scalable Boolean and
399 other set operations, statistical calculations, archiving, conversion and
400 other management of genomic data of arbitrary scale. Tasks can be easily
401 split by chromosome for distributing whole-genome analyses across a
402 computational cluster.")
403 (license license:gpl2+)))
405 (define-public bedtools
411 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
412 "download/v" version "/"
413 "bedtools-" version ".tar.gz"))
416 "1ndg5yknrxl4djx8ddzgk12rrbiidfpmkkg5z3f95jzryfxarhn8"))))
417 (build-system gnu-build-system)
419 '(#:test-target "test"
421 (list (string-append "prefix=" (assoc-ref %outputs "out")))
423 (modify-phases %standard-phases
424 (delete 'configure))))
425 (native-inputs `(("python" ,python-2)))
427 `(("samtools" ,samtools)
429 (home-page "https://github.com/arq5x/bedtools2")
430 (synopsis "Tools for genome analysis and arithmetic")
432 "Collectively, the bedtools utilities are a swiss-army knife of tools for
433 a wide-range of genomics analysis tasks. The most widely-used tools enable
434 genome arithmetic: that is, set theory on the genome. For example, bedtools
435 allows one to intersect, merge, count, complement, and shuffle genomic
436 intervals from multiple files in widely-used genomic file formats such as BAM,
438 (license license:gpl2)))
440 ;; Later releases of bedtools produce files with more columns than
441 ;; what Ribotaper expects.
442 (define-public bedtools-2.18
443 (package (inherit bedtools)
448 (uri (string-append "https://github.com/arq5x/bedtools2/"
449 "releases/download/v" version
450 "/bedtools-" version ".tar.gz"))
453 "11rvca19ncg03kxd0wzlfx5ws7r3nisd0z8s9j9n182d8ksp2pxz"))))
455 '(#:test-target "test"
457 (modify-phases %standard-phases
460 (lambda* (#:key outputs #:allow-other-keys)
461 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
462 (for-each (lambda (file)
463 (install-file file bin))
464 (find-files "bin" ".*")))
467 ;; Needed for pybedtools.
468 (define-public bedtools-2.26
469 (package (inherit bedtools)
474 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
475 "download/v" version "/"
476 "bedtools-" version ".tar.gz"))
479 "0jhavwifnf7lmkb11h9y7dynr8d699h0rd2l52j1pfgircr2zwv5"))))))
488 (url "https://github.com/PacificBiosciences/pbbam.git")
490 (file-name (git-file-name name version))
493 "0h9gkrpf2lrxklxp72xfl5bi3h5zcm5hprrya9gf0hr3xwlbpp0x"))))
494 (build-system meson-build-system)
497 (modify-phases %standard-phases
498 (add-after 'unpack 'find-googletest
499 (lambda* (#:key inputs #:allow-other-keys)
500 ;; It doesn't find gtest_main because there's no pkg-config file
501 ;; for it. Find it another way.
502 (substitute* "tests/meson.build"
503 (("pbbam_gtest_dep = dependency\\('gtest_main'.*")
504 (format #f "cpp = meson.get_compiler('cpp')
505 pbbam_gtest_dep = cpp.find_library('gtest_main', dirs : '~a')\n"
506 (assoc-ref inputs "googletest"))))
508 ;; TODO: tests/pbbam_test cannot be linked
509 ;; ld: tests/59830eb@@pbbam_test@exe/src_test_Accuracy.cpp.o:
510 ;; undefined reference to symbol '_ZTIN7testing4TestE'
511 ;; ld: /gnu/store/...-googletest-1.8.0/lib/libgtest.so:
512 ;; error adding symbols: DSO missing from command line
514 #:configure-flags '("-Dtests=false")))
515 ;; These libraries are listed as "Required" in the pkg-config file.
521 ("samtools" ,samtools)))
523 `(("googletest" ,googletest)
524 ("pkg-config" ,pkg-config)
525 ("python" ,python-wrapper))) ; for tests
526 (home-page "https://github.com/PacificBiosciences/pbbam")
527 (synopsis "Work with PacBio BAM files")
529 "The pbbam software package provides components to create, query, and
530 edit PacBio BAM files and associated indices. These components include a core
531 C++ library, bindings for additional languages, and command-line utilities.
532 This library is not intended to be used as a general-purpose BAM utility - all
533 input and output BAMs must adhere to the PacBio BAM format specification.
534 Non-PacBio BAMs will cause exceptions to be thrown.")
535 (license license:bsd-3)))
537 (define-public blasr-libcpp
539 (name "blasr-libcpp")
544 (url "https://github.com/PacificBiosciences/blasr_libcpp.git")
546 (file-name (git-file-name name version))
549 "0cn5l42zyq67sj0g2imqkhayz2iqvv0a1pgpbmlq0qynjmsrbfd2"))))
550 (build-system meson-build-system)
553 (modify-phases %standard-phases
554 (add-after 'unpack 'link-with-hdf5
555 (lambda* (#:key inputs #:allow-other-keys)
556 (let ((hdf5 (assoc-ref inputs "hdf5")))
557 (substitute* "meson.build"
558 (("libblasr_deps = \\[" m)
561 (format #f "cpp.find_library('hdf5', dirs : '~a'), \
562 cpp.find_library('hdf5_cpp', dirs : '~a'), "
565 (add-after 'unpack 'find-googletest
566 (lambda* (#:key inputs #:allow-other-keys)
567 ;; It doesn't find gtest_main because there's no pkg-config file
568 ;; for it. Find it another way.
569 (substitute* "unittest/meson.build"
570 (("libblasr_gtest_dep = dependency\\('gtest_main'.*")
571 (format #f "cpp = meson.get_compiler('cpp')
572 libblasr_gtest_dep = cpp.find_library('gtest_main', dirs : '~a')\n"
573 (assoc-ref inputs "googletest"))))
575 ;; TODO: unittest/libblasr_unittest cannot be linked
576 ;; ld: ;; unittest/df08227@@libblasr_unittest@exe/alignment_utils_FileUtils_gtest.cpp.o:
577 ;; undefined reference to symbol
578 ;; '_ZN7testing8internal9DeathTest6CreateEPKcPKNS0_2REES3_iPPS1_'
579 ;; ld: /gnu/store/...-googletest-1.8.0/lib/libgtest.so:
580 ;; error adding symbols: DSO missing from command line
582 #:configure-flags '("-Dtests=false")))
589 `(("googletest" ,googletest)
590 ("pkg-config" ,pkg-config)))
591 (home-page "https://github.com/PacificBiosciences/blasr_libcpp")
592 (synopsis "Library for analyzing PacBio genomic sequences")
594 "This package provides three libraries used by applications for analyzing
595 PacBio genomic sequences. This library contains three sub-libraries: pbdata,
597 (license license:bsd-3)))
606 (url "https://github.com/PacificBiosciences/blasr.git")
608 (file-name (git-file-name name version))
611 "1skgy2mvz8gsgfh1gc2nfgwvpyzb1hpmp2cf2773h5wsj8nw22kl"))))
612 (build-system meson-build-system)
615 (modify-phases %standard-phases
616 (add-after 'unpack 'link-with-hdf5
617 (lambda* (#:key inputs #:allow-other-keys)
618 (let ((hdf5 (assoc-ref inputs "hdf5")))
619 (substitute* "meson.build"
620 (("blasr_deps = \\[" m)
623 (format #f "cpp.find_library('hdf5', dirs : '~a'), \
624 cpp.find_library('hdf5_cpp', dirs : '~a'), "
627 ;; Tests require "cram" executable, which is not packaged.
629 #:configure-flags '("-Dtests=false")))
632 ("blasr-libcpp" ,blasr-libcpp)
637 `(("pkg-config" ,pkg-config)))
638 (home-page "https://github.com/PacificBiosciences/blasr")
639 (synopsis "PacBio long read aligner")
641 "Blasr is a genomic sequence aligner for processing PacBio long reads.")
642 (license license:bsd-3)))
644 (define-public ribotaper
650 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
651 "files/RiboTaper/RiboTaper_Version_"
655 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
656 (build-system gnu-build-system)
659 (modify-phases %standard-phases
660 (add-after 'install 'wrap-executables
661 (lambda* (#:key inputs outputs #:allow-other-keys)
662 (let* ((out (assoc-ref outputs "out")))
665 (wrap-program (string-append out "/bin/" script)
666 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
667 '("create_annotations_files.bash"
668 "create_metaplots.bash"
669 "Ribotaper_ORF_find.sh"
673 `(("bedtools" ,bedtools-2.18)
674 ("samtools" ,samtools-0.1)
675 ("r-minimal" ,r-minimal)
676 ("r-foreach" ,r-foreach)
677 ("r-xnomial" ,r-xnomial)
679 ("r-multitaper" ,r-multitaper)
680 ("r-seqinr" ,r-seqinr)))
681 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
682 (synopsis "Define translated ORFs using ribosome profiling data")
684 "Ribotaper is a method for defining translated @dfn{open reading
685 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
686 provides the Ribotaper pipeline.")
687 (license license:gpl3+)))
689 (define-public ribodiff
697 (url "https://github.com/ratschlab/RiboDiff.git")
698 (commit (string-append "v" version))))
699 (file-name (git-file-name name version))
702 "0x75nlp7qnmm64jasbi6l21f2cy99r2cjyl6b4hr8zf2bq22drnz"))))
703 (build-system python-build-system)
707 (modify-phases %standard-phases
708 ;; Generate an installable executable script wrapper.
709 (add-after 'unpack 'patch-setup.py
711 (substitute* "setup.py"
712 (("^(.*)packages=.*" line prefix)
713 (string-append line "\n"
714 prefix "scripts=['scripts/TE.py'],\n")))
717 `(("python-numpy" ,python2-numpy)
718 ("python-matplotlib" ,python2-matplotlib)
719 ("python-scipy" ,python2-scipy)
720 ("python-statsmodels" ,python2-statsmodels)))
722 `(("python-mock" ,python2-mock)
723 ("python-nose" ,python2-nose)))
724 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
725 (synopsis "Detect translation efficiency changes from ribosome footprints")
726 (description "RiboDiff is a statistical tool that detects the protein
727 translational efficiency change from Ribo-Seq (ribosome footprinting) and
728 RNA-Seq data. It uses a generalized linear model to detect genes showing
729 difference in translational profile taking mRNA abundance into account. It
730 facilitates us to decipher the translational regulation that behave
731 independently with transcriptional regulation.")
732 (license license:gpl3+)))
734 (define-public bioawk
741 (url "https://github.com/lh3/bioawk.git")
742 (commit (string-append "v" version))))
743 (file-name (git-file-name name version))
746 "1pxc3zdnirxbf9a0az698hd8xdik7qkhypm7v6hn922x8y9qmspm"))))
747 (build-system gnu-build-system)
753 `(#:tests? #f ; There are no tests to run.
754 ;; Bison must generate files, before other targets can build.
757 (modify-phases %standard-phases
758 (delete 'configure) ; There is no configure phase.
760 (lambda* (#:key outputs #:allow-other-keys)
761 (let* ((out (assoc-ref outputs "out"))
762 (bin (string-append out "/bin"))
763 (man (string-append out "/share/man/man1")))
765 (copy-file "awk.1" (string-append man "/bioawk.1"))
766 (install-file "bioawk" bin))
768 (home-page "https://github.com/lh3/bioawk")
769 (synopsis "AWK with bioinformatics extensions")
770 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
771 support of several common biological data formats, including optionally gzip'ed
772 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
773 also adds a few built-in functions and a command line option to use TAB as the
774 input/output delimiter. When the new functionality is not used, bioawk is
775 intended to behave exactly the same as the original BWK awk.")
776 (license license:x11)))
778 (define-public python-pybedtools
780 (name "python-pybedtools")
784 (uri (pypi-uri "pybedtools" version))
787 "1xl454ijvd4dzfvqgfahad49b49j7qy710fq9xh1rvk42z6x5ssf"))))
788 (build-system python-build-system)
790 `(#:modules ((ice-9 ftw)
794 (guix build python-build-system))
795 ;; See https://github.com/daler/pybedtools/issues/192
797 (modify-phases %standard-phases
798 ;; See https://github.com/daler/pybedtools/issues/261
799 (add-after 'unpack 'disable-broken-tests
801 ;; This test (pybedtools.test.test_scripts.test_venn_mpl) needs a
802 ;; graphical environment.
803 (substitute* "pybedtools/test/test_scripts.py"
804 (("def test_venn_mpl")
805 "def _do_not_test_venn_mpl"))
806 (substitute* "pybedtools/test/test_helpers.py"
807 ;; Requires internet access.
808 (("def test_chromsizes")
809 "def _do_not_test_chromsizes")
810 ;; Broken as a result of the workaround used in the check phase
811 ;; (see: https://github.com/daler/pybedtools/issues/192).
812 (("def test_getting_example_beds")
813 "def _do_not_test_getting_example_beds"))
815 ;; TODO: Remove phase after it's part of PYTHON-BUILD-SYSTEM.
817 ;; Force the Cythonization of C++ files to guard against compilation
819 (add-after 'unpack 'remove-cython-generated-files
821 (let ((cython-sources (map (cut string-drop-right <> 4)
822 (find-files "." "\\.pyx$")))
823 (c/c++-files (find-files "." "\\.(c|cpp|cxx)$")))
824 (define (strip-extension filename)
825 (string-take filename (string-index-right filename #\.)))
826 (define (cythonized? c/c++-file)
827 (member (strip-extension c/c++-file) cython-sources))
828 (for-each delete-file (filter cythonized? c/c++-files))
830 (add-after 'remove-cython-generated-files 'generate-cython-extensions
832 (invoke "python" "setup.py" "cythonize")))
835 (let* ((cwd (getcwd))
836 (build-root-directory (string-append cwd "/build/"))
837 (build (string-append
839 (find (cut string-prefix? "lib" <>)
840 (scandir (string-append
841 build-root-directory)))))
842 (scripts (string-append
844 (find (cut string-prefix? "scripts" <>)
845 (scandir build-root-directory)))))
847 (string-append build ":" (getenv "PYTHONPATH")))
848 ;; Executable scripts such as 'intron_exon_reads.py' must be
849 ;; available in the PATH.
851 (string-append scripts ":" (getenv "PATH"))))
852 ;; The tests need to be run from elsewhere...
853 (mkdir-p "/tmp/test")
854 (copy-recursively "pybedtools/test" "/tmp/test")
855 (with-directory-excursion "/tmp/test"
856 (invoke "pytest")))))))
858 `(("bedtools" ,bedtools)
859 ("samtools" ,samtools)
860 ("python-matplotlib" ,python-matplotlib)
861 ("python-pysam" ,python-pysam)
862 ("python-pyyaml" ,python-pyyaml)))
864 `(("python-numpy" ,python-numpy)
865 ("python-pandas" ,python-pandas)
866 ("python-cython" ,python-cython)
867 ("kentutils" ,kentutils) ; for bedGraphToBigWig
868 ("python-six" ,python-six)
869 ;; For the test suite.
870 ("python-pytest" ,python-pytest)
871 ("python-psutil" ,python-psutil)))
872 (home-page "https://pythonhosted.org/pybedtools/")
873 (synopsis "Python wrapper for BEDtools programs")
875 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
876 which are widely used for genomic interval manipulation or \"genome algebra\".
877 pybedtools extends BEDTools by offering feature-level manipulations from with
879 (license license:gpl2+)))
881 (define-public python2-pybedtools
882 (package-with-python2 python-pybedtools))
884 (define-public python-biom-format
886 (name "python-biom-format")
891 ;; Use GitHub as source because PyPI distribution does not contain
892 ;; test data: https://github.com/biocore/biom-format/issues/693
894 (url "https://github.com/biocore/biom-format.git")
896 (file-name (git-file-name name version))
899 "1rna16lyk5aqhnv0dp77wwaplias93f1vw28ad3jmyw6hwkai05v"))))
900 (build-system python-build-system)
903 (modify-phases %standard-phases
904 (add-after 'unpack 'use-cython
905 (lambda _ (setenv "USE_CYTHON" "1") #t))
906 (add-after 'unpack 'disable-broken-test
908 (substitute* "biom/tests/test_cli/test_validate_table.py"
909 (("^(.+)def test_invalid_hdf5" m indent)
910 (string-append indent
911 "@npt.dec.skipif(True, msg='Guix')\n"
914 (add-before 'reset-gzip-timestamps 'make-files-writable
915 (lambda* (#:key outputs #:allow-other-keys)
916 (let ((out (assoc-ref outputs "out")))
917 (for-each (lambda (file) (chmod file #o644))
918 (find-files out "\\.gz"))
921 `(("python-numpy" ,python-numpy)
922 ("python-scipy" ,python-scipy)
923 ("python-flake8" ,python-flake8)
924 ("python-future" ,python-future)
925 ("python-click" ,python-click)
926 ("python-h5py" ,python-h5py)
927 ("python-pandas" ,python-pandas)))
929 `(("python-cython" ,python-cython)
930 ("python-pytest" ,python-pytest)
931 ("python-pytest-cov" ,python-pytest-cov)
932 ("python-nose" ,python-nose)))
933 (home-page "http://www.biom-format.org")
934 (synopsis "Biological Observation Matrix (BIOM) format utilities")
936 "The BIOM file format is designed to be a general-use format for
937 representing counts of observations e.g. operational taxonomic units, KEGG
938 orthology groups or lipid types, in one or more biological samples
939 e.g. microbiome samples, genomes, metagenomes.")
940 (license license:bsd-3)
941 (properties `((python2-variant . ,(delay python2-biom-format))))))
943 (define-public python2-biom-format
944 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
948 (substitute-keyword-arguments (package-arguments base)
950 `(modify-phases ,phases
951 ;; Do not require the unmaintained pyqi library.
952 (add-after 'unpack 'remove-pyqi
954 (substitute* "setup.py"
955 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
958 (define-public bioperl-minimal
959 (let* ((inputs `(("perl-module-build" ,perl-module-build)
960 ("perl-data-stag" ,perl-data-stag)
961 ("perl-libwww" ,perl-libwww)
962 ("perl-uri" ,perl-uri)))
964 (map (compose package-name cadr)
967 (map (compose package-transitive-target-inputs cadr) inputs))))))
969 (name "bioperl-minimal")
974 (uri (string-append "https://github.com/bioperl/bioperl-live/"
976 (string-map (lambda (c)
982 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
983 (build-system perl-build-system)
986 (modify-phases %standard-phases
988 'install 'wrap-programs
989 (lambda* (#:key outputs #:allow-other-keys)
990 ;; Make sure all executables in "bin" find the required Perl
991 ;; modules at runtime. As the PERL5LIB variable contains also
992 ;; the paths of native inputs, we pick the transitive target
993 ;; inputs from %build-inputs.
994 (let* ((out (assoc-ref outputs "out"))
995 (bin (string-append out "/bin/"))
997 (cons (string-append out "/lib/perl5/site_perl")
999 (assoc-ref %build-inputs name))
1000 ',transitive-inputs))
1002 (for-each (lambda (file)
1004 `("PERL5LIB" ":" prefix (,path))))
1005 (find-files bin "\\.pl$"))
1009 `(("perl-test-most" ,perl-test-most)))
1010 (home-page "https://metacpan.org/release/BioPerl")
1011 (synopsis "Bioinformatics toolkit")
1013 "BioPerl is the product of a community effort to produce Perl code which
1014 is useful in biology. Examples include Sequence objects, Alignment objects
1015 and database searching objects. These objects not only do what they are
1016 advertised to do in the documentation, but they also interact - Alignment
1017 objects are made from the Sequence objects, Sequence objects have access to
1018 Annotation and SeqFeature objects and databases, Blast objects can be
1019 converted to Alignment objects, and so on. This means that the objects
1020 provide a coordinated and extensible framework to do computational biology.")
1021 (license license:perl-license))))
1023 (define-public python-biopython
1025 (name "python-biopython")
1029 ;; use PyPi rather than biopython.org to ease updating
1030 (uri (pypi-uri "biopython" version))
1033 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
1034 (build-system python-build-system)
1037 (modify-phases %standard-phases
1038 (add-before 'check 'set-home
1039 ;; Some tests require a home directory to be set.
1040 (lambda _ (setenv "HOME" "/tmp") #t)))))
1042 `(("python-numpy" ,python-numpy)))
1043 (home-page "http://biopython.org/")
1044 (synopsis "Tools for biological computation in Python")
1046 "Biopython is a set of tools for biological computation including parsers
1047 for bioinformatics files into Python data structures; interfaces to common
1048 bioinformatics programs; a standard sequence class and tools for performing
1049 common operations on them; code to perform data classification; code for
1050 dealing with alignments; code making it easy to split up parallelizable tasks
1051 into separate processes; and more.")
1052 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
1054 (define-public python2-biopython
1055 (package-with-python2 python-biopython))
1057 (define-public python-fastalite
1059 (name "python-fastalite")
1064 (uri (pypi-uri "fastalite" version))
1067 "1qli6pxp77i9xn2wfciq2zaxhl82bdxb33cpzqzj1z25yd036wqj"))))
1068 (build-system python-build-system)
1070 `(#:tests? #f)) ; Test data is not distributed.
1071 (home-page "https://github.com/nhoffman/fastalite")
1072 (synopsis "Simplest possible FASTA parser")
1073 (description "This library implements a FASTA and a FASTQ parser without
1074 relying on a complex dependency tree.")
1075 (license license:expat)))
1077 (define-public python2-fastalite
1078 (package-with-python2 python-fastalite))
1080 (define-public bpp-core
1081 ;; The last release was in 2014 and the recommended way to install from source
1082 ;; is to clone the git repository, so we do this.
1083 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1084 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
1087 (version (string-append "2.2.0-1." (string-take commit 7)))
1091 (url "http://biopp.univ-montp2.fr/git/bpp-core")
1093 (file-name (string-append name "-" version "-checkout"))
1096 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
1097 (build-system cmake-build-system)
1099 `(#:parallel-build? #f))
1101 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
1102 ; compile all of the bpp packages with GCC 5.
1103 (home-page "http://biopp.univ-montp2.fr")
1104 (synopsis "C++ libraries for Bioinformatics")
1106 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1107 analysis, phylogenetics, molecular evolution and population genetics. It is
1108 Object Oriented and is designed to be both easy to use and computer efficient.
1109 Bio++ intends to help programmers to write computer expensive programs, by
1110 providing them a set of re-usable tools.")
1111 (license license:cecill-c))))
1113 (define-public bpp-phyl
1114 ;; The last release was in 2014 and the recommended way to install from source
1115 ;; is to clone the git repository, so we do this.
1116 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1117 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
1120 (version (string-append "2.2.0-1." (string-take commit 7)))
1124 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
1126 (file-name (string-append name "-" version "-checkout"))
1129 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
1130 (build-system cmake-build-system)
1132 `(#:parallel-build? #f
1133 ;; If out-of-source, test data is not copied into the build directory
1134 ;; so the tests fail.
1135 #:out-of-source? #f))
1137 `(("bpp-core" ,bpp-core)
1138 ("bpp-seq" ,bpp-seq)
1139 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
1142 (home-page "http://biopp.univ-montp2.fr")
1143 (synopsis "Bio++ phylogenetic Library")
1145 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1146 analysis, phylogenetics, molecular evolution and population genetics. This
1147 library provides phylogenetics-related modules.")
1148 (license license:cecill-c))))
1150 (define-public bpp-popgen
1151 ;; The last release was in 2014 and the recommended way to install from source
1152 ;; is to clone the git repository, so we do this.
1153 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1154 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
1157 (version (string-append "2.2.0-1." (string-take commit 7)))
1161 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
1163 (file-name (string-append name "-" version "-checkout"))
1166 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
1167 (build-system cmake-build-system)
1169 `(#:parallel-build? #f
1170 #:tests? #f)) ; There are no tests.
1172 `(("bpp-core" ,bpp-core)
1173 ("bpp-seq" ,bpp-seq)
1175 (home-page "http://biopp.univ-montp2.fr")
1176 (synopsis "Bio++ population genetics library")
1178 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1179 analysis, phylogenetics, molecular evolution and population genetics. This
1180 library provides population genetics-related modules.")
1181 (license license:cecill-c))))
1183 (define-public bpp-seq
1184 ;; The last release was in 2014 and the recommended way to install from source
1185 ;; is to clone the git repository, so we do this.
1186 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1187 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
1190 (version (string-append "2.2.0-1." (string-take commit 7)))
1194 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
1196 (file-name (string-append name "-" version "-checkout"))
1199 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
1200 (build-system cmake-build-system)
1202 `(#:parallel-build? #f
1203 ;; If out-of-source, test data is not copied into the build directory
1204 ;; so the tests fail.
1205 #:out-of-source? #f))
1207 `(("bpp-core" ,bpp-core)
1208 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
1209 (home-page "http://biopp.univ-montp2.fr")
1210 (synopsis "Bio++ sequence library")
1212 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1213 analysis, phylogenetics, molecular evolution and population genetics. This
1214 library provides sequence-related modules.")
1215 (license license:cecill-c))))
1217 (define-public bppsuite
1218 ;; The last release was in 2014 and the recommended way to install from source
1219 ;; is to clone the git repository, so we do this.
1220 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1221 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
1224 (version (string-append "2.2.0-1." (string-take commit 7)))
1228 (url "http://biopp.univ-montp2.fr/git/bppsuite")
1230 (file-name (string-append name "-" version "-checkout"))
1233 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
1234 (build-system cmake-build-system)
1236 `(#:parallel-build? #f
1237 #:tests? #f)) ; There are no tests.
1241 ("texinfo" ,texinfo)))
1243 `(("bpp-core" ,bpp-core)
1244 ("bpp-seq" ,bpp-seq)
1245 ("bpp-phyl" ,bpp-phyl)
1246 ("bpp-phyl" ,bpp-popgen)
1248 (home-page "http://biopp.univ-montp2.fr")
1249 (synopsis "Bioinformatics tools written with the Bio++ libraries")
1251 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1252 analysis, phylogenetics, molecular evolution and population genetics. This
1253 package provides command line tools using the Bio++ library.")
1254 (license license:cecill-c))))
1256 (define-public blast+
1263 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
1264 version "/ncbi-blast-" version "+-src.tar.gz"))
1267 "1jlq0afxxgczpp35k6mxh8mn4jzq7vqcnaixk166sfj10wq8v9qh"))
1268 (modules '((guix build utils)))
1271 ;; Remove bundled bzip2, zlib and pcre.
1272 (delete-file-recursively "c++/src/util/compress/bzip2")
1273 (delete-file-recursively "c++/src/util/compress/zlib")
1274 (delete-file-recursively "c++/src/util/regexp")
1275 (substitute* "c++/src/util/compress/Makefile.in"
1276 (("bzip2 zlib api") "api"))
1277 ;; Remove useless msbuild directory
1278 (delete-file-recursively
1279 "c++/src/build-system/project_tree_builder/msbuild")
1281 (build-system gnu-build-system)
1283 `(;; There are two(!) tests for this massive library, and both fail with
1284 ;; "unparsable timing stats".
1285 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
1286 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
1289 #:parallel-build? #f ; not supported
1291 (modify-phases %standard-phases
1292 (add-before 'configure 'set-HOME
1293 ;; $HOME needs to be set at some point during the configure phase
1294 (lambda _ (setenv "HOME" "/tmp") #t))
1295 (add-after 'unpack 'enter-dir
1296 (lambda _ (chdir "c++") #t))
1297 (add-after 'enter-dir 'fix-build-system
1299 (define (which* cmd)
1300 (cond ((string=? cmd "date")
1301 ;; make call to "date" deterministic
1306 (format (current-error-port)
1307 "WARNING: Unable to find absolute path for ~s~%"
1311 ;; Rewrite hardcoded paths to various tools
1312 (substitute* (append '("src/build-system/configure.ac"
1313 "src/build-system/configure"
1314 "src/build-system/helpers/run_with_lock.c"
1315 "scripts/common/impl/if_diff.sh"
1316 "scripts/common/impl/run_with_lock.sh"
1317 "src/build-system/Makefile.configurables.real"
1318 "src/build-system/Makefile.in.top"
1319 "src/build-system/Makefile.meta.gmake=no"
1320 "src/build-system/Makefile.meta.in"
1321 "src/build-system/Makefile.meta_l"
1322 "src/build-system/Makefile.meta_p"
1323 "src/build-system/Makefile.meta_r"
1324 "src/build-system/Makefile.mk.in"
1325 "src/build-system/Makefile.requirements"
1326 "src/build-system/Makefile.rules_with_autodep.in")
1327 (find-files "scripts/common/check" "\\.sh$"))
1328 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1329 (or (which* cmd) all)))
1331 (substitute* (find-files "src/build-system" "^config.*")
1332 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1335 ;; rewrite "/var/tmp" in check script
1336 (substitute* "scripts/common/check/check_make_unix.sh"
1337 (("/var/tmp") "/tmp"))
1339 ;; do not reset PATH
1340 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1342 (("action=/bin/") "action=")
1343 (("export PATH") ":"))
1346 (lambda* (#:key inputs outputs #:allow-other-keys)
1347 (let ((out (assoc-ref outputs "out"))
1348 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1349 (include (string-append (assoc-ref outputs "include")
1350 "/include/ncbi-tools++")))
1351 ;; The 'configure' script doesn't recognize things like
1352 ;; '--enable-fast-install'.
1353 (invoke "./configure.orig"
1354 (string-append "--with-build-root=" (getcwd) "/build")
1355 (string-append "--prefix=" out)
1356 (string-append "--libdir=" lib)
1357 (string-append "--includedir=" include)
1358 (string-append "--with-bz2="
1359 (assoc-ref inputs "bzip2"))
1360 (string-append "--with-z="
1361 (assoc-ref inputs "zlib"))
1362 (string-append "--with-pcre="
1363 (assoc-ref inputs "pcre"))
1364 ;; Each library is built twice by default, once
1365 ;; with "-static" in its name, and again
1370 (outputs '("out" ; 21 MB
1379 ("python" ,python-wrapper)))
1382 (home-page "http://blast.ncbi.nlm.nih.gov")
1383 (synopsis "Basic local alignment search tool")
1385 "BLAST is a popular method of performing a DNA or protein sequence
1386 similarity search, using heuristics to produce results quickly. It also
1387 calculates an “expect value” that estimates how many matches would have
1388 occurred at a given score by chance, which can aid a user in judging how much
1389 confidence to have in an alignment.")
1390 ;; Most of the sources are in the public domain, with the following
1393 ;; * ./c++/include/util/bitset/
1394 ;; * ./c++/src/html/ncbi_menu*.js
1396 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1398 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1400 ;; * ./c++/src/corelib/teamcity_*
1401 (license (list license:public-domain
1407 (define-public bless
1413 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1417 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1418 (modules '((guix build utils)))
1421 ;; Remove bundled boost, pigz, zlib, and .git directory
1422 ;; FIXME: also remove bundled sources for murmurhash3 and
1423 ;; kmc once packaged.
1424 (delete-file-recursively "boost")
1425 (delete-file-recursively "pigz")
1426 (delete-file-recursively "google-sparsehash")
1427 (delete-file-recursively "zlib")
1428 (delete-file-recursively ".git")
1430 (build-system gnu-build-system)
1432 '(#:tests? #f ;no "check" target
1434 (list (string-append "ZLIB="
1435 (assoc-ref %build-inputs "zlib:static")
1437 (string-append "LDFLAGS="
1438 (string-join '("-lboost_filesystem"
1445 (modify-phases %standard-phases
1446 (add-after 'unpack 'do-not-build-bundled-pigz
1447 (lambda* (#:key inputs outputs #:allow-other-keys)
1448 (substitute* "Makefile"
1449 (("cd pigz/pigz-2.3.3; make") ""))
1451 (add-after 'unpack 'patch-paths-to-executables
1452 (lambda* (#:key inputs outputs #:allow-other-keys)
1453 (substitute* "parse_args.cpp"
1454 (("kmc_binary = .*")
1455 (string-append "kmc_binary = \""
1456 (assoc-ref outputs "out")
1458 (("pigz_binary = .*")
1459 (string-append "pigz_binary = \""
1460 (assoc-ref inputs "pigz")
1464 (lambda* (#:key outputs #:allow-other-keys)
1465 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1466 (for-each (lambda (file)
1467 (install-file file bin))
1468 '("bless" "kmc/bin/kmc"))
1470 (delete 'configure))))
1474 `(("openmpi" ,openmpi)
1476 ("sparsehash" ,sparsehash)
1478 ("zlib:static" ,zlib "static")
1480 (supported-systems '("x86_64-linux"))
1481 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1482 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1484 "@dfn{Bloom-filter-based error correction solution for high-throughput
1485 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1486 correction tool for genomic reads produced by @dfn{Next-generation
1487 sequencing} (NGS). BLESS produces accurate correction results with much less
1488 memory compared with previous solutions and is also able to tolerate a higher
1489 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1490 errors at the end of reads.")
1491 (license license:gpl3+)))
1493 (define-public bowtie
1500 (url "https://github.com/BenLangmead/bowtie2.git")
1501 (commit (string-append "v" version))))
1502 (file-name (git-file-name name version))
1505 "1zl3cf327y2p7p03cavymbh7b00djc7lncfaqih33n96iy9q8ibp"))
1506 (modules '((guix build utils)))
1509 (substitute* "Makefile"
1510 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1511 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1512 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
1514 (build-system gnu-build-system)
1519 (string-append "prefix=" (assoc-ref %outputs "out")))
1521 (modify-phases %standard-phases
1526 "scripts/test/simple_tests.pl"
1527 "--bowtie2=./bowtie2"
1528 "--bowtie2-build=./bowtie2-build")
1533 ("python" ,python-wrapper)))
1536 ("perl-clone" ,perl-clone)
1537 ("perl-test-deep" ,perl-test-deep)
1538 ("perl-test-simple" ,perl-test-simple)))
1539 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1540 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1542 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1543 reads to long reference sequences. It is particularly good at aligning reads
1544 of about 50 up to 100s or 1,000s of characters, and particularly good at
1545 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1546 genome with an FM Index to keep its memory footprint small: for the human
1547 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1548 gapped, local, and paired-end alignment modes.")
1549 (supported-systems '("x86_64-linux"))
1550 (license license:gpl3+)))
1552 (define-public bowtie1
1558 (uri (string-append "mirror://sourceforge/bowtie-bio/bowtie/"
1559 version "/bowtie-" version "-src.zip"))
1562 "1jl2cj9bz8lwz8dwnxbycn8yp8g4kky62fkcxifyf1ri0y6n2vc0"))
1563 (modules '((guix build utils)))
1565 '(substitute* "Makefile"
1566 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1567 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1568 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1569 (build-system gnu-build-system)
1571 '(#:tests? #f ; no "check" target
1574 (string-append "prefix=" (assoc-ref %outputs "out")))
1576 (modify-phases %standard-phases
1577 (delete 'configure))))
1581 (supported-systems '("x86_64-linux"))
1582 (home-page "http://bowtie-bio.sourceforge.net/index.shtml")
1583 (synopsis "Fast aligner for short nucleotide sequence reads")
1585 "Bowtie is a fast, memory-efficient short read aligner. It aligns short
1586 DNA sequences (reads) to the human genome at a rate of over 25 million 35-bp
1587 reads per hour. Bowtie indexes the genome with a Burrows-Wheeler index to
1588 keep its memory footprint small: typically about 2.2 GB for the human
1589 genome (2.9 GB for paired-end).")
1590 (license license:artistic2.0)))
1592 (define-public tophat
1599 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1603 "19add02kv2xhd6ihd779dr7x35ggym3jqr0m5c4315i1yfb0p11p"))
1604 (modules '((guix build utils)))
1607 ;; Remove bundled SeqAn and samtools
1608 (delete-file-recursively "src/SeqAn-1.4.2")
1609 (delete-file-recursively "src/samtools-0.1.18")
1611 (build-system gnu-build-system)
1613 '(#:parallel-build? #f ; not supported
1615 (modify-phases %standard-phases
1616 (add-after 'unpack 'use-system-samtools
1617 (lambda* (#:key inputs #:allow-other-keys)
1618 (substitute* "src/Makefile.in"
1619 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1620 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1621 (("SAMPROG = samtools_0\\.1\\.18") "")
1622 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1623 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1624 (substitute* '("src/common.cpp"
1626 (("samtools_0.1.18") (which "samtools")))
1627 (substitute* '("src/common.h"
1628 "src/bam2fastx.cpp")
1629 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1630 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1631 (substitute* '("src/bwt_map.h"
1633 "src/align_status.h")
1634 (("#include <bam.h>") "#include <samtools/bam.h>")
1635 (("#include <sam.h>") "#include <samtools/sam.h>"))
1640 ("samtools" ,samtools-0.1)
1641 ("ncurses" ,ncurses)
1642 ("python" ,python-2)
1645 ("seqan" ,seqan-1)))
1646 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1647 (synopsis "Spliced read mapper for RNA-Seq data")
1649 "TopHat is a fast splice junction mapper for nucleotide sequence
1650 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1651 mammalian-sized genomes using the ultra high-throughput short read
1652 aligner Bowtie, and then analyzes the mapping results to identify
1653 splice junctions between exons.")
1654 ;; TopHat is released under the Boost Software License, Version 1.0
1655 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1656 (license license:boost1.0)))
1665 "https://github.com/lh3/bwa/releases/download/v"
1666 version "/bwa-" version ".tar.bz2"))
1669 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1670 (build-system gnu-build-system)
1672 '(#:tests? #f ;no "check" target
1674 (modify-phases %standard-phases
1676 (lambda* (#:key outputs #:allow-other-keys)
1677 (let ((bin (string-append
1678 (assoc-ref outputs "out") "/bin"))
1680 (assoc-ref outputs "out") "/share/doc/bwa"))
1682 (assoc-ref outputs "out") "/share/man/man1")))
1683 (install-file "bwa" bin)
1684 (install-file "README.md" doc)
1685 (install-file "bwa.1" man))
1687 ;; no "configure" script
1688 (delete 'configure))))
1689 (inputs `(("zlib" ,zlib)))
1690 ;; Non-portable SSE instructions are used so building fails on platforms
1691 ;; other than x86_64.
1692 (supported-systems '("x86_64-linux"))
1693 (home-page "http://bio-bwa.sourceforge.net/")
1694 (synopsis "Burrows-Wheeler sequence aligner")
1696 "BWA is a software package for mapping low-divergent sequences against a
1697 large reference genome, such as the human genome. It consists of three
1698 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1699 designed for Illumina sequence reads up to 100bp, while the rest two for
1700 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1701 features such as long-read support and split alignment, but BWA-MEM, which is
1702 the latest, is generally recommended for high-quality queries as it is faster
1703 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1704 70-100bp Illumina reads.")
1705 (license license:gpl3+)))
1707 (define-public bwa-pssm
1708 (package (inherit bwa)
1714 (url "https://github.com/pkerpedjiev/bwa-pssm.git")
1716 (file-name (git-file-name name version))
1719 "076c4q0cdqz8jgylb067y9zmvxglppnzi3qiscn0xiypgc6lgb5r"))))
1720 (build-system gnu-build-system)
1725 (home-page "http://bwa-pssm.binf.ku.dk/")
1726 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1728 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1729 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1730 existing aligners it is fast and sensitive. Unlike most other aligners,
1731 however, it is also adaptible in the sense that one can direct the alignment
1732 based on known biases within the data set. It is coded as a modification of
1733 the original BWA alignment program and shares the genome index structure as
1734 well as many of the command line options.")
1735 (license license:gpl3+)))
1737 (define-public bwa-meth
1744 (url "https://github.com/brentp/bwa-meth.git")
1745 (commit (string-append "v" version))))
1746 (file-name (git-file-name name version))
1749 "17j31i7zws5j7mhsq9x3qgkxly6mlmrgwhfq0qbflgxrmx04yaiz"))))
1750 (build-system python-build-system)
1753 (modify-phases %standard-phases
1754 (add-after 'unpack 'keep-references-to-bwa
1755 (lambda* (#:key inputs #:allow-other-keys)
1756 (substitute* "bwameth.py"
1758 (string-append (which "bwa") " mem"))
1759 ;; There's an ill-advised check for "samtools" on PATH.
1765 `(("python-toolshed" ,python-toolshed)))
1766 (home-page "https://github.com/brentp/bwa-meth")
1767 (synopsis "Fast and accurante alignment of BS-Seq reads")
1769 "BWA-Meth works for single-end reads and for paired-end reads from the
1770 directional protocol (most common). It uses the method employed by
1771 methylcoder and Bismark of in silico conversion of all C's to T's in both
1772 reference and reads. It recovers the original read (needed to tabulate
1773 methylation) by attaching it as a comment which BWA appends as a tag to the
1774 read. It performs favorably to existing aligners gauged by number of on and
1775 off-target reads for a capture method that targets CpG-rich region.")
1776 (license license:expat)))
1778 (define-public python-bx-python
1780 (name "python-bx-python")
1784 (uri (pypi-uri "bx-python" version))
1787 "11kksg2rbzihpmcid823xvg42xi88m7sz58rzk29abybkxy0rszs"))))
1788 (build-system python-build-system)
1789 ;; Tests fail because test data are not included
1790 (arguments '(#:tests? #f))
1792 `(("python-numpy" ,python-numpy)
1793 ("python-six" ,python-six)))
1797 `(("python-lzo" ,python-lzo)
1798 ("python-nose" ,python-nose)
1799 ("python-cython" ,python-cython)))
1800 (home-page "https://github.com/bxlab/bx-python")
1801 (synopsis "Tools for manipulating biological data")
1803 "bx-python provides tools for manipulating biological data, particularly
1804 multiple sequence alignments.")
1805 (license license:expat)))
1807 (define-public python2-bx-python
1808 (package-with-python2 python-bx-python))
1810 (define-public python-pysam
1812 (name "python-pysam")
1816 ;; Test data is missing on PyPi.
1818 (url "https://github.com/pysam-developers/pysam.git")
1819 (commit (string-append "v" version))))
1820 (file-name (git-file-name name version))
1823 "1vj367w6xbn9bpmksm162l1aipf7cj97h1q83y7jcpm33ihwpf7x"))
1824 (modules '((guix build utils)))
1826 ;; Drop bundled htslib. TODO: Also remove samtools
1828 (delete-file-recursively "htslib")
1830 (build-system python-build-system)
1832 `(#:modules ((ice-9 ftw)
1834 (guix build python-build-system)
1837 (modify-phases %standard-phases
1838 (add-before 'build 'set-flags
1839 (lambda* (#:key inputs #:allow-other-keys)
1840 (setenv "HTSLIB_MODE" "external")
1841 (setenv "HTSLIB_LIBRARY_DIR"
1842 (string-append (assoc-ref inputs "htslib") "/lib"))
1843 (setenv "HTSLIB_INCLUDE_DIR"
1844 (string-append (assoc-ref inputs "htslib") "/include"))
1845 (setenv "LDFLAGS" "-lncurses")
1846 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1849 (lambda* (#:key inputs outputs #:allow-other-keys)
1850 ;; This file contains tests that require a connection to the
1852 (delete-file "tests/tabix_test.py")
1853 ;; FIXME: This test fails
1854 (delete-file "tests/AlignmentFile_test.py")
1855 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1856 (setenv "PYTHONPATH"
1858 (getenv "PYTHONPATH")
1859 ":" (getcwd) "/build/"
1860 (car (scandir "build"
1861 (negate (cut string-prefix? "." <>))))))
1862 ;; Step out of source dir so python does not import from CWD.
1863 (with-directory-excursion "tests"
1864 (setenv "HOME" "/tmp")
1865 (invoke "make" "-C" "pysam_data")
1866 (invoke "make" "-C" "cbcf_data")
1867 ;; Running nosetests without explicitly asking for a single
1868 ;; process leads to a crash. Running with multiple processes
1869 ;; fails because the tests are not designed to run in parallel.
1871 ;; FIXME: tests keep timing out on some systems.
1872 (invoke "nosetests" "-v" "--processes" "1")))))))
1874 `(("htslib" ,htslib))) ; Included from installed header files.
1876 `(("ncurses" ,ncurses)
1880 `(("python-cython" ,python-cython)
1881 ;; Dependencies below are are for tests only.
1882 ("samtools" ,samtools)
1883 ("bcftools" ,bcftools)
1884 ("python-nose" ,python-nose)))
1885 (home-page "https://github.com/pysam-developers/pysam")
1886 (synopsis "Python bindings to the SAMtools C API")
1888 "Pysam is a Python module for reading and manipulating files in the
1889 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1890 also includes an interface for tabix.")
1891 (license license:expat)))
1893 (define-public python2-pysam
1894 (package-with-python2 python-pysam))
1896 (define-public python-twobitreader
1898 (name "python-twobitreader")
1903 (url "https://github.com/benjschiller/twobitreader")
1905 (file-name (git-file-name name version))
1908 "1qbxvv1h58cismbk1anpjrkpghsaiy64a11ir3lhy6qch6xf8n62"))))
1909 (build-system python-build-system)
1910 ;; Tests are not included
1911 (arguments '(#:tests? #f))
1913 `(("python-sphinx" ,python-sphinx)))
1914 (home-page "https://github.com/benjschiller/twobitreader")
1915 (synopsis "Python library for reading .2bit files")
1917 "twobitreader is a Python library for reading .2bit files as used by the
1918 UCSC genome browser.")
1919 (license license:artistic2.0)))
1921 (define-public python2-twobitreader
1922 (package-with-python2 python-twobitreader))
1924 (define-public python-plastid
1926 (name "python-plastid")
1930 (uri (pypi-uri "plastid" version))
1933 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1934 (build-system python-build-system)
1936 ;; Some test files are not included.
1939 `(("python-numpy" ,python-numpy)
1940 ("python-scipy" ,python-scipy)
1941 ("python-pandas" ,python-pandas)
1942 ("python-pysam" ,python-pysam)
1943 ("python-matplotlib" ,python-matplotlib)
1944 ("python-biopython" ,python-biopython)
1945 ("python-twobitreader" ,python-twobitreader)
1946 ("python-termcolor" ,python-termcolor)))
1948 `(("python-cython" ,python-cython)
1949 ("python-nose" ,python-nose)))
1950 (home-page "https://github.com/joshuagryphon/plastid")
1951 (synopsis "Python library for genomic analysis")
1953 "plastid is a Python library for genomic analysis – in particular,
1954 high-throughput sequencing data – with an emphasis on simplicity.")
1955 (license license:bsd-3)))
1957 (define-public python2-plastid
1958 (package-with-python2 python-plastid))
1960 (define-public tetoolkit
1967 (url "https://github.com/mhammell-laboratory/tetoolkit.git")
1969 (file-name (git-file-name name version))
1972 "1yzi0kfpzip8zpjb82x1ik6h22yzfyjiz2dv85v6as2awwqvk807"))))
1973 (build-system python-build-system)
1975 `(#:python ,python-2 ; not guaranteed to work with Python 3
1977 (modify-phases %standard-phases
1978 (add-after 'unpack 'make-writable
1980 (for-each make-file-writable (find-files "."))
1982 (add-after 'unpack 'patch-invocations
1983 (lambda* (#:key inputs #:allow-other-keys)
1984 (substitute* '("bin/TEtranscripts"
1987 (string-append "'" (which "sort") " "))
1989 (string-append "'" (which "rm") " -f "))
1990 (("'Rscript'") (string-append "'" (which "Rscript") "'")))
1991 (substitute* "TEToolkit/IO/ReadInputs.py"
1992 (("BamToBED") (which "bamToBed")))
1993 (substitute* "TEToolkit/Normalization.py"
1995 (string-append "\"" (which "Rscript") "\"")))
1997 (add-after 'install 'wrap-program
1998 (lambda* (#:key outputs #:allow-other-keys)
1999 ;; Make sure the executables find R packages.
2000 (let ((out (assoc-ref outputs "out")))
2003 (wrap-program (string-append out "/bin/" script)
2004 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
2009 `(("coreutils" ,coreutils)
2010 ("bedtools" ,bedtools)
2011 ("python-argparse" ,python2-argparse)
2012 ("python-pysam" ,python2-pysam)
2013 ("r-minimal" ,r-minimal)
2014 ("r-deseq2" ,r-deseq2)))
2015 (home-page "https://github.com/mhammell-laboratory/tetoolkit")
2016 (synopsis "Transposable elements in differential enrichment analysis")
2018 "This is package for including transposable elements in differential
2019 enrichment analysis of sequencing datasets. TEtranscripts and TEcount take
2020 RNA-seq (and similar data) and annotates reads to both genes and transposable
2021 elements. TEtranscripts then performs differential analysis using DESeq2.
2022 Note that TEtranscripts and TEcount rely on specially curated GTF files, which
2023 are not included due to their size.")
2024 (license license:gpl3+)))
2026 (define-public cd-hit
2032 (uri (string-append "https://github.com/weizhongli/cdhit"
2033 "/releases/download/V" version
2035 "-2017-0621-source.tar.gz"))
2038 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
2039 (build-system gnu-build-system)
2041 `(#:tests? #f ; there are no tests
2043 ;; Executables are copied directly to the PREFIX.
2044 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin")
2045 ;; Support longer sequences (e.g. Pacbio sequences)
2048 (modify-phases %standard-phases
2049 ;; No "configure" script
2051 ;; Remove sources of non-determinism
2052 (add-after 'unpack 'be-timeless
2054 (substitute* "cdhit-utility.c++"
2055 ((" \\(built on \" __DATE__ \"\\)") ""))
2056 (substitute* "cdhit-common.c++"
2057 (("__DATE__") "\"0\"")
2058 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
2060 ;; The "install" target does not create the target directory.
2061 (add-before 'install 'create-target-dir
2062 (lambda* (#:key outputs #:allow-other-keys)
2063 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
2067 (home-page "http://weizhongli-lab.org/cd-hit/")
2068 (synopsis "Cluster and compare protein or nucleotide sequences")
2070 "CD-HIT is a program for clustering and comparing protein or nucleotide
2071 sequences. CD-HIT is designed to be fast and handle extremely large
2073 ;; The manual says: "It can be copied under the GNU General Public License
2074 ;; version 2 (GPLv2)."
2075 (license license:gpl2)))
2077 (define-public clipper
2084 (url "https://github.com/YeoLab/clipper.git")
2086 (file-name (git-file-name name version))
2089 "0fja1rj84wp9vpj8rxpj3n8zqzcqq454m904yp9as1w4phccirjb"))
2090 (modules '((guix build utils)))
2093 ;; remove unnecessary setup dependency
2094 (substitute* "setup.py"
2095 (("setup_requires = .*") ""))
2097 (build-system python-build-system)
2099 `(#:python ,python-2 ; only Python 2 is supported
2101 (modify-phases %standard-phases
2102 ;; This is fixed in upstream commit
2103 ;; f6c2990198f906bf97730d95695b4bd5a6d01ddb.
2104 (add-after 'unpack 'fix-typo
2106 (substitute* "clipper/src/readsToWiggle.pyx"
2110 `(("htseq" ,python2-htseq)
2111 ("python-pybedtools" ,python2-pybedtools)
2112 ("python-cython" ,python2-cython)
2113 ("python-scikit-learn" ,python2-scikit-learn)
2114 ("python-matplotlib" ,python2-matplotlib)
2115 ("python-pandas" ,python2-pandas)
2116 ("python-pysam" ,python2-pysam)
2117 ("python-numpy" ,python2-numpy)
2118 ("python-scipy" ,python2-scipy)))
2120 `(("python-mock" ,python2-mock) ; for tests
2121 ("python-nose" ,python2-nose) ; for tests
2122 ("python-pytz" ,python2-pytz))) ; for tests
2123 (home-page "https://github.com/YeoLab/clipper")
2124 (synopsis "CLIP peak enrichment recognition")
2126 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
2127 (license license:gpl2)))
2129 (define-public codingquarry
2131 (name "codingquarry")
2136 "mirror://sourceforge/codingquarry/CodingQuarry_v"
2140 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
2141 (build-system gnu-build-system)
2143 '(#:tests? #f ; no "check" target
2145 (modify-phases %standard-phases
2148 (lambda* (#:key outputs #:allow-other-keys)
2149 (let* ((out (assoc-ref outputs "out"))
2150 (bin (string-append out "/bin"))
2151 (doc (string-append out "/share/doc/codingquarry")))
2152 (install-file "INSTRUCTIONS.pdf" doc)
2153 (copy-recursively "QuarryFiles"
2154 (string-append out "/QuarryFiles"))
2155 (install-file "CodingQuarry" bin)
2156 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin))
2158 (inputs `(("openmpi" ,openmpi)))
2159 (native-search-paths
2160 (list (search-path-specification
2161 (variable "QUARRY_PATH")
2162 (files '("QuarryFiles")))))
2163 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
2164 (synopsis "Fungal gene predictor")
2165 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
2166 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
2167 (home-page "https://sourceforge.net/projects/codingquarry/")
2168 (license license:gpl3+)))
2170 (define-public couger
2177 "http://couger.oit.duke.edu/static/assets/COUGER"
2181 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
2182 (build-system gnu-build-system)
2186 (modify-phases %standard-phases
2191 (lambda* (#:key outputs #:allow-other-keys)
2192 (let* ((out (assoc-ref outputs "out"))
2193 (bin (string-append out "/bin")))
2194 (copy-recursively "src" (string-append out "/src"))
2196 ;; Add "src" directory to module lookup path.
2197 (substitute* "couger"
2199 (string-append "import sys\nsys.path.append(\""
2200 out "\")\nfrom argparse")))
2201 (install-file "couger" bin))
2204 'install 'wrap-program
2205 (lambda* (#:key inputs outputs #:allow-other-keys)
2206 ;; Make sure 'couger' runs with the correct PYTHONPATH.
2207 (let* ((out (assoc-ref outputs "out"))
2208 (path (getenv "PYTHONPATH")))
2209 (wrap-program (string-append out "/bin/couger")
2210 `("PYTHONPATH" ":" prefix (,path))))
2213 `(("python" ,python-2)
2214 ("python2-pillow" ,python2-pillow)
2215 ("python2-numpy" ,python2-numpy)
2216 ("python2-scipy" ,python2-scipy)
2217 ("python2-matplotlib" ,python2-matplotlib)))
2219 `(("r-minimal" ,r-minimal)
2221 ("randomjungle" ,randomjungle)))
2223 `(("unzip" ,unzip)))
2224 (home-page "http://couger.oit.duke.edu")
2225 (synopsis "Identify co-factors in sets of genomic regions")
2227 "COUGER can be applied to any two sets of genomic regions bound by
2228 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
2229 putative co-factors that provide specificity to each TF. The framework
2230 determines the genomic targets uniquely-bound by each TF, and identifies a
2231 small set of co-factors that best explain the in vivo binding differences
2232 between the two TFs.
2234 COUGER uses classification algorithms (support vector machines and random
2235 forests) with features that reflect the DNA binding specificities of putative
2236 co-factors. The features are generated either from high-throughput TF-DNA
2237 binding data (from protein binding microarray experiments), or from large
2238 collections of DNA motifs.")
2239 (license license:gpl3+)))
2241 (define-public clustal-omega
2243 (name "clustal-omega")
2247 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
2251 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
2252 (build-system gnu-build-system)
2254 `(("argtable" ,argtable)))
2255 (home-page "http://www.clustal.org/omega/")
2256 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
2258 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
2259 program for protein and DNA/RNA. It produces high quality MSAs and is capable
2260 of handling data-sets of hundreds of thousands of sequences in reasonable
2262 (license license:gpl2+)))
2264 (define-public crossmap
2270 (uri (pypi-uri "CrossMap" version))
2273 "1byhclrqnqpvc1rqkfh4jwj6yhn0x9y7jk47i0qcjlhk0pjkw92p"))))
2274 (build-system python-build-system)
2275 (arguments `(#:python ,python-2))
2277 `(("python-bx-python" ,python2-bx-python)
2278 ("python-numpy" ,python2-numpy)
2279 ("python-pysam" ,python2-pysam)
2282 `(("python-cython" ,python2-cython)
2283 ("python-nose" ,python2-nose)))
2284 (home-page "http://crossmap.sourceforge.net/")
2285 (synopsis "Convert genome coordinates between assemblies")
2287 "CrossMap is a program for conversion of genome coordinates or annotation
2288 files between different genome assemblies. It supports most commonly used
2289 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
2290 (license license:gpl2+)))
2292 (define-public python-dnaio
2294 (name "python-dnaio")
2299 (uri (pypi-uri "dnaio" version))
2302 "0f16m7hdlm0fz1n7y5asy0v9ghyrq17ni1p9iybq22ddzyd49r27"))))
2303 (build-system python-build-system)
2305 `(("python-cython" ,python-cython)
2306 ("python-pytest" ,python-pytest)
2307 ("python-xopen" ,python-xopen)))
2308 (home-page "https://github.com/marcelm/dnaio/")
2309 (synopsis "Read FASTA and FASTQ files efficiently")
2311 "dnaio is a Python library for fast parsing of FASTQ and also FASTA
2312 files. The code was previously part of the cutadapt tool.")
2313 (license license:expat)))
2315 (define-public cutadapt
2322 (url "https://github.com/marcelm/cutadapt.git")
2323 (commit (string-append "v" version))))
2324 (file-name (git-file-name name version))
2327 "08bbfwyc0kvcd95jf2s95xiv9s3cbsxm39ydl0qck3fw3cviwxpg"))))
2328 (build-system python-build-system)
2330 `(("python-dnaio" ,python-dnaio)
2331 ("python-xopen" ,python-xopen)))
2333 `(("python-cython" ,python-cython)
2334 ("python-pytest" ,python-pytest)))
2335 (home-page "https://cutadapt.readthedocs.io/en/stable/")
2336 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
2338 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
2339 other types of unwanted sequence from high-throughput sequencing reads.")
2340 (license license:expat)))
2342 (define-public libbigwig
2349 (url "https://github.com/dpryan79/libBigWig.git")
2351 (file-name (string-append name "-" version "-checkout"))
2354 "0h2smg24v5srdcqzrmz2g23cmlp4va465mgx8r2z571sfz8pv454"))))
2355 (build-system gnu-build-system)
2357 `(#:test-target "test"
2358 #:tests? #f ; tests require access to the web
2361 (string-append "prefix=" (assoc-ref %outputs "out")))
2363 (modify-phases %standard-phases
2364 (delete 'configure))))
2369 `(("doxygen" ,doxygen)
2371 ("python" ,python-2)))
2372 (home-page "https://github.com/dpryan79/libBigWig")
2373 (synopsis "C library for handling bigWig files")
2375 "This package provides a C library for parsing local and remote BigWig
2377 (license license:expat)))
2379 (define-public python-pybigwig
2381 (name "python-pybigwig")
2385 (uri (pypi-uri "pyBigWig" version))
2388 "00w4kfnm2c5l7wdwr2nj1z5djv8kzgf7h1zhsgv6njff1rwr26g0"))
2389 (modules '((guix build utils)))
2392 ;; Delete bundled libBigWig sources
2393 (delete-file-recursively "libBigWig")
2395 (build-system python-build-system)
2398 (modify-phases %standard-phases
2399 (add-after 'unpack 'link-with-libBigWig
2400 (lambda* (#:key inputs #:allow-other-keys)
2401 (substitute* "setup.py"
2402 (("libs=\\[") "libs=[\"BigWig\", "))
2405 `(("python-numpy" ,python-numpy)))
2407 `(("libbigwig" ,libbigwig)
2410 (home-page "https://github.com/dpryan79/pyBigWig")
2411 (synopsis "Access bigWig files in Python using libBigWig")
2413 "This package provides Python bindings to the libBigWig library for
2414 accessing bigWig files.")
2415 (license license:expat)))
2417 (define-public python2-pybigwig
2418 (package-with-python2 python-pybigwig))
2420 (define-public python-dendropy
2422 (name "python-dendropy")
2427 ;; Source from GitHub so that tests are included.
2429 (url "https://github.com/jeetsukumaran/DendroPy.git")
2430 (commit (string-append "v" version))))
2431 (file-name (git-file-name name version))
2434 "097hfyv2kaf4x92i4rjx0paw2cncxap48qivv8zxng4z7nhid0x9"))))
2435 (build-system python-build-system)
2436 (home-page "http://packages.python.org/DendroPy/")
2437 (synopsis "Library for phylogenetics and phylogenetic computing")
2439 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
2440 writing, simulation, processing and manipulation of phylogenetic
2441 trees (phylogenies) and characters.")
2442 (license license:bsd-3)))
2444 (define-public python2-dendropy
2445 (let ((base (package-with-python2 python-dendropy)))
2450 (modify-phases %standard-phases
2451 (add-after 'unpack 'remove-failing-test
2453 ;; This test fails when the full test suite is run, as documented
2454 ;; at https://github.com/jeetsukumaran/DendroPy/issues/74
2455 (substitute* "tests/test_dataio_nexml_reader_tree_list.py"
2456 (("test_collection_comments_and_annotations")
2457 "do_not_test_collection_comments_and_annotations"))
2459 ,@(package-arguments base))))))
2461 (define-public python-py2bit
2463 (name "python-py2bit")
2468 (uri (pypi-uri "py2bit" version))
2471 "1vw2nvw1yrl7ikkqsqs1pg239yr5nspvd969r1x9arms1k25a1a5"))))
2472 (build-system python-build-system)
2473 (home-page "https://github.com/dpryan79/py2bit")
2474 (synopsis "Access 2bit files using lib2bit")
2476 "This package provides Python bindings for lib2bit to access 2bit files
2478 (license license:expat)))
2480 (define-public deeptools
2487 (url "https://github.com/deeptools/deepTools.git")
2489 (file-name (git-file-name name version))
2492 "1vggnf52g6q2vifdl4cyi7s2fnfqq0ky2zrkj5zv2qfzsc3p3siw"))))
2493 (build-system python-build-system)
2496 (modify-phases %standard-phases
2497 ;; This phase fails, but it's not needed.
2498 (delete 'reset-gzip-timestamps))))
2500 `(("python-plotly" ,python-plotly)
2501 ("python-scipy" ,python-scipy)
2502 ("python-numpy" ,python-numpy)
2503 ("python-numpydoc" ,python-numpydoc)
2504 ("python-matplotlib" ,python-matplotlib)
2505 ("python-pysam" ,python-pysam)
2506 ("python-py2bit" ,python-py2bit)
2507 ("python-pybigwig" ,python-pybigwig)))
2509 `(("python-mock" ,python-mock) ;for tests
2510 ("python-nose" ,python-nose) ;for tests
2511 ("python-pytz" ,python-pytz))) ;for tests
2512 (home-page "https://github.com/deeptools/deepTools")
2513 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2515 "DeepTools addresses the challenge of handling the large amounts of data
2516 that are now routinely generated from DNA sequencing centers. To do so,
2517 deepTools contains useful modules to process the mapped reads data to create
2518 coverage files in standard bedGraph and bigWig file formats. By doing so,
2519 deepTools allows the creation of normalized coverage files or the comparison
2520 between two files (for example, treatment and control). Finally, using such
2521 normalized and standardized files, multiple visualizations can be created to
2522 identify enrichments with functional annotations of the genome.")
2523 (license license:gpl3+)))
2525 (define-public delly
2532 (url "https://github.com/dellytools/delly.git")
2533 (commit (string-append "v" version))))
2534 (file-name (git-file-name name version))
2536 (base32 "034jqsxswy9gqdh2zkgc1js99qkv75ks4xvzgmh0284sraagv61z"))
2537 (modules '((guix build utils)))
2540 (delete-file-recursively "src/htslib")
2542 (build-system gnu-build-system)
2544 `(#:tests? #f ; There are no tests to run.
2546 (list "PARALLEL=1" ; Allow parallel execution at run-time.
2547 (string-append "prefix=" (assoc-ref %outputs "out")))
2549 (modify-phases %standard-phases
2550 (delete 'configure) ; There is no configure phase.
2551 (add-after 'install 'install-templates
2552 (lambda* (#:key outputs #:allow-other-keys)
2553 (let ((templates (string-append (assoc-ref outputs "out")
2554 "/share/delly/templates")))
2556 (copy-recursively "excludeTemplates" templates)
2563 (home-page "https://github.com/dellytools/delly")
2564 (synopsis "Integrated structural variant prediction method")
2565 (description "Delly is an integrated structural variant prediction method
2566 that can discover and genotype deletions, tandem duplications, inversions and
2567 translocations at single-nucleotide resolution in short-read massively parallel
2568 sequencing data. It uses paired-ends and split-reads to sensitively and
2569 accurately delineate genomic rearrangements throughout the genome.")
2570 (license license:gpl3+)))
2572 (define-public diamond
2579 (url "https://github.com/bbuchfink/diamond.git")
2580 (commit (string-append "v" version))))
2581 (file-name (git-file-name name version))
2584 "0bky78v79g3wmdpsd706cscckgw1v09fg8vdd0z8z0d5b97aj9zl"))))
2585 (build-system cmake-build-system)
2587 '(#:tests? #f ; no "check" target
2589 (modify-phases %standard-phases
2590 (add-after 'unpack 'remove-native-compilation
2592 (substitute* "CMakeLists.txt" (("-march=native") ""))
2596 (home-page "https://github.com/bbuchfink/diamond")
2597 (synopsis "Accelerated BLAST compatible local sequence aligner")
2599 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2600 translated DNA query sequences against a protein reference database (BLASTP
2601 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2602 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2603 data and settings.")
2604 (license license:agpl3+)))
2606 (define-public discrover
2614 (url "https://github.com/maaskola/discrover.git")
2616 (file-name (git-file-name name version))
2619 "173fwi2vb6a5kp406hm3jj6j7v4whww796f2qcygp4rpvamh307y"))))
2620 (build-system cmake-build-system)
2622 `(#:tests? #f ; there are no tests
2624 (modify-phases %standard-phases
2625 (add-after 'unpack 'fix-latex-errors
2627 (with-fluids ((%default-port-encoding #f))
2628 (substitute* "doc/references.bib"
2629 (("\\{S\\}illanp[^,]+,")
2630 "{S}illanp{\\\"a}{\\\"a},")))
2631 ;; XXX: I just can't get pdflatex to not complain about these
2632 ;; characters. They end up in the manual via the generated
2633 ;; discrover-cli-help.txt.
2634 (substitute* "src/hmm/cli.cpp"
2638 ;; This seems to be a syntax error.
2639 (substitute* "doc/discrover-manual.tex"
2640 (("theverbbox\\[t\\]") "theverbbox"))
2642 (add-after 'unpack 'add-missing-includes
2644 (substitute* "src/executioninformation.hpp"
2645 (("#define EXECUTIONINFORMATION_HPP" line)
2646 (string-append line "\n#include <random>")))
2647 (substitute* "src/plasma/fasta.hpp"
2648 (("#define FASTA_HPP" line)
2649 (string-append line "\n#include <random>")))
2651 ;; FIXME: this is needed because we're using texlive-union, which
2652 ;; doesn't handle fonts correctly. It expects to be able to generate
2653 ;; fonts in the home directory.
2654 (add-before 'build 'setenv-HOME
2655 (lambda _ (setenv "HOME" "/tmp") #t)))))
2659 ("rmath-standalone" ,rmath-standalone)))
2661 `(("texlive" ,(texlive-union (list texlive-fonts-cm
2662 texlive-fonts-amsfonts
2665 texlive-latex-examplep
2666 texlive-latex-hyperref
2668 texlive-latex-natbib
2669 texlive-bibtex ; style files used by natbib
2670 texlive-latex-pgf ; tikz
2671 texlive-latex-verbatimbox)))
2672 ("imagemagick" ,imagemagick)))
2673 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2674 (synopsis "Discover discriminative nucleotide sequence motifs")
2675 (description "Discrover is a motif discovery method to find binding sites
2676 of nucleic acid binding proteins.")
2677 (license license:gpl3+)))
2679 (define-public eigensoft
2687 (url "https://github.com/DReichLab/EIG.git")
2688 (commit (string-append "v" version))))
2689 (file-name (git-file-name name version))
2692 "1c141fqvhnzibmnf22sv23vbmzm20kjjyrib44cfh75wyndp2d9k"))
2693 (modules '((guix build utils)))
2694 ;; Remove pre-built binaries.
2696 (delete-file-recursively "bin")
2699 (build-system gnu-build-system)
2701 `(#:tests? #f ; There are no tests.
2702 #:make-flags '("CC=gcc")
2704 (modify-phases %standard-phases
2705 ;; There is no configure phase, but the Makefile is in a
2708 (lambda _ (chdir "src") #t))
2709 ;; The provided install target only copies executables to
2710 ;; the "bin" directory in the build root.
2711 (add-after 'install 'actually-install
2712 (lambda* (#:key outputs #:allow-other-keys)
2713 (let* ((out (assoc-ref outputs "out"))
2714 (bin (string-append out "/bin")))
2715 (for-each (lambda (file)
2716 (install-file file bin))
2717 (find-files "../bin" ".*"))
2722 ("openblas" ,openblas)
2724 ("gfortran" ,gfortran "lib")))
2725 (home-page "https://github.com/DReichLab/EIG")
2726 (synopsis "Tools for population genetics")
2727 (description "The EIGENSOFT package provides tools for population
2728 genetics and stratification correction. EIGENSOFT implements methods commonly
2729 used in population genetics analyses such as PCA, computation of Tracy-Widom
2730 statistics, and finding related individuals in structured populations. It
2731 comes with a built-in plotting script and supports multiple file formats and
2732 quantitative phenotypes.")
2733 ;; The license of the eigensoft tools is Expat, but since it's
2734 ;; linking with the GNU Scientific Library (GSL) the effective
2735 ;; license is the GPL.
2736 (license license:gpl3+)))
2738 (define-public edirect
2741 (version "10.2.20181018")
2744 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect"
2745 "/versions/" version
2746 "/edirect-" version ".tar.gz"))
2749 "091f4aigzpbqih6h82nq566gkp3y07i72yqndmqskfgar1vwgci7"))))
2750 (build-system perl-build-system)
2753 (modify-phases %standard-phases
2756 (delete 'check) ; simple check after install
2758 (lambda* (#:key outputs #:allow-other-keys)
2759 (install-file "edirect.pl"
2760 (string-append (assoc-ref outputs "out") "/bin"))
2762 (add-after 'install 'wrap-program
2763 (lambda* (#:key outputs #:allow-other-keys)
2764 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2765 (let* ((out (assoc-ref outputs "out"))
2766 (path (getenv "PERL5LIB")))
2767 (wrap-program (string-append out "/bin/edirect.pl")
2768 `("PERL5LIB" ":" prefix (,path))))
2770 (add-after 'wrap-program 'check
2771 (lambda* (#:key outputs #:allow-other-keys)
2772 (invoke (string-append (assoc-ref outputs "out")
2777 `(("perl-html-parser" ,perl-html-parser)
2778 ("perl-encode-locale" ,perl-encode-locale)
2779 ("perl-file-listing" ,perl-file-listing)
2780 ("perl-html-tagset" ,perl-html-tagset)
2781 ("perl-html-tree" ,perl-html-tree)
2782 ("perl-http-cookies" ,perl-http-cookies)
2783 ("perl-http-date" ,perl-http-date)
2784 ("perl-http-message" ,perl-http-message)
2785 ("perl-http-negotiate" ,perl-http-negotiate)
2786 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2787 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2788 ("perl-net-http" ,perl-net-http)
2789 ("perl-uri" ,perl-uri)
2790 ("perl-www-robotrules" ,perl-www-robotrules)
2791 ("perl-xml-simple" ,perl-xml-simple)
2793 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2794 (synopsis "Tools for accessing the NCBI's set of databases")
2796 "Entrez Direct (EDirect) is a method for accessing the National Center
2797 for Biotechnology Information's (NCBI) set of interconnected
2798 databases (publication, sequence, structure, gene, variation, expression,
2799 etc.) from a terminal. Functions take search terms from command-line
2800 arguments. Individual operations are combined to build multi-step queries.
2801 Record retrieval and formatting normally complete the process.
2803 EDirect also provides an argument-driven function that simplifies the
2804 extraction of data from document summaries or other results that are returned
2805 in structured XML format. This can eliminate the need for writing custom
2806 software to answer ad hoc questions.")
2807 (license license:public-domain)))
2809 (define-public exonerate
2818 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2819 "exonerate-" version ".tar.gz"))
2822 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2823 (build-system gnu-build-system)
2825 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2827 `(("pkg-config" ,pkg-config)))
2831 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2832 (synopsis "Generic tool for biological sequence alignment")
2834 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2835 the alignment of sequences using a many alignment models, either exhaustive
2836 dynamic programming or a variety of heuristics.")
2837 (license license:gpl3)))
2839 (define-public express
2847 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2848 version "/express-" version "-src.tgz"))
2851 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2852 (build-system cmake-build-system)
2854 `(#:tests? #f ;no "check" target
2856 (modify-phases %standard-phases
2857 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2858 (lambda* (#:key inputs #:allow-other-keys)
2859 (substitute* "CMakeLists.txt"
2860 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2861 "set(Boost_USE_STATIC_LIBS OFF)")
2862 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2863 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2864 (substitute* "src/CMakeLists.txt"
2865 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2866 (string-append (assoc-ref inputs "bamtools") "/lib"))
2867 (("libprotobuf.a") "libprotobuf.so"))
2871 ("bamtools" ,bamtools)
2872 ("protobuf" ,protobuf)
2874 (home-page "http://bio.math.berkeley.edu/eXpress")
2875 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2877 "eXpress is a streaming tool for quantifying the abundances of a set of
2878 target sequences from sampled subsequences. Example applications include
2879 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2880 analysis (from RNA-Seq), transcription factor binding quantification in
2881 ChIP-Seq, and analysis of metagenomic data.")
2882 (license license:artistic2.0)))
2884 (define-public express-beta-diversity
2886 (name "express-beta-diversity")
2891 (url "https://github.com/dparks1134/ExpressBetaDiversity.git")
2892 (commit (string-append "v" version))))
2893 (file-name (git-file-name name version))
2896 "0s0yzg5c21349rh7x4w9266jsvnp7j1hp9cf8sk32hz8nvrj745x"))))
2897 (build-system gnu-build-system)
2900 (modify-phases %standard-phases
2902 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2904 (lambda _ (invoke "../bin/ExpressBetaDiversity" "-u") #t))
2906 (lambda* (#:key outputs #:allow-other-keys)
2907 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
2908 (install-file "../scripts/convertToEBD.py" bin)
2909 (install-file "../bin/ExpressBetaDiversity" bin)
2912 `(("python" ,python-2)))
2913 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2914 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2916 "Express Beta Diversity (EBD) calculates ecological beta diversity
2917 (dissimilarity) measures between biological communities. EBD implements a
2918 variety of diversity measures including those that make use of phylogenetic
2919 similarity of community members.")
2920 (license license:gpl3+)))
2922 (define-public fasttree
2929 "http://www.microbesonline.org/fasttree/FastTree-"
2933 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2934 (build-system gnu-build-system)
2936 `(#:tests? #f ; no "check" target
2938 (modify-phases %standard-phases
2942 (lambda* (#:key source #:allow-other-keys)
2945 "-finline-functions"
2956 "-finline-functions"
2965 (lambda* (#:key outputs #:allow-other-keys)
2966 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
2967 (install-file "FastTree" bin)
2968 (install-file "FastTreeMP" bin)
2970 (home-page "http://www.microbesonline.org/fasttree")
2971 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2973 "FastTree can handle alignments with up to a million of sequences in a
2974 reasonable amount of time and memory. For large alignments, FastTree is
2975 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2976 (license license:gpl2+)))
2978 (define-public fastx-toolkit
2980 (name "fastx-toolkit")
2986 "https://github.com/agordon/fastx_toolkit/releases/download/"
2987 version "/fastx_toolkit-" version ".tar.bz2"))
2990 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2991 (build-system gnu-build-system)
2993 `(("libgtextutils" ,libgtextutils)))
2995 `(("pkg-config" ,pkg-config)))
2996 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
2997 (synopsis "Tools for FASTA/FASTQ file preprocessing")
2999 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
3000 FASTA/FASTQ files preprocessing.
3002 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
3003 containing multiple short-reads sequences. The main processing of such
3004 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
3005 is sometimes more productive to preprocess the files before mapping the
3006 sequences to the genome---manipulating the sequences to produce better mapping
3007 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
3008 (license license:agpl3+)))
3010 (define-public flexbar
3017 (url "https://github.com/seqan/flexbar.git")
3018 (commit (string-append "v" version))))
3019 (file-name (git-file-name name version))
3022 "1pq9sxvdnldl14libk234m72dqhwgzs3acgl943wchwdqlcsi5r2"))))
3023 (build-system cmake-build-system)
3026 (modify-phases %standard-phases
3027 (add-after 'unpack 'do-not-tune-to-CPU
3029 (substitute* "src/CMakeLists.txt"
3030 ((" -march=native") ""))
3033 (lambda* (#:key outputs #:allow-other-keys)
3034 (setenv "PATH" (string-append (getcwd) ":" (getenv "PATH")))
3035 (with-directory-excursion "../source/test"
3036 (invoke "bash" "flexbar_test.sh"))
3039 (lambda* (#:key outputs #:allow-other-keys)
3040 (let* ((out (string-append (assoc-ref outputs "out")))
3041 (bin (string-append out "/bin/")))
3042 (install-file "flexbar" bin))
3048 `(("pkg-config" ,pkg-config)
3050 (home-page "https://github.com/seqan/flexbar")
3051 (synopsis "Barcode and adapter removal tool for sequencing platforms")
3053 "Flexbar preprocesses high-throughput nucleotide sequencing data
3054 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
3055 Moreover, trimming and filtering features are provided. Flexbar increases
3056 read mapping rates and improves genome and transcriptome assemblies. It
3057 supports next-generation sequencing data in fasta/q and csfasta/q format from
3058 Illumina, Roche 454, and the SOLiD platform.")
3059 (license license:bsd-3)))
3061 (define-public fraggenescan
3063 (name "fraggenescan")
3069 (string-append "mirror://sourceforge/fraggenescan/"
3070 "FragGeneScan" version ".tar.gz"))
3072 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
3073 (build-system gnu-build-system)
3076 (modify-phases %standard-phases
3078 (add-before 'build 'patch-paths
3079 (lambda* (#:key outputs #:allow-other-keys)
3080 (let* ((out (string-append (assoc-ref outputs "out")))
3081 (share (string-append out "/share/fraggenescan/")))
3082 (substitute* "run_FragGeneScan.pl"
3084 (string-append "system(\"" (which "rm")))
3086 (string-append "system(\"" (which "mv")))
3087 (("\\\"awk") (string-append "\"" (which "awk")))
3088 ;; This script and other programs expect the training files
3089 ;; to be in the non-standard location bin/train/XXX. Change
3090 ;; this to be share/fraggenescan/train/XXX instead.
3091 (("^\\$train.file = \\$dir.*")
3092 (string-append "$train_file = \""
3094 "train/\".$FGS_train_file;")))
3095 (substitute* "run_hmm.c"
3096 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
3097 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
3101 (invoke "make" "clean")
3102 (invoke "make" "fgs")
3105 (lambda* (#:key outputs #:allow-other-keys)
3106 (let* ((out (string-append (assoc-ref outputs "out")))
3107 (bin (string-append out "/bin/"))
3108 (share (string-append out "/share/fraggenescan/train")))
3109 (install-file "run_FragGeneScan.pl" bin)
3110 (install-file "FragGeneScan" bin)
3111 (copy-recursively "train" share))
3114 (add-after 'install 'post-install-check
3115 ;; In lieu of 'make check', run one of the examples and check the
3116 ;; output files gets created.
3117 (lambda* (#:key outputs #:allow-other-keys)
3118 (let* ((out (string-append (assoc-ref outputs "out")))
3119 (bin (string-append out "/bin/"))
3120 (frag (string-append bin "run_FragGeneScan.pl")))
3121 ;; Test complete genome.
3123 "-genome=./example/NC_000913.fna"
3127 (unless (and (file-exists? "test2.faa")
3128 (file-exists? "test2.ffn")
3129 (file-exists? "test2.gff")
3130 (file-exists? "test2.out"))
3131 (error "Expected files do not exist."))
3132 ;; Test incomplete sequences.
3134 "-genome=./example/NC_000913-fgs.ffn"
3141 ("python" ,python-2))) ;not compatible with python 3.
3142 (home-page "https://sourceforge.net/projects/fraggenescan/")
3143 (synopsis "Finds potentially fragmented genes in short reads")
3145 "FragGeneScan is a program for predicting bacterial and archaeal genes in
3146 short and error-prone DNA sequencing reads. It can also be applied to predict
3147 genes in incomplete assemblies or complete genomes.")
3148 ;; GPL3+ according to private correspondense with the authors.
3149 (license license:gpl3+)))
3151 (define-public fxtract
3152 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
3160 (url "https://github.com/ctSkennerton/fxtract.git")
3162 (file-name (git-file-name name version))
3165 "0hab3gpwf4w9s87qlbswq6ws1qqybh4dcqk79q1ahyldzai5fgp5"))))
3166 (build-system gnu-build-system)
3168 `(#:make-flags (list
3169 (string-append "PREFIX=" (assoc-ref %outputs "out"))
3171 #:test-target "fxtract_test"
3173 (modify-phases %standard-phases
3175 (add-before 'build 'copy-util
3176 (lambda* (#:key inputs #:allow-other-keys)
3178 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
3180 ;; Do not use make install as this requires additional dependencies.
3182 (lambda* (#:key outputs #:allow-other-keys)
3183 (let* ((out (assoc-ref outputs "out"))
3184 (bin (string-append out"/bin")))
3185 (install-file "fxtract" bin)
3191 ;; ctskennerton-util is licensed under GPL2.
3192 `(("ctskennerton-util"
3196 (url "https://github.com/ctSkennerton/util.git")
3197 (commit util-commit)))
3198 (file-name (string-append
3199 "ctstennerton-util-" util-commit "-checkout"))
3202 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
3203 (home-page "https://github.com/ctSkennerton/fxtract")
3204 (synopsis "Extract sequences from FASTA and FASTQ files")
3206 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
3207 or FASTQ) file given a subsequence. It uses a simple substring search for
3208 basic tasks but can change to using POSIX regular expressions, PCRE, hash
3209 lookups or multi-pattern searching as required. By default fxtract looks in
3210 the sequence of each record but can also be told to look in the header,
3211 comment or quality sections.")
3212 ;; 'util' requires SSE instructions.
3213 (supported-systems '("x86_64-linux"))
3214 (license license:expat))))
3216 (define-public gemma
3223 (url "https://github.com/xiangzhou/GEMMA.git")
3224 (commit (string-append "v" version))))
3225 (file-name (git-file-name name version))
3228 "1s3ncnbn45r2hh1cvrqky1kbqq6546biypr4f5mkw1kqlrgyh0yg"))))
3231 ("gfortran" ,gfortran "lib")
3234 ("openblas" ,openblas)
3236 (build-system gnu-build-system)
3239 '(,@(match (%current-system)
3241 '("FORCE_DYNAMIC=1"))
3243 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
3245 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
3247 (modify-phases %standard-phases
3249 (add-after 'unpack 'find-eigen
3250 (lambda* (#:key inputs #:allow-other-keys)
3251 ;; Ensure that Eigen headers can be found
3252 (setenv "CPLUS_INCLUDE_PATH"
3253 (string-append (getenv "CPLUS_INCLUDE_PATH")
3255 (assoc-ref inputs "eigen")
3258 (add-before 'build 'bin-mkdir
3263 (lambda* (#:key outputs #:allow-other-keys)
3264 (let ((out (assoc-ref outputs "out")))
3265 (install-file "bin/gemma"
3269 #:tests? #f)) ; no tests included yet
3270 (home-page "https://github.com/xiangzhou/GEMMA")
3271 (synopsis "Tool for genome-wide efficient mixed model association")
3273 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
3274 standard linear mixed model resolver with application in genome-wide
3275 association studies (GWAS).")
3276 (license license:gpl3)))
3285 (url "https://github.com/nboley/grit.git")
3287 (file-name (git-file-name name version))
3290 "1l5v8vfvfbrpmgnrvbrbv40d0arhxcnmxgv2f1mlcqfa3q6bkqm9"))))
3291 (build-system python-build-system)
3293 `(#:python ,python-2
3295 (modify-phases %standard-phases
3296 (add-after 'unpack 'generate-from-cython-sources
3297 (lambda* (#:key inputs outputs #:allow-other-keys)
3298 ;; Delete these C files to force fresh generation from pyx sources.
3299 (delete-file "grit/sparsify_support_fns.c")
3300 (delete-file "grit/call_peaks_support_fns.c")
3301 (substitute* "setup.py"
3302 (("Cython.Setup") "Cython.Build"))
3305 `(("python-scipy" ,python2-scipy)
3306 ("python-numpy" ,python2-numpy)
3307 ("python-pysam" ,python2-pysam)
3308 ("python-networkx" ,python2-networkx)))
3310 `(("python-cython" ,python2-cython)))
3311 (home-page "http://grit-bio.org")
3312 (synopsis "Tool for integrative analysis of RNA-seq type assays")
3314 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
3315 full length transcript models. When none of these data sources are available,
3316 GRIT can be run by providing a candidate set of TES or TSS sites. In
3317 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
3318 also be run in quantification mode, where it uses a provided GTF file and just
3319 estimates transcript expression.")
3320 (license license:gpl3+)))
3322 (define-public hisat
3329 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
3330 version "-beta-source.zip"))
3333 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
3334 (build-system gnu-build-system)
3336 `(#:tests? #f ;no check target
3337 #:make-flags '("allall"
3338 ;; Disable unsupported `popcnt' instructions on
3339 ;; architectures other than x86_64
3340 ,@(if (string-prefix? "x86_64"
3341 (or (%current-target-system)
3344 '("POPCNT_CAPABILITY=0")))
3346 (modify-phases %standard-phases
3347 (add-after 'unpack 'patch-sources
3349 ;; XXX Cannot use snippet because zip files are not supported
3350 (substitute* "Makefile"
3351 (("^CC = .*$") "CC = gcc")
3352 (("^CPP = .*$") "CPP = g++")
3353 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
3354 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
3355 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
3356 (substitute* '("hisat-build" "hisat-inspect")
3357 (("/usr/bin/env") (which "env")))
3360 (lambda* (#:key outputs #:allow-other-keys)
3361 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
3362 (for-each (lambda (file)
3363 (install-file file bin))
3366 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
3368 (delete 'configure))))
3370 `(("unzip" ,unzip)))
3375 ;; Non-portable SSE instructions are used so building fails on platforms
3376 ;; other than x86_64.
3377 (supported-systems '("x86_64-linux"))
3378 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
3379 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
3381 "HISAT is a fast and sensitive spliced alignment program for mapping
3382 RNA-seq reads. In addition to one global FM index that represents a whole
3383 genome, HISAT uses a large set of small FM indexes that collectively cover the
3384 whole genome. These small indexes (called local indexes) combined with
3385 several alignment strategies enable effective alignment of RNA-seq reads, in
3386 particular, reads spanning multiple exons.")
3387 (license license:gpl3+)))
3389 (define-public hisat2
3396 (uri (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
3397 "/downloads/hisat2-" version "-source.zip"))
3400 "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"))))
3401 (build-system gnu-build-system)
3403 `(#:tests? #f ; no check target
3404 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
3405 #:modules ((guix build gnu-build-system)
3409 (modify-phases %standard-phases
3410 (add-after 'unpack 'make-deterministic
3412 (substitute* "Makefile"
3417 (lambda* (#:key outputs #:allow-other-keys)
3418 (let* ((out (assoc-ref outputs "out"))
3419 (bin (string-append out "/bin/"))
3420 (doc (string-append out "/share/doc/hisat2/")))
3422 (cut install-file <> bin)
3424 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
3426 (install-file "doc/manual.inc.html" doc))
3429 `(("unzip" ,unzip) ; needed for archive from ftp
3431 ("pandoc" ,ghc-pandoc))) ; for documentation
3432 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
3433 (synopsis "Graph-based alignment of genomic sequencing reads")
3434 (description "HISAT2 is a fast and sensitive alignment program for mapping
3435 next-generation sequencing reads (both DNA and RNA) to a population of human
3436 genomes (as well as to a single reference genome). In addition to using one
3437 global @dfn{graph FM} (GFM) index that represents a population of human
3438 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
3439 the whole genome. These small indexes, combined with several alignment
3440 strategies, enable rapid and accurate alignment of sequencing reads. This new
3441 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
3442 ;; HISAT2 contains files from Bowtie2, which is released under
3443 ;; GPLv2 or later. The HISAT2 source files are released under
3445 (license license:gpl3+)))
3447 (define-public hmmer
3455 "http://eddylab.org/software/hmmer/hmmer-" version ".tar.gz"))
3458 "171bivy6xhgjsz5nv53n81pc3frnwz29ylblawk2bv46szwjjqd5"))))
3459 (build-system gnu-build-system)
3460 (native-inputs `(("perl" ,perl)))
3461 (home-page "http://hmmer.org/")
3462 (synopsis "Biosequence analysis using profile hidden Markov models")
3464 "HMMER is used for searching sequence databases for homologs of protein
3465 sequences, and for making protein sequence alignments. It implements methods
3466 using probabilistic models called profile hidden Markov models (profile
3468 ;; hmmer uses non-portable SSE intrinsics so building fails on other
3470 (supported-systems '("x86_64-linux" "i686-linux"))
3471 (license license:bsd-3)))
3473 (define-public htseq
3479 (uri (pypi-uri "HTSeq" version))
3482 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
3483 (build-system python-build-system)
3485 `(("python-cython" ,python-cython)))
3486 ;; Numpy needs to be propagated when htseq is used as a Python library.
3488 `(("python-numpy" ,python-numpy)))
3490 `(("python-pysam" ,python-pysam)
3491 ("python-matplotlib" ,python-matplotlib)))
3492 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
3493 (synopsis "Analysing high-throughput sequencing data with Python")
3495 "HTSeq is a Python package that provides infrastructure to process data
3496 from high-throughput sequencing assays.")
3497 (license license:gpl3+)))
3499 (define-public python2-htseq
3500 (package-with-python2 htseq))
3502 (define-public java-htsjdk
3504 (name "java-htsjdk")
3505 (version "2.3.0") ; last version without build dependency on gradle
3509 (url "https://github.com/samtools/htsjdk.git")
3511 (file-name (git-file-name name version))
3514 "1b178ixcabanm834ydjl3jiakpyxdmki32hqfv2abrzn3rcwa28i"))
3515 (modules '((guix build utils)))
3517 ;; Delete pre-built binaries
3519 (delete-file-recursively "lib")
3522 (build-system ant-build-system)
3524 `(#:tests? #f ; test require Internet access
3527 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3528 "/share/java/htsjdk/"))
3529 #:build-target "all"
3531 (modify-phases %standard-phases
3532 ;; The build phase also installs the jars
3533 (delete 'install))))
3535 `(("java-ngs" ,java-ngs)
3536 ("java-snappy-1" ,java-snappy-1)
3537 ("java-commons-compress" ,java-commons-compress)
3538 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3539 ("java-commons-jexl-2" ,java-commons-jexl-2)
3540 ("java-xz" ,java-xz)))
3542 `(("java-testng" ,java-testng)))
3543 (home-page "http://samtools.github.io/htsjdk/")
3544 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3546 "HTSJDK is an implementation of a unified Java library for accessing
3547 common file formats, such as SAM and VCF, used for high-throughput
3548 sequencing (HTS) data. There are also an number of useful utilities for
3549 manipulating HTS data.")
3550 (license license:expat)))
3552 (define-public java-htsjdk-latest
3554 (name "java-htsjdk")
3559 (url "https://github.com/samtools/htsjdk.git")
3561 (file-name (string-append name "-" version "-checkout"))
3564 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
3565 (build-system ant-build-system)
3567 `(#:tests? #f ; test require Scala
3569 #:jar-name "htsjdk.jar"
3571 (modify-phases %standard-phases
3572 (add-after 'unpack 'remove-useless-build.xml
3573 (lambda _ (delete-file "build.xml") #t))
3574 ;; The tests require the scalatest package.
3575 (add-after 'unpack 'remove-tests
3576 (lambda _ (delete-file-recursively "src/test") #t)))))
3578 `(("java-ngs" ,java-ngs)
3579 ("java-snappy-1" ,java-snappy-1)
3580 ("java-commons-compress" ,java-commons-compress)
3581 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3582 ("java-commons-jexl-2" ,java-commons-jexl-2)
3583 ("java-xz" ,java-xz)))
3585 `(("java-junit" ,java-junit)))
3586 (home-page "http://samtools.github.io/htsjdk/")
3587 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3589 "HTSJDK is an implementation of a unified Java library for accessing
3590 common file formats, such as SAM and VCF, used for high-throughput
3591 sequencing (HTS) data. There are also an number of useful utilities for
3592 manipulating HTS data.")
3593 (license license:expat)))
3595 ;; This is needed for picard 2.10.3
3596 (define-public java-htsjdk-2.10.1
3597 (package (inherit java-htsjdk-latest)
3598 (name "java-htsjdk")
3603 (url "https://github.com/samtools/htsjdk.git")
3605 (file-name (string-append name "-" version "-checkout"))
3608 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
3609 (build-system ant-build-system)
3611 `(#:tests? #f ; tests require Scala
3613 #:jar-name "htsjdk.jar"
3615 (modify-phases %standard-phases
3616 (add-after 'unpack 'remove-useless-build.xml
3617 (lambda _ (delete-file "build.xml") #t))
3618 ;; The tests require the scalatest package.
3619 (add-after 'unpack 'remove-tests
3620 (lambda _ (delete-file-recursively "src/test") #t)))))))
3622 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3623 ;; recent version of java-htsjdk, which depends on gradle.
3624 (define-public java-picard
3626 (name "java-picard")
3631 (url "https://github.com/broadinstitute/picard.git")
3633 (file-name (string-append "java-picard-" version "-checkout"))
3636 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3637 (modules '((guix build utils)))
3640 ;; Delete pre-built binaries.
3641 (delete-file-recursively "lib")
3643 (substitute* "build.xml"
3644 ;; Remove build-time dependency on git.
3645 (("failifexecutionfails=\"true\"")
3646 "failifexecutionfails=\"false\"")
3648 (("depends=\"compile-htsjdk, ")
3650 (("depends=\"compile-htsjdk-tests, ")
3652 ;; Build picard-lib.jar before building picard.jar
3653 (("name=\"picard-jar\" depends=\"" line)
3654 (string-append line "picard-lib-jar, ")))
3656 (build-system ant-build-system)
3658 `(#:build-target "picard-jar"
3659 #:test-target "test"
3660 ;; Tests require jacoco:coverage.
3663 (list (string-append "-Dhtsjdk_lib_dir="
3664 (assoc-ref %build-inputs "java-htsjdk")
3665 "/share/java/htsjdk/")
3666 "-Dhtsjdk-classes=dist/tmp"
3667 (string-append "-Dhtsjdk-version="
3668 ,(package-version java-htsjdk)))
3671 (modify-phases %standard-phases
3672 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3673 (delete 'generate-jar-indices)
3674 (add-after 'unpack 'use-our-htsjdk
3675 (lambda* (#:key inputs #:allow-other-keys)
3676 (substitute* "build.xml"
3677 (("\\$\\{htsjdk\\}/lib")
3678 (string-append (assoc-ref inputs "java-htsjdk")
3679 "/share/java/htsjdk/")))
3681 (add-after 'unpack 'make-test-target-independent
3682 (lambda* (#:key inputs #:allow-other-keys)
3683 (substitute* "build.xml"
3684 (("name=\"test\" depends=\"compile, ")
3685 "name=\"test\" depends=\""))
3687 (replace 'install (install-jars "dist")))))
3689 `(("java-htsjdk" ,java-htsjdk)
3690 ("java-guava" ,java-guava)))
3692 `(("java-testng" ,java-testng)))
3693 (home-page "http://broadinstitute.github.io/picard/")
3694 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3695 (description "Picard is a set of Java command line tools for manipulating
3696 high-throughput sequencing (HTS) data and formats. Picard is implemented
3697 using the HTSJDK Java library to support accessing file formats that are
3698 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3700 (license license:expat)))
3702 ;; This is needed for dropseq-tools
3703 (define-public java-picard-2.10.3
3705 (name "java-picard")
3710 (url "https://github.com/broadinstitute/picard.git")
3712 (file-name (string-append "java-picard-" version "-checkout"))
3715 "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi"))))
3716 (build-system ant-build-system)
3718 `(#:jar-name "picard.jar"
3719 ;; Tests require jacoco:coverage.
3722 #:main-class "picard.cmdline.PicardCommandLine"
3723 #:modules ((guix build ant-build-system)
3725 (guix build java-utils)
3730 (modify-phases %standard-phases
3731 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3732 (delete 'generate-jar-indices)
3733 (add-after 'unpack 'remove-useless-build.xml
3734 (lambda _ (delete-file "build.xml") #t))
3735 ;; This is necessary to ensure that htsjdk is found when using
3736 ;; picard.jar as an executable.
3737 (add-before 'build 'edit-classpath-in-manifest
3738 (lambda* (#:key inputs #:allow-other-keys)
3739 (chmod "build.xml" #o664)
3740 (call-with-output-file "build.xml.new"
3744 (with-input-from-file "build.xml"
3745 (lambda _ (xml->sxml #:trim-whitespace? #t)))
3746 `((target . ,(lambda (tag . kids)
3747 (let ((name ((sxpath '(name *text*))
3749 ;; FIXME: We're breaking the line
3750 ;; early with a dummy path to
3751 ;; ensure that the store reference
3752 ;; isn't broken apart and can still
3753 ;; be found by the reference
3758 ~a/share/java/htsjdk.jar${line.separator}${line.separator}"
3759 ;; maximum line length is 70
3760 (string-tabulate (const #\b) 57)
3761 (assoc-ref inputs "java-htsjdk"))))
3762 (if (member "manifest" name)
3765 (@ (file "${manifest.file}")
3766 (match "\\r\\n\\r\\n")
3767 (replace "${line.separator}")))
3770 (file "${manifest.file}")
3773 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
3774 (*text* . ,(lambda (_ txt) txt))))
3776 (rename-file "build.xml.new" "build.xml")
3779 `(("java-htsjdk" ,java-htsjdk-2.10.1)))
3781 `(("java-testng" ,java-testng)
3782 ("java-guava" ,java-guava)))
3783 (home-page "http://broadinstitute.github.io/picard/")
3784 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3785 (description "Picard is a set of Java command line tools for manipulating
3786 high-throughput sequencing (HTS) data and formats. Picard is implemented
3787 using the HTSJDK Java library to support accessing file formats that are
3788 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3790 (license license:expat)))
3792 ;; This is the last version of Picard to provide net.sf.samtools
3793 (define-public java-picard-1.113
3794 (package (inherit java-picard)
3795 (name "java-picard")
3800 (url "https://github.com/broadinstitute/picard.git")
3802 (file-name (string-append "java-picard-" version "-checkout"))
3805 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
3806 (modules '((guix build utils)))
3809 ;; Delete pre-built binaries.
3810 (delete-file-recursively "lib")
3813 (build-system ant-build-system)
3815 `(#:build-target "picard-jar"
3816 #:test-target "test"
3817 ;; FIXME: the class path at test time is wrong.
3818 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
3819 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
3822 ;; This is only used for tests.
3824 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
3826 (modify-phases %standard-phases
3827 ;; FIXME: This phase fails.
3828 (delete 'generate-jar-indices)
3829 ;; Do not use bundled ant bzip2.
3830 (add-after 'unpack 'use-ant-bzip
3831 (lambda* (#:key inputs #:allow-other-keys)
3832 (substitute* "build.xml"
3833 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
3834 (string-append (assoc-ref inputs "ant")
3837 (add-after 'unpack 'make-test-target-independent
3838 (lambda* (#:key inputs #:allow-other-keys)
3839 (substitute* "build.xml"
3840 (("name=\"test\" depends=\"compile, ")
3841 "name=\"test\" depends=\"compile-tests, ")
3842 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
3843 "name=\"compile\" depends=\"compile-src\""))
3845 (add-after 'unpack 'fix-deflater-path
3846 (lambda* (#:key outputs #:allow-other-keys)
3847 (substitute* "src/java/net/sf/samtools/Defaults.java"
3848 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
3849 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
3850 (assoc-ref outputs "out")
3851 "/lib/jni/libIntelDeflater.so"
3854 ;; Build the deflater library, because we've previously deleted the
3855 ;; pre-built one. This can only be built with access to the JDK
3857 (add-after 'build 'build-jni
3858 (lambda* (#:key inputs #:allow-other-keys)
3861 (invoke "tar" "--strip-components=1" "-C" "jdk-src"
3862 "-xf" (assoc-ref inputs "jdk-src"))
3863 (invoke "javah" "-jni"
3864 "-classpath" "classes"
3866 "net.sf.samtools.util.zip.IntelDeflater")
3867 (with-directory-excursion "src/c/inteldeflater"
3868 (invoke "gcc" "-I../../../lib" "-I."
3869 (string-append "-I" (assoc-ref inputs "jdk")
3871 "-I../../../jdk-src/src/share/native/common/"
3872 "-I../../../jdk-src/src/solaris/native/common/"
3873 "-c" "-O3" "-fPIC" "IntelDeflater.c")
3874 (invoke "gcc" "-shared"
3875 "-o" "../../../lib/jni/libIntelDeflater.so"
3876 "IntelDeflater.o" "-lz" "-lstdc++"))
3878 ;; We can only build everything else after building the JNI library.
3879 (add-after 'build-jni 'build-rest
3880 (lambda* (#:key make-flags #:allow-other-keys)
3881 (apply invoke `("ant" "all" ,@make-flags))
3883 (add-before 'build 'set-JAVA6_HOME
3885 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
3887 (replace 'install (install-jars "dist"))
3888 (add-after 'install 'install-jni-lib
3889 (lambda* (#:key outputs #:allow-other-keys)
3890 (let ((jni (string-append (assoc-ref outputs "out")
3893 (install-file "lib/jni/libIntelDeflater.so" jni)
3896 `(("java-snappy-1" ,java-snappy-1)
3897 ("java-commons-jexl-2" ,java-commons-jexl-2)
3898 ("java-cofoja" ,java-cofoja)
3899 ("ant" ,ant) ; for bzip2 support at runtime
3902 `(("ant-apache-bcel" ,ant-apache-bcel)
3903 ("ant-junit" ,ant-junit)
3904 ("java-testng" ,java-testng)
3905 ("java-commons-bcel" ,java-commons-bcel)
3906 ("java-jcommander" ,java-jcommander)
3907 ("jdk" ,icedtea-8 "jdk")
3908 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
3910 (define-public fastqc
3917 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
3918 "projects/fastqc/fastqc_v"
3919 version "_source.zip"))
3922 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
3923 (build-system ant-build-system)
3925 `(#:tests? #f ; there are no tests
3926 #:build-target "build"
3928 (modify-phases %standard-phases
3929 (add-after 'unpack 'fix-dependencies
3930 (lambda* (#:key inputs #:allow-other-keys)
3931 (substitute* "build.xml"
3933 (string-append (assoc-ref inputs "java-jbzip2")
3934 "/share/java/jbzip2.jar"))
3936 (string-append (assoc-ref inputs "java-picard-1.113")
3937 "/share/java/sam-1.112.jar"))
3939 (string-append (assoc-ref inputs "java-cisd-jhdf5")
3940 "/share/java/sis-jhdf5.jar")))
3942 ;; There is no installation target
3944 (lambda* (#:key inputs outputs #:allow-other-keys)
3945 (let* ((out (assoc-ref outputs "out"))
3946 (bin (string-append out "/bin"))
3947 (share (string-append out "/share/fastqc/"))
3948 (exe (string-append share "/fastqc")))
3949 (for-each mkdir-p (list bin share))
3950 (copy-recursively "bin" share)
3952 (("my \\$java_bin = 'java';")
3953 (string-append "my $java_bin = '"
3954 (assoc-ref inputs "java")
3957 (symlink exe (string-append bin "/fastqc"))
3961 ("perl" ,perl) ; needed for the wrapper script
3962 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
3963 ("java-picard-1.113" ,java-picard-1.113)
3964 ("java-jbzip2" ,java-jbzip2)))
3966 `(("unzip" ,unzip)))
3967 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
3968 (synopsis "Quality control tool for high throughput sequence data")
3970 "FastQC aims to provide a simple way to do some quality control
3971 checks on raw sequence data coming from high throughput sequencing
3972 pipelines. It provides a modular set of analyses which you can use to
3973 give a quick impression of whether your data has any problems of which
3974 you should be aware before doing any further analysis.
3976 The main functions of FastQC are:
3979 @item Import of data from BAM, SAM or FastQ files (any variant);
3980 @item Providing a quick overview to tell you in which areas there may
3982 @item Summary graphs and tables to quickly assess your data;
3983 @item Export of results to an HTML based permanent report;
3984 @item Offline operation to allow automated generation of reports
3985 without running the interactive application.
3987 (license license:gpl3+)))
3989 (define-public fastp
3997 (url "https://github.com/OpenGene/fastp.git")
3998 (commit (string-append "v" version))))
3999 (file-name (git-file-name name version))
4002 "1r6ms5zbf5rps4rgp4z73nczadl00b5rqylw8f684isfz27dp0xh"))))
4003 (build-system gnu-build-system)
4005 `(#:tests? #f ; there are none
4007 (list (string-append "BINDIR=" (assoc-ref %outputs "out") "/bin"))
4009 (modify-phases %standard-phases
4011 (add-before 'install 'create-target-dir
4012 (lambda* (#:key outputs #:allow-other-keys)
4013 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4017 (home-page "https://github.com/OpenGene/fastp/")
4018 (synopsis "All-in-one FastQ preprocessor")
4020 "Fastp is a tool designed to provide fast all-in-one preprocessing for
4021 FastQ files. This tool has multi-threading support to afford high
4023 (license license:expat)))
4025 (define-public htslib
4032 "https://github.com/samtools/htslib/releases/download/"
4033 version "/htslib-" version ".tar.bz2"))
4036 "16ljv43sc3fxmv63w7b2ff8m1s7h89xhazwmbm1bicz8axq8fjz0"))))
4037 (build-system gnu-build-system)
4039 `(("openssl" ,openssl)
4044 (home-page "http://www.htslib.org")
4045 (synopsis "C library for reading/writing high-throughput sequencing data")
4047 "HTSlib is a C library for reading/writing high-throughput sequencing
4048 data. It also provides the @command{bgzip}, @command{htsfile}, and
4049 @command{tabix} utilities.")
4050 ;; Files under cram/ are released under the modified BSD license;
4051 ;; the rest is released under the Expat license
4052 (license (list license:expat license:bsd-3))))
4054 ;; This package should be removed once no packages rely upon it.
4062 "https://github.com/samtools/htslib/releases/download/"
4063 version "/htslib-" version ".tar.bz2"))
4066 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
4075 (url "https://github.com/nboley/idr.git")
4077 (file-name (git-file-name name version))
4080 "04j876h6z444v2q79drxx283d3k5snd72kj895wbalnl42206x9g"))
4081 ;; Delete generated C code.
4083 '(begin (delete-file "idr/inv_cdf.c") #t))))
4084 (build-system python-build-system)
4085 ;; There is only one test ("test_inv_cdf.py") and it tests features that
4086 ;; are no longer part of this package. It also asserts False, which
4087 ;; causes the tests to always fail.
4088 (arguments `(#:tests? #f))
4090 `(("python-scipy" ,python-scipy)
4091 ("python-sympy" ,python-sympy)
4092 ("python-numpy" ,python-numpy)
4093 ("python-matplotlib" ,python-matplotlib)))
4095 `(("python-cython" ,python-cython)))
4096 (home-page "https://github.com/nboley/idr")
4097 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
4099 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
4100 to measure the reproducibility of findings identified from replicate
4101 experiments and provide highly stable thresholds based on reproducibility.")
4102 (license license:gpl2+)))
4104 (define-public jellyfish
4110 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
4111 "releases/download/v" version
4112 "/jellyfish-" version ".tar.gz"))
4115 "1k4pc3fvv6w1km2yph4m5sd78fbxp21d6xyzgmy0gjihzc6mb249"))))
4116 (build-system gnu-build-system)
4117 (outputs '("out" ;for library
4118 "ruby" ;for Ruby bindings
4119 "python")) ;for Python bindings
4122 (list (string-append "--enable-ruby-binding="
4123 (assoc-ref %outputs "ruby"))
4124 (string-append "--enable-python-binding="
4125 (assoc-ref %outputs "python")))
4127 (modify-phases %standard-phases
4128 (add-before 'check 'set-SHELL-variable
4130 ;; generator_manager.hpp either uses /bin/sh or $SHELL
4132 (setenv "SHELL" (which "bash"))
4138 ("python" ,python-2)
4139 ("pkg-config" ,pkg-config)))
4141 `(("htslib" ,htslib)))
4142 (synopsis "Tool for fast counting of k-mers in DNA")
4144 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
4145 DNA. A k-mer is a substring of length k, and counting the occurrences of all
4146 such substrings is a central step in many analyses of DNA sequence. Jellyfish
4147 is a command-line program that reads FASTA and multi-FASTA files containing
4148 DNA sequences. It outputs its k-mer counts in a binary format, which can be
4149 translated into a human-readable text format using the @code{jellyfish dump}
4150 command, or queried for specific k-mers with @code{jellyfish query}.")
4151 (home-page "http://www.genome.umd.edu/jellyfish.html")
4152 ;; JELLYFISH seems to be 64-bit only.
4153 (supported-systems '("x86_64-linux" "aarch64-linux" "mips64el-linux"))
4154 ;; The combined work is published under the GPLv3 or later. Individual
4155 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
4156 (license (list license:gpl3+ license:expat))))
4158 (define-public khmer
4166 (url "https://github.com/dib-lab/khmer.git")
4167 (commit (string-append "v" version))))
4168 (file-name (git-file-name name version))
4171 "02x38d9jw2r58y8dmnj4hffy9wxv1yc1jwbvdbhby9dxndv94r9m"))
4172 (patches (search-patches "khmer-use-libraries.patch"))
4173 (modules '((guix build utils)))
4176 ;; Delete bundled libraries. We do not replace the bundled seqan
4177 ;; as it is a modified subset of the old version 1.4.1.
4179 ;; We do not replace the bundled MurmurHash as the canonical
4180 ;; repository for this code 'SMHasher' is unsuitable for providing
4182 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
4183 (delete-file-recursively "third-party/zlib")
4184 (delete-file-recursively "third-party/bzip2")
4186 (build-system python-build-system)
4189 (modify-phases %standard-phases
4190 (add-after 'unpack 'set-cc
4191 (lambda _ (setenv "CC" "gcc") #t))
4192 ;; FIXME: This fails with "permission denied".
4193 (delete 'reset-gzip-timestamps))))
4195 `(("python-cython" ,python-cython)
4196 ("python-pytest" ,python-pytest)
4197 ("python-pytest-runner" ,python-pytest-runner)))
4201 ("python-screed" ,python-screed)
4202 ("python-bz2file" ,python-bz2file)))
4203 (home-page "https://khmer.readthedocs.org/")
4204 (synopsis "K-mer counting, filtering and graph traversal library")
4205 (description "The khmer software is a set of command-line tools for
4206 working with DNA shotgun sequencing data from genomes, transcriptomes,
4207 metagenomes and single cells. Khmer can make de novo assemblies faster, and
4208 sometimes better. Khmer can also identify and fix problems with shotgun
4210 ;; When building on i686, armhf and mips64el, we get the following error:
4211 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
4212 (supported-systems '("x86_64-linux" "aarch64-linux"))
4213 (license license:bsd-3)))
4215 (define-public kaiju
4222 (url "https://github.com/bioinformatics-centre/kaiju")
4223 (commit (string-append "v" version))))
4224 (file-name (git-file-name name version))
4227 "119pzi0ddzv9mjg4wwa6han0cwr3k3ssn7kirvsjfcq05mi5ka0x"))))
4228 (build-system gnu-build-system)
4230 `(#:tests? #f ; There are no tests.
4232 (modify-phases %standard-phases
4234 (add-before 'build 'move-to-src-dir
4235 (lambda _ (chdir "src") #t))
4237 (lambda* (#:key inputs outputs #:allow-other-keys)
4238 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
4241 (copy-recursively "bin" bin))
4246 (home-page "http://kaiju.binf.ku.dk/")
4247 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
4248 (description "Kaiju is a program for sensitive taxonomic classification
4249 of high-throughput sequencing reads from metagenomic whole genome sequencing
4251 (license license:gpl3+)))
4256 (version "2.1.1.20160309")
4259 (uri (pypi-uri "MACS2" version))
4262 "09ixspd1vcqmz1c81ih70xs4m7qml2iy5vyx1y74zww3iy1vl210"))))
4263 (build-system python-build-system)
4265 `(#:python ,python-2 ; only compatible with Python 2.7
4266 #:tests? #f)) ; no test target
4268 `(("python-numpy" ,python2-numpy)))
4269 (home-page "https://github.com/taoliu/MACS/")
4270 (synopsis "Model based analysis for ChIP-Seq data")
4272 "MACS is an implementation of a ChIP-Seq analysis algorithm for
4273 identifying transcript factor binding sites named Model-based Analysis of
4274 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
4275 the significance of enriched ChIP regions and it improves the spatial
4276 resolution of binding sites through combining the information of both
4277 sequencing tag position and orientation.")
4278 (license license:bsd-3)))
4280 (define-public mafft
4287 "https://mafft.cbrc.jp/alignment/software/mafft-" version
4288 "-without-extensions-src.tgz"))
4289 (file-name (string-append name "-" version ".tgz"))
4292 "0bacjkxfg944p5khhyh5rd4y7wkjc9qk4v2jjj442sqlq0f8ar7b"))))
4293 (build-system gnu-build-system)
4295 `(#:tests? #f ; no automated tests, though there are tests in the read me
4296 #:make-flags (let ((out (assoc-ref %outputs "out")))
4297 (list (string-append "PREFIX=" out)
4298 (string-append "BINDIR="
4299 (string-append out "/bin"))))
4301 (modify-phases %standard-phases
4302 (add-after 'unpack 'enter-dir
4303 (lambda _ (chdir "core") #t))
4304 (add-after 'enter-dir 'patch-makefile
4306 ;; on advice from the MAFFT authors, there is no need to
4307 ;; distribute mafft-profile, mafft-distance, or
4308 ;; mafft-homologs.rb as they are too "specialised".
4309 (substitute* "Makefile"
4310 ;; remove mafft-homologs.rb from SCRIPTS
4311 (("^SCRIPTS = mafft mafft-homologs.rb")
4313 ;; remove mafft-homologs from MANPAGES
4314 (("^MANPAGES = mafft.1 mafft-homologs.1")
4315 "MANPAGES = mafft.1")
4316 ;; remove mafft-distance from PROGS
4317 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
4318 "PROGS = dvtditr dndfast7 dndblast sextet5")
4319 ;; remove mafft-profile from PROGS
4320 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
4321 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
4322 (("^rm -f mafft-profile mafft-profile.exe") "#")
4323 (("^rm -f mafft-distance mafft-distance.exe") ")#")
4324 ;; do not install MAN pages in libexec folder
4325 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
4326 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
4328 (add-after 'enter-dir 'patch-paths
4329 (lambda* (#:key inputs #:allow-other-keys)
4330 (substitute* '("pairash.c"
4332 (("perl") (which "perl"))
4333 (("([\"`| ])awk" _ prefix)
4334 (string-append prefix (which "awk")))
4335 (("grep") (which "grep")))
4338 (add-after 'install 'wrap-programs
4339 (lambda* (#:key outputs #:allow-other-keys)
4340 (let* ((out (assoc-ref outputs "out"))
4341 (bin (string-append out "/bin"))
4342 (path (string-append
4343 (assoc-ref %build-inputs "coreutils") "/bin:")))
4344 (for-each (lambda (file)
4346 `("PATH" ":" prefix (,path))))
4354 ("coreutils" ,coreutils)))
4355 (home-page "http://mafft.cbrc.jp/alignment/software/")
4356 (synopsis "Multiple sequence alignment program")
4358 "MAFFT offers a range of multiple alignment methods for nucleotide and
4359 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
4360 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
4362 (license (license:non-copyleft
4363 "http://mafft.cbrc.jp/alignment/software/license.txt"
4364 "BSD-3 with different formatting"))))
4373 (url "https://github.com/marbl/mash.git")
4374 (commit (string-append "v" version))))
4375 (file-name (git-file-name name version))
4378 "049hwcc059p2fd9vwndn63laifvvsi0wmv84i6y1fr79k15dxwy6"))
4379 (modules '((guix build utils)))
4382 ;; Delete bundled kseq.
4383 ;; TODO: Also delete bundled murmurhash and open bloom filter.
4384 (delete-file "src/mash/kseq.h")
4386 (build-system gnu-build-system)
4388 `(#:tests? #f ; No tests.
4391 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
4392 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
4393 #:make-flags (list "CC=gcc")
4395 (modify-phases %standard-phases
4396 (add-after 'unpack 'fix-includes
4398 (substitute* '("src/mash/Sketch.cpp"
4399 "src/mash/CommandFind.cpp"
4400 "src/mash/CommandScreen.cpp")
4401 (("^#include \"kseq\\.h\"")
4402 "#include \"htslib/kseq.h\""))
4404 (add-after 'fix-includes 'use-c++14
4406 ;; capnproto 0.7 requires c++14 to build
4407 (substitute* "configure.ac"
4408 (("c\\+\\+11") "c++14"))
4409 (substitute* "Makefile.in"
4410 (("c\\+\\+11") "c++14"))
4413 `(("autoconf" ,autoconf)
4414 ;; Capnproto and htslib are statically embedded in the final
4415 ;; application. Therefore we also list their licenses, below.
4416 ("capnproto" ,capnproto)
4417 ("htslib" ,htslib)))
4421 (supported-systems '("x86_64-linux"))
4422 (home-page "https://mash.readthedocs.io")
4423 (synopsis "Fast genome and metagenome distance estimation using MinHash")
4424 (description "Mash is a fast sequence distance estimator that uses the
4425 MinHash algorithm and is designed to work with genomes and metagenomes in the
4426 form of assemblies or reads.")
4427 (license (list license:bsd-3 ; Mash
4428 license:expat ; HTSlib and capnproto
4429 license:public-domain ; MurmurHash 3
4430 license:cpl1.0)))) ; Open Bloom Filter
4432 (define-public metabat
4440 (url "https://bitbucket.org/berkeleylab/metabat.git")
4441 (commit (string-append "v" version))))
4442 (file-name (git-file-name name version))
4445 "0hyg2smw1nz69mfvjpk45xyyychmda92c80a0cv7baji84ri4iyn"))
4446 (patches (search-patches "metabat-fix-compilation.patch"))))
4447 (build-system scons-build-system)
4449 `(#:scons ,scons-python2
4451 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
4452 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
4453 #:tests? #f ;; Tests are run during the build phase.
4455 (modify-phases %standard-phases
4456 (add-after 'unpack 'fix-includes
4458 (substitute* "src/BamUtils.h"
4459 (("^#include \"bam/bam\\.h\"")
4460 "#include \"samtools/bam.h\"")
4461 (("^#include \"bam/sam\\.h\"")
4462 "#include \"samtools/sam.h\""))
4463 (substitute* "src/KseqReader.h"
4464 (("^#include \"bam/kseq\\.h\"")
4465 "#include \"htslib/kseq.h\""))
4467 (add-after 'unpack 'fix-scons
4468 (lambda* (#:key inputs #:allow-other-keys)
4469 (substitute* "SConstruct"
4470 (("^htslib_dir += 'samtools'")
4471 (string-append "htslib_dir = '"
4472 (assoc-ref inputs "htslib")
4474 (("^samtools_dir = 'samtools'")
4475 (string-append "samtools_dir = '"
4476 (assoc-ref inputs "samtools")
4478 (("^findStaticOrShared\\('bam', hts_lib")
4479 (string-append "findStaticOrShared('bam', '"
4480 (assoc-ref inputs "samtools")
4482 ;; Do not distribute README.
4483 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
4488 ("samtools" ,samtools)
4491 (home-page "https://bitbucket.org/berkeleylab/metabat")
4493 "Reconstruction of single genomes from complex microbial communities")
4495 "Grouping large genomic fragments assembled from shotgun metagenomic
4496 sequences to deconvolute complex microbial communities, or metagenome binning,
4497 enables the study of individual organisms and their interactions. MetaBAT is
4498 an automated metagenome binning software, which integrates empirical
4499 probabilistic distances of genome abundance and tetranucleotide frequency.")
4500 ;; The source code contains inline assembly.
4501 (supported-systems '("x86_64-linux" "i686-linux"))
4502 (license (license:non-copyleft "file://license.txt"
4503 "See license.txt in the distribution."))))
4505 (define-public minced
4512 (url "https://github.com/ctSkennerton/minced.git")
4514 (file-name (git-file-name name version))
4517 "1f5h9him0gd355cnx7p6pnxpknhckd4g0v62mg8zyhfbx9as25fv"))))
4518 (build-system gnu-build-system)
4520 `(#:test-target "test"
4522 (modify-phases %standard-phases
4524 (add-before 'check 'fix-test
4526 ;; Fix test for latest version.
4527 (substitute* "t/Aquifex_aeolicus_VF5.expected"
4528 (("minced:0.1.6") "minced:0.2.0"))
4530 (replace 'install ; No install target.
4531 (lambda* (#:key inputs outputs #:allow-other-keys)
4532 (let* ((out (assoc-ref outputs "out"))
4533 (bin (string-append out "/bin"))
4534 (wrapper (string-append bin "/minced")))
4535 ;; Minced comes with a wrapper script that tries to figure out where
4536 ;; it is located before running the JAR. Since these paths are known
4537 ;; to us, we build our own wrapper to avoid coreutils dependency.
4538 (install-file "minced.jar" bin)
4539 (with-output-to-file wrapper
4543 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
4544 (assoc-ref inputs "jre") "/bin/java -jar "
4545 bin "/minced.jar \"$@\"\n"))))
4546 (chmod wrapper #o555))
4549 `(("jdk" ,icedtea "jdk")))
4552 ("jre" ,icedtea "out")))
4553 (home-page "https://github.com/ctSkennerton/minced")
4554 (synopsis "Mining CRISPRs in Environmental Datasets")
4556 "MinCED is a program to find Clustered Regularly Interspaced Short
4557 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
4558 unassembled metagenomic reads, but is mainly designed for full genomes and
4559 assembled metagenomic sequence.")
4560 (license license:gpl3+)))
4568 (uri (pypi-uri "misopy" version))
4571 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
4572 (modules '((guix build utils)))
4574 (substitute* "setup.py"
4575 ;; Use setuptools, or else the executables are not
4577 (("distutils.core") "setuptools")
4578 ;; use "gcc" instead of "cc" for compilation
4580 "cc.set_executables(
4584 linker_so='gcc -shared'); defines"))
4586 (build-system python-build-system)
4588 `(#:python ,python-2 ; only Python 2 is supported
4589 #:tests? #f)) ; no "test" target
4591 `(("samtools" ,samtools)
4592 ("python-numpy" ,python2-numpy)
4593 ("python-pysam" ,python2-pysam)
4594 ("python-scipy" ,python2-scipy)
4595 ("python-matplotlib" ,python2-matplotlib)))
4597 `(("python-mock" ,python2-mock) ;for tests
4598 ("python-pytz" ,python2-pytz))) ;for tests
4599 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
4600 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
4602 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
4603 the expression level of alternatively spliced genes from RNA-Seq data, and
4604 identifies differentially regulated isoforms or exons across samples. By
4605 modeling the generative process by which reads are produced from isoforms in
4606 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
4607 that a read originated from a particular isoform.")
4608 (license license:gpl2)))
4610 (define-public muscle
4613 (version "3.8.1551")
4615 (method url-fetch/tarbomb)
4617 "http://www.drive5.com/muscle/muscle_src_"
4621 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
4622 (build-system gnu-build-system)
4624 `(#:make-flags (list "LDLIBS = -lm")
4626 (modify-phases %standard-phases
4629 ;; There are no tests, so just test if it runs.
4630 (lambda _ (invoke "./muscle" "-version") #t))
4632 (lambda* (#:key outputs #:allow-other-keys)
4633 (let* ((out (assoc-ref outputs "out"))
4634 (bin (string-append out "/bin")))
4635 (install-file "muscle" bin)
4637 (home-page "http://www.drive5.com/muscle")
4638 (synopsis "Multiple sequence alignment program")
4640 "MUSCLE aims to be a fast and accurate multiple sequence alignment
4641 program for nucleotide and protein sequences.")
4642 ;; License information found in 'muscle -h' and usage.cpp.
4643 (license license:public-domain)))
4645 (define-public newick-utils
4646 ;; There are no recent releases so we package from git.
4647 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
4649 (name "newick-utils")
4650 (version (string-append "1.6-1." (string-take commit 8)))
4654 (url "https://github.com/tjunier/newick_utils.git")
4656 (file-name (string-append name "-" version "-checkout"))
4659 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4660 (build-system gnu-build-system)
4662 ;; XXX: TODO: Enable Lua and Guile bindings.
4663 ;; https://github.com/tjunier/newick_utils/issues/13
4664 `(("libxml2" ,libxml2)
4668 `(("autoconf" ,autoconf)
4669 ("automake" ,automake)
4670 ("libtool" ,libtool)))
4671 (synopsis "Programs for working with newick format phylogenetic trees")
4673 "Newick-utils is a suite of utilities for processing phylogenetic trees
4674 in Newick format. Functions include re-rooting, extracting subtrees,
4675 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4676 (home-page "https://github.com/tjunier/newick_utils")
4677 (license license:bsd-3))))
4686 "https://github.com/wwood/OrfM/releases/download/v"
4687 version "/orfm-" version ".tar.gz"))
4690 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4691 (build-system gnu-build-system)
4692 (inputs `(("zlib" ,zlib)))
4694 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4695 ("ruby-rspec" ,ruby-rspec)
4697 (synopsis "Simple and not slow open reading frame (ORF) caller")
4699 "An ORF caller finds stretches of DNA that, when translated, are not
4700 interrupted by stop codons. OrfM finds and prints these ORFs.")
4701 (home-page "https://github.com/wwood/OrfM")
4702 (license license:lgpl3+)))
4704 (define-public python2-pbcore
4706 (name "python2-pbcore")
4710 (uri (pypi-uri "pbcore" version))
4713 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4714 (build-system python-build-system)
4715 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
4717 `(("python-cython" ,python2-cython)
4718 ("python-numpy" ,python2-numpy)
4719 ("python-pysam" ,python2-pysam)
4720 ("python-h5py" ,python2-h5py)))
4722 `(("python-nose" ,python2-nose)
4723 ("python-sphinx" ,python2-sphinx)
4724 ("python-pyxb" ,python2-pyxb)))
4725 (home-page "http://pacificbiosciences.github.io/pbcore/")
4726 (synopsis "Library for reading and writing PacBio data files")
4728 "The pbcore package provides Python APIs for interacting with PacBio data
4729 files and writing bioinformatics applications.")
4730 (license license:bsd-3)))
4732 (define-public python2-warpedlmm
4734 (name "python2-warpedlmm")
4739 (uri (pypi-uri "WarpedLMM" version ".zip"))
4742 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4743 (build-system python-build-system)
4745 `(#:python ,python-2)) ; requires Python 2.7
4747 `(("python-scipy" ,python2-scipy)
4748 ("python-numpy" ,python2-numpy)
4749 ("python-matplotlib" ,python2-matplotlib)
4750 ("python-fastlmm" ,python2-fastlmm)
4751 ("python-pandas" ,python2-pandas)
4752 ("python-pysnptools" ,python2-pysnptools)))
4754 `(("python-mock" ,python2-mock)
4755 ("python-nose" ,python2-nose)
4757 (home-page "https://github.com/PMBio/warpedLMM")
4758 (synopsis "Implementation of warped linear mixed models")
4760 "WarpedLMM is a Python implementation of the warped linear mixed model,
4761 which automatically learns an optimal warping function (or transformation) for
4762 the phenotype as it models the data.")
4763 (license license:asl2.0)))
4765 (define-public pbtranscript-tofu
4766 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
4768 (name "pbtranscript-tofu")
4769 (version (string-append "2.2.3." (string-take commit 7)))
4773 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
4775 (file-name (string-append name "-" version "-checkout"))
4778 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
4779 (modules '((guix build utils)))
4782 ;; remove bundled Cython sources
4783 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
4785 (build-system python-build-system)
4787 `(#:python ,python-2
4788 ;; FIXME: Tests fail with "No such file or directory:
4789 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
4792 (modify-phases %standard-phases
4793 (add-after 'unpack 'enter-directory
4795 (chdir "pbtranscript-tofu/pbtranscript/")
4797 ;; With setuptools version 18.0 and later this setup.py hack causes
4798 ;; a build error, so we disable it.
4799 (add-after 'enter-directory 'patch-setuppy
4801 (substitute* "setup.py"
4802 (("if 'setuptools.extension' in sys.modules:")
4806 `(("python-numpy" ,python2-numpy)
4807 ("python-bx-python" ,python2-bx-python)
4808 ("python-networkx" ,python2-networkx)
4809 ("python-scipy" ,python2-scipy)
4810 ("python-pbcore" ,python2-pbcore)
4811 ("python-h5py" ,python2-h5py)))
4813 `(("python-cython" ,python2-cython)
4814 ("python-nose" ,python2-nose)))
4815 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4816 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4818 "pbtranscript-tofu contains scripts to analyze transcriptome data
4819 generated using the PacBio Iso-Seq protocol.")
4820 (license license:bsd-3))))
4822 (define-public prank
4829 "http://wasabiapp.org/download/prank/prank.source."
4833 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
4834 (build-system gnu-build-system)
4837 (modify-phases %standard-phases
4838 (add-after 'unpack 'enter-src-dir
4842 (add-after 'unpack 'remove-m64-flag
4843 ;; Prank will build with the correct 'bit-ness' without this flag
4844 ;; and this allows building on 32-bit machines.
4845 (lambda _ (substitute* "src/Makefile"
4850 (lambda* (#:key outputs #:allow-other-keys)
4851 (let* ((out (assoc-ref outputs "out"))
4852 (bin (string-append out "/bin"))
4853 (man (string-append out "/share/man/man1"))
4854 (path (string-append
4855 (assoc-ref %build-inputs "mafft") "/bin:"
4856 (assoc-ref %build-inputs "exonerate") "/bin:"
4857 (assoc-ref %build-inputs "bppsuite") "/bin")))
4858 (install-file "prank" bin)
4859 (wrap-program (string-append bin "/prank")
4860 `("PATH" ":" prefix (,path)))
4861 (install-file "prank.1" man))
4865 ("exonerate" ,exonerate)
4866 ("bppsuite" ,bppsuite)))
4867 (home-page "http://wasabiapp.org/software/prank/")
4868 (synopsis "Probabilistic multiple sequence alignment program")
4870 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4871 codon and amino-acid sequences. It is based on a novel algorithm that treats
4872 insertions correctly and avoids over-estimation of the number of deletion
4873 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4874 in phylogenetics and correctly takes into account the evolutionary distances
4875 between sequences. Lastly, PRANK allows for defining a potential structure
4876 for sequences to be aligned and then, simultaneously with the alignment,
4877 predicts the locations of structural units in the sequences.")
4878 (license license:gpl2+)))
4880 (define-public proteinortho
4882 (name "proteinortho")
4889 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4890 version "_src.tar.gz"))
4893 "1wl0dawpssqwfjvr651r4wlww8hhjin8nba6xh71ks7sbypx886j"))))
4894 (build-system gnu-build-system)
4896 `(#:test-target "test"
4898 (modify-phases %standard-phases
4900 ;; There is no configure script, so we modify the Makefile directly.
4901 (lambda* (#:key outputs #:allow-other-keys)
4902 (substitute* "Makefile"
4905 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4907 (add-before 'install 'make-install-directory
4908 ;; The install directory is not created during 'make install'.
4909 (lambda* (#:key outputs #:allow-other-keys)
4910 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4912 (add-after 'install 'wrap-programs
4913 (lambda* (#:key inputs outputs #:allow-other-keys)
4914 (let* ((path (getenv "PATH"))
4915 (out (assoc-ref outputs "out"))
4916 (binary (string-append out "/bin/proteinortho5.pl")))
4917 (wrap-program binary `("PATH" ":" prefix (,path))))
4921 ("python" ,python-2)
4922 ("blast+" ,blast+)))
4923 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4924 (synopsis "Detect orthologous genes across species")
4926 "Proteinortho is a tool to detect orthologous genes across different
4927 species. For doing so, it compares similarities of given gene sequences and
4928 clusters them to find significant groups. The algorithm was designed to handle
4929 large-scale data and can be applied to hundreds of species at once.")
4930 (license license:gpl2+)))
4932 (define-public pyicoteo
4940 (url "https://bitbucket.org/regulatorygenomicsupf/pyicoteo.git")
4941 (commit (string-append "v" version))))
4942 (file-name (git-file-name name version))
4945 "0hz5g8d25lbjy1wpscr490l0lmyvaix893hhax4fxnh1h9w34w8p"))))
4946 (build-system python-build-system)
4948 `(#:python ,python-2 ; does not work with Python 3
4949 #:tests? #f)) ; there are no tests
4951 `(("python2-matplotlib" ,python2-matplotlib)))
4952 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4953 (synopsis "Analyze high-throughput genetic sequencing data")
4955 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4956 sequencing data. It works with genomic coordinates. There are currently six
4957 different command-line tools:
4960 @item pyicoregion: for generating exploratory regions automatically;
4961 @item pyicoenrich: for differential enrichment between two conditions;
4962 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4963 @item pyicos: for genomic coordinates manipulation;
4964 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4965 @item pyicount: to count how many reads from N experiment files overlap in a
4967 @item pyicotrocol: to combine operations from pyicoteo.
4969 (license license:gpl3+)))
4971 (define-public prodigal
4978 (url "https://github.com/hyattpd/Prodigal.git")
4979 (commit (string-append "v" version))))
4980 (file-name (git-file-name name version))
4983 "1fs1hqk83qjbjhrvhw6ni75zakx5ki1ayy3v6wwkn3xvahc9hi5s"))))
4984 (build-system gnu-build-system)
4986 `(#:tests? #f ;no check target
4987 #:make-flags (list (string-append "INSTALLDIR="
4988 (assoc-ref %outputs "out")
4991 (modify-phases %standard-phases
4992 (delete 'configure))))
4993 (home-page "http://prodigal.ornl.gov")
4994 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
4996 "Prodigal runs smoothly on finished genomes, draft genomes, and
4997 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
4998 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
4999 partial genes, and identifies translation initiation sites.")
5000 (license license:gpl3+)))
5002 (define-public roary
5010 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
5014 "0qxrds9wx7cfhlkihrp6697kx0flhhxymap9fwan0b3rbdhcnmff"))))
5015 (build-system perl-build-system)
5018 (modify-phases %standard-phases
5023 ;; The tests are not run by default, so we run each test file
5025 (setenv "PATH" (string-append (getcwd) "/bin" ":"
5027 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
5028 (getenv "PERL5LIB")))
5029 (for-each (lambda (file)
5030 (display file)(display "\n")
5031 (invoke "perl" file))
5032 (find-files "t" ".*\\.t$"))
5035 ;; There is no 'install' target in the Makefile.
5036 (lambda* (#:key outputs #:allow-other-keys)
5037 (let* ((out (assoc-ref outputs "out"))
5038 (bin (string-append out "/bin"))
5039 (perl (string-append out "/lib/perl5/site_perl"))
5040 (roary-plots "contrib/roary_plots"))
5043 (copy-recursively "bin" bin)
5044 (copy-recursively "lib" perl)
5046 (add-after 'install 'wrap-programs
5047 (lambda* (#:key inputs outputs #:allow-other-keys)
5048 (let* ((out (assoc-ref outputs "out"))
5049 (perl5lib (getenv "PERL5LIB"))
5050 (path (getenv "PATH")))
5051 (for-each (lambda (prog)
5052 (let ((binary (string-append out "/" prog)))
5053 (wrap-program binary
5054 `("PERL5LIB" ":" prefix
5055 (,(string-append perl5lib ":" out
5056 "/lib/perl5/site_perl"))))
5057 (wrap-program binary
5059 (,(string-append path ":" out "/bin"))))))
5060 (find-files "bin" ".*[^R]$"))
5062 (string-append out "/bin/roary-create_pan_genome_plots.R"))
5063 (r-site-lib (getenv "R_LIBS_SITE"))
5065 (string-append (assoc-ref inputs "coreutils") "/bin")))
5067 `("R_LIBS_SITE" ":" prefix
5068 (,(string-append r-site-lib ":" out "/site-library/"))))
5071 (,(string-append coreutils-path ":" out "/bin"))))))
5074 `(("perl-env-path" ,perl-env-path)
5075 ("perl-test-files" ,perl-test-files)
5076 ("perl-test-most" ,perl-test-most)
5077 ("perl-test-output" ,perl-test-output)))
5079 `(("perl-array-utils" ,perl-array-utils)
5080 ("bioperl" ,bioperl-minimal)
5081 ("perl-digest-md5-file" ,perl-digest-md5-file)
5082 ("perl-exception-class" ,perl-exception-class)
5083 ("perl-file-find-rule" ,perl-file-find-rule)
5084 ("perl-file-grep" ,perl-file-grep)
5085 ("perl-file-slurper" ,perl-file-slurper)
5086 ("perl-file-which" ,perl-file-which)
5087 ("perl-graph" ,perl-graph)
5088 ("perl-graph-readwrite" ,perl-graph-readwrite)
5089 ("perl-log-log4perl" ,perl-log-log4perl)
5090 ("perl-moose" ,perl-moose)
5091 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
5092 ("perl-text-csv" ,perl-text-csv)
5093 ("bedtools" ,bedtools)
5097 ("parallel" ,parallel)
5100 ("fasttree" ,fasttree)
5104 ("r-minimal" ,r-minimal)
5105 ("r-ggplot2" ,r-ggplot2)
5106 ("coreutils" ,coreutils)))
5107 (home-page "http://sanger-pathogens.github.io/Roary")
5108 (synopsis "High speed stand-alone pan genome pipeline")
5110 "Roary is a high speed stand alone pan genome pipeline, which takes
5111 annotated assemblies in GFF3 format (produced by the Prokka program) and
5112 calculates the pan genome. Using a standard desktop PC, it can analyse
5113 datasets with thousands of samples, without compromising the quality of the
5114 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
5115 single processor. Roary is not intended for metagenomics or for comparing
5116 extremely diverse sets of genomes.")
5117 (license license:gpl3)))
5119 (define-public raxml
5127 (url "https://github.com/stamatak/standard-RAxML.git")
5128 (commit (string-append "v" version))))
5129 (file-name (git-file-name name version))
5132 "1jqjzhch0rips0vp04prvb8vmc20c5pdmsqn8knadcf91yy859fh"))))
5133 (build-system gnu-build-system)
5135 `(#:tests? #f ; There are no tests.
5136 ;; Use 'standard' Makefile rather than SSE or AVX ones.
5137 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
5139 (modify-phases %standard-phases
5142 (lambda* (#:key outputs #:allow-other-keys)
5143 (let* ((out (assoc-ref outputs "out"))
5144 (bin (string-append out "/bin"))
5145 (executable "raxmlHPC-HYBRID"))
5146 (install-file executable bin)
5147 (symlink (string-append bin "/" executable) "raxml"))
5150 `(("openmpi" ,openmpi)))
5151 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
5152 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
5154 "RAxML is a tool for phylogenetic analysis and post-analysis of large
5156 ;; The source includes x86 specific code
5157 (supported-systems '("x86_64-linux" "i686-linux"))
5158 (license license:gpl2+)))
5168 (url "https://github.com/deweylab/RSEM.git")
5169 (commit (string-append "v" version))))
5171 (base32 "1jlq11d1p8qp64w75yj8cnbbd1a93viq10pzsbwal7vdn8fg13j1"))
5172 (file-name (git-file-name name version))
5173 (modules '((guix build utils)))
5176 ;; remove bundled copy of boost and samtools
5177 (delete-file-recursively "boost")
5178 (delete-file-recursively "samtools-1.3")
5180 (build-system gnu-build-system)
5182 `(#:tests? #f ;no "check" target
5184 (list (string-append "BOOST="
5185 (assoc-ref %build-inputs "boost")
5187 (string-append "SAMHEADERS="
5188 (assoc-ref %build-inputs "htslib")
5189 "/include/htslib/sam.h")
5190 (string-append "SAMLIBS="
5191 (assoc-ref %build-inputs "htslib")
5194 (modify-phases %standard-phases
5195 ;; No "configure" script.
5196 ;; Do not build bundled samtools library.
5199 (substitute* "Makefile"
5200 (("^all : \\$\\(PROGRAMS\\).*") "all: $(PROGRAMS)\n")
5201 (("^\\$\\(SAMLIBS\\).*") ""))
5204 (lambda* (#:key outputs #:allow-other-keys)
5205 (let* ((out (string-append (assoc-ref outputs "out")))
5206 (bin (string-append out "/bin/"))
5207 (perl (string-append out "/lib/perl5/site_perl")))
5210 (for-each (lambda (file)
5211 (install-file file bin))
5212 (find-files "." "rsem-.*"))
5213 (install-file "rsem_perl_utils.pm" perl))
5215 (add-after 'install 'wrap-program
5216 (lambda* (#:key outputs #:allow-other-keys)
5217 (let ((out (assoc-ref outputs "out")))
5218 (for-each (lambda (prog)
5219 (wrap-program (string-append out "/bin/" prog)
5220 `("PERL5LIB" ":" prefix
5221 (,(string-append out "/lib/perl5/site_perl")))))
5222 '("rsem-calculate-expression"
5224 "rsem-generate-data-matrix"
5225 "rsem-generate-ngvector"
5226 "rsem-plot-transcript-wiggles"
5227 "rsem-prepare-reference"
5229 "rsem-run-prsem-testing-procedure")))
5233 ("r-minimal" ,r-minimal)
5235 ("htslib" ,htslib-1.3)
5237 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
5238 (synopsis "Estimate gene expression levels from RNA-Seq data")
5240 "RSEM is a software package for estimating gene and isoform expression
5241 levels from RNA-Seq data. The RSEM package provides a user-friendly
5242 interface, supports threads for parallel computation of the EM algorithm,
5243 single-end and paired-end read data, quality scores, variable-length reads and
5244 RSPD estimation. In addition, it provides posterior mean and 95% credibility
5245 interval estimates for expression levels. For visualization, it can generate
5246 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
5247 (license license:gpl3+)))
5249 (define-public rseqc
5257 (string-append "mirror://sourceforge/rseqc/"
5258 "RSeQC-" version ".tar.gz"))
5260 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
5261 (modules '((guix build utils)))
5264 ;; remove bundled copy of pysam
5265 (delete-file-recursively "lib/pysam")
5266 (substitute* "setup.py"
5267 ;; remove dependency on outdated "distribute" module
5268 (("^from distribute_setup import use_setuptools") "")
5269 (("^use_setuptools\\(\\)") "")
5270 ;; do not use bundled copy of pysam
5271 (("^have_pysam = False") "have_pysam = True"))
5273 (build-system python-build-system)
5274 (arguments `(#:python ,python-2))
5276 `(("python-cython" ,python2-cython)
5277 ("python-pysam" ,python2-pysam)
5278 ("python-numpy" ,python2-numpy)
5281 `(("python-nose" ,python2-nose)))
5282 (home-page "http://rseqc.sourceforge.net/")
5283 (synopsis "RNA-seq quality control package")
5285 "RSeQC provides a number of modules that can comprehensively evaluate
5286 high throughput sequence data, especially RNA-seq data. Some basic modules
5287 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
5288 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
5289 distribution, coverage uniformity, strand specificity, etc.")
5290 (license license:gpl3+)))
5293 ;; There are no release tarballs. According to the installation
5294 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
5295 ;; stable release is identified by this changeset ID.
5296 (let ((changeset "2329130")
5300 (version (string-append "0-" revision "." changeset))
5304 (url "https://bitbucket.org/libsleipnir/sleipnir")
5305 (changeset changeset)))
5306 (file-name (string-append name "-" version "-checkout"))
5309 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
5310 (build-system gnu-build-system)
5312 `(#:modules ((srfi srfi-1)
5313 (guix build gnu-build-system)
5316 (let ((dirs '("SeekMiner"
5322 (modify-phases %standard-phases
5325 (substitute* "gen_tools_am"
5326 (("/usr/bin/env.*") (which "perl")))
5327 (invoke "bash" "gen_auto")
5329 (add-after 'build 'build-additional-tools
5330 (lambda* (#:key make-flags #:allow-other-keys)
5331 (for-each (lambda (dir)
5332 (with-directory-excursion (string-append "tools/" dir)
5333 (apply invoke "make" make-flags)))
5336 (add-after 'install 'install-additional-tools
5337 (lambda* (#:key make-flags #:allow-other-keys)
5338 (for-each (lambda (dir)
5339 (with-directory-excursion (string-append "tools/" dir)
5340 (apply invoke `("make" ,@make-flags "install"))))
5347 ("readline" ,readline)
5348 ("gengetopt" ,gengetopt)
5349 ("log4cpp" ,log4cpp)))
5351 `(("autoconf" ,autoconf)
5352 ("automake" ,automake)
5354 (home-page "http://seek.princeton.edu")
5355 (synopsis "Gene co-expression search engine")
5357 "SEEK is a computational gene co-expression search engine. SEEK provides
5358 biologists with a way to navigate the massive human expression compendium that
5359 now contains thousands of expression datasets. SEEK returns a robust ranking
5360 of co-expressed genes in the biological area of interest defined by the user's
5361 query genes. It also prioritizes thousands of expression datasets according
5362 to the user's query of interest.")
5363 (license license:cc-by3.0))))
5365 (define-public samtools
5373 (string-append "mirror://sourceforge/samtools/samtools/"
5374 version "/samtools-" version ".tar.bz2"))
5377 "10ilqbmm7ri8z431sn90lvbjwizd0hhkf9rcqw8j823hf26nhgq8"))
5378 (modules '((guix build utils)))
5380 ;; Delete bundled htslib.
5381 (delete-file-recursively "htslib-1.9")
5383 (build-system gnu-build-system)
5385 `(#:modules ((ice-9 ftw)
5387 (guix build gnu-build-system)
5389 #:configure-flags (list "--with-ncurses")
5391 (modify-phases %standard-phases
5392 (add-after 'unpack 'patch-tests
5394 (substitute* "test/test.pl"
5395 ;; The test script calls out to /bin/bash
5396 (("/bin/bash") (which "bash")))
5398 (add-after 'install 'install-library
5399 (lambda* (#:key outputs #:allow-other-keys)
5400 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
5401 (install-file "libbam.a" lib)
5403 (add-after 'install 'install-headers
5404 (lambda* (#:key outputs #:allow-other-keys)
5405 (let ((include (string-append (assoc-ref outputs "out")
5406 "/include/samtools/")))
5407 (for-each (lambda (file)
5408 (install-file file include))
5409 (scandir "." (lambda (name) (string-match "\\.h$" name))))
5411 (native-inputs `(("pkg-config" ,pkg-config)))
5413 `(("htslib" ,htslib)
5414 ("ncurses" ,ncurses)
5418 (home-page "http://samtools.sourceforge.net")
5419 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
5421 "Samtools implements various utilities for post-processing nucleotide
5422 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
5423 variant calling (in conjunction with bcftools), and a simple alignment
5425 (license license:expat)))
5427 (define-public samtools-0.1
5428 ;; This is the most recent version of the 0.1 line of samtools. The input
5429 ;; and output formats differ greatly from that used and produced by samtools
5430 ;; 1.x and is still used in many bioinformatics pipelines.
5431 (package (inherit samtools)
5437 (string-append "mirror://sourceforge/samtools/samtools/"
5438 version "/samtools-" version ".tar.bz2"))
5440 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
5442 `(#:tests? #f ;no "check" target
5444 (list "LIBCURSES=-lncurses")
5445 ,@(substitute-keyword-arguments (package-arguments samtools)
5447 `(modify-phases ,phases
5449 (lambda* (#:key outputs #:allow-other-keys)
5450 (let ((bin (string-append
5451 (assoc-ref outputs "out") "/bin")))
5453 (install-file "samtools" bin)
5455 (delete 'patch-tests)
5456 (delete 'configure))))))))
5458 (define-public mosaik
5459 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
5464 ;; There are no release tarballs nor tags.
5467 (url "https://github.com/wanpinglee/MOSAIK.git")
5469 (file-name (string-append name "-" version))
5472 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
5473 (build-system gnu-build-system)
5475 `(#:tests? #f ; no tests
5476 #:make-flags (list "CC=gcc")
5478 (modify-phases %standard-phases
5480 (lambda _ (chdir "src") #t))
5482 (lambda* (#:key outputs #:allow-other-keys)
5483 (let ((bin (string-append (assoc-ref outputs "out")
5486 (copy-recursively "../bin" bin)
5490 ("zlib:static" ,zlib "static")
5492 (supported-systems '("x86_64-linux"))
5493 (home-page "https://github.com/wanpinglee/MOSAIK")
5494 (synopsis "Map nucleotide sequence reads to reference genomes")
5496 "MOSAIK is a program for mapping second and third-generation sequencing
5497 reads to a reference genome. MOSAIK can align reads generated by all the
5498 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
5499 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
5500 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
5501 ;; code released into the public domain:
5502 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
5503 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
5504 (license (list license:gpl2+ license:public-domain)))))
5506 (define-public ngs-sdk
5513 (url "https://github.com/ncbi/ngs.git")
5515 (file-name (git-file-name name version))
5518 "17c0v1nah3g3d2ib5bbi0vhma1ghd6vb9xycavqsh64lhp840rk3"))))
5519 (build-system gnu-build-system)
5521 `(#:parallel-build? #f ; not supported
5522 #:tests? #f ; no "check" target
5524 (modify-phases %standard-phases
5526 (lambda* (#:key outputs #:allow-other-keys)
5527 (let ((out (assoc-ref outputs "out")))
5528 ;; Allow 'konfigure.perl' to find 'package.prl'.
5530 (string-append ".:" (getenv "PERL5LIB")))
5532 ;; The 'configure' script doesn't recognize things like
5533 ;; '--enable-fast-install'.
5534 (invoke "./configure"
5535 (string-append "--build-prefix=" (getcwd) "/build")
5536 (string-append "--prefix=" out))
5538 (add-after 'unpack 'enter-dir
5539 (lambda _ (chdir "ngs-sdk") #t)))))
5540 (native-inputs `(("perl" ,perl)))
5541 ;; According to the test
5542 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
5543 ;; in ngs-sdk/setup/konfigure.perl
5544 (supported-systems '("i686-linux" "x86_64-linux"))
5545 (home-page "https://github.com/ncbi/ngs")
5546 (synopsis "API for accessing Next Generation Sequencing data")
5548 "NGS is a domain-specific API for accessing reads, alignments and pileups
5549 produced from Next Generation Sequencing. The API itself is independent from
5550 any particular back-end implementation, and supports use of multiple back-ends
5552 (license license:public-domain)))
5554 (define-public java-ngs
5555 (package (inherit ngs-sdk)
5558 `(,@(substitute-keyword-arguments
5559 `(#:modules ((guix build gnu-build-system)
5563 ,@(package-arguments ngs-sdk))
5565 `(modify-phases ,phases
5566 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5568 `(("jdk" ,icedtea "jdk")
5569 ("ngs-sdk" ,ngs-sdk)))
5570 (synopsis "Java bindings for NGS SDK")))
5572 (define-public ncbi-vdb
5579 (url "https://github.com/ncbi/ncbi-vdb.git")
5581 (file-name (git-file-name name version))
5584 "1l4ny67nxwv1lagk9wwjbrgm7ln7adci6dnpc7k1yaln6shj0qpm"))))
5585 (build-system gnu-build-system)
5587 `(#:parallel-build? #f ; not supported
5588 #:tests? #f ; no "check" target
5590 (modify-phases %standard-phases
5591 (add-after 'unpack 'make-files-writable
5592 (lambda _ (for-each make-file-writable (find-files "." ".*")) #t))
5593 (add-before 'configure 'set-perl-search-path
5595 ;; Work around "dotless @INC" build failure.
5597 (string-append (getcwd) "/setup:"
5598 (getenv "PERL5LIB")))
5601 (lambda* (#:key inputs outputs #:allow-other-keys)
5602 (let ((out (assoc-ref outputs "out")))
5603 ;; Override include path for libmagic
5604 (substitute* "setup/package.prl"
5605 (("name => 'magic', Include => '/usr/include'")
5606 (string-append "name=> 'magic', Include => '"
5607 (assoc-ref inputs "libmagic")
5610 ;; Install kdf5 library (needed by sra-tools)
5611 (substitute* "build/Makefile.install"
5612 (("LIBRARIES_TO_INSTALL =")
5613 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5615 (substitute* "build/Makefile.env"
5616 (("CFLAGS =" prefix)
5617 (string-append prefix "-msse2 ")))
5619 ;; Override search path for ngs-java
5620 (substitute* "setup/package.prl"
5621 (("/usr/local/ngs/ngs-java")
5622 (assoc-ref inputs "java-ngs")))
5624 ;; The 'configure' script doesn't recognize things like
5625 ;; '--enable-fast-install'.
5626 (invoke "./configure"
5627 (string-append "--build-prefix=" (getcwd) "/build")
5628 (string-append "--prefix=" (assoc-ref outputs "out"))
5629 (string-append "--debug")
5630 (string-append "--with-xml2-prefix="
5631 (assoc-ref inputs "libxml2"))
5632 (string-append "--with-ngs-sdk-prefix="
5633 (assoc-ref inputs "ngs-sdk"))
5634 (string-append "--with-hdf5-prefix="
5635 (assoc-ref inputs "hdf5")))
5637 (add-after 'install 'install-interfaces
5638 (lambda* (#:key outputs #:allow-other-keys)
5639 ;; Install interface libraries. On i686 the interface libraries
5640 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5641 ;; architecture name ("i386") instead of the target system prefix
5643 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5644 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5645 ,(system->linux-architecture
5646 (or (%current-target-system)
5649 (string-append (assoc-ref outputs "out")
5651 ;; Install interface headers
5652 (copy-recursively "interfaces"
5653 (string-append (assoc-ref outputs "out")
5656 ;; These files are needed by sra-tools.
5657 (add-after 'install 'install-configuration-files
5658 (lambda* (#:key outputs #:allow-other-keys)
5659 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5661 (install-file "libs/kfg/default.kfg" target)
5662 (install-file "libs/kfg/certs.kfg" target))
5665 `(("libxml2" ,libxml2)
5666 ("ngs-sdk" ,ngs-sdk)
5667 ("java-ngs" ,java-ngs)
5670 (native-inputs `(("perl" ,perl)))
5671 ;; NCBI-VDB requires SSE capability.
5672 (supported-systems '("i686-linux" "x86_64-linux"))
5673 (home-page "https://github.com/ncbi/ncbi-vdb")
5674 (synopsis "Database engine for genetic information")
5676 "The NCBI-VDB library implements a highly compressed columnar data
5677 warehousing engine that is most often used to store genetic information.
5678 Databases are stored in a portable image within the file system, and can be
5679 accessed/downloaded on demand across HTTP.")
5680 (license license:public-domain)))
5682 (define-public plink
5690 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5691 version "-src.zip"))
5693 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5694 (patches (search-patches "plink-1.07-unclobber-i.patch"
5695 "plink-endian-detection.patch"))))
5696 (build-system gnu-build-system)
5698 '(#:tests? #f ;no "check" target
5699 #:make-flags (list (string-append "LIB_LAPACK="
5700 (assoc-ref %build-inputs "lapack")
5701 "/lib/liblapack.so")
5704 ;; disable phoning home
5707 (modify-phases %standard-phases
5708 ;; no "configure" script
5711 (lambda* (#:key outputs #:allow-other-keys)
5712 (let ((bin (string-append (assoc-ref outputs "out")
5714 (install-file "plink" bin)
5718 ("lapack" ,lapack)))
5720 `(("unzip" ,unzip)))
5721 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5722 (synopsis "Whole genome association analysis toolset")
5724 "PLINK is a whole genome association analysis toolset, designed to
5725 perform a range of basic, large-scale analyses in a computationally efficient
5726 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5727 so there is no support for steps prior to this (e.g. study design and
5728 planning, generating genotype or CNV calls from raw data). Through
5729 integration with gPLINK and Haploview, there is some support for the
5730 subsequent visualization, annotation and storage of results.")
5731 ;; Code is released under GPLv2, except for fisher.h, which is under
5733 (license (list license:gpl2 license:lgpl2.1+))))
5735 (define-public plink-ng
5736 (package (inherit plink)
5743 (url "https://github.com/chrchang/plink-ng.git")
5744 (commit (string-append "v" version))))
5745 (file-name (git-file-name name version))
5747 (base32 "02npdwgkpfkdnhw819rhj5kw02a5k5m90b14zq9zzya4hyg929c0"))))
5748 (build-system gnu-build-system)
5750 '(#:tests? #f ;no "check" target
5751 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5752 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5754 "-f" "Makefile.std")
5756 (modify-phases %standard-phases
5757 (add-after 'unpack 'chdir
5758 (lambda _ (chdir "1.9") #t))
5759 (delete 'configure) ; no "configure" script
5761 (lambda* (#:key outputs #:allow-other-keys)
5762 (let ((bin (string-append (assoc-ref outputs "out")
5764 (install-file "plink" bin)
5769 ("openblas" ,openblas)))
5770 (home-page "https://www.cog-genomics.org/plink/")
5771 (license license:gpl3+)))
5773 (define-public smithlab-cpp
5774 (let ((revision "1")
5775 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
5777 (name "smithlab-cpp")
5778 (version (string-append "0." revision "." (string-take commit 7)))
5782 (url "https://github.com/smithlabcode/smithlab_cpp.git")
5784 (file-name (string-append name "-" version "-checkout"))
5787 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
5788 (build-system gnu-build-system)
5790 `(#:modules ((guix build gnu-build-system)
5793 #:tests? #f ;no "check" target
5795 (modify-phases %standard-phases
5796 (add-after 'unpack 'use-samtools-headers
5798 (substitute* '("SAM.cpp"
5800 (("sam.h") "samtools/sam.h"))
5803 (lambda* (#:key outputs #:allow-other-keys)
5804 (let* ((out (assoc-ref outputs "out"))
5805 (lib (string-append out "/lib"))
5806 (include (string-append out "/include/smithlab-cpp")))
5809 (for-each (cut install-file <> lib)
5810 (find-files "." "\\.o$"))
5811 (for-each (cut install-file <> include)
5812 (find-files "." "\\.hpp$")))
5814 (delete 'configure))))
5816 `(("samtools" ,samtools-0.1)
5818 (home-page "https://github.com/smithlabcode/smithlab_cpp")
5819 (synopsis "C++ helper library for functions used in Smith lab projects")
5821 "Smithlab CPP is a C++ library that includes functions used in many of
5822 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
5823 structures, classes for genomic regions, mapped sequencing reads, etc.")
5824 (license license:gpl3+))))
5826 (define-public preseq
5832 (uri (string-append "https://github.com/smithlabcode/preseq/"
5833 "releases/download/v" version
5834 "/preseq_v" version ".tar.bz2"))
5836 (base32 "149x9xmk1wy1gff85325yfzqc0qk4sgp1w6gbyj9cnji4x1dszbl"))
5837 (modules '((guix build utils)))
5839 ;; Remove bundled samtools.
5840 (delete-file-recursively "samtools")
5842 (build-system gnu-build-system)
5844 `(#:tests? #f ;no "check" target
5846 (modify-phases %standard-phases
5847 (delete 'configure))
5849 (list (string-append "PREFIX="
5850 (assoc-ref %outputs "out"))
5851 (string-append "LIBBAM="
5852 (assoc-ref %build-inputs "samtools")
5854 (string-append "SMITHLAB_CPP="
5855 (assoc-ref %build-inputs "smithlab-cpp")
5858 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
5861 ("samtools" ,samtools-0.1)
5862 ("smithlab-cpp" ,smithlab-cpp)
5864 (home-page "http://smithlabresearch.org/software/preseq/")
5865 (synopsis "Program for analyzing library complexity")
5867 "The preseq package is aimed at predicting and estimating the complexity
5868 of a genomic sequencing library, equivalent to predicting and estimating the
5869 number of redundant reads from a given sequencing depth and how many will be
5870 expected from additional sequencing using an initial sequencing experiment.
5871 The estimates can then be used to examine the utility of further sequencing,
5872 optimize the sequencing depth, or to screen multiple libraries to avoid low
5873 complexity samples.")
5874 (license license:gpl3+)))
5876 (define-public python-screed
5878 (name "python-screed")
5883 (uri (pypi-uri "screed" version))
5886 "148vcb7w2wr6a4w6vs2bsxanbqibxfk490zbcbg4m61s8669zdjx"))))
5887 (build-system python-build-system)
5890 (modify-phases %standard-phases
5891 ;; Tests must be run after installation, as the "screed" command does
5892 ;; not exist right after building.
5894 (add-after 'install 'check
5895 (lambda* (#:key inputs outputs #:allow-other-keys)
5896 (let ((out (assoc-ref outputs "out")))
5897 (setenv "PYTHONPATH"
5898 (string-append out "/lib/python"
5899 (string-take (string-take-right
5900 (assoc-ref inputs "python")
5903 (getenv "PYTHONPATH")))
5904 (setenv "PATH" (string-append out "/bin:" (getenv "PATH"))))
5905 (invoke "python" "setup.py" "test")
5908 `(("python-pytest" ,python-pytest)
5909 ("python-pytest-cov" ,python-pytest-cov)
5910 ("python-pytest-runner" ,python-pytest-runner)))
5912 `(("python-bz2file" ,python-bz2file)))
5913 (home-page "https://github.com/dib-lab/screed/")
5914 (synopsis "Short read sequence database utilities")
5915 (description "Screed parses FASTA and FASTQ files and generates databases.
5916 Values such as sequence name, sequence description, sequence quality and the
5917 sequence itself can be retrieved from these databases.")
5918 (license license:bsd-3)))
5920 (define-public python2-screed
5921 (package-with-python2 python-screed))
5923 (define-public sra-tools
5931 (url "https://github.com/ncbi/sra-tools.git")
5933 (file-name (git-file-name name version))
5936 "0663gcdxkziwsmlznjxysb00621rllpbz6jwsfifq7z3dj3lwm8b"))))
5937 (build-system gnu-build-system)
5939 `(#:parallel-build? #f ; not supported
5940 #:tests? #f ; no "check" target
5942 (list (string-append "DEFAULT_CRT="
5943 (assoc-ref %build-inputs "ncbi-vdb")
5945 (string-append "DEFAULT_KFG="
5946 (assoc-ref %build-inputs "ncbi-vdb")
5948 (string-append "VDB_LIBDIR="
5949 (assoc-ref %build-inputs "ncbi-vdb")
5950 ,(if (string-prefix? "x86_64"
5951 (or (%current-target-system)
5956 (modify-phases %standard-phases
5957 (add-before 'configure 'set-perl-search-path
5959 ;; Work around "dotless @INC" build failure.
5961 (string-append (getcwd) "/setup:"
5962 (getenv "PERL5LIB")))
5965 (lambda* (#:key inputs outputs #:allow-other-keys)
5966 ;; The build system expects a directory containing the sources and
5967 ;; raw build output of ncbi-vdb, including files that are not
5968 ;; installed. Since we are building against an installed version of
5969 ;; ncbi-vdb, the following modifications are needed.
5970 (substitute* "setup/konfigure.perl"
5971 ;; Make the configure script look for the "ilib" directory of
5972 ;; "ncbi-vdb" without first checking for the existence of a
5973 ;; matching library in its "lib" directory.
5974 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5975 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5976 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5977 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5978 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
5981 (substitute* "tools/copycat/Makefile"
5982 (("smagic-static") "lmagic"))
5984 ;; The 'configure' script doesn't recognize things like
5985 ;; '--enable-fast-install'.
5986 (invoke "./configure"
5987 (string-append "--build-prefix=" (getcwd) "/build")
5988 (string-append "--prefix=" (assoc-ref outputs "out"))
5989 (string-append "--debug")
5990 (string-append "--with-fuse-prefix="
5991 (assoc-ref inputs "fuse"))
5992 (string-append "--with-magic-prefix="
5993 (assoc-ref inputs "libmagic"))
5994 ;; TODO: building with libxml2 fails with linker errors
5995 ;; (string-append "--with-xml2-prefix="
5996 ;; (assoc-ref inputs "libxml2"))
5997 (string-append "--with-ncbi-vdb-sources="
5998 (assoc-ref inputs "ncbi-vdb"))
5999 (string-append "--with-ncbi-vdb-build="
6000 (assoc-ref inputs "ncbi-vdb"))
6001 (string-append "--with-ngs-sdk-prefix="
6002 (assoc-ref inputs "ngs-sdk"))
6003 (string-append "--with-hdf5-prefix="
6004 (assoc-ref inputs "hdf5")))
6006 (native-inputs `(("perl" ,perl)))
6008 `(("ngs-sdk" ,ngs-sdk)
6009 ("ncbi-vdb" ,ncbi-vdb)
6014 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
6015 (synopsis "Tools and libraries for reading and writing sequencing data")
6017 "The SRA Toolkit from NCBI is a collection of tools and libraries for
6018 reading of sequencing files from the Sequence Read Archive (SRA) database and
6019 writing files into the .sra format.")
6020 (license license:public-domain)))
6022 (define-public seqan
6028 (uri (string-append "https://github.com/seqan/seqan/releases/"
6029 "download/seqan-v" version
6030 "/seqan-library-" version ".tar.xz"))
6033 "19a1rlxx03qy1i1iriicly68w64yjxbv24g9gdywnfmq998v35yx"))))
6034 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6035 ;; makes sense to split the outputs.
6036 (outputs '("out" "doc"))
6037 (build-system trivial-build-system)
6039 `(#:modules ((guix build utils))
6042 (use-modules (guix build utils))
6043 (let ((tar (assoc-ref %build-inputs "tar"))
6044 (xz (assoc-ref %build-inputs "xz"))
6045 (out (assoc-ref %outputs "out"))
6046 (doc (assoc-ref %outputs "doc")))
6047 (setenv "PATH" (string-append tar "/bin:" xz "/bin"))
6048 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6049 (chdir (string-append "seqan-library-" ,version))
6050 (copy-recursively "include" (string-append out "/include"))
6051 (copy-recursively "share" (string-append doc "/share"))
6054 `(("source" ,source)
6057 (home-page "http://www.seqan.de")
6058 (synopsis "Library for nucleotide sequence analysis")
6060 "SeqAn is a C++ library of efficient algorithms and data structures for
6061 the analysis of sequences with the focus on biological data. It contains
6062 algorithms and data structures for string representation and their
6063 manipulation, online and indexed string search, efficient I/O of
6064 bioinformatics file formats, sequence alignment, and more.")
6065 (license license:bsd-3)))
6067 (define-public seqan-1
6068 (package (inherit seqan)
6073 (uri (string-append "http://packages.seqan.de/seqan-library/"
6074 "seqan-library-" version ".tar.bz2"))
6077 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
6078 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6079 ;; makes sense to split the outputs.
6080 (outputs '("out" "doc"))
6081 (build-system trivial-build-system)
6083 `(#:modules ((guix build utils))
6086 (use-modules (guix build utils))
6087 (let ((tar (assoc-ref %build-inputs "tar"))
6088 (bzip (assoc-ref %build-inputs "bzip2"))
6089 (out (assoc-ref %outputs "out"))
6090 (doc (assoc-ref %outputs "doc")))
6091 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
6092 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6093 (chdir (string-append "seqan-library-" ,version))
6094 (copy-recursively "include" (string-append out "/include"))
6095 (copy-recursively "share" (string-append doc "/share"))
6098 `(("source" ,source)
6100 ("bzip2" ,bzip2)))))
6102 (define-public seqmagick
6109 (uri (pypi-uri "seqmagick" version))
6112 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
6113 (build-system python-build-system)
6115 `(("python-biopython" ,python-biopython)))
6117 `(("python-nose" ,python-nose)))
6118 (home-page "https://github.com/fhcrc/seqmagick")
6119 (synopsis "Tools for converting and modifying sequence files")
6121 "Bioinformaticians often have to convert sequence files between formats
6122 and do little manipulations on them, and it's not worth writing scripts for
6123 that. Seqmagick is a utility to expose the file format conversion in
6124 BioPython in a convenient way. Instead of having a big mess of scripts, there
6125 is one that takes arguments.")
6126 (license license:gpl3)))
6128 (define-public seqtk
6135 (url "https://github.com/lh3/seqtk.git")
6136 (commit (string-append "v" version))))
6137 (file-name (git-file-name name version))
6140 "1bfzlqa84b5s1qi22blmmw2s8xdyp9h9ydcq22pfjhh5gab3yz6l"))))
6141 (build-system gnu-build-system)
6144 (modify-phases %standard-phases
6147 ;; There are no tests, so we just run a sanity check.
6148 (lambda _ (invoke "./seqtk" "seq") #t))
6150 (lambda* (#:key outputs #:allow-other-keys)
6151 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6152 (install-file "seqtk" bin)
6156 (home-page "https://github.com/lh3/seqtk")
6157 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
6159 "Seqtk is a fast and lightweight tool for processing sequences in the
6160 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
6161 optionally compressed by gzip.")
6162 (license license:expat)))
6164 (define-public snap-aligner
6166 (name "snap-aligner")
6167 (version "1.0beta.18")
6171 (url "https://github.com/amplab/snap.git")
6172 (commit (string-append "v" version))))
6173 (file-name (git-file-name name version))
6176 "01w3qq4wm07z73vky0cfwlmrbf50n3w722cxrlzxfi99mnb808d8"))))
6177 (build-system gnu-build-system)
6180 (modify-phases %standard-phases
6182 (replace 'check (lambda _ (invoke "./unit_tests") #t))
6184 (lambda* (#:key outputs #:allow-other-keys)
6185 (let* ((out (assoc-ref outputs "out"))
6186 (bin (string-append out "/bin")))
6187 (install-file "snap-aligner" bin)
6188 (install-file "SNAPCommand" bin)
6192 (home-page "http://snap.cs.berkeley.edu/")
6193 (synopsis "Short read DNA sequence aligner")
6195 "SNAP is a fast and accurate aligner for short DNA reads. It is
6196 optimized for modern read lengths of 100 bases or higher, and takes advantage
6197 of these reads to align data quickly through a hash-based indexing scheme.")
6198 ;; 32-bit systems are not supported by the unpatched code.
6199 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
6200 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
6201 ;; systems without a lot of memory cannot make good use of this program.
6202 (supported-systems '("x86_64-linux"))
6203 (license license:asl2.0)))
6205 (define-public sortmerna
6213 (url "https://github.com/biocore/sortmerna.git")
6215 (file-name (git-file-name name version))
6218 "0j3mbz4n25738yijmjbr5r4fyvkgm8v5vn3sshyfvmyqf5q9byqf"))))
6219 (build-system gnu-build-system)
6220 (outputs '("out" ;for binaries
6221 "db")) ;for sequence databases
6224 (modify-phases %standard-phases
6226 (lambda* (#:key outputs #:allow-other-keys)
6227 (let* ((out (assoc-ref outputs "out"))
6228 (bin (string-append out "/bin"))
6229 (db (assoc-ref outputs "db"))
6231 (string-append db "/share/sortmerna/rRNA_databases")))
6232 (install-file "sortmerna" bin)
6233 (install-file "indexdb_rna" bin)
6234 (for-each (lambda (file)
6235 (install-file file share))
6236 (find-files "rRNA_databases" ".*fasta"))
6240 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
6241 (synopsis "Biological sequence analysis tool for NGS reads")
6243 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
6244 and operational taxonomic unit (OTU) picking of next generation
6245 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
6246 allows for fast and sensitive analyses of nucleotide sequences. The main
6247 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
6248 ;; The source includes x86 specific code
6249 (supported-systems '("x86_64-linux" "i686-linux"))
6250 (license license:lgpl3)))
6259 (url "https://github.com/alexdobin/STAR.git")
6261 (file-name (string-append name "-" version "-checkout"))
6264 "1lih6cbpvnvhyvvswdhy06mwyzvwax96m723378v4z6psqzsh11d"))
6265 (modules '((guix build utils)))
6268 (substitute* "source/Makefile"
6270 ;; Remove pre-built binaries and bundled htslib sources.
6271 (delete-file-recursively "bin/MacOSX_x86_64")
6272 (delete-file-recursively "bin/Linux_x86_64")
6273 (delete-file-recursively "bin/Linux_x86_64_static")
6274 (delete-file-recursively "source/htslib")
6276 (build-system gnu-build-system)
6278 '(#:tests? #f ;no check target
6279 #:make-flags '("STAR")
6281 (modify-phases %standard-phases
6282 (add-after 'unpack 'enter-source-dir
6283 (lambda _ (chdir "source") #t))
6284 (add-after 'enter-source-dir 'make-reproducible
6286 (substitute* "Makefile"
6287 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
6288 (string-append pre "Built with Guix" post)))
6290 ;; See https://github.com/alexdobin/STAR/pull/562
6291 (add-after 'enter-source-dir 'add-missing-header
6293 (substitute* "SoloReadFeature_inputRecords.cpp"
6294 (("#include \"binarySearch2.h\"" h)
6295 (string-append h "\n#include <math.h>")))
6297 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
6299 (substitute* "Makefile"
6300 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
6302 (substitute* '("BAMfunctions.cpp"
6307 "bamRemoveDuplicates.cpp")
6308 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
6309 (string-append "#include <" header ">")))
6310 (substitute* "IncludeDefine.h"
6311 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
6312 (string-append "<" header ">")))
6315 (lambda* (#:key outputs #:allow-other-keys)
6316 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6317 (install-file "STAR" bin))
6319 (delete 'configure))))
6323 `(("htslib" ,htslib)
6325 (home-page "https://github.com/alexdobin/STAR")
6326 (synopsis "Universal RNA-seq aligner")
6328 "The Spliced Transcripts Alignment to a Reference (STAR) software is
6329 based on a previously undescribed RNA-seq alignment algorithm that uses
6330 sequential maximum mappable seed search in uncompressed suffix arrays followed
6331 by seed clustering and stitching procedure. In addition to unbiased de novo
6332 detection of canonical junctions, STAR can discover non-canonical splices and
6333 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
6335 ;; Only 64-bit systems are supported according to the README.
6336 (supported-systems '("x86_64-linux" "mips64el-linux"))
6337 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
6338 (license license:gpl3+)))
6340 (define-public subread
6346 (uri (string-append "mirror://sourceforge/subread/subread-"
6347 version "/subread-" version "-source.tar.gz"))
6350 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
6351 (build-system gnu-build-system)
6353 `(#:tests? #f ;no "check" target
6354 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
6355 ;; optimizations by default, so we override these flags such that x86_64
6356 ;; flags are only added when the build target is an x86_64 system.
6358 (list (let ((system ,(or (%current-target-system)
6360 (flags '("-ggdb" "-fomit-frame-pointer"
6361 "-ffast-math" "-funroll-loops"
6362 "-fmessage-length=0"
6363 "-O9" "-Wall" "-DMAKE_FOR_EXON"
6365 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
6366 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
6367 (if (string-prefix? "x86_64" system)
6368 (string-append "CCFLAGS=" (string-join (append flags flags64)))
6369 (string-append "CCFLAGS=" (string-join flags))))
6370 "-f" "Makefile.Linux"
6371 "CC=gcc ${CCFLAGS}")
6373 (modify-phases %standard-phases
6374 (add-after 'unpack 'enter-dir
6375 (lambda _ (chdir "src") #t))
6377 (lambda* (#:key outputs #:allow-other-keys)
6378 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6380 (copy-recursively "../bin" bin))
6382 ;; no "configure" script
6383 (delete 'configure))))
6384 (inputs `(("zlib" ,zlib)))
6385 (home-page "http://bioinf.wehi.edu.au/subread-package/")
6386 (synopsis "Tool kit for processing next-gen sequencing data")
6388 "The subread package contains the following tools: subread aligner, a
6389 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
6390 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
6391 features; exactSNP: a SNP caller that discovers SNPs by testing signals
6392 against local background noises.")
6393 (license license:gpl3+)))
6395 (define-public stringtie
6401 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
6402 "stringtie-" version ".tar.gz"))
6405 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
6406 (modules '((guix build utils)))
6409 (delete-file-recursively "samtools-0.1.18")
6411 (build-system gnu-build-system)
6413 `(#:tests? #f ;no test suite
6415 (modify-phases %standard-phases
6416 ;; no configure script
6418 (add-before 'build 'use-system-samtools
6420 (substitute* "Makefile"
6421 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
6423 (substitute* '("gclib/GBam.h"
6425 (("#include \"(bam|sam|kstring).h\"" _ header)
6426 (string-append "#include <samtools/" header ".h>")))
6428 (add-after 'unpack 'remove-duplicate-typedef
6430 ;; This typedef conflicts with the typedef in
6431 ;; glibc-2.25/include/bits/types.h
6432 (substitute* "gclib/GThreads.h"
6433 (("typedef long long __intmax_t;") ""))
6436 (lambda* (#:key outputs #:allow-other-keys)
6437 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6438 (install-file "stringtie" bin)
6441 `(("samtools" ,samtools-0.1)
6443 (home-page "http://ccb.jhu.edu/software/stringtie/")
6444 (synopsis "Transcript assembly and quantification for RNA-Seq data")
6446 "StringTie is a fast and efficient assembler of RNA-Seq sequence
6447 alignments into potential transcripts. It uses a novel network flow algorithm
6448 as well as an optional de novo assembly step to assemble and quantitate
6449 full-length transcripts representing multiple splice variants for each gene
6450 locus. Its input can include not only the alignments of raw reads used by
6451 other transcript assemblers, but also alignments of longer sequences that have
6452 been assembled from those reads. To identify differentially expressed genes
6453 between experiments, StringTie's output can be processed either by the
6454 Cuffdiff or Ballgown programs.")
6455 (license license:artistic2.0)))
6457 (define-public taxtastic
6463 (uri (pypi-uri "taxtastic" version))
6466 "03pysw79lsrvz4lwzis88j15067ffqbi4cid5pqhrlxmd6bh8rrk"))))
6467 (build-system python-build-system)
6469 `(#:python ,python-2
6471 (modify-phases %standard-phases
6473 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t)))))
6475 `(("python-sqlalchemy" ,python2-sqlalchemy)
6476 ("python-decorator" ,python2-decorator)
6477 ("python-biopython" ,python2-biopython)
6478 ("python-pandas" ,python2-pandas)
6479 ("python-psycopg2" ,python2-psycopg2)
6480 ("python-fastalite" ,python2-fastalite)
6481 ("python-pyyaml" ,python2-pyyaml)
6482 ("python-six" ,python2-six)
6483 ("python-jinja2" ,python2-jinja2)
6484 ("python-dendropy" ,python2-dendropy)))
6485 (home-page "https://github.com/fhcrc/taxtastic")
6486 (synopsis "Tools for taxonomic naming and annotation")
6488 "Taxtastic is software written in python used to build and maintain
6489 reference packages i.e. collections of reference trees, reference alignments,
6490 profiles, and associated taxonomic information.")
6491 (license license:gpl3+)))
6493 (define-public vcftools
6500 "https://github.com/vcftools/vcftools/releases/download/v"
6501 version "/vcftools-" version ".tar.gz"))
6504 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
6505 (build-system gnu-build-system)
6507 `(#:tests? #f ; no "check" target
6509 "CFLAGS=-O2" ; override "-m64" flag
6510 (string-append "PREFIX=" (assoc-ref %outputs "out"))
6511 (string-append "MANDIR=" (assoc-ref %outputs "out")
6512 "/share/man/man1"))))
6514 `(("pkg-config" ,pkg-config)))
6518 (home-page "https://vcftools.github.io/")
6519 (synopsis "Tools for working with VCF files")
6521 "VCFtools is a program package designed for working with VCF files, such
6522 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
6523 provide easily accessible methods for working with complex genetic variation
6524 data in the form of VCF files.")
6525 ;; The license is declared as LGPLv3 in the README and
6526 ;; at https://vcftools.github.io/license.html
6527 (license license:lgpl3)))
6529 (define-public infernal
6535 (uri (string-append "http://eddylab.org/software/infernal/"
6536 "infernal-" version ".tar.gz"))
6539 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
6540 (build-system gnu-build-system)
6542 `(("perl" ,perl))) ; for tests
6543 (home-page "http://eddylab.org/infernal/")
6544 (synopsis "Inference of RNA alignments")
6545 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
6546 searching DNA sequence databases for RNA structure and sequence similarities.
6547 It is an implementation of a special case of profile stochastic context-free
6548 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
6549 profile, but it scores a combination of sequence consensus and RNA secondary
6550 structure consensus, so in many cases, it is more capable of identifying RNA
6551 homologs that conserve their secondary structure more than their primary
6553 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
6554 (supported-systems '("i686-linux" "x86_64-linux"))
6555 (license license:bsd-3)))
6557 (define-public r-scde
6564 (url "https://github.com/hms-dbmi/scde.git")
6566 (file-name (git-file-name name version))
6569 "10na2gyka24mszdxf92wz9h2c13hdf1ww30c68gfsw53lvvhhhxb"))))
6570 (build-system r-build-system)
6572 `(("r-rcpp" ,r-rcpp)
6573 ("r-rcpparmadillo" ,r-rcpparmadillo)
6576 ("r-rjson" ,r-rjson)
6577 ("r-cairo" ,r-cairo)
6578 ("r-rcolorbrewer" ,r-rcolorbrewer)
6579 ("r-edger" ,r-edger)
6580 ("r-quantreg" ,r-quantreg)
6582 ("r-rmtstat" ,r-rmtstat)
6583 ("r-extremes" ,r-extremes)
6584 ("r-pcamethods" ,r-pcamethods)
6585 ("r-biocparallel" ,r-biocparallel)
6586 ("r-flexmix" ,r-flexmix)))
6587 (home-page "https://hms-dbmi.github.io/scde/")
6588 (synopsis "R package for analyzing single-cell RNA-seq data")
6589 (description "The SCDE package implements a set of statistical methods for
6590 analyzing single-cell RNA-seq data. SCDE fits individual error models for
6591 single-cell RNA-seq measurements. These models can then be used for
6592 assessment of differential expression between groups of cells, as well as
6593 other types of analysis. The SCDE package also contains the pagoda framework
6594 which applies pathway and gene set overdispersion analysis to identify aspects
6595 of transcriptional heterogeneity among single cells.")
6596 ;; See https://github.com/hms-dbmi/scde/issues/38
6597 (license license:gpl2)))
6599 (define-public r-centipede
6601 (name "r-centipede")
6605 (uri (string-append "http://download.r-forge.r-project.org/"
6606 "src/contrib/CENTIPEDE_" version ".tar.gz"))
6609 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
6610 (build-system r-build-system)
6611 (home-page "http://centipede.uchicago.edu/")
6612 (synopsis "Predict transcription factor binding sites")
6614 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
6615 of the genome that are bound by particular transcription factors. It starts
6616 by identifying a set of candidate binding sites, and then aims to classify the
6617 sites according to whether each site is bound or not bound by a transcription
6618 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
6619 between two different types of motif instances using as much relevant
6620 information as possible.")
6621 (license (list license:gpl2+ license:gpl3+))))
6623 (define-public r-genefilter
6625 (name "r-genefilter")
6630 (uri (bioconductor-uri "genefilter" version))
6633 "0p64s1n1627yafnp25wjr4b22p34lqw574fx2qg4s1m0lffh1z6i"))))
6634 (build-system r-build-system)
6636 `(("gfortran" ,gfortran)))
6638 `(("r-annotate" ,r-annotate)
6639 ("r-annotationdbi" ,r-annotationdbi)
6640 ("r-biobase" ,r-biobase)
6641 ("r-s4vectors" ,r-s4vectors)
6642 ("r-survival" ,r-survival)))
6643 (home-page "https://bioconductor.org/packages/genefilter")
6644 (synopsis "Filter genes from high-throughput experiments")
6646 "This package provides basic functions for filtering genes from
6647 high-throughput sequencing experiments.")
6648 (license license:artistic2.0)))
6650 (define-public r-deseq2
6657 (uri (bioconductor-uri "DESeq2" version))
6660 "0n5ah84mxn87p45drzy0wh2yknmzj1q5i6gv0v9vgg1lj7awb91r"))))
6661 (properties `((upstream-name . "DESeq2")))
6662 (build-system r-build-system)
6664 `(("r-biobase" ,r-biobase)
6665 ("r-biocgenerics" ,r-biocgenerics)
6666 ("r-biocparallel" ,r-biocparallel)
6667 ("r-genefilter" ,r-genefilter)
6668 ("r-geneplotter" ,r-geneplotter)
6669 ("r-genomicranges" ,r-genomicranges)
6670 ("r-ggplot2" ,r-ggplot2)
6671 ("r-hmisc" ,r-hmisc)
6672 ("r-iranges" ,r-iranges)
6673 ("r-locfit" ,r-locfit)
6675 ("r-rcpparmadillo" ,r-rcpparmadillo)
6676 ("r-s4vectors" ,r-s4vectors)
6677 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6678 (home-page "https://bioconductor.org/packages/DESeq2")
6679 (synopsis "Differential gene expression analysis")
6681 "This package provides functions to estimate variance-mean dependence in
6682 count data from high-throughput nucleotide sequencing assays and test for
6683 differential expression based on a model using the negative binomial
6685 (license license:lgpl3+)))
6687 (define-public r-dexseq
6694 (uri (bioconductor-uri "DEXSeq" version))
6697 "134znafy7hn38rp4nia4pglz56fz6nbkxrf7z2k1sajfsgxa1hs6"))))
6698 (properties `((upstream-name . "DEXSeq")))
6699 (build-system r-build-system)
6701 `(("r-annotationdbi" ,r-annotationdbi)
6702 ("r-biobase" ,r-biobase)
6703 ("r-biocgenerics" ,r-biocgenerics)
6704 ("r-biocparallel" ,r-biocparallel)
6705 ("r-biomart" ,r-biomart)
6706 ("r-deseq2" ,r-deseq2)
6707 ("r-genefilter" ,r-genefilter)
6708 ("r-geneplotter" ,r-geneplotter)
6709 ("r-genomicranges" ,r-genomicranges)
6710 ("r-hwriter" ,r-hwriter)
6711 ("r-iranges" ,r-iranges)
6712 ("r-rcolorbrewer" ,r-rcolorbrewer)
6713 ("r-rsamtools" ,r-rsamtools)
6714 ("r-s4vectors" ,r-s4vectors)
6715 ("r-statmod" ,r-statmod)
6716 ("r-stringr" ,r-stringr)
6717 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6718 (home-page "https://bioconductor.org/packages/DEXSeq")
6719 (synopsis "Inference of differential exon usage in RNA-Seq")
6721 "This package is focused on finding differential exon usage using RNA-seq
6722 exon counts between samples with different experimental designs. It provides
6723 functions that allows the user to make the necessary statistical tests based
6724 on a model that uses the negative binomial distribution to estimate the
6725 variance between biological replicates and generalized linear models for
6726 testing. The package also provides functions for the visualization and
6727 exploration of the results.")
6728 (license license:gpl3+)))
6730 (define-public r-annotationforge
6732 (name "r-annotationforge")
6737 (uri (bioconductor-uri "AnnotationForge" version))
6740 "13yvhf3yskmvhs8szs6rkw93h81h5xqa3h19h91pp6nprhc8s3ll"))))
6742 `((upstream-name . "AnnotationForge")))
6743 (build-system r-build-system)
6745 `(("r-annotationdbi" ,r-annotationdbi)
6746 ("r-biobase" ,r-biobase)
6747 ("r-biocgenerics" ,r-biocgenerics)
6749 ("r-rcurl" ,r-rcurl)
6750 ("r-rsqlite" ,r-rsqlite)
6751 ("r-s4vectors" ,r-s4vectors)
6753 (home-page "https://bioconductor.org/packages/AnnotationForge")
6754 (synopsis "Code for building annotation database packages")
6756 "This package provides code for generating Annotation packages and their
6757 databases. Packages produced are intended to be used with AnnotationDbi.")
6758 (license license:artistic2.0)))
6760 (define-public r-rbgl
6767 (uri (bioconductor-uri "RBGL" version))
6770 "1l5x2icv9di1lr3gqfi0vjnyd9xc3l77yc42ippqd4cadj3d1pzf"))))
6771 (properties `((upstream-name . "RBGL")))
6772 (build-system r-build-system)
6773 (propagated-inputs `(("r-graph" ,r-graph)))
6774 (home-page "https://www.bioconductor.org/packages/RBGL")
6775 (synopsis "Interface to the Boost graph library")
6777 "This package provides a fairly extensive and comprehensive interface to
6778 the graph algorithms contained in the Boost library.")
6779 (license license:artistic2.0)))
6781 (define-public r-gseabase
6788 (uri (bioconductor-uri "GSEABase" version))
6791 "110al7x0ig8plzrprvhwc7xshi1jzpj2n8llhhg2fh6v6k0k6awr"))))
6792 (properties `((upstream-name . "GSEABase")))
6793 (build-system r-build-system)
6795 `(("r-annotate" ,r-annotate)
6796 ("r-annotationdbi" ,r-annotationdbi)
6797 ("r-biobase" ,r-biobase)
6798 ("r-biocgenerics" ,r-biocgenerics)
6799 ("r-graph" ,r-graph)
6801 (home-page "https://bioconductor.org/packages/GSEABase")
6802 (synopsis "Gene set enrichment data structures and methods")
6804 "This package provides classes and methods to support @dfn{Gene Set
6805 Enrichment Analysis} (GSEA).")
6806 (license license:artistic2.0)))
6808 (define-public r-category
6815 (uri (bioconductor-uri "Category" version))
6818 "1jdm83bwdfhpfm1y6hwgvxzj6l83h1bdkqv23799kzywnwm016kv"))))
6819 (properties `((upstream-name . "Category")))
6820 (build-system r-build-system)
6822 `(("r-annotate" ,r-annotate)
6823 ("r-annotationdbi" ,r-annotationdbi)
6824 ("r-biobase" ,r-biobase)
6825 ("r-biocgenerics" ,r-biocgenerics)
6826 ("r-genefilter" ,r-genefilter)
6827 ("r-graph" ,r-graph)
6828 ("r-gseabase" ,r-gseabase)
6829 ("r-matrix" ,r-matrix)
6832 (home-page "https://bioconductor.org/packages/Category")
6833 (synopsis "Category analysis")
6835 "This package provides a collection of tools for performing category
6837 (license license:artistic2.0)))
6839 (define-public r-gostats
6846 (uri (bioconductor-uri "GOstats" version))
6849 "0wlqqgfynwqnqhckhsfjwg9zkj6hkmzwd5y76dhqz720vy21rcln"))))
6850 (properties `((upstream-name . "GOstats")))
6851 (build-system r-build-system)
6853 `(("r-annotate" ,r-annotate)
6854 ("r-annotationdbi" ,r-annotationdbi)
6855 ("r-annotationforge" ,r-annotationforge)
6856 ("r-biobase" ,r-biobase)
6857 ("r-category" ,r-category)
6858 ("r-go-db" ,r-go-db)
6859 ("r-graph" ,r-graph)
6860 ("r-rgraphviz" ,r-rgraphviz)
6861 ("r-rbgl" ,r-rbgl)))
6862 (home-page "https://bioconductor.org/packages/GOstats")
6863 (synopsis "Tools for manipulating GO and microarrays")
6865 "This package provides a set of tools for interacting with GO and
6866 microarray data. A variety of basic manipulation tools for graphs, hypothesis
6867 testing and other simple calculations.")
6868 (license license:artistic2.0)))
6870 (define-public r-shortread
6872 (name "r-shortread")
6877 (uri (bioconductor-uri "ShortRead" version))
6880 "0iks123i1adkb9i2q4wvfqdmmj9dy867jvngj9757y8gj6xbcpy1"))))
6881 (properties `((upstream-name . "ShortRead")))
6882 (build-system r-build-system)
6886 `(("r-biobase" ,r-biobase)
6887 ("r-biocgenerics" ,r-biocgenerics)
6888 ("r-biocparallel" ,r-biocparallel)
6889 ("r-biostrings" ,r-biostrings)
6890 ("r-genomeinfodb" ,r-genomeinfodb)
6891 ("r-genomicalignments" ,r-genomicalignments)
6892 ("r-genomicranges" ,r-genomicranges)
6893 ("r-hwriter" ,r-hwriter)
6894 ("r-iranges" ,r-iranges)
6895 ("r-lattice" ,r-lattice)
6896 ("r-latticeextra" ,r-latticeextra)
6897 ("r-rsamtools" ,r-rsamtools)
6898 ("r-s4vectors" ,r-s4vectors)
6899 ("r-xvector" ,r-xvector)
6900 ("r-zlibbioc" ,r-zlibbioc)))
6901 (home-page "https://bioconductor.org/packages/ShortRead")
6902 (synopsis "FASTQ input and manipulation tools")
6904 "This package implements sampling, iteration, and input of FASTQ files.
6905 It includes functions for filtering and trimming reads, and for generating a
6906 quality assessment report. Data are represented as
6907 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6908 purposes. The package also contains legacy support for early single-end,
6909 ungapped alignment formats.")
6910 (license license:artistic2.0)))
6912 (define-public r-systempiper
6914 (name "r-systempiper")
6919 (uri (bioconductor-uri "systemPipeR" version))
6922 "0qzydz87rld2nhwzbfgrw5jfgh8maa9y54mjx9c4285m11qj2shq"))))
6923 (properties `((upstream-name . "systemPipeR")))
6924 (build-system r-build-system)
6926 `(("r-annotate" ,r-annotate)
6927 ("r-batchjobs" ,r-batchjobs)
6928 ("r-biocgenerics" ,r-biocgenerics)
6929 ("r-biostrings" ,r-biostrings)
6930 ("r-deseq2" ,r-deseq2)
6931 ("r-edger" ,r-edger)
6932 ("r-genomicfeatures" ,r-genomicfeatures)
6933 ("r-genomicranges" ,r-genomicranges)
6934 ("r-ggplot2" ,r-ggplot2)
6935 ("r-go-db" ,r-go-db)
6936 ("r-gostats" ,r-gostats)
6937 ("r-limma" ,r-limma)
6938 ("r-pheatmap" ,r-pheatmap)
6939 ("r-rjson" ,r-rjson)
6940 ("r-rsamtools" ,r-rsamtools)
6941 ("r-shortread" ,r-shortread)
6942 ("r-summarizedexperiment" ,r-summarizedexperiment)
6943 ("r-variantannotation" ,r-variantannotation)))
6944 (home-page "https://github.com/tgirke/systemPipeR")
6945 (synopsis "Next generation sequencing workflow and reporting environment")
6947 "This R package provides tools for building and running automated
6948 end-to-end analysis workflows for a wide range of @dfn{next generation
6949 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6950 Important features include a uniform workflow interface across different NGS
6951 applications, automated report generation, and support for running both R and
6952 command-line software, such as NGS aligners or peak/variant callers, on local
6953 computers or compute clusters. Efficient handling of complex sample sets and
6954 experimental designs is facilitated by a consistently implemented sample
6955 annotation infrastructure.")
6956 (license license:artistic2.0)))
6958 (define-public r-grohmm
6965 (uri (bioconductor-uri "groHMM" version))
6968 "1ph92fv44b90v7mk4b1mjvv0dlrhl8ba01klxbnd0vs4qn9zxplh"))))
6969 (properties `((upstream-name . "groHMM")))
6970 (build-system r-build-system)
6972 `(("r-genomeinfodb" ,r-genomeinfodb)
6973 ("r-genomicalignments" ,r-genomicalignments)
6974 ("r-genomicranges" ,r-genomicranges)
6975 ("r-iranges" ,r-iranges)
6977 ("r-rtracklayer" ,r-rtracklayer)
6978 ("r-s4vectors" ,r-s4vectors)))
6979 (home-page "https://github.com/Kraus-Lab/groHMM")
6980 (synopsis "GRO-seq analysis pipeline")
6982 "This package provides a pipeline for the analysis of GRO-seq data.")
6983 (license license:gpl3+)))
6985 (define-public r-sparql
6991 (uri (cran-uri "SPARQL" version))
6994 "0gak1q06yyhdmcxb2n3v0h9gr1vqd0viqji52wpw211qp6r6dcrc"))))
6995 (properties `((upstream-name . "SPARQL")))
6996 (build-system r-build-system)
6998 `(("r-rcurl" ,r-rcurl)
7000 (home-page "https://cran.r-project.org/web/packages/SPARQL")
7001 (synopsis "SPARQL client for R")
7002 (description "This package provides an interface to use SPARQL to pose
7003 SELECT or UPDATE queries to an end-point.")
7004 ;; The only license indication is found in the DESCRIPTION file,
7005 ;; which states GPL-3. So we cannot assume GPLv3+.
7006 (license license:gpl3)))
7008 (define-public vsearch
7016 (url "https://github.com/torognes/vsearch.git")
7017 (commit (string-append "v" version))))
7018 (file-name (git-file-name name version))
7021 "0vhrpjfdf75ba04b24xknp41790cvcgwl0vgpy7qbzj5xh2521ss"))
7022 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
7025 ;; Remove bundled cityhash sources. The vsearch source is adjusted
7026 ;; for this in the patch.
7027 (delete-file "src/city.h")
7028 (delete-file "src/citycrc.h")
7029 (delete-file "src/city.cc")
7031 (build-system gnu-build-system)
7035 ("cityhash" ,cityhash)))
7037 `(("autoconf" ,autoconf)
7038 ("automake" ,automake)))
7039 (synopsis "Sequence search tools for metagenomics")
7041 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
7042 dereplication, pairwise alignment, shuffling, subsampling, sorting and
7043 masking. The tool takes advantage of parallelism in the form of SIMD
7044 vectorization as well as multiple threads to perform accurate alignments at
7045 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
7046 Needleman-Wunsch).")
7047 (home-page "https://github.com/torognes/vsearch")
7048 ;; vsearch uses non-portable SSE intrinsics so building fails on other
7050 (supported-systems '("x86_64-linux"))
7051 ;; Dual licensed; also includes public domain source.
7052 (license (list license:gpl3 license:bsd-2))))
7054 (define-public pardre
7057 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
7062 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
7066 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
7067 (build-system gnu-build-system)
7069 `(#:tests? #f ; no tests included
7071 (modify-phases %standard-phases
7074 (lambda* (#:key outputs #:allow-other-keys)
7075 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
7076 (install-file "ParDRe" bin)
7079 `(("openmpi" ,openmpi)
7081 (synopsis "Parallel tool to remove duplicate DNA reads")
7083 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
7084 Duplicate reads can be seen as identical or nearly identical sequences with
7085 some mismatches. This tool lets users avoid the analysis of unnecessary
7086 reads, reducing the time of subsequent procedures with the
7087 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
7088 in order to exploit the parallel capabilities of multicore clusters. It is
7089 faster than multithreaded counterparts (end of 2015) for the same number of
7090 cores and, thanks to the message-passing technology, it can be executed on
7092 (home-page "https://sourceforge.net/projects/pardre/")
7093 (license license:gpl3+)))
7095 (define-public ruby-bio-kseq
7097 (name "ruby-bio-kseq")
7102 (uri (rubygems-uri "bio-kseq" version))
7105 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
7106 (build-system ruby-build-system)
7108 `(#:test-target "spec"))
7110 `(("bundler" ,bundler)
7111 ("ruby-rspec" ,ruby-rspec)
7112 ("ruby-rake-compiler" ,ruby-rake-compiler)))
7115 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
7117 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
7118 FASTQ parsing code. It provides a fast iterator over sequences and their
7120 (home-page "https://github.com/gusevfe/bio-kseq")
7121 (license license:expat)))
7123 (define-public bio-locus
7130 (uri (rubygems-uri "bio-locus" version))
7133 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
7134 (build-system ruby-build-system)
7136 `(("ruby-rspec" ,ruby-rspec)))
7137 (synopsis "Tool for fast querying of genome locations")
7139 "Bio-locus is a tabix-like tool for fast querying of genome
7140 locations. Many file formats in bioinformatics contain records that
7141 start with a chromosome name and a position for a SNP, or a start-end
7142 position for indels. Bio-locus allows users to store this chr+pos or
7143 chr+pos+alt information in a database.")
7144 (home-page "https://github.com/pjotrp/bio-locus")
7145 (license license:expat)))
7147 (define-public bio-blastxmlparser
7149 (name "bio-blastxmlparser")
7153 (uri (rubygems-uri "bio-blastxmlparser" version))
7156 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
7157 (build-system ruby-build-system)
7159 `(("ruby-bio-logger" ,ruby-bio-logger)
7160 ("ruby-nokogiri" ,ruby-nokogiri)))
7162 `(("ruby-rspec" ,ruby-rspec)))
7163 (synopsis "Fast big data BLAST XML parser and library")
7165 "Very fast parallel big-data BLAST XML file parser which can be used as
7166 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
7167 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
7168 (home-page "https://github.com/pjotrp/blastxmlparser")
7169 (license license:expat)))
7171 (define-public bioruby
7178 (uri (rubygems-uri "bio" version))
7181 "1d56amdsjv1mag7m6gv2w0xij8hqx1v5xbdjsix8sp3yp36m7938"))))
7182 (build-system ruby-build-system)
7184 `(("ruby-libxml" ,ruby-libxml)))
7186 `(("which" ,which))) ; required for test phase
7189 (modify-phases %standard-phases
7190 (add-before 'build 'patch-test-command
7192 (substitute* '("test/functional/bio/test_command.rb")
7193 (("/bin/sh") (which "sh")))
7194 (substitute* '("test/functional/bio/test_command.rb")
7195 (("/bin/ls") (which "ls")))
7196 (substitute* '("test/functional/bio/test_command.rb")
7197 (("which") (which "which")))
7198 (substitute* '("test/functional/bio/test_command.rb",
7199 "test/data/command/echoarg2.sh")
7200 (("/bin/echo") (which "echo")))
7202 (synopsis "Ruby library, shell and utilities for bioinformatics")
7203 (description "BioRuby comes with a comprehensive set of Ruby development
7204 tools and libraries for bioinformatics and molecular biology. BioRuby has
7205 components for sequence analysis, pathway analysis, protein modelling and
7206 phylogenetic analysis; it supports many widely used data formats and provides
7207 easy access to databases, external programs and public web services, including
7208 BLAST, KEGG, GenBank, MEDLINE and GO.")
7209 (home-page "http://bioruby.org/")
7210 ;; Code is released under Ruby license, except for setup
7211 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
7212 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
7214 (define-public r-acsnminer
7216 (name "r-acsnminer")
7217 (version "0.16.8.25")
7220 (uri (cran-uri "ACSNMineR" version))
7223 "0gh604s8qall6zfjlwcg2ilxjvz08dplf9k5g47idhv43scm748l"))))
7224 (properties `((upstream-name . "ACSNMineR")))
7225 (build-system r-build-system)
7227 `(("r-ggplot2" ,r-ggplot2)
7228 ("r-gridextra" ,r-gridextra)))
7229 (home-page "https://cran.r-project.org/web/packages/ACSNMineR")
7230 (synopsis "Gene enrichment analysis")
7232 "This package provides tools to compute and represent gene set enrichment
7233 or depletion from your data based on pre-saved maps from the @dfn{Atlas of
7234 Cancer Signalling Networks} (ACSN) or user imported maps. The gene set
7235 enrichment can be run with hypergeometric test or Fisher exact test, and can
7236 use multiple corrections. Visualization of data can be done either by
7237 barplots or heatmaps.")
7238 (license license:gpl2+)))
7240 (define-public r-biocinstaller
7242 (name "r-biocinstaller")
7246 (uri (bioconductor-uri "BiocInstaller" version))
7249 "1s1f9qhyf3mc73ir25x2zlgi9hf45a37lg4z8fbva4i21hqisgsl"))))
7251 `((upstream-name . "BiocInstaller")))
7252 (build-system r-build-system)
7253 (home-page "https://bioconductor.org/packages/BiocInstaller")
7254 (synopsis "Install Bioconductor packages")
7255 (description "This package is used to install and update R packages from
7256 Bioconductor, CRAN, and Github.")
7257 (license license:artistic2.0)))
7259 (define-public r-biocviews
7261 (name "r-biocviews")
7265 (uri (bioconductor-uri "biocViews" version))
7268 "06ms82pyc5rxbd9crfvqjxcwpafv0c627i83v80d12925mrc51h8"))))
7270 `((upstream-name . "biocViews")))
7271 (build-system r-build-system)
7273 `(("r-biobase" ,r-biobase)
7274 ("r-graph" ,r-graph)
7276 ("r-rcurl" ,r-rcurl)
7278 ("r-runit" ,r-runit)))
7279 (home-page "https://bioconductor.org/packages/biocViews")
7280 (synopsis "Bioconductor package categorization helper")
7281 (description "The purpose of biocViews is to create HTML pages that
7282 categorize packages in a Bioconductor package repository according to keywords,
7283 also known as views, in a controlled vocabulary.")
7284 (license license:artistic2.0)))
7286 (define-public r-bookdown
7292 (uri (cran-uri "bookdown" version))
7295 "0vg1s1w0l9pm95asqb21yf39mfk1nc9rdhmlys9xwr7p7i7rsz32"))))
7296 (build-system r-build-system)
7298 `(("r-htmltools" ,r-htmltools)
7299 ("r-knitr" ,r-knitr)
7300 ("r-rmarkdown" ,r-rmarkdown)
7301 ("r-tinytex" ,r-tinytex)
7303 ("r-xfun" ,r-xfun)))
7304 (home-page "https://github.com/rstudio/bookdown")
7305 (synopsis "Authoring books and technical documents with R markdown")
7306 (description "This package provides output formats and utilities for
7307 authoring books and technical documents with R Markdown.")
7308 (license license:gpl3)))
7310 (define-public r-biocstyle
7312 (name "r-biocstyle")
7316 (uri (bioconductor-uri "BiocStyle" version))
7319 "01lm8xljilj666fcl3wnw82dxkcxnlr294lddr553rm8xr5nwg31"))))
7321 `((upstream-name . "BiocStyle")))
7322 (build-system r-build-system)
7324 `(("r-biocmanager" ,r-biocmanager)
7325 ("r-bookdown" ,r-bookdown)
7326 ("r-knitr" ,r-knitr)
7327 ("r-rmarkdown" ,r-rmarkdown)
7328 ("r-yaml" ,r-yaml)))
7329 (home-page "https://bioconductor.org/packages/BiocStyle")
7330 (synopsis "Bioconductor formatting styles")
7331 (description "This package provides standard formatting styles for
7332 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
7334 (license license:artistic2.0)))
7336 (define-public r-bioccheck
7338 (name "r-bioccheck")
7342 (uri (bioconductor-uri "BiocCheck" version))
7345 "0zamvs5jar38293ff27imvwy0ra25y64ls9z8w3q1y4jcp8p8pg7"))))
7347 `((upstream-name . "BiocCheck")))
7348 (build-system r-build-system)
7351 (modify-phases %standard-phases
7352 ;; This package can be used by calling BiocCheck(<package>) from
7353 ;; within R, or by running R CMD BiocCheck <package>. This phase
7354 ;; makes sure the latter works. For this to work, the BiocCheck
7355 ;; script must be somewhere on the PATH (not the R bin directory).
7356 (add-after 'install 'install-bioccheck-subcommand
7357 (lambda* (#:key outputs #:allow-other-keys)
7358 (let* ((out (assoc-ref outputs "out"))
7359 (dest-dir (string-append out "/bin"))
7361 (string-append out "/site-library/BiocCheck/script/")))
7363 (symlink (string-append script-dir "/checkBadDeps.R")
7364 (string-append dest-dir "/checkBadDeps.R"))
7365 (symlink (string-append script-dir "/BiocCheck")
7366 (string-append dest-dir "/BiocCheck")))
7369 `(("r-codetools" ,r-codetools)
7370 ("r-graph" ,r-graph)
7372 ("r-knitr" ,r-knitr)
7373 ("r-optparse" ,r-optparse)
7374 ("r-biocmanager" ,r-biocmanager)
7375 ("r-biocviews" ,r-biocviews)
7376 ("r-stringdist" ,r-stringdist)))
7377 (home-page "https://bioconductor.org/packages/BiocCheck")
7378 (synopsis "Executes Bioconductor-specific package checks")
7379 (description "This package contains tools to perform additional quality
7380 checks on R packages that are to be submitted to the Bioconductor repository.")
7381 (license license:artistic2.0)))
7383 (define-public r-optparse
7390 (uri (cran-uri "optparse" version))
7393 "04vyb6dhcga30mvghsg1p052jmf69xqxkvh3hzqz7dscyppy76w1"))))
7394 (build-system r-build-system)
7396 `(("r-getopt" ,r-getopt)))
7398 "https://github.com/trevorld/optparse")
7399 (synopsis "Command line option parser")
7401 "This package provides a command line parser inspired by Python's
7402 @code{optparse} library to be used with Rscript to write shebang scripts
7403 that accept short and long options.")
7404 (license license:gpl2+)))
7406 (define-public r-s4vectors
7408 (name "r-s4vectors")
7412 (uri (bioconductor-uri "S4Vectors" version))
7415 "18whrw67nxn82xshckl2pjy7d14sa3c27h3n9naqyqwz88lr6dzg"))))
7417 `((upstream-name . "S4Vectors")))
7418 (build-system r-build-system)
7420 `(("r-biocgenerics" ,r-biocgenerics)))
7421 (home-page "https://bioconductor.org/packages/S4Vectors")
7422 (synopsis "S4 implementation of vectors and lists")
7424 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7425 classes and a set of generic functions that extend the semantic of ordinary
7426 vectors and lists in R. Package developers can easily implement vector-like
7427 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7428 In addition, a few low-level concrete subclasses of general interest (e.g.
7429 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7430 S4Vectors package itself.")
7431 (license license:artistic2.0)))
7433 (define-public r-seqinr
7440 (uri (cran-uri "seqinr" version))
7443 "17zv0n5cji17izwmwg0jcbxbjl3w5rls91w15svcnlpxjms38ahn"))))
7444 (build-system r-build-system)
7446 `(("r-ade4" ,r-ade4)
7447 ("r-segmented" ,r-segmented)))
7450 (home-page "http://seqinr.r-forge.r-project.org/")
7451 (synopsis "Biological sequences retrieval and analysis")
7453 "This package provides tools for exploratory data analysis and data
7454 visualization of biological sequence (DNA and protein) data. It also includes
7455 utilities for sequence data management under the ACNUC system.")
7456 (license license:gpl2+)))
7458 (define-public r-iranges
7464 (uri (bioconductor-uri "IRanges" version))
7467 "0ljppsk611xi72gc8mbdx1311b63b1ijd401jz5xmxk5frla1nc1"))))
7469 `((upstream-name . "IRanges")))
7470 (build-system r-build-system)
7472 `(("r-biocgenerics" ,r-biocgenerics)
7473 ("r-s4vectors" ,r-s4vectors)))
7474 (home-page "https://bioconductor.org/packages/IRanges")
7475 (synopsis "Infrastructure for manipulating intervals on sequences")
7477 "This package provides efficient low-level and highly reusable S4 classes
7478 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7479 generally, data that can be organized sequentially (formally defined as
7480 @code{Vector} objects), as well as views on these @code{Vector} objects.
7481 Efficient list-like classes are also provided for storing big collections of
7482 instances of the basic classes. All classes in the package use consistent
7483 naming and share the same rich and consistent \"Vector API\" as much as
7485 (license license:artistic2.0)))
7487 (define-public r-genomeinfodbdata
7489 (name "r-genomeinfodbdata")
7493 ;; We cannot use bioconductor-uri here because this tarball is
7494 ;; located under "data/annotation/" instead of "bioc/".
7495 (uri (string-append "https://bioconductor.org/packages/release/"
7496 "data/annotation/src/contrib/GenomeInfoDbData_"
7500 "0di6nlqpsyqf693k2na65ayqldih563x3zfrczpqc5q2hl5kg35c"))))
7502 `((upstream-name . "GenomeInfoDbData")))
7503 (build-system r-build-system)
7504 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7505 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7506 (description "This package contains data for mapping between NCBI taxonomy
7507 ID and species. It is used by functions in the GenomeInfoDb package.")
7508 (license license:artistic2.0)))
7510 (define-public r-genomeinfodb
7512 (name "r-genomeinfodb")
7516 (uri (bioconductor-uri "GenomeInfoDb" version))
7519 "07bm35jcczpyxap0b3gky4b28z38z423sngzsm19d9krjxr76b5p"))))
7521 `((upstream-name . "GenomeInfoDb")))
7522 (build-system r-build-system)
7524 `(("r-biocgenerics" ,r-biocgenerics)
7525 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7526 ("r-iranges" ,r-iranges)
7527 ("r-rcurl" ,r-rcurl)
7528 ("r-s4vectors" ,r-s4vectors)))
7529 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7530 (synopsis "Utilities for manipulating chromosome identifiers")
7532 "This package contains data and functions that define and allow
7533 translation between different chromosome sequence naming conventions (e.g.,
7534 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7535 names in their natural, rather than lexicographic, order.")
7536 (license license:artistic2.0)))
7538 (define-public r-edger
7544 (uri (bioconductor-uri "edgeR" version))
7547 "15yimsbsxmxhlsfmgw5j7fd8qn08zz4xqxrir1c6n2dc103y22xg"))))
7548 (properties `((upstream-name . "edgeR")))
7549 (build-system r-build-system)
7551 `(("r-limma" ,r-limma)
7552 ("r-locfit" ,r-locfit)
7554 ("r-statmod" ,r-statmod))) ;for estimateDisp
7555 (home-page "http://bioinf.wehi.edu.au/edgeR")
7556 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7557 (description "This package can do differential expression analysis of
7558 RNA-seq expression profiles with biological replication. It implements a range
7559 of statistical methodology based on the negative binomial distributions,
7560 including empirical Bayes estimation, exact tests, generalized linear models
7561 and quasi-likelihood tests. It be applied to differential signal analysis of
7562 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7564 (license license:gpl2+)))
7566 (define-public r-variantannotation
7568 (name "r-variantannotation")
7572 (uri (bioconductor-uri "VariantAnnotation" version))
7575 "19bxi5b9fzqdjadb8bfm8xsgi6nvrwbgn1xcpk59bnmv9vzjkwrh"))))
7577 `((upstream-name . "VariantAnnotation")))
7581 `(("r-annotationdbi" ,r-annotationdbi)
7582 ("r-biobase" ,r-biobase)
7583 ("r-biocgenerics" ,r-biocgenerics)
7584 ("r-biostrings" ,r-biostrings)
7585 ("r-bsgenome" ,r-bsgenome)
7587 ("r-genomeinfodb" ,r-genomeinfodb)
7588 ("r-genomicfeatures" ,r-genomicfeatures)
7589 ("r-genomicranges" ,r-genomicranges)
7590 ("r-iranges" ,r-iranges)
7591 ("r-summarizedexperiment" ,r-summarizedexperiment)
7592 ("r-rsamtools" ,r-rsamtools)
7593 ("r-rtracklayer" ,r-rtracklayer)
7594 ("r-s4vectors" ,r-s4vectors)
7595 ("r-xvector" ,r-xvector)
7596 ("r-zlibbioc" ,r-zlibbioc)))
7597 (build-system r-build-system)
7598 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7599 (synopsis "Package for annotation of genetic variants")
7600 (description "This R package can annotate variants, compute amino acid
7601 coding changes and predict coding outcomes.")
7602 (license license:artistic2.0)))
7604 (define-public r-limma
7610 (uri (bioconductor-uri "limma" version))
7613 "08va8jggmv61wym955mnb1n31mgikrmjys7dl1kp5hp3yia8jg7l"))))
7614 (build-system r-build-system)
7615 (home-page "http://bioinf.wehi.edu.au/limma")
7616 (synopsis "Package for linear models for microarray and RNA-seq data")
7617 (description "This package can be used for the analysis of gene expression
7618 studies, especially the use of linear models for analysing designed experiments
7619 and the assessment of differential expression. The analysis methods apply to
7620 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7621 (license license:gpl2+)))
7623 (define-public r-xvector
7629 (uri (bioconductor-uri "XVector" version))
7632 "01fph1ydd6g0rl5mcw54spx22glq2kqv7wyw8bqw0plmabzcwwdm"))))
7634 `((upstream-name . "XVector")))
7635 (build-system r-build-system)
7638 (modify-phases %standard-phases
7639 (add-after 'unpack 'use-system-zlib
7641 (substitute* "DESCRIPTION"
7642 (("zlibbioc, ") ""))
7643 (substitute* "NAMESPACE"
7644 (("import\\(zlibbioc\\)") ""))
7649 `(("r-biocgenerics" ,r-biocgenerics)
7650 ("r-iranges" ,r-iranges)
7651 ("r-s4vectors" ,r-s4vectors)))
7652 (home-page "https://bioconductor.org/packages/XVector")
7653 (synopsis "Representation and manpulation of external sequences")
7655 "This package provides memory efficient S4 classes for storing sequences
7656 \"externally\" (behind an R external pointer, or on disk).")
7657 (license license:artistic2.0)))
7659 (define-public r-genomicranges
7661 (name "r-genomicranges")
7665 (uri (bioconductor-uri "GenomicRanges" version))
7668 "0bgh14d15dpf2iy36qinw45r6n45rqkf0ghazrdl3jfva6vbrb29"))))
7670 `((upstream-name . "GenomicRanges")))
7671 (build-system r-build-system)
7673 `(("r-biocgenerics" ,r-biocgenerics)
7674 ("r-genomeinfodb" ,r-genomeinfodb)
7675 ("r-iranges" ,r-iranges)
7676 ("r-s4vectors" ,r-s4vectors)
7677 ("r-xvector" ,r-xvector)))
7678 (home-page "https://bioconductor.org/packages/GenomicRanges")
7679 (synopsis "Representation and manipulation of genomic intervals")
7681 "This package provides tools to efficiently represent and manipulate
7682 genomic annotations and alignments is playing a central role when it comes to
7683 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7684 GenomicRanges package defines general purpose containers for storing and
7685 manipulating genomic intervals and variables defined along a genome.")
7686 (license license:artistic2.0)))
7688 (define-public r-biobase
7694 (uri (bioconductor-uri "Biobase" version))
7697 "10nr6nrkj5vlq8hsgbhbhv669z0dbpz4m3vz9k32rx1czbrrqwin"))))
7699 `((upstream-name . "Biobase")))
7700 (build-system r-build-system)
7702 `(("r-biocgenerics" ,r-biocgenerics)))
7703 (home-page "https://bioconductor.org/packages/Biobase")
7704 (synopsis "Base functions for Bioconductor")
7706 "This package provides functions that are needed by many other packages
7707 on Bioconductor or which replace R functions.")
7708 (license license:artistic2.0)))
7710 (define-public r-annotationdbi
7712 (name "r-annotationdbi")
7716 (uri (bioconductor-uri "AnnotationDbi" version))
7719 "1954vimkx5yb9irppq8vssq0f3yjkg36w38b9r0rqmijx1ps7x5d"))))
7721 `((upstream-name . "AnnotationDbi")))
7722 (build-system r-build-system)
7724 `(("r-biobase" ,r-biobase)
7725 ("r-biocgenerics" ,r-biocgenerics)
7727 ("r-iranges" ,r-iranges)
7728 ("r-rsqlite" ,r-rsqlite)
7729 ("r-s4vectors" ,r-s4vectors)))
7730 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7731 (synopsis "Annotation database interface")
7733 "This package provides user interface and database connection code for
7734 annotation data packages using SQLite data storage.")
7735 (license license:artistic2.0)))
7737 (define-public r-biomart
7743 (uri (bioconductor-uri "biomaRt" version))
7746 "1lshkknp7dmr3p6dd2zbv86cc71h53ggh9ji83jcjym8sgbbspl2"))))
7748 `((upstream-name . "biomaRt")))
7749 (build-system r-build-system)
7751 `(("r-annotationdbi" ,r-annotationdbi)
7753 ("r-progress" ,r-progress)
7754 ("r-rcurl" ,r-rcurl)
7755 ("r-stringr" ,r-stringr)
7757 (home-page "https://bioconductor.org/packages/biomaRt")
7758 (synopsis "Interface to BioMart databases")
7760 "biomaRt provides an interface to a growing collection of databases
7761 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7762 package enables retrieval of large amounts of data in a uniform way without
7763 the need to know the underlying database schemas or write complex SQL queries.
7764 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7765 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7766 users direct access to a diverse set of data and enable a wide range of
7767 powerful online queries from gene annotation to database mining.")
7768 (license license:artistic2.0)))
7770 (define-public r-biocparallel
7772 (name "r-biocparallel")
7776 (uri (bioconductor-uri "BiocParallel" version))
7779 "1iv2xzm6lz371z0llhcxl8hmc5jfw0hjwnf1qc8d7jk9djgcaks2"))))
7781 `((upstream-name . "BiocParallel")))
7782 (build-system r-build-system)
7784 `(("r-futile-logger" ,r-futile-logger)
7787 (home-page "https://bioconductor.org/packages/BiocParallel")
7788 (synopsis "Bioconductor facilities for parallel evaluation")
7790 "This package provides modified versions and novel implementation of
7791 functions for parallel evaluation, tailored to use with Bioconductor
7793 (license (list license:gpl2+ license:gpl3+))))
7795 (define-public r-biostrings
7797 (name "r-biostrings")
7801 (uri (bioconductor-uri "Biostrings" version))
7804 "16cqqc8i6gb0jcz0lizfqqxsq7g0yb0ll2s9qzmb45brp07dg8f7"))))
7806 `((upstream-name . "Biostrings")))
7807 (build-system r-build-system)
7809 `(("r-biocgenerics" ,r-biocgenerics)
7810 ("r-iranges" ,r-iranges)
7811 ("r-s4vectors" ,r-s4vectors)
7812 ("r-xvector" ,r-xvector)))
7813 (home-page "https://bioconductor.org/packages/Biostrings")
7814 (synopsis "String objects and algorithms for biological sequences")
7816 "This package provides memory efficient string containers, string
7817 matching algorithms, and other utilities, for fast manipulation of large
7818 biological sequences or sets of sequences.")
7819 (license license:artistic2.0)))
7821 (define-public r-rsamtools
7823 (name "r-rsamtools")
7827 (uri (bioconductor-uri "Rsamtools" version))
7830 "02paq7klabdkaf1b8pmmbpmyqsj3yncnfsz62rgka6r4dpsilwk9"))))
7832 `((upstream-name . "Rsamtools")))
7833 (build-system r-build-system)
7836 (modify-phases %standard-phases
7837 (add-after 'unpack 'use-system-zlib
7839 (substitute* "DESCRIPTION"
7840 (("zlibbioc, ") ""))
7841 (substitute* "NAMESPACE"
7842 (("import\\(zlibbioc\\)") ""))
7847 `(("r-biocgenerics" ,r-biocgenerics)
7848 ("r-biocparallel" ,r-biocparallel)
7849 ("r-biostrings" ,r-biostrings)
7850 ("r-bitops" ,r-bitops)
7851 ("r-genomeinfodb" ,r-genomeinfodb)
7852 ("r-genomicranges" ,r-genomicranges)
7853 ("r-iranges" ,r-iranges)
7854 ("r-s4vectors" ,r-s4vectors)
7855 ("r-xvector" ,r-xvector)))
7856 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7857 (synopsis "Interface to samtools, bcftools, and tabix")
7859 "This package provides an interface to the 'samtools', 'bcftools', and
7860 'tabix' utilities for manipulating SAM (Sequence Alignment / Map), FASTA,
7861 binary variant call (BCF) and compressed indexed tab-delimited (tabix)
7863 (license license:expat)))
7865 (define-public r-delayedarray
7867 (name "r-delayedarray")
7871 (uri (bioconductor-uri "DelayedArray" version))
7874 "0cl5anqkjwvqx19snjhz0zj8cp8ibckiifl28h821h50g62nvb2f"))))
7876 `((upstream-name . "DelayedArray")))
7877 (build-system r-build-system)
7879 `(("r-biocgenerics" ,r-biocgenerics)
7880 ("r-biocparallel" ,r-biocparallel)
7881 ("r-s4vectors" ,r-s4vectors)
7882 ("r-iranges" ,r-iranges)
7883 ("r-matrixstats" ,r-matrixstats)))
7884 (home-page "https://bioconductor.org/packages/DelayedArray")
7885 (synopsis "Delayed operations on array-like objects")
7887 "Wrapping an array-like object (typically an on-disk object) in a
7888 @code{DelayedArray} object allows one to perform common array operations on it
7889 without loading the object in memory. In order to reduce memory usage and
7890 optimize performance, operations on the object are either delayed or executed
7891 using a block processing mechanism. Note that this also works on in-memory
7892 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7893 @code{Matrix} objects, and ordinary arrays and data frames.")
7894 (license license:artistic2.0)))
7896 (define-public r-summarizedexperiment
7898 (name "r-summarizedexperiment")
7902 (uri (bioconductor-uri "SummarizedExperiment" version))
7905 "07805572xhpj5mfwq6kw1ha21wgalqvhh4ydvafyl1bnf3r20vps"))))
7907 `((upstream-name . "SummarizedExperiment")))
7908 (build-system r-build-system)
7910 `(("r-biobase" ,r-biobase)
7911 ("r-biocgenerics" ,r-biocgenerics)
7912 ("r-delayedarray" ,r-delayedarray)
7913 ("r-genomeinfodb" ,r-genomeinfodb)
7914 ("r-genomicranges" ,r-genomicranges)
7915 ("r-iranges" ,r-iranges)
7916 ("r-matrix" ,r-matrix)
7917 ("r-s4vectors" ,r-s4vectors)))
7918 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
7919 (synopsis "Container for representing genomic ranges by sample")
7921 "The SummarizedExperiment container contains one or more assays, each
7922 represented by a matrix-like object of numeric or other mode. The rows
7923 typically represent genomic ranges of interest and the columns represent
7925 (license license:artistic2.0)))
7927 (define-public r-genomicalignments
7929 (name "r-genomicalignments")
7933 (uri (bioconductor-uri "GenomicAlignments" version))
7936 "1maslav2r34wjyzh2nlwa862in1ir7i5xk57nw2nlfh5gqy112jd"))))
7938 `((upstream-name . "GenomicAlignments")))
7939 (build-system r-build-system)
7941 `(("r-biocgenerics" ,r-biocgenerics)
7942 ("r-biocparallel" ,r-biocparallel)
7943 ("r-biostrings" ,r-biostrings)
7944 ("r-genomeinfodb" ,r-genomeinfodb)
7945 ("r-genomicranges" ,r-genomicranges)
7946 ("r-iranges" ,r-iranges)
7947 ("r-rsamtools" ,r-rsamtools)
7948 ("r-s4vectors" ,r-s4vectors)
7949 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7950 (home-page "https://bioconductor.org/packages/GenomicAlignments")
7951 (synopsis "Representation and manipulation of short genomic alignments")
7953 "This package provides efficient containers for storing and manipulating
7954 short genomic alignments (typically obtained by aligning short reads to a
7955 reference genome). This includes read counting, computing the coverage,
7956 junction detection, and working with the nucleotide content of the
7958 (license license:artistic2.0)))
7960 (define-public r-rtracklayer
7962 (name "r-rtracklayer")
7966 (uri (bioconductor-uri "rtracklayer" version))
7969 "1c76g6h9lx2nm7dvb2zp9dmrpk3vanx3zaz6q9clggpj7yj5lmjd"))))
7970 (build-system r-build-system)
7973 (modify-phases %standard-phases
7974 (add-after 'unpack 'use-system-zlib
7976 (substitute* "DESCRIPTION"
7977 ((" zlibbioc,") ""))
7978 (substitute* "NAMESPACE"
7979 (("import\\(zlibbioc\\)") ""))
7982 `(("pkg-config" ,pkg-config)))
7986 `(("r-biocgenerics" ,r-biocgenerics)
7987 ("r-biostrings" ,r-biostrings)
7988 ("r-genomeinfodb" ,r-genomeinfodb)
7989 ("r-genomicalignments" ,r-genomicalignments)
7990 ("r-genomicranges" ,r-genomicranges)
7991 ("r-iranges" ,r-iranges)
7992 ("r-rcurl" ,r-rcurl)
7993 ("r-rsamtools" ,r-rsamtools)
7994 ("r-s4vectors" ,r-s4vectors)
7996 ("r-xvector" ,r-xvector)))
7997 (home-page "https://bioconductor.org/packages/rtracklayer")
7998 (synopsis "R interface to genome browsers and their annotation tracks")
8000 "rtracklayer is an extensible framework for interacting with multiple
8001 genome browsers (currently UCSC built-in) and manipulating annotation tracks
8002 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
8003 built-in). The user may export/import tracks to/from the supported browsers,
8004 as well as query and modify the browser state, such as the current viewport.")
8005 (license license:artistic2.0)))
8007 (define-public r-genomicfeatures
8009 (name "r-genomicfeatures")
8013 (uri (bioconductor-uri "GenomicFeatures" version))
8016 "09gc1vbqszrr3ixv4hsfan2l18fcf3gg58783mrfwjv6ci9c4w0d"))))
8018 `((upstream-name . "GenomicFeatures")))
8019 (build-system r-build-system)
8021 `(("r-annotationdbi" ,r-annotationdbi)
8022 ("r-biobase" ,r-biobase)
8023 ("r-biocgenerics" ,r-biocgenerics)
8024 ("r-biomart" ,r-biomart)
8025 ("r-biostrings" ,r-biostrings)
8027 ("r-genomeinfodb" ,r-genomeinfodb)
8028 ("r-genomicranges" ,r-genomicranges)
8029 ("r-iranges" ,r-iranges)
8030 ("r-rcurl" ,r-rcurl)
8031 ("r-rsqlite" ,r-rsqlite)
8032 ("r-rtracklayer" ,r-rtracklayer)
8033 ("r-s4vectors" ,r-s4vectors)
8034 ("r-xvector" ,r-xvector)))
8035 (home-page "https://bioconductor.org/packages/GenomicFeatures")
8036 (synopsis "Tools for working with transcript centric annotations")
8038 "This package provides a set of tools and methods for making and
8039 manipulating transcript centric annotations. With these tools the user can
8040 easily download the genomic locations of the transcripts, exons and cds of a
8041 given organism, from either the UCSC Genome Browser or a BioMart
8042 database (more sources will be supported in the future). This information is
8043 then stored in a local database that keeps track of the relationship between
8044 transcripts, exons, cds and genes. Flexible methods are provided for
8045 extracting the desired features in a convenient format.")
8046 (license license:artistic2.0)))
8048 (define-public r-go-db
8054 (uri (string-append "https://www.bioconductor.org/packages/"
8055 "release/data/annotation/src/contrib/GO.db_"
8059 "0i3wcf5h3n0dawzc1hy0kv74f06j80c47n4p3g3fmrcxlhi3jpa5"))))
8061 `((upstream-name . "GO.db")))
8062 (build-system r-build-system)
8064 `(("r-annotationdbi" ,r-annotationdbi)))
8065 (home-page "https://bioconductor.org/packages/GO.db")
8066 (synopsis "Annotation maps describing the entire Gene Ontology")
8068 "The purpose of this GO.db annotation package is to provide detailed
8069 information about the latest version of the Gene Ontologies.")
8070 (license license:artistic2.0)))
8072 (define-public r-topgo
8078 (uri (bioconductor-uri "topGO" version))
8081 "1j1jcd16j564kr6qz28140fzmnh9xasi84v1c1fi98sqv30zq9bh"))))
8083 `((upstream-name . "topGO")))
8084 (build-system r-build-system)
8086 `(("r-annotationdbi" ,r-annotationdbi)
8088 ("r-biobase" ,r-biobase)
8089 ("r-biocgenerics" ,r-biocgenerics)
8090 ("r-go-db" ,r-go-db)
8091 ("r-graph" ,r-graph)
8092 ("r-lattice" ,r-lattice)
8093 ("r-matrixstats" ,r-matrixstats)
8094 ("r-sparsem" ,r-sparsem)))
8095 (home-page "https://bioconductor.org/packages/topGO")
8096 (synopsis "Enrichment analysis for gene ontology")
8098 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
8099 terms while accounting for the topology of the GO graph. Different test
8100 statistics and different methods for eliminating local similarities and
8101 dependencies between GO terms can be implemented and applied.")
8102 ;; Any version of the LGPL applies.
8103 (license license:lgpl2.1+)))
8105 (define-public r-bsgenome
8111 (uri (bioconductor-uri "BSgenome" version))
8114 "07z4zxx0khrc86qqvc7vxww8df9fh6pyks9ajxkc9gdqr5nn79j7"))))
8116 `((upstream-name . "BSgenome")))
8117 (build-system r-build-system)
8119 `(("r-biocgenerics" ,r-biocgenerics)
8120 ("r-biostrings" ,r-biostrings)
8121 ("r-genomeinfodb" ,r-genomeinfodb)
8122 ("r-genomicranges" ,r-genomicranges)
8123 ("r-iranges" ,r-iranges)
8124 ("r-rsamtools" ,r-rsamtools)
8125 ("r-rtracklayer" ,r-rtracklayer)
8126 ("r-s4vectors" ,r-s4vectors)
8127 ("r-xvector" ,r-xvector)))
8128 (home-page "https://bioconductor.org/packages/BSgenome")
8129 (synopsis "Infrastructure for Biostrings-based genome data packages")
8131 "This package provides infrastructure shared by all Biostrings-based
8132 genome data packages and support for efficient SNP representation.")
8133 (license license:artistic2.0)))
8135 (define-public r-impute
8141 (uri (bioconductor-uri "impute" version))
8144 "08z0pj1dz5iq967nwj67qyka7ir7m5an2ggv7bsrlz3apzfsla33"))))
8146 `(("gfortran" ,gfortran)))
8147 (build-system r-build-system)
8148 (home-page "https://bioconductor.org/packages/impute")
8149 (synopsis "Imputation for microarray data")
8151 "This package provides a function to impute missing gene expression
8152 microarray data, using nearest neighbor averaging.")
8153 (license license:gpl2+)))
8155 (define-public r-seqpattern
8157 (name "r-seqpattern")
8161 (uri (bioconductor-uri "seqPattern" version))
8164 "0di83qi83mrlw7i12khsq55d03hlazcywaa9m9pki1sfhafpq733"))))
8166 `((upstream-name . "seqPattern")))
8167 (build-system r-build-system)
8169 `(("r-biostrings" ,r-biostrings)
8170 ("r-genomicranges" ,r-genomicranges)
8171 ("r-iranges" ,r-iranges)
8172 ("r-kernsmooth" ,r-kernsmooth)
8173 ("r-plotrix" ,r-plotrix)))
8174 (home-page "https://bioconductor.org/packages/seqPattern")
8175 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
8177 "This package provides tools to visualize oligonucleotide patterns and
8178 sequence motif occurrences across a large set of sequences centred at a common
8179 reference point and sorted by a user defined feature.")
8180 (license license:gpl3+)))
8182 (define-public r-genomation
8184 (name "r-genomation")
8188 (uri (bioconductor-uri "genomation" version))
8191 "0g0v4alfpqlinqinjnyzl3mrjnpbdx9ri34mcaiqbvbvg8ic8wvg"))))
8192 (build-system r-build-system)
8194 `(("r-biostrings" ,r-biostrings)
8195 ("r-bsgenome" ,r-bsgenome)
8196 ("r-data-table" ,r-data-table)
8197 ("r-genomeinfodb" ,r-genomeinfodb)
8198 ("r-genomicalignments" ,r-genomicalignments)
8199 ("r-genomicranges" ,r-genomicranges)
8200 ("r-ggplot2" ,r-ggplot2)
8201 ("r-gridbase" ,r-gridbase)
8202 ("r-impute" ,r-impute)
8203 ("r-iranges" ,r-iranges)
8204 ("r-matrixstats" ,r-matrixstats)
8205 ("r-plotrix" ,r-plotrix)
8208 ("r-readr" ,r-readr)
8209 ("r-reshape2" ,r-reshape2)
8210 ("r-rsamtools" ,r-rsamtools)
8211 ("r-rtracklayer" ,r-rtracklayer)
8212 ("r-runit" ,r-runit)
8213 ("r-s4vectors" ,r-s4vectors)
8214 ("r-seqpattern" ,r-seqpattern)))
8215 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8216 (synopsis "Summary, annotation and visualization of genomic data")
8218 "This package provides a package for summary and annotation of genomic
8219 intervals. Users can visualize and quantify genomic intervals over
8220 pre-defined functional regions, such as promoters, exons, introns, etc. The
8221 genomic intervals represent regions with a defined chromosome position, which
8222 may be associated with a score, such as aligned reads from HT-seq experiments,
8223 TF binding sites, methylation scores, etc. The package can use any tabular
8224 genomic feature data as long as it has minimal information on the locations of
8225 genomic intervals. In addition, it can use BAM or BigWig files as input.")
8226 (license license:artistic2.0)))
8228 (define-public r-genomationdata
8230 (name "r-genomationdata")
8234 ;; We cannot use bioconductor-uri here because this tarball is
8235 ;; located under "data/annotation/" instead of "bioc/".
8236 (uri (string-append "https://bioconductor.org/packages/"
8237 "release/data/experiment/src/contrib/"
8238 "genomationData_" version ".tar.gz"))
8241 "10xyb8akjrhmak2i0mnv1agny2ipy364q9nlibyplpzc7vdb6bw7"))))
8242 (build-system r-build-system)
8243 ;; As this package provides little more than large data files, it doesn't
8244 ;; make sense to build substitutes.
8245 (arguments `(#:substitutable? #f))
8247 `(("r-knitr" ,r-knitr)))
8248 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8249 (synopsis "Experimental data for use with the genomation package")
8251 "This package contains experimental genetic data for use with the
8252 genomation package. Included are Chip Seq, Methylation and Cage data,
8253 downloaded from Encode.")
8254 (license license:gpl3+)))
8256 (define-public r-seqlogo
8263 (uri (bioconductor-uri "seqLogo" version))
8266 "022vr9ydwcivs7rw7kwj73gfk5gc7ckwa1q66vhd4kw9ylh70v68"))))
8267 (properties `((upstream-name . "seqLogo")))
8268 (build-system r-build-system)
8269 (home-page "https://bioconductor.org/packages/seqLogo")
8270 (synopsis "Sequence logos for DNA sequence alignments")
8272 "seqLogo takes the position weight matrix of a DNA sequence motif and
8273 plots the corresponding sequence logo as introduced by Schneider and
8275 (license license:lgpl2.0+)))
8277 (define-public r-motifrg
8284 (uri (bioconductor-uri "motifRG" version))
8287 "1wxww6i0jgyapqclcwy0zzf9kqjvrvylr89z7yhg1izi7jnw2fka"))))
8288 (properties `((upstream-name . "motifRG")))
8289 (build-system r-build-system)
8291 `(("r-biostrings" ,r-biostrings)
8292 ("r-bsgenome" ,r-bsgenome)
8293 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8294 ("r-iranges" ,r-iranges)
8295 ("r-seqlogo" ,r-seqlogo)
8296 ("r-xvector" ,r-xvector)))
8297 (home-page "https://bioconductor.org/packages/motifRG")
8298 (synopsis "Discover motifs in high throughput sequencing data")
8300 "This package provides tools for discriminative motif discovery in high
8301 throughput genetic sequencing data sets using regression methods.")
8302 (license license:artistic2.0)))
8304 (define-public r-qtl
8311 (uri (string-append "mirror://cran/src/contrib/qtl_"
8315 "03lmvydln8b7666b6w46qbryhf83vsd11d4y2v95rfgvqgq66l1i"))))
8316 (build-system r-build-system)
8317 (home-page "http://rqtl.org/")
8318 (synopsis "R package for analyzing QTL experiments in genetics")
8319 (description "R/qtl is an extension library for the R statistics
8320 system. It is used to analyze experimental crosses for identifying
8321 genes contributing to variation in quantitative traits (so-called
8322 quantitative trait loci, QTLs).
8324 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
8325 identify genotyping errors, and to perform single-QTL and two-QTL,
8326 two-dimensional genome scans.")
8327 (license license:gpl3)))
8329 (define-public r-zlibbioc
8335 (uri (bioconductor-uri "zlibbioc" version))
8338 "0bjvzy24kab7ank02cc1qk2ikcz4dllgf66wpsdl0d3zp4gn3l2h"))))
8340 `((upstream-name . "zlibbioc")))
8341 (build-system r-build-system)
8342 (home-page "https://bioconductor.org/packages/zlibbioc")
8343 (synopsis "Provider for zlib-1.2.5 to R packages")
8344 (description "This package uses the source code of zlib-1.2.5 to create
8345 libraries for systems that do not have these available via other means.")
8346 (license license:artistic2.0)))
8348 (define-public r-r4rna
8355 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8359 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8360 (build-system r-build-system)
8362 `(("r-optparse" ,r-optparse)
8363 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8364 (home-page "http://www.e-rna.org/r-chie/index.cgi")
8365 (synopsis "Analysis framework for RNA secondary structure")
8367 "The R4RNA package aims to be a general framework for the analysis of RNA
8368 secondary structure and comparative analysis in R.")
8369 (license license:gpl3+)))
8371 (define-public r-rhtslib
8378 (uri (bioconductor-uri "Rhtslib" version))
8381 "13fv78sk5g0gqfl3ks3rps3zc1k66a4lzxvgn36r7ix43yxk7hnr"))))
8382 (properties `((upstream-name . "Rhtslib")))
8383 (build-system r-build-system)
8385 `(("r-zlibbioc" ,r-zlibbioc)))
8389 `(("pkg-config" ,pkg-config)))
8390 (home-page "https://github.com/nhayden/Rhtslib")
8391 (synopsis "High-throughput sequencing library as an R package")
8393 "This package provides the HTSlib C library for high-throughput
8394 nucleotide sequence analysis. The package is primarily useful to developers
8395 of other R packages who wish to make use of HTSlib.")
8396 (license license:lgpl2.0+)))
8398 (define-public r-bamsignals
8400 (name "r-bamsignals")
8405 (uri (bioconductor-uri "bamsignals" version))
8408 "19irfx1y1izf903vq59wxsdbf88g143zy9l89gxqawh7jfxds8w8"))))
8409 (build-system r-build-system)
8411 `(("r-biocgenerics" ,r-biocgenerics)
8412 ("r-genomicranges" ,r-genomicranges)
8413 ("r-iranges" ,r-iranges)
8415 ("r-rhtslib" ,r-rhtslib)
8416 ("r-zlibbioc" ,r-zlibbioc)))
8419 (home-page "https://bioconductor.org/packages/bamsignals")
8420 (synopsis "Extract read count signals from bam files")
8422 "This package allows to efficiently obtain count vectors from indexed bam
8423 files. It counts the number of nucleotide sequence reads in given genomic
8424 ranges and it computes reads profiles and coverage profiles. It also handles
8426 (license license:gpl2+)))
8428 (define-public r-rcas
8434 (uri (bioconductor-uri "RCAS" version))
8437 "0ss5hcg2m7gjji6dd23zxa5bd5a7knwcnada4qs5q2l4clgk39ad"))))
8438 (build-system r-build-system)
8440 `(("r-annotationdbi" ,r-annotationdbi)
8441 ("r-biocgenerics" ,r-biocgenerics)
8442 ("r-biomart" ,r-biomart)
8443 ("r-biostrings" ,r-biostrings)
8444 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8445 ("r-cowplot" ,r-cowplot)
8446 ("r-data-table" ,r-data-table)
8449 ("r-genomation" ,r-genomation)
8450 ("r-genomeinfodb" ,r-genomeinfodb)
8451 ("r-genomicfeatures" ,r-genomicfeatures)
8452 ("r-genomicranges" ,r-genomicranges)
8453 ("r-ggplot2" ,r-ggplot2)
8454 ("r-ggseqlogo" ,r-ggseqlogo)
8455 ("r-knitr" ,r-knitr)
8456 ("r-motifrg" ,r-motifrg)
8457 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8458 ("r-pbapply" ,r-pbapply)
8459 ("r-pheatmap" ,r-pheatmap)
8460 ("r-plotly" ,r-plotly)
8461 ("r-plotrix" ,r-plotrix)
8462 ("r-proxy" ,r-proxy)
8463 ("r-rsqlite" ,r-rsqlite)
8464 ("r-rtracklayer" ,r-rtracklayer)
8465 ("r-rmarkdown" ,r-rmarkdown)
8466 ("r-s4vectors" ,r-s4vectors)
8467 ("r-topgo" ,r-topgo)))
8468 (synopsis "RNA-centric annotation system")
8470 "RCAS aims to be a standalone RNA-centric annotation system that provides
8471 intuitive reports and publication-ready graphics. This package provides the R
8472 library implementing most of the pipeline's features.")
8473 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8474 (license license:artistic2.0)))
8476 (define-public rcas-web
8483 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8484 "releases/download/v" version
8485 "/rcas-web-" version ".tar.gz"))
8488 "0wq951aj45gqki1bickg876i993lmawkp8x24agg264br5x716db"))))
8489 (build-system gnu-build-system)
8492 (modify-phases %standard-phases
8493 (add-after 'install 'wrap-executable
8494 (lambda* (#:key inputs outputs #:allow-other-keys)
8495 (let* ((out (assoc-ref outputs "out"))
8496 (json (assoc-ref inputs "guile-json"))
8497 (redis (assoc-ref inputs "guile-redis"))
8498 (path (string-append
8499 json "/share/guile/site/2.2:"
8500 redis "/share/guile/site/2.2")))
8501 (wrap-program (string-append out "/bin/rcas-web")
8502 `("GUILE_LOAD_PATH" ":" = (,path))
8503 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8504 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8507 `(("r-minimal" ,r-minimal)
8509 ("guile-next" ,guile-2.2)
8510 ("guile-json" ,guile-json)
8511 ("guile-redis" ,guile-redis)))
8513 `(("pkg-config" ,pkg-config)))
8514 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8515 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8516 (description "This package provides a simple web interface for the
8517 @dfn{RNA-centric annotation system} (RCAS).")
8518 (license license:agpl3+)))
8520 (define-public r-mutationalpatterns
8522 (name "r-mutationalpatterns")
8527 (uri (bioconductor-uri "MutationalPatterns" version))
8530 "0w9lg1zs106h6rqvy8mhikq6q6q9syw6c1prcxr38ssh85rcih12"))))
8531 (build-system r-build-system)
8533 `(("r-biocgenerics" ,r-biocgenerics)
8534 ("r-biostrings" ,r-biostrings)
8535 ;; These two packages are suggested packages
8536 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8537 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8538 ("r-genomicranges" ,r-genomicranges)
8539 ("r-genomeinfodb" ,r-genomeinfodb)
8540 ("r-ggplot2" ,r-ggplot2)
8541 ("r-iranges" ,r-iranges)
8544 ("r-pracma" ,r-pracma)
8545 ("r-reshape2" ,r-reshape2)
8546 ("r-cowplot" ,r-cowplot)
8547 ("r-ggdendro" ,r-ggdendro)
8548 ("r-s4vectors" ,r-s4vectors)
8549 ("r-summarizedexperiment" ,r-summarizedexperiment)
8550 ("r-variantannotation" ,r-variantannotation)))
8551 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8552 (synopsis "Extract and visualize mutational patterns in genomic data")
8553 (description "This package provides an extensive toolset for the
8554 characterization and visualization of a wide range of mutational patterns
8555 in SNV base substitution data.")
8556 (license license:expat)))
8558 (define-public r-wgcna
8565 (uri (cran-uri "WGCNA" version))
8568 "0rhnyhzfn93yp24jz9v6dzrmyizwzdw070a7idm0k33w1cm8sjqv"))))
8569 (properties `((upstream-name . "WGCNA")))
8570 (build-system r-build-system)
8572 `(("r-annotationdbi" ,r-annotationdbi)
8573 ("r-doparallel" ,r-doparallel)
8574 ("r-dynamictreecut" ,r-dynamictreecut)
8575 ("r-fastcluster" ,r-fastcluster)
8576 ("r-foreach" ,r-foreach)
8577 ("r-go-db" ,r-go-db)
8578 ("r-hmisc" ,r-hmisc)
8579 ("r-impute" ,r-impute)
8581 ("r-robust" ,r-robust)
8582 ("r-survival" ,r-survival)
8583 ("r-matrixstats" ,r-matrixstats)
8584 ("r-preprocesscore" ,r-preprocesscore)))
8586 "http://www.genetics.ucla.edu/labs/horvath/CoexpressionNetwork/Rpackages/WGCNA/")
8587 (synopsis "Weighted correlation network analysis")
8589 "This package provides functions necessary to perform Weighted
8590 Correlation Network Analysis on high-dimensional data. It includes functions
8591 for rudimentary data cleaning, construction and summarization of correlation
8592 networks, module identification and functions for relating both variables and
8593 modules to sample traits. It also includes a number of utility functions for
8594 data manipulation and visualization.")
8595 (license license:gpl2+)))
8597 (define-public r-chipkernels
8598 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8601 (name "r-chipkernels")
8602 (version (string-append "1.1-" revision "." (string-take commit 9)))
8607 (url "https://github.com/ManuSetty/ChIPKernels.git")
8609 (file-name (string-append name "-" version))
8612 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8613 (build-system r-build-system)
8615 `(("r-iranges" ,r-iranges)
8616 ("r-xvector" ,r-xvector)
8617 ("r-biostrings" ,r-biostrings)
8618 ("r-bsgenome" ,r-bsgenome)
8619 ("r-gtools" ,r-gtools)
8620 ("r-genomicranges" ,r-genomicranges)
8621 ("r-sfsmisc" ,r-sfsmisc)
8622 ("r-kernlab" ,r-kernlab)
8623 ("r-s4vectors" ,r-s4vectors)
8624 ("r-biocgenerics" ,r-biocgenerics)))
8625 (home-page "https://github.com/ManuSetty/ChIPKernels")
8626 (synopsis "Build string kernels for DNA Sequence analysis")
8627 (description "ChIPKernels is an R package for building different string
8628 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8629 must be built and this dictionary can be used for determining kernels for DNA
8631 (license license:gpl2+))))
8633 (define-public r-seqgl
8641 (url "https://github.com/ManuSetty/SeqGL.git")
8643 (file-name (git-file-name name version))
8646 "1r6ywvhxl3ffv48lgj7sbd582mcc6dha3ksgc2qjlvjrnkbj3799"))))
8647 (build-system r-build-system)
8649 `(("r-biostrings" ,r-biostrings)
8650 ("r-chipkernels" ,r-chipkernels)
8651 ("r-genomicranges" ,r-genomicranges)
8652 ("r-spams" ,r-spams)
8653 ("r-wgcna" ,r-wgcna)
8654 ("r-fastcluster" ,r-fastcluster)))
8655 (home-page "https://github.com/ManuSetty/SeqGL")
8656 (synopsis "Group lasso for Dnase/ChIP-seq data")
8657 (description "SeqGL is a group lasso based algorithm to extract
8658 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8659 This package presents a method which uses group lasso to discriminate between
8660 bound and non bound genomic regions to accurately identify transcription
8661 factors bound at the specific regions.")
8662 (license license:gpl2+)))
8664 (define-public r-gkmsvm
8671 (uri (cran-uri "gkmSVM" version))
8674 "04dakbgfvfalz4rm4fvvybp506dn5fbj5g86ybfhrc6wywjllsz3"))))
8675 (properties `((upstream-name . "gkmSVM")))
8676 (build-system r-build-system)
8678 `(("r-biocgenerics" ,r-biocgenerics)
8679 ("r-biostrings" ,r-biostrings)
8680 ("r-genomeinfodb" ,r-genomeinfodb)
8681 ("r-genomicranges" ,r-genomicranges)
8682 ("r-iranges" ,r-iranges)
8683 ("r-kernlab" ,r-kernlab)
8686 ("r-rtracklayer" ,r-rtracklayer)
8687 ("r-s4vectors" ,r-s4vectors)
8688 ("r-seqinr" ,r-seqinr)))
8689 (home-page "https://cran.r-project.org/web/packages/gkmSVM")
8690 (synopsis "Gapped-kmer support vector machine")
8692 "This R package provides tools for training gapped-kmer SVM classifiers
8693 for DNA and protein sequences. This package supports several sequence
8694 kernels, including: gkmSVM, kmer-SVM, mismatch kernel and wildcard kernel.")
8695 (license license:gpl2+)))
8697 (define-public r-tximport
8703 (uri (bioconductor-uri "tximport" version))
8706 "16wp09dm0cpb4mc00nmglfb8ica7qb4a55vm8ajgzyagbpfdd44l"))))
8707 (build-system r-build-system)
8708 (home-page "https://bioconductor.org/packages/tximport")
8709 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8711 "This package provides tools to import transcript-level abundance,
8712 estimated counts and transcript lengths, and to summarize them into matrices
8713 for use with downstream gene-level analysis packages. Average transcript
8714 length, weighted by sample-specific transcript abundance estimates, is
8715 provided as a matrix which can be used as an offset for different expression
8716 of gene-level counts.")
8717 (license license:gpl2+)))
8719 (define-public r-rhdf5
8725 (uri (bioconductor-uri "rhdf5" version))
8728 "10zkw3k13wmvyif417gplyf6rwp2gpkjasw97lhwv2f9i32rry9l"))))
8729 (build-system r-build-system)
8731 `(("r-rhdf5lib" ,r-rhdf5lib)))
8734 (home-page "https://bioconductor.org/packages/rhdf5")
8735 (synopsis "HDF5 interface to R")
8737 "This R/Bioconductor package provides an interface between HDF5 and R.
8738 HDF5's main features are the ability to store and access very large and/or
8739 complex datasets and a wide variety of metadata on mass storage (disk) through
8740 a completely portable file format. The rhdf5 package is thus suited for the
8741 exchange of large and/or complex datasets between R and other software
8742 package, and for letting R applications work on datasets that are larger than
8743 the available RAM.")
8744 (license license:artistic2.0)))
8746 (define-public r-annotationfilter
8748 (name "r-annotationfilter")
8752 (uri (bioconductor-uri "AnnotationFilter" version))
8755 "0wrr10cxjzmxx46vjzq2nsf6xlqz1sqwx4xm0sk3d77ff8wmph4x"))))
8757 `((upstream-name . "AnnotationFilter")))
8758 (build-system r-build-system)
8760 `(("r-genomicranges" ,r-genomicranges)
8761 ("r-lazyeval" ,r-lazyeval)))
8762 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8763 (synopsis "Facilities for filtering Bioconductor annotation resources")
8765 "This package provides classes and other infrastructure to implement
8766 filters for manipulating Bioconductor annotation resources. The filters are
8767 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8768 (license license:artistic2.0)))
8770 (define-public emboss
8776 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8777 (version-major+minor version) ".0/"
8778 "EMBOSS-" version ".tar.gz"))
8781 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8782 (build-system gnu-build-system)
8785 (list (string-append "--with-hpdf="
8786 (assoc-ref %build-inputs "libharu")))
8788 (modify-phases %standard-phases
8789 (add-after 'unpack 'fix-checks
8791 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8792 ;; and zlib, but assume that they are all found at the same
8794 (substitute* "configure.in"
8795 (("CHECK_PNGDRIVER")
8796 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8797 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8798 AM_CONDITIONAL(AMPNG, true)"))
8800 (add-after 'fix-checks 'disable-update-check
8802 ;; At build time there is no connection to the Internet, so
8803 ;; looking for updates will not work.
8804 (substitute* "Makefile.am"
8805 (("\\$\\(bindir\\)/embossupdate") ""))
8807 (add-after 'disable-update-check 'autogen
8808 (lambda _ (invoke "autoreconf" "-vif") #t)))))
8814 ("libharu" ,libharu)
8817 `(("autoconf" ,autoconf)
8818 ("automake" ,automake)
8819 ("libtool" ,libtool)
8820 ("pkg-config" ,pkg-config)))
8821 (home-page "http://emboss.sourceforge.net")
8822 (synopsis "Molecular biology analysis suite")
8823 (description "EMBOSS is the \"European Molecular Biology Open Software
8824 Suite\". EMBOSS is an analysis package specially developed for the needs of
8825 the molecular biology (e.g. EMBnet) user community. The software
8826 automatically copes with data in a variety of formats and even allows
8827 transparent retrieval of sequence data from the web. It also provides a
8828 number of libraries for the development of software in the field of molecular
8829 biology. EMBOSS also integrates a range of currently available packages and
8830 tools for sequence analysis into a seamless whole.")
8831 (license license:gpl2+)))
8834 (let ((revision "1")
8835 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8838 ;; The version is 2.13.0 even though no release archives have been
8839 ;; published as yet.
8840 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8844 (url "https://github.com/arq5x/bits.git")
8846 (file-name (string-append name "-" version "-checkout"))
8849 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8850 (build-system gnu-build-system)
8852 `(#:tests? #f ;no tests included
8854 (modify-phases %standard-phases
8856 (add-after 'unpack 'remove-cuda
8858 (substitute* "Makefile"
8860 (("(bits_test_intersections) \\\\" _ match) match))
8863 (lambda* (#:key outputs #:allow-other-keys)
8865 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8870 (home-page "https://github.com/arq5x/bits")
8871 (synopsis "Implementation of binary interval search algorithm")
8872 (description "This package provides an implementation of the
8873 BITS (Binary Interval Search) algorithm, an approach to interval set
8874 intersection. It is especially suited for the comparison of diverse genomic
8875 datasets and the exploration of large datasets of genome
8876 intervals (e.g. genes, sequence alignments).")
8877 (license license:gpl2))))
8879 (define-public piranha
8880 ;; There is no release tarball for the latest version. The latest commit is
8881 ;; older than one year at the time of this writing.
8882 (let ((revision "1")
8883 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8886 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8890 (url "https://github.com/smithlabcode/piranha.git")
8892 (file-name (git-file-name name version))
8895 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
8896 (build-system gnu-build-system)
8898 `(#:test-target "test"
8900 (modify-phases %standard-phases
8901 (add-after 'unpack 'copy-smithlab-cpp
8902 (lambda* (#:key inputs #:allow-other-keys)
8903 (for-each (lambda (file)
8904 (install-file file "./src/smithlab_cpp/"))
8905 (find-files (assoc-ref inputs "smithlab-cpp")))
8907 (add-after 'install 'install-to-store
8908 (lambda* (#:key outputs #:allow-other-keys)
8909 (let* ((out (assoc-ref outputs "out"))
8910 (bin (string-append out "/bin")))
8911 (for-each (lambda (file)
8912 (install-file file bin))
8913 (find-files "bin" ".*")))
8916 (list (string-append "--with-bam_tools_headers="
8917 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
8918 (string-append "--with-bam_tools_library="
8919 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
8921 `(("bamtools" ,bamtools)
8922 ("samtools" ,samtools-0.1)
8925 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8929 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8931 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8934 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8936 `(("python" ,python-2)))
8937 (home-page "https://github.com/smithlabcode/piranha")
8938 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
8940 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
8941 RIP-seq experiments. It takes input in BED or BAM format and identifies
8942 regions of statistically significant read enrichment. Additional covariates
8943 may optionally be provided to further inform the peak-calling process.")
8944 (license license:gpl3+))))
8952 (uri (pypi-uri "PePr" version))
8955 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
8956 (build-system python-build-system)
8958 `(#:python ,python-2 ; python2 only
8959 #:tests? #f)) ; no tests included
8961 `(("python2-numpy" ,python2-numpy)
8962 ("python2-scipy" ,python2-scipy)
8963 ("python2-pysam" ,python2-pysam)))
8964 (home-page "https://github.com/shawnzhangyx/PePr")
8965 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
8967 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
8968 that is primarily designed for data with biological replicates. It uses a
8969 negative binomial distribution to model the read counts among the samples in
8970 the same group, and look for consistent differences between ChIP and control
8971 group or two ChIP groups run under different conditions.")
8972 (license license:gpl3+)))
8974 (define-public filevercmp
8975 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
8978 (version (string-append "0-1." (string-take commit 7)))
8982 (url "https://github.com/ekg/filevercmp.git")
8984 (file-name (git-file-name name commit))
8987 "1j9vxsy0y050v59h0q1d6501fcw1kjvj0d18l1xk2zyg0jzj247c"))))
8988 (build-system gnu-build-system)
8990 `(#:tests? #f ; There are no tests to run.
8992 (modify-phases %standard-phases
8993 (delete 'configure) ; There is no configure phase.
8995 (lambda* (#:key outputs #:allow-other-keys)
8996 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
8997 (install-file "filevercmp" bin)
8999 (home-page "https://github.com/ekg/filevercmp")
9000 (synopsis "This program compares version strings")
9001 (description "This program compares version strings. It intends to be a
9002 replacement for strverscmp.")
9003 (license license:gpl3+))))
9005 (define-public multiqc
9012 (uri (pypi-uri "multiqc" version))
9015 "02iihfl0w0hpnr4pa0sbd1y9qxrg3ycyhjp5lidkcrqh1lmzs3zy"))))
9016 (build-system python-build-system)
9018 `(("python-jinja2" ,python-jinja2)
9019 ("python-simplejson" ,python-simplejson)
9020 ("python-pyyaml" ,python-pyyaml)
9021 ("python-click" ,python-click)
9022 ("python-spectra" ,python-spectra)
9023 ("python-requests" ,python-requests)
9024 ("python-markdown" ,python-markdown)
9025 ("python-lzstring" ,python-lzstring)
9026 ("python-matplotlib" ,python-matplotlib)
9027 ("python-numpy" ,python-numpy)
9028 ;; MultQC checks for the presence of nose at runtime.
9029 ("python-nose" ,python-nose)))
9032 (modify-phases %standard-phases
9033 (add-after 'unpack 'relax-requirements
9035 (substitute* "setup.py"
9036 ;; MultiQC 1.5 ‘requires’ a version of python-matplotlib older
9037 ;; than the one in Guix, but should work fine with 2.2.2.
9038 ;; See <https://github.com/ewels/MultiQC/issues/725> and
9039 ;; <https://github.com/ewels/MultiQC/issues/732> for details.
9040 (("['\"]matplotlib.*?['\"]")
9043 (home-page "http://multiqc.info")
9044 (synopsis "Aggregate bioinformatics analysis reports")
9046 "MultiQC is a tool to aggregate bioinformatics results across many
9047 samples into a single report. It contains modules for a large number of
9048 common bioinformatics tools.")
9049 (license license:gpl3+)))
9051 (define-public r-chipseq
9058 (uri (bioconductor-uri "chipseq" version))
9061 "1pp1rm5fs3hlar5x4dl3a3b4gara7qwf81dbvka6r1n78hrf9x1b"))))
9062 (build-system r-build-system)
9064 `(("r-biocgenerics" ,r-biocgenerics)
9065 ("r-genomicranges" ,r-genomicranges)
9066 ("r-iranges" ,r-iranges)
9067 ("r-lattice" ,r-lattice)
9068 ("r-s4vectors" ,r-s4vectors)
9069 ("r-shortread" ,r-shortread)))
9070 (home-page "https://bioconductor.org/packages/chipseq")
9071 (synopsis "Package for analyzing ChIPseq data")
9073 "This package provides tools for processing short read data from ChIPseq
9075 (license license:artistic2.0)))
9077 (define-public r-copyhelper
9079 (name "r-copyhelper")
9084 (uri (string-append "https://bioconductor.org/packages/release/"
9085 "data/experiment/src/contrib/CopyhelpeR_"
9089 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
9090 (properties `((upstream-name . "CopyhelpeR")))
9091 (build-system r-build-system)
9092 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
9093 (synopsis "Helper files for CopywriteR")
9095 "This package contains the helper files that are required to run the
9096 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
9097 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
9098 mm10. In addition, it contains a blacklist filter to remove regions that
9099 display copy number variation. Files are stored as GRanges objects from the
9100 GenomicRanges Bioconductor package.")
9101 (license license:gpl2)))
9103 (define-public r-copywriter
9105 (name "r-copywriter")
9110 (uri (bioconductor-uri "CopywriteR" version))
9113 "1hbiw0m9hmx4na9v502pxf8y5wvxzr68r4d3fqr2755gxx86qck6"))))
9114 (properties `((upstream-name . "CopywriteR")))
9115 (build-system r-build-system)
9117 `(("r-biocparallel" ,r-biocparallel)
9118 ("r-chipseq" ,r-chipseq)
9119 ("r-copyhelper" ,r-copyhelper)
9120 ("r-data-table" ,r-data-table)
9121 ("r-dnacopy" ,r-dnacopy)
9122 ("r-futile-logger" ,r-futile-logger)
9123 ("r-genomeinfodb" ,r-genomeinfodb)
9124 ("r-genomicalignments" ,r-genomicalignments)
9125 ("r-genomicranges" ,r-genomicranges)
9126 ("r-gtools" ,r-gtools)
9127 ("r-iranges" ,r-iranges)
9128 ("r-matrixstats" ,r-matrixstats)
9129 ("r-rsamtools" ,r-rsamtools)
9130 ("r-s4vectors" ,r-s4vectors)))
9131 (home-page "https://github.com/PeeperLab/CopywriteR")
9132 (synopsis "Copy number information from targeted sequencing")
9134 "CopywriteR extracts DNA copy number information from targeted sequencing
9135 by utilizing off-target reads. It allows for extracting uniformly distributed
9136 copy number information, can be used without reference, and can be applied to
9137 sequencing data obtained from various techniques including chromatin
9138 immunoprecipitation and target enrichment on small gene panels. Thereby,
9139 CopywriteR constitutes a widely applicable alternative to available copy
9140 number detection tools.")
9141 (license license:gpl2)))
9143 (define-public r-methylkit
9145 (name "r-methylkit")
9149 (uri (bioconductor-uri "methylKit" version))
9152 "1zcfwy7i10aqgnf7r0c41hakb5aai3s3n9y8pc6a98vimz51ly2z"))))
9153 (properties `((upstream-name . "methylKit")))
9154 (build-system r-build-system)
9156 `(("r-data-table" ,r-data-table)
9157 ("r-emdbook" ,r-emdbook)
9158 ("r-fastseg" ,r-fastseg)
9159 ("r-genomeinfodb" ,r-genomeinfodb)
9160 ("r-genomicranges" ,r-genomicranges)
9161 ("r-gtools" ,r-gtools)
9162 ("r-iranges" ,r-iranges)
9163 ("r-kernsmooth" ,r-kernsmooth)
9164 ("r-limma" ,r-limma)
9165 ("r-mclust" ,r-mclust)
9166 ("r-qvalue" ,r-qvalue)
9167 ("r-r-utils" ,r-r-utils)
9169 ("r-rhtslib" ,r-rhtslib)
9170 ("r-rsamtools" ,r-rsamtools)
9171 ("r-rtracklayer" ,r-rtracklayer)
9172 ("r-s4vectors" ,r-s4vectors)
9173 ("r-zlibbioc" ,r-zlibbioc)))
9176 (home-page "https://github.com/al2na/methylKit")
9178 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9180 "MethylKit is an R package for DNA methylation analysis and annotation
9181 from high-throughput bisulfite sequencing. The package is designed to deal
9182 with sequencing data from @dfn{Reduced representation bisulfite
9183 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9184 genome bisulfite sequencing. It also has functions to analyze base-pair
9185 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9187 (license license:artistic2.0)))
9189 (define-public r-sva
9196 (uri (bioconductor-uri "sva" version))
9199 "0czja4c5jxa0g3fspi90nyajqmvzb29my4ykv2wi66h43f5dlwhq"))))
9200 (build-system r-build-system)
9202 `(("r-genefilter" ,r-genefilter)
9204 ("r-biocparallel" ,r-biocparallel)
9205 ("r-matrixstats" ,r-matrixstats)
9206 ("r-limma" ,r-limma)))
9207 (home-page "https://bioconductor.org/packages/sva")
9208 (synopsis "Surrogate variable analysis")
9210 "This package contains functions for removing batch effects and other
9211 unwanted variation in high-throughput experiment. It also contains functions
9212 for identifying and building surrogate variables for high-dimensional data
9213 sets. Surrogate variables are covariates constructed directly from
9214 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9215 imaging data that can be used in subsequent analyses to adjust for unknown,
9216 unmodeled, or latent sources of noise.")
9217 (license license:artistic2.0)))
9219 (define-public r-seqminer
9226 (uri (cran-uri "seqminer" version))
9229 "1jydcpkw4rwfp983j83kipvsvr10as9pb49zzn3c2v09k1gh3ymy"))))
9230 (build-system r-build-system)
9233 (home-page "http://seqminer.genomic.codes")
9234 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9236 "This package provides tools to integrate nucleotide sequencing
9237 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9238 ;; Any version of the GPL is acceptable
9239 (license (list license:gpl2+ license:gpl3+))))
9241 (define-public r-raremetals2
9243 (name "r-raremetals2")
9248 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9249 "b/b7/RareMETALS2_" version ".tar.gz"))
9252 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9253 (properties `((upstream-name . "RareMETALS2")))
9254 (build-system r-build-system)
9256 `(("r-seqminer" ,r-seqminer)
9257 ("r-mvtnorm" ,r-mvtnorm)
9259 ("r-compquadform" ,r-compquadform)
9260 ("r-getopt" ,r-getopt)))
9261 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9262 (synopsis "Analyze gene-level association tests for binary trait")
9264 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9265 It was designed to meta-analyze gene-level association tests for binary trait.
9266 While rareMETALS offers a near-complete solution for meta-analysis of
9267 gene-level tests for quantitative trait, it does not offer the optimal
9268 solution for binary trait. The package rareMETALS2 offers improved features
9269 for analyzing gene-level association tests in meta-analyses for binary
9271 (license license:gpl3)))
9273 (define-public r-maldiquant
9275 (name "r-maldiquant")
9280 (uri (cran-uri "MALDIquant" version))
9283 "18nl214xjsxkcpbg79jkmw0yznwm5szyh2qb84n7ip46mm779ha6"))))
9284 (properties `((upstream-name . "MALDIquant")))
9285 (build-system r-build-system)
9286 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9287 (synopsis "Quantitative analysis of mass spectrometry data")
9289 "This package provides a complete analysis pipeline for matrix-assisted
9290 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9291 two-dimensional mass spectrometry data. In addition to commonly used plotting
9292 and processing methods it includes distinctive features, namely baseline
9293 subtraction methods such as morphological filters (TopHat) or the
9294 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9295 alignment using warping functions, handling of replicated measurements as well
9296 as allowing spectra with different resolutions.")
9297 (license license:gpl3+)))
9299 (define-public r-protgenerics
9301 (name "r-protgenerics")
9306 (uri (bioconductor-uri "ProtGenerics" version))
9309 "053mmxhzncqgigl2iqjlq56qzimlw2zzw31wpzw19rf7rld1vi3b"))))
9310 (properties `((upstream-name . "ProtGenerics")))
9311 (build-system r-build-system)
9312 (home-page "https://github.com/lgatto/ProtGenerics")
9313 (synopsis "S4 generic functions for proteomics infrastructure")
9315 "This package provides S4 generic functions needed by Bioconductor
9316 proteomics packages.")
9317 (license license:artistic2.0)))
9319 (define-public r-mzr
9326 (uri (bioconductor-uri "mzR" version))
9329 "19fn58zl59kd0hsjjc6y975y9187nfls0028a4k3v0s9wfg5b3vn"))
9330 (modules '((guix build utils)))
9333 (delete-file-recursively "src/boost")
9335 (properties `((upstream-name . "mzR")))
9336 (build-system r-build-system)
9339 (modify-phases %standard-phases
9340 (add-after 'unpack 'use-system-boost
9342 (substitute* "src/Makevars"
9343 (("\\./boost/libs.*") "")
9344 (("ARCH_OBJS=" line)
9346 "\nARCH_LIBS=-lboost_system -lboost_regex \
9347 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9350 `(;; XXX Boost 1.69 will not work here.
9351 ("boost" ,boost-for-mysql) ; use this instead of the bundled boost sources
9354 `(("r-biobase" ,r-biobase)
9355 ("r-biocgenerics" ,r-biocgenerics)
9356 ("r-ncdf4" ,r-ncdf4)
9357 ("r-protgenerics" ,r-protgenerics)
9359 ("r-rhdf5lib" ,r-rhdf5lib)
9360 ("r-zlibbioc" ,r-zlibbioc)))
9361 (home-page "https://github.com/sneumann/mzR/")
9362 (synopsis "Parser for mass spectrometry data files")
9364 "The mzR package provides a unified API to the common file formats and
9365 parsers available for mass spectrometry data. It comes with a wrapper for the
9366 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9367 The package contains the original code written by the ISB, and a subset of the
9368 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9369 previously been used in XCMS.")
9370 (license license:artistic2.0)))
9372 (define-public r-affyio
9379 (uri (bioconductor-uri "affyio" version))
9382 "1s4zp1211vf0krxzch9v3q3r6vs8hihqppq18i2fpvwlknfja7c1"))))
9383 (build-system r-build-system)
9385 `(("r-zlibbioc" ,r-zlibbioc)))
9388 (home-page "https://github.com/bmbolstad/affyio")
9389 (synopsis "Tools for parsing Affymetrix data files")
9391 "This package provides routines for parsing Affymetrix data files based
9392 upon file format information. The primary focus is on accessing the CEL and
9394 (license license:lgpl2.0+)))
9396 (define-public r-affy
9403 (uri (bioconductor-uri "affy" version))
9406 "0x8h4fk2igv7vykqfvf6v9whmx3344v5rf3gyfajd431xkjldz6k"))))
9407 (build-system r-build-system)
9409 `(("r-affyio" ,r-affyio)
9410 ("r-biobase" ,r-biobase)
9411 ("r-biocgenerics" ,r-biocgenerics)
9412 ("r-biocmanager" ,r-biocmanager)
9413 ("r-preprocesscore" ,r-preprocesscore)
9414 ("r-zlibbioc" ,r-zlibbioc)))
9417 (home-page "https://bioconductor.org/packages/affy")
9418 (synopsis "Methods for affymetrix oligonucleotide arrays")
9420 "This package contains functions for exploratory oligonucleotide array
9422 (license license:lgpl2.0+)))
9424 (define-public r-vsn
9431 (uri (bioconductor-uri "vsn" version))
9434 "1g6qkpykw99jm2wv2i61dg2ffwk0n8fm4s5pm2q4c024vw5c9b69"))))
9435 (build-system r-build-system)
9437 `(("r-affy" ,r-affy)
9438 ("r-biobase" ,r-biobase)
9439 ("r-ggplot2" ,r-ggplot2)
9440 ("r-lattice" ,r-lattice)
9441 ("r-limma" ,r-limma)))
9442 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9443 (synopsis "Variance stabilization and calibration for microarray data")
9445 "The package implements a method for normalising microarray intensities,
9446 and works for single- and multiple-color arrays. It can also be used for data
9447 from other technologies, as long as they have similar format. The method uses
9448 a robust variant of the maximum-likelihood estimator for an
9449 additive-multiplicative error model and affine calibration. The model
9450 incorporates data calibration step (a.k.a. normalization), a model for the
9451 dependence of the variance on the mean intensity and a variance stabilizing
9452 data transformation. Differences between transformed intensities are
9453 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9454 their variance is independent of the mean, and they are usually more sensitive
9455 and specific in detecting differential transcription.")
9456 (license license:artistic2.0)))
9458 (define-public r-mzid
9465 (uri (bioconductor-uri "mzID" version))
9468 "15yd4bdxprw3kg7zj2k652y3yr3si781iw28jqvnkm0gsc23rd0c"))))
9469 (properties `((upstream-name . "mzID")))
9470 (build-system r-build-system)
9472 `(("r-doparallel" ,r-doparallel)
9473 ("r-foreach" ,r-foreach)
9474 ("r-iterators" ,r-iterators)
9476 ("r-protgenerics" ,r-protgenerics)
9479 (home-page "https://bioconductor.org/packages/mzID")
9480 (synopsis "Parser for mzIdentML files")
9482 "This package provides a parser for mzIdentML files implemented using the
9483 XML package. The parser tries to be general and able to handle all types of
9484 mzIdentML files with the drawback of having less pretty output than a vendor
9486 (license license:gpl2+)))
9488 (define-public r-pcamethods
9490 (name "r-pcamethods")
9495 (uri (bioconductor-uri "pcaMethods" version))
9498 "0ik82s9bsdj4a1mmv0a3k6yisa92mxx7maf3dvip1r8gqlm3dyng"))))
9499 (properties `((upstream-name . "pcaMethods")))
9500 (build-system r-build-system)
9502 `(("r-biobase" ,r-biobase)
9503 ("r-biocgenerics" ,r-biocgenerics)
9505 ("r-rcpp" ,r-rcpp)))
9506 (home-page "https://github.com/hredestig/pcamethods")
9507 (synopsis "Collection of PCA methods")
9509 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9510 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9511 for missing value estimation is included for comparison. BPCA, PPCA and
9512 NipalsPCA may be used to perform PCA on incomplete data as well as for
9513 accurate missing value estimation. A set of methods for printing and plotting
9514 the results is also provided. All PCA methods make use of the same data
9515 structure (pcaRes) to provide a common interface to the PCA results.")
9516 (license license:gpl3+)))
9518 (define-public r-msnbase
9525 (uri (bioconductor-uri "MSnbase" version))
9528 "1kl1d7byphnfpmbl5fzbgs68dxskhpsdyx7ka51bpfn0nv3pp492"))))
9529 (properties `((upstream-name . "MSnbase")))
9530 (build-system r-build-system)
9532 `(("r-affy" ,r-affy)
9533 ("r-biobase" ,r-biobase)
9534 ("r-biocgenerics" ,r-biocgenerics)
9535 ("r-biocparallel" ,r-biocparallel)
9536 ("r-digest" ,r-digest)
9537 ("r-ggplot2" ,r-ggplot2)
9538 ("r-impute" ,r-impute)
9539 ("r-iranges" ,r-iranges)
9540 ("r-lattice" ,r-lattice)
9541 ("r-maldiquant" ,r-maldiquant)
9545 ("r-pcamethods" ,r-pcamethods)
9547 ("r-preprocesscore" ,r-preprocesscore)
9548 ("r-protgenerics" ,r-protgenerics)
9550 ("r-s4vectors" ,r-s4vectors)
9551 ("r-scales" ,r-scales)
9554 (home-page "https://github.com/lgatto/MSnbase")
9555 (synopsis "Base functions and classes for MS-based proteomics")
9557 "This package provides basic plotting, data manipulation and processing
9558 of mass spectrometry based proteomics data.")
9559 (license license:artistic2.0)))
9561 (define-public r-msnid
9568 (uri (bioconductor-uri "MSnID" version))
9571 "077n6ljcnnl7q4w0qj8v46vm4sjk9vzzfqf7wsc6lz0wmyzqdng3"))))
9572 (properties `((upstream-name . "MSnID")))
9573 (build-system r-build-system)
9575 `(("r-biobase" ,r-biobase)
9576 ("r-data-table" ,r-data-table)
9577 ("r-doparallel" ,r-doparallel)
9578 ("r-dplyr" ,r-dplyr)
9579 ("r-foreach" ,r-foreach)
9580 ("r-iterators" ,r-iterators)
9581 ("r-msnbase" ,r-msnbase)
9584 ("r-protgenerics" ,r-protgenerics)
9585 ("r-r-cache" ,r-r-cache)
9587 ("r-reshape2" ,r-reshape2)))
9588 (home-page "https://bioconductor.org/packages/MSnID")
9589 (synopsis "Utilities for LC-MSn proteomics identifications")
9591 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9592 from mzIdentML (leveraging the mzID package) or text files. After collating
9593 the search results from multiple datasets it assesses their identification
9594 quality and optimize filtering criteria to achieve the maximum number of
9595 identifications while not exceeding a specified false discovery rate. It also
9596 contains a number of utilities to explore the MS/MS results and assess missed
9597 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9598 (license license:artistic2.0)))
9600 (define-public r-seurat
9606 (uri (cran-uri "Seurat" version))
9609 "0l8bv4i9nzz26mirnva10mq6pimibj24vk7vpvfypgn7xk4942hd"))))
9610 (properties `((upstream-name . "Seurat")))
9611 (build-system r-build-system)
9614 ("r-cluster" ,r-cluster)
9615 ("r-cowplot" ,r-cowplot)
9616 ("r-dosnow" ,r-dosnow)
9617 ("r-dplyr" ,r-dplyr)
9619 ("r-fitdistrplus" ,r-fitdistrplus)
9620 ("r-foreach" ,r-foreach)
9622 ("r-ggplot2" ,r-ggplot2)
9623 ("r-ggridges" ,r-ggridges)
9624 ("r-gplots" ,r-gplots)
9625 ("r-hdf5r" ,r-hdf5r)
9626 ("r-hmisc" ,r-hmisc)
9629 ("r-igraph" ,r-igraph)
9630 ("r-irlba" ,r-irlba)
9632 ("r-lmtest" ,r-lmtest)
9634 ("r-matrix" ,r-matrix)
9635 ("r-metap" ,r-metap)
9636 ("r-mixtools" ,r-mixtools)
9637 ("r-pbapply" ,r-pbapply)
9638 ("r-plotly" ,r-plotly)
9641 ("r-rcolorbrewer" ,r-rcolorbrewer)
9643 ("r-rcppeigen" ,r-rcppeigen)
9644 ("r-rcppprogress" ,r-rcppprogress)
9645 ("r-reshape2" ,r-reshape2)
9646 ("r-reticulate" ,r-reticulate)
9648 ("r-rtsne" ,r-rtsne)
9649 ("r-sdmtools" ,r-sdmtools)
9650 ("r-tidyr" ,r-tidyr)
9651 ("r-tsne" ,r-tsne)))
9652 (home-page "http://www.satijalab.org/seurat")
9653 (synopsis "Seurat is an R toolkit for single cell genomics")
9655 "This package is an R package designed for QC, analysis, and
9656 exploration of single cell RNA-seq data. It easily enables widely-used
9657 analytical techniques, including the identification of highly variable genes,
9658 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9659 algorithms; density clustering, hierarchical clustering, k-means, and the
9660 discovery of differentially expressed genes and markers.")
9661 (license license:gpl3)))
9663 (define-public r-aroma-light
9665 (name "r-aroma-light")
9670 (uri (bioconductor-uri "aroma.light" version))
9673 "0vfifgpqxjjncbiv6gvlk9jmj14j90r9f30bqk3ks9v1csjnjhrb"))))
9674 (properties `((upstream-name . "aroma.light")))
9675 (build-system r-build-system)
9677 `(("r-matrixstats" ,r-matrixstats)
9678 ("r-r-methodss3" ,r-r-methodss3)
9680 ("r-r-utils" ,r-r-utils)))
9681 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9682 (synopsis "Methods for normalization and visualization of microarray data")
9684 "This package provides methods for microarray analysis that take basic
9685 data types such as matrices and lists of vectors. These methods can be used
9686 standalone, be utilized in other packages, or be wrapped up in higher-level
9688 (license license:gpl2+)))
9690 (define-public r-deseq
9697 (uri (bioconductor-uri "DESeq" version))
9700 "0bpiixczbhlyaiinpbl6xrpmv72k2bq76bxnw06gl35m4pgs94p2"))))
9701 (properties `((upstream-name . "DESeq")))
9702 (build-system r-build-system)
9704 `(("r-biobase" ,r-biobase)
9705 ("r-biocgenerics" ,r-biocgenerics)
9706 ("r-genefilter" ,r-genefilter)
9707 ("r-geneplotter" ,r-geneplotter)
9708 ("r-lattice" ,r-lattice)
9709 ("r-locfit" ,r-locfit)
9711 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9712 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9713 (synopsis "Differential gene expression analysis")
9715 "This package provides tools for estimating variance-mean dependence in
9716 count data from high-throughput genetic sequencing assays and for testing for
9717 differential expression based on a model using the negative binomial
9719 (license license:gpl3+)))
9721 (define-public r-edaseq
9728 (uri (bioconductor-uri "EDASeq" version))
9731 "0559ph606ps2g9bwbl0a2knkcs5w581n9igngpjxvk5p56k24gb5"))))
9732 (properties `((upstream-name . "EDASeq")))
9733 (build-system r-build-system)
9735 `(("r-annotationdbi" ,r-annotationdbi)
9736 ("r-aroma-light" ,r-aroma-light)
9737 ("r-biobase" ,r-biobase)
9738 ("r-biocgenerics" ,r-biocgenerics)
9739 ("r-biocmanager" ,r-biocmanager)
9740 ("r-biomart" ,r-biomart)
9741 ("r-biostrings" ,r-biostrings)
9742 ("r-deseq" ,r-deseq)
9743 ("r-genomicfeatures" ,r-genomicfeatures)
9744 ("r-genomicranges" ,r-genomicranges)
9745 ("r-iranges" ,r-iranges)
9746 ("r-rsamtools" ,r-rsamtools)
9747 ("r-shortread" ,r-shortread)))
9748 (home-page "https://github.com/drisso/EDASeq")
9749 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9751 "This package provides support for numerical and graphical summaries of
9752 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9753 adjust for GC-content effect (or other gene-level effects) on read counts:
9754 loess robust local regression, global-scaling, and full-quantile
9755 normalization. Between-lane normalization procedures to adjust for
9756 distributional differences between lanes (e.g., sequencing depth):
9757 global-scaling and full-quantile normalization.")
9758 (license license:artistic2.0)))
9760 (define-public r-interactivedisplaybase
9762 (name "r-interactivedisplaybase")
9767 (uri (bioconductor-uri "interactiveDisplayBase" version))
9770 "04xz3dkwan2s5ic1mwkdfnggm0l41mgqfagx160bcsrpkw6z7ark"))))
9772 `((upstream-name . "interactiveDisplayBase")))
9773 (build-system r-build-system)
9775 `(("r-biocgenerics" ,r-biocgenerics)
9776 ("r-shiny" ,r-shiny)))
9777 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9778 (synopsis "Base package for web displays of Bioconductor objects")
9780 "This package contains the basic methods needed to generate interactive
9781 Shiny-based display methods for Bioconductor objects.")
9782 (license license:artistic2.0)))
9784 (define-public r-annotationhub
9786 (name "r-annotationhub")
9791 (uri (bioconductor-uri "AnnotationHub" version))
9794 "18v2mk395svq3c19wzi6bjwjfnmrvjqkzmj7cmaji7rx4xdgz6ck"))))
9795 (properties `((upstream-name . "AnnotationHub")))
9796 (build-system r-build-system)
9798 `(("r-annotationdbi" ,r-annotationdbi)
9799 ("r-biocgenerics" ,r-biocgenerics)
9800 ("r-biocmanager" ,r-biocmanager)
9803 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9804 ("r-rsqlite" ,r-rsqlite)
9805 ("r-s4vectors" ,r-s4vectors)
9806 ("r-yaml" ,r-yaml)))
9807 (home-page "https://bioconductor.org/packages/AnnotationHub")
9808 (synopsis "Client to access AnnotationHub resources")
9810 "This package provides a client for the Bioconductor AnnotationHub web
9811 resource. The AnnotationHub web resource provides a central location where
9812 genomic files (e.g. VCF, bed, wig) and other resources from standard
9813 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9814 metadata about each resource, e.g., a textual description, tags, and date of
9815 modification. The client creates and manages a local cache of files retrieved
9816 by the user, helping with quick and reproducible access.")
9817 (license license:artistic2.0)))
9819 (define-public r-fastseg
9826 (uri (bioconductor-uri "fastseg" version))
9829 "1l8mdjpfpgwqdss2ywjkb8b4h55wf8v6kmyxdlvy04ds2hj16sb1"))))
9830 (build-system r-build-system)
9832 `(("r-biobase" ,r-biobase)
9833 ("r-biocgenerics" ,r-biocgenerics)
9834 ("r-genomicranges" ,r-genomicranges)
9835 ("r-iranges" ,r-iranges)
9836 ("r-s4vectors" ,r-s4vectors)))
9837 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
9838 (synopsis "Fast segmentation algorithm for genetic sequencing data")
9840 "Fastseg implements a very fast and efficient segmentation algorithm.
9841 It can segment data from DNA microarrays and data from next generation
9842 sequencing for example to detect copy number segments. Further it can segment
9843 data from RNA microarrays like tiling arrays to identify transcripts. Most
9844 generally, it can segment data given as a matrix or as a vector. Various data
9845 formats can be used as input to fastseg like expression set objects for
9846 microarrays or GRanges for sequencing data.")
9847 (license license:lgpl2.0+)))
9849 (define-public r-keggrest
9856 (uri (bioconductor-uri "KEGGREST" version))
9859 "0blpd5a7whd2sswfhqd17h58hg06ymaf80gapdr9ja43hnnlj309"))))
9860 (properties `((upstream-name . "KEGGREST")))
9861 (build-system r-build-system)
9863 `(("r-biostrings" ,r-biostrings)
9866 (home-page "https://bioconductor.org/packages/KEGGREST")
9867 (synopsis "Client-side REST access to KEGG")
9869 "This package provides a package that provides a client interface to the
9870 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
9871 (license license:artistic2.0)))
9873 (define-public r-gage
9880 (uri (bioconductor-uri "gage" version))
9883 "02g796sb1800ff0f1mq9f2m5wwzpf8pnfzajs49i68dhq2hm01a8"))))
9884 (build-system r-build-system)
9886 `(("r-annotationdbi" ,r-annotationdbi)
9887 ("r-graph" ,r-graph)
9888 ("r-keggrest" ,r-keggrest)))
9889 (home-page "http://www.biomedcentral.com/1471-2105/10/161")
9890 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
9892 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
9893 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
9894 data attributes including sample sizes, experimental designs, assay platforms,
9895 and other types of heterogeneity. The gage package provides functions for
9896 basic GAGE analysis, result processing and presentation. In addition, it
9897 provides demo microarray data and commonly used gene set data based on KEGG
9898 pathways and GO terms. These funtions and data are also useful for gene set
9899 analysis using other methods.")
9900 (license license:gpl2+)))
9902 (define-public r-genomicfiles
9904 (name "r-genomicfiles")
9909 (uri (bioconductor-uri "GenomicFiles" version))
9912 "0qf2yj4lfnnk64fk125n8sqms01shfqiik04nasx2z3k129ykpxp"))))
9913 (properties `((upstream-name . "GenomicFiles")))
9914 (build-system r-build-system)
9916 `(("r-biocgenerics" ,r-biocgenerics)
9917 ("r-biocparallel" ,r-biocparallel)
9918 ("r-genomeinfodb" ,r-genomeinfodb)
9919 ("r-genomicalignments" ,r-genomicalignments)
9920 ("r-genomicranges" ,r-genomicranges)
9921 ("r-iranges" ,r-iranges)
9922 ("r-rsamtools" ,r-rsamtools)
9923 ("r-rtracklayer" ,r-rtracklayer)
9924 ("r-s4vectors" ,r-s4vectors)
9925 ("r-summarizedexperiment" ,r-summarizedexperiment)
9926 ("r-variantannotation" ,r-variantannotation)))
9927 (home-page "https://bioconductor.org/packages/GenomicFiles")
9928 (synopsis "Distributed computing by file or by range")
9930 "This package provides infrastructure for parallel computations
9931 distributed by file or by range. User defined mapper and reducer functions
9932 provide added flexibility for data combination and manipulation.")
9933 (license license:artistic2.0)))
9935 (define-public r-complexheatmap
9937 (name "r-complexheatmap")
9942 (uri (bioconductor-uri "ComplexHeatmap" version))
9945 "0s01dzcfj1lmpqfpsbqw7r4858krfzy499lz4cwx4fq3mbyvy2aj"))))
9947 `((upstream-name . "ComplexHeatmap")))
9948 (build-system r-build-system)
9950 `(("r-circlize" ,r-circlize)
9951 ("r-colorspace" ,r-colorspace)
9952 ("r-getoptlong" ,r-getoptlong)
9953 ("r-globaloptions" ,r-globaloptions)
9954 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9956 "https://github.com/jokergoo/ComplexHeatmap")
9957 (synopsis "Making Complex Heatmaps")
9959 "Complex heatmaps are efficient to visualize associations between
9960 different sources of data sets and reveal potential structures. This package
9961 provides a highly flexible way to arrange multiple heatmaps and supports
9962 self-defined annotation graphics.")
9963 (license license:gpl2+)))
9965 (define-public r-dirichletmultinomial
9967 (name "r-dirichletmultinomial")
9972 (uri (bioconductor-uri "DirichletMultinomial" version))
9975 "0vazfjzqy78p5g7dnv30lbqbj4bhq4zafd2wh6gdwy2il1fd78xa"))))
9977 `((upstream-name . "DirichletMultinomial")))
9978 (build-system r-build-system)
9982 `(("r-biocgenerics" ,r-biocgenerics)
9983 ("r-iranges" ,r-iranges)
9984 ("r-s4vectors" ,r-s4vectors)))
9985 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
9986 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
9988 "Dirichlet-multinomial mixture models can be used to describe variability
9989 in microbial metagenomic data. This package is an interface to code
9990 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
9992 (license license:lgpl3)))
9994 (define-public r-ensembldb
9996 (name "r-ensembldb")
10001 (uri (bioconductor-uri "ensembldb" version))
10004 "1wqq0m1fgvgkzq5zr2s9cj2s7qkg9lx3dwwsqixzs5fn52p4dn7f"))))
10005 (build-system r-build-system)
10007 `(("r-annotationdbi" ,r-annotationdbi)
10008 ("r-annotationfilter" ,r-annotationfilter)
10009 ("r-biobase" ,r-biobase)
10010 ("r-biocgenerics" ,r-biocgenerics)
10011 ("r-biostrings" ,r-biostrings)
10014 ("r-genomeinfodb" ,r-genomeinfodb)
10015 ("r-genomicfeatures" ,r-genomicfeatures)
10016 ("r-genomicranges" ,r-genomicranges)
10017 ("r-iranges" ,r-iranges)
10018 ("r-protgenerics" ,r-protgenerics)
10019 ("r-rsamtools" ,r-rsamtools)
10020 ("r-rsqlite" ,r-rsqlite)
10021 ("r-rtracklayer" ,r-rtracklayer)
10022 ("r-s4vectors" ,r-s4vectors)))
10023 (home-page "https://github.com/jotsetung/ensembldb")
10024 (synopsis "Utilities to create and use Ensembl-based annotation databases")
10026 "The package provides functions to create and use transcript-centric
10027 annotation databases/packages. The annotation for the databases are directly
10028 fetched from Ensembl using their Perl API. The functionality and data is
10029 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
10030 but, in addition to retrieve all gene/transcript models and annotations from
10031 the database, the @code{ensembldb} package also provides a filter framework
10032 allowing to retrieve annotations for specific entries like genes encoded on a
10033 chromosome region or transcript models of lincRNA genes.")
10034 ;; No version specified
10035 (license license:lgpl3+)))
10037 (define-public r-organismdbi
10039 (name "r-organismdbi")
10044 (uri (bioconductor-uri "OrganismDbi" version))
10047 "11pyv56cy4iy095h40k6k0mpjdlh6gsb4ld3s57nfa9nd4ypx3yi"))))
10048 (properties `((upstream-name . "OrganismDbi")))
10049 (build-system r-build-system)
10051 `(("r-annotationdbi" ,r-annotationdbi)
10052 ("r-biobase" ,r-biobase)
10053 ("r-biocgenerics" ,r-biocgenerics)
10054 ("r-biocmanager" ,r-biocmanager)
10056 ("r-genomicfeatures" ,r-genomicfeatures)
10057 ("r-genomicranges" ,r-genomicranges)
10058 ("r-graph" ,r-graph)
10059 ("r-iranges" ,r-iranges)
10061 ("r-s4vectors" ,r-s4vectors)))
10062 (home-page "https://bioconductor.org/packages/OrganismDbi")
10063 (synopsis "Software to enable the smooth interfacing of database packages")
10064 (description "The package enables a simple unified interface to several
10065 annotation packages each of which has its own schema by taking advantage of
10066 the fact that each of these packages implements a select methods.")
10067 (license license:artistic2.0)))
10069 (define-public r-biovizbase
10071 (name "r-biovizbase")
10076 (uri (bioconductor-uri "biovizBase" version))
10079 "0v5gvcx180qn5487i1dph9abadw3ggqwp5yzy41jswzbdc8q6sbm"))))
10080 (properties `((upstream-name . "biovizBase")))
10081 (build-system r-build-system)
10083 `(("r-annotationdbi" ,r-annotationdbi)
10084 ("r-annotationfilter" ,r-annotationfilter)
10085 ("r-biocgenerics" ,r-biocgenerics)
10086 ("r-biostrings" ,r-biostrings)
10087 ("r-dichromat" ,r-dichromat)
10088 ("r-ensembldb" ,r-ensembldb)
10089 ("r-genomeinfodb" ,r-genomeinfodb)
10090 ("r-genomicalignments" ,r-genomicalignments)
10091 ("r-genomicfeatures" ,r-genomicfeatures)
10092 ("r-genomicranges" ,r-genomicranges)
10093 ("r-hmisc" ,r-hmisc)
10094 ("r-iranges" ,r-iranges)
10095 ("r-rcolorbrewer" ,r-rcolorbrewer)
10096 ("r-rlang" ,r-rlang)
10097 ("r-rsamtools" ,r-rsamtools)
10098 ("r-s4vectors" ,r-s4vectors)
10099 ("r-scales" ,r-scales)
10100 ("r-summarizedexperiment" ,r-summarizedexperiment)
10101 ("r-variantannotation" ,r-variantannotation)))
10102 (home-page "https://bioconductor.org/packages/biovizBase")
10103 (synopsis "Basic graphic utilities for visualization of genomic data")
10105 "The biovizBase package is designed to provide a set of utilities, color
10106 schemes and conventions for genomic data. It serves as the base for various
10107 high-level packages for biological data visualization. This saves development
10108 effort and encourages consistency.")
10109 (license license:artistic2.0)))
10111 (define-public r-ggbio
10118 (uri (bioconductor-uri "ggbio" version))
10121 "0wq49qqzkcn8s19xgaxf2s1j1a563d7pbhhvris6fhxfdjsz4934"))))
10122 (build-system r-build-system)
10124 `(("r-annotationdbi" ,r-annotationdbi)
10125 ("r-annotationfilter" ,r-annotationfilter)
10126 ("r-biobase" ,r-biobase)
10127 ("r-biocgenerics" ,r-biocgenerics)
10128 ("r-biostrings" ,r-biostrings)
10129 ("r-biovizbase" ,r-biovizbase)
10130 ("r-bsgenome" ,r-bsgenome)
10131 ("r-ensembldb" ,r-ensembldb)
10132 ("r-genomeinfodb" ,r-genomeinfodb)
10133 ("r-genomicalignments" ,r-genomicalignments)
10134 ("r-genomicfeatures" ,r-genomicfeatures)
10135 ("r-genomicranges" ,r-genomicranges)
10136 ("r-ggally" ,r-ggally)
10137 ("r-ggplot2" ,r-ggplot2)
10138 ("r-gridextra" ,r-gridextra)
10139 ("r-gtable" ,r-gtable)
10140 ("r-hmisc" ,r-hmisc)
10141 ("r-iranges" ,r-iranges)
10142 ("r-organismdbi" ,r-organismdbi)
10143 ("r-reshape2" ,r-reshape2)
10144 ("r-rlang" ,r-rlang)
10145 ("r-rsamtools" ,r-rsamtools)
10146 ("r-rtracklayer" ,r-rtracklayer)
10147 ("r-s4vectors" ,r-s4vectors)
10148 ("r-scales" ,r-scales)
10149 ("r-summarizedexperiment" ,r-summarizedexperiment)
10150 ("r-variantannotation" ,r-variantannotation)))
10151 (home-page "http://www.tengfei.name/ggbio/")
10152 (synopsis "Visualization tools for genomic data")
10154 "The ggbio package extends and specializes the grammar of graphics for
10155 biological data. The graphics are designed to answer common scientific
10156 questions, in particular those often asked of high throughput genomics data.
10157 All core Bioconductor data structures are supported, where appropriate. The
10158 package supports detailed views of particular genomic regions, as well as
10159 genome-wide overviews. Supported overviews include ideograms and grand linear
10160 views. High-level plots include sequence fragment length, edge-linked
10161 interval to data view, mismatch pileup, and several splicing summaries.")
10162 (license license:artistic2.0)))
10164 (define-public r-gprofiler
10166 (name "r-gprofiler")
10171 (uri (cran-uri "gProfileR" version))
10174 "12nwidbnqmnfy5dnqga26byslvdnkrpz2fi19qfcby6xx0wbndk7"))))
10175 (properties `((upstream-name . "gProfileR")))
10176 (build-system r-build-system)
10178 `(("r-plyr" ,r-plyr)
10179 ("r-rcurl" ,r-rcurl)))
10180 (home-page "https://cran.r-project.org/web/packages/gProfileR/")
10181 (synopsis "Interface to the g:Profiler toolkit")
10183 "This package provides tools for functional enrichment analysis,
10184 gene identifier conversion and mapping homologous genes across related
10185 organisms via the @code{g:Profiler} toolkit.")
10186 (license license:gpl2+)))
10188 (define-public r-gqtlbase
10190 (name "r-gqtlbase")
10195 (uri (bioconductor-uri "gQTLBase" version))
10198 "1lbk1m1mkvbk30flk5pf3pcrnm2s0sj5r48kbjgad39dsvd8zgqx"))))
10199 (properties `((upstream-name . "gQTLBase")))
10200 (build-system r-build-system)
10202 `(("r-batchjobs" ,r-batchjobs)
10203 ("r-bbmisc" ,r-bbmisc)
10204 ("r-biocgenerics" ,r-biocgenerics)
10206 ("r-doparallel" ,r-doparallel)
10208 ("r-ffbase" ,r-ffbase)
10209 ("r-foreach" ,r-foreach)
10210 ("r-genomicfiles" ,r-genomicfiles)
10211 ("r-genomicranges" ,r-genomicranges)
10212 ("r-rtracklayer" ,r-rtracklayer)
10213 ("r-s4vectors" ,r-s4vectors)
10214 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10215 (home-page "https://bioconductor.org/packages/gQTLBase")
10216 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10218 "The purpose of this package is to simplify the storage and interrogation
10219 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10221 (license license:artistic2.0)))
10223 (define-public r-snpstats
10225 (name "r-snpstats")
10230 (uri (bioconductor-uri "snpStats" version))
10233 "1pplx4pf9bqi7v5v1l74yknc1s61carvbqkf327ky7vbvp0bck33"))))
10234 (properties `((upstream-name . "snpStats")))
10235 (build-system r-build-system)
10236 (inputs `(("zlib" ,zlib)))
10238 `(("r-biocgenerics" ,r-biocgenerics)
10239 ("r-matrix" ,r-matrix)
10240 ("r-survival" ,r-survival)
10241 ("r-zlibbioc" ,r-zlibbioc)))
10242 (home-page "https://bioconductor.org/packages/snpStats")
10243 (synopsis "Methods for SNP association studies")
10245 "This package provides classes and statistical methods for large
10246 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10247 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10248 (license license:gpl3)))
10250 (define-public r-homo-sapiens
10252 (name "r-homo-sapiens")
10256 ;; We cannot use bioconductor-uri here because this tarball is
10257 ;; located under "data/annotation/" instead of "bioc/".
10258 (uri (string-append "http://www.bioconductor.org/packages/"
10259 "release/data/annotation/src/contrib/"
10261 version ".tar.gz"))
10264 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10266 `((upstream-name . "Homo.sapiens")))
10267 (build-system r-build-system)
10269 `(("r-genomicfeatures" ,r-genomicfeatures)
10270 ("r-go-db" ,r-go-db)
10271 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10272 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10273 ("r-organismdbi" ,r-organismdbi)
10274 ("r-annotationdbi" ,r-annotationdbi)))
10275 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10276 (synopsis "Annotation package for the Homo.sapiens object")
10278 "This package contains the Homo.sapiens object to access data from
10279 several related annotation packages.")
10280 (license license:artistic2.0)))
10282 (define-public r-erma
10289 (uri (bioconductor-uri "erma" version))
10292 "0hj9iz904rr1y66442lkxjywkw1ydyxxlhmjirawbf09ic5ad4g9"))))
10293 (build-system r-build-system)
10295 `(("r-annotationdbi" ,r-annotationdbi)
10296 ("r-biobase" ,r-biobase)
10297 ("r-biocgenerics" ,r-biocgenerics)
10298 ("r-biocparallel" ,r-biocparallel)
10299 ("r-genomeinfodb" ,r-genomeinfodb)
10300 ("r-genomicfiles" ,r-genomicfiles)
10301 ("r-genomicranges" ,r-genomicranges)
10302 ("r-ggplot2" ,r-ggplot2)
10303 ("r-homo-sapiens" ,r-homo-sapiens)
10304 ("r-iranges" ,r-iranges)
10305 ("r-rtracklayer" ,r-rtracklayer)
10306 ("r-s4vectors" ,r-s4vectors)
10307 ("r-shiny" ,r-shiny)
10308 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10309 (home-page "https://bioconductor.org/packages/erma")
10310 (synopsis "Epigenomic road map adventures")
10312 "The epigenomics road map describes locations of epigenetic marks in DNA
10313 from a variety of cell types. Of interest are locations of histone
10314 modifications, sites of DNA methylation, and regions of accessible chromatin.
10315 This package presents a selection of elements of the road map including
10316 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10317 by Ernst and Kellis.")
10318 (license license:artistic2.0)))
10320 (define-public r-ldblock
10327 (uri (bioconductor-uri "ldblock" version))
10330 "0xbf4pmhrk5fnd1iz5wzjvdr75v114bwpznhcig4wiqmxc27sips"))))
10331 (build-system r-build-system)
10333 `(("r-biocgenerics" ,r-biocgenerics)
10335 ("r-genomeinfodb" ,r-genomeinfodb)
10336 ("r-genomicfiles" ,r-genomicfiles)
10337 ("r-go-db" ,r-go-db)
10338 ("r-homo-sapiens" ,r-homo-sapiens)
10339 ("r-matrix" ,r-matrix)
10340 ("r-rsamtools" ,r-rsamtools)
10341 ("r-snpstats" ,r-snpstats)
10342 ("r-variantannotation" ,r-variantannotation)))
10343 (home-page "https://bioconductor.org/packages/ldblock")
10344 (synopsis "Data structures for linkage disequilibrium measures in populations")
10346 "This package defines data structures for @dfn{linkage
10347 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10348 handling of existing population-level data for the purpose of flexibly
10349 defining LD blocks.")
10350 (license license:artistic2.0)))
10352 (define-public r-gqtlstats
10354 (name "r-gqtlstats")
10359 (uri (bioconductor-uri "gQTLstats" version))
10362 "1sg9kw59dlayj7qxql9pd93d4hmml504sa3kkfpzfh3xri7m5pxf"))))
10363 (properties `((upstream-name . "gQTLstats")))
10364 (build-system r-build-system)
10366 `(("r-annotationdbi" ,r-annotationdbi)
10367 ("r-batchjobs" ,r-batchjobs)
10368 ("r-bbmisc" ,r-bbmisc)
10369 ("r-beeswarm" ,r-beeswarm)
10370 ("r-biobase" ,r-biobase)
10371 ("r-biocgenerics" ,r-biocgenerics)
10372 ("r-doparallel" ,r-doparallel)
10373 ("r-dplyr" ,r-dplyr)
10375 ("r-ffbase" ,r-ffbase)
10376 ("r-foreach" ,r-foreach)
10377 ("r-genomeinfodb" ,r-genomeinfodb)
10378 ("r-genomicfeatures" ,r-genomicfeatures)
10379 ("r-genomicfiles" ,r-genomicfiles)
10380 ("r-genomicranges" ,r-genomicranges)
10381 ("r-ggbeeswarm" ,r-ggbeeswarm)
10382 ("r-ggplot2" ,r-ggplot2)
10383 ("r-gqtlbase" ,r-gqtlbase)
10384 ("r-hardyweinberg" ,r-hardyweinberg)
10385 ("r-homo-sapiens" ,r-homo-sapiens)
10386 ("r-iranges" ,r-iranges)
10387 ("r-limma" ,r-limma)
10389 ("r-plotly" ,r-plotly)
10390 ("r-reshape2" ,r-reshape2)
10391 ("r-s4vectors" ,r-s4vectors)
10392 ("r-shiny" ,r-shiny)
10393 ("r-snpstats" ,r-snpstats)
10394 ("r-summarizedexperiment" ,r-summarizedexperiment)
10395 ("r-variantannotation" ,r-variantannotation)))
10396 (home-page "https://bioconductor.org/packages/gQTLstats")
10397 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10399 "This package provides tools for the computationally efficient analysis
10400 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10401 The software in this package aims to support refinements and functional
10402 interpretation of members of a collection of association statistics on a
10403 family of feature/genome hypotheses.")
10404 (license license:artistic2.0)))
10406 (define-public r-gviz
10413 (uri (bioconductor-uri "Gviz" version))
10416 "1dpkcaar7qgzg3vgafvkplprhwmhzpb7ph009kr6ajm36hx4z81c"))))
10417 (properties `((upstream-name . "Gviz")))
10418 (build-system r-build-system)
10420 `(("r-annotationdbi" ,r-annotationdbi)
10421 ("r-biobase" ,r-biobase)
10422 ("r-biocgenerics" ,r-biocgenerics)
10423 ("r-biomart" ,r-biomart)
10424 ("r-biostrings" ,r-biostrings)
10425 ("r-biovizbase" ,r-biovizbase)
10426 ("r-bsgenome" ,r-bsgenome)
10427 ("r-digest" ,r-digest)
10428 ("r-genomeinfodb" ,r-genomeinfodb)
10429 ("r-genomicalignments" ,r-genomicalignments)
10430 ("r-genomicfeatures" ,r-genomicfeatures)
10431 ("r-genomicranges" ,r-genomicranges)
10432 ("r-iranges" ,r-iranges)
10433 ("r-lattice" ,r-lattice)
10434 ("r-latticeextra" ,r-latticeextra)
10435 ("r-matrixstats" ,r-matrixstats)
10436 ("r-rcolorbrewer" ,r-rcolorbrewer)
10437 ("r-rsamtools" ,r-rsamtools)
10438 ("r-rtracklayer" ,r-rtracklayer)
10439 ("r-s4vectors" ,r-s4vectors)
10440 ("r-xvector" ,r-xvector)))
10441 (home-page "https://bioconductor.org/packages/Gviz")
10442 (synopsis "Plotting data and annotation information along genomic coordinates")
10444 "Genomic data analyses requires integrated visualization of known genomic
10445 information and new experimental data. Gviz uses the biomaRt and the
10446 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10447 and translates this to e.g. gene/transcript structures in viewports of the
10448 grid graphics package. This results in genomic information plotted together
10450 (license license:artistic2.0)))
10452 (define-public r-gwascat
10459 (uri (bioconductor-uri "gwascat" version))
10462 "1fnyjydhicq4ayrv0lqjv48h9bd72h40s6l82g1h2ng0icwz38g0"))))
10463 (build-system r-build-system)
10465 `(("r-annotationdbi" ,r-annotationdbi)
10466 ("r-annotationhub" ,r-annotationhub)
10467 ("r-biocgenerics" ,r-biocgenerics)
10468 ("r-biostrings" ,r-biostrings)
10469 ("r-genomeinfodb" ,r-genomeinfodb)
10470 ("r-genomicfeatures" ,r-genomicfeatures)
10471 ("r-genomicranges" ,r-genomicranges)
10472 ("r-ggbio" ,r-ggbio)
10473 ("r-ggplot2" ,r-ggplot2)
10474 ("r-gqtlstats" ,r-gqtlstats)
10475 ("r-graph" ,r-graph)
10477 ("r-homo-sapiens" ,r-homo-sapiens)
10478 ("r-iranges" ,r-iranges)
10479 ("r-rsamtools" ,r-rsamtools)
10480 ("r-rtracklayer" ,r-rtracklayer)
10481 ("r-s4vectors" ,r-s4vectors)
10482 ("r-snpstats" ,r-snpstats)
10483 ("r-summarizedexperiment" ,r-summarizedexperiment)
10484 ("r-variantannotation" ,r-variantannotation)))
10485 (home-page "https://bioconductor.org/packages/gwascat")
10486 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10488 "This package provides tools for representing and modeling data in the
10489 EMBL-EBI GWAS catalog.")
10490 (license license:artistic2.0)))
10492 (define-public r-sushi
10498 (uri (bioconductor-uri "Sushi" version))
10501 "0dv5di0hgbvk9cxnqhyf18mdjl50k6bk00a89r6zgp83rbxwr1r8"))))
10502 (properties `((upstream-name . "Sushi")))
10503 (build-system r-build-system)
10505 `(("r-biomart" ,r-biomart)
10507 (home-page "https://bioconductor.org/packages/Sushi")
10508 (synopsis "Tools for visualizing genomics data")
10510 "This package provides flexible, quantitative, and integrative genomic
10511 visualizations for publication-quality multi-panel figures.")
10512 (license license:gpl2+)))
10514 (define-public r-fithic
10520 (uri (bioconductor-uri "FitHiC" version))
10523 "15xd8mz7660q4zr9p74mq1pqps4iz7pxp8f9ifn21gwg94aq1avn"))))
10524 (properties `((upstream-name . "FitHiC")))
10525 (build-system r-build-system)
10527 `(("r-data-table" ,r-data-table)
10528 ("r-fdrtool" ,r-fdrtool)
10529 ("r-rcpp" ,r-rcpp)))
10530 (home-page "https://bioconductor.org/packages/FitHiC")
10531 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10533 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10534 intra-chromosomal contact maps produced by genome-wide genome architecture
10535 assays such as Hi-C.")
10536 (license license:gpl2+)))
10538 (define-public r-hitc
10544 (uri (bioconductor-uri "HiTC" version))
10547 "11f96k1707g6milpjgnrjf3b5r42hsrxhb5d8znkcr3y3mrskdbj"))))
10548 (properties `((upstream-name . "HiTC")))
10549 (build-system r-build-system)
10551 `(("r-biostrings" ,r-biostrings)
10552 ("r-genomeinfodb" ,r-genomeinfodb)
10553 ("r-genomicranges" ,r-genomicranges)
10554 ("r-iranges" ,r-iranges)
10555 ("r-matrix" ,r-matrix)
10556 ("r-rcolorbrewer" ,r-rcolorbrewer)
10557 ("r-rtracklayer" ,r-rtracklayer)))
10558 (home-page "https://bioconductor.org/packages/HiTC")
10559 (synopsis "High throughput chromosome conformation capture analysis")
10561 "The HiTC package was developed to explore high-throughput \"C\" data
10562 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10563 quality controls, normalization, visualization, and further analysis are also
10565 (license license:artistic2.0)))
10567 (define-public r-hdf5array
10569 (name "r-hdf5array")
10574 (uri (bioconductor-uri "HDF5Array" version))
10577 "1qwdsygcadl58qj598hfyvs8hp0hqcl9ghnhknahrlhmb7k2bd2d"))))
10578 (properties `((upstream-name . "HDF5Array")))
10579 (build-system r-build-system)
10581 `(("r-biocgenerics" ,r-biocgenerics)
10582 ("r-delayedarray" ,r-delayedarray)
10583 ("r-iranges" ,r-iranges)
10584 ("r-rhdf5" ,r-rhdf5)
10585 ("r-s4vectors" ,r-s4vectors)))
10586 (home-page "https://bioconductor.org/packages/HDF5Array")
10587 (synopsis "HDF5 back end for DelayedArray objects")
10588 (description "This package provides an array-like container for convenient
10589 access and manipulation of HDF5 datasets. It supports delayed operations and
10590 block processing.")
10591 (license license:artistic2.0)))
10593 (define-public r-rhdf5lib
10595 (name "r-rhdf5lib")
10600 (uri (bioconductor-uri "Rhdf5lib" version))
10603 "06bxd3wz8lrvh2hzvmjpdv4lvzj5lz9353bw5b3zb98cb8w9r2j5"))
10604 (modules '((guix build utils)))
10607 ;; Delete bundled binaries
10608 (delete-file-recursively "src/winlib/")
10610 (properties `((upstream-name . "Rhdf5lib")))
10611 (build-system r-build-system)
10614 (modify-phases %standard-phases
10615 (add-after 'unpack 'do-not-use-bundled-hdf5
10616 (lambda* (#:key inputs #:allow-other-keys)
10617 (for-each delete-file '("configure" "configure.ac"))
10618 ;; Do not make other packages link with the proprietary libsz.
10619 (substitute* "R/zzz.R"
10620 (("'%s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a -lz'")
10621 "'%s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a -lz'")
10622 (("'%s/libhdf5.a %s/libsz.a -lz'")
10623 "'%s/libhdf5.a %s/libhdf5.a -lz'"))
10624 (with-directory-excursion "src"
10625 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10626 (rename-file (string-append "hdf5-" ,(package-version hdf5-1.10))
10628 ;; Remove timestamp and host system information to make
10629 ;; the build reproducible.
10630 (substitute* "hdf5/src/libhdf5.settings.in"
10631 (("Configured on: @CONFIG_DATE@")
10632 "Configured on: Guix")
10633 (("Uname information:.*")
10634 "Uname information: Linux\n")
10635 ;; Remove unnecessary store reference.
10637 "C Compiler: GCC\n"))
10638 (rename-file "Makevars.in" "Makevars")
10639 (substitute* "Makevars"
10640 (("HDF5_CXX_LIB=.*")
10641 (string-append "HDF5_CXX_LIB="
10642 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10644 (string-append "HDF5_LIB="
10645 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10646 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10647 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10648 ;; szip is non-free software
10649 (("cp \\$\\{SZIP_LIB\\}.*") "")
10650 (("\\$\\{USER_LIB_DIR\\}libsz.a") "")))
10655 `(("hdf5" ,hdf5-1.10)))
10657 `(("hdf5-source" ,(package-source hdf5-1.10))))
10658 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10659 (synopsis "HDF5 library as an R package")
10660 (description "This package provides C and C++ HDF5 libraries for use in R
10662 (license license:artistic2.0)))
10664 (define-public r-beachmat
10666 (name "r-beachmat")
10671 (uri (bioconductor-uri "beachmat" version))
10674 "07zgmms0qg8gw7x0js46965bbhpfj2aa1h5ixdz9r332bxv9cdmr"))))
10675 (build-system r-build-system)
10680 `(("r-biocgenerics" ,r-biocgenerics)
10681 ("r-delayedarray" ,r-delayedarray)
10682 ("r-hdf5array" ,r-hdf5array)
10684 ("r-rhdf5" ,r-rhdf5)
10685 ("r-rhdf5lib" ,r-rhdf5lib)))
10686 (home-page "https://bioconductor.org/packages/beachmat")
10687 (synopsis "Compiling Bioconductor to handle each matrix type")
10688 (description "This package provides a consistent C++ class interface for a
10689 variety of commonly used matrix types, including sparse and HDF5-backed
10691 (license license:gpl3)))
10693 (define-public r-singlecellexperiment
10695 (name "r-singlecellexperiment")
10700 (uri (bioconductor-uri "SingleCellExperiment" version))
10703 "12139kk9cqgzpm6f3cwdsq31gj5lxamz2q939dy9fa0fa54gdaq4"))))
10705 `((upstream-name . "SingleCellExperiment")))
10706 (build-system r-build-system)
10708 `(("r-biocgenerics" ,r-biocgenerics)
10709 ("r-s4vectors" ,r-s4vectors)
10710 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10711 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10712 (synopsis "S4 classes for single cell data")
10713 (description "This package defines an S4 class for storing data from
10714 single-cell experiments. This includes specialized methods to store and
10715 retrieve spike-in information, dimensionality reduction coordinates and size
10716 factors for each cell, along with the usual metadata for genes and
10718 (license license:gpl3)))
10720 (define-public r-scater
10726 (uri (bioconductor-uri "scater" version))
10729 "0rijhy7g5qmcn927y1wyd63la1fhyar9fv1hccsqd23jd98yc55a"))))
10730 (build-system r-build-system)
10732 `(("r-beachmat" ,r-beachmat)
10733 ("r-biocgenerics" ,r-biocgenerics)
10734 ("r-biocparallel" ,r-biocparallel)
10735 ("r-delayedarray" ,r-delayedarray)
10736 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10737 ("r-dplyr" ,r-dplyr)
10738 ("r-ggbeeswarm" ,r-ggbeeswarm)
10739 ("r-ggplot2" ,r-ggplot2)
10740 ("r-matrix" ,r-matrix)
10743 ("r-reshape2" ,r-reshape2)
10744 ("r-rhdf5lib" ,r-rhdf5lib)
10745 ("r-s4vectors" ,r-s4vectors)
10746 ("r-singlecellexperiment" ,r-singlecellexperiment)
10747 ("r-summarizedexperiment" ,r-summarizedexperiment)
10748 ("r-viridis" ,r-viridis)))
10749 (home-page "https://github.com/davismcc/scater")
10750 (synopsis "Single-cell analysis toolkit for gene expression data in R")
10751 (description "This package provides a collection of tools for doing
10752 various analyses of single-cell RNA-seq gene expression data, with a focus on
10754 (license license:gpl2+)))
10756 (define-public r-scran
10763 (uri (bioconductor-uri "scran" version))
10766 "07mgilr3gq3lnrm1fjm9zhz4w7970bjhsykln1drqy9gkzj5sn7g"))))
10767 (build-system r-build-system)
10769 `(("r-beachmat" ,r-beachmat)
10770 ("r-biocgenerics" ,r-biocgenerics)
10771 ("r-biocneighbors" ,r-biocneighbors)
10772 ("r-biocparallel" ,r-biocparallel)
10773 ("r-delayedarray" ,r-delayedarray)
10774 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10775 ("r-dynamictreecut" ,r-dynamictreecut)
10776 ("r-edger" ,r-edger)
10777 ("r-igraph" ,r-igraph)
10778 ("r-limma" ,r-limma)
10779 ("r-matrix" ,r-matrix)
10781 ("r-rhdf5lib" ,r-rhdf5lib)
10782 ("r-s4vectors" ,r-s4vectors)
10783 ("r-scater" ,r-scater)
10784 ("r-singlecellexperiment" ,r-singlecellexperiment)
10785 ("r-statmod" ,r-statmod)
10786 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10787 (home-page "https://bioconductor.org/packages/scran")
10788 (synopsis "Methods for single-cell RNA-Seq data analysis")
10789 (description "This package implements a variety of low-level analyses of
10790 single-cell RNA-seq data. Methods are provided for normalization of
10791 cell-specific biases, assignment of cell cycle phase, and detection of highly
10792 variable and significantly correlated genes.")
10793 (license license:gpl3)))
10795 (define-public r-delayedmatrixstats
10797 (name "r-delayedmatrixstats")
10802 (uri (bioconductor-uri "DelayedMatrixStats" version))
10805 "03fk2avl1vyjv2wslczkc82qr0zmp1ra8iimd47pbmnnm839ly4w"))))
10807 `((upstream-name . "DelayedMatrixStats")))
10808 (build-system r-build-system)
10810 `(("r-biocparallel" ,r-biocparallel)
10811 ("r-delayedarray" ,r-delayedarray)
10812 ("r-hdf5array" ,r-hdf5array)
10813 ("r-iranges" ,r-iranges)
10814 ("r-matrix" ,r-matrix)
10815 ("r-matrixstats" ,r-matrixstats)
10816 ("r-s4vectors" ,r-s4vectors)))
10817 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
10818 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
10820 "This package provides a port of the @code{matrixStats} API for use with
10821 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
10822 contains high-performing functions operating on rows and columns of
10823 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
10824 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
10825 are optimized per data type and for subsetted calculations such that both
10826 memory usage and processing time is minimized.")
10827 (license license:expat)))
10829 (define-public r-phangorn
10831 (name "r-phangorn")
10836 (uri (cran-uri "phangorn" version))
10839 "0xc8k552nxczy19jr0xjjagrzc8x6lafasgk2c099ls8bc1yml1i"))))
10840 (build-system r-build-system)
10843 ("r-fastmatch" ,r-fastmatch)
10844 ("r-igraph" ,r-igraph)
10845 ("r-magrittr" ,r-magrittr)
10846 ("r-matrix" ,r-matrix)
10847 ("r-quadprog" ,r-quadprog)
10848 ("r-rcpp" ,r-rcpp)))
10849 (home-page "https://github.com/KlausVigo/phangorn")
10850 (synopsis "Phylogenetic analysis in R")
10852 "Phangorn is a package for phylogenetic analysis in R. It supports
10853 estimation of phylogenetic trees and networks using Maximum Likelihood,
10854 Maximum Parsimony, distance methods and Hadamard conjugation.")
10855 (license license:gpl2+)))
10857 (define-public r-dropbead
10858 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
10861 (name "r-dropbead")
10862 (version (string-append "0-" revision "." (string-take commit 7)))
10866 (uri (git-reference
10867 (url "https://github.com/rajewsky-lab/dropbead.git")
10869 (file-name (git-file-name name version))
10872 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
10873 (build-system r-build-system)
10875 `(("r-ggplot2" ,r-ggplot2)
10876 ("r-rcolorbrewer" ,r-rcolorbrewer)
10877 ("r-gridextra" ,r-gridextra)
10878 ("r-gplots" ,r-gplots)
10879 ("r-plyr" ,r-plyr)))
10880 (home-page "https://github.com/rajewsky-lab/dropbead")
10881 (synopsis "Basic exploration and analysis of Drop-seq data")
10882 (description "This package offers a quick and straight-forward way to
10883 explore and perform basic analysis of single cell sequencing data coming from
10884 droplet sequencing. It has been particularly tailored for Drop-seq.")
10885 (license license:gpl3))))
10887 (define htslib-for-sambamba
10888 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
10891 (name "htslib-for-sambamba")
10892 (version (string-append "1.3.1-1." (string-take commit 9)))
10896 (uri (git-reference
10897 (url "https://github.com/lomereiter/htslib.git")
10899 (file-name (string-append "htslib-" version "-checkout"))
10902 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
10904 `(("autoconf" ,autoconf)
10905 ("automake" ,automake)
10906 ,@(package-native-inputs htslib))))))
10908 (define-public sambamba
10915 (uri (git-reference
10916 (url "https://github.com/lomereiter/sambamba.git")
10917 (commit (string-append "v" version))))
10918 (file-name (string-append name "-" version "-checkout"))
10921 "0k0cz3qcv98p6cq09zlbgnjsggxcqbcmzxg5zikgcgbr2nfq4lry"))))
10922 (build-system gnu-build-system)
10924 `(#:tests? #f ; there is no test target
10925 #:parallel-build? #f ; not supported
10927 (modify-phases %standard-phases
10928 (delete 'configure)
10929 (add-after 'unpack 'fix-ldc-version
10931 (substitute* "gen_ldc_version_info.py"
10932 (("/usr/bin/env.*") (which "python3")))
10933 (substitute* "Makefile"
10934 ;; We use ldc2 instead of ldmd2 to compile sambamba.
10935 (("\\$\\(shell which ldmd2\\)") (which "ldc2")))
10937 (add-after 'unpack 'place-biod-and-undead
10938 (lambda* (#:key inputs #:allow-other-keys)
10939 (copy-recursively (assoc-ref inputs "biod") "BioD")
10940 (copy-recursively (assoc-ref inputs "undead") "undeaD")
10942 (add-after 'unpack 'unbundle-prerequisites
10944 (substitute* "Makefile"
10945 (("htslib/libhts.a lz4/lib/liblz4.a")
10947 ((" lz4-static htslib-static") ""))
10950 (lambda* (#:key outputs #:allow-other-keys)
10951 (let* ((out (assoc-ref outputs "out"))
10952 (bin (string-append out "/bin")))
10954 (install-file "bin/sambamba" bin)
10961 ,(let ((commit "4f1a7d2fb7ef3dfe962aa357d672f354ebfbe42e"))
10964 (uri (git-reference
10965 (url "https://github.com/biod/BioD.git")
10967 (file-name (string-append "biod-"
10968 (string-take commit 9)
10972 "1k5pdjv1qvi0a3rwd1sfq6zbj37l86i7bf710m4c0y6737lxj426")))))
10974 ,(let ((commit "9be93876982b5f14fcca60832563b3cd767dd84d"))
10977 (uri (git-reference
10978 (url "https://github.com/biod/undeaD.git")
10980 (file-name (string-append "undead-"
10981 (string-take commit 9)
10985 "1xfarj0nqlmi5jd1vmcmm7pabzaf9hxyvk6hp0d6jslb5k9r8r3d")))))))
10988 ("htslib" ,htslib-for-sambamba)))
10989 (home-page "http://lomereiter.github.io/sambamba")
10990 (synopsis "Tools for working with SAM/BAM data")
10991 (description "Sambamba is a high performance modern robust and
10992 fast tool (and library), written in the D programming language, for
10993 working with SAM and BAM files. Current parallelised functionality is
10994 an important subset of samtools functionality, including view, index,
10995 sort, markdup, and depth.")
10996 (license license:gpl2+)))
10998 (define-public ritornello
11000 (name "ritornello")
11004 (uri (git-reference
11005 (url "https://github.com/KlugerLab/Ritornello.git")
11006 (commit (string-append "v" version))))
11007 (file-name (git-file-name name version))
11010 "1xahvq215qld7x1w8vpa5zbrsj6p9crb9shqa2x89sb0aaxa02jk"))))
11011 (build-system gnu-build-system)
11013 `(#:tests? #f ; there are no tests
11015 (modify-phases %standard-phases
11016 (add-after 'unpack 'patch-samtools-references
11017 (lambda* (#:key inputs #:allow-other-keys)
11018 (substitute* '("src/SamStream.h"
11020 (("<sam.h>") "<samtools/sam.h>"))
11022 (delete 'configure)
11024 (lambda* (#:key inputs outputs #:allow-other-keys)
11025 (let* ((out (assoc-ref outputs "out"))
11026 (bin (string-append out "/bin/")))
11028 (install-file "bin/Ritornello" bin)
11031 `(("samtools" ,samtools-0.1)
11035 (home-page "https://github.com/KlugerLab/Ritornello")
11036 (synopsis "Control-free peak caller for ChIP-seq data")
11037 (description "Ritornello is a ChIP-seq peak calling algorithm based on
11038 signal processing that can accurately call binding events without the need to
11039 do a pair total DNA input or IgG control sample. It has been tested for use
11040 with narrow binding events such as transcription factor ChIP-seq.")
11041 (license license:gpl3+)))
11043 (define-public trim-galore
11045 (name "trim-galore")
11050 (uri (git-reference
11051 (url "https://github.com/FelixKrueger/TrimGalore.git")
11053 (file-name (string-append name "-" version "-checkout"))
11056 "0x5892l48c816pf00wmnz5vq0zq6170d3xc8zrxncd4jcz7h1p71"))))
11057 (build-system gnu-build-system)
11059 `(#:tests? #f ; no tests
11061 (modify-phases %standard-phases
11062 (delete 'configure)
11064 (add-after 'unpack 'hardcode-tool-references
11065 (lambda* (#:key inputs #:allow-other-keys)
11066 (substitute* "trim_galore"
11067 (("\\$path_to_cutadapt = 'cutadapt'")
11068 (string-append "$path_to_cutadapt = '"
11069 (assoc-ref inputs "cutadapt")
11072 (string-append "| "
11073 (assoc-ref inputs "gzip")
11076 (string-append "\""
11077 (assoc-ref inputs "gzip")
11081 (lambda* (#:key outputs #:allow-other-keys)
11082 (let ((bin (string-append (assoc-ref outputs "out")
11085 (install-file "trim_galore" bin)
11090 ("cutadapt" ,cutadapt)))
11092 `(("unzip" ,unzip)))
11093 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
11094 (synopsis "Wrapper around Cutadapt and FastQC")
11095 (description "Trim Galore! is a wrapper script to automate quality and
11096 adapter trimming as well as quality control, with some added functionality to
11097 remove biased methylation positions for RRBS sequence files.")
11098 (license license:gpl3+)))
11100 (define-public gess
11106 (uri (string-append "http://compbio.uthscsa.edu/"
11108 "gess-" version ".src.tar.gz"))
11111 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
11112 (build-system gnu-build-system)
11114 `(#:tests? #f ; no tests
11116 (modify-phases %standard-phases
11117 (delete 'configure)
11120 (lambda* (#:key inputs outputs #:allow-other-keys)
11121 (let* ((python (assoc-ref inputs "python"))
11122 (out (assoc-ref outputs "out"))
11123 (bin (string-append out "/bin/"))
11124 (target (string-append
11126 ,(version-major+minor
11127 (package-version python))
11128 "/site-packages/gess/")))
11130 (copy-recursively "." target)
11131 ;; Make GESS.py executable
11132 (chmod (string-append target "GESS.py") #o555)
11133 ;; Add Python shebang to the top and make Matplotlib
11135 (substitute* (string-append target "GESS.py")
11136 (("\"\"\"Description:" line)
11137 (string-append "#!" (which "python") "
11139 matplotlib.use('Agg')
11141 ;; Make sure GESS has all modules in its path
11142 (wrap-program (string-append target "GESS.py")
11143 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
11145 (symlink (string-append target "GESS.py")
11146 (string-append bin "GESS.py"))
11149 `(("python" ,python-2)
11150 ("python2-pysam" ,python2-pysam)
11151 ("python2-scipy" ,python2-scipy)
11152 ("python2-numpy" ,python2-numpy)
11153 ("python2-networkx" ,python2-networkx)
11154 ("python2-biopython" ,python2-biopython)))
11155 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
11156 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11158 "GESS is an implementation of a novel computational method to detect de
11159 novo exon-skipping events directly from raw RNA-seq data without the prior
11160 knowledge of gene annotation information. GESS stands for the graph-based
11161 exon-skipping scanner detection scheme.")
11162 (license license:bsd-3)))
11164 (define-public phylip
11171 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11172 "download/phylip-" version ".tar.gz"))
11175 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11176 (build-system gnu-build-system)
11178 `(#:tests? #f ; no check target
11179 #:make-flags (list "-f" "Makefile.unx" "install")
11180 #:parallel-build? #f ; not supported
11182 (modify-phases %standard-phases
11183 (add-after 'unpack 'enter-dir
11184 (lambda _ (chdir "src") #t))
11185 (delete 'configure)
11187 (lambda* (#:key inputs outputs #:allow-other-keys)
11188 (let ((target (string-append (assoc-ref outputs "out")
11191 (for-each (lambda (file)
11192 (install-file file target))
11193 (find-files "../exe" ".*")))
11195 (home-page "http://evolution.genetics.washington.edu/phylip/")
11196 (synopsis "Tools for inferring phylogenies")
11197 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11198 programs for inferring phylogenies (evolutionary trees).")
11199 (license license:bsd-2)))
11208 (uri (string-append "https://integrativemodeling.org/"
11209 version "/download/imp-" version ".tar.gz"))
11212 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
11213 (build-system cmake-build-system)
11215 `(;; FIXME: Some tests fail because they produce warnings, others fail
11216 ;; because the PYTHONPATH does not include the modeller's directory.
11224 ("python" ,python-2)))
11226 `(("python2-numpy" ,python2-numpy)
11227 ("python2-scipy" ,python2-scipy)
11228 ("python2-pandas" ,python2-pandas)
11229 ("python2-scikit-learn" ,python2-scikit-learn)
11230 ("python2-networkx" ,python2-networkx)))
11231 (home-page "https://integrativemodeling.org")
11232 (synopsis "Integrative modeling platform")
11233 (description "IMP's broad goal is to contribute to a comprehensive
11234 structural characterization of biomolecules ranging in size and complexity
11235 from small peptides to large macromolecular assemblies, by integrating data
11236 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11237 Python toolbox for solving complex modeling problems, and a number of
11238 applications for tackling some common problems in a user-friendly way.")
11239 ;; IMP is largely available under the GNU Lesser GPL; see the file
11240 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11241 ;; available under the GNU GPL (see the file COPYING.GPL).
11242 (license (list license:lgpl2.1+
11245 (define-public tadbit
11251 (uri (git-reference
11252 (url "https://github.com/3DGenomes/TADbit.git")
11253 (commit (string-append "v" version))))
11254 (file-name (git-file-name name version))
11257 "07g3aj648prmsvxp9caz5yl41k0y0647vxh0f5p3w8376mfiljd0"))))
11258 (build-system python-build-system)
11260 `(;; Tests are included and must be run after installation, but
11261 ;; they are incomplete and thus cannot be run.
11265 (modify-phases %standard-phases
11266 (add-after 'unpack 'fix-problems-with-setup.py
11267 (lambda* (#:key outputs #:allow-other-keys)
11268 ;; setup.py opens these files for writing
11269 (chmod "_pytadbit/_version.py" #o664)
11270 (chmod "README.rst" #o664)
11272 ;; Don't attempt to install the bash completions to
11273 ;; the home directory.
11274 (rename-file "extras/.bash_completion"
11276 (substitute* "setup.py"
11277 (("\\(path.expanduser\\('~'\\)")
11278 (string-append "(\""
11279 (assoc-ref outputs "out")
11280 "/etc/bash_completion.d\""))
11281 (("extras/\\.bash_completion")
11285 ;; TODO: add Chimera for visualization
11288 ("python2-scipy" ,python2-scipy)
11289 ("python2-numpy" ,python2-numpy)
11290 ("python2-matplotlib" ,python2-matplotlib)
11291 ("python2-pysam" ,python2-pysam)))
11292 (home-page "https://3dgenomes.github.io/TADbit/")
11293 (synopsis "Analyze, model, and explore 3C-based data")
11295 "TADbit is a complete Python library to deal with all steps to analyze,
11296 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11297 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11298 correct interaction matrices, identify and compare the so-called
11299 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11300 interaction matrices, and finally, extract structural properties from the
11301 models. TADbit is complemented by TADkit for visualizing 3D models.")
11302 (license license:gpl3+)))
11304 (define-public kentutils
11307 ;; 302.1.0 is out, but the only difference is the inclusion of
11308 ;; pre-built binaries.
11309 (version "302.0.0")
11313 (uri (git-reference
11314 (url "https://github.com/ENCODE-DCC/kentUtils.git")
11315 (commit (string-append "v" version))))
11316 (file-name (git-file-name name version))
11319 "0n1wbyjpzii2b9qhyp9r1q76j623cggpg3y8fmw78ld3z4y7ivha"))
11320 (modules '((guix build utils)
11325 ;; Only the contents of the specified directories are free
11326 ;; for all uses, so we remove the rest. "hg/autoSql" and
11327 ;; "hg/autoXml" are nominally free, but they depend on a
11328 ;; library that is built from the sources in "hg/lib",
11329 ;; which is nonfree.
11330 (let ((free (list "." ".."
11331 "utils" "lib" "inc" "tagStorm"
11332 "parasol" "htslib"))
11333 (directory? (lambda (file)
11334 (eq? 'directory (stat:type (stat file))))))
11335 (for-each (lambda (file)
11336 (and (directory? file)
11337 (delete-file-recursively file)))
11338 (map (cut string-append "src/" <>)
11341 (not (member file free)))))))
11342 ;; Only make the utils target, not the userApps target,
11343 ;; because that requires libraries we won't build.
11344 (substitute* "Makefile"
11345 ((" userApps") " utils"))
11346 ;; Only build libraries that are free.
11347 (substitute* "src/makefile"
11348 (("DIRS =.*") "DIRS =\n")
11349 (("cd jkOwnLib.*") "")
11352 (substitute* "src/utils/makefile"
11353 ;; These tools depend on "jkhgap.a", which is part of the
11354 ;; nonfree "src/hg/lib" directory.
11355 (("raSqlQuery") "")
11356 (("pslLiftSubrangeBlat") "")
11358 ;; Do not build UCSC tools, which may require nonfree
11360 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11362 (build-system gnu-build-system)
11364 `( ;; There is no global test target and the test target for
11365 ;; individual tools depends on input files that are not
11369 (modify-phases %standard-phases
11370 (add-after 'unpack 'fix-permissions
11371 (lambda _ (make-file-writable "src/inc/localEnvironment.mk") #t))
11372 (add-after 'unpack 'fix-paths
11374 (substitute* "Makefile"
11375 (("/bin/echo") (which "echo")))
11377 (add-after 'unpack 'prepare-samtabix
11378 (lambda* (#:key inputs #:allow-other-keys)
11379 (copy-recursively (assoc-ref inputs "samtabix")
11382 (delete 'configure)
11384 (lambda* (#:key outputs #:allow-other-keys)
11385 (let ((bin (string-append (assoc-ref outputs "out")
11387 (copy-recursively "bin" bin))
11393 (uri (git-reference
11394 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11395 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11398 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11404 ("mariadb" ,mariadb)
11405 ("openssl" ,openssl)))
11406 (home-page "http://genome.cse.ucsc.edu/index.html")
11407 (synopsis "Assorted bioinformatics utilities")
11408 (description "This package provides the kentUtils, a selection of
11409 bioinformatics utilities used in combination with the UCSC genome
11411 ;; Only a subset of the sources are released under a non-copyleft
11412 ;; free software license. All other sources are removed in a
11413 ;; snippet. See this bug report for an explanation of how the
11414 ;; license statements apply:
11415 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11416 (license (license:non-copyleft
11417 "http://genome.ucsc.edu/license/"
11418 "The contents of this package are free for all uses."))))
11420 (define-public f-seq
11421 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11425 (version (string-append "1.1-" revision "." (string-take commit 7)))
11428 (uri (git-reference
11429 (url "https://github.com/aboyle/F-seq.git")
11431 (file-name (string-append name "-" version))
11434 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11435 (modules '((guix build utils)))
11436 ;; Remove bundled Java library archives.
11439 (for-each delete-file (find-files "lib" ".*"))
11441 (build-system ant-build-system)
11443 `(#:tests? #f ; no tests included
11445 (modify-phases %standard-phases
11447 (lambda* (#:key inputs outputs #:allow-other-keys)
11448 (let* ((target (assoc-ref outputs "out"))
11449 (bin (string-append target "/bin"))
11450 (doc (string-append target "/share/doc/f-seq"))
11451 (lib (string-append target "/lib")))
11454 (substitute* "bin/linux/fseq"
11455 (("java") (which "java"))
11456 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11457 (string-append (assoc-ref inputs "java-commons-cli")
11458 "/share/java/commons-cli.jar"))
11460 (string-append "REALDIR=" bin "\n")))
11461 (install-file "README.txt" doc)
11462 (install-file "bin/linux/fseq" bin)
11463 (install-file "build~/fseq.jar" lib)
11464 (copy-recursively "lib" lib)
11468 ("java-commons-cli" ,java-commons-cli)))
11469 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11470 (synopsis "Feature density estimator for high-throughput sequence tags")
11472 "F-Seq is a software package that generates a continuous tag sequence
11473 density estimation allowing identification of biologically meaningful sites
11474 such as transcription factor binding sites (ChIP-seq) or regions of open
11475 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11477 (license license:gpl3+))))
11479 (define-public bismark
11486 (uri (git-reference
11487 (url "https://github.com/FelixKrueger/Bismark.git")
11489 (file-name (string-append name "-" version "-checkout"))
11492 "0xchm3rgilj6vfjnyzfzzymfd7djr64sbrmrvs3njbwi66jqbzw9"))))
11493 (build-system perl-build-system)
11495 `(#:tests? #f ; there are no tests
11496 #:modules ((guix build utils)
11499 (guix build perl-build-system))
11501 (modify-phases %standard-phases
11502 ;; The bundled plotly.js is minified.
11503 (add-after 'unpack 'replace-plotly.js
11504 (lambda* (#:key inputs #:allow-other-keys)
11505 (let* ((file (assoc-ref inputs "plotly.js"))
11506 (installed "plotly/plotly.js"))
11507 (let ((minified (open-pipe* OPEN_READ "uglify-js" file)))
11508 (call-with-output-file installed
11509 (cut dump-port minified <>))))
11511 (delete 'configure)
11514 (lambda* (#:key inputs outputs #:allow-other-keys)
11515 (let* ((out (assoc-ref outputs "out"))
11516 (bin (string-append out "/bin"))
11517 (share (string-append out "/share/bismark"))
11518 (docdir (string-append out "/share/doc/bismark"))
11519 (docs '("Docs/Bismark_User_Guide.html"))
11520 (scripts '("bismark"
11521 "bismark_genome_preparation"
11522 "bismark_methylation_extractor"
11525 "coverage2cytosine"
11526 "deduplicate_bismark"
11527 "filter_non_conversion"
11530 "NOMe_filtering")))
11531 (substitute* "bismark2report"
11532 (("\\$RealBin/plotly")
11533 (string-append share "/plotly")))
11537 (for-each (lambda (file) (install-file file bin))
11539 (for-each (lambda (file) (install-file file docdir))
11541 (copy-recursively "Docs/Images" (string-append docdir "/Images"))
11542 (copy-recursively "plotly"
11543 (string-append share "/plotly"))
11545 ;; Fix references to gunzip
11546 (substitute* (map (lambda (file)
11547 (string-append bin "/" file))
11550 (string-append "\"" (assoc-ref inputs "gzip")
11551 "/bin/gunzip -c")))
11555 ("perl-carp" ,perl-carp)
11556 ("perl-getopt-long" ,perl-getopt-long)))
11561 (uri (string-append "https://raw.githubusercontent.com/plotly/plotly.js/"
11562 "v1.39.4/dist/plotly.js"))
11564 (base32 "138mwsr4nf5qif4mrxx286mpnagxd1xwl6k8aidrjgknaqg88zyr"))))
11565 ("uglify-js" ,uglify-js)))
11566 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11567 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11568 (description "Bismark is a program to map bisulfite treated sequencing
11569 reads to a genome of interest and perform methylation calls in a single step.
11570 The output can be easily imported into a genome viewer, such as SeqMonk, and
11571 enables a researcher to analyse the methylation levels of their samples
11572 straight away. Its main features are:
11575 @item Bisulfite mapping and methylation calling in one single step
11576 @item Supports single-end and paired-end read alignments
11577 @item Supports ungapped and gapped alignments
11578 @item Alignment seed length, number of mismatches etc are adjustable
11579 @item Output discriminates between cytosine methylation in CpG, CHG
11582 (license license:gpl3+)))
11584 (define-public paml
11590 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11591 "paml" version ".tgz"))
11594 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11595 (modules '((guix build utils)))
11596 ;; Remove Windows binaries
11599 (for-each delete-file (find-files "." "\\.exe$"))
11601 (build-system gnu-build-system)
11603 `(#:tests? #f ; there are no tests
11604 #:make-flags '("CC=gcc")
11606 (modify-phases %standard-phases
11607 (replace 'configure
11609 (substitute* "src/BFdriver.c"
11610 (("/bin/bash") (which "bash")))
11614 (lambda* (#:key outputs #:allow-other-keys)
11615 (let ((tools '("baseml" "basemlg" "codeml"
11616 "pamp" "evolver" "yn00" "chi2"))
11617 (bin (string-append (assoc-ref outputs "out") "/bin"))
11618 (docdir (string-append (assoc-ref outputs "out")
11619 "/share/doc/paml")))
11621 (for-each (lambda (file) (install-file file bin)) tools)
11622 (copy-recursively "../doc" docdir)
11624 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11625 (synopsis "Phylogentic analysis by maximum likelihood")
11626 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11627 contains a few programs for model fitting and phylogenetic tree reconstruction
11628 using nucleotide or amino-acid sequence data.")
11630 (license license:gpl3)))
11632 (define-public kallisto
11638 (uri (git-reference
11639 (url "https://github.com/pachterlab/kallisto.git")
11640 (commit (string-append "v" version))))
11641 (file-name (git-file-name name version))
11644 "0nj382jiywqnpgvyhichajpkkh5r0bapn43f4dx40zdaq5v4m40m"))))
11645 (build-system cmake-build-system)
11647 `(#:tests? #f ; no "check" target
11649 (modify-phases %standard-phases
11650 (add-after 'unpack 'do-not-use-bundled-htslib
11652 (substitute* "CMakeLists.txt"
11653 (("^ExternalProject_Add" m)
11654 (string-append "if (NEVER)\n" m))
11656 (string-append ")\nendif(NEVER)"))
11657 (("include_directories\\(\\$\\{htslib_PREFIX.*" m)
11658 (string-append "# " m)))
11659 (substitute* "src/CMakeLists.txt"
11660 (("target_link_libraries\\(kallisto kallisto_core pthread \
11661 \\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/../ext/htslib/libhts.a\\)")
11662 "target_link_libraries(kallisto kallisto_core pthread hts)")
11663 (("include_directories\\(\\.\\./ext/htslib\\)") ""))
11669 (home-page "http://pachterlab.github.io/kallisto/")
11670 (synopsis "Near-optimal RNA-Seq quantification")
11672 "Kallisto is a program for quantifying abundances of transcripts from
11673 RNA-Seq data, or more generally of target sequences using high-throughput
11674 sequencing reads. It is based on the novel idea of pseudoalignment for
11675 rapidly determining the compatibility of reads with targets, without the need
11676 for alignment. Pseudoalignment of reads preserves the key information needed
11677 for quantification, and kallisto is therefore not only fast, but also as
11678 accurate as existing quantification tools.")
11679 (license license:bsd-2)))
11681 (define-public libgff
11687 (uri (git-reference
11688 (url "https://github.com/Kingsford-Group/libgff.git")
11689 (commit (string-append "v" version))))
11690 (file-name (git-file-name name version))
11693 "0n6vfjnq7a2mianipscbshrvbncss8z4zkgkbjw754p9043nfkps"))))
11694 (build-system cmake-build-system)
11695 (arguments `(#:tests? #f)) ; no tests included
11696 (home-page "https://github.com/Kingsford-Group/libgff")
11697 (synopsis "Parser library for reading/writing GFF files")
11698 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11699 code that is used in the Cufflinks codebase. The goal of this library is to
11700 provide this functionality without the necessity of drawing in a heavy-weight
11701 dependency like SeqAn.")
11702 (license (license:x11-style "https://www.boost.org/LICENSE_1_0.txt"))))
11704 (define-public libdivsufsort
11706 (name "libdivsufsort")
11710 (uri (git-reference
11711 (url "https://github.com/y-256/libdivsufsort.git")
11713 (file-name (git-file-name name version))
11716 "0fgdz9fzihlvjjrxy01md1bv9vh12rkgkwbm90b1hj5xpbaqp7z2"))))
11717 (build-system cmake-build-system)
11719 '(#:tests? #f ; there are no tests
11721 ;; Needed for rapmap and sailfish.
11722 '("-DBUILD_DIVSUFSORT64=ON")))
11723 (home-page "https://github.com/y-256/libdivsufsort")
11724 (synopsis "Lightweight suffix-sorting library")
11725 (description "libdivsufsort is a software library that implements a
11726 lightweight suffix array construction algorithm. This library provides a
11727 simple and an efficient C API to construct a suffix array and a
11728 Burrows-Wheeler transformed string from a given string over a constant-size
11729 alphabet. The algorithm runs in O(n log n) worst-case time using only 5n+O(1)
11730 bytes of memory space, where n is the length of the string.")
11731 (license license:expat)))
11733 (define-public sailfish
11739 (uri (git-reference
11740 (url "https://github.com/kingsfordgroup/sailfish.git")
11741 (commit (string-append "v" version))))
11742 (file-name (git-file-name name version))
11745 "1amcc5hqvsl42hg4x19bi9vy47cl874s0lw1fmi0hwsdk9i8c03v"))
11746 (modules '((guix build utils)))
11749 ;; Delete bundled headers for eigen3.
11750 (delete-file-recursively "include/eigen3/")
11752 (build-system cmake-build-system)
11754 `(#:configure-flags
11755 (list (string-append "-DBOOST_INCLUDEDIR="
11756 (assoc-ref %build-inputs "boost")
11758 (string-append "-DBOOST_LIBRARYDIR="
11759 (assoc-ref %build-inputs "boost")
11761 (string-append "-DBoost_LIBRARIES="
11762 "-lboost_iostreams "
11763 "-lboost_filesystem "
11768 "-lboost_program_options")
11769 "-DBoost_FOUND=TRUE"
11770 ;; Don't download RapMap---we already have it!
11771 "-DFETCHED_RAPMAP=1")
11772 ;; Tests must be run after installation and the location of the test
11773 ;; data file must be overridden. But the tests fail. It looks like
11774 ;; they are not really meant to be run.
11777 (modify-phases %standard-phases
11778 ;; Boost cannot be found, even though it's right there.
11779 (add-after 'unpack 'do-not-look-for-boost
11780 (lambda* (#:key inputs #:allow-other-keys)
11781 (substitute* "CMakeLists.txt"
11782 (("find_package\\(Boost 1\\.53\\.0") "#"))
11784 (add-after 'unpack 'do-not-assign-to-macro
11786 (substitute* "include/spdlog/details/format.cc"
11787 (("const unsigned CHAR_WIDTH = 1;") ""))
11789 (add-after 'unpack 'prepare-rapmap
11790 (lambda* (#:key inputs #:allow-other-keys)
11791 (let ((src "external/install/src/rapmap/")
11792 (include "external/install/include/rapmap/")
11793 (rapmap (assoc-ref inputs "rapmap")))
11794 (mkdir-p "/tmp/rapmap")
11796 (assoc-ref inputs "rapmap")
11798 "--strip-components=1")
11801 (for-each (lambda (file)
11802 (install-file file src))
11803 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
11804 (copy-recursively "/tmp/rapmap/include" include))
11806 (add-after 'unpack 'use-system-libraries
11807 (lambda* (#:key inputs #:allow-other-keys)
11808 (substitute* '("src/SailfishIndexer.cpp"
11809 "src/SailfishUtils.cpp"
11810 "src/SailfishQuantify.cpp"
11811 "src/FASTAParser.cpp"
11813 "include/SailfishUtils.hpp"
11814 "include/SailfishIndex.hpp"
11815 "include/CollapsedEMOptimizer.hpp"
11816 "src/CollapsedEMOptimizer.cpp")
11817 (("#include \"jellyfish/config.h\"") ""))
11818 (substitute* "src/CMakeLists.txt"
11819 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11820 (string-append (assoc-ref inputs "jellyfish")
11821 "/include/jellyfish-" ,(package-version jellyfish)))
11822 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11823 (string-append (assoc-ref inputs "jellyfish")
11824 "/lib/libjellyfish-2.0.a"))
11825 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11826 (string-append (assoc-ref inputs "libdivsufsort")
11827 "/lib/libdivsufsort.so"))
11828 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11829 (string-append (assoc-ref inputs "libdivsufsort")
11830 "/lib/libdivsufsort64.so")))
11831 (substitute* "CMakeLists.txt"
11832 ;; Don't prefer static libs
11833 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11834 (("find_package\\(Jellyfish.*") "")
11835 (("ExternalProject_Add\\(libjellyfish") "message(")
11836 (("ExternalProject_Add\\(libgff") "message(")
11837 (("ExternalProject_Add\\(libsparsehash") "message(")
11838 (("ExternalProject_Add\\(libdivsufsort") "message("))
11840 ;; Ensure that Eigen headers can be found
11841 (setenv "CPLUS_INCLUDE_PATH"
11842 (string-append (getenv "CPLUS_INCLUDE_PATH")
11844 (assoc-ref inputs "eigen")
11845 "/include/eigen3"))
11850 ("jemalloc" ,jemalloc)
11851 ("jellyfish" ,jellyfish)
11852 ("sparsehash" ,sparsehash)
11855 (uri (git-reference
11856 (url "https://github.com/COMBINE-lab/RapMap.git")
11857 (commit (string-append "sf-v" version))))
11858 (file-name (string-append "rapmap-sf-v" version "-checkout"))
11861 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
11862 (modules '((guix build utils)))
11863 ;; These files are expected to be excluded.
11865 '(begin (delete-file-recursively "include/spdlog")
11866 (for-each delete-file '("include/xxhash.h"
11869 ("libdivsufsort" ,libdivsufsort)
11874 `(("pkg-config" ,pkg-config)))
11875 (home-page "http://www.cs.cmu.edu/~ckingsf/software/sailfish")
11876 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
11877 (description "Sailfish is a tool for genomic transcript quantification
11878 from RNA-seq data. It requires a set of target transcripts (either from a
11879 reference or de-novo assembly) to quantify. All you need to run sailfish is a
11880 fasta file containing your reference transcripts and a (set of) fasta/fastq
11881 file(s) containing your reads.")
11882 (license license:gpl3+)))
11884 (define libstadenio-for-salmon
11886 (name "libstadenio")
11890 (uri (git-reference
11891 (url "https://github.com/COMBINE-lab/staden-io_lib.git")
11892 (commit (string-append "v" version))))
11893 (file-name (string-append name "-" version "-checkout"))
11896 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
11897 (build-system gnu-build-system)
11898 (arguments '(#:parallel-tests? #f)) ; not supported
11902 `(("perl" ,perl))) ; for tests
11903 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
11904 (synopsis "General purpose trace and experiment file library")
11905 (description "This package provides a library of file reading and writing
11906 code to provide a general purpose Trace file (and Experiment File) reading
11909 The following file formats are supported:
11912 @item SCF trace files
11913 @item ABI trace files
11914 @item ALF trace files
11915 @item ZTR trace files
11916 @item SFF trace archives
11917 @item SRF trace archives
11918 @item Experiment files
11919 @item Plain text files
11920 @item SAM/BAM sequence files
11921 @item CRAM sequence files
11923 (license license:bsd-3)))
11925 (define spdlog-for-salmon
11931 (uri (git-reference
11932 (url "https://github.com/COMBINE-lab/spdlog.git")
11933 (commit (string-append "v" version))))
11934 (file-name (string-append name "-" version "-checkout"))
11937 "13730429gwlabi432ilpnja3sfvy0nn2719vnhhmii34xcdyc57q"))))
11938 (build-system cmake-build-system)
11939 (home-page "https://github.com/COMBINE-lab/spdlog")
11940 (synopsis "Very fast C++ logging library")
11941 (description "Spdlog is a very fast header-only C++ logging library with
11942 performance as its primary goal.")
11943 (license license:expat)))
11945 ;; This is a modified variant of bwa for use with Salmon. It installs a
11946 ;; library to avoid having to build this as part of Salmon.
11947 (define bwa-for-salmon
11948 (package (inherit bwa)
11950 (version "0.7.12.5")
11953 (uri (git-reference
11954 (url "https://github.com/COMBINE-lab/bwa.git")
11955 (commit (string-append "v" version))))
11956 (file-name (string-append "bwa-for-salmon-" version "-checkout"))
11959 "1z2qa64y0c5hky10510x137mnzlhz6k8qf27csw4w9j6qihq95gb"))))
11960 (build-system gnu-build-system)
11962 '(#:tests? #f ;no "check" target
11964 (modify-phases %standard-phases
11966 (lambda* (#:key outputs #:allow-other-keys)
11967 (let* ((out (assoc-ref outputs "out"))
11968 (bin (string-append out "/bin"))
11969 (lib (string-append out "/lib"))
11970 (doc (string-append out "/share/doc/bwa"))
11971 (man (string-append out "/share/man/man1"))
11972 (inc (string-append out "/include/bwa")))
11973 (install-file "bwa" bin)
11974 (install-file "README.md" doc)
11975 (install-file "bwa.1" man)
11976 (install-file "libbwa.a" lib)
11979 (for-each (lambda (file)
11980 (install-file file inc))
11981 (find-files "." "\\.h$")))
11983 ;; no "configure" script
11984 (delete 'configure))))))
11986 (define-public salmon
11992 (uri (git-reference
11993 (url "https://github.com/COMBINE-lab/salmon.git")
11994 (commit (string-append "v" version))))
11995 (file-name (string-append name "-" version "-checkout"))
11998 "1zi1ff4i7y2ykk0vdzysgwzzzv166vg2x77pj1mf4baclavxj87a"))
11999 (modules '((guix build utils)))
12002 ;; Delete bundled headers for eigen3.
12003 (delete-file-recursively "include/eigen3/")
12005 (build-system cmake-build-system)
12007 `(#:configure-flags
12008 (list (string-append "-DBOOST_INCLUDEDIR="
12009 (assoc-ref %build-inputs "boost")
12011 (string-append "-DBOOST_LIBRARYDIR="
12012 (assoc-ref %build-inputs "boost")
12014 (string-append "-DBoost_LIBRARIES="
12015 "-lboost_iostreams "
12016 "-lboost_filesystem "
12021 "-lboost_program_options")
12022 "-DBoost_FOUND=TRUE"
12023 "-DTBB_LIBRARIES=tbb tbbmalloc"
12024 ;; Don't download RapMap---we already have it!
12025 "-DFETCHED_RAPMAP=1")
12027 (modify-phases %standard-phases
12028 ;; Boost cannot be found, even though it's right there.
12029 (add-after 'unpack 'do-not-look-for-boost
12030 (lambda* (#:key inputs #:allow-other-keys)
12031 (substitute* "CMakeLists.txt"
12032 (("find_package\\(Boost 1\\.53\\.0") "#"))
12034 (add-after 'unpack 'do-not-phone-home
12036 (substitute* "src/Salmon.cpp"
12037 (("getVersionMessage\\(\\)") "\"\""))
12039 (add-after 'unpack 'prepare-rapmap
12040 (lambda* (#:key inputs #:allow-other-keys)
12041 (let ((src "external/install/src/rapmap/")
12042 (include "external/install/include/rapmap/")
12043 (rapmap (assoc-ref inputs "rapmap")))
12046 (for-each (lambda (file)
12047 (install-file file src))
12048 (find-files (string-append rapmap "/src") "\\.(c|cpp)"))
12049 (copy-recursively (string-append rapmap "/include") include)
12050 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
12051 "external/install/include/rapmap/FastxParser.hpp"
12052 "external/install/include/rapmap/concurrentqueue.h"
12053 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
12054 "external/install/src/rapmap/FastxParser.cpp"
12055 "external/install/src/rapmap/xxhash.c")))
12057 (add-after 'unpack 'use-system-libraries
12058 (lambda* (#:key inputs #:allow-other-keys)
12059 (substitute* "src/CMakeLists.txt"
12060 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
12061 (string-append (assoc-ref inputs "jellyfish")
12062 "/include/jellyfish-" ,(package-version jellyfish)))
12063 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
12064 (string-append (assoc-ref inputs "jellyfish")
12065 "/lib/libjellyfish-2.0.a"))
12066 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12067 (string-append (assoc-ref inputs "libdivsufsort")
12068 "/lib/libdivsufsort.so"))
12069 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
12070 (string-append (assoc-ref inputs "libstadenio-for-salmon")
12071 "/lib/libstaden-read.a"))
12072 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libbwa.a")
12073 (string-append (assoc-ref inputs "bwa") "/lib/libbwa.a"))
12074 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12075 (string-append (assoc-ref inputs "libdivsufsort")
12076 "/lib/libdivsufsort64.so")))
12077 (substitute* "CMakeLists.txt"
12078 ;; Don't prefer static libs
12079 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12080 (("set\\(TBB_LIBRARIES") "message(")
12081 (("find_package\\(Jellyfish.*") "")
12082 (("ExternalProject_Add\\(libcereal") "message(")
12083 (("ExternalProject_Add\\(libbwa") "message(")
12084 (("ExternalProject_Add\\(libjellyfish") "message(")
12085 (("ExternalProject_Add\\(libgff") "message(")
12086 (("ExternalProject_Add\\(libtbb") "message(")
12087 (("ExternalProject_Add\\(libspdlog") "message(")
12088 (("ExternalProject_Add\\(libdivsufsort") "message(")
12089 (("ExternalProject_Add\\(libstadenio") "message(")
12090 (("ExternalProject_Add_Step\\(") "message("))
12092 ;; Ensure that all headers can be found
12093 (setenv "CPLUS_INCLUDE_PATH"
12094 (string-append (getenv "CPLUS_INCLUDE_PATH")
12096 (assoc-ref inputs "bwa")
12099 (assoc-ref inputs "eigen")
12100 "/include/eigen3"))
12102 (string-append (assoc-ref inputs "bwa")
12105 (assoc-ref inputs "eigen")
12106 "/include/eigen3"))
12108 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
12109 ;; run. It only exists after the install phase.
12110 (add-after 'unpack 'fix-tests
12112 (substitute* "src/CMakeLists.txt"
12113 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
12114 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
12118 ("bwa" ,bwa-for-salmon)
12124 (uri (git-reference
12125 (url "https://github.com/COMBINE-lab/RapMap.git")
12126 (commit (string-append "salmon-v" version))))
12127 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
12130 "1yc12yqsz6f0r8sg1qnk57xg34aqwc9jbqq6gd5ys28xw3plj98p"))))
12131 ("jemalloc" ,jemalloc)
12132 ("jellyfish" ,jellyfish)
12135 ("libdivsufsort" ,libdivsufsort)
12136 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
12137 ("spdlog-for-salmon" ,spdlog-for-salmon)
12140 (home-page "https://github.com/COMBINE-lab/salmon")
12141 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
12142 (description "Salmon is a program to produce highly-accurate,
12143 transcript-level quantification estimates from RNA-seq data. Salmon achieves
12144 its accuracy and speed via a number of different innovations, including the
12145 use of lightweight alignments (accurate but fast-to-compute proxies for
12146 traditional read alignments) and massively-parallel stochastic collapsed
12147 variational inference.")
12148 (license license:gpl3+)))
12150 (define-public python-loompy
12152 (name "python-loompy")
12154 ;; The tarball on Pypi does not include the tests.
12157 (uri (git-reference
12158 (url "https://github.com/linnarsson-lab/loompy.git")
12160 (file-name (git-file-name name version))
12163 "12a5kjgiikapv93wahfw0frszx1lblnppyz3vs5gy8fgmgngra07"))))
12164 (build-system python-build-system)
12167 (modify-phases %standard-phases
12170 (setenv "PYTHONPATH"
12171 (string-append (getcwd) ":"
12172 (getenv "PYTHONPATH")))
12173 (invoke "pytest" "tests")
12176 `(("python-h5py" ,python-h5py)
12177 ("python-numpy" ,python-numpy)
12178 ("python-pandas" ,python-pandas)
12179 ("python-scipy" ,python-scipy)))
12181 `(("python-pytest" ,python-pytest)))
12182 (home-page "https://github.com/linnarsson-lab/loompy")
12183 (synopsis "Work with .loom files for single-cell RNA-seq data")
12184 (description "The loom file format is an efficient format for very large
12185 omics datasets, consisting of a main matrix, optional additional layers, a
12186 variable number of row and column annotations. Loom also supports sparse
12187 graphs. This library makes it easy to work with @file{.loom} files for
12188 single-cell RNA-seq data.")
12189 (license license:bsd-3)))
12191 ;; We cannot use the latest commit because it requires Java 9.
12192 (define-public java-forester
12193 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
12196 (name "java-forester")
12197 (version (string-append "0-" revision "." (string-take commit 7)))
12200 (uri (git-reference
12201 (url "https://github.com/cmzmasek/forester.git")
12203 (file-name (string-append name "-" version "-checkout"))
12206 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12207 (modules '((guix build utils)))
12210 ;; Delete bundled jars and pre-built classes
12211 (delete-file-recursively "forester/java/resources")
12212 (delete-file-recursively "forester/java/classes")
12213 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12214 ;; Delete bundled applications
12215 (delete-file-recursively "forester_applications")
12217 (build-system ant-build-system)
12219 `(#:tests? #f ; there are none
12221 #:modules ((guix build ant-build-system)
12223 (guix build java-utils)
12227 (modify-phases %standard-phases
12228 (add-after 'unpack 'chdir
12229 (lambda _ (chdir "forester/java") #t))
12230 (add-after 'chdir 'fix-dependencies
12232 (chmod "build.xml" #o664)
12233 (call-with-output-file "build.xml.new"
12237 (with-input-from-file "build.xml"
12238 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12239 `(;; Remove all unjar tags to avoid repacking classes.
12240 (unjar . ,(lambda _ '()))
12241 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12242 (*text* . ,(lambda (_ txt) txt))))
12244 (rename-file "build.xml.new" "build.xml")
12246 ;; FIXME: itext is difficult to package as it depends on a few
12247 ;; unpackaged libraries.
12248 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12250 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12251 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12252 (("pdf_written_to = PdfExporter.*")
12253 "throw new IOException(\"PDF export is not available.\");"))
12255 ;; There is no install target
12256 (replace 'install (install-jars ".")))))
12258 `(("java-commons-codec" ,java-commons-codec)
12259 ("java-openchart2" ,java-openchart2)))
12260 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12261 (synopsis "Phylogenomics libraries for Java")
12262 (description "Forester is a collection of Java libraries for
12263 phylogenomics and evolutionary biology research. It includes support for
12264 reading, writing, and exporting phylogenetic trees.")
12265 (license license:lgpl2.1+))))
12267 (define-public java-forester-1.005
12269 (name "java-forester")
12273 (uri (string-append "http://search.maven.org/remotecontent?"
12274 "filepath=org/biojava/thirdparty/forester/"
12275 version "/forester-" version "-sources.jar"))
12276 (file-name (string-append name "-" version ".jar"))
12279 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12280 (build-system ant-build-system)
12282 `(#:tests? #f ; there are none
12284 #:modules ((guix build ant-build-system)
12286 (guix build java-utils)
12290 (modify-phases %standard-phases
12291 (add-after 'unpack 'fix-dependencies
12292 (lambda* (#:key inputs #:allow-other-keys)
12293 (call-with-output-file "build.xml"
12297 (with-input-from-file "src/build.xml"
12298 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12299 `(;; Remove all unjar tags to avoid repacking classes.
12300 (unjar . ,(lambda _ '()))
12301 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12302 (*text* . ,(lambda (_ txt) txt))))
12304 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12305 "synth_look_and_feel_1.xml")
12306 (copy-file (assoc-ref inputs "phyloxml.xsd")
12308 (substitute* "build.xml"
12309 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12310 "synth_look_and_feel_1.xml")
12311 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12314 ;; FIXME: itext is difficult to package as it depends on a few
12315 ;; unpackaged libraries.
12316 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12318 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12319 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12320 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12321 (("pdf_written_to = PdfExporter.*")
12322 "throw new IOException(\"PDF export is not available.\"); /*")
12323 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12324 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12326 (add-after 'unpack 'delete-pre-built-classes
12327 (lambda _ (delete-file-recursively "src/classes") #t))
12328 ;; There is no install target
12329 (replace 'install (install-jars ".")))))
12331 `(("java-commons-codec" ,java-commons-codec)
12332 ("java-openchart2" ,java-openchart2)))
12333 ;; The source archive does not contain the resources.
12338 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12339 "b61cc2dcede0bede317db362472333115756b8c6/"
12340 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12341 (file-name (string-append name "-phyloxml-" version ".xsd"))
12344 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12345 ("synth_look_and_feel_1.xml"
12348 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12349 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12350 "forester/java/classes/resources/synth_look_and_feel_1.xml"))
12351 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12354 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12355 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12356 (synopsis "Phylogenomics libraries for Java")
12357 (description "Forester is a collection of Java libraries for
12358 phylogenomics and evolutionary biology research. It includes support for
12359 reading, writing, and exporting phylogenetic trees.")
12360 (license license:lgpl2.1+)))
12362 (define-public java-biojava-core
12364 (name "java-biojava-core")
12368 (uri (git-reference
12369 (url "https://github.com/biojava/biojava")
12370 (commit (string-append "biojava-" version))))
12371 (file-name (string-append name "-" version "-checkout"))
12374 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12375 (build-system ant-build-system)
12378 #:jar-name "biojava-core.jar"
12379 #:source-dir "biojava-core/src/main/java/"
12380 #:test-dir "biojava-core/src/test"
12381 ;; These tests seem to require internet access.
12382 #:test-exclude (list "**/SearchIOTest.java"
12383 "**/BlastXMLParserTest.java"
12384 "**/GenbankCookbookTest.java"
12385 "**/GenbankProxySequenceReaderTest.java")
12387 (modify-phases %standard-phases
12388 (add-before 'build 'copy-resources
12390 (copy-recursively "biojava-core/src/main/resources"
12393 (add-before 'check 'copy-test-resources
12395 (copy-recursively "biojava-core/src/test/resources"
12396 "build/test-classes")
12399 `(("java-log4j-api" ,java-log4j-api)
12400 ("java-log4j-core" ,java-log4j-core)
12401 ("java-slf4j-api" ,java-slf4j-api)
12402 ("java-slf4j-simple" ,java-slf4j-simple)))
12404 `(("java-junit" ,java-junit)
12405 ("java-hamcrest-core" ,java-hamcrest-core)))
12406 (home-page "http://biojava.org")
12407 (synopsis "Core libraries of Java framework for processing biological data")
12408 (description "BioJava is a project dedicated to providing a Java framework
12409 for processing biological data. It provides analytical and statistical
12410 routines, parsers for common file formats, reference implementations of
12411 popular algorithms, and allows the manipulation of sequences and 3D
12412 structures. The goal of the biojava project is to facilitate rapid
12413 application development for bioinformatics.
12415 This package provides the core libraries.")
12416 (license license:lgpl2.1+)))
12418 (define-public java-biojava-phylo
12419 (package (inherit java-biojava-core)
12420 (name "java-biojava-phylo")
12421 (build-system ant-build-system)
12424 #:jar-name "biojava-phylo.jar"
12425 #:source-dir "biojava-phylo/src/main/java/"
12426 #:test-dir "biojava-phylo/src/test"
12428 (modify-phases %standard-phases
12429 (add-before 'build 'copy-resources
12431 (copy-recursively "biojava-phylo/src/main/resources"
12434 (add-before 'check 'copy-test-resources
12436 (copy-recursively "biojava-phylo/src/test/resources"
12437 "build/test-classes")
12440 `(("java-log4j-api" ,java-log4j-api)
12441 ("java-log4j-core" ,java-log4j-core)
12442 ("java-slf4j-api" ,java-slf4j-api)
12443 ("java-slf4j-simple" ,java-slf4j-simple)
12444 ("java-biojava-core" ,java-biojava-core)
12445 ("java-forester" ,java-forester)))
12447 `(("java-junit" ,java-junit)
12448 ("java-hamcrest-core" ,java-hamcrest-core)))
12449 (home-page "http://biojava.org")
12450 (synopsis "Biojava interface to the forester phylogenomics library")
12451 (description "The phylo module provides a biojava interface layer to the
12452 forester phylogenomics library for constructing phylogenetic trees.")))
12454 (define-public java-biojava-alignment
12455 (package (inherit java-biojava-core)
12456 (name "java-biojava-alignment")
12457 (build-system ant-build-system)
12460 #:jar-name "biojava-alignment.jar"
12461 #:source-dir "biojava-alignment/src/main/java/"
12462 #:test-dir "biojava-alignment/src/test"
12464 (modify-phases %standard-phases
12465 (add-before 'build 'copy-resources
12467 (copy-recursively "biojava-alignment/src/main/resources"
12470 (add-before 'check 'copy-test-resources
12472 (copy-recursively "biojava-alignment/src/test/resources"
12473 "build/test-classes")
12476 `(("java-log4j-api" ,java-log4j-api)
12477 ("java-log4j-core" ,java-log4j-core)
12478 ("java-slf4j-api" ,java-slf4j-api)
12479 ("java-slf4j-simple" ,java-slf4j-simple)
12480 ("java-biojava-core" ,java-biojava-core)
12481 ("java-biojava-phylo" ,java-biojava-phylo)
12482 ("java-forester" ,java-forester)))
12484 `(("java-junit" ,java-junit)
12485 ("java-hamcrest-core" ,java-hamcrest-core)))
12486 (home-page "http://biojava.org")
12487 (synopsis "Biojava API for genetic sequence alignment")
12488 (description "The alignment module of BioJava provides an API that
12492 @item implementations of dynamic programming algorithms for sequence
12494 @item reading and writing of popular alignment file formats;
12495 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12498 (define-public java-biojava-core-4.0
12499 (package (inherit java-biojava-core)
12500 (name "java-biojava-core")
12504 (uri (git-reference
12505 (url "https://github.com/biojava/biojava")
12506 (commit (string-append "biojava-" version))))
12507 (file-name (string-append name "-" version "-checkout"))
12510 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12512 (define-public java-biojava-phylo-4.0
12513 (package (inherit java-biojava-core-4.0)
12514 (name "java-biojava-phylo")
12515 (build-system ant-build-system)
12518 #:jar-name "biojava-phylo.jar"
12519 #:source-dir "biojava-phylo/src/main/java/"
12520 #:test-dir "biojava-phylo/src/test"
12522 (modify-phases %standard-phases
12523 (add-before 'build 'copy-resources
12525 (copy-recursively "biojava-phylo/src/main/resources"
12528 (add-before 'check 'copy-test-resources
12530 (copy-recursively "biojava-phylo/src/test/resources"
12531 "build/test-classes")
12534 `(("java-log4j-api" ,java-log4j-api)
12535 ("java-log4j-core" ,java-log4j-core)
12536 ("java-slf4j-api" ,java-slf4j-api)
12537 ("java-slf4j-simple" ,java-slf4j-simple)
12538 ("java-biojava-core" ,java-biojava-core-4.0)
12539 ("java-forester" ,java-forester-1.005)))
12541 `(("java-junit" ,java-junit)
12542 ("java-hamcrest-core" ,java-hamcrest-core)))
12543 (home-page "http://biojava.org")
12544 (synopsis "Biojava interface to the forester phylogenomics library")
12545 (description "The phylo module provides a biojava interface layer to the
12546 forester phylogenomics library for constructing phylogenetic trees.")))
12548 (define-public java-biojava-alignment-4.0
12549 (package (inherit java-biojava-core-4.0)
12550 (name "java-biojava-alignment")
12551 (build-system ant-build-system)
12554 #:jar-name "biojava-alignment.jar"
12555 #:source-dir "biojava-alignment/src/main/java/"
12556 #:test-dir "biojava-alignment/src/test"
12558 (modify-phases %standard-phases
12559 (add-before 'build 'copy-resources
12561 (copy-recursively "biojava-alignment/src/main/resources"
12564 (add-before 'check 'copy-test-resources
12566 (copy-recursively "biojava-alignment/src/test/resources"
12567 "build/test-classes")
12570 `(("java-log4j-api" ,java-log4j-api)
12571 ("java-log4j-core" ,java-log4j-core)
12572 ("java-slf4j-api" ,java-slf4j-api)
12573 ("java-slf4j-simple" ,java-slf4j-simple)
12574 ("java-biojava-core" ,java-biojava-core-4.0)
12575 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12576 ("java-forester" ,java-forester-1.005)))
12578 `(("java-junit" ,java-junit)
12579 ("java-hamcrest-core" ,java-hamcrest-core)))
12580 (home-page "http://biojava.org")
12581 (synopsis "Biojava API for genetic sequence alignment")
12582 (description "The alignment module of BioJava provides an API that
12586 @item implementations of dynamic programming algorithms for sequence
12588 @item reading and writing of popular alignment file formats;
12589 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12592 (define-public dropseq-tools
12594 (name "dropseq-tools")
12599 (uri "http://mccarrolllab.com/download/1276/")
12600 (file-name (string-append "dropseq-tools-" version ".zip"))
12603 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12604 ;; Delete bundled libraries
12605 (modules '((guix build utils)))
12608 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12609 (delete-file-recursively "3rdParty")
12611 (build-system ant-build-system)
12613 `(#:tests? #f ; test data are not included
12614 #:test-target "test"
12615 #:build-target "all"
12616 #:source-dir "public/src/"
12619 (list (string-append "-Dpicard.executable.dir="
12620 (assoc-ref %build-inputs "java-picard")
12622 #:modules ((ice-9 match)
12625 (guix build java-utils)
12626 (guix build ant-build-system))
12628 (modify-phases %standard-phases
12629 ;; FIXME: fails with "java.io.FileNotFoundException:
12630 ;; /gnu/store/…-dropseq-tools-1.13/share/java/lib/biojava-alignment.jar"
12631 (delete 'generate-jar-indices)
12632 ;; All dependencies must be linked to "lib", because that's where
12633 ;; they will be searched for when the Class-Path property of the
12634 ;; manifest is computed.
12635 (add-after 'unpack 'record-references
12636 (lambda* (#:key inputs #:allow-other-keys)
12637 (mkdir-p "jar/lib")
12638 (let ((dirs (filter-map (match-lambda
12640 (if (and (string-prefix? "java-" name)
12641 (not (string=? name "java-testng")))
12644 (for-each (lambda (jar)
12645 (symlink jar (string-append "jar/lib/" (basename jar))))
12646 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12649 ;; There is no installation target
12651 (lambda* (#:key inputs outputs #:allow-other-keys)
12652 (let* ((out (assoc-ref outputs "out"))
12653 (bin (string-append out "/bin"))
12654 (share (string-append out "/share/java/"))
12655 (lib (string-append share "/lib/"))
12656 (scripts (list "BAMTagHistogram"
12657 "BAMTagofTagCounts"
12658 "BaseDistributionAtReadPosition"
12659 "CollapseBarcodesInPlace"
12660 "CollapseTagWithContext"
12662 "CreateIntervalsFiles"
12663 "DetectBeadSynthesisErrors"
12664 "DigitalExpression"
12665 "Drop-seq_alignment.sh"
12668 "GatherGeneGCLength"
12669 "GatherMolecularBarcodeDistributionByGene"
12670 "GatherReadQualityMetrics"
12673 "SelectCellsByNumTranscripts"
12674 "SingleCellRnaSeqMetricsCollector"
12675 "TagBamWithReadSequenceExtended"
12676 "TagReadWithGeneExon"
12677 "TagReadWithInterval"
12678 "TrimStartingSequence"
12679 "ValidateReference")))
12680 (for-each mkdir-p (list bin share lib))
12681 (install-file "dist/dropseq.jar" share)
12682 (for-each (lambda (script)
12683 (chmod script #o555)
12684 (install-file script bin))
12686 (substitute* (map (lambda (script)
12687 (string-append bin "/" script))
12689 (("^java") (which "java"))
12690 (("jar_deploy_dir=.*")
12691 (string-append "jar_deploy_dir=" share "\n"))))
12693 ;; FIXME: We do this after stripping jars because we don't want it to
12694 ;; copy all these jars and strip them. We only want to install
12695 ;; links. Arguably, this is a problem with the ant-build-system.
12696 (add-after 'strip-jar-timestamps 'install-links
12697 (lambda* (#:key outputs #:allow-other-keys)
12698 (let* ((out (assoc-ref outputs "out"))
12699 (share (string-append out "/share/java/"))
12700 (lib (string-append share "/lib/")))
12701 (for-each (lambda (jar)
12702 (symlink (readlink jar)
12703 (string-append lib (basename jar))))
12704 (find-files "jar/lib" "\\.jar$")))
12707 `(("jdk" ,icedtea-8)
12708 ("java-picard" ,java-picard-2.10.3)
12709 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12710 ("java-commons-math3" ,java-commons-math3)
12711 ("java-commons-jexl2" ,java-commons-jexl-2)
12712 ("java-commons-collections4" ,java-commons-collections4)
12713 ("java-commons-lang2" ,java-commons-lang)
12714 ("java-commons-io" ,java-commons-io)
12715 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12716 ("java-guava" ,java-guava)
12717 ("java-la4j" ,java-la4j)
12718 ("java-biojava-core" ,java-biojava-core-4.0)
12719 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12720 ("java-jdistlib" ,java-jdistlib)
12721 ("java-simple-xml" ,java-simple-xml)
12722 ("java-snakeyaml" ,java-snakeyaml)))
12725 ("java-testng" ,java-testng)))
12726 (home-page "http://mccarrolllab.com/dropseq/")
12727 (synopsis "Tools for Drop-seq analyses")
12728 (description "Drop-seq is a technology to enable biologists to
12729 analyze RNA expression genome-wide in thousands of individual cells at
12730 once. This package provides tools to perform Drop-seq analyses.")
12731 (license license:expat)))
12733 (define-public pigx-rnaseq
12735 (name "pigx-rnaseq")
12739 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12740 "releases/download/v" version
12741 "/pigx_rnaseq-" version ".tar.gz"))
12744 "05gn658zpj9xki5dbs728z9zxq1mcm25hkwr5vzwqxsfi15l5f2l"))))
12745 (build-system gnu-build-system)
12747 `(#:parallel-tests? #f ; not supported
12749 (modify-phases %standard-phases
12750 ;; "test.sh" runs STAR, which requires excessive amounts of memory.
12751 (add-after 'unpack 'disable-resource-intensive-test
12753 (substitute* "Makefile.in"
12754 (("(^ tests/test_trim_galore/test.sh).*" _ m) m)
12755 (("^ tests/test_multiqc/test.sh") "")
12756 (("^ test.sh") ""))
12760 ("snakemake" ,snakemake)
12762 ("multiqc" ,multiqc)
12764 ("trim-galore" ,trim-galore)
12766 ("samtools" ,samtools)
12767 ("bedtools" ,bedtools)
12768 ("r-minimal" ,r-minimal)
12769 ("r-rmarkdown" ,r-rmarkdown)
12770 ("r-ggplot2" ,r-ggplot2)
12771 ("r-ggrepel" ,r-ggrepel)
12772 ("r-gprofiler" ,r-gprofiler)
12773 ("r-deseq2" ,r-deseq2)
12775 ("r-knitr" ,r-knitr)
12776 ("r-pheatmap" ,r-pheatmap)
12777 ("r-corrplot" ,r-corrplot)
12778 ("r-reshape2" ,r-reshape2)
12779 ("r-plotly" ,r-plotly)
12780 ("r-scales" ,r-scales)
12781 ("r-summarizedexperiment" ,r-summarizedexperiment)
12782 ("r-crosstalk" ,r-crosstalk)
12783 ("r-tximport" ,r-tximport)
12784 ("r-rtracklayer" ,r-rtracklayer)
12785 ("r-rjson" ,r-rjson)
12787 ("ghc-pandoc" ,ghc-pandoc)
12788 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12789 ("python-wrapper" ,python-wrapper)
12790 ("python-pyyaml" ,python-pyyaml)))
12791 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12792 (synopsis "Analysis pipeline for RNA sequencing experiments")
12793 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
12794 reporting for RNA sequencing experiments. It is easy to use and produces high
12795 quality reports. The inputs are reads files from the sequencing experiment,
12796 and a configuration file which describes the experiment. In addition to
12797 quality control of the experiment, the pipeline produces a differential
12798 expression report comparing samples in an easily configurable manner.")
12799 (license license:gpl3+)))
12801 (define-public pigx-chipseq
12803 (name "pigx-chipseq")
12807 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
12808 "releases/download/v" version
12809 "/pigx_chipseq-" version ".tar.gz"))
12812 "0l3vd9xwqzap3mmyj8xwqp84kj7scbq308diqnwg2albphl75xqs"))))
12813 (build-system gnu-build-system)
12814 ;; parts of the tests rely on access to the network
12815 (arguments '(#:tests? #f))
12818 ("coreutils" ,coreutils)
12819 ("r-minimal" ,r-minimal)
12820 ("r-argparser" ,r-argparser)
12821 ("r-biocparallel" ,r-biocparallel)
12822 ("r-biostrings" ,r-biostrings)
12823 ("r-chipseq" ,r-chipseq)
12824 ("r-data-table" ,r-data-table)
12825 ("r-dplyr" ,r-dplyr)
12826 ("r-genomation" ,r-genomation)
12827 ("r-genomicalignments" ,r-genomicalignments)
12828 ("r-genomicranges" ,r-genomicranges)
12829 ("r-rsamtools" ,r-rsamtools)
12830 ("r-rtracklayer" ,r-rtracklayer)
12831 ("r-s4vectors" ,r-s4vectors)
12832 ("r-stringr" ,r-stringr)
12833 ("r-tibble" ,r-tibble)
12834 ("r-tidyr" ,r-tidyr)
12835 ("r-jsonlite" ,r-jsonlite)
12836 ("r-heatmaply" ,r-heatmaply)
12837 ("r-htmlwidgets" ,r-htmlwidgets)
12838 ("r-ggplot2" ,r-ggplot2)
12839 ("r-plotly" ,r-plotly)
12840 ("r-rmarkdown" ,r-rmarkdown)
12841 ("python-wrapper" ,python-wrapper)
12842 ("python-pyyaml" ,python-pyyaml)
12843 ("python-magic" ,python-magic)
12844 ("python-xlrd" ,python-xlrd)
12845 ("trim-galore" ,trim-galore)
12847 ("multiqc" ,multiqc)
12849 ("ghc-pandoc" ,ghc-pandoc)
12850 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12854 ("snakemake" ,snakemake)
12855 ("samtools" ,samtools)
12856 ("bedtools" ,bedtools)
12857 ("kentutils" ,kentutils)))
12859 `(("python-pytest" ,python-pytest)))
12860 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12861 (synopsis "Analysis pipeline for ChIP sequencing experiments")
12862 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
12863 calling and reporting for ChIP sequencing experiments. It is easy to use and
12864 produces high quality reports. The inputs are reads files from the sequencing
12865 experiment, and a configuration file which describes the experiment. In
12866 addition to quality control of the experiment, the pipeline enables to set up
12867 multiple peak calling analysis and allows the generation of a UCSC track hub
12868 in an easily configurable manner.")
12869 (license license:gpl3+)))
12871 (define-public pigx-bsseq
12873 (name "pigx-bsseq")
12877 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
12878 "releases/download/v" version
12879 "/pigx_bsseq-" version ".tar.gz"))
12882 "0l97wvkq4diq8lcarraj33bby1zzf0w804jwi8mlc5qddp8idwhy"))))
12883 (build-system gnu-build-system)
12886 (modify-phases %standard-phases
12887 (add-before 'check 'set-timezone
12888 ;; The readr package is picky about timezones.
12889 (lambda* (#:key inputs #:allow-other-keys)
12890 (setenv "TZ" "UTC+1")
12892 (string-append (assoc-ref inputs "tzdata")
12893 "/share/zoneinfo"))
12896 `(("tzdata" ,tzdata)))
12898 `(("coreutils" ,coreutils)
12901 ("r-minimal" ,r-minimal)
12902 ("r-annotationhub" ,r-annotationhub)
12904 ("r-genomation" ,r-genomation)
12905 ("r-methylkit" ,r-methylkit)
12906 ("r-rtracklayer" ,r-rtracklayer)
12907 ("r-rmarkdown" ,r-rmarkdown)
12908 ("r-bookdown" ,r-bookdown)
12909 ("r-ggplot2" ,r-ggplot2)
12910 ("r-ggbio" ,r-ggbio)
12911 ("ghc-pandoc" ,ghc-pandoc)
12912 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12913 ("python-wrapper" ,python-wrapper)
12914 ("python-pyyaml" ,python-pyyaml)
12915 ("snakemake" ,snakemake)
12916 ("bismark" ,bismark)
12919 ("trim-galore" ,trim-galore)
12920 ("cutadapt" ,cutadapt)
12921 ("samtools" ,samtools)))
12922 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12923 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
12924 (description "PiGx BSseq is a data processing pipeline for raw fastq read
12925 data of bisulfite experiments; it produces reports on aggregate methylation
12926 and coverage and can be used to produce information on differential
12927 methylation and segmentation.")
12928 (license license:gpl3+)))
12930 (define-public pigx-scrnaseq
12932 (name "pigx-scrnaseq")
12936 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/"
12937 "releases/download/v" version
12938 "/pigx_scrnaseq-" version ".tar.gz"))
12941 "131zarirv16w8653m0d66jgjnwqfsxqc0hix0rypssz4d83bl51j"))))
12942 (build-system gnu-build-system)
12944 `(#:configure-flags
12945 (list (string-append "PICARDJAR=" (assoc-ref %build-inputs "java-picard")
12946 "/share/java/picard.jar")
12947 (string-append "DROPSEQJAR=" (assoc-ref %build-inputs "dropseq-tools")
12948 "/share/java/dropseq.jar"))))
12950 `(("coreutils" ,coreutils)
12952 ("dropseq-tools" ,dropseq-tools)
12954 ("java-picard" ,java-picard-2.10.3) ; same as for dropseq
12955 ("java" ,icedtea-8)
12956 ("python-wrapper" ,python-wrapper)
12957 ("python-pyyaml" ,python-pyyaml)
12958 ("python-pandas" ,python-pandas)
12959 ("python-magic" ,python-magic)
12960 ("python-numpy" ,python-numpy)
12961 ("python-loompy" ,python-loompy)
12962 ("ghc-pandoc" ,ghc-pandoc)
12963 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12964 ("samtools" ,samtools)
12965 ("snakemake" ,snakemake)
12967 ("r-minimal" ,r-minimal)
12968 ("r-argparser" ,r-argparser)
12969 ("r-cowplot" ,r-cowplot)
12970 ("r-data-table" ,r-data-table)
12971 ("r-delayedarray" ,r-delayedarray)
12972 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
12973 ("r-dplyr" ,r-dplyr)
12974 ("r-dropbead" ,r-dropbead)
12976 ("r-genomicalignments" ,r-genomicalignments)
12977 ("r-genomicfiles" ,r-genomicfiles)
12978 ("r-genomicranges" ,r-genomicranges)
12979 ("r-ggplot2" ,r-ggplot2)
12980 ("r-hdf5array" ,r-hdf5array)
12981 ("r-pheatmap" ,r-pheatmap)
12982 ("r-rmarkdown" ,r-rmarkdown)
12983 ("r-rsamtools" ,r-rsamtools)
12984 ("r-rtracklayer" ,r-rtracklayer)
12985 ("r-rtsne" ,r-rtsne)
12986 ("r-scater" ,r-scater)
12987 ("r-scran" ,r-scran)
12988 ("r-singlecellexperiment" ,r-singlecellexperiment)
12989 ("r-stringr" ,r-stringr)
12990 ("r-yaml" ,r-yaml)))
12991 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12992 (synopsis "Analysis pipeline for single-cell RNA sequencing experiments")
12993 (description "PiGX scRNAseq is an analysis pipeline for preprocessing and
12994 quality control for single cell RNA sequencing experiments. The inputs are
12995 read files from the sequencing experiment, and a configuration file which
12996 describes the experiment. It produces processed files for downstream analysis
12997 and interactive quality reports. The pipeline is designed to work with UMI
12999 (license license:gpl3+)))
13001 (define-public pigx
13007 (uri (string-append "https://github.com/BIMSBbioinfo/pigx/"
13008 "releases/download/v" version
13009 "/pigx-" version ".tar.gz"))
13012 "1i5njdy1clj5ncw45d16p7mwmqvb1ilikl9n797pxklc3f4s7mq7"))))
13013 (build-system gnu-build-system)
13015 `(("python" ,python)
13016 ("pigx-bsseq" ,pigx-bsseq)
13017 ("pigx-chipseq" ,pigx-chipseq)
13018 ("pigx-rnaseq" ,pigx-rnaseq)
13019 ("pigx-scrnaseq" ,pigx-scrnaseq)))
13020 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
13021 (synopsis "Analysis pipelines for genomics")
13022 (description "PiGx is a collection of genomics pipelines. It includes the
13023 following pipelines:
13026 @item PiGx BSseq for raw fastq read data of bisulfite experiments
13027 @item PiGx RNAseq for RNAseq samples
13028 @item PiGx scRNAseq for single cell dropseq analysis
13029 @item PiGx ChIPseq for reads from ChIPseq experiments
13032 All pipelines are easily configured with a simple sample sheet and a
13033 descriptive settings file. The result is a set of comprehensive, interactive
13034 HTML reports with interesting findings about your samples.")
13035 (license license:gpl3+)))
13037 (define-public genrich
13043 (uri (git-reference
13044 (url "https://github.com/jsh58/Genrich.git")
13045 (commit (string-append "v" version))))
13048 "0x0q6z0208n3cxzqjla4rgjqpyqgwpmz27852lcvzkzaigymq4zp"))))
13049 (build-system gnu-build-system)
13051 `(#:tests? #f ; there are none
13053 (modify-phases %standard-phases
13054 (delete 'configure)
13056 (lambda* (#:key outputs #:allow-other-keys)
13057 (install-file "Genrich" (string-append (assoc-ref outputs "out") "/bin"))
13061 (home-page "https://github.com/jsh58/Genrich")
13062 (synopsis "Detecting sites of genomic enrichment")
13063 (description "Genrich is a peak-caller for genomic enrichment
13064 assays (e.g. ChIP-seq, ATAC-seq). It analyzes alignment files generated
13065 following the assay and produces a file detailing peaks of significant
13067 (license license:expat)))
13069 (define-public mantis
13070 (let ((commit "4ffd171632c2cb0056a86d709dfd2bf21bc69b84")
13074 (version (git-version "0" revision commit))
13077 (uri (git-reference
13078 (url "https://github.com/splatlab/mantis.git")
13080 (file-name (git-file-name name version))
13083 "0iqbr0dhmlc8mzpirmm2s4pkzkwdgrcx50yx6cv3wlr2qi064p55"))))
13084 (build-system cmake-build-system)
13085 (arguments '(#:tests? #f)) ; there are none
13087 `(("sdsl-lite" ,sdsl-lite)
13088 ("openssl" ,openssl)
13090 (home-page "https://github.com/splatlab/mantis")
13091 (synopsis "Large-scale sequence-search index data structure")
13092 (description "Mantis is a space-efficient data structure that can be
13093 used to index thousands of raw-read genomics experiments and facilitate
13094 large-scale sequence searches on those experiments. Mantis uses counting
13095 quotient filters instead of Bloom filters, enabling rapid index builds and
13096 queries, small indexes, and exact results, i.e., no false positives or
13097 negatives. Furthermore, Mantis is also a colored de Bruijn graph
13098 representation, so it supports fast graph traversal and other topological
13099 analyses in addition to large-scale sequence-level searches.")
13100 ;; uses __uint128_t and inline assembly
13101 (supported-systems '("x86_64-linux"))
13102 (license license:bsd-3))))
13104 (define-public r-diversitree
13106 (name "r-diversitree")
13111 (uri (cran-uri "diversitree" version))
13114 "0gh4rcrp0an3jh8915i1fsxlgyfk7njywgbd5ln5r2jhr085kpz7"))))
13115 (build-system r-build-system)
13117 `(("gfortran" ,gfortran)))
13118 (inputs `(("fftw" ,fftw) ("gsl" ,gsl)))
13121 ("r-desolve" ,r-desolve)
13123 ("r-suplex" ,r-subplex)))
13124 (home-page "https://www.zoology.ubc.ca/prog/diversitree")
13125 (synopsis "Comparative 'phylogenetic' analyses of diversification")
13126 (description "This package contains a number of comparative \"phylogenetic\"
13127 methods, mostly focusing on analysing diversification and character evolution.
13128 Contains implementations of \"BiSSE\" (Binary State Speciation and Extinction)
13129 and its unresolved tree extensions, \"MuSSE\" (Multiple State Speciation and
13130 Extinction), \"QuaSSE\", \"GeoSSE\", and \"BiSSE-ness\" Other included methods
13131 include Markov models of discrete and continuous trait evolution and constant
13132 rate speciation and extinction.")
13133 (license license:gpl2+)))
13135 (define-public sjcount
13136 ;; There is no tag for version 3.2, nor is there a release archive.
13137 (let ((commit "292d3917cadb3f6834c81e509c30e61cd7ead6e5")
13141 (version (git-version "3.2" revision commit))
13144 (uri (git-reference
13145 (url "https://github.com/pervouchine/sjcount-full.git")
13147 (file-name (string-append name "-" version "-checkout"))
13150 "0gdgj35j249f04rqgq8ymcc1xg1vi9kzbajnjqpaq2wpbh8bl234"))))
13151 (build-system gnu-build-system)
13153 `(#:tests? #f ; requires a 1.4G test file
13155 (list (string-append "SAMTOOLS_DIR="
13156 (assoc-ref %build-inputs "samtools")
13159 (modify-phases %standard-phases
13160 (replace 'configure
13161 (lambda* (#:key inputs #:allow-other-keys)
13162 (substitute* "makefile"
13163 (("-I \\$\\{SAMTOOLS_DIR\\}")
13164 (string-append "-I" (assoc-ref inputs "samtools")
13165 "/include/samtools"))
13166 (("-lz ") "-lz -lpthread "))
13169 (lambda* (#:key outputs #:allow-other-keys)
13170 (for-each (lambda (tool)
13172 (string-append (assoc-ref outputs "out")
13174 '("j_count" "b_count" "sjcount"))
13177 `(("samtools" ,samtools-0.1)
13179 (home-page "https://github.com/pervouchine/sjcount-full/")
13180 (synopsis "Annotation-agnostic splice junction counting pipeline")
13181 (description "Sjcount is a utility for fast quantification of splice
13182 junctions in RNA-seq data. It is annotation-agnostic and offset-aware. This
13183 version does count multisplits.")
13184 (license license:gpl3+))))
13186 (define-public minimap2
13193 (uri (string-append "https://github.com/lh3/minimap2/"
13194 "releases/download/v" version "/"
13195 "minimap2-" version ".tar.bz2"))
13198 "080w9066irkbhbyr4nmf19pzkdd2s4v31hpzlajgq2y0drr6zcsj"))))
13199 (build-system gnu-build-system)
13201 `(#:tests? #f ; there are none
13204 (let ((system ,(or (%current-target-system)
13205 (%current-system))))
13207 ((string-prefix? "x86_64" system)
13209 ((or (string-prefix? "armhf" system)
13210 (string-prefix? "aarch64" system))
13212 (_ "sse2only=1"))))
13214 (modify-phases %standard-phases
13215 (delete 'configure)
13217 (lambda* (#:key outputs #:allow-other-keys)
13218 (let* ((out (assoc-ref outputs "out"))
13219 (bin (string-append out "/bin"))
13220 (man (string-append out "/share/man/man1")))
13221 (install-file "minimap2" bin)
13223 (install-file "minimap2.1" man))
13227 (home-page "https://lh3.github.io/minimap2/")
13228 (synopsis "Pairwise aligner for genomic and spliced nucleotide sequences")
13229 (description "Minimap2 is a versatile sequence alignment program that
13230 aligns DNA or mRNA sequences against a large reference database. Typical use
13234 @item mapping PacBio or Oxford Nanopore genomic reads to the human genome;
13235 @item finding overlaps between long reads with error rate up to ~15%;
13236 @item splice-aware alignment of PacBio Iso-Seq or Nanopore cDNA or Direct RNA
13237 reads against a reference genome;
13238 @item aligning Illumina single- or paired-end reads;
13239 @item assembly-to-assembly alignment;
13240 @item full-genome alignment between two closely related species with
13241 divergence below ~15%.
13243 (license license:expat)))
13245 (define-public r-circus
13252 (uri (git-reference
13253 (url "https://github.com/BIMSBbioinfo/ciRcus.git")
13254 (commit (string-append "v" version))))
13255 (file-name (git-file-name name version))
13258 "0jhjn3ilb057hbf6yzrihj13ifxxs32y7nkby8l3lkm28dg4p97h"))))
13259 (build-system r-build-system)
13261 `(("r-annotationdbi" ,r-annotationdbi)
13262 ("r-annotationhub" ,r-annotationhub)
13263 ("r-biomart" ,r-biomart)
13264 ("r-data-table" ,r-data-table)
13266 ("r-genomicfeatures" ,r-genomicfeatures)
13267 ("r-genomicranges" ,r-genomicranges)
13268 ("r-ggplot2" ,r-ggplot2)
13270 ("r-iranges" ,r-iranges)
13271 ("r-rcolorbrewer" ,r-rcolorbrewer)
13272 ("r-rmysql" ,r-rmysql)
13273 ("r-s4vectors" ,r-s4vectors)
13274 ("r-stringr" ,r-stringr)
13275 ("r-summarizedexperiment" ,r-summarizedexperiment)))
13277 `(("r-knitr" ,r-knitr)))
13278 (home-page "https://github.com/BIMSBbioinfo/ciRcus")
13279 (synopsis "Annotation, analysis and visualization of circRNA data")
13280 (description "Circus is an R package for annotation, analysis and
13281 visualization of circRNA data. Users can annotate their circRNA candidates
13282 with host genes, gene featrues they are spliced from, and discriminate between
13283 known and yet unknown splice junctions. Circular-to-linear ratios of circRNAs
13284 can be calculated, and a number of descriptive plots easily generated.")
13285 (license license:artistic2.0)))
13287 (define-public r-loomr
13288 (let ((commit "df0144bd2bbceca6fadef9edc1bbc5ca672d4739")
13292 (version (git-version "0.2.0" revision commit))
13296 (uri (git-reference
13297 (url "https://github.com/mojaveazure/loomR.git")
13299 (file-name (git-file-name name version))
13302 "1b1g4dlmfdyhn56bz1mkh9ymirri43wiz7rjhs7py3y7bdw1s3yr"))))
13303 (build-system r-build-system)
13306 ("r-hdf5r" ,r-hdf5r)
13307 ("r-iterators" ,r-iterators)
13308 ("r-itertools" ,r-itertools)
13309 ("r-matrix" ,r-matrix)))
13310 (home-page "https://github.com/mojaveazure/loomR")
13311 (synopsis "R interface for loom files")
13312 (description "This package provides an R interface to access, create,
13313 and modify loom files. loomR aims to be completely compatible with loompy.")
13314 (license license:gpl3))))
13316 (define-public gffread
13317 ;; We cannot use the tagged release because it is not in sync with gclib.
13318 ;; See https://github.com/gpertea/gffread/issues/26
13319 (let ((commit "ba7535fcb3cea55a6e5a491d916e93b454e87fd0")
13323 (version (git-version "0.9.12" revision commit))
13327 (uri (git-reference
13328 (url "https://github.com/gpertea/gffread.git")
13330 (file-name (git-file-name name version))
13333 "1dl2nbcg96lxpd0drg48ssa8343nf7pw9s9mkrc4mjjmfwsin3ki"))))
13334 (build-system gnu-build-system)
13336 `(#:tests? #f ; no check target
13338 (list "GCLDIR=gclib")
13340 (modify-phases %standard-phases
13341 (delete 'configure)
13342 (add-after 'unpack 'copy-gclib-source
13343 (lambda* (#:key inputs #:allow-other-keys)
13345 (copy-recursively (assoc-ref inputs "gclib-source") "gclib")
13347 ;; There is no install target
13349 (lambda* (#:key outputs #:allow-other-keys)
13350 (let* ((out (assoc-ref outputs "out"))
13351 (bin (string-append out "/bin")))
13352 (install-file "gffread" bin))
13356 ,(let ((version "0.10.3")
13357 (commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13361 (uri (git-reference
13362 (url "https://github.com/gpertea/gclib.git")
13364 (file-name (git-file-name "gclib" version))
13367 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13368 (home-page "https://github.com/gpertea/gffread/")
13369 (synopsis "Parse and convert GFF/GTF files")
13371 "This package provides a GFF/GTF file parsing utility providing format
13372 conversions, region filtering, FASTA sequence extraction and more.")
13373 ;; gffread is under Expat, but gclib is under Artistic 2.0
13374 (license (list license:expat
13375 license:artistic2.0)))))
13377 (define-public find-circ
13378 ;; The last release was in 2015. The license was clarified in 2017, so we
13379 ;; take the latest commit.
13380 (let ((commit "8655dca54970fcf7e92e22fbf57e1188724dda7d")
13384 (version (git-version "1.2" revision commit))
13388 (uri (git-reference
13389 (url "https://github.com/marvin-jens/find_circ.git")
13391 (file-name (git-file-name name version))
13394 "0p77pbqbclqr4srms34y1b9b4njybfpjiknc11ki84f3p8skb3cg"))))
13395 (build-system gnu-build-system)
13397 `(#:tests? #f ; there are none
13399 ;; There is no actual build system.
13400 (modify-phases %standard-phases
13401 (delete 'configure)
13404 (lambda* (#:key outputs #:allow-other-keys)
13405 (let* ((out (assoc-ref outputs "out"))
13406 (bin (string-append out "/bin"))
13407 (path (getenv "PYTHONPATH")))
13408 (for-each (lambda (script)
13409 (install-file script bin)
13410 (wrap-program (string-append bin "/" script)
13411 `("PYTHONPATH" ":" prefix (,path))))
13416 "unmapped2anchors.py")))
13419 `(("python2" ,python-2)
13420 ("python2-pysam" ,python2-pysam)
13421 ("python2-numpy" ,python2-numpy)))
13422 (home-page "https://github.com/marvin-jens/find_circ")
13423 (synopsis "circRNA detection from RNA-seq reads")
13424 (description "This package provides tools to detect head-to-tail
13425 spliced (back-spliced) sequencing reads, indicative of circular RNA (circRNA)
13427 (license license:gpl3))))
13429 (define-public python-scanpy
13431 (name "python-scanpy")
13436 (uri (pypi-uri "scanpy" version))
13439 "1ak7bxms5a0yvf65prppq2g38clkv7c7jnjbnfpkh3xxv7q512jz"))))
13440 (build-system python-build-system)
13442 `(("python-anndata" ,python-anndata)
13443 ("python-igraph" ,python-igraph)
13444 ("python-numba" ,python-numba)
13445 ("python-joblib" ,python-joblib)
13446 ("python-natsort" ,python-natsort)
13447 ("python-networkx" ,python-networkx)
13448 ("python-statsmodels" ,python-statsmodels)
13449 ("python-scikit-learn" ,python-scikit-learn)
13450 ("python-matplotlib" ,python-matplotlib)
13451 ("python-pandas" ,python-pandas)
13452 ("python-scipy" ,python-scipy)
13453 ("python-seaborn" ,python-seaborn)
13454 ("python-h5py" ,python-h5py)
13455 ("python-tables" ,python-tables)))
13456 (home-page "http://github.com/theislab/scanpy")
13457 (synopsis "Single-Cell Analysis in Python.")
13458 (description "Scanpy is a scalable toolkit for analyzing single-cell gene
13459 expression data. It includes preprocessing, visualization, clustering,
13460 pseudotime and trajectory inference and differential expression testing. The
13461 Python-based implementation efficiently deals with datasets of more than one
13463 (license license:bsd-3)))
13465 (define-public gffcompare
13466 (let ((commit "be56ef4349ea3966c12c6397f85e49e047361c41")
13469 (name "gffcompare")
13470 (version (git-version "0.10.15" revision commit))
13474 (uri (git-reference
13475 (url "https://github.com/gpertea/gffcompare/")
13477 (file-name (git-file-name name version))
13479 (base32 "0cp5qpxdhw4mxpya5dld8wi3jk00zyklm6rcri426wydinrnfmkg"))))
13480 (build-system gnu-build-system)
13482 `(#:tests? #f ; no check target
13484 (modify-phases %standard-phases
13485 (delete 'configure)
13486 (add-before 'build 'copy-gclib-source
13487 (lambda* (#:key inputs #:allow-other-keys)
13490 (assoc-ref inputs "gclib-source") "../gclib")
13493 (lambda* (#:key outputs #:allow-other-keys)
13494 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
13495 (install-file "gffcompare" bin)
13498 `(("gclib-source" ; see 'README.md' of gffcompare
13499 ,(let ((commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13502 (version (git-version "0.10.3" revision commit)))
13505 (uri (git-reference
13506 (url "https://github.com/gpertea/gclib/")
13508 (file-name (git-file-name name version))
13510 (base32 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13511 (home-page "https://github.com/gpertea/gffcompare/")
13512 (synopsis "Tool for comparing or classifing transcripts of RNA-Seq")
13514 "@code{gffcompare} is a tool that can:
13516 @item compare and evaluate the accuracy of RNA-Seq transcript assemblers
13517 (Cufflinks, Stringtie);
13518 @item collapse (merge) duplicate transcripts from multiple GTF/GFF3 files (e.g.
13519 resulted from assembly of different samples);
13520 @item classify transcripts from one or multiple GTF/GFF3 files as they relate to
13521 reference transcripts provided in a annotation file (also in GTF/GFF3 format).
13525 license:expat ;license for gffcompare
13526 license:artistic2.0))))) ;license for gclib
13528 (define-public python-intervaltree
13530 (name "python-intervaltree")
13535 (uri (pypi-uri "intervaltree" version))
13538 "02w191m9zxkcjqr1kv2slxvhymwhj3jnsyy3a28b837pi15q19dc"))))
13539 (build-system python-build-system)
13540 ;; FIXME: error when collecting tests
13541 (arguments '(#:tests? #f))
13543 `(("python-sortedcontainers" ,python-sortedcontainers)))
13545 `(("python-pytest" ,python-pytest)))
13546 (home-page "https://github.com/chaimleib/intervaltree")
13547 (synopsis "Editable interval tree data structure")
13549 "This package provides a mutable, self-balancing interval tree
13550 implementation for Python. Queries may be by point, by range overlap, or by
13551 range envelopment. This library was designed to allow tagging text and time
13552 intervals, where the intervals include the lower bound but not the upper
13554 (license license:asl2.0)))
13556 (define-public python-pypairix
13558 (name "python-pypairix")
13563 (uri (pypi-uri "pypairix" version))
13566 "0zs92b74s5v4xy2h16s15f3z6l4nnbw8x8zyif7xx5xpafjn0xss"))))
13567 (build-system python-build-system)
13568 ;; FIXME: the tests fail because test.support cannot be loaded:
13569 ;; ImportError: cannot import name 'support'
13570 (arguments '(#:tests? #f))
13573 (home-page "https://github.com/4dn-dcic/pairix")
13574 (synopsis "Support for querying pairix-indexed bgzipped text files")
13576 "Pypairix is a Python module for fast querying on a pairix-indexed
13577 bgzipped text file that contains a pair of genomic coordinates per line.")
13578 (license license:expat)))
13580 (define-public python-pyfaidx
13582 (name "python-pyfaidx")
13583 (version "0.5.4.2")
13587 (uri (pypi-uri "pyfaidx" version))
13590 "0y5zyjksj1rdglj601xd2bbni5abhdh622y3ck76chyzxz9z4rx8"))))
13591 (build-system python-build-system)
13593 `(("python-setuptools" ,python-setuptools)
13594 ("python-six" ,python-six)))
13595 (home-page "http://mattshirley.com")
13596 (synopsis "Random access to fasta subsequences")
13598 "This package provides procedures for efficient pythonic random access to
13599 fasta subsequences.")
13600 (license license:bsd-3)))
13602 (define-public python-cooler
13604 (name "python-cooler")
13609 (uri (pypi-uri "cooler" version))
13612 "08k5nxnxa6qsbk15z5z0q01n28042k87wi4905hh95rzqib15mhx"))))
13613 (build-system python-build-system)
13615 `(("python-biopython" ,python-biopython)
13616 ("python-click" ,python-click)
13617 ("python-cytoolz" ,python-cytoolz)
13618 ("python-dask" ,python-dask)
13619 ("python-h5py" ,python-h5py)
13620 ("python-multiprocess" ,python-multiprocess)
13621 ("python-pandas" ,python-pandas)
13622 ("python-pyfaidx" ,python-pyfaidx)
13623 ("python-pypairix" ,python-pypairix)
13624 ("python-pysam" ,python-pysam)
13625 ("python-scipy" ,python-scipy)))
13627 `(("python-mock" ,python-mock)
13628 ("python-nose" ,python-nose)
13629 ("python-numpydoc" ,python-numpydoc)
13630 ("python-sphinx" ,python-sphinx)))
13631 (home-page "https://github.com/mirnylab/cooler")
13632 (synopsis "Sparse binary format for genomic interaction matrices")
13634 "Cooler is a support library for a sparse, compressed, binary persistent
13635 storage format, called @code{cool}, used to store genomic interaction data,
13636 such as Hi-C contact matrices.")
13637 (license license:bsd-3)))
13639 (define-public python-hicexplorer
13641 (name "python-hicexplorer")
13645 ;; The latest version is not available on Pypi.
13647 (uri (git-reference
13648 (url "https://github.com/deeptools/HiCExplorer.git")
13650 (file-name (git-file-name name version))
13653 "0q5gpbzmrkvygqgw524q36b4nrivcmyi5v194vsx0qw7b3gcmq08"))))
13654 (build-system python-build-system)
13657 (modify-phases %standard-phases
13658 (add-after 'unpack 'loosen-up-requirements
13660 (substitute* "setup.py"
13664 `(("python-biopython" ,python-biopython)
13665 ("python-configparser" ,python-configparser)
13666 ("python-cooler" ,python-cooler)
13667 ("python-future" ,python-future)
13668 ("python-intervaltree" ,python-intervaltree)
13669 ("python-jinja2" ,python-jinja2)
13670 ("python-matplotlib" ,python-matplotlib)
13671 ("python-numpy" ,python-numpy)
13672 ("python-pandas" ,python-pandas)
13673 ("python-pybigwig" ,python-pybigwig)
13674 ("python-pysam" ,python-pysam)
13675 ("python-scipy" ,python-scipy)
13676 ("python-six" ,python-six)
13677 ("python-tables" ,python-tables)
13678 ("python-unidecode" ,python-unidecode)))
13679 (home-page "http://hicexplorer.readthedocs.io")
13680 (synopsis "Process, analyze and visualize Hi-C data")
13682 "HiCExplorer is a powerful and easy to use set of tools to process,
13683 normalize and visualize Hi-C data. HiCExplorer facilitates the creation of
13684 contact matrices, correction of contacts, TAD detection, A/B compartments,
13685 merging, reordering or chromosomes, conversion from different formats
13686 including cooler and detection of long-range contacts. Moreover, it allows
13687 the visualization of multiple contact matrices along with other types of data
13688 like genes, compartments, ChIP-seq coverage tracks (and in general any type of
13689 genomic scores), long range contacts and the visualization of viewpoints.")
13690 (license license:gpl3)))
13692 (define-public python-pygenometracks
13694 (name "python-pygenometracks")
13699 (uri (pypi-uri "pyGenomeTracks" version))
13702 "1fws6bqsyy9kj3qiabhkqx4wd4i775gsxnhszqd3zg7w67sc1ic5"))))
13703 (build-system python-build-system)
13705 `(("python-configparser" ,python-configparser)
13706 ("python-future" ,python-future)
13707 ("python-hicexplorer" ,python-hicexplorer)
13708 ("python-intervaltree" ,python-intervaltree)
13709 ("python-matplotlib" ,python-matplotlib)
13710 ("python-numpy" ,python-numpy)
13711 ("python-pybigwig" ,python-pybigwig)))
13713 `(("python-pytest" ,python-pytest)))
13714 (home-page "https://pygenometracks.readthedocs.io")
13715 (synopsis "Program and library to plot beautiful genome browser tracks")
13717 "This package aims to produce high-quality genome browser tracks that
13718 are highly customizable. Currently, it is possible to plot: bigwig, bed (many
13719 options), bedgraph, links (represented as arcs), and Hi-C matrices.
13720 pyGenomeTracks can make plots with or without Hi-C data.")
13721 (license license:gpl3+)))
13723 (define-public python-hic2cool
13725 (name "python-hic2cool")
13730 (uri (pypi-uri "hic2cool" version))
13733 "0xy6mhfns2lzib1kcr6419jjp6pmh0qx8z8na55lmiwn0ds8q9cl"))))
13734 (build-system python-build-system)
13735 (arguments '(#:tests? #f)) ; no tests included
13737 `(("python-cooler" ,python-cooler)))
13738 (home-page "https://github.com/4dn-dcic/hic2cool")
13739 (synopsis "Converter for .hic and .cool files")
13741 "This package provides a converter between @code{.hic} files (from
13742 juicer) and single-resolution or multi-resolution @code{.cool} files (for
13743 cooler). Both @code{hic} and @code{cool} files describe Hi-C contact
13745 (license license:expat)))
13747 (define-public r-pore
13755 (string-append "mirror://sourceforge/rpore/" version
13756 "/poRe_" version ".tar.gz"))
13758 (base32 "0pih9nljbv8g4x8rkk29i7aqq681b782r5s5ynp4nw9yzqnmmksv"))))
13759 (properties `((upstream-name . "poRe")))
13760 (build-system r-build-system)
13762 `(("r-bit64" ,r-bit64)
13763 ("r-data-table" ,r-data-table)
13764 ("r-rhdf5" ,r-rhdf5)
13765 ("r-shiny" ,r-shiny)
13766 ("r-svdialogs" ,r-svdialogs)))
13767 (home-page "https://sourceforge.net/projects/rpore/")
13768 (synopsis "Visualize Nanopore sequencing data")
13770 "This package provides graphical user interfaces to organize and visualize Nanopore
13772 ;; This is free software but the license variant is unclear:
13773 ;; <https://github.com/mw55309/poRe_docs/issues/10>.
13774 (license license:bsd-3)))
13776 (define-public r-xbioc
13777 (let ((revision "1")
13778 (commit "f798c187e376fd1ba27abd559f47bbae7e3e466b"))
13781 (version (git-version "0.1.15" revision commit))
13784 (uri (git-reference
13785 (url "https://github.com/renozao/xbioc.git")
13787 (file-name (git-file-name name version))
13790 "03hffh2f6z71y6l6dqpa5cql3hdaw7zigdi8sm2dzgx379k9rgrr"))))
13791 (build-system r-build-system)
13793 `(("r-annotationdbi" ,r-annotationdbi)
13794 ("r-assertthat" ,r-assertthat)
13795 ("r-biobase" ,r-biobase)
13796 ("r-biocinstaller" ,r-biocinstaller)
13797 ("r-digest" ,r-digest)
13798 ("r-pkgmaker" ,r-pkgmaker)
13800 ("r-reshape2" ,r-reshape2)
13801 ("r-stringr" ,r-stringr)))
13802 (home-page "https://github.com/renozao/xbioc/")
13803 (synopsis "Extra base functions for Bioconductor")
13804 (description "This package provides extra utility functions to perform
13805 common tasks in the analysis of omics data, leveraging and enhancing features
13806 provided by Bioconductor packages.")
13807 (license license:gpl3+))))
13809 (define-public r-cssam
13810 (let ((revision "1")
13811 (commit "9ec58c982fa551af0d80b1a266890d92954833f2"))
13814 (version (git-version "1.4" revision commit))
13817 (uri (git-reference
13818 (url "https://github.com/shenorrLab/csSAM.git")
13820 (file-name (git-file-name name version))
13823 "128syf9v39gk0z3ip000qpsjbg6l1siyq6c8b0hz41dzg5achyb3"))))
13824 (build-system r-build-system)
13826 `(("r-formula" ,r-formula)
13827 ("r-ggplot2" ,r-ggplot2)
13828 ("r-pkgmaker" ,r-pkgmaker)
13830 ("r-rngtools" ,r-rngtools)
13831 ("r-scales" ,r-scales)))
13832 (home-page "https://github.com/shenorrLab/csSAM/")
13833 (synopsis "Cell type-specific statistical analysis of microarray")
13834 (description "This package implements the method csSAM that computes
13835 cell-specific differential expression from measured cell proportions using
13838 (license license:lgpl2.1+))))
13840 (define-public r-bseqsc
13841 (let ((revision "1")
13842 (commit "fef3f3e38dcf3df37103348b5780937982b43b98"))
13845 (version (git-version "1.0" revision commit))
13848 (uri (git-reference
13849 (url "https://github.com/shenorrLab/bseqsc.git")
13851 (file-name (git-file-name name version))
13854 "1prw13wa20f7wlc3gkkls66n1kxz8d28qrb8icfqdwdnnv8w5qg8"))))
13855 (build-system r-build-system)
13857 `(("r-abind" ,r-abind)
13858 ("r-annotationdbi" ,r-annotationdbi)
13859 ("r-biobase" ,r-biobase)
13860 ("r-cssam" ,r-cssam)
13861 ("r-dplyr" ,r-dplyr)
13862 ("r-e1071" ,r-e1071)
13863 ("r-edger" ,r-edger)
13864 ("r-ggplot2" ,r-ggplot2)
13866 ("r-openxlsx" ,r-openxlsx)
13867 ("r-pkgmaker" ,r-pkgmaker)
13869 ("r-preprocesscore" ,r-preprocesscore)
13870 ("r-rngtools" ,r-rngtools)
13871 ("r-scales" ,r-scales)
13872 ("r-stringr" ,r-stringr)
13873 ("r-xbioc" ,r-xbioc)))
13874 (home-page "https://github.com/shenorrLab/bseqsc")
13875 (synopsis "Deconvolution of bulk sequencing experiments using single cell data")
13876 (description "BSeq-sc is a bioinformatics analysis pipeline that
13877 leverages single-cell sequencing data to estimate cell type proportion and
13878 cell type-specific gene expression differences from RNA-seq data from bulk
13879 tissue samples. This is a companion package to the publication \"A
13880 single-cell transcriptomic map of the human and mouse pancreas reveals inter-
13881 and intra-cell population structure.\" Baron et al. Cell Systems (2016)
13882 @url{https://www.ncbi.nlm.nih.gov/pubmed/27667365}.")
13883 (license license:gpl2+))))
13885 (define-public porechop
13886 ;; The recommended way to install is to clone the git repository
13887 ;; https://github.com/rrwick/Porechop#installation
13888 (let ((commit "289d5dca4a5fc327f97b3f8cecb68ecaf1014861")
13892 (version (git-version "0.2.3" revision commit))
13896 (uri (git-reference
13897 (url "https://github.com/rrwick/Porechop.git")
13899 (file-name (git-file-name name version))
13901 (base32 "05ps43gig0d3ia9x5lj84lb00hbsl6ba9n7y7jz927npxbr2ym23"))))
13902 (build-system python-build-system)
13903 (home-page "https://github.com/rrwick/porechop")
13904 (synopsis "Finding, trimming or splitting adapters, in Oxford Nanopore reads")
13906 "The porechop package is a tool for finding and removing adapters from Oxford
13907 Nanopore reads. Adapters on the ends of reads are trimmed off, and when a read
13908 has an adapter in its middle, it is treated as chimeric and chopped into
13909 separate reads. Porechop performs thorough alignments to effectively find
13910 adapters, even at low sequence identity. Porechop also supports demultiplexing
13911 of Nanopore reads that were barcoded with the Native Barcoding Kit, PCR
13912 Barcoding Kit or Rapid Barcoding Kit.")
13913 (license license:gpl3+))))
13915 (define-public poretools
13916 ;; The latest release was in 2016 and the latest commit is from 2017
13917 ;; the recommended way to install is to clone the git repository
13918 ;; https://poretools.readthedocs.io/en/latest/content/installation.html
13919 (let ((commit "e426b1f09e86ac259a00c261c79df91510777407")
13923 (version (git-version "0.6.0" revision commit))
13927 (uri (git-reference
13928 (url "https://github.com/arq5x/poretools.git")
13930 (file-name (git-file-name name version))
13932 (base32 "0bglj833wxpp3cq430p1d3xp085ls221js2y90w7ir2x5ay8l7am"))))
13933 (build-system python-build-system)
13934 ;; requires python >=2.7, <3.0, and the same for python dependencies
13935 (arguments `(#:python ,python-2))
13939 `(("python-dateutil" ,python2-dateutil)
13940 ("python-h5py" ,python2-h5py)
13941 ("python-matplotlib" ,python2-matplotlib)
13942 ("python-pandas" ,python2-pandas)
13943 ("python-seaborn" ,python2-seaborn)))
13944 (home-page "https://poretools.readthedocs.io")
13945 (synopsis "Toolkit for working with nanopore sequencing data")
13947 "The MinION from Oxford Nanopore Technologies is a nanopore sequencer.
13948 This @code{poretools} package is a flexible toolkit for exploring datasets
13949 generated by nanopore sequencing devices for the purposes of quality control and
13950 downstream analysis. Poretools operates directly on the native FAST5, a variant
13951 of the Hierarchical Data Format (HDF5) standard.")
13952 (license license:expat))))
13954 (define-public r-absfiltergsea
13956 (name "r-absfiltergsea")
13961 (uri (cran-uri "AbsFilterGSEA" version))
13963 (base32 "15srxkxsvn38kd5frdrwfdf0ad8gskrd0h01wmdf9hglq8fjrp7w"))))
13964 (properties `((upstream-name . "AbsFilterGSEA")))
13965 (build-system r-build-system)
13967 `(("r-biobase" ,r-biobase)
13968 ("r-deseq" ,r-deseq)
13969 ("r-limma" ,r-limma)
13971 ("r-rcpparmadillo" ,r-rcpparmadillo)))
13972 (home-page "https://cran.r-project.org/web/packages/AbsFilterGSEA/")
13973 (synopsis "Improved false positive control of gene-permuting with absolute filtering")
13975 "This package provides a function that performs gene-permuting of a gene-set
13976 enrichment analysis (GSEA) calculation with or without the absolute filtering.
13977 Without filtering, users can perform (original) two-tailed or one-tailed
13979 (license license:gpl2)))
13981 (define-public jamm
13984 (version "1.0.7.5")
13988 (uri (git-reference
13989 (url "https://github.com/mahmoudibrahim/JAMM.git")
13990 (commit (string-append "JAMMv" version))))
13991 (file-name (git-file-name name version))
13994 "0ls889jcma1ch9h21jjhnkadgszgqj41842hhcjh6cg88f85qf3i"))))
13995 (build-system gnu-build-system)
13997 `(#:tests? #f ; there are none
13999 (modify-phases %standard-phases
14000 (delete 'configure)
14003 (lambda* (#:key inputs outputs #:allow-other-keys)
14004 (let* ((out (assoc-ref outputs "out"))
14005 (libexec (string-append out "/libexec/jamm"))
14006 (bin (string-append out "/bin")))
14007 (substitute* '("JAMM.sh"
14008 "SignalGenerator.sh")
14010 (string-append "sPath=\"" libexec "\"\n")))
14011 (for-each (lambda (file)
14012 (install-file file libexec))
14013 (list "bincalculator.r"
14025 (chmod script #o555)
14026 (install-file script bin)
14027 (wrap-program (string-append bin "/" script)
14028 `("PATH" ":" prefix
14029 (,(string-append (assoc-ref inputs "coreutils") "/bin")
14030 ,(string-append (assoc-ref inputs "gawk") "/bin")
14031 ,(string-append (assoc-ref inputs "perl") "/bin")
14032 ,(string-append (assoc-ref inputs "r-minimal") "/bin")))
14033 `("PERL5LIB" ":" prefix (,(getenv "PERL5LIB")))
14034 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
14035 (list "JAMM.sh" "SignalGenerator.sh")))
14039 ("coreutils" ,coreutils)
14042 ("r-minimal" ,r-minimal)
14043 ;;("r-parallel" ,r-parallel)
14044 ("r-signal" ,r-signal)
14045 ("r-mclust" ,r-mclust)))
14046 (home-page "https://github.com/mahmoudibrahim/JAMM")
14047 (synopsis "Peak finder for NGS datasets")
14049 "JAMM is a peak finder for next generation sequencing datasets (ChIP-Seq,
14050 ATAC-Seq, DNase-Seq, etc.) that can integrate replicates and assign peak
14051 boundaries accurately. JAMM is applicable to both broad and narrow
14053 (license license:gpl3+)))
14055 (define-public ngless
14062 (uri (git-reference
14063 (url "https://gitlab.com/ngless/ngless.git")
14064 (commit (string-append "v" version))))
14065 (file-name (git-file-name name version))
14068 "0mc2gi7h4lx74zylvyp76mvc0w6706j858ii9vlgzqsw6acpr117"))))
14069 (build-system haskell-build-system)
14071 `(#:haddock? #f ; The haddock phase fails with: NGLess/CmdArgs.hs:20:1:
14072 ; error: parse error on input import
14073 ; import Options.Applicative
14075 (modify-phases %standard-phases
14076 (add-after 'unpack 'create-cabal-file
14077 (lambda _ (invoke "hpack") #t))
14078 ;; These tools are expected to be installed alongside ngless.
14079 (add-after 'install 'link-tools
14080 (lambda* (#:key inputs outputs #:allow-other-keys)
14081 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
14082 (symlink (string-append (assoc-ref inputs "prodigal")
14084 (string-append bin "ngless-" ,version "-prodigal"))
14085 (symlink (string-append (assoc-ref inputs "minimap2")
14087 (string-append bin "ngless-" ,version "-minimap2"))
14088 (symlink (string-append (assoc-ref inputs "samtools")
14090 (string-append bin "ngless-" ,version "-samtools"))
14091 (symlink (string-append (assoc-ref inputs "bwa")
14093 (string-append bin "ngless-" ,version "-bwa"))
14096 `(("prodigal" ,prodigal)
14098 ("samtools" ,samtools)
14099 ("minimap2" ,minimap2)
14100 ("ghc-aeson" ,ghc-aeson)
14101 ("ghc-ansi-terminal" ,ghc-ansi-terminal)
14102 ("ghc-async" ,ghc-async)
14103 ("ghc-atomic-write" ,ghc-atomic-write)
14104 ("ghc-bytestring-lexing" ,ghc-bytestring-lexing)
14105 ("ghc-chart" ,ghc-chart)
14106 ("ghc-chart-cairo" ,ghc-chart-cairo)
14107 ("ghc-conduit" ,ghc-conduit)
14108 ("ghc-conduit-algorithms" ,ghc-conduit-algorithms)
14109 ("ghc-conduit-combinators" ,ghc-conduit-combinators)
14110 ("ghc-conduit-extra" ,ghc-conduit-extra)
14111 ("ghc-configurator" ,ghc-configurator)
14112 ("ghc-convertible" ,ghc-convertible)
14113 ("ghc-data-default" ,ghc-data-default)
14114 ("ghc-double-conversion" ,ghc-double-conversion)
14115 ("ghc-edit-distance" ,ghc-edit-distance)
14116 ("ghc-either" ,ghc-either)
14117 ("ghc-errors" ,ghc-errors)
14118 ("ghc-extra" ,ghc-extra)
14119 ("ghc-filemanip" ,ghc-filemanip)
14120 ("ghc-file-embed" ,ghc-file-embed)
14121 ("ghc-gitrev" ,ghc-gitrev)
14122 ("ghc-hashtables" ,ghc-hashtables)
14123 ("ghc-http-conduit" ,ghc-http-conduit)
14124 ("ghc-inline-c" ,ghc-inline-c)
14125 ("ghc-inline-c-cpp" ,ghc-inline-c-cpp)
14126 ("ghc-intervalmap" ,ghc-intervalmap)
14127 ("ghc-missingh" ,ghc-missingh)
14128 ("ghc-optparse-applicative" ,ghc-optparse-applicative)
14129 ("ghc-parsec" ,ghc-parsec)
14130 ("ghc-regex" ,ghc-regex)
14131 ("ghc-safe" ,ghc-safe)
14132 ("ghc-safeio" ,ghc-safeio)
14133 ("ghc-strict" ,ghc-strict)
14134 ("ghc-tar" ,ghc-tar)
14135 ("ghc-text" ,ghc-text)
14136 ("ghc-unliftio" ,ghc-unliftio)
14137 ("ghc-unliftio-core" ,ghc-unliftio-core)
14138 ("ghc-vector" ,ghc-vector)
14139 ("ghc-yaml" ,ghc-yaml)
14140 ("ghc-zlib" ,ghc-zlib)))
14143 ("r-hdf5r" ,r-hdf5r)
14144 ("r-iterators" ,r-iterators)
14145 ("r-itertools" ,r-itertools)
14146 ("r-matrix" ,r-matrix)))
14148 `(("ghc-hpack" ,ghc-hpack)
14149 ("ghc-quickcheck" ,ghc-quickcheck)
14150 ("ghc-test-framework" ,ghc-test-framework)
14151 ("ghc-test-framework-hunit",ghc-test-framework-hunit)
14152 ("ghc-test-framework-quickcheck2" ,ghc-test-framework-quickcheck2)
14153 ("ghc-test-framework-th" ,ghc-test-framework-th)))
14154 (home-page "https://gitlab.com/ngless/ngless")
14155 (synopsis "DSL for processing next-generation sequencing data")
14156 (description "Ngless is a domain-specific language for
14157 @dfn{next-generation sequencing} (NGS) data processing.")
14158 (license license:expat)))
14160 (define-public filtlong
14161 ;; The recommended way to install is to clone the git repository
14162 ;; https://github.com/rrwick/Filtlong#installation
14163 ;; and the lastest release is more than nine months old
14164 (let ((commit "d1bb46dfe8bc7efe6257b5ce222c04bfe8aedaab")
14168 (version (git-version "0.2.0" revision commit))
14172 (uri (git-reference
14173 (url "https://github.com/rrwick/Filtlong.git")
14175 (file-name (git-file-name name version))
14177 (base32 "1xr92r820x8qlkcr3b57iw223yq8vjgyi42jr79w2xgw47qzr575"))))
14178 (build-system gnu-build-system)
14180 `(#:tests? #f ; no check target
14182 (modify-phases %standard-phases
14183 (delete 'configure)
14185 (lambda* (#:key outputs #:allow-other-keys)
14186 (let* ((out (assoc-ref outputs "out"))
14187 (bin (string-append out "/bin"))
14188 (scripts (string-append out "/share/filtlong/scripts")))
14189 (install-file "bin/filtlong" bin)
14190 (install-file "scripts/histogram.py" scripts)
14191 (install-file "scripts/read_info_histograms.sh" scripts))
14193 (add-after 'install 'wrap-program
14194 (lambda* (#:key inputs outputs #:allow-other-keys)
14195 (let* ((out (assoc-ref outputs "out"))
14196 (path (getenv "PYTHONPATH")))
14197 (wrap-program (string-append out
14198 "/share/filtlong/scripts/histogram.py")
14199 `("PYTHONPATH" ":" prefix (,path))))
14201 (add-before 'check 'patch-tests
14203 (substitute* "scripts/read_info_histograms.sh"
14204 (("awk") (which "gawk")))
14207 `(("gawk" ,gawk) ;for read_info_histograms.sh
14208 ("python" ,python-2) ;required for histogram.py
14210 (home-page "https://github.com/rrwick/Filtlong/")
14211 (synopsis "Tool for quality filtering of Nanopore and PacBio data")
14213 "The Filtlong package is a tool for filtering long reads by quality.
14214 It can take a set of long reads and produce a smaller, better subset. It uses
14215 both read length (longer is better) and read identity (higher is better) when
14216 choosing which reads pass the filter.")
14217 (license (list license:gpl3 ;filtlong
14218 license:asl2.0))))) ;histogram.py
14220 (define-public nanopolish
14221 ;; The recommended way to install is to clone the git repository
14222 ;; <https://github.com/jts/nanopolish#installing-a-particular-release>.
14223 ;; Also, the differences between release and current version seem to be
14225 (let ((commit "50e8b5cc62f9b46f5445f5c5e8c5ab7263ea6d9d")
14228 (name "nanopolish")
14229 (version (git-version "0.10.2" revision commit))
14233 (uri (git-reference
14234 (url "https://github.com/jts/nanopolish.git")
14237 (file-name (git-file-name name version))
14239 (base32 "09j5gz57yr9i34a27vbl72i4g8syv2zzgmsfyjq02yshmnrvkjs6"))))
14240 (build-system gnu-build-system)
14243 `("HDF5=noinstall" "EIGEN=noinstall" "HTS=noinstall" "CC=gcc")
14244 #:tests? #f ; no check target
14246 (modify-phases %standard-phases
14247 (add-after 'unpack 'find-eigen
14248 (lambda* (#:key inputs #:allow-other-keys)
14250 (string-append (assoc-ref inputs "eigen")
14251 "/include/eigen3"))
14253 (delete 'configure)
14255 (lambda* (#:key outputs #:allow-other-keys)
14256 (let* ((out (assoc-ref outputs "out"))
14257 (bin (string-append out "/bin"))
14258 (scripts (string-append out "/share/nanopolish/scripts")))
14260 (install-file "nanopolish" bin)
14261 (for-each (lambda (file) (install-file file scripts))
14262 (find-files "scripts" ".*"))
14264 (add-after 'install 'wrap-programs
14265 (lambda* (#:key outputs #:allow-other-keys)
14266 (for-each (lambda (file)
14267 (wrap-program file `("PYTHONPATH" ":" prefix (,path))))
14268 (find-files "/share/nanopolish/scripts" "\\.py"))
14269 (for-each (lambda (file)
14270 (wrap-program file `("PERL5LIB" ":" prefix (,path))))
14271 (find-files "/share/nanopolish/scripts" "\\.pl"))
14279 ("python-biopython" ,python-biopython)
14280 ("python-numpy" ,python-numpy)
14281 ("python-pysam" ,python-pysam)
14282 ("python-scikit-learn" , python-scikit-learn)
14283 ("python-scipy" ,python-scipy)
14285 (home-page "https://github.com/jts/nanopolish")
14286 (synopsis "Signal-level analysis of Oxford Nanopore sequencing data")
14288 "This package analyses the Oxford Nanopore sequencing data at signal-level.
14289 Nanopolish can calculate an improved consensus sequence for a draft genome
14290 assembly, detect base modifications, call SNPs (Single nucleotide
14291 polymorphisms) and indels with respect to a reference genome and more.")
14292 (license license:expat))))
14294 (define-public cnvkit
14301 (uri (git-reference
14302 (url "https://github.com/etal/cnvkit.git")
14303 (commit (string-append "v" version))))
14304 (file-name (git-file-name name version))
14306 (base32 "0g2f78k68yglmj4fsfmgs8idqv3di9aj53fg0ld0hqljg8chhh82"))))
14307 (build-system python-build-system)
14309 `(("python-biopython" ,python-biopython)
14310 ("python-future" ,python-future)
14311 ("python-matplotlib" ,python-matplotlib)
14312 ("python-numpy" ,python-numpy)
14313 ("python-reportlab" ,python-reportlab)
14314 ("python-pandas" ,python-pandas)
14315 ("python-pysam" ,python-pysam)
14316 ("python-pyfaidx" ,python-pyfaidx)
14317 ("python-scipy" ,python-scipy)
14319 ("r-dnacopy" ,r-dnacopy)))
14320 (home-page "https://cnvkit.readthedocs.org/")
14321 (synopsis "Copy number variant detection from targeted DNA sequencing")
14323 "CNVkit is a Python library and command-line software toolkit to infer
14324 and visualize copy number from high-throughput DNA sequencing data. It is
14325 designed for use with hybrid capture, including both whole-exome and custom
14326 target panels, and short-read sequencing platforms such as Illumina and Ion
14328 (license license:asl2.0)))
14330 (define-public python-pyfit-sne
14332 (name "python-pyfit-sne")
14337 (uri (git-reference
14338 (url "https://github.com/KlugerLab/pyFIt-SNE.git")
14340 (file-name (git-file-name name version))
14342 (base32 "13wh3qkzs56azmmgnxib6xfr29g7xh09sxylzjpni5j0pp0rc5qw"))))
14343 (build-system python-build-system)
14345 `(("python-numpy" ,python-numpy)))
14349 `(("python-cython" ,python-cython)))
14350 (home-page "https://github.com/KlugerLab/pyFIt-SNE")
14351 (synopsis "FFT-accelerated Interpolation-based t-SNE")
14353 "t-Stochastic Neighborhood Embedding (t-SNE) is a highly successful
14354 method for dimensionality reduction and visualization of high dimensional
14355 datasets. A popular implementation of t-SNE uses the Barnes-Hut algorithm to
14356 approximate the gradient at each iteration of gradient descent. This package
14357 is a Cython wrapper for FIt-SNE.")
14358 (license license:bsd-4)))
14360 (define-public velvet
14366 (uri (string-append "https://www.ebi.ac.uk/~zerbino/velvet/"
14367 "velvet_" version ".tgz"))
14370 "0h3njwy66p6bx14r3ar1byb0ccaxmxka4c65rn4iybyiqa4d8kc8"))
14371 ;; Delete bundled libraries
14372 (modules '((guix build utils)))
14375 (delete-file "Manual.pdf")
14376 (delete-file-recursively "third-party")
14378 (build-system gnu-build-system)
14380 `(#:make-flags '("OPENMP=t")
14381 #:test-target "test"
14383 (modify-phases %standard-phases
14384 (delete 'configure)
14385 (add-after 'unpack 'fix-zlib-include
14387 (substitute* "src/binarySequences.c"
14388 (("../third-party/zlib-1.2.3/zlib.h") "zlib.h"))
14391 (lambda* (#:key outputs #:allow-other-keys)
14392 (let* ((out (assoc-ref outputs "out"))
14393 (bin (string-append out "/bin"))
14394 (doc (string-append out "/share/doc/velvet")))
14397 (install-file "velveth" bin)
14398 (install-file "velvetg" bin)
14399 (install-file "Manual.pdf" doc)
14400 (install-file "Columbus_manual.pdf" doc)
14403 `(("openmpi" ,openmpi)
14406 `(("texlive" ,(texlive-union (list texlive-latex-graphics
14407 texlive-latex-hyperref)))))
14408 (home-page "https://www.ebi.ac.uk/~zerbino/velvet/")
14409 (synopsis "Nucleic acid sequence assembler for very short reads")
14411 "Velvet is a de novo genomic assembler specially designed for short read
14412 sequencing technologies, such as Solexa or 454. Velvet currently takes in
14413 short read sequences, removes errors then produces high quality unique
14414 contigs. It then uses paired read information, if available, to retrieve the
14415 repeated areas between contigs.")
14416 (license license:gpl2+)))
14418 (define-public python-velocyto
14420 (name "python-velocyto")
14421 (version "0.17.17")
14425 (uri (pypi-uri "velocyto" version))
14428 "0fgygyzqgrq32dv6a00biq1p1cwi6kbl5iqblxq1kklj6b2mzmhs"))))
14429 (build-system python-build-system)
14431 `(("python-click" ,python-click)
14432 ("python-cython" ,python-cython)
14433 ("python-h5py" ,python-h5py)
14434 ("python-loompy" ,python-loompy)
14435 ("python-matplotlib" ,python-matplotlib)
14436 ("python-numba" ,python-numba)
14437 ("python-numpy" ,python-numpy)
14438 ("python-pandas" ,python-pandas)
14439 ("python-pysam" ,python-pysam)
14440 ("python-scikit-learn" ,python-scikit-learn)
14441 ("python-scipy" ,python-scipy)))
14442 (home-page "https://github.com/velocyto-team/velocyto.py")
14443 (synopsis "RNA velocity analysis for single cell RNA-seq data")
14445 "Velocyto is a library for the analysis of RNA velocity. Velocyto
14446 includes a command line tool and an analysis pipeline.")
14447 (license license:bsd-2)))
14449 (define-public arriba
14456 (uri (string-append "https://github.com/suhrig/arriba/releases/"
14457 "download/v" version "/arriba_v" version ".tar.gz"))
14460 "0jx9656ry766vb8z08m1c3im87b0c82qpnjby9wz4kcz8vn87dx2"))))
14461 (build-system gnu-build-system)
14463 `(#:tests? #f ; there are none
14465 (modify-phases %standard-phases
14466 (replace 'configure
14467 (lambda* (#:key inputs #:allow-other-keys)
14468 (let ((htslib (assoc-ref inputs "htslib")))
14469 (substitute* "Makefile"
14470 (("-I\\$\\(HTSLIB\\)/htslib")
14471 (string-append "-I" htslib "/include/htslib"))
14472 ((" \\$\\(HTSLIB\\)/libhts.a")
14473 (string-append " " htslib "/lib/libhts.so"))))
14474 (substitute* "run_arriba.sh"
14475 (("^STAR ") (string-append (which "STAR") " "))
14476 (("samtools --version-only")
14477 (string-append (which "samtools") " --version-only"))
14478 (("samtools index")
14479 (string-append (which "samtools") " index"))
14481 (string-append (which "samtools") " sort")))
14484 (lambda* (#:key outputs #:allow-other-keys)
14485 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
14486 (install-file "arriba" bin)
14487 (install-file "run_arriba.sh" bin)
14488 (install-file "draw_fusions.R" bin)
14489 (wrap-program (string-append bin "/draw_fusions.R")
14490 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
14493 `(("htslib" ,htslib)
14494 ("r-minimal" ,r-minimal)
14495 ("r-circlize" ,r-circlize)
14496 ("r-genomicalignments" ,r-genomicalignments)
14497 ("r-genomicranges" ,r-genomicranges)
14498 ("samtools" ,samtools)
14501 (home-page "https://github.com/suhrig/arriba")
14502 (synopsis "Gene fusion detection from RNA-Seq data ")
14504 "Arriba is a command-line tool for the detection of gene fusions from
14505 RNA-Seq data. It was developed for the use in a clinical research setting.
14506 Therefore, short runtimes and high sensitivity were important design criteria.
14507 It is based on the fast STAR aligner and the post-alignment runtime is
14508 typically just around two minutes. In contrast to many other fusion detection
14509 tools which build on STAR, Arriba does not require to reduce the
14510 @code{alignIntronMax} parameter of STAR to detect small deletions.")
14511 ;; All code is under the Expat license with the exception of
14512 ;; "draw_fusions.R", which is under GPLv3.
14513 (license (list license:expat license:gpl3))))