1 ;;; GNU Guix --- Functional package management for GNU
2 ;;; Copyright © 2014, 2015, 2016, 2017, 2018, 2019, 2020 Ricardo Wurmus <rekado@elephly.net>
3 ;;; Copyright © 2015, 2016, 2017, 2018 Ben Woodcroft <donttrustben@gmail.com>
4 ;;; Copyright © 2015, 2016 Pjotr Prins <pjotr.guix@thebird.nl>
5 ;;; Copyright © 2015 Andreas Enge <andreas@enge.fr>
6 ;;; Copyright © 2016 Roel Janssen <roel@gnu.org>
7 ;;; Copyright © 2016, 2017, 2018, 2019, 2020 Efraim Flashner <efraim@flashner.co.il>
8 ;;; Copyright © 2016, 2020 Marius Bakke <mbakke@fastmail.com>
9 ;;; Copyright © 2016, 2018 Raoul Bonnal <ilpuccio.febo@gmail.com>
10 ;;; Copyright © 2017, 2018 Tobias Geerinckx-Rice <me@tobias.gr>
11 ;;; Copyright © 2017 Arun Isaac <arunisaac@systemreboot.net>
12 ;;; Copyright © 2018 Joshua Sierles, Nextjournal <joshua@nextjournal.com>
13 ;;; Copyright © 2018 Gábor Boskovits <boskovits@gmail.com>
14 ;;; Copyright © 2018, 2019 Mădălin Ionel Patrașcu <madalinionel.patrascu@mdc-berlin.de>
15 ;;; Copyright © 2019 Maxim Cournoyer <maxim.cournoyer@gmail.com>
16 ;;; Copyright © 2019 Brian Leung <bkleung89@gmail.com>
17 ;;; Copyright © 2019 Brett Gilio <brettg@gnu.org>
18 ;;; Copyright © 2020 Björn Höfling <bjoern.hoefling@bjoernhoefling.de>
19 ;;; Copyright © 2020 Jakub Kądziołka <kuba@kadziolka.net>
21 ;;; This file is part of GNU Guix.
23 ;;; GNU Guix is free software; you can redistribute it and/or modify it
24 ;;; under the terms of the GNU General Public License as published by
25 ;;; the Free Software Foundation; either version 3 of the License, or (at
26 ;;; your option) any later version.
28 ;;; GNU Guix is distributed in the hope that it will be useful, but
29 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
30 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
31 ;;; GNU General Public License for more details.
33 ;;; You should have received a copy of the GNU General Public License
34 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
36 (define-module (gnu packages bioinformatics)
37 #:use-module ((guix licenses) #:prefix license:)
38 #:use-module (guix packages)
39 #:use-module (guix utils)
40 #:use-module (guix download)
41 #:use-module (guix git-download)
42 #:use-module (guix hg-download)
43 #:use-module (guix build-system ant)
44 #:use-module (guix build-system gnu)
45 #:use-module (guix build-system cmake)
46 #:use-module (guix build-system go)
47 #:use-module (guix build-system haskell)
48 #:use-module (guix build-system meson)
49 #:use-module (guix build-system ocaml)
50 #:use-module (guix build-system perl)
51 #:use-module (guix build-system python)
52 #:use-module (guix build-system r)
53 #:use-module (guix build-system ruby)
54 #:use-module (guix build-system scons)
55 #:use-module (guix build-system trivial)
56 #:use-module (gnu packages)
57 #:use-module (gnu packages autotools)
58 #:use-module (gnu packages algebra)
59 #:use-module (gnu packages base)
60 #:use-module (gnu packages bash)
61 #:use-module (gnu packages bison)
62 #:use-module (gnu packages bioconductor)
63 #:use-module (gnu packages boost)
64 #:use-module (gnu packages check)
65 #:use-module (gnu packages code)
66 #:use-module (gnu packages compression)
67 #:use-module (gnu packages cpio)
68 #:use-module (gnu packages cran)
69 #:use-module (gnu packages curl)
70 #:use-module (gnu packages documentation)
71 #:use-module (gnu packages databases)
72 #:use-module (gnu packages datastructures)
73 #:use-module (gnu packages dlang)
74 #:use-module (gnu packages file)
75 #:use-module (gnu packages flex)
76 #:use-module (gnu packages gawk)
77 #:use-module (gnu packages gcc)
78 #:use-module (gnu packages gd)
79 #:use-module (gnu packages golang)
80 #:use-module (gnu packages glib)
81 #:use-module (gnu packages graph)
82 #:use-module (gnu packages groff)
83 #:use-module (gnu packages gtk)
84 #:use-module (gnu packages guile)
85 #:use-module (gnu packages guile-xyz)
86 #:use-module (gnu packages haskell-check)
87 #:use-module (gnu packages haskell-web)
88 #:use-module (gnu packages haskell-xyz)
89 #:use-module (gnu packages image)
90 #:use-module (gnu packages imagemagick)
91 #:use-module (gnu packages java)
92 #:use-module (gnu packages java-compression)
93 #:use-module (gnu packages jemalloc)
94 #:use-module (gnu packages linux)
95 #:use-module (gnu packages lisp-xyz)
96 #:use-module (gnu packages logging)
97 #:use-module (gnu packages machine-learning)
98 #:use-module (gnu packages man)
99 #:use-module (gnu packages maths)
100 #:use-module (gnu packages mpi)
101 #:use-module (gnu packages ncurses)
102 #:use-module (gnu packages ocaml)
103 #:use-module (gnu packages pcre)
104 #:use-module (gnu packages parallel)
105 #:use-module (gnu packages pdf)
106 #:use-module (gnu packages perl)
107 #:use-module (gnu packages perl-check)
108 #:use-module (gnu packages pkg-config)
109 #:use-module (gnu packages popt)
110 #:use-module (gnu packages protobuf)
111 #:use-module (gnu packages python)
112 #:use-module (gnu packages python-compression)
113 #:use-module (gnu packages python-science)
114 #:use-module (gnu packages python-web)
115 #:use-module (gnu packages python-xyz)
116 #:use-module (gnu packages readline)
117 #:use-module (gnu packages ruby)
118 #:use-module (gnu packages serialization)
119 #:use-module (gnu packages shells)
120 #:use-module (gnu packages sphinx)
121 #:use-module (gnu packages statistics)
122 #:use-module (gnu packages swig)
123 #:use-module (gnu packages tbb)
124 #:use-module (gnu packages tex)
125 #:use-module (gnu packages texinfo)
126 #:use-module (gnu packages textutils)
127 #:use-module (gnu packages time)
128 #:use-module (gnu packages tls)
129 #:use-module (gnu packages vim)
130 #:use-module (gnu packages web)
131 #:use-module (gnu packages xml)
132 #:use-module (gnu packages xorg)
133 #:use-module (srfi srfi-1)
134 #:use-module (ice-9 match))
136 (define-public aragorn
143 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
147 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
148 (build-system gnu-build-system)
150 `(#:tests? #f ; there are no tests
152 (modify-phases %standard-phases
162 (string-append "aragorn" ,version ".c"))
165 (lambda* (#:key outputs #:allow-other-keys)
166 (let* ((out (assoc-ref outputs "out"))
167 (bin (string-append out "/bin"))
168 (man (string-append out "/share/man/man1")))
169 (install-file "aragorn" bin)
170 (install-file "aragorn.1" man))
172 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
173 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
175 "Aragorn identifies transfer RNA, mitochondrial RNA and
176 transfer-messenger RNA from nucleotide sequences, based on homology to known
177 tRNA consensus sequences and RNA structure. It also outputs the secondary
178 structure of the predicted RNA.")
179 (license license:gpl2)))
187 ;; BamM is not available on pypi.
189 (url "https://github.com/Ecogenomics/BamM.git")
192 (file-name (git-file-name name version))
195 "1p83ahi984ipslxlg4yqy1gdnya9rkn1v71z8djgxkm9d2chw4c5"))
196 (modules '((guix build utils)))
199 ;; Delete bundled htslib.
200 (delete-file-recursively "c/htslib-1.3.1")
202 (build-system python-build-system)
204 `(#:python ,python-2 ; BamM is Python 2 only.
205 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
206 ;; been modified from its original form.
208 (let ((htslib (assoc-ref %build-inputs "htslib")))
209 (list "--with-libhts-lib" (string-append htslib "/lib")
210 "--with-libhts-inc" (string-append htslib "/include/htslib")))
212 (modify-phases %standard-phases
213 (add-after 'unpack 'autogen
215 (with-directory-excursion "c"
216 (let ((sh (which "sh")))
217 (for-each make-file-writable (find-files "." ".*"))
218 ;; Use autogen so that 'configure' works.
219 (substitute* "autogen.sh" (("/bin/sh") sh))
220 (setenv "CONFIG_SHELL" sh)
221 (invoke "./autogen.sh")))
224 ;; Run tests after installation so compilation only happens once.
226 (add-after 'install 'wrap-executable
227 (lambda* (#:key outputs #:allow-other-keys)
228 (let* ((out (assoc-ref outputs "out"))
229 (path (getenv "PATH")))
230 (wrap-program (string-append out "/bin/bamm")
231 `("PATH" ":" prefix (,path))))
233 (add-after 'wrap-executable 'post-install-check
234 (lambda* (#:key inputs outputs #:allow-other-keys)
236 (string-append (assoc-ref outputs "out")
241 (assoc-ref outputs "out")
243 (string-take (string-take-right
244 (assoc-ref inputs "python") 5) 3)
246 (getenv "PYTHONPATH")))
247 ;; There are 2 errors printed, but they are safe to ignore:
248 ;; 1) [E::hts_open_format] fail to open file ...
249 ;; 2) samtools view: failed to open ...
253 `(("autoconf" ,autoconf)
254 ("automake" ,automake)
257 ("python-nose" ,python2-nose)
258 ("python-pysam" ,python2-pysam)))
260 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
261 ("samtools" ,samtools)
265 ("coreutils" ,coreutils)))
267 `(("python-numpy" ,python2-numpy)))
268 (home-page "https://ecogenomics.github.io/BamM/")
269 (synopsis "Metagenomics-focused BAM file manipulator")
271 "BamM is a C library, wrapped in python, to efficiently generate and
272 parse BAM files, specifically for the analysis of metagenomic data. For
273 instance, it implements several methods to assess contig-wise read coverage.")
274 (license license:lgpl3+)))
276 (define-public bamtools
283 (url "https://github.com/pezmaster31/bamtools.git")
284 (commit (string-append "v" version))))
285 (file-name (git-file-name name version))
288 "0nfb2ypcx9959xnbz6wxh6py3xfizgmg8nrknxl95c507m9hmq8b"))))
289 (build-system cmake-build-system)
291 `(#:tests? #f ;no "check" target
293 (modify-phases %standard-phases
295 'configure 'set-ldflags
296 (lambda* (#:key outputs #:allow-other-keys)
300 (assoc-ref outputs "out") "/lib/bamtools"))
302 (inputs `(("zlib" ,zlib)))
303 (home-page "https://github.com/pezmaster31/bamtools")
304 (synopsis "C++ API and command-line toolkit for working with BAM data")
306 "BamTools provides both a C++ API and a command-line toolkit for handling
308 (license license:expat)))
310 (define-public bcftools
316 (uri (string-append "https://github.com/samtools/bcftools/"
318 version "/bcftools-" version ".tar.bz2"))
321 "1j3h638i8kgihzyrlnpj82xg1b23sijibys9hvwari3fy7kd0dkg"))
322 (modules '((guix build utils)))
324 ;; Delete bundled htslib.
325 (delete-file-recursively "htslib-1.9")
327 (build-system gnu-build-system)
330 (list "--enable-libgsl")
333 (modify-phases %standard-phases
334 (add-before 'check 'patch-tests
336 (substitute* "test/test.pl"
337 (("/bin/bash") (which "bash")))
345 (home-page "https://samtools.github.io/bcftools/")
346 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
348 "BCFtools is a set of utilities that manipulate variant calls in the
349 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
350 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
351 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
352 (license (list license:gpl3+ license:expat))))
354 (define-public bedops
361 (url "https://github.com/bedops/bedops.git")
362 (commit (string-append "v" version))))
363 (file-name (git-file-name name version))
366 "0mmgsgwz5r9w76hzgxkxc9s9lkdhhaf7vr6i02b09vbswvs1fyqx"))))
367 (build-system gnu-build-system)
370 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
372 (modify-phases %standard-phases
373 (add-after 'unpack 'unpack-tarballs
375 ;; FIXME: Bedops includes tarballs of minimally patched upstream
376 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
377 ;; libraries because at least one of the libraries (zlib) is
378 ;; patched to add a C++ function definition (deflateInit2cpp).
379 ;; Until the Bedops developers offer a way to link against system
380 ;; libraries we have to build the in-tree copies of these three
383 ;; See upstream discussion:
384 ;; https://github.com/bedops/bedops/issues/124
386 ;; Unpack the tarballs to benefit from shebang patching.
387 (with-directory-excursion "third-party"
388 (invoke "tar" "xvf" "jansson-2.6.tar.bz2")
389 (invoke "tar" "xvf" "zlib-1.2.7.tar.bz2")
390 (invoke "tar" "xvf" "bzip2-1.0.6.tar.bz2"))
391 ;; Disable unpacking of tarballs in Makefile.
392 (substitute* "system.mk/Makefile.linux"
393 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
394 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
395 (substitute* "third-party/zlib-1.2.7/Makefile.in"
396 (("^SHELL=.*$") "SHELL=bash\n"))
398 (delete 'configure))))
399 (home-page "https://github.com/bedops/bedops")
400 (synopsis "Tools for high-performance genomic feature operations")
402 "BEDOPS is a suite of tools to address common questions raised in genomic
403 studies---mostly with regard to overlap and proximity relationships between
404 data sets. It aims to be scalable and flexible, facilitating the efficient
405 and accurate analysis and management of large-scale genomic data.
407 BEDOPS provides tools that perform highly efficient and scalable Boolean and
408 other set operations, statistical calculations, archiving, conversion and
409 other management of genomic data of arbitrary scale. Tasks can be easily
410 split by chromosome for distributing whole-genome analyses across a
411 computational cluster.")
412 (license license:gpl2+)))
414 (define-public bedtools
420 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
421 "download/v" version "/"
422 "bedtools-" version ".tar.gz"))
425 "0m3hk6548846w83a9s5drsczvy67n2azx41kj71n03klb2gbzwg3"))))
426 (build-system gnu-build-system)
428 '(#:test-target "test"
430 (list (string-append "prefix=" (assoc-ref %outputs "out")))
432 (modify-phases %standard-phases
433 (delete 'configure))))
435 `(("python" ,python-wrapper)))
437 `(("samtools" ,samtools)
439 (home-page "https://github.com/arq5x/bedtools2")
440 (synopsis "Tools for genome analysis and arithmetic")
442 "Collectively, the bedtools utilities are a swiss-army knife of tools for
443 a wide-range of genomics analysis tasks. The most widely-used tools enable
444 genome arithmetic: that is, set theory on the genome. For example, bedtools
445 allows one to intersect, merge, count, complement, and shuffle genomic
446 intervals from multiple files in widely-used genomic file formats such as BAM,
448 (license license:expat)))
450 ;; Later releases of bedtools produce files with more columns than
451 ;; what Ribotaper expects.
452 (define-public bedtools-2.18
453 (package (inherit bedtools)
458 (uri (string-append "https://github.com/arq5x/bedtools2/"
459 "releases/download/v" version
460 "/bedtools-" version ".tar.gz"))
463 "11rvca19ncg03kxd0wzlfx5ws7r3nisd0z8s9j9n182d8ksp2pxz"))))
465 '(#:test-target "test"
467 (modify-phases %standard-phases
470 (lambda* (#:key outputs #:allow-other-keys)
471 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
472 (for-each (lambda (file)
473 (install-file file bin))
474 (find-files "bin" ".*")))
477 ;; Needed for pybedtools.
478 (define-public bedtools-2.26
479 (package (inherit bedtools)
484 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
485 "download/v" version "/"
486 "bedtools-" version ".tar.gz"))
489 "0jhavwifnf7lmkb11h9y7dynr8d699h0rd2l52j1pfgircr2zwv5"))))))
498 (url "https://github.com/PacificBiosciences/pbbam.git")
500 (file-name (git-file-name name version))
503 "0h9gkrpf2lrxklxp72xfl5bi3h5zcm5hprrya9gf0hr3xwlbpp0x"))))
504 (build-system meson-build-system)
507 (modify-phases %standard-phases
508 (add-after 'unpack 'find-googletest
509 (lambda* (#:key inputs #:allow-other-keys)
510 ;; It doesn't find gtest_main because there's no pkg-config file
511 ;; for it. Find it another way.
512 (substitute* "tests/meson.build"
513 (("pbbam_gtest_dep = dependency\\('gtest_main'.*")
514 (format #f "cpp = meson.get_compiler('cpp')
515 pbbam_gtest_dep = cpp.find_library('gtest_main', dirs : '~a')\n"
516 (assoc-ref inputs "googletest"))))
518 ;; TODO: tests/pbbam_test cannot be linked
519 ;; ld: tests/59830eb@@pbbam_test@exe/src_test_Accuracy.cpp.o:
520 ;; undefined reference to symbol '_ZTIN7testing4TestE'
521 ;; ld: /gnu/store/...-googletest-1.8.0/lib/libgtest.so:
522 ;; error adding symbols: DSO missing from command line
524 #:configure-flags '("-Dtests=false")))
525 ;; These libraries are listed as "Required" in the pkg-config file.
531 ("samtools" ,samtools)))
533 `(("googletest" ,googletest)
534 ("pkg-config" ,pkg-config)
535 ("python" ,python-wrapper))) ; for tests
536 (home-page "https://github.com/PacificBiosciences/pbbam")
537 (synopsis "Work with PacBio BAM files")
539 "The pbbam software package provides components to create, query, and
540 edit PacBio BAM files and associated indices. These components include a core
541 C++ library, bindings for additional languages, and command-line utilities.
542 This library is not intended to be used as a general-purpose BAM utility - all
543 input and output BAMs must adhere to the PacBio BAM format specification.
544 Non-PacBio BAMs will cause exceptions to be thrown.")
545 (license license:bsd-3)))
547 (define-public blasr-libcpp
549 (name "blasr-libcpp")
554 (url "https://github.com/PacificBiosciences/blasr_libcpp.git")
556 (file-name (git-file-name name version))
559 "0cn5l42zyq67sj0g2imqkhayz2iqvv0a1pgpbmlq0qynjmsrbfd2"))))
560 (build-system meson-build-system)
563 (modify-phases %standard-phases
564 (add-after 'unpack 'link-with-hdf5
565 (lambda* (#:key inputs #:allow-other-keys)
566 (let ((hdf5 (assoc-ref inputs "hdf5")))
567 (substitute* "meson.build"
568 (("libblasr_deps = \\[" m)
571 (format #f "cpp.find_library('hdf5', dirs : '~a'), \
572 cpp.find_library('hdf5_cpp', dirs : '~a'), "
575 (add-after 'unpack 'find-googletest
576 (lambda* (#:key inputs #:allow-other-keys)
577 ;; It doesn't find gtest_main because there's no pkg-config file
578 ;; for it. Find it another way.
579 (substitute* "unittest/meson.build"
580 (("libblasr_gtest_dep = dependency\\('gtest_main'.*")
581 (format #f "cpp = meson.get_compiler('cpp')
582 libblasr_gtest_dep = cpp.find_library('gtest_main', dirs : '~a')\n"
583 (assoc-ref inputs "googletest"))))
585 ;; TODO: unittest/libblasr_unittest cannot be linked
586 ;; ld: ;; unittest/df08227@@libblasr_unittest@exe/alignment_utils_FileUtils_gtest.cpp.o:
587 ;; undefined reference to symbol
588 ;; '_ZN7testing8internal9DeathTest6CreateEPKcPKNS0_2REES3_iPPS1_'
589 ;; ld: /gnu/store/...-googletest-1.8.0/lib/libgtest.so:
590 ;; error adding symbols: DSO missing from command line
592 #:configure-flags '("-Dtests=false")))
599 `(("googletest" ,googletest)
600 ("pkg-config" ,pkg-config)))
601 (home-page "https://github.com/PacificBiosciences/blasr_libcpp")
602 (synopsis "Library for analyzing PacBio genomic sequences")
604 "This package provides three libraries used by applications for analyzing
605 PacBio genomic sequences. This library contains three sub-libraries: pbdata,
607 (license license:bsd-3)))
616 (url "https://github.com/PacificBiosciences/blasr.git")
618 (file-name (git-file-name name version))
621 "1skgy2mvz8gsgfh1gc2nfgwvpyzb1hpmp2cf2773h5wsj8nw22kl"))))
622 (build-system meson-build-system)
625 (modify-phases %standard-phases
626 (add-after 'unpack 'link-with-hdf5
627 (lambda* (#:key inputs #:allow-other-keys)
628 (let ((hdf5 (assoc-ref inputs "hdf5")))
629 (substitute* "meson.build"
630 (("blasr_deps = \\[" m)
633 (format #f "cpp.find_library('hdf5', dirs : '~a'), \
634 cpp.find_library('hdf5_cpp', dirs : '~a'), "
637 ;; Tests require "cram" executable, which is not packaged.
639 #:configure-flags '("-Dtests=false")))
642 ("blasr-libcpp" ,blasr-libcpp)
647 `(("pkg-config" ,pkg-config)))
648 (home-page "https://github.com/PacificBiosciences/blasr")
649 (synopsis "PacBio long read aligner")
651 "Blasr is a genomic sequence aligner for processing PacBio long reads.")
652 (license license:bsd-3)))
654 (define-public ribotaper
660 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
661 "files/RiboTaper/RiboTaper_Version_"
665 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
666 (build-system gnu-build-system)
669 (modify-phases %standard-phases
670 (add-after 'install 'wrap-executables
671 (lambda* (#:key inputs outputs #:allow-other-keys)
672 (let* ((out (assoc-ref outputs "out")))
675 (wrap-program (string-append out "/bin/" script)
676 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
677 '("create_annotations_files.bash"
678 "create_metaplots.bash"
679 "Ribotaper_ORF_find.sh"
683 `(("bedtools" ,bedtools-2.18)
684 ("samtools" ,samtools-0.1)
685 ("r-minimal" ,r-minimal)
686 ("r-foreach" ,r-foreach)
687 ("r-xnomial" ,r-xnomial)
689 ("r-multitaper" ,r-multitaper)
690 ("r-seqinr" ,r-seqinr)))
691 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
692 (synopsis "Define translated ORFs using ribosome profiling data")
694 "Ribotaper is a method for defining translated @dfn{open reading
695 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
696 provides the Ribotaper pipeline.")
697 (license license:gpl3+)))
699 (define-public ribodiff
707 (url "https://github.com/ratschlab/RiboDiff.git")
708 (commit (string-append "v" version))))
709 (file-name (git-file-name name version))
712 "0x75nlp7qnmm64jasbi6l21f2cy99r2cjyl6b4hr8zf2bq22drnz"))))
713 (build-system python-build-system)
717 (modify-phases %standard-phases
718 ;; Generate an installable executable script wrapper.
719 (add-after 'unpack 'patch-setup.py
721 (substitute* "setup.py"
722 (("^(.*)packages=.*" line prefix)
723 (string-append line "\n"
724 prefix "scripts=['scripts/TE.py'],\n")))
727 `(("python-numpy" ,python2-numpy)
728 ("python-matplotlib" ,python2-matplotlib)
729 ("python-scipy" ,python2-scipy)
730 ("python-statsmodels" ,python2-statsmodels)))
732 `(("python-mock" ,python2-mock)
733 ("python-nose" ,python2-nose)))
734 (home-page "https://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
735 (synopsis "Detect translation efficiency changes from ribosome footprints")
736 (description "RiboDiff is a statistical tool that detects the protein
737 translational efficiency change from Ribo-Seq (ribosome footprinting) and
738 RNA-Seq data. It uses a generalized linear model to detect genes showing
739 difference in translational profile taking mRNA abundance into account. It
740 facilitates us to decipher the translational regulation that behave
741 independently with transcriptional regulation.")
742 (license license:gpl3+)))
744 (define-public bioawk
751 (url "https://github.com/lh3/bioawk.git")
752 (commit (string-append "v" version))))
753 (file-name (git-file-name name version))
756 "1pxc3zdnirxbf9a0az698hd8xdik7qkhypm7v6hn922x8y9qmspm"))))
757 (build-system gnu-build-system)
763 `(#:tests? #f ; There are no tests to run.
764 ;; Bison must generate files, before other targets can build.
767 (modify-phases %standard-phases
768 (delete 'configure) ; There is no configure phase.
770 (lambda* (#:key outputs #:allow-other-keys)
771 (let* ((out (assoc-ref outputs "out"))
772 (bin (string-append out "/bin"))
773 (man (string-append out "/share/man/man1")))
775 (copy-file "awk.1" (string-append man "/bioawk.1"))
776 (install-file "bioawk" bin))
778 (home-page "https://github.com/lh3/bioawk")
779 (synopsis "AWK with bioinformatics extensions")
780 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
781 support of several common biological data formats, including optionally gzip'ed
782 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
783 also adds a few built-in functions and a command line option to use TAB as the
784 input/output delimiter. When the new functionality is not used, bioawk is
785 intended to behave exactly the same as the original BWK awk.")
786 (license license:x11)))
788 (define-public python-pybedtools
790 (name "python-pybedtools")
794 (uri (pypi-uri "pybedtools" version))
797 "14w5i40gi25clrr7h4wa2pcpnyipya8hrqi7nq77553zc5wf0df0"))))
798 (build-system python-build-system)
800 `(#:modules ((ice-9 ftw)
804 (guix build python-build-system))
805 ;; See https://github.com/daler/pybedtools/issues/192
807 (modify-phases %standard-phases
808 ;; See https://github.com/daler/pybedtools/issues/261
809 (add-after 'unpack 'disable-broken-tests
811 ;; This test (pybedtools.test.test_scripts.test_venn_mpl) needs a
812 ;; graphical environment.
813 (substitute* "pybedtools/test/test_scripts.py"
814 (("def test_venn_mpl")
815 "def _do_not_test_venn_mpl"))
816 (substitute* "pybedtools/test/test_helpers.py"
817 ;; Requires internet access.
818 (("def test_chromsizes")
819 "def _do_not_test_chromsizes")
820 ;; Broken as a result of the workaround used in the check phase
821 ;; (see: https://github.com/daler/pybedtools/issues/192).
822 (("def test_getting_example_beds")
823 "def _do_not_test_getting_example_beds"))
824 ;; This issue still occurs on python2
825 (substitute* "pybedtools/test/test_issues.py"
826 (("def test_issue_303")
827 "def _test_issue_303"))
829 ;; TODO: Remove phase after it's part of PYTHON-BUILD-SYSTEM.
831 ;; Force the Cythonization of C++ files to guard against compilation
833 (add-after 'unpack 'remove-cython-generated-files
835 (let ((cython-sources (map (cut string-drop-right <> 4)
836 (find-files "." "\\.pyx$")))
837 (c/c++-files (find-files "." "\\.(c|cpp|cxx)$")))
838 (define (strip-extension filename)
839 (string-take filename (string-index-right filename #\.)))
840 (define (cythonized? c/c++-file)
841 (member (strip-extension c/c++-file) cython-sources))
842 (for-each delete-file (filter cythonized? c/c++-files))
844 (add-after 'remove-cython-generated-files 'generate-cython-extensions
846 (invoke "python" "setup.py" "cythonize")))
849 (let* ((cwd (getcwd))
850 (build-root-directory (string-append cwd "/build/"))
851 (build (string-append
853 (find (cut string-prefix? "lib" <>)
854 (scandir (string-append
855 build-root-directory)))))
856 (scripts (string-append
858 (find (cut string-prefix? "scripts" <>)
859 (scandir build-root-directory)))))
861 (string-append build ":" (getenv "PYTHONPATH")))
862 ;; Executable scripts such as 'intron_exon_reads.py' must be
863 ;; available in the PATH.
865 (string-append scripts ":" (getenv "PATH"))))
866 ;; The tests need to be run from elsewhere...
867 (mkdir-p "/tmp/test")
868 (copy-recursively "pybedtools/test" "/tmp/test")
869 (with-directory-excursion "/tmp/test"
870 (invoke "pytest")))))))
872 `(("bedtools" ,bedtools)
873 ("samtools" ,samtools)
874 ("python-matplotlib" ,python-matplotlib)
875 ("python-pysam" ,python-pysam)
876 ("python-pyyaml" ,python-pyyaml)))
878 `(("python-numpy" ,python-numpy)
879 ("python-pandas" ,python-pandas)
880 ("python-cython" ,python-cython)
881 ("kentutils" ,kentutils) ; for bedGraphToBigWig
882 ("python-six" ,python-six)
883 ;; For the test suite.
884 ("python-pytest" ,python-pytest)
885 ("python-psutil" ,python-psutil)))
886 (home-page "https://pythonhosted.org/pybedtools/")
887 (synopsis "Python wrapper for BEDtools programs")
889 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
890 which are widely used for genomic interval manipulation or \"genome algebra\".
891 pybedtools extends BEDTools by offering feature-level manipulations from with
893 (license license:gpl2+)))
895 (define-public python2-pybedtools
896 (let ((pybedtools (package-with-python2 python-pybedtools)))
900 `(("python2-pathlib" ,python2-pathlib)
901 ,@(package-native-inputs pybedtools))))))
903 (define-public python-biom-format
905 (name "python-biom-format")
910 ;; Use GitHub as source because PyPI distribution does not contain
911 ;; test data: https://github.com/biocore/biom-format/issues/693
913 (url "https://github.com/biocore/biom-format.git")
915 (file-name (git-file-name name version))
918 "1rna16lyk5aqhnv0dp77wwaplias93f1vw28ad3jmyw6hwkai05v"))
919 (modules '((guix build utils)))
921 ;; Delete generated C files.
922 (for-each delete-file (find-files "." "\\.c"))
924 (build-system python-build-system)
927 (modify-phases %standard-phases
928 (add-after 'unpack 'use-cython
929 (lambda _ (setenv "USE_CYTHON" "1") #t))
930 (add-after 'unpack 'disable-broken-tests
932 (substitute* "biom/tests/test_cli/test_validate_table.py"
933 (("^(.+)def test_invalid_hdf5" m indent)
934 (string-append indent
935 "@npt.dec.skipif(True, msg='Guix')\n"
937 (substitute* "biom/tests/test_table.py"
938 (("^(.+)def test_from_hdf5_issue_731" m indent)
939 (string-append indent
940 "@npt.dec.skipif(True, msg='Guix')\n"
943 (add-before 'reset-gzip-timestamps 'make-files-writable
944 (lambda* (#:key outputs #:allow-other-keys)
945 (let ((out (assoc-ref outputs "out")))
946 (for-each (lambda (file) (chmod file #o644))
947 (find-files out "\\.gz"))
950 `(("python-numpy" ,python-numpy)
951 ("python-scipy" ,python-scipy)
952 ("python-flake8" ,python-flake8)
953 ("python-future" ,python-future)
954 ("python-click" ,python-click)
955 ("python-h5py" ,python-h5py)
956 ("python-pandas" ,python-pandas)))
958 `(("python-cython" ,python-cython)
959 ("python-pytest" ,python-pytest)
960 ("python-pytest-cov" ,python-pytest-cov)
961 ("python-nose" ,python-nose)))
962 (home-page "http://www.biom-format.org")
963 (synopsis "Biological Observation Matrix (BIOM) format utilities")
965 "The BIOM file format is designed to be a general-use format for
966 representing counts of observations e.g. operational taxonomic units, KEGG
967 orthology groups or lipid types, in one or more biological samples
968 e.g. microbiome samples, genomes, metagenomes.")
969 (license license:bsd-3)
970 (properties `((python2-variant . ,(delay python2-biom-format))))))
972 (define-public python2-biom-format
973 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
977 (substitute-keyword-arguments (package-arguments base)
979 `(modify-phases ,phases
980 ;; Do not require the unmaintained pyqi library.
981 (add-after 'unpack 'remove-pyqi
983 (substitute* "setup.py"
984 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
987 (define-public bioperl-minimal
988 (let* ((inputs `(("perl-module-build" ,perl-module-build)
989 ("perl-data-stag" ,perl-data-stag)
990 ("perl-libwww" ,perl-libwww)
991 ("perl-uri" ,perl-uri)))
993 (map (compose package-name cadr)
996 (map (compose package-transitive-target-inputs cadr) inputs))))))
998 (name "bioperl-minimal")
1004 (url "https://github.com/bioperl/bioperl-live")
1005 (commit (string-append "release-"
1006 (string-map (lambda (c)
1008 #\- c)) version)))))
1009 (file-name (git-file-name name version))
1012 "0wl8yvzcls59pwwk6m8ahy87pwg6nnibzy5cldbvmcwg2x2w7783"))))
1013 (build-system perl-build-system)
1016 (modify-phases %standard-phases
1018 'install 'wrap-programs
1019 (lambda* (#:key outputs #:allow-other-keys)
1020 ;; Make sure all executables in "bin" find the required Perl
1021 ;; modules at runtime. As the PERL5LIB variable contains also
1022 ;; the paths of native inputs, we pick the transitive target
1023 ;; inputs from %build-inputs.
1024 (let* ((out (assoc-ref outputs "out"))
1025 (bin (string-append out "/bin/"))
1027 (cons (string-append out "/lib/perl5/site_perl")
1029 (assoc-ref %build-inputs name))
1030 ',transitive-inputs))
1032 (for-each (lambda (file)
1034 `("PERL5LIB" ":" prefix (,path))))
1035 (find-files bin "\\.pl$"))
1039 `(("perl-test-most" ,perl-test-most)))
1040 (home-page "https://metacpan.org/release/BioPerl")
1041 (synopsis "Bioinformatics toolkit")
1043 "BioPerl is the product of a community effort to produce Perl code which
1044 is useful in biology. Examples include Sequence objects, Alignment objects
1045 and database searching objects. These objects not only do what they are
1046 advertised to do in the documentation, but they also interact - Alignment
1047 objects are made from the Sequence objects, Sequence objects have access to
1048 Annotation and SeqFeature objects and databases, Blast objects can be
1049 converted to Alignment objects, and so on. This means that the objects
1050 provide a coordinated and extensible framework to do computational biology.")
1051 (license license:perl-license))))
1053 (define-public python-biopython
1055 (name "python-biopython")
1059 ;; use PyPi rather than biopython.org to ease updating
1060 (uri (pypi-uri "biopython" version))
1063 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
1064 (build-system python-build-system)
1067 (modify-phases %standard-phases
1068 (add-before 'check 'set-home
1069 ;; Some tests require a home directory to be set.
1070 (lambda _ (setenv "HOME" "/tmp") #t)))))
1072 `(("python-numpy" ,python-numpy)))
1073 (home-page "https://biopython.org/")
1074 (synopsis "Tools for biological computation in Python")
1076 "Biopython is a set of tools for biological computation including parsers
1077 for bioinformatics files into Python data structures; interfaces to common
1078 bioinformatics programs; a standard sequence class and tools for performing
1079 common operations on them; code to perform data classification; code for
1080 dealing with alignments; code making it easy to split up parallelizable tasks
1081 into separate processes; and more.")
1082 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
1084 (define-public python2-biopython
1085 (package-with-python2 python-biopython))
1087 (define-public python-fastalite
1089 (name "python-fastalite")
1094 (uri (pypi-uri "fastalite" version))
1097 "1qli6pxp77i9xn2wfciq2zaxhl82bdxb33cpzqzj1z25yd036wqj"))))
1098 (build-system python-build-system)
1100 `(#:tests? #f)) ; Test data is not distributed.
1101 (home-page "https://github.com/nhoffman/fastalite")
1102 (synopsis "Simplest possible FASTA parser")
1103 (description "This library implements a FASTA and a FASTQ parser without
1104 relying on a complex dependency tree.")
1105 (license license:expat)))
1107 (define-public python2-fastalite
1108 (package-with-python2 python-fastalite))
1110 (define-public bpp-core
1111 ;; The last release was in 2014 and the recommended way to install from source
1112 ;; is to clone the git repository, so we do this.
1113 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1114 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
1117 (version (string-append "2.2.0-1." (string-take commit 7)))
1121 (url "http://biopp.univ-montp2.fr/git/bpp-core")
1123 (file-name (string-append name "-" version "-checkout"))
1126 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
1127 (build-system cmake-build-system)
1129 `(#:parallel-build? #f))
1130 (home-page "http://biopp.univ-montp2.fr")
1131 (synopsis "C++ libraries for Bioinformatics")
1133 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1134 analysis, phylogenetics, molecular evolution and population genetics. It is
1135 Object Oriented and is designed to be both easy to use and computer efficient.
1136 Bio++ intends to help programmers to write computer expensive programs, by
1137 providing them a set of re-usable tools.")
1138 (license license:cecill-c))))
1140 (define-public bpp-phyl
1141 ;; The last release was in 2014 and the recommended way to install from source
1142 ;; is to clone the git repository, so we do this.
1143 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1144 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
1147 (version (string-append "2.2.0-1." (string-take commit 7)))
1151 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
1153 (file-name (string-append name "-" version "-checkout"))
1156 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
1157 (build-system cmake-build-system)
1159 `(#:parallel-build? #f
1160 ;; If out-of-source, test data is not copied into the build directory
1161 ;; so the tests fail.
1162 #:out-of-source? #f))
1164 `(("bpp-core" ,bpp-core)
1165 ("bpp-seq" ,bpp-seq)))
1166 (home-page "http://biopp.univ-montp2.fr")
1167 (synopsis "Bio++ phylogenetic Library")
1169 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1170 analysis, phylogenetics, molecular evolution and population genetics. This
1171 library provides phylogenetics-related modules.")
1172 (license license:cecill-c))))
1174 (define-public bpp-popgen
1175 ;; The last release was in 2014 and the recommended way to install from source
1176 ;; is to clone the git repository, so we do this.
1177 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1178 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
1181 (version (string-append "2.2.0-1." (string-take commit 7)))
1185 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
1187 (file-name (string-append name "-" version "-checkout"))
1190 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
1191 (build-system cmake-build-system)
1193 `(#:parallel-build? #f
1194 #:tests? #f)) ; There are no tests.
1196 `(("bpp-core" ,bpp-core)
1197 ("bpp-seq" ,bpp-seq)))
1198 (home-page "http://biopp.univ-montp2.fr")
1199 (synopsis "Bio++ population genetics library")
1201 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1202 analysis, phylogenetics, molecular evolution and population genetics. This
1203 library provides population genetics-related modules.")
1204 (license license:cecill-c))))
1206 (define-public bpp-seq
1207 ;; The last release was in 2014 and the recommended way to install from source
1208 ;; is to clone the git repository, so we do this.
1209 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1210 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
1213 (version (string-append "2.2.0-1." (string-take commit 7)))
1217 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
1219 (file-name (string-append name "-" version "-checkout"))
1222 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
1223 (build-system cmake-build-system)
1225 `(#:parallel-build? #f
1226 ;; If out-of-source, test data is not copied into the build directory
1227 ;; so the tests fail.
1228 #:out-of-source? #f))
1230 `(("bpp-core" ,bpp-core)))
1231 (home-page "http://biopp.univ-montp2.fr")
1232 (synopsis "Bio++ sequence library")
1234 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1235 analysis, phylogenetics, molecular evolution and population genetics. This
1236 library provides sequence-related modules.")
1237 (license license:cecill-c))))
1239 (define-public bppsuite
1240 ;; The last release was in 2014 and the recommended way to install from source
1241 ;; is to clone the git repository, so we do this.
1242 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1243 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
1246 (version (string-append "2.2.0-1." (string-take commit 7)))
1250 (url "http://biopp.univ-montp2.fr/git/bppsuite")
1252 (file-name (string-append name "-" version "-checkout"))
1255 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
1256 (build-system cmake-build-system)
1258 `(#:parallel-build? #f
1259 #:tests? #f)) ; There are no tests.
1263 ("texinfo" ,texinfo)))
1265 `(("bpp-core" ,bpp-core)
1266 ("bpp-seq" ,bpp-seq)
1267 ("bpp-phyl" ,bpp-phyl)
1268 ("bpp-phyl" ,bpp-popgen)))
1269 (home-page "http://biopp.univ-montp2.fr")
1270 (synopsis "Bioinformatics tools written with the Bio++ libraries")
1272 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1273 analysis, phylogenetics, molecular evolution and population genetics. This
1274 package provides command line tools using the Bio++ library.")
1275 (license license:cecill-c))))
1277 (define-public blast+
1284 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
1285 version "/ncbi-blast-" version "+-src.tar.gz"))
1288 "1jlq0afxxgczpp35k6mxh8mn4jzq7vqcnaixk166sfj10wq8v9qh"))
1289 (modules '((guix build utils)))
1292 ;; Remove bundled bzip2, zlib and pcre.
1293 (delete-file-recursively "c++/src/util/compress/bzip2")
1294 (delete-file-recursively "c++/src/util/compress/zlib")
1295 (delete-file-recursively "c++/src/util/regexp")
1296 (substitute* "c++/src/util/compress/Makefile.in"
1297 (("bzip2 zlib api") "api"))
1298 ;; Remove useless msbuild directory
1299 (delete-file-recursively
1300 "c++/src/build-system/project_tree_builder/msbuild")
1302 (build-system gnu-build-system)
1304 `(;; There are two(!) tests for this massive library, and both fail with
1305 ;; "unparsable timing stats".
1306 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
1307 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
1310 #:parallel-build? #f ; not supported
1312 (modify-phases %standard-phases
1313 (add-before 'configure 'set-HOME
1314 ;; $HOME needs to be set at some point during the configure phase
1315 (lambda _ (setenv "HOME" "/tmp") #t))
1316 (add-after 'unpack 'enter-dir
1317 (lambda _ (chdir "c++") #t))
1318 (add-after 'enter-dir 'fix-build-system
1320 (define (which* cmd)
1321 (cond ((string=? cmd "date")
1322 ;; make call to "date" deterministic
1327 (format (current-error-port)
1328 "WARNING: Unable to find absolute path for ~s~%"
1332 ;; Rewrite hardcoded paths to various tools
1333 (substitute* (append '("src/build-system/configure.ac"
1334 "src/build-system/configure"
1335 "src/build-system/helpers/run_with_lock.c"
1336 "scripts/common/impl/if_diff.sh"
1337 "scripts/common/impl/run_with_lock.sh"
1338 "src/build-system/Makefile.configurables.real"
1339 "src/build-system/Makefile.in.top"
1340 "src/build-system/Makefile.meta.gmake=no"
1341 "src/build-system/Makefile.meta.in"
1342 "src/build-system/Makefile.meta_l"
1343 "src/build-system/Makefile.meta_p"
1344 "src/build-system/Makefile.meta_r"
1345 "src/build-system/Makefile.mk.in"
1346 "src/build-system/Makefile.requirements"
1347 "src/build-system/Makefile.rules_with_autodep.in")
1348 (find-files "scripts/common/check" "\\.sh$"))
1349 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1350 (or (which* cmd) all)))
1352 (substitute* (find-files "src/build-system" "^config.*")
1353 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1356 ;; rewrite "/var/tmp" in check script
1357 (substitute* "scripts/common/check/check_make_unix.sh"
1358 (("/var/tmp") "/tmp"))
1360 ;; do not reset PATH
1361 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1363 (("action=/bin/") "action=")
1364 (("export PATH") ":"))
1367 (lambda* (#:key inputs outputs #:allow-other-keys)
1368 (let ((out (assoc-ref outputs "out"))
1369 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1370 (include (string-append (assoc-ref outputs "include")
1371 "/include/ncbi-tools++")))
1372 ;; The 'configure' script doesn't recognize things like
1373 ;; '--enable-fast-install'.
1374 (invoke "./configure.orig"
1375 (string-append "--with-build-root=" (getcwd) "/build")
1376 (string-append "--prefix=" out)
1377 (string-append "--libdir=" lib)
1378 (string-append "--includedir=" include)
1379 (string-append "--with-bz2="
1380 (assoc-ref inputs "bzip2"))
1381 (string-append "--with-z="
1382 (assoc-ref inputs "zlib"))
1383 (string-append "--with-pcre="
1384 (assoc-ref inputs "pcre"))
1385 ;; Each library is built twice by default, once
1386 ;; with "-static" in its name, and again
1391 (outputs '("out" ; 21 MB
1400 ("python" ,python-wrapper)))
1403 (home-page "http://blast.ncbi.nlm.nih.gov")
1404 (synopsis "Basic local alignment search tool")
1406 "BLAST is a popular method of performing a DNA or protein sequence
1407 similarity search, using heuristics to produce results quickly. It also
1408 calculates an “expect value” that estimates how many matches would have
1409 occurred at a given score by chance, which can aid a user in judging how much
1410 confidence to have in an alignment.")
1411 ;; Most of the sources are in the public domain, with the following
1414 ;; * ./c++/include/util/bitset/
1415 ;; * ./c++/src/html/ncbi_menu*.js
1417 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1419 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1421 ;; * ./c++/src/corelib/teamcity_*
1422 (license (list license:public-domain
1428 (define-public bless
1434 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1438 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1439 (modules '((guix build utils)))
1442 ;; Remove bundled boost, pigz, zlib, and .git directory
1443 ;; FIXME: also remove bundled sources for murmurhash3 and
1444 ;; kmc once packaged.
1445 (delete-file-recursively "boost")
1446 (delete-file-recursively "pigz")
1447 (delete-file-recursively "google-sparsehash")
1448 (delete-file-recursively "zlib")
1449 (delete-file-recursively ".git")
1451 (build-system gnu-build-system)
1453 '(#:tests? #f ;no "check" target
1455 (list (string-append "ZLIB="
1456 (assoc-ref %build-inputs "zlib:static")
1458 (string-append "LDFLAGS="
1459 (string-join '("-lboost_filesystem"
1465 (modify-phases %standard-phases
1466 (add-after 'unpack 'do-not-build-bundled-pigz
1467 (lambda* (#:key inputs outputs #:allow-other-keys)
1468 (substitute* "Makefile"
1469 (("cd pigz/pigz-2.3.3; make") ""))
1471 (add-after 'unpack 'patch-paths-to-executables
1472 (lambda* (#:key inputs outputs #:allow-other-keys)
1473 (substitute* "parse_args.cpp"
1474 (("kmc_binary = .*")
1475 (string-append "kmc_binary = \""
1476 (assoc-ref outputs "out")
1478 (("pigz_binary = .*")
1479 (string-append "pigz_binary = \""
1480 (assoc-ref inputs "pigz")
1484 (lambda* (#:key outputs #:allow-other-keys)
1485 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1486 (for-each (lambda (file)
1487 (install-file file bin))
1488 '("bless" "kmc/bin/kmc"))
1490 (delete 'configure))))
1494 `(("openmpi" ,openmpi)
1496 ("sparsehash" ,sparsehash)
1498 ("zlib:static" ,zlib "static")
1500 (supported-systems '("x86_64-linux"))
1501 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1502 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1504 "@dfn{Bloom-filter-based error correction solution for high-throughput
1505 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1506 correction tool for genomic reads produced by @dfn{Next-generation
1507 sequencing} (NGS). BLESS produces accurate correction results with much less
1508 memory compared with previous solutions and is also able to tolerate a higher
1509 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1510 errors at the end of reads.")
1511 (license license:gpl3+)))
1513 (define-public bowtie
1520 (url "https://github.com/BenLangmead/bowtie2.git")
1521 (commit (string-append "v" version))))
1522 (file-name (git-file-name name version))
1525 "1zl3cf327y2p7p03cavymbh7b00djc7lncfaqih33n96iy9q8ibp"))
1526 (modules '((guix build utils)))
1529 (substitute* "Makefile"
1530 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1531 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1532 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
1534 (build-system gnu-build-system)
1539 (string-append "prefix=" (assoc-ref %outputs "out")))
1541 (modify-phases %standard-phases
1546 "scripts/test/simple_tests.pl"
1547 "--bowtie2=./bowtie2"
1548 "--bowtie2-build=./bowtie2-build")
1553 ("python" ,python-wrapper)))
1556 ("perl-clone" ,perl-clone)
1557 ("perl-test-deep" ,perl-test-deep)
1558 ("perl-test-simple" ,perl-test-simple)))
1559 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1560 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1562 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1563 reads to long reference sequences. It is particularly good at aligning reads
1564 of about 50 up to 100s or 1,000s of characters, and particularly good at
1565 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1566 genome with an FM Index to keep its memory footprint small: for the human
1567 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1568 gapped, local, and paired-end alignment modes.")
1569 (supported-systems '("x86_64-linux"))
1570 (license license:gpl3+)))
1572 (define-public bowtie1
1578 (uri (string-append "mirror://sourceforge/bowtie-bio/bowtie/"
1579 version "/bowtie-src-x86_64.zip"))
1582 "0vmiqdhc9dzyfy9sh6vgi7k9xy2hiw8g87vbamnc6cgpm179zsa4"))
1583 (modules '((guix build utils)))
1585 '(substitute* "Makefile"
1586 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1587 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1588 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1589 (build-system gnu-build-system)
1591 '(#:tests? #f ; no "check" target
1594 (string-append "prefix=" (assoc-ref %outputs "out")))
1596 (modify-phases %standard-phases
1597 (delete 'configure))))
1601 (supported-systems '("x86_64-linux"))
1602 (home-page "http://bowtie-bio.sourceforge.net/index.shtml")
1603 (synopsis "Fast aligner for short nucleotide sequence reads")
1605 "Bowtie is a fast, memory-efficient short read aligner. It aligns short
1606 DNA sequences (reads) to the human genome at a rate of over 25 million 35-bp
1607 reads per hour. Bowtie indexes the genome with a Burrows-Wheeler index to
1608 keep its memory footprint small: typically about 2.2 GB for the human
1609 genome (2.9 GB for paired-end).")
1610 (license license:artistic2.0)))
1612 (define-public tophat
1619 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1623 "19add02kv2xhd6ihd779dr7x35ggym3jqr0m5c4315i1yfb0p11p"))
1624 (modules '((guix build utils)))
1627 ;; Remove bundled SeqAn and samtools
1628 (delete-file-recursively "src/SeqAn-1.4.2")
1629 (delete-file-recursively "src/samtools-0.1.18")
1631 (build-system gnu-build-system)
1633 '(#:parallel-build? #f ; not supported
1635 (modify-phases %standard-phases
1636 (add-after 'unpack 'use-system-samtools
1637 (lambda* (#:key inputs #:allow-other-keys)
1638 (substitute* "src/Makefile.in"
1639 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1640 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1641 (("SAMPROG = samtools_0\\.1\\.18") "")
1642 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1643 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1644 (substitute* '("src/common.cpp"
1646 (("samtools_0.1.18") (which "samtools")))
1647 (substitute* '("src/common.h"
1648 "src/bam2fastx.cpp")
1649 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1650 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1651 (substitute* '("src/bwt_map.h"
1653 "src/align_status.h")
1654 (("#include <bam.h>") "#include <samtools/bam.h>")
1655 (("#include <sam.h>") "#include <samtools/sam.h>"))
1658 `(("gcc" ,gcc-5))) ;; doesn't build with later versions
1662 ("ncurses" ,ncurses)
1664 ("python" ,python-2)
1665 ("samtools" ,samtools-0.1)
1668 (home-page "https://ccb.jhu.edu/software/tophat/index.shtml")
1669 (synopsis "Spliced read mapper for RNA-Seq data")
1671 "TopHat is a fast splice junction mapper for nucleotide sequence
1672 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1673 mammalian-sized genomes using the ultra high-throughput short read
1674 aligner Bowtie, and then analyzes the mapping results to identify
1675 splice junctions between exons.")
1676 ;; TopHat is released under the Boost Software License, Version 1.0
1677 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1678 (license license:boost1.0)))
1687 "https://github.com/lh3/bwa/releases/download/v"
1688 version "/bwa-" version ".tar.bz2"))
1691 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1692 (build-system gnu-build-system)
1694 '(#:tests? #f ;no "check" target
1696 (modify-phases %standard-phases
1698 (lambda* (#:key outputs #:allow-other-keys)
1699 (let* ((out (assoc-ref outputs "out"))
1700 (bin (string-append out "/bin"))
1701 (lib (string-append out "/lib"))
1702 (doc (string-append out "/share/doc/bwa"))
1703 (man (string-append out "/share/man/man1")))
1704 (install-file "bwa" bin)
1705 (install-file "libbwa.a" lib)
1706 (install-file "README.md" doc)
1707 (install-file "bwa.1" man))
1709 ;; no "configure" script
1710 (delete 'configure))))
1711 (inputs `(("zlib" ,zlib)))
1712 ;; Non-portable SSE instructions are used so building fails on platforms
1713 ;; other than x86_64.
1714 (supported-systems '("x86_64-linux"))
1715 (home-page "http://bio-bwa.sourceforge.net/")
1716 (synopsis "Burrows-Wheeler sequence aligner")
1718 "BWA is a software package for mapping low-divergent sequences against a
1719 large reference genome, such as the human genome. It consists of three
1720 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1721 designed for Illumina sequence reads up to 100bp, while the rest two for
1722 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1723 features such as long-read support and split alignment, but BWA-MEM, which is
1724 the latest, is generally recommended for high-quality queries as it is faster
1725 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1726 70-100bp Illumina reads.")
1727 (license license:gpl3+)))
1729 (define-public bwa-pssm
1730 (package (inherit bwa)
1736 (url "https://github.com/pkerpedjiev/bwa-pssm.git")
1738 (file-name (git-file-name name version))
1741 "076c4q0cdqz8jgylb067y9zmvxglppnzi3qiscn0xiypgc6lgb5r"))))
1742 (build-system gnu-build-system)
1747 (home-page "http://bwa-pssm.binf.ku.dk/")
1748 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1750 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1751 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1752 existing aligners it is fast and sensitive. Unlike most other aligners,
1753 however, it is also adaptible in the sense that one can direct the alignment
1754 based on known biases within the data set. It is coded as a modification of
1755 the original BWA alignment program and shares the genome index structure as
1756 well as many of the command line options.")
1757 (license license:gpl3+)))
1759 (define-public bwa-meth
1766 (url "https://github.com/brentp/bwa-meth.git")
1767 (commit (string-append "v" version))))
1768 (file-name (git-file-name name version))
1771 "17j31i7zws5j7mhsq9x3qgkxly6mlmrgwhfq0qbflgxrmx04yaiz"))))
1772 (build-system python-build-system)
1775 (modify-phases %standard-phases
1776 (add-after 'unpack 'keep-references-to-bwa
1777 (lambda* (#:key inputs #:allow-other-keys)
1778 (substitute* "bwameth.py"
1779 (("bwa (mem|index)" _ command)
1780 (string-append (which "bwa") " " command))
1781 ;; There's an ill-advised check for "samtools" on PATH.
1787 `(("python-toolshed" ,python-toolshed)))
1788 (home-page "https://github.com/brentp/bwa-meth")
1789 (synopsis "Fast and accurante alignment of BS-Seq reads")
1791 "BWA-Meth works for single-end reads and for paired-end reads from the
1792 directional protocol (most common). It uses the method employed by
1793 methylcoder and Bismark of in silico conversion of all C's to T's in both
1794 reference and reads. It recovers the original read (needed to tabulate
1795 methylation) by attaching it as a comment which BWA appends as a tag to the
1796 read. It performs favorably to existing aligners gauged by number of on and
1797 off-target reads for a capture method that targets CpG-rich region.")
1798 (license license:expat)))
1800 (define-public python-bx-python
1802 (name "python-bx-python")
1806 (uri (pypi-uri "bx-python" version))
1809 "11kksg2rbzihpmcid823xvg42xi88m7sz58rzk29abybkxy0rszs"))))
1810 (build-system python-build-system)
1811 ;; Tests fail because test data are not included
1812 (arguments '(#:tests? #f))
1814 `(("python-numpy" ,python-numpy)
1815 ("python-six" ,python-six)))
1819 `(("python-lzo" ,python-lzo)
1820 ("python-nose" ,python-nose)
1821 ("python-cython" ,python-cython)))
1822 (home-page "https://github.com/bxlab/bx-python")
1823 (synopsis "Tools for manipulating biological data")
1825 "bx-python provides tools for manipulating biological data, particularly
1826 multiple sequence alignments.")
1827 (license license:expat)))
1829 (define-public python2-bx-python
1830 (package-with-python2 python-bx-python))
1832 (define-public python-pysam
1834 (name "python-pysam")
1838 ;; Test data is missing on PyPi.
1840 (url "https://github.com/pysam-developers/pysam.git")
1841 (commit (string-append "v" version))))
1842 (file-name (git-file-name name version))
1845 "1vj367w6xbn9bpmksm162l1aipf7cj97h1q83y7jcpm33ihwpf7x"))
1846 (modules '((guix build utils)))
1848 ;; Drop bundled htslib. TODO: Also remove samtools
1850 (delete-file-recursively "htslib")
1852 (build-system python-build-system)
1854 `(#:modules ((ice-9 ftw)
1856 (guix build python-build-system)
1859 (modify-phases %standard-phases
1860 (add-before 'build 'set-flags
1861 (lambda* (#:key inputs #:allow-other-keys)
1862 (setenv "HTSLIB_MODE" "external")
1863 (setenv "HTSLIB_LIBRARY_DIR"
1864 (string-append (assoc-ref inputs "htslib") "/lib"))
1865 (setenv "HTSLIB_INCLUDE_DIR"
1866 (string-append (assoc-ref inputs "htslib") "/include"))
1867 (setenv "LDFLAGS" "-lncurses")
1868 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1871 (lambda* (#:key inputs outputs #:allow-other-keys)
1872 ;; This file contains tests that require a connection to the
1874 (delete-file "tests/tabix_test.py")
1875 ;; FIXME: This test fails
1876 (delete-file "tests/AlignmentFile_test.py")
1877 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1878 (setenv "PYTHONPATH"
1880 (getenv "PYTHONPATH")
1881 ":" (getcwd) "/build/"
1882 (car (scandir "build"
1883 (negate (cut string-prefix? "." <>))))))
1884 ;; Step out of source dir so python does not import from CWD.
1885 (with-directory-excursion "tests"
1886 (setenv "HOME" "/tmp")
1887 (invoke "make" "-C" "pysam_data")
1888 (invoke "make" "-C" "cbcf_data")
1889 ;; Running nosetests without explicitly asking for a single
1890 ;; process leads to a crash. Running with multiple processes
1891 ;; fails because the tests are not designed to run in parallel.
1893 ;; FIXME: tests keep timing out on some systems.
1894 (invoke "nosetests" "-v" "--processes" "1")))))))
1896 `(("htslib" ,htslib))) ; Included from installed header files.
1898 `(("ncurses" ,ncurses)
1902 `(("python-cython" ,python-cython)
1903 ;; Dependencies below are are for tests only.
1904 ("samtools" ,samtools)
1905 ("bcftools" ,bcftools)
1906 ("python-nose" ,python-nose)))
1907 (home-page "https://github.com/pysam-developers/pysam")
1908 (synopsis "Python bindings to the SAMtools C API")
1910 "Pysam is a Python module for reading and manipulating files in the
1911 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1912 also includes an interface for tabix.")
1913 (license license:expat)))
1915 (define-public python2-pysam
1916 (package-with-python2 python-pysam))
1918 (define-public python-twobitreader
1920 (name "python-twobitreader")
1925 (url "https://github.com/benjschiller/twobitreader")
1927 (file-name (git-file-name name version))
1930 "1qbxvv1h58cismbk1anpjrkpghsaiy64a11ir3lhy6qch6xf8n62"))))
1931 (build-system python-build-system)
1932 ;; Tests are not included
1933 (arguments '(#:tests? #f))
1935 `(("python-sphinx" ,python-sphinx)))
1936 (home-page "https://github.com/benjschiller/twobitreader")
1937 (synopsis "Python library for reading .2bit files")
1939 "twobitreader is a Python library for reading .2bit files as used by the
1940 UCSC genome browser.")
1941 (license license:artistic2.0)))
1943 (define-public python2-twobitreader
1944 (package-with-python2 python-twobitreader))
1946 (define-public python-plastid
1948 (name "python-plastid")
1952 (uri (pypi-uri "plastid" version))
1955 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1956 (build-system python-build-system)
1958 ;; Some test files are not included.
1961 `(("python-numpy" ,python-numpy)
1962 ("python-scipy" ,python-scipy)
1963 ("python-pandas" ,python-pandas)
1964 ("python-pysam" ,python-pysam)
1965 ("python-matplotlib" ,python-matplotlib)
1966 ("python-biopython" ,python-biopython)
1967 ("python-twobitreader" ,python-twobitreader)
1968 ("python-termcolor" ,python-termcolor)))
1970 `(("python-cython" ,python-cython)
1971 ("python-nose" ,python-nose)))
1972 (home-page "https://github.com/joshuagryphon/plastid")
1973 (synopsis "Python library for genomic analysis")
1975 "plastid is a Python library for genomic analysis – in particular,
1976 high-throughput sequencing data – with an emphasis on simplicity.")
1977 (license license:bsd-3)))
1979 (define-public python2-plastid
1980 (package-with-python2 python-plastid))
1982 (define-public tetoolkit
1989 (url "https://github.com/mhammell-laboratory/tetoolkit.git")
1991 (file-name (git-file-name name version))
1994 "1yzi0kfpzip8zpjb82x1ik6h22yzfyjiz2dv85v6as2awwqvk807"))))
1995 (build-system python-build-system)
1997 `(#:python ,python-2 ; not guaranteed to work with Python 3
1999 (modify-phases %standard-phases
2000 (add-after 'unpack 'make-writable
2002 (for-each make-file-writable (find-files "."))
2004 (add-after 'unpack 'patch-invocations
2005 (lambda* (#:key inputs #:allow-other-keys)
2006 (substitute* '("bin/TEtranscripts"
2009 (string-append "'" (which "sort") " "))
2011 (string-append "'" (which "rm") " -f "))
2012 (("'Rscript'") (string-append "'" (which "Rscript") "'")))
2013 (substitute* "TEToolkit/IO/ReadInputs.py"
2014 (("BamToBED") (which "bamToBed")))
2015 (substitute* "TEToolkit/Normalization.py"
2017 (string-append "\"" (which "Rscript") "\"")))
2019 (add-after 'install 'wrap-program
2020 (lambda* (#:key outputs #:allow-other-keys)
2021 ;; Make sure the executables find R packages.
2022 (let ((out (assoc-ref outputs "out")))
2025 (wrap-program (string-append out "/bin/" script)
2026 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
2031 `(("coreutils" ,coreutils)
2032 ("bedtools" ,bedtools)
2033 ("python-argparse" ,python2-argparse)
2034 ("python-pysam" ,python2-pysam)
2035 ("r-minimal" ,r-minimal)
2036 ("r-deseq2" ,r-deseq2)))
2037 (home-page "https://github.com/mhammell-laboratory/tetoolkit")
2038 (synopsis "Transposable elements in differential enrichment analysis")
2040 "This is package for including transposable elements in differential
2041 enrichment analysis of sequencing datasets. TEtranscripts and TEcount take
2042 RNA-seq (and similar data) and annotates reads to both genes and transposable
2043 elements. TEtranscripts then performs differential analysis using DESeq2.
2044 Note that TEtranscripts and TEcount rely on specially curated GTF files, which
2045 are not included due to their size.")
2046 (license license:gpl3+)))
2048 (define-public cd-hit
2054 (uri (string-append "https://github.com/weizhongli/cdhit"
2055 "/releases/download/V" version
2057 "-2017-0621-source.tar.gz"))
2060 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
2061 (build-system gnu-build-system)
2063 `(#:tests? #f ; there are no tests
2065 ;; Executables are copied directly to the PREFIX.
2066 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin")
2067 ;; Support longer sequences (e.g. Pacbio sequences)
2070 (modify-phases %standard-phases
2071 ;; No "configure" script
2073 ;; Remove sources of non-determinism
2074 (add-after 'unpack 'be-timeless
2076 (substitute* "cdhit-utility.c++"
2077 ((" \\(built on \" __DATE__ \"\\)") ""))
2078 (substitute* "cdhit-common.c++"
2079 (("__DATE__") "\"0\"")
2080 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
2082 ;; The "install" target does not create the target directory.
2083 (add-before 'install 'create-target-dir
2084 (lambda* (#:key outputs #:allow-other-keys)
2085 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
2089 (home-page "http://weizhongli-lab.org/cd-hit/")
2090 (synopsis "Cluster and compare protein or nucleotide sequences")
2092 "CD-HIT is a program for clustering and comparing protein or nucleotide
2093 sequences. CD-HIT is designed to be fast and handle extremely large
2095 ;; The manual says: "It can be copied under the GNU General Public License
2096 ;; version 2 (GPLv2)."
2097 (license license:gpl2)))
2099 (define-public clipper
2106 (url "https://github.com/YeoLab/clipper.git")
2108 (file-name (git-file-name name version))
2111 "0fja1rj84wp9vpj8rxpj3n8zqzcqq454m904yp9as1w4phccirjb"))
2112 (modules '((guix build utils)))
2115 ;; remove unnecessary setup dependency
2116 (substitute* "setup.py"
2117 (("setup_requires = .*") ""))
2119 (build-system python-build-system)
2121 `(#:python ,python-2 ; only Python 2 is supported
2123 (modify-phases %standard-phases
2124 ;; This is fixed in upstream commit
2125 ;; f6c2990198f906bf97730d95695b4bd5a6d01ddb.
2126 (add-after 'unpack 'fix-typo
2128 (substitute* "clipper/src/readsToWiggle.pyx"
2132 `(("htseq" ,python2-htseq)
2133 ("python-pybedtools" ,python2-pybedtools)
2134 ("python-cython" ,python2-cython)
2135 ("python-scikit-learn" ,python2-scikit-learn)
2136 ("python-matplotlib" ,python2-matplotlib)
2137 ("python-pandas" ,python2-pandas)
2138 ("python-pysam" ,python2-pysam)
2139 ("python-numpy" ,python2-numpy)
2140 ("python-scipy" ,python2-scipy)))
2142 `(("python-mock" ,python2-mock) ; for tests
2143 ("python-nose" ,python2-nose) ; for tests
2144 ("python-pytz" ,python2-pytz))) ; for tests
2145 (home-page "https://github.com/YeoLab/clipper")
2146 (synopsis "CLIP peak enrichment recognition")
2148 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
2149 (license license:gpl2)))
2151 (define-public codingquarry
2153 (name "codingquarry")
2158 "mirror://sourceforge/codingquarry/CodingQuarry_v"
2162 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
2163 (build-system gnu-build-system)
2165 '(#:tests? #f ; no "check" target
2167 (modify-phases %standard-phases
2170 (lambda* (#:key outputs #:allow-other-keys)
2171 (let* ((out (assoc-ref outputs "out"))
2172 (bin (string-append out "/bin"))
2173 (doc (string-append out "/share/doc/codingquarry")))
2174 (install-file "INSTRUCTIONS.pdf" doc)
2175 (copy-recursively "QuarryFiles"
2176 (string-append out "/QuarryFiles"))
2177 (install-file "CodingQuarry" bin)
2178 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin))
2180 (inputs `(("openmpi" ,openmpi)))
2181 (native-search-paths
2182 (list (search-path-specification
2183 (variable "QUARRY_PATH")
2184 (files '("QuarryFiles")))))
2185 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
2186 (synopsis "Fungal gene predictor")
2187 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
2188 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
2189 (home-page "https://sourceforge.net/projects/codingquarry/")
2190 (license license:gpl3+)))
2192 (define-public couger
2199 "http://couger.oit.duke.edu/static/assets/COUGER"
2203 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
2204 (build-system gnu-build-system)
2208 (modify-phases %standard-phases
2213 (lambda* (#:key outputs #:allow-other-keys)
2214 (let* ((out (assoc-ref outputs "out"))
2215 (bin (string-append out "/bin")))
2216 (copy-recursively "src" (string-append out "/src"))
2218 ;; Add "src" directory to module lookup path.
2219 (substitute* "couger"
2221 (string-append "import sys\nsys.path.append(\""
2222 out "\")\nfrom argparse")))
2223 (install-file "couger" bin))
2226 'install 'wrap-program
2227 (lambda* (#:key inputs outputs #:allow-other-keys)
2228 ;; Make sure 'couger' runs with the correct PYTHONPATH.
2229 (let* ((out (assoc-ref outputs "out"))
2230 (path (getenv "PYTHONPATH")))
2231 (wrap-program (string-append out "/bin/couger")
2232 `("PYTHONPATH" ":" prefix (,path))))
2235 `(("python" ,python-2)
2236 ("python2-pillow" ,python2-pillow)
2237 ("python2-numpy" ,python2-numpy)
2238 ("python2-scipy" ,python2-scipy)
2239 ("python2-matplotlib" ,python2-matplotlib)))
2241 `(("r-minimal" ,r-minimal)
2243 ("randomjungle" ,randomjungle)))
2245 `(("unzip" ,unzip)))
2246 (home-page "http://couger.oit.duke.edu")
2247 (synopsis "Identify co-factors in sets of genomic regions")
2249 "COUGER can be applied to any two sets of genomic regions bound by
2250 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
2251 putative co-factors that provide specificity to each TF. The framework
2252 determines the genomic targets uniquely-bound by each TF, and identifies a
2253 small set of co-factors that best explain the in vivo binding differences
2254 between the two TFs.
2256 COUGER uses classification algorithms (support vector machines and random
2257 forests) with features that reflect the DNA binding specificities of putative
2258 co-factors. The features are generated either from high-throughput TF-DNA
2259 binding data (from protein binding microarray experiments), or from large
2260 collections of DNA motifs.")
2261 (license license:gpl3+)))
2263 (define-public clustal-omega
2265 (name "clustal-omega")
2269 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
2273 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
2274 (build-system gnu-build-system)
2276 `(("argtable" ,argtable)))
2277 (home-page "http://www.clustal.org/omega/")
2278 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
2280 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
2281 program for protein and DNA/RNA. It produces high quality MSAs and is capable
2282 of handling data-sets of hundreds of thousands of sequences in reasonable
2284 (license license:gpl2+)))
2286 (define-public crossmap
2292 (uri (pypi-uri "CrossMap" version))
2295 "1sb2f2qbxya4fzw3yjl09vbrs8vfmw22zrygrvz004sf9gb1vkan"))))
2296 (build-system python-build-system)
2298 `(("python-bx-python" ,python-bx-python)
2299 ("python-numpy" ,python-numpy)
2300 ("python-pybigwig" ,python-pybigwig)
2301 ("python-pysam" ,python-pysam)
2304 `(("python-cython" ,python-cython)
2305 ("python-nose" ,python-nose)))
2306 (home-page "http://crossmap.sourceforge.net/")
2307 (synopsis "Convert genome coordinates between assemblies")
2309 "CrossMap is a program for conversion of genome coordinates or annotation
2310 files between different genome assemblies. It supports most commonly used
2311 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
2312 (license license:gpl2+)))
2314 (define-public python-dnaio
2316 (name "python-dnaio")
2321 (uri (pypi-uri "dnaio" version))
2324 "0f16m7hdlm0fz1n7y5asy0v9ghyrq17ni1p9iybq22ddzyd49r27"))))
2325 (build-system python-build-system)
2327 `(("python-cython" ,python-cython)
2328 ("python-pytest" ,python-pytest)
2329 ("python-xopen" ,python-xopen)))
2330 (home-page "https://github.com/marcelm/dnaio/")
2331 (synopsis "Read FASTA and FASTQ files efficiently")
2333 "dnaio is a Python library for fast parsing of FASTQ and also FASTA
2334 files. The code was previously part of the cutadapt tool.")
2335 (license license:expat)))
2337 (define-public cutadapt
2343 (uri (pypi-uri "cutadapt" version))
2346 "1vqmsfkm6llxzmsz9wcfcvzx9a9f8iabvwik2rbyn7nc4wm25z89"))))
2347 (build-system python-build-system)
2349 `(("python-dnaio" ,python-dnaio)
2350 ("python-xopen" ,python-xopen)))
2352 `(("python-cython" ,python-cython)
2353 ("python-pytest" ,python-pytest)
2354 ("python-setuptools-scm" ,python-setuptools-scm)))
2355 (home-page "https://cutadapt.readthedocs.io/en/stable/")
2356 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
2358 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
2359 other types of unwanted sequence from high-throughput sequencing reads.")
2360 (license license:expat)))
2362 (define-public libbigwig
2369 (url "https://github.com/dpryan79/libBigWig.git")
2371 (file-name (git-file-name name version))
2374 "09693dmf1scdac5pyq6qyn8b4mcipvnmc370k9a5z41z81m3dcsj"))))
2375 (build-system gnu-build-system)
2377 `(#:test-target "test"
2378 #:tests? #f ; tests require access to the web
2381 (string-append "prefix=" (assoc-ref %outputs "out")))
2383 (modify-phases %standard-phases
2384 (delete 'configure))))
2389 `(("doxygen" ,doxygen)
2391 ("python" ,python-2)))
2392 (home-page "https://github.com/dpryan79/libBigWig")
2393 (synopsis "C library for handling bigWig files")
2395 "This package provides a C library for parsing local and remote BigWig
2397 (license license:expat)))
2399 (define-public python-pybigwig
2401 (name "python-pybigwig")
2405 (uri (pypi-uri "pyBigWig" version))
2408 "157x6v48y299zm382krf1dw08fdxg95im8lnabhp5vc94s04zxj1"))
2409 (modules '((guix build utils)))
2412 ;; Delete bundled libBigWig sources
2413 (delete-file-recursively "libBigWig")
2415 (build-system python-build-system)
2418 (modify-phases %standard-phases
2419 (add-after 'unpack 'link-with-libBigWig
2420 (lambda* (#:key inputs #:allow-other-keys)
2421 (substitute* "setup.py"
2422 (("libs=\\[") "libs=[\"BigWig\", "))
2425 `(("python-numpy" ,python-numpy)))
2427 `(("libbigwig" ,libbigwig)
2430 (home-page "https://github.com/dpryan79/pyBigWig")
2431 (synopsis "Access bigWig files in Python using libBigWig")
2433 "This package provides Python bindings to the libBigWig library for
2434 accessing bigWig files.")
2435 (license license:expat)))
2437 (define-public python2-pybigwig
2438 (package-with-python2 python-pybigwig))
2440 (define-public python-dendropy
2442 (name "python-dendropy")
2447 ;; Source from GitHub so that tests are included.
2449 (url "https://github.com/jeetsukumaran/DendroPy.git")
2450 (commit (string-append "v" version))))
2451 (file-name (git-file-name name version))
2454 "097hfyv2kaf4x92i4rjx0paw2cncxap48qivv8zxng4z7nhid0x9"))))
2455 (build-system python-build-system)
2456 (home-page "https://dendropy.org/")
2457 (synopsis "Library for phylogenetics and phylogenetic computing")
2459 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
2460 writing, simulation, processing and manipulation of phylogenetic
2461 trees (phylogenies) and characters.")
2462 (license license:bsd-3)))
2464 (define-public python2-dendropy
2465 (let ((base (package-with-python2 python-dendropy)))
2470 (modify-phases %standard-phases
2471 (add-after 'unpack 'remove-failing-test
2473 ;; This test fails when the full test suite is run, as documented
2474 ;; at https://github.com/jeetsukumaran/DendroPy/issues/74
2475 (substitute* "tests/test_dataio_nexml_reader_tree_list.py"
2476 (("test_collection_comments_and_annotations")
2477 "do_not_test_collection_comments_and_annotations"))
2479 ,@(package-arguments base))))))
2481 (define-public python-py2bit
2483 (name "python-py2bit")
2488 (uri (pypi-uri "py2bit" version))
2491 "1vw2nvw1yrl7ikkqsqs1pg239yr5nspvd969r1x9arms1k25a1a5"))))
2492 (build-system python-build-system)
2493 (home-page "https://github.com/dpryan79/py2bit")
2494 (synopsis "Access 2bit files using lib2bit")
2496 "This package provides Python bindings for lib2bit to access 2bit files
2498 (license license:expat)))
2500 (define-public deeptools
2507 (url "https://github.com/deeptools/deepTools.git")
2509 (file-name (git-file-name name version))
2512 "1vggnf52g6q2vifdl4cyi7s2fnfqq0ky2zrkj5zv2qfzsc3p3siw"))))
2513 (build-system python-build-system)
2516 (modify-phases %standard-phases
2517 ;; This phase fails, but it's not needed.
2518 (delete 'reset-gzip-timestamps))))
2520 `(("python-plotly" ,python-plotly)
2521 ("python-scipy" ,python-scipy)
2522 ("python-numpy" ,python-numpy)
2523 ("python-numpydoc" ,python-numpydoc)
2524 ("python-matplotlib" ,python-matplotlib)
2525 ("python-pysam" ,python-pysam)
2526 ("python-py2bit" ,python-py2bit)
2527 ("python-pybigwig" ,python-pybigwig)))
2529 `(("python-mock" ,python-mock) ;for tests
2530 ("python-nose" ,python-nose) ;for tests
2531 ("python-pytz" ,python-pytz))) ;for tests
2532 (home-page "https://github.com/deeptools/deepTools")
2533 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2535 "DeepTools addresses the challenge of handling the large amounts of data
2536 that are now routinely generated from DNA sequencing centers. To do so,
2537 deepTools contains useful modules to process the mapped reads data to create
2538 coverage files in standard bedGraph and bigWig file formats. By doing so,
2539 deepTools allows the creation of normalized coverage files or the comparison
2540 between two files (for example, treatment and control). Finally, using such
2541 normalized and standardized files, multiple visualizations can be created to
2542 identify enrichments with functional annotations of the genome.")
2543 (license license:gpl3+)))
2545 (define-public delly
2552 (url "https://github.com/dellytools/delly.git")
2553 (commit (string-append "v" version))))
2554 (file-name (git-file-name name version))
2556 (base32 "034jqsxswy9gqdh2zkgc1js99qkv75ks4xvzgmh0284sraagv61z"))
2557 (modules '((guix build utils)))
2560 (delete-file-recursively "src/htslib")
2562 (build-system gnu-build-system)
2564 `(#:tests? #f ; There are no tests to run.
2566 (list "PARALLEL=1" ; Allow parallel execution at run-time.
2567 (string-append "prefix=" (assoc-ref %outputs "out")))
2569 (modify-phases %standard-phases
2570 (delete 'configure) ; There is no configure phase.
2571 (add-after 'install 'install-templates
2572 (lambda* (#:key outputs #:allow-other-keys)
2573 (let ((templates (string-append (assoc-ref outputs "out")
2574 "/share/delly/templates")))
2576 (copy-recursively "excludeTemplates" templates)
2583 (home-page "https://github.com/dellytools/delly")
2584 (synopsis "Integrated structural variant prediction method")
2585 (description "Delly is an integrated structural variant prediction method
2586 that can discover and genotype deletions, tandem duplications, inversions and
2587 translocations at single-nucleotide resolution in short-read massively parallel
2588 sequencing data. It uses paired-ends and split-reads to sensitively and
2589 accurately delineate genomic rearrangements throughout the genome.")
2590 (license license:gpl3+)))
2592 (define-public diamond
2599 (url "https://github.com/bbuchfink/diamond.git")
2600 (commit (string-append "v" version))))
2601 (file-name (git-file-name name version))
2604 "0k6f3kb6cniw11xw6763kkbs1sl0yack7xsy7q5fl5v170ssphq4"))))
2605 (build-system cmake-build-system)
2607 '(#:tests? #f ; no "check" target
2609 (modify-phases %standard-phases
2610 (add-after 'unpack 'remove-native-compilation
2612 (substitute* "CMakeLists.txt" (("-march=native") ""))
2616 (home-page "https://github.com/bbuchfink/diamond")
2617 (synopsis "Accelerated BLAST compatible local sequence aligner")
2619 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2620 translated DNA query sequences against a protein reference database (BLASTP
2621 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2622 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2623 data and settings.")
2624 (license license:agpl3+)))
2626 (define-public discrover
2634 (url "https://github.com/maaskola/discrover.git")
2636 (file-name (git-file-name name version))
2639 "173fwi2vb6a5kp406hm3jj6j7v4whww796f2qcygp4rpvamh307y"))))
2640 (build-system cmake-build-system)
2642 `(#:tests? #f ; there are no tests
2644 (modify-phases %standard-phases
2645 (add-after 'unpack 'fix-latex-errors
2647 (with-fluids ((%default-port-encoding #f))
2648 (substitute* "doc/references.bib"
2649 (("\\{S\\}illanp[^,]+,")
2650 "{S}illanp{\\\"a}{\\\"a},")))
2651 ;; XXX: I just can't get pdflatex to not complain about these
2652 ;; characters. They end up in the manual via the generated
2653 ;; discrover-cli-help.txt.
2654 (substitute* "src/hmm/cli.cpp"
2658 ;; This seems to be a syntax error.
2659 (substitute* "doc/discrover-manual.tex"
2660 (("theverbbox\\[t\\]") "theverbbox"))
2662 (add-after 'unpack 'add-missing-includes
2664 (substitute* "src/executioninformation.hpp"
2665 (("#define EXECUTIONINFORMATION_HPP" line)
2666 (string-append line "\n#include <random>")))
2667 (substitute* "src/plasma/fasta.hpp"
2668 (("#define FASTA_HPP" line)
2669 (string-append line "\n#include <random>")))
2671 ;; FIXME: this is needed because we're using texlive-union, which
2672 ;; doesn't handle fonts correctly. It expects to be able to generate
2673 ;; fonts in the home directory.
2674 (add-before 'build 'setenv-HOME
2675 (lambda _ (setenv "HOME" "/tmp") #t)))))
2679 ("rmath-standalone" ,rmath-standalone)))
2681 `(("texlive" ,(texlive-union (list texlive-fonts-cm
2682 texlive-fonts-amsfonts
2685 texlive-latex-examplep
2686 texlive-latex-hyperref
2688 texlive-latex-natbib
2689 texlive-bibtex ; style files used by natbib
2690 texlive-latex-pgf ; tikz
2691 texlive-latex-verbatimbox)))
2692 ("imagemagick" ,imagemagick)))
2693 (home-page "https://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2694 (synopsis "Discover discriminative nucleotide sequence motifs")
2695 (description "Discrover is a motif discovery method to find binding sites
2696 of nucleic acid binding proteins.")
2697 (license license:gpl3+)))
2699 (define-public eigensoft
2707 (url "https://github.com/DReichLab/EIG.git")
2708 (commit (string-append "v" version))))
2709 (file-name (git-file-name name version))
2712 "1c141fqvhnzibmnf22sv23vbmzm20kjjyrib44cfh75wyndp2d9k"))
2713 (modules '((guix build utils)))
2714 ;; Remove pre-built binaries.
2716 (delete-file-recursively "bin")
2719 (build-system gnu-build-system)
2721 `(#:tests? #f ; There are no tests.
2722 #:make-flags '("CC=gcc")
2724 (modify-phases %standard-phases
2725 ;; There is no configure phase, but the Makefile is in a
2728 (lambda _ (chdir "src") #t))
2729 ;; The provided install target only copies executables to
2730 ;; the "bin" directory in the build root.
2731 (add-after 'install 'actually-install
2732 (lambda* (#:key outputs #:allow-other-keys)
2733 (let* ((out (assoc-ref outputs "out"))
2734 (bin (string-append out "/bin")))
2735 (for-each (lambda (file)
2736 (install-file file bin))
2737 (find-files "../bin" ".*"))
2742 ("openblas" ,openblas)
2744 ("gfortran" ,gfortran "lib")))
2745 (home-page "https://github.com/DReichLab/EIG")
2746 (synopsis "Tools for population genetics")
2747 (description "The EIGENSOFT package provides tools for population
2748 genetics and stratification correction. EIGENSOFT implements methods commonly
2749 used in population genetics analyses such as PCA, computation of Tracy-Widom
2750 statistics, and finding related individuals in structured populations. It
2751 comes with a built-in plotting script and supports multiple file formats and
2752 quantitative phenotypes.")
2753 ;; The license of the eigensoft tools is Expat, but since it's
2754 ;; linking with the GNU Scientific Library (GSL) the effective
2755 ;; license is the GPL.
2756 (license license:gpl3+)))
2758 (define-public edirect
2761 (version "13.3.20200128")
2764 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect"
2765 "/versions/" version
2766 "/edirect-" version ".tar.gz"))
2769 "093zp7klv81ph0y8mm8d78a9hnpfxbv2kdym70gzdf3vz176rw33"))
2770 (modules '((guix build utils)))
2772 '(begin (delete-file "Mozilla-CA.tar.gz")
2773 (substitute* "rchive.go"
2774 ;; This go library does not have any license.
2775 (("github.com/fiam/gounidecode/unidecode")
2776 "golang.org/rainycape/unidecode"))
2778 (build-system perl-build-system)
2781 (modify-phases %standard-phases
2784 (delete 'check) ; simple check after install
2785 (add-after 'unpack 'patch-programs
2786 (lambda* (#:key inputs #:allow-other-keys)
2787 ;; Ignore errors about missing xtract.Linux and rchive.Linux.
2788 (substitute* "pm-refresh"
2789 (("cat \\\"\\$target")
2790 "grep ^[[:digit:]] \"$target"))
2793 (lambda* (#:key inputs outputs #:allow-other-keys)
2794 (let ((bin (string-append (assoc-ref outputs "out") "/bin"))
2795 (edirect-go (assoc-ref inputs "edirect-go-programs")))
2798 (install-file file bin))
2799 '("archive-pubmed" "asp-cp" "asp-ls" "download-ncbi-data"
2800 "download-pubmed" "edirect.pl" "efetch" "epost" "esearch"
2801 "fetch-pubmed" "ftp-cp" "ftp-ls" "has-asp" "index-pubmed"
2802 "pm-prepare" "pm-refresh" "pm-stash" "pm-collect"
2803 "pm-index" "pm-invert" "pm-merge" "pm-promote"))
2804 (symlink (string-append edirect-go "/bin/xtract.Linux")
2805 (string-append bin "/xtract"))
2806 (symlink (string-append edirect-go "/bin/rchive.Linux")
2807 (string-append bin "/rchive")))
2809 (add-after 'install 'wrap-program
2810 (lambda* (#:key outputs #:allow-other-keys)
2811 ;; Make sure everything can run in a pure environment.
2812 (let ((out (assoc-ref outputs "out"))
2813 (path (getenv "PERL5LIB")))
2817 `("PERL5LIB" ":" prefix (,path)))
2819 `("PATH" ":" prefix (,(string-append out "/bin")
2820 ,(dirname (which "sed"))
2821 ,(dirname (which "gzip"))
2822 ,(dirname (which "grep"))
2823 ,(dirname (which "perl"))
2824 ,(dirname (which "uname"))))))
2825 (find-files out ".")))
2827 (add-after 'wrap-program 'check
2828 (lambda* (#:key outputs #:allow-other-keys)
2829 (invoke (string-append (assoc-ref outputs "out")
2834 `(("edirect-go-programs" ,edirect-go-programs)
2835 ("perl-html-parser" ,perl-html-parser)
2836 ("perl-encode-locale" ,perl-encode-locale)
2837 ("perl-file-listing" ,perl-file-listing)
2838 ("perl-html-tagset" ,perl-html-tagset)
2839 ("perl-html-tree" ,perl-html-tree)
2840 ("perl-http-cookies" ,perl-http-cookies)
2841 ("perl-http-date" ,perl-http-date)
2842 ("perl-http-message" ,perl-http-message)
2843 ("perl-http-negotiate" ,perl-http-negotiate)
2844 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2845 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2846 ("perl-net-http" ,perl-net-http)
2847 ("perl-uri" ,perl-uri)
2848 ("perl-www-robotrules" ,perl-www-robotrules)
2849 ("perl-xml-simple" ,perl-xml-simple)
2851 (home-page "https://www.ncbi.nlm.nih.gov/books/NBK179288/")
2852 (synopsis "Tools for accessing the NCBI's set of databases")
2854 "Entrez Direct (EDirect) is a method for accessing the National Center
2855 for Biotechnology Information's (NCBI) set of interconnected
2856 databases (publication, sequence, structure, gene, variation, expression,
2857 etc.) from a terminal. Functions take search terms from command-line
2858 arguments. Individual operations are combined to build multi-step queries.
2859 Record retrieval and formatting normally complete the process.
2861 EDirect also provides an argument-driven function that simplifies the
2862 extraction of data from document summaries or other results that are returned
2863 in structured XML format. This can eliminate the need for writing custom
2864 software to answer ad hoc questions.")
2865 (native-search-paths
2866 ;; Ideally this should be set for LWP somewhere.
2867 (list (search-path-specification
2868 (variable "PERL_LWP_SSL_CA_FILE")
2869 (file-type 'regular)
2871 (files '("/etc/ssl/certs/ca-certificates.crt")))))
2872 (license license:public-domain)))
2874 (define-public edirect-go-programs
2877 (name "edirect-go-programs")
2878 (build-system go-build-system)
2880 `(#:install-source? #f
2881 #:tests? #f ; No tests.
2882 #:import-path "ncbi.nlm.nih.gov/entrez/edirect"
2884 (modify-phases %standard-phases
2886 (lambda* (#:key import-path #:allow-other-keys)
2887 (with-directory-excursion (string-append "src/" import-path)
2888 (invoke "go" "build" "-v" "-x" "j2x.go")
2889 (invoke "go" "build" "-v" "-x" "t2x.go")
2890 (invoke "go" "build" "-v" "-x" "-o"
2891 "xtract.Linux" "xtract.go" "common.go")
2892 (invoke "go" "build" "-v" "-x" "-o"
2893 "rchive.Linux" "rchive.go" "common.go")
2894 (invoke "go" "build" "-v" "-x" "-o" "symbols.Linux" "s2p.go"))))
2896 (lambda* (#:key outputs import-path #:allow-other-keys)
2897 (let ((dest (string-append (assoc-ref outputs "out") "/bin"))
2898 (source (string-append "src/" import-path "/")))
2899 (for-each (lambda (file)
2900 (format #t "installing ~a~%" file)
2901 (install-file (string-append source file) dest))
2902 '("j2x" "t2x" "symbols.Linux" "xtract.Linux" "rchive.Linux"))
2905 (propagated-inputs '())
2907 `(("go-github-com-fatih-color" ,go-github-com-fatih-color)
2908 ("go-github-com-fogleman-gg" ,go-github-com-fogleman-gg)
2909 ("go-github-com-gedex-inflector" ,go-github-com-gedex-inflector)
2910 ("go-github-com-golang-freetype" ,go-github-com-golang-freetype)
2911 ("go-github-com-klauspost-cpuid" ,go-github-com-klauspost-cpuid)
2912 ("go-github-com-pbnjay-memory" ,go-github-com-pbnjay-memory)
2913 ("go-github-com-surgebase-porter2" ,go-github-com-surgebase-porter2)
2914 ("go-golang-org-rainycape-unidecode" ,go-golang-org-rainycape-unidecode)
2915 ("go-golang-org-x-image" ,go-golang-org-x-image)
2916 ("go-golang-org-x-text" ,go-golang-org-x-text)))))
2918 (define-public exonerate
2927 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2928 "exonerate-" version ".tar.gz"))
2931 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2932 (build-system gnu-build-system)
2934 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2936 `(("pkg-config" ,pkg-config)))
2940 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2941 (synopsis "Generic tool for biological sequence alignment")
2943 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2944 the alignment of sequences using a many alignment models, either exhaustive
2945 dynamic programming or a variety of heuristics.")
2946 (license license:gpl3)))
2948 (define-public express
2956 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2957 version "/express-" version "-src.tgz"))
2960 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2961 (build-system cmake-build-system)
2963 `(#:tests? #f ;no "check" target
2965 (modify-phases %standard-phases
2966 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2967 (lambda* (#:key inputs #:allow-other-keys)
2968 (substitute* "CMakeLists.txt"
2969 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2970 "set(Boost_USE_STATIC_LIBS OFF)")
2971 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2972 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2973 (substitute* "src/CMakeLists.txt"
2974 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2975 (string-append (assoc-ref inputs "bamtools") "/lib"))
2976 (("libprotobuf.a") "libprotobuf.so"))
2980 ("bamtools" ,bamtools)
2981 ("protobuf" ,protobuf)
2983 (home-page "http://bio.math.berkeley.edu/eXpress")
2984 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2986 "eXpress is a streaming tool for quantifying the abundances of a set of
2987 target sequences from sampled subsequences. Example applications include
2988 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2989 analysis (from RNA-Seq), transcription factor binding quantification in
2990 ChIP-Seq, and analysis of metagenomic data.")
2991 (license license:artistic2.0)))
2993 (define-public express-beta-diversity
2995 (name "express-beta-diversity")
3000 (url "https://github.com/dparks1134/ExpressBetaDiversity.git")
3001 (commit (string-append "v" version))))
3002 (file-name (git-file-name name version))
3005 "0s0yzg5c21349rh7x4w9266jsvnp7j1hp9cf8sk32hz8nvrj745x"))))
3006 (build-system gnu-build-system)
3009 (modify-phases %standard-phases
3011 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
3013 (lambda _ (invoke "../bin/ExpressBetaDiversity" "-u") #t))
3015 (lambda* (#:key outputs #:allow-other-keys)
3016 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3017 (install-file "../scripts/convertToEBD.py" bin)
3018 (install-file "../bin/ExpressBetaDiversity" bin)
3021 `(("python" ,python-2)))
3022 (home-page "https://github.com/dparks1134/ExpressBetaDiversity")
3023 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
3025 "Express Beta Diversity (EBD) calculates ecological beta diversity
3026 (dissimilarity) measures between biological communities. EBD implements a
3027 variety of diversity measures including those that make use of phylogenetic
3028 similarity of community members.")
3029 (license license:gpl3+)))
3031 (define-public fasttree
3038 "http://www.microbesonline.org/fasttree/FastTree-"
3042 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
3043 (build-system gnu-build-system)
3045 `(#:tests? #f ; no "check" target
3047 (modify-phases %standard-phases
3051 (lambda* (#:key source #:allow-other-keys)
3054 "-finline-functions"
3065 "-finline-functions"
3074 (lambda* (#:key outputs #:allow-other-keys)
3075 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
3076 (install-file "FastTree" bin)
3077 (install-file "FastTreeMP" bin)
3079 (home-page "http://www.microbesonline.org/fasttree")
3080 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
3082 "FastTree can handle alignments with up to a million of sequences in a
3083 reasonable amount of time and memory. For large alignments, FastTree is
3084 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
3085 (license license:gpl2+)))
3087 (define-public fastx-toolkit
3089 (name "fastx-toolkit")
3095 "https://github.com/agordon/fastx_toolkit/releases/download/"
3096 version "/fastx_toolkit-" version ".tar.bz2"))
3099 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
3100 (build-system gnu-build-system)
3102 `(("libgtextutils" ,libgtextutils)))
3104 `(("gcc" ,gcc-6) ;; doesn't build with later versions
3105 ("pkg-config" ,pkg-config)))
3106 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
3107 (synopsis "Tools for FASTA/FASTQ file preprocessing")
3109 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
3110 FASTA/FASTQ files preprocessing.
3112 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
3113 containing multiple short-reads sequences. The main processing of such
3114 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
3115 is sometimes more productive to preprocess the files before mapping the
3116 sequences to the genome---manipulating the sequences to produce better mapping
3117 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
3118 (license license:agpl3+)))
3120 (define-public flexbar
3127 (url "https://github.com/seqan/flexbar.git")
3128 (commit (string-append "v" version))))
3129 (file-name (git-file-name name version))
3132 "1pq9sxvdnldl14libk234m72dqhwgzs3acgl943wchwdqlcsi5r2"))))
3133 (build-system cmake-build-system)
3136 (modify-phases %standard-phases
3137 (add-after 'unpack 'do-not-tune-to-CPU
3139 (substitute* "src/CMakeLists.txt"
3140 ((" -march=native") ""))
3143 (lambda* (#:key outputs #:allow-other-keys)
3144 (setenv "PATH" (string-append (getcwd) ":" (getenv "PATH")))
3145 (with-directory-excursion "../source/test"
3146 (invoke "bash" "flexbar_test.sh"))
3149 (lambda* (#:key outputs #:allow-other-keys)
3150 (let* ((out (string-append (assoc-ref outputs "out")))
3151 (bin (string-append out "/bin/")))
3152 (install-file "flexbar" bin))
3158 `(("pkg-config" ,pkg-config)
3160 (home-page "https://github.com/seqan/flexbar")
3161 (synopsis "Barcode and adapter removal tool for sequencing platforms")
3163 "Flexbar preprocesses high-throughput nucleotide sequencing data
3164 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
3165 Moreover, trimming and filtering features are provided. Flexbar increases
3166 read mapping rates and improves genome and transcriptome assemblies. It
3167 supports next-generation sequencing data in fasta/q and csfasta/q format from
3168 Illumina, Roche 454, and the SOLiD platform.")
3169 (license license:bsd-3)))
3171 (define-public fraggenescan
3173 (name "fraggenescan")
3179 (string-append "mirror://sourceforge/fraggenescan/"
3180 "FragGeneScan" version ".tar.gz"))
3182 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
3183 (build-system gnu-build-system)
3186 (modify-phases %standard-phases
3188 (add-before 'build 'patch-paths
3189 (lambda* (#:key outputs #:allow-other-keys)
3190 (let* ((out (string-append (assoc-ref outputs "out")))
3191 (share (string-append out "/share/fraggenescan/")))
3192 (substitute* "run_FragGeneScan.pl"
3194 (string-append "system(\"" (which "rm")))
3196 (string-append "system(\"" (which "mv")))
3197 (("\\\"awk") (string-append "\"" (which "awk")))
3198 ;; This script and other programs expect the training files
3199 ;; to be in the non-standard location bin/train/XXX. Change
3200 ;; this to be share/fraggenescan/train/XXX instead.
3201 (("^\\$train.file = \\$dir.*")
3202 (string-append "$train_file = \""
3204 "train/\".$FGS_train_file;")))
3205 (substitute* "run_hmm.c"
3206 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
3207 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
3211 (invoke "make" "clean")
3212 (invoke "make" "fgs")
3215 (lambda* (#:key outputs #:allow-other-keys)
3216 (let* ((out (string-append (assoc-ref outputs "out")))
3217 (bin (string-append out "/bin/"))
3218 (share (string-append out "/share/fraggenescan/train")))
3219 (install-file "run_FragGeneScan.pl" bin)
3220 (install-file "FragGeneScan" bin)
3221 (copy-recursively "train" share))
3224 (add-after 'install 'post-install-check
3225 ;; In lieu of 'make check', run one of the examples and check the
3226 ;; output files gets created.
3227 (lambda* (#:key outputs #:allow-other-keys)
3228 (let* ((out (string-append (assoc-ref outputs "out")))
3229 (bin (string-append out "/bin/"))
3230 (frag (string-append bin "run_FragGeneScan.pl")))
3231 ;; Test complete genome.
3233 "-genome=./example/NC_000913.fna"
3237 (unless (and (file-exists? "test2.faa")
3238 (file-exists? "test2.ffn")
3239 (file-exists? "test2.gff")
3240 (file-exists? "test2.out"))
3241 (error "Expected files do not exist."))
3242 ;; Test incomplete sequences.
3244 "-genome=./example/NC_000913-fgs.ffn"
3251 ("python" ,python-2))) ;not compatible with python 3.
3252 (home-page "https://sourceforge.net/projects/fraggenescan/")
3253 (synopsis "Finds potentially fragmented genes in short reads")
3255 "FragGeneScan is a program for predicting bacterial and archaeal genes in
3256 short and error-prone DNA sequencing reads. It can also be applied to predict
3257 genes in incomplete assemblies or complete genomes.")
3258 ;; GPL3+ according to private correspondense with the authors.
3259 (license license:gpl3+)))
3261 (define-public fxtract
3262 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
3270 (url "https://github.com/ctSkennerton/fxtract.git")
3272 (file-name (git-file-name name version))
3275 "0hab3gpwf4w9s87qlbswq6ws1qqybh4dcqk79q1ahyldzai5fgp5"))))
3276 (build-system gnu-build-system)
3278 `(#:make-flags (list
3279 (string-append "PREFIX=" (assoc-ref %outputs "out"))
3281 #:test-target "fxtract_test"
3283 (modify-phases %standard-phases
3285 (add-before 'build 'copy-util
3286 (lambda* (#:key inputs #:allow-other-keys)
3288 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
3290 ;; Do not use make install as this requires additional dependencies.
3292 (lambda* (#:key outputs #:allow-other-keys)
3293 (let* ((out (assoc-ref outputs "out"))
3294 (bin (string-append out"/bin")))
3295 (install-file "fxtract" bin)
3301 ;; ctskennerton-util is licensed under GPL2.
3302 `(("ctskennerton-util"
3306 (url "https://github.com/ctSkennerton/util.git")
3307 (commit util-commit)))
3308 (file-name (string-append
3309 "ctstennerton-util-" util-commit "-checkout"))
3312 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
3313 (home-page "https://github.com/ctSkennerton/fxtract")
3314 (synopsis "Extract sequences from FASTA and FASTQ files")
3316 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
3317 or FASTQ) file given a subsequence. It uses a simple substring search for
3318 basic tasks but can change to using POSIX regular expressions, PCRE, hash
3319 lookups or multi-pattern searching as required. By default fxtract looks in
3320 the sequence of each record but can also be told to look in the header,
3321 comment or quality sections.")
3322 ;; 'util' requires SSE instructions.
3323 (supported-systems '("x86_64-linux"))
3324 (license license:expat))))
3326 (define-public gemma
3333 (url "https://github.com/xiangzhou/GEMMA.git")
3334 (commit (string-append "v" version))))
3335 (file-name (git-file-name name version))
3338 "1s3ncnbn45r2hh1cvrqky1kbqq6546biypr4f5mkw1kqlrgyh0yg"))))
3341 ("gfortran" ,gfortran "lib")
3344 ("openblas" ,openblas)
3346 (build-system gnu-build-system)
3349 '(,@(match (%current-system)
3351 '("FORCE_DYNAMIC=1"))
3353 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
3355 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
3357 (modify-phases %standard-phases
3359 (add-after 'unpack 'find-eigen
3360 (lambda* (#:key inputs #:allow-other-keys)
3361 ;; Ensure that Eigen headers can be found
3362 (setenv "CPLUS_INCLUDE_PATH"
3363 (string-append (assoc-ref inputs "eigen")
3366 (add-before 'build 'bin-mkdir
3371 (lambda* (#:key outputs #:allow-other-keys)
3372 (let ((out (assoc-ref outputs "out")))
3373 (install-file "bin/gemma"
3377 #:tests? #f)) ; no tests included yet
3378 (home-page "https://github.com/xiangzhou/GEMMA")
3379 (synopsis "Tool for genome-wide efficient mixed model association")
3381 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
3382 standard linear mixed model resolver with application in genome-wide
3383 association studies (GWAS).")
3384 (license license:gpl3)))
3393 (url "https://github.com/nboley/grit.git")
3395 (file-name (git-file-name name version))
3398 "1l5v8vfvfbrpmgnrvbrbv40d0arhxcnmxgv2f1mlcqfa3q6bkqm9"))))
3399 (build-system python-build-system)
3401 `(#:python ,python-2
3403 (modify-phases %standard-phases
3404 (add-after 'unpack 'generate-from-cython-sources
3405 (lambda* (#:key inputs outputs #:allow-other-keys)
3406 ;; Delete these C files to force fresh generation from pyx sources.
3407 (delete-file "grit/sparsify_support_fns.c")
3408 (delete-file "grit/call_peaks_support_fns.c")
3409 (substitute* "setup.py"
3410 (("Cython.Setup") "Cython.Build"))
3413 `(("python-scipy" ,python2-scipy)
3414 ("python-numpy" ,python2-numpy)
3415 ("python-pysam" ,python2-pysam)
3416 ("python-networkx" ,python2-networkx)))
3418 `(("python-cython" ,python2-cython)))
3419 ;; The canonical <http://grit-bio.org> home page times out as of 2020-01-21.
3420 (home-page "https://github.com/nboley/grit")
3421 (synopsis "Tool for integrative analysis of RNA-seq type assays")
3423 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
3424 full length transcript models. When none of these data sources are available,
3425 GRIT can be run by providing a candidate set of TES or TSS sites. In
3426 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
3427 also be run in quantification mode, where it uses a provided GTF file and just
3428 estimates transcript expression.")
3429 (license license:gpl3+)))
3431 (define-public hisat
3438 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
3439 version "-beta-source.zip"))
3442 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
3443 (build-system gnu-build-system)
3445 `(#:tests? #f ;no check target
3446 #:make-flags '("allall"
3447 ;; Disable unsupported `popcnt' instructions on
3448 ;; architectures other than x86_64
3449 ,@(if (string-prefix? "x86_64"
3450 (or (%current-target-system)
3453 '("POPCNT_CAPABILITY=0")))
3455 (modify-phases %standard-phases
3456 (add-after 'unpack 'patch-sources
3458 ;; XXX Cannot use snippet because zip files are not supported
3459 (substitute* "Makefile"
3460 (("^CC = .*$") "CC = gcc")
3461 (("^CPP = .*$") "CPP = g++")
3462 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
3463 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
3464 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
3465 (substitute* '("hisat-build" "hisat-inspect")
3466 (("/usr/bin/env") (which "env")))
3469 (lambda* (#:key outputs #:allow-other-keys)
3470 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
3471 (for-each (lambda (file)
3472 (install-file file bin))
3475 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
3477 (delete 'configure))))
3479 `(("unzip" ,unzip)))
3484 ;; Non-portable SSE instructions are used so building fails on platforms
3485 ;; other than x86_64.
3486 (supported-systems '("x86_64-linux"))
3487 (home-page "https://ccb.jhu.edu/software/hisat/index.shtml")
3488 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
3490 "HISAT is a fast and sensitive spliced alignment program for mapping
3491 RNA-seq reads. In addition to one global FM index that represents a whole
3492 genome, HISAT uses a large set of small FM indexes that collectively cover the
3493 whole genome. These small indexes (called local indexes) combined with
3494 several alignment strategies enable effective alignment of RNA-seq reads, in
3495 particular, reads spanning multiple exons.")
3496 (license license:gpl3+)))
3498 (define-public hisat2
3505 (uri (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
3506 "/downloads/hisat2-" version "-source.zip"))
3509 "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"))))
3510 (build-system gnu-build-system)
3512 `(#:tests? #f ; no check target
3513 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
3514 #:modules ((guix build gnu-build-system)
3518 (modify-phases %standard-phases
3519 (add-after 'unpack 'make-deterministic
3521 (substitute* "Makefile"
3526 (lambda* (#:key outputs #:allow-other-keys)
3527 (let* ((out (assoc-ref outputs "out"))
3528 (bin (string-append out "/bin/"))
3529 (doc (string-append out "/share/doc/hisat2/")))
3531 (cut install-file <> bin)
3533 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
3535 (install-file "doc/manual.inc.html" doc))
3538 `(("unzip" ,unzip) ; needed for archive from ftp
3540 ("pandoc" ,ghc-pandoc))) ; for documentation
3541 (home-page "https://ccb.jhu.edu/software/hisat2/index.shtml")
3542 (synopsis "Graph-based alignment of genomic sequencing reads")
3543 (description "HISAT2 is a fast and sensitive alignment program for mapping
3544 next-generation sequencing reads (both DNA and RNA) to a population of human
3545 genomes (as well as to a single reference genome). In addition to using one
3546 global @dfn{graph FM} (GFM) index that represents a population of human
3547 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
3548 the whole genome. These small indexes, combined with several alignment
3549 strategies, enable rapid and accurate alignment of sequencing reads. This new
3550 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
3551 ;; HISAT2 contains files from Bowtie2, which is released under
3552 ;; GPLv2 or later. The HISAT2 source files are released under
3554 (license license:gpl3+)))
3556 (define-public hmmer
3564 "http://eddylab.org/software/hmmer/hmmer-" version ".tar.gz"))
3567 "171bivy6xhgjsz5nv53n81pc3frnwz29ylblawk2bv46szwjjqd5"))))
3568 (build-system gnu-build-system)
3569 (native-inputs `(("perl" ,perl)))
3570 (home-page "http://hmmer.org/")
3571 (synopsis "Biosequence analysis using profile hidden Markov models")
3573 "HMMER is used for searching sequence databases for homologs of protein
3574 sequences, and for making protein sequence alignments. It implements methods
3575 using probabilistic models called profile hidden Markov models (profile
3577 ;; hmmer uses non-portable SSE intrinsics so building fails on other
3579 (supported-systems '("x86_64-linux" "i686-linux"))
3580 (license license:bsd-3)))
3582 (define-public htseq
3588 (uri (pypi-uri "HTSeq" version))
3591 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
3592 (build-system python-build-system)
3594 `(("python-cython" ,python-cython)))
3595 ;; Numpy needs to be propagated when htseq is used as a Python library.
3597 `(("python-numpy" ,python-numpy)))
3599 `(("python-pysam" ,python-pysam)
3600 ("python-matplotlib" ,python-matplotlib)))
3601 (home-page "https://htseq.readthedocs.io/")
3602 (synopsis "Analysing high-throughput sequencing data with Python")
3604 "HTSeq is a Python package that provides infrastructure to process data
3605 from high-throughput sequencing assays.")
3606 (license license:gpl3+)))
3608 (define-public python2-htseq
3609 (package-with-python2 htseq))
3611 (define-public java-htsjdk
3613 (name "java-htsjdk")
3614 (version "2.3.0") ; last version without build dependency on gradle
3618 (url "https://github.com/samtools/htsjdk.git")
3620 (file-name (git-file-name name version))
3623 "1b178ixcabanm834ydjl3jiakpyxdmki32hqfv2abrzn3rcwa28i"))
3624 (modules '((guix build utils)))
3626 ;; Delete pre-built binaries
3628 (delete-file-recursively "lib")
3631 (build-system ant-build-system)
3633 `(#:tests? #f ; test require Internet access
3636 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3637 "/share/java/htsjdk/"))
3638 #:build-target "all"
3640 (modify-phases %standard-phases
3641 ;; The build phase also installs the jars
3642 (delete 'install))))
3644 `(("java-ngs" ,java-ngs)
3645 ("java-snappy-1" ,java-snappy-1)
3646 ("java-commons-compress" ,java-commons-compress)
3647 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3648 ("java-commons-jexl-2" ,java-commons-jexl-2)
3649 ("java-xz" ,java-xz)))
3651 `(("java-testng" ,java-testng)))
3652 (home-page "http://samtools.github.io/htsjdk/")
3653 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3655 "HTSJDK is an implementation of a unified Java library for accessing
3656 common file formats, such as SAM and VCF, used for high-throughput
3657 sequencing (HTS) data. There are also an number of useful utilities for
3658 manipulating HTS data.")
3659 (license license:expat)))
3661 (define-public java-htsjdk-latest
3663 (name "java-htsjdk")
3668 (url "https://github.com/samtools/htsjdk.git")
3670 (file-name (string-append name "-" version "-checkout"))
3673 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
3674 (build-system ant-build-system)
3676 `(#:tests? #f ; test require Scala
3678 #:jar-name "htsjdk.jar"
3680 (modify-phases %standard-phases
3681 (add-after 'unpack 'remove-useless-build.xml
3682 (lambda _ (delete-file "build.xml") #t))
3683 ;; The tests require the scalatest package.
3684 (add-after 'unpack 'remove-tests
3685 (lambda _ (delete-file-recursively "src/test") #t)))))
3687 `(("java-ngs" ,java-ngs)
3688 ("java-snappy-1" ,java-snappy-1)
3689 ("java-commons-compress" ,java-commons-compress)
3690 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3691 ("java-commons-jexl-2" ,java-commons-jexl-2)
3692 ("java-xz" ,java-xz)))
3694 `(("java-junit" ,java-junit)))
3695 (home-page "http://samtools.github.io/htsjdk/")
3696 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3698 "HTSJDK is an implementation of a unified Java library for accessing
3699 common file formats, such as SAM and VCF, used for high-throughput
3700 sequencing (HTS) data. There are also an number of useful utilities for
3701 manipulating HTS data.")
3702 (license license:expat)))
3704 ;; This is needed for picard 2.10.3
3705 (define-public java-htsjdk-2.10.1
3706 (package (inherit java-htsjdk-latest)
3707 (name "java-htsjdk")
3712 (url "https://github.com/samtools/htsjdk.git")
3714 (file-name (string-append name "-" version "-checkout"))
3717 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
3718 (build-system ant-build-system)
3720 `(#:tests? #f ; tests require Scala
3722 #:jar-name "htsjdk.jar"
3724 (modify-phases %standard-phases
3725 (add-after 'unpack 'remove-useless-build.xml
3726 (lambda _ (delete-file "build.xml") #t))
3727 ;; The tests require the scalatest package.
3728 (add-after 'unpack 'remove-tests
3729 (lambda _ (delete-file-recursively "src/test") #t)))))))
3731 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3732 ;; recent version of java-htsjdk, which depends on gradle.
3733 (define-public java-picard
3735 (name "java-picard")
3740 (url "https://github.com/broadinstitute/picard.git")
3742 (file-name (string-append "java-picard-" version "-checkout"))
3745 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3746 (modules '((guix build utils)))
3749 ;; Delete pre-built binaries.
3750 (delete-file-recursively "lib")
3752 (substitute* "build.xml"
3753 ;; Remove build-time dependency on git.
3754 (("failifexecutionfails=\"true\"")
3755 "failifexecutionfails=\"false\"")
3757 (("depends=\"compile-htsjdk, ")
3759 (("depends=\"compile-htsjdk-tests, ")
3761 ;; Build picard-lib.jar before building picard.jar
3762 (("name=\"picard-jar\" depends=\"" line)
3763 (string-append line "picard-lib-jar, ")))
3765 (build-system ant-build-system)
3767 `(#:build-target "picard-jar"
3768 #:test-target "test"
3769 ;; Tests require jacoco:coverage.
3772 (list (string-append "-Dhtsjdk_lib_dir="
3773 (assoc-ref %build-inputs "java-htsjdk")
3774 "/share/java/htsjdk/")
3775 "-Dhtsjdk-classes=dist/tmp"
3776 (string-append "-Dhtsjdk-version="
3777 ,(package-version java-htsjdk)))
3780 (modify-phases %standard-phases
3781 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3782 (delete 'generate-jar-indices)
3783 (add-after 'unpack 'use-our-htsjdk
3784 (lambda* (#:key inputs #:allow-other-keys)
3785 (substitute* "build.xml"
3786 (("\\$\\{htsjdk\\}/lib")
3787 (string-append (assoc-ref inputs "java-htsjdk")
3788 "/share/java/htsjdk/")))
3790 (add-after 'unpack 'make-test-target-independent
3791 (lambda* (#:key inputs #:allow-other-keys)
3792 (substitute* "build.xml"
3793 (("name=\"test\" depends=\"compile, ")
3794 "name=\"test\" depends=\""))
3796 (replace 'install (install-jars "dist")))))
3798 `(("java-htsjdk" ,java-htsjdk)
3799 ("java-guava" ,java-guava)))
3801 `(("java-testng" ,java-testng)))
3802 (home-page "http://broadinstitute.github.io/picard/")
3803 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3804 (description "Picard is a set of Java command line tools for manipulating
3805 high-throughput sequencing (HTS) data and formats. Picard is implemented
3806 using the HTSJDK Java library to support accessing file formats that are
3807 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3809 (license license:expat)))
3811 ;; This is needed for dropseq-tools
3812 (define-public java-picard-2.10.3
3814 (name "java-picard")
3819 (url "https://github.com/broadinstitute/picard.git")
3821 (file-name (string-append "java-picard-" version "-checkout"))
3824 "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi"))))
3825 (build-system ant-build-system)
3827 `(#:jar-name "picard.jar"
3828 ;; Tests require jacoco:coverage.
3831 #:main-class "picard.cmdline.PicardCommandLine"
3832 #:modules ((guix build ant-build-system)
3834 (guix build java-utils)
3839 (modify-phases %standard-phases
3840 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3841 (delete 'generate-jar-indices)
3842 (add-after 'unpack 'remove-useless-build.xml
3843 (lambda _ (delete-file "build.xml") #t))
3844 ;; This is necessary to ensure that htsjdk is found when using
3845 ;; picard.jar as an executable.
3846 (add-before 'build 'edit-classpath-in-manifest
3847 (lambda* (#:key inputs #:allow-other-keys)
3848 (chmod "build.xml" #o664)
3849 (call-with-output-file "build.xml.new"
3853 (with-input-from-file "build.xml"
3854 (lambda _ (xml->sxml #:trim-whitespace? #t)))
3855 `((target . ,(lambda (tag . kids)
3856 (let ((name ((sxpath '(name *text*))
3858 ;; FIXME: We're breaking the line
3859 ;; early with a dummy path to
3860 ;; ensure that the store reference
3861 ;; isn't broken apart and can still
3862 ;; be found by the reference
3867 ~a/share/java/htsjdk.jar${line.separator}${line.separator}"
3868 ;; maximum line length is 70
3869 (string-tabulate (const #\b) 57)
3870 (assoc-ref inputs "java-htsjdk"))))
3871 (if (member "manifest" name)
3874 (@ (file "${manifest.file}")
3875 (match "\\r\\n\\r\\n")
3876 (replace "${line.separator}")))
3879 (file "${manifest.file}")
3882 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
3883 (*text* . ,(lambda (_ txt) txt))))
3885 (rename-file "build.xml.new" "build.xml")
3888 `(("java-htsjdk" ,java-htsjdk-2.10.1)))
3890 `(("java-testng" ,java-testng)
3891 ("java-guava" ,java-guava)))
3892 (home-page "http://broadinstitute.github.io/picard/")
3893 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3894 (description "Picard is a set of Java command line tools for manipulating
3895 high-throughput sequencing (HTS) data and formats. Picard is implemented
3896 using the HTSJDK Java library to support accessing file formats that are
3897 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3899 (license license:expat)))
3901 ;; This is the last version of Picard to provide net.sf.samtools
3902 (define-public java-picard-1.113
3903 (package (inherit java-picard)
3904 (name "java-picard")
3909 (url "https://github.com/broadinstitute/picard.git")
3911 (file-name (string-append "java-picard-" version "-checkout"))
3914 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
3915 (modules '((guix build utils)))
3918 ;; Delete pre-built binaries.
3919 (delete-file-recursively "lib")
3922 (build-system ant-build-system)
3924 `(#:build-target "picard-jar"
3925 #:test-target "test"
3926 ;; FIXME: the class path at test time is wrong.
3927 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
3928 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
3931 ;; This is only used for tests.
3933 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
3935 (modify-phases %standard-phases
3936 ;; FIXME: This phase fails.
3937 (delete 'generate-jar-indices)
3938 ;; Do not use bundled ant bzip2.
3939 (add-after 'unpack 'use-ant-bzip
3940 (lambda* (#:key inputs #:allow-other-keys)
3941 (substitute* "build.xml"
3942 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
3943 (string-append (assoc-ref inputs "ant")
3946 (add-after 'unpack 'make-test-target-independent
3947 (lambda* (#:key inputs #:allow-other-keys)
3948 (substitute* "build.xml"
3949 (("name=\"test\" depends=\"compile, ")
3950 "name=\"test\" depends=\"compile-tests, ")
3951 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
3952 "name=\"compile\" depends=\"compile-src\""))
3954 (add-after 'unpack 'fix-deflater-path
3955 (lambda* (#:key outputs #:allow-other-keys)
3956 (substitute* "src/java/net/sf/samtools/Defaults.java"
3957 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
3958 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
3959 (assoc-ref outputs "out")
3960 "/lib/jni/libIntelDeflater.so"
3963 ;; Build the deflater library, because we've previously deleted the
3964 ;; pre-built one. This can only be built with access to the JDK
3966 (add-after 'build 'build-jni
3967 (lambda* (#:key inputs #:allow-other-keys)
3970 (invoke "tar" "--strip-components=1" "-C" "jdk-src"
3971 "-xf" (assoc-ref inputs "jdk-src"))
3972 (invoke "javah" "-jni"
3973 "-classpath" "classes"
3975 "net.sf.samtools.util.zip.IntelDeflater")
3976 (with-directory-excursion "src/c/inteldeflater"
3977 (invoke "gcc" "-I../../../lib" "-I."
3978 (string-append "-I" (assoc-ref inputs "jdk")
3980 "-I../../../jdk-src/src/share/native/common/"
3981 "-I../../../jdk-src/src/solaris/native/common/"
3982 "-c" "-O3" "-fPIC" "IntelDeflater.c")
3983 (invoke "gcc" "-shared"
3984 "-o" "../../../lib/jni/libIntelDeflater.so"
3985 "IntelDeflater.o" "-lz" "-lstdc++"))
3987 ;; We can only build everything else after building the JNI library.
3988 (add-after 'build-jni 'build-rest
3989 (lambda* (#:key make-flags #:allow-other-keys)
3990 (apply invoke `("ant" "all" ,@make-flags))
3992 (add-before 'build 'set-JAVA6_HOME
3994 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
3996 (replace 'install (install-jars "dist"))
3997 (add-after 'install 'install-jni-lib
3998 (lambda* (#:key outputs #:allow-other-keys)
3999 (let ((jni (string-append (assoc-ref outputs "out")
4002 (install-file "lib/jni/libIntelDeflater.so" jni)
4005 `(("java-snappy-1" ,java-snappy-1)
4006 ("java-commons-jexl-2" ,java-commons-jexl-2)
4007 ("java-cofoja" ,java-cofoja)
4008 ("ant" ,ant) ; for bzip2 support at runtime
4011 `(("ant-apache-bcel" ,ant-apache-bcel)
4012 ("ant-junit" ,ant-junit)
4013 ("java-testng" ,java-testng)
4014 ("java-commons-bcel" ,java-commons-bcel)
4015 ("java-jcommander" ,java-jcommander)
4016 ("jdk" ,icedtea-8 "jdk")
4017 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
4019 (define-public fastqc
4026 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
4027 "projects/fastqc/fastqc_v"
4028 version "_source.zip"))
4031 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
4032 (build-system ant-build-system)
4034 `(#:tests? #f ; there are no tests
4035 #:build-target "build"
4037 (modify-phases %standard-phases
4038 (add-after 'unpack 'fix-dependencies
4039 (lambda* (#:key inputs #:allow-other-keys)
4040 (substitute* "build.xml"
4042 (string-append (assoc-ref inputs "java-jbzip2")
4043 "/share/java/jbzip2.jar"))
4045 (string-append (assoc-ref inputs "java-picard-1.113")
4046 "/share/java/sam-1.112.jar"))
4048 (string-append (assoc-ref inputs "java-cisd-jhdf5")
4049 "/share/java/sis-jhdf5.jar")))
4051 ;; There is no installation target
4053 (lambda* (#:key inputs outputs #:allow-other-keys)
4054 (let* ((out (assoc-ref outputs "out"))
4055 (bin (string-append out "/bin"))
4056 (share (string-append out "/share/fastqc/"))
4057 (exe (string-append share "/fastqc")))
4058 (for-each mkdir-p (list bin share))
4059 (copy-recursively "bin" share)
4061 (("my \\$java_bin = 'java';")
4062 (string-append "my $java_bin = '"
4063 (assoc-ref inputs "java")
4066 (symlink exe (string-append bin "/fastqc"))
4070 ("perl" ,perl) ; needed for the wrapper script
4071 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
4072 ("java-picard-1.113" ,java-picard-1.113)
4073 ("java-jbzip2" ,java-jbzip2)))
4075 `(("unzip" ,unzip)))
4076 (home-page "https://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
4077 (synopsis "Quality control tool for high throughput sequence data")
4079 "FastQC aims to provide a simple way to do some quality control
4080 checks on raw sequence data coming from high throughput sequencing
4081 pipelines. It provides a modular set of analyses which you can use to
4082 give a quick impression of whether your data has any problems of which
4083 you should be aware before doing any further analysis.
4085 The main functions of FastQC are:
4088 @item Import of data from BAM, SAM or FastQ files (any variant);
4089 @item Providing a quick overview to tell you in which areas there may
4091 @item Summary graphs and tables to quickly assess your data;
4092 @item Export of results to an HTML based permanent report;
4093 @item Offline operation to allow automated generation of reports
4094 without running the interactive application.
4096 (license license:gpl3+)))
4098 (define-public fastp
4106 (url "https://github.com/OpenGene/fastp.git")
4107 (commit (string-append "v" version))))
4108 (file-name (git-file-name name version))
4111 "1r6ms5zbf5rps4rgp4z73nczadl00b5rqylw8f684isfz27dp0xh"))))
4112 (build-system gnu-build-system)
4114 `(#:tests? #f ; there are none
4116 (list (string-append "BINDIR=" (assoc-ref %outputs "out") "/bin"))
4118 (modify-phases %standard-phases
4120 (add-before 'install 'create-target-dir
4121 (lambda* (#:key outputs #:allow-other-keys)
4122 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4126 (home-page "https://github.com/OpenGene/fastp/")
4127 (synopsis "All-in-one FastQ preprocessor")
4129 "Fastp is a tool designed to provide fast all-in-one preprocessing for
4130 FastQ files. This tool has multi-threading support to afford high
4132 (license license:expat)))
4134 (define-public htslib
4141 "https://github.com/samtools/htslib/releases/download/"
4142 version "/htslib-" version ".tar.bz2"))
4145 "16ljv43sc3fxmv63w7b2ff8m1s7h89xhazwmbm1bicz8axq8fjz0"))))
4146 (build-system gnu-build-system)
4149 ("openssl" ,openssl)))
4150 ;; This is referred to in the pkg-config file as a required library.
4155 (home-page "https://www.htslib.org")
4156 (synopsis "C library for reading/writing high-throughput sequencing data")
4158 "HTSlib is a C library for reading/writing high-throughput sequencing
4159 data. It also provides the @command{bgzip}, @command{htsfile}, and
4160 @command{tabix} utilities.")
4161 ;; Files under cram/ are released under the modified BSD license;
4162 ;; the rest is released under the Expat license
4163 (license (list license:expat license:bsd-3))))
4165 ;; This package should be removed once no packages rely upon it.
4173 "https://github.com/samtools/htslib/releases/download/"
4174 version "/htslib-" version ".tar.bz2"))
4177 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
4186 (url "https://github.com/nboley/idr.git")
4188 (file-name (git-file-name name version))
4191 "04j876h6z444v2q79drxx283d3k5snd72kj895wbalnl42206x9g"))
4192 ;; Delete generated C code.
4194 '(begin (delete-file "idr/inv_cdf.c") #t))))
4195 (build-system python-build-system)
4196 ;; There is only one test ("test_inv_cdf.py") and it tests features that
4197 ;; are no longer part of this package. It also asserts False, which
4198 ;; causes the tests to always fail.
4199 (arguments `(#:tests? #f))
4201 `(("python-scipy" ,python-scipy)
4202 ("python-sympy" ,python-sympy)
4203 ("python-numpy" ,python-numpy)
4204 ("python-matplotlib" ,python-matplotlib)))
4206 `(("python-cython" ,python-cython)))
4207 (home-page "https://github.com/nboley/idr")
4208 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
4210 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
4211 to measure the reproducibility of findings identified from replicate
4212 experiments and provide highly stable thresholds based on reproducibility.")
4213 (license license:gpl2+)))
4215 (define-public jellyfish
4221 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
4222 "releases/download/v" version
4223 "/jellyfish-" version ".tar.gz"))
4226 "1k4pc3fvv6w1km2yph4m5sd78fbxp21d6xyzgmy0gjihzc6mb249"))))
4227 (build-system gnu-build-system)
4228 (outputs '("out" ;for library
4229 "ruby" ;for Ruby bindings
4230 "python")) ;for Python bindings
4233 (list (string-append "--enable-ruby-binding="
4234 (assoc-ref %outputs "ruby"))
4235 (string-append "--enable-python-binding="
4236 (assoc-ref %outputs "python")))
4238 (modify-phases %standard-phases
4239 (add-before 'check 'set-SHELL-variable
4241 ;; generator_manager.hpp either uses /bin/sh or $SHELL
4243 (setenv "SHELL" (which "bash"))
4249 ("python" ,python-2)
4250 ("pkg-config" ,pkg-config)))
4252 `(("htslib" ,htslib)))
4253 (synopsis "Tool for fast counting of k-mers in DNA")
4255 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
4256 DNA. A k-mer is a substring of length k, and counting the occurrences of all
4257 such substrings is a central step in many analyses of DNA sequence. Jellyfish
4258 is a command-line program that reads FASTA and multi-FASTA files containing
4259 DNA sequences. It outputs its k-mer counts in a binary format, which can be
4260 translated into a human-readable text format using the @code{jellyfish dump}
4261 command, or queried for specific k-mers with @code{jellyfish query}.")
4262 (home-page "http://www.genome.umd.edu/jellyfish.html")
4263 ;; JELLYFISH seems to be 64-bit only.
4264 (supported-systems '("x86_64-linux" "aarch64-linux" "mips64el-linux"))
4265 ;; The combined work is published under the GPLv3 or later. Individual
4266 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
4267 (license (list license:gpl3+ license:expat))))
4269 (define-public khmer
4277 (url "https://github.com/dib-lab/khmer.git")
4278 (commit (string-append "v" version))))
4279 (file-name (git-file-name name version))
4282 "01l4jczglkl7yfhgvzx8j0df7k54bk1r8sli9ll16i1mis0d8f37"))
4283 (modules '((guix build utils)))
4286 ;; Delete bundled libraries. We do not replace the bundled seqan
4287 ;; as it is a modified subset of the old version 1.4.1.
4289 ;; We do not replace the bundled MurmurHash as the canonical
4290 ;; repository for this code 'SMHasher' is unsuitable for providing
4292 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
4293 (delete-file-recursively "third-party/zlib")
4294 (delete-file-recursively "third-party/bzip2")
4295 (delete-file-recursively "third-party/seqan")
4296 (substitute* "setup.cfg"
4297 (("# libraries = z,bz2")
4298 "libraries = z,bz2")
4299 (("include:third-party/zlib:third-party/bzip2")
4302 (build-system python-build-system)
4305 (modify-phases %standard-phases
4306 (add-after 'unpack 'set-cc
4307 (lambda _ (setenv "CC" "gcc") #t))
4309 (add-before 'reset-gzip-timestamps 'make-files-writable
4310 (lambda* (#:key outputs #:allow-other-keys)
4311 ;; Make sure .gz files are writable so that the
4312 ;; 'reset-gzip-timestamps' phase can do its work.
4313 (let ((out (assoc-ref outputs "out")))
4314 (for-each make-file-writable
4315 (find-files out "\\.gz$"))
4318 `(("python-cython" ,python-cython)
4319 ("python-pytest" ,python-pytest)
4320 ("python-pytest-runner" ,python-pytest-runner)))
4325 ("python-screed" ,python-screed)
4326 ("python-bz2file" ,python-bz2file)))
4327 (home-page "https://khmer.readthedocs.org/")
4328 (synopsis "K-mer counting, filtering and graph traversal library")
4329 (description "The khmer software is a set of command-line tools for
4330 working with DNA shotgun sequencing data from genomes, transcriptomes,
4331 metagenomes and single cells. Khmer can make de novo assemblies faster, and
4332 sometimes better. Khmer can also identify and fix problems with shotgun
4334 ;; When building on i686, armhf and mips64el, we get the following error:
4335 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
4336 (supported-systems '("x86_64-linux" "aarch64-linux"))
4337 (license license:bsd-3)))
4339 (define-public kaiju
4346 (url "https://github.com/bioinformatics-centre/kaiju")
4347 (commit (string-append "v" version))))
4348 (file-name (git-file-name name version))
4351 "119pzi0ddzv9mjg4wwa6han0cwr3k3ssn7kirvsjfcq05mi5ka0x"))))
4352 (build-system gnu-build-system)
4354 `(#:tests? #f ; There are no tests.
4356 (modify-phases %standard-phases
4358 (add-before 'build 'move-to-src-dir
4359 (lambda _ (chdir "src") #t))
4361 (lambda* (#:key inputs outputs #:allow-other-keys)
4362 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
4365 (copy-recursively "bin" bin))
4370 (home-page "http://kaiju.binf.ku.dk/")
4371 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
4372 (description "Kaiju is a program for sensitive taxonomic classification
4373 of high-throughput sequencing reads from metagenomic whole genome sequencing
4375 (license license:gpl3+)))
4382 ;; The PyPi tarball does not contain tests.
4385 (url "https://github.com/taoliu/MACS.git")
4386 (commit (string-append "v" version))))
4387 (file-name (git-file-name name version))
4390 "1c5gxr0mk6hkd4vclf0k00wvyvzw2vrmk52c85338p7aqjwg6n15"))))
4391 (build-system python-build-system)
4394 (modify-phases %standard-phases
4396 (add-after 'install 'check
4397 (lambda* (#:key inputs outputs #:allow-other-keys)
4398 (add-installed-pythonpath inputs outputs)
4399 (invoke "pytest" "-v"))))))
4401 `(("python-numpy" ,python-numpy)))
4403 `(("python-pytest" ,python-pytest)))
4404 (home-page "https://github.com/taoliu/MACS/")
4405 (synopsis "Model based analysis for ChIP-Seq data")
4407 "MACS is an implementation of a ChIP-Seq analysis algorithm for
4408 identifying transcript factor binding sites named Model-based Analysis of
4409 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
4410 the significance of enriched ChIP regions and it improves the spatial
4411 resolution of binding sites through combining the information of both
4412 sequencing tag position and orientation.")
4413 (license license:bsd-3)))
4415 (define-public mafft
4422 "https://mafft.cbrc.jp/alignment/software/mafft-" version
4423 "-without-extensions-src.tgz"))
4424 (file-name (string-append name "-" version ".tgz"))
4427 "0bacjkxfg944p5khhyh5rd4y7wkjc9qk4v2jjj442sqlq0f8ar7b"))))
4428 (build-system gnu-build-system)
4430 `(#:tests? #f ; no automated tests, though there are tests in the read me
4431 #:make-flags (let ((out (assoc-ref %outputs "out")))
4432 (list (string-append "PREFIX=" out)
4433 (string-append "BINDIR="
4434 (string-append out "/bin"))))
4436 (modify-phases %standard-phases
4437 (add-after 'unpack 'enter-dir
4438 (lambda _ (chdir "core") #t))
4439 (add-after 'enter-dir 'patch-makefile
4441 ;; on advice from the MAFFT authors, there is no need to
4442 ;; distribute mafft-profile, mafft-distance, or
4443 ;; mafft-homologs.rb as they are too "specialised".
4444 (substitute* "Makefile"
4445 ;; remove mafft-homologs.rb from SCRIPTS
4446 (("^SCRIPTS = mafft mafft-homologs.rb")
4448 ;; remove mafft-homologs from MANPAGES
4449 (("^MANPAGES = mafft.1 mafft-homologs.1")
4450 "MANPAGES = mafft.1")
4451 ;; remove mafft-distance from PROGS
4452 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
4453 "PROGS = dvtditr dndfast7 dndblast sextet5")
4454 ;; remove mafft-profile from PROGS
4455 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
4456 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
4457 (("^rm -f mafft-profile mafft-profile.exe") "#")
4458 (("^rm -f mafft-distance mafft-distance.exe") ")#")
4459 ;; do not install MAN pages in libexec folder
4460 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
4461 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
4463 (add-after 'enter-dir 'patch-paths
4464 (lambda* (#:key inputs #:allow-other-keys)
4465 (substitute* '("pairash.c"
4467 (("perl") (which "perl"))
4468 (("([\"`| ])awk" _ prefix)
4469 (string-append prefix (which "awk")))
4470 (("grep") (which "grep")))
4473 (add-after 'install 'wrap-programs
4474 (lambda* (#:key outputs #:allow-other-keys)
4475 (let* ((out (assoc-ref outputs "out"))
4476 (bin (string-append out "/bin"))
4477 (path (string-append
4478 (assoc-ref %build-inputs "coreutils") "/bin:")))
4479 (for-each (lambda (file)
4481 `("PATH" ":" prefix (,path))))
4489 ("coreutils" ,coreutils)))
4490 (home-page "http://mafft.cbrc.jp/alignment/software/")
4491 (synopsis "Multiple sequence alignment program")
4493 "MAFFT offers a range of multiple alignment methods for nucleotide and
4494 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
4495 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
4497 (license (license:non-copyleft
4498 "http://mafft.cbrc.jp/alignment/software/license.txt"
4499 "BSD-3 with different formatting"))))
4508 (url "https://github.com/marbl/mash.git")
4509 (commit (string-append "v" version))))
4510 (file-name (git-file-name name version))
4513 "049hwcc059p2fd9vwndn63laifvvsi0wmv84i6y1fr79k15dxwy6"))
4514 (modules '((guix build utils)))
4517 ;; Delete bundled kseq.
4518 ;; TODO: Also delete bundled murmurhash and open bloom filter.
4519 (delete-file "src/mash/kseq.h")
4521 (build-system gnu-build-system)
4523 `(#:tests? #f ; No tests.
4526 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
4527 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
4528 #:make-flags (list "CC=gcc")
4530 (modify-phases %standard-phases
4531 (add-after 'unpack 'fix-includes
4533 (substitute* '("src/mash/Sketch.cpp"
4534 "src/mash/CommandFind.cpp"
4535 "src/mash/CommandScreen.cpp")
4536 (("^#include \"kseq\\.h\"")
4537 "#include \"htslib/kseq.h\""))
4539 (add-after 'fix-includes 'use-c++14
4541 ;; capnproto 0.7 requires c++14 to build
4542 (substitute* "configure.ac"
4543 (("c\\+\\+11") "c++14"))
4544 (substitute* "Makefile.in"
4545 (("c\\+\\+11") "c++14"))
4548 `(("autoconf" ,autoconf)
4549 ;; Capnproto and htslib are statically embedded in the final
4550 ;; application. Therefore we also list their licenses, below.
4551 ("capnproto" ,capnproto)
4552 ("htslib" ,htslib)))
4556 (supported-systems '("x86_64-linux"))
4557 (home-page "https://mash.readthedocs.io")
4558 (synopsis "Fast genome and metagenome distance estimation using MinHash")
4559 (description "Mash is a fast sequence distance estimator that uses the
4560 MinHash algorithm and is designed to work with genomes and metagenomes in the
4561 form of assemblies or reads.")
4562 (license (list license:bsd-3 ; Mash
4563 license:expat ; HTSlib and capnproto
4564 license:public-domain ; MurmurHash 3
4565 license:cpl1.0)))) ; Open Bloom Filter
4567 (define-public metabat
4575 (url "https://bitbucket.org/berkeleylab/metabat.git")
4576 (commit (string-append "v" version))))
4577 (file-name (git-file-name name version))
4580 "0hyg2smw1nz69mfvjpk45xyyychmda92c80a0cv7baji84ri4iyn"))
4581 (patches (search-patches "metabat-fix-compilation.patch"))))
4582 (build-system scons-build-system)
4584 `(#:scons ,scons-python2
4586 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
4587 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
4588 #:tests? #f ;; Tests are run during the build phase.
4590 (modify-phases %standard-phases
4591 (add-after 'unpack 'fix-includes
4593 (substitute* "src/BamUtils.h"
4594 (("^#include \"bam/bam\\.h\"")
4595 "#include \"samtools/bam.h\"")
4596 (("^#include \"bam/sam\\.h\"")
4597 "#include \"samtools/sam.h\""))
4598 (substitute* "src/KseqReader.h"
4599 (("^#include \"bam/kseq\\.h\"")
4600 "#include \"htslib/kseq.h\""))
4602 (add-after 'unpack 'fix-scons
4603 (lambda* (#:key inputs #:allow-other-keys)
4604 (substitute* "SConstruct"
4605 (("^htslib_dir += 'samtools'")
4606 (string-append "htslib_dir = '"
4607 (assoc-ref inputs "htslib")
4609 (("^samtools_dir = 'samtools'")
4610 (string-append "samtools_dir = '"
4611 (assoc-ref inputs "samtools")
4613 (("^findStaticOrShared\\('bam', hts_lib")
4614 (string-append "findStaticOrShared('bam', '"
4615 (assoc-ref inputs "samtools")
4617 ;; Do not distribute README.
4618 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
4623 ("samtools" ,samtools)
4626 (home-page "https://bitbucket.org/berkeleylab/metabat")
4628 "Reconstruction of single genomes from complex microbial communities")
4630 "Grouping large genomic fragments assembled from shotgun metagenomic
4631 sequences to deconvolute complex microbial communities, or metagenome binning,
4632 enables the study of individual organisms and their interactions. MetaBAT is
4633 an automated metagenome binning software, which integrates empirical
4634 probabilistic distances of genome abundance and tetranucleotide frequency.")
4635 ;; The source code contains inline assembly.
4636 (supported-systems '("x86_64-linux" "i686-linux"))
4637 (license (license:non-copyleft "file://license.txt"
4638 "See license.txt in the distribution."))))
4640 (define-public minced
4647 (url "https://github.com/ctSkennerton/minced.git")
4649 (file-name (git-file-name name version))
4652 "1f5h9him0gd355cnx7p6pnxpknhckd4g0v62mg8zyhfbx9as25fv"))))
4653 (build-system gnu-build-system)
4655 `(#:test-target "test"
4657 (modify-phases %standard-phases
4659 (add-before 'check 'fix-test
4661 ;; Fix test for latest version.
4662 (substitute* "t/Aquifex_aeolicus_VF5.expected"
4663 (("minced:0.1.6") "minced:0.2.0"))
4665 (replace 'install ; No install target.
4666 (lambda* (#:key inputs outputs #:allow-other-keys)
4667 (let* ((out (assoc-ref outputs "out"))
4668 (bin (string-append out "/bin"))
4669 (wrapper (string-append bin "/minced")))
4670 ;; Minced comes with a wrapper script that tries to figure out where
4671 ;; it is located before running the JAR. Since these paths are known
4672 ;; to us, we build our own wrapper to avoid coreutils dependency.
4673 (install-file "minced.jar" bin)
4674 (with-output-to-file wrapper
4678 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
4679 (assoc-ref inputs "jre") "/bin/java -jar "
4680 bin "/minced.jar \"$@\"\n"))))
4681 (chmod wrapper #o555))
4684 `(("jdk" ,icedtea "jdk")))
4687 ("jre" ,icedtea "out")))
4688 (home-page "https://github.com/ctSkennerton/minced")
4689 (synopsis "Mining CRISPRs in Environmental Datasets")
4691 "MinCED is a program to find Clustered Regularly Interspaced Short
4692 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
4693 unassembled metagenomic reads, but is mainly designed for full genomes and
4694 assembled metagenomic sequence.")
4695 (license license:gpl3+)))
4703 (uri (pypi-uri "misopy" version))
4706 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
4707 (modules '((guix build utils)))
4709 (substitute* "setup.py"
4710 ;; Use setuptools, or else the executables are not
4712 (("distutils.core") "setuptools")
4713 ;; Use "gcc" instead of "cc" for compilation.
4715 "cc.set_executables(
4719 linker_so='gcc -shared'); defines"))
4721 (build-system python-build-system)
4723 `(#:python ,python-2 ; only Python 2 is supported
4724 #:tests? #f)) ; no "test" target
4726 `(("samtools" ,samtools)
4727 ("python-numpy" ,python2-numpy)
4728 ("python-pysam" ,python2-pysam)
4729 ("python-scipy" ,python2-scipy)
4730 ("python-matplotlib" ,python2-matplotlib)))
4732 `(("python-mock" ,python2-mock) ; for tests
4733 ("python-pytz" ,python2-pytz))) ; for tests
4734 (home-page "https://www.genes.mit.edu/burgelab/miso/index.html")
4735 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
4737 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
4738 the expression level of alternatively spliced genes from RNA-Seq data, and
4739 identifies differentially regulated isoforms or exons across samples. By
4740 modeling the generative process by which reads are produced from isoforms in
4741 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
4742 that a read originated from a particular isoform.")
4743 (license license:gpl2)))
4745 (define-public muscle
4748 (version "3.8.1551")
4750 (method url-fetch/tarbomb)
4752 "http://www.drive5.com/muscle/muscle_src_"
4756 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
4757 (build-system gnu-build-system)
4759 `(#:make-flags (list "LDLIBS = -lm")
4761 (modify-phases %standard-phases
4764 ;; There are no tests, so just test if it runs.
4765 (lambda _ (invoke "./muscle" "-version") #t))
4767 (lambda* (#:key outputs #:allow-other-keys)
4768 (let* ((out (assoc-ref outputs "out"))
4769 (bin (string-append out "/bin")))
4770 (install-file "muscle" bin)
4772 (home-page "http://www.drive5.com/muscle")
4773 (synopsis "Multiple sequence alignment program")
4775 "MUSCLE aims to be a fast and accurate multiple sequence alignment
4776 program for nucleotide and protein sequences.")
4777 ;; License information found in 'muscle -h' and usage.cpp.
4778 (license license:public-domain)))
4780 (define-public newick-utils
4781 ;; There are no recent releases so we package from git.
4782 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
4784 (name "newick-utils")
4785 (version (string-append "1.6-1." (string-take commit 8)))
4789 (url "https://github.com/tjunier/newick_utils.git")
4791 (file-name (string-append name "-" version "-checkout"))
4794 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4795 (build-system gnu-build-system)
4797 ;; XXX: TODO: Enable Lua and Guile bindings.
4798 ;; https://github.com/tjunier/newick_utils/issues/13
4799 `(("libxml2" ,libxml2)
4803 `(("autoconf" ,autoconf)
4804 ("automake" ,automake)
4805 ("libtool" ,libtool)))
4806 (synopsis "Programs for working with newick format phylogenetic trees")
4808 "Newick-utils is a suite of utilities for processing phylogenetic trees
4809 in Newick format. Functions include re-rooting, extracting subtrees,
4810 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4811 (home-page "https://github.com/tjunier/newick_utils")
4812 (license license:bsd-3))))
4821 "https://github.com/wwood/OrfM/releases/download/v"
4822 version "/orfm-" version ".tar.gz"))
4825 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4826 (build-system gnu-build-system)
4827 (inputs `(("zlib" ,zlib)))
4829 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4830 ("ruby-rspec" ,ruby-rspec)
4832 (synopsis "Simple and not slow open reading frame (ORF) caller")
4834 "An ORF caller finds stretches of DNA that, when translated, are not
4835 interrupted by stop codons. OrfM finds and prints these ORFs.")
4836 (home-page "https://github.com/wwood/OrfM")
4837 (license license:lgpl3+)))
4839 (define-public python2-pbcore
4841 (name "python2-pbcore")
4845 (uri (pypi-uri "pbcore" version))
4848 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4849 (build-system python-build-system)
4851 `(#:python ,python-2 ;pbcore < 2.0 requires Python 2.7
4852 #:phases (modify-phases %standard-phases
4853 (add-after 'unpack 'remove-sphinx-dependency
4855 ;; Sphinx is only required for documentation tests, which
4856 ;; we do not run; furthermore it depends on python2-sphinx
4857 ;; which is no longer maintained.
4858 (substitute* "requirements-dev.txt"
4862 `(("python-cython" ,python2-cython)
4863 ("python-numpy" ,python2-numpy)
4864 ("python-pysam" ,python2-pysam)
4865 ("python-h5py" ,python2-h5py)))
4867 `(("python-nose" ,python2-nose)
4868 ("python-pyxb" ,python2-pyxb)))
4869 (home-page "https://pacificbiosciences.github.io/pbcore/")
4870 (synopsis "Library for reading and writing PacBio data files")
4872 "The pbcore package provides Python APIs for interacting with PacBio data
4873 files and writing bioinformatics applications.")
4874 (license license:bsd-3)))
4876 (define-public python2-warpedlmm
4878 (name "python2-warpedlmm")
4883 (uri (pypi-uri "WarpedLMM" version ".zip"))
4886 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4887 (build-system python-build-system)
4889 `(#:python ,python-2)) ; requires Python 2.7
4891 `(("python-scipy" ,python2-scipy)
4892 ("python-numpy" ,python2-numpy)
4893 ("python-matplotlib" ,python2-matplotlib)
4894 ("python-fastlmm" ,python2-fastlmm)
4895 ("python-pandas" ,python2-pandas)
4896 ("python-pysnptools" ,python2-pysnptools)))
4898 `(("python-mock" ,python2-mock)
4899 ("python-nose" ,python2-nose)
4901 (home-page "https://github.com/PMBio/warpedLMM")
4902 (synopsis "Implementation of warped linear mixed models")
4904 "WarpedLMM is a Python implementation of the warped linear mixed model,
4905 which automatically learns an optimal warping function (or transformation) for
4906 the phenotype as it models the data.")
4907 (license license:asl2.0)))
4909 (define-public pbtranscript-tofu
4910 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
4912 (name "pbtranscript-tofu")
4913 (version (string-append "2.2.3." (string-take commit 7)))
4917 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
4919 (file-name (string-append name "-" version "-checkout"))
4922 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
4923 (modules '((guix build utils)))
4926 ;; remove bundled Cython sources
4927 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
4929 (build-system python-build-system)
4931 `(#:python ,python-2
4932 ;; FIXME: Tests fail with "No such file or directory:
4933 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
4936 (modify-phases %standard-phases
4937 (add-after 'unpack 'enter-directory
4939 (chdir "pbtranscript-tofu/pbtranscript/")
4941 ;; With setuptools version 18.0 and later this setup.py hack causes
4942 ;; a build error, so we disable it.
4943 (add-after 'enter-directory 'patch-setuppy
4945 (substitute* "setup.py"
4946 (("if 'setuptools.extension' in sys.modules:")
4950 `(("python-numpy" ,python2-numpy)
4951 ("python-bx-python" ,python2-bx-python)
4952 ("python-networkx" ,python2-networkx)
4953 ("python-scipy" ,python2-scipy)
4954 ("python-pbcore" ,python2-pbcore)
4955 ("python-h5py" ,python2-h5py)))
4957 `(("python-cython" ,python2-cython)
4958 ("python-nose" ,python2-nose)))
4959 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4960 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4962 "pbtranscript-tofu contains scripts to analyze transcriptome data
4963 generated using the PacBio Iso-Seq protocol.")
4964 (license license:bsd-3))))
4966 (define-public prank
4973 "http://wasabiapp.org/download/prank/prank.source."
4977 "0nc8g9c5rkdxcir46s0in9ci1sxwzbjibxrvkksf22ybnplvagk2"))))
4978 (build-system gnu-build-system)
4981 (modify-phases %standard-phases
4982 (add-after 'unpack 'enter-src-dir
4986 (add-after 'unpack 'remove-m64-flag
4987 ;; Prank will build with the correct 'bit-ness' without this flag
4988 ;; and this allows building on 32-bit machines.
4989 (lambda _ (substitute* "src/Makefile"
4994 (lambda* (#:key outputs #:allow-other-keys)
4995 (let* ((out (assoc-ref outputs "out"))
4996 (bin (string-append out "/bin"))
4997 (man (string-append out "/share/man/man1"))
4998 (path (string-append
4999 (assoc-ref %build-inputs "mafft") "/bin:"
5000 (assoc-ref %build-inputs "exonerate") "/bin:"
5001 (assoc-ref %build-inputs "bppsuite") "/bin")))
5002 (install-file "prank" bin)
5003 (wrap-program (string-append bin "/prank")
5004 `("PATH" ":" prefix (,path)))
5005 (install-file "prank.1" man))
5009 ("exonerate" ,exonerate)
5010 ("bppsuite" ,bppsuite)))
5011 (home-page "http://wasabiapp.org/software/prank/")
5012 (synopsis "Probabilistic multiple sequence alignment program")
5014 "PRANK is a probabilistic multiple sequence alignment program for DNA,
5015 codon and amino-acid sequences. It is based on a novel algorithm that treats
5016 insertions correctly and avoids over-estimation of the number of deletion
5017 events. In addition, PRANK borrows ideas from maximum likelihood methods used
5018 in phylogenetics and correctly takes into account the evolutionary distances
5019 between sequences. Lastly, PRANK allows for defining a potential structure
5020 for sequences to be aligned and then, simultaneously with the alignment,
5021 predicts the locations of structural units in the sequences.")
5022 (license license:gpl2+)))
5024 (define-public proteinortho
5026 (name "proteinortho")
5031 (url "https://gitlab.com/paulklemm_PHD/proteinortho.git")
5032 (commit (string-append "v" version))))
5033 (file-name (git-file-name name version))
5036 "0pmy617zy2z2w6hjqxjhf3rzikf5n3mpia80ysq8233vfr7wrzff"))
5037 (modules '((guix build utils)))
5040 ;; remove pre-built scripts
5041 (delete-file-recursively "src/BUILD/")
5043 (build-system gnu-build-system)
5045 `(#:test-target "test"
5046 #:make-flags '("CC=gcc")
5048 (modify-phases %standard-phases
5050 ;; There is no configure script, so we modify the Makefile directly.
5051 (lambda* (#:key outputs #:allow-other-keys)
5052 (substitute* "Makefile"
5055 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
5057 (add-before 'install 'make-install-directory
5058 ;; The install directory is not created during 'make install'.
5059 (lambda* (#:key outputs #:allow-other-keys)
5060 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
5062 (add-after 'install 'wrap-programs
5063 (lambda* (#:key inputs outputs #:allow-other-keys)
5064 (let ((path (getenv "PATH"))
5065 (out (assoc-ref outputs "out")))
5066 (for-each (lambda (script)
5067 (wrap-script script `("PATH" ":" prefix (,path))))
5068 (cons (string-append out "/bin/proteinortho")
5069 (find-files out "\\.(pl|py)$"))))
5072 `(("guile" ,guile-3.0) ; for wrap-script
5073 ("diamond" ,diamond)
5075 ("python" ,python-wrapper)
5078 ("openblas" ,openblas)))
5080 `(("which" ,which)))
5081 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
5082 (synopsis "Detect orthologous genes across species")
5084 "Proteinortho is a tool to detect orthologous genes across different
5085 species. For doing so, it compares similarities of given gene sequences and
5086 clusters them to find significant groups. The algorithm was designed to handle
5087 large-scale data and can be applied to hundreds of species at once.")
5088 (license license:gpl3+)))
5090 (define-public pyicoteo
5098 (url "https://bitbucket.org/regulatorygenomicsupf/pyicoteo.git")
5099 (commit (string-append "v" version))))
5100 (file-name (git-file-name name version))
5103 "0hz5g8d25lbjy1wpscr490l0lmyvaix893hhax4fxnh1h9w34w8p"))))
5104 (build-system python-build-system)
5106 `(#:python ,python-2 ; does not work with Python 3
5107 #:tests? #f)) ; there are no tests
5109 `(("python2-matplotlib" ,python2-matplotlib)))
5110 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
5111 (synopsis "Analyze high-throughput genetic sequencing data")
5113 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
5114 sequencing data. It works with genomic coordinates. There are currently six
5115 different command-line tools:
5118 @item pyicoregion: for generating exploratory regions automatically;
5119 @item pyicoenrich: for differential enrichment between two conditions;
5120 @item pyicoclip: for calling CLIP-Seq peaks without a control;
5121 @item pyicos: for genomic coordinates manipulation;
5122 @item pyicoller: for peak calling on punctuated ChIP-Seq;
5123 @item pyicount: to count how many reads from N experiment files overlap in a
5125 @item pyicotrocol: to combine operations from pyicoteo.
5127 (license license:gpl3+)))
5129 (define-public prodigal
5132 ;; Check for a new home page when updating this package:
5133 ;; https://github.com/hyattpd/Prodigal/issues/36#issuecomment-536617588
5138 (url "https://github.com/hyattpd/Prodigal.git")
5139 (commit (string-append "v" version))))
5140 (file-name (git-file-name name version))
5143 "1fs1hqk83qjbjhrvhw6ni75zakx5ki1ayy3v6wwkn3xvahc9hi5s"))))
5144 (build-system gnu-build-system)
5146 `(#:tests? #f ; no check target
5147 #:make-flags (list (string-append "INSTALLDIR="
5148 (assoc-ref %outputs "out")
5151 (modify-phases %standard-phases
5152 (delete 'configure))))
5153 (home-page "https://github.com/hyattpd/Prodigal")
5154 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
5156 "Prodigal runs smoothly on finished genomes, draft genomes, and
5157 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
5158 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
5159 partial genes, and identifies translation initiation sites.")
5160 (license license:gpl3+)))
5162 (define-public roary
5170 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
5174 "0qxrds9wx7cfhlkihrp6697kx0flhhxymap9fwan0b3rbdhcnmff"))))
5175 (build-system perl-build-system)
5178 (modify-phases %standard-phases
5183 ;; The tests are not run by default, so we run each test file
5185 (setenv "PATH" (string-append (getcwd) "/bin" ":"
5187 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
5188 (getenv "PERL5LIB")))
5189 (for-each (lambda (file)
5190 (display file)(display "\n")
5191 (invoke "perl" file))
5192 (find-files "t" ".*\\.t$"))
5195 ;; There is no 'install' target in the Makefile.
5196 (lambda* (#:key outputs #:allow-other-keys)
5197 (let* ((out (assoc-ref outputs "out"))
5198 (bin (string-append out "/bin"))
5199 (perl (string-append out "/lib/perl5/site_perl"))
5200 (roary-plots "contrib/roary_plots"))
5203 (copy-recursively "bin" bin)
5204 (copy-recursively "lib" perl)
5206 (add-after 'install 'wrap-programs
5207 (lambda* (#:key inputs outputs #:allow-other-keys)
5208 (let* ((out (assoc-ref outputs "out"))
5209 (perl5lib (getenv "PERL5LIB"))
5210 (path (getenv "PATH")))
5211 (for-each (lambda (prog)
5212 (let ((binary (string-append out "/" prog)))
5213 (wrap-program binary
5214 `("PERL5LIB" ":" prefix
5215 (,(string-append perl5lib ":" out
5216 "/lib/perl5/site_perl"))))
5217 (wrap-program binary
5219 (,(string-append path ":" out "/bin"))))))
5220 (find-files "bin" ".*[^R]$"))
5222 (string-append out "/bin/roary-create_pan_genome_plots.R"))
5223 (r-site-lib (getenv "R_LIBS_SITE"))
5225 (string-append (assoc-ref inputs "coreutils") "/bin")))
5227 `("R_LIBS_SITE" ":" prefix
5228 (,(string-append r-site-lib ":" out "/site-library/"))))
5231 (,(string-append coreutils-path ":" out "/bin"))))))
5234 `(("perl-env-path" ,perl-env-path)
5235 ("perl-test-files" ,perl-test-files)
5236 ("perl-test-most" ,perl-test-most)
5237 ("perl-test-output" ,perl-test-output)))
5239 `(("perl-array-utils" ,perl-array-utils)
5240 ("bioperl" ,bioperl-minimal)
5241 ("perl-digest-md5-file" ,perl-digest-md5-file)
5242 ("perl-exception-class" ,perl-exception-class)
5243 ("perl-file-find-rule" ,perl-file-find-rule)
5244 ("perl-file-grep" ,perl-file-grep)
5245 ("perl-file-slurper" ,perl-file-slurper)
5246 ("perl-file-which" ,perl-file-which)
5247 ("perl-graph" ,perl-graph)
5248 ("perl-graph-readwrite" ,perl-graph-readwrite)
5249 ("perl-log-log4perl" ,perl-log-log4perl)
5250 ("perl-moose" ,perl-moose)
5251 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
5252 ("perl-text-csv" ,perl-text-csv)
5253 ("bedtools" ,bedtools)
5257 ("parallel" ,parallel)
5260 ("fasttree" ,fasttree)
5264 ("r-minimal" ,r-minimal)
5265 ("r-ggplot2" ,r-ggplot2)
5266 ("coreutils" ,coreutils)))
5267 (home-page "https://sanger-pathogens.github.io/Roary/")
5268 (synopsis "High speed stand-alone pan genome pipeline")
5270 "Roary is a high speed stand alone pan genome pipeline, which takes
5271 annotated assemblies in GFF3 format (produced by the Prokka program) and
5272 calculates the pan genome. Using a standard desktop PC, it can analyse
5273 datasets with thousands of samples, without compromising the quality of the
5274 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
5275 single processor. Roary is not intended for metagenomics or for comparing
5276 extremely diverse sets of genomes.")
5277 (license license:gpl3)))
5279 (define-public raxml
5287 (url "https://github.com/stamatak/standard-RAxML.git")
5288 (commit (string-append "v" version))))
5289 (file-name (git-file-name name version))
5292 "1jqjzhch0rips0vp04prvb8vmc20c5pdmsqn8knadcf91yy859fh"))))
5293 (build-system gnu-build-system)
5295 `(#:tests? #f ; There are no tests.
5296 ;; Use 'standard' Makefile rather than SSE or AVX ones.
5297 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
5299 (modify-phases %standard-phases
5302 (lambda* (#:key outputs #:allow-other-keys)
5303 (let* ((out (assoc-ref outputs "out"))
5304 (bin (string-append out "/bin"))
5305 (executable "raxmlHPC-HYBRID"))
5306 (install-file executable bin)
5307 (symlink (string-append bin "/" executable) "raxml"))
5310 `(("openmpi" ,openmpi)))
5311 (home-page "https://cme.h-its.org/exelixis/web/software/raxml/index.html")
5312 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
5314 "RAxML is a tool for phylogenetic analysis and post-analysis of large
5316 ;; The source includes x86 specific code
5317 (supported-systems '("x86_64-linux" "i686-linux"))
5318 (license license:gpl2+)))
5328 (url "https://github.com/deweylab/RSEM.git")
5329 (commit (string-append "v" version))))
5331 (base32 "1jlq11d1p8qp64w75yj8cnbbd1a93viq10pzsbwal7vdn8fg13j1"))
5332 (file-name (git-file-name name version))
5333 (modules '((guix build utils)))
5336 ;; remove bundled copy of boost and samtools
5337 (delete-file-recursively "boost")
5338 (delete-file-recursively "samtools-1.3")
5340 (build-system gnu-build-system)
5342 `(#:tests? #f ;no "check" target
5344 (list (string-append "BOOST="
5345 (assoc-ref %build-inputs "boost")
5347 (string-append "SAMHEADERS="
5348 (assoc-ref %build-inputs "htslib")
5349 "/include/htslib/sam.h")
5350 (string-append "SAMLIBS="
5351 (assoc-ref %build-inputs "htslib")
5354 (modify-phases %standard-phases
5355 ;; No "configure" script.
5356 ;; Do not build bundled samtools library.
5359 (substitute* "Makefile"
5360 (("^all : \\$\\(PROGRAMS\\).*") "all: $(PROGRAMS)\n")
5361 (("^\\$\\(SAMLIBS\\).*") ""))
5364 (lambda* (#:key outputs #:allow-other-keys)
5365 (let* ((out (string-append (assoc-ref outputs "out")))
5366 (bin (string-append out "/bin/"))
5367 (perl (string-append out "/lib/perl5/site_perl")))
5370 (for-each (lambda (file)
5371 (install-file file bin))
5372 (find-files "." "rsem-.*"))
5373 (install-file "rsem_perl_utils.pm" perl))
5375 (add-after 'install 'wrap-program
5376 (lambda* (#:key outputs #:allow-other-keys)
5377 (let ((out (assoc-ref outputs "out")))
5378 (for-each (lambda (prog)
5379 (wrap-program (string-append out "/bin/" prog)
5380 `("PERL5LIB" ":" prefix
5381 (,(string-append out "/lib/perl5/site_perl")))))
5382 '("rsem-calculate-expression"
5384 "rsem-generate-data-matrix"
5385 "rsem-generate-ngvector"
5386 "rsem-plot-transcript-wiggles"
5387 "rsem-prepare-reference"
5389 "rsem-run-prsem-testing-procedure")))
5393 ("r-minimal" ,r-minimal)
5395 ("htslib" ,htslib-1.3)
5397 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
5398 (synopsis "Estimate gene expression levels from RNA-Seq data")
5400 "RSEM is a software package for estimating gene and isoform expression
5401 levels from RNA-Seq data. The RSEM package provides a user-friendly
5402 interface, supports threads for parallel computation of the EM algorithm,
5403 single-end and paired-end read data, quality scores, variable-length reads and
5404 RSPD estimation. In addition, it provides posterior mean and 95% credibility
5405 interval estimates for expression levels. For visualization, it can generate
5406 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
5407 (license license:gpl3+)))
5409 (define-public rseqc
5417 (string-append "mirror://sourceforge/rseqc/"
5418 "RSeQC-" version ".tar.gz"))
5421 "0gbb9iyb7swiv5455fm5rg98r7l6qn27v564yllqjd574hncpx6m"))))
5422 (build-system python-build-system)
5424 `(("python-cython" ,python-cython)
5425 ("python-bx-python" ,python-bx-python)
5426 ("python-pybigwig" ,python-pybigwig)
5427 ("python-pysam" ,python-pysam)
5428 ("python-numpy" ,python-numpy)
5431 `(("python-nose" ,python-nose)))
5432 (home-page "http://rseqc.sourceforge.net/")
5433 (synopsis "RNA-seq quality control package")
5435 "RSeQC provides a number of modules that can comprehensively evaluate
5436 high throughput sequence data, especially RNA-seq data. Some basic modules
5437 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
5438 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
5439 distribution, coverage uniformity, strand specificity, etc.")
5440 (license license:gpl3+)))
5443 ;; There are no release tarballs. According to the installation
5444 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
5445 ;; stable release is identified by this changeset ID.
5446 (let ((changeset "2329130")
5450 (version (string-append "0-" revision "." changeset))
5454 (url "https://bitbucket.org/libsleipnir/sleipnir")
5455 (changeset changeset)))
5456 (file-name (string-append name "-" version "-checkout"))
5459 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
5460 (build-system gnu-build-system)
5462 `(#:modules ((srfi srfi-1)
5463 (guix build gnu-build-system)
5466 (let ((dirs '("SeekMiner"
5472 (modify-phases %standard-phases
5475 (substitute* "gen_tools_am"
5476 (("/usr/bin/env.*") (which "perl")))
5477 (invoke "bash" "gen_auto")
5479 (add-after 'build 'build-additional-tools
5480 (lambda* (#:key make-flags #:allow-other-keys)
5481 (for-each (lambda (dir)
5482 (with-directory-excursion (string-append "tools/" dir)
5483 (apply invoke "make" make-flags)))
5486 (add-after 'install 'install-additional-tools
5487 (lambda* (#:key make-flags #:allow-other-keys)
5488 (for-each (lambda (dir)
5489 (with-directory-excursion (string-append "tools/" dir)
5490 (apply invoke `("make" ,@make-flags "install"))))
5497 ("readline" ,readline)
5498 ("gengetopt" ,gengetopt)
5499 ("log4cpp" ,log4cpp)))
5501 `(("autoconf" ,autoconf)
5502 ("automake" ,automake)
5504 (home-page "http://seek.princeton.edu")
5505 (synopsis "Gene co-expression search engine")
5507 "SEEK is a computational gene co-expression search engine. SEEK provides
5508 biologists with a way to navigate the massive human expression compendium that
5509 now contains thousands of expression datasets. SEEK returns a robust ranking
5510 of co-expressed genes in the biological area of interest defined by the user's
5511 query genes. It also prioritizes thousands of expression datasets according
5512 to the user's query of interest.")
5513 (license license:cc-by3.0))))
5515 (define-public samtools
5523 (string-append "mirror://sourceforge/samtools/samtools/"
5524 version "/samtools-" version ".tar.bz2"))
5527 "10ilqbmm7ri8z431sn90lvbjwizd0hhkf9rcqw8j823hf26nhgq8"))
5528 (modules '((guix build utils)))
5530 ;; Delete bundled htslib.
5531 (delete-file-recursively "htslib-1.9")
5533 (build-system gnu-build-system)
5535 `(#:modules ((ice-9 ftw)
5537 (guix build gnu-build-system)
5539 #:configure-flags (list "--with-ncurses")
5541 (modify-phases %standard-phases
5542 (add-after 'unpack 'patch-tests
5544 (substitute* "test/test.pl"
5545 ;; The test script calls out to /bin/bash
5546 (("/bin/bash") (which "bash")))
5548 (add-after 'install 'install-library
5549 (lambda* (#:key outputs #:allow-other-keys)
5550 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
5551 (install-file "libbam.a" lib)
5553 (add-after 'install 'install-headers
5554 (lambda* (#:key outputs #:allow-other-keys)
5555 (let ((include (string-append (assoc-ref outputs "out")
5556 "/include/samtools/")))
5557 (for-each (lambda (file)
5558 (install-file file include))
5559 (scandir "." (lambda (name) (string-match "\\.h$" name))))
5561 (native-inputs `(("pkg-config" ,pkg-config)))
5563 `(("htslib" ,htslib)
5564 ("ncurses" ,ncurses)
5568 (home-page "http://samtools.sourceforge.net")
5569 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
5571 "Samtools implements various utilities for post-processing nucleotide
5572 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
5573 variant calling (in conjunction with bcftools), and a simple alignment
5575 (license license:expat)))
5577 (define-public samtools-0.1
5578 ;; This is the most recent version of the 0.1 line of samtools. The input
5579 ;; and output formats differ greatly from that used and produced by samtools
5580 ;; 1.x and is still used in many bioinformatics pipelines.
5581 (package (inherit samtools)
5587 (string-append "mirror://sourceforge/samtools/samtools/"
5588 version "/samtools-" version ".tar.bz2"))
5590 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
5592 `(#:tests? #f ;no "check" target
5594 (list "LIBCURSES=-lncurses")
5595 ,@(substitute-keyword-arguments (package-arguments samtools)
5597 `(modify-phases ,phases
5599 (lambda* (#:key outputs #:allow-other-keys)
5600 (let ((bin (string-append
5601 (assoc-ref outputs "out") "/bin")))
5603 (install-file "samtools" bin)
5605 (delete 'patch-tests)
5606 (delete 'configure))))))))
5608 (define-public mosaik
5609 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
5614 ;; There are no release tarballs nor tags.
5617 (url "https://github.com/wanpinglee/MOSAIK.git")
5619 (file-name (string-append name "-" version))
5622 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
5623 (build-system gnu-build-system)
5625 `(#:tests? #f ; no tests
5626 #:make-flags (list "CC=gcc")
5628 (modify-phases %standard-phases
5630 (lambda _ (chdir "src") #t))
5632 (lambda* (#:key outputs #:allow-other-keys)
5633 (let ((bin (string-append (assoc-ref outputs "out")
5636 (copy-recursively "../bin" bin)
5640 ("zlib:static" ,zlib "static")
5642 (supported-systems '("x86_64-linux"))
5643 (home-page "https://github.com/wanpinglee/MOSAIK")
5644 (synopsis "Map nucleotide sequence reads to reference genomes")
5646 "MOSAIK is a program for mapping second and third-generation sequencing
5647 reads to a reference genome. MOSAIK can align reads generated by all the
5648 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
5649 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
5650 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
5651 ;; code released into the public domain:
5652 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
5653 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
5654 (license (list license:gpl2+ license:public-domain)))))
5656 (define-public ngs-sdk
5663 (url "https://github.com/ncbi/ngs.git")
5665 (file-name (git-file-name name version))
5668 "0d5k5kabgl15as37kj9x65xc92j4gcqms86hvihw3yb6wag0r0q3"))))
5669 (build-system gnu-build-system)
5671 `(#:parallel-build? #f ; not supported
5672 #:tests? #f ; no "check" target
5674 (modify-phases %standard-phases
5676 (lambda* (#:key outputs #:allow-other-keys)
5677 (let ((out (assoc-ref outputs "out")))
5678 ;; Allow 'konfigure.perl' to find 'package.prl'.
5680 (string-append ".:" (getenv "PERL5LIB")))
5682 ;; The 'configure' script doesn't recognize things like
5683 ;; '--enable-fast-install'.
5684 (invoke "./configure"
5685 (string-append "--build-prefix=" (getcwd) "/build")
5686 (string-append "--prefix=" out))
5688 (add-after 'unpack 'enter-dir
5689 (lambda _ (chdir "ngs-sdk") #t)))))
5690 (native-inputs `(("perl" ,perl)))
5691 ;; According to the test
5692 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
5693 ;; in ngs-sdk/setup/konfigure.perl
5694 (supported-systems '("i686-linux" "x86_64-linux"))
5695 (home-page "https://github.com/ncbi/ngs")
5696 (synopsis "API for accessing Next Generation Sequencing data")
5698 "NGS is a domain-specific API for accessing reads, alignments and pileups
5699 produced from Next Generation Sequencing. The API itself is independent from
5700 any particular back-end implementation, and supports use of multiple back-ends
5702 (license license:public-domain)))
5704 (define-public java-ngs
5705 (package (inherit ngs-sdk)
5708 `(,@(substitute-keyword-arguments
5709 `(#:modules ((guix build gnu-build-system)
5713 ,@(package-arguments ngs-sdk))
5715 `(modify-phases ,phases
5716 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5718 `(("jdk" ,icedtea "jdk")
5719 ("ngs-sdk" ,ngs-sdk)))
5720 (synopsis "Java bindings for NGS SDK")))
5722 (define-public ncbi-vdb
5729 (url "https://github.com/ncbi/ncbi-vdb.git")
5731 (file-name (git-file-name name version))
5734 "0knkj1sq34hlivgv5qd6jlczqrs3ldmfgn6vbbw7p4mqxvb9mirk"))))
5735 (build-system gnu-build-system)
5737 `(#:parallel-build? #f ; not supported
5738 #:tests? #f ; no "check" target
5739 #:make-flags '("HAVE_HDF5=1")
5741 (modify-phases %standard-phases
5742 (add-after 'unpack 'make-files-writable
5743 (lambda _ (for-each make-file-writable (find-files "." ".*")) #t))
5744 (add-before 'configure 'set-perl-search-path
5746 ;; Work around "dotless @INC" build failure.
5748 (string-append (getcwd) "/setup:"
5749 (getenv "PERL5LIB")))
5751 ;; See https://github.com/ncbi/ncbi-vdb/issues/14
5752 (add-after 'unpack 'patch-krypto-flags
5754 (substitute* "libs/krypto/Makefile"
5755 (("-Wa,-march=generic64\\+aes") "")
5756 (("-Wa,-march=generic64\\+sse4") ""))
5759 (lambda* (#:key inputs outputs #:allow-other-keys)
5760 (let ((out (assoc-ref outputs "out")))
5761 ;; Override include path for libmagic
5762 (substitute* "setup/package.prl"
5763 (("name => 'magic', Include => '/usr/include'")
5764 (string-append "name=> 'magic', Include => '"
5765 (assoc-ref inputs "libmagic")
5768 ;; Install kdf5 library (needed by sra-tools)
5769 (substitute* "build/Makefile.install"
5770 (("LIBRARIES_TO_INSTALL =")
5771 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5773 (substitute* "build/Makefile.env"
5774 (("CFLAGS =" prefix)
5775 (string-append prefix "-msse2 ")))
5777 ;; Override search path for ngs-java
5778 (substitute* "setup/package.prl"
5779 (("/usr/local/ngs/ngs-java")
5780 (assoc-ref inputs "java-ngs")))
5782 ;; The 'configure' script doesn't recognize things like
5783 ;; '--enable-fast-install'.
5784 (invoke "./configure"
5785 (string-append "--build-prefix=" (getcwd) "/build")
5786 (string-append "--prefix=" (assoc-ref outputs "out"))
5787 (string-append "--debug")
5788 (string-append "--with-xml2-prefix="
5789 (assoc-ref inputs "libxml2"))
5790 (string-append "--with-ngs-sdk-prefix="
5791 (assoc-ref inputs "ngs-sdk"))
5792 (string-append "--with-hdf5-prefix="
5793 (assoc-ref inputs "hdf5")))
5795 (add-after 'install 'install-interfaces
5796 (lambda* (#:key outputs #:allow-other-keys)
5797 ;; Install interface libraries. On i686 the interface libraries
5798 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5799 ;; architecture name ("i386") instead of the target system prefix
5801 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5802 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5803 ,(system->linux-architecture
5804 (or (%current-target-system)
5807 (string-append (assoc-ref outputs "out")
5809 ;; Install interface headers
5810 (copy-recursively "interfaces"
5811 (string-append (assoc-ref outputs "out")
5814 ;; These files are needed by sra-tools.
5815 (add-after 'install 'install-configuration-files
5816 (lambda* (#:key outputs #:allow-other-keys)
5817 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5819 (install-file "libs/kfg/default.kfg" target)
5820 (install-file "libs/kfg/certs.kfg" target))
5823 `(("libxml2" ,libxml2)
5824 ("ngs-sdk" ,ngs-sdk)
5825 ("java-ngs" ,java-ngs)
5828 (native-inputs `(("perl" ,perl)))
5829 ;; NCBI-VDB requires SSE capability.
5830 (supported-systems '("i686-linux" "x86_64-linux"))
5831 (home-page "https://github.com/ncbi/ncbi-vdb")
5832 (synopsis "Database engine for genetic information")
5834 "The NCBI-VDB library implements a highly compressed columnar data
5835 warehousing engine that is most often used to store genetic information.
5836 Databases are stored in a portable image within the file system, and can be
5837 accessed/downloaded on demand across HTTP.")
5838 (license license:public-domain)))
5840 (define-public plink
5848 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5849 version "-src.zip"))
5851 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5852 (patches (search-patches "plink-1.07-unclobber-i.patch"
5853 "plink-endian-detection.patch"))))
5854 (build-system gnu-build-system)
5856 '(#:tests? #f ;no "check" target
5857 #:make-flags (list (string-append "LIB_LAPACK="
5858 (assoc-ref %build-inputs "lapack")
5859 "/lib/liblapack.so")
5862 ;; disable phoning home
5865 (modify-phases %standard-phases
5866 ;; no "configure" script
5869 (lambda* (#:key outputs #:allow-other-keys)
5870 (let ((bin (string-append (assoc-ref outputs "out")
5872 (install-file "plink" bin)
5876 ("lapack" ,lapack)))
5878 `(("unzip" ,unzip)))
5879 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5880 (synopsis "Whole genome association analysis toolset")
5882 "PLINK is a whole genome association analysis toolset, designed to
5883 perform a range of basic, large-scale analyses in a computationally efficient
5884 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5885 so there is no support for steps prior to this (e.g. study design and
5886 planning, generating genotype or CNV calls from raw data). Through
5887 integration with gPLINK and Haploview, there is some support for the
5888 subsequent visualization, annotation and storage of results.")
5889 ;; Code is released under GPLv2, except for fisher.h, which is under
5891 (license (list license:gpl2 license:lgpl2.1+))))
5893 (define-public plink-ng
5894 (package (inherit plink)
5901 (url "https://github.com/chrchang/plink-ng.git")
5902 (commit (string-append "v" version))))
5903 (file-name (git-file-name name version))
5905 (base32 "02npdwgkpfkdnhw819rhj5kw02a5k5m90b14zq9zzya4hyg929c0"))))
5906 (build-system gnu-build-system)
5908 '(#:tests? #f ;no "check" target
5909 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5910 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5912 "-f" "Makefile.std")
5914 (modify-phases %standard-phases
5915 (add-after 'unpack 'chdir
5916 (lambda _ (chdir "1.9") #t))
5917 (delete 'configure) ; no "configure" script
5919 (lambda* (#:key outputs #:allow-other-keys)
5920 (let ((bin (string-append (assoc-ref outputs "out")
5922 (install-file "plink" bin)
5927 ("openblas" ,openblas)))
5928 (home-page "https://www.cog-genomics.org/plink/")
5929 (license license:gpl3+)))
5931 (define-public smithlab-cpp
5932 (let ((revision "1")
5933 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
5935 (name "smithlab-cpp")
5936 (version (string-append "0." revision "." (string-take commit 7)))
5940 (url "https://github.com/smithlabcode/smithlab_cpp.git")
5942 (file-name (string-append name "-" version "-checkout"))
5945 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
5946 (build-system gnu-build-system)
5948 `(#:modules ((guix build gnu-build-system)
5951 #:tests? #f ;no "check" target
5953 (modify-phases %standard-phases
5954 (add-after 'unpack 'use-samtools-headers
5956 (substitute* '("SAM.cpp"
5958 (("sam.h") "samtools/sam.h"))
5961 (lambda* (#:key outputs #:allow-other-keys)
5962 (let* ((out (assoc-ref outputs "out"))
5963 (lib (string-append out "/lib"))
5964 (include (string-append out "/include/smithlab-cpp")))
5967 (for-each (cut install-file <> lib)
5968 (find-files "." "\\.o$"))
5969 (for-each (cut install-file <> include)
5970 (find-files "." "\\.hpp$")))
5972 (delete 'configure))))
5974 `(("samtools" ,samtools-0.1)
5976 (home-page "https://github.com/smithlabcode/smithlab_cpp")
5977 (synopsis "C++ helper library for functions used in Smith lab projects")
5979 "Smithlab CPP is a C++ library that includes functions used in many of
5980 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
5981 structures, classes for genomic regions, mapped sequencing reads, etc.")
5982 (license license:gpl3+))))
5984 (define-public preseq
5990 (uri (string-append "https://github.com/smithlabcode/preseq/"
5991 "releases/download/v" version
5992 "/preseq_v" version ".tar.bz2"))
5994 (base32 "149x9xmk1wy1gff85325yfzqc0qk4sgp1w6gbyj9cnji4x1dszbl"))
5995 (modules '((guix build utils)))
5997 ;; Remove bundled samtools.
5998 (delete-file-recursively "samtools")
6000 (build-system gnu-build-system)
6002 `(#:tests? #f ;no "check" target
6004 (modify-phases %standard-phases
6005 (delete 'configure))
6007 (list (string-append "PREFIX="
6008 (assoc-ref %outputs "out"))
6009 (string-append "LIBBAM="
6010 (assoc-ref %build-inputs "samtools")
6012 (string-append "SMITHLAB_CPP="
6013 (assoc-ref %build-inputs "smithlab-cpp")
6016 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
6019 ("samtools" ,samtools-0.1)
6020 ("smithlab-cpp" ,smithlab-cpp)
6022 (home-page "http://smithlabresearch.org/software/preseq/")
6023 (synopsis "Program for analyzing library complexity")
6025 "The preseq package is aimed at predicting and estimating the complexity
6026 of a genomic sequencing library, equivalent to predicting and estimating the
6027 number of redundant reads from a given sequencing depth and how many will be
6028 expected from additional sequencing using an initial sequencing experiment.
6029 The estimates can then be used to examine the utility of further sequencing,
6030 optimize the sequencing depth, or to screen multiple libraries to avoid low
6031 complexity samples.")
6032 (license license:gpl3+)))
6034 (define-public python-screed
6036 (name "python-screed")
6041 (uri (pypi-uri "screed" version))
6044 "148vcb7w2wr6a4w6vs2bsxanbqibxfk490zbcbg4m61s8669zdjx"))))
6045 (build-system python-build-system)
6048 (modify-phases %standard-phases
6049 ;; Tests must be run after installation, as the "screed" command does
6050 ;; not exist right after building.
6052 (add-after 'install 'check
6053 (lambda* (#:key inputs outputs #:allow-other-keys)
6054 (let ((out (assoc-ref outputs "out")))
6055 (setenv "PYTHONPATH"
6056 (string-append out "/lib/python"
6057 (string-take (string-take-right
6058 (assoc-ref inputs "python")
6061 (getenv "PYTHONPATH")))
6062 (setenv "PATH" (string-append out "/bin:" (getenv "PATH"))))
6063 (invoke "python" "setup.py" "test")
6066 `(("python-pytest" ,python-pytest)
6067 ("python-pytest-cov" ,python-pytest-cov)
6068 ("python-pytest-runner" ,python-pytest-runner)))
6070 `(("python-bz2file" ,python-bz2file)))
6071 (home-page "https://github.com/dib-lab/screed/")
6072 (synopsis "Short read sequence database utilities")
6073 (description "Screed parses FASTA and FASTQ files and generates databases.
6074 Values such as sequence name, sequence description, sequence quality and the
6075 sequence itself can be retrieved from these databases.")
6076 (license license:bsd-3)))
6078 (define-public python2-screed
6079 (package-with-python2 python-screed))
6081 (define-public sra-tools
6089 (url "https://github.com/ncbi/sra-tools.git")
6091 (file-name (git-file-name name version))
6094 "0vqzap68v81k0zif2mnqfy8pnw2nrhsg87p6mgq8qk3nk2jv2rgy"))))
6095 (build-system gnu-build-system)
6097 `(#:parallel-build? #f ; not supported
6098 #:tests? #f ; no "check" target
6100 (list (string-append "DEFAULT_CRT="
6101 (assoc-ref %build-inputs "ncbi-vdb")
6103 (string-append "DEFAULT_KFG="
6104 (assoc-ref %build-inputs "ncbi-vdb")
6106 (string-append "VDB_LIBDIR="
6107 (assoc-ref %build-inputs "ncbi-vdb")
6108 ,(if (string-prefix? "x86_64"
6109 (or (%current-target-system)
6114 (modify-phases %standard-phases
6115 (add-before 'configure 'set-perl-search-path
6117 ;; Work around "dotless @INC" build failure.
6119 (string-append (getcwd) "/setup:"
6120 (getenv "PERL5LIB")))
6123 (lambda* (#:key inputs outputs #:allow-other-keys)
6124 ;; The build system expects a directory containing the sources and
6125 ;; raw build output of ncbi-vdb, including files that are not
6126 ;; installed. Since we are building against an installed version of
6127 ;; ncbi-vdb, the following modifications are needed.
6128 (substitute* "setup/konfigure.perl"
6129 ;; Make the configure script look for the "ilib" directory of
6130 ;; "ncbi-vdb" without first checking for the existence of a
6131 ;; matching library in its "lib" directory.
6132 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
6133 "my $f = File::Spec->catdir($ilibdir, $ilib);")
6134 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
6135 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
6136 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
6139 (substitute* "tools/copycat/Makefile"
6140 (("smagic-static") "lmagic"))
6142 ;; The 'configure' script doesn't recognize things like
6143 ;; '--enable-fast-install'.
6144 (invoke "./configure"
6145 (string-append "--build-prefix=" (getcwd) "/build")
6146 (string-append "--prefix=" (assoc-ref outputs "out"))
6147 (string-append "--debug")
6148 (string-append "--with-fuse-prefix="
6149 (assoc-ref inputs "fuse"))
6150 (string-append "--with-magic-prefix="
6151 (assoc-ref inputs "libmagic"))
6152 ;; TODO: building with libxml2 fails with linker errors
6153 ;; (string-append "--with-xml2-prefix="
6154 ;; (assoc-ref inputs "libxml2"))
6155 (string-append "--with-ncbi-vdb-sources="
6156 (assoc-ref inputs "ncbi-vdb"))
6157 (string-append "--with-ncbi-vdb-build="
6158 (assoc-ref inputs "ncbi-vdb"))
6159 (string-append "--with-ngs-sdk-prefix="
6160 (assoc-ref inputs "ngs-sdk"))
6161 (string-append "--with-hdf5-prefix="
6162 (assoc-ref inputs "hdf5")))
6164 (native-inputs `(("perl" ,perl)))
6166 `(("ngs-sdk" ,ngs-sdk)
6167 ("ncbi-vdb" ,ncbi-vdb)
6173 "https://trace.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
6174 (synopsis "Tools and libraries for reading and writing sequencing data")
6176 "The SRA Toolkit from NCBI is a collection of tools and libraries for
6177 reading of sequencing files from the Sequence Read Archive (SRA) database and
6178 writing files into the .sra format.")
6179 (license license:public-domain)))
6181 (define-public seqan
6187 (uri (string-append "https://github.com/seqan/seqan/releases/"
6188 "download/seqan-v" version
6189 "/seqan-library-" version ".tar.xz"))
6192 "19a1rlxx03qy1i1iriicly68w64yjxbv24g9gdywnfmq998v35yx"))))
6193 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6194 ;; makes sense to split the outputs.
6195 (outputs '("out" "doc"))
6196 (build-system trivial-build-system)
6198 `(#:modules ((guix build utils))
6201 (use-modules (guix build utils))
6202 (let ((tar (assoc-ref %build-inputs "tar"))
6203 (xz (assoc-ref %build-inputs "xz"))
6204 (out (assoc-ref %outputs "out"))
6205 (doc (assoc-ref %outputs "doc")))
6206 (setenv "PATH" (string-append tar "/bin:" xz "/bin"))
6207 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6208 (chdir (string-append "seqan-library-" ,version))
6209 (copy-recursively "include" (string-append out "/include"))
6210 (copy-recursively "share" (string-append doc "/share"))
6213 `(("source" ,source)
6216 (home-page "http://www.seqan.de")
6217 (synopsis "Library for nucleotide sequence analysis")
6219 "SeqAn is a C++ library of efficient algorithms and data structures for
6220 the analysis of sequences with the focus on biological data. It contains
6221 algorithms and data structures for string representation and their
6222 manipulation, online and indexed string search, efficient I/O of
6223 bioinformatics file formats, sequence alignment, and more.")
6224 (license license:bsd-3)))
6226 (define-public seqan-1
6227 (package (inherit seqan)
6232 (uri (string-append "http://packages.seqan.de/seqan-library/"
6233 "seqan-library-" version ".tar.bz2"))
6236 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
6237 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6238 ;; makes sense to split the outputs.
6239 (outputs '("out" "doc"))
6240 (build-system trivial-build-system)
6242 `(#:modules ((guix build utils))
6245 (use-modules (guix build utils))
6246 (let ((tar (assoc-ref %build-inputs "tar"))
6247 (bzip (assoc-ref %build-inputs "bzip2"))
6248 (out (assoc-ref %outputs "out"))
6249 (doc (assoc-ref %outputs "doc")))
6250 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
6251 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6252 (chdir (string-append "seqan-library-" ,version))
6253 (copy-recursively "include" (string-append out "/include"))
6254 (copy-recursively "share" (string-append doc "/share"))
6257 `(("source" ,source)
6259 ("bzip2" ,bzip2)))))
6261 (define-public seqmagick
6268 (uri (pypi-uri "seqmagick" version))
6271 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
6272 (build-system python-build-system)
6274 `(("python-biopython" ,python-biopython)))
6276 `(("python-nose" ,python-nose)))
6277 (home-page "https://github.com/fhcrc/seqmagick")
6278 (synopsis "Tools for converting and modifying sequence files")
6280 "Bioinformaticians often have to convert sequence files between formats
6281 and do little manipulations on them, and it's not worth writing scripts for
6282 that. Seqmagick is a utility to expose the file format conversion in
6283 BioPython in a convenient way. Instead of having a big mess of scripts, there
6284 is one that takes arguments.")
6285 (license license:gpl3)))
6287 (define-public seqtk
6294 (url "https://github.com/lh3/seqtk.git")
6295 (commit (string-append "v" version))))
6296 (file-name (git-file-name name version))
6299 "1bfzlqa84b5s1qi22blmmw2s8xdyp9h9ydcq22pfjhh5gab3yz6l"))))
6300 (build-system gnu-build-system)
6303 (modify-phases %standard-phases
6306 ;; There are no tests, so we just run a sanity check.
6307 (lambda _ (invoke "./seqtk" "seq") #t))
6309 (lambda* (#:key outputs #:allow-other-keys)
6310 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6311 (install-file "seqtk" bin)
6315 (home-page "https://github.com/lh3/seqtk")
6316 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
6318 "Seqtk is a fast and lightweight tool for processing sequences in the
6319 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
6320 optionally compressed by gzip.")
6321 (license license:expat)))
6323 (define-public snap-aligner
6325 (name "snap-aligner")
6326 (version "1.0beta.18")
6330 (url "https://github.com/amplab/snap.git")
6331 (commit (string-append "v" version))))
6332 (file-name (git-file-name name version))
6335 "01w3qq4wm07z73vky0cfwlmrbf50n3w722cxrlzxfi99mnb808d8"))))
6336 (build-system gnu-build-system)
6339 (modify-phases %standard-phases
6341 (replace 'check (lambda _ (invoke "./unit_tests") #t))
6343 (lambda* (#:key outputs #:allow-other-keys)
6344 (let* ((out (assoc-ref outputs "out"))
6345 (bin (string-append out "/bin")))
6346 (install-file "snap-aligner" bin)
6347 (install-file "SNAPCommand" bin)
6351 (home-page "http://snap.cs.berkeley.edu/")
6352 (synopsis "Short read DNA sequence aligner")
6354 "SNAP is a fast and accurate aligner for short DNA reads. It is
6355 optimized for modern read lengths of 100 bases or higher, and takes advantage
6356 of these reads to align data quickly through a hash-based indexing scheme.")
6357 ;; 32-bit systems are not supported by the unpatched code.
6358 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
6359 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
6360 ;; systems without a lot of memory cannot make good use of this program.
6361 (supported-systems '("x86_64-linux"))
6362 (license license:asl2.0)))
6364 (define-public sortmerna
6372 (url "https://github.com/biocore/sortmerna.git")
6374 (file-name (git-file-name name version))
6377 "0j3mbz4n25738yijmjbr5r4fyvkgm8v5vn3sshyfvmyqf5q9byqf"))))
6378 (build-system gnu-build-system)
6379 (outputs '("out" ;for binaries
6380 "db")) ;for sequence databases
6383 (modify-phases %standard-phases
6385 (lambda* (#:key outputs #:allow-other-keys)
6386 (let* ((out (assoc-ref outputs "out"))
6387 (bin (string-append out "/bin"))
6388 (db (assoc-ref outputs "db"))
6390 (string-append db "/share/sortmerna/rRNA_databases")))
6391 (install-file "sortmerna" bin)
6392 (install-file "indexdb_rna" bin)
6393 (for-each (lambda (file)
6394 (install-file file share))
6395 (find-files "rRNA_databases" ".*fasta"))
6399 (home-page "https://bioinfo.lifl.fr/RNA/sortmerna/")
6400 (synopsis "Biological sequence analysis tool for NGS reads")
6402 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
6403 and operational taxonomic unit (OTU) picking of next generation
6404 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
6405 allows for fast and sensitive analyses of nucleotide sequences. The main
6406 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
6407 ;; The source includes x86 specific code
6408 (supported-systems '("x86_64-linux" "i686-linux"))
6409 (license license:lgpl3)))
6418 (url "https://github.com/alexdobin/STAR.git")
6420 (file-name (git-file-name name version))
6423 "1hgiqw5qhs0pc1xazzihcfd92na02xyq2kb469z04y1v51kpvvjq"))
6424 (modules '((guix build utils)))
6427 (substitute* "source/Makefile"
6429 ;; Remove pre-built binaries and bundled htslib sources.
6430 (delete-file-recursively "bin/MacOSX_x86_64")
6431 (delete-file-recursively "bin/Linux_x86_64")
6432 (delete-file-recursively "bin/Linux_x86_64_static")
6433 (delete-file-recursively "source/htslib")
6435 (build-system gnu-build-system)
6437 '(#:tests? #f ;no check target
6438 #:make-flags '("STAR")
6440 (modify-phases %standard-phases
6441 (add-after 'unpack 'enter-source-dir
6442 (lambda _ (chdir "source") #t))
6443 (add-after 'enter-source-dir 'make-reproducible
6445 (substitute* "Makefile"
6446 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
6447 (string-append pre "Built with Guix" post)))
6449 ;; See https://github.com/alexdobin/STAR/pull/562
6450 (add-after 'enter-source-dir 'add-missing-header
6452 (substitute* "SoloReadFeature_inputRecords.cpp"
6453 (("#include \"binarySearch2.h\"" h)
6454 (string-append h "\n#include <math.h>")))
6456 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
6458 (substitute* "Makefile"
6459 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
6461 (substitute* '("BAMfunctions.cpp"
6466 "bamRemoveDuplicates.cpp")
6467 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
6468 (string-append "#include <" header ">")))
6469 (substitute* "IncludeDefine.h"
6470 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
6471 (string-append "<" header ">")))
6474 (lambda* (#:key outputs #:allow-other-keys)
6475 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6476 (install-file "STAR" bin))
6478 (delete 'configure))))
6482 `(("htslib" ,htslib)
6484 (home-page "https://github.com/alexdobin/STAR")
6485 (synopsis "Universal RNA-seq aligner")
6487 "The Spliced Transcripts Alignment to a Reference (STAR) software is
6488 based on a previously undescribed RNA-seq alignment algorithm that uses
6489 sequential maximum mappable seed search in uncompressed suffix arrays followed
6490 by seed clustering and stitching procedure. In addition to unbiased de novo
6491 detection of canonical junctions, STAR can discover non-canonical splices and
6492 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
6494 ;; Only 64-bit systems are supported according to the README.
6495 (supported-systems '("x86_64-linux" "mips64el-linux"))
6496 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
6497 (license license:gpl3+)))
6499 (define-public starlong
6500 (package (inherit star)
6503 (substitute-keyword-arguments (package-arguments star)
6504 ((#:make-flags flags)
6507 `(modify-phases ,phases
6508 ;; Allow extra long sequence reads.
6509 (add-after 'unpack 'make-extra-long
6511 (substitute* "source/IncludeDefine.h"
6512 (("(#define DEF_readNameLengthMax ).*" _ match)
6513 (string-append match "900000\n")))
6516 (lambda* (#:key outputs #:allow-other-keys)
6517 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6518 (install-file "STARlong" bin))
6521 (define-public subread
6527 (uri (string-append "mirror://sourceforge/subread/subread-"
6528 version "/subread-" version "-source.tar.gz"))
6531 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
6532 (build-system gnu-build-system)
6534 `(#:tests? #f ;no "check" target
6535 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
6536 ;; optimizations by default, so we override these flags such that x86_64
6537 ;; flags are only added when the build target is an x86_64 system.
6539 (list (let ((system ,(or (%current-target-system)
6541 (flags '("-ggdb" "-fomit-frame-pointer"
6542 "-ffast-math" "-funroll-loops"
6543 "-fmessage-length=0"
6544 "-O9" "-Wall" "-DMAKE_FOR_EXON"
6546 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
6547 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
6548 (if (string-prefix? "x86_64" system)
6549 (string-append "CCFLAGS=" (string-join (append flags flags64)))
6550 (string-append "CCFLAGS=" (string-join flags))))
6551 "-f" "Makefile.Linux"
6552 "CC=gcc ${CCFLAGS}")
6554 (modify-phases %standard-phases
6555 (add-after 'unpack 'enter-dir
6556 (lambda _ (chdir "src") #t))
6558 (lambda* (#:key outputs #:allow-other-keys)
6559 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6561 (copy-recursively "../bin" bin))
6563 ;; no "configure" script
6564 (delete 'configure))))
6565 (inputs `(("zlib" ,zlib)))
6566 (home-page "http://bioinf.wehi.edu.au/subread-package/")
6567 (synopsis "Tool kit for processing next-gen sequencing data")
6569 "The subread package contains the following tools: subread aligner, a
6570 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
6571 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
6572 features; exactSNP: a SNP caller that discovers SNPs by testing signals
6573 against local background noises.")
6574 (license license:gpl3+)))
6576 (define-public stringtie
6582 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
6583 "stringtie-" version ".tar.gz"))
6586 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
6587 (modules '((guix build utils)))
6590 (delete-file-recursively "samtools-0.1.18")
6592 (build-system gnu-build-system)
6594 `(#:tests? #f ;no test suite
6596 (modify-phases %standard-phases
6597 ;; no configure script
6599 (add-before 'build 'use-system-samtools
6601 (substitute* "Makefile"
6602 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
6604 (substitute* '("gclib/GBam.h"
6606 (("#include \"(bam|sam|kstring).h\"" _ header)
6607 (string-append "#include <samtools/" header ".h>")))
6609 (add-after 'unpack 'remove-duplicate-typedef
6611 ;; This typedef conflicts with the typedef in
6612 ;; glibc-2.25/include/bits/types.h
6613 (substitute* "gclib/GThreads.h"
6614 (("typedef long long __intmax_t;") ""))
6617 (lambda* (#:key outputs #:allow-other-keys)
6618 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6619 (install-file "stringtie" bin)
6622 `(("samtools" ,samtools-0.1)
6624 (home-page "http://ccb.jhu.edu/software/stringtie/")
6625 (synopsis "Transcript assembly and quantification for RNA-Seq data")
6627 "StringTie is a fast and efficient assembler of RNA-Seq sequence
6628 alignments into potential transcripts. It uses a novel network flow algorithm
6629 as well as an optional de novo assembly step to assemble and quantitate
6630 full-length transcripts representing multiple splice variants for each gene
6631 locus. Its input can include not only the alignments of raw reads used by
6632 other transcript assemblers, but also alignments of longer sequences that have
6633 been assembled from those reads. To identify differentially expressed genes
6634 between experiments, StringTie's output can be processed either by the
6635 Cuffdiff or Ballgown programs.")
6636 (license license:artistic2.0)))
6638 (define-public taxtastic
6643 ;; The Pypi version does not include tests.
6646 (url "https://github.com/fhcrc/taxtastic.git")
6647 (commit (string-append "v" version))))
6648 (file-name (git-file-name name version))
6651 "1sv8mkg64jn7zdwf1jj71c16686yrwxk0apb1l8sjszy9p166g0p"))))
6652 (build-system python-build-system)
6655 (modify-phases %standard-phases
6656 (add-after 'unpack 'prepare-directory
6658 ;; The git checkout must be writable for tests.
6659 (for-each make-file-writable (find-files "."))
6660 ;; This test fails, but the error is not caught by the test
6661 ;; framework, so the tests fail...
6662 (substitute* "tests/test_taxit.py"
6663 (("self.cmd_fails\\(''\\)")
6664 "self.cmd_fails('nothing')"))
6665 ;; This version file is expected to be created with git describe.
6666 (mkdir-p "taxtastic/data")
6667 (with-output-to-file "taxtastic/data/ver"
6668 (lambda () (display ,version)))
6670 (add-after 'unpack 'python37-compatibility
6672 (substitute* "taxtastic/utils.py"
6673 (("import csv") "import csv, errno")
6674 (("os.errno") "errno"))
6677 ;; Note, this fails to run with "-v" as it tries to write to a
6678 ;; closed output stream.
6679 (lambda _ (invoke "python" "-m" "unittest") #t)))))
6681 `(("python-sqlalchemy" ,python-sqlalchemy)
6682 ("python-decorator" ,python-decorator)
6683 ("python-biopython" ,python-biopython)
6684 ("python-pandas" ,python-pandas)
6685 ("python-psycopg2" ,python-psycopg2)
6686 ("python-fastalite" ,python-fastalite)
6687 ("python-pyyaml" ,python-pyyaml)
6688 ("python-six" ,python-six)
6689 ("python-jinja2" ,python-jinja2)
6690 ("python-dendropy" ,python-dendropy)))
6691 (home-page "https://github.com/fhcrc/taxtastic")
6692 (synopsis "Tools for taxonomic naming and annotation")
6694 "Taxtastic is software written in python used to build and maintain
6695 reference packages i.e. collections of reference trees, reference alignments,
6696 profiles, and associated taxonomic information.")
6697 (license license:gpl3+)))
6699 (define-public vcftools
6706 "https://github.com/vcftools/vcftools/releases/download/v"
6707 version "/vcftools-" version ".tar.gz"))
6710 "1qqlx7flfv7axrjwkaz6njkscsl1d0jw98ns8d8bh1n1hd1pgz6v"))))
6711 (build-system gnu-build-system)
6713 `(#:tests? #f ; no "check" target
6715 "CFLAGS=-O2" ; override "-m64" flag
6716 (string-append "PREFIX=" (assoc-ref %outputs "out"))
6717 (string-append "MANDIR=" (assoc-ref %outputs "out")
6718 "/share/man/man1"))))
6720 `(("pkg-config" ,pkg-config)))
6724 (home-page "https://vcftools.github.io/")
6725 (synopsis "Tools for working with VCF files")
6727 "VCFtools is a program package designed for working with VCF files, such
6728 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
6729 provide easily accessible methods for working with complex genetic variation
6730 data in the form of VCF files.")
6731 ;; The license is declared as LGPLv3 in the README and
6732 ;; at https://vcftools.github.io/license.html
6733 (license license:lgpl3)))
6735 (define-public infernal
6741 (uri (string-append "http://eddylab.org/software/infernal/"
6742 "infernal-" version ".tar.gz"))
6745 "0pm8bm3s6nfa0av4x6m6h27lsg12b3lz3jm0fyh1mc77l2isd61v"))))
6746 (build-system gnu-build-system)
6749 ("python" ,python))) ; for tests
6750 (home-page "http://eddylab.org/infernal/")
6751 (synopsis "Inference of RNA alignments")
6752 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
6753 searching DNA sequence databases for RNA structure and sequence similarities.
6754 It is an implementation of a special case of profile stochastic context-free
6755 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
6756 profile, but it scores a combination of sequence consensus and RNA secondary
6757 structure consensus, so in many cases, it is more capable of identifying RNA
6758 homologs that conserve their secondary structure more than their primary
6760 ;; Infernal 1.1.3 requires VMX or SSE capability for parallel instructions.
6761 (supported-systems '("i686-linux" "x86_64-linux"))
6762 (license license:bsd-3)))
6764 (define-public r-scde
6771 (url "https://github.com/hms-dbmi/scde.git")
6773 (file-name (git-file-name name version))
6776 "10na2gyka24mszdxf92wz9h2c13hdf1ww30c68gfsw53lvvhhhxb"))))
6777 (build-system r-build-system)
6779 `(("r-rcpp" ,r-rcpp)
6780 ("r-rcpparmadillo" ,r-rcpparmadillo)
6783 ("r-rjson" ,r-rjson)
6784 ("r-cairo" ,r-cairo)
6785 ("r-rcolorbrewer" ,r-rcolorbrewer)
6786 ("r-edger" ,r-edger)
6787 ("r-quantreg" ,r-quantreg)
6789 ("r-rmtstat" ,r-rmtstat)
6790 ("r-extremes" ,r-extremes)
6791 ("r-pcamethods" ,r-pcamethods)
6792 ("r-biocparallel" ,r-biocparallel)
6793 ("r-flexmix" ,r-flexmix)))
6794 (home-page "https://hms-dbmi.github.io/scde/")
6795 (synopsis "R package for analyzing single-cell RNA-seq data")
6796 (description "The SCDE package implements a set of statistical methods for
6797 analyzing single-cell RNA-seq data. SCDE fits individual error models for
6798 single-cell RNA-seq measurements. These models can then be used for
6799 assessment of differential expression between groups of cells, as well as
6800 other types of analysis. The SCDE package also contains the pagoda framework
6801 which applies pathway and gene set overdispersion analysis to identify aspects
6802 of transcriptional heterogeneity among single cells.")
6803 ;; See https://github.com/hms-dbmi/scde/issues/38
6804 (license license:gpl2)))
6806 (define-public r-centipede
6808 (name "r-centipede")
6812 (uri (string-append "http://download.r-forge.r-project.org/"
6813 "src/contrib/CENTIPEDE_" version ".tar.gz"))
6816 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
6817 (build-system r-build-system)
6818 (home-page "http://centipede.uchicago.edu/")
6819 (synopsis "Predict transcription factor binding sites")
6821 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
6822 of the genome that are bound by particular transcription factors. It starts
6823 by identifying a set of candidate binding sites, and then aims to classify the
6824 sites according to whether each site is bound or not bound by a transcription
6825 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
6826 between two different types of motif instances using as much relevant
6827 information as possible.")
6828 (license (list license:gpl2+ license:gpl3+))))
6830 (define-public r-genefilter
6832 (name "r-genefilter")
6837 (uri (bioconductor-uri "genefilter" version))
6840 "1xjr02qhldspjwd6y374wgik18fgywb6408wsz471i8b4ik98ckc"))))
6841 (build-system r-build-system)
6843 `(("gfortran" ,gfortran)))
6845 `(("r-annotate" ,r-annotate)
6846 ("r-annotationdbi" ,r-annotationdbi)
6847 ("r-biobase" ,r-biobase)
6848 ("r-biocgenerics" ,r-biocgenerics)
6849 ("r-survival" ,r-survival)))
6850 (home-page "https://bioconductor.org/packages/genefilter")
6851 (synopsis "Filter genes from high-throughput experiments")
6853 "This package provides basic functions for filtering genes from
6854 high-throughput sequencing experiments.")
6855 (license license:artistic2.0)))
6857 (define-public r-deseq2
6864 (uri (bioconductor-uri "DESeq2" version))
6867 "1lmbhznfs8dz9ipd53z4ccwvwxqwzx1ayw56jlrvlsambaj8fash"))))
6868 (properties `((upstream-name . "DESeq2")))
6869 (build-system r-build-system)
6871 `(("r-biobase" ,r-biobase)
6872 ("r-biocgenerics" ,r-biocgenerics)
6873 ("r-biocparallel" ,r-biocparallel)
6874 ("r-genefilter" ,r-genefilter)
6875 ("r-geneplotter" ,r-geneplotter)
6876 ("r-genomicranges" ,r-genomicranges)
6877 ("r-ggplot2" ,r-ggplot2)
6878 ("r-hmisc" ,r-hmisc)
6879 ("r-iranges" ,r-iranges)
6880 ("r-locfit" ,r-locfit)
6882 ("r-rcpparmadillo" ,r-rcpparmadillo)
6883 ("r-s4vectors" ,r-s4vectors)
6884 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6885 (home-page "https://bioconductor.org/packages/DESeq2")
6886 (synopsis "Differential gene expression analysis")
6888 "This package provides functions to estimate variance-mean dependence in
6889 count data from high-throughput nucleotide sequencing assays and test for
6890 differential expression based on a model using the negative binomial
6892 (license license:lgpl3+)))
6894 (define-public r-dexseq
6901 (uri (bioconductor-uri "DEXSeq" version))
6904 "0sqqb65ckliif2nmvlvc7w49id59z0nvqcdz5gry8l2mn6azrf6a"))))
6905 (properties `((upstream-name . "DEXSeq")))
6906 (build-system r-build-system)
6908 `(("r-annotationdbi" ,r-annotationdbi)
6909 ("r-biobase" ,r-biobase)
6910 ("r-biocgenerics" ,r-biocgenerics)
6911 ("r-biocparallel" ,r-biocparallel)
6912 ("r-biomart" ,r-biomart)
6913 ("r-deseq2" ,r-deseq2)
6914 ("r-genefilter" ,r-genefilter)
6915 ("r-geneplotter" ,r-geneplotter)
6916 ("r-genomicranges" ,r-genomicranges)
6917 ("r-hwriter" ,r-hwriter)
6918 ("r-iranges" ,r-iranges)
6919 ("r-rcolorbrewer" ,r-rcolorbrewer)
6920 ("r-rsamtools" ,r-rsamtools)
6921 ("r-s4vectors" ,r-s4vectors)
6922 ("r-statmod" ,r-statmod)
6923 ("r-stringr" ,r-stringr)
6924 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6925 (home-page "https://bioconductor.org/packages/DEXSeq")
6926 (synopsis "Inference of differential exon usage in RNA-Seq")
6928 "This package is focused on finding differential exon usage using RNA-seq
6929 exon counts between samples with different experimental designs. It provides
6930 functions that allows the user to make the necessary statistical tests based
6931 on a model that uses the negative binomial distribution to estimate the
6932 variance between biological replicates and generalized linear models for
6933 testing. The package also provides functions for the visualization and
6934 exploration of the results.")
6935 (license license:gpl3+)))
6937 (define-public r-annotationforge
6939 (name "r-annotationforge")
6944 (uri (bioconductor-uri "AnnotationForge" version))
6947 "0h2r60v339ajk5r6xq4iwwcpihdvf12fi8255byr2dhglzrd8xl7"))))
6949 `((upstream-name . "AnnotationForge")))
6950 (build-system r-build-system)
6952 `(("r-annotationdbi" ,r-annotationdbi)
6953 ("r-biobase" ,r-biobase)
6954 ("r-biocgenerics" ,r-biocgenerics)
6956 ("r-rcurl" ,r-rcurl)
6957 ("r-rsqlite" ,r-rsqlite)
6958 ("r-s4vectors" ,r-s4vectors)
6960 (home-page "https://bioconductor.org/packages/AnnotationForge")
6961 (synopsis "Code for building annotation database packages")
6963 "This package provides code for generating Annotation packages and their
6964 databases. Packages produced are intended to be used with AnnotationDbi.")
6965 (license license:artistic2.0)))
6967 (define-public r-rbgl
6974 (uri (bioconductor-uri "RBGL" version))
6977 "0ixbkdirf08i400db587r262j52sdwdgk3884nxk5xkbhx2m6vg0"))))
6978 (properties `((upstream-name . "RBGL")))
6979 (build-system r-build-system)
6982 ("r-graph" ,r-graph)))
6983 (home-page "https://www.bioconductor.org/packages/RBGL")
6984 (synopsis "Interface to the Boost graph library")
6986 "This package provides a fairly extensive and comprehensive interface to
6987 the graph algorithms contained in the Boost library.")
6988 (license license:artistic2.0)))
6990 (define-public r-gseabase
6997 (uri (bioconductor-uri "GSEABase" version))
7000 "0kcb90sxlf19d5dxhdbqk9x62svky4262cccl0wxarbq6gf3bd57"))))
7001 (properties `((upstream-name . "GSEABase")))
7002 (build-system r-build-system)
7004 `(("r-annotate" ,r-annotate)
7005 ("r-annotationdbi" ,r-annotationdbi)
7006 ("r-biobase" ,r-biobase)
7007 ("r-biocgenerics" ,r-biocgenerics)
7008 ("r-graph" ,r-graph)
7010 (home-page "https://bioconductor.org/packages/GSEABase")
7011 (synopsis "Gene set enrichment data structures and methods")
7013 "This package provides classes and methods to support @dfn{Gene Set
7014 Enrichment Analysis} (GSEA).")
7015 (license license:artistic2.0)))
7017 (define-public r-category
7024 (uri (bioconductor-uri "Category" version))
7027 "0ga0ij9hyzsxa5pavwmv35i8xggia2wygrk4m4z8an0qcvgy3v5g"))))
7028 (properties `((upstream-name . "Category")))
7029 (build-system r-build-system)
7031 `(("r-annotate" ,r-annotate)
7032 ("r-annotationdbi" ,r-annotationdbi)
7033 ("r-biobase" ,r-biobase)
7034 ("r-biocgenerics" ,r-biocgenerics)
7035 ("r-genefilter" ,r-genefilter)
7036 ("r-graph" ,r-graph)
7037 ("r-gseabase" ,r-gseabase)
7038 ("r-matrix" ,r-matrix)
7041 (home-page "https://bioconductor.org/packages/Category")
7042 (synopsis "Category analysis")
7044 "This package provides a collection of tools for performing category
7046 (license license:artistic2.0)))
7048 (define-public r-gostats
7055 (uri (bioconductor-uri "GOstats" version))
7058 "19f4gxm3sbprqrnwzvskvywv6j4ibm8xkrbgg4h0fvh2b5331nwc"))))
7059 (properties `((upstream-name . "GOstats")))
7060 (build-system r-build-system)
7062 `(("r-annotate" ,r-annotate)
7063 ("r-annotationdbi" ,r-annotationdbi)
7064 ("r-annotationforge" ,r-annotationforge)
7065 ("r-biobase" ,r-biobase)
7066 ("r-category" ,r-category)
7067 ("r-go-db" ,r-go-db)
7068 ("r-graph" ,r-graph)
7069 ("r-rgraphviz" ,r-rgraphviz)
7070 ("r-rbgl" ,r-rbgl)))
7071 (home-page "https://bioconductor.org/packages/GOstats")
7072 (synopsis "Tools for manipulating GO and microarrays")
7074 "This package provides a set of tools for interacting with GO and
7075 microarray data. A variety of basic manipulation tools for graphs, hypothesis
7076 testing and other simple calculations.")
7077 (license license:artistic2.0)))
7079 (define-public r-shortread
7081 (name "r-shortread")
7086 (uri (bioconductor-uri "ShortRead" version))
7089 "0ykyrj4g6vc67d5s46sp4659qvar2iavflzhggm79w4p50hxia4s"))))
7090 (properties `((upstream-name . "ShortRead")))
7091 (build-system r-build-system)
7095 `(("r-biobase" ,r-biobase)
7096 ("r-biocgenerics" ,r-biocgenerics)
7097 ("r-biocparallel" ,r-biocparallel)
7098 ("r-biostrings" ,r-biostrings)
7099 ("r-genomeinfodb" ,r-genomeinfodb)
7100 ("r-genomicalignments" ,r-genomicalignments)
7101 ("r-genomicranges" ,r-genomicranges)
7102 ("r-hwriter" ,r-hwriter)
7103 ("r-iranges" ,r-iranges)
7104 ("r-lattice" ,r-lattice)
7105 ("r-latticeextra" ,r-latticeextra)
7106 ("r-rsamtools" ,r-rsamtools)
7107 ("r-s4vectors" ,r-s4vectors)
7108 ("r-xvector" ,r-xvector)
7109 ("r-zlibbioc" ,r-zlibbioc)))
7110 (home-page "https://bioconductor.org/packages/ShortRead")
7111 (synopsis "FASTQ input and manipulation tools")
7113 "This package implements sampling, iteration, and input of FASTQ files.
7114 It includes functions for filtering and trimming reads, and for generating a
7115 quality assessment report. Data are represented as
7116 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
7117 purposes. The package also contains legacy support for early single-end,
7118 ungapped alignment formats.")
7119 (license license:artistic2.0)))
7121 (define-public r-systempiper
7123 (name "r-systempiper")
7128 (uri (bioconductor-uri "systemPipeR" version))
7131 "17r25v9wcglyma2v1c8fka80dm7fx86saxlsb2aprmwi4h3dhb0j"))))
7132 (properties `((upstream-name . "systemPipeR")))
7133 (build-system r-build-system)
7135 `(("r-annotate" ,r-annotate)
7136 ("r-batchtools" ,r-batchtools)
7137 ("r-biocgenerics" ,r-biocgenerics)
7138 ("r-biostrings" ,r-biostrings)
7139 ("r-deseq2" ,r-deseq2)
7140 ("r-edger" ,r-edger)
7141 ("r-genomicfeatures" ,r-genomicfeatures)
7142 ("r-genomicranges" ,r-genomicranges)
7143 ("r-ggplot2" ,r-ggplot2)
7144 ("r-go-db" ,r-go-db)
7145 ("r-gostats" ,r-gostats)
7146 ("r-limma" ,r-limma)
7147 ("r-pheatmap" ,r-pheatmap)
7148 ("r-rjson" ,r-rjson)
7149 ("r-rsamtools" ,r-rsamtools)
7150 ("r-shortread" ,r-shortread)
7151 ("r-summarizedexperiment" ,r-summarizedexperiment)
7153 ("r-variantannotation" ,r-variantannotation)))
7154 (home-page "https://github.com/tgirke/systemPipeR")
7155 (synopsis "Next generation sequencing workflow and reporting environment")
7157 "This R package provides tools for building and running automated
7158 end-to-end analysis workflows for a wide range of @dfn{next generation
7159 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
7160 Important features include a uniform workflow interface across different NGS
7161 applications, automated report generation, and support for running both R and
7162 command-line software, such as NGS aligners or peak/variant callers, on local
7163 computers or compute clusters. Efficient handling of complex sample sets and
7164 experimental designs is facilitated by a consistently implemented sample
7165 annotation infrastructure.")
7166 (license license:artistic2.0)))
7168 (define-public r-grohmm
7175 (uri (bioconductor-uri "groHMM" version))
7178 "0ywr8f6bfhg2ia3n4rmsxr4v1xqmlyhkwh0rvkgh3yqgnbvihndg"))))
7179 (properties `((upstream-name . "groHMM")))
7180 (build-system r-build-system)
7182 `(("r-genomeinfodb" ,r-genomeinfodb)
7183 ("r-genomicalignments" ,r-genomicalignments)
7184 ("r-genomicranges" ,r-genomicranges)
7185 ("r-iranges" ,r-iranges)
7187 ("r-rtracklayer" ,r-rtracklayer)
7188 ("r-s4vectors" ,r-s4vectors)))
7189 (home-page "https://github.com/Kraus-Lab/groHMM")
7190 (synopsis "GRO-seq analysis pipeline")
7192 "This package provides a pipeline for the analysis of GRO-seq data.")
7193 (license license:gpl3+)))
7195 (define-public vsearch
7203 (url "https://github.com/torognes/vsearch.git")
7204 (commit (string-append "v" version))))
7205 (file-name (git-file-name name version))
7208 "0vhrpjfdf75ba04b24xknp41790cvcgwl0vgpy7qbzj5xh2521ss"))
7209 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
7212 ;; Remove bundled cityhash sources. The vsearch source is adjusted
7213 ;; for this in the patch.
7214 (delete-file "src/city.h")
7215 (delete-file "src/citycrc.h")
7216 (delete-file "src/city.cc")
7218 (build-system gnu-build-system)
7222 ("cityhash" ,cityhash)))
7224 `(("autoconf" ,autoconf)
7225 ("automake" ,automake)))
7226 (synopsis "Sequence search tools for metagenomics")
7228 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
7229 dereplication, pairwise alignment, shuffling, subsampling, sorting and
7230 masking. The tool takes advantage of parallelism in the form of SIMD
7231 vectorization as well as multiple threads to perform accurate alignments at
7232 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
7233 Needleman-Wunsch).")
7234 (home-page "https://github.com/torognes/vsearch")
7235 ;; vsearch uses non-portable SSE intrinsics so building fails on other
7237 (supported-systems '("x86_64-linux"))
7238 ;; Dual licensed; also includes public domain source.
7239 (license (list license:gpl3 license:bsd-2))))
7241 (define-public pardre
7244 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
7249 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
7253 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
7254 (build-system gnu-build-system)
7256 `(#:tests? #f ; no tests included
7258 (modify-phases %standard-phases
7261 (lambda* (#:key outputs #:allow-other-keys)
7262 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
7263 (install-file "ParDRe" bin)
7266 `(("openmpi" ,openmpi)
7268 (synopsis "Parallel tool to remove duplicate DNA reads")
7270 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
7271 Duplicate reads can be seen as identical or nearly identical sequences with
7272 some mismatches. This tool lets users avoid the analysis of unnecessary
7273 reads, reducing the time of subsequent procedures with the
7274 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
7275 in order to exploit the parallel capabilities of multicore clusters. It is
7276 faster than multithreaded counterparts (end of 2015) for the same number of
7277 cores and, thanks to the message-passing technology, it can be executed on
7279 (home-page "https://sourceforge.net/projects/pardre/")
7280 (license license:gpl3+)))
7282 (define-public ruby-bio-kseq
7284 (name "ruby-bio-kseq")
7289 (uri (rubygems-uri "bio-kseq" version))
7292 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
7293 (build-system ruby-build-system)
7295 `(#:test-target "spec"))
7297 `(("bundler" ,bundler)
7298 ("ruby-rspec" ,ruby-rspec)
7299 ("ruby-rake-compiler" ,ruby-rake-compiler)))
7302 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
7304 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
7305 FASTQ parsing code. It provides a fast iterator over sequences and their
7307 (home-page "https://github.com/gusevfe/bio-kseq")
7308 (license license:expat)))
7310 (define-public bio-locus
7317 (uri (rubygems-uri "bio-locus" version))
7320 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
7321 (build-system ruby-build-system)
7323 `(("ruby-rspec" ,ruby-rspec)))
7324 (synopsis "Tool for fast querying of genome locations")
7326 "Bio-locus is a tabix-like tool for fast querying of genome
7327 locations. Many file formats in bioinformatics contain records that
7328 start with a chromosome name and a position for a SNP, or a start-end
7329 position for indels. Bio-locus allows users to store this chr+pos or
7330 chr+pos+alt information in a database.")
7331 (home-page "https://github.com/pjotrp/bio-locus")
7332 (license license:expat)))
7334 (define-public bio-blastxmlparser
7336 (name "bio-blastxmlparser")
7340 (uri (rubygems-uri "bio-blastxmlparser" version))
7343 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
7344 (build-system ruby-build-system)
7346 `(("ruby-bio-logger" ,ruby-bio-logger)
7347 ("ruby-nokogiri" ,ruby-nokogiri)))
7349 `(("ruby-rspec" ,ruby-rspec)))
7350 (synopsis "Fast big data BLAST XML parser and library")
7352 "Very fast parallel big-data BLAST XML file parser which can be used as
7353 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
7354 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
7355 (home-page "https://github.com/pjotrp/blastxmlparser")
7356 (license license:expat)))
7358 (define-public bioruby
7365 (uri (rubygems-uri "bio" version))
7368 "1d56amdsjv1mag7m6gv2w0xij8hqx1v5xbdjsix8sp3yp36m7938"))))
7369 (build-system ruby-build-system)
7371 `(("ruby-libxml" ,ruby-libxml)))
7373 `(("which" ,which))) ; required for test phase
7376 (modify-phases %standard-phases
7377 (add-before 'build 'patch-test-command
7379 (substitute* '("test/functional/bio/test_command.rb")
7380 (("/bin/sh") (which "sh")))
7381 (substitute* '("test/functional/bio/test_command.rb")
7382 (("/bin/ls") (which "ls")))
7383 (substitute* '("test/functional/bio/test_command.rb")
7384 (("which") (which "which")))
7385 (substitute* '("test/functional/bio/test_command.rb",
7386 "test/data/command/echoarg2.sh")
7387 (("/bin/echo") (which "echo")))
7389 (synopsis "Ruby library, shell and utilities for bioinformatics")
7390 (description "BioRuby comes with a comprehensive set of Ruby development
7391 tools and libraries for bioinformatics and molecular biology. BioRuby has
7392 components for sequence analysis, pathway analysis, protein modelling and
7393 phylogenetic analysis; it supports many widely used data formats and provides
7394 easy access to databases, external programs and public web services, including
7395 BLAST, KEGG, GenBank, MEDLINE and GO.")
7396 (home-page "http://bioruby.org/")
7397 ;; Code is released under Ruby license, except for setup
7398 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
7399 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
7401 (define-public r-biocviews
7403 (name "r-biocviews")
7407 (uri (bioconductor-uri "biocViews" version))
7410 "0yn8jys1900d31haayz0ppqk5y79mwjajwp4alz6pln3dbs70f3g"))))
7412 `((upstream-name . "biocViews")))
7413 (build-system r-build-system)
7415 `(("r-biobase" ,r-biobase)
7416 ("r-biocmanager" ,r-biocmanager)
7417 ("r-graph" ,r-graph)
7419 ("r-rcurl" ,r-rcurl)
7421 ("r-runit" ,r-runit)))
7422 (home-page "https://bioconductor.org/packages/biocViews")
7423 (synopsis "Bioconductor package categorization helper")
7424 (description "The purpose of biocViews is to create HTML pages that
7425 categorize packages in a Bioconductor package repository according to keywords,
7426 also known as views, in a controlled vocabulary.")
7427 (license license:artistic2.0)))
7429 (define-public r-biocstyle
7431 (name "r-biocstyle")
7435 (uri (bioconductor-uri "BiocStyle" version))
7438 "1x71in059zql40f4c87bd1gf96r945kdvwbq61jmch9d3d8nwxbb"))))
7440 `((upstream-name . "BiocStyle")))
7441 (build-system r-build-system)
7443 `(("r-biocmanager" ,r-biocmanager)
7444 ("r-bookdown" ,r-bookdown)
7445 ("r-knitr" ,r-knitr)
7446 ("r-rmarkdown" ,r-rmarkdown)
7447 ("r-yaml" ,r-yaml)))
7448 (home-page "https://bioconductor.org/packages/BiocStyle")
7449 (synopsis "Bioconductor formatting styles")
7450 (description "This package provides standard formatting styles for
7451 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
7453 (license license:artistic2.0)))
7455 (define-public r-bioccheck
7457 (name "r-bioccheck")
7461 (uri (bioconductor-uri "BiocCheck" version))
7464 "1qnvl5yajgh67ijkq6gdsafri1k5hyw5gzn2ccqk9ymx6i2xd80g"))))
7466 `((upstream-name . "BiocCheck")))
7467 (build-system r-build-system)
7470 (modify-phases %standard-phases
7471 ;; This package can be used by calling BiocCheck(<package>) from
7472 ;; within R, or by running R CMD BiocCheck <package>. This phase
7473 ;; makes sure the latter works. For this to work, the BiocCheck
7474 ;; script must be somewhere on the PATH (not the R bin directory).
7475 (add-after 'install 'install-bioccheck-subcommand
7476 (lambda* (#:key outputs #:allow-other-keys)
7477 (let* ((out (assoc-ref outputs "out"))
7478 (dest-dir (string-append out "/bin"))
7480 (string-append out "/site-library/BiocCheck/script/")))
7482 (symlink (string-append script-dir "/checkBadDeps.R")
7483 (string-append dest-dir "/checkBadDeps.R"))
7484 (symlink (string-append script-dir "/BiocCheck")
7485 (string-append dest-dir "/BiocCheck")))
7488 `(("r-codetools" ,r-codetools)
7489 ("r-graph" ,r-graph)
7491 ("r-knitr" ,r-knitr)
7492 ("r-optparse" ,r-optparse)
7493 ("r-biocmanager" ,r-biocmanager)
7494 ("r-biocviews" ,r-biocviews)
7495 ("r-stringdist" ,r-stringdist)))
7496 (home-page "https://bioconductor.org/packages/BiocCheck")
7497 (synopsis "Executes Bioconductor-specific package checks")
7498 (description "This package contains tools to perform additional quality
7499 checks on R packages that are to be submitted to the Bioconductor repository.")
7500 (license license:artistic2.0)))
7502 (define-public r-s4vectors
7504 (name "r-s4vectors")
7508 (uri (bioconductor-uri "S4Vectors" version))
7511 "1fzs8j2d3wwfzm2fq63ywf68a4dbggyl5l098f148yn4jw7jd3bc"))))
7513 `((upstream-name . "S4Vectors")))
7514 (build-system r-build-system)
7516 `(("r-biocgenerics" ,r-biocgenerics)))
7517 (home-page "https://bioconductor.org/packages/S4Vectors")
7518 (synopsis "S4 implementation of vectors and lists")
7520 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7521 classes and a set of generic functions that extend the semantic of ordinary
7522 vectors and lists in R. Package developers can easily implement vector-like
7523 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7524 In addition, a few low-level concrete subclasses of general interest (e.g.
7525 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7526 S4Vectors package itself.")
7527 (license license:artistic2.0)))
7529 (define-public r-iranges
7535 (uri (bioconductor-uri "IRanges" version))
7538 "1jhnxb9yacmj2z82b6992gihjvj1a0gnjwbjiagyyx03fqnv23kg"))))
7540 `((upstream-name . "IRanges")))
7541 (build-system r-build-system)
7543 `(("r-biocgenerics" ,r-biocgenerics)
7544 ("r-s4vectors" ,r-s4vectors)))
7545 (home-page "https://bioconductor.org/packages/IRanges")
7546 (synopsis "Infrastructure for manipulating intervals on sequences")
7548 "This package provides efficient low-level and highly reusable S4 classes
7549 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7550 generally, data that can be organized sequentially (formally defined as
7551 @code{Vector} objects), as well as views on these @code{Vector} objects.
7552 Efficient list-like classes are also provided for storing big collections of
7553 instances of the basic classes. All classes in the package use consistent
7554 naming and share the same rich and consistent \"Vector API\" as much as
7556 (license license:artistic2.0)))
7558 (define-public r-genomeinfodbdata
7560 (name "r-genomeinfodbdata")
7564 ;; We cannot use bioconductor-uri here because this tarball is
7565 ;; located under "data/annotation/" instead of "bioc/".
7566 (uri (string-append "https://bioconductor.org/packages/release/"
7567 "data/annotation/src/contrib/GenomeInfoDbData_"
7571 "0di6nlqpsyqf693k2na65ayqldih563x3zfrczpqc5q2hl5kg35c"))))
7573 `((upstream-name . "GenomeInfoDbData")))
7574 (build-system r-build-system)
7575 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7576 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7577 (description "This package contains data for mapping between NCBI taxonomy
7578 ID and species. It is used by functions in the GenomeInfoDb package.")
7579 (license license:artistic2.0)))
7581 (define-public r-genomeinfodb
7583 (name "r-genomeinfodb")
7587 (uri (bioconductor-uri "GenomeInfoDb" version))
7590 "0phadr67yb4l25x41a9wg4pjy1wbxlk14jhidhz6g5n4z6x45qbm"))))
7592 `((upstream-name . "GenomeInfoDb")))
7593 (build-system r-build-system)
7595 `(("r-biocgenerics" ,r-biocgenerics)
7596 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7597 ("r-iranges" ,r-iranges)
7598 ("r-rcurl" ,r-rcurl)
7599 ("r-s4vectors" ,r-s4vectors)))
7601 `(("r-knitr" ,r-knitr)))
7602 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7603 (synopsis "Utilities for manipulating chromosome identifiers")
7605 "This package contains data and functions that define and allow
7606 translation between different chromosome sequence naming conventions (e.g.,
7607 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7608 names in their natural, rather than lexicographic, order.")
7609 (license license:artistic2.0)))
7611 (define-public r-edger
7617 (uri (bioconductor-uri "edgeR" version))
7620 "07dv99kl7jfa62nzcq705r56gcpb1hq7p4px48j71y2ddi1rqmr6"))))
7621 (properties `((upstream-name . "edgeR")))
7622 (build-system r-build-system)
7624 `(("r-limma" ,r-limma)
7625 ("r-locfit" ,r-locfit)
7627 ("r-statmod" ,r-statmod))) ;for estimateDisp
7628 (home-page "http://bioinf.wehi.edu.au/edgeR")
7629 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7630 (description "This package can do differential expression analysis of
7631 RNA-seq expression profiles with biological replication. It implements a range
7632 of statistical methodology based on the negative binomial distributions,
7633 including empirical Bayes estimation, exact tests, generalized linear models
7634 and quasi-likelihood tests. It be applied to differential signal analysis of
7635 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7637 (license license:gpl2+)))
7639 (define-public r-variantannotation
7641 (name "r-variantannotation")
7645 (uri (bioconductor-uri "VariantAnnotation" version))
7648 "009s7rzp78s2w6iybizina42qx2w8qv3xwjbkpqphmm451maykgs"))))
7650 `((upstream-name . "VariantAnnotation")))
7654 `(("r-annotationdbi" ,r-annotationdbi)
7655 ("r-biobase" ,r-biobase)
7656 ("r-biocgenerics" ,r-biocgenerics)
7657 ("r-biostrings" ,r-biostrings)
7658 ("r-bsgenome" ,r-bsgenome)
7660 ("r-genomeinfodb" ,r-genomeinfodb)
7661 ("r-genomicfeatures" ,r-genomicfeatures)
7662 ("r-genomicranges" ,r-genomicranges)
7663 ("r-iranges" ,r-iranges)
7664 ("r-summarizedexperiment" ,r-summarizedexperiment)
7665 ("r-rhtslib" ,r-rhtslib)
7666 ("r-rsamtools" ,r-rsamtools)
7667 ("r-rtracklayer" ,r-rtracklayer)
7668 ("r-s4vectors" ,r-s4vectors)
7669 ("r-xvector" ,r-xvector)
7670 ("r-zlibbioc" ,r-zlibbioc)))
7671 (build-system r-build-system)
7672 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7673 (synopsis "Package for annotation of genetic variants")
7674 (description "This R package can annotate variants, compute amino acid
7675 coding changes and predict coding outcomes.")
7676 (license license:artistic2.0)))
7678 (define-public r-limma
7684 (uri (bioconductor-uri "limma" version))
7687 "1nd01r7rd7jb5qz84vbgfnyrmgm9wiq7fsdji68537kjgvrzmm9z"))))
7688 (build-system r-build-system)
7689 (home-page "http://bioinf.wehi.edu.au/limma")
7690 (synopsis "Package for linear models for microarray and RNA-seq data")
7691 (description "This package can be used for the analysis of gene expression
7692 studies, especially the use of linear models for analysing designed experiments
7693 and the assessment of differential expression. The analysis methods apply to
7694 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7695 (license license:gpl2+)))
7697 (define-public r-xvector
7703 (uri (bioconductor-uri "XVector" version))
7706 "0s2gg84yzl5ffkzp6n7kh0jjk1vd90z189f5hkfn18rn67cy2nv7"))))
7708 `((upstream-name . "XVector")))
7709 (build-system r-build-system)
7712 (modify-phases %standard-phases
7713 (add-after 'unpack 'use-system-zlib
7715 (substitute* "DESCRIPTION"
7716 (("zlibbioc, ") ""))
7717 (substitute* "NAMESPACE"
7718 (("import\\(zlibbioc\\)") ""))
7723 `(("r-biocgenerics" ,r-biocgenerics)
7724 ("r-iranges" ,r-iranges)
7725 ("r-s4vectors" ,r-s4vectors)))
7726 (home-page "https://bioconductor.org/packages/XVector")
7727 (synopsis "Representation and manpulation of external sequences")
7729 "This package provides memory efficient S4 classes for storing sequences
7730 \"externally\" (behind an R external pointer, or on disk).")
7731 (license license:artistic2.0)))
7733 (define-public r-genomicranges
7735 (name "r-genomicranges")
7739 (uri (bioconductor-uri "GenomicRanges" version))
7742 "0xdds6ws7jjdfy4x3mb0qhy43kpxdmifmpw0jdk4wgw999zabb50"))))
7744 `((upstream-name . "GenomicRanges")))
7745 (build-system r-build-system)
7747 `(("r-biocgenerics" ,r-biocgenerics)
7748 ("r-genomeinfodb" ,r-genomeinfodb)
7749 ("r-iranges" ,r-iranges)
7750 ("r-s4vectors" ,r-s4vectors)
7751 ("r-xvector" ,r-xvector)))
7752 (home-page "https://bioconductor.org/packages/GenomicRanges")
7753 (synopsis "Representation and manipulation of genomic intervals")
7755 "This package provides tools to efficiently represent and manipulate
7756 genomic annotations and alignments is playing a central role when it comes to
7757 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7758 GenomicRanges package defines general purpose containers for storing and
7759 manipulating genomic intervals and variables defined along a genome.")
7760 (license license:artistic2.0)))
7762 (define-public r-biobase
7768 (uri (bioconductor-uri "Biobase" version))
7771 "1gx41083dqlm59vwqdxvc4ny31x91j48mda9n3scg0f2zwasvqgl"))))
7773 `((upstream-name . "Biobase")))
7774 (build-system r-build-system)
7776 `(("r-biocgenerics" ,r-biocgenerics)))
7777 (home-page "https://bioconductor.org/packages/Biobase")
7778 (synopsis "Base functions for Bioconductor")
7780 "This package provides functions that are needed by many other packages
7781 on Bioconductor or which replace R functions.")
7782 (license license:artistic2.0)))
7784 (define-public r-annotationdbi
7786 (name "r-annotationdbi")
7790 (uri (bioconductor-uri "AnnotationDbi" version))
7793 "09piz1f0xpbb4amskx4ilby6lfrn27hhwk75il2c4lq6m3hr4w8s"))))
7795 `((upstream-name . "AnnotationDbi")))
7796 (build-system r-build-system)
7798 `(("r-biobase" ,r-biobase)
7799 ("r-biocgenerics" ,r-biocgenerics)
7801 ("r-iranges" ,r-iranges)
7802 ("r-rsqlite" ,r-rsqlite)
7803 ("r-s4vectors" ,r-s4vectors)))
7804 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7805 (synopsis "Annotation database interface")
7807 "This package provides user interface and database connection code for
7808 annotation data packages using SQLite data storage.")
7809 (license license:artistic2.0)))
7811 (define-public r-biomart
7817 (uri (bioconductor-uri "biomaRt" version))
7820 "0676s8aq9xj2pdrfk28kf5j69fmssn900k4vxrp11ghwjr8z24h7"))))
7822 `((upstream-name . "biomaRt")))
7823 (build-system r-build-system)
7825 `(("r-annotationdbi" ,r-annotationdbi)
7826 ("r-biocfilecache" ,r-biocfilecache)
7828 ("r-openssl" ,r-openssl)
7829 ("r-progress" ,r-progress)
7830 ("r-rappdirs" ,r-rappdirs)
7831 ("r-stringr" ,r-stringr)
7834 `(("r-knitr" ,r-knitr)))
7835 (home-page "https://bioconductor.org/packages/biomaRt")
7836 (synopsis "Interface to BioMart databases")
7838 "biomaRt provides an interface to a growing collection of databases
7839 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7840 package enables retrieval of large amounts of data in a uniform way without
7841 the need to know the underlying database schemas or write complex SQL queries.
7842 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7843 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7844 users direct access to a diverse set of data and enable a wide range of
7845 powerful online queries from gene annotation to database mining.")
7846 (license license:artistic2.0)))
7848 (define-public r-biocparallel
7850 (name "r-biocparallel")
7854 (uri (bioconductor-uri "BiocParallel" version))
7857 "0g0znb4whsvb9hpwx9xaasdi5n4vjqw8cpdyqgrdrjm91rls1h21"))))
7859 `((upstream-name . "BiocParallel")))
7860 (build-system r-build-system)
7862 `(("r-futile-logger" ,r-futile-logger)
7865 (home-page "https://bioconductor.org/packages/BiocParallel")
7866 (synopsis "Bioconductor facilities for parallel evaluation")
7868 "This package provides modified versions and novel implementation of
7869 functions for parallel evaluation, tailored to use with Bioconductor
7871 (license (list license:gpl2+ license:gpl3+))))
7873 (define-public r-biostrings
7875 (name "r-biostrings")
7879 (uri (bioconductor-uri "Biostrings" version))
7882 "0pq7g2hflx2cjlpwdj6mscw9hnxvlf5y50dxf48lbrf9r3q9kmyp"))))
7884 `((upstream-name . "Biostrings")))
7885 (build-system r-build-system)
7887 `(("r-biocgenerics" ,r-biocgenerics)
7888 ("r-iranges" ,r-iranges)
7889 ("r-s4vectors" ,r-s4vectors)
7890 ("r-xvector" ,r-xvector)))
7891 (home-page "https://bioconductor.org/packages/Biostrings")
7892 (synopsis "String objects and algorithms for biological sequences")
7894 "This package provides memory efficient string containers, string
7895 matching algorithms, and other utilities, for fast manipulation of large
7896 biological sequences or sets of sequences.")
7897 (license license:artistic2.0)))
7899 (define-public r-rsamtools
7901 (name "r-rsamtools")
7905 (uri (bioconductor-uri "Rsamtools" version))
7908 "1vj43acawqqkf9yval9fzxarpsf04fmn78m2hq4f083w1k0myhyr"))))
7910 `((upstream-name . "Rsamtools")))
7911 (build-system r-build-system)
7914 (modify-phases %standard-phases
7915 (add-after 'unpack 'use-system-zlib
7917 (substitute* "DESCRIPTION"
7918 (("zlibbioc, ") ""))
7919 (substitute* "NAMESPACE"
7920 (("import\\(zlibbioc\\)") ""))
7925 `(("r-biocgenerics" ,r-biocgenerics)
7926 ("r-biocparallel" ,r-biocparallel)
7927 ("r-biostrings" ,r-biostrings)
7928 ("r-bitops" ,r-bitops)
7929 ("r-genomeinfodb" ,r-genomeinfodb)
7930 ("r-genomicranges" ,r-genomicranges)
7931 ("r-iranges" ,r-iranges)
7932 ("r-rhtslib" ,r-rhtslib)
7933 ("r-s4vectors" ,r-s4vectors)
7934 ("r-xvector" ,r-xvector)))
7935 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7936 (synopsis "Interface to samtools, bcftools, and tabix")
7938 "This package provides an interface to the @code{samtools},
7939 @code{bcftools}, and @code{tabix} utilities for manipulating SAM (Sequence
7940 Alignment / Map), FASTA, binary variant call (BCF) and compressed indexed
7941 tab-delimited (tabix) files.")
7942 (license license:expat)))
7944 (define-public r-delayedarray
7946 (name "r-delayedarray")
7950 (uri (bioconductor-uri "DelayedArray" version))
7953 "02i88ll2d7r83nk0wdj28akvsz3jq19g6ixpaahfy3jy5av4byv6"))))
7955 `((upstream-name . "DelayedArray")))
7956 (build-system r-build-system)
7958 `(("r-biocgenerics" ,r-biocgenerics)
7959 ("r-biocparallel" ,r-biocparallel)
7960 ("r-s4vectors" ,r-s4vectors)
7961 ("r-iranges" ,r-iranges)
7962 ("r-matrix" ,r-matrix)
7963 ("r-matrixstats" ,r-matrixstats)))
7965 `(("r-knitr" ,r-knitr)))
7966 (home-page "https://bioconductor.org/packages/DelayedArray")
7967 (synopsis "Delayed operations on array-like objects")
7969 "Wrapping an array-like object (typically an on-disk object) in a
7970 @code{DelayedArray} object allows one to perform common array operations on it
7971 without loading the object in memory. In order to reduce memory usage and
7972 optimize performance, operations on the object are either delayed or executed
7973 using a block processing mechanism. Note that this also works on in-memory
7974 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7975 @code{Matrix} objects, and ordinary arrays and data frames.")
7976 (license license:artistic2.0)))
7978 (define-public r-summarizedexperiment
7980 (name "r-summarizedexperiment")
7984 (uri (bioconductor-uri "SummarizedExperiment" version))
7987 "1z9bdk49dajafkfvv99nv6zyn6v70iyyy2jgdp5w5z8174a2bnn1"))))
7989 `((upstream-name . "SummarizedExperiment")))
7990 (build-system r-build-system)
7992 `(("r-biobase" ,r-biobase)
7993 ("r-biocgenerics" ,r-biocgenerics)
7994 ("r-delayedarray" ,r-delayedarray)
7995 ("r-genomeinfodb" ,r-genomeinfodb)
7996 ("r-genomicranges" ,r-genomicranges)
7997 ("r-iranges" ,r-iranges)
7998 ("r-matrix" ,r-matrix)
7999 ("r-s4vectors" ,r-s4vectors)))
8000 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
8001 (synopsis "Container for representing genomic ranges by sample")
8003 "The SummarizedExperiment container contains one or more assays, each
8004 represented by a matrix-like object of numeric or other mode. The rows
8005 typically represent genomic ranges of interest and the columns represent
8007 (license license:artistic2.0)))
8009 (define-public r-genomicalignments
8011 (name "r-genomicalignments")
8015 (uri (bioconductor-uri "GenomicAlignments" version))
8018 "065xvy4pkda0ajvl1b75iski95k1pnbhxwdq7vkfl8v55915vqh6"))))
8020 `((upstream-name . "GenomicAlignments")))
8021 (build-system r-build-system)
8023 `(("r-biocgenerics" ,r-biocgenerics)
8024 ("r-biocparallel" ,r-biocparallel)
8025 ("r-biostrings" ,r-biostrings)
8026 ("r-genomeinfodb" ,r-genomeinfodb)
8027 ("r-genomicranges" ,r-genomicranges)
8028 ("r-iranges" ,r-iranges)
8029 ("r-rsamtools" ,r-rsamtools)
8030 ("r-s4vectors" ,r-s4vectors)
8031 ("r-summarizedexperiment" ,r-summarizedexperiment)))
8032 (home-page "https://bioconductor.org/packages/GenomicAlignments")
8033 (synopsis "Representation and manipulation of short genomic alignments")
8035 "This package provides efficient containers for storing and manipulating
8036 short genomic alignments (typically obtained by aligning short reads to a
8037 reference genome). This includes read counting, computing the coverage,
8038 junction detection, and working with the nucleotide content of the
8040 (license license:artistic2.0)))
8042 (define-public r-rtracklayer
8044 (name "r-rtracklayer")
8048 (uri (bioconductor-uri "rtracklayer" version))
8051 "0lp9xsm8kqrgpwgwj7qaqcv1z6qynbz084grlpwp94zsp2ppf0n6"))))
8052 (build-system r-build-system)
8055 (modify-phases %standard-phases
8056 (add-after 'unpack 'use-system-zlib
8058 (substitute* "DESCRIPTION"
8059 ((" zlibbioc,") ""))
8060 (substitute* "NAMESPACE"
8061 (("import\\(zlibbioc\\)") ""))
8064 `(("pkg-config" ,pkg-config)))
8068 `(("r-biocgenerics" ,r-biocgenerics)
8069 ("r-biostrings" ,r-biostrings)
8070 ("r-genomeinfodb" ,r-genomeinfodb)
8071 ("r-genomicalignments" ,r-genomicalignments)
8072 ("r-genomicranges" ,r-genomicranges)
8073 ("r-iranges" ,r-iranges)
8074 ("r-rcurl" ,r-rcurl)
8075 ("r-rsamtools" ,r-rsamtools)
8076 ("r-s4vectors" ,r-s4vectors)
8078 ("r-xvector" ,r-xvector)))
8079 (home-page "https://bioconductor.org/packages/rtracklayer")
8080 (synopsis "R interface to genome browsers and their annotation tracks")
8082 "rtracklayer is an extensible framework for interacting with multiple
8083 genome browsers (currently UCSC built-in) and manipulating annotation tracks
8084 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
8085 built-in). The user may export/import tracks to/from the supported browsers,
8086 as well as query and modify the browser state, such as the current viewport.")
8087 (license license:artistic2.0)))
8089 (define-public r-genomicfeatures
8091 (name "r-genomicfeatures")
8095 (uri (bioconductor-uri "GenomicFeatures" version))
8098 "0dd226kgks50jdx5w35f3wmg95hy8aibi4kcn8p5kmqp5i8j580b"))))
8100 `((upstream-name . "GenomicFeatures")))
8101 (build-system r-build-system)
8103 `(("r-annotationdbi" ,r-annotationdbi)
8104 ("r-biobase" ,r-biobase)
8105 ("r-biocgenerics" ,r-biocgenerics)
8106 ("r-biomart" ,r-biomart)
8107 ("r-biostrings" ,r-biostrings)
8109 ("r-genomeinfodb" ,r-genomeinfodb)
8110 ("r-genomicranges" ,r-genomicranges)
8111 ("r-iranges" ,r-iranges)
8112 ("r-rcurl" ,r-rcurl)
8113 ("r-rsqlite" ,r-rsqlite)
8114 ("r-rtracklayer" ,r-rtracklayer)
8115 ("r-s4vectors" ,r-s4vectors)
8116 ("r-xvector" ,r-xvector)))
8117 (home-page "https://bioconductor.org/packages/GenomicFeatures")
8118 (synopsis "Tools for working with transcript centric annotations")
8120 "This package provides a set of tools and methods for making and
8121 manipulating transcript centric annotations. With these tools the user can
8122 easily download the genomic locations of the transcripts, exons and cds of a
8123 given organism, from either the UCSC Genome Browser or a BioMart
8124 database (more sources will be supported in the future). This information is
8125 then stored in a local database that keeps track of the relationship between
8126 transcripts, exons, cds and genes. Flexible methods are provided for
8127 extracting the desired features in a convenient format.")
8128 (license license:artistic2.0)))
8130 (define-public r-go-db
8136 (uri (string-append "https://www.bioconductor.org/packages/"
8137 "release/data/annotation/src/contrib/GO.db_"
8141 "0i3wcf5h3n0dawzc1hy0kv74f06j80c47n4p3g3fmrcxlhi3jpa5"))))
8143 `((upstream-name . "GO.db")))
8144 (build-system r-build-system)
8146 `(("r-annotationdbi" ,r-annotationdbi)))
8147 (home-page "https://bioconductor.org/packages/GO.db")
8148 (synopsis "Annotation maps describing the entire Gene Ontology")
8150 "The purpose of this GO.db annotation package is to provide detailed
8151 information about the latest version of the Gene Ontologies.")
8152 (license license:artistic2.0)))
8154 (define-public r-topgo
8160 (uri (bioconductor-uri "topGO" version))
8163 "1kw9m2j67895k58lx9msc248pjwblp8clxwgsl01cql7sgi1xzlf"))))
8165 `((upstream-name . "topGO")))
8166 (build-system r-build-system)
8168 `(("r-annotationdbi" ,r-annotationdbi)
8170 ("r-biobase" ,r-biobase)
8171 ("r-biocgenerics" ,r-biocgenerics)
8172 ("r-go-db" ,r-go-db)
8173 ("r-graph" ,r-graph)
8174 ("r-lattice" ,r-lattice)
8175 ("r-matrixstats" ,r-matrixstats)
8176 ("r-sparsem" ,r-sparsem)))
8177 (home-page "https://bioconductor.org/packages/topGO")
8178 (synopsis "Enrichment analysis for gene ontology")
8180 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
8181 terms while accounting for the topology of the GO graph. Different test
8182 statistics and different methods for eliminating local similarities and
8183 dependencies between GO terms can be implemented and applied.")
8184 ;; Any version of the LGPL applies.
8185 (license license:lgpl2.1+)))
8187 (define-public r-bsgenome
8193 (uri (bioconductor-uri "BSgenome" version))
8196 "0nn1b3h4hmnx5whf2cmzmyxdrcf4myj8c38rwr0sw4rc07xfzndy"))))
8198 `((upstream-name . "BSgenome")))
8199 (build-system r-build-system)
8201 `(("r-biocgenerics" ,r-biocgenerics)
8202 ("r-biostrings" ,r-biostrings)
8203 ("r-genomeinfodb" ,r-genomeinfodb)
8204 ("r-genomicranges" ,r-genomicranges)
8205 ("r-iranges" ,r-iranges)
8206 ("r-rsamtools" ,r-rsamtools)
8207 ("r-rtracklayer" ,r-rtracklayer)
8208 ("r-s4vectors" ,r-s4vectors)
8209 ("r-xvector" ,r-xvector)))
8210 (home-page "https://bioconductor.org/packages/BSgenome")
8211 (synopsis "Infrastructure for Biostrings-based genome data packages")
8213 "This package provides infrastructure shared by all Biostrings-based
8214 genome data packages and support for efficient SNP representation.")
8215 (license license:artistic2.0)))
8217 (define-public r-impute
8223 (uri (bioconductor-uri "impute" version))
8226 "0igz1phjd1j9bg9z4kyy7j8v9bxi9sdwz4df26r51i2vavlbrf4q"))))
8228 `(("gfortran" ,gfortran)))
8229 (build-system r-build-system)
8230 (home-page "https://bioconductor.org/packages/impute")
8231 (synopsis "Imputation for microarray data")
8233 "This package provides a function to impute missing gene expression
8234 microarray data, using nearest neighbor averaging.")
8235 (license license:gpl2+)))
8237 (define-public r-seqpattern
8239 (name "r-seqpattern")
8243 (uri (bioconductor-uri "seqPattern" version))
8246 "1gxrq6s2hiyac69idh5r1nbr1s69n0hg4ap2skm4g6857av9pwqf"))))
8248 `((upstream-name . "seqPattern")))
8249 (build-system r-build-system)
8251 `(("r-biostrings" ,r-biostrings)
8252 ("r-genomicranges" ,r-genomicranges)
8253 ("r-iranges" ,r-iranges)
8254 ("r-kernsmooth" ,r-kernsmooth)
8255 ("r-plotrix" ,r-plotrix)))
8256 (home-page "https://bioconductor.org/packages/seqPattern")
8257 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
8259 "This package provides tools to visualize oligonucleotide patterns and
8260 sequence motif occurrences across a large set of sequences centred at a common
8261 reference point and sorted by a user defined feature.")
8262 (license license:gpl3+)))
8264 (define-public r-genomation
8266 (name "r-genomation")
8270 (uri (bioconductor-uri "genomation" version))
8273 "1sba928h23b67gr3i4yj1bg655g24l3bcgsf5gvymzrv5idrss1l"))))
8274 (build-system r-build-system)
8276 `(("r-biostrings" ,r-biostrings)
8277 ("r-bsgenome" ,r-bsgenome)
8278 ("r-data-table" ,r-data-table)
8279 ("r-genomeinfodb" ,r-genomeinfodb)
8280 ("r-genomicalignments" ,r-genomicalignments)
8281 ("r-genomicranges" ,r-genomicranges)
8282 ("r-ggplot2" ,r-ggplot2)
8283 ("r-gridbase" ,r-gridbase)
8284 ("r-impute" ,r-impute)
8285 ("r-iranges" ,r-iranges)
8286 ("r-matrixstats" ,r-matrixstats)
8287 ("r-plotrix" ,r-plotrix)
8290 ("r-readr" ,r-readr)
8291 ("r-reshape2" ,r-reshape2)
8292 ("r-rsamtools" ,r-rsamtools)
8293 ("r-rtracklayer" ,r-rtracklayer)
8294 ("r-runit" ,r-runit)
8295 ("r-s4vectors" ,r-s4vectors)
8296 ("r-seqpattern" ,r-seqpattern)))
8297 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8298 (synopsis "Summary, annotation and visualization of genomic data")
8300 "This package provides a package for summary and annotation of genomic
8301 intervals. Users can visualize and quantify genomic intervals over
8302 pre-defined functional regions, such as promoters, exons, introns, etc. The
8303 genomic intervals represent regions with a defined chromosome position, which
8304 may be associated with a score, such as aligned reads from HT-seq experiments,
8305 TF binding sites, methylation scores, etc. The package can use any tabular
8306 genomic feature data as long as it has minimal information on the locations of
8307 genomic intervals. In addition, it can use BAM or BigWig files as input.")
8308 (license license:artistic2.0)))
8310 (define-public r-genomationdata
8312 (name "r-genomationdata")
8316 ;; We cannot use bioconductor-uri here because this tarball is
8317 ;; located under "data/annotation/" instead of "bioc/".
8318 (uri (string-append "https://bioconductor.org/packages/"
8319 "release/data/experiment/src/contrib/"
8320 "genomationData_" version ".tar.gz"))
8323 "10xyb8akjrhmak2i0mnv1agny2ipy364q9nlibyplpzc7vdb6bw7"))))
8324 (build-system r-build-system)
8325 ;; As this package provides little more than large data files, it doesn't
8326 ;; make sense to build substitutes.
8327 (arguments `(#:substitutable? #f))
8329 `(("r-knitr" ,r-knitr)))
8330 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8331 (synopsis "Experimental data for use with the genomation package")
8333 "This package contains experimental genetic data for use with the
8334 genomation package. Included are Chip Seq, Methylation and Cage data,
8335 downloaded from Encode.")
8336 (license license:gpl3+)))
8338 (define-public r-seqlogo
8345 (uri (bioconductor-uri "seqLogo" version))
8348 "0s94aahp8ma1crmp83dz65ifjwrx6wqi3q6005lmbp8yk2x1rkj4"))))
8349 (properties `((upstream-name . "seqLogo")))
8350 (build-system r-build-system)
8351 (home-page "https://bioconductor.org/packages/seqLogo")
8352 (synopsis "Sequence logos for DNA sequence alignments")
8354 "seqLogo takes the position weight matrix of a DNA sequence motif and
8355 plots the corresponding sequence logo as introduced by Schneider and
8357 (license license:lgpl2.0+)))
8359 (define-public r-motifrg
8366 (uri (bioconductor-uri "motifRG" version))
8369 "0s6wdr036lra9x93r9k8wvicbkgzypjh3jp46h92yacw8d829k0d"))))
8370 (properties `((upstream-name . "motifRG")))
8371 (build-system r-build-system)
8373 `(("r-biostrings" ,r-biostrings)
8374 ("r-bsgenome" ,r-bsgenome)
8375 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8376 ("r-iranges" ,r-iranges)
8377 ("r-seqlogo" ,r-seqlogo)
8378 ("r-xvector" ,r-xvector)))
8379 (home-page "https://bioconductor.org/packages/motifRG")
8380 (synopsis "Discover motifs in high throughput sequencing data")
8382 "This package provides tools for discriminative motif discovery in high
8383 throughput genetic sequencing data sets using regression methods.")
8384 (license license:artistic2.0)))
8386 (define-public r-qtl
8393 (uri (string-append "mirror://cran/src/contrib/qtl_"
8397 "0rbwcnvyy96gq1dsgpxx03pv423qya26h6ws5y0blj3blfdmj83a"))))
8398 (build-system r-build-system)
8399 (home-page "https://rqtl.org/")
8400 (synopsis "R package for analyzing QTL experiments in genetics")
8401 (description "R/qtl is an extension library for the R statistics
8402 system. It is used to analyze experimental crosses for identifying
8403 genes contributing to variation in quantitative traits (so-called
8404 quantitative trait loci, QTLs).
8406 Using a hidden Markov model, R/qtl estimates genetic maps, to
8407 identify genotyping errors, and to perform single-QTL and two-QTL,
8408 two-dimensional genome scans.")
8409 (license license:gpl3)))
8411 (define-public r-qtl2
8417 ;; Not yet available in cran.
8419 (url "https://github.com/rqtl/qtl2.git")
8421 (file-name (git-file-name name version))
8423 (base32 "0l1asr28q25jzbwrbg5490962sg3y4sjrd0qf09p78ws1aq8vfs0"))))
8424 (build-system r-build-system)
8426 `(("r-data-table" ,r-data-table)
8427 ("r-jsonlite" ,r-jsonlite)
8429 ("r-rcppeigen" ,r-rcppeigen)
8430 ("r-rsqlite" ,r-rsqlite)
8431 ("r-yaml" ,r-yaml)))
8432 (home-page "https://kbroman.org/qtl2/")
8434 "QTL analysis software for high-dimensional data and complex cross designs")
8436 "R/qtl2 (aka qtl2) is a reimplementation of the QTL analysis software
8437 R/qtl, to better handle high-dimensional data and complex cross designs.")
8438 (license license:gpl3)))
8440 (define-public r-zlibbioc
8446 (uri (bioconductor-uri "zlibbioc" version))
8449 "1xh7qan0w62mzsmanbx9vcj6ygdfhzw1abaxijkq7f4nh5w87idj"))))
8451 `((upstream-name . "zlibbioc")))
8452 (build-system r-build-system)
8453 (home-page "https://bioconductor.org/packages/zlibbioc")
8454 (synopsis "Provider for zlib-1.2.5 to R packages")
8455 (description "This package uses the source code of zlib-1.2.5 to create
8456 libraries for systems that do not have these available via other means.")
8457 (license license:artistic2.0)))
8459 (define-public r-r4rna
8466 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8470 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8471 (build-system r-build-system)
8473 `(("r-optparse" ,r-optparse)
8474 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8475 (home-page "https://www.e-rna.org/r-chie/index.cgi")
8476 (synopsis "Analysis framework for RNA secondary structure")
8478 "The R4RNA package aims to be a general framework for the analysis of RNA
8479 secondary structure and comparative analysis in R.")
8480 (license license:gpl3+)))
8482 (define-public r-rhtslib
8489 (uri (bioconductor-uri "Rhtslib" version))
8492 "0gkbrmrcg55c9s5166ifljlx0v25rv4ijdyp4wf4c292xd6chy2l"))))
8493 (properties `((upstream-name . "Rhtslib")))
8494 (build-system r-build-system)
8495 ;; Without this a temporary directory ends up in the Rhtslib.so binary,
8496 ;; which makes R abort the build.
8497 (arguments '(#:configure-flags '("--no-staged-install")))
8500 ("r-zlibbioc" ,r-zlibbioc)))
8504 `(("pkg-config" ,pkg-config)))
8505 (home-page "https://github.com/nhayden/Rhtslib")
8506 (synopsis "High-throughput sequencing library as an R package")
8508 "This package provides the HTSlib C library for high-throughput
8509 nucleotide sequence analysis. The package is primarily useful to developers
8510 of other R packages who wish to make use of HTSlib.")
8511 (license license:lgpl2.0+)))
8513 (define-public r-bamsignals
8515 (name "r-bamsignals")
8520 (uri (bioconductor-uri "bamsignals" version))
8523 "0699b0pqbs0dvs91yjibcjc90lxj9mg8rcml4a6wchfr9md7n74w"))))
8524 (build-system r-build-system)
8526 `(("r-biocgenerics" ,r-biocgenerics)
8527 ("r-genomicranges" ,r-genomicranges)
8528 ("r-iranges" ,r-iranges)
8530 ("r-rhtslib" ,r-rhtslib)
8531 ("r-zlibbioc" ,r-zlibbioc)))
8534 (home-page "https://bioconductor.org/packages/bamsignals")
8535 (synopsis "Extract read count signals from bam files")
8537 "This package efficiently obtains count vectors from indexed bam
8538 files. It counts the number of nucleotide sequence reads in given genomic
8539 ranges and it computes reads profiles and coverage profiles. It also handles
8541 (license license:gpl2+)))
8543 (define-public r-rcas
8549 (uri (bioconductor-uri "RCAS" version))
8552 "1s3gvvxi1029d1vfwnjh21nnw3mlx08kcwz63891hml9y850cvsn"))))
8553 (properties `((upstream-name . "RCAS")))
8554 (build-system r-build-system)
8556 `(("r-annotationdbi" ,r-annotationdbi)
8557 ("r-biocgenerics" ,r-biocgenerics)
8558 ("r-biomart" ,r-biomart)
8559 ("r-biostrings" ,r-biostrings)
8560 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8561 ("r-cowplot" ,r-cowplot)
8562 ("r-data-table" ,r-data-table)
8565 ("r-genomation" ,r-genomation)
8566 ("r-genomeinfodb" ,r-genomeinfodb)
8567 ("r-genomicfeatures" ,r-genomicfeatures)
8568 ("r-genomicranges" ,r-genomicranges)
8569 ("r-ggplot2" ,r-ggplot2)
8570 ("r-ggseqlogo" ,r-ggseqlogo)
8571 ("r-knitr" ,r-knitr)
8572 ("r-motifrg" ,r-motifrg)
8573 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8574 ("r-pbapply" ,r-pbapply)
8575 ("r-pheatmap" ,r-pheatmap)
8576 ("r-plotly" ,r-plotly)
8577 ("r-plotrix" ,r-plotrix)
8578 ("r-proxy" ,r-proxy)
8579 ("r-rsqlite" ,r-rsqlite)
8580 ("r-rtracklayer" ,r-rtracklayer)
8581 ("r-rmarkdown" ,r-rmarkdown)
8582 ("r-s4vectors" ,r-s4vectors)
8583 ("r-topgo" ,r-topgo)
8584 ("pandoc" ,ghc-pandoc)))
8585 (synopsis "RNA-centric annotation system")
8587 "RCAS aims to be a standalone RNA-centric annotation system that provides
8588 intuitive reports and publication-ready graphics. This package provides the R
8589 library implementing most of the pipeline's features.")
8590 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8591 (license license:artistic2.0)))
8593 (define-public rcas-web
8600 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8601 "releases/download/v" version
8602 "/rcas-web-" version ".tar.gz"))
8605 "0wq951aj45gqki1bickg876i993lmawkp8x24agg264br5x716db"))))
8606 (build-system gnu-build-system)
8609 (modify-phases %standard-phases
8610 (add-before 'configure 'find-RCAS
8611 ;; The configure script can't find non-1.3.x versions of RCAS because
8612 ;; its R expression ‘1.10.1 >= 1.3.4’ evaluates to false.
8614 (substitute* "configure"
8615 (("1\\.3\\.4") "0.0.0"))
8617 (add-after 'install 'wrap-executable
8618 (lambda* (#:key inputs outputs #:allow-other-keys)
8619 (let* ((out (assoc-ref outputs "out"))
8620 (json (assoc-ref inputs "guile-json"))
8621 (redis (assoc-ref inputs "guile-redis"))
8622 (path (string-append
8623 json "/share/guile/site/2.2:"
8624 redis "/share/guile/site/2.2")))
8625 (wrap-program (string-append out "/bin/rcas-web")
8626 `("GUILE_LOAD_PATH" ":" = (,path))
8627 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8628 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8631 `(("r-minimal" ,r-minimal)
8633 ("guile-next" ,guile-2.2)
8634 ("guile-json" ,guile-json-1)
8635 ("guile-redis" ,guile-redis)))
8637 `(("pkg-config" ,pkg-config)))
8638 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8639 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8640 (description "This package provides a simple web interface for the
8641 @dfn{RNA-centric annotation system} (RCAS).")
8642 (license license:agpl3+)))
8644 (define-public r-mutationalpatterns
8646 (name "r-mutationalpatterns")
8651 (uri (bioconductor-uri "MutationalPatterns" version))
8654 "08715l6swrlccviw7932v5hyrd2x4c6049vy9qnxk0lw3sp1zvsf"))))
8655 (build-system r-build-system)
8657 `(("r-biocgenerics" ,r-biocgenerics)
8658 ("r-biostrings" ,r-biostrings)
8659 ;; These two packages are suggested packages
8660 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8661 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8662 ("r-genomicranges" ,r-genomicranges)
8663 ("r-genomeinfodb" ,r-genomeinfodb)
8664 ("r-ggplot2" ,r-ggplot2)
8665 ("r-iranges" ,r-iranges)
8668 ("r-pracma" ,r-pracma)
8669 ("r-reshape2" ,r-reshape2)
8670 ("r-cowplot" ,r-cowplot)
8671 ("r-ggdendro" ,r-ggdendro)
8672 ("r-s4vectors" ,r-s4vectors)
8673 ("r-summarizedexperiment" ,r-summarizedexperiment)
8674 ("r-variantannotation" ,r-variantannotation)))
8675 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8676 (synopsis "Extract and visualize mutational patterns in genomic data")
8677 (description "This package provides an extensive toolset for the
8678 characterization and visualization of a wide range of mutational patterns
8679 in SNV base substitution data.")
8680 (license license:expat)))
8682 (define-public r-chipkernels
8683 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8686 (name "r-chipkernels")
8687 (version (string-append "1.1-" revision "." (string-take commit 9)))
8692 (url "https://github.com/ManuSetty/ChIPKernels.git")
8694 (file-name (string-append name "-" version))
8697 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8698 (build-system r-build-system)
8700 `(("r-iranges" ,r-iranges)
8701 ("r-xvector" ,r-xvector)
8702 ("r-biostrings" ,r-biostrings)
8703 ("r-bsgenome" ,r-bsgenome)
8704 ("r-gtools" ,r-gtools)
8705 ("r-genomicranges" ,r-genomicranges)
8706 ("r-sfsmisc" ,r-sfsmisc)
8707 ("r-kernlab" ,r-kernlab)
8708 ("r-s4vectors" ,r-s4vectors)
8709 ("r-biocgenerics" ,r-biocgenerics)))
8710 (home-page "https://github.com/ManuSetty/ChIPKernels")
8711 (synopsis "Build string kernels for DNA Sequence analysis")
8712 (description "ChIPKernels is an R package for building different string
8713 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8714 must be built and this dictionary can be used for determining kernels for DNA
8716 (license license:gpl2+))))
8718 (define-public r-seqgl
8726 (url "https://github.com/ManuSetty/SeqGL.git")
8728 (file-name (git-file-name name version))
8731 "1r6ywvhxl3ffv48lgj7sbd582mcc6dha3ksgc2qjlvjrnkbj3799"))))
8732 (build-system r-build-system)
8734 `(("r-biostrings" ,r-biostrings)
8735 ("r-chipkernels" ,r-chipkernels)
8736 ("r-genomicranges" ,r-genomicranges)
8737 ("r-spams" ,r-spams)
8738 ("r-wgcna" ,r-wgcna)
8739 ("r-fastcluster" ,r-fastcluster)))
8740 (home-page "https://github.com/ManuSetty/SeqGL")
8741 (synopsis "Group lasso for Dnase/ChIP-seq data")
8742 (description "SeqGL is a group lasso based algorithm to extract
8743 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8744 This package presents a method which uses group lasso to discriminate between
8745 bound and non bound genomic regions to accurately identify transcription
8746 factors bound at the specific regions.")
8747 (license license:gpl2+)))
8749 (define-public r-tximport
8755 (uri (bioconductor-uri "tximport" version))
8758 "1avy0zhgnszmg0dr9w74yq9ml10kwdrrgcni2wysrd48zzskc1n0"))))
8759 (build-system r-build-system)
8761 `(("r-knitr" ,r-knitr)))
8762 (home-page "https://bioconductor.org/packages/tximport")
8763 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8765 "This package provides tools to import transcript-level abundance,
8766 estimated counts and transcript lengths, and to summarize them into matrices
8767 for use with downstream gene-level analysis packages. Average transcript
8768 length, weighted by sample-specific transcript abundance estimates, is
8769 provided as a matrix which can be used as an offset for different expression
8770 of gene-level counts.")
8771 (license license:gpl2+)))
8773 (define-public r-rhdf5
8779 (uri (bioconductor-uri "rhdf5" version))
8782 "18pv74jj4wr1981r92ss10qkgf5g1b09dsbz3im3j70a4l5l0df0"))))
8783 (build-system r-build-system)
8785 `(("r-rhdf5lib" ,r-rhdf5lib)))
8788 (home-page "https://bioconductor.org/packages/rhdf5")
8789 (synopsis "HDF5 interface to R")
8791 "This R/Bioconductor package provides an interface between HDF5 and R.
8792 HDF5's main features are the ability to store and access very large and/or
8793 complex datasets and a wide variety of metadata on mass storage (disk) through
8794 a completely portable file format. The rhdf5 package is thus suited for the
8795 exchange of large and/or complex datasets between R and other software
8796 package, and for letting R applications work on datasets that are larger than
8797 the available RAM.")
8798 (license license:artistic2.0)))
8800 (define-public r-annotationfilter
8802 (name "r-annotationfilter")
8806 (uri (bioconductor-uri "AnnotationFilter" version))
8809 "1l9sxhlvnwn6327vgg02h11ppmqr2zr07ff8wmcng0i1jbqwa8q5"))))
8811 `((upstream-name . "AnnotationFilter")))
8812 (build-system r-build-system)
8814 `(("r-genomicranges" ,r-genomicranges)
8815 ("r-lazyeval" ,r-lazyeval)))
8816 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8817 (synopsis "Facilities for filtering Bioconductor annotation resources")
8819 "This package provides classes and other infrastructure to implement
8820 filters for manipulating Bioconductor annotation resources. The filters are
8821 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8822 (license license:artistic2.0)))
8824 (define-public emboss
8830 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8831 (version-major+minor version) ".0/"
8832 "EMBOSS-" version ".tar.gz"))
8835 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8836 (build-system gnu-build-system)
8839 (list (string-append "--with-hpdf="
8840 (assoc-ref %build-inputs "libharu")))
8842 (modify-phases %standard-phases
8843 (add-after 'unpack 'fix-checks
8845 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8846 ;; and zlib, but assume that they are all found at the same
8848 (substitute* "configure.in"
8849 (("CHECK_PNGDRIVER")
8850 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8851 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8852 AM_CONDITIONAL(AMPNG, true)"))
8854 (add-after 'fix-checks 'disable-update-check
8856 ;; At build time there is no connection to the Internet, so
8857 ;; looking for updates will not work.
8858 (substitute* "Makefile.am"
8859 (("\\$\\(bindir\\)/embossupdate") ""))
8861 (add-after 'disable-update-check 'autogen
8862 (lambda _ (invoke "autoreconf" "-vif") #t)))))
8868 ("libharu" ,libharu)
8871 `(("autoconf" ,autoconf)
8872 ("automake" ,automake)
8873 ("libtool" ,libtool)
8874 ("pkg-config" ,pkg-config)))
8875 (home-page "http://emboss.sourceforge.net")
8876 (synopsis "Molecular biology analysis suite")
8877 (description "EMBOSS is the \"European Molecular Biology Open Software
8878 Suite\". EMBOSS is an analysis package specially developed for the needs of
8879 the molecular biology (e.g. EMBnet) user community. The software
8880 automatically copes with data in a variety of formats and even allows
8881 transparent retrieval of sequence data from the web. It also provides a
8882 number of libraries for the development of software in the field of molecular
8883 biology. EMBOSS also integrates a range of currently available packages and
8884 tools for sequence analysis into a seamless whole.")
8885 (license license:gpl2+)))
8888 (let ((revision "1")
8889 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8892 ;; The version is 2.13.0 even though no release archives have been
8893 ;; published as yet.
8894 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8898 (url "https://github.com/arq5x/bits.git")
8900 (file-name (string-append name "-" version "-checkout"))
8903 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8904 (build-system gnu-build-system)
8906 `(#:tests? #f ;no tests included
8908 (modify-phases %standard-phases
8910 (add-after 'unpack 'remove-cuda
8912 (substitute* "Makefile"
8914 (("(bits_test_intersections) \\\\" _ match) match))
8917 (lambda* (#:key outputs #:allow-other-keys)
8919 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8924 (home-page "https://github.com/arq5x/bits")
8925 (synopsis "Implementation of binary interval search algorithm")
8926 (description "This package provides an implementation of the
8927 BITS (Binary Interval Search) algorithm, an approach to interval set
8928 intersection. It is especially suited for the comparison of diverse genomic
8929 datasets and the exploration of large datasets of genome
8930 intervals (e.g. genes, sequence alignments).")
8931 (license license:gpl2))))
8933 (define-public piranha
8934 ;; There is no release tarball for the latest version. The latest commit is
8935 ;; older than one year at the time of this writing.
8936 (let ((revision "1")
8937 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8940 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8944 (url "https://github.com/smithlabcode/piranha.git")
8946 (file-name (git-file-name name version))
8949 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
8950 (build-system gnu-build-system)
8952 `(#:test-target "test"
8954 (modify-phases %standard-phases
8955 (add-after 'unpack 'copy-smithlab-cpp
8956 (lambda* (#:key inputs #:allow-other-keys)
8957 (for-each (lambda (file)
8958 (install-file file "./src/smithlab_cpp/"))
8959 (find-files (assoc-ref inputs "smithlab-cpp")))
8961 (add-after 'install 'install-to-store
8962 (lambda* (#:key outputs #:allow-other-keys)
8963 (let* ((out (assoc-ref outputs "out"))
8964 (bin (string-append out "/bin")))
8965 (for-each (lambda (file)
8966 (install-file file bin))
8967 (find-files "bin" ".*")))
8970 (list (string-append "--with-bam_tools_headers="
8971 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
8972 (string-append "--with-bam_tools_library="
8973 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
8975 `(("bamtools" ,bamtools)
8976 ("samtools" ,samtools-0.1)
8979 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8983 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8985 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8988 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8990 `(("python" ,python-2)))
8991 (home-page "https://github.com/smithlabcode/piranha")
8992 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
8994 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
8995 RIP-seq experiments. It takes input in BED or BAM format and identifies
8996 regions of statistically significant read enrichment. Additional covariates
8997 may optionally be provided to further inform the peak-calling process.")
8998 (license license:gpl3+))))
9006 (uri (pypi-uri "PePr" version))
9009 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
9010 (build-system python-build-system)
9012 `(#:python ,python-2 ; python2 only
9013 #:tests? #f)) ; no tests included
9015 `(("python2-numpy" ,python2-numpy)
9016 ("python2-scipy" ,python2-scipy)
9017 ("python2-pysam" ,python2-pysam)))
9018 (home-page "https://github.com/shawnzhangyx/PePr")
9019 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
9021 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
9022 that is primarily designed for data with biological replicates. It uses a
9023 negative binomial distribution to model the read counts among the samples in
9024 the same group, and look for consistent differences between ChIP and control
9025 group or two ChIP groups run under different conditions.")
9026 (license license:gpl3+)))
9028 (define-public filevercmp
9029 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
9032 (version (string-append "0-1." (string-take commit 7)))
9036 (url "https://github.com/ekg/filevercmp.git")
9038 (file-name (git-file-name name commit))
9041 "1j9vxsy0y050v59h0q1d6501fcw1kjvj0d18l1xk2zyg0jzj247c"))))
9042 (build-system gnu-build-system)
9044 `(#:tests? #f ; There are no tests to run.
9046 (modify-phases %standard-phases
9047 (delete 'configure) ; There is no configure phase.
9049 (lambda* (#:key outputs #:allow-other-keys)
9050 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
9051 (install-file "filevercmp" bin)
9053 (home-page "https://github.com/ekg/filevercmp")
9054 (synopsis "This program compares version strings")
9055 (description "This program compares version strings. It intends to be a
9056 replacement for strverscmp.")
9057 (license license:gpl3+))))
9059 (define-public multiqc
9066 (uri (pypi-uri "multiqc" version))
9069 "02iihfl0w0hpnr4pa0sbd1y9qxrg3ycyhjp5lidkcrqh1lmzs3zy"))))
9070 (build-system python-build-system)
9072 `(("python-jinja2" ,python-jinja2)
9073 ("python-simplejson" ,python-simplejson)
9074 ("python-pyyaml" ,python-pyyaml)
9075 ("python-click" ,python-click)
9076 ("python-spectra" ,python-spectra)
9077 ("python-requests" ,python-requests)
9078 ("python-markdown" ,python-markdown)
9079 ("python-lzstring" ,python-lzstring)
9080 ("python-matplotlib" ,python-matplotlib)
9081 ("python-numpy" ,python-numpy)
9082 ;; MultQC checks for the presence of nose at runtime.
9083 ("python-nose" ,python-nose)))
9086 (modify-phases %standard-phases
9087 (add-after 'unpack 'relax-requirements
9089 (substitute* "setup.py"
9090 ;; MultiQC 1.5 ‘requires’ a version of python-matplotlib older
9091 ;; than the one in Guix, but should work fine with 2.2.2.
9092 ;; See <https://github.com/ewels/MultiQC/issues/725> and
9093 ;; <https://github.com/ewels/MultiQC/issues/732> for details.
9094 (("['\"]matplotlib.*?['\"]")
9097 (home-page "https://multiqc.info")
9098 (synopsis "Aggregate bioinformatics analysis reports")
9100 "MultiQC is a tool to aggregate bioinformatics results across many
9101 samples into a single report. It contains modules for a large number of
9102 common bioinformatics tools.")
9103 (license license:gpl3+)))
9105 (define-public r-chipseq
9112 (uri (bioconductor-uri "chipseq" version))
9115 "1ln6bn08xig3j6ryak1xfkjhvpnlm2vf1czz9hlj6f02299nbs6l"))))
9116 (build-system r-build-system)
9118 `(("r-biocgenerics" ,r-biocgenerics)
9119 ("r-genomicranges" ,r-genomicranges)
9120 ("r-iranges" ,r-iranges)
9121 ("r-lattice" ,r-lattice)
9122 ("r-s4vectors" ,r-s4vectors)
9123 ("r-shortread" ,r-shortread)))
9124 (home-page "https://bioconductor.org/packages/chipseq")
9125 (synopsis "Package for analyzing ChIPseq data")
9127 "This package provides tools for processing short read data from ChIPseq
9129 (license license:artistic2.0)))
9131 (define-public r-copyhelper
9133 (name "r-copyhelper")
9138 (uri (string-append "https://bioconductor.org/packages/release/"
9139 "data/experiment/src/contrib/CopyhelpeR_"
9143 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
9144 (properties `((upstream-name . "CopyhelpeR")))
9145 (build-system r-build-system)
9146 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
9147 (synopsis "Helper files for CopywriteR")
9149 "This package contains the helper files that are required to run the
9150 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
9151 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
9152 mm10. In addition, it contains a blacklist filter to remove regions that
9153 display copy number variation. Files are stored as GRanges objects from the
9154 GenomicRanges Bioconductor package.")
9155 (license license:gpl2)))
9157 (define-public r-copywriter
9159 (name "r-copywriter")
9164 (uri (bioconductor-uri "CopywriteR" version))
9167 "0llg1zpxg7qnvja5f5w1z1xic0jdg6zc4mfn97h2sm44skxxcyl1"))))
9168 (properties `((upstream-name . "CopywriteR")))
9169 (build-system r-build-system)
9171 `(("r-biocparallel" ,r-biocparallel)
9172 ("r-chipseq" ,r-chipseq)
9173 ("r-copyhelper" ,r-copyhelper)
9174 ("r-data-table" ,r-data-table)
9175 ("r-dnacopy" ,r-dnacopy)
9176 ("r-futile-logger" ,r-futile-logger)
9177 ("r-genomeinfodb" ,r-genomeinfodb)
9178 ("r-genomicalignments" ,r-genomicalignments)
9179 ("r-genomicranges" ,r-genomicranges)
9180 ("r-gtools" ,r-gtools)
9181 ("r-iranges" ,r-iranges)
9182 ("r-matrixstats" ,r-matrixstats)
9183 ("r-rsamtools" ,r-rsamtools)
9184 ("r-s4vectors" ,r-s4vectors)))
9185 (home-page "https://github.com/PeeperLab/CopywriteR")
9186 (synopsis "Copy number information from targeted sequencing")
9188 "CopywriteR extracts DNA copy number information from targeted sequencing
9189 by utilizing off-target reads. It allows for extracting uniformly distributed
9190 copy number information, can be used without reference, and can be applied to
9191 sequencing data obtained from various techniques including chromatin
9192 immunoprecipitation and target enrichment on small gene panels. Thereby,
9193 CopywriteR constitutes a widely applicable alternative to available copy
9194 number detection tools.")
9195 (license license:gpl2)))
9197 (define-public r-methylkit
9199 (name "r-methylkit")
9203 (uri (bioconductor-uri "methylKit" version))
9206 "0klwc0sbmrxj1lxbz16pl39rxjm0pi57gjw547hlgnac1p9fspzy"))))
9207 (properties `((upstream-name . "methylKit")))
9208 (build-system r-build-system)
9210 `(("r-data-table" ,r-data-table)
9211 ("r-emdbook" ,r-emdbook)
9212 ("r-fastseg" ,r-fastseg)
9213 ("r-genomeinfodb" ,r-genomeinfodb)
9214 ("r-genomicranges" ,r-genomicranges)
9215 ("r-gtools" ,r-gtools)
9216 ("r-iranges" ,r-iranges)
9217 ("r-kernsmooth" ,r-kernsmooth)
9218 ("r-limma" ,r-limma)
9219 ("r-mclust" ,r-mclust)
9221 ("r-qvalue" ,r-qvalue)
9222 ("r-r-utils" ,r-r-utils)
9224 ("r-rhtslib" ,r-rhtslib)
9225 ("r-rsamtools" ,r-rsamtools)
9226 ("r-rtracklayer" ,r-rtracklayer)
9227 ("r-s4vectors" ,r-s4vectors)
9228 ("r-zlibbioc" ,r-zlibbioc)))
9230 `(("r-knitr" ,r-knitr))) ; for vignettes
9233 (home-page "https://github.com/al2na/methylKit")
9235 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9237 "MethylKit is an R package for DNA methylation analysis and annotation
9238 from high-throughput bisulfite sequencing. The package is designed to deal
9239 with sequencing data from @dfn{Reduced representation bisulfite
9240 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9241 genome bisulfite sequencing. It also has functions to analyze base-pair
9242 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9244 (license license:artistic2.0)))
9246 (define-public r-sva
9253 (uri (bioconductor-uri "sva" version))
9256 "1bzms6idx30s4nxl610zwa8rjxsyxb5pf3vxsdfmxg8j4pab9gh1"))))
9257 (build-system r-build-system)
9259 `(("r-genefilter" ,r-genefilter)
9261 ("r-biocparallel" ,r-biocparallel)
9262 ("r-matrixstats" ,r-matrixstats)
9263 ("r-limma" ,r-limma)))
9264 (home-page "https://bioconductor.org/packages/sva")
9265 (synopsis "Surrogate variable analysis")
9267 "This package contains functions for removing batch effects and other
9268 unwanted variation in high-throughput experiment. It also contains functions
9269 for identifying and building surrogate variables for high-dimensional data
9270 sets. Surrogate variables are covariates constructed directly from
9271 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9272 imaging data that can be used in subsequent analyses to adjust for unknown,
9273 unmodeled, or latent sources of noise.")
9274 (license license:artistic2.0)))
9276 (define-public r-seqminer
9283 (uri (cran-uri "seqminer" version))
9286 "00jzj8mwb0zaiwlifd41b26mrq9mzigj18nc29dydi0r42hxg16i"))))
9287 (build-system r-build-system)
9290 (home-page "http://seqminer.genomic.codes")
9291 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9293 "This package provides tools to integrate nucleotide sequencing
9294 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9295 ;; Any version of the GPL is acceptable
9296 (license (list license:gpl2+ license:gpl3+))))
9298 (define-public r-raremetals2
9300 (name "r-raremetals2")
9305 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9306 "b/b7/RareMETALS2_" version ".tar.gz"))
9309 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9310 (properties `((upstream-name . "RareMETALS2")))
9311 (build-system r-build-system)
9313 `(("r-seqminer" ,r-seqminer)
9314 ("r-mvtnorm" ,r-mvtnorm)
9316 ("r-compquadform" ,r-compquadform)
9317 ("r-getopt" ,r-getopt)))
9318 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9319 (synopsis "Analyze gene-level association tests for binary trait")
9321 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9322 It was designed to meta-analyze gene-level association tests for binary trait.
9323 While rareMETALS offers a near-complete solution for meta-analysis of
9324 gene-level tests for quantitative trait, it does not offer the optimal
9325 solution for binary trait. The package rareMETALS2 offers improved features
9326 for analyzing gene-level association tests in meta-analyses for binary
9328 (license license:gpl3)))
9330 (define-public r-maldiquant
9332 (name "r-maldiquant")
9337 (uri (cran-uri "MALDIquant" version))
9340 "0b7kdz3x4sdq413h1q09l1qhcvdnnwv6fqsqwllks1cd3xy34c57"))))
9341 (properties `((upstream-name . "MALDIquant")))
9342 (build-system r-build-system)
9343 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9344 (synopsis "Quantitative analysis of mass spectrometry data")
9346 "This package provides a complete analysis pipeline for matrix-assisted
9347 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9348 two-dimensional mass spectrometry data. In addition to commonly used plotting
9349 and processing methods it includes distinctive features, namely baseline
9350 subtraction methods such as morphological filters (TopHat) or the
9351 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9352 alignment using warping functions, handling of replicated measurements as well
9353 as allowing spectra with different resolutions.")
9354 (license license:gpl3+)))
9356 (define-public r-protgenerics
9358 (name "r-protgenerics")
9363 (uri (bioconductor-uri "ProtGenerics" version))
9366 "1k1ggjgx2la8b21841a4ngkp6xfxwz0czv7x960r7i1jqif8y48z"))))
9367 (properties `((upstream-name . "ProtGenerics")))
9368 (build-system r-build-system)
9369 (home-page "https://github.com/lgatto/ProtGenerics")
9370 (synopsis "S4 generic functions for proteomics infrastructure")
9372 "This package provides S4 generic functions needed by Bioconductor
9373 proteomics packages.")
9374 (license license:artistic2.0)))
9376 (define-public r-mzr
9383 (uri (bioconductor-uri "mzR" version))
9386 "1cwd7phlc5jbx6r6cznyfbdpvcin5fvsaasbbi65zn0s92a80r13"))
9387 (modules '((guix build utils)))
9390 (delete-file-recursively "src/boost")
9392 (properties `((upstream-name . "mzR")))
9393 (build-system r-build-system)
9396 (modify-phases %standard-phases
9397 (add-after 'unpack 'use-system-boost
9399 (substitute* "src/Makevars"
9400 (("\\./boost/libs.*") "")
9401 (("ARCH_OBJS=" line)
9403 "\nARCH_LIBS=-lboost_system -lboost_regex \
9404 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9407 `(;; Our default boost package won't work here, unfortunately, even with
9408 ;; mzR version 2.20.0.
9409 ("boost" ,boost-for-mysql) ; use this instead of the bundled boost sources
9412 `(("r-biobase" ,r-biobase)
9413 ("r-biocgenerics" ,r-biocgenerics)
9414 ("r-ncdf4" ,r-ncdf4)
9415 ("r-protgenerics" ,r-protgenerics)
9417 ("r-rhdf5lib" ,r-rhdf5lib)
9418 ("r-zlibbioc" ,r-zlibbioc)))
9419 (home-page "https://github.com/sneumann/mzR/")
9420 (synopsis "Parser for mass spectrometry data files")
9422 "The mzR package provides a unified API to the common file formats and
9423 parsers available for mass spectrometry data. It comes with a wrapper for the
9424 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9425 The package contains the original code written by the ISB, and a subset of the
9426 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9427 previously been used in XCMS.")
9428 (license license:artistic2.0)))
9430 (define-public r-affyio
9437 (uri (bioconductor-uri "affyio" version))
9440 "0sbkadxdlx7qzxc8z8iv90y6j9b2f62mk3i54dijjh56x3hjy3hb"))))
9441 (build-system r-build-system)
9443 `(("r-zlibbioc" ,r-zlibbioc)))
9446 (home-page "https://github.com/bmbolstad/affyio")
9447 (synopsis "Tools for parsing Affymetrix data files")
9449 "This package provides routines for parsing Affymetrix data files based
9450 upon file format information. The primary focus is on accessing the CEL and
9452 (license license:lgpl2.0+)))
9454 (define-public r-affy
9461 (uri (bioconductor-uri "affy" version))
9464 "131za66wbaz9y86gvjqcc2yd1f2ngl2b796xw726g75djhdgxgap"))))
9465 (build-system r-build-system)
9467 `(("r-affyio" ,r-affyio)
9468 ("r-biobase" ,r-biobase)
9469 ("r-biocgenerics" ,r-biocgenerics)
9470 ("r-biocmanager" ,r-biocmanager)
9471 ("r-preprocesscore" ,r-preprocesscore)
9472 ("r-zlibbioc" ,r-zlibbioc)))
9475 (home-page "https://bioconductor.org/packages/affy")
9476 (synopsis "Methods for affymetrix oligonucleotide arrays")
9478 "This package contains functions for exploratory oligonucleotide array
9480 (license license:lgpl2.0+)))
9482 (define-public r-vsn
9489 (uri (bioconductor-uri "vsn" version))
9492 "1naqzb2m0km8fzr6chf9z71sisrwviy1fdi9b3hn4i8p18b4kqzh"))))
9493 (build-system r-build-system)
9495 `(("r-affy" ,r-affy)
9496 ("r-biobase" ,r-biobase)
9497 ("r-ggplot2" ,r-ggplot2)
9498 ("r-lattice" ,r-lattice)
9499 ("r-limma" ,r-limma)))
9501 `(("r-knitr" ,r-knitr))) ; for vignettes
9502 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9503 (synopsis "Variance stabilization and calibration for microarray data")
9505 "The package implements a method for normalising microarray intensities,
9506 and works for single- and multiple-color arrays. It can also be used for data
9507 from other technologies, as long as they have similar format. The method uses
9508 a robust variant of the maximum-likelihood estimator for an
9509 additive-multiplicative error model and affine calibration. The model
9510 incorporates data calibration step (a.k.a. normalization), a model for the
9511 dependence of the variance on the mean intensity and a variance stabilizing
9512 data transformation. Differences between transformed intensities are
9513 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9514 their variance is independent of the mean, and they are usually more sensitive
9515 and specific in detecting differential transcription.")
9516 (license license:artistic2.0)))
9518 (define-public r-mzid
9525 (uri (bioconductor-uri "mzID" version))
9528 "1glcv096bn6pxlw89dlij1nzpwnjvrbxysvw2gm6qgm7rhxlaxrw"))))
9529 (properties `((upstream-name . "mzID")))
9530 (build-system r-build-system)
9532 `(("r-doparallel" ,r-doparallel)
9533 ("r-foreach" ,r-foreach)
9534 ("r-iterators" ,r-iterators)
9536 ("r-protgenerics" ,r-protgenerics)
9539 (home-page "https://bioconductor.org/packages/mzID")
9540 (synopsis "Parser for mzIdentML files")
9542 "This package provides a parser for mzIdentML files implemented using the
9543 XML package. The parser tries to be general and able to handle all types of
9544 mzIdentML files with the drawback of having less pretty output than a vendor
9546 (license license:gpl2+)))
9548 (define-public r-pcamethods
9550 (name "r-pcamethods")
9555 (uri (bioconductor-uri "pcaMethods" version))
9558 "1wir67kfjm0m9gf0ki8qmvh45n4gx2k0wfl9pd1hp4g62fbrj1pj"))))
9559 (properties `((upstream-name . "pcaMethods")))
9560 (build-system r-build-system)
9562 `(("r-biobase" ,r-biobase)
9563 ("r-biocgenerics" ,r-biocgenerics)
9565 ("r-rcpp" ,r-rcpp)))
9566 (home-page "https://github.com/hredestig/pcamethods")
9567 (synopsis "Collection of PCA methods")
9569 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9570 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9571 for missing value estimation is included for comparison. BPCA, PPCA and
9572 NipalsPCA may be used to perform PCA on incomplete data as well as for
9573 accurate missing value estimation. A set of methods for printing and plotting
9574 the results is also provided. All PCA methods make use of the same data
9575 structure (pcaRes) to provide a common interface to the PCA results.")
9576 (license license:gpl3+)))
9578 (define-public r-msnbase
9585 (uri (bioconductor-uri "MSnbase" version))
9588 "1z889xkfphqqmv31i8hh5xqyclv660ic26rfck5bjpgk3s2zzwi6"))))
9589 (properties `((upstream-name . "MSnbase")))
9590 (build-system r-build-system)
9592 `(("r-affy" ,r-affy)
9593 ("r-biobase" ,r-biobase)
9594 ("r-biocgenerics" ,r-biocgenerics)
9595 ("r-biocparallel" ,r-biocparallel)
9596 ("r-digest" ,r-digest)
9597 ("r-ggplot2" ,r-ggplot2)
9598 ("r-impute" ,r-impute)
9599 ("r-iranges" ,r-iranges)
9600 ("r-lattice" ,r-lattice)
9601 ("r-maldiquant" ,r-maldiquant)
9605 ("r-pcamethods" ,r-pcamethods)
9607 ("r-preprocesscore" ,r-preprocesscore)
9608 ("r-protgenerics" ,r-protgenerics)
9610 ("r-s4vectors" ,r-s4vectors)
9611 ("r-scales" ,r-scales)
9614 (home-page "https://github.com/lgatto/MSnbase")
9615 (synopsis "Base functions and classes for MS-based proteomics")
9617 "This package provides basic plotting, data manipulation and processing
9618 of mass spectrometry based proteomics data.")
9619 (license license:artistic2.0)))
9621 (define-public r-msnid
9628 (uri (bioconductor-uri "MSnID" version))
9631 "0m71f2y12hmwvng45kzz4r4qrgc2jbd7j9gprmw8y5laawpdaifg"))))
9632 (properties `((upstream-name . "MSnID")))
9633 (build-system r-build-system)
9635 `(("r-biobase" ,r-biobase)
9636 ("r-data-table" ,r-data-table)
9637 ("r-doparallel" ,r-doparallel)
9638 ("r-dplyr" ,r-dplyr)
9639 ("r-foreach" ,r-foreach)
9640 ("r-iterators" ,r-iterators)
9641 ("r-msnbase" ,r-msnbase)
9644 ("r-protgenerics" ,r-protgenerics)
9645 ("r-r-cache" ,r-r-cache)
9647 ("r-reshape2" ,r-reshape2)))
9648 (home-page "https://bioconductor.org/packages/MSnID")
9649 (synopsis "Utilities for LC-MSn proteomics identifications")
9651 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9652 from mzIdentML (leveraging the mzID package) or text files. After collating
9653 the search results from multiple datasets it assesses their identification
9654 quality and optimize filtering criteria to achieve the maximum number of
9655 identifications while not exceeding a specified false discovery rate. It also
9656 contains a number of utilities to explore the MS/MS results and assess missed
9657 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9658 (license license:artistic2.0)))
9660 (define-public r-seurat
9666 (uri (cran-uri "Seurat" version))
9669 "0lhjbjhv1hnx5i3gkx41k68i8ykay3f24708h30wx9xywww9lsvi"))))
9670 (properties `((upstream-name . "Seurat")))
9671 (build-system r-build-system)
9674 ("r-cluster" ,r-cluster)
9675 ("r-cowplot" ,r-cowplot)
9676 ("r-fitdistrplus" ,r-fitdistrplus)
9677 ("r-future" ,r-future)
9678 ("r-future-apply" ,r-future-apply)
9679 ("r-ggplot2" ,r-ggplot2)
9680 ("r-ggrepel" ,r-ggrepel)
9681 ("r-ggridges" ,r-ggridges)
9684 ("r-igraph" ,r-igraph)
9685 ("r-irlba" ,r-irlba)
9686 ("r-kernsmooth" ,r-kernsmooth)
9687 ("r-leiden" ,r-leiden)
9688 ("r-lmtest" ,r-lmtest)
9690 ("r-matrix" ,r-matrix)
9691 ("r-metap" ,r-metap)
9692 ("r-patchwork" ,r-patchwork)
9693 ("r-pbapply" ,r-pbapply)
9694 ("r-plotly" ,r-plotly)
9697 ("r-rcolorbrewer" ,r-rcolorbrewer)
9699 ("r-rcppannoy" ,r-rcppannoy)
9700 ("r-rcppeigen" ,r-rcppeigen)
9701 ("r-rcppprogress" ,r-rcppprogress)
9702 ("r-reticulate" ,r-reticulate)
9703 ("r-rlang" ,r-rlang)
9706 ("r-rtsne" ,r-rtsne)
9707 ("r-scales" ,r-scales)
9708 ("r-sctransform" ,r-sctransform)
9710 ("r-uwot" ,r-uwot)))
9711 (home-page "http://www.satijalab.org/seurat")
9712 (synopsis "Seurat is an R toolkit for single cell genomics")
9714 "This package is an R package designed for QC, analysis, and
9715 exploration of single cell RNA-seq data. It easily enables widely-used
9716 analytical techniques, including the identification of highly variable genes,
9717 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9718 algorithms; density clustering, hierarchical clustering, k-means, and the
9719 discovery of differentially expressed genes and markers.")
9720 (license license:gpl3)))
9722 (define-public r-aroma-light
9724 (name "r-aroma-light")
9729 (uri (bioconductor-uri "aroma.light" version))
9732 "0cgdg650j4dl0b45pwaw49ib97dwjazrv9sqzkygrjmcnnfxry8x"))))
9733 (properties `((upstream-name . "aroma.light")))
9734 (build-system r-build-system)
9736 `(("r-matrixstats" ,r-matrixstats)
9737 ("r-r-methodss3" ,r-r-methodss3)
9739 ("r-r-utils" ,r-r-utils)))
9740 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9741 (synopsis "Methods for normalization and visualization of microarray data")
9743 "This package provides methods for microarray analysis that take basic
9744 data types such as matrices and lists of vectors. These methods can be used
9745 standalone, be utilized in other packages, or be wrapped up in higher-level
9747 (license license:gpl2+)))
9749 (define-public r-deseq
9756 (uri (bioconductor-uri "DESeq" version))
9759 "14pys93gsl50xmq5pc7pp1g20v3ywlg0yzkkhwb3kiy8573xn9nc"))))
9760 (properties `((upstream-name . "DESeq")))
9761 (build-system r-build-system)
9763 `(("r-biobase" ,r-biobase)
9764 ("r-biocgenerics" ,r-biocgenerics)
9765 ("r-genefilter" ,r-genefilter)
9766 ("r-geneplotter" ,r-geneplotter)
9767 ("r-lattice" ,r-lattice)
9768 ("r-locfit" ,r-locfit)
9770 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9771 (home-page "https://www-huber.embl.de/users/anders/DESeq/")
9772 (synopsis "Differential gene expression analysis")
9774 "This package provides tools for estimating variance-mean dependence in
9775 count data from high-throughput genetic sequencing assays and for testing for
9776 differential expression based on a model using the negative binomial
9778 (license license:gpl3+)))
9780 (define-public r-edaseq
9787 (uri (bioconductor-uri "EDASeq" version))
9790 "19mgzbv8yxgvw86wpq401l27q55ygawlngl775yavwccz1zbhjnj"))))
9791 (properties `((upstream-name . "EDASeq")))
9792 (build-system r-build-system)
9794 `(("r-annotationdbi" ,r-annotationdbi)
9795 ("r-aroma-light" ,r-aroma-light)
9796 ("r-biobase" ,r-biobase)
9797 ("r-biocgenerics" ,r-biocgenerics)
9798 ("r-biocmanager" ,r-biocmanager)
9799 ("r-biomart" ,r-biomart)
9800 ("r-biostrings" ,r-biostrings)
9801 ("r-deseq" ,r-deseq)
9802 ("r-genomicfeatures" ,r-genomicfeatures)
9803 ("r-genomicranges" ,r-genomicranges)
9804 ("r-iranges" ,r-iranges)
9805 ("r-rsamtools" ,r-rsamtools)
9806 ("r-shortread" ,r-shortread)))
9807 (home-page "https://github.com/drisso/EDASeq")
9808 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9810 "This package provides support for numerical and graphical summaries of
9811 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9812 adjust for GC-content effect (or other gene-level effects) on read counts:
9813 loess robust local regression, global-scaling, and full-quantile
9814 normalization. Between-lane normalization procedures to adjust for
9815 distributional differences between lanes (e.g., sequencing depth):
9816 global-scaling and full-quantile normalization.")
9817 (license license:artistic2.0)))
9819 (define-public r-interactivedisplaybase
9821 (name "r-interactivedisplaybase")
9826 (uri (bioconductor-uri "interactiveDisplayBase" version))
9829 "0zwf3ma6wf4zypl6bgjp0n72k2hmp0g16gzl4v3y4157rxcbpl0n"))))
9831 `((upstream-name . "interactiveDisplayBase")))
9832 (build-system r-build-system)
9834 `(("r-biocgenerics" ,r-biocgenerics)
9835 ("r-shiny" ,r-shiny)))
9836 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9837 (synopsis "Base package for web displays of Bioconductor objects")
9839 "This package contains the basic methods needed to generate interactive
9840 Shiny-based display methods for Bioconductor objects.")
9841 (license license:artistic2.0)))
9843 (define-public r-annotationhub
9845 (name "r-annotationhub")
9850 (uri (bioconductor-uri "AnnotationHub" version))
9853 "19vj3bk8jz68q84g3j8xs1s9bqz90lbwbciig1h45zvn2zc6087m"))))
9854 (properties `((upstream-name . "AnnotationHub")))
9855 (build-system r-build-system)
9857 `(("r-annotationdbi" ,r-annotationdbi)
9858 ("r-biocfilecache" ,r-biocfilecache)
9859 ("r-biocgenerics" ,r-biocgenerics)
9860 ("r-biocmanager" ,r-biocmanager)
9861 ("r-biocversion" ,r-biocversion)
9863 ("r-dplyr" ,r-dplyr)
9865 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9866 ("r-rappdirs" ,r-rappdirs)
9867 ("r-rsqlite" ,r-rsqlite)
9868 ("r-s4vectors" ,r-s4vectors)
9869 ("r-yaml" ,r-yaml)))
9870 (home-page "https://bioconductor.org/packages/AnnotationHub")
9871 (synopsis "Client to access AnnotationHub resources")
9873 "This package provides a client for the Bioconductor AnnotationHub web
9874 resource. The AnnotationHub web resource provides a central location where
9875 genomic files (e.g. VCF, bed, wig) and other resources from standard
9876 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9877 metadata about each resource, e.g., a textual description, tags, and date of
9878 modification. The client creates and manages a local cache of files retrieved
9879 by the user, helping with quick and reproducible access.")
9880 (license license:artistic2.0)))
9882 (define-public r-fastseg
9889 (uri (bioconductor-uri "fastseg" version))
9892 "1cys6frmbizc8bf933mwvvnr31sfya9ahcc0wm66pbd1x3mygkmk"))))
9893 (build-system r-build-system)
9895 `(("r-biobase" ,r-biobase)
9896 ("r-biocgenerics" ,r-biocgenerics)
9897 ("r-genomicranges" ,r-genomicranges)
9898 ("r-iranges" ,r-iranges)
9899 ("r-s4vectors" ,r-s4vectors)))
9900 (home-page "https://www.bioinf.jku.at/software/fastseg/index.html")
9901 (synopsis "Fast segmentation algorithm for genetic sequencing data")
9903 "Fastseg implements a very fast and efficient segmentation algorithm.
9904 It can segment data from DNA microarrays and data from next generation
9905 sequencing for example to detect copy number segments. Further it can segment
9906 data from RNA microarrays like tiling arrays to identify transcripts. Most
9907 generally, it can segment data given as a matrix or as a vector. Various data
9908 formats can be used as input to fastseg like expression set objects for
9909 microarrays or GRanges for sequencing data.")
9910 (license license:lgpl2.0+)))
9912 (define-public r-keggrest
9919 (uri (bioconductor-uri "KEGGREST" version))
9922 "1cgjvv9n88y3ah21356mh8z2l08vjn42hjy8hcljsibknzc4v247"))))
9923 (properties `((upstream-name . "KEGGREST")))
9924 (build-system r-build-system)
9926 `(("r-biostrings" ,r-biostrings)
9929 (home-page "https://bioconductor.org/packages/KEGGREST")
9930 (synopsis "Client-side REST access to KEGG")
9932 "This package provides a package that provides a client interface to the
9933 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
9934 (license license:artistic2.0)))
9936 (define-public r-gage
9943 (uri (bioconductor-uri "gage" version))
9946 "1qxfmg0id19iy3ia8h5nrvk3d1azqb28kl7m08i23654wb6b45c6"))))
9947 (build-system r-build-system)
9949 `(("r-annotationdbi" ,r-annotationdbi)
9950 ("r-graph" ,r-graph)
9951 ("r-keggrest" ,r-keggrest)))
9952 (home-page (string-append "https://bmcbioinformatics.biomedcentral.com/"
9953 "articles/10.1186/1471-2105-10-161"))
9954 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
9956 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
9957 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
9958 data attributes including sample sizes, experimental designs, assay platforms,
9959 and other types of heterogeneity. The gage package provides functions for
9960 basic GAGE analysis, result processing and presentation. In addition, it
9961 provides demo microarray data and commonly used gene set data based on KEGG
9962 pathways and GO terms. These functions and data are also useful for gene set
9963 analysis using other methods.")
9964 (license license:gpl2+)))
9966 (define-public r-genomicfiles
9968 (name "r-genomicfiles")
9973 (uri (bioconductor-uri "GenomicFiles" version))
9976 "1x6q827ms2l5lwzha1vsgfrshh35n9f19jq57xagrqlafxgpz86s"))))
9977 (properties `((upstream-name . "GenomicFiles")))
9978 (build-system r-build-system)
9980 `(("r-biocgenerics" ,r-biocgenerics)
9981 ("r-biocparallel" ,r-biocparallel)
9982 ("r-genomeinfodb" ,r-genomeinfodb)
9983 ("r-genomicalignments" ,r-genomicalignments)
9984 ("r-genomicranges" ,r-genomicranges)
9985 ("r-iranges" ,r-iranges)
9986 ("r-rsamtools" ,r-rsamtools)
9987 ("r-rtracklayer" ,r-rtracklayer)
9988 ("r-s4vectors" ,r-s4vectors)
9989 ("r-summarizedexperiment" ,r-summarizedexperiment)
9990 ("r-variantannotation" ,r-variantannotation)))
9991 (home-page "https://bioconductor.org/packages/GenomicFiles")
9992 (synopsis "Distributed computing by file or by range")
9994 "This package provides infrastructure for parallel computations
9995 distributed by file or by range. User defined mapper and reducer functions
9996 provide added flexibility for data combination and manipulation.")
9997 (license license:artistic2.0)))
9999 (define-public r-complexheatmap
10001 (name "r-complexheatmap")
10006 (uri (bioconductor-uri "ComplexHeatmap" version))
10009 "1pj6a6rmqckk033pkklk6hr4066rzavamy6w194rfdhind90rk0p"))))
10011 `((upstream-name . "ComplexHeatmap")))
10012 (build-system r-build-system)
10014 `(("r-circlize" ,r-circlize)
10016 ("r-colorspace" ,r-colorspace)
10017 ("r-getoptlong" ,r-getoptlong)
10018 ("r-globaloptions" ,r-globaloptions)
10020 ("r-rcolorbrewer" ,r-rcolorbrewer)))
10022 "https://github.com/jokergoo/ComplexHeatmap")
10023 (synopsis "Making Complex Heatmaps")
10025 "Complex heatmaps are efficient to visualize associations between
10026 different sources of data sets and reveal potential structures. This package
10027 provides a highly flexible way to arrange multiple heatmaps and supports
10028 self-defined annotation graphics.")
10029 (license license:gpl2+)))
10031 (define-public r-dirichletmultinomial
10033 (name "r-dirichletmultinomial")
10038 (uri (bioconductor-uri "DirichletMultinomial" version))
10041 "0knmncmkkf2ypyqfcl5s8nmyyf9nrzkqprzn9w3w8182c0v49r0s"))))
10043 `((upstream-name . "DirichletMultinomial")))
10044 (build-system r-build-system)
10048 `(("r-biocgenerics" ,r-biocgenerics)
10049 ("r-iranges" ,r-iranges)
10050 ("r-s4vectors" ,r-s4vectors)))
10051 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
10052 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
10054 "Dirichlet-multinomial mixture models can be used to describe variability
10055 in microbial metagenomic data. This package is an interface to code
10056 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
10058 (license license:lgpl3)))
10060 (define-public r-ensembldb
10062 (name "r-ensembldb")
10067 (uri (bioconductor-uri "ensembldb" version))
10070 "02lnpyp85zchmz404hr5381zmihvq4x9zgxdrbn2afi352vg0vab"))))
10071 (build-system r-build-system)
10073 `(("r-annotationdbi" ,r-annotationdbi)
10074 ("r-annotationfilter" ,r-annotationfilter)
10075 ("r-biobase" ,r-biobase)
10076 ("r-biocgenerics" ,r-biocgenerics)
10077 ("r-biostrings" ,r-biostrings)
10080 ("r-genomeinfodb" ,r-genomeinfodb)
10081 ("r-genomicfeatures" ,r-genomicfeatures)
10082 ("r-genomicranges" ,r-genomicranges)
10083 ("r-iranges" ,r-iranges)
10084 ("r-protgenerics" ,r-protgenerics)
10085 ("r-rsamtools" ,r-rsamtools)
10086 ("r-rsqlite" ,r-rsqlite)
10087 ("r-rtracklayer" ,r-rtracklayer)
10088 ("r-s4vectors" ,r-s4vectors)))
10089 (home-page "https://github.com/jotsetung/ensembldb")
10090 (synopsis "Utilities to create and use Ensembl-based annotation databases")
10092 "The package provides functions to create and use transcript-centric
10093 annotation databases/packages. The annotation for the databases are directly
10094 fetched from Ensembl using their Perl API. The functionality and data is
10095 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
10096 but, in addition to retrieve all gene/transcript models and annotations from
10097 the database, the @code{ensembldb} package also provides a filter framework
10098 allowing to retrieve annotations for specific entries like genes encoded on a
10099 chromosome region or transcript models of lincRNA genes.")
10100 ;; No version specified
10101 (license license:lgpl3+)))
10103 (define-public r-organismdbi
10105 (name "r-organismdbi")
10110 (uri (bioconductor-uri "OrganismDbi" version))
10113 "1bvfyh733mhka9zd00hrzpalgjs255c2blnxyf60ipzk5jg7yllb"))))
10114 (properties `((upstream-name . "OrganismDbi")))
10115 (build-system r-build-system)
10117 `(("r-annotationdbi" ,r-annotationdbi)
10118 ("r-biobase" ,r-biobase)
10119 ("r-biocgenerics" ,r-biocgenerics)
10120 ("r-biocmanager" ,r-biocmanager)
10122 ("r-genomicfeatures" ,r-genomicfeatures)
10123 ("r-genomicranges" ,r-genomicranges)
10124 ("r-graph" ,r-graph)
10125 ("r-iranges" ,r-iranges)
10127 ("r-s4vectors" ,r-s4vectors)))
10128 (home-page "https://bioconductor.org/packages/OrganismDbi")
10129 (synopsis "Software to enable the smooth interfacing of database packages")
10130 (description "The package enables a simple unified interface to several
10131 annotation packages each of which has its own schema by taking advantage of
10132 the fact that each of these packages implements a select methods.")
10133 (license license:artistic2.0)))
10135 (define-public r-biovizbase
10137 (name "r-biovizbase")
10142 (uri (bioconductor-uri "biovizBase" version))
10145 "04vvj907bgs67w8rb7n1haf80p6cd0qj5fdxw0dwryb455y35vir"))))
10146 (properties `((upstream-name . "biovizBase")))
10147 (build-system r-build-system)
10149 `(("r-annotationdbi" ,r-annotationdbi)
10150 ("r-annotationfilter" ,r-annotationfilter)
10151 ("r-biocgenerics" ,r-biocgenerics)
10152 ("r-biostrings" ,r-biostrings)
10153 ("r-dichromat" ,r-dichromat)
10154 ("r-ensembldb" ,r-ensembldb)
10155 ("r-genomeinfodb" ,r-genomeinfodb)
10156 ("r-genomicalignments" ,r-genomicalignments)
10157 ("r-genomicfeatures" ,r-genomicfeatures)
10158 ("r-genomicranges" ,r-genomicranges)
10159 ("r-hmisc" ,r-hmisc)
10160 ("r-iranges" ,r-iranges)
10161 ("r-rcolorbrewer" ,r-rcolorbrewer)
10162 ("r-rlang" ,r-rlang)
10163 ("r-rsamtools" ,r-rsamtools)
10164 ("r-s4vectors" ,r-s4vectors)
10165 ("r-scales" ,r-scales)
10166 ("r-summarizedexperiment" ,r-summarizedexperiment)
10167 ("r-variantannotation" ,r-variantannotation)))
10168 (home-page "https://bioconductor.org/packages/biovizBase")
10169 (synopsis "Basic graphic utilities for visualization of genomic data")
10171 "The biovizBase package is designed to provide a set of utilities, color
10172 schemes and conventions for genomic data. It serves as the base for various
10173 high-level packages for biological data visualization. This saves development
10174 effort and encourages consistency.")
10175 (license license:artistic2.0)))
10177 (define-public r-ggbio
10184 (uri (bioconductor-uri "ggbio" version))
10187 "13wzwh40anh8l53yp19bg4w5cpxykcaf228dc8cxvjndyib711qb"))))
10188 (build-system r-build-system)
10191 (modify-phases %standard-phases
10192 ;; See https://github.com/tengfei/ggbio/issues/117
10193 ;; This fix will be included in the next release.
10194 (add-after 'unpack 'fix-typo
10196 (substitute* "R/GGbio-class.R"
10197 (("fechable") "fetchable"))
10200 `(("r-annotationdbi" ,r-annotationdbi)
10201 ("r-annotationfilter" ,r-annotationfilter)
10202 ("r-biobase" ,r-biobase)
10203 ("r-biocgenerics" ,r-biocgenerics)
10204 ("r-biostrings" ,r-biostrings)
10205 ("r-biovizbase" ,r-biovizbase)
10206 ("r-bsgenome" ,r-bsgenome)
10207 ("r-ensembldb" ,r-ensembldb)
10208 ("r-genomeinfodb" ,r-genomeinfodb)
10209 ("r-genomicalignments" ,r-genomicalignments)
10210 ("r-genomicfeatures" ,r-genomicfeatures)
10211 ("r-genomicranges" ,r-genomicranges)
10212 ("r-ggally" ,r-ggally)
10213 ("r-ggplot2" ,r-ggplot2)
10214 ("r-gridextra" ,r-gridextra)
10215 ("r-gtable" ,r-gtable)
10216 ("r-hmisc" ,r-hmisc)
10217 ("r-iranges" ,r-iranges)
10218 ("r-organismdbi" ,r-organismdbi)
10219 ("r-reshape2" ,r-reshape2)
10220 ("r-rlang" ,r-rlang)
10221 ("r-rsamtools" ,r-rsamtools)
10222 ("r-rtracklayer" ,r-rtracklayer)
10223 ("r-s4vectors" ,r-s4vectors)
10224 ("r-scales" ,r-scales)
10225 ("r-summarizedexperiment" ,r-summarizedexperiment)
10226 ("r-variantannotation" ,r-variantannotation)))
10227 (home-page "http://www.tengfei.name/ggbio/")
10228 (synopsis "Visualization tools for genomic data")
10230 "The ggbio package extends and specializes the grammar of graphics for
10231 biological data. The graphics are designed to answer common scientific
10232 questions, in particular those often asked of high throughput genomics data.
10233 All core Bioconductor data structures are supported, where appropriate. The
10234 package supports detailed views of particular genomic regions, as well as
10235 genome-wide overviews. Supported overviews include ideograms and grand linear
10236 views. High-level plots include sequence fragment length, edge-linked
10237 interval to data view, mismatch pileup, and several splicing summaries.")
10238 (license license:artistic2.0)))
10240 (define-public r-gprofiler
10242 (name "r-gprofiler")
10247 (uri (cran-uri "gProfileR" version))
10250 "1h1v0kgpsn04ald2izznh7fr2riwisj5hcgz4k7h3qc931rf0r4k"))))
10251 (properties `((upstream-name . "gProfileR")))
10252 (build-system r-build-system)
10254 `(("r-plyr" ,r-plyr)
10255 ("r-rcurl" ,r-rcurl)))
10256 (home-page "https://cran.r-project.org/web/packages/gProfileR/")
10257 (synopsis "Interface to the g:Profiler toolkit")
10259 "This package provides tools for functional enrichment analysis,
10260 gene identifier conversion and mapping homologous genes across related
10261 organisms via the @code{g:Profiler} toolkit.")
10262 (license license:gpl2+)))
10264 (define-public r-gqtlbase
10266 (name "r-gqtlbase")
10271 (uri (bioconductor-uri "gQTLBase" version))
10274 "1qr8dqjbmj1mdjbzbnxwzfrm8f02wqfsgic8ws5kv7pmsby63y4x"))))
10275 (properties `((upstream-name . "gQTLBase")))
10276 (build-system r-build-system)
10278 `(("r-batchjobs" ,r-batchjobs)
10279 ("r-bbmisc" ,r-bbmisc)
10280 ("r-biocgenerics" ,r-biocgenerics)
10282 ("r-doparallel" ,r-doparallel)
10284 ("r-ffbase" ,r-ffbase)
10285 ("r-foreach" ,r-foreach)
10286 ("r-genomicfiles" ,r-genomicfiles)
10287 ("r-genomicranges" ,r-genomicranges)
10288 ("r-rtracklayer" ,r-rtracklayer)
10289 ("r-s4vectors" ,r-s4vectors)
10290 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10291 (home-page "https://bioconductor.org/packages/gQTLBase")
10292 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10294 "The purpose of this package is to simplify the storage and interrogation
10295 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10297 (license license:artistic2.0)))
10299 (define-public r-snpstats
10301 (name "r-snpstats")
10306 (uri (bioconductor-uri "snpStats" version))
10309 "1xq1rjljg70h5mshdza56dis0iv1a20sivs6dav3w5jbdd1l5qkh"))))
10310 (properties `((upstream-name . "snpStats")))
10311 (build-system r-build-system)
10312 (inputs `(("zlib" ,zlib)))
10314 `(("r-biocgenerics" ,r-biocgenerics)
10315 ("r-matrix" ,r-matrix)
10316 ("r-survival" ,r-survival)
10317 ("r-zlibbioc" ,r-zlibbioc)))
10318 (home-page "https://bioconductor.org/packages/snpStats")
10319 (synopsis "Methods for SNP association studies")
10321 "This package provides classes and statistical methods for large
10322 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10323 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10324 (license license:gpl3)))
10326 (define-public r-homo-sapiens
10328 (name "r-homo-sapiens")
10332 ;; We cannot use bioconductor-uri here because this tarball is
10333 ;; located under "data/annotation/" instead of "bioc/".
10334 (uri (string-append "https://www.bioconductor.org/packages/"
10335 "release/data/annotation/src/contrib/"
10337 version ".tar.gz"))
10340 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10342 `((upstream-name . "Homo.sapiens")))
10343 (build-system r-build-system)
10345 `(("r-genomicfeatures" ,r-genomicfeatures)
10346 ("r-go-db" ,r-go-db)
10347 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10348 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10349 ("r-organismdbi" ,r-organismdbi)
10350 ("r-annotationdbi" ,r-annotationdbi)))
10351 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10352 (synopsis "Annotation package for the Homo.sapiens object")
10354 "This package contains the Homo.sapiens object to access data from
10355 several related annotation packages.")
10356 (license license:artistic2.0)))
10358 (define-public r-erma
10365 (uri (bioconductor-uri "erma" version))
10368 "085qsr73p8nyp435f15l4l1jkfd64bfd9gl4z496nfxdnqn95srz"))))
10369 (build-system r-build-system)
10371 `(("r-annotationdbi" ,r-annotationdbi)
10372 ("r-biobase" ,r-biobase)
10373 ("r-biocgenerics" ,r-biocgenerics)
10374 ("r-biocparallel" ,r-biocparallel)
10375 ("r-genomeinfodb" ,r-genomeinfodb)
10376 ("r-genomicfiles" ,r-genomicfiles)
10377 ("r-genomicranges" ,r-genomicranges)
10378 ("r-ggplot2" ,r-ggplot2)
10379 ("r-homo-sapiens" ,r-homo-sapiens)
10380 ("r-iranges" ,r-iranges)
10381 ("r-rtracklayer" ,r-rtracklayer)
10382 ("r-s4vectors" ,r-s4vectors)
10383 ("r-shiny" ,r-shiny)
10384 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10385 (home-page "https://bioconductor.org/packages/erma")
10386 (synopsis "Epigenomic road map adventures")
10388 "The epigenomics road map describes locations of epigenetic marks in DNA
10389 from a variety of cell types. Of interest are locations of histone
10390 modifications, sites of DNA methylation, and regions of accessible chromatin.
10391 This package presents a selection of elements of the road map including
10392 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10393 by Ernst and Kellis.")
10394 (license license:artistic2.0)))
10396 (define-public r-ldblock
10403 (uri (bioconductor-uri "ldblock" version))
10406 "0xpigfidmylfawy6vzshqnsw1lzjs4qms8q7zffij6bkvkv7920x"))))
10407 (build-system r-build-system)
10409 `(("r-biocgenerics" ,r-biocgenerics)
10410 ("r-ensdb-hsapiens-v75" ,r-ensdb-hsapiens-v75)
10411 ("r-ensembldb" ,r-ensembldb)
10412 ("r-genomeinfodb" ,r-genomeinfodb)
10413 ("r-genomicfiles" ,r-genomicfiles)
10415 ("r-matrix" ,r-matrix)
10416 ("r-rsamtools" ,r-rsamtools)
10417 ("r-snpstats" ,r-snpstats)
10418 ("r-variantannotation" ,r-variantannotation)))
10419 (home-page "https://bioconductor.org/packages/ldblock")
10420 (synopsis "Data structures for linkage disequilibrium measures in populations")
10422 "This package defines data structures for @dfn{linkage
10423 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10424 handling of existing population-level data for the purpose of flexibly
10425 defining LD blocks.")
10426 (license license:artistic2.0)))
10428 (define-public r-gqtlstats
10430 (name "r-gqtlstats")
10435 (uri (bioconductor-uri "gQTLstats" version))
10438 "1dly4p9r4231hf31xg1nzqiyvjbcfjljfmhb88ic1jxwnvniyv2f"))))
10439 (properties `((upstream-name . "gQTLstats")))
10440 (build-system r-build-system)
10442 `(("r-annotationdbi" ,r-annotationdbi)
10443 ("r-batchjobs" ,r-batchjobs)
10444 ("r-bbmisc" ,r-bbmisc)
10445 ("r-beeswarm" ,r-beeswarm)
10446 ("r-biobase" ,r-biobase)
10447 ("r-biocgenerics" ,r-biocgenerics)
10448 ("r-doparallel" ,r-doparallel)
10449 ("r-dplyr" ,r-dplyr)
10451 ("r-ffbase" ,r-ffbase)
10452 ("r-foreach" ,r-foreach)
10453 ("r-genomeinfodb" ,r-genomeinfodb)
10454 ("r-genomicfeatures" ,r-genomicfeatures)
10455 ("r-genomicfiles" ,r-genomicfiles)
10456 ("r-genomicranges" ,r-genomicranges)
10457 ("r-ggbeeswarm" ,r-ggbeeswarm)
10458 ("r-ggplot2" ,r-ggplot2)
10459 ("r-gqtlbase" ,r-gqtlbase)
10460 ("r-hardyweinberg" ,r-hardyweinberg)
10461 ("r-homo-sapiens" ,r-homo-sapiens)
10462 ("r-iranges" ,r-iranges)
10463 ("r-limma" ,r-limma)
10465 ("r-plotly" ,r-plotly)
10466 ("r-reshape2" ,r-reshape2)
10467 ("r-s4vectors" ,r-s4vectors)
10468 ("r-shiny" ,r-shiny)
10469 ("r-snpstats" ,r-snpstats)
10470 ("r-summarizedexperiment" ,r-summarizedexperiment)
10471 ("r-variantannotation" ,r-variantannotation)))
10472 (home-page "https://bioconductor.org/packages/gQTLstats")
10473 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10475 "This package provides tools for the computationally efficient analysis
10476 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10477 The software in this package aims to support refinements and functional
10478 interpretation of members of a collection of association statistics on a
10479 family of feature/genome hypotheses.")
10480 (license license:artistic2.0)))
10482 (define-public r-gviz
10489 (uri (bioconductor-uri "Gviz" version))
10492 "0c9i26h5czm60n1bxzmdxxpywcj0sig6wcj913pb41mr83bbgra3"))))
10493 (properties `((upstream-name . "Gviz")))
10494 (build-system r-build-system)
10496 `(("r-annotationdbi" ,r-annotationdbi)
10497 ("r-biobase" ,r-biobase)
10498 ("r-biocgenerics" ,r-biocgenerics)
10499 ("r-biomart" ,r-biomart)
10500 ("r-biostrings" ,r-biostrings)
10501 ("r-biovizbase" ,r-biovizbase)
10502 ("r-bsgenome" ,r-bsgenome)
10503 ("r-digest" ,r-digest)
10504 ("r-genomeinfodb" ,r-genomeinfodb)
10505 ("r-genomicalignments" ,r-genomicalignments)
10506 ("r-genomicfeatures" ,r-genomicfeatures)
10507 ("r-genomicranges" ,r-genomicranges)
10508 ("r-iranges" ,r-iranges)
10509 ("r-lattice" ,r-lattice)
10510 ("r-latticeextra" ,r-latticeextra)
10511 ("r-matrixstats" ,r-matrixstats)
10512 ("r-rcolorbrewer" ,r-rcolorbrewer)
10513 ("r-rsamtools" ,r-rsamtools)
10514 ("r-rtracklayer" ,r-rtracklayer)
10515 ("r-s4vectors" ,r-s4vectors)
10516 ("r-xvector" ,r-xvector)))
10517 (home-page "https://bioconductor.org/packages/Gviz")
10518 (synopsis "Plotting data and annotation information along genomic coordinates")
10520 "Genomic data analyses requires integrated visualization of known genomic
10521 information and new experimental data. Gviz uses the biomaRt and the
10522 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10523 and translates this to e.g. gene/transcript structures in viewports of the
10524 grid graphics package. This results in genomic information plotted together
10526 (license license:artistic2.0)))
10528 (define-public r-gwascat
10535 (uri (bioconductor-uri "gwascat" version))
10538 "038vhfsk2vs7inn5di093cmjbb81k7j0af385sg7l01jj70bdqq1"))))
10539 (build-system r-build-system)
10541 `(("r-annotationdbi" ,r-annotationdbi)
10542 ("r-biocgenerics" ,r-biocgenerics)
10543 ("r-biostrings" ,r-biostrings)
10544 ("r-genomeinfodb" ,r-genomeinfodb)
10545 ("r-genomicfeatures" ,r-genomicfeatures)
10546 ("r-genomicranges" ,r-genomicranges)
10547 ("r-homo-sapiens" ,r-homo-sapiens)
10548 ("r-iranges" ,r-iranges)
10549 ("r-rsamtools" ,r-rsamtools)
10550 ("r-rtracklayer" ,r-rtracklayer)
10551 ("r-s4vectors" ,r-s4vectors)))
10552 (home-page "https://bioconductor.org/packages/gwascat")
10553 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10555 "This package provides tools for representing and modeling data in the
10556 EMBL-EBI GWAS catalog.")
10557 (license license:artistic2.0)))
10559 (define-public r-sushi
10565 (uri (bioconductor-uri "Sushi" version))
10568 "15xng21hd09fb234ravrry3b872zg82w8x9lijxab9n96xihcpz5"))))
10569 (properties `((upstream-name . "Sushi")))
10570 (build-system r-build-system)
10572 `(("r-biomart" ,r-biomart)
10574 (home-page "https://bioconductor.org/packages/Sushi")
10575 (synopsis "Tools for visualizing genomics data")
10577 "This package provides flexible, quantitative, and integrative genomic
10578 visualizations for publication-quality multi-panel figures.")
10579 (license license:gpl2+)))
10581 (define-public r-fithic
10587 (uri (bioconductor-uri "FitHiC" version))
10590 "1irwkwi4afdj395134k31mvx7c2vpdd0rv8zrblnldascdsb04kc"))))
10591 (properties `((upstream-name . "FitHiC")))
10592 (build-system r-build-system)
10594 `(("r-data-table" ,r-data-table)
10595 ("r-fdrtool" ,r-fdrtool)
10596 ("r-rcpp" ,r-rcpp)))
10597 (home-page "https://bioconductor.org/packages/FitHiC")
10598 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10600 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10601 intra-chromosomal contact maps produced by genome-wide genome architecture
10602 assays such as Hi-C.")
10603 (license license:gpl2+)))
10605 (define-public r-hitc
10611 (uri (bioconductor-uri "HiTC" version))
10614 "0byahi0fz0dzjyklz8v9whax9ygg7gwb4pl1j3zbl6z8a9qx8pps"))))
10615 (properties `((upstream-name . "HiTC")))
10616 (build-system r-build-system)
10618 `(("r-biostrings" ,r-biostrings)
10619 ("r-genomeinfodb" ,r-genomeinfodb)
10620 ("r-genomicranges" ,r-genomicranges)
10621 ("r-iranges" ,r-iranges)
10622 ("r-matrix" ,r-matrix)
10623 ("r-rcolorbrewer" ,r-rcolorbrewer)
10624 ("r-rtracklayer" ,r-rtracklayer)))
10625 (home-page "https://bioconductor.org/packages/HiTC")
10626 (synopsis "High throughput chromosome conformation capture analysis")
10628 "The HiTC package was developed to explore high-throughput \"C\" data
10629 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10630 quality controls, normalization, visualization, and further analysis are also
10632 (license license:artistic2.0)))
10634 (define-public r-hdf5array
10636 (name "r-hdf5array")
10641 (uri (bioconductor-uri "HDF5Array" version))
10644 "1z153a7nxmlml72pl1saasj2il9g5ahpynkpv3mkhhsvl5kbwbh6"))))
10645 (properties `((upstream-name . "HDF5Array")))
10646 (build-system r-build-system)
10650 `(("r-biocgenerics" ,r-biocgenerics)
10651 ("r-delayedarray" ,r-delayedarray)
10652 ("r-iranges" ,r-iranges)
10653 ("r-matrix" ,r-matrix)
10654 ("r-rhdf5" ,r-rhdf5)
10655 ("r-rhdf5lib" ,r-rhdf5lib)
10656 ("r-s4vectors" ,r-s4vectors)))
10657 (home-page "https://bioconductor.org/packages/HDF5Array")
10658 (synopsis "HDF5 back end for DelayedArray objects")
10659 (description "This package provides an array-like container for convenient
10660 access and manipulation of HDF5 datasets. It supports delayed operations and
10661 block processing.")
10662 (license license:artistic2.0)))
10664 (define-public r-rhdf5lib
10666 (name "r-rhdf5lib")
10671 (uri (bioconductor-uri "Rhdf5lib" version))
10674 "17lhwnm9rqsvbqkvwp0m07vjrk63a4389p2y39zffv8fgznxqzd7"))
10675 (modules '((guix build utils)))
10678 ;; Delete bundled binaries
10679 (delete-file-recursively "src/winlib/")
10681 (properties `((upstream-name . "Rhdf5lib")))
10682 (build-system r-build-system)
10685 (modify-phases %standard-phases
10686 (add-after 'unpack 'do-not-use-bundled-hdf5
10687 (lambda* (#:key inputs #:allow-other-keys)
10688 (for-each delete-file '("configure" "configure.ac"))
10689 ;; Do not make other packages link with the proprietary libsz.
10690 (substitute* "R/zzz.R"
10691 (("'\"%s/libhdf5.a\" \"%s/libsz.a\" -lz'")
10692 "'\"%s/libhdf5.a\" \"%s/libhdf5.a\" -lz'")
10693 (("'\"%s/libhdf5_cpp.a\" \"%s/libhdf5.a\" \"%s/libsz.a\" -lz'")
10694 "'\"%s/libhdf5_cpp.a\" \"%s/libhdf5.a\" \"%s/libhdf5.a\" -lz'")
10695 (("'%s/libhdf5_hl.a %s/libhdf5.a %s/libsz.a -lz'")
10696 "'%s/libhdf5_hl.a %s/libhdf5.a %s/libhdf5.a -lz'")
10697 (("'%s/libhdf5_hl_cpp.a %s/libhdf5_hl.a %s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a -lz'")
10698 "'%s/libhdf5_hl_cpp.a %s/libhdf5_hl.a %s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a -lz'"))
10699 (with-directory-excursion "src"
10700 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10701 (rename-file (string-append "hdf5-" ,(package-version hdf5-1.10))
10703 ;; Remove timestamp and host system information to make
10704 ;; the build reproducible.
10705 (substitute* "hdf5/src/libhdf5.settings.in"
10706 (("Configured on: @CONFIG_DATE@")
10707 "Configured on: Guix")
10708 (("Uname information:.*")
10709 "Uname information: Linux\n")
10710 ;; Remove unnecessary store reference.
10712 "C Compiler: GCC\n"))
10713 (rename-file "Makevars.in" "Makevars")
10714 (substitute* "Makevars"
10715 (("HDF5_CXX_LIB=.*")
10716 (string-append "HDF5_CXX_LIB="
10717 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10719 (string-append "HDF5_LIB="
10720 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10721 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10722 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10723 (("HDF5_HL_INCLUDE=.*") "HDF5_HL_INCLUDE=./hdf5/hl/src\n")
10724 (("HDF5_HL_CXX_INCLUDE=.*") "HDF5_HL_CXX_INCLUDE=./hdf5/hl/c++/src\n")
10725 (("HDF5_HL_LIB=.*")
10726 (string-append "HDF5_HL_LIB="
10727 (assoc-ref inputs "hdf5") "/lib/libhdf5_hl.a\n"))
10728 (("HDF5_HL_CXX_LIB=.*")
10729 (string-append "HDF5_HL_CXX_LIB="
10730 (assoc-ref inputs "hdf5") "/lib/libhdf5_hl_cpp.a\n"))
10731 ;; szip is non-free software
10732 (("cp \"\\$\\{SZIP_LIB\\}.*") "")
10733 (("PKG_LIBS =.*") "PKG_LIBS = -lz -lhdf5\n")))
10738 `(("hdf5" ,hdf5-1.10)))
10740 `(("hdf5-source" ,(package-source hdf5-1.10))))
10741 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10742 (synopsis "HDF5 library as an R package")
10743 (description "This package provides C and C++ HDF5 libraries for use in R
10745 (license license:artistic2.0)))
10747 (define-public r-beachmat
10749 (name "r-beachmat")
10754 (uri (bioconductor-uri "beachmat" version))
10757 "1bpnlw2kdy9yc2vq948k980r0j25ipb80llhvn0j3kxjiwyfgs3i"))))
10758 (build-system r-build-system)
10760 `(("r-biocgenerics" ,r-biocgenerics)
10761 ("r-delayedarray" ,r-delayedarray)
10762 ("r-matrix" ,r-matrix)))
10763 (home-page "https://bioconductor.org/packages/beachmat")
10764 (synopsis "Compiling Bioconductor to handle each matrix type")
10765 (description "This package provides a consistent C++ class interface for a
10766 variety of commonly used matrix types, including sparse and HDF5-backed
10768 (license license:gpl3)))
10770 (define-public r-singlecellexperiment
10772 (name "r-singlecellexperiment")
10777 (uri (bioconductor-uri "SingleCellExperiment" version))
10780 "11pqb3cigi9xbhxq2k3n7z23v1ibd03ws1lcrh5c5ffgb33nlyw5"))))
10782 `((upstream-name . "SingleCellExperiment")))
10783 (build-system r-build-system)
10785 `(("r-biocgenerics" ,r-biocgenerics)
10786 ("r-s4vectors" ,r-s4vectors)
10787 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10788 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10789 (synopsis "S4 classes for single cell data")
10790 (description "This package defines an S4 class for storing data from
10791 single-cell experiments. This includes specialized methods to store and
10792 retrieve spike-in information, dimensionality reduction coordinates and size
10793 factors for each cell, along with the usual metadata for genes and
10795 (license license:gpl3)))
10797 (define-public r-scater
10803 (uri (bioconductor-uri "scater" version))
10806 "0sxd1s8wdlj9926bagq4crjrk1nnmh3j3bhgrw160zfgc3y8pzck"))))
10807 (build-system r-build-system)
10809 `(("r-beachmat" ,r-beachmat)
10810 ("r-biocgenerics" ,r-biocgenerics)
10811 ("r-biocneighbors" ,r-biocneighbors)
10812 ("r-biocparallel" ,r-biocparallel)
10813 ("r-biocsingular" ,r-biocsingular)
10814 ("r-delayedarray" ,r-delayedarray)
10815 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10816 ("r-ggbeeswarm" ,r-ggbeeswarm)
10817 ("r-ggplot2" ,r-ggplot2)
10818 ("r-matrix" ,r-matrix)
10820 ("r-s4vectors" ,r-s4vectors)
10821 ("r-singlecellexperiment" ,r-singlecellexperiment)
10822 ("r-summarizedexperiment" ,r-summarizedexperiment)
10823 ("r-viridis" ,r-viridis)))
10824 (home-page "https://github.com/davismcc/scater")
10825 (synopsis "Single-cell analysis toolkit for gene expression data in R")
10826 (description "This package provides a collection of tools for doing
10827 various analyses of single-cell RNA-seq gene expression data, with a focus on
10829 (license license:gpl2+)))
10831 (define-public r-scran
10838 (uri (bioconductor-uri "scran" version))
10841 "1y8wlgk5zbv7c7gcp0ahfpbh9lifab7y3zwf0093fzaw7vr1y6cr"))))
10842 (build-system r-build-system)
10844 `(("r-beachmat" ,r-beachmat)
10846 ("r-biocgenerics" ,r-biocgenerics)
10847 ("r-biocneighbors" ,r-biocneighbors)
10848 ("r-biocparallel" ,r-biocparallel)
10849 ("r-biocsingular" ,r-biocsingular)
10850 ("r-delayedarray" ,r-delayedarray)
10851 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10852 ("r-dqrng" ,r-dqrng)
10853 ("r-edger" ,r-edger)
10854 ("r-igraph" ,r-igraph)
10855 ("r-limma" ,r-limma)
10856 ("r-matrix" ,r-matrix)
10858 ("r-s4vectors" ,r-s4vectors)
10859 ("r-scater" ,r-scater)
10860 ("r-singlecellexperiment" ,r-singlecellexperiment)
10861 ("r-statmod" ,r-statmod)
10862 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10863 (home-page "https://bioconductor.org/packages/scran")
10864 (synopsis "Methods for single-cell RNA-Seq data analysis")
10865 (description "This package implements a variety of low-level analyses of
10866 single-cell RNA-seq data. Methods are provided for normalization of
10867 cell-specific biases, assignment of cell cycle phase, and detection of highly
10868 variable and significantly correlated genes.")
10869 (license license:gpl3)))
10871 (define-public r-delayedmatrixstats
10873 (name "r-delayedmatrixstats")
10878 (uri (bioconductor-uri "DelayedMatrixStats" version))
10881 "0mv2rl6a6l404piabcazxz1s6ars016pxhjf5v40hhr6y1r0wbqy"))))
10883 `((upstream-name . "DelayedMatrixStats")))
10884 (build-system r-build-system)
10886 `(("r-biocparallel" ,r-biocparallel)
10887 ("r-delayedarray" ,r-delayedarray)
10888 ("r-hdf5array" ,r-hdf5array)
10889 ("r-iranges" ,r-iranges)
10890 ("r-matrix" ,r-matrix)
10891 ("r-matrixstats" ,r-matrixstats)
10892 ("r-s4vectors" ,r-s4vectors)))
10893 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
10894 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
10896 "This package provides a port of the @code{matrixStats} API for use with
10897 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
10898 contains high-performing functions operating on rows and columns of
10899 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
10900 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
10901 are optimized per data type and for subsetted calculations such that both
10902 memory usage and processing time is minimized.")
10903 (license license:expat)))
10905 (define-public r-phangorn
10907 (name "r-phangorn")
10912 (uri (cran-uri "phangorn" version))
10915 "0ihkaykqjmf80d8wrk3saphxvnv58zma6pd13633bd3cwanc33f5"))))
10916 (build-system r-build-system)
10919 ("r-fastmatch" ,r-fastmatch)
10920 ("r-igraph" ,r-igraph)
10921 ("r-magrittr" ,r-magrittr)
10922 ("r-matrix" ,r-matrix)
10923 ("r-quadprog" ,r-quadprog)
10924 ("r-rcpp" ,r-rcpp)))
10925 (home-page "https://github.com/KlausVigo/phangorn")
10926 (synopsis "Phylogenetic analysis in R")
10928 "Phangorn is a package for phylogenetic analysis in R. It supports
10929 estimation of phylogenetic trees and networks using Maximum Likelihood,
10930 Maximum Parsimony, distance methods and Hadamard conjugation.")
10931 (license license:gpl2+)))
10933 (define-public r-dropbead
10934 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
10937 (name "r-dropbead")
10938 (version (string-append "0-" revision "." (string-take commit 7)))
10942 (uri (git-reference
10943 (url "https://github.com/rajewsky-lab/dropbead.git")
10945 (file-name (git-file-name name version))
10948 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
10949 (build-system r-build-system)
10951 `(("r-ggplot2" ,r-ggplot2)
10952 ("r-rcolorbrewer" ,r-rcolorbrewer)
10953 ("r-gridextra" ,r-gridextra)
10954 ("r-gplots" ,r-gplots)
10955 ("r-plyr" ,r-plyr)))
10956 (home-page "https://github.com/rajewsky-lab/dropbead")
10957 (synopsis "Basic exploration and analysis of Drop-seq data")
10958 (description "This package offers a quick and straight-forward way to
10959 explore and perform basic analysis of single cell sequencing data coming from
10960 droplet sequencing. It has been particularly tailored for Drop-seq.")
10961 (license license:gpl3))))
10963 (define htslib-for-sambamba
10964 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
10967 (name "htslib-for-sambamba")
10968 (version (string-append "1.3.1-1." (string-take commit 9)))
10972 (uri (git-reference
10973 (url "https://github.com/lomereiter/htslib.git")
10975 (file-name (string-append "htslib-" version "-checkout"))
10978 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
10980 `(("autoconf" ,autoconf)
10981 ("automake" ,automake)
10982 ,@(package-native-inputs htslib))))))
10984 (define-public sambamba
10991 (uri (git-reference
10992 (url "https://github.com/lomereiter/sambamba.git")
10993 (commit (string-append "v" version))))
10994 (file-name (string-append name "-" version "-checkout"))
10997 "111h05b60pj8dxbidiamy4imc92x2962b3lmb7wgysl6lx064qis"))))
10998 (build-system gnu-build-system)
11000 `(#:tests? #f ; there is no test target
11001 #:parallel-build? #f ; not supported
11003 (modify-phases %standard-phases
11004 (delete 'configure)
11005 (add-after 'unpack 'fix-ldc-version
11007 (substitute* "gen_ldc_version_info.py"
11008 (("/usr/bin/env.*") (which "python3")))
11009 (substitute* "Makefile"
11010 ;; We use ldc2 instead of ldmd2 to compile sambamba.
11011 (("\\$\\(shell which ldmd2\\)") (which "ldc2")))
11013 (add-after 'unpack 'place-biod-and-undead
11014 (lambda* (#:key inputs #:allow-other-keys)
11015 (copy-recursively (assoc-ref inputs "biod") "BioD")
11017 (add-after 'unpack 'unbundle-prerequisites
11019 (substitute* "Makefile"
11020 (("htslib/libhts.a lz4/lib/liblz4.a")
11022 ((" lz4-static htslib-static") ""))
11025 (lambda* (#:key outputs #:allow-other-keys)
11026 (let* ((out (assoc-ref outputs "out"))
11027 (bin (string-append out "/bin")))
11029 (copy-file (string-append "bin/sambamba-" ,version)
11030 (string-append bin "/sambamba"))
11037 ,(let ((commit "7969eb0a847b05874e83ffddead26e193ece8101"))
11040 (uri (git-reference
11041 (url "https://github.com/biod/BioD.git")
11043 (file-name (string-append "biod-"
11044 (string-take commit 9)
11048 "0mjxsmbmv0jxl3pq21p8j5r829d648if8q58ka50b2956lc6qkpm")))))))
11051 ("htslib" ,htslib-for-sambamba)))
11052 (home-page "https://lomereiter.github.io/sambamba/")
11053 (synopsis "Tools for working with SAM/BAM data")
11054 (description "Sambamba is a high performance modern robust and
11055 fast tool (and library), written in the D programming language, for
11056 working with SAM and BAM files. Current parallelised functionality is
11057 an important subset of samtools functionality, including view, index,
11058 sort, markdup, and depth.")
11059 (license license:gpl2+)))
11061 (define-public ritornello
11063 (name "ritornello")
11067 (uri (git-reference
11068 (url "https://github.com/KlugerLab/Ritornello.git")
11069 (commit (string-append "v" version))))
11070 (file-name (git-file-name name version))
11073 "1xahvq215qld7x1w8vpa5zbrsj6p9crb9shqa2x89sb0aaxa02jk"))))
11074 (build-system gnu-build-system)
11076 `(#:tests? #f ; there are no tests
11078 (modify-phases %standard-phases
11079 (add-after 'unpack 'patch-samtools-references
11080 (lambda* (#:key inputs #:allow-other-keys)
11081 (substitute* '("src/SamStream.h"
11083 (("<sam.h>") "<samtools/sam.h>"))
11085 (delete 'configure)
11087 (lambda* (#:key inputs outputs #:allow-other-keys)
11088 (let* ((out (assoc-ref outputs "out"))
11089 (bin (string-append out "/bin/")))
11091 (install-file "bin/Ritornello" bin)
11094 `(("samtools" ,samtools-0.1)
11098 (home-page "https://github.com/KlugerLab/Ritornello")
11099 (synopsis "Control-free peak caller for ChIP-seq data")
11100 (description "Ritornello is a ChIP-seq peak calling algorithm based on
11101 signal processing that can accurately call binding events without the need to
11102 do a pair total DNA input or IgG control sample. It has been tested for use
11103 with narrow binding events such as transcription factor ChIP-seq.")
11104 (license license:gpl3+)))
11106 (define-public trim-galore
11108 (name "trim-galore")
11113 (uri (git-reference
11114 (url "https://github.com/FelixKrueger/TrimGalore.git")
11116 (file-name (git-file-name name version))
11119 "1y31wbxwkm9xqzr5zv1pk5q418whnmlmgmfyxxpnl12h83m2i9iv"))))
11120 (build-system gnu-build-system)
11122 `(#:tests? #f ; no tests
11124 (modify-phases %standard-phases
11125 (replace 'configure
11127 ;; Trim Galore tries to figure out what version of Python
11128 ;; cutadapt is using by looking at the shebang. Of course that
11129 ;; doesn't work, because cutadapt is wrapped in a shell script.
11130 (substitute* "trim_galore"
11131 (("my \\$python_return.*")
11132 "my $python_return = \"Python 3.999\";\n"))
11135 (add-after 'unpack 'hardcode-tool-references
11136 (lambda* (#:key inputs #:allow-other-keys)
11137 (substitute* "trim_galore"
11138 (("\\$path_to_cutadapt = 'cutadapt'")
11139 (string-append "$path_to_cutadapt = '"
11140 (assoc-ref inputs "cutadapt")
11142 (("\\$compression_path = \"gzip\"")
11143 (string-append "$compression_path = \""
11144 (assoc-ref inputs "gzip")
11147 (string-append "\""
11148 (assoc-ref inputs "gzip")
11151 (string-append "\""
11152 (assoc-ref inputs "pigz")
11156 (lambda* (#:key outputs #:allow-other-keys)
11157 (let ((bin (string-append (assoc-ref outputs "out")
11160 (install-file "trim_galore" bin)
11166 ("cutadapt" ,cutadapt)))
11168 `(("unzip" ,unzip)))
11169 (home-page "https://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
11170 (synopsis "Wrapper around Cutadapt and FastQC")
11171 (description "Trim Galore! is a wrapper script to automate quality and
11172 adapter trimming as well as quality control, with some added functionality to
11173 remove biased methylation positions for RRBS sequence files.")
11174 (license license:gpl3+)))
11176 (define-public gess
11182 (uri (string-append "http://compbio.uthscsa.edu/"
11184 "gess-" version ".src.tar.gz"))
11187 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
11188 (build-system gnu-build-system)
11190 `(#:tests? #f ; no tests
11192 (modify-phases %standard-phases
11193 (delete 'configure)
11196 (lambda* (#:key inputs outputs #:allow-other-keys)
11197 (let* ((python (assoc-ref inputs "python"))
11198 (out (assoc-ref outputs "out"))
11199 (bin (string-append out "/bin/"))
11200 (target (string-append
11202 ,(version-major+minor
11203 (package-version python))
11204 "/site-packages/gess/")))
11206 (copy-recursively "." target)
11207 ;; Make GESS.py executable
11208 (chmod (string-append target "GESS.py") #o555)
11209 ;; Add Python shebang to the top and make Matplotlib
11211 (substitute* (string-append target "GESS.py")
11212 (("\"\"\"Description:" line)
11213 (string-append "#!" (which "python") "
11215 matplotlib.use('Agg')
11217 ;; Make sure GESS has all modules in its path
11218 (wrap-script (string-append target "GESS.py")
11219 `("PYTHONPATH" ":" = (,target ,(getenv "PYTHONPATH"))))
11221 (symlink (string-append target "GESS.py")
11222 (string-append bin "GESS.py"))
11225 `(("python" ,python-2)
11226 ("python2-pysam" ,python2-pysam)
11227 ("python2-scipy" ,python2-scipy)
11228 ("python2-numpy" ,python2-numpy)
11229 ("python2-networkx" ,python2-networkx)
11230 ("python2-biopython" ,python2-biopython)
11231 ("guile" ,guile-3.0))) ; for the script wrapper
11232 (home-page "https://compbio.uthscsa.edu/GESS_Web/")
11233 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11235 "GESS is an implementation of a novel computational method to detect de
11236 novo exon-skipping events directly from raw RNA-seq data without the prior
11237 knowledge of gene annotation information. GESS stands for the graph-based
11238 exon-skipping scanner detection scheme.")
11239 (license license:bsd-3)))
11241 (define-public phylip
11248 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11249 "download/phylip-" version ".tar.gz"))
11252 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11253 (build-system gnu-build-system)
11255 `(#:tests? #f ; no check target
11256 #:make-flags (list "-f" "Makefile.unx" "install")
11257 #:parallel-build? #f ; not supported
11259 (modify-phases %standard-phases
11260 (add-after 'unpack 'enter-dir
11261 (lambda _ (chdir "src") #t))
11262 (delete 'configure)
11264 (lambda* (#:key inputs outputs #:allow-other-keys)
11265 (let ((target (string-append (assoc-ref outputs "out")
11268 (for-each (lambda (file)
11269 (install-file file target))
11270 (find-files "../exe" ".*")))
11272 (home-page "http://evolution.genetics.washington.edu/phylip/")
11273 (synopsis "Tools for inferring phylogenies")
11274 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11275 programs for inferring phylogenies (evolutionary trees).")
11276 (license license:bsd-2)))
11285 (uri (string-append "https://integrativemodeling.org/"
11286 version "/download/imp-" version ".tar.gz"))
11289 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
11290 (build-system cmake-build-system)
11292 `(;; FIXME: Some tests fail because they produce warnings, others fail
11293 ;; because the PYTHONPATH does not include the modeller's directory.
11301 ("python" ,python-2)))
11303 `(("python2-numpy" ,python2-numpy)
11304 ("python2-scipy" ,python2-scipy)
11305 ("python2-pandas" ,python2-pandas)
11306 ("python2-scikit-learn" ,python2-scikit-learn)
11307 ("python2-networkx" ,python2-networkx)))
11308 (home-page "https://integrativemodeling.org")
11309 (synopsis "Integrative modeling platform")
11310 (description "IMP's broad goal is to contribute to a comprehensive
11311 structural characterization of biomolecules ranging in size and complexity
11312 from small peptides to large macromolecular assemblies, by integrating data
11313 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11314 Python toolbox for solving complex modeling problems, and a number of
11315 applications for tackling some common problems in a user-friendly way.")
11316 ;; IMP is largely available under the GNU Lesser GPL; see the file
11317 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11318 ;; available under the GNU GPL (see the file COPYING.GPL).
11319 (license (list license:lgpl2.1+
11322 (define-public tadbit
11328 (uri (git-reference
11329 (url "https://github.com/3DGenomes/TADbit.git")
11330 (commit (string-append "v" version))))
11331 (file-name (git-file-name name version))
11334 "07g3aj648prmsvxp9caz5yl41k0y0647vxh0f5p3w8376mfiljd0"))))
11335 (build-system python-build-system)
11337 `(;; Tests are included and must be run after installation, but
11338 ;; they are incomplete and thus cannot be run.
11342 (modify-phases %standard-phases
11343 (add-after 'unpack 'fix-problems-with-setup.py
11344 (lambda* (#:key outputs #:allow-other-keys)
11345 ;; setup.py opens these files for writing
11346 (chmod "_pytadbit/_version.py" #o664)
11347 (chmod "README.rst" #o664)
11349 ;; Don't attempt to install the bash completions to
11350 ;; the home directory.
11351 (rename-file "extras/.bash_completion"
11353 (substitute* "setup.py"
11354 (("\\(path.expanduser\\('~'\\)")
11355 (string-append "(\""
11356 (assoc-ref outputs "out")
11357 "/etc/bash_completion.d\""))
11358 (("extras/\\.bash_completion")
11362 ;; TODO: add Chimera for visualization
11365 ("python2-scipy" ,python2-scipy)
11366 ("python2-numpy" ,python2-numpy)
11367 ("python2-matplotlib" ,python2-matplotlib)
11368 ("python2-pysam" ,python2-pysam)))
11369 (home-page "https://3dgenomes.github.io/TADbit/")
11370 (synopsis "Analyze, model, and explore 3C-based data")
11372 "TADbit is a complete Python library to deal with all steps to analyze,
11373 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11374 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11375 correct interaction matrices, identify and compare the so-called
11376 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11377 interaction matrices, and finally, extract structural properties from the
11378 models. TADbit is complemented by TADkit for visualizing 3D models.")
11379 (license license:gpl3+)))
11381 (define-public kentutils
11384 ;; 302.1.0 is out, but the only difference is the inclusion of
11385 ;; pre-built binaries.
11386 (version "302.0.0")
11390 (uri (git-reference
11391 (url "https://github.com/ENCODE-DCC/kentUtils.git")
11392 (commit (string-append "v" version))))
11393 (file-name (git-file-name name version))
11396 "0n1wbyjpzii2b9qhyp9r1q76j623cggpg3y8fmw78ld3z4y7ivha"))
11397 (modules '((guix build utils)
11402 ;; Only the contents of the specified directories are free
11403 ;; for all uses, so we remove the rest. "hg/autoSql" and
11404 ;; "hg/autoXml" are nominally free, but they depend on a
11405 ;; library that is built from the sources in "hg/lib",
11406 ;; which is nonfree.
11407 (let ((free (list "." ".."
11408 "utils" "lib" "inc" "tagStorm"
11409 "parasol" "htslib"))
11410 (directory? (lambda (file)
11411 (eq? 'directory (stat:type (stat file))))))
11412 (for-each (lambda (file)
11413 (and (directory? file)
11414 (delete-file-recursively file)))
11415 (map (cut string-append "src/" <>)
11418 (not (member file free)))))))
11419 ;; Only make the utils target, not the userApps target,
11420 ;; because that requires libraries we won't build.
11421 (substitute* "Makefile"
11422 ((" userApps") " utils"))
11423 ;; Only build libraries that are free.
11424 (substitute* "src/makefile"
11425 (("DIRS =.*") "DIRS =\n")
11426 (("cd jkOwnLib.*") "")
11429 (substitute* "src/utils/makefile"
11430 ;; These tools depend on "jkhgap.a", which is part of the
11431 ;; nonfree "src/hg/lib" directory.
11432 (("raSqlQuery") "")
11433 (("pslLiftSubrangeBlat") "")
11435 ;; Do not build UCSC tools, which may require nonfree
11437 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11439 (build-system gnu-build-system)
11441 `( ;; There is no global test target and the test target for
11442 ;; individual tools depends on input files that are not
11446 (modify-phases %standard-phases
11447 (add-after 'unpack 'fix-permissions
11448 (lambda _ (make-file-writable "src/inc/localEnvironment.mk") #t))
11449 (add-after 'unpack 'fix-paths
11451 (substitute* "Makefile"
11452 (("/bin/echo") (which "echo")))
11454 (add-after 'unpack 'prepare-samtabix
11455 (lambda* (#:key inputs #:allow-other-keys)
11456 (copy-recursively (assoc-ref inputs "samtabix")
11459 (delete 'configure)
11461 (lambda* (#:key outputs #:allow-other-keys)
11462 (let ((bin (string-append (assoc-ref outputs "out")
11464 (copy-recursively "bin" bin))
11470 (uri (git-reference
11471 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11472 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11475 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11481 ("mariadb" ,mariadb "lib")
11482 ("mariadb-dev" ,mariadb "dev")
11483 ("openssl" ,openssl-1.0)))
11484 (home-page "https://genome.cse.ucsc.edu/index.html")
11485 (synopsis "Assorted bioinformatics utilities")
11486 (description "This package provides the kentUtils, a selection of
11487 bioinformatics utilities used in combination with the UCSC genome
11489 ;; Only a subset of the sources are released under a non-copyleft
11490 ;; free software license. All other sources are removed in a
11491 ;; snippet. See this bug report for an explanation of how the
11492 ;; license statements apply:
11493 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11494 (license (license:non-copyleft
11495 "http://genome.ucsc.edu/license/"
11496 "The contents of this package are free for all uses."))))
11498 (define-public f-seq
11499 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11503 (version (string-append "1.1-" revision "." (string-take commit 7)))
11506 (uri (git-reference
11507 (url "https://github.com/aboyle/F-seq.git")
11509 (file-name (string-append name "-" version))
11512 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11513 (modules '((guix build utils)))
11514 ;; Remove bundled Java library archives.
11517 (for-each delete-file (find-files "lib" ".*"))
11519 (build-system ant-build-system)
11521 `(#:tests? #f ; no tests included
11523 (modify-phases %standard-phases
11525 (lambda* (#:key inputs outputs #:allow-other-keys)
11526 (let* ((target (assoc-ref outputs "out"))
11527 (bin (string-append target "/bin"))
11528 (doc (string-append target "/share/doc/f-seq"))
11529 (lib (string-append target "/lib")))
11532 (substitute* "bin/linux/fseq"
11533 (("java") (which "java"))
11534 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11535 (string-append (assoc-ref inputs "java-commons-cli")
11536 "/share/java/commons-cli.jar"))
11538 (string-append "REALDIR=" bin "\n")))
11539 (install-file "README.txt" doc)
11540 (install-file "bin/linux/fseq" bin)
11541 (install-file "build~/fseq.jar" lib)
11542 (copy-recursively "lib" lib)
11546 ("java-commons-cli" ,java-commons-cli)))
11547 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11548 (synopsis "Feature density estimator for high-throughput sequence tags")
11550 "F-Seq is a software package that generates a continuous tag sequence
11551 density estimation allowing identification of biologically meaningful sites
11552 such as transcription factor binding sites (ChIP-seq) or regions of open
11553 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11555 (license license:gpl3+))))
11557 (define-public bismark
11564 (uri (git-reference
11565 (url "https://github.com/FelixKrueger/Bismark.git")
11567 (file-name (string-append name "-" version "-checkout"))
11570 "0xchm3rgilj6vfjnyzfzzymfd7djr64sbrmrvs3njbwi66jqbzw9"))))
11571 (build-system perl-build-system)
11573 `(#:tests? #f ; there are no tests
11574 #:modules ((guix build utils)
11577 (guix build perl-build-system))
11579 (modify-phases %standard-phases
11580 ;; The bundled plotly.js is minified.
11581 (add-after 'unpack 'replace-plotly.js
11582 (lambda* (#:key inputs #:allow-other-keys)
11583 (let* ((file (assoc-ref inputs "plotly.js"))
11584 (installed "plotly/plotly.js"))
11585 (let ((minified (open-pipe* OPEN_READ "uglify-js" file)))
11586 (call-with-output-file installed
11587 (cut dump-port minified <>))))
11589 (delete 'configure)
11592 (lambda* (#:key inputs outputs #:allow-other-keys)
11593 (let* ((out (assoc-ref outputs "out"))
11594 (bin (string-append out "/bin"))
11595 (share (string-append out "/share/bismark"))
11596 (docdir (string-append out "/share/doc/bismark"))
11597 (docs '("Docs/Bismark_User_Guide.html"))
11598 (scripts '("bismark"
11599 "bismark_genome_preparation"
11600 "bismark_methylation_extractor"
11603 "coverage2cytosine"
11604 "deduplicate_bismark"
11605 "filter_non_conversion"
11608 "NOMe_filtering")))
11609 (substitute* "bismark2report"
11610 (("\\$RealBin/plotly")
11611 (string-append share "/plotly")))
11615 (for-each (lambda (file) (install-file file bin))
11617 (for-each (lambda (file) (install-file file docdir))
11619 (copy-recursively "Docs/Images" (string-append docdir "/Images"))
11620 (copy-recursively "plotly"
11621 (string-append share "/plotly"))
11623 ;; Fix references to gunzip
11624 (substitute* (map (lambda (file)
11625 (string-append bin "/" file))
11628 (string-append "\"" (assoc-ref inputs "gzip")
11629 "/bin/gunzip -c")))
11633 ("perl-carp" ,perl-carp)
11634 ("perl-getopt-long" ,perl-getopt-long)))
11639 (uri (string-append "https://raw.githubusercontent.com/plotly/plotly.js/"
11640 "v1.39.4/dist/plotly.js"))
11642 (base32 "138mwsr4nf5qif4mrxx286mpnagxd1xwl6k8aidrjgknaqg88zyr"))))
11643 ("uglify-js" ,uglify-js)))
11644 (home-page "https://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11645 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11646 (description "Bismark is a program to map bisulfite treated sequencing
11647 reads to a genome of interest and perform methylation calls in a single step.
11648 The output can be easily imported into a genome viewer, such as SeqMonk, and
11649 enables a researcher to analyse the methylation levels of their samples
11650 straight away. Its main features are:
11653 @item Bisulfite mapping and methylation calling in one single step
11654 @item Supports single-end and paired-end read alignments
11655 @item Supports ungapped and gapped alignments
11656 @item Alignment seed length, number of mismatches etc are adjustable
11657 @item Output discriminates between cytosine methylation in CpG, CHG
11660 (license license:gpl3+)))
11662 (define-public paml
11668 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11669 "paml" version ".tgz"))
11672 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11673 (modules '((guix build utils)))
11674 ;; Remove Windows binaries
11677 (for-each delete-file (find-files "." "\\.exe$"))
11679 (build-system gnu-build-system)
11681 `(#:tests? #f ; there are no tests
11682 #:make-flags '("CC=gcc")
11684 (modify-phases %standard-phases
11685 (replace 'configure
11687 (substitute* "src/BFdriver.c"
11688 (("/bin/bash") (which "bash")))
11692 (lambda* (#:key outputs #:allow-other-keys)
11693 (let ((tools '("baseml" "basemlg" "codeml"
11694 "pamp" "evolver" "yn00" "chi2"))
11695 (bin (string-append (assoc-ref outputs "out") "/bin"))
11696 (docdir (string-append (assoc-ref outputs "out")
11697 "/share/doc/paml")))
11699 (for-each (lambda (file) (install-file file bin)) tools)
11700 (copy-recursively "../doc" docdir)
11702 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11703 (synopsis "Phylogentic analysis by maximum likelihood")
11704 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11705 contains a few programs for model fitting and phylogenetic tree reconstruction
11706 using nucleotide or amino-acid sequence data.")
11708 (license license:gpl3)))
11710 (define-public kallisto
11716 (uri (git-reference
11717 (url "https://github.com/pachterlab/kallisto.git")
11718 (commit (string-append "v" version))))
11719 (file-name (git-file-name name version))
11722 "0nj382jiywqnpgvyhichajpkkh5r0bapn43f4dx40zdaq5v4m40m"))))
11723 (build-system cmake-build-system)
11725 `(#:tests? #f ; no "check" target
11727 (modify-phases %standard-phases
11728 (add-after 'unpack 'do-not-use-bundled-htslib
11730 (substitute* "CMakeLists.txt"
11731 (("^ExternalProject_Add" m)
11732 (string-append "if (NEVER)\n" m))
11734 (string-append ")\nendif(NEVER)"))
11735 (("include_directories\\(\\$\\{htslib_PREFIX.*" m)
11736 (string-append "# " m)))
11737 (substitute* "src/CMakeLists.txt"
11738 (("target_link_libraries\\(kallisto kallisto_core pthread \
11739 \\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/../ext/htslib/libhts.a\\)")
11740 "target_link_libraries(kallisto kallisto_core pthread hts)")
11741 (("include_directories\\(\\.\\./ext/htslib\\)") ""))
11747 (home-page "https://pachterlab.github.io/kallisto/")
11748 (synopsis "Near-optimal RNA-Seq quantification")
11750 "Kallisto is a program for quantifying abundances of transcripts from
11751 RNA-Seq data, or more generally of target sequences using high-throughput
11752 sequencing reads. It is based on the novel idea of pseudoalignment for
11753 rapidly determining the compatibility of reads with targets, without the need
11754 for alignment. Pseudoalignment of reads preserves the key information needed
11755 for quantification, and kallisto is therefore not only fast, but also as
11756 accurate as existing quantification tools.")
11757 (license license:bsd-2)))
11759 (define-public libgff
11765 (uri (git-reference
11766 (url "https://github.com/Kingsford-Group/libgff.git")
11767 (commit (string-append "v" version))))
11768 (file-name (git-file-name name version))
11771 "0n6vfjnq7a2mianipscbshrvbncss8z4zkgkbjw754p9043nfkps"))))
11772 (build-system cmake-build-system)
11773 (arguments `(#:tests? #f)) ; no tests included
11774 (home-page "https://github.com/Kingsford-Group/libgff")
11775 (synopsis "Parser library for reading/writing GFF files")
11776 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11777 code that is used in the Cufflinks codebase. The goal of this library is to
11778 provide this functionality without the necessity of drawing in a heavy-weight
11779 dependency like SeqAn.")
11780 (license (license:x11-style "https://www.boost.org/LICENSE_1_0.txt"))))
11782 (define-public sailfish
11788 (uri (git-reference
11789 (url "https://github.com/kingsfordgroup/sailfish.git")
11790 (commit (string-append "v" version))))
11791 (file-name (git-file-name name version))
11794 "1amcc5hqvsl42hg4x19bi9vy47cl874s0lw1fmi0hwsdk9i8c03v"))
11795 (modules '((guix build utils)))
11798 ;; Delete bundled headers for eigen3.
11799 (delete-file-recursively "include/eigen3/")
11801 (build-system cmake-build-system)
11803 `(#:configure-flags
11804 (list (string-append "-DBOOST_INCLUDEDIR="
11805 (assoc-ref %build-inputs "boost")
11807 (string-append "-DBOOST_LIBRARYDIR="
11808 (assoc-ref %build-inputs "boost")
11810 (string-append "-DBoost_LIBRARIES="
11811 "-lboost_iostreams "
11812 "-lboost_filesystem "
11817 "-lboost_program_options")
11818 "-DBoost_FOUND=TRUE"
11819 ;; Don't download RapMap---we already have it!
11820 "-DFETCHED_RAPMAP=1")
11821 ;; Tests must be run after installation and the location of the test
11822 ;; data file must be overridden. But the tests fail. It looks like
11823 ;; they are not really meant to be run.
11826 (modify-phases %standard-phases
11827 ;; Boost cannot be found, even though it's right there.
11828 (add-after 'unpack 'do-not-look-for-boost
11829 (lambda* (#:key inputs #:allow-other-keys)
11830 (substitute* "CMakeLists.txt"
11831 (("find_package\\(Boost 1\\.53\\.0") "#"))
11833 (add-after 'unpack 'do-not-assign-to-macro
11835 (substitute* "include/spdlog/details/format.cc"
11836 (("const unsigned CHAR_WIDTH = 1;") ""))
11838 (add-after 'unpack 'prepare-rapmap
11839 (lambda* (#:key inputs #:allow-other-keys)
11840 (let ((src "external/install/src/rapmap/")
11841 (include "external/install/include/rapmap/")
11842 (rapmap (assoc-ref inputs "rapmap")))
11843 (mkdir-p "/tmp/rapmap")
11845 (assoc-ref inputs "rapmap")
11847 "--strip-components=1")
11850 (for-each (lambda (file)
11851 (install-file file src))
11852 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
11853 (copy-recursively "/tmp/rapmap/include" include))
11855 (add-after 'unpack 'use-system-libraries
11856 (lambda* (#:key inputs #:allow-other-keys)
11857 (substitute* '("src/SailfishIndexer.cpp"
11858 "src/SailfishUtils.cpp"
11859 "src/SailfishQuantify.cpp"
11860 "src/FASTAParser.cpp"
11862 "include/SailfishUtils.hpp"
11863 "include/SailfishIndex.hpp"
11864 "include/CollapsedEMOptimizer.hpp"
11865 "src/CollapsedEMOptimizer.cpp")
11866 (("#include \"jellyfish/config.h\"") ""))
11867 (substitute* "src/CMakeLists.txt"
11868 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11869 (string-append (assoc-ref inputs "jellyfish")
11870 "/include/jellyfish-" ,(package-version jellyfish)))
11871 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11872 (string-append (assoc-ref inputs "jellyfish")
11873 "/lib/libjellyfish-2.0.a"))
11874 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11875 (string-append (assoc-ref inputs "libdivsufsort")
11876 "/lib/libdivsufsort.so"))
11877 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11878 (string-append (assoc-ref inputs "libdivsufsort")
11879 "/lib/libdivsufsort64.so")))
11880 (substitute* "CMakeLists.txt"
11881 ;; Don't prefer static libs
11882 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11883 (("find_package\\(Jellyfish.*") "")
11884 (("ExternalProject_Add\\(libjellyfish") "message(")
11885 (("ExternalProject_Add\\(libgff") "message(")
11886 (("ExternalProject_Add\\(libsparsehash") "message(")
11887 (("ExternalProject_Add\\(libdivsufsort") "message("))
11889 ;; Ensure that Eigen headers can be found
11890 (setenv "CPLUS_INCLUDE_PATH"
11891 (string-append (assoc-ref inputs "eigen")
11892 "/include/eigen3"))
11897 ("jemalloc" ,jemalloc)
11898 ("jellyfish" ,jellyfish)
11899 ("sparsehash" ,sparsehash)
11902 (uri (git-reference
11903 (url "https://github.com/COMBINE-lab/RapMap.git")
11904 (commit (string-append "sf-v" version))))
11905 (file-name (string-append "rapmap-sf-v" version "-checkout"))
11908 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
11909 (modules '((guix build utils)))
11910 ;; These files are expected to be excluded.
11912 '(begin (delete-file-recursively "include/spdlog")
11913 (for-each delete-file '("include/xxhash.h"
11916 ("libdivsufsort" ,libdivsufsort)
11921 `(("pkg-config" ,pkg-config)))
11922 (home-page "https://www.cs.cmu.edu/~ckingsf/software/sailfish/")
11923 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
11924 (description "Sailfish is a tool for genomic transcript quantification
11925 from RNA-seq data. It requires a set of target transcripts (either from a
11926 reference or de-novo assembly) to quantify. All you need to run sailfish is a
11927 fasta file containing your reference transcripts and a (set of) fasta/fastq
11928 file(s) containing your reads.")
11929 (license license:gpl3+)))
11931 (define libstadenio-for-salmon
11933 (name "libstadenio")
11937 (uri (git-reference
11938 (url "https://github.com/COMBINE-lab/staden-io_lib.git")
11939 (commit (string-append "v" version))))
11940 (file-name (string-append name "-" version "-checkout"))
11943 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
11944 (build-system gnu-build-system)
11945 (arguments '(#:parallel-tests? #f)) ; not supported
11949 `(("perl" ,perl))) ; for tests
11950 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
11951 (synopsis "General purpose trace and experiment file library")
11952 (description "This package provides a library of file reading and writing
11953 code to provide a general purpose Trace file (and Experiment File) reading
11956 The following file formats are supported:
11959 @item SCF trace files
11960 @item ABI trace files
11961 @item ALF trace files
11962 @item ZTR trace files
11963 @item SFF trace archives
11964 @item SRF trace archives
11965 @item Experiment files
11966 @item Plain text files
11967 @item SAM/BAM sequence files
11968 @item CRAM sequence files
11970 (license license:bsd-3)))
11972 (define-public salmon
11978 (uri (git-reference
11979 (url "https://github.com/COMBINE-lab/salmon.git")
11980 (commit (string-append "v" version))))
11981 (file-name (git-file-name name version))
11984 "1i2z4aivicmiixdz9bxalp7vmfzi3k92fxa63iqa8kgvfw5a4aq5"))
11985 (modules '((guix build utils)))
11988 ;; Delete bundled headers for eigen3.
11989 (delete-file-recursively "include/eigen3/")
11991 (build-system cmake-build-system)
11993 `(#:configure-flags
11994 (list (string-append "-DBOOST_INCLUDEDIR="
11995 (assoc-ref %build-inputs "boost")
11997 (string-append "-DBOOST_LIBRARYDIR="
11998 (assoc-ref %build-inputs "boost")
12000 (string-append "-DBoost_LIBRARIES="
12001 "-lboost_iostreams "
12002 "-lboost_filesystem "
12007 "-lboost_program_options")
12008 "-DBoost_FOUND=TRUE"
12009 "-DTBB_LIBRARIES=tbb tbbmalloc"
12010 ;; Don't download RapMap---we already have it!
12011 "-DFETCHED_RAPMAP=1")
12013 (modify-phases %standard-phases
12014 ;; Boost cannot be found, even though it's right there.
12015 (add-after 'unpack 'do-not-look-for-boost
12016 (lambda* (#:key inputs #:allow-other-keys)
12017 (substitute* "CMakeLists.txt"
12018 (("find_package\\(Boost 1\\.59\\.0") "#"))
12020 (add-after 'unpack 'do-not-phone-home
12022 (substitute* "src/Salmon.cpp"
12023 (("getVersionMessage\\(\\)") "\"\""))
12025 (add-after 'unpack 'prepare-rapmap
12026 (lambda* (#:key inputs #:allow-other-keys)
12027 (let ((src "external/install/src/rapmap/")
12028 (include "external/install/include/rapmap/")
12029 (rapmap (assoc-ref inputs "rapmap")))
12032 (copy-recursively (string-append rapmap "/src") src)
12033 (copy-recursively (string-append rapmap "/include") include)
12034 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
12035 "external/install/include/rapmap/FastxParser.hpp"
12036 "external/install/include/rapmap/concurrentqueue.h"
12037 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
12038 "external/install/src/rapmap/FastxParser.cpp"
12039 "external/install/src/rapmap/xxhash.c"))
12040 (delete-file-recursively "external/install/include/rapmap/spdlog"))
12042 (add-after 'unpack 'use-system-libraries
12043 (lambda* (#:key inputs #:allow-other-keys)
12044 (substitute* "CMakeLists.txt"
12045 ;; Don't prefer static libs
12046 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
12047 (("set\\(TBB_LIBRARIES") "message(")
12048 ;; Don't download anything
12049 (("DOWNLOAD_COMMAND") "DOWNLOAD_COMMAND echo")
12050 (("externalproject_add\\(libcereal") "message(")
12051 (("externalproject_add\\(libgff") "message(")
12052 (("externalproject_add\\(libtbb") "message(")
12053 (("externalproject_add\\(libdivsufsort") "message(")
12054 (("externalproject_add\\(libstadenio") "message(")
12055 (("externalproject_add_step\\(") "message("))
12056 (substitute* "src/CMakeLists.txt"
12057 (("add_dependencies") "#")
12058 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
12059 (string-append (assoc-ref inputs "libstadenio-for-salmon")
12060 "/lib/libstaden-read.so"))
12061 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
12062 (string-append (assoc-ref inputs "libdivsufsort")
12063 "/lib/libdivsufsort.so"))
12064 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
12065 (string-append (assoc-ref inputs "libdivsufsort")
12066 "/lib/libdivsufsort64.so"))
12067 (("lib/libdivsufsort.a") "/lib/libdivsufsort.so"))
12069 ;; Ensure that all headers can be found
12071 (string-append (getenv "CPATH")
12073 (assoc-ref inputs "eigen")
12074 "/include/eigen3"))
12076 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
12077 ;; run. It only exists after the install phase.
12078 (add-after 'unpack 'fix-tests
12080 (substitute* "src/CMakeLists.txt"
12081 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
12082 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
12091 (uri (git-reference
12092 (url "https://github.com/COMBINE-lab/RapMap.git")
12093 (commit (string-append "salmon-v" version))))
12094 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
12097 "1biplxf0csc7a8h1wf219b0vmjkvw6wk2zylhdklb577kgmihdms"))))
12098 ("jemalloc" ,jemalloc)
12101 ("libdivsufsort" ,libdivsufsort)
12102 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
12106 `(("pkg-config" ,pkg-config)))
12107 (home-page "https://github.com/COMBINE-lab/salmon")
12108 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
12109 (description "Salmon is a program to produce highly-accurate,
12110 transcript-level quantification estimates from RNA-seq data. Salmon achieves
12111 its accuracy and speed via a number of different innovations, including the
12112 use of lightweight alignments (accurate but fast-to-compute proxies for
12113 traditional read alignments) and massively-parallel stochastic collapsed
12114 variational inference.")
12115 (license license:gpl3+)))
12117 (define-public python-loompy
12119 (name "python-loompy")
12121 ;; The tarball on Pypi does not include the tests.
12124 (uri (git-reference
12125 (url "https://github.com/linnarsson-lab/loompy.git")
12127 (file-name (git-file-name name version))
12130 "12a5kjgiikapv93wahfw0frszx1lblnppyz3vs5gy8fgmgngra07"))))
12131 (build-system python-build-system)
12134 (modify-phases %standard-phases
12137 (setenv "PYTHONPATH"
12138 (string-append (getcwd) ":"
12139 (getenv "PYTHONPATH")))
12140 (invoke "pytest" "tests")
12143 `(("python-h5py" ,python-h5py)
12144 ("python-numpy" ,python-numpy)
12145 ("python-pandas" ,python-pandas)
12146 ("python-scipy" ,python-scipy)))
12148 `(("python-pytest" ,python-pytest)))
12149 (home-page "https://github.com/linnarsson-lab/loompy")
12150 (synopsis "Work with .loom files for single-cell RNA-seq data")
12151 (description "The loom file format is an efficient format for very large
12152 omics datasets, consisting of a main matrix, optional additional layers, a
12153 variable number of row and column annotations. Loom also supports sparse
12154 graphs. This library makes it easy to work with @file{.loom} files for
12155 single-cell RNA-seq data.")
12156 (license license:bsd-3)))
12158 ;; We cannot use the latest commit because it requires Java 9.
12159 (define-public java-forester
12160 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
12163 (name "java-forester")
12164 (version (string-append "0-" revision "." (string-take commit 7)))
12167 (uri (git-reference
12168 (url "https://github.com/cmzmasek/forester.git")
12170 (file-name (string-append name "-" version "-checkout"))
12173 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12174 (modules '((guix build utils)))
12177 ;; Delete bundled jars and pre-built classes
12178 (delete-file-recursively "forester/java/resources")
12179 (delete-file-recursively "forester/java/classes")
12180 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12181 ;; Delete bundled applications
12182 (delete-file-recursively "forester_applications")
12184 (build-system ant-build-system)
12186 `(#:tests? #f ; there are none
12188 #:modules ((guix build ant-build-system)
12190 (guix build java-utils)
12194 (modify-phases %standard-phases
12195 (add-after 'unpack 'chdir
12196 (lambda _ (chdir "forester/java") #t))
12197 (add-after 'chdir 'fix-dependencies
12199 (chmod "build.xml" #o664)
12200 (call-with-output-file "build.xml.new"
12204 (with-input-from-file "build.xml"
12205 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12206 `(;; Remove all unjar tags to avoid repacking classes.
12207 (unjar . ,(lambda _ '()))
12208 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12209 (*text* . ,(lambda (_ txt) txt))))
12211 (rename-file "build.xml.new" "build.xml")
12213 ;; FIXME: itext is difficult to package as it depends on a few
12214 ;; unpackaged libraries.
12215 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12217 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12218 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12219 (("pdf_written_to = PdfExporter.*")
12220 "throw new IOException(\"PDF export is not available.\");"))
12222 ;; There is no install target
12223 (replace 'install (install-jars ".")))))
12225 `(("java-commons-codec" ,java-commons-codec)
12226 ("java-openchart2" ,java-openchart2)))
12227 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12228 (synopsis "Phylogenomics libraries for Java")
12229 (description "Forester is a collection of Java libraries for
12230 phylogenomics and evolutionary biology research. It includes support for
12231 reading, writing, and exporting phylogenetic trees.")
12232 (license license:lgpl2.1+))))
12234 (define-public java-forester-1.005
12236 (name "java-forester")
12240 (uri (string-append "https://repo1.maven.org/maven2/"
12241 "org/biojava/thirdparty/forester/"
12242 version "/forester-" version "-sources.jar"))
12243 (file-name (string-append name "-" version ".jar"))
12246 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12247 (build-system ant-build-system)
12249 `(#:tests? #f ; there are none
12251 #:modules ((guix build ant-build-system)
12253 (guix build java-utils)
12257 (modify-phases %standard-phases
12258 (add-after 'unpack 'fix-dependencies
12259 (lambda* (#:key inputs #:allow-other-keys)
12260 (call-with-output-file "build.xml"
12264 (with-input-from-file "src/build.xml"
12265 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12266 `(;; Remove all unjar tags to avoid repacking classes.
12267 (unjar . ,(lambda _ '()))
12268 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12269 (*text* . ,(lambda (_ txt) txt))))
12271 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12272 "synth_look_and_feel_1.xml")
12273 (copy-file (assoc-ref inputs "phyloxml.xsd")
12275 (substitute* "build.xml"
12276 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12277 "synth_look_and_feel_1.xml")
12278 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12281 ;; FIXME: itext is difficult to package as it depends on a few
12282 ;; unpackaged libraries.
12283 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12285 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12286 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12287 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12288 (("pdf_written_to = PdfExporter.*")
12289 "throw new IOException(\"PDF export is not available.\"); /*")
12290 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12291 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12293 (add-after 'unpack 'delete-pre-built-classes
12294 (lambda _ (delete-file-recursively "src/classes") #t))
12295 ;; There is no install target
12296 (replace 'install (install-jars ".")))))
12298 `(("java-commons-codec" ,java-commons-codec)
12299 ("java-openchart2" ,java-openchart2)))
12300 ;; The source archive does not contain the resources.
12305 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12306 "b61cc2dcede0bede317db362472333115756b8c6/"
12307 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12308 (file-name (string-append name "-phyloxml-" version ".xsd"))
12311 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12312 ("synth_look_and_feel_1.xml"
12315 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12316 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12317 "forester/java/classes/resources/"
12318 "synth_look_and_feel_1.xml"))
12319 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12322 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12323 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12324 (synopsis "Phylogenomics libraries for Java")
12325 (description "Forester is a collection of Java libraries for
12326 phylogenomics and evolutionary biology research. It includes support for
12327 reading, writing, and exporting phylogenetic trees.")
12328 (license license:lgpl2.1+)))
12330 (define-public java-biojava-core
12332 (name "java-biojava-core")
12336 (uri (git-reference
12337 (url "https://github.com/biojava/biojava")
12338 (commit (string-append "biojava-" version))))
12339 (file-name (string-append name "-" version "-checkout"))
12342 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12343 (build-system ant-build-system)
12346 #:jar-name "biojava-core.jar"
12347 #:source-dir "biojava-core/src/main/java/"
12348 #:test-dir "biojava-core/src/test"
12349 ;; These tests seem to require internet access.
12350 #:test-exclude (list "**/SearchIOTest.java"
12351 "**/BlastXMLParserTest.java"
12352 "**/GenbankCookbookTest.java"
12353 "**/GenbankProxySequenceReaderTest.java")
12355 (modify-phases %standard-phases
12356 (add-before 'build 'copy-resources
12358 (copy-recursively "biojava-core/src/main/resources"
12361 (add-before 'check 'copy-test-resources
12363 (copy-recursively "biojava-core/src/test/resources"
12364 "build/test-classes")
12367 `(("java-log4j-api" ,java-log4j-api)
12368 ("java-log4j-core" ,java-log4j-core)
12369 ("java-slf4j-api" ,java-slf4j-api)
12370 ("java-slf4j-simple" ,java-slf4j-simple)))
12372 `(("java-junit" ,java-junit)
12373 ("java-hamcrest-core" ,java-hamcrest-core)))
12374 (home-page "http://biojava.org")
12375 (synopsis "Core libraries of Java framework for processing biological data")
12376 (description "BioJava is a project dedicated to providing a Java framework
12377 for processing biological data. It provides analytical and statistical
12378 routines, parsers for common file formats, reference implementations of
12379 popular algorithms, and allows the manipulation of sequences and 3D
12380 structures. The goal of the biojava project is to facilitate rapid
12381 application development for bioinformatics.
12383 This package provides the core libraries.")
12384 (license license:lgpl2.1+)))
12386 (define-public java-biojava-phylo
12387 (package (inherit java-biojava-core)
12388 (name "java-biojava-phylo")
12389 (build-system ant-build-system)
12392 #:jar-name "biojava-phylo.jar"
12393 #:source-dir "biojava-phylo/src/main/java/"
12394 #:test-dir "biojava-phylo/src/test"
12396 (modify-phases %standard-phases
12397 (add-before 'build 'copy-resources
12399 (copy-recursively "biojava-phylo/src/main/resources"
12402 (add-before 'check 'copy-test-resources
12404 (copy-recursively "biojava-phylo/src/test/resources"
12405 "build/test-classes")
12408 `(("java-log4j-api" ,java-log4j-api)
12409 ("java-log4j-core" ,java-log4j-core)
12410 ("java-slf4j-api" ,java-slf4j-api)
12411 ("java-slf4j-simple" ,java-slf4j-simple)
12412 ("java-biojava-core" ,java-biojava-core)
12413 ("java-forester" ,java-forester)))
12415 `(("java-junit" ,java-junit)
12416 ("java-hamcrest-core" ,java-hamcrest-core)))
12417 (home-page "http://biojava.org")
12418 (synopsis "Biojava interface to the forester phylogenomics library")
12419 (description "The phylo module provides a biojava interface layer to the
12420 forester phylogenomics library for constructing phylogenetic trees.")))
12422 (define-public java-biojava-alignment
12423 (package (inherit java-biojava-core)
12424 (name "java-biojava-alignment")
12425 (build-system ant-build-system)
12428 #:jar-name "biojava-alignment.jar"
12429 #:source-dir "biojava-alignment/src/main/java/"
12430 #:test-dir "biojava-alignment/src/test"
12432 (modify-phases %standard-phases
12433 (add-before 'build 'copy-resources
12435 (copy-recursively "biojava-alignment/src/main/resources"
12438 (add-before 'check 'copy-test-resources
12440 (copy-recursively "biojava-alignment/src/test/resources"
12441 "build/test-classes")
12444 `(("java-log4j-api" ,java-log4j-api)
12445 ("java-log4j-core" ,java-log4j-core)
12446 ("java-slf4j-api" ,java-slf4j-api)
12447 ("java-slf4j-simple" ,java-slf4j-simple)
12448 ("java-biojava-core" ,java-biojava-core)
12449 ("java-biojava-phylo" ,java-biojava-phylo)
12450 ("java-forester" ,java-forester)))
12452 `(("java-junit" ,java-junit)
12453 ("java-hamcrest-core" ,java-hamcrest-core)))
12454 (home-page "http://biojava.org")
12455 (synopsis "Biojava API for genetic sequence alignment")
12456 (description "The alignment module of BioJava provides an API that
12460 @item implementations of dynamic programming algorithms for sequence
12462 @item reading and writing of popular alignment file formats;
12463 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12466 (define-public java-biojava-core-4.0
12467 (package (inherit java-biojava-core)
12468 (name "java-biojava-core")
12472 (uri (git-reference
12473 (url "https://github.com/biojava/biojava")
12474 (commit (string-append "biojava-" version))))
12475 (file-name (string-append name "-" version "-checkout"))
12478 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12480 (define-public java-biojava-phylo-4.0
12481 (package (inherit java-biojava-core-4.0)
12482 (name "java-biojava-phylo")
12483 (build-system ant-build-system)
12486 #:jar-name "biojava-phylo.jar"
12487 #:source-dir "biojava-phylo/src/main/java/"
12488 #:test-dir "biojava-phylo/src/test"
12490 (modify-phases %standard-phases
12491 (add-before 'build 'copy-resources
12493 (copy-recursively "biojava-phylo/src/main/resources"
12496 (add-before 'check 'copy-test-resources
12498 (copy-recursively "biojava-phylo/src/test/resources"
12499 "build/test-classes")
12502 `(("java-log4j-api" ,java-log4j-api)
12503 ("java-log4j-core" ,java-log4j-core)
12504 ("java-slf4j-api" ,java-slf4j-api)
12505 ("java-slf4j-simple" ,java-slf4j-simple)
12506 ("java-biojava-core" ,java-biojava-core-4.0)
12507 ("java-forester" ,java-forester-1.005)))
12509 `(("java-junit" ,java-junit)
12510 ("java-hamcrest-core" ,java-hamcrest-core)))
12511 (home-page "http://biojava.org")
12512 (synopsis "Biojava interface to the forester phylogenomics library")
12513 (description "The phylo module provides a biojava interface layer to the
12514 forester phylogenomics library for constructing phylogenetic trees.")))
12516 (define-public java-biojava-alignment-4.0
12517 (package (inherit java-biojava-core-4.0)
12518 (name "java-biojava-alignment")
12519 (build-system ant-build-system)
12522 #:jar-name "biojava-alignment.jar"
12523 #:source-dir "biojava-alignment/src/main/java/"
12524 #:test-dir "biojava-alignment/src/test"
12526 (modify-phases %standard-phases
12527 (add-before 'build 'copy-resources
12529 (copy-recursively "biojava-alignment/src/main/resources"
12532 (add-before 'check 'copy-test-resources
12534 (copy-recursively "biojava-alignment/src/test/resources"
12535 "build/test-classes")
12538 `(("java-log4j-api" ,java-log4j-api)
12539 ("java-log4j-core" ,java-log4j-core)
12540 ("java-slf4j-api" ,java-slf4j-api)
12541 ("java-slf4j-simple" ,java-slf4j-simple)
12542 ("java-biojava-core" ,java-biojava-core-4.0)
12543 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12544 ("java-forester" ,java-forester-1.005)))
12546 `(("java-junit" ,java-junit)
12547 ("java-hamcrest-core" ,java-hamcrest-core)))
12548 (home-page "http://biojava.org")
12549 (synopsis "Biojava API for genetic sequence alignment")
12550 (description "The alignment module of BioJava provides an API that
12554 @item implementations of dynamic programming algorithms for sequence
12556 @item reading and writing of popular alignment file formats;
12557 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12560 (define-public dropseq-tools
12562 (name "dropseq-tools")
12567 (uri "http://mccarrolllab.com/download/1276/")
12568 (file-name (string-append "dropseq-tools-" version ".zip"))
12571 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12572 ;; Delete bundled libraries
12573 (modules '((guix build utils)))
12576 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12577 (delete-file-recursively "3rdParty")
12579 (build-system ant-build-system)
12581 `(#:tests? #f ; test data are not included
12582 #:test-target "test"
12583 #:build-target "all"
12584 #:source-dir "public/src/"
12587 (list (string-append "-Dpicard.executable.dir="
12588 (assoc-ref %build-inputs "java-picard")
12590 #:modules ((ice-9 match)
12593 (guix build java-utils)
12594 (guix build ant-build-system))
12596 (modify-phases %standard-phases
12597 ;; FIXME: fails with "java.io.FileNotFoundException:
12598 ;; /gnu/store/…-dropseq-tools-1.13/share/java/lib/biojava-alignment.jar"
12599 (delete 'generate-jar-indices)
12600 ;; All dependencies must be linked to "lib", because that's where
12601 ;; they will be searched for when the Class-Path property of the
12602 ;; manifest is computed.
12603 (add-after 'unpack 'record-references
12604 (lambda* (#:key inputs #:allow-other-keys)
12605 (mkdir-p "jar/lib")
12606 (let ((dirs (filter-map (match-lambda
12608 (if (and (string-prefix? "java-" name)
12609 (not (string=? name "java-testng")))
12612 (for-each (lambda (jar)
12613 (symlink jar (string-append "jar/lib/" (basename jar))))
12614 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12617 ;; There is no installation target
12619 (lambda* (#:key inputs outputs #:allow-other-keys)
12620 (let* ((out (assoc-ref outputs "out"))
12621 (bin (string-append out "/bin"))
12622 (share (string-append out "/share/java/"))
12623 (lib (string-append share "/lib/"))
12624 (scripts (list "BAMTagHistogram"
12625 "BAMTagofTagCounts"
12626 "BaseDistributionAtReadPosition"
12627 "CollapseBarcodesInPlace"
12628 "CollapseTagWithContext"
12630 "CreateIntervalsFiles"
12631 "DetectBeadSynthesisErrors"
12632 "DigitalExpression"
12633 "Drop-seq_alignment.sh"
12636 "GatherGeneGCLength"
12637 "GatherMolecularBarcodeDistributionByGene"
12638 "GatherReadQualityMetrics"
12641 "SelectCellsByNumTranscripts"
12642 "SingleCellRnaSeqMetricsCollector"
12643 "TagBamWithReadSequenceExtended"
12644 "TagReadWithGeneExon"
12645 "TagReadWithInterval"
12646 "TrimStartingSequence"
12647 "ValidateReference")))
12648 (for-each mkdir-p (list bin share lib))
12649 (install-file "dist/dropseq.jar" share)
12650 (for-each (lambda (script)
12651 (chmod script #o555)
12652 (install-file script bin))
12654 (substitute* (map (lambda (script)
12655 (string-append bin "/" script))
12657 (("^java") (which "java"))
12658 (("jar_deploy_dir=.*")
12659 (string-append "jar_deploy_dir=" share "\n"))))
12661 ;; FIXME: We do this after stripping jars because we don't want it to
12662 ;; copy all these jars and strip them. We only want to install
12663 ;; links. Arguably, this is a problem with the ant-build-system.
12664 (add-after 'strip-jar-timestamps 'install-links
12665 (lambda* (#:key outputs #:allow-other-keys)
12666 (let* ((out (assoc-ref outputs "out"))
12667 (share (string-append out "/share/java/"))
12668 (lib (string-append share "/lib/")))
12669 (for-each (lambda (jar)
12670 (symlink (readlink jar)
12671 (string-append lib (basename jar))))
12672 (find-files "jar/lib" "\\.jar$")))
12675 `(("jdk" ,icedtea-8)
12676 ("java-picard" ,java-picard-2.10.3)
12677 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12678 ("java-commons-math3" ,java-commons-math3)
12679 ("java-commons-jexl2" ,java-commons-jexl-2)
12680 ("java-commons-collections4" ,java-commons-collections4)
12681 ("java-commons-lang2" ,java-commons-lang)
12682 ("java-commons-io" ,java-commons-io)
12683 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12684 ("java-guava" ,java-guava)
12685 ("java-la4j" ,java-la4j)
12686 ("java-biojava-core" ,java-biojava-core-4.0)
12687 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12688 ("java-jdistlib" ,java-jdistlib)
12689 ("java-simple-xml" ,java-simple-xml)
12690 ("java-snakeyaml" ,java-snakeyaml)))
12693 ("java-testng" ,java-testng)))
12694 (home-page "http://mccarrolllab.com/dropseq/")
12695 (synopsis "Tools for Drop-seq analyses")
12696 (description "Drop-seq is a technology to enable biologists to
12697 analyze RNA expression genome-wide in thousands of individual cells at
12698 once. This package provides tools to perform Drop-seq analyses.")
12699 (license license:expat)))
12701 (define-public pigx-rnaseq
12703 (name "pigx-rnaseq")
12707 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12708 "releases/download/v" version
12709 "/pigx_rnaseq-" version ".tar.gz"))
12712 "0z3hr120wk2vrlmlpz1vp3n9wy3rq4y2mnzh2vf08qgqn2xfdwcw"))))
12713 (build-system gnu-build-system)
12715 `(#:parallel-tests? #f ; not supported
12717 (modify-phases %standard-phases
12718 ;; "test.sh" runs STAR, which requires excessive amounts of memory.
12719 (add-after 'unpack 'disable-resource-intensive-test
12721 (substitute* "Makefile.in"
12722 (("(^ tests/test_trim_galore/test.sh).*" _ m) m)
12723 (("^ tests/test_multiqc/test.sh") "")
12724 (("^ test.sh") ""))
12727 `(("coreutils" ,coreutils)
12730 ("snakemake" ,snakemake)
12732 ("multiqc" ,multiqc)
12734 ("trim-galore" ,trim-galore)
12736 ("samtools" ,samtools)
12737 ("r-minimal" ,r-minimal)
12738 ("r-rmarkdown" ,r-rmarkdown)
12739 ("r-ggplot2" ,r-ggplot2)
12740 ("r-ggrepel" ,r-ggrepel)
12741 ("r-gprofiler" ,r-gprofiler)
12742 ("r-deseq2" ,r-deseq2)
12744 ("r-knitr" ,r-knitr)
12745 ("r-pheatmap" ,r-pheatmap)
12746 ("r-corrplot" ,r-corrplot)
12747 ("r-reshape2" ,r-reshape2)
12748 ("r-plotly" ,r-plotly)
12749 ("r-scales" ,r-scales)
12750 ("r-summarizedexperiment" ,r-summarizedexperiment)
12751 ("r-crosstalk" ,r-crosstalk)
12752 ("r-tximport" ,r-tximport)
12753 ("r-rtracklayer" ,r-rtracklayer)
12754 ("r-rjson" ,r-rjson)
12756 ("ghc-pandoc" ,ghc-pandoc)
12757 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12758 ("python-wrapper" ,python-wrapper)
12759 ("python-pyyaml" ,python-pyyaml)))
12760 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12761 (synopsis "Analysis pipeline for RNA sequencing experiments")
12762 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
12763 reporting for RNA sequencing experiments. It is easy to use and produces high
12764 quality reports. The inputs are reads files from the sequencing experiment,
12765 and a configuration file which describes the experiment. In addition to
12766 quality control of the experiment, the pipeline produces a differential
12767 expression report comparing samples in an easily configurable manner.")
12768 (license license:gpl3+)))
12770 (define-public pigx-chipseq
12772 (name "pigx-chipseq")
12776 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
12777 "releases/download/v" version
12778 "/pigx_chipseq-" version ".tar.gz"))
12781 "0xbvgqpk32a8iczhvac56cacr46rdkqb0allhhpvmj940idf72bi"))))
12782 (build-system gnu-build-system)
12783 ;; parts of the tests rely on access to the network
12784 (arguments '(#:tests? #f))
12787 ("coreutils" ,coreutils)
12788 ("r-minimal" ,r-minimal)
12789 ("r-argparser" ,r-argparser)
12790 ("r-biocparallel" ,r-biocparallel)
12791 ("r-biostrings" ,r-biostrings)
12792 ("r-chipseq" ,r-chipseq)
12793 ("r-data-table" ,r-data-table)
12794 ("r-dplyr" ,r-dplyr)
12795 ("r-genomation" ,r-genomation)
12796 ("r-genomicalignments" ,r-genomicalignments)
12797 ("r-genomicranges" ,r-genomicranges)
12798 ("r-rsamtools" ,r-rsamtools)
12799 ("r-rtracklayer" ,r-rtracklayer)
12800 ("r-s4vectors" ,r-s4vectors)
12801 ("r-stringr" ,r-stringr)
12802 ("r-tibble" ,r-tibble)
12803 ("r-tidyr" ,r-tidyr)
12804 ("r-jsonlite" ,r-jsonlite)
12805 ("r-heatmaply" ,r-heatmaply)
12806 ("r-htmlwidgets" ,r-htmlwidgets)
12807 ("r-ggplot2" ,r-ggplot2)
12808 ("r-plotly" ,r-plotly)
12809 ("r-rmarkdown" ,r-rmarkdown)
12810 ("python-wrapper" ,python-wrapper)
12811 ("python-pyyaml" ,python-pyyaml)
12812 ("python-magic" ,python-magic)
12813 ("python-xlrd" ,python-xlrd)
12814 ("trim-galore" ,trim-galore)
12816 ("multiqc" ,multiqc)
12818 ("ghc-pandoc" ,ghc-pandoc)
12819 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12823 ("snakemake" ,snakemake)
12824 ("samtools" ,samtools)
12825 ("bedtools" ,bedtools)
12826 ("kentutils" ,kentutils)))
12828 `(("python-pytest" ,python-pytest)))
12829 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12830 (synopsis "Analysis pipeline for ChIP sequencing experiments")
12831 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
12832 calling and reporting for ChIP sequencing experiments. It is easy to use and
12833 produces high quality reports. The inputs are reads files from the sequencing
12834 experiment, and a configuration file which describes the experiment. In
12835 addition to quality control of the experiment, the pipeline enables to set up
12836 multiple peak calling analysis and allows the generation of a UCSC track hub
12837 in an easily configurable manner.")
12838 (license license:gpl3+)))
12840 (define-public pigx-bsseq
12842 (name "pigx-bsseq")
12846 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
12847 "releases/download/v" version
12848 "/pigx_bsseq-" version ".tar.gz"))
12851 "0l97wvkq4diq8lcarraj33bby1zzf0w804jwi8mlc5qddp8idwhy"))))
12852 (build-system gnu-build-system)
12855 (modify-phases %standard-phases
12856 (add-before 'check 'set-timezone
12857 ;; The readr package is picky about timezones.
12858 (lambda* (#:key inputs #:allow-other-keys)
12859 (setenv "TZ" "UTC+1")
12861 (string-append (assoc-ref inputs "tzdata")
12862 "/share/zoneinfo"))
12865 `(("tzdata" ,tzdata)))
12867 `(("coreutils" ,coreutils)
12870 ("r-minimal" ,r-minimal)
12871 ("r-annotationhub" ,r-annotationhub)
12873 ("r-genomation" ,r-genomation)
12874 ("r-methylkit" ,r-methylkit)
12875 ("r-rtracklayer" ,r-rtracklayer)
12876 ("r-rmarkdown" ,r-rmarkdown)
12877 ("r-bookdown" ,r-bookdown)
12878 ("r-ggplot2" ,r-ggplot2)
12879 ("r-ggbio" ,r-ggbio)
12880 ("ghc-pandoc" ,ghc-pandoc)
12881 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12882 ("python-wrapper" ,python-wrapper)
12883 ("python-pyyaml" ,python-pyyaml)
12884 ("snakemake" ,snakemake)
12885 ("bismark" ,bismark)
12888 ("trim-galore" ,trim-galore)
12889 ("cutadapt" ,cutadapt)
12890 ("samtools" ,samtools)))
12891 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12892 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
12893 (description "PiGx BSseq is a data processing pipeline for raw fastq read
12894 data of bisulfite experiments; it produces reports on aggregate methylation
12895 and coverage and can be used to produce information on differential
12896 methylation and segmentation.")
12897 (license license:gpl3+)))
12899 (define-public pigx-scrnaseq
12901 (name "pigx-scrnaseq")
12905 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/"
12906 "releases/download/v" version
12907 "/pigx_scrnaseq-" version ".tar.gz"))
12910 "1d5l3gywypi67yz9advxq5xkgfhr4733gj0bwnngm723i3hdf5w9"))))
12911 (build-system gnu-build-system)
12913 `(("coreutils" ,coreutils)
12916 ("flexbar" ,flexbar)
12917 ("java" ,icedtea-8)
12918 ("jellyfish" ,jellyfish)
12919 ("python-wrapper" ,python-wrapper)
12920 ("python-pyyaml" ,python-pyyaml)
12921 ("python-pandas" ,python-pandas)
12922 ("python-magic" ,python-magic)
12923 ("python-numpy" ,python-numpy)
12924 ("python-loompy" ,python-loompy)
12925 ("ghc-pandoc" ,ghc-pandoc)
12926 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12927 ("samtools" ,samtools)
12928 ("snakemake" ,snakemake)
12930 ("r-minimal" ,r-minimal)
12931 ("r-argparser" ,r-argparser)
12932 ("r-cowplot" ,r-cowplot)
12933 ("r-data-table" ,r-data-table)
12934 ("r-delayedarray" ,r-delayedarray)
12935 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
12936 ("r-dplyr" ,r-dplyr)
12937 ("r-dropbead" ,r-dropbead)
12939 ("r-genomicalignments" ,r-genomicalignments)
12940 ("r-genomicfiles" ,r-genomicfiles)
12941 ("r-genomicranges" ,r-genomicranges)
12942 ("r-ggplot2" ,r-ggplot2)
12943 ("r-hdf5array" ,r-hdf5array)
12944 ("r-pheatmap" ,r-pheatmap)
12945 ("r-rmarkdown" ,r-rmarkdown)
12946 ("r-rsamtools" ,r-rsamtools)
12947 ("r-rtracklayer" ,r-rtracklayer)
12948 ("r-rtsne" ,r-rtsne)
12949 ("r-scater" ,r-scater)
12950 ("r-scran" ,r-scran)
12951 ("r-seurat" ,r-seurat)
12952 ("r-singlecellexperiment" ,r-singlecellexperiment)
12953 ("r-stringr" ,r-stringr)
12954 ("r-yaml" ,r-yaml)))
12955 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12956 (synopsis "Analysis pipeline for single-cell RNA sequencing experiments")
12957 (description "PiGX scRNAseq is an analysis pipeline for preprocessing and
12958 quality control for single cell RNA sequencing experiments. The inputs are
12959 read files from the sequencing experiment, and a configuration file which
12960 describes the experiment. It produces processed files for downstream analysis
12961 and interactive quality reports. The pipeline is designed to work with UMI
12963 (license license:gpl3+)))
12965 (define-public pigx
12971 (uri (string-append "https://github.com/BIMSBbioinfo/pigx/"
12972 "releases/download/v" version
12973 "/pigx-" version ".tar.gz"))
12976 "1i5njdy1clj5ncw45d16p7mwmqvb1ilikl9n797pxklc3f4s7mq7"))))
12977 (build-system gnu-build-system)
12979 `(("python" ,python)
12980 ("pigx-bsseq" ,pigx-bsseq)
12981 ("pigx-chipseq" ,pigx-chipseq)
12982 ("pigx-rnaseq" ,pigx-rnaseq)
12983 ("pigx-scrnaseq" ,pigx-scrnaseq)))
12984 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12985 (synopsis "Analysis pipelines for genomics")
12986 (description "PiGx is a collection of genomics pipelines. It includes the
12987 following pipelines:
12990 @item PiGx BSseq for raw fastq read data of bisulfite experiments
12991 @item PiGx RNAseq for RNAseq samples
12992 @item PiGx scRNAseq for single cell dropseq analysis
12993 @item PiGx ChIPseq for reads from ChIPseq experiments
12996 All pipelines are easily configured with a simple sample sheet and a
12997 descriptive settings file. The result is a set of comprehensive, interactive
12998 HTML reports with interesting findings about your samples.")
12999 (license license:gpl3+)))
13001 (define-public genrich
13007 (uri (git-reference
13008 (url "https://github.com/jsh58/Genrich.git")
13009 (commit (string-append "v" version))))
13010 (file-name (git-file-name name version))
13013 "0x0q6z0208n3cxzqjla4rgjqpyqgwpmz27852lcvzkzaigymq4zp"))))
13014 (build-system gnu-build-system)
13016 `(#:tests? #f ; there are none
13018 (modify-phases %standard-phases
13019 (delete 'configure)
13021 (lambda* (#:key outputs #:allow-other-keys)
13022 (install-file "Genrich" (string-append (assoc-ref outputs "out") "/bin"))
13026 (home-page "https://github.com/jsh58/Genrich")
13027 (synopsis "Detecting sites of genomic enrichment")
13028 (description "Genrich is a peak-caller for genomic enrichment
13029 assays (e.g. ChIP-seq, ATAC-seq). It analyzes alignment files generated
13030 following the assay and produces a file detailing peaks of significant
13032 (license license:expat)))
13034 (define-public mantis
13035 (let ((commit "4ffd171632c2cb0056a86d709dfd2bf21bc69b84")
13039 (version (git-version "0" revision commit))
13042 (uri (git-reference
13043 (url "https://github.com/splatlab/mantis.git")
13045 (file-name (git-file-name name version))
13048 "0iqbr0dhmlc8mzpirmm2s4pkzkwdgrcx50yx6cv3wlr2qi064p55"))))
13049 (build-system cmake-build-system)
13050 (arguments '(#:tests? #f)) ; there are none
13052 `(("sdsl-lite" ,sdsl-lite)
13053 ("openssl" ,openssl)
13055 (home-page "https://github.com/splatlab/mantis")
13056 (synopsis "Large-scale sequence-search index data structure")
13057 (description "Mantis is a space-efficient data structure that can be
13058 used to index thousands of raw-read genomics experiments and facilitate
13059 large-scale sequence searches on those experiments. Mantis uses counting
13060 quotient filters instead of Bloom filters, enabling rapid index builds and
13061 queries, small indexes, and exact results, i.e., no false positives or
13062 negatives. Furthermore, Mantis is also a colored de Bruijn graph
13063 representation, so it supports fast graph traversal and other topological
13064 analyses in addition to large-scale sequence-level searches.")
13065 ;; uses __uint128_t and inline assembly
13066 (supported-systems '("x86_64-linux"))
13067 (license license:bsd-3))))
13069 (define-public r-diversitree
13071 (name "r-diversitree")
13076 (uri (cran-uri "diversitree" version))
13079 "00vi4klywi35hd170ksjv3xja3hqqbkcidcnrrlpgv4179k0azix"))))
13080 (build-system r-build-system)
13082 `(("gfortran" ,gfortran)))
13083 (inputs `(("fftw" ,fftw) ("gsl" ,gsl)))
13086 ("r-desolve" ,r-desolve)
13088 ("r-subplex" ,r-subplex)))
13089 (home-page "https://www.zoology.ubc.ca/prog/diversitree")
13090 (synopsis "Comparative 'phylogenetic' analyses of diversification")
13091 (description "This package contains a number of comparative \"phylogenetic\"
13092 methods, mostly focusing on analysing diversification and character evolution.
13093 Contains implementations of \"BiSSE\" (Binary State Speciation and Extinction)
13094 and its unresolved tree extensions, \"MuSSE\" (Multiple State Speciation and
13095 Extinction), \"QuaSSE\", \"GeoSSE\", and \"BiSSE-ness\" Other included methods
13096 include Markov models of discrete and continuous trait evolution and constant
13097 rate speciation and extinction.")
13098 (license license:gpl2+)))
13100 (define-public sjcount
13101 ;; There is no tag for version 3.2, nor is there a release archive.
13102 (let ((commit "292d3917cadb3f6834c81e509c30e61cd7ead6e5")
13106 (version (git-version "3.2" revision commit))
13109 (uri (git-reference
13110 (url "https://github.com/pervouchine/sjcount-full.git")
13112 (file-name (string-append name "-" version "-checkout"))
13115 "0gdgj35j249f04rqgq8ymcc1xg1vi9kzbajnjqpaq2wpbh8bl234"))))
13116 (build-system gnu-build-system)
13118 `(#:tests? #f ; requires a 1.4G test file
13120 (list (string-append "SAMTOOLS_DIR="
13121 (assoc-ref %build-inputs "samtools")
13124 (modify-phases %standard-phases
13125 (replace 'configure
13126 (lambda* (#:key inputs #:allow-other-keys)
13127 (substitute* "makefile"
13128 (("-I \\$\\{SAMTOOLS_DIR\\}")
13129 (string-append "-I" (assoc-ref inputs "samtools")
13130 "/include/samtools"))
13131 (("-lz ") "-lz -lpthread "))
13134 (lambda* (#:key outputs #:allow-other-keys)
13135 (for-each (lambda (tool)
13137 (string-append (assoc-ref outputs "out")
13139 '("j_count" "b_count" "sjcount"))
13142 `(("samtools" ,samtools-0.1)
13144 (home-page "https://github.com/pervouchine/sjcount-full/")
13145 (synopsis "Annotation-agnostic splice junction counting pipeline")
13146 (description "Sjcount is a utility for fast quantification of splice
13147 junctions in RNA-seq data. It is annotation-agnostic and offset-aware. This
13148 version does count multisplits.")
13149 (license license:gpl3+))))
13151 (define-public minimap2
13158 (uri (string-append "https://github.com/lh3/minimap2/"
13159 "releases/download/v" version "/"
13160 "minimap2-" version ".tar.bz2"))
13163 "080w9066irkbhbyr4nmf19pzkdd2s4v31hpzlajgq2y0drr6zcsj"))))
13164 (build-system gnu-build-system)
13166 `(#:tests? #f ; there are none
13169 (let ((system ,(or (%current-target-system)
13170 (%current-system))))
13172 ((string-prefix? "x86_64" system)
13174 ((or (string-prefix? "armhf" system)
13175 (string-prefix? "aarch64" system))
13177 (else "sse2only=1"))))
13179 (modify-phases %standard-phases
13180 (delete 'configure)
13182 (lambda* (#:key outputs #:allow-other-keys)
13183 (let* ((out (assoc-ref outputs "out"))
13184 (bin (string-append out "/bin"))
13185 (man (string-append out "/share/man/man1")))
13186 (install-file "minimap2" bin)
13188 (install-file "minimap2.1" man))
13192 (home-page "https://lh3.github.io/minimap2/")
13193 (synopsis "Pairwise aligner for genomic and spliced nucleotide sequences")
13194 (description "Minimap2 is a versatile sequence alignment program that
13195 aligns DNA or mRNA sequences against a large reference database. Typical use
13199 @item mapping PacBio or Oxford Nanopore genomic reads to the human genome;
13200 @item finding overlaps between long reads with error rate up to ~15%;
13201 @item splice-aware alignment of PacBio Iso-Seq or Nanopore cDNA or Direct RNA
13202 reads against a reference genome;
13203 @item aligning Illumina single- or paired-end reads;
13204 @item assembly-to-assembly alignment;
13205 @item full-genome alignment between two closely related species with
13206 divergence below ~15%.
13208 (license license:expat)))
13210 (define-public r-circus
13217 (uri (git-reference
13218 (url "https://github.com/BIMSBbioinfo/ciRcus.git")
13219 (commit (string-append "v" version))))
13220 (file-name (git-file-name name version))
13223 "0jhjn3ilb057hbf6yzrihj13ifxxs32y7nkby8l3lkm28dg4p97h"))))
13224 (build-system r-build-system)
13226 `(("r-annotationdbi" ,r-annotationdbi)
13227 ("r-annotationhub" ,r-annotationhub)
13228 ("r-biomart" ,r-biomart)
13229 ("r-data-table" ,r-data-table)
13231 ("r-genomicfeatures" ,r-genomicfeatures)
13232 ("r-genomicranges" ,r-genomicranges)
13233 ("r-ggplot2" ,r-ggplot2)
13235 ("r-iranges" ,r-iranges)
13236 ("r-rcolorbrewer" ,r-rcolorbrewer)
13237 ("r-rmysql" ,r-rmysql)
13238 ("r-s4vectors" ,r-s4vectors)
13239 ("r-stringr" ,r-stringr)
13240 ("r-summarizedexperiment" ,r-summarizedexperiment)))
13242 `(("r-knitr" ,r-knitr)))
13243 (home-page "https://github.com/BIMSBbioinfo/ciRcus")
13244 (synopsis "Annotation, analysis and visualization of circRNA data")
13245 (description "Circus is an R package for annotation, analysis and
13246 visualization of circRNA data. Users can annotate their circRNA candidates
13247 with host genes, gene featrues they are spliced from, and discriminate between
13248 known and yet unknown splice junctions. Circular-to-linear ratios of circRNAs
13249 can be calculated, and a number of descriptive plots easily generated.")
13250 (license license:artistic2.0)))
13252 (define-public gffread
13253 ;; We cannot use the tagged release because it is not in sync with gclib.
13254 ;; See https://github.com/gpertea/gffread/issues/26
13255 (let ((commit "ba7535fcb3cea55a6e5a491d916e93b454e87fd0")
13259 (version (git-version "0.9.12" revision commit))
13263 (uri (git-reference
13264 (url "https://github.com/gpertea/gffread.git")
13266 (file-name (git-file-name name version))
13269 "1dl2nbcg96lxpd0drg48ssa8343nf7pw9s9mkrc4mjjmfwsin3ki"))))
13270 (build-system gnu-build-system)
13272 `(#:tests? #f ; no check target
13274 (list "GCLDIR=gclib")
13276 (modify-phases %standard-phases
13277 (delete 'configure)
13278 (add-after 'unpack 'copy-gclib-source
13279 (lambda* (#:key inputs #:allow-other-keys)
13281 (copy-recursively (assoc-ref inputs "gclib-source") "gclib")
13283 ;; There is no install target
13285 (lambda* (#:key outputs #:allow-other-keys)
13286 (let* ((out (assoc-ref outputs "out"))
13287 (bin (string-append out "/bin")))
13288 (install-file "gffread" bin))
13292 ,(let ((version "0.10.3")
13293 (commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13297 (uri (git-reference
13298 (url "https://github.com/gpertea/gclib.git")
13300 (file-name (git-file-name "gclib" version))
13303 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13304 (home-page "https://github.com/gpertea/gffread/")
13305 (synopsis "Parse and convert GFF/GTF files")
13307 "This package provides a GFF/GTF file parsing utility providing format
13308 conversions, region filtering, FASTA sequence extraction and more.")
13309 ;; gffread is under Expat, but gclib is under Artistic 2.0
13310 (license (list license:expat
13311 license:artistic2.0)))))
13313 (define-public find-circ
13314 ;; The last release was in 2015. The license was clarified in 2017, so we
13315 ;; take the latest commit.
13316 (let ((commit "8655dca54970fcf7e92e22fbf57e1188724dda7d")
13320 (version (git-version "1.2" revision commit))
13324 (uri (git-reference
13325 (url "https://github.com/marvin-jens/find_circ.git")
13327 (file-name (git-file-name name version))
13330 "0p77pbqbclqr4srms34y1b9b4njybfpjiknc11ki84f3p8skb3cg"))))
13331 (build-system gnu-build-system)
13333 `(#:tests? #f ; there are none
13335 ;; There is no actual build system.
13336 (modify-phases %standard-phases
13337 (delete 'configure)
13340 (lambda* (#:key outputs #:allow-other-keys)
13341 (let* ((out (assoc-ref outputs "out"))
13342 (bin (string-append out "/bin"))
13343 (path (getenv "PYTHONPATH")))
13344 (for-each (lambda (script)
13345 (install-file script bin)
13346 (wrap-program (string-append bin "/" script)
13347 `("PYTHONPATH" ":" prefix (,path))))
13352 "unmapped2anchors.py")))
13355 `(("python2" ,python-2)
13356 ("python2-pysam" ,python2-pysam)
13357 ("python2-numpy" ,python2-numpy)))
13358 (home-page "https://github.com/marvin-jens/find_circ")
13359 (synopsis "circRNA detection from RNA-seq reads")
13360 (description "This package provides tools to detect head-to-tail
13361 spliced (back-spliced) sequencing reads, indicative of circular RNA (circRNA)
13363 (license license:gpl3))))
13365 (define-public python-scanpy
13367 (name "python-scanpy")
13368 (version "1.4.5.1")
13372 (uri (pypi-uri "scanpy" version))
13375 "14kh1ji70xxhmri5q8sgcibsidhr6f221wxrcw8a5xvibj5da17j"))))
13376 (build-system python-build-system)
13379 (modify-phases %standard-phases
13381 (lambda* (#:key inputs #:allow-other-keys)
13382 ;; These tests require Internet access.
13383 (delete-file-recursively "scanpy/tests/notebooks")
13384 (delete-file "scanpy/tests/test_clustering.py")
13386 ;; TODO: I can't get the plotting tests to work, even with Xvfb.
13387 (delete-file "scanpy/tests/test_plotting.py")
13388 (delete-file "scanpy/tests/test_preprocessing.py")
13389 (delete-file "scanpy/tests/test_read_10x.py")
13391 (setenv "PYTHONPATH"
13392 (string-append (getcwd) ":"
13393 (getenv "PYTHONPATH")))
13397 `(("python-anndata" ,python-anndata)
13398 ("python-h5py" ,python-h5py)
13399 ("python-igraph" ,python-igraph)
13400 ("python-joblib" ,python-joblib)
13401 ("python-louvain" ,python-louvain)
13402 ("python-legacy-api-wrap" ,python-legacy-api-wrap)
13403 ("python-matplotlib" ,python-matplotlib)
13404 ("python-natsort" ,python-natsort)
13405 ("python-networkx" ,python-networkx)
13406 ("python-numba" ,python-numba)
13407 ("python-packaging" ,python-packaging)
13408 ("python-pandas" ,python-pandas)
13409 ("python-patsy" ,python-patsy)
13410 ("python-scikit-learn" ,python-scikit-learn)
13411 ("python-scipy" ,python-scipy)
13412 ("python-seaborn" ,python-seaborn)
13413 ("python-statsmodels" ,python-statsmodels)
13414 ("python-tables" ,python-tables)
13415 ("python-umap-learn" ,python-umap-learn)))
13417 `(("python-pytest" ,python-pytest)
13418 ("python-setuptools-scm" ,python-setuptools-scm)))
13419 (home-page "https://github.com/theislab/scanpy")
13420 (synopsis "Single-Cell Analysis in Python.")
13421 (description "Scanpy is a scalable toolkit for analyzing single-cell gene
13422 expression data. It includes preprocessing, visualization, clustering,
13423 pseudotime and trajectory inference and differential expression testing. The
13424 Python-based implementation efficiently deals with datasets of more than one
13426 (license license:bsd-3)))
13428 (define-public python-bbknn
13430 (name "python-bbknn")
13435 (uri (pypi-uri "bbknn" version))
13438 "1jbsh01f57zj4bhvjr3jh4532zznqd6nccmgrl3qi9gnhkf7c4y0"))))
13439 (build-system python-build-system)
13441 `(#:tests? #f)) ; TODO: Enable after migration to scikit-learn.
13443 `(("python-annoy" ,python-annoy)
13444 ("python-cython" ,python-cython)
13445 ("python-numpy" ,python-numpy)
13446 ("python-scipy" ,python-scipy)
13447 ("python-umap-learn" ,python-umap-learn)))
13448 (home-page "https://github.com/Teichlab/bbknn")
13449 (synopsis "Batch balanced KNN")
13450 (description "BBKNN is a batch effect removal tool that can be directly
13451 used in the Scanpy workflow. It serves as an alternative to
13452 @code{scanpy.api.pp.neighbors()}, with both functions creating a neighbour
13453 graph for subsequent use in clustering, pseudotime and UMAP visualisation. If
13454 technical artifacts are present in the data, they will make it challenging to
13455 link corresponding cell types across different batches. BBKNN actively
13456 combats this effect by splitting your data into batches and finding a smaller
13457 number of neighbours for each cell within each of the groups. This helps
13458 create connections between analogous cells in different batches without
13459 altering the counts or PCA space.")
13460 (license license:expat)))
13462 (define-public gffcompare
13463 (let ((commit "be56ef4349ea3966c12c6397f85e49e047361c41")
13466 (name "gffcompare")
13467 (version (git-version "0.10.15" revision commit))
13471 (uri (git-reference
13472 (url "https://github.com/gpertea/gffcompare/")
13474 (file-name (git-file-name name version))
13476 (base32 "0cp5qpxdhw4mxpya5dld8wi3jk00zyklm6rcri426wydinrnfmkg"))))
13477 (build-system gnu-build-system)
13479 `(#:tests? #f ; no check target
13481 (modify-phases %standard-phases
13482 (delete 'configure)
13483 (add-before 'build 'copy-gclib-source
13484 (lambda* (#:key inputs #:allow-other-keys)
13487 (assoc-ref inputs "gclib-source") "../gclib")
13490 (lambda* (#:key outputs #:allow-other-keys)
13491 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
13492 (install-file "gffcompare" bin)
13495 `(("gclib-source" ; see 'README.md' of gffcompare
13496 ,(let ((commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13499 (version (git-version "0.10.3" revision commit)))
13502 (uri (git-reference
13503 (url "https://github.com/gpertea/gclib/")
13505 (file-name (git-file-name name version))
13507 (base32 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13508 (home-page "https://github.com/gpertea/gffcompare/")
13509 (synopsis "Tool for comparing or classifing transcripts of RNA-Seq")
13511 "@code{gffcompare} is a tool that can:
13513 @item compare and evaluate the accuracy of RNA-Seq transcript assemblers
13514 (Cufflinks, Stringtie);
13515 @item collapse (merge) duplicate transcripts from multiple GTF/GFF3 files (e.g.
13516 resulted from assembly of different samples);
13517 @item classify transcripts from one or multiple GTF/GFF3 files as they relate to
13518 reference transcripts provided in a annotation file (also in GTF/GFF3 format).
13522 license:expat ;license for gffcompare
13523 license:artistic2.0))))) ;license for gclib
13525 (define-public intervaltree
13526 (let ((commit "b90527f9e6d51cd36ecbb50429e4524d3a418ea5"))
13528 (name "intervaltree")
13529 (version (git-version "0.0.0" "1" commit))
13533 (uri (git-reference
13534 (url "https://github.com/ekg/intervaltree/")
13536 (file-name (git-file-name name version))
13538 (base32 "0rgv6q5fl4x5d74n6p5wvdna6zmbdbqpb4jqqh6vq3670gn08xad"))))
13539 (build-system gnu-build-system)
13541 '(#:tests? #f ; No tests.
13542 #:make-flags (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
13545 (modify-phases %standard-phases
13546 (delete 'configure)))) ; There is no configure phase.
13547 (home-page "https://github.com/ekg/intervaltree")
13548 (synopsis "Minimal C++ interval tree implementation")
13549 (description "An interval tree can be used to efficiently find a set of
13550 numeric intervals overlapping or containing another interval. This library
13551 provides a basic implementation of an interval tree using C++ templates,
13552 allowing the insertion of arbitrary types into the tree.")
13553 (license license:expat))))
13555 (define-public python-intervaltree
13557 (name "python-intervaltree")
13562 (uri (pypi-uri "intervaltree" version))
13565 "0wz234g6irlm4hivs2qzmnywk0ss06ckagwh15nflkyb3p462kyb"))))
13566 (build-system python-build-system)
13569 (modify-phases %standard-phases
13570 ;; pytest seems to have a check to make sure the user is testing
13571 ;; their checked-out code and not an installed, potentially
13572 ;; out-of-date copy. This is harmless here, since we just installed
13573 ;; the package, so we disable the check to avoid skipping tests
13575 (add-before 'check 'import-mismatch-error-workaround
13577 (setenv "PY_IGNORE_IMPORTMISMATCH" "1")
13580 `(("python-sortedcontainers" ,python-sortedcontainers)))
13582 `(("python-pytest" ,python-pytest)))
13583 (home-page "https://github.com/chaimleib/intervaltree")
13584 (synopsis "Editable interval tree data structure")
13586 "This package provides a mutable, self-balancing interval tree
13587 implementation for Python. Queries may be by point, by range overlap, or by
13588 range envelopment. This library was designed to allow tagging text and time
13589 intervals, where the intervals include the lower bound but not the upper
13591 (license license:asl2.0)))
13593 (define-public python-pypairix
13595 (name "python-pypairix")
13600 (uri (pypi-uri "pypairix" version))
13603 "0zs92b74s5v4xy2h16s15f3z6l4nnbw8x8zyif7xx5xpafjn0xss"))))
13604 (build-system python-build-system)
13605 ;; FIXME: the tests fail because test.support cannot be loaded:
13606 ;; ImportError: cannot import name 'support'
13607 (arguments '(#:tests? #f))
13610 (home-page "https://github.com/4dn-dcic/pairix")
13611 (synopsis "Support for querying pairix-indexed bgzipped text files")
13613 "Pypairix is a Python module for fast querying on a pairix-indexed
13614 bgzipped text file that contains a pair of genomic coordinates per line.")
13615 (license license:expat)))
13617 (define-public python-pyfaidx
13619 (name "python-pyfaidx")
13624 (uri (pypi-uri "pyfaidx" version))
13627 "038xi3a6zvrxbyyfpp64ka8pcjgsdq4fgw9cl5lpxbvmm1bzzw2q"))))
13628 (build-system python-build-system)
13630 `(("python-six" ,python-six)))
13631 (home-page "http://mattshirley.com")
13632 (synopsis "Random access to fasta subsequences")
13634 "This package provides procedures for efficient pythonic random access to
13635 fasta subsequences.")
13636 (license license:bsd-3)))
13638 (define-public python2-pyfaidx
13639 (package-with-python2 python-pyfaidx))
13641 (define-public python-cooler
13643 (name "python-cooler")
13648 (uri (pypi-uri "cooler" version))
13651 "01g6gqix9ba27sappz6nfyiwabzrlf8i5fn8kwcz8ra356cq9crp"))))
13652 (build-system python-build-system)
13654 `(("python-asciitree" ,python-asciitree)
13655 ("python-biopython" ,python-biopython)
13656 ("python-click" ,python-click)
13657 ("python-cytoolz" ,python-cytoolz)
13658 ("python-dask" ,python-dask)
13659 ("python-h5py" ,python-h5py)
13660 ("python-multiprocess" ,python-multiprocess)
13661 ("python-numpy" ,python-numpy)
13662 ("python-pandas" ,python-pandas)
13663 ("python-pyfaidx" ,python-pyfaidx)
13664 ("python-pypairix" ,python-pypairix)
13665 ("python-pysam" ,python-pysam)
13666 ("python-pyyaml" ,python-pyyaml)
13667 ("python-scipy" ,python-scipy)
13668 ("python-simplejson" ,python-simplejson)))
13670 `(("python-mock" ,python-mock)
13671 ("python-pytest" ,python-pytest)))
13672 (home-page "https://github.com/mirnylab/cooler")
13673 (synopsis "Sparse binary format for genomic interaction matrices")
13675 "Cooler is a support library for a sparse, compressed, binary persistent
13676 storage format, called @code{cool}, used to store genomic interaction data,
13677 such as Hi-C contact matrices.")
13678 (license license:bsd-3)))
13680 (define-public python-hicmatrix
13682 (name "python-hicmatrix")
13686 ;; Version 12 is not available on pypi.
13688 (uri (git-reference
13689 (url "https://github.com/deeptools/HiCMatrix.git")
13691 (file-name (git-file-name name version))
13694 "1xhdyx16f3brgxgxybixdi64ki8nbbkq5vk4h9ahi11pzpjfn1pj"))))
13695 (build-system python-build-system)
13698 (modify-phases %standard-phases
13699 (add-after 'unpack 'relax-requirements
13701 (substitute* '("requirements.txt"
13703 (("cooler *=+ *0.8.5")
13707 `(("python-cooler" ,python-cooler)
13708 ("python-intervaltree" ,python-intervaltree)
13709 ("python-numpy" ,python-numpy)
13710 ("python-pandas" ,python-pandas)
13711 ("python-scipy" ,python-scipy)
13712 ("python-tables" ,python-tables)))
13713 (home-page "https://github.com/deeptools/HiCMatrix/")
13714 (synopsis "HiCMatrix class for HiCExplorer and pyGenomeTracks")
13716 "This helper package implements the @code{HiCMatrix} class for
13717 the HiCExplorer and pyGenomeTracks packages.")
13718 (license license:gpl3+)))
13720 (define-public python-hicexplorer
13722 (name "python-hicexplorer")
13726 ;; The latest version is not available on Pypi.
13728 (uri (git-reference
13729 (url "https://github.com/deeptools/HiCExplorer.git")
13731 (file-name (git-file-name name version))
13734 "0q5gpbzmrkvygqgw524q36b4nrivcmyi5v194vsx0qw7b3gcmq08"))))
13735 (build-system python-build-system)
13738 (modify-phases %standard-phases
13739 (add-after 'unpack 'loosen-up-requirements
13741 (substitute* "setup.py"
13745 `(("python-biopython" ,python-biopython)
13746 ("python-configparser" ,python-configparser)
13747 ("python-cooler" ,python-cooler)
13748 ("python-future" ,python-future)
13749 ("python-intervaltree" ,python-intervaltree)
13750 ("python-jinja2" ,python-jinja2)
13751 ("python-matplotlib" ,python-matplotlib)
13752 ("python-numpy" ,python-numpy)
13753 ("python-pandas" ,python-pandas)
13754 ("python-pybigwig" ,python-pybigwig)
13755 ("python-pysam" ,python-pysam)
13756 ("python-scipy" ,python-scipy)
13757 ("python-six" ,python-six)
13758 ("python-tables" ,python-tables)
13759 ("python-unidecode" ,python-unidecode)))
13760 (home-page "https://hicexplorer.readthedocs.io")
13761 (synopsis "Process, analyze and visualize Hi-C data")
13763 "HiCExplorer is a powerful and easy to use set of tools to process,
13764 normalize and visualize Hi-C data. HiCExplorer facilitates the creation of
13765 contact matrices, correction of contacts, TAD detection, A/B compartments,
13766 merging, reordering or chromosomes, conversion from different formats
13767 including cooler and detection of long-range contacts. Moreover, it allows
13768 the visualization of multiple contact matrices along with other types of data
13769 like genes, compartments, ChIP-seq coverage tracks (and in general any type of
13770 genomic scores), long range contacts and the visualization of viewpoints.")
13771 (license license:gpl3)))
13773 (define-public python-pygenometracks
13775 (name "python-pygenometracks")
13780 (uri (pypi-uri "pyGenomeTracks" version))
13783 "16laa0wnf4qn9fb9ych4w1vqhqwjss70v0y0f6wp4gwqfrlgac0f"))))
13784 (build-system python-build-system)
13786 `(#:tests? #f ; there are none
13788 (modify-phases %standard-phases
13789 (add-after 'unpack 'relax-requirements
13791 (substitute* "setup.py"
13792 (("matplotlib ==3.1.1")
13793 "matplotlib >=3.1.1"))
13796 `(("python-future" ,python-future)
13797 ("python-gffutils" ,python-gffutils)
13798 ("python-hicmatrix" ,python-hicmatrix)
13799 ("python-intervaltree" ,python-intervaltree)
13800 ("python-matplotlib" ,python-matplotlib)
13801 ("python-numpy" ,python-numpy)
13802 ("python-pybigwig" ,python-pybigwig)
13803 ("python-pysam" ,python-pysam)
13804 ("python-tqdm" ,python-tqdm)))
13806 `(("python-pytest" ,python-pytest)))
13807 (home-page "https://pygenometracks.readthedocs.io")
13808 (synopsis "Program and library to plot beautiful genome browser tracks")
13810 "This package aims to produce high-quality genome browser tracks that
13811 are highly customizable. Currently, it is possible to plot: bigwig, bed (many
13812 options), bedgraph, links (represented as arcs), and Hi-C matrices.
13813 pyGenomeTracks can make plots with or without Hi-C data.")
13814 (license license:gpl3+)))
13816 (define-public python-hic2cool
13818 (name "python-hic2cool")
13823 (uri (pypi-uri "hic2cool" version))
13826 "0xy6mhfns2lzib1kcr6419jjp6pmh0qx8z8na55lmiwn0ds8q9cl"))))
13827 (build-system python-build-system)
13828 (arguments '(#:tests? #f)) ; no tests included
13830 `(("python-cooler" ,python-cooler)))
13831 (home-page "https://github.com/4dn-dcic/hic2cool")
13832 (synopsis "Converter for .hic and .cool files")
13834 "This package provides a converter between @code{.hic} files (from
13835 juicer) and single-resolution or multi-resolution @code{.cool} files (for
13836 cooler). Both @code{hic} and @code{cool} files describe Hi-C contact
13838 (license license:expat)))
13840 (define-public r-pore
13848 (string-append "mirror://sourceforge/rpore/" version
13849 "/poRe_" version ".tar.gz"))
13851 (base32 "0pih9nljbv8g4x8rkk29i7aqq681b782r5s5ynp4nw9yzqnmmksv"))))
13852 (properties `((upstream-name . "poRe")))
13853 (build-system r-build-system)
13855 `(("r-bit64" ,r-bit64)
13856 ("r-data-table" ,r-data-table)
13857 ("r-rhdf5" ,r-rhdf5)
13858 ("r-shiny" ,r-shiny)
13859 ("r-svdialogs" ,r-svdialogs)))
13860 (home-page "https://sourceforge.net/projects/rpore/")
13861 (synopsis "Visualize Nanopore sequencing data")
13863 "This package provides graphical user interfaces to organize and visualize Nanopore
13865 ;; This is free software but the license variant is unclear:
13866 ;; <https://github.com/mw55309/poRe_docs/issues/10>.
13867 (license license:bsd-3)))
13869 (define-public r-xbioc
13870 (let ((revision "1")
13871 (commit "6ff0670a37ab3036aaf1d94aa4b208310946b0b5"))
13874 (version (git-version "0.1.16" revision commit))
13877 (uri (git-reference
13878 (url "https://github.com/renozao/xbioc.git")
13880 (file-name (git-file-name name version))
13883 "0w8bsq5myiwkfhh83nm6is5ichiyvwa1axx2szvxnzq39x6knf66"))))
13884 (build-system r-build-system)
13886 `(("r-annotationdbi" ,r-annotationdbi)
13887 ("r-assertthat" ,r-assertthat)
13888 ("r-biobase" ,r-biobase)
13889 ("r-biocmanager" ,r-biocmanager)
13890 ("r-digest" ,r-digest)
13891 ("r-pkgmaker" ,r-pkgmaker)
13893 ("r-reshape2" ,r-reshape2)
13894 ("r-stringr" ,r-stringr)))
13895 (home-page "https://github.com/renozao/xbioc/")
13896 (synopsis "Extra base functions for Bioconductor")
13897 (description "This package provides extra utility functions to perform
13898 common tasks in the analysis of omics data, leveraging and enhancing features
13899 provided by Bioconductor packages.")
13900 (license license:gpl3+))))
13902 (define-public r-cssam
13903 (let ((revision "1")
13904 (commit "9ec58c982fa551af0d80b1a266890d92954833f2"))
13907 (version (git-version "1.4" revision commit))
13910 (uri (git-reference
13911 (url "https://github.com/shenorrLab/csSAM.git")
13913 (file-name (git-file-name name version))
13916 "128syf9v39gk0z3ip000qpsjbg6l1siyq6c8b0hz41dzg5achyb3"))))
13917 (build-system r-build-system)
13919 `(("r-formula" ,r-formula)
13920 ("r-ggplot2" ,r-ggplot2)
13921 ("r-pkgmaker" ,r-pkgmaker)
13923 ("r-rngtools" ,r-rngtools)
13924 ("r-scales" ,r-scales)))
13925 (home-page "https://github.com/shenorrLab/csSAM/")
13926 (synopsis "Cell type-specific statistical analysis of microarray")
13927 (description "This package implements the method csSAM that computes
13928 cell-specific differential expression from measured cell proportions using
13931 (license license:lgpl2.1+))))
13933 (define-public r-bseqsc
13934 (let ((revision "1")
13935 (commit "fef3f3e38dcf3df37103348b5780937982b43b98"))
13938 (version (git-version "1.0" revision commit))
13941 (uri (git-reference
13942 (url "https://github.com/shenorrLab/bseqsc.git")
13944 (file-name (git-file-name name version))
13947 "1prw13wa20f7wlc3gkkls66n1kxz8d28qrb8icfqdwdnnv8w5qg8"))))
13948 (build-system r-build-system)
13950 `(("r-abind" ,r-abind)
13951 ("r-annotationdbi" ,r-annotationdbi)
13952 ("r-biobase" ,r-biobase)
13953 ("r-cssam" ,r-cssam)
13954 ("r-dplyr" ,r-dplyr)
13955 ("r-e1071" ,r-e1071)
13956 ("r-edger" ,r-edger)
13957 ("r-ggplot2" ,r-ggplot2)
13959 ("r-openxlsx" ,r-openxlsx)
13960 ("r-pkgmaker" ,r-pkgmaker)
13962 ("r-preprocesscore" ,r-preprocesscore)
13963 ("r-rngtools" ,r-rngtools)
13964 ("r-scales" ,r-scales)
13965 ("r-stringr" ,r-stringr)
13966 ("r-xbioc" ,r-xbioc)))
13967 (home-page "https://github.com/shenorrLab/bseqsc")
13968 (synopsis "Deconvolution of bulk sequencing experiments using single cell data")
13969 (description "BSeq-sc is a bioinformatics analysis pipeline that
13970 leverages single-cell sequencing data to estimate cell type proportion and
13971 cell type-specific gene expression differences from RNA-seq data from bulk
13972 tissue samples. This is a companion package to the publication \"A
13973 single-cell transcriptomic map of the human and mouse pancreas reveals inter-
13974 and intra-cell population structure.\" Baron et al. Cell Systems (2016)
13975 @url{https://www.ncbi.nlm.nih.gov/pubmed/27667365}.")
13976 (license license:gpl2+))))
13978 (define-public porechop
13979 ;; The recommended way to install is to clone the git repository
13980 ;; https://github.com/rrwick/Porechop#installation
13981 (let ((commit "289d5dca4a5fc327f97b3f8cecb68ecaf1014861")
13985 (version (git-version "0.2.3" revision commit))
13989 (uri (git-reference
13990 (url "https://github.com/rrwick/Porechop.git")
13992 (file-name (git-file-name name version))
13994 (base32 "05ps43gig0d3ia9x5lj84lb00hbsl6ba9n7y7jz927npxbr2ym23"))))
13995 (build-system python-build-system)
13996 (home-page "https://github.com/rrwick/porechop")
13997 (synopsis "Finding, trimming or splitting adapters, in Oxford Nanopore reads")
13999 "The porechop package is a tool for finding and removing adapters from Oxford
14000 Nanopore reads. Adapters on the ends of reads are trimmed off, and when a read
14001 has an adapter in its middle, it is treated as chimeric and chopped into
14002 separate reads. Porechop performs thorough alignments to effectively find
14003 adapters, even at low sequence identity. Porechop also supports demultiplexing
14004 of Nanopore reads that were barcoded with the Native Barcoding Kit, PCR
14005 Barcoding Kit or Rapid Barcoding Kit.")
14006 (license license:gpl3+))))
14008 (define-public poretools
14009 ;; The latest release was in 2016 and the latest commit is from 2017
14010 ;; the recommended way to install is to clone the git repository
14011 ;; https://poretools.readthedocs.io/en/latest/content/installation.html
14012 (let ((commit "e426b1f09e86ac259a00c261c79df91510777407")
14016 (version (git-version "0.6.0" revision commit))
14020 (uri (git-reference
14021 (url "https://github.com/arq5x/poretools.git")
14023 (file-name (git-file-name name version))
14025 (base32 "0bglj833wxpp3cq430p1d3xp085ls221js2y90w7ir2x5ay8l7am"))))
14026 (build-system python-build-system)
14027 ;; requires python >=2.7, <3.0, and the same for python dependencies
14028 (arguments `(#:python ,python-2))
14032 `(("python-dateutil" ,python2-dateutil)
14033 ("python-h5py" ,python2-h5py)
14034 ("python-matplotlib" ,python2-matplotlib)
14035 ("python-pandas" ,python2-pandas)
14036 ("python-seaborn" ,python2-seaborn)))
14037 (home-page "https://poretools.readthedocs.io")
14038 (synopsis "Toolkit for working with nanopore sequencing data")
14040 "The MinION from Oxford Nanopore Technologies is a nanopore sequencer.
14041 This @code{poretools} package is a flexible toolkit for exploring datasets
14042 generated by nanopore sequencing devices for the purposes of quality control and
14043 downstream analysis. Poretools operates directly on the native FAST5, a variant
14044 of the Hierarchical Data Format (HDF5) standard.")
14045 (license license:expat))))
14047 (define-public r-absfiltergsea
14049 (name "r-absfiltergsea")
14054 (uri (cran-uri "AbsFilterGSEA" version))
14056 (base32 "15srxkxsvn38kd5frdrwfdf0ad8gskrd0h01wmdf9hglq8fjrp7w"))))
14057 (properties `((upstream-name . "AbsFilterGSEA")))
14058 (build-system r-build-system)
14060 `(("r-biobase" ,r-biobase)
14061 ("r-deseq" ,r-deseq)
14062 ("r-limma" ,r-limma)
14064 ("r-rcpparmadillo" ,r-rcpparmadillo)))
14065 (home-page "https://cran.r-project.org/web/packages/AbsFilterGSEA/")
14066 (synopsis "Improved false positive control of gene-permuting with absolute filtering")
14068 "This package provides a function that performs gene-permuting of a gene-set
14069 enrichment analysis (GSEA) calculation with or without the absolute filtering.
14070 Without filtering, users can perform (original) two-tailed or one-tailed
14072 (license license:gpl2)))
14074 (define-public jamm
14077 (version "1.0.7.6")
14081 (uri (git-reference
14082 (url "https://github.com/mahmoudibrahim/JAMM.git")
14083 (commit (string-append "JAMMv" version))))
14084 (file-name (git-file-name name version))
14087 "0bsa5mf9n9q5jz7mmacrra41l7r8rac5vgsn6wv1fb52ya58b970"))))
14088 (build-system gnu-build-system)
14090 `(#:tests? #f ; there are none
14092 (modify-phases %standard-phases
14093 (delete 'configure)
14096 (lambda* (#:key inputs outputs #:allow-other-keys)
14097 (let* ((out (assoc-ref outputs "out"))
14098 (libexec (string-append out "/libexec/jamm"))
14099 (bin (string-append out "/bin")))
14100 (substitute* '("JAMM.sh"
14101 "SignalGenerator.sh")
14103 (string-append "sPath=\"" libexec "\"\n")))
14104 (for-each (lambda (file)
14105 (install-file file libexec))
14106 (list "bincalculator.r"
14118 (chmod script #o555)
14119 (install-file script bin)
14120 (wrap-program (string-append bin "/" script)
14121 `("PATH" ":" prefix
14122 (,(string-append (assoc-ref inputs "coreutils") "/bin")
14123 ,(string-append (assoc-ref inputs "gawk") "/bin")
14124 ,(string-append (assoc-ref inputs "perl") "/bin")
14125 ,(string-append (assoc-ref inputs "r-minimal") "/bin")))
14126 `("PERL5LIB" ":" prefix (,(getenv "PERL5LIB")))
14127 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
14128 (list "JAMM.sh" "SignalGenerator.sh")))
14132 ("coreutils" ,coreutils)
14135 ("r-minimal" ,r-minimal)
14136 ;;("r-parallel" ,r-parallel)
14137 ("r-signal" ,r-signal)
14138 ("r-mclust" ,r-mclust)))
14139 (home-page "https://github.com/mahmoudibrahim/JAMM")
14140 (synopsis "Peak finder for NGS datasets")
14142 "JAMM is a peak finder for next generation sequencing datasets (ChIP-Seq,
14143 ATAC-Seq, DNase-Seq, etc.) that can integrate replicates and assign peak
14144 boundaries accurately. JAMM is applicable to both broad and narrow
14146 (license license:gpl3+)))
14148 (define-public ngless
14155 (uri (git-reference
14156 (url "https://gitlab.com/ngless/ngless.git")
14157 (commit (string-append "v" version))))
14158 (file-name (git-file-name name version))
14161 "1wim8wpqyff080dfcazynrmjwqas38m24m0v350w245mmhrapdma"))))
14162 (build-system haskell-build-system)
14164 `(#:haddock? #f ; The haddock phase fails with: NGLess/CmdArgs.hs:20:1:
14165 ; error: parse error on input import
14166 ; import Options.Applicative
14168 (modify-phases %standard-phases
14169 (add-after 'unpack 'create-Versions.hs
14171 (substitute* "Makefile"
14172 (("BWA_VERSION = .*")
14173 (string-append "BWA_VERSION = "
14174 ,(package-version bwa) "\n"))
14175 (("SAM_VERSION = .*")
14176 (string-append "SAM_VERSION = "
14177 ,(package-version samtools) "\n"))
14178 (("PRODIGAL_VERSION = .*")
14179 (string-append "PRODIGAL_VERSION = "
14180 ,(package-version prodigal) "\n"))
14181 (("MINIMAP2_VERSION = .*")
14182 (string-append "MINIMAP2_VERSION = "
14183 ,(package-version minimap2) "\n")))
14184 (invoke "make" "NGLess/Dependencies/Versions.hs")
14186 (add-after 'create-Versions.hs 'create-cabal-file
14187 (lambda _ (invoke "hpack") #t))
14188 ;; These tools are expected to be installed alongside ngless.
14189 (add-after 'install 'link-tools
14190 (lambda* (#:key inputs outputs #:allow-other-keys)
14191 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
14192 (symlink (string-append (assoc-ref inputs "prodigal")
14194 (string-append bin "ngless-" ,version "-prodigal"))
14195 (symlink (string-append (assoc-ref inputs "minimap2")
14197 (string-append bin "ngless-" ,version "-minimap2"))
14198 (symlink (string-append (assoc-ref inputs "samtools")
14200 (string-append bin "ngless-" ,version "-samtools"))
14201 (symlink (string-append (assoc-ref inputs "bwa")
14203 (string-append bin "ngless-" ,version "-bwa"))
14206 `(("prodigal" ,prodigal)
14208 ("samtools" ,samtools)
14209 ("minimap2" ,minimap2)
14210 ("ghc-aeson" ,ghc-aeson)
14211 ("ghc-ansi-terminal" ,ghc-ansi-terminal)
14212 ("ghc-async" ,ghc-async)
14213 ("ghc-atomic-write" ,ghc-atomic-write)
14214 ("ghc-bytestring-lexing" ,ghc-bytestring-lexing)
14215 ("ghc-conduit" ,ghc-conduit)
14216 ("ghc-conduit-algorithms" ,ghc-conduit-algorithms)
14217 ("ghc-conduit-extra" ,ghc-conduit-extra)
14218 ("ghc-configurator" ,ghc-configurator)
14219 ("ghc-convertible" ,ghc-convertible)
14220 ("ghc-data-default" ,ghc-data-default)
14221 ("ghc-diagrams-core" ,ghc-diagrams-core)
14222 ("ghc-diagrams-lib" ,ghc-diagrams-lib)
14223 ("ghc-diagrams-svg" ,ghc-diagrams-svg)
14224 ("ghc-double-conversion" ,ghc-double-conversion)
14225 ("ghc-edit-distance" ,ghc-edit-distance)
14226 ("ghc-either" ,ghc-either)
14227 ("ghc-errors" ,ghc-errors)
14228 ("ghc-extra" ,ghc-extra)
14229 ("ghc-filemanip" ,ghc-filemanip)
14230 ("ghc-file-embed" ,ghc-file-embed)
14231 ("ghc-gitrev" ,ghc-gitrev)
14232 ("ghc-hashtables" ,ghc-hashtables)
14233 ("ghc-http-conduit" ,ghc-http-conduit)
14234 ("ghc-inline-c" ,ghc-inline-c)
14235 ("ghc-inline-c-cpp" ,ghc-inline-c-cpp)
14236 ("ghc-intervalmap" ,ghc-intervalmap)
14237 ("ghc-missingh" ,ghc-missingh)
14238 ("ghc-optparse-applicative" ,ghc-optparse-applicative)
14239 ("ghc-regex" ,ghc-regex)
14240 ("ghc-safe" ,ghc-safe)
14241 ("ghc-safeio" ,ghc-safeio)
14242 ("ghc-strict" ,ghc-strict)
14243 ("ghc-tar" ,ghc-tar)
14244 ("ghc-tar-conduit" ,ghc-tar-conduit)
14245 ("ghc-unliftio" ,ghc-unliftio)
14246 ("ghc-unliftio-core" ,ghc-unliftio-core)
14247 ("ghc-vector" ,ghc-vector)
14248 ("ghc-yaml" ,ghc-yaml)
14249 ("ghc-zlib" ,ghc-zlib)))
14252 ("r-hdf5r" ,r-hdf5r)
14253 ("r-iterators" ,r-iterators)
14254 ("r-itertools" ,r-itertools)
14255 ("r-matrix" ,r-matrix)))
14257 `(("ghc-hpack" ,ghc-hpack)
14258 ("ghc-quickcheck" ,ghc-quickcheck)
14259 ("ghc-test-framework" ,ghc-test-framework)
14260 ("ghc-test-framework-hunit",ghc-test-framework-hunit)
14261 ("ghc-test-framework-quickcheck2" ,ghc-test-framework-quickcheck2)
14262 ("ghc-test-framework-th" ,ghc-test-framework-th)))
14263 (home-page "https://gitlab.com/ngless/ngless")
14264 (synopsis "DSL for processing next-generation sequencing data")
14265 (description "Ngless is a domain-specific language for
14266 @dfn{next-generation sequencing} (NGS) data processing.")
14267 (license license:expat)))
14269 (define-public filtlong
14270 ;; The recommended way to install is to clone the git repository
14271 ;; https://github.com/rrwick/Filtlong#installation
14272 ;; and the lastest release is more than nine months old
14273 (let ((commit "d1bb46dfe8bc7efe6257b5ce222c04bfe8aedaab")
14277 (version (git-version "0.2.0" revision commit))
14281 (uri (git-reference
14282 (url "https://github.com/rrwick/Filtlong.git")
14284 (file-name (git-file-name name version))
14286 (base32 "1xr92r820x8qlkcr3b57iw223yq8vjgyi42jr79w2xgw47qzr575"))))
14287 (build-system gnu-build-system)
14289 `(#:tests? #f ; no check target
14291 (modify-phases %standard-phases
14292 (delete 'configure)
14294 (lambda* (#:key outputs #:allow-other-keys)
14295 (let* ((out (assoc-ref outputs "out"))
14296 (bin (string-append out "/bin"))
14297 (scripts (string-append out "/share/filtlong/scripts")))
14298 (install-file "bin/filtlong" bin)
14299 (install-file "scripts/histogram.py" scripts)
14300 (install-file "scripts/read_info_histograms.sh" scripts))
14302 (add-after 'install 'wrap-program
14303 (lambda* (#:key inputs outputs #:allow-other-keys)
14304 (let* ((out (assoc-ref outputs "out"))
14305 (path (getenv "PYTHONPATH")))
14306 (wrap-program (string-append out
14307 "/share/filtlong/scripts/histogram.py")
14308 `("PYTHONPATH" ":" prefix (,path))))
14310 (add-before 'check 'patch-tests
14312 (substitute* "scripts/read_info_histograms.sh"
14313 (("awk") (which "gawk")))
14316 `(("gawk" ,gawk) ;for read_info_histograms.sh
14317 ("python" ,python-2) ;required for histogram.py
14319 (home-page "https://github.com/rrwick/Filtlong/")
14320 (synopsis "Tool for quality filtering of Nanopore and PacBio data")
14322 "The Filtlong package is a tool for filtering long reads by quality.
14323 It can take a set of long reads and produce a smaller, better subset. It uses
14324 both read length (longer is better) and read identity (higher is better) when
14325 choosing which reads pass the filter.")
14326 (license (list license:gpl3 ;filtlong
14327 license:asl2.0))))) ;histogram.py
14329 (define-public nanopolish
14330 ;; The recommended way to install is to clone the git repository
14331 ;; <https://github.com/jts/nanopolish#installing-a-particular-release>.
14332 ;; Also, the differences between release and current version seem to be
14334 (let ((commit "6331dc4f15b9dfabb954ba3fae9d76b6c3ca6377")
14337 (name "nanopolish")
14338 (version (git-version "0.11.1" revision commit))
14342 (uri (git-reference
14343 (url "https://github.com/jts/nanopolish.git")
14346 (file-name (git-file-name name version))
14348 (base32 "15ikl3d37y49pwd7vx36xksgsqajhf24q7qqsnpl15dqqyy5qgbc"))
14349 (modules '((guix build utils)))
14352 (delete-file-recursively "htslib")
14354 (build-system gnu-build-system)
14357 `("HDF5=noinstall" "EIGEN=noinstall" "HTS=noinstall" "CC=gcc")
14358 #:tests? #f ; no check target
14360 (modify-phases %standard-phases
14361 (add-after 'unpack 'find-eigen
14362 (lambda* (#:key inputs #:allow-other-keys)
14364 (string-append (assoc-ref inputs "eigen")
14366 (or (getenv "CPATH") "")))
14368 (delete 'configure)
14370 (lambda* (#:key outputs #:allow-other-keys)
14371 (let* ((out (assoc-ref outputs "out"))
14372 (bin (string-append out "/bin"))
14373 (scripts (string-append out "/share/nanopolish/scripts")))
14375 (install-file "nanopolish" bin)
14376 (for-each (lambda (file) (install-file file scripts))
14377 (find-files "scripts" ".*"))
14379 (add-after 'install 'wrap-programs
14380 (lambda* (#:key outputs #:allow-other-keys)
14381 (for-each (lambda (file)
14382 (wrap-program file `("PYTHONPATH" ":" prefix (,path))))
14383 (find-files "/share/nanopolish/scripts" "\\.py"))
14384 (for-each (lambda (file)
14385 (wrap-program file `("PERL5LIB" ":" prefix (,path))))
14386 (find-files "/share/nanopolish/scripts" "\\.pl"))
14393 ("python" ,python-wrapper)
14394 ("python-biopython" ,python-biopython)
14395 ("python-numpy" ,python-numpy)
14396 ("python-pysam" ,python-pysam)
14397 ("python-scikit-learn" , python-scikit-learn)
14398 ("python-scipy" ,python-scipy)
14400 (home-page "https://github.com/jts/nanopolish")
14401 (synopsis "Signal-level analysis of Oxford Nanopore sequencing data")
14403 "This package analyses the Oxford Nanopore sequencing data at signal-level.
14404 Nanopolish can calculate an improved consensus sequence for a draft genome
14405 assembly, detect base modifications, call SNPs (Single nucleotide
14406 polymorphisms) and indels with respect to a reference genome and more.")
14407 (license license:expat))))
14409 (define-public cnvkit
14416 (uri (git-reference
14417 (url "https://github.com/etal/cnvkit.git")
14418 (commit (string-append "v" version))))
14419 (file-name (git-file-name name version))
14421 (base32 "0g2f78k68yglmj4fsfmgs8idqv3di9aj53fg0ld0hqljg8chhh82"))))
14422 (build-system python-build-system)
14424 `(("python-biopython" ,python-biopython)
14425 ("python-future" ,python-future)
14426 ("python-matplotlib" ,python-matplotlib)
14427 ("python-numpy" ,python-numpy)
14428 ("python-reportlab" ,python-reportlab)
14429 ("python-pandas" ,python-pandas)
14430 ("python-pysam" ,python-pysam)
14431 ("python-pyfaidx" ,python-pyfaidx)
14432 ("python-scipy" ,python-scipy)
14434 ("r-dnacopy" ,r-dnacopy)))
14435 (home-page "https://cnvkit.readthedocs.org/")
14436 (synopsis "Copy number variant detection from targeted DNA sequencing")
14438 "CNVkit is a Python library and command-line software toolkit to infer
14439 and visualize copy number from high-throughput DNA sequencing data. It is
14440 designed for use with hybrid capture, including both whole-exome and custom
14441 target panels, and short-read sequencing platforms such as Illumina and Ion
14443 (license license:asl2.0)))
14445 (define-public python-pyfit-sne
14447 (name "python-pyfit-sne")
14452 (uri (git-reference
14453 (url "https://github.com/KlugerLab/pyFIt-SNE.git")
14455 (file-name (git-file-name name version))
14457 (base32 "13wh3qkzs56azmmgnxib6xfr29g7xh09sxylzjpni5j0pp0rc5qw"))))
14458 (build-system python-build-system)
14460 `(("python-numpy" ,python-numpy)))
14464 `(("python-cython" ,python-cython)))
14465 (home-page "https://github.com/KlugerLab/pyFIt-SNE")
14466 (synopsis "FFT-accelerated Interpolation-based t-SNE")
14468 "t-Stochastic Neighborhood Embedding (t-SNE) is a highly successful
14469 method for dimensionality reduction and visualization of high dimensional
14470 datasets. A popular implementation of t-SNE uses the Barnes-Hut algorithm to
14471 approximate the gradient at each iteration of gradient descent. This package
14472 is a Cython wrapper for FIt-SNE.")
14473 (license license:bsd-4)))
14475 (define-public bbmap
14481 (uri (string-append
14482 "mirror://sourceforge/bbmap/BBMap_" version ".tar.gz"))
14485 "1q4rfhxcb6z3gm8zg2davjz98w22lkf4hm9ikxz9kdl93pil3wkd"))))
14486 (build-system ant-build-system)
14488 `(#:build-target "dist"
14489 #:tests? #f ; there are none
14491 (list (string-append "-Dmpijar="
14492 (assoc-ref %build-inputs "java-openmpi")
14494 #:modules ((guix build ant-build-system)
14496 (guix build java-utils))
14498 (modify-phases %standard-phases
14499 (add-after 'build 'build-jni-library
14501 (with-directory-excursion "jni"
14502 (invoke "make" "-f" "makefile.linux"))))
14503 ;; There is no install target
14504 (replace 'install (install-jars "dist"))
14505 (add-after 'install 'install-scripts-and-documentation
14506 (lambda* (#:key outputs #:allow-other-keys)
14507 (substitute* "calcmem.sh"
14508 (("\\| awk ") (string-append "| " (which "awk") " ")))
14509 (let* ((scripts (find-files "." "\\.sh$"))
14510 (out (assoc-ref outputs "out"))
14511 (bin (string-append out "/bin"))
14512 (doc (string-append out "/share/doc/bbmap"))
14513 (jni (string-append out "/lib/jni")))
14514 (substitute* scripts
14515 (("\\$DIR\"\"docs") doc)
14517 (string-append "CP=" out "/share/java/BBTools.jar\n"))
14518 (("^NATIVELIBDIR.*")
14519 (string-append "NATIVELIBDIR=" jni "\n"))
14521 (string-append "CMD=\"" (which "java"))))
14522 (for-each (lambda (script) (install-file script bin)) scripts)
14524 ;; Install JNI library
14525 (install-file "jni/libbbtoolsjni.so" jni)
14527 ;; Install documentation
14528 (install-file "docs/readme.txt" doc)
14529 (copy-recursively "docs/guides" doc))
14534 ("java-eclipse-jdt-core" ,java-eclipse-jdt-core)
14535 ("java-eclipse-jdt-compiler-apt" ,java-eclipse-jdt-compiler-apt)
14536 ("java-openmpi" ,java-openmpi)))
14537 (home-page "http://sourceforge.net/projects/bbmap/")
14538 (synopsis "Aligner and other tools for short sequencing reads")
14540 "This package provides bioinformatic tools to align, deduplicate,
14541 reformat, filter and normalize DNA and RNA-seq data. It includes the
14542 following tools: BBMap, a short read aligner for DNA and RNA-seq data; BBNorm,
14543 a kmer-based error-correction and normalization tool; Dedupe, a tool to
14544 simplify assemblies by removing duplicate or contained subsequences that share
14545 a target percent identity; Reformat, to convert reads between
14546 fasta/fastq/scarf/fasta+qual/sam, interleaved/paired, and ASCII-33/64, at over
14547 500 MB/s; and BBDuk, a tool to filter, trim, or mask reads with kmer matches
14548 to an artifact/contaminant file.")
14549 (license license:bsd-3)))
14551 (define-public velvet
14557 (uri (string-append "https://www.ebi.ac.uk/~zerbino/velvet/"
14558 "velvet_" version ".tgz"))
14561 "0h3njwy66p6bx14r3ar1byb0ccaxmxka4c65rn4iybyiqa4d8kc8"))
14562 ;; Delete bundled libraries
14563 (modules '((guix build utils)))
14566 (delete-file "Manual.pdf")
14567 (delete-file-recursively "third-party")
14569 (build-system gnu-build-system)
14571 `(#:make-flags '("OPENMP=t")
14572 #:test-target "test"
14574 (modify-phases %standard-phases
14575 (delete 'configure)
14576 (add-after 'unpack 'fix-zlib-include
14578 (substitute* "src/binarySequences.c"
14579 (("../third-party/zlib-1.2.3/zlib.h") "zlib.h"))
14582 (lambda* (#:key outputs #:allow-other-keys)
14583 (let* ((out (assoc-ref outputs "out"))
14584 (bin (string-append out "/bin"))
14585 (doc (string-append out "/share/doc/velvet")))
14588 (install-file "velveth" bin)
14589 (install-file "velvetg" bin)
14590 (install-file "Manual.pdf" doc)
14591 (install-file "Columbus_manual.pdf" doc)
14594 `(("openmpi" ,openmpi)
14597 `(("texlive" ,(texlive-union (list texlive-latex-graphics
14598 texlive-latex-hyperref)))))
14599 (home-page "https://www.ebi.ac.uk/~zerbino/velvet/")
14600 (synopsis "Nucleic acid sequence assembler for very short reads")
14602 "Velvet is a de novo genomic assembler specially designed for short read
14603 sequencing technologies, such as Solexa or 454. Velvet currently takes in
14604 short read sequences, removes errors then produces high quality unique
14605 contigs. It then uses paired read information, if available, to retrieve the
14606 repeated areas between contigs.")
14607 (license license:gpl2+)))
14609 (define-public python-velocyto
14611 (name "python-velocyto")
14612 (version "0.17.17")
14616 (uri (pypi-uri "velocyto" version))
14619 "0fgygyzqgrq32dv6a00biq1p1cwi6kbl5iqblxq1kklj6b2mzmhs"))))
14620 (build-system python-build-system)
14622 `(("python-joblib" ,python-joblib)))
14624 `(("python-click" ,python-click)
14625 ("python-cython" ,python-cython)
14626 ("python-h5py" ,python-h5py)
14627 ("python-loompy" ,python-loompy)
14628 ("python-matplotlib" ,python-matplotlib)
14629 ("python-numba" ,python-numba)
14630 ("python-numpy" ,python-numpy)
14631 ("python-pandas" ,python-pandas)
14632 ("python-pysam" ,python-pysam)
14633 ("python-scikit-learn" ,python-scikit-learn)
14634 ("python-scipy" ,python-scipy)))
14635 (home-page "https://github.com/velocyto-team/velocyto.py")
14636 (synopsis "RNA velocity analysis for single cell RNA-seq data")
14638 "Velocyto is a library for the analysis of RNA velocity. Velocyto
14639 includes a command line tool and an analysis pipeline.")
14640 (license license:bsd-2)))
14642 (define-public arriba
14649 (uri (string-append "https://github.com/suhrig/arriba/releases/"
14650 "download/v" version "/arriba_v" version ".tar.gz"))
14653 "0jx9656ry766vb8z08m1c3im87b0c82qpnjby9wz4kcz8vn87dx2"))))
14654 (build-system gnu-build-system)
14656 `(#:tests? #f ; there are none
14658 (modify-phases %standard-phases
14659 (replace 'configure
14660 (lambda* (#:key inputs #:allow-other-keys)
14661 (let ((htslib (assoc-ref inputs "htslib")))
14662 (substitute* "Makefile"
14663 (("-I\\$\\(HTSLIB\\)/htslib")
14664 (string-append "-I" htslib "/include/htslib"))
14665 ((" \\$\\(HTSLIB\\)/libhts.a")
14666 (string-append " " htslib "/lib/libhts.so"))))
14667 (substitute* "run_arriba.sh"
14668 (("^STAR ") (string-append (which "STAR") " "))
14669 (("samtools --version-only")
14670 (string-append (which "samtools") " --version-only"))
14671 (("samtools index")
14672 (string-append (which "samtools") " index"))
14674 (string-append (which "samtools") " sort")))
14677 (lambda* (#:key outputs #:allow-other-keys)
14678 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
14679 (install-file "arriba" bin)
14680 (install-file "run_arriba.sh" bin)
14681 (install-file "draw_fusions.R" bin)
14682 (wrap-program (string-append bin "/draw_fusions.R")
14683 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
14686 `(("htslib" ,htslib)
14687 ("r-minimal" ,r-minimal)
14688 ("r-circlize" ,r-circlize)
14689 ("r-genomicalignments" ,r-genomicalignments)
14690 ("r-genomicranges" ,r-genomicranges)
14691 ("samtools" ,samtools)
14694 (home-page "https://github.com/suhrig/arriba")
14695 (synopsis "Gene fusion detection from RNA-Seq data ")
14697 "Arriba is a command-line tool for the detection of gene fusions from
14698 RNA-Seq data. It was developed for the use in a clinical research setting.
14699 Therefore, short runtimes and high sensitivity were important design criteria.
14700 It is based on the fast STAR aligner and the post-alignment runtime is
14701 typically just around two minutes. In contrast to many other fusion detection
14702 tools which build on STAR, Arriba does not require to reduce the
14703 @code{alignIntronMax} parameter of STAR to detect small deletions.")
14704 ;; All code is under the Expat license with the exception of
14705 ;; "draw_fusions.R", which is under GPLv3.
14706 (license (list license:expat license:gpl3))))
14708 (define-public adapterremoval
14710 (name "adapterremoval")
14715 (uri (git-reference
14716 (url "https://github.com/MikkelSchubert/adapterremoval.git")
14717 (commit (string-append "v" version))))
14718 (file-name (git-file-name name version))
14721 "1nf3ki5pfzalhrx2fr1y6pfqfi133yj2m7q4fj9irf5fb94bapwr"))))
14722 (build-system gnu-build-system)
14724 `(#:make-flags (list "COLOR_BUILD=no"
14725 (string-append "PREFIX="
14726 (assoc-ref %outputs "out")))
14727 #:test-target "test"
14729 (modify-phases %standard-phases
14730 (delete 'configure))))
14733 (home-page "https://adapterremoval.readthedocs.io/")
14734 (synopsis "Rapid sequence adapter trimming, identification, and read merging")
14736 "This program searches for and removes remnant adapter sequences from
14737 @dfn{High-Throughput Sequencing} (HTS) data and (optionally) trims low quality
14738 bases from the 3' end of reads following adapter removal. AdapterRemoval can
14739 analyze both single end and paired end data, and can be used to merge
14740 overlapping paired-ended reads into (longer) consensus sequences.
14741 Additionally, the AdapterRemoval may be used to recover a consensus adapter
14742 sequence for paired-ended data, for which this information is not available.")
14743 (license license:gpl3+)))
14745 (define-public pplacer
14746 (let ((commit "807f6f3"))
14749 ;; The commit should be updated with each version change.
14750 (version "1.1.alpha19")
14754 (uri (git-reference
14755 (url "https://github.com/matsen/pplacer.git")
14756 (commit (string-append "v" version))))
14757 (file-name (git-file-name name version))
14759 (base32 "11ppbbbx20p2g9wj3ff64dhnarb12q79v7qh4rk0gj6lkbz4n7cn"))))
14760 (build-system ocaml-build-system)
14762 `(#:modules ((guix build ocaml-build-system)
14766 (modify-phases %standard-phases
14767 (delete 'configure)
14768 (add-after 'unpack 'fix-build-with-latest-ocaml
14770 (substitute* "myocamlbuild.ml"
14771 (("dep \\[\"c_pam\"\\]" m)
14772 (string-append "flag [\"ocaml\"; \"compile\"] (A \"-unsafe-string\");\n"
14774 (("let run_and_read" m)
14779 let pos = String.index s ch in
14780 x := (String.before s pos)::!x;
14781 go (String.after s (pos + 1))
14784 with Not_found -> !x
14785 let split_nl s = split s '\\n'
14786 let before_space s =
14787 try String.before s (String.index s ' ')
14788 with Not_found -> s
14791 (("run_and_read \"ocamlfind list \\| cut -d' ' -f1\"" m)
14792 (string-append "List.map before_space (split_nl & " m ")"))
14793 ((" blank_sep_strings &") "")
14794 ((" Lexing.from_string &") ""))
14796 (add-after 'unpack 'replace-bundled-cddlib
14797 (lambda* (#:key inputs #:allow-other-keys)
14798 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
14799 (local-dir "cddlib_guix"))
14801 (with-directory-excursion local-dir
14802 (invoke "tar" "xvf" cddlib-src))
14803 (let ((cddlib-src-folder
14804 (string-append local-dir "/"
14805 (list-ref (scandir local-dir) 2)
14807 (for-each make-file-writable (find-files "cdd_src" ".*"))
14811 (string-append "cdd_src/" (basename file))))
14812 (find-files cddlib-src-folder ".*[ch]$")))
14814 (add-after 'unpack 'fix-makefile
14816 ;; Remove system calls to 'git'.
14817 (substitute* "Makefile"
14818 (("^DESCRIPT:=pplacer-.*")
14820 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
14821 (substitute* "myocamlbuild.ml"
14822 (("git describe --tags --long .*\\\" with")
14824 "echo -n v" ,version "-" ,commit "\" with")))
14827 (lambda* (#:key outputs #:allow-other-keys)
14828 (let* ((out (assoc-ref outputs "out"))
14829 (bin (string-append out "/bin")))
14830 (copy-recursively "bin" bin))
14832 #:ocaml ,ocaml-4.07
14833 #:findlib ,ocaml4.07-findlib))
14835 `(("zlib" ,zlib "static")
14837 ("ocaml-ounit" ,(package-with-ocaml4.07 ocaml-ounit))
14838 ("ocaml-batteries" ,(package-with-ocaml4.07 ocaml-batteries))
14839 ("ocaml-camlzip" ,(package-with-ocaml4.07 camlzip))
14840 ("ocaml-csv" ,(package-with-ocaml4.07 ocaml-csv))
14841 ("ocaml-sqlite3" ,ocaml4.07-sqlite3)
14842 ("ocaml-xmlm" ,(package-with-ocaml4.07 ocaml-xmlm))
14843 ("ocaml-mcl" ,(package-with-ocaml4.07 ocaml-mcl))
14844 ("ocaml-gsl" ,ocaml4.07-gsl-1)))
14846 `(("cddlib-src" ,(package-source cddlib))
14847 ("ocamlbuild" ,(package-with-ocaml4.07 ocamlbuild))
14848 ("pkg-config" ,pkg-config)))
14850 `(("pplacer-scripts" ,pplacer-scripts)))
14851 (synopsis "Phylogenetic placement of biological sequences")
14853 "Pplacer places query sequences on a fixed reference phylogenetic tree
14854 to maximize phylogenetic likelihood or posterior probability according to a
14855 reference alignment. Pplacer is designed to be fast, to give useful
14856 information about uncertainty, and to offer advanced visualization and
14857 downstream analysis.")
14858 (home-page "https://matsen.fhcrc.org/pplacer/")
14859 (license license:gpl3))))
14861 ;; This package is installed alongside 'pplacer'. It is a separate package so
14862 ;; that it can use the python-build-system for the scripts that are
14863 ;; distributed alongside the main OCaml binaries.
14864 (define pplacer-scripts
14867 (name "pplacer-scripts")
14868 (build-system python-build-system)
14870 `(#:python ,python-2
14872 (modify-phases %standard-phases
14873 (add-after 'unpack 'enter-scripts-dir
14874 (lambda _ (chdir "scripts") #t))
14876 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t))
14877 (add-after 'install 'wrap-executables
14878 (lambda* (#:key inputs outputs #:allow-other-keys)
14879 (let* ((out (assoc-ref outputs "out"))
14880 (bin (string-append out "/bin")))
14881 (let ((path (string-append
14882 (assoc-ref inputs "hmmer") "/bin:"
14883 (assoc-ref inputs "infernal") "/bin")))
14885 (wrap-program (string-append bin "/refpkg_align.py")
14886 `("PATH" ":" prefix (,path))))
14887 (let ((path (string-append
14888 (assoc-ref inputs "hmmer") "/bin")))
14889 (wrap-program (string-append bin "/hrefpkg_query.py")
14890 `("PATH" ":" prefix (,path)))))
14893 `(("infernal" ,infernal)
14896 `(("python-biopython" ,python2-biopython)
14897 ("taxtastic" ,taxtastic)))
14898 (synopsis "Pplacer Python scripts")))
14900 (define-public python2-checkm-genome
14902 (name "python2-checkm-genome")
14907 (uri (pypi-uri "checkm-genome" version))
14910 "0bm8gpxjmzxsxxl8lzwqhgx8g1dlnmp6znz7wv3hgb0gdjbf9dzz"))))
14911 (build-system python-build-system)
14913 `(#:python ,python-2
14914 #:tests? #f)) ; some tests are interactive
14916 `(("python-dendropy" ,python2-dendropy)
14917 ("python-matplotlib" ,python2-matplotlib)
14918 ("python-numpy" ,python2-numpy)
14919 ("python-pysam" ,python2-pysam)
14920 ("python-scipy" ,python2-scipy)))
14921 (home-page "https://pypi.org/project/Checkm/")
14922 (synopsis "Assess the quality of putative genome bins")
14924 "CheckM provides a set of tools for assessing the quality of genomes
14925 recovered from isolates, single cells, or metagenomes. It provides robust
14926 estimates of genome completeness and contamination by using collocated sets of
14927 genes that are ubiquitous and single-copy within a phylogenetic lineage.
14928 Assessment of genome quality can also be examined using plots depicting key
14929 genomic characteristics (e.g., GC, coding density) which highlight sequences
14930 outside the expected distributions of a typical genome. CheckM also provides
14931 tools for identifying genome bins that are likely candidates for merging based
14932 on marker set compatibility, similarity in genomic characteristics, and
14933 proximity within a reference genome.")
14934 (license license:gpl3+)))
14936 (define-public umi-tools
14943 (uri (pypi-uri "umi_tools" version))
14946 "08y3vz1vcx09whmbsn722lcs6jl9wyrh9i4p3k8j4cb1i32bij4a"))))
14947 (build-system python-build-system)
14949 `(("python-pandas" ,python-pandas)
14950 ("python-future" ,python-future)
14951 ("python-scipy" ,python-scipy)
14952 ("python-matplotlib" ,python-matplotlib)
14953 ("python-regex" ,python-regex)
14954 ("python-pysam" ,python-pysam)))
14956 `(("python-cython" ,python-cython)))
14957 (home-page "https://github.com/CGATOxford/UMI-tools")
14958 (synopsis "Tools for analyzing unique modular identifiers")
14959 (description "This package provides tools for dealing with @dfn{Unique
14960 Molecular Identifiers} (UMIs) and @dfn{Random Molecular Tags} (RMTs) in
14961 genetic sequences. There are six tools: the @code{extract} and
14962 @code{whitelist} commands are used to prepare a fastq containing UMIs @code{+/-}
14963 cell barcodes for alignment. The remaining commands, @code{group},
14964 @code{dedup}, and @{count}/@code{count_tab}, are used to identify PCR
14965 duplicates using the UMIs and perform different levels of analysis depending
14966 on the needs of the user.")
14967 (license license:expat)))
14969 (define-public ataqv
14976 (uri (git-reference
14977 (url "https://github.com/ParkerLab/ataqv.git")
14979 (file-name (git-file-name name version))
14982 "031xr6jx1aprh26y5b1lv3gzrlmzg4alfl73vvshymx8cq8asrqi"))))
14983 (build-system gnu-build-system)
14986 (list (string-append "prefix=" (assoc-ref %outputs "out"))
14987 (string-append "BOOST_ROOT="
14988 (assoc-ref %build-inputs "boost"))
14989 (string-append "HTSLIB_ROOT="
14990 (assoc-ref %build-inputs "htslib")))
14991 #:test-target "test"
14993 (modify-phases %standard-phases
14994 (delete 'configure))))
14998 ("ncurses" ,ncurses)
15002 (home-page "https://github.com/ParkerLab/ataqv")
15003 (synopsis "Toolkit for quality control and visualization of ATAC-seq data")
15004 (description "This package provides a toolkit for measuring and comparing
15005 ATAC-seq results. It was written to make it easier to spot differences that
15006 might be caused by ATAC-seq library prep or sequencing. The main program,
15007 @code{ataqv}, examines aligned reads and reports some basic metrics.")
15008 (license license:gpl3+)))
15010 (define-public r-psiplot
15017 (uri (git-reference
15018 (url "https://github.com/kcha/psiplot.git")
15019 (commit (string-append "v" version))))
15020 (file-name (git-file-name name version))
15022 (base32 "08438h16cfry5kqh3y9hs8q1b1a8bxhblsm75knviz5r6q0n1jxh"))))
15023 (build-system r-build-system)
15025 `(("r-mass" ,r-mass)
15026 ("r-dplyr" ,r-dplyr)
15027 ("r-tidyr" ,r-tidyr)
15028 ("r-purrr" ,r-purrr)
15029 ("r-readr" ,r-readr)
15030 ("r-magrittr" ,r-magrittr)
15031 ("r-ggplot2" ,r-ggplot2)))
15032 (home-page "https://github.com/kcha/psiplot")
15033 (synopsis "Plot percent spliced-in values of alternatively-spliced exons")
15035 "PSIplot is an R package for generating plots of @dfn{percent
15036 spliced-in} (PSI) values of alternatively-spliced exons that were computed by
15037 vast-tools, an RNA-Seq pipeline for alternative splicing analysis. The plots
15038 are generated using @code{ggplot2}.")
15039 (license license:expat)))
15041 (define-public python-ont-fast5-api
15043 (name "python-ont-fast5-api")
15048 (uri (git-reference
15049 (url "https://github.com/nanoporetech/ont_fast5_api.git")
15050 (commit (string-append "release_" version))))
15051 (file-name (git-file-name name version))
15054 "03cbq4zbbwhll8ml2m9k8sa31mirsvcbjkrq1yna0kkzz9fad5fm"))))
15055 (build-system python-build-system)
15057 `(("python-numpy" ,python-numpy)
15058 ("python-six" ,python-six)
15059 ("python-h5py" ,python-h5py)
15060 ("python-progressbar33" ,python-progressbar33)))
15061 (home-page "https://github.com/nanoporetech/ont_fast5_api")
15062 (synopsis "Interface to HDF5 files of the Oxford Nanopore fast5 file format")
15064 "This package provides a concrete implementation of the fast5 file schema
15065 using the generic @code{h5py} library, plain-named methods to interact with
15066 and reflect the fast5 file schema, and tools to convert between
15067 @code{multi_read} and @code{single_read} formats.")
15068 (license license:mpl2.0)))
15070 (define-public tbsp
15071 (let ((commit "ec8fff4410cfb13a677dbbb95cbbc60217e64907")
15075 (version (git-version "1.0.0" revision commit))
15079 (uri (git-reference
15080 (url "https://github.com/phoenixding/tbsp.git")
15082 (file-name (git-file-name name version))
15085 "025ym14x8gbd6hb55lsinqj6f5qzw36i10klgs7ldzxxd7s39ki1"))))
15086 (build-system python-build-system)
15087 (arguments '(#:tests? #f)) ; no tests included
15089 `(("python-matplotlib" ,python-matplotlib)
15090 ("python-networkx" ,python-networkx)
15091 ("python-numpy" ,python-numpy)
15092 ("python-pybigwig" ,python-pybigwig)
15093 ("python-biopython" ,python-biopython)
15094 ("python-scikit-learn" ,python-scikit-learn)
15095 ("python-scipy" ,python-scipy)))
15096 (home-page "https://github.com/phoenixding/tbsp/")
15097 (synopsis "SNP-based trajectory inference")
15099 "Several studies focus on the inference of developmental and response
15100 trajectories from single cell RNA-Seq (scRNA-Seq) data. A number of
15101 computational methods, often referred to as pseudo-time ordering, have been
15102 developed for this task. CRISPR has also been used to reconstruct lineage
15103 trees by inserting random mutations. The tbsp package implements an
15104 alternative method to detect significant, cell type specific sequence
15105 mutations from scRNA-Seq data.")
15106 (license license:expat))))
15108 (define-public tabixpp
15114 (uri (git-reference
15115 (url "https://github.com/ekg/tabixpp")
15116 (commit (string-append "v" version))))
15117 (file-name (git-file-name name version))
15119 (base32 "1k2a3vbq96ic4lw72iwp5s3mwwc4xhdffjj584yn6l9637q9j1yd"))
15120 (modules '((guix build utils)))
15123 (delete-file-recursively "htslib") #t))))
15124 (build-system gnu-build-system)
15126 `(("htslib" ,htslib)
15129 `(#:tests? #f ; There are no tests to run.
15131 (modify-phases %standard-phases
15132 (delete 'configure) ; There is no configure phase.
15133 ;; The build phase needs overriding the location of htslib.
15135 (lambda* (#:key inputs #:allow-other-keys)
15136 (let ((htslib-ref (assoc-ref inputs "htslib")))
15138 (string-append "HTS_LIB=" htslib-ref "/lib/libhts.a")
15139 (string-append "INCLUDES= -I" htslib-ref "/include/htslib")
15140 "HTS_HEADERS=" ; No need to check for headers here.
15141 (string-append "LIBPATH=-L. -L" htslib-ref "/include")))))
15143 (lambda* (#:key outputs #:allow-other-keys)
15144 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15145 (install-file "tabix++" bin))
15147 (home-page "https://github.com/ekg/tabixpp")
15148 (synopsis "C++ wrapper around tabix project")
15149 (description "This is a C++ wrapper around the Tabix project which abstracts
15150 some of the details of opening and jumping in tabix-indexed files.")
15151 (license license:expat)))
15153 (define-public smithwaterman
15154 (let ((commit "2610e259611ae4cde8f03c72499d28f03f6d38a7"))
15156 (name "smithwaterman")
15157 (version (git-version "0.0.0" "2" commit))
15160 (uri (git-reference
15161 (url "https://github.com/ekg/smithwaterman/")
15163 (file-name (git-file-name name version))
15165 (base32 "0i9d8zrxpiracw3mxzd9siybpy62p06rqz9mc2w93arajgbk45bs"))))
15166 (build-system gnu-build-system)
15168 `(#:tests? #f ; There are no tests to run.
15169 #:make-flags '("libsw.a" "all")
15171 (modify-phases %standard-phases
15172 (delete 'configure) ; There is no configure phase.
15174 (lambda* (#:key outputs #:allow-other-keys)
15175 (let* ((out (assoc-ref outputs "out"))
15176 (bin (string-append out "/bin"))
15177 (lib (string-append out "/lib")))
15178 (install-file "smithwaterman" bin)
15179 (install-file "libsw.a" lib))
15181 (home-page "https://github.com/ekg/smithwaterman")
15182 (synopsis "Implementation of the Smith-Waterman algorithm")
15183 (description "Implementation of the Smith-Waterman algorithm.")
15184 ;; The licensing terms are unclear: https://github.com/ekg/smithwaterman/issues/9.
15185 (license (list license:gpl2 license:expat)))))
15187 (define-public multichoose
15189 (name "multichoose")
15193 (uri (git-reference
15194 (url "https://github.com/ekg/multichoose/")
15195 (commit (string-append "v" version))))
15196 (file-name (git-file-name name version))
15198 (base32 "0ci5fqvmpamwgxvmyd79ygj6n3bnbl3vc7b6h1sxz58186sm3pfs"))))
15199 (build-system gnu-build-system)
15201 `(#:tests? #f ; Tests require node.
15203 (modify-phases %standard-phases
15204 (delete 'configure) ; There is no configure phase.
15206 (lambda* (#:key outputs #:allow-other-keys)
15207 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15208 ;; TODO: There are Python modules for these programs too.
15209 (install-file "multichoose" bin)
15210 (install-file "multipermute" bin))
15212 (home-page "https://github.com/ekg/multichoose")
15213 (synopsis "Efficient loopless multiset combination generation algorithm")
15214 (description "This library implements an efficient loopless multiset
15215 combination generation algorithm which is (approximately) described in
15216 \"Loopless algorithms for generating permutations, combinations, and other
15217 combinatorial configurations.\", G. Ehrlich - Journal of the ACM (JACM),
15218 1973. (Algorithm 7.)")
15219 (license license:expat)))
15221 (define-public fsom
15222 (let ((commit "a6ef318fbd347c53189384aef7f670c0e6ce89a3"))
15225 (version (git-version "0.0.0" "1" commit))
15228 (uri (git-reference
15229 (url "https://github.com/ekg/fsom/")
15231 (file-name (git-file-name name version))
15233 (base32 "0gw1lpvr812pywg9y546x0h1hhj261xwls41r6kqhddjlrcjc0pi"))))
15234 (build-system gnu-build-system)
15236 `(#:tests? #f ; There are no tests to run.
15238 (modify-phases %standard-phases
15239 (delete 'configure) ; There is no configure phase.
15241 (lambda* (#:key outputs #:allow-other-keys)
15242 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15243 (install-file "fsom" bin))
15245 (home-page "https://github.com/ekg/fsom")
15246 (synopsis "Manage SOM (Self-Organizing Maps) neural networks")
15247 (description "A tiny C library for managing SOM (Self-Organizing Maps)
15249 (license license:gpl3))))
15251 (define-public fastahack
15257 (uri (git-reference
15258 (url "https://github.com/ekg/fastahack/")
15259 (commit (string-append "v" version))))
15260 (file-name (git-file-name name version))
15262 (base32 "0rp1blskhzxf7vbh253ibpxbgl9wwgyzf1wbkxndi08d3j4vcss9"))))
15263 (build-system gnu-build-system)
15265 `(#:tests? #f ; Unclear how to run tests: https://github.com/ekg/fastahack/issues/15
15267 (modify-phases %standard-phases
15268 (delete 'configure) ; There is no configure phase.
15270 (lambda* (#:key outputs #:allow-other-keys)
15271 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15272 (install-file "fastahack" bin))
15274 (home-page "https://github.com/ekg/fastahack")
15275 (synopsis "Indexing and sequence extraction from FASTA files")
15276 (description "Fastahack is a small application for indexing and
15277 extracting sequences and subsequences from FASTA files. The included library
15278 provides a FASTA reader and indexer that can be embedded into applications
15279 which would benefit from directly reading subsequences from FASTA files. The
15280 library automatically handles index file generation and use.")
15281 (license (list license:expat license:gpl2))))
15283 (define-public vcflib
15290 (uri (string-append "https://github.com/vcflib/vcflib/releases/"
15291 "download/v" version
15292 "/vcflib-" version "-src.tar.gz"))
15294 (base32 "14zzrg8hg8cq9cvq2wdvp21j7nmxxkjrbagw2apd2yqv2kyx42lm"))
15295 (modules '((guix build utils)))
15298 (for-each delete-file-recursively
15299 '("fastahack" "filevercmp" "fsom" "googletest" "intervaltree"
15300 "libVCFH" "multichoose" "smithwaterman" "tabixpp"))
15302 (build-system gnu-build-system)
15304 `(("htslib" ,htslib)
15310 ;; This package builds against the .o files so we need to extract the source.
15311 ("fastahack-src" ,(package-source fastahack))
15312 ("filevercmp-src" ,(package-source filevercmp))
15313 ("fsom-src" ,(package-source fsom))
15314 ("intervaltree-src" ,(package-source intervaltree))
15315 ("multichoose-src" ,(package-source multichoose))
15316 ("smithwaterman-src" ,(package-source smithwaterman))
15317 ("tabixpp-src" ,(package-source tabixpp))))
15319 `(#:tests? #f ; no tests
15320 #:make-flags (list (string-append "HTS_LIB="
15321 (assoc-ref %build-inputs "htslib")
15323 (string-append "HTS_INCLUDES= -I"
15324 (assoc-ref %build-inputs "htslib")
15326 (string-append "HTS_LDFLAGS= -L"
15327 (assoc-ref %build-inputs "htslib")
15328 "/include/htslib" " -lhts"))
15330 (modify-phases %standard-phases
15331 (delete 'configure)
15333 (add-after 'unpack 'unpack-submodule-sources
15334 (lambda* (#:key inputs #:allow-other-keys)
15335 (let ((unpack (lambda (source target)
15337 (with-directory-excursion target
15338 (if (file-is-directory? (assoc-ref inputs source))
15339 (copy-recursively (assoc-ref inputs source) ".")
15340 (invoke "tar" "xvf"
15341 (assoc-ref inputs source)
15342 "--strip-components=1"))))))
15344 (unpack "fastahack-src" "fastahack")
15345 (unpack "filevercmp-src" "filevercmp")
15346 (unpack "fsom-src" "fsom")
15347 (unpack "intervaltree-src" "intervaltree")
15348 (unpack "multichoose-src" "multichoose")
15349 (unpack "smithwaterman-src" "smithwaterman")
15350 (unpack "tabixpp-src" "tabixpp")))))
15352 (lambda* (#:key inputs make-flags #:allow-other-keys)
15353 (let ((htslib (assoc-ref inputs "htslib")))
15354 (with-directory-excursion "tabixpp"
15355 (substitute* "Makefile"
15356 (("-Ihtslib") (string-append "-I" htslib "/include/htslib"))
15357 (("-Lhtslib") (string-append "-L" htslib "/lib/htslib"))
15358 (("htslib/htslib") (string-append htslib "/include/htslib")))
15360 (string-append "HTS_LIB=" htslib "/lib/libhts.a")))
15361 (apply invoke "make" "CC=gcc" "CFLAGS=-Itabixpp" make-flags))))
15363 (lambda* (#:key outputs #:allow-other-keys)
15364 (let ((bin (string-append (assoc-ref outputs "out") "/bin"))
15365 (lib (string-append (assoc-ref outputs "out") "/lib")))
15366 (for-each (lambda (file)
15367 (install-file file bin))
15368 (find-files "bin" ".*"))
15369 ;; The header files in src/ do not interface libvcflib,
15370 ;; therefore they are left out.
15371 (install-file "libvcflib.a" lib))
15373 (home-page "https://github.com/vcflib/vcflib/")
15374 (synopsis "Library for parsing and manipulating VCF files")
15375 (description "Vcflib provides methods to manipulate and interpret
15376 sequence variation as it can be described by VCF. It is both an API for parsing
15377 and operating on records of genomic variation as it can be described by the VCF
15378 format, and a collection of command-line utilities for executing complex
15379 manipulations on VCF files.")
15380 (license license:expat)))
15382 (define-public freebayes
15383 (let ((commit "3ce827d8ebf89bb3bdc097ee0fe7f46f9f30d5fb")
15388 (version (git-version version revision commit))
15391 (uri (git-reference
15392 (url "https://github.com/ekg/freebayes.git")
15394 (file-name (git-file-name name version))
15396 (base32 "1sbzwmcbn78ybymjnhwk7qc5r912azy5vqz2y7y81616yc3ba2a2"))))
15397 (build-system gnu-build-system)
15399 `(("bamtools" ,bamtools)
15403 `(("bc" ,bc) ; Needed for running tests.
15404 ("samtools" ,samtools) ; Needed for running tests.
15405 ("parallel" ,parallel) ; Needed for running tests.
15406 ("perl" ,perl) ; Needed for running tests.
15407 ("procps" ,procps) ; Needed for running tests.
15408 ("python" ,python-2) ; Needed for running tests.
15409 ("vcflib-src" ,(package-source vcflib))
15410 ;; These are submodules for the vcflib version used in freebayes.
15411 ;; This package builds against the .o files so we need to extract the source.
15412 ("tabixpp-src" ,(package-source tabixpp))
15413 ("smithwaterman-src" ,(package-source smithwaterman))
15414 ("multichoose-src" ,(package-source multichoose))
15415 ("fsom-src" ,(package-source fsom))
15416 ("filevercmp-src" ,(package-source filevercmp))
15417 ("fastahack-src" ,(package-source fastahack))
15418 ("intervaltree-src" ,(package-source intervaltree))
15419 ;; These submodules are needed to run the tests.
15420 ("bash-tap-src" ,(package-source bash-tap))
15421 ("test-simple-bash-src"
15424 (uri (git-reference
15425 (url "https://github.com/ingydotnet/test-simple-bash/")
15426 (commit "124673ff204b01c8e96b7fc9f9b32ee35d898acc")))
15427 (file-name "test-simple-bash-src-checkout")
15429 (base32 "043plp6z0x9yf7mdpky1fw7zcpwn1p47px95w9mh16603zqqqpga"))))))
15433 (string-append "BAMTOOLS_ROOT="
15434 (assoc-ref %build-inputs "bamtools")))
15435 #:test-target "test"
15437 (modify-phases %standard-phases
15438 (delete 'configure)
15439 (add-after 'unpack 'fix-tests
15441 (substitute* "test/t/01_call_variants.t"
15442 (("grep -P \"\\(\\\\t500\\$\\|\\\\t11000\\$\\|\\\\t1000\\$\\)\"")
15443 "grep -E ' (500|11000|1000)$'"))
15445 (add-after 'unpack 'unpack-submodule-sources
15446 (lambda* (#:key inputs #:allow-other-keys)
15447 (let ((unpack (lambda (source target)
15448 (with-directory-excursion target
15449 (if (file-is-directory? (assoc-ref inputs source))
15450 (copy-recursively (assoc-ref inputs source) ".")
15451 (invoke "tar" "xvf"
15452 (assoc-ref inputs source)
15453 "--strip-components=1"))))))
15455 (unpack "vcflib-src" "vcflib")
15456 (unpack "fastahack-src" "vcflib/fastahack")
15457 (unpack "filevercmp-src" "vcflib/filevercmp")
15458 (unpack "fsom-src" "vcflib/fsom")
15459 (unpack "intervaltree-src" "vcflib/intervaltree")
15460 (unpack "multichoose-src" "vcflib/multichoose")
15461 (unpack "smithwaterman-src" "vcflib/smithwaterman")
15462 (unpack "tabixpp-src" "vcflib/tabixpp")
15463 (unpack "test-simple-bash-src" "test/test-simple-bash")
15464 (unpack "bash-tap-src" "test/bash-tap")))))
15465 (add-after 'unpack-submodule-sources 'fix-makefiles
15467 ;; We don't have the .git folder to get the version tag from.
15468 (substitute* "vcflib/Makefile"
15469 (("^GIT_VERSION.*")
15470 (string-append "GIT_VERSION = v" ,version)))
15471 (substitute* "src/Makefile"
15472 (("-I\\$\\(BAMTOOLS_ROOT\\)/src")
15473 "-I$(BAMTOOLS_ROOT)/include/bamtools"))
15475 (add-before 'build 'build-tabixpp-and-vcflib
15476 (lambda* (#:key inputs make-flags #:allow-other-keys)
15477 (with-directory-excursion "vcflib"
15478 (with-directory-excursion "tabixpp"
15479 (apply invoke "make"
15480 (string-append "HTS_LIB="
15481 (assoc-ref inputs "htslib")
15484 (apply invoke "make"
15485 (string-append "CFLAGS=-Itabixpp")
15489 (lambda* (#:key outputs #:allow-other-keys)
15490 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15491 (install-file "bin/freebayes" bin)
15492 (install-file "bin/bamleftalign" bin))
15494 (home-page "https://github.com/ekg/freebayes")
15495 (synopsis "Haplotype-based variant detector")
15496 (description "FreeBayes is a Bayesian genetic variant detector designed to
15497 find small polymorphisms, specifically SNPs (single-nucleotide polymorphisms),
15498 indels (insertions and deletions), MNPs (multi-nucleotide polymorphisms), and
15499 complex events (composite insertion and substitution events) smaller than the
15500 length of a short-read sequencing alignment.")
15501 (license license:expat))))
15503 (define-public samblaster
15505 (name "samblaster")
15509 (uri (git-reference
15510 (url "https://github.com/GregoryFaust/samblaster.git")
15511 (commit (string-append "v." version))))
15512 (file-name (git-file-name name version))
15515 "0iv2ddfw8363vb2x8gr3p8g88whb6mb9m0pf71i2cqsbv6jghap7"))))
15516 (build-system gnu-build-system)
15518 `(#:tests? #f ; there are none
15520 (modify-phases %standard-phases
15521 (delete 'configure) ; There is no configure phase.
15523 (lambda* (#:key outputs #:allow-other-keys)
15524 (install-file "samblaster"
15525 (string-append (assoc-ref outputs "out") "/bin"))
15527 (home-page "https://github.com/GregoryFaust/samblaster")
15528 (synopsis "Mark duplicates in paired-end SAM files")
15529 (description "Samblaster is a fast and flexible program for marking
15530 duplicates in read-id grouped paired-end SAM files. It can also optionally
15531 output discordant read pairs and/or split read mappings to separate SAM files,
15532 and/or unmapped/clipped reads to a separate FASTQ file. When marking
15533 duplicates, samblaster will require approximately 20MB of memory per 1M read
15535 (license license:expat)))
15537 (define-public r-velocyto
15538 (let ((commit "d7790346cb99f49ab9c2b23ba70dcf9d2c9fc350")
15541 (name "r-velocyto")
15542 (version (git-version "0.6" revision commit))
15546 (uri (git-reference
15547 (url "https://github.com/velocyto-team/velocyto.R.git")
15549 (file-name (git-file-name name version))
15552 "16wqf70j7rd7pay2q513iyz12i8n9vrpg1bisah4lddbcpx5dz1n"))))
15553 (build-system r-build-system)
15555 `(("boost" ,boost)))
15557 `(("r-hdf5r" ,r-hdf5r)
15560 ("r-pcamethods" ,r-pcamethods)
15562 ("r-rcpparmadillo" ,r-rcpparmadillo)
15563 ;; Suggested packages
15564 ("r-rtsne" ,r-rtsne)
15565 ("r-cluster" ,r-cluster)
15566 ("r-abind" ,r-abind)
15568 ("r-biocgenerics" ,r-biocgenerics)
15569 ("r-genomicalignments" ,r-genomicalignments)
15570 ("r-rsamtools" ,r-rsamtools)
15571 ("r-edger" ,r-edger)
15572 ("r-igraph" ,r-igraph)))
15573 (home-page "https://velocyto.org")
15574 (synopsis "RNA velocity estimation in R")
15576 "This package provides basic routines for estimation of gene-specific
15577 transcriptional derivatives and visualization of the resulting velocity
15579 (license license:gpl3))))
15581 (define-public methyldackel
15583 (name "methyldackel")
15587 (uri (git-reference
15588 (url "https://github.com/dpryan79/MethylDackel.git")
15590 (file-name (git-file-name name version))
15593 "10gh8k0ca92kywnrw5pkacq3g6r8s976s12k8jhp8g3g49q9a97g"))))
15594 (build-system gnu-build-system)
15596 `(#:test-target "test"
15599 (string-append "prefix="
15600 (assoc-ref %outputs "out") "/bin/"))
15602 (modify-phases %standard-phases
15603 (replace 'configure
15604 (lambda* (#:key outputs #:allow-other-keys)
15605 (substitute* "Makefile"
15606 (("install MethylDackel \\$\\(prefix\\)" match)
15607 (string-append "install -d $(prefix); " match)))
15610 `(("htslib" ,htslib)
15612 ;; Needed for tests
15614 `(("python" ,python-wrapper)))
15615 (home-page "https://github.com/dpryan79/MethylDackel")
15616 (synopsis "Universal methylation extractor for BS-seq experiments")
15618 "MethylDackel will process a coordinate-sorted and indexed BAM or CRAM
15619 file containing some form of BS-seq alignments and extract per-base
15620 methylation metrics from them. MethylDackel requires an indexed fasta file
15621 containing the reference genome as well.")
15622 ;; See https://github.com/dpryan79/MethylDackel/issues/85
15623 (license license:expat)))
15625 (define-public python-gffutils
15626 ;; The latest release is older more than a year than the latest commit
15627 (let ((commit "4034c54600813b1402945e12faa91b3a53162cf1")
15630 (name "python-gffutils")
15631 (version (git-version "0.9" revision commit))
15635 (uri (git-reference
15636 (url "https://github.com/daler/gffutils.git")
15638 (file-name (git-file-name name version))
15641 "1rwafjdnbir5wnk0ap06ww4lra3p5frhy7mfs03rlldgfnwxymsn"))))
15642 (build-system python-build-system)
15645 (modify-phases %standard-phases
15648 ;; Tests need to access the HOME directory
15649 (setenv "HOME" "/tmp")
15650 (invoke "nosetests" "-a" "!slow")))
15651 (add-after 'unpack 'make-gz-files-writable
15653 (for-each make-file-writable
15654 (find-files "." "\\.gz"))
15657 `(("python-argcomplete" ,python-argcomplete)
15658 ("python-argh" ,python-argh)
15659 ("python-biopython" ,python-biopython)
15660 ("python-pybedtools" ,python-pybedtools)
15661 ("python-pyfaidx" ,python-pyfaidx)
15662 ("python-simplejson" ,python-simplejson)
15663 ("python-six" ,python-six)))
15665 `(("python-nose" , python-nose)))
15666 (home-page "https://github.com/daler/gffutils")
15667 (synopsis "Tool for manipulation of GFF and GTF files")
15669 "python-gffutils is a Python package for working with and manipulating
15670 the GFF and GTF format files typically used for genomic annotations. The
15671 files are loaded into a SQLite database, allowing much more complex
15672 manipulation of hierarchical features (e.g., genes, transcripts, and exons)
15673 than is possible with plain-text methods alone.")
15674 (license license:expat))))
15676 (define-public libsbml
15682 (uri (string-append "mirror://sourceforge/sbml/libsbml/"
15683 version "/stable/libSBML-"
15684 version "-core-src.tar.gz"))
15687 "0slkagrk3nfi2qsksv6b1brj6zhx4bj4bkib2sdycvrcd10ql2lh"))))
15688 (build-system cmake-build-system)
15690 `(#:test-target "test"
15692 (list "-DWITH_CHECK=ON"
15693 (string-append "-DLIBXML_LIBRARY="
15694 (assoc-ref %build-inputs "libxml2")
15696 (string-append "-DLIBXML_INCLUDE_DIR="
15697 (assoc-ref %build-inputs "libxml2")
15698 "/include/libxml2"))))
15700 `(("libxml2" ,libxml2)))
15704 (home-page "http://sbml.org/Software/libSBML")
15705 (synopsis "Process SBML files and data streams")
15706 (description "LibSBML is a library to help you read, write, manipulate,
15707 translate, and validate SBML files and data streams. The @dfn{Systems Biology
15708 Markup Language} (SBML) is an interchange format for computer models of
15709 biological processes. SBML is useful for models of metabolism, cell
15710 signaling, and more. It continues to be evolved and expanded by an
15711 international community.")
15712 (license license:lgpl2.1+)))