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>
19 ;;; This file is part of GNU Guix.
21 ;;; GNU Guix is free software; you can redistribute it and/or modify it
22 ;;; under the terms of the GNU General Public License as published by
23 ;;; the Free Software Foundation; either version 3 of the License, or (at
24 ;;; your option) any later version.
26 ;;; GNU Guix is distributed in the hope that it will be useful, but
27 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
28 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
29 ;;; GNU General Public License for more details.
31 ;;; You should have received a copy of the GNU General Public License
32 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
34 (define-module (gnu packages bioinformatics)
35 #:use-module ((guix licenses) #:prefix license:)
36 #:use-module (guix packages)
37 #:use-module (guix utils)
38 #:use-module (guix download)
39 #:use-module (guix git-download)
40 #:use-module (guix hg-download)
41 #:use-module (guix build-system ant)
42 #:use-module (guix build-system gnu)
43 #:use-module (guix build-system cmake)
44 #:use-module (guix build-system haskell)
45 #:use-module (guix build-system meson)
46 #:use-module (guix build-system ocaml)
47 #:use-module (guix build-system perl)
48 #:use-module (guix build-system python)
49 #:use-module (guix build-system r)
50 #:use-module (guix build-system ruby)
51 #:use-module (guix build-system scons)
52 #:use-module (guix build-system trivial)
53 #:use-module (gnu packages)
54 #:use-module (gnu packages autotools)
55 #:use-module (gnu packages algebra)
56 #:use-module (gnu packages base)
57 #:use-module (gnu packages bash)
58 #:use-module (gnu packages bison)
59 #:use-module (gnu packages bioconductor)
60 #:use-module (gnu packages boost)
61 #:use-module (gnu packages check)
62 #:use-module (gnu packages code)
63 #:use-module (gnu packages compression)
64 #:use-module (gnu packages cpio)
65 #:use-module (gnu packages cran)
66 #:use-module (gnu packages curl)
67 #:use-module (gnu packages documentation)
68 #:use-module (gnu packages databases)
69 #:use-module (gnu packages datastructures)
70 #:use-module (gnu packages file)
71 #:use-module (gnu packages flex)
72 #:use-module (gnu packages gawk)
73 #:use-module (gnu packages gcc)
74 #:use-module (gnu packages gd)
75 #:use-module (gnu packages gtk)
76 #:use-module (gnu packages glib)
77 #:use-module (gnu packages graph)
78 #:use-module (gnu packages groff)
79 #:use-module (gnu packages guile)
80 #:use-module (gnu packages guile-xyz)
81 #:use-module (gnu packages haskell-check)
82 #:use-module (gnu packages haskell-web)
83 #:use-module (gnu packages haskell-xyz)
84 #:use-module (gnu packages image)
85 #:use-module (gnu packages imagemagick)
86 #:use-module (gnu packages java)
87 #:use-module (gnu packages java-compression)
88 #:use-module (gnu packages jemalloc)
89 #:use-module (gnu packages dlang)
90 #:use-module (gnu packages linux)
91 #:use-module (gnu packages lisp-xyz)
92 #:use-module (gnu packages logging)
93 #:use-module (gnu packages machine-learning)
94 #:use-module (gnu packages man)
95 #:use-module (gnu packages maths)
96 #:use-module (gnu packages mpi)
97 #:use-module (gnu packages ncurses)
98 #:use-module (gnu packages ocaml)
99 #:use-module (gnu packages pcre)
100 #:use-module (gnu packages parallel)
101 #:use-module (gnu packages pdf)
102 #:use-module (gnu packages perl)
103 #:use-module (gnu packages perl-check)
104 #:use-module (gnu packages pkg-config)
105 #:use-module (gnu packages popt)
106 #:use-module (gnu packages protobuf)
107 #:use-module (gnu packages python)
108 #:use-module (gnu packages python-compression)
109 #:use-module (gnu packages python-science)
110 #:use-module (gnu packages python-web)
111 #:use-module (gnu packages python-xyz)
112 #:use-module (gnu packages readline)
113 #:use-module (gnu packages ruby)
114 #:use-module (gnu packages serialization)
115 #:use-module (gnu packages shells)
116 #:use-module (gnu packages sphinx)
117 #:use-module (gnu packages statistics)
118 #:use-module (gnu packages swig)
119 #:use-module (gnu packages tbb)
120 #:use-module (gnu packages tex)
121 #:use-module (gnu packages texinfo)
122 #:use-module (gnu packages textutils)
123 #:use-module (gnu packages time)
124 #:use-module (gnu packages tls)
125 #:use-module (gnu packages vim)
126 #:use-module (gnu packages web)
127 #:use-module (gnu packages xml)
128 #:use-module (gnu packages xorg)
129 #:use-module (srfi srfi-1)
130 #:use-module (ice-9 match))
132 (define-public aragorn
139 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
143 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
144 (build-system gnu-build-system)
146 `(#:tests? #f ; there are no tests
148 (modify-phases %standard-phases
158 (string-append "aragorn" ,version ".c"))
161 (lambda* (#:key outputs #:allow-other-keys)
162 (let* ((out (assoc-ref outputs "out"))
163 (bin (string-append out "/bin"))
164 (man (string-append out "/share/man/man1")))
165 (install-file "aragorn" bin)
166 (install-file "aragorn.1" man))
168 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
169 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
171 "Aragorn identifies transfer RNA, mitochondrial RNA and
172 transfer-messenger RNA from nucleotide sequences, based on homology to known
173 tRNA consensus sequences and RNA structure. It also outputs the secondary
174 structure of the predicted RNA.")
175 (license license:gpl2)))
183 ;; BamM is not available on pypi.
185 (url "https://github.com/Ecogenomics/BamM.git")
188 (file-name (git-file-name name version))
191 "1p83ahi984ipslxlg4yqy1gdnya9rkn1v71z8djgxkm9d2chw4c5"))
192 (modules '((guix build utils)))
195 ;; Delete bundled htslib.
196 (delete-file-recursively "c/htslib-1.3.1")
198 (build-system python-build-system)
200 `(#:python ,python-2 ; BamM is Python 2 only.
201 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
202 ;; been modified from its original form.
204 (let ((htslib (assoc-ref %build-inputs "htslib")))
205 (list "--with-libhts-lib" (string-append htslib "/lib")
206 "--with-libhts-inc" (string-append htslib "/include/htslib")))
208 (modify-phases %standard-phases
209 (add-after 'unpack 'autogen
211 (with-directory-excursion "c"
212 (let ((sh (which "sh")))
213 (for-each make-file-writable (find-files "." ".*"))
214 ;; Use autogen so that 'configure' works.
215 (substitute* "autogen.sh" (("/bin/sh") sh))
216 (setenv "CONFIG_SHELL" sh)
217 (invoke "./autogen.sh")))
220 ;; Run tests after installation so compilation only happens once.
222 (add-after 'install 'wrap-executable
223 (lambda* (#:key outputs #:allow-other-keys)
224 (let* ((out (assoc-ref outputs "out"))
225 (path (getenv "PATH")))
226 (wrap-program (string-append out "/bin/bamm")
227 `("PATH" ":" prefix (,path))))
229 (add-after 'wrap-executable 'post-install-check
230 (lambda* (#:key inputs outputs #:allow-other-keys)
232 (string-append (assoc-ref outputs "out")
237 (assoc-ref outputs "out")
239 (string-take (string-take-right
240 (assoc-ref inputs "python") 5) 3)
242 (getenv "PYTHONPATH")))
243 ;; There are 2 errors printed, but they are safe to ignore:
244 ;; 1) [E::hts_open_format] fail to open file ...
245 ;; 2) samtools view: failed to open ...
249 `(("autoconf" ,autoconf)
250 ("automake" ,automake)
253 ("python-nose" ,python2-nose)
254 ("python-pysam" ,python2-pysam)))
256 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
257 ("samtools" ,samtools)
261 ("coreutils" ,coreutils)))
263 `(("python-numpy" ,python2-numpy)))
264 (home-page "https://ecogenomics.github.io/BamM/")
265 (synopsis "Metagenomics-focused BAM file manipulator")
267 "BamM is a C library, wrapped in python, to efficiently generate and
268 parse BAM files, specifically for the analysis of metagenomic data. For
269 instance, it implements several methods to assess contig-wise read coverage.")
270 (license license:lgpl3+)))
272 (define-public bamtools
279 (url "https://github.com/pezmaster31/bamtools.git")
280 (commit (string-append "v" version))))
281 (file-name (git-file-name name version))
284 "0nfb2ypcx9959xnbz6wxh6py3xfizgmg8nrknxl95c507m9hmq8b"))))
285 (build-system cmake-build-system)
287 `(#:tests? #f ;no "check" target
289 (modify-phases %standard-phases
291 'configure 'set-ldflags
292 (lambda* (#:key outputs #:allow-other-keys)
296 (assoc-ref outputs "out") "/lib/bamtools"))
298 (inputs `(("zlib" ,zlib)))
299 (home-page "https://github.com/pezmaster31/bamtools")
300 (synopsis "C++ API and command-line toolkit for working with BAM data")
302 "BamTools provides both a C++ API and a command-line toolkit for handling
304 (license license:expat)))
306 (define-public bcftools
312 (uri (string-append "https://github.com/samtools/bcftools/"
314 version "/bcftools-" version ".tar.bz2"))
317 "1j3h638i8kgihzyrlnpj82xg1b23sijibys9hvwari3fy7kd0dkg"))
318 (modules '((guix build utils)))
320 ;; Delete bundled htslib.
321 (delete-file-recursively "htslib-1.9")
323 (build-system gnu-build-system)
326 (list "--enable-libgsl")
329 (modify-phases %standard-phases
330 (add-before 'check 'patch-tests
332 (substitute* "test/test.pl"
333 (("/bin/bash") (which "bash")))
341 (home-page "https://samtools.github.io/bcftools/")
342 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
344 "BCFtools is a set of utilities that manipulate variant calls in the
345 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
346 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
347 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
348 (license (list license:gpl3+ license:expat))))
350 (define-public bedops
357 (url "https://github.com/bedops/bedops.git")
358 (commit (string-append "v" version))))
359 (file-name (git-file-name name version))
362 "0mmgsgwz5r9w76hzgxkxc9s9lkdhhaf7vr6i02b09vbswvs1fyqx"))))
363 (build-system gnu-build-system)
366 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
368 (modify-phases %standard-phases
369 (add-after 'unpack 'unpack-tarballs
371 ;; FIXME: Bedops includes tarballs of minimally patched upstream
372 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
373 ;; libraries because at least one of the libraries (zlib) is
374 ;; patched to add a C++ function definition (deflateInit2cpp).
375 ;; Until the Bedops developers offer a way to link against system
376 ;; libraries we have to build the in-tree copies of these three
379 ;; See upstream discussion:
380 ;; https://github.com/bedops/bedops/issues/124
382 ;; Unpack the tarballs to benefit from shebang patching.
383 (with-directory-excursion "third-party"
384 (invoke "tar" "xvf" "jansson-2.6.tar.bz2")
385 (invoke "tar" "xvf" "zlib-1.2.7.tar.bz2")
386 (invoke "tar" "xvf" "bzip2-1.0.6.tar.bz2"))
387 ;; Disable unpacking of tarballs in Makefile.
388 (substitute* "system.mk/Makefile.linux"
389 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
390 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
391 (substitute* "third-party/zlib-1.2.7/Makefile.in"
392 (("^SHELL=.*$") "SHELL=bash\n"))
394 (delete 'configure))))
395 (home-page "https://github.com/bedops/bedops")
396 (synopsis "Tools for high-performance genomic feature operations")
398 "BEDOPS is a suite of tools to address common questions raised in genomic
399 studies---mostly with regard to overlap and proximity relationships between
400 data sets. It aims to be scalable and flexible, facilitating the efficient
401 and accurate analysis and management of large-scale genomic data.
403 BEDOPS provides tools that perform highly efficient and scalable Boolean and
404 other set operations, statistical calculations, archiving, conversion and
405 other management of genomic data of arbitrary scale. Tasks can be easily
406 split by chromosome for distributing whole-genome analyses across a
407 computational cluster.")
408 (license license:gpl2+)))
410 (define-public bedtools
416 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
417 "download/v" version "/"
418 "bedtools-" version ".tar.gz"))
421 "0m3hk6548846w83a9s5drsczvy67n2azx41kj71n03klb2gbzwg3"))))
422 (build-system gnu-build-system)
424 '(#:test-target "test"
426 (list (string-append "prefix=" (assoc-ref %outputs "out")))
428 (modify-phases %standard-phases
429 (delete 'configure))))
431 `(("python" ,python-wrapper)))
433 `(("samtools" ,samtools)
435 (home-page "https://github.com/arq5x/bedtools2")
436 (synopsis "Tools for genome analysis and arithmetic")
438 "Collectively, the bedtools utilities are a swiss-army knife of tools for
439 a wide-range of genomics analysis tasks. The most widely-used tools enable
440 genome arithmetic: that is, set theory on the genome. For example, bedtools
441 allows one to intersect, merge, count, complement, and shuffle genomic
442 intervals from multiple files in widely-used genomic file formats such as BAM,
444 (license license:expat)))
446 ;; Later releases of bedtools produce files with more columns than
447 ;; what Ribotaper expects.
448 (define-public bedtools-2.18
449 (package (inherit bedtools)
454 (uri (string-append "https://github.com/arq5x/bedtools2/"
455 "releases/download/v" version
456 "/bedtools-" version ".tar.gz"))
459 "11rvca19ncg03kxd0wzlfx5ws7r3nisd0z8s9j9n182d8ksp2pxz"))))
461 '(#:test-target "test"
463 (modify-phases %standard-phases
466 (lambda* (#:key outputs #:allow-other-keys)
467 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
468 (for-each (lambda (file)
469 (install-file file bin))
470 (find-files "bin" ".*")))
473 ;; Needed for pybedtools.
474 (define-public bedtools-2.26
475 (package (inherit bedtools)
480 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
481 "download/v" version "/"
482 "bedtools-" version ".tar.gz"))
485 "0jhavwifnf7lmkb11h9y7dynr8d699h0rd2l52j1pfgircr2zwv5"))))))
494 (url "https://github.com/PacificBiosciences/pbbam.git")
496 (file-name (git-file-name name version))
499 "0h9gkrpf2lrxklxp72xfl5bi3h5zcm5hprrya9gf0hr3xwlbpp0x"))))
500 (build-system meson-build-system)
503 (modify-phases %standard-phases
504 (add-after 'unpack 'find-googletest
505 (lambda* (#:key inputs #:allow-other-keys)
506 ;; It doesn't find gtest_main because there's no pkg-config file
507 ;; for it. Find it another way.
508 (substitute* "tests/meson.build"
509 (("pbbam_gtest_dep = dependency\\('gtest_main'.*")
510 (format #f "cpp = meson.get_compiler('cpp')
511 pbbam_gtest_dep = cpp.find_library('gtest_main', dirs : '~a')\n"
512 (assoc-ref inputs "googletest"))))
514 ;; TODO: tests/pbbam_test cannot be linked
515 ;; ld: tests/59830eb@@pbbam_test@exe/src_test_Accuracy.cpp.o:
516 ;; undefined reference to symbol '_ZTIN7testing4TestE'
517 ;; ld: /gnu/store/...-googletest-1.8.0/lib/libgtest.so:
518 ;; error adding symbols: DSO missing from command line
520 #:configure-flags '("-Dtests=false")))
521 ;; These libraries are listed as "Required" in the pkg-config file.
527 ("samtools" ,samtools)))
529 `(("googletest" ,googletest)
530 ("pkg-config" ,pkg-config)
531 ("python" ,python-wrapper))) ; for tests
532 (home-page "https://github.com/PacificBiosciences/pbbam")
533 (synopsis "Work with PacBio BAM files")
535 "The pbbam software package provides components to create, query, and
536 edit PacBio BAM files and associated indices. These components include a core
537 C++ library, bindings for additional languages, and command-line utilities.
538 This library is not intended to be used as a general-purpose BAM utility - all
539 input and output BAMs must adhere to the PacBio BAM format specification.
540 Non-PacBio BAMs will cause exceptions to be thrown.")
541 (license license:bsd-3)))
543 (define-public blasr-libcpp
545 (name "blasr-libcpp")
550 (url "https://github.com/PacificBiosciences/blasr_libcpp.git")
552 (file-name (git-file-name name version))
555 "0cn5l42zyq67sj0g2imqkhayz2iqvv0a1pgpbmlq0qynjmsrbfd2"))))
556 (build-system meson-build-system)
559 (modify-phases %standard-phases
560 (add-after 'unpack 'link-with-hdf5
561 (lambda* (#:key inputs #:allow-other-keys)
562 (let ((hdf5 (assoc-ref inputs "hdf5")))
563 (substitute* "meson.build"
564 (("libblasr_deps = \\[" m)
567 (format #f "cpp.find_library('hdf5', dirs : '~a'), \
568 cpp.find_library('hdf5_cpp', dirs : '~a'), "
571 (add-after 'unpack 'find-googletest
572 (lambda* (#:key inputs #:allow-other-keys)
573 ;; It doesn't find gtest_main because there's no pkg-config file
574 ;; for it. Find it another way.
575 (substitute* "unittest/meson.build"
576 (("libblasr_gtest_dep = dependency\\('gtest_main'.*")
577 (format #f "cpp = meson.get_compiler('cpp')
578 libblasr_gtest_dep = cpp.find_library('gtest_main', dirs : '~a')\n"
579 (assoc-ref inputs "googletest"))))
581 ;; TODO: unittest/libblasr_unittest cannot be linked
582 ;; ld: ;; unittest/df08227@@libblasr_unittest@exe/alignment_utils_FileUtils_gtest.cpp.o:
583 ;; undefined reference to symbol
584 ;; '_ZN7testing8internal9DeathTest6CreateEPKcPKNS0_2REES3_iPPS1_'
585 ;; ld: /gnu/store/...-googletest-1.8.0/lib/libgtest.so:
586 ;; error adding symbols: DSO missing from command line
588 #:configure-flags '("-Dtests=false")))
595 `(("googletest" ,googletest)
596 ("pkg-config" ,pkg-config)))
597 (home-page "https://github.com/PacificBiosciences/blasr_libcpp")
598 (synopsis "Library for analyzing PacBio genomic sequences")
600 "This package provides three libraries used by applications for analyzing
601 PacBio genomic sequences. This library contains three sub-libraries: pbdata,
603 (license license:bsd-3)))
612 (url "https://github.com/PacificBiosciences/blasr.git")
614 (file-name (git-file-name name version))
617 "1skgy2mvz8gsgfh1gc2nfgwvpyzb1hpmp2cf2773h5wsj8nw22kl"))))
618 (build-system meson-build-system)
621 (modify-phases %standard-phases
622 (add-after 'unpack 'link-with-hdf5
623 (lambda* (#:key inputs #:allow-other-keys)
624 (let ((hdf5 (assoc-ref inputs "hdf5")))
625 (substitute* "meson.build"
626 (("blasr_deps = \\[" m)
629 (format #f "cpp.find_library('hdf5', dirs : '~a'), \
630 cpp.find_library('hdf5_cpp', dirs : '~a'), "
633 ;; Tests require "cram" executable, which is not packaged.
635 #:configure-flags '("-Dtests=false")))
638 ("blasr-libcpp" ,blasr-libcpp)
643 `(("pkg-config" ,pkg-config)))
644 (home-page "https://github.com/PacificBiosciences/blasr")
645 (synopsis "PacBio long read aligner")
647 "Blasr is a genomic sequence aligner for processing PacBio long reads.")
648 (license license:bsd-3)))
650 (define-public ribotaper
656 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
657 "files/RiboTaper/RiboTaper_Version_"
661 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
662 (build-system gnu-build-system)
665 (modify-phases %standard-phases
666 (add-after 'install 'wrap-executables
667 (lambda* (#:key inputs outputs #:allow-other-keys)
668 (let* ((out (assoc-ref outputs "out")))
671 (wrap-program (string-append out "/bin/" script)
672 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
673 '("create_annotations_files.bash"
674 "create_metaplots.bash"
675 "Ribotaper_ORF_find.sh"
679 `(("bedtools" ,bedtools-2.18)
680 ("samtools" ,samtools-0.1)
681 ("r-minimal" ,r-minimal)
682 ("r-foreach" ,r-foreach)
683 ("r-xnomial" ,r-xnomial)
685 ("r-multitaper" ,r-multitaper)
686 ("r-seqinr" ,r-seqinr)))
687 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
688 (synopsis "Define translated ORFs using ribosome profiling data")
690 "Ribotaper is a method for defining translated @dfn{open reading
691 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
692 provides the Ribotaper pipeline.")
693 (license license:gpl3+)))
695 (define-public ribodiff
703 (url "https://github.com/ratschlab/RiboDiff.git")
704 (commit (string-append "v" version))))
705 (file-name (git-file-name name version))
708 "0x75nlp7qnmm64jasbi6l21f2cy99r2cjyl6b4hr8zf2bq22drnz"))))
709 (build-system python-build-system)
713 (modify-phases %standard-phases
714 ;; Generate an installable executable script wrapper.
715 (add-after 'unpack 'patch-setup.py
717 (substitute* "setup.py"
718 (("^(.*)packages=.*" line prefix)
719 (string-append line "\n"
720 prefix "scripts=['scripts/TE.py'],\n")))
723 `(("python-numpy" ,python2-numpy)
724 ("python-matplotlib" ,python2-matplotlib)
725 ("python-scipy" ,python2-scipy)
726 ("python-statsmodels" ,python2-statsmodels)))
728 `(("python-mock" ,python2-mock)
729 ("python-nose" ,python2-nose)))
730 (home-page "https://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
731 (synopsis "Detect translation efficiency changes from ribosome footprints")
732 (description "RiboDiff is a statistical tool that detects the protein
733 translational efficiency change from Ribo-Seq (ribosome footprinting) and
734 RNA-Seq data. It uses a generalized linear model to detect genes showing
735 difference in translational profile taking mRNA abundance into account. It
736 facilitates us to decipher the translational regulation that behave
737 independently with transcriptional regulation.")
738 (license license:gpl3+)))
740 (define-public bioawk
747 (url "https://github.com/lh3/bioawk.git")
748 (commit (string-append "v" version))))
749 (file-name (git-file-name name version))
752 "1pxc3zdnirxbf9a0az698hd8xdik7qkhypm7v6hn922x8y9qmspm"))))
753 (build-system gnu-build-system)
759 `(#:tests? #f ; There are no tests to run.
760 ;; Bison must generate files, before other targets can build.
763 (modify-phases %standard-phases
764 (delete 'configure) ; There is no configure phase.
766 (lambda* (#:key outputs #:allow-other-keys)
767 (let* ((out (assoc-ref outputs "out"))
768 (bin (string-append out "/bin"))
769 (man (string-append out "/share/man/man1")))
771 (copy-file "awk.1" (string-append man "/bioawk.1"))
772 (install-file "bioawk" bin))
774 (home-page "https://github.com/lh3/bioawk")
775 (synopsis "AWK with bioinformatics extensions")
776 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
777 support of several common biological data formats, including optionally gzip'ed
778 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
779 also adds a few built-in functions and a command line option to use TAB as the
780 input/output delimiter. When the new functionality is not used, bioawk is
781 intended to behave exactly the same as the original BWK awk.")
782 (license license:x11)))
784 (define-public python-pybedtools
786 (name "python-pybedtools")
790 (uri (pypi-uri "pybedtools" version))
793 "1xl454ijvd4dzfvqgfahad49b49j7qy710fq9xh1rvk42z6x5ssf"))))
794 (build-system python-build-system)
796 `(#:modules ((ice-9 ftw)
800 (guix build python-build-system))
801 ;; See https://github.com/daler/pybedtools/issues/192
803 (modify-phases %standard-phases
804 ;; See https://github.com/daler/pybedtools/issues/261
805 (add-after 'unpack 'disable-broken-tests
807 ;; This test (pybedtools.test.test_scripts.test_venn_mpl) needs a
808 ;; graphical environment.
809 (substitute* "pybedtools/test/test_scripts.py"
810 (("def test_venn_mpl")
811 "def _do_not_test_venn_mpl"))
812 (substitute* "pybedtools/test/test_helpers.py"
813 ;; Requires internet access.
814 (("def test_chromsizes")
815 "def _do_not_test_chromsizes")
816 ;; Broken as a result of the workaround used in the check phase
817 ;; (see: https://github.com/daler/pybedtools/issues/192).
818 (("def test_getting_example_beds")
819 "def _do_not_test_getting_example_beds"))
821 ;; TODO: Remove phase after it's part of PYTHON-BUILD-SYSTEM.
823 ;; Force the Cythonization of C++ files to guard against compilation
825 (add-after 'unpack 'remove-cython-generated-files
827 (let ((cython-sources (map (cut string-drop-right <> 4)
828 (find-files "." "\\.pyx$")))
829 (c/c++-files (find-files "." "\\.(c|cpp|cxx)$")))
830 (define (strip-extension filename)
831 (string-take filename (string-index-right filename #\.)))
832 (define (cythonized? c/c++-file)
833 (member (strip-extension c/c++-file) cython-sources))
834 (for-each delete-file (filter cythonized? c/c++-files))
836 (add-after 'remove-cython-generated-files 'generate-cython-extensions
838 (invoke "python" "setup.py" "cythonize")))
841 (let* ((cwd (getcwd))
842 (build-root-directory (string-append cwd "/build/"))
843 (build (string-append
845 (find (cut string-prefix? "lib" <>)
846 (scandir (string-append
847 build-root-directory)))))
848 (scripts (string-append
850 (find (cut string-prefix? "scripts" <>)
851 (scandir build-root-directory)))))
853 (string-append build ":" (getenv "PYTHONPATH")))
854 ;; Executable scripts such as 'intron_exon_reads.py' must be
855 ;; available in the PATH.
857 (string-append scripts ":" (getenv "PATH"))))
858 ;; The tests need to be run from elsewhere...
859 (mkdir-p "/tmp/test")
860 (copy-recursively "pybedtools/test" "/tmp/test")
861 (with-directory-excursion "/tmp/test"
862 (invoke "pytest")))))))
864 `(("bedtools" ,bedtools)
865 ("samtools" ,samtools)
866 ("python-matplotlib" ,python-matplotlib)
867 ("python-pysam" ,python-pysam)
868 ("python-pyyaml" ,python-pyyaml)))
870 `(("python-numpy" ,python-numpy)
871 ("python-pandas" ,python-pandas)
872 ("python-cython" ,python-cython)
873 ("kentutils" ,kentutils) ; for bedGraphToBigWig
874 ("python-six" ,python-six)
875 ;; For the test suite.
876 ("python-pytest" ,python-pytest)
877 ("python-psutil" ,python-psutil)))
878 (home-page "https://pythonhosted.org/pybedtools/")
879 (synopsis "Python wrapper for BEDtools programs")
881 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
882 which are widely used for genomic interval manipulation or \"genome algebra\".
883 pybedtools extends BEDTools by offering feature-level manipulations from with
885 (license license:gpl2+)))
887 (define-public python2-pybedtools
888 (package-with-python2 python-pybedtools))
890 (define-public python-biom-format
892 (name "python-biom-format")
897 ;; Use GitHub as source because PyPI distribution does not contain
898 ;; test data: https://github.com/biocore/biom-format/issues/693
900 (url "https://github.com/biocore/biom-format.git")
902 (file-name (git-file-name name version))
905 "1rna16lyk5aqhnv0dp77wwaplias93f1vw28ad3jmyw6hwkai05v"))
906 (modules '((guix build utils)))
908 ;; Delete generated C files.
909 (for-each delete-file (find-files "." "\\.c"))
911 (build-system python-build-system)
914 (modify-phases %standard-phases
915 (add-after 'unpack 'use-cython
916 (lambda _ (setenv "USE_CYTHON" "1") #t))
917 (add-after 'unpack 'disable-broken-tests
919 (substitute* "biom/tests/test_cli/test_validate_table.py"
920 (("^(.+)def test_invalid_hdf5" m indent)
921 (string-append indent
922 "@npt.dec.skipif(True, msg='Guix')\n"
924 (substitute* "biom/tests/test_table.py"
925 (("^(.+)def test_from_hdf5_issue_731" m indent)
926 (string-append indent
927 "@npt.dec.skipif(True, msg='Guix')\n"
930 (add-before 'reset-gzip-timestamps 'make-files-writable
931 (lambda* (#:key outputs #:allow-other-keys)
932 (let ((out (assoc-ref outputs "out")))
933 (for-each (lambda (file) (chmod file #o644))
934 (find-files out "\\.gz"))
937 `(("python-numpy" ,python-numpy)
938 ("python-scipy" ,python-scipy)
939 ("python-flake8" ,python-flake8)
940 ("python-future" ,python-future)
941 ("python-click" ,python-click)
942 ("python-h5py" ,python-h5py)
943 ("python-pandas" ,python-pandas)))
945 `(("python-cython" ,python-cython)
946 ("python-pytest" ,python-pytest)
947 ("python-pytest-cov" ,python-pytest-cov)
948 ("python-nose" ,python-nose)))
949 (home-page "http://www.biom-format.org")
950 (synopsis "Biological Observation Matrix (BIOM) format utilities")
952 "The BIOM file format is designed to be a general-use format for
953 representing counts of observations e.g. operational taxonomic units, KEGG
954 orthology groups or lipid types, in one or more biological samples
955 e.g. microbiome samples, genomes, metagenomes.")
956 (license license:bsd-3)
957 (properties `((python2-variant . ,(delay python2-biom-format))))))
959 (define-public python2-biom-format
960 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
964 (substitute-keyword-arguments (package-arguments base)
966 `(modify-phases ,phases
967 ;; Do not require the unmaintained pyqi library.
968 (add-after 'unpack 'remove-pyqi
970 (substitute* "setup.py"
971 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
974 (define-public bioperl-minimal
975 (let* ((inputs `(("perl-module-build" ,perl-module-build)
976 ("perl-data-stag" ,perl-data-stag)
977 ("perl-libwww" ,perl-libwww)
978 ("perl-uri" ,perl-uri)))
980 (map (compose package-name cadr)
983 (map (compose package-transitive-target-inputs cadr) inputs))))))
985 (name "bioperl-minimal")
991 (url "https://github.com/bioperl/bioperl-live")
992 (commit (string-append "release-"
993 (string-map (lambda (c)
996 (file-name (git-file-name name version))
999 "0wl8yvzcls59pwwk6m8ahy87pwg6nnibzy5cldbvmcwg2x2w7783"))))
1000 (build-system perl-build-system)
1003 (modify-phases %standard-phases
1005 'install 'wrap-programs
1006 (lambda* (#:key outputs #:allow-other-keys)
1007 ;; Make sure all executables in "bin" find the required Perl
1008 ;; modules at runtime. As the PERL5LIB variable contains also
1009 ;; the paths of native inputs, we pick the transitive target
1010 ;; inputs from %build-inputs.
1011 (let* ((out (assoc-ref outputs "out"))
1012 (bin (string-append out "/bin/"))
1014 (cons (string-append out "/lib/perl5/site_perl")
1016 (assoc-ref %build-inputs name))
1017 ',transitive-inputs))
1019 (for-each (lambda (file)
1021 `("PERL5LIB" ":" prefix (,path))))
1022 (find-files bin "\\.pl$"))
1026 `(("perl-test-most" ,perl-test-most)))
1027 (home-page "https://metacpan.org/release/BioPerl")
1028 (synopsis "Bioinformatics toolkit")
1030 "BioPerl is the product of a community effort to produce Perl code which
1031 is useful in biology. Examples include Sequence objects, Alignment objects
1032 and database searching objects. These objects not only do what they are
1033 advertised to do in the documentation, but they also interact - Alignment
1034 objects are made from the Sequence objects, Sequence objects have access to
1035 Annotation and SeqFeature objects and databases, Blast objects can be
1036 converted to Alignment objects, and so on. This means that the objects
1037 provide a coordinated and extensible framework to do computational biology.")
1038 (license license:perl-license))))
1040 (define-public python-biopython
1042 (name "python-biopython")
1046 ;; use PyPi rather than biopython.org to ease updating
1047 (uri (pypi-uri "biopython" version))
1050 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
1051 (build-system python-build-system)
1054 (modify-phases %standard-phases
1055 (add-before 'check 'set-home
1056 ;; Some tests require a home directory to be set.
1057 (lambda _ (setenv "HOME" "/tmp") #t)))))
1059 `(("python-numpy" ,python-numpy)))
1060 (home-page "https://biopython.org/")
1061 (synopsis "Tools for biological computation in Python")
1063 "Biopython is a set of tools for biological computation including parsers
1064 for bioinformatics files into Python data structures; interfaces to common
1065 bioinformatics programs; a standard sequence class and tools for performing
1066 common operations on them; code to perform data classification; code for
1067 dealing with alignments; code making it easy to split up parallelizable tasks
1068 into separate processes; and more.")
1069 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
1071 (define-public python2-biopython
1072 (package-with-python2 python-biopython))
1074 (define-public python-fastalite
1076 (name "python-fastalite")
1081 (uri (pypi-uri "fastalite" version))
1084 "1qli6pxp77i9xn2wfciq2zaxhl82bdxb33cpzqzj1z25yd036wqj"))))
1085 (build-system python-build-system)
1087 `(#:tests? #f)) ; Test data is not distributed.
1088 (home-page "https://github.com/nhoffman/fastalite")
1089 (synopsis "Simplest possible FASTA parser")
1090 (description "This library implements a FASTA and a FASTQ parser without
1091 relying on a complex dependency tree.")
1092 (license license:expat)))
1094 (define-public python2-fastalite
1095 (package-with-python2 python-fastalite))
1097 (define-public bpp-core
1098 ;; The last release was in 2014 and the recommended way to install from source
1099 ;; is to clone the git repository, so we do this.
1100 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1101 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
1104 (version (string-append "2.2.0-1." (string-take commit 7)))
1108 (url "http://biopp.univ-montp2.fr/git/bpp-core")
1110 (file-name (string-append name "-" version "-checkout"))
1113 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
1114 (build-system cmake-build-system)
1116 `(#:parallel-build? #f))
1117 (home-page "http://biopp.univ-montp2.fr")
1118 (synopsis "C++ libraries for Bioinformatics")
1120 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1121 analysis, phylogenetics, molecular evolution and population genetics. It is
1122 Object Oriented and is designed to be both easy to use and computer efficient.
1123 Bio++ intends to help programmers to write computer expensive programs, by
1124 providing them a set of re-usable tools.")
1125 (license license:cecill-c))))
1127 (define-public bpp-phyl
1128 ;; The last release was in 2014 and the recommended way to install from source
1129 ;; is to clone the git repository, so we do this.
1130 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1131 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
1134 (version (string-append "2.2.0-1." (string-take commit 7)))
1138 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
1140 (file-name (string-append name "-" version "-checkout"))
1143 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
1144 (build-system cmake-build-system)
1146 `(#:parallel-build? #f
1147 ;; If out-of-source, test data is not copied into the build directory
1148 ;; so the tests fail.
1149 #:out-of-source? #f))
1151 `(("bpp-core" ,bpp-core)
1152 ("bpp-seq" ,bpp-seq)))
1153 (home-page "http://biopp.univ-montp2.fr")
1154 (synopsis "Bio++ phylogenetic Library")
1156 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1157 analysis, phylogenetics, molecular evolution and population genetics. This
1158 library provides phylogenetics-related modules.")
1159 (license license:cecill-c))))
1161 (define-public bpp-popgen
1162 ;; The last release was in 2014 and the recommended way to install from source
1163 ;; is to clone the git repository, so we do this.
1164 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1165 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
1168 (version (string-append "2.2.0-1." (string-take commit 7)))
1172 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
1174 (file-name (string-append name "-" version "-checkout"))
1177 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
1178 (build-system cmake-build-system)
1180 `(#:parallel-build? #f
1181 #:tests? #f)) ; There are no tests.
1183 `(("bpp-core" ,bpp-core)
1184 ("bpp-seq" ,bpp-seq)))
1185 (home-page "http://biopp.univ-montp2.fr")
1186 (synopsis "Bio++ population genetics library")
1188 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1189 analysis, phylogenetics, molecular evolution and population genetics. This
1190 library provides population genetics-related modules.")
1191 (license license:cecill-c))))
1193 (define-public bpp-seq
1194 ;; The last release was in 2014 and the recommended way to install from source
1195 ;; is to clone the git repository, so we do this.
1196 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1197 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
1200 (version (string-append "2.2.0-1." (string-take commit 7)))
1204 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
1206 (file-name (string-append name "-" version "-checkout"))
1209 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
1210 (build-system cmake-build-system)
1212 `(#:parallel-build? #f
1213 ;; If out-of-source, test data is not copied into the build directory
1214 ;; so the tests fail.
1215 #:out-of-source? #f))
1217 `(("bpp-core" ,bpp-core)))
1218 (home-page "http://biopp.univ-montp2.fr")
1219 (synopsis "Bio++ sequence library")
1221 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1222 analysis, phylogenetics, molecular evolution and population genetics. This
1223 library provides sequence-related modules.")
1224 (license license:cecill-c))))
1226 (define-public bppsuite
1227 ;; The last release was in 2014 and the recommended way to install from source
1228 ;; is to clone the git repository, so we do this.
1229 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1230 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
1233 (version (string-append "2.2.0-1." (string-take commit 7)))
1237 (url "http://biopp.univ-montp2.fr/git/bppsuite")
1239 (file-name (string-append name "-" version "-checkout"))
1242 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
1243 (build-system cmake-build-system)
1245 `(#:parallel-build? #f
1246 #:tests? #f)) ; There are no tests.
1250 ("texinfo" ,texinfo)))
1252 `(("bpp-core" ,bpp-core)
1253 ("bpp-seq" ,bpp-seq)
1254 ("bpp-phyl" ,bpp-phyl)
1255 ("bpp-phyl" ,bpp-popgen)))
1256 (home-page "http://biopp.univ-montp2.fr")
1257 (synopsis "Bioinformatics tools written with the Bio++ libraries")
1259 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1260 analysis, phylogenetics, molecular evolution and population genetics. This
1261 package provides command line tools using the Bio++ library.")
1262 (license license:cecill-c))))
1264 (define-public blast+
1271 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
1272 version "/ncbi-blast-" version "+-src.tar.gz"))
1275 "1jlq0afxxgczpp35k6mxh8mn4jzq7vqcnaixk166sfj10wq8v9qh"))
1276 (modules '((guix build utils)))
1279 ;; Remove bundled bzip2, zlib and pcre.
1280 (delete-file-recursively "c++/src/util/compress/bzip2")
1281 (delete-file-recursively "c++/src/util/compress/zlib")
1282 (delete-file-recursively "c++/src/util/regexp")
1283 (substitute* "c++/src/util/compress/Makefile.in"
1284 (("bzip2 zlib api") "api"))
1285 ;; Remove useless msbuild directory
1286 (delete-file-recursively
1287 "c++/src/build-system/project_tree_builder/msbuild")
1289 (build-system gnu-build-system)
1291 `(;; There are two(!) tests for this massive library, and both fail with
1292 ;; "unparsable timing stats".
1293 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
1294 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
1297 #:parallel-build? #f ; not supported
1299 (modify-phases %standard-phases
1300 (add-before 'configure 'set-HOME
1301 ;; $HOME needs to be set at some point during the configure phase
1302 (lambda _ (setenv "HOME" "/tmp") #t))
1303 (add-after 'unpack 'enter-dir
1304 (lambda _ (chdir "c++") #t))
1305 (add-after 'enter-dir 'fix-build-system
1307 (define (which* cmd)
1308 (cond ((string=? cmd "date")
1309 ;; make call to "date" deterministic
1314 (format (current-error-port)
1315 "WARNING: Unable to find absolute path for ~s~%"
1319 ;; Rewrite hardcoded paths to various tools
1320 (substitute* (append '("src/build-system/configure.ac"
1321 "src/build-system/configure"
1322 "src/build-system/helpers/run_with_lock.c"
1323 "scripts/common/impl/if_diff.sh"
1324 "scripts/common/impl/run_with_lock.sh"
1325 "src/build-system/Makefile.configurables.real"
1326 "src/build-system/Makefile.in.top"
1327 "src/build-system/Makefile.meta.gmake=no"
1328 "src/build-system/Makefile.meta.in"
1329 "src/build-system/Makefile.meta_l"
1330 "src/build-system/Makefile.meta_p"
1331 "src/build-system/Makefile.meta_r"
1332 "src/build-system/Makefile.mk.in"
1333 "src/build-system/Makefile.requirements"
1334 "src/build-system/Makefile.rules_with_autodep.in")
1335 (find-files "scripts/common/check" "\\.sh$"))
1336 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1337 (or (which* cmd) all)))
1339 (substitute* (find-files "src/build-system" "^config.*")
1340 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1343 ;; rewrite "/var/tmp" in check script
1344 (substitute* "scripts/common/check/check_make_unix.sh"
1345 (("/var/tmp") "/tmp"))
1347 ;; do not reset PATH
1348 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1350 (("action=/bin/") "action=")
1351 (("export PATH") ":"))
1354 (lambda* (#:key inputs outputs #:allow-other-keys)
1355 (let ((out (assoc-ref outputs "out"))
1356 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1357 (include (string-append (assoc-ref outputs "include")
1358 "/include/ncbi-tools++")))
1359 ;; The 'configure' script doesn't recognize things like
1360 ;; '--enable-fast-install'.
1361 (invoke "./configure.orig"
1362 (string-append "--with-build-root=" (getcwd) "/build")
1363 (string-append "--prefix=" out)
1364 (string-append "--libdir=" lib)
1365 (string-append "--includedir=" include)
1366 (string-append "--with-bz2="
1367 (assoc-ref inputs "bzip2"))
1368 (string-append "--with-z="
1369 (assoc-ref inputs "zlib"))
1370 (string-append "--with-pcre="
1371 (assoc-ref inputs "pcre"))
1372 ;; Each library is built twice by default, once
1373 ;; with "-static" in its name, and again
1378 (outputs '("out" ; 21 MB
1387 ("python" ,python-wrapper)))
1390 (home-page "http://blast.ncbi.nlm.nih.gov")
1391 (synopsis "Basic local alignment search tool")
1393 "BLAST is a popular method of performing a DNA or protein sequence
1394 similarity search, using heuristics to produce results quickly. It also
1395 calculates an “expect value” that estimates how many matches would have
1396 occurred at a given score by chance, which can aid a user in judging how much
1397 confidence to have in an alignment.")
1398 ;; Most of the sources are in the public domain, with the following
1401 ;; * ./c++/include/util/bitset/
1402 ;; * ./c++/src/html/ncbi_menu*.js
1404 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1406 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1408 ;; * ./c++/src/corelib/teamcity_*
1409 (license (list license:public-domain
1415 (define-public bless
1421 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1425 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1426 (modules '((guix build utils)))
1429 ;; Remove bundled boost, pigz, zlib, and .git directory
1430 ;; FIXME: also remove bundled sources for murmurhash3 and
1431 ;; kmc once packaged.
1432 (delete-file-recursively "boost")
1433 (delete-file-recursively "pigz")
1434 (delete-file-recursively "google-sparsehash")
1435 (delete-file-recursively "zlib")
1436 (delete-file-recursively ".git")
1438 (build-system gnu-build-system)
1440 '(#:tests? #f ;no "check" target
1442 (list (string-append "ZLIB="
1443 (assoc-ref %build-inputs "zlib:static")
1445 (string-append "LDFLAGS="
1446 (string-join '("-lboost_filesystem"
1452 (modify-phases %standard-phases
1453 (add-after 'unpack 'do-not-build-bundled-pigz
1454 (lambda* (#:key inputs outputs #:allow-other-keys)
1455 (substitute* "Makefile"
1456 (("cd pigz/pigz-2.3.3; make") ""))
1458 (add-after 'unpack 'patch-paths-to-executables
1459 (lambda* (#:key inputs outputs #:allow-other-keys)
1460 (substitute* "parse_args.cpp"
1461 (("kmc_binary = .*")
1462 (string-append "kmc_binary = \""
1463 (assoc-ref outputs "out")
1465 (("pigz_binary = .*")
1466 (string-append "pigz_binary = \""
1467 (assoc-ref inputs "pigz")
1471 (lambda* (#:key outputs #:allow-other-keys)
1472 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1473 (for-each (lambda (file)
1474 (install-file file bin))
1475 '("bless" "kmc/bin/kmc"))
1477 (delete 'configure))))
1481 `(("openmpi" ,openmpi)
1483 ("sparsehash" ,sparsehash)
1485 ("zlib:static" ,zlib "static")
1487 (supported-systems '("x86_64-linux"))
1488 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1489 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1491 "@dfn{Bloom-filter-based error correction solution for high-throughput
1492 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1493 correction tool for genomic reads produced by @dfn{Next-generation
1494 sequencing} (NGS). BLESS produces accurate correction results with much less
1495 memory compared with previous solutions and is also able to tolerate a higher
1496 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1497 errors at the end of reads.")
1498 (license license:gpl3+)))
1500 (define-public bowtie
1507 (url "https://github.com/BenLangmead/bowtie2.git")
1508 (commit (string-append "v" version))))
1509 (file-name (git-file-name name version))
1512 "1zl3cf327y2p7p03cavymbh7b00djc7lncfaqih33n96iy9q8ibp"))
1513 (modules '((guix build utils)))
1516 (substitute* "Makefile"
1517 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1518 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1519 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
1521 (build-system gnu-build-system)
1526 (string-append "prefix=" (assoc-ref %outputs "out")))
1528 (modify-phases %standard-phases
1533 "scripts/test/simple_tests.pl"
1534 "--bowtie2=./bowtie2"
1535 "--bowtie2-build=./bowtie2-build")
1540 ("python" ,python-wrapper)))
1543 ("perl-clone" ,perl-clone)
1544 ("perl-test-deep" ,perl-test-deep)
1545 ("perl-test-simple" ,perl-test-simple)))
1546 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1547 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1549 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1550 reads to long reference sequences. It is particularly good at aligning reads
1551 of about 50 up to 100s or 1,000s of characters, and particularly good at
1552 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1553 genome with an FM Index to keep its memory footprint small: for the human
1554 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1555 gapped, local, and paired-end alignment modes.")
1556 (supported-systems '("x86_64-linux"))
1557 (license license:gpl3+)))
1559 (define-public bowtie1
1565 (uri (string-append "mirror://sourceforge/bowtie-bio/bowtie/"
1566 version "/bowtie-src-x86_64.zip"))
1569 "0vmiqdhc9dzyfy9sh6vgi7k9xy2hiw8g87vbamnc6cgpm179zsa4"))
1570 (modules '((guix build utils)))
1572 '(substitute* "Makefile"
1573 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1574 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1575 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1576 (build-system gnu-build-system)
1578 '(#:tests? #f ; no "check" target
1581 (string-append "prefix=" (assoc-ref %outputs "out")))
1583 (modify-phases %standard-phases
1584 (delete 'configure))))
1588 (supported-systems '("x86_64-linux"))
1589 (home-page "http://bowtie-bio.sourceforge.net/index.shtml")
1590 (synopsis "Fast aligner for short nucleotide sequence reads")
1592 "Bowtie is a fast, memory-efficient short read aligner. It aligns short
1593 DNA sequences (reads) to the human genome at a rate of over 25 million 35-bp
1594 reads per hour. Bowtie indexes the genome with a Burrows-Wheeler index to
1595 keep its memory footprint small: typically about 2.2 GB for the human
1596 genome (2.9 GB for paired-end).")
1597 (license license:artistic2.0)))
1599 (define-public tophat
1606 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1610 "19add02kv2xhd6ihd779dr7x35ggym3jqr0m5c4315i1yfb0p11p"))
1611 (modules '((guix build utils)))
1614 ;; Remove bundled SeqAn and samtools
1615 (delete-file-recursively "src/SeqAn-1.4.2")
1616 (delete-file-recursively "src/samtools-0.1.18")
1618 (build-system gnu-build-system)
1620 '(#:parallel-build? #f ; not supported
1622 (modify-phases %standard-phases
1623 (add-after 'unpack 'use-system-samtools
1624 (lambda* (#:key inputs #:allow-other-keys)
1625 (substitute* "src/Makefile.in"
1626 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1627 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1628 (("SAMPROG = samtools_0\\.1\\.18") "")
1629 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1630 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1631 (substitute* '("src/common.cpp"
1633 (("samtools_0.1.18") (which "samtools")))
1634 (substitute* '("src/common.h"
1635 "src/bam2fastx.cpp")
1636 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1637 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1638 (substitute* '("src/bwt_map.h"
1640 "src/align_status.h")
1641 (("#include <bam.h>") "#include <samtools/bam.h>")
1642 (("#include <sam.h>") "#include <samtools/sam.h>"))
1645 `(("gcc" ,gcc-5))) ;; doesn't build with later versions
1649 ("ncurses" ,ncurses)
1651 ("python" ,python-2)
1652 ("samtools" ,samtools-0.1)
1655 (home-page "https://ccb.jhu.edu/software/tophat/index.shtml")
1656 (synopsis "Spliced read mapper for RNA-Seq data")
1658 "TopHat is a fast splice junction mapper for nucleotide sequence
1659 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1660 mammalian-sized genomes using the ultra high-throughput short read
1661 aligner Bowtie, and then analyzes the mapping results to identify
1662 splice junctions between exons.")
1663 ;; TopHat is released under the Boost Software License, Version 1.0
1664 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1665 (license license:boost1.0)))
1674 "https://github.com/lh3/bwa/releases/download/v"
1675 version "/bwa-" version ".tar.bz2"))
1678 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1679 (build-system gnu-build-system)
1681 '(#:tests? #f ;no "check" target
1683 (modify-phases %standard-phases
1685 (lambda* (#:key outputs #:allow-other-keys)
1686 (let* ((out (assoc-ref outputs "out"))
1687 (bin (string-append out "/bin"))
1688 (lib (string-append out "/lib"))
1689 (doc (string-append out "/share/doc/bwa"))
1690 (man (string-append out "/share/man/man1")))
1691 (install-file "bwa" bin)
1692 (install-file "libbwa.a" lib)
1693 (install-file "README.md" doc)
1694 (install-file "bwa.1" man))
1696 ;; no "configure" script
1697 (delete 'configure))))
1698 (inputs `(("zlib" ,zlib)))
1699 ;; Non-portable SSE instructions are used so building fails on platforms
1700 ;; other than x86_64.
1701 (supported-systems '("x86_64-linux"))
1702 (home-page "http://bio-bwa.sourceforge.net/")
1703 (synopsis "Burrows-Wheeler sequence aligner")
1705 "BWA is a software package for mapping low-divergent sequences against a
1706 large reference genome, such as the human genome. It consists of three
1707 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1708 designed for Illumina sequence reads up to 100bp, while the rest two for
1709 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1710 features such as long-read support and split alignment, but BWA-MEM, which is
1711 the latest, is generally recommended for high-quality queries as it is faster
1712 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1713 70-100bp Illumina reads.")
1714 (license license:gpl3+)))
1716 (define-public bwa-pssm
1717 (package (inherit bwa)
1723 (url "https://github.com/pkerpedjiev/bwa-pssm.git")
1725 (file-name (git-file-name name version))
1728 "076c4q0cdqz8jgylb067y9zmvxglppnzi3qiscn0xiypgc6lgb5r"))))
1729 (build-system gnu-build-system)
1734 (home-page "http://bwa-pssm.binf.ku.dk/")
1735 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1737 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1738 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1739 existing aligners it is fast and sensitive. Unlike most other aligners,
1740 however, it is also adaptible in the sense that one can direct the alignment
1741 based on known biases within the data set. It is coded as a modification of
1742 the original BWA alignment program and shares the genome index structure as
1743 well as many of the command line options.")
1744 (license license:gpl3+)))
1746 (define-public bwa-meth
1753 (url "https://github.com/brentp/bwa-meth.git")
1754 (commit (string-append "v" version))))
1755 (file-name (git-file-name name version))
1758 "17j31i7zws5j7mhsq9x3qgkxly6mlmrgwhfq0qbflgxrmx04yaiz"))))
1759 (build-system python-build-system)
1762 (modify-phases %standard-phases
1763 (add-after 'unpack 'keep-references-to-bwa
1764 (lambda* (#:key inputs #:allow-other-keys)
1765 (substitute* "bwameth.py"
1766 (("bwa (mem|index)" _ command)
1767 (string-append (which "bwa") " " command))
1768 ;; There's an ill-advised check for "samtools" on PATH.
1774 `(("python-toolshed" ,python-toolshed)))
1775 (home-page "https://github.com/brentp/bwa-meth")
1776 (synopsis "Fast and accurante alignment of BS-Seq reads")
1778 "BWA-Meth works for single-end reads and for paired-end reads from the
1779 directional protocol (most common). It uses the method employed by
1780 methylcoder and Bismark of in silico conversion of all C's to T's in both
1781 reference and reads. It recovers the original read (needed to tabulate
1782 methylation) by attaching it as a comment which BWA appends as a tag to the
1783 read. It performs favorably to existing aligners gauged by number of on and
1784 off-target reads for a capture method that targets CpG-rich region.")
1785 (license license:expat)))
1787 (define-public python-bx-python
1789 (name "python-bx-python")
1793 (uri (pypi-uri "bx-python" version))
1796 "11kksg2rbzihpmcid823xvg42xi88m7sz58rzk29abybkxy0rszs"))))
1797 (build-system python-build-system)
1798 ;; Tests fail because test data are not included
1799 (arguments '(#:tests? #f))
1801 `(("python-numpy" ,python-numpy)
1802 ("python-six" ,python-six)))
1806 `(("python-lzo" ,python-lzo)
1807 ("python-nose" ,python-nose)
1808 ("python-cython" ,python-cython)))
1809 (home-page "https://github.com/bxlab/bx-python")
1810 (synopsis "Tools for manipulating biological data")
1812 "bx-python provides tools for manipulating biological data, particularly
1813 multiple sequence alignments.")
1814 (license license:expat)))
1816 (define-public python2-bx-python
1817 (package-with-python2 python-bx-python))
1819 (define-public python-pysam
1821 (name "python-pysam")
1825 ;; Test data is missing on PyPi.
1827 (url "https://github.com/pysam-developers/pysam.git")
1828 (commit (string-append "v" version))))
1829 (file-name (git-file-name name version))
1832 "1vj367w6xbn9bpmksm162l1aipf7cj97h1q83y7jcpm33ihwpf7x"))
1833 (modules '((guix build utils)))
1835 ;; Drop bundled htslib. TODO: Also remove samtools
1837 (delete-file-recursively "htslib")
1839 (build-system python-build-system)
1841 `(#:modules ((ice-9 ftw)
1843 (guix build python-build-system)
1846 (modify-phases %standard-phases
1847 (add-before 'build 'set-flags
1848 (lambda* (#:key inputs #:allow-other-keys)
1849 (setenv "HTSLIB_MODE" "external")
1850 (setenv "HTSLIB_LIBRARY_DIR"
1851 (string-append (assoc-ref inputs "htslib") "/lib"))
1852 (setenv "HTSLIB_INCLUDE_DIR"
1853 (string-append (assoc-ref inputs "htslib") "/include"))
1854 (setenv "LDFLAGS" "-lncurses")
1855 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1858 (lambda* (#:key inputs outputs #:allow-other-keys)
1859 ;; This file contains tests that require a connection to the
1861 (delete-file "tests/tabix_test.py")
1862 ;; FIXME: This test fails
1863 (delete-file "tests/AlignmentFile_test.py")
1864 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1865 (setenv "PYTHONPATH"
1867 (getenv "PYTHONPATH")
1868 ":" (getcwd) "/build/"
1869 (car (scandir "build"
1870 (negate (cut string-prefix? "." <>))))))
1871 ;; Step out of source dir so python does not import from CWD.
1872 (with-directory-excursion "tests"
1873 (setenv "HOME" "/tmp")
1874 (invoke "make" "-C" "pysam_data")
1875 (invoke "make" "-C" "cbcf_data")
1876 ;; Running nosetests without explicitly asking for a single
1877 ;; process leads to a crash. Running with multiple processes
1878 ;; fails because the tests are not designed to run in parallel.
1880 ;; FIXME: tests keep timing out on some systems.
1881 (invoke "nosetests" "-v" "--processes" "1")))))))
1883 `(("htslib" ,htslib))) ; Included from installed header files.
1885 `(("ncurses" ,ncurses)
1889 `(("python-cython" ,python-cython)
1890 ;; Dependencies below are are for tests only.
1891 ("samtools" ,samtools)
1892 ("bcftools" ,bcftools)
1893 ("python-nose" ,python-nose)))
1894 (home-page "https://github.com/pysam-developers/pysam")
1895 (synopsis "Python bindings to the SAMtools C API")
1897 "Pysam is a Python module for reading and manipulating files in the
1898 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1899 also includes an interface for tabix.")
1900 (license license:expat)))
1902 (define-public python2-pysam
1903 (package-with-python2 python-pysam))
1905 (define-public python-twobitreader
1907 (name "python-twobitreader")
1912 (url "https://github.com/benjschiller/twobitreader")
1914 (file-name (git-file-name name version))
1917 "1qbxvv1h58cismbk1anpjrkpghsaiy64a11ir3lhy6qch6xf8n62"))))
1918 (build-system python-build-system)
1919 ;; Tests are not included
1920 (arguments '(#:tests? #f))
1922 `(("python-sphinx" ,python-sphinx)))
1923 (home-page "https://github.com/benjschiller/twobitreader")
1924 (synopsis "Python library for reading .2bit files")
1926 "twobitreader is a Python library for reading .2bit files as used by the
1927 UCSC genome browser.")
1928 (license license:artistic2.0)))
1930 (define-public python2-twobitreader
1931 (package-with-python2 python-twobitreader))
1933 (define-public python-plastid
1935 (name "python-plastid")
1939 (uri (pypi-uri "plastid" version))
1942 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1943 (build-system python-build-system)
1945 ;; Some test files are not included.
1948 `(("python-numpy" ,python-numpy)
1949 ("python-scipy" ,python-scipy)
1950 ("python-pandas" ,python-pandas)
1951 ("python-pysam" ,python-pysam)
1952 ("python-matplotlib" ,python-matplotlib)
1953 ("python-biopython" ,python-biopython)
1954 ("python-twobitreader" ,python-twobitreader)
1955 ("python-termcolor" ,python-termcolor)))
1957 `(("python-cython" ,python-cython)
1958 ("python-nose" ,python-nose)))
1959 (home-page "https://github.com/joshuagryphon/plastid")
1960 (synopsis "Python library for genomic analysis")
1962 "plastid is a Python library for genomic analysis – in particular,
1963 high-throughput sequencing data – with an emphasis on simplicity.")
1964 (license license:bsd-3)))
1966 (define-public python2-plastid
1967 (package-with-python2 python-plastid))
1969 (define-public tetoolkit
1976 (url "https://github.com/mhammell-laboratory/tetoolkit.git")
1978 (file-name (git-file-name name version))
1981 "1yzi0kfpzip8zpjb82x1ik6h22yzfyjiz2dv85v6as2awwqvk807"))))
1982 (build-system python-build-system)
1984 `(#:python ,python-2 ; not guaranteed to work with Python 3
1986 (modify-phases %standard-phases
1987 (add-after 'unpack 'make-writable
1989 (for-each make-file-writable (find-files "."))
1991 (add-after 'unpack 'patch-invocations
1992 (lambda* (#:key inputs #:allow-other-keys)
1993 (substitute* '("bin/TEtranscripts"
1996 (string-append "'" (which "sort") " "))
1998 (string-append "'" (which "rm") " -f "))
1999 (("'Rscript'") (string-append "'" (which "Rscript") "'")))
2000 (substitute* "TEToolkit/IO/ReadInputs.py"
2001 (("BamToBED") (which "bamToBed")))
2002 (substitute* "TEToolkit/Normalization.py"
2004 (string-append "\"" (which "Rscript") "\"")))
2006 (add-after 'install 'wrap-program
2007 (lambda* (#:key outputs #:allow-other-keys)
2008 ;; Make sure the executables find R packages.
2009 (let ((out (assoc-ref outputs "out")))
2012 (wrap-program (string-append out "/bin/" script)
2013 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
2018 `(("coreutils" ,coreutils)
2019 ("bedtools" ,bedtools)
2020 ("python-argparse" ,python2-argparse)
2021 ("python-pysam" ,python2-pysam)
2022 ("r-minimal" ,r-minimal)
2023 ("r-deseq2" ,r-deseq2)))
2024 (home-page "https://github.com/mhammell-laboratory/tetoolkit")
2025 (synopsis "Transposable elements in differential enrichment analysis")
2027 "This is package for including transposable elements in differential
2028 enrichment analysis of sequencing datasets. TEtranscripts and TEcount take
2029 RNA-seq (and similar data) and annotates reads to both genes and transposable
2030 elements. TEtranscripts then performs differential analysis using DESeq2.
2031 Note that TEtranscripts and TEcount rely on specially curated GTF files, which
2032 are not included due to their size.")
2033 (license license:gpl3+)))
2035 (define-public cd-hit
2041 (uri (string-append "https://github.com/weizhongli/cdhit"
2042 "/releases/download/V" version
2044 "-2017-0621-source.tar.gz"))
2047 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
2048 (build-system gnu-build-system)
2050 `(#:tests? #f ; there are no tests
2052 ;; Executables are copied directly to the PREFIX.
2053 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin")
2054 ;; Support longer sequences (e.g. Pacbio sequences)
2057 (modify-phases %standard-phases
2058 ;; No "configure" script
2060 ;; Remove sources of non-determinism
2061 (add-after 'unpack 'be-timeless
2063 (substitute* "cdhit-utility.c++"
2064 ((" \\(built on \" __DATE__ \"\\)") ""))
2065 (substitute* "cdhit-common.c++"
2066 (("__DATE__") "\"0\"")
2067 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
2069 ;; The "install" target does not create the target directory.
2070 (add-before 'install 'create-target-dir
2071 (lambda* (#:key outputs #:allow-other-keys)
2072 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
2076 (home-page "http://weizhongli-lab.org/cd-hit/")
2077 (synopsis "Cluster and compare protein or nucleotide sequences")
2079 "CD-HIT is a program for clustering and comparing protein or nucleotide
2080 sequences. CD-HIT is designed to be fast and handle extremely large
2082 ;; The manual says: "It can be copied under the GNU General Public License
2083 ;; version 2 (GPLv2)."
2084 (license license:gpl2)))
2086 (define-public clipper
2093 (url "https://github.com/YeoLab/clipper.git")
2095 (file-name (git-file-name name version))
2098 "0fja1rj84wp9vpj8rxpj3n8zqzcqq454m904yp9as1w4phccirjb"))
2099 (modules '((guix build utils)))
2102 ;; remove unnecessary setup dependency
2103 (substitute* "setup.py"
2104 (("setup_requires = .*") ""))
2106 (build-system python-build-system)
2108 `(#:python ,python-2 ; only Python 2 is supported
2110 (modify-phases %standard-phases
2111 ;; This is fixed in upstream commit
2112 ;; f6c2990198f906bf97730d95695b4bd5a6d01ddb.
2113 (add-after 'unpack 'fix-typo
2115 (substitute* "clipper/src/readsToWiggle.pyx"
2119 `(("htseq" ,python2-htseq)
2120 ("python-pybedtools" ,python2-pybedtools)
2121 ("python-cython" ,python2-cython)
2122 ("python-scikit-learn" ,python2-scikit-learn)
2123 ("python-matplotlib" ,python2-matplotlib)
2124 ("python-pandas" ,python2-pandas)
2125 ("python-pysam" ,python2-pysam)
2126 ("python-numpy" ,python2-numpy)
2127 ("python-scipy" ,python2-scipy)))
2129 `(("python-mock" ,python2-mock) ; for tests
2130 ("python-nose" ,python2-nose) ; for tests
2131 ("python-pytz" ,python2-pytz))) ; for tests
2132 (home-page "https://github.com/YeoLab/clipper")
2133 (synopsis "CLIP peak enrichment recognition")
2135 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
2136 (license license:gpl2)))
2138 (define-public codingquarry
2140 (name "codingquarry")
2145 "mirror://sourceforge/codingquarry/CodingQuarry_v"
2149 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
2150 (build-system gnu-build-system)
2152 '(#:tests? #f ; no "check" target
2154 (modify-phases %standard-phases
2157 (lambda* (#:key outputs #:allow-other-keys)
2158 (let* ((out (assoc-ref outputs "out"))
2159 (bin (string-append out "/bin"))
2160 (doc (string-append out "/share/doc/codingquarry")))
2161 (install-file "INSTRUCTIONS.pdf" doc)
2162 (copy-recursively "QuarryFiles"
2163 (string-append out "/QuarryFiles"))
2164 (install-file "CodingQuarry" bin)
2165 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin))
2167 (inputs `(("openmpi" ,openmpi)))
2168 (native-search-paths
2169 (list (search-path-specification
2170 (variable "QUARRY_PATH")
2171 (files '("QuarryFiles")))))
2172 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
2173 (synopsis "Fungal gene predictor")
2174 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
2175 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
2176 (home-page "https://sourceforge.net/projects/codingquarry/")
2177 (license license:gpl3+)))
2179 (define-public couger
2186 "http://couger.oit.duke.edu/static/assets/COUGER"
2190 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
2191 (build-system gnu-build-system)
2195 (modify-phases %standard-phases
2200 (lambda* (#:key outputs #:allow-other-keys)
2201 (let* ((out (assoc-ref outputs "out"))
2202 (bin (string-append out "/bin")))
2203 (copy-recursively "src" (string-append out "/src"))
2205 ;; Add "src" directory to module lookup path.
2206 (substitute* "couger"
2208 (string-append "import sys\nsys.path.append(\""
2209 out "\")\nfrom argparse")))
2210 (install-file "couger" bin))
2213 'install 'wrap-program
2214 (lambda* (#:key inputs outputs #:allow-other-keys)
2215 ;; Make sure 'couger' runs with the correct PYTHONPATH.
2216 (let* ((out (assoc-ref outputs "out"))
2217 (path (getenv "PYTHONPATH")))
2218 (wrap-program (string-append out "/bin/couger")
2219 `("PYTHONPATH" ":" prefix (,path))))
2222 `(("python" ,python-2)
2223 ("python2-pillow" ,python2-pillow)
2224 ("python2-numpy" ,python2-numpy)
2225 ("python2-scipy" ,python2-scipy)
2226 ("python2-matplotlib" ,python2-matplotlib)))
2228 `(("r-minimal" ,r-minimal)
2230 ("randomjungle" ,randomjungle)))
2232 `(("unzip" ,unzip)))
2233 (home-page "http://couger.oit.duke.edu")
2234 (synopsis "Identify co-factors in sets of genomic regions")
2236 "COUGER can be applied to any two sets of genomic regions bound by
2237 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
2238 putative co-factors that provide specificity to each TF. The framework
2239 determines the genomic targets uniquely-bound by each TF, and identifies a
2240 small set of co-factors that best explain the in vivo binding differences
2241 between the two TFs.
2243 COUGER uses classification algorithms (support vector machines and random
2244 forests) with features that reflect the DNA binding specificities of putative
2245 co-factors. The features are generated either from high-throughput TF-DNA
2246 binding data (from protein binding microarray experiments), or from large
2247 collections of DNA motifs.")
2248 (license license:gpl3+)))
2250 (define-public clustal-omega
2252 (name "clustal-omega")
2256 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
2260 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
2261 (build-system gnu-build-system)
2263 `(("argtable" ,argtable)))
2264 (home-page "http://www.clustal.org/omega/")
2265 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
2267 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
2268 program for protein and DNA/RNA. It produces high quality MSAs and is capable
2269 of handling data-sets of hundreds of thousands of sequences in reasonable
2271 (license license:gpl2+)))
2273 (define-public crossmap
2279 (uri (pypi-uri "CrossMap" version))
2282 "1sb2f2qbxya4fzw3yjl09vbrs8vfmw22zrygrvz004sf9gb1vkan"))))
2283 (build-system python-build-system)
2285 `(("python-bx-python" ,python-bx-python)
2286 ("python-numpy" ,python-numpy)
2287 ("python-pybigwig" ,python-pybigwig)
2288 ("python-pysam" ,python-pysam)
2291 `(("python-cython" ,python-cython)
2292 ("python-nose" ,python-nose)))
2293 (home-page "http://crossmap.sourceforge.net/")
2294 (synopsis "Convert genome coordinates between assemblies")
2296 "CrossMap is a program for conversion of genome coordinates or annotation
2297 files between different genome assemblies. It supports most commonly used
2298 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
2299 (license license:gpl2+)))
2301 (define-public python-dnaio
2303 (name "python-dnaio")
2308 (uri (pypi-uri "dnaio" version))
2311 "0f16m7hdlm0fz1n7y5asy0v9ghyrq17ni1p9iybq22ddzyd49r27"))))
2312 (build-system python-build-system)
2314 `(("python-cython" ,python-cython)
2315 ("python-pytest" ,python-pytest)
2316 ("python-xopen" ,python-xopen)))
2317 (home-page "https://github.com/marcelm/dnaio/")
2318 (synopsis "Read FASTA and FASTQ files efficiently")
2320 "dnaio is a Python library for fast parsing of FASTQ and also FASTA
2321 files. The code was previously part of the cutadapt tool.")
2322 (license license:expat)))
2324 (define-public cutadapt
2330 (uri (pypi-uri "cutadapt" version))
2333 "1vqmsfkm6llxzmsz9wcfcvzx9a9f8iabvwik2rbyn7nc4wm25z89"))))
2334 (build-system python-build-system)
2336 `(("python-dnaio" ,python-dnaio)
2337 ("python-xopen" ,python-xopen)))
2339 `(("python-cython" ,python-cython)
2340 ("python-pytest" ,python-pytest)
2341 ("python-setuptools-scm" ,python-setuptools-scm)))
2342 (home-page "https://cutadapt.readthedocs.io/en/stable/")
2343 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
2345 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
2346 other types of unwanted sequence from high-throughput sequencing reads.")
2347 (license license:expat)))
2349 (define-public libbigwig
2356 (url "https://github.com/dpryan79/libBigWig.git")
2358 (file-name (git-file-name name version))
2361 "09693dmf1scdac5pyq6qyn8b4mcipvnmc370k9a5z41z81m3dcsj"))))
2362 (build-system gnu-build-system)
2364 `(#:test-target "test"
2365 #:tests? #f ; tests require access to the web
2368 (string-append "prefix=" (assoc-ref %outputs "out")))
2370 (modify-phases %standard-phases
2371 (delete 'configure))))
2376 `(("doxygen" ,doxygen)
2378 ("python" ,python-2)))
2379 (home-page "https://github.com/dpryan79/libBigWig")
2380 (synopsis "C library for handling bigWig files")
2382 "This package provides a C library for parsing local and remote BigWig
2384 (license license:expat)))
2386 (define-public python-pybigwig
2388 (name "python-pybigwig")
2392 (uri (pypi-uri "pyBigWig" version))
2395 "00w4kfnm2c5l7wdwr2nj1z5djv8kzgf7h1zhsgv6njff1rwr26g0"))
2396 (modules '((guix build utils)))
2399 ;; Delete bundled libBigWig sources
2400 (delete-file-recursively "libBigWig")
2402 (build-system python-build-system)
2405 (modify-phases %standard-phases
2406 (add-after 'unpack 'link-with-libBigWig
2407 (lambda* (#:key inputs #:allow-other-keys)
2408 (substitute* "setup.py"
2409 (("libs=\\[") "libs=[\"BigWig\", "))
2412 `(("python-numpy" ,python-numpy)))
2414 `(("libbigwig" ,libbigwig)
2417 (home-page "https://github.com/dpryan79/pyBigWig")
2418 (synopsis "Access bigWig files in Python using libBigWig")
2420 "This package provides Python bindings to the libBigWig library for
2421 accessing bigWig files.")
2422 (license license:expat)))
2424 (define-public python2-pybigwig
2425 (package-with-python2 python-pybigwig))
2427 (define-public python-dendropy
2429 (name "python-dendropy")
2434 ;; Source from GitHub so that tests are included.
2436 (url "https://github.com/jeetsukumaran/DendroPy.git")
2437 (commit (string-append "v" version))))
2438 (file-name (git-file-name name version))
2441 "097hfyv2kaf4x92i4rjx0paw2cncxap48qivv8zxng4z7nhid0x9"))))
2442 (build-system python-build-system)
2443 (home-page "https://dendropy.org/")
2444 (synopsis "Library for phylogenetics and phylogenetic computing")
2446 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
2447 writing, simulation, processing and manipulation of phylogenetic
2448 trees (phylogenies) and characters.")
2449 (license license:bsd-3)))
2451 (define-public python2-dendropy
2452 (let ((base (package-with-python2 python-dendropy)))
2457 (modify-phases %standard-phases
2458 (add-after 'unpack 'remove-failing-test
2460 ;; This test fails when the full test suite is run, as documented
2461 ;; at https://github.com/jeetsukumaran/DendroPy/issues/74
2462 (substitute* "tests/test_dataio_nexml_reader_tree_list.py"
2463 (("test_collection_comments_and_annotations")
2464 "do_not_test_collection_comments_and_annotations"))
2466 ,@(package-arguments base))))))
2468 (define-public python-py2bit
2470 (name "python-py2bit")
2475 (uri (pypi-uri "py2bit" version))
2478 "1vw2nvw1yrl7ikkqsqs1pg239yr5nspvd969r1x9arms1k25a1a5"))))
2479 (build-system python-build-system)
2480 (home-page "https://github.com/dpryan79/py2bit")
2481 (synopsis "Access 2bit files using lib2bit")
2483 "This package provides Python bindings for lib2bit to access 2bit files
2485 (license license:expat)))
2487 (define-public deeptools
2494 (url "https://github.com/deeptools/deepTools.git")
2496 (file-name (git-file-name name version))
2499 "1vggnf52g6q2vifdl4cyi7s2fnfqq0ky2zrkj5zv2qfzsc3p3siw"))))
2500 (build-system python-build-system)
2503 (modify-phases %standard-phases
2504 ;; This phase fails, but it's not needed.
2505 (delete 'reset-gzip-timestamps))))
2507 `(("python-plotly" ,python-plotly)
2508 ("python-scipy" ,python-scipy)
2509 ("python-numpy" ,python-numpy)
2510 ("python-numpydoc" ,python-numpydoc)
2511 ("python-matplotlib" ,python-matplotlib)
2512 ("python-pysam" ,python-pysam)
2513 ("python-py2bit" ,python-py2bit)
2514 ("python-pybigwig" ,python-pybigwig)))
2516 `(("python-mock" ,python-mock) ;for tests
2517 ("python-nose" ,python-nose) ;for tests
2518 ("python-pytz" ,python-pytz))) ;for tests
2519 (home-page "https://github.com/deeptools/deepTools")
2520 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2522 "DeepTools addresses the challenge of handling the large amounts of data
2523 that are now routinely generated from DNA sequencing centers. To do so,
2524 deepTools contains useful modules to process the mapped reads data to create
2525 coverage files in standard bedGraph and bigWig file formats. By doing so,
2526 deepTools allows the creation of normalized coverage files or the comparison
2527 between two files (for example, treatment and control). Finally, using such
2528 normalized and standardized files, multiple visualizations can be created to
2529 identify enrichments with functional annotations of the genome.")
2530 (license license:gpl3+)))
2532 (define-public delly
2539 (url "https://github.com/dellytools/delly.git")
2540 (commit (string-append "v" version))))
2541 (file-name (git-file-name name version))
2543 (base32 "034jqsxswy9gqdh2zkgc1js99qkv75ks4xvzgmh0284sraagv61z"))
2544 (modules '((guix build utils)))
2547 (delete-file-recursively "src/htslib")
2549 (build-system gnu-build-system)
2551 `(#:tests? #f ; There are no tests to run.
2553 (list "PARALLEL=1" ; Allow parallel execution at run-time.
2554 (string-append "prefix=" (assoc-ref %outputs "out")))
2556 (modify-phases %standard-phases
2557 (delete 'configure) ; There is no configure phase.
2558 (add-after 'install 'install-templates
2559 (lambda* (#:key outputs #:allow-other-keys)
2560 (let ((templates (string-append (assoc-ref outputs "out")
2561 "/share/delly/templates")))
2563 (copy-recursively "excludeTemplates" templates)
2570 (home-page "https://github.com/dellytools/delly")
2571 (synopsis "Integrated structural variant prediction method")
2572 (description "Delly is an integrated structural variant prediction method
2573 that can discover and genotype deletions, tandem duplications, inversions and
2574 translocations at single-nucleotide resolution in short-read massively parallel
2575 sequencing data. It uses paired-ends and split-reads to sensitively and
2576 accurately delineate genomic rearrangements throughout the genome.")
2577 (license license:gpl3+)))
2579 (define-public diamond
2586 (url "https://github.com/bbuchfink/diamond.git")
2587 (commit (string-append "v" version))))
2588 (file-name (git-file-name name version))
2591 "0k6f3kb6cniw11xw6763kkbs1sl0yack7xsy7q5fl5v170ssphq4"))))
2592 (build-system cmake-build-system)
2594 '(#:tests? #f ; no "check" target
2596 (modify-phases %standard-phases
2597 (add-after 'unpack 'remove-native-compilation
2599 (substitute* "CMakeLists.txt" (("-march=native") ""))
2603 (home-page "https://github.com/bbuchfink/diamond")
2604 (synopsis "Accelerated BLAST compatible local sequence aligner")
2606 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2607 translated DNA query sequences against a protein reference database (BLASTP
2608 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2609 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2610 data and settings.")
2611 (license license:agpl3+)))
2613 (define-public discrover
2621 (url "https://github.com/maaskola/discrover.git")
2623 (file-name (git-file-name name version))
2626 "173fwi2vb6a5kp406hm3jj6j7v4whww796f2qcygp4rpvamh307y"))))
2627 (build-system cmake-build-system)
2629 `(#:tests? #f ; there are no tests
2631 (modify-phases %standard-phases
2632 (add-after 'unpack 'fix-latex-errors
2634 (with-fluids ((%default-port-encoding #f))
2635 (substitute* "doc/references.bib"
2636 (("\\{S\\}illanp[^,]+,")
2637 "{S}illanp{\\\"a}{\\\"a},")))
2638 ;; XXX: I just can't get pdflatex to not complain about these
2639 ;; characters. They end up in the manual via the generated
2640 ;; discrover-cli-help.txt.
2641 (substitute* "src/hmm/cli.cpp"
2645 ;; This seems to be a syntax error.
2646 (substitute* "doc/discrover-manual.tex"
2647 (("theverbbox\\[t\\]") "theverbbox"))
2649 (add-after 'unpack 'add-missing-includes
2651 (substitute* "src/executioninformation.hpp"
2652 (("#define EXECUTIONINFORMATION_HPP" line)
2653 (string-append line "\n#include <random>")))
2654 (substitute* "src/plasma/fasta.hpp"
2655 (("#define FASTA_HPP" line)
2656 (string-append line "\n#include <random>")))
2658 ;; FIXME: this is needed because we're using texlive-union, which
2659 ;; doesn't handle fonts correctly. It expects to be able to generate
2660 ;; fonts in the home directory.
2661 (add-before 'build 'setenv-HOME
2662 (lambda _ (setenv "HOME" "/tmp") #t)))))
2666 ("rmath-standalone" ,rmath-standalone)))
2668 `(("texlive" ,(texlive-union (list texlive-fonts-cm
2669 texlive-fonts-amsfonts
2672 texlive-latex-examplep
2673 texlive-latex-hyperref
2675 texlive-latex-natbib
2676 texlive-bibtex ; style files used by natbib
2677 texlive-latex-pgf ; tikz
2678 texlive-latex-verbatimbox)))
2679 ("imagemagick" ,imagemagick)))
2680 (home-page "https://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2681 (synopsis "Discover discriminative nucleotide sequence motifs")
2682 (description "Discrover is a motif discovery method to find binding sites
2683 of nucleic acid binding proteins.")
2684 (license license:gpl3+)))
2686 (define-public eigensoft
2694 (url "https://github.com/DReichLab/EIG.git")
2695 (commit (string-append "v" version))))
2696 (file-name (git-file-name name version))
2699 "1c141fqvhnzibmnf22sv23vbmzm20kjjyrib44cfh75wyndp2d9k"))
2700 (modules '((guix build utils)))
2701 ;; Remove pre-built binaries.
2703 (delete-file-recursively "bin")
2706 (build-system gnu-build-system)
2708 `(#:tests? #f ; There are no tests.
2709 #:make-flags '("CC=gcc")
2711 (modify-phases %standard-phases
2712 ;; There is no configure phase, but the Makefile is in a
2715 (lambda _ (chdir "src") #t))
2716 ;; The provided install target only copies executables to
2717 ;; the "bin" directory in the build root.
2718 (add-after 'install 'actually-install
2719 (lambda* (#:key outputs #:allow-other-keys)
2720 (let* ((out (assoc-ref outputs "out"))
2721 (bin (string-append out "/bin")))
2722 (for-each (lambda (file)
2723 (install-file file bin))
2724 (find-files "../bin" ".*"))
2729 ("openblas" ,openblas)
2731 ("gfortran" ,gfortran "lib")))
2732 (home-page "https://github.com/DReichLab/EIG")
2733 (synopsis "Tools for population genetics")
2734 (description "The EIGENSOFT package provides tools for population
2735 genetics and stratification correction. EIGENSOFT implements methods commonly
2736 used in population genetics analyses such as PCA, computation of Tracy-Widom
2737 statistics, and finding related individuals in structured populations. It
2738 comes with a built-in plotting script and supports multiple file formats and
2739 quantitative phenotypes.")
2740 ;; The license of the eigensoft tools is Expat, but since it's
2741 ;; linking with the GNU Scientific Library (GSL) the effective
2742 ;; license is the GPL.
2743 (license license:gpl3+)))
2745 (define-public edirect
2748 (version "12.1.20190829")
2751 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect"
2752 "/versions/" version
2753 "/edirect-" version ".tar.gz"))
2756 "1xb330z28dgp7slrvp8r7rgncsasv9lpcpqim571yg728dq7xdik"))))
2757 (build-system perl-build-system)
2760 (modify-phases %standard-phases
2763 (delete 'check) ; simple check after install
2765 (lambda* (#:key outputs #:allow-other-keys)
2766 (install-file "edirect.pl"
2767 (string-append (assoc-ref outputs "out") "/bin"))
2769 (add-after 'install 'wrap-program
2770 (lambda* (#:key outputs #:allow-other-keys)
2771 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2772 (let* ((out (assoc-ref outputs "out"))
2773 (path (getenv "PERL5LIB")))
2774 (wrap-program (string-append out "/bin/edirect.pl")
2775 `("PERL5LIB" ":" prefix (,path))))
2777 (add-after 'wrap-program 'check
2778 (lambda* (#:key outputs #:allow-other-keys)
2779 (invoke (string-append (assoc-ref outputs "out")
2784 `(("perl-html-parser" ,perl-html-parser)
2785 ("perl-encode-locale" ,perl-encode-locale)
2786 ("perl-file-listing" ,perl-file-listing)
2787 ("perl-html-tagset" ,perl-html-tagset)
2788 ("perl-html-tree" ,perl-html-tree)
2789 ("perl-http-cookies" ,perl-http-cookies)
2790 ("perl-http-date" ,perl-http-date)
2791 ("perl-http-message" ,perl-http-message)
2792 ("perl-http-negotiate" ,perl-http-negotiate)
2793 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2794 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2795 ("perl-net-http" ,perl-net-http)
2796 ("perl-uri" ,perl-uri)
2797 ("perl-www-robotrules" ,perl-www-robotrules)
2798 ("perl-xml-simple" ,perl-xml-simple)
2800 (home-page "https://www.ncbi.nlm.nih.gov/books/NBK179288/")
2801 (synopsis "Tools for accessing the NCBI's set of databases")
2803 "Entrez Direct (EDirect) is a method for accessing the National Center
2804 for Biotechnology Information's (NCBI) set of interconnected
2805 databases (publication, sequence, structure, gene, variation, expression,
2806 etc.) from a terminal. Functions take search terms from command-line
2807 arguments. Individual operations are combined to build multi-step queries.
2808 Record retrieval and formatting normally complete the process.
2810 EDirect also provides an argument-driven function that simplifies the
2811 extraction of data from document summaries or other results that are returned
2812 in structured XML format. This can eliminate the need for writing custom
2813 software to answer ad hoc questions.")
2814 (license license:public-domain)))
2816 (define-public exonerate
2825 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2826 "exonerate-" version ".tar.gz"))
2829 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2830 (build-system gnu-build-system)
2832 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2834 `(("pkg-config" ,pkg-config)))
2838 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2839 (synopsis "Generic tool for biological sequence alignment")
2841 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2842 the alignment of sequences using a many alignment models, either exhaustive
2843 dynamic programming or a variety of heuristics.")
2844 (license license:gpl3)))
2846 (define-public express
2854 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2855 version "/express-" version "-src.tgz"))
2858 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2859 (build-system cmake-build-system)
2861 `(#:tests? #f ;no "check" target
2863 (modify-phases %standard-phases
2864 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2865 (lambda* (#:key inputs #:allow-other-keys)
2866 (substitute* "CMakeLists.txt"
2867 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2868 "set(Boost_USE_STATIC_LIBS OFF)")
2869 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2870 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2871 (substitute* "src/CMakeLists.txt"
2872 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2873 (string-append (assoc-ref inputs "bamtools") "/lib"))
2874 (("libprotobuf.a") "libprotobuf.so"))
2878 ("bamtools" ,bamtools)
2879 ("protobuf" ,protobuf)
2881 (home-page "http://bio.math.berkeley.edu/eXpress")
2882 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2884 "eXpress is a streaming tool for quantifying the abundances of a set of
2885 target sequences from sampled subsequences. Example applications include
2886 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2887 analysis (from RNA-Seq), transcription factor binding quantification in
2888 ChIP-Seq, and analysis of metagenomic data.")
2889 (license license:artistic2.0)))
2891 (define-public express-beta-diversity
2893 (name "express-beta-diversity")
2898 (url "https://github.com/dparks1134/ExpressBetaDiversity.git")
2899 (commit (string-append "v" version))))
2900 (file-name (git-file-name name version))
2903 "0s0yzg5c21349rh7x4w9266jsvnp7j1hp9cf8sk32hz8nvrj745x"))))
2904 (build-system gnu-build-system)
2907 (modify-phases %standard-phases
2909 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2911 (lambda _ (invoke "../bin/ExpressBetaDiversity" "-u") #t))
2913 (lambda* (#:key outputs #:allow-other-keys)
2914 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
2915 (install-file "../scripts/convertToEBD.py" bin)
2916 (install-file "../bin/ExpressBetaDiversity" bin)
2919 `(("python" ,python-2)))
2920 (home-page "https://github.com/dparks1134/ExpressBetaDiversity")
2921 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2923 "Express Beta Diversity (EBD) calculates ecological beta diversity
2924 (dissimilarity) measures between biological communities. EBD implements a
2925 variety of diversity measures including those that make use of phylogenetic
2926 similarity of community members.")
2927 (license license:gpl3+)))
2929 (define-public fasttree
2936 "http://www.microbesonline.org/fasttree/FastTree-"
2940 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2941 (build-system gnu-build-system)
2943 `(#:tests? #f ; no "check" target
2945 (modify-phases %standard-phases
2949 (lambda* (#:key source #:allow-other-keys)
2952 "-finline-functions"
2963 "-finline-functions"
2972 (lambda* (#:key outputs #:allow-other-keys)
2973 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
2974 (install-file "FastTree" bin)
2975 (install-file "FastTreeMP" bin)
2977 (home-page "http://www.microbesonline.org/fasttree")
2978 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2980 "FastTree can handle alignments with up to a million of sequences in a
2981 reasonable amount of time and memory. For large alignments, FastTree is
2982 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2983 (license license:gpl2+)))
2985 (define-public fastx-toolkit
2987 (name "fastx-toolkit")
2993 "https://github.com/agordon/fastx_toolkit/releases/download/"
2994 version "/fastx_toolkit-" version ".tar.bz2"))
2997 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2998 (build-system gnu-build-system)
3000 `(("libgtextutils" ,libgtextutils)))
3002 `(("gcc" ,gcc-6) ;; doesn't build with later versions
3003 ("pkg-config" ,pkg-config)))
3004 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
3005 (synopsis "Tools for FASTA/FASTQ file preprocessing")
3007 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
3008 FASTA/FASTQ files preprocessing.
3010 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
3011 containing multiple short-reads sequences. The main processing of such
3012 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
3013 is sometimes more productive to preprocess the files before mapping the
3014 sequences to the genome---manipulating the sequences to produce better mapping
3015 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
3016 (license license:agpl3+)))
3018 (define-public flexbar
3025 (url "https://github.com/seqan/flexbar.git")
3026 (commit (string-append "v" version))))
3027 (file-name (git-file-name name version))
3030 "1pq9sxvdnldl14libk234m72dqhwgzs3acgl943wchwdqlcsi5r2"))))
3031 (build-system cmake-build-system)
3034 (modify-phases %standard-phases
3035 (add-after 'unpack 'do-not-tune-to-CPU
3037 (substitute* "src/CMakeLists.txt"
3038 ((" -march=native") ""))
3041 (lambda* (#:key outputs #:allow-other-keys)
3042 (setenv "PATH" (string-append (getcwd) ":" (getenv "PATH")))
3043 (with-directory-excursion "../source/test"
3044 (invoke "bash" "flexbar_test.sh"))
3047 (lambda* (#:key outputs #:allow-other-keys)
3048 (let* ((out (string-append (assoc-ref outputs "out")))
3049 (bin (string-append out "/bin/")))
3050 (install-file "flexbar" bin))
3056 `(("pkg-config" ,pkg-config)
3058 (home-page "https://github.com/seqan/flexbar")
3059 (synopsis "Barcode and adapter removal tool for sequencing platforms")
3061 "Flexbar preprocesses high-throughput nucleotide sequencing data
3062 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
3063 Moreover, trimming and filtering features are provided. Flexbar increases
3064 read mapping rates and improves genome and transcriptome assemblies. It
3065 supports next-generation sequencing data in fasta/q and csfasta/q format from
3066 Illumina, Roche 454, and the SOLiD platform.")
3067 (license license:bsd-3)))
3069 (define-public fraggenescan
3071 (name "fraggenescan")
3077 (string-append "mirror://sourceforge/fraggenescan/"
3078 "FragGeneScan" version ".tar.gz"))
3080 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
3081 (build-system gnu-build-system)
3084 (modify-phases %standard-phases
3086 (add-before 'build 'patch-paths
3087 (lambda* (#:key outputs #:allow-other-keys)
3088 (let* ((out (string-append (assoc-ref outputs "out")))
3089 (share (string-append out "/share/fraggenescan/")))
3090 (substitute* "run_FragGeneScan.pl"
3092 (string-append "system(\"" (which "rm")))
3094 (string-append "system(\"" (which "mv")))
3095 (("\\\"awk") (string-append "\"" (which "awk")))
3096 ;; This script and other programs expect the training files
3097 ;; to be in the non-standard location bin/train/XXX. Change
3098 ;; this to be share/fraggenescan/train/XXX instead.
3099 (("^\\$train.file = \\$dir.*")
3100 (string-append "$train_file = \""
3102 "train/\".$FGS_train_file;")))
3103 (substitute* "run_hmm.c"
3104 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
3105 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
3109 (invoke "make" "clean")
3110 (invoke "make" "fgs")
3113 (lambda* (#:key outputs #:allow-other-keys)
3114 (let* ((out (string-append (assoc-ref outputs "out")))
3115 (bin (string-append out "/bin/"))
3116 (share (string-append out "/share/fraggenescan/train")))
3117 (install-file "run_FragGeneScan.pl" bin)
3118 (install-file "FragGeneScan" bin)
3119 (copy-recursively "train" share))
3122 (add-after 'install 'post-install-check
3123 ;; In lieu of 'make check', run one of the examples and check the
3124 ;; output files gets created.
3125 (lambda* (#:key outputs #:allow-other-keys)
3126 (let* ((out (string-append (assoc-ref outputs "out")))
3127 (bin (string-append out "/bin/"))
3128 (frag (string-append bin "run_FragGeneScan.pl")))
3129 ;; Test complete genome.
3131 "-genome=./example/NC_000913.fna"
3135 (unless (and (file-exists? "test2.faa")
3136 (file-exists? "test2.ffn")
3137 (file-exists? "test2.gff")
3138 (file-exists? "test2.out"))
3139 (error "Expected files do not exist."))
3140 ;; Test incomplete sequences.
3142 "-genome=./example/NC_000913-fgs.ffn"
3149 ("python" ,python-2))) ;not compatible with python 3.
3150 (home-page "https://sourceforge.net/projects/fraggenescan/")
3151 (synopsis "Finds potentially fragmented genes in short reads")
3153 "FragGeneScan is a program for predicting bacterial and archaeal genes in
3154 short and error-prone DNA sequencing reads. It can also be applied to predict
3155 genes in incomplete assemblies or complete genomes.")
3156 ;; GPL3+ according to private correspondense with the authors.
3157 (license license:gpl3+)))
3159 (define-public fxtract
3160 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
3168 (url "https://github.com/ctSkennerton/fxtract.git")
3170 (file-name (git-file-name name version))
3173 "0hab3gpwf4w9s87qlbswq6ws1qqybh4dcqk79q1ahyldzai5fgp5"))))
3174 (build-system gnu-build-system)
3176 `(#:make-flags (list
3177 (string-append "PREFIX=" (assoc-ref %outputs "out"))
3179 #:test-target "fxtract_test"
3181 (modify-phases %standard-phases
3183 (add-before 'build 'copy-util
3184 (lambda* (#:key inputs #:allow-other-keys)
3186 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
3188 ;; Do not use make install as this requires additional dependencies.
3190 (lambda* (#:key outputs #:allow-other-keys)
3191 (let* ((out (assoc-ref outputs "out"))
3192 (bin (string-append out"/bin")))
3193 (install-file "fxtract" bin)
3199 ;; ctskennerton-util is licensed under GPL2.
3200 `(("ctskennerton-util"
3204 (url "https://github.com/ctSkennerton/util.git")
3205 (commit util-commit)))
3206 (file-name (string-append
3207 "ctstennerton-util-" util-commit "-checkout"))
3210 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
3211 (home-page "https://github.com/ctSkennerton/fxtract")
3212 (synopsis "Extract sequences from FASTA and FASTQ files")
3214 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
3215 or FASTQ) file given a subsequence. It uses a simple substring search for
3216 basic tasks but can change to using POSIX regular expressions, PCRE, hash
3217 lookups or multi-pattern searching as required. By default fxtract looks in
3218 the sequence of each record but can also be told to look in the header,
3219 comment or quality sections.")
3220 ;; 'util' requires SSE instructions.
3221 (supported-systems '("x86_64-linux"))
3222 (license license:expat))))
3224 (define-public gemma
3231 (url "https://github.com/xiangzhou/GEMMA.git")
3232 (commit (string-append "v" version))))
3233 (file-name (git-file-name name version))
3236 "1s3ncnbn45r2hh1cvrqky1kbqq6546biypr4f5mkw1kqlrgyh0yg"))))
3239 ("gfortran" ,gfortran "lib")
3242 ("openblas" ,openblas)
3244 (build-system gnu-build-system)
3247 '(,@(match (%current-system)
3249 '("FORCE_DYNAMIC=1"))
3251 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
3253 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
3255 (modify-phases %standard-phases
3257 (add-after 'unpack 'find-eigen
3258 (lambda* (#:key inputs #:allow-other-keys)
3259 ;; Ensure that Eigen headers can be found
3260 (setenv "CPLUS_INCLUDE_PATH"
3261 (string-append (assoc-ref inputs "eigen")
3264 (add-before 'build 'bin-mkdir
3269 (lambda* (#:key outputs #:allow-other-keys)
3270 (let ((out (assoc-ref outputs "out")))
3271 (install-file "bin/gemma"
3275 #:tests? #f)) ; no tests included yet
3276 (home-page "https://github.com/xiangzhou/GEMMA")
3277 (synopsis "Tool for genome-wide efficient mixed model association")
3279 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
3280 standard linear mixed model resolver with application in genome-wide
3281 association studies (GWAS).")
3282 (license license:gpl3)))
3291 (url "https://github.com/nboley/grit.git")
3293 (file-name (git-file-name name version))
3296 "1l5v8vfvfbrpmgnrvbrbv40d0arhxcnmxgv2f1mlcqfa3q6bkqm9"))))
3297 (build-system python-build-system)
3299 `(#:python ,python-2
3301 (modify-phases %standard-phases
3302 (add-after 'unpack 'generate-from-cython-sources
3303 (lambda* (#:key inputs outputs #:allow-other-keys)
3304 ;; Delete these C files to force fresh generation from pyx sources.
3305 (delete-file "grit/sparsify_support_fns.c")
3306 (delete-file "grit/call_peaks_support_fns.c")
3307 (substitute* "setup.py"
3308 (("Cython.Setup") "Cython.Build"))
3311 `(("python-scipy" ,python2-scipy)
3312 ("python-numpy" ,python2-numpy)
3313 ("python-pysam" ,python2-pysam)
3314 ("python-networkx" ,python2-networkx)))
3316 `(("python-cython" ,python2-cython)))
3317 ;; The canonical <http://grit-bio.org> home page times out as of 2020-01-21.
3318 (home-page "https://github.com/nboley/grit")
3319 (synopsis "Tool for integrative analysis of RNA-seq type assays")
3321 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
3322 full length transcript models. When none of these data sources are available,
3323 GRIT can be run by providing a candidate set of TES or TSS sites. In
3324 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
3325 also be run in quantification mode, where it uses a provided GTF file and just
3326 estimates transcript expression.")
3327 (license license:gpl3+)))
3329 (define-public hisat
3336 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
3337 version "-beta-source.zip"))
3340 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
3341 (build-system gnu-build-system)
3343 `(#:tests? #f ;no check target
3344 #:make-flags '("allall"
3345 ;; Disable unsupported `popcnt' instructions on
3346 ;; architectures other than x86_64
3347 ,@(if (string-prefix? "x86_64"
3348 (or (%current-target-system)
3351 '("POPCNT_CAPABILITY=0")))
3353 (modify-phases %standard-phases
3354 (add-after 'unpack 'patch-sources
3356 ;; XXX Cannot use snippet because zip files are not supported
3357 (substitute* "Makefile"
3358 (("^CC = .*$") "CC = gcc")
3359 (("^CPP = .*$") "CPP = g++")
3360 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
3361 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
3362 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
3363 (substitute* '("hisat-build" "hisat-inspect")
3364 (("/usr/bin/env") (which "env")))
3367 (lambda* (#:key outputs #:allow-other-keys)
3368 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
3369 (for-each (lambda (file)
3370 (install-file file bin))
3373 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
3375 (delete 'configure))))
3377 `(("unzip" ,unzip)))
3382 ;; Non-portable SSE instructions are used so building fails on platforms
3383 ;; other than x86_64.
3384 (supported-systems '("x86_64-linux"))
3385 (home-page "https://ccb.jhu.edu/software/hisat/index.shtml")
3386 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
3388 "HISAT is a fast and sensitive spliced alignment program for mapping
3389 RNA-seq reads. In addition to one global FM index that represents a whole
3390 genome, HISAT uses a large set of small FM indexes that collectively cover the
3391 whole genome. These small indexes (called local indexes) combined with
3392 several alignment strategies enable effective alignment of RNA-seq reads, in
3393 particular, reads spanning multiple exons.")
3394 (license license:gpl3+)))
3396 (define-public hisat2
3403 (uri (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
3404 "/downloads/hisat2-" version "-source.zip"))
3407 "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"))))
3408 (build-system gnu-build-system)
3410 `(#:tests? #f ; no check target
3411 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
3412 #:modules ((guix build gnu-build-system)
3416 (modify-phases %standard-phases
3417 (add-after 'unpack 'make-deterministic
3419 (substitute* "Makefile"
3424 (lambda* (#:key outputs #:allow-other-keys)
3425 (let* ((out (assoc-ref outputs "out"))
3426 (bin (string-append out "/bin/"))
3427 (doc (string-append out "/share/doc/hisat2/")))
3429 (cut install-file <> bin)
3431 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
3433 (install-file "doc/manual.inc.html" doc))
3436 `(("unzip" ,unzip) ; needed for archive from ftp
3438 ("pandoc" ,ghc-pandoc))) ; for documentation
3439 (home-page "https://ccb.jhu.edu/software/hisat2/index.shtml")
3440 (synopsis "Graph-based alignment of genomic sequencing reads")
3441 (description "HISAT2 is a fast and sensitive alignment program for mapping
3442 next-generation sequencing reads (both DNA and RNA) to a population of human
3443 genomes (as well as to a single reference genome). In addition to using one
3444 global @dfn{graph FM} (GFM) index that represents a population of human
3445 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
3446 the whole genome. These small indexes, combined with several alignment
3447 strategies, enable rapid and accurate alignment of sequencing reads. This new
3448 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
3449 ;; HISAT2 contains files from Bowtie2, which is released under
3450 ;; GPLv2 or later. The HISAT2 source files are released under
3452 (license license:gpl3+)))
3454 (define-public hmmer
3462 "http://eddylab.org/software/hmmer/hmmer-" version ".tar.gz"))
3465 "171bivy6xhgjsz5nv53n81pc3frnwz29ylblawk2bv46szwjjqd5"))))
3466 (build-system gnu-build-system)
3467 (native-inputs `(("perl" ,perl)))
3468 (home-page "http://hmmer.org/")
3469 (synopsis "Biosequence analysis using profile hidden Markov models")
3471 "HMMER is used for searching sequence databases for homologs of protein
3472 sequences, and for making protein sequence alignments. It implements methods
3473 using probabilistic models called profile hidden Markov models (profile
3475 ;; hmmer uses non-portable SSE intrinsics so building fails on other
3477 (supported-systems '("x86_64-linux" "i686-linux"))
3478 (license license:bsd-3)))
3480 (define-public htseq
3486 (uri (pypi-uri "HTSeq" version))
3489 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
3490 (build-system python-build-system)
3492 `(("python-cython" ,python-cython)))
3493 ;; Numpy needs to be propagated when htseq is used as a Python library.
3495 `(("python-numpy" ,python-numpy)))
3497 `(("python-pysam" ,python-pysam)
3498 ("python-matplotlib" ,python-matplotlib)))
3499 (home-page "https://htseq.readthedocs.io/")
3500 (synopsis "Analysing high-throughput sequencing data with Python")
3502 "HTSeq is a Python package that provides infrastructure to process data
3503 from high-throughput sequencing assays.")
3504 (license license:gpl3+)))
3506 (define-public python2-htseq
3507 (package-with-python2 htseq))
3509 (define-public java-htsjdk
3511 (name "java-htsjdk")
3512 (version "2.3.0") ; last version without build dependency on gradle
3516 (url "https://github.com/samtools/htsjdk.git")
3518 (file-name (git-file-name name version))
3521 "1b178ixcabanm834ydjl3jiakpyxdmki32hqfv2abrzn3rcwa28i"))
3522 (modules '((guix build utils)))
3524 ;; Delete pre-built binaries
3526 (delete-file-recursively "lib")
3529 (build-system ant-build-system)
3531 `(#:tests? #f ; test require Internet access
3534 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3535 "/share/java/htsjdk/"))
3536 #:build-target "all"
3538 (modify-phases %standard-phases
3539 ;; The build phase also installs the jars
3540 (delete 'install))))
3542 `(("java-ngs" ,java-ngs)
3543 ("java-snappy-1" ,java-snappy-1)
3544 ("java-commons-compress" ,java-commons-compress)
3545 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3546 ("java-commons-jexl-2" ,java-commons-jexl-2)
3547 ("java-xz" ,java-xz)))
3549 `(("java-testng" ,java-testng)))
3550 (home-page "http://samtools.github.io/htsjdk/")
3551 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3553 "HTSJDK is an implementation of a unified Java library for accessing
3554 common file formats, such as SAM and VCF, used for high-throughput
3555 sequencing (HTS) data. There are also an number of useful utilities for
3556 manipulating HTS data.")
3557 (license license:expat)))
3559 (define-public java-htsjdk-latest
3561 (name "java-htsjdk")
3566 (url "https://github.com/samtools/htsjdk.git")
3568 (file-name (string-append name "-" version "-checkout"))
3571 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
3572 (build-system ant-build-system)
3574 `(#:tests? #f ; test require Scala
3576 #:jar-name "htsjdk.jar"
3578 (modify-phases %standard-phases
3579 (add-after 'unpack 'remove-useless-build.xml
3580 (lambda _ (delete-file "build.xml") #t))
3581 ;; The tests require the scalatest package.
3582 (add-after 'unpack 'remove-tests
3583 (lambda _ (delete-file-recursively "src/test") #t)))))
3585 `(("java-ngs" ,java-ngs)
3586 ("java-snappy-1" ,java-snappy-1)
3587 ("java-commons-compress" ,java-commons-compress)
3588 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3589 ("java-commons-jexl-2" ,java-commons-jexl-2)
3590 ("java-xz" ,java-xz)))
3592 `(("java-junit" ,java-junit)))
3593 (home-page "http://samtools.github.io/htsjdk/")
3594 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3596 "HTSJDK is an implementation of a unified Java library for accessing
3597 common file formats, such as SAM and VCF, used for high-throughput
3598 sequencing (HTS) data. There are also an number of useful utilities for
3599 manipulating HTS data.")
3600 (license license:expat)))
3602 ;; This is needed for picard 2.10.3
3603 (define-public java-htsjdk-2.10.1
3604 (package (inherit java-htsjdk-latest)
3605 (name "java-htsjdk")
3610 (url "https://github.com/samtools/htsjdk.git")
3612 (file-name (string-append name "-" version "-checkout"))
3615 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
3616 (build-system ant-build-system)
3618 `(#:tests? #f ; tests require Scala
3620 #:jar-name "htsjdk.jar"
3622 (modify-phases %standard-phases
3623 (add-after 'unpack 'remove-useless-build.xml
3624 (lambda _ (delete-file "build.xml") #t))
3625 ;; The tests require the scalatest package.
3626 (add-after 'unpack 'remove-tests
3627 (lambda _ (delete-file-recursively "src/test") #t)))))))
3629 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3630 ;; recent version of java-htsjdk, which depends on gradle.
3631 (define-public java-picard
3633 (name "java-picard")
3638 (url "https://github.com/broadinstitute/picard.git")
3640 (file-name (string-append "java-picard-" version "-checkout"))
3643 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3644 (modules '((guix build utils)))
3647 ;; Delete pre-built binaries.
3648 (delete-file-recursively "lib")
3650 (substitute* "build.xml"
3651 ;; Remove build-time dependency on git.
3652 (("failifexecutionfails=\"true\"")
3653 "failifexecutionfails=\"false\"")
3655 (("depends=\"compile-htsjdk, ")
3657 (("depends=\"compile-htsjdk-tests, ")
3659 ;; Build picard-lib.jar before building picard.jar
3660 (("name=\"picard-jar\" depends=\"" line)
3661 (string-append line "picard-lib-jar, ")))
3663 (build-system ant-build-system)
3665 `(#:build-target "picard-jar"
3666 #:test-target "test"
3667 ;; Tests require jacoco:coverage.
3670 (list (string-append "-Dhtsjdk_lib_dir="
3671 (assoc-ref %build-inputs "java-htsjdk")
3672 "/share/java/htsjdk/")
3673 "-Dhtsjdk-classes=dist/tmp"
3674 (string-append "-Dhtsjdk-version="
3675 ,(package-version java-htsjdk)))
3678 (modify-phases %standard-phases
3679 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3680 (delete 'generate-jar-indices)
3681 (add-after 'unpack 'use-our-htsjdk
3682 (lambda* (#:key inputs #:allow-other-keys)
3683 (substitute* "build.xml"
3684 (("\\$\\{htsjdk\\}/lib")
3685 (string-append (assoc-ref inputs "java-htsjdk")
3686 "/share/java/htsjdk/")))
3688 (add-after 'unpack 'make-test-target-independent
3689 (lambda* (#:key inputs #:allow-other-keys)
3690 (substitute* "build.xml"
3691 (("name=\"test\" depends=\"compile, ")
3692 "name=\"test\" depends=\""))
3694 (replace 'install (install-jars "dist")))))
3696 `(("java-htsjdk" ,java-htsjdk)
3697 ("java-guava" ,java-guava)))
3699 `(("java-testng" ,java-testng)))
3700 (home-page "http://broadinstitute.github.io/picard/")
3701 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3702 (description "Picard is a set of Java command line tools for manipulating
3703 high-throughput sequencing (HTS) data and formats. Picard is implemented
3704 using the HTSJDK Java library to support accessing file formats that are
3705 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3707 (license license:expat)))
3709 ;; This is needed for dropseq-tools
3710 (define-public java-picard-2.10.3
3712 (name "java-picard")
3717 (url "https://github.com/broadinstitute/picard.git")
3719 (file-name (string-append "java-picard-" version "-checkout"))
3722 "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi"))))
3723 (build-system ant-build-system)
3725 `(#:jar-name "picard.jar"
3726 ;; Tests require jacoco:coverage.
3729 #:main-class "picard.cmdline.PicardCommandLine"
3730 #:modules ((guix build ant-build-system)
3732 (guix build java-utils)
3737 (modify-phases %standard-phases
3738 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3739 (delete 'generate-jar-indices)
3740 (add-after 'unpack 'remove-useless-build.xml
3741 (lambda _ (delete-file "build.xml") #t))
3742 ;; This is necessary to ensure that htsjdk is found when using
3743 ;; picard.jar as an executable.
3744 (add-before 'build 'edit-classpath-in-manifest
3745 (lambda* (#:key inputs #:allow-other-keys)
3746 (chmod "build.xml" #o664)
3747 (call-with-output-file "build.xml.new"
3751 (with-input-from-file "build.xml"
3752 (lambda _ (xml->sxml #:trim-whitespace? #t)))
3753 `((target . ,(lambda (tag . kids)
3754 (let ((name ((sxpath '(name *text*))
3756 ;; FIXME: We're breaking the line
3757 ;; early with a dummy path to
3758 ;; ensure that the store reference
3759 ;; isn't broken apart and can still
3760 ;; be found by the reference
3765 ~a/share/java/htsjdk.jar${line.separator}${line.separator}"
3766 ;; maximum line length is 70
3767 (string-tabulate (const #\b) 57)
3768 (assoc-ref inputs "java-htsjdk"))))
3769 (if (member "manifest" name)
3772 (@ (file "${manifest.file}")
3773 (match "\\r\\n\\r\\n")
3774 (replace "${line.separator}")))
3777 (file "${manifest.file}")
3780 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
3781 (*text* . ,(lambda (_ txt) txt))))
3783 (rename-file "build.xml.new" "build.xml")
3786 `(("java-htsjdk" ,java-htsjdk-2.10.1)))
3788 `(("java-testng" ,java-testng)
3789 ("java-guava" ,java-guava)))
3790 (home-page "http://broadinstitute.github.io/picard/")
3791 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3792 (description "Picard is a set of Java command line tools for manipulating
3793 high-throughput sequencing (HTS) data and formats. Picard is implemented
3794 using the HTSJDK Java library to support accessing file formats that are
3795 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3797 (license license:expat)))
3799 ;; This is the last version of Picard to provide net.sf.samtools
3800 (define-public java-picard-1.113
3801 (package (inherit java-picard)
3802 (name "java-picard")
3807 (url "https://github.com/broadinstitute/picard.git")
3809 (file-name (string-append "java-picard-" version "-checkout"))
3812 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
3813 (modules '((guix build utils)))
3816 ;; Delete pre-built binaries.
3817 (delete-file-recursively "lib")
3820 (build-system ant-build-system)
3822 `(#:build-target "picard-jar"
3823 #:test-target "test"
3824 ;; FIXME: the class path at test time is wrong.
3825 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
3826 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
3829 ;; This is only used for tests.
3831 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
3833 (modify-phases %standard-phases
3834 ;; FIXME: This phase fails.
3835 (delete 'generate-jar-indices)
3836 ;; Do not use bundled ant bzip2.
3837 (add-after 'unpack 'use-ant-bzip
3838 (lambda* (#:key inputs #:allow-other-keys)
3839 (substitute* "build.xml"
3840 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
3841 (string-append (assoc-ref inputs "ant")
3844 (add-after 'unpack 'make-test-target-independent
3845 (lambda* (#:key inputs #:allow-other-keys)
3846 (substitute* "build.xml"
3847 (("name=\"test\" depends=\"compile, ")
3848 "name=\"test\" depends=\"compile-tests, ")
3849 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
3850 "name=\"compile\" depends=\"compile-src\""))
3852 (add-after 'unpack 'fix-deflater-path
3853 (lambda* (#:key outputs #:allow-other-keys)
3854 (substitute* "src/java/net/sf/samtools/Defaults.java"
3855 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
3856 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
3857 (assoc-ref outputs "out")
3858 "/lib/jni/libIntelDeflater.so"
3861 ;; Build the deflater library, because we've previously deleted the
3862 ;; pre-built one. This can only be built with access to the JDK
3864 (add-after 'build 'build-jni
3865 (lambda* (#:key inputs #:allow-other-keys)
3868 (invoke "tar" "--strip-components=1" "-C" "jdk-src"
3869 "-xf" (assoc-ref inputs "jdk-src"))
3870 (invoke "javah" "-jni"
3871 "-classpath" "classes"
3873 "net.sf.samtools.util.zip.IntelDeflater")
3874 (with-directory-excursion "src/c/inteldeflater"
3875 (invoke "gcc" "-I../../../lib" "-I."
3876 (string-append "-I" (assoc-ref inputs "jdk")
3878 "-I../../../jdk-src/src/share/native/common/"
3879 "-I../../../jdk-src/src/solaris/native/common/"
3880 "-c" "-O3" "-fPIC" "IntelDeflater.c")
3881 (invoke "gcc" "-shared"
3882 "-o" "../../../lib/jni/libIntelDeflater.so"
3883 "IntelDeflater.o" "-lz" "-lstdc++"))
3885 ;; We can only build everything else after building the JNI library.
3886 (add-after 'build-jni 'build-rest
3887 (lambda* (#:key make-flags #:allow-other-keys)
3888 (apply invoke `("ant" "all" ,@make-flags))
3890 (add-before 'build 'set-JAVA6_HOME
3892 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
3894 (replace 'install (install-jars "dist"))
3895 (add-after 'install 'install-jni-lib
3896 (lambda* (#:key outputs #:allow-other-keys)
3897 (let ((jni (string-append (assoc-ref outputs "out")
3900 (install-file "lib/jni/libIntelDeflater.so" jni)
3903 `(("java-snappy-1" ,java-snappy-1)
3904 ("java-commons-jexl-2" ,java-commons-jexl-2)
3905 ("java-cofoja" ,java-cofoja)
3906 ("ant" ,ant) ; for bzip2 support at runtime
3909 `(("ant-apache-bcel" ,ant-apache-bcel)
3910 ("ant-junit" ,ant-junit)
3911 ("java-testng" ,java-testng)
3912 ("java-commons-bcel" ,java-commons-bcel)
3913 ("java-jcommander" ,java-jcommander)
3914 ("jdk" ,icedtea-8 "jdk")
3915 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
3917 (define-public fastqc
3924 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
3925 "projects/fastqc/fastqc_v"
3926 version "_source.zip"))
3929 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
3930 (build-system ant-build-system)
3932 `(#:tests? #f ; there are no tests
3933 #:build-target "build"
3935 (modify-phases %standard-phases
3936 (add-after 'unpack 'fix-dependencies
3937 (lambda* (#:key inputs #:allow-other-keys)
3938 (substitute* "build.xml"
3940 (string-append (assoc-ref inputs "java-jbzip2")
3941 "/share/java/jbzip2.jar"))
3943 (string-append (assoc-ref inputs "java-picard-1.113")
3944 "/share/java/sam-1.112.jar"))
3946 (string-append (assoc-ref inputs "java-cisd-jhdf5")
3947 "/share/java/sis-jhdf5.jar")))
3949 ;; There is no installation target
3951 (lambda* (#:key inputs outputs #:allow-other-keys)
3952 (let* ((out (assoc-ref outputs "out"))
3953 (bin (string-append out "/bin"))
3954 (share (string-append out "/share/fastqc/"))
3955 (exe (string-append share "/fastqc")))
3956 (for-each mkdir-p (list bin share))
3957 (copy-recursively "bin" share)
3959 (("my \\$java_bin = 'java';")
3960 (string-append "my $java_bin = '"
3961 (assoc-ref inputs "java")
3964 (symlink exe (string-append bin "/fastqc"))
3968 ("perl" ,perl) ; needed for the wrapper script
3969 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
3970 ("java-picard-1.113" ,java-picard-1.113)
3971 ("java-jbzip2" ,java-jbzip2)))
3973 `(("unzip" ,unzip)))
3974 (home-page "https://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
3975 (synopsis "Quality control tool for high throughput sequence data")
3977 "FastQC aims to provide a simple way to do some quality control
3978 checks on raw sequence data coming from high throughput sequencing
3979 pipelines. It provides a modular set of analyses which you can use to
3980 give a quick impression of whether your data has any problems of which
3981 you should be aware before doing any further analysis.
3983 The main functions of FastQC are:
3986 @item Import of data from BAM, SAM or FastQ files (any variant);
3987 @item Providing a quick overview to tell you in which areas there may
3989 @item Summary graphs and tables to quickly assess your data;
3990 @item Export of results to an HTML based permanent report;
3991 @item Offline operation to allow automated generation of reports
3992 without running the interactive application.
3994 (license license:gpl3+)))
3996 (define-public fastp
4004 (url "https://github.com/OpenGene/fastp.git")
4005 (commit (string-append "v" version))))
4006 (file-name (git-file-name name version))
4009 "1r6ms5zbf5rps4rgp4z73nczadl00b5rqylw8f684isfz27dp0xh"))))
4010 (build-system gnu-build-system)
4012 `(#:tests? #f ; there are none
4014 (list (string-append "BINDIR=" (assoc-ref %outputs "out") "/bin"))
4016 (modify-phases %standard-phases
4018 (add-before 'install 'create-target-dir
4019 (lambda* (#:key outputs #:allow-other-keys)
4020 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4024 (home-page "https://github.com/OpenGene/fastp/")
4025 (synopsis "All-in-one FastQ preprocessor")
4027 "Fastp is a tool designed to provide fast all-in-one preprocessing for
4028 FastQ files. This tool has multi-threading support to afford high
4030 (license license:expat)))
4032 (define-public htslib
4039 "https://github.com/samtools/htslib/releases/download/"
4040 version "/htslib-" version ".tar.bz2"))
4043 "16ljv43sc3fxmv63w7b2ff8m1s7h89xhazwmbm1bicz8axq8fjz0"))))
4044 (build-system gnu-build-system)
4047 ("openssl" ,openssl)))
4048 ;; This is referred to in the pkg-config file as a required library.
4053 (home-page "https://www.htslib.org")
4054 (synopsis "C library for reading/writing high-throughput sequencing data")
4056 "HTSlib is a C library for reading/writing high-throughput sequencing
4057 data. It also provides the @command{bgzip}, @command{htsfile}, and
4058 @command{tabix} utilities.")
4059 ;; Files under cram/ are released under the modified BSD license;
4060 ;; the rest is released under the Expat license
4061 (license (list license:expat license:bsd-3))))
4063 ;; This package should be removed once no packages rely upon it.
4071 "https://github.com/samtools/htslib/releases/download/"
4072 version "/htslib-" version ".tar.bz2"))
4075 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
4084 (url "https://github.com/nboley/idr.git")
4086 (file-name (git-file-name name version))
4089 "04j876h6z444v2q79drxx283d3k5snd72kj895wbalnl42206x9g"))
4090 ;; Delete generated C code.
4092 '(begin (delete-file "idr/inv_cdf.c") #t))))
4093 (build-system python-build-system)
4094 ;; There is only one test ("test_inv_cdf.py") and it tests features that
4095 ;; are no longer part of this package. It also asserts False, which
4096 ;; causes the tests to always fail.
4097 (arguments `(#:tests? #f))
4099 `(("python-scipy" ,python-scipy)
4100 ("python-sympy" ,python-sympy)
4101 ("python-numpy" ,python-numpy)
4102 ("python-matplotlib" ,python-matplotlib)))
4104 `(("python-cython" ,python-cython)))
4105 (home-page "https://github.com/nboley/idr")
4106 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
4108 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
4109 to measure the reproducibility of findings identified from replicate
4110 experiments and provide highly stable thresholds based on reproducibility.")
4111 (license license:gpl2+)))
4113 (define-public jellyfish
4119 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
4120 "releases/download/v" version
4121 "/jellyfish-" version ".tar.gz"))
4124 "1k4pc3fvv6w1km2yph4m5sd78fbxp21d6xyzgmy0gjihzc6mb249"))))
4125 (build-system gnu-build-system)
4126 (outputs '("out" ;for library
4127 "ruby" ;for Ruby bindings
4128 "python")) ;for Python bindings
4131 (list (string-append "--enable-ruby-binding="
4132 (assoc-ref %outputs "ruby"))
4133 (string-append "--enable-python-binding="
4134 (assoc-ref %outputs "python")))
4136 (modify-phases %standard-phases
4137 (add-before 'check 'set-SHELL-variable
4139 ;; generator_manager.hpp either uses /bin/sh or $SHELL
4141 (setenv "SHELL" (which "bash"))
4147 ("python" ,python-2)
4148 ("pkg-config" ,pkg-config)))
4150 `(("htslib" ,htslib)))
4151 (synopsis "Tool for fast counting of k-mers in DNA")
4153 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
4154 DNA. A k-mer is a substring of length k, and counting the occurrences of all
4155 such substrings is a central step in many analyses of DNA sequence. Jellyfish
4156 is a command-line program that reads FASTA and multi-FASTA files containing
4157 DNA sequences. It outputs its k-mer counts in a binary format, which can be
4158 translated into a human-readable text format using the @code{jellyfish dump}
4159 command, or queried for specific k-mers with @code{jellyfish query}.")
4160 (home-page "http://www.genome.umd.edu/jellyfish.html")
4161 ;; JELLYFISH seems to be 64-bit only.
4162 (supported-systems '("x86_64-linux" "aarch64-linux" "mips64el-linux"))
4163 ;; The combined work is published under the GPLv3 or later. Individual
4164 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
4165 (license (list license:gpl3+ license:expat))))
4167 (define-public khmer
4175 (url "https://github.com/dib-lab/khmer.git")
4176 (commit (string-append "v" version))))
4177 (file-name (git-file-name name version))
4180 "01l4jczglkl7yfhgvzx8j0df7k54bk1r8sli9ll16i1mis0d8f37"))
4181 (modules '((guix build utils)))
4184 ;; Delete bundled libraries. We do not replace the bundled seqan
4185 ;; as it is a modified subset of the old version 1.4.1.
4187 ;; We do not replace the bundled MurmurHash as the canonical
4188 ;; repository for this code 'SMHasher' is unsuitable for providing
4190 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
4191 (delete-file-recursively "third-party/zlib")
4192 (delete-file-recursively "third-party/bzip2")
4193 (delete-file-recursively "third-party/seqan")
4194 (substitute* "setup.cfg"
4195 (("# libraries = z,bz2")
4196 "libraries = z,bz2")
4197 (("include:third-party/zlib:third-party/bzip2")
4200 (build-system python-build-system)
4203 (modify-phases %standard-phases
4204 (add-after 'unpack 'set-cc
4205 (lambda _ (setenv "CC" "gcc") #t))
4207 (add-before 'reset-gzip-timestamps 'make-files-writable
4208 (lambda* (#:key outputs #:allow-other-keys)
4209 ;; Make sure .gz files are writable so that the
4210 ;; 'reset-gzip-timestamps' phase can do its work.
4211 (let ((out (assoc-ref outputs "out")))
4212 (for-each make-file-writable
4213 (find-files out "\\.gz$"))
4216 `(("python-cython" ,python-cython)
4217 ("python-pytest" ,python-pytest)
4218 ("python-pytest-runner" ,python-pytest-runner)))
4223 ("python-screed" ,python-screed)
4224 ("python-bz2file" ,python-bz2file)))
4225 (home-page "https://khmer.readthedocs.org/")
4226 (synopsis "K-mer counting, filtering and graph traversal library")
4227 (description "The khmer software is a set of command-line tools for
4228 working with DNA shotgun sequencing data from genomes, transcriptomes,
4229 metagenomes and single cells. Khmer can make de novo assemblies faster, and
4230 sometimes better. Khmer can also identify and fix problems with shotgun
4232 ;; When building on i686, armhf and mips64el, we get the following error:
4233 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
4234 (supported-systems '("x86_64-linux" "aarch64-linux"))
4235 (license license:bsd-3)))
4237 (define-public kaiju
4244 (url "https://github.com/bioinformatics-centre/kaiju")
4245 (commit (string-append "v" version))))
4246 (file-name (git-file-name name version))
4249 "119pzi0ddzv9mjg4wwa6han0cwr3k3ssn7kirvsjfcq05mi5ka0x"))))
4250 (build-system gnu-build-system)
4252 `(#:tests? #f ; There are no tests.
4254 (modify-phases %standard-phases
4256 (add-before 'build 'move-to-src-dir
4257 (lambda _ (chdir "src") #t))
4259 (lambda* (#:key inputs outputs #:allow-other-keys)
4260 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
4263 (copy-recursively "bin" bin))
4268 (home-page "http://kaiju.binf.ku.dk/")
4269 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
4270 (description "Kaiju is a program for sensitive taxonomic classification
4271 of high-throughput sequencing reads from metagenomic whole genome sequencing
4273 (license license:gpl3+)))
4280 ;; The PyPi tarball does not contain tests.
4283 (url "https://github.com/taoliu/MACS.git")
4284 (commit (string-append "v" version))))
4285 (file-name (git-file-name name version))
4288 "1c5gxr0mk6hkd4vclf0k00wvyvzw2vrmk52c85338p7aqjwg6n15"))))
4289 (build-system python-build-system)
4292 (modify-phases %standard-phases
4294 (add-after 'install 'check
4295 (lambda* (#:key inputs outputs #:allow-other-keys)
4296 (add-installed-pythonpath inputs outputs)
4297 (invoke "pytest" "-v"))))))
4299 `(("python-numpy" ,python-numpy)))
4301 `(("python-pytest" ,python-pytest)))
4302 (home-page "https://github.com/taoliu/MACS/")
4303 (synopsis "Model based analysis for ChIP-Seq data")
4305 "MACS is an implementation of a ChIP-Seq analysis algorithm for
4306 identifying transcript factor binding sites named Model-based Analysis of
4307 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
4308 the significance of enriched ChIP regions and it improves the spatial
4309 resolution of binding sites through combining the information of both
4310 sequencing tag position and orientation.")
4311 (license license:bsd-3)))
4313 (define-public mafft
4320 "https://mafft.cbrc.jp/alignment/software/mafft-" version
4321 "-without-extensions-src.tgz"))
4322 (file-name (string-append name "-" version ".tgz"))
4325 "0bacjkxfg944p5khhyh5rd4y7wkjc9qk4v2jjj442sqlq0f8ar7b"))))
4326 (build-system gnu-build-system)
4328 `(#:tests? #f ; no automated tests, though there are tests in the read me
4329 #:make-flags (let ((out (assoc-ref %outputs "out")))
4330 (list (string-append "PREFIX=" out)
4331 (string-append "BINDIR="
4332 (string-append out "/bin"))))
4334 (modify-phases %standard-phases
4335 (add-after 'unpack 'enter-dir
4336 (lambda _ (chdir "core") #t))
4337 (add-after 'enter-dir 'patch-makefile
4339 ;; on advice from the MAFFT authors, there is no need to
4340 ;; distribute mafft-profile, mafft-distance, or
4341 ;; mafft-homologs.rb as they are too "specialised".
4342 (substitute* "Makefile"
4343 ;; remove mafft-homologs.rb from SCRIPTS
4344 (("^SCRIPTS = mafft mafft-homologs.rb")
4346 ;; remove mafft-homologs from MANPAGES
4347 (("^MANPAGES = mafft.1 mafft-homologs.1")
4348 "MANPAGES = mafft.1")
4349 ;; remove mafft-distance from PROGS
4350 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
4351 "PROGS = dvtditr dndfast7 dndblast sextet5")
4352 ;; remove mafft-profile from PROGS
4353 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
4354 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
4355 (("^rm -f mafft-profile mafft-profile.exe") "#")
4356 (("^rm -f mafft-distance mafft-distance.exe") ")#")
4357 ;; do not install MAN pages in libexec folder
4358 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
4359 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
4361 (add-after 'enter-dir 'patch-paths
4362 (lambda* (#:key inputs #:allow-other-keys)
4363 (substitute* '("pairash.c"
4365 (("perl") (which "perl"))
4366 (("([\"`| ])awk" _ prefix)
4367 (string-append prefix (which "awk")))
4368 (("grep") (which "grep")))
4371 (add-after 'install 'wrap-programs
4372 (lambda* (#:key outputs #:allow-other-keys)
4373 (let* ((out (assoc-ref outputs "out"))
4374 (bin (string-append out "/bin"))
4375 (path (string-append
4376 (assoc-ref %build-inputs "coreutils") "/bin:")))
4377 (for-each (lambda (file)
4379 `("PATH" ":" prefix (,path))))
4387 ("coreutils" ,coreutils)))
4388 (home-page "http://mafft.cbrc.jp/alignment/software/")
4389 (synopsis "Multiple sequence alignment program")
4391 "MAFFT offers a range of multiple alignment methods for nucleotide and
4392 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
4393 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
4395 (license (license:non-copyleft
4396 "http://mafft.cbrc.jp/alignment/software/license.txt"
4397 "BSD-3 with different formatting"))))
4406 (url "https://github.com/marbl/mash.git")
4407 (commit (string-append "v" version))))
4408 (file-name (git-file-name name version))
4411 "049hwcc059p2fd9vwndn63laifvvsi0wmv84i6y1fr79k15dxwy6"))
4412 (modules '((guix build utils)))
4415 ;; Delete bundled kseq.
4416 ;; TODO: Also delete bundled murmurhash and open bloom filter.
4417 (delete-file "src/mash/kseq.h")
4419 (build-system gnu-build-system)
4421 `(#:tests? #f ; No tests.
4424 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
4425 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
4426 #:make-flags (list "CC=gcc")
4428 (modify-phases %standard-phases
4429 (add-after 'unpack 'fix-includes
4431 (substitute* '("src/mash/Sketch.cpp"
4432 "src/mash/CommandFind.cpp"
4433 "src/mash/CommandScreen.cpp")
4434 (("^#include \"kseq\\.h\"")
4435 "#include \"htslib/kseq.h\""))
4437 (add-after 'fix-includes 'use-c++14
4439 ;; capnproto 0.7 requires c++14 to build
4440 (substitute* "configure.ac"
4441 (("c\\+\\+11") "c++14"))
4442 (substitute* "Makefile.in"
4443 (("c\\+\\+11") "c++14"))
4446 `(("autoconf" ,autoconf)
4447 ;; Capnproto and htslib are statically embedded in the final
4448 ;; application. Therefore we also list their licenses, below.
4449 ("capnproto" ,capnproto)
4450 ("htslib" ,htslib)))
4454 (supported-systems '("x86_64-linux"))
4455 (home-page "https://mash.readthedocs.io")
4456 (synopsis "Fast genome and metagenome distance estimation using MinHash")
4457 (description "Mash is a fast sequence distance estimator that uses the
4458 MinHash algorithm and is designed to work with genomes and metagenomes in the
4459 form of assemblies or reads.")
4460 (license (list license:bsd-3 ; Mash
4461 license:expat ; HTSlib and capnproto
4462 license:public-domain ; MurmurHash 3
4463 license:cpl1.0)))) ; Open Bloom Filter
4465 (define-public metabat
4473 (url "https://bitbucket.org/berkeleylab/metabat.git")
4474 (commit (string-append "v" version))))
4475 (file-name (git-file-name name version))
4478 "0hyg2smw1nz69mfvjpk45xyyychmda92c80a0cv7baji84ri4iyn"))
4479 (patches (search-patches "metabat-fix-compilation.patch"))))
4480 (build-system scons-build-system)
4482 `(#:scons ,scons-python2
4484 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
4485 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
4486 #:tests? #f ;; Tests are run during the build phase.
4488 (modify-phases %standard-phases
4489 (add-after 'unpack 'fix-includes
4491 (substitute* "src/BamUtils.h"
4492 (("^#include \"bam/bam\\.h\"")
4493 "#include \"samtools/bam.h\"")
4494 (("^#include \"bam/sam\\.h\"")
4495 "#include \"samtools/sam.h\""))
4496 (substitute* "src/KseqReader.h"
4497 (("^#include \"bam/kseq\\.h\"")
4498 "#include \"htslib/kseq.h\""))
4500 (add-after 'unpack 'fix-scons
4501 (lambda* (#:key inputs #:allow-other-keys)
4502 (substitute* "SConstruct"
4503 (("^htslib_dir += 'samtools'")
4504 (string-append "htslib_dir = '"
4505 (assoc-ref inputs "htslib")
4507 (("^samtools_dir = 'samtools'")
4508 (string-append "samtools_dir = '"
4509 (assoc-ref inputs "samtools")
4511 (("^findStaticOrShared\\('bam', hts_lib")
4512 (string-append "findStaticOrShared('bam', '"
4513 (assoc-ref inputs "samtools")
4515 ;; Do not distribute README.
4516 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
4521 ("samtools" ,samtools)
4524 (home-page "https://bitbucket.org/berkeleylab/metabat")
4526 "Reconstruction of single genomes from complex microbial communities")
4528 "Grouping large genomic fragments assembled from shotgun metagenomic
4529 sequences to deconvolute complex microbial communities, or metagenome binning,
4530 enables the study of individual organisms and their interactions. MetaBAT is
4531 an automated metagenome binning software, which integrates empirical
4532 probabilistic distances of genome abundance and tetranucleotide frequency.")
4533 ;; The source code contains inline assembly.
4534 (supported-systems '("x86_64-linux" "i686-linux"))
4535 (license (license:non-copyleft "file://license.txt"
4536 "See license.txt in the distribution."))))
4538 (define-public minced
4545 (url "https://github.com/ctSkennerton/minced.git")
4547 (file-name (git-file-name name version))
4550 "1f5h9him0gd355cnx7p6pnxpknhckd4g0v62mg8zyhfbx9as25fv"))))
4551 (build-system gnu-build-system)
4553 `(#:test-target "test"
4555 (modify-phases %standard-phases
4557 (add-before 'check 'fix-test
4559 ;; Fix test for latest version.
4560 (substitute* "t/Aquifex_aeolicus_VF5.expected"
4561 (("minced:0.1.6") "minced:0.2.0"))
4563 (replace 'install ; No install target.
4564 (lambda* (#:key inputs outputs #:allow-other-keys)
4565 (let* ((out (assoc-ref outputs "out"))
4566 (bin (string-append out "/bin"))
4567 (wrapper (string-append bin "/minced")))
4568 ;; Minced comes with a wrapper script that tries to figure out where
4569 ;; it is located before running the JAR. Since these paths are known
4570 ;; to us, we build our own wrapper to avoid coreutils dependency.
4571 (install-file "minced.jar" bin)
4572 (with-output-to-file wrapper
4576 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
4577 (assoc-ref inputs "jre") "/bin/java -jar "
4578 bin "/minced.jar \"$@\"\n"))))
4579 (chmod wrapper #o555))
4582 `(("jdk" ,icedtea "jdk")))
4585 ("jre" ,icedtea "out")))
4586 (home-page "https://github.com/ctSkennerton/minced")
4587 (synopsis "Mining CRISPRs in Environmental Datasets")
4589 "MinCED is a program to find Clustered Regularly Interspaced Short
4590 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
4591 unassembled metagenomic reads, but is mainly designed for full genomes and
4592 assembled metagenomic sequence.")
4593 (license license:gpl3+)))
4601 (uri (pypi-uri "misopy" version))
4604 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
4605 (modules '((guix build utils)))
4607 (substitute* "setup.py"
4608 ;; Use setuptools, or else the executables are not
4610 (("distutils.core") "setuptools")
4611 ;; Use "gcc" instead of "cc" for compilation.
4613 "cc.set_executables(
4617 linker_so='gcc -shared'); defines"))
4619 (build-system python-build-system)
4621 `(#:python ,python-2 ; only Python 2 is supported
4622 #:tests? #f)) ; no "test" target
4624 `(("samtools" ,samtools)
4625 ("python-numpy" ,python2-numpy)
4626 ("python-pysam" ,python2-pysam)
4627 ("python-scipy" ,python2-scipy)
4628 ("python-matplotlib" ,python2-matplotlib)))
4630 `(("python-mock" ,python2-mock) ; for tests
4631 ("python-pytz" ,python2-pytz))) ; for tests
4632 (home-page "https://www.genes.mit.edu/burgelab/miso/index.html")
4633 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
4635 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
4636 the expression level of alternatively spliced genes from RNA-Seq data, and
4637 identifies differentially regulated isoforms or exons across samples. By
4638 modeling the generative process by which reads are produced from isoforms in
4639 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
4640 that a read originated from a particular isoform.")
4641 (license license:gpl2)))
4643 (define-public muscle
4646 (version "3.8.1551")
4648 (method url-fetch/tarbomb)
4650 "http://www.drive5.com/muscle/muscle_src_"
4654 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
4655 (build-system gnu-build-system)
4657 `(#:make-flags (list "LDLIBS = -lm")
4659 (modify-phases %standard-phases
4662 ;; There are no tests, so just test if it runs.
4663 (lambda _ (invoke "./muscle" "-version") #t))
4665 (lambda* (#:key outputs #:allow-other-keys)
4666 (let* ((out (assoc-ref outputs "out"))
4667 (bin (string-append out "/bin")))
4668 (install-file "muscle" bin)
4670 (home-page "http://www.drive5.com/muscle")
4671 (synopsis "Multiple sequence alignment program")
4673 "MUSCLE aims to be a fast and accurate multiple sequence alignment
4674 program for nucleotide and protein sequences.")
4675 ;; License information found in 'muscle -h' and usage.cpp.
4676 (license license:public-domain)))
4678 (define-public newick-utils
4679 ;; There are no recent releases so we package from git.
4680 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
4682 (name "newick-utils")
4683 (version (string-append "1.6-1." (string-take commit 8)))
4687 (url "https://github.com/tjunier/newick_utils.git")
4689 (file-name (string-append name "-" version "-checkout"))
4692 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4693 (build-system gnu-build-system)
4695 ;; XXX: TODO: Enable Lua and Guile bindings.
4696 ;; https://github.com/tjunier/newick_utils/issues/13
4697 `(("libxml2" ,libxml2)
4701 `(("autoconf" ,autoconf)
4702 ("automake" ,automake)
4703 ("libtool" ,libtool)))
4704 (synopsis "Programs for working with newick format phylogenetic trees")
4706 "Newick-utils is a suite of utilities for processing phylogenetic trees
4707 in Newick format. Functions include re-rooting, extracting subtrees,
4708 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4709 (home-page "https://github.com/tjunier/newick_utils")
4710 (license license:bsd-3))))
4719 "https://github.com/wwood/OrfM/releases/download/v"
4720 version "/orfm-" version ".tar.gz"))
4723 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4724 (build-system gnu-build-system)
4725 (inputs `(("zlib" ,zlib)))
4727 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4728 ("ruby-rspec" ,ruby-rspec)
4730 (synopsis "Simple and not slow open reading frame (ORF) caller")
4732 "An ORF caller finds stretches of DNA that, when translated, are not
4733 interrupted by stop codons. OrfM finds and prints these ORFs.")
4734 (home-page "https://github.com/wwood/OrfM")
4735 (license license:lgpl3+)))
4737 (define-public python2-pbcore
4739 (name "python2-pbcore")
4743 (uri (pypi-uri "pbcore" version))
4746 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4747 (build-system python-build-system)
4749 `(#:python ,python-2 ;pbcore < 2.0 requires Python 2.7
4750 #:phases (modify-phases %standard-phases
4751 (add-after 'unpack 'remove-sphinx-dependency
4753 ;; Sphinx is only required for documentation tests, which
4754 ;; we do not run; furthermore it depends on python2-sphinx
4755 ;; which is no longer maintained.
4756 (substitute* "requirements-dev.txt"
4760 `(("python-cython" ,python2-cython)
4761 ("python-numpy" ,python2-numpy)
4762 ("python-pysam" ,python2-pysam)
4763 ("python-h5py" ,python2-h5py)))
4765 `(("python-nose" ,python2-nose)
4766 ("python-pyxb" ,python2-pyxb)))
4767 (home-page "https://pacificbiosciences.github.io/pbcore/")
4768 (synopsis "Library for reading and writing PacBio data files")
4770 "The pbcore package provides Python APIs for interacting with PacBio data
4771 files and writing bioinformatics applications.")
4772 (license license:bsd-3)))
4774 (define-public python2-warpedlmm
4776 (name "python2-warpedlmm")
4781 (uri (pypi-uri "WarpedLMM" version ".zip"))
4784 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4785 (build-system python-build-system)
4787 `(#:python ,python-2)) ; requires Python 2.7
4789 `(("python-scipy" ,python2-scipy)
4790 ("python-numpy" ,python2-numpy)
4791 ("python-matplotlib" ,python2-matplotlib)
4792 ("python-fastlmm" ,python2-fastlmm)
4793 ("python-pandas" ,python2-pandas)
4794 ("python-pysnptools" ,python2-pysnptools)))
4796 `(("python-mock" ,python2-mock)
4797 ("python-nose" ,python2-nose)
4799 (home-page "https://github.com/PMBio/warpedLMM")
4800 (synopsis "Implementation of warped linear mixed models")
4802 "WarpedLMM is a Python implementation of the warped linear mixed model,
4803 which automatically learns an optimal warping function (or transformation) for
4804 the phenotype as it models the data.")
4805 (license license:asl2.0)))
4807 (define-public pbtranscript-tofu
4808 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
4810 (name "pbtranscript-tofu")
4811 (version (string-append "2.2.3." (string-take commit 7)))
4815 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
4817 (file-name (string-append name "-" version "-checkout"))
4820 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
4821 (modules '((guix build utils)))
4824 ;; remove bundled Cython sources
4825 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
4827 (build-system python-build-system)
4829 `(#:python ,python-2
4830 ;; FIXME: Tests fail with "No such file or directory:
4831 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
4834 (modify-phases %standard-phases
4835 (add-after 'unpack 'enter-directory
4837 (chdir "pbtranscript-tofu/pbtranscript/")
4839 ;; With setuptools version 18.0 and later this setup.py hack causes
4840 ;; a build error, so we disable it.
4841 (add-after 'enter-directory 'patch-setuppy
4843 (substitute* "setup.py"
4844 (("if 'setuptools.extension' in sys.modules:")
4848 `(("python-numpy" ,python2-numpy)
4849 ("python-bx-python" ,python2-bx-python)
4850 ("python-networkx" ,python2-networkx)
4851 ("python-scipy" ,python2-scipy)
4852 ("python-pbcore" ,python2-pbcore)
4853 ("python-h5py" ,python2-h5py)))
4855 `(("python-cython" ,python2-cython)
4856 ("python-nose" ,python2-nose)))
4857 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4858 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4860 "pbtranscript-tofu contains scripts to analyze transcriptome data
4861 generated using the PacBio Iso-Seq protocol.")
4862 (license license:bsd-3))))
4864 (define-public prank
4871 "http://wasabiapp.org/download/prank/prank.source."
4875 "0nc8g9c5rkdxcir46s0in9ci1sxwzbjibxrvkksf22ybnplvagk2"))))
4876 (build-system gnu-build-system)
4879 (modify-phases %standard-phases
4880 (add-after 'unpack 'enter-src-dir
4884 (add-after 'unpack 'remove-m64-flag
4885 ;; Prank will build with the correct 'bit-ness' without this flag
4886 ;; and this allows building on 32-bit machines.
4887 (lambda _ (substitute* "src/Makefile"
4892 (lambda* (#:key outputs #:allow-other-keys)
4893 (let* ((out (assoc-ref outputs "out"))
4894 (bin (string-append out "/bin"))
4895 (man (string-append out "/share/man/man1"))
4896 (path (string-append
4897 (assoc-ref %build-inputs "mafft") "/bin:"
4898 (assoc-ref %build-inputs "exonerate") "/bin:"
4899 (assoc-ref %build-inputs "bppsuite") "/bin")))
4900 (install-file "prank" bin)
4901 (wrap-program (string-append bin "/prank")
4902 `("PATH" ":" prefix (,path)))
4903 (install-file "prank.1" man))
4907 ("exonerate" ,exonerate)
4908 ("bppsuite" ,bppsuite)))
4909 (home-page "http://wasabiapp.org/software/prank/")
4910 (synopsis "Probabilistic multiple sequence alignment program")
4912 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4913 codon and amino-acid sequences. It is based on a novel algorithm that treats
4914 insertions correctly and avoids over-estimation of the number of deletion
4915 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4916 in phylogenetics and correctly takes into account the evolutionary distances
4917 between sequences. Lastly, PRANK allows for defining a potential structure
4918 for sequences to be aligned and then, simultaneously with the alignment,
4919 predicts the locations of structural units in the sequences.")
4920 (license license:gpl2+)))
4922 (define-public proteinortho
4924 (name "proteinortho")
4929 (url "https://gitlab.com/paulklemm_PHD/proteinortho.git")
4930 (commit (string-append "v" version))))
4931 (file-name (git-file-name name version))
4934 "0pmy617zy2z2w6hjqxjhf3rzikf5n3mpia80ysq8233vfr7wrzff"))
4935 (modules '((guix build utils)))
4938 ;; remove pre-built scripts
4939 (delete-file-recursively "src/BUILD/")
4941 (build-system gnu-build-system)
4943 `(#:test-target "test"
4944 #:make-flags '("CC=gcc")
4946 (modify-phases %standard-phases
4948 ;; There is no configure script, so we modify the Makefile directly.
4949 (lambda* (#:key outputs #:allow-other-keys)
4950 (substitute* "Makefile"
4953 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4955 (add-before 'install 'make-install-directory
4956 ;; The install directory is not created during 'make install'.
4957 (lambda* (#:key outputs #:allow-other-keys)
4958 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4960 (add-after 'install 'wrap-programs
4961 (lambda* (#:key inputs outputs #:allow-other-keys)
4962 (let ((path (getenv "PATH"))
4963 (out (assoc-ref outputs "out")))
4964 (for-each (lambda (script)
4965 (wrap-script script `("PATH" ":" prefix (,path))))
4966 (cons (string-append out "/bin/proteinortho")
4967 (find-files out "\\.(pl|py)$"))))
4970 `(("guile" ,guile-3.0) ; for wrap-script
4971 ("diamond" ,diamond)
4973 ("python" ,python-wrapper)
4976 ("openblas" ,openblas)))
4978 `(("which" ,which)))
4979 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4980 (synopsis "Detect orthologous genes across species")
4982 "Proteinortho is a tool to detect orthologous genes across different
4983 species. For doing so, it compares similarities of given gene sequences and
4984 clusters them to find significant groups. The algorithm was designed to handle
4985 large-scale data and can be applied to hundreds of species at once.")
4986 (license license:gpl3+)))
4988 (define-public pyicoteo
4996 (url "https://bitbucket.org/regulatorygenomicsupf/pyicoteo.git")
4997 (commit (string-append "v" version))))
4998 (file-name (git-file-name name version))
5001 "0hz5g8d25lbjy1wpscr490l0lmyvaix893hhax4fxnh1h9w34w8p"))))
5002 (build-system python-build-system)
5004 `(#:python ,python-2 ; does not work with Python 3
5005 #:tests? #f)) ; there are no tests
5007 `(("python2-matplotlib" ,python2-matplotlib)))
5008 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
5009 (synopsis "Analyze high-throughput genetic sequencing data")
5011 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
5012 sequencing data. It works with genomic coordinates. There are currently six
5013 different command-line tools:
5016 @item pyicoregion: for generating exploratory regions automatically;
5017 @item pyicoenrich: for differential enrichment between two conditions;
5018 @item pyicoclip: for calling CLIP-Seq peaks without a control;
5019 @item pyicos: for genomic coordinates manipulation;
5020 @item pyicoller: for peak calling on punctuated ChIP-Seq;
5021 @item pyicount: to count how many reads from N experiment files overlap in a
5023 @item pyicotrocol: to combine operations from pyicoteo.
5025 (license license:gpl3+)))
5027 (define-public prodigal
5030 ;; Check for a new home page when updating this package:
5031 ;; https://github.com/hyattpd/Prodigal/issues/36#issuecomment-536617588
5036 (url "https://github.com/hyattpd/Prodigal.git")
5037 (commit (string-append "v" version))))
5038 (file-name (git-file-name name version))
5041 "1fs1hqk83qjbjhrvhw6ni75zakx5ki1ayy3v6wwkn3xvahc9hi5s"))))
5042 (build-system gnu-build-system)
5044 `(#:tests? #f ; no check target
5045 #:make-flags (list (string-append "INSTALLDIR="
5046 (assoc-ref %outputs "out")
5049 (modify-phases %standard-phases
5050 (delete 'configure))))
5051 (home-page "https://github.com/hyattpd/Prodigal")
5052 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
5054 "Prodigal runs smoothly on finished genomes, draft genomes, and
5055 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
5056 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
5057 partial genes, and identifies translation initiation sites.")
5058 (license license:gpl3+)))
5060 (define-public roary
5068 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
5072 "0qxrds9wx7cfhlkihrp6697kx0flhhxymap9fwan0b3rbdhcnmff"))))
5073 (build-system perl-build-system)
5076 (modify-phases %standard-phases
5081 ;; The tests are not run by default, so we run each test file
5083 (setenv "PATH" (string-append (getcwd) "/bin" ":"
5085 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
5086 (getenv "PERL5LIB")))
5087 (for-each (lambda (file)
5088 (display file)(display "\n")
5089 (invoke "perl" file))
5090 (find-files "t" ".*\\.t$"))
5093 ;; There is no 'install' target in the Makefile.
5094 (lambda* (#:key outputs #:allow-other-keys)
5095 (let* ((out (assoc-ref outputs "out"))
5096 (bin (string-append out "/bin"))
5097 (perl (string-append out "/lib/perl5/site_perl"))
5098 (roary-plots "contrib/roary_plots"))
5101 (copy-recursively "bin" bin)
5102 (copy-recursively "lib" perl)
5104 (add-after 'install 'wrap-programs
5105 (lambda* (#:key inputs outputs #:allow-other-keys)
5106 (let* ((out (assoc-ref outputs "out"))
5107 (perl5lib (getenv "PERL5LIB"))
5108 (path (getenv "PATH")))
5109 (for-each (lambda (prog)
5110 (let ((binary (string-append out "/" prog)))
5111 (wrap-program binary
5112 `("PERL5LIB" ":" prefix
5113 (,(string-append perl5lib ":" out
5114 "/lib/perl5/site_perl"))))
5115 (wrap-program binary
5117 (,(string-append path ":" out "/bin"))))))
5118 (find-files "bin" ".*[^R]$"))
5120 (string-append out "/bin/roary-create_pan_genome_plots.R"))
5121 (r-site-lib (getenv "R_LIBS_SITE"))
5123 (string-append (assoc-ref inputs "coreutils") "/bin")))
5125 `("R_LIBS_SITE" ":" prefix
5126 (,(string-append r-site-lib ":" out "/site-library/"))))
5129 (,(string-append coreutils-path ":" out "/bin"))))))
5132 `(("perl-env-path" ,perl-env-path)
5133 ("perl-test-files" ,perl-test-files)
5134 ("perl-test-most" ,perl-test-most)
5135 ("perl-test-output" ,perl-test-output)))
5137 `(("perl-array-utils" ,perl-array-utils)
5138 ("bioperl" ,bioperl-minimal)
5139 ("perl-digest-md5-file" ,perl-digest-md5-file)
5140 ("perl-exception-class" ,perl-exception-class)
5141 ("perl-file-find-rule" ,perl-file-find-rule)
5142 ("perl-file-grep" ,perl-file-grep)
5143 ("perl-file-slurper" ,perl-file-slurper)
5144 ("perl-file-which" ,perl-file-which)
5145 ("perl-graph" ,perl-graph)
5146 ("perl-graph-readwrite" ,perl-graph-readwrite)
5147 ("perl-log-log4perl" ,perl-log-log4perl)
5148 ("perl-moose" ,perl-moose)
5149 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
5150 ("perl-text-csv" ,perl-text-csv)
5151 ("bedtools" ,bedtools)
5155 ("parallel" ,parallel)
5158 ("fasttree" ,fasttree)
5162 ("r-minimal" ,r-minimal)
5163 ("r-ggplot2" ,r-ggplot2)
5164 ("coreutils" ,coreutils)))
5165 (home-page "https://sanger-pathogens.github.io/Roary/")
5166 (synopsis "High speed stand-alone pan genome pipeline")
5168 "Roary is a high speed stand alone pan genome pipeline, which takes
5169 annotated assemblies in GFF3 format (produced by the Prokka program) and
5170 calculates the pan genome. Using a standard desktop PC, it can analyse
5171 datasets with thousands of samples, without compromising the quality of the
5172 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
5173 single processor. Roary is not intended for metagenomics or for comparing
5174 extremely diverse sets of genomes.")
5175 (license license:gpl3)))
5177 (define-public raxml
5185 (url "https://github.com/stamatak/standard-RAxML.git")
5186 (commit (string-append "v" version))))
5187 (file-name (git-file-name name version))
5190 "1jqjzhch0rips0vp04prvb8vmc20c5pdmsqn8knadcf91yy859fh"))))
5191 (build-system gnu-build-system)
5193 `(#:tests? #f ; There are no tests.
5194 ;; Use 'standard' Makefile rather than SSE or AVX ones.
5195 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
5197 (modify-phases %standard-phases
5200 (lambda* (#:key outputs #:allow-other-keys)
5201 (let* ((out (assoc-ref outputs "out"))
5202 (bin (string-append out "/bin"))
5203 (executable "raxmlHPC-HYBRID"))
5204 (install-file executable bin)
5205 (symlink (string-append bin "/" executable) "raxml"))
5208 `(("openmpi" ,openmpi)))
5209 (home-page "https://cme.h-its.org/exelixis/web/software/raxml/index.html")
5210 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
5212 "RAxML is a tool for phylogenetic analysis and post-analysis of large
5214 ;; The source includes x86 specific code
5215 (supported-systems '("x86_64-linux" "i686-linux"))
5216 (license license:gpl2+)))
5226 (url "https://github.com/deweylab/RSEM.git")
5227 (commit (string-append "v" version))))
5229 (base32 "1jlq11d1p8qp64w75yj8cnbbd1a93viq10pzsbwal7vdn8fg13j1"))
5230 (file-name (git-file-name name version))
5231 (modules '((guix build utils)))
5234 ;; remove bundled copy of boost and samtools
5235 (delete-file-recursively "boost")
5236 (delete-file-recursively "samtools-1.3")
5238 (build-system gnu-build-system)
5240 `(#:tests? #f ;no "check" target
5242 (list (string-append "BOOST="
5243 (assoc-ref %build-inputs "boost")
5245 (string-append "SAMHEADERS="
5246 (assoc-ref %build-inputs "htslib")
5247 "/include/htslib/sam.h")
5248 (string-append "SAMLIBS="
5249 (assoc-ref %build-inputs "htslib")
5252 (modify-phases %standard-phases
5253 ;; No "configure" script.
5254 ;; Do not build bundled samtools library.
5257 (substitute* "Makefile"
5258 (("^all : \\$\\(PROGRAMS\\).*") "all: $(PROGRAMS)\n")
5259 (("^\\$\\(SAMLIBS\\).*") ""))
5262 (lambda* (#:key outputs #:allow-other-keys)
5263 (let* ((out (string-append (assoc-ref outputs "out")))
5264 (bin (string-append out "/bin/"))
5265 (perl (string-append out "/lib/perl5/site_perl")))
5268 (for-each (lambda (file)
5269 (install-file file bin))
5270 (find-files "." "rsem-.*"))
5271 (install-file "rsem_perl_utils.pm" perl))
5273 (add-after 'install 'wrap-program
5274 (lambda* (#:key outputs #:allow-other-keys)
5275 (let ((out (assoc-ref outputs "out")))
5276 (for-each (lambda (prog)
5277 (wrap-program (string-append out "/bin/" prog)
5278 `("PERL5LIB" ":" prefix
5279 (,(string-append out "/lib/perl5/site_perl")))))
5280 '("rsem-calculate-expression"
5282 "rsem-generate-data-matrix"
5283 "rsem-generate-ngvector"
5284 "rsem-plot-transcript-wiggles"
5285 "rsem-prepare-reference"
5287 "rsem-run-prsem-testing-procedure")))
5291 ("r-minimal" ,r-minimal)
5293 ("htslib" ,htslib-1.3)
5295 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
5296 (synopsis "Estimate gene expression levels from RNA-Seq data")
5298 "RSEM is a software package for estimating gene and isoform expression
5299 levels from RNA-Seq data. The RSEM package provides a user-friendly
5300 interface, supports threads for parallel computation of the EM algorithm,
5301 single-end and paired-end read data, quality scores, variable-length reads and
5302 RSPD estimation. In addition, it provides posterior mean and 95% credibility
5303 interval estimates for expression levels. For visualization, it can generate
5304 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
5305 (license license:gpl3+)))
5307 (define-public rseqc
5315 (string-append "mirror://sourceforge/rseqc/"
5316 "RSeQC-" version ".tar.gz"))
5319 "0gbb9iyb7swiv5455fm5rg98r7l6qn27v564yllqjd574hncpx6m"))))
5320 (build-system python-build-system)
5322 `(("python-cython" ,python-cython)
5323 ("python-bx-python" ,python-bx-python)
5324 ("python-pybigwig" ,python-pybigwig)
5325 ("python-pysam" ,python-pysam)
5326 ("python-numpy" ,python-numpy)
5329 `(("python-nose" ,python-nose)))
5330 (home-page "http://rseqc.sourceforge.net/")
5331 (synopsis "RNA-seq quality control package")
5333 "RSeQC provides a number of modules that can comprehensively evaluate
5334 high throughput sequence data, especially RNA-seq data. Some basic modules
5335 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
5336 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
5337 distribution, coverage uniformity, strand specificity, etc.")
5338 (license license:gpl3+)))
5341 ;; There are no release tarballs. According to the installation
5342 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
5343 ;; stable release is identified by this changeset ID.
5344 (let ((changeset "2329130")
5348 (version (string-append "0-" revision "." changeset))
5352 (url "https://bitbucket.org/libsleipnir/sleipnir")
5353 (changeset changeset)))
5354 (file-name (string-append name "-" version "-checkout"))
5357 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
5358 (build-system gnu-build-system)
5360 `(#:modules ((srfi srfi-1)
5361 (guix build gnu-build-system)
5364 (let ((dirs '("SeekMiner"
5370 (modify-phases %standard-phases
5373 (substitute* "gen_tools_am"
5374 (("/usr/bin/env.*") (which "perl")))
5375 (invoke "bash" "gen_auto")
5377 (add-after 'build 'build-additional-tools
5378 (lambda* (#:key make-flags #:allow-other-keys)
5379 (for-each (lambda (dir)
5380 (with-directory-excursion (string-append "tools/" dir)
5381 (apply invoke "make" make-flags)))
5384 (add-after 'install 'install-additional-tools
5385 (lambda* (#:key make-flags #:allow-other-keys)
5386 (for-each (lambda (dir)
5387 (with-directory-excursion (string-append "tools/" dir)
5388 (apply invoke `("make" ,@make-flags "install"))))
5395 ("readline" ,readline)
5396 ("gengetopt" ,gengetopt)
5397 ("log4cpp" ,log4cpp)))
5399 `(("autoconf" ,autoconf)
5400 ("automake" ,automake)
5402 (home-page "http://seek.princeton.edu")
5403 (synopsis "Gene co-expression search engine")
5405 "SEEK is a computational gene co-expression search engine. SEEK provides
5406 biologists with a way to navigate the massive human expression compendium that
5407 now contains thousands of expression datasets. SEEK returns a robust ranking
5408 of co-expressed genes in the biological area of interest defined by the user's
5409 query genes. It also prioritizes thousands of expression datasets according
5410 to the user's query of interest.")
5411 (license license:cc-by3.0))))
5413 (define-public samtools
5421 (string-append "mirror://sourceforge/samtools/samtools/"
5422 version "/samtools-" version ".tar.bz2"))
5425 "10ilqbmm7ri8z431sn90lvbjwizd0hhkf9rcqw8j823hf26nhgq8"))
5426 (modules '((guix build utils)))
5428 ;; Delete bundled htslib.
5429 (delete-file-recursively "htslib-1.9")
5431 (build-system gnu-build-system)
5433 `(#:modules ((ice-9 ftw)
5435 (guix build gnu-build-system)
5437 #:configure-flags (list "--with-ncurses")
5439 (modify-phases %standard-phases
5440 (add-after 'unpack 'patch-tests
5442 (substitute* "test/test.pl"
5443 ;; The test script calls out to /bin/bash
5444 (("/bin/bash") (which "bash")))
5446 (add-after 'install 'install-library
5447 (lambda* (#:key outputs #:allow-other-keys)
5448 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
5449 (install-file "libbam.a" lib)
5451 (add-after 'install 'install-headers
5452 (lambda* (#:key outputs #:allow-other-keys)
5453 (let ((include (string-append (assoc-ref outputs "out")
5454 "/include/samtools/")))
5455 (for-each (lambda (file)
5456 (install-file file include))
5457 (scandir "." (lambda (name) (string-match "\\.h$" name))))
5459 (native-inputs `(("pkg-config" ,pkg-config)))
5461 `(("htslib" ,htslib)
5462 ("ncurses" ,ncurses)
5466 (home-page "http://samtools.sourceforge.net")
5467 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
5469 "Samtools implements various utilities for post-processing nucleotide
5470 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
5471 variant calling (in conjunction with bcftools), and a simple alignment
5473 (license license:expat)))
5475 (define-public samtools-0.1
5476 ;; This is the most recent version of the 0.1 line of samtools. The input
5477 ;; and output formats differ greatly from that used and produced by samtools
5478 ;; 1.x and is still used in many bioinformatics pipelines.
5479 (package (inherit samtools)
5485 (string-append "mirror://sourceforge/samtools/samtools/"
5486 version "/samtools-" version ".tar.bz2"))
5488 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
5490 `(#:tests? #f ;no "check" target
5492 (list "LIBCURSES=-lncurses")
5493 ,@(substitute-keyword-arguments (package-arguments samtools)
5495 `(modify-phases ,phases
5497 (lambda* (#:key outputs #:allow-other-keys)
5498 (let ((bin (string-append
5499 (assoc-ref outputs "out") "/bin")))
5501 (install-file "samtools" bin)
5503 (delete 'patch-tests)
5504 (delete 'configure))))))))
5506 (define-public mosaik
5507 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
5512 ;; There are no release tarballs nor tags.
5515 (url "https://github.com/wanpinglee/MOSAIK.git")
5517 (file-name (string-append name "-" version))
5520 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
5521 (build-system gnu-build-system)
5523 `(#:tests? #f ; no tests
5524 #:make-flags (list "CC=gcc")
5526 (modify-phases %standard-phases
5528 (lambda _ (chdir "src") #t))
5530 (lambda* (#:key outputs #:allow-other-keys)
5531 (let ((bin (string-append (assoc-ref outputs "out")
5534 (copy-recursively "../bin" bin)
5538 ("zlib:static" ,zlib "static")
5540 (supported-systems '("x86_64-linux"))
5541 (home-page "https://github.com/wanpinglee/MOSAIK")
5542 (synopsis "Map nucleotide sequence reads to reference genomes")
5544 "MOSAIK is a program for mapping second and third-generation sequencing
5545 reads to a reference genome. MOSAIK can align reads generated by all the
5546 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
5547 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
5548 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
5549 ;; code released into the public domain:
5550 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
5551 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
5552 (license (list license:gpl2+ license:public-domain)))))
5554 (define-public ngs-sdk
5561 (url "https://github.com/ncbi/ngs.git")
5563 (file-name (git-file-name name version))
5566 "0d5k5kabgl15as37kj9x65xc92j4gcqms86hvihw3yb6wag0r0q3"))))
5567 (build-system gnu-build-system)
5569 `(#:parallel-build? #f ; not supported
5570 #:tests? #f ; no "check" target
5572 (modify-phases %standard-phases
5574 (lambda* (#:key outputs #:allow-other-keys)
5575 (let ((out (assoc-ref outputs "out")))
5576 ;; Allow 'konfigure.perl' to find 'package.prl'.
5578 (string-append ".:" (getenv "PERL5LIB")))
5580 ;; The 'configure' script doesn't recognize things like
5581 ;; '--enable-fast-install'.
5582 (invoke "./configure"
5583 (string-append "--build-prefix=" (getcwd) "/build")
5584 (string-append "--prefix=" out))
5586 (add-after 'unpack 'enter-dir
5587 (lambda _ (chdir "ngs-sdk") #t)))))
5588 (native-inputs `(("perl" ,perl)))
5589 ;; According to the test
5590 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
5591 ;; in ngs-sdk/setup/konfigure.perl
5592 (supported-systems '("i686-linux" "x86_64-linux"))
5593 (home-page "https://github.com/ncbi/ngs")
5594 (synopsis "API for accessing Next Generation Sequencing data")
5596 "NGS is a domain-specific API for accessing reads, alignments and pileups
5597 produced from Next Generation Sequencing. The API itself is independent from
5598 any particular back-end implementation, and supports use of multiple back-ends
5600 (license license:public-domain)))
5602 (define-public java-ngs
5603 (package (inherit ngs-sdk)
5606 `(,@(substitute-keyword-arguments
5607 `(#:modules ((guix build gnu-build-system)
5611 ,@(package-arguments ngs-sdk))
5613 `(modify-phases ,phases
5614 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5616 `(("jdk" ,icedtea "jdk")
5617 ("ngs-sdk" ,ngs-sdk)))
5618 (synopsis "Java bindings for NGS SDK")))
5620 (define-public ncbi-vdb
5627 (url "https://github.com/ncbi/ncbi-vdb.git")
5629 (file-name (git-file-name name version))
5632 "0knkj1sq34hlivgv5qd6jlczqrs3ldmfgn6vbbw7p4mqxvb9mirk"))))
5633 (build-system gnu-build-system)
5635 `(#:parallel-build? #f ; not supported
5636 #:tests? #f ; no "check" target
5637 #:make-flags '("HAVE_HDF5=1")
5639 (modify-phases %standard-phases
5640 (add-after 'unpack 'make-files-writable
5641 (lambda _ (for-each make-file-writable (find-files "." ".*")) #t))
5642 (add-before 'configure 'set-perl-search-path
5644 ;; Work around "dotless @INC" build failure.
5646 (string-append (getcwd) "/setup:"
5647 (getenv "PERL5LIB")))
5649 ;; See https://github.com/ncbi/ncbi-vdb/issues/14
5650 (add-after 'unpack 'patch-krypto-flags
5652 (substitute* "libs/krypto/Makefile"
5653 (("-Wa,-march=generic64\\+aes") "")
5654 (("-Wa,-march=generic64\\+sse4") ""))
5657 (lambda* (#:key inputs outputs #:allow-other-keys)
5658 (let ((out (assoc-ref outputs "out")))
5659 ;; Override include path for libmagic
5660 (substitute* "setup/package.prl"
5661 (("name => 'magic', Include => '/usr/include'")
5662 (string-append "name=> 'magic', Include => '"
5663 (assoc-ref inputs "libmagic")
5666 ;; Install kdf5 library (needed by sra-tools)
5667 (substitute* "build/Makefile.install"
5668 (("LIBRARIES_TO_INSTALL =")
5669 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5671 (substitute* "build/Makefile.env"
5672 (("CFLAGS =" prefix)
5673 (string-append prefix "-msse2 ")))
5675 ;; Override search path for ngs-java
5676 (substitute* "setup/package.prl"
5677 (("/usr/local/ngs/ngs-java")
5678 (assoc-ref inputs "java-ngs")))
5680 ;; The 'configure' script doesn't recognize things like
5681 ;; '--enable-fast-install'.
5682 (invoke "./configure"
5683 (string-append "--build-prefix=" (getcwd) "/build")
5684 (string-append "--prefix=" (assoc-ref outputs "out"))
5685 (string-append "--debug")
5686 (string-append "--with-xml2-prefix="
5687 (assoc-ref inputs "libxml2"))
5688 (string-append "--with-ngs-sdk-prefix="
5689 (assoc-ref inputs "ngs-sdk"))
5690 (string-append "--with-hdf5-prefix="
5691 (assoc-ref inputs "hdf5")))
5693 (add-after 'install 'install-interfaces
5694 (lambda* (#:key outputs #:allow-other-keys)
5695 ;; Install interface libraries. On i686 the interface libraries
5696 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5697 ;; architecture name ("i386") instead of the target system prefix
5699 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5700 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5701 ,(system->linux-architecture
5702 (or (%current-target-system)
5705 (string-append (assoc-ref outputs "out")
5707 ;; Install interface headers
5708 (copy-recursively "interfaces"
5709 (string-append (assoc-ref outputs "out")
5712 ;; These files are needed by sra-tools.
5713 (add-after 'install 'install-configuration-files
5714 (lambda* (#:key outputs #:allow-other-keys)
5715 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5717 (install-file "libs/kfg/default.kfg" target)
5718 (install-file "libs/kfg/certs.kfg" target))
5721 `(("libxml2" ,libxml2)
5722 ("ngs-sdk" ,ngs-sdk)
5723 ("java-ngs" ,java-ngs)
5726 (native-inputs `(("perl" ,perl)))
5727 ;; NCBI-VDB requires SSE capability.
5728 (supported-systems '("i686-linux" "x86_64-linux"))
5729 (home-page "https://github.com/ncbi/ncbi-vdb")
5730 (synopsis "Database engine for genetic information")
5732 "The NCBI-VDB library implements a highly compressed columnar data
5733 warehousing engine that is most often used to store genetic information.
5734 Databases are stored in a portable image within the file system, and can be
5735 accessed/downloaded on demand across HTTP.")
5736 (license license:public-domain)))
5738 (define-public plink
5746 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5747 version "-src.zip"))
5749 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5750 (patches (search-patches "plink-1.07-unclobber-i.patch"
5751 "plink-endian-detection.patch"))))
5752 (build-system gnu-build-system)
5754 '(#:tests? #f ;no "check" target
5755 #:make-flags (list (string-append "LIB_LAPACK="
5756 (assoc-ref %build-inputs "lapack")
5757 "/lib/liblapack.so")
5760 ;; disable phoning home
5763 (modify-phases %standard-phases
5764 ;; no "configure" script
5767 (lambda* (#:key outputs #:allow-other-keys)
5768 (let ((bin (string-append (assoc-ref outputs "out")
5770 (install-file "plink" bin)
5774 ("lapack" ,lapack)))
5776 `(("unzip" ,unzip)))
5777 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5778 (synopsis "Whole genome association analysis toolset")
5780 "PLINK is a whole genome association analysis toolset, designed to
5781 perform a range of basic, large-scale analyses in a computationally efficient
5782 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5783 so there is no support for steps prior to this (e.g. study design and
5784 planning, generating genotype or CNV calls from raw data). Through
5785 integration with gPLINK and Haploview, there is some support for the
5786 subsequent visualization, annotation and storage of results.")
5787 ;; Code is released under GPLv2, except for fisher.h, which is under
5789 (license (list license:gpl2 license:lgpl2.1+))))
5791 (define-public plink-ng
5792 (package (inherit plink)
5799 (url "https://github.com/chrchang/plink-ng.git")
5800 (commit (string-append "v" version))))
5801 (file-name (git-file-name name version))
5803 (base32 "02npdwgkpfkdnhw819rhj5kw02a5k5m90b14zq9zzya4hyg929c0"))))
5804 (build-system gnu-build-system)
5806 '(#:tests? #f ;no "check" target
5807 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5808 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5810 "-f" "Makefile.std")
5812 (modify-phases %standard-phases
5813 (add-after 'unpack 'chdir
5814 (lambda _ (chdir "1.9") #t))
5815 (delete 'configure) ; no "configure" script
5817 (lambda* (#:key outputs #:allow-other-keys)
5818 (let ((bin (string-append (assoc-ref outputs "out")
5820 (install-file "plink" bin)
5825 ("openblas" ,openblas)))
5826 (home-page "https://www.cog-genomics.org/plink/")
5827 (license license:gpl3+)))
5829 (define-public smithlab-cpp
5830 (let ((revision "1")
5831 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
5833 (name "smithlab-cpp")
5834 (version (string-append "0." revision "." (string-take commit 7)))
5838 (url "https://github.com/smithlabcode/smithlab_cpp.git")
5840 (file-name (string-append name "-" version "-checkout"))
5843 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
5844 (build-system gnu-build-system)
5846 `(#:modules ((guix build gnu-build-system)
5849 #:tests? #f ;no "check" target
5851 (modify-phases %standard-phases
5852 (add-after 'unpack 'use-samtools-headers
5854 (substitute* '("SAM.cpp"
5856 (("sam.h") "samtools/sam.h"))
5859 (lambda* (#:key outputs #:allow-other-keys)
5860 (let* ((out (assoc-ref outputs "out"))
5861 (lib (string-append out "/lib"))
5862 (include (string-append out "/include/smithlab-cpp")))
5865 (for-each (cut install-file <> lib)
5866 (find-files "." "\\.o$"))
5867 (for-each (cut install-file <> include)
5868 (find-files "." "\\.hpp$")))
5870 (delete 'configure))))
5872 `(("samtools" ,samtools-0.1)
5874 (home-page "https://github.com/smithlabcode/smithlab_cpp")
5875 (synopsis "C++ helper library for functions used in Smith lab projects")
5877 "Smithlab CPP is a C++ library that includes functions used in many of
5878 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
5879 structures, classes for genomic regions, mapped sequencing reads, etc.")
5880 (license license:gpl3+))))
5882 (define-public preseq
5888 (uri (string-append "https://github.com/smithlabcode/preseq/"
5889 "releases/download/v" version
5890 "/preseq_v" version ".tar.bz2"))
5892 (base32 "149x9xmk1wy1gff85325yfzqc0qk4sgp1w6gbyj9cnji4x1dszbl"))
5893 (modules '((guix build utils)))
5895 ;; Remove bundled samtools.
5896 (delete-file-recursively "samtools")
5898 (build-system gnu-build-system)
5900 `(#:tests? #f ;no "check" target
5902 (modify-phases %standard-phases
5903 (delete 'configure))
5905 (list (string-append "PREFIX="
5906 (assoc-ref %outputs "out"))
5907 (string-append "LIBBAM="
5908 (assoc-ref %build-inputs "samtools")
5910 (string-append "SMITHLAB_CPP="
5911 (assoc-ref %build-inputs "smithlab-cpp")
5914 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
5917 ("samtools" ,samtools-0.1)
5918 ("smithlab-cpp" ,smithlab-cpp)
5920 (home-page "http://smithlabresearch.org/software/preseq/")
5921 (synopsis "Program for analyzing library complexity")
5923 "The preseq package is aimed at predicting and estimating the complexity
5924 of a genomic sequencing library, equivalent to predicting and estimating the
5925 number of redundant reads from a given sequencing depth and how many will be
5926 expected from additional sequencing using an initial sequencing experiment.
5927 The estimates can then be used to examine the utility of further sequencing,
5928 optimize the sequencing depth, or to screen multiple libraries to avoid low
5929 complexity samples.")
5930 (license license:gpl3+)))
5932 (define-public python-screed
5934 (name "python-screed")
5939 (uri (pypi-uri "screed" version))
5942 "148vcb7w2wr6a4w6vs2bsxanbqibxfk490zbcbg4m61s8669zdjx"))))
5943 (build-system python-build-system)
5946 (modify-phases %standard-phases
5947 ;; Tests must be run after installation, as the "screed" command does
5948 ;; not exist right after building.
5950 (add-after 'install 'check
5951 (lambda* (#:key inputs outputs #:allow-other-keys)
5952 (let ((out (assoc-ref outputs "out")))
5953 (setenv "PYTHONPATH"
5954 (string-append out "/lib/python"
5955 (string-take (string-take-right
5956 (assoc-ref inputs "python")
5959 (getenv "PYTHONPATH")))
5960 (setenv "PATH" (string-append out "/bin:" (getenv "PATH"))))
5961 (invoke "python" "setup.py" "test")
5964 `(("python-pytest" ,python-pytest)
5965 ("python-pytest-cov" ,python-pytest-cov)
5966 ("python-pytest-runner" ,python-pytest-runner)))
5968 `(("python-bz2file" ,python-bz2file)))
5969 (home-page "https://github.com/dib-lab/screed/")
5970 (synopsis "Short read sequence database utilities")
5971 (description "Screed parses FASTA and FASTQ files and generates databases.
5972 Values such as sequence name, sequence description, sequence quality and the
5973 sequence itself can be retrieved from these databases.")
5974 (license license:bsd-3)))
5976 (define-public python2-screed
5977 (package-with-python2 python-screed))
5979 (define-public sra-tools
5987 (url "https://github.com/ncbi/sra-tools.git")
5989 (file-name (git-file-name name version))
5992 "0vqzap68v81k0zif2mnqfy8pnw2nrhsg87p6mgq8qk3nk2jv2rgy"))))
5993 (build-system gnu-build-system)
5995 `(#:parallel-build? #f ; not supported
5996 #:tests? #f ; no "check" target
5998 (list (string-append "DEFAULT_CRT="
5999 (assoc-ref %build-inputs "ncbi-vdb")
6001 (string-append "DEFAULT_KFG="
6002 (assoc-ref %build-inputs "ncbi-vdb")
6004 (string-append "VDB_LIBDIR="
6005 (assoc-ref %build-inputs "ncbi-vdb")
6006 ,(if (string-prefix? "x86_64"
6007 (or (%current-target-system)
6012 (modify-phases %standard-phases
6013 (add-before 'configure 'set-perl-search-path
6015 ;; Work around "dotless @INC" build failure.
6017 (string-append (getcwd) "/setup:"
6018 (getenv "PERL5LIB")))
6021 (lambda* (#:key inputs outputs #:allow-other-keys)
6022 ;; The build system expects a directory containing the sources and
6023 ;; raw build output of ncbi-vdb, including files that are not
6024 ;; installed. Since we are building against an installed version of
6025 ;; ncbi-vdb, the following modifications are needed.
6026 (substitute* "setup/konfigure.perl"
6027 ;; Make the configure script look for the "ilib" directory of
6028 ;; "ncbi-vdb" without first checking for the existence of a
6029 ;; matching library in its "lib" directory.
6030 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
6031 "my $f = File::Spec->catdir($ilibdir, $ilib);")
6032 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
6033 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
6034 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
6037 (substitute* "tools/copycat/Makefile"
6038 (("smagic-static") "lmagic"))
6040 ;; The 'configure' script doesn't recognize things like
6041 ;; '--enable-fast-install'.
6042 (invoke "./configure"
6043 (string-append "--build-prefix=" (getcwd) "/build")
6044 (string-append "--prefix=" (assoc-ref outputs "out"))
6045 (string-append "--debug")
6046 (string-append "--with-fuse-prefix="
6047 (assoc-ref inputs "fuse"))
6048 (string-append "--with-magic-prefix="
6049 (assoc-ref inputs "libmagic"))
6050 ;; TODO: building with libxml2 fails with linker errors
6051 ;; (string-append "--with-xml2-prefix="
6052 ;; (assoc-ref inputs "libxml2"))
6053 (string-append "--with-ncbi-vdb-sources="
6054 (assoc-ref inputs "ncbi-vdb"))
6055 (string-append "--with-ncbi-vdb-build="
6056 (assoc-ref inputs "ncbi-vdb"))
6057 (string-append "--with-ngs-sdk-prefix="
6058 (assoc-ref inputs "ngs-sdk"))
6059 (string-append "--with-hdf5-prefix="
6060 (assoc-ref inputs "hdf5")))
6062 (native-inputs `(("perl" ,perl)))
6064 `(("ngs-sdk" ,ngs-sdk)
6065 ("ncbi-vdb" ,ncbi-vdb)
6071 "https://trace.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
6072 (synopsis "Tools and libraries for reading and writing sequencing data")
6074 "The SRA Toolkit from NCBI is a collection of tools and libraries for
6075 reading of sequencing files from the Sequence Read Archive (SRA) database and
6076 writing files into the .sra format.")
6077 (license license:public-domain)))
6079 (define-public seqan
6085 (uri (string-append "https://github.com/seqan/seqan/releases/"
6086 "download/seqan-v" version
6087 "/seqan-library-" version ".tar.xz"))
6090 "19a1rlxx03qy1i1iriicly68w64yjxbv24g9gdywnfmq998v35yx"))))
6091 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6092 ;; makes sense to split the outputs.
6093 (outputs '("out" "doc"))
6094 (build-system trivial-build-system)
6096 `(#:modules ((guix build utils))
6099 (use-modules (guix build utils))
6100 (let ((tar (assoc-ref %build-inputs "tar"))
6101 (xz (assoc-ref %build-inputs "xz"))
6102 (out (assoc-ref %outputs "out"))
6103 (doc (assoc-ref %outputs "doc")))
6104 (setenv "PATH" (string-append tar "/bin:" xz "/bin"))
6105 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6106 (chdir (string-append "seqan-library-" ,version))
6107 (copy-recursively "include" (string-append out "/include"))
6108 (copy-recursively "share" (string-append doc "/share"))
6111 `(("source" ,source)
6114 (home-page "http://www.seqan.de")
6115 (synopsis "Library for nucleotide sequence analysis")
6117 "SeqAn is a C++ library of efficient algorithms and data structures for
6118 the analysis of sequences with the focus on biological data. It contains
6119 algorithms and data structures for string representation and their
6120 manipulation, online and indexed string search, efficient I/O of
6121 bioinformatics file formats, sequence alignment, and more.")
6122 (license license:bsd-3)))
6124 (define-public seqan-1
6125 (package (inherit seqan)
6130 (uri (string-append "http://packages.seqan.de/seqan-library/"
6131 "seqan-library-" version ".tar.bz2"))
6134 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
6135 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6136 ;; makes sense to split the outputs.
6137 (outputs '("out" "doc"))
6138 (build-system trivial-build-system)
6140 `(#:modules ((guix build utils))
6143 (use-modules (guix build utils))
6144 (let ((tar (assoc-ref %build-inputs "tar"))
6145 (bzip (assoc-ref %build-inputs "bzip2"))
6146 (out (assoc-ref %outputs "out"))
6147 (doc (assoc-ref %outputs "doc")))
6148 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
6149 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6150 (chdir (string-append "seqan-library-" ,version))
6151 (copy-recursively "include" (string-append out "/include"))
6152 (copy-recursively "share" (string-append doc "/share"))
6155 `(("source" ,source)
6157 ("bzip2" ,bzip2)))))
6159 (define-public seqmagick
6166 (uri (pypi-uri "seqmagick" version))
6169 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
6170 (build-system python-build-system)
6172 `(("python-biopython" ,python-biopython)))
6174 `(("python-nose" ,python-nose)))
6175 (home-page "https://github.com/fhcrc/seqmagick")
6176 (synopsis "Tools for converting and modifying sequence files")
6178 "Bioinformaticians often have to convert sequence files between formats
6179 and do little manipulations on them, and it's not worth writing scripts for
6180 that. Seqmagick is a utility to expose the file format conversion in
6181 BioPython in a convenient way. Instead of having a big mess of scripts, there
6182 is one that takes arguments.")
6183 (license license:gpl3)))
6185 (define-public seqtk
6192 (url "https://github.com/lh3/seqtk.git")
6193 (commit (string-append "v" version))))
6194 (file-name (git-file-name name version))
6197 "1bfzlqa84b5s1qi22blmmw2s8xdyp9h9ydcq22pfjhh5gab3yz6l"))))
6198 (build-system gnu-build-system)
6201 (modify-phases %standard-phases
6204 ;; There are no tests, so we just run a sanity check.
6205 (lambda _ (invoke "./seqtk" "seq") #t))
6207 (lambda* (#:key outputs #:allow-other-keys)
6208 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6209 (install-file "seqtk" bin)
6213 (home-page "https://github.com/lh3/seqtk")
6214 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
6216 "Seqtk is a fast and lightweight tool for processing sequences in the
6217 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
6218 optionally compressed by gzip.")
6219 (license license:expat)))
6221 (define-public snap-aligner
6223 (name "snap-aligner")
6224 (version "1.0beta.18")
6228 (url "https://github.com/amplab/snap.git")
6229 (commit (string-append "v" version))))
6230 (file-name (git-file-name name version))
6233 "01w3qq4wm07z73vky0cfwlmrbf50n3w722cxrlzxfi99mnb808d8"))))
6234 (build-system gnu-build-system)
6237 (modify-phases %standard-phases
6239 (replace 'check (lambda _ (invoke "./unit_tests") #t))
6241 (lambda* (#:key outputs #:allow-other-keys)
6242 (let* ((out (assoc-ref outputs "out"))
6243 (bin (string-append out "/bin")))
6244 (install-file "snap-aligner" bin)
6245 (install-file "SNAPCommand" bin)
6249 (home-page "http://snap.cs.berkeley.edu/")
6250 (synopsis "Short read DNA sequence aligner")
6252 "SNAP is a fast and accurate aligner for short DNA reads. It is
6253 optimized for modern read lengths of 100 bases or higher, and takes advantage
6254 of these reads to align data quickly through a hash-based indexing scheme.")
6255 ;; 32-bit systems are not supported by the unpatched code.
6256 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
6257 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
6258 ;; systems without a lot of memory cannot make good use of this program.
6259 (supported-systems '("x86_64-linux"))
6260 (license license:asl2.0)))
6262 (define-public sortmerna
6270 (url "https://github.com/biocore/sortmerna.git")
6272 (file-name (git-file-name name version))
6275 "0j3mbz4n25738yijmjbr5r4fyvkgm8v5vn3sshyfvmyqf5q9byqf"))))
6276 (build-system gnu-build-system)
6277 (outputs '("out" ;for binaries
6278 "db")) ;for sequence databases
6281 (modify-phases %standard-phases
6283 (lambda* (#:key outputs #:allow-other-keys)
6284 (let* ((out (assoc-ref outputs "out"))
6285 (bin (string-append out "/bin"))
6286 (db (assoc-ref outputs "db"))
6288 (string-append db "/share/sortmerna/rRNA_databases")))
6289 (install-file "sortmerna" bin)
6290 (install-file "indexdb_rna" bin)
6291 (for-each (lambda (file)
6292 (install-file file share))
6293 (find-files "rRNA_databases" ".*fasta"))
6297 (home-page "https://bioinfo.lifl.fr/RNA/sortmerna/")
6298 (synopsis "Biological sequence analysis tool for NGS reads")
6300 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
6301 and operational taxonomic unit (OTU) picking of next generation
6302 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
6303 allows for fast and sensitive analyses of nucleotide sequences. The main
6304 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
6305 ;; The source includes x86 specific code
6306 (supported-systems '("x86_64-linux" "i686-linux"))
6307 (license license:lgpl3)))
6316 (url "https://github.com/alexdobin/STAR.git")
6318 (file-name (string-append name "-" version "-checkout"))
6321 "0n6g4s4hgw7qygs1z97j7a2dgz8gfaa4cv5pjvvvmarvk0x07hyg"))
6322 (modules '((guix build utils)))
6325 (substitute* "source/Makefile"
6327 ;; Remove pre-built binaries and bundled htslib sources.
6328 (delete-file-recursively "bin/MacOSX_x86_64")
6329 (delete-file-recursively "bin/Linux_x86_64")
6330 (delete-file-recursively "bin/Linux_x86_64_static")
6331 (delete-file-recursively "source/htslib")
6333 (build-system gnu-build-system)
6335 '(#:tests? #f ;no check target
6336 #:make-flags '("STAR")
6338 (modify-phases %standard-phases
6339 (add-after 'unpack 'enter-source-dir
6340 (lambda _ (chdir "source") #t))
6341 (add-after 'enter-source-dir 'make-reproducible
6343 (substitute* "Makefile"
6344 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
6345 (string-append pre "Built with Guix" post)))
6347 ;; See https://github.com/alexdobin/STAR/pull/562
6348 (add-after 'enter-source-dir 'add-missing-header
6350 (substitute* "SoloReadFeature_inputRecords.cpp"
6351 (("#include \"binarySearch2.h\"" h)
6352 (string-append h "\n#include <math.h>")))
6354 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
6356 (substitute* "Makefile"
6357 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
6359 (substitute* '("BAMfunctions.cpp"
6364 "bamRemoveDuplicates.cpp")
6365 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
6366 (string-append "#include <" header ">")))
6367 (substitute* "IncludeDefine.h"
6368 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
6369 (string-append "<" header ">")))
6372 (lambda* (#:key outputs #:allow-other-keys)
6373 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6374 (install-file "STAR" bin))
6376 (delete 'configure))))
6380 `(("htslib" ,htslib)
6382 (home-page "https://github.com/alexdobin/STAR")
6383 (synopsis "Universal RNA-seq aligner")
6385 "The Spliced Transcripts Alignment to a Reference (STAR) software is
6386 based on a previously undescribed RNA-seq alignment algorithm that uses
6387 sequential maximum mappable seed search in uncompressed suffix arrays followed
6388 by seed clustering and stitching procedure. In addition to unbiased de novo
6389 detection of canonical junctions, STAR can discover non-canonical splices and
6390 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
6392 ;; Only 64-bit systems are supported according to the README.
6393 (supported-systems '("x86_64-linux" "mips64el-linux"))
6394 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
6395 (license license:gpl3+)))
6397 (define-public starlong
6398 (package (inherit star)
6401 (substitute-keyword-arguments (package-arguments star)
6402 ((#:make-flags flags)
6405 `(modify-phases ,phases
6406 ;; Allow extra long sequence reads.
6407 (add-after 'unpack 'make-extra-long
6409 (substitute* "source/IncludeDefine.h"
6410 (("(#define DEF_readNameLengthMax ).*" _ match)
6411 (string-append match "900000\n")))
6414 (lambda* (#:key outputs #:allow-other-keys)
6415 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6416 (install-file "STARlong" bin))
6419 (define-public subread
6425 (uri (string-append "mirror://sourceforge/subread/subread-"
6426 version "/subread-" version "-source.tar.gz"))
6429 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
6430 (build-system gnu-build-system)
6432 `(#:tests? #f ;no "check" target
6433 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
6434 ;; optimizations by default, so we override these flags such that x86_64
6435 ;; flags are only added when the build target is an x86_64 system.
6437 (list (let ((system ,(or (%current-target-system)
6439 (flags '("-ggdb" "-fomit-frame-pointer"
6440 "-ffast-math" "-funroll-loops"
6441 "-fmessage-length=0"
6442 "-O9" "-Wall" "-DMAKE_FOR_EXON"
6444 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
6445 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
6446 (if (string-prefix? "x86_64" system)
6447 (string-append "CCFLAGS=" (string-join (append flags flags64)))
6448 (string-append "CCFLAGS=" (string-join flags))))
6449 "-f" "Makefile.Linux"
6450 "CC=gcc ${CCFLAGS}")
6452 (modify-phases %standard-phases
6453 (add-after 'unpack 'enter-dir
6454 (lambda _ (chdir "src") #t))
6456 (lambda* (#:key outputs #:allow-other-keys)
6457 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6459 (copy-recursively "../bin" bin))
6461 ;; no "configure" script
6462 (delete 'configure))))
6463 (inputs `(("zlib" ,zlib)))
6464 (home-page "http://bioinf.wehi.edu.au/subread-package/")
6465 (synopsis "Tool kit for processing next-gen sequencing data")
6467 "The subread package contains the following tools: subread aligner, a
6468 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
6469 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
6470 features; exactSNP: a SNP caller that discovers SNPs by testing signals
6471 against local background noises.")
6472 (license license:gpl3+)))
6474 (define-public stringtie
6480 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
6481 "stringtie-" version ".tar.gz"))
6484 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
6485 (modules '((guix build utils)))
6488 (delete-file-recursively "samtools-0.1.18")
6490 (build-system gnu-build-system)
6492 `(#:tests? #f ;no test suite
6494 (modify-phases %standard-phases
6495 ;; no configure script
6497 (add-before 'build 'use-system-samtools
6499 (substitute* "Makefile"
6500 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
6502 (substitute* '("gclib/GBam.h"
6504 (("#include \"(bam|sam|kstring).h\"" _ header)
6505 (string-append "#include <samtools/" header ".h>")))
6507 (add-after 'unpack 'remove-duplicate-typedef
6509 ;; This typedef conflicts with the typedef in
6510 ;; glibc-2.25/include/bits/types.h
6511 (substitute* "gclib/GThreads.h"
6512 (("typedef long long __intmax_t;") ""))
6515 (lambda* (#:key outputs #:allow-other-keys)
6516 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6517 (install-file "stringtie" bin)
6520 `(("samtools" ,samtools-0.1)
6522 (home-page "http://ccb.jhu.edu/software/stringtie/")
6523 (synopsis "Transcript assembly and quantification for RNA-Seq data")
6525 "StringTie is a fast and efficient assembler of RNA-Seq sequence
6526 alignments into potential transcripts. It uses a novel network flow algorithm
6527 as well as an optional de novo assembly step to assemble and quantitate
6528 full-length transcripts representing multiple splice variants for each gene
6529 locus. Its input can include not only the alignments of raw reads used by
6530 other transcript assemblers, but also alignments of longer sequences that have
6531 been assembled from those reads. To identify differentially expressed genes
6532 between experiments, StringTie's output can be processed either by the
6533 Cuffdiff or Ballgown programs.")
6534 (license license:artistic2.0)))
6536 (define-public taxtastic
6541 ;; The Pypi version does not include tests.
6544 (url "https://github.com/fhcrc/taxtastic.git")
6545 (commit (string-append "v" version))))
6546 (file-name (git-file-name name version))
6549 "1sv8mkg64jn7zdwf1jj71c16686yrwxk0apb1l8sjszy9p166g0p"))))
6550 (build-system python-build-system)
6553 (modify-phases %standard-phases
6554 (add-after 'unpack 'prepare-directory
6556 ;; The git checkout must be writable for tests.
6557 (for-each make-file-writable (find-files "."))
6558 ;; This test fails, but the error is not caught by the test
6559 ;; framework, so the tests fail...
6560 (substitute* "tests/test_taxit.py"
6561 (("self.cmd_fails\\(''\\)")
6562 "self.cmd_fails('nothing')"))
6563 ;; This version file is expected to be created with git describe.
6564 (mkdir-p "taxtastic/data")
6565 (with-output-to-file "taxtastic/data/ver"
6566 (lambda () (display ,version)))
6568 (add-after 'unpack 'python37-compatibility
6570 (substitute* "taxtastic/utils.py"
6571 (("import csv") "import csv, errno")
6572 (("os.errno") "errno"))
6575 ;; Note, this fails to run with "-v" as it tries to write to a
6576 ;; closed output stream.
6577 (lambda _ (invoke "python" "-m" "unittest") #t)))))
6579 `(("python-sqlalchemy" ,python-sqlalchemy)
6580 ("python-decorator" ,python-decorator)
6581 ("python-biopython" ,python-biopython)
6582 ("python-pandas" ,python-pandas)
6583 ("python-psycopg2" ,python-psycopg2)
6584 ("python-fastalite" ,python-fastalite)
6585 ("python-pyyaml" ,python-pyyaml)
6586 ("python-six" ,python-six)
6587 ("python-jinja2" ,python-jinja2)
6588 ("python-dendropy" ,python-dendropy)))
6589 (home-page "https://github.com/fhcrc/taxtastic")
6590 (synopsis "Tools for taxonomic naming and annotation")
6592 "Taxtastic is software written in python used to build and maintain
6593 reference packages i.e. collections of reference trees, reference alignments,
6594 profiles, and associated taxonomic information.")
6595 (license license:gpl3+)))
6597 (define-public vcftools
6604 "https://github.com/vcftools/vcftools/releases/download/v"
6605 version "/vcftools-" version ".tar.gz"))
6608 "1qqlx7flfv7axrjwkaz6njkscsl1d0jw98ns8d8bh1n1hd1pgz6v"))))
6609 (build-system gnu-build-system)
6611 `(#:tests? #f ; no "check" target
6613 "CFLAGS=-O2" ; override "-m64" flag
6614 (string-append "PREFIX=" (assoc-ref %outputs "out"))
6615 (string-append "MANDIR=" (assoc-ref %outputs "out")
6616 "/share/man/man1"))))
6618 `(("pkg-config" ,pkg-config)))
6622 (home-page "https://vcftools.github.io/")
6623 (synopsis "Tools for working with VCF files")
6625 "VCFtools is a program package designed for working with VCF files, such
6626 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
6627 provide easily accessible methods for working with complex genetic variation
6628 data in the form of VCF files.")
6629 ;; The license is declared as LGPLv3 in the README and
6630 ;; at https://vcftools.github.io/license.html
6631 (license license:lgpl3)))
6633 (define-public infernal
6639 (uri (string-append "http://eddylab.org/software/infernal/"
6640 "infernal-" version ".tar.gz"))
6643 "0pm8bm3s6nfa0av4x6m6h27lsg12b3lz3jm0fyh1mc77l2isd61v"))))
6644 (build-system gnu-build-system)
6647 ("python" ,python))) ; for tests
6648 (home-page "http://eddylab.org/infernal/")
6649 (synopsis "Inference of RNA alignments")
6650 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
6651 searching DNA sequence databases for RNA structure and sequence similarities.
6652 It is an implementation of a special case of profile stochastic context-free
6653 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
6654 profile, but it scores a combination of sequence consensus and RNA secondary
6655 structure consensus, so in many cases, it is more capable of identifying RNA
6656 homologs that conserve their secondary structure more than their primary
6658 ;; Infernal 1.1.3 requires VMX or SSE capability for parallel instructions.
6659 (supported-systems '("i686-linux" "x86_64-linux"))
6660 (license license:bsd-3)))
6662 (define-public r-scde
6669 (url "https://github.com/hms-dbmi/scde.git")
6671 (file-name (git-file-name name version))
6674 "10na2gyka24mszdxf92wz9h2c13hdf1ww30c68gfsw53lvvhhhxb"))))
6675 (build-system r-build-system)
6677 `(("r-rcpp" ,r-rcpp)
6678 ("r-rcpparmadillo" ,r-rcpparmadillo)
6681 ("r-rjson" ,r-rjson)
6682 ("r-cairo" ,r-cairo)
6683 ("r-rcolorbrewer" ,r-rcolorbrewer)
6684 ("r-edger" ,r-edger)
6685 ("r-quantreg" ,r-quantreg)
6687 ("r-rmtstat" ,r-rmtstat)
6688 ("r-extremes" ,r-extremes)
6689 ("r-pcamethods" ,r-pcamethods)
6690 ("r-biocparallel" ,r-biocparallel)
6691 ("r-flexmix" ,r-flexmix)))
6692 (home-page "https://hms-dbmi.github.io/scde/")
6693 (synopsis "R package for analyzing single-cell RNA-seq data")
6694 (description "The SCDE package implements a set of statistical methods for
6695 analyzing single-cell RNA-seq data. SCDE fits individual error models for
6696 single-cell RNA-seq measurements. These models can then be used for
6697 assessment of differential expression between groups of cells, as well as
6698 other types of analysis. The SCDE package also contains the pagoda framework
6699 which applies pathway and gene set overdispersion analysis to identify aspects
6700 of transcriptional heterogeneity among single cells.")
6701 ;; See https://github.com/hms-dbmi/scde/issues/38
6702 (license license:gpl2)))
6704 (define-public r-centipede
6706 (name "r-centipede")
6710 (uri (string-append "http://download.r-forge.r-project.org/"
6711 "src/contrib/CENTIPEDE_" version ".tar.gz"))
6714 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
6715 (build-system r-build-system)
6716 (home-page "http://centipede.uchicago.edu/")
6717 (synopsis "Predict transcription factor binding sites")
6719 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
6720 of the genome that are bound by particular transcription factors. It starts
6721 by identifying a set of candidate binding sites, and then aims to classify the
6722 sites according to whether each site is bound or not bound by a transcription
6723 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
6724 between two different types of motif instances using as much relevant
6725 information as possible.")
6726 (license (list license:gpl2+ license:gpl3+))))
6728 (define-public r-genefilter
6730 (name "r-genefilter")
6735 (uri (bioconductor-uri "genefilter" version))
6738 "1xjr02qhldspjwd6y374wgik18fgywb6408wsz471i8b4ik98ckc"))))
6739 (build-system r-build-system)
6741 `(("gfortran" ,gfortran)))
6743 `(("r-annotate" ,r-annotate)
6744 ("r-annotationdbi" ,r-annotationdbi)
6745 ("r-biobase" ,r-biobase)
6746 ("r-biocgenerics" ,r-biocgenerics)
6747 ("r-survival" ,r-survival)))
6748 (home-page "https://bioconductor.org/packages/genefilter")
6749 (synopsis "Filter genes from high-throughput experiments")
6751 "This package provides basic functions for filtering genes from
6752 high-throughput sequencing experiments.")
6753 (license license:artistic2.0)))
6755 (define-public r-deseq2
6762 (uri (bioconductor-uri "DESeq2" version))
6765 "1lmbhznfs8dz9ipd53z4ccwvwxqwzx1ayw56jlrvlsambaj8fash"))))
6766 (properties `((upstream-name . "DESeq2")))
6767 (build-system r-build-system)
6769 `(("r-biobase" ,r-biobase)
6770 ("r-biocgenerics" ,r-biocgenerics)
6771 ("r-biocparallel" ,r-biocparallel)
6772 ("r-genefilter" ,r-genefilter)
6773 ("r-geneplotter" ,r-geneplotter)
6774 ("r-genomicranges" ,r-genomicranges)
6775 ("r-ggplot2" ,r-ggplot2)
6776 ("r-hmisc" ,r-hmisc)
6777 ("r-iranges" ,r-iranges)
6778 ("r-locfit" ,r-locfit)
6780 ("r-rcpparmadillo" ,r-rcpparmadillo)
6781 ("r-s4vectors" ,r-s4vectors)
6782 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6783 (home-page "https://bioconductor.org/packages/DESeq2")
6784 (synopsis "Differential gene expression analysis")
6786 "This package provides functions to estimate variance-mean dependence in
6787 count data from high-throughput nucleotide sequencing assays and test for
6788 differential expression based on a model using the negative binomial
6790 (license license:lgpl3+)))
6792 (define-public r-dexseq
6799 (uri (bioconductor-uri "DEXSeq" version))
6802 "0sqqb65ckliif2nmvlvc7w49id59z0nvqcdz5gry8l2mn6azrf6a"))))
6803 (properties `((upstream-name . "DEXSeq")))
6804 (build-system r-build-system)
6806 `(("r-annotationdbi" ,r-annotationdbi)
6807 ("r-biobase" ,r-biobase)
6808 ("r-biocgenerics" ,r-biocgenerics)
6809 ("r-biocparallel" ,r-biocparallel)
6810 ("r-biomart" ,r-biomart)
6811 ("r-deseq2" ,r-deseq2)
6812 ("r-genefilter" ,r-genefilter)
6813 ("r-geneplotter" ,r-geneplotter)
6814 ("r-genomicranges" ,r-genomicranges)
6815 ("r-hwriter" ,r-hwriter)
6816 ("r-iranges" ,r-iranges)
6817 ("r-rcolorbrewer" ,r-rcolorbrewer)
6818 ("r-rsamtools" ,r-rsamtools)
6819 ("r-s4vectors" ,r-s4vectors)
6820 ("r-statmod" ,r-statmod)
6821 ("r-stringr" ,r-stringr)
6822 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6823 (home-page "https://bioconductor.org/packages/DEXSeq")
6824 (synopsis "Inference of differential exon usage in RNA-Seq")
6826 "This package is focused on finding differential exon usage using RNA-seq
6827 exon counts between samples with different experimental designs. It provides
6828 functions that allows the user to make the necessary statistical tests based
6829 on a model that uses the negative binomial distribution to estimate the
6830 variance between biological replicates and generalized linear models for
6831 testing. The package also provides functions for the visualization and
6832 exploration of the results.")
6833 (license license:gpl3+)))
6835 (define-public r-annotationforge
6837 (name "r-annotationforge")
6842 (uri (bioconductor-uri "AnnotationForge" version))
6845 "0h2r60v339ajk5r6xq4iwwcpihdvf12fi8255byr2dhglzrd8xl7"))))
6847 `((upstream-name . "AnnotationForge")))
6848 (build-system r-build-system)
6850 `(("r-annotationdbi" ,r-annotationdbi)
6851 ("r-biobase" ,r-biobase)
6852 ("r-biocgenerics" ,r-biocgenerics)
6854 ("r-rcurl" ,r-rcurl)
6855 ("r-rsqlite" ,r-rsqlite)
6856 ("r-s4vectors" ,r-s4vectors)
6858 (home-page "https://bioconductor.org/packages/AnnotationForge")
6859 (synopsis "Code for building annotation database packages")
6861 "This package provides code for generating Annotation packages and their
6862 databases. Packages produced are intended to be used with AnnotationDbi.")
6863 (license license:artistic2.0)))
6865 (define-public r-rbgl
6872 (uri (bioconductor-uri "RBGL" version))
6875 "0ixbkdirf08i400db587r262j52sdwdgk3884nxk5xkbhx2m6vg0"))))
6876 (properties `((upstream-name . "RBGL")))
6877 (build-system r-build-system)
6880 ("r-graph" ,r-graph)))
6881 (home-page "https://www.bioconductor.org/packages/RBGL")
6882 (synopsis "Interface to the Boost graph library")
6884 "This package provides a fairly extensive and comprehensive interface to
6885 the graph algorithms contained in the Boost library.")
6886 (license license:artistic2.0)))
6888 (define-public r-gseabase
6895 (uri (bioconductor-uri "GSEABase" version))
6898 "0kcb90sxlf19d5dxhdbqk9x62svky4262cccl0wxarbq6gf3bd57"))))
6899 (properties `((upstream-name . "GSEABase")))
6900 (build-system r-build-system)
6902 `(("r-annotate" ,r-annotate)
6903 ("r-annotationdbi" ,r-annotationdbi)
6904 ("r-biobase" ,r-biobase)
6905 ("r-biocgenerics" ,r-biocgenerics)
6906 ("r-graph" ,r-graph)
6908 (home-page "https://bioconductor.org/packages/GSEABase")
6909 (synopsis "Gene set enrichment data structures and methods")
6911 "This package provides classes and methods to support @dfn{Gene Set
6912 Enrichment Analysis} (GSEA).")
6913 (license license:artistic2.0)))
6915 (define-public r-category
6922 (uri (bioconductor-uri "Category" version))
6925 "0ga0ij9hyzsxa5pavwmv35i8xggia2wygrk4m4z8an0qcvgy3v5g"))))
6926 (properties `((upstream-name . "Category")))
6927 (build-system r-build-system)
6929 `(("r-annotate" ,r-annotate)
6930 ("r-annotationdbi" ,r-annotationdbi)
6931 ("r-biobase" ,r-biobase)
6932 ("r-biocgenerics" ,r-biocgenerics)
6933 ("r-genefilter" ,r-genefilter)
6934 ("r-graph" ,r-graph)
6935 ("r-gseabase" ,r-gseabase)
6936 ("r-matrix" ,r-matrix)
6939 (home-page "https://bioconductor.org/packages/Category")
6940 (synopsis "Category analysis")
6942 "This package provides a collection of tools for performing category
6944 (license license:artistic2.0)))
6946 (define-public r-gostats
6953 (uri (bioconductor-uri "GOstats" version))
6956 "19f4gxm3sbprqrnwzvskvywv6j4ibm8xkrbgg4h0fvh2b5331nwc"))))
6957 (properties `((upstream-name . "GOstats")))
6958 (build-system r-build-system)
6960 `(("r-annotate" ,r-annotate)
6961 ("r-annotationdbi" ,r-annotationdbi)
6962 ("r-annotationforge" ,r-annotationforge)
6963 ("r-biobase" ,r-biobase)
6964 ("r-category" ,r-category)
6965 ("r-go-db" ,r-go-db)
6966 ("r-graph" ,r-graph)
6967 ("r-rgraphviz" ,r-rgraphviz)
6968 ("r-rbgl" ,r-rbgl)))
6969 (home-page "https://bioconductor.org/packages/GOstats")
6970 (synopsis "Tools for manipulating GO and microarrays")
6972 "This package provides a set of tools for interacting with GO and
6973 microarray data. A variety of basic manipulation tools for graphs, hypothesis
6974 testing and other simple calculations.")
6975 (license license:artistic2.0)))
6977 (define-public r-shortread
6979 (name "r-shortread")
6984 (uri (bioconductor-uri "ShortRead" version))
6987 "0ykyrj4g6vc67d5s46sp4659qvar2iavflzhggm79w4p50hxia4s"))))
6988 (properties `((upstream-name . "ShortRead")))
6989 (build-system r-build-system)
6993 `(("r-biobase" ,r-biobase)
6994 ("r-biocgenerics" ,r-biocgenerics)
6995 ("r-biocparallel" ,r-biocparallel)
6996 ("r-biostrings" ,r-biostrings)
6997 ("r-genomeinfodb" ,r-genomeinfodb)
6998 ("r-genomicalignments" ,r-genomicalignments)
6999 ("r-genomicranges" ,r-genomicranges)
7000 ("r-hwriter" ,r-hwriter)
7001 ("r-iranges" ,r-iranges)
7002 ("r-lattice" ,r-lattice)
7003 ("r-latticeextra" ,r-latticeextra)
7004 ("r-rsamtools" ,r-rsamtools)
7005 ("r-s4vectors" ,r-s4vectors)
7006 ("r-xvector" ,r-xvector)
7007 ("r-zlibbioc" ,r-zlibbioc)))
7008 (home-page "https://bioconductor.org/packages/ShortRead")
7009 (synopsis "FASTQ input and manipulation tools")
7011 "This package implements sampling, iteration, and input of FASTQ files.
7012 It includes functions for filtering and trimming reads, and for generating a
7013 quality assessment report. Data are represented as
7014 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
7015 purposes. The package also contains legacy support for early single-end,
7016 ungapped alignment formats.")
7017 (license license:artistic2.0)))
7019 (define-public r-systempiper
7021 (name "r-systempiper")
7026 (uri (bioconductor-uri "systemPipeR" version))
7029 "17r25v9wcglyma2v1c8fka80dm7fx86saxlsb2aprmwi4h3dhb0j"))))
7030 (properties `((upstream-name . "systemPipeR")))
7031 (build-system r-build-system)
7033 `(("r-annotate" ,r-annotate)
7034 ("r-batchtools" ,r-batchtools)
7035 ("r-biocgenerics" ,r-biocgenerics)
7036 ("r-biostrings" ,r-biostrings)
7037 ("r-deseq2" ,r-deseq2)
7038 ("r-edger" ,r-edger)
7039 ("r-genomicfeatures" ,r-genomicfeatures)
7040 ("r-genomicranges" ,r-genomicranges)
7041 ("r-ggplot2" ,r-ggplot2)
7042 ("r-go-db" ,r-go-db)
7043 ("r-gostats" ,r-gostats)
7044 ("r-limma" ,r-limma)
7045 ("r-pheatmap" ,r-pheatmap)
7046 ("r-rjson" ,r-rjson)
7047 ("r-rsamtools" ,r-rsamtools)
7048 ("r-shortread" ,r-shortread)
7049 ("r-summarizedexperiment" ,r-summarizedexperiment)
7051 ("r-variantannotation" ,r-variantannotation)))
7052 (home-page "https://github.com/tgirke/systemPipeR")
7053 (synopsis "Next generation sequencing workflow and reporting environment")
7055 "This R package provides tools for building and running automated
7056 end-to-end analysis workflows for a wide range of @dfn{next generation
7057 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
7058 Important features include a uniform workflow interface across different NGS
7059 applications, automated report generation, and support for running both R and
7060 command-line software, such as NGS aligners or peak/variant callers, on local
7061 computers or compute clusters. Efficient handling of complex sample sets and
7062 experimental designs is facilitated by a consistently implemented sample
7063 annotation infrastructure.")
7064 (license license:artistic2.0)))
7066 (define-public r-grohmm
7073 (uri (bioconductor-uri "groHMM" version))
7076 "0ywr8f6bfhg2ia3n4rmsxr4v1xqmlyhkwh0rvkgh3yqgnbvihndg"))))
7077 (properties `((upstream-name . "groHMM")))
7078 (build-system r-build-system)
7080 `(("r-genomeinfodb" ,r-genomeinfodb)
7081 ("r-genomicalignments" ,r-genomicalignments)
7082 ("r-genomicranges" ,r-genomicranges)
7083 ("r-iranges" ,r-iranges)
7085 ("r-rtracklayer" ,r-rtracklayer)
7086 ("r-s4vectors" ,r-s4vectors)))
7087 (home-page "https://github.com/Kraus-Lab/groHMM")
7088 (synopsis "GRO-seq analysis pipeline")
7090 "This package provides a pipeline for the analysis of GRO-seq data.")
7091 (license license:gpl3+)))
7093 (define-public vsearch
7101 (url "https://github.com/torognes/vsearch.git")
7102 (commit (string-append "v" version))))
7103 (file-name (git-file-name name version))
7106 "0vhrpjfdf75ba04b24xknp41790cvcgwl0vgpy7qbzj5xh2521ss"))
7107 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
7110 ;; Remove bundled cityhash sources. The vsearch source is adjusted
7111 ;; for this in the patch.
7112 (delete-file "src/city.h")
7113 (delete-file "src/citycrc.h")
7114 (delete-file "src/city.cc")
7116 (build-system gnu-build-system)
7120 ("cityhash" ,cityhash)))
7122 `(("autoconf" ,autoconf)
7123 ("automake" ,automake)))
7124 (synopsis "Sequence search tools for metagenomics")
7126 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
7127 dereplication, pairwise alignment, shuffling, subsampling, sorting and
7128 masking. The tool takes advantage of parallelism in the form of SIMD
7129 vectorization as well as multiple threads to perform accurate alignments at
7130 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
7131 Needleman-Wunsch).")
7132 (home-page "https://github.com/torognes/vsearch")
7133 ;; vsearch uses non-portable SSE intrinsics so building fails on other
7135 (supported-systems '("x86_64-linux"))
7136 ;; Dual licensed; also includes public domain source.
7137 (license (list license:gpl3 license:bsd-2))))
7139 (define-public pardre
7142 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
7147 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
7151 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
7152 (build-system gnu-build-system)
7154 `(#:tests? #f ; no tests included
7156 (modify-phases %standard-phases
7159 (lambda* (#:key outputs #:allow-other-keys)
7160 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
7161 (install-file "ParDRe" bin)
7164 `(("openmpi" ,openmpi)
7166 (synopsis "Parallel tool to remove duplicate DNA reads")
7168 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
7169 Duplicate reads can be seen as identical or nearly identical sequences with
7170 some mismatches. This tool lets users avoid the analysis of unnecessary
7171 reads, reducing the time of subsequent procedures with the
7172 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
7173 in order to exploit the parallel capabilities of multicore clusters. It is
7174 faster than multithreaded counterparts (end of 2015) for the same number of
7175 cores and, thanks to the message-passing technology, it can be executed on
7177 (home-page "https://sourceforge.net/projects/pardre/")
7178 (license license:gpl3+)))
7180 (define-public ruby-bio-kseq
7182 (name "ruby-bio-kseq")
7187 (uri (rubygems-uri "bio-kseq" version))
7190 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
7191 (build-system ruby-build-system)
7193 `(#:test-target "spec"))
7195 `(("bundler" ,bundler)
7196 ("ruby-rspec" ,ruby-rspec)
7197 ("ruby-rake-compiler" ,ruby-rake-compiler)))
7200 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
7202 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
7203 FASTQ parsing code. It provides a fast iterator over sequences and their
7205 (home-page "https://github.com/gusevfe/bio-kseq")
7206 (license license:expat)))
7208 (define-public bio-locus
7215 (uri (rubygems-uri "bio-locus" version))
7218 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
7219 (build-system ruby-build-system)
7221 `(("ruby-rspec" ,ruby-rspec)))
7222 (synopsis "Tool for fast querying of genome locations")
7224 "Bio-locus is a tabix-like tool for fast querying of genome
7225 locations. Many file formats in bioinformatics contain records that
7226 start with a chromosome name and a position for a SNP, or a start-end
7227 position for indels. Bio-locus allows users to store this chr+pos or
7228 chr+pos+alt information in a database.")
7229 (home-page "https://github.com/pjotrp/bio-locus")
7230 (license license:expat)))
7232 (define-public bio-blastxmlparser
7234 (name "bio-blastxmlparser")
7238 (uri (rubygems-uri "bio-blastxmlparser" version))
7241 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
7242 (build-system ruby-build-system)
7244 `(("ruby-bio-logger" ,ruby-bio-logger)
7245 ("ruby-nokogiri" ,ruby-nokogiri)))
7247 `(("ruby-rspec" ,ruby-rspec)))
7248 (synopsis "Fast big data BLAST XML parser and library")
7250 "Very fast parallel big-data BLAST XML file parser which can be used as
7251 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
7252 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
7253 (home-page "https://github.com/pjotrp/blastxmlparser")
7254 (license license:expat)))
7256 (define-public bioruby
7263 (uri (rubygems-uri "bio" version))
7266 "1d56amdsjv1mag7m6gv2w0xij8hqx1v5xbdjsix8sp3yp36m7938"))))
7267 (build-system ruby-build-system)
7269 `(("ruby-libxml" ,ruby-libxml)))
7271 `(("which" ,which))) ; required for test phase
7274 (modify-phases %standard-phases
7275 (add-before 'build 'patch-test-command
7277 (substitute* '("test/functional/bio/test_command.rb")
7278 (("/bin/sh") (which "sh")))
7279 (substitute* '("test/functional/bio/test_command.rb")
7280 (("/bin/ls") (which "ls")))
7281 (substitute* '("test/functional/bio/test_command.rb")
7282 (("which") (which "which")))
7283 (substitute* '("test/functional/bio/test_command.rb",
7284 "test/data/command/echoarg2.sh")
7285 (("/bin/echo") (which "echo")))
7287 (synopsis "Ruby library, shell and utilities for bioinformatics")
7288 (description "BioRuby comes with a comprehensive set of Ruby development
7289 tools and libraries for bioinformatics and molecular biology. BioRuby has
7290 components for sequence analysis, pathway analysis, protein modelling and
7291 phylogenetic analysis; it supports many widely used data formats and provides
7292 easy access to databases, external programs and public web services, including
7293 BLAST, KEGG, GenBank, MEDLINE and GO.")
7294 (home-page "http://bioruby.org/")
7295 ;; Code is released under Ruby license, except for setup
7296 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
7297 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
7299 (define-public r-biocviews
7301 (name "r-biocviews")
7305 (uri (bioconductor-uri "biocViews" version))
7308 "0yn8jys1900d31haayz0ppqk5y79mwjajwp4alz6pln3dbs70f3g"))))
7310 `((upstream-name . "biocViews")))
7311 (build-system r-build-system)
7313 `(("r-biobase" ,r-biobase)
7314 ("r-biocmanager" ,r-biocmanager)
7315 ("r-graph" ,r-graph)
7317 ("r-rcurl" ,r-rcurl)
7319 ("r-runit" ,r-runit)))
7320 (home-page "https://bioconductor.org/packages/biocViews")
7321 (synopsis "Bioconductor package categorization helper")
7322 (description "The purpose of biocViews is to create HTML pages that
7323 categorize packages in a Bioconductor package repository according to keywords,
7324 also known as views, in a controlled vocabulary.")
7325 (license license:artistic2.0)))
7327 (define-public r-biocstyle
7329 (name "r-biocstyle")
7333 (uri (bioconductor-uri "BiocStyle" version))
7336 "1x71in059zql40f4c87bd1gf96r945kdvwbq61jmch9d3d8nwxbb"))))
7338 `((upstream-name . "BiocStyle")))
7339 (build-system r-build-system)
7341 `(("r-biocmanager" ,r-biocmanager)
7342 ("r-bookdown" ,r-bookdown)
7343 ("r-knitr" ,r-knitr)
7344 ("r-rmarkdown" ,r-rmarkdown)
7345 ("r-yaml" ,r-yaml)))
7346 (home-page "https://bioconductor.org/packages/BiocStyle")
7347 (synopsis "Bioconductor formatting styles")
7348 (description "This package provides standard formatting styles for
7349 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
7351 (license license:artistic2.0)))
7353 (define-public r-bioccheck
7355 (name "r-bioccheck")
7359 (uri (bioconductor-uri "BiocCheck" version))
7362 "1qnvl5yajgh67ijkq6gdsafri1k5hyw5gzn2ccqk9ymx6i2xd80g"))))
7364 `((upstream-name . "BiocCheck")))
7365 (build-system r-build-system)
7368 (modify-phases %standard-phases
7369 ;; This package can be used by calling BiocCheck(<package>) from
7370 ;; within R, or by running R CMD BiocCheck <package>. This phase
7371 ;; makes sure the latter works. For this to work, the BiocCheck
7372 ;; script must be somewhere on the PATH (not the R bin directory).
7373 (add-after 'install 'install-bioccheck-subcommand
7374 (lambda* (#:key outputs #:allow-other-keys)
7375 (let* ((out (assoc-ref outputs "out"))
7376 (dest-dir (string-append out "/bin"))
7378 (string-append out "/site-library/BiocCheck/script/")))
7380 (symlink (string-append script-dir "/checkBadDeps.R")
7381 (string-append dest-dir "/checkBadDeps.R"))
7382 (symlink (string-append script-dir "/BiocCheck")
7383 (string-append dest-dir "/BiocCheck")))
7386 `(("r-codetools" ,r-codetools)
7387 ("r-graph" ,r-graph)
7389 ("r-knitr" ,r-knitr)
7390 ("r-optparse" ,r-optparse)
7391 ("r-biocmanager" ,r-biocmanager)
7392 ("r-biocviews" ,r-biocviews)
7393 ("r-stringdist" ,r-stringdist)))
7394 (home-page "https://bioconductor.org/packages/BiocCheck")
7395 (synopsis "Executes Bioconductor-specific package checks")
7396 (description "This package contains tools to perform additional quality
7397 checks on R packages that are to be submitted to the Bioconductor repository.")
7398 (license license:artistic2.0)))
7400 (define-public r-s4vectors
7402 (name "r-s4vectors")
7406 (uri (bioconductor-uri "S4Vectors" version))
7409 "01f7dms4kw9ajwqlvh5s47riv748xrrs41na03byhjvn4fbdc44y"))))
7411 `((upstream-name . "S4Vectors")))
7412 (build-system r-build-system)
7414 `(("r-biocgenerics" ,r-biocgenerics)))
7415 (home-page "https://bioconductor.org/packages/S4Vectors")
7416 (synopsis "S4 implementation of vectors and lists")
7418 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7419 classes and a set of generic functions that extend the semantic of ordinary
7420 vectors and lists in R. Package developers can easily implement vector-like
7421 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7422 In addition, a few low-level concrete subclasses of general interest (e.g.
7423 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7424 S4Vectors package itself.")
7425 (license license:artistic2.0)))
7427 (define-public r-iranges
7433 (uri (bioconductor-uri "IRanges" version))
7436 "1jhnxb9yacmj2z82b6992gihjvj1a0gnjwbjiagyyx03fqnv23kg"))))
7438 `((upstream-name . "IRanges")))
7439 (build-system r-build-system)
7441 `(("r-biocgenerics" ,r-biocgenerics)
7442 ("r-s4vectors" ,r-s4vectors)))
7443 (home-page "https://bioconductor.org/packages/IRanges")
7444 (synopsis "Infrastructure for manipulating intervals on sequences")
7446 "This package provides efficient low-level and highly reusable S4 classes
7447 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7448 generally, data that can be organized sequentially (formally defined as
7449 @code{Vector} objects), as well as views on these @code{Vector} objects.
7450 Efficient list-like classes are also provided for storing big collections of
7451 instances of the basic classes. All classes in the package use consistent
7452 naming and share the same rich and consistent \"Vector API\" as much as
7454 (license license:artistic2.0)))
7456 (define-public r-genomeinfodbdata
7458 (name "r-genomeinfodbdata")
7462 ;; We cannot use bioconductor-uri here because this tarball is
7463 ;; located under "data/annotation/" instead of "bioc/".
7464 (uri (string-append "https://bioconductor.org/packages/release/"
7465 "data/annotation/src/contrib/GenomeInfoDbData_"
7469 "0di6nlqpsyqf693k2na65ayqldih563x3zfrczpqc5q2hl5kg35c"))))
7471 `((upstream-name . "GenomeInfoDbData")))
7472 (build-system r-build-system)
7473 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7474 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7475 (description "This package contains data for mapping between NCBI taxonomy
7476 ID and species. It is used by functions in the GenomeInfoDb package.")
7477 (license license:artistic2.0)))
7479 (define-public r-genomeinfodb
7481 (name "r-genomeinfodb")
7485 (uri (bioconductor-uri "GenomeInfoDb" version))
7488 "07zljs2mfi8rf31g903f43v2f7767xbnflfrx9qjnmgf7bm039x0"))))
7490 `((upstream-name . "GenomeInfoDb")))
7491 (build-system r-build-system)
7493 `(("r-biocgenerics" ,r-biocgenerics)
7494 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7495 ("r-iranges" ,r-iranges)
7496 ("r-rcurl" ,r-rcurl)
7497 ("r-s4vectors" ,r-s4vectors)))
7498 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7499 (synopsis "Utilities for manipulating chromosome identifiers")
7501 "This package contains data and functions that define and allow
7502 translation between different chromosome sequence naming conventions (e.g.,
7503 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7504 names in their natural, rather than lexicographic, order.")
7505 (license license:artistic2.0)))
7507 (define-public r-edger
7513 (uri (bioconductor-uri "edgeR" version))
7516 "07dv99kl7jfa62nzcq705r56gcpb1hq7p4px48j71y2ddi1rqmr6"))))
7517 (properties `((upstream-name . "edgeR")))
7518 (build-system r-build-system)
7520 `(("r-limma" ,r-limma)
7521 ("r-locfit" ,r-locfit)
7523 ("r-statmod" ,r-statmod))) ;for estimateDisp
7524 (home-page "http://bioinf.wehi.edu.au/edgeR")
7525 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7526 (description "This package can do differential expression analysis of
7527 RNA-seq expression profiles with biological replication. It implements a range
7528 of statistical methodology based on the negative binomial distributions,
7529 including empirical Bayes estimation, exact tests, generalized linear models
7530 and quasi-likelihood tests. It be applied to differential signal analysis of
7531 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7533 (license license:gpl2+)))
7535 (define-public r-variantannotation
7537 (name "r-variantannotation")
7541 (uri (bioconductor-uri "VariantAnnotation" version))
7544 "009s7rzp78s2w6iybizina42qx2w8qv3xwjbkpqphmm451maykgs"))))
7546 `((upstream-name . "VariantAnnotation")))
7550 `(("r-annotationdbi" ,r-annotationdbi)
7551 ("r-biobase" ,r-biobase)
7552 ("r-biocgenerics" ,r-biocgenerics)
7553 ("r-biostrings" ,r-biostrings)
7554 ("r-bsgenome" ,r-bsgenome)
7556 ("r-genomeinfodb" ,r-genomeinfodb)
7557 ("r-genomicfeatures" ,r-genomicfeatures)
7558 ("r-genomicranges" ,r-genomicranges)
7559 ("r-iranges" ,r-iranges)
7560 ("r-summarizedexperiment" ,r-summarizedexperiment)
7561 ("r-rhtslib" ,r-rhtslib)
7562 ("r-rsamtools" ,r-rsamtools)
7563 ("r-rtracklayer" ,r-rtracklayer)
7564 ("r-s4vectors" ,r-s4vectors)
7565 ("r-xvector" ,r-xvector)
7566 ("r-zlibbioc" ,r-zlibbioc)))
7567 (build-system r-build-system)
7568 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7569 (synopsis "Package for annotation of genetic variants")
7570 (description "This R package can annotate variants, compute amino acid
7571 coding changes and predict coding outcomes.")
7572 (license license:artistic2.0)))
7574 (define-public r-limma
7580 (uri (bioconductor-uri "limma" version))
7583 "1nd01r7rd7jb5qz84vbgfnyrmgm9wiq7fsdji68537kjgvrzmm9z"))))
7584 (build-system r-build-system)
7585 (home-page "http://bioinf.wehi.edu.au/limma")
7586 (synopsis "Package for linear models for microarray and RNA-seq data")
7587 (description "This package can be used for the analysis of gene expression
7588 studies, especially the use of linear models for analysing designed experiments
7589 and the assessment of differential expression. The analysis methods apply to
7590 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7591 (license license:gpl2+)))
7593 (define-public r-xvector
7599 (uri (bioconductor-uri "XVector" version))
7602 "0s2gg84yzl5ffkzp6n7kh0jjk1vd90z189f5hkfn18rn67cy2nv7"))))
7604 `((upstream-name . "XVector")))
7605 (build-system r-build-system)
7608 (modify-phases %standard-phases
7609 (add-after 'unpack 'use-system-zlib
7611 (substitute* "DESCRIPTION"
7612 (("zlibbioc, ") ""))
7613 (substitute* "NAMESPACE"
7614 (("import\\(zlibbioc\\)") ""))
7619 `(("r-biocgenerics" ,r-biocgenerics)
7620 ("r-iranges" ,r-iranges)
7621 ("r-s4vectors" ,r-s4vectors)))
7622 (home-page "https://bioconductor.org/packages/XVector")
7623 (synopsis "Representation and manpulation of external sequences")
7625 "This package provides memory efficient S4 classes for storing sequences
7626 \"externally\" (behind an R external pointer, or on disk).")
7627 (license license:artistic2.0)))
7629 (define-public r-genomicranges
7631 (name "r-genomicranges")
7635 (uri (bioconductor-uri "GenomicRanges" version))
7638 "0xdds6ws7jjdfy4x3mb0qhy43kpxdmifmpw0jdk4wgw999zabb50"))))
7640 `((upstream-name . "GenomicRanges")))
7641 (build-system r-build-system)
7643 `(("r-biocgenerics" ,r-biocgenerics)
7644 ("r-genomeinfodb" ,r-genomeinfodb)
7645 ("r-iranges" ,r-iranges)
7646 ("r-s4vectors" ,r-s4vectors)
7647 ("r-xvector" ,r-xvector)))
7648 (home-page "https://bioconductor.org/packages/GenomicRanges")
7649 (synopsis "Representation and manipulation of genomic intervals")
7651 "This package provides tools to efficiently represent and manipulate
7652 genomic annotations and alignments is playing a central role when it comes to
7653 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7654 GenomicRanges package defines general purpose containers for storing and
7655 manipulating genomic intervals and variables defined along a genome.")
7656 (license license:artistic2.0)))
7658 (define-public r-biobase
7664 (uri (bioconductor-uri "Biobase" version))
7667 "1gx41083dqlm59vwqdxvc4ny31x91j48mda9n3scg0f2zwasvqgl"))))
7669 `((upstream-name . "Biobase")))
7670 (build-system r-build-system)
7672 `(("r-biocgenerics" ,r-biocgenerics)))
7673 (home-page "https://bioconductor.org/packages/Biobase")
7674 (synopsis "Base functions for Bioconductor")
7676 "This package provides functions that are needed by many other packages
7677 on Bioconductor or which replace R functions.")
7678 (license license:artistic2.0)))
7680 (define-public r-annotationdbi
7682 (name "r-annotationdbi")
7686 (uri (bioconductor-uri "AnnotationDbi" version))
7689 "09piz1f0xpbb4amskx4ilby6lfrn27hhwk75il2c4lq6m3hr4w8s"))))
7691 `((upstream-name . "AnnotationDbi")))
7692 (build-system r-build-system)
7694 `(("r-biobase" ,r-biobase)
7695 ("r-biocgenerics" ,r-biocgenerics)
7697 ("r-iranges" ,r-iranges)
7698 ("r-rsqlite" ,r-rsqlite)
7699 ("r-s4vectors" ,r-s4vectors)))
7700 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7701 (synopsis "Annotation database interface")
7703 "This package provides user interface and database connection code for
7704 annotation data packages using SQLite data storage.")
7705 (license license:artistic2.0)))
7707 (define-public r-biomart
7713 (uri (bioconductor-uri "biomaRt" version))
7716 "0difh4dsccjzhpfkvajy2adh98ym9164gd6clnsnic6qr6sk86ss"))))
7718 `((upstream-name . "biomaRt")))
7719 (build-system r-build-system)
7721 `(("r-annotationdbi" ,r-annotationdbi)
7722 ("r-biocfilecache" ,r-biocfilecache)
7724 ("r-openssl" ,r-openssl)
7725 ("r-progress" ,r-progress)
7726 ("r-rappdirs" ,r-rappdirs)
7727 ("r-stringr" ,r-stringr)
7729 (home-page "https://bioconductor.org/packages/biomaRt")
7730 (synopsis "Interface to BioMart databases")
7732 "biomaRt provides an interface to a growing collection of databases
7733 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7734 package enables retrieval of large amounts of data in a uniform way without
7735 the need to know the underlying database schemas or write complex SQL queries.
7736 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7737 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7738 users direct access to a diverse set of data and enable a wide range of
7739 powerful online queries from gene annotation to database mining.")
7740 (license license:artistic2.0)))
7742 (define-public r-biocparallel
7744 (name "r-biocparallel")
7748 (uri (bioconductor-uri "BiocParallel" version))
7751 "0g0znb4whsvb9hpwx9xaasdi5n4vjqw8cpdyqgrdrjm91rls1h21"))))
7753 `((upstream-name . "BiocParallel")))
7754 (build-system r-build-system)
7756 `(("r-futile-logger" ,r-futile-logger)
7759 (home-page "https://bioconductor.org/packages/BiocParallel")
7760 (synopsis "Bioconductor facilities for parallel evaluation")
7762 "This package provides modified versions and novel implementation of
7763 functions for parallel evaluation, tailored to use with Bioconductor
7765 (license (list license:gpl2+ license:gpl3+))))
7767 (define-public r-biostrings
7769 (name "r-biostrings")
7773 (uri (bioconductor-uri "Biostrings" version))
7776 "0pq7g2hflx2cjlpwdj6mscw9hnxvlf5y50dxf48lbrf9r3q9kmyp"))))
7778 `((upstream-name . "Biostrings")))
7779 (build-system r-build-system)
7781 `(("r-biocgenerics" ,r-biocgenerics)
7782 ("r-iranges" ,r-iranges)
7783 ("r-s4vectors" ,r-s4vectors)
7784 ("r-xvector" ,r-xvector)))
7785 (home-page "https://bioconductor.org/packages/Biostrings")
7786 (synopsis "String objects and algorithms for biological sequences")
7788 "This package provides memory efficient string containers, string
7789 matching algorithms, and other utilities, for fast manipulation of large
7790 biological sequences or sets of sequences.")
7791 (license license:artistic2.0)))
7793 (define-public r-rsamtools
7795 (name "r-rsamtools")
7799 (uri (bioconductor-uri "Rsamtools" version))
7802 "1vj43acawqqkf9yval9fzxarpsf04fmn78m2hq4f083w1k0myhyr"))))
7804 `((upstream-name . "Rsamtools")))
7805 (build-system r-build-system)
7808 (modify-phases %standard-phases
7809 (add-after 'unpack 'use-system-zlib
7811 (substitute* "DESCRIPTION"
7812 (("zlibbioc, ") ""))
7813 (substitute* "NAMESPACE"
7814 (("import\\(zlibbioc\\)") ""))
7819 `(("r-biocgenerics" ,r-biocgenerics)
7820 ("r-biocparallel" ,r-biocparallel)
7821 ("r-biostrings" ,r-biostrings)
7822 ("r-bitops" ,r-bitops)
7823 ("r-genomeinfodb" ,r-genomeinfodb)
7824 ("r-genomicranges" ,r-genomicranges)
7825 ("r-iranges" ,r-iranges)
7826 ("r-rhtslib" ,r-rhtslib)
7827 ("r-s4vectors" ,r-s4vectors)
7828 ("r-xvector" ,r-xvector)))
7829 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7830 (synopsis "Interface to samtools, bcftools, and tabix")
7832 "This package provides an interface to the @code{samtools},
7833 @code{bcftools}, and @code{tabix} utilities for manipulating SAM (Sequence
7834 Alignment / Map), FASTA, binary variant call (BCF) and compressed indexed
7835 tab-delimited (tabix) files.")
7836 (license license:expat)))
7838 (define-public r-delayedarray
7840 (name "r-delayedarray")
7844 (uri (bioconductor-uri "DelayedArray" version))
7847 "09lackgix5jpm16k0mz2zkibflfb4wzidbz4q32mlxmklf40037q"))))
7849 `((upstream-name . "DelayedArray")))
7850 (build-system r-build-system)
7852 `(("r-biocgenerics" ,r-biocgenerics)
7853 ("r-biocparallel" ,r-biocparallel)
7854 ("r-s4vectors" ,r-s4vectors)
7855 ("r-iranges" ,r-iranges)
7856 ("r-matrix" ,r-matrix)
7857 ("r-matrixstats" ,r-matrixstats)))
7858 (home-page "https://bioconductor.org/packages/DelayedArray")
7859 (synopsis "Delayed operations on array-like objects")
7861 "Wrapping an array-like object (typically an on-disk object) in a
7862 @code{DelayedArray} object allows one to perform common array operations on it
7863 without loading the object in memory. In order to reduce memory usage and
7864 optimize performance, operations on the object are either delayed or executed
7865 using a block processing mechanism. Note that this also works on in-memory
7866 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7867 @code{Matrix} objects, and ordinary arrays and data frames.")
7868 (license license:artistic2.0)))
7870 (define-public r-summarizedexperiment
7872 (name "r-summarizedexperiment")
7876 (uri (bioconductor-uri "SummarizedExperiment" version))
7879 "1z9bdk49dajafkfvv99nv6zyn6v70iyyy2jgdp5w5z8174a2bnn1"))))
7881 `((upstream-name . "SummarizedExperiment")))
7882 (build-system r-build-system)
7884 `(("r-biobase" ,r-biobase)
7885 ("r-biocgenerics" ,r-biocgenerics)
7886 ("r-delayedarray" ,r-delayedarray)
7887 ("r-genomeinfodb" ,r-genomeinfodb)
7888 ("r-genomicranges" ,r-genomicranges)
7889 ("r-iranges" ,r-iranges)
7890 ("r-matrix" ,r-matrix)
7891 ("r-s4vectors" ,r-s4vectors)))
7892 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
7893 (synopsis "Container for representing genomic ranges by sample")
7895 "The SummarizedExperiment container contains one or more assays, each
7896 represented by a matrix-like object of numeric or other mode. The rows
7897 typically represent genomic ranges of interest and the columns represent
7899 (license license:artistic2.0)))
7901 (define-public r-genomicalignments
7903 (name "r-genomicalignments")
7907 (uri (bioconductor-uri "GenomicAlignments" version))
7910 "065xvy4pkda0ajvl1b75iski95k1pnbhxwdq7vkfl8v55915vqh6"))))
7912 `((upstream-name . "GenomicAlignments")))
7913 (build-system r-build-system)
7915 `(("r-biocgenerics" ,r-biocgenerics)
7916 ("r-biocparallel" ,r-biocparallel)
7917 ("r-biostrings" ,r-biostrings)
7918 ("r-genomeinfodb" ,r-genomeinfodb)
7919 ("r-genomicranges" ,r-genomicranges)
7920 ("r-iranges" ,r-iranges)
7921 ("r-rsamtools" ,r-rsamtools)
7922 ("r-s4vectors" ,r-s4vectors)
7923 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7924 (home-page "https://bioconductor.org/packages/GenomicAlignments")
7925 (synopsis "Representation and manipulation of short genomic alignments")
7927 "This package provides efficient containers for storing and manipulating
7928 short genomic alignments (typically obtained by aligning short reads to a
7929 reference genome). This includes read counting, computing the coverage,
7930 junction detection, and working with the nucleotide content of the
7932 (license license:artistic2.0)))
7934 (define-public r-rtracklayer
7936 (name "r-rtracklayer")
7940 (uri (bioconductor-uri "rtracklayer" version))
7943 "0lp9xsm8kqrgpwgwj7qaqcv1z6qynbz084grlpwp94zsp2ppf0n6"))))
7944 (build-system r-build-system)
7947 (modify-phases %standard-phases
7948 (add-after 'unpack 'use-system-zlib
7950 (substitute* "DESCRIPTION"
7951 ((" zlibbioc,") ""))
7952 (substitute* "NAMESPACE"
7953 (("import\\(zlibbioc\\)") ""))
7956 `(("pkg-config" ,pkg-config)))
7960 `(("r-biocgenerics" ,r-biocgenerics)
7961 ("r-biostrings" ,r-biostrings)
7962 ("r-genomeinfodb" ,r-genomeinfodb)
7963 ("r-genomicalignments" ,r-genomicalignments)
7964 ("r-genomicranges" ,r-genomicranges)
7965 ("r-iranges" ,r-iranges)
7966 ("r-rcurl" ,r-rcurl)
7967 ("r-rsamtools" ,r-rsamtools)
7968 ("r-s4vectors" ,r-s4vectors)
7970 ("r-xvector" ,r-xvector)))
7971 (home-page "https://bioconductor.org/packages/rtracklayer")
7972 (synopsis "R interface to genome browsers and their annotation tracks")
7974 "rtracklayer is an extensible framework for interacting with multiple
7975 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7976 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7977 built-in). The user may export/import tracks to/from the supported browsers,
7978 as well as query and modify the browser state, such as the current viewport.")
7979 (license license:artistic2.0)))
7981 (define-public r-genomicfeatures
7983 (name "r-genomicfeatures")
7987 (uri (bioconductor-uri "GenomicFeatures" version))
7990 "0dd226kgks50jdx5w35f3wmg95hy8aibi4kcn8p5kmqp5i8j580b"))))
7992 `((upstream-name . "GenomicFeatures")))
7993 (build-system r-build-system)
7995 `(("r-annotationdbi" ,r-annotationdbi)
7996 ("r-biobase" ,r-biobase)
7997 ("r-biocgenerics" ,r-biocgenerics)
7998 ("r-biomart" ,r-biomart)
7999 ("r-biostrings" ,r-biostrings)
8001 ("r-genomeinfodb" ,r-genomeinfodb)
8002 ("r-genomicranges" ,r-genomicranges)
8003 ("r-iranges" ,r-iranges)
8004 ("r-rcurl" ,r-rcurl)
8005 ("r-rsqlite" ,r-rsqlite)
8006 ("r-rtracklayer" ,r-rtracklayer)
8007 ("r-s4vectors" ,r-s4vectors)
8008 ("r-xvector" ,r-xvector)))
8009 (home-page "https://bioconductor.org/packages/GenomicFeatures")
8010 (synopsis "Tools for working with transcript centric annotations")
8012 "This package provides a set of tools and methods for making and
8013 manipulating transcript centric annotations. With these tools the user can
8014 easily download the genomic locations of the transcripts, exons and cds of a
8015 given organism, from either the UCSC Genome Browser or a BioMart
8016 database (more sources will be supported in the future). This information is
8017 then stored in a local database that keeps track of the relationship between
8018 transcripts, exons, cds and genes. Flexible methods are provided for
8019 extracting the desired features in a convenient format.")
8020 (license license:artistic2.0)))
8022 (define-public r-go-db
8028 (uri (string-append "https://www.bioconductor.org/packages/"
8029 "release/data/annotation/src/contrib/GO.db_"
8033 "0i3wcf5h3n0dawzc1hy0kv74f06j80c47n4p3g3fmrcxlhi3jpa5"))))
8035 `((upstream-name . "GO.db")))
8036 (build-system r-build-system)
8038 `(("r-annotationdbi" ,r-annotationdbi)))
8039 (home-page "https://bioconductor.org/packages/GO.db")
8040 (synopsis "Annotation maps describing the entire Gene Ontology")
8042 "The purpose of this GO.db annotation package is to provide detailed
8043 information about the latest version of the Gene Ontologies.")
8044 (license license:artistic2.0)))
8046 (define-public r-topgo
8052 (uri (bioconductor-uri "topGO" version))
8055 "1kw9m2j67895k58lx9msc248pjwblp8clxwgsl01cql7sgi1xzlf"))))
8057 `((upstream-name . "topGO")))
8058 (build-system r-build-system)
8060 `(("r-annotationdbi" ,r-annotationdbi)
8062 ("r-biobase" ,r-biobase)
8063 ("r-biocgenerics" ,r-biocgenerics)
8064 ("r-go-db" ,r-go-db)
8065 ("r-graph" ,r-graph)
8066 ("r-lattice" ,r-lattice)
8067 ("r-matrixstats" ,r-matrixstats)
8068 ("r-sparsem" ,r-sparsem)))
8069 (home-page "https://bioconductor.org/packages/topGO")
8070 (synopsis "Enrichment analysis for gene ontology")
8072 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
8073 terms while accounting for the topology of the GO graph. Different test
8074 statistics and different methods for eliminating local similarities and
8075 dependencies between GO terms can be implemented and applied.")
8076 ;; Any version of the LGPL applies.
8077 (license license:lgpl2.1+)))
8079 (define-public r-bsgenome
8085 (uri (bioconductor-uri "BSgenome" version))
8088 "0nn1b3h4hmnx5whf2cmzmyxdrcf4myj8c38rwr0sw4rc07xfzndy"))))
8090 `((upstream-name . "BSgenome")))
8091 (build-system r-build-system)
8093 `(("r-biocgenerics" ,r-biocgenerics)
8094 ("r-biostrings" ,r-biostrings)
8095 ("r-genomeinfodb" ,r-genomeinfodb)
8096 ("r-genomicranges" ,r-genomicranges)
8097 ("r-iranges" ,r-iranges)
8098 ("r-rsamtools" ,r-rsamtools)
8099 ("r-rtracklayer" ,r-rtracklayer)
8100 ("r-s4vectors" ,r-s4vectors)
8101 ("r-xvector" ,r-xvector)))
8102 (home-page "https://bioconductor.org/packages/BSgenome")
8103 (synopsis "Infrastructure for Biostrings-based genome data packages")
8105 "This package provides infrastructure shared by all Biostrings-based
8106 genome data packages and support for efficient SNP representation.")
8107 (license license:artistic2.0)))
8109 (define-public r-impute
8115 (uri (bioconductor-uri "impute" version))
8118 "0igz1phjd1j9bg9z4kyy7j8v9bxi9sdwz4df26r51i2vavlbrf4q"))))
8120 `(("gfortran" ,gfortran)))
8121 (build-system r-build-system)
8122 (home-page "https://bioconductor.org/packages/impute")
8123 (synopsis "Imputation for microarray data")
8125 "This package provides a function to impute missing gene expression
8126 microarray data, using nearest neighbor averaging.")
8127 (license license:gpl2+)))
8129 (define-public r-seqpattern
8131 (name "r-seqpattern")
8135 (uri (bioconductor-uri "seqPattern" version))
8138 "1gxrq6s2hiyac69idh5r1nbr1s69n0hg4ap2skm4g6857av9pwqf"))))
8140 `((upstream-name . "seqPattern")))
8141 (build-system r-build-system)
8143 `(("r-biostrings" ,r-biostrings)
8144 ("r-genomicranges" ,r-genomicranges)
8145 ("r-iranges" ,r-iranges)
8146 ("r-kernsmooth" ,r-kernsmooth)
8147 ("r-plotrix" ,r-plotrix)))
8148 (home-page "https://bioconductor.org/packages/seqPattern")
8149 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
8151 "This package provides tools to visualize oligonucleotide patterns and
8152 sequence motif occurrences across a large set of sequences centred at a common
8153 reference point and sorted by a user defined feature.")
8154 (license license:gpl3+)))
8156 (define-public r-genomation
8158 (name "r-genomation")
8162 (uri (bioconductor-uri "genomation" version))
8165 "1sba928h23b67gr3i4yj1bg655g24l3bcgsf5gvymzrv5idrss1l"))))
8166 (build-system r-build-system)
8168 `(("r-biostrings" ,r-biostrings)
8169 ("r-bsgenome" ,r-bsgenome)
8170 ("r-data-table" ,r-data-table)
8171 ("r-genomeinfodb" ,r-genomeinfodb)
8172 ("r-genomicalignments" ,r-genomicalignments)
8173 ("r-genomicranges" ,r-genomicranges)
8174 ("r-ggplot2" ,r-ggplot2)
8175 ("r-gridbase" ,r-gridbase)
8176 ("r-impute" ,r-impute)
8177 ("r-iranges" ,r-iranges)
8178 ("r-matrixstats" ,r-matrixstats)
8179 ("r-plotrix" ,r-plotrix)
8182 ("r-readr" ,r-readr)
8183 ("r-reshape2" ,r-reshape2)
8184 ("r-rsamtools" ,r-rsamtools)
8185 ("r-rtracklayer" ,r-rtracklayer)
8186 ("r-runit" ,r-runit)
8187 ("r-s4vectors" ,r-s4vectors)
8188 ("r-seqpattern" ,r-seqpattern)))
8189 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8190 (synopsis "Summary, annotation and visualization of genomic data")
8192 "This package provides a package for summary and annotation of genomic
8193 intervals. Users can visualize and quantify genomic intervals over
8194 pre-defined functional regions, such as promoters, exons, introns, etc. The
8195 genomic intervals represent regions with a defined chromosome position, which
8196 may be associated with a score, such as aligned reads from HT-seq experiments,
8197 TF binding sites, methylation scores, etc. The package can use any tabular
8198 genomic feature data as long as it has minimal information on the locations of
8199 genomic intervals. In addition, it can use BAM or BigWig files as input.")
8200 (license license:artistic2.0)))
8202 (define-public r-genomationdata
8204 (name "r-genomationdata")
8208 ;; We cannot use bioconductor-uri here because this tarball is
8209 ;; located under "data/annotation/" instead of "bioc/".
8210 (uri (string-append "https://bioconductor.org/packages/"
8211 "release/data/experiment/src/contrib/"
8212 "genomationData_" version ".tar.gz"))
8215 "10xyb8akjrhmak2i0mnv1agny2ipy364q9nlibyplpzc7vdb6bw7"))))
8216 (build-system r-build-system)
8217 ;; As this package provides little more than large data files, it doesn't
8218 ;; make sense to build substitutes.
8219 (arguments `(#:substitutable? #f))
8221 `(("r-knitr" ,r-knitr)))
8222 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8223 (synopsis "Experimental data for use with the genomation package")
8225 "This package contains experimental genetic data for use with the
8226 genomation package. Included are Chip Seq, Methylation and Cage data,
8227 downloaded from Encode.")
8228 (license license:gpl3+)))
8230 (define-public r-seqlogo
8237 (uri (bioconductor-uri "seqLogo" version))
8240 "0s94aahp8ma1crmp83dz65ifjwrx6wqi3q6005lmbp8yk2x1rkj4"))))
8241 (properties `((upstream-name . "seqLogo")))
8242 (build-system r-build-system)
8243 (home-page "https://bioconductor.org/packages/seqLogo")
8244 (synopsis "Sequence logos for DNA sequence alignments")
8246 "seqLogo takes the position weight matrix of a DNA sequence motif and
8247 plots the corresponding sequence logo as introduced by Schneider and
8249 (license license:lgpl2.0+)))
8251 (define-public r-motifrg
8258 (uri (bioconductor-uri "motifRG" version))
8261 "0s6wdr036lra9x93r9k8wvicbkgzypjh3jp46h92yacw8d829k0d"))))
8262 (properties `((upstream-name . "motifRG")))
8263 (build-system r-build-system)
8265 `(("r-biostrings" ,r-biostrings)
8266 ("r-bsgenome" ,r-bsgenome)
8267 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8268 ("r-iranges" ,r-iranges)
8269 ("r-seqlogo" ,r-seqlogo)
8270 ("r-xvector" ,r-xvector)))
8271 (home-page "https://bioconductor.org/packages/motifRG")
8272 (synopsis "Discover motifs in high throughput sequencing data")
8274 "This package provides tools for discriminative motif discovery in high
8275 throughput genetic sequencing data sets using regression methods.")
8276 (license license:artistic2.0)))
8278 (define-public r-qtl
8285 (uri (string-append "mirror://cran/src/contrib/qtl_"
8289 "1d6qgj602fm6zia3djl4hmca0ri4v57ffp3g93p2yc3cabx2hq90"))))
8290 (build-system r-build-system)
8291 (home-page "https://rqtl.org/")
8292 (synopsis "R package for analyzing QTL experiments in genetics")
8293 (description "R/qtl is an extension library for the R statistics
8294 system. It is used to analyze experimental crosses for identifying
8295 genes contributing to variation in quantitative traits (so-called
8296 quantitative trait loci, QTLs).
8298 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
8299 identify genotyping errors, and to perform single-QTL and two-QTL,
8300 two-dimensional genome scans.")
8301 (license license:gpl3)))
8303 (define-public r-qtl2
8309 ;; Not yet available in cran.
8311 (url "https://github.com/rqtl/qtl2.git")
8313 (file-name (git-file-name name version))
8315 (base32 "0l1asr28q25jzbwrbg5490962sg3y4sjrd0qf09p78ws1aq8vfs0"))))
8316 (build-system r-build-system)
8318 `(("r-data-table" ,r-data-table)
8319 ("r-jsonlite" ,r-jsonlite)
8321 ("r-rcppeigen" ,r-rcppeigen)
8322 ("r-rsqlite" ,r-rsqlite)
8323 ("r-yaml" ,r-yaml)))
8324 (home-page "https://kbroman.org/qtl2/")
8326 "QTL analysis software for high-dimensional data and complex cross designs")
8328 "R/qtl2 (aka qtl2) is a reimplementation of the QTL analysis software
8329 R/qtl, to better handle high-dimensional data and complex cross designs.")
8330 (license license:gpl3)))
8332 (define-public r-zlibbioc
8338 (uri (bioconductor-uri "zlibbioc" version))
8341 "1xh7qan0w62mzsmanbx9vcj6ygdfhzw1abaxijkq7f4nh5w87idj"))))
8343 `((upstream-name . "zlibbioc")))
8344 (build-system r-build-system)
8345 (home-page "https://bioconductor.org/packages/zlibbioc")
8346 (synopsis "Provider for zlib-1.2.5 to R packages")
8347 (description "This package uses the source code of zlib-1.2.5 to create
8348 libraries for systems that do not have these available via other means.")
8349 (license license:artistic2.0)))
8351 (define-public r-r4rna
8358 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8362 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8363 (build-system r-build-system)
8365 `(("r-optparse" ,r-optparse)
8366 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8367 (home-page "https://www.e-rna.org/r-chie/index.cgi")
8368 (synopsis "Analysis framework for RNA secondary structure")
8370 "The R4RNA package aims to be a general framework for the analysis of RNA
8371 secondary structure and comparative analysis in R.")
8372 (license license:gpl3+)))
8374 (define-public r-rhtslib
8381 (uri (bioconductor-uri "Rhtslib" version))
8384 "0gkbrmrcg55c9s5166ifljlx0v25rv4ijdyp4wf4c292xd6chy2l"))))
8385 (properties `((upstream-name . "Rhtslib")))
8386 (build-system r-build-system)
8387 ;; Without this a temporary directory ends up in the Rhtslib.so binary,
8388 ;; which makes R abort the build.
8389 (arguments '(#:configure-flags '("--no-staged-install")))
8392 ("r-zlibbioc" ,r-zlibbioc)))
8396 `(("pkg-config" ,pkg-config)))
8397 (home-page "https://github.com/nhayden/Rhtslib")
8398 (synopsis "High-throughput sequencing library as an R package")
8400 "This package provides the HTSlib C library for high-throughput
8401 nucleotide sequence analysis. The package is primarily useful to developers
8402 of other R packages who wish to make use of HTSlib.")
8403 (license license:lgpl2.0+)))
8405 (define-public r-bamsignals
8407 (name "r-bamsignals")
8412 (uri (bioconductor-uri "bamsignals" version))
8415 "0699b0pqbs0dvs91yjibcjc90lxj9mg8rcml4a6wchfr9md7n74w"))))
8416 (build-system r-build-system)
8418 `(("r-biocgenerics" ,r-biocgenerics)
8419 ("r-genomicranges" ,r-genomicranges)
8420 ("r-iranges" ,r-iranges)
8422 ("r-rhtslib" ,r-rhtslib)
8423 ("r-zlibbioc" ,r-zlibbioc)))
8426 (home-page "https://bioconductor.org/packages/bamsignals")
8427 (synopsis "Extract read count signals from bam files")
8429 "This package allows to efficiently obtain count vectors from indexed bam
8430 files. It counts the number of nucleotide sequence reads in given genomic
8431 ranges and it computes reads profiles and coverage profiles. It also handles
8433 (license license:gpl2+)))
8435 (define-public r-rcas
8441 (uri (bioconductor-uri "RCAS" version))
8444 "1s3gvvxi1029d1vfwnjh21nnw3mlx08kcwz63891hml9y850cvsn"))))
8445 (properties `((upstream-name . "RCAS")))
8446 (build-system r-build-system)
8448 `(("r-annotationdbi" ,r-annotationdbi)
8449 ("r-biocgenerics" ,r-biocgenerics)
8450 ("r-biomart" ,r-biomart)
8451 ("r-biostrings" ,r-biostrings)
8452 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8453 ("r-cowplot" ,r-cowplot)
8454 ("r-data-table" ,r-data-table)
8457 ("r-genomation" ,r-genomation)
8458 ("r-genomeinfodb" ,r-genomeinfodb)
8459 ("r-genomicfeatures" ,r-genomicfeatures)
8460 ("r-genomicranges" ,r-genomicranges)
8461 ("r-ggplot2" ,r-ggplot2)
8462 ("r-ggseqlogo" ,r-ggseqlogo)
8463 ("r-knitr" ,r-knitr)
8464 ("r-motifrg" ,r-motifrg)
8465 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8466 ("r-pbapply" ,r-pbapply)
8467 ("r-pheatmap" ,r-pheatmap)
8468 ("r-plotly" ,r-plotly)
8469 ("r-plotrix" ,r-plotrix)
8470 ("r-proxy" ,r-proxy)
8471 ("r-rsqlite" ,r-rsqlite)
8472 ("r-rtracklayer" ,r-rtracklayer)
8473 ("r-rmarkdown" ,r-rmarkdown)
8474 ("r-s4vectors" ,r-s4vectors)
8475 ("r-topgo" ,r-topgo)
8476 ("pandoc" ,ghc-pandoc)))
8477 (synopsis "RNA-centric annotation system")
8479 "RCAS aims to be a standalone RNA-centric annotation system that provides
8480 intuitive reports and publication-ready graphics. This package provides the R
8481 library implementing most of the pipeline's features.")
8482 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8483 (license license:artistic2.0)))
8485 (define-public rcas-web
8492 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8493 "releases/download/v" version
8494 "/rcas-web-" version ".tar.gz"))
8497 "0wq951aj45gqki1bickg876i993lmawkp8x24agg264br5x716db"))))
8498 (build-system gnu-build-system)
8501 (modify-phases %standard-phases
8502 (add-before 'configure 'find-RCAS
8503 ;; The configure script can't find non-1.3.x versions of RCAS because
8504 ;; its R expression ‘1.10.1 >= 1.3.4’ evaluates to false.
8506 (substitute* "configure"
8507 (("1\\.3\\.4") "0.0.0"))
8509 (add-after 'install 'wrap-executable
8510 (lambda* (#:key inputs outputs #:allow-other-keys)
8511 (let* ((out (assoc-ref outputs "out"))
8512 (json (assoc-ref inputs "guile-json"))
8513 (redis (assoc-ref inputs "guile-redis"))
8514 (path (string-append
8515 json "/share/guile/site/2.2:"
8516 redis "/share/guile/site/2.2")))
8517 (wrap-program (string-append out "/bin/rcas-web")
8518 `("GUILE_LOAD_PATH" ":" = (,path))
8519 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8520 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8523 `(("r-minimal" ,r-minimal)
8525 ("guile-next" ,guile-2.2)
8526 ("guile-json" ,guile-json-1)
8527 ("guile-redis" ,guile-redis)))
8529 `(("pkg-config" ,pkg-config)))
8530 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8531 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8532 (description "This package provides a simple web interface for the
8533 @dfn{RNA-centric annotation system} (RCAS).")
8534 (license license:agpl3+)))
8536 (define-public r-mutationalpatterns
8538 (name "r-mutationalpatterns")
8543 (uri (bioconductor-uri "MutationalPatterns" version))
8546 "08715l6swrlccviw7932v5hyrd2x4c6049vy9qnxk0lw3sp1zvsf"))))
8547 (build-system r-build-system)
8549 `(("r-biocgenerics" ,r-biocgenerics)
8550 ("r-biostrings" ,r-biostrings)
8551 ;; These two packages are suggested packages
8552 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8553 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8554 ("r-genomicranges" ,r-genomicranges)
8555 ("r-genomeinfodb" ,r-genomeinfodb)
8556 ("r-ggplot2" ,r-ggplot2)
8557 ("r-iranges" ,r-iranges)
8560 ("r-pracma" ,r-pracma)
8561 ("r-reshape2" ,r-reshape2)
8562 ("r-cowplot" ,r-cowplot)
8563 ("r-ggdendro" ,r-ggdendro)
8564 ("r-s4vectors" ,r-s4vectors)
8565 ("r-summarizedexperiment" ,r-summarizedexperiment)
8566 ("r-variantannotation" ,r-variantannotation)))
8567 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8568 (synopsis "Extract and visualize mutational patterns in genomic data")
8569 (description "This package provides an extensive toolset for the
8570 characterization and visualization of a wide range of mutational patterns
8571 in SNV base substitution data.")
8572 (license license:expat)))
8574 (define-public r-chipkernels
8575 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8578 (name "r-chipkernels")
8579 (version (string-append "1.1-" revision "." (string-take commit 9)))
8584 (url "https://github.com/ManuSetty/ChIPKernels.git")
8586 (file-name (string-append name "-" version))
8589 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8590 (build-system r-build-system)
8592 `(("r-iranges" ,r-iranges)
8593 ("r-xvector" ,r-xvector)
8594 ("r-biostrings" ,r-biostrings)
8595 ("r-bsgenome" ,r-bsgenome)
8596 ("r-gtools" ,r-gtools)
8597 ("r-genomicranges" ,r-genomicranges)
8598 ("r-sfsmisc" ,r-sfsmisc)
8599 ("r-kernlab" ,r-kernlab)
8600 ("r-s4vectors" ,r-s4vectors)
8601 ("r-biocgenerics" ,r-biocgenerics)))
8602 (home-page "https://github.com/ManuSetty/ChIPKernels")
8603 (synopsis "Build string kernels for DNA Sequence analysis")
8604 (description "ChIPKernels is an R package for building different string
8605 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8606 must be built and this dictionary can be used for determining kernels for DNA
8608 (license license:gpl2+))))
8610 (define-public r-seqgl
8618 (url "https://github.com/ManuSetty/SeqGL.git")
8620 (file-name (git-file-name name version))
8623 "1r6ywvhxl3ffv48lgj7sbd582mcc6dha3ksgc2qjlvjrnkbj3799"))))
8624 (build-system r-build-system)
8626 `(("r-biostrings" ,r-biostrings)
8627 ("r-chipkernels" ,r-chipkernels)
8628 ("r-genomicranges" ,r-genomicranges)
8629 ("r-spams" ,r-spams)
8630 ("r-wgcna" ,r-wgcna)
8631 ("r-fastcluster" ,r-fastcluster)))
8632 (home-page "https://github.com/ManuSetty/SeqGL")
8633 (synopsis "Group lasso for Dnase/ChIP-seq data")
8634 (description "SeqGL is a group lasso based algorithm to extract
8635 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8636 This package presents a method which uses group lasso to discriminate between
8637 bound and non bound genomic regions to accurately identify transcription
8638 factors bound at the specific regions.")
8639 (license license:gpl2+)))
8641 (define-public r-tximport
8647 (uri (bioconductor-uri "tximport" version))
8650 "09r23n2812q89by0r0cz2fx1gfnmn3jb3hwbg61m52bika82pakj"))))
8651 (build-system r-build-system)
8652 (home-page "https://bioconductor.org/packages/tximport")
8653 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8655 "This package provides tools to import transcript-level abundance,
8656 estimated counts and transcript lengths, and to summarize them into matrices
8657 for use with downstream gene-level analysis packages. Average transcript
8658 length, weighted by sample-specific transcript abundance estimates, is
8659 provided as a matrix which can be used as an offset for different expression
8660 of gene-level counts.")
8661 (license license:gpl2+)))
8663 (define-public r-rhdf5
8669 (uri (bioconductor-uri "rhdf5" version))
8672 "18pv74jj4wr1981r92ss10qkgf5g1b09dsbz3im3j70a4l5l0df0"))))
8673 (build-system r-build-system)
8675 `(("r-rhdf5lib" ,r-rhdf5lib)))
8678 (home-page "https://bioconductor.org/packages/rhdf5")
8679 (synopsis "HDF5 interface to R")
8681 "This R/Bioconductor package provides an interface between HDF5 and R.
8682 HDF5's main features are the ability to store and access very large and/or
8683 complex datasets and a wide variety of metadata on mass storage (disk) through
8684 a completely portable file format. The rhdf5 package is thus suited for the
8685 exchange of large and/or complex datasets between R and other software
8686 package, and for letting R applications work on datasets that are larger than
8687 the available RAM.")
8688 (license license:artistic2.0)))
8690 (define-public r-annotationfilter
8692 (name "r-annotationfilter")
8696 (uri (bioconductor-uri "AnnotationFilter" version))
8699 "1l9sxhlvnwn6327vgg02h11ppmqr2zr07ff8wmcng0i1jbqwa8q5"))))
8701 `((upstream-name . "AnnotationFilter")))
8702 (build-system r-build-system)
8704 `(("r-genomicranges" ,r-genomicranges)
8705 ("r-lazyeval" ,r-lazyeval)))
8706 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8707 (synopsis "Facilities for filtering Bioconductor annotation resources")
8709 "This package provides classes and other infrastructure to implement
8710 filters for manipulating Bioconductor annotation resources. The filters are
8711 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8712 (license license:artistic2.0)))
8714 (define-public emboss
8720 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8721 (version-major+minor version) ".0/"
8722 "EMBOSS-" version ".tar.gz"))
8725 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8726 (build-system gnu-build-system)
8729 (list (string-append "--with-hpdf="
8730 (assoc-ref %build-inputs "libharu")))
8732 (modify-phases %standard-phases
8733 (add-after 'unpack 'fix-checks
8735 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8736 ;; and zlib, but assume that they are all found at the same
8738 (substitute* "configure.in"
8739 (("CHECK_PNGDRIVER")
8740 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8741 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8742 AM_CONDITIONAL(AMPNG, true)"))
8744 (add-after 'fix-checks 'disable-update-check
8746 ;; At build time there is no connection to the Internet, so
8747 ;; looking for updates will not work.
8748 (substitute* "Makefile.am"
8749 (("\\$\\(bindir\\)/embossupdate") ""))
8751 (add-after 'disable-update-check 'autogen
8752 (lambda _ (invoke "autoreconf" "-vif") #t)))))
8758 ("libharu" ,libharu)
8761 `(("autoconf" ,autoconf)
8762 ("automake" ,automake)
8763 ("libtool" ,libtool)
8764 ("pkg-config" ,pkg-config)))
8765 (home-page "http://emboss.sourceforge.net")
8766 (synopsis "Molecular biology analysis suite")
8767 (description "EMBOSS is the \"European Molecular Biology Open Software
8768 Suite\". EMBOSS is an analysis package specially developed for the needs of
8769 the molecular biology (e.g. EMBnet) user community. The software
8770 automatically copes with data in a variety of formats and even allows
8771 transparent retrieval of sequence data from the web. It also provides a
8772 number of libraries for the development of software in the field of molecular
8773 biology. EMBOSS also integrates a range of currently available packages and
8774 tools for sequence analysis into a seamless whole.")
8775 (license license:gpl2+)))
8778 (let ((revision "1")
8779 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8782 ;; The version is 2.13.0 even though no release archives have been
8783 ;; published as yet.
8784 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8788 (url "https://github.com/arq5x/bits.git")
8790 (file-name (string-append name "-" version "-checkout"))
8793 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8794 (build-system gnu-build-system)
8796 `(#:tests? #f ;no tests included
8798 (modify-phases %standard-phases
8800 (add-after 'unpack 'remove-cuda
8802 (substitute* "Makefile"
8804 (("(bits_test_intersections) \\\\" _ match) match))
8807 (lambda* (#:key outputs #:allow-other-keys)
8809 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8814 (home-page "https://github.com/arq5x/bits")
8815 (synopsis "Implementation of binary interval search algorithm")
8816 (description "This package provides an implementation of the
8817 BITS (Binary Interval Search) algorithm, an approach to interval set
8818 intersection. It is especially suited for the comparison of diverse genomic
8819 datasets and the exploration of large datasets of genome
8820 intervals (e.g. genes, sequence alignments).")
8821 (license license:gpl2))))
8823 (define-public piranha
8824 ;; There is no release tarball for the latest version. The latest commit is
8825 ;; older than one year at the time of this writing.
8826 (let ((revision "1")
8827 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8830 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8834 (url "https://github.com/smithlabcode/piranha.git")
8836 (file-name (git-file-name name version))
8839 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
8840 (build-system gnu-build-system)
8842 `(#:test-target "test"
8844 (modify-phases %standard-phases
8845 (add-after 'unpack 'copy-smithlab-cpp
8846 (lambda* (#:key inputs #:allow-other-keys)
8847 (for-each (lambda (file)
8848 (install-file file "./src/smithlab_cpp/"))
8849 (find-files (assoc-ref inputs "smithlab-cpp")))
8851 (add-after 'install 'install-to-store
8852 (lambda* (#:key outputs #:allow-other-keys)
8853 (let* ((out (assoc-ref outputs "out"))
8854 (bin (string-append out "/bin")))
8855 (for-each (lambda (file)
8856 (install-file file bin))
8857 (find-files "bin" ".*")))
8860 (list (string-append "--with-bam_tools_headers="
8861 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
8862 (string-append "--with-bam_tools_library="
8863 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
8865 `(("bamtools" ,bamtools)
8866 ("samtools" ,samtools-0.1)
8869 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8873 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8875 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8878 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8880 `(("python" ,python-2)))
8881 (home-page "https://github.com/smithlabcode/piranha")
8882 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
8884 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
8885 RIP-seq experiments. It takes input in BED or BAM format and identifies
8886 regions of statistically significant read enrichment. Additional covariates
8887 may optionally be provided to further inform the peak-calling process.")
8888 (license license:gpl3+))))
8896 (uri (pypi-uri "PePr" version))
8899 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
8900 (build-system python-build-system)
8902 `(#:python ,python-2 ; python2 only
8903 #:tests? #f)) ; no tests included
8905 `(("python2-numpy" ,python2-numpy)
8906 ("python2-scipy" ,python2-scipy)
8907 ("python2-pysam" ,python2-pysam)))
8908 (home-page "https://github.com/shawnzhangyx/PePr")
8909 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
8911 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
8912 that is primarily designed for data with biological replicates. It uses a
8913 negative binomial distribution to model the read counts among the samples in
8914 the same group, and look for consistent differences between ChIP and control
8915 group or two ChIP groups run under different conditions.")
8916 (license license:gpl3+)))
8918 (define-public filevercmp
8919 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
8922 (version (string-append "0-1." (string-take commit 7)))
8926 (url "https://github.com/ekg/filevercmp.git")
8928 (file-name (git-file-name name commit))
8931 "1j9vxsy0y050v59h0q1d6501fcw1kjvj0d18l1xk2zyg0jzj247c"))))
8932 (build-system gnu-build-system)
8934 `(#:tests? #f ; There are no tests to run.
8936 (modify-phases %standard-phases
8937 (delete 'configure) ; There is no configure phase.
8939 (lambda* (#:key outputs #:allow-other-keys)
8940 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
8941 (install-file "filevercmp" bin)
8943 (home-page "https://github.com/ekg/filevercmp")
8944 (synopsis "This program compares version strings")
8945 (description "This program compares version strings. It intends to be a
8946 replacement for strverscmp.")
8947 (license license:gpl3+))))
8949 (define-public multiqc
8956 (uri (pypi-uri "multiqc" version))
8959 "02iihfl0w0hpnr4pa0sbd1y9qxrg3ycyhjp5lidkcrqh1lmzs3zy"))))
8960 (build-system python-build-system)
8962 `(("python-jinja2" ,python-jinja2)
8963 ("python-simplejson" ,python-simplejson)
8964 ("python-pyyaml" ,python-pyyaml)
8965 ("python-click" ,python-click)
8966 ("python-spectra" ,python-spectra)
8967 ("python-requests" ,python-requests)
8968 ("python-markdown" ,python-markdown)
8969 ("python-lzstring" ,python-lzstring)
8970 ("python-matplotlib" ,python-matplotlib)
8971 ("python-numpy" ,python-numpy)
8972 ;; MultQC checks for the presence of nose at runtime.
8973 ("python-nose" ,python-nose)))
8976 (modify-phases %standard-phases
8977 (add-after 'unpack 'relax-requirements
8979 (substitute* "setup.py"
8980 ;; MultiQC 1.5 ‘requires’ a version of python-matplotlib older
8981 ;; than the one in Guix, but should work fine with 2.2.2.
8982 ;; See <https://github.com/ewels/MultiQC/issues/725> and
8983 ;; <https://github.com/ewels/MultiQC/issues/732> for details.
8984 (("['\"]matplotlib.*?['\"]")
8987 (home-page "https://multiqc.info")
8988 (synopsis "Aggregate bioinformatics analysis reports")
8990 "MultiQC is a tool to aggregate bioinformatics results across many
8991 samples into a single report. It contains modules for a large number of
8992 common bioinformatics tools.")
8993 (license license:gpl3+)))
8995 (define-public r-chipseq
9002 (uri (bioconductor-uri "chipseq" version))
9005 "1ln6bn08xig3j6ryak1xfkjhvpnlm2vf1czz9hlj6f02299nbs6l"))))
9006 (build-system r-build-system)
9008 `(("r-biocgenerics" ,r-biocgenerics)
9009 ("r-genomicranges" ,r-genomicranges)
9010 ("r-iranges" ,r-iranges)
9011 ("r-lattice" ,r-lattice)
9012 ("r-s4vectors" ,r-s4vectors)
9013 ("r-shortread" ,r-shortread)))
9014 (home-page "https://bioconductor.org/packages/chipseq")
9015 (synopsis "Package for analyzing ChIPseq data")
9017 "This package provides tools for processing short read data from ChIPseq
9019 (license license:artistic2.0)))
9021 (define-public r-copyhelper
9023 (name "r-copyhelper")
9028 (uri (string-append "https://bioconductor.org/packages/release/"
9029 "data/experiment/src/contrib/CopyhelpeR_"
9033 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
9034 (properties `((upstream-name . "CopyhelpeR")))
9035 (build-system r-build-system)
9036 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
9037 (synopsis "Helper files for CopywriteR")
9039 "This package contains the helper files that are required to run the
9040 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
9041 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
9042 mm10. In addition, it contains a blacklist filter to remove regions that
9043 display copy number variation. Files are stored as GRanges objects from the
9044 GenomicRanges Bioconductor package.")
9045 (license license:gpl2)))
9047 (define-public r-copywriter
9049 (name "r-copywriter")
9054 (uri (bioconductor-uri "CopywriteR" version))
9057 "0llg1zpxg7qnvja5f5w1z1xic0jdg6zc4mfn97h2sm44skxxcyl1"))))
9058 (properties `((upstream-name . "CopywriteR")))
9059 (build-system r-build-system)
9061 `(("r-biocparallel" ,r-biocparallel)
9062 ("r-chipseq" ,r-chipseq)
9063 ("r-copyhelper" ,r-copyhelper)
9064 ("r-data-table" ,r-data-table)
9065 ("r-dnacopy" ,r-dnacopy)
9066 ("r-futile-logger" ,r-futile-logger)
9067 ("r-genomeinfodb" ,r-genomeinfodb)
9068 ("r-genomicalignments" ,r-genomicalignments)
9069 ("r-genomicranges" ,r-genomicranges)
9070 ("r-gtools" ,r-gtools)
9071 ("r-iranges" ,r-iranges)
9072 ("r-matrixstats" ,r-matrixstats)
9073 ("r-rsamtools" ,r-rsamtools)
9074 ("r-s4vectors" ,r-s4vectors)))
9075 (home-page "https://github.com/PeeperLab/CopywriteR")
9076 (synopsis "Copy number information from targeted sequencing")
9078 "CopywriteR extracts DNA copy number information from targeted sequencing
9079 by utilizing off-target reads. It allows for extracting uniformly distributed
9080 copy number information, can be used without reference, and can be applied to
9081 sequencing data obtained from various techniques including chromatin
9082 immunoprecipitation and target enrichment on small gene panels. Thereby,
9083 CopywriteR constitutes a widely applicable alternative to available copy
9084 number detection tools.")
9085 (license license:gpl2)))
9087 (define-public r-methylkit
9089 (name "r-methylkit")
9093 (uri (bioconductor-uri "methylKit" version))
9096 "0klwc0sbmrxj1lxbz16pl39rxjm0pi57gjw547hlgnac1p9fspzy"))))
9097 (properties `((upstream-name . "methylKit")))
9098 (build-system r-build-system)
9100 `(("r-data-table" ,r-data-table)
9101 ("r-emdbook" ,r-emdbook)
9102 ("r-fastseg" ,r-fastseg)
9103 ("r-genomeinfodb" ,r-genomeinfodb)
9104 ("r-genomicranges" ,r-genomicranges)
9105 ("r-gtools" ,r-gtools)
9106 ("r-iranges" ,r-iranges)
9107 ("r-kernsmooth" ,r-kernsmooth)
9108 ("r-limma" ,r-limma)
9109 ("r-mclust" ,r-mclust)
9111 ("r-qvalue" ,r-qvalue)
9112 ("r-r-utils" ,r-r-utils)
9114 ("r-rhtslib" ,r-rhtslib)
9115 ("r-rsamtools" ,r-rsamtools)
9116 ("r-rtracklayer" ,r-rtracklayer)
9117 ("r-s4vectors" ,r-s4vectors)
9118 ("r-zlibbioc" ,r-zlibbioc)))
9120 `(("r-knitr" ,r-knitr))) ; for vignettes
9123 (home-page "https://github.com/al2na/methylKit")
9125 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9127 "MethylKit is an R package for DNA methylation analysis and annotation
9128 from high-throughput bisulfite sequencing. The package is designed to deal
9129 with sequencing data from @dfn{Reduced representation bisulfite
9130 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9131 genome bisulfite sequencing. It also has functions to analyze base-pair
9132 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9134 (license license:artistic2.0)))
9136 (define-public r-sva
9143 (uri (bioconductor-uri "sva" version))
9146 "1bzms6idx30s4nxl610zwa8rjxsyxb5pf3vxsdfmxg8j4pab9gh1"))))
9147 (build-system r-build-system)
9149 `(("r-genefilter" ,r-genefilter)
9151 ("r-biocparallel" ,r-biocparallel)
9152 ("r-matrixstats" ,r-matrixstats)
9153 ("r-limma" ,r-limma)))
9154 (home-page "https://bioconductor.org/packages/sva")
9155 (synopsis "Surrogate variable analysis")
9157 "This package contains functions for removing batch effects and other
9158 unwanted variation in high-throughput experiment. It also contains functions
9159 for identifying and building surrogate variables for high-dimensional data
9160 sets. Surrogate variables are covariates constructed directly from
9161 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9162 imaging data that can be used in subsequent analyses to adjust for unknown,
9163 unmodeled, or latent sources of noise.")
9164 (license license:artistic2.0)))
9166 (define-public r-seqminer
9173 (uri (cran-uri "seqminer" version))
9176 "00jzj8mwb0zaiwlifd41b26mrq9mzigj18nc29dydi0r42hxg16i"))))
9177 (build-system r-build-system)
9180 (home-page "http://seqminer.genomic.codes")
9181 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9183 "This package provides tools to integrate nucleotide sequencing
9184 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9185 ;; Any version of the GPL is acceptable
9186 (license (list license:gpl2+ license:gpl3+))))
9188 (define-public r-raremetals2
9190 (name "r-raremetals2")
9195 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9196 "b/b7/RareMETALS2_" version ".tar.gz"))
9199 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9200 (properties `((upstream-name . "RareMETALS2")))
9201 (build-system r-build-system)
9203 `(("r-seqminer" ,r-seqminer)
9204 ("r-mvtnorm" ,r-mvtnorm)
9206 ("r-compquadform" ,r-compquadform)
9207 ("r-getopt" ,r-getopt)))
9208 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9209 (synopsis "Analyze gene-level association tests for binary trait")
9211 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9212 It was designed to meta-analyze gene-level association tests for binary trait.
9213 While rareMETALS offers a near-complete solution for meta-analysis of
9214 gene-level tests for quantitative trait, it does not offer the optimal
9215 solution for binary trait. The package rareMETALS2 offers improved features
9216 for analyzing gene-level association tests in meta-analyses for binary
9218 (license license:gpl3)))
9220 (define-public r-maldiquant
9222 (name "r-maldiquant")
9227 (uri (cran-uri "MALDIquant" version))
9230 "0b7kdz3x4sdq413h1q09l1qhcvdnnwv6fqsqwllks1cd3xy34c57"))))
9231 (properties `((upstream-name . "MALDIquant")))
9232 (build-system r-build-system)
9233 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9234 (synopsis "Quantitative analysis of mass spectrometry data")
9236 "This package provides a complete analysis pipeline for matrix-assisted
9237 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9238 two-dimensional mass spectrometry data. In addition to commonly used plotting
9239 and processing methods it includes distinctive features, namely baseline
9240 subtraction methods such as morphological filters (TopHat) or the
9241 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9242 alignment using warping functions, handling of replicated measurements as well
9243 as allowing spectra with different resolutions.")
9244 (license license:gpl3+)))
9246 (define-public r-protgenerics
9248 (name "r-protgenerics")
9253 (uri (bioconductor-uri "ProtGenerics" version))
9256 "1k1ggjgx2la8b21841a4ngkp6xfxwz0czv7x960r7i1jqif8y48z"))))
9257 (properties `((upstream-name . "ProtGenerics")))
9258 (build-system r-build-system)
9259 (home-page "https://github.com/lgatto/ProtGenerics")
9260 (synopsis "S4 generic functions for proteomics infrastructure")
9262 "This package provides S4 generic functions needed by Bioconductor
9263 proteomics packages.")
9264 (license license:artistic2.0)))
9266 (define-public r-mzr
9273 (uri (bioconductor-uri "mzR" version))
9276 "1cwd7phlc5jbx6r6cznyfbdpvcin5fvsaasbbi65zn0s92a80r13"))
9277 (modules '((guix build utils)))
9280 (delete-file-recursively "src/boost")
9282 (properties `((upstream-name . "mzR")))
9283 (build-system r-build-system)
9286 (modify-phases %standard-phases
9287 (add-after 'unpack 'use-system-boost
9289 (substitute* "src/Makevars"
9290 (("\\./boost/libs.*") "")
9291 (("ARCH_OBJS=" line)
9293 "\nARCH_LIBS=-lboost_system -lboost_regex \
9294 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9297 `(;; Our default boost package won't work here, unfortunately, even with
9298 ;; mzR version 2.20.0.
9299 ("boost" ,boost-for-mysql) ; use this instead of the bundled boost sources
9302 `(("r-biobase" ,r-biobase)
9303 ("r-biocgenerics" ,r-biocgenerics)
9304 ("r-ncdf4" ,r-ncdf4)
9305 ("r-protgenerics" ,r-protgenerics)
9307 ("r-rhdf5lib" ,r-rhdf5lib)
9308 ("r-zlibbioc" ,r-zlibbioc)))
9309 (home-page "https://github.com/sneumann/mzR/")
9310 (synopsis "Parser for mass spectrometry data files")
9312 "The mzR package provides a unified API to the common file formats and
9313 parsers available for mass spectrometry data. It comes with a wrapper for the
9314 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9315 The package contains the original code written by the ISB, and a subset of the
9316 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9317 previously been used in XCMS.")
9318 (license license:artistic2.0)))
9320 (define-public r-affyio
9327 (uri (bioconductor-uri "affyio" version))
9330 "0sbkadxdlx7qzxc8z8iv90y6j9b2f62mk3i54dijjh56x3hjy3hb"))))
9331 (build-system r-build-system)
9333 `(("r-zlibbioc" ,r-zlibbioc)))
9336 (home-page "https://github.com/bmbolstad/affyio")
9337 (synopsis "Tools for parsing Affymetrix data files")
9339 "This package provides routines for parsing Affymetrix data files based
9340 upon file format information. The primary focus is on accessing the CEL and
9342 (license license:lgpl2.0+)))
9344 (define-public r-affy
9351 (uri (bioconductor-uri "affy" version))
9354 "131za66wbaz9y86gvjqcc2yd1f2ngl2b796xw726g75djhdgxgap"))))
9355 (build-system r-build-system)
9357 `(("r-affyio" ,r-affyio)
9358 ("r-biobase" ,r-biobase)
9359 ("r-biocgenerics" ,r-biocgenerics)
9360 ("r-biocmanager" ,r-biocmanager)
9361 ("r-preprocesscore" ,r-preprocesscore)
9362 ("r-zlibbioc" ,r-zlibbioc)))
9365 (home-page "https://bioconductor.org/packages/affy")
9366 (synopsis "Methods for affymetrix oligonucleotide arrays")
9368 "This package contains functions for exploratory oligonucleotide array
9370 (license license:lgpl2.0+)))
9372 (define-public r-vsn
9379 (uri (bioconductor-uri "vsn" version))
9382 "1naqzb2m0km8fzr6chf9z71sisrwviy1fdi9b3hn4i8p18b4kqzh"))))
9383 (build-system r-build-system)
9385 `(("r-affy" ,r-affy)
9386 ("r-biobase" ,r-biobase)
9387 ("r-ggplot2" ,r-ggplot2)
9388 ("r-lattice" ,r-lattice)
9389 ("r-limma" ,r-limma)))
9391 `(("r-knitr" ,r-knitr))) ; for vignettes
9392 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9393 (synopsis "Variance stabilization and calibration for microarray data")
9395 "The package implements a method for normalising microarray intensities,
9396 and works for single- and multiple-color arrays. It can also be used for data
9397 from other technologies, as long as they have similar format. The method uses
9398 a robust variant of the maximum-likelihood estimator for an
9399 additive-multiplicative error model and affine calibration. The model
9400 incorporates data calibration step (a.k.a. normalization), a model for the
9401 dependence of the variance on the mean intensity and a variance stabilizing
9402 data transformation. Differences between transformed intensities are
9403 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9404 their variance is independent of the mean, and they are usually more sensitive
9405 and specific in detecting differential transcription.")
9406 (license license:artistic2.0)))
9408 (define-public r-mzid
9415 (uri (bioconductor-uri "mzID" version))
9418 "1glcv096bn6pxlw89dlij1nzpwnjvrbxysvw2gm6qgm7rhxlaxrw"))))
9419 (properties `((upstream-name . "mzID")))
9420 (build-system r-build-system)
9422 `(("r-doparallel" ,r-doparallel)
9423 ("r-foreach" ,r-foreach)
9424 ("r-iterators" ,r-iterators)
9426 ("r-protgenerics" ,r-protgenerics)
9429 (home-page "https://bioconductor.org/packages/mzID")
9430 (synopsis "Parser for mzIdentML files")
9432 "This package provides a parser for mzIdentML files implemented using the
9433 XML package. The parser tries to be general and able to handle all types of
9434 mzIdentML files with the drawback of having less pretty output than a vendor
9436 (license license:gpl2+)))
9438 (define-public r-pcamethods
9440 (name "r-pcamethods")
9445 (uri (bioconductor-uri "pcaMethods" version))
9448 "1wir67kfjm0m9gf0ki8qmvh45n4gx2k0wfl9pd1hp4g62fbrj1pj"))))
9449 (properties `((upstream-name . "pcaMethods")))
9450 (build-system r-build-system)
9452 `(("r-biobase" ,r-biobase)
9453 ("r-biocgenerics" ,r-biocgenerics)
9455 ("r-rcpp" ,r-rcpp)))
9456 (home-page "https://github.com/hredestig/pcamethods")
9457 (synopsis "Collection of PCA methods")
9459 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9460 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9461 for missing value estimation is included for comparison. BPCA, PPCA and
9462 NipalsPCA may be used to perform PCA on incomplete data as well as for
9463 accurate missing value estimation. A set of methods for printing and plotting
9464 the results is also provided. All PCA methods make use of the same data
9465 structure (pcaRes) to provide a common interface to the PCA results.")
9466 (license license:gpl3+)))
9468 (define-public r-msnbase
9475 (uri (bioconductor-uri "MSnbase" version))
9478 "1z889xkfphqqmv31i8hh5xqyclv660ic26rfck5bjpgk3s2zzwi6"))))
9479 (properties `((upstream-name . "MSnbase")))
9480 (build-system r-build-system)
9482 `(("r-affy" ,r-affy)
9483 ("r-biobase" ,r-biobase)
9484 ("r-biocgenerics" ,r-biocgenerics)
9485 ("r-biocparallel" ,r-biocparallel)
9486 ("r-digest" ,r-digest)
9487 ("r-ggplot2" ,r-ggplot2)
9488 ("r-impute" ,r-impute)
9489 ("r-iranges" ,r-iranges)
9490 ("r-lattice" ,r-lattice)
9491 ("r-maldiquant" ,r-maldiquant)
9495 ("r-pcamethods" ,r-pcamethods)
9497 ("r-preprocesscore" ,r-preprocesscore)
9498 ("r-protgenerics" ,r-protgenerics)
9500 ("r-s4vectors" ,r-s4vectors)
9501 ("r-scales" ,r-scales)
9504 (home-page "https://github.com/lgatto/MSnbase")
9505 (synopsis "Base functions and classes for MS-based proteomics")
9507 "This package provides basic plotting, data manipulation and processing
9508 of mass spectrometry based proteomics data.")
9509 (license license:artistic2.0)))
9511 (define-public r-msnid
9518 (uri (bioconductor-uri "MSnID" version))
9521 "0m71f2y12hmwvng45kzz4r4qrgc2jbd7j9gprmw8y5laawpdaifg"))))
9522 (properties `((upstream-name . "MSnID")))
9523 (build-system r-build-system)
9525 `(("r-biobase" ,r-biobase)
9526 ("r-data-table" ,r-data-table)
9527 ("r-doparallel" ,r-doparallel)
9528 ("r-dplyr" ,r-dplyr)
9529 ("r-foreach" ,r-foreach)
9530 ("r-iterators" ,r-iterators)
9531 ("r-msnbase" ,r-msnbase)
9534 ("r-protgenerics" ,r-protgenerics)
9535 ("r-r-cache" ,r-r-cache)
9537 ("r-reshape2" ,r-reshape2)))
9538 (home-page "https://bioconductor.org/packages/MSnID")
9539 (synopsis "Utilities for LC-MSn proteomics identifications")
9541 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9542 from mzIdentML (leveraging the mzID package) or text files. After collating
9543 the search results from multiple datasets it assesses their identification
9544 quality and optimize filtering criteria to achieve the maximum number of
9545 identifications while not exceeding a specified false discovery rate. It also
9546 contains a number of utilities to explore the MS/MS results and assess missed
9547 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9548 (license license:artistic2.0)))
9550 (define-public r-seurat
9556 (uri (cran-uri "Seurat" version))
9559 "0lhjbjhv1hnx5i3gkx41k68i8ykay3f24708h30wx9xywww9lsvi"))))
9560 (properties `((upstream-name . "Seurat")))
9561 (build-system r-build-system)
9564 ("r-cluster" ,r-cluster)
9565 ("r-cowplot" ,r-cowplot)
9566 ("r-fitdistrplus" ,r-fitdistrplus)
9567 ("r-future" ,r-future)
9568 ("r-future-apply" ,r-future-apply)
9569 ("r-ggplot2" ,r-ggplot2)
9570 ("r-ggrepel" ,r-ggrepel)
9571 ("r-ggridges" ,r-ggridges)
9574 ("r-igraph" ,r-igraph)
9575 ("r-irlba" ,r-irlba)
9576 ("r-kernsmooth" ,r-kernsmooth)
9577 ("r-leiden" ,r-leiden)
9578 ("r-lmtest" ,r-lmtest)
9580 ("r-matrix" ,r-matrix)
9581 ("r-metap" ,r-metap)
9582 ("r-patchwork" ,r-patchwork)
9583 ("r-pbapply" ,r-pbapply)
9584 ("r-plotly" ,r-plotly)
9587 ("r-rcolorbrewer" ,r-rcolorbrewer)
9589 ("r-rcppannoy" ,r-rcppannoy)
9590 ("r-rcppeigen" ,r-rcppeigen)
9591 ("r-rcppprogress" ,r-rcppprogress)
9592 ("r-reticulate" ,r-reticulate)
9593 ("r-rlang" ,r-rlang)
9596 ("r-rtsne" ,r-rtsne)
9597 ("r-scales" ,r-scales)
9598 ("r-sctransform" ,r-sctransform)
9600 ("r-uwot" ,r-uwot)))
9601 (home-page "http://www.satijalab.org/seurat")
9602 (synopsis "Seurat is an R toolkit for single cell genomics")
9604 "This package is an R package designed for QC, analysis, and
9605 exploration of single cell RNA-seq data. It easily enables widely-used
9606 analytical techniques, including the identification of highly variable genes,
9607 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9608 algorithms; density clustering, hierarchical clustering, k-means, and the
9609 discovery of differentially expressed genes and markers.")
9610 (license license:gpl3)))
9612 (define-public r-aroma-light
9614 (name "r-aroma-light")
9619 (uri (bioconductor-uri "aroma.light" version))
9622 "0cgdg650j4dl0b45pwaw49ib97dwjazrv9sqzkygrjmcnnfxry8x"))))
9623 (properties `((upstream-name . "aroma.light")))
9624 (build-system r-build-system)
9626 `(("r-matrixstats" ,r-matrixstats)
9627 ("r-r-methodss3" ,r-r-methodss3)
9629 ("r-r-utils" ,r-r-utils)))
9630 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9631 (synopsis "Methods for normalization and visualization of microarray data")
9633 "This package provides methods for microarray analysis that take basic
9634 data types such as matrices and lists of vectors. These methods can be used
9635 standalone, be utilized in other packages, or be wrapped up in higher-level
9637 (license license:gpl2+)))
9639 (define-public r-deseq
9646 (uri (bioconductor-uri "DESeq" version))
9649 "14pys93gsl50xmq5pc7pp1g20v3ywlg0yzkkhwb3kiy8573xn9nc"))))
9650 (properties `((upstream-name . "DESeq")))
9651 (build-system r-build-system)
9653 `(("r-biobase" ,r-biobase)
9654 ("r-biocgenerics" ,r-biocgenerics)
9655 ("r-genefilter" ,r-genefilter)
9656 ("r-geneplotter" ,r-geneplotter)
9657 ("r-lattice" ,r-lattice)
9658 ("r-locfit" ,r-locfit)
9660 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9661 (home-page "https://www-huber.embl.de/users/anders/DESeq/")
9662 (synopsis "Differential gene expression analysis")
9664 "This package provides tools for estimating variance-mean dependence in
9665 count data from high-throughput genetic sequencing assays and for testing for
9666 differential expression based on a model using the negative binomial
9668 (license license:gpl3+)))
9670 (define-public r-edaseq
9677 (uri (bioconductor-uri "EDASeq" version))
9680 "19mgzbv8yxgvw86wpq401l27q55ygawlngl775yavwccz1zbhjnj"))))
9681 (properties `((upstream-name . "EDASeq")))
9682 (build-system r-build-system)
9684 `(("r-annotationdbi" ,r-annotationdbi)
9685 ("r-aroma-light" ,r-aroma-light)
9686 ("r-biobase" ,r-biobase)
9687 ("r-biocgenerics" ,r-biocgenerics)
9688 ("r-biocmanager" ,r-biocmanager)
9689 ("r-biomart" ,r-biomart)
9690 ("r-biostrings" ,r-biostrings)
9691 ("r-deseq" ,r-deseq)
9692 ("r-genomicfeatures" ,r-genomicfeatures)
9693 ("r-genomicranges" ,r-genomicranges)
9694 ("r-iranges" ,r-iranges)
9695 ("r-rsamtools" ,r-rsamtools)
9696 ("r-shortread" ,r-shortread)))
9697 (home-page "https://github.com/drisso/EDASeq")
9698 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9700 "This package provides support for numerical and graphical summaries of
9701 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9702 adjust for GC-content effect (or other gene-level effects) on read counts:
9703 loess robust local regression, global-scaling, and full-quantile
9704 normalization. Between-lane normalization procedures to adjust for
9705 distributional differences between lanes (e.g., sequencing depth):
9706 global-scaling and full-quantile normalization.")
9707 (license license:artistic2.0)))
9709 (define-public r-interactivedisplaybase
9711 (name "r-interactivedisplaybase")
9716 (uri (bioconductor-uri "interactiveDisplayBase" version))
9719 "0zwf3ma6wf4zypl6bgjp0n72k2hmp0g16gzl4v3y4157rxcbpl0n"))))
9721 `((upstream-name . "interactiveDisplayBase")))
9722 (build-system r-build-system)
9724 `(("r-biocgenerics" ,r-biocgenerics)
9725 ("r-shiny" ,r-shiny)))
9726 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9727 (synopsis "Base package for web displays of Bioconductor objects")
9729 "This package contains the basic methods needed to generate interactive
9730 Shiny-based display methods for Bioconductor objects.")
9731 (license license:artistic2.0)))
9733 (define-public r-annotationhub
9735 (name "r-annotationhub")
9740 (uri (bioconductor-uri "AnnotationHub" version))
9743 "19vj3bk8jz68q84g3j8xs1s9bqz90lbwbciig1h45zvn2zc6087m"))))
9744 (properties `((upstream-name . "AnnotationHub")))
9745 (build-system r-build-system)
9747 `(("r-annotationdbi" ,r-annotationdbi)
9748 ("r-biocfilecache" ,r-biocfilecache)
9749 ("r-biocgenerics" ,r-biocgenerics)
9750 ("r-biocmanager" ,r-biocmanager)
9751 ("r-biocversion" ,r-biocversion)
9753 ("r-dplyr" ,r-dplyr)
9755 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9756 ("r-rappdirs" ,r-rappdirs)
9757 ("r-rsqlite" ,r-rsqlite)
9758 ("r-s4vectors" ,r-s4vectors)
9759 ("r-yaml" ,r-yaml)))
9760 (home-page "https://bioconductor.org/packages/AnnotationHub")
9761 (synopsis "Client to access AnnotationHub resources")
9763 "This package provides a client for the Bioconductor AnnotationHub web
9764 resource. The AnnotationHub web resource provides a central location where
9765 genomic files (e.g. VCF, bed, wig) and other resources from standard
9766 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9767 metadata about each resource, e.g., a textual description, tags, and date of
9768 modification. The client creates and manages a local cache of files retrieved
9769 by the user, helping with quick and reproducible access.")
9770 (license license:artistic2.0)))
9772 (define-public r-fastseg
9779 (uri (bioconductor-uri "fastseg" version))
9782 "1cys6frmbizc8bf933mwvvnr31sfya9ahcc0wm66pbd1x3mygkmk"))))
9783 (build-system r-build-system)
9785 `(("r-biobase" ,r-biobase)
9786 ("r-biocgenerics" ,r-biocgenerics)
9787 ("r-genomicranges" ,r-genomicranges)
9788 ("r-iranges" ,r-iranges)
9789 ("r-s4vectors" ,r-s4vectors)))
9790 (home-page "https://www.bioinf.jku.at/software/fastseg/index.html")
9791 (synopsis "Fast segmentation algorithm for genetic sequencing data")
9793 "Fastseg implements a very fast and efficient segmentation algorithm.
9794 It can segment data from DNA microarrays and data from next generation
9795 sequencing for example to detect copy number segments. Further it can segment
9796 data from RNA microarrays like tiling arrays to identify transcripts. Most
9797 generally, it can segment data given as a matrix or as a vector. Various data
9798 formats can be used as input to fastseg like expression set objects for
9799 microarrays or GRanges for sequencing data.")
9800 (license license:lgpl2.0+)))
9802 (define-public r-keggrest
9809 (uri (bioconductor-uri "KEGGREST" version))
9812 "1cgjvv9n88y3ah21356mh8z2l08vjn42hjy8hcljsibknzc4v247"))))
9813 (properties `((upstream-name . "KEGGREST")))
9814 (build-system r-build-system)
9816 `(("r-biostrings" ,r-biostrings)
9819 (home-page "https://bioconductor.org/packages/KEGGREST")
9820 (synopsis "Client-side REST access to KEGG")
9822 "This package provides a package that provides a client interface to the
9823 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
9824 (license license:artistic2.0)))
9826 (define-public r-gage
9833 (uri (bioconductor-uri "gage" version))
9836 "1qxfmg0id19iy3ia8h5nrvk3d1azqb28kl7m08i23654wb6b45c6"))))
9837 (build-system r-build-system)
9839 `(("r-annotationdbi" ,r-annotationdbi)
9840 ("r-graph" ,r-graph)
9841 ("r-keggrest" ,r-keggrest)))
9842 (home-page (string-append "https://bmcbioinformatics.biomedcentral.com/"
9843 "articles/10.1186/1471-2105-10-161"))
9844 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
9846 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
9847 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
9848 data attributes including sample sizes, experimental designs, assay platforms,
9849 and other types of heterogeneity. The gage package provides functions for
9850 basic GAGE analysis, result processing and presentation. In addition, it
9851 provides demo microarray data and commonly used gene set data based on KEGG
9852 pathways and GO terms. These functions and data are also useful for gene set
9853 analysis using other methods.")
9854 (license license:gpl2+)))
9856 (define-public r-genomicfiles
9858 (name "r-genomicfiles")
9863 (uri (bioconductor-uri "GenomicFiles" version))
9866 "1x6q827ms2l5lwzha1vsgfrshh35n9f19jq57xagrqlafxgpz86s"))))
9867 (properties `((upstream-name . "GenomicFiles")))
9868 (build-system r-build-system)
9870 `(("r-biocgenerics" ,r-biocgenerics)
9871 ("r-biocparallel" ,r-biocparallel)
9872 ("r-genomeinfodb" ,r-genomeinfodb)
9873 ("r-genomicalignments" ,r-genomicalignments)
9874 ("r-genomicranges" ,r-genomicranges)
9875 ("r-iranges" ,r-iranges)
9876 ("r-rsamtools" ,r-rsamtools)
9877 ("r-rtracklayer" ,r-rtracklayer)
9878 ("r-s4vectors" ,r-s4vectors)
9879 ("r-summarizedexperiment" ,r-summarizedexperiment)
9880 ("r-variantannotation" ,r-variantannotation)))
9881 (home-page "https://bioconductor.org/packages/GenomicFiles")
9882 (synopsis "Distributed computing by file or by range")
9884 "This package provides infrastructure for parallel computations
9885 distributed by file or by range. User defined mapper and reducer functions
9886 provide added flexibility for data combination and manipulation.")
9887 (license license:artistic2.0)))
9889 (define-public r-complexheatmap
9891 (name "r-complexheatmap")
9896 (uri (bioconductor-uri "ComplexHeatmap" version))
9899 "1pj6a6rmqckk033pkklk6hr4066rzavamy6w194rfdhind90rk0p"))))
9901 `((upstream-name . "ComplexHeatmap")))
9902 (build-system r-build-system)
9904 `(("r-circlize" ,r-circlize)
9906 ("r-colorspace" ,r-colorspace)
9907 ("r-getoptlong" ,r-getoptlong)
9908 ("r-globaloptions" ,r-globaloptions)
9910 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9912 "https://github.com/jokergoo/ComplexHeatmap")
9913 (synopsis "Making Complex Heatmaps")
9915 "Complex heatmaps are efficient to visualize associations between
9916 different sources of data sets and reveal potential structures. This package
9917 provides a highly flexible way to arrange multiple heatmaps and supports
9918 self-defined annotation graphics.")
9919 (license license:gpl2+)))
9921 (define-public r-dirichletmultinomial
9923 (name "r-dirichletmultinomial")
9928 (uri (bioconductor-uri "DirichletMultinomial" version))
9931 "0knmncmkkf2ypyqfcl5s8nmyyf9nrzkqprzn9w3w8182c0v49r0s"))))
9933 `((upstream-name . "DirichletMultinomial")))
9934 (build-system r-build-system)
9938 `(("r-biocgenerics" ,r-biocgenerics)
9939 ("r-iranges" ,r-iranges)
9940 ("r-s4vectors" ,r-s4vectors)))
9941 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
9942 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
9944 "Dirichlet-multinomial mixture models can be used to describe variability
9945 in microbial metagenomic data. This package is an interface to code
9946 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
9948 (license license:lgpl3)))
9950 (define-public r-ensembldb
9952 (name "r-ensembldb")
9957 (uri (bioconductor-uri "ensembldb" version))
9960 "02lnpyp85zchmz404hr5381zmihvq4x9zgxdrbn2afi352vg0vab"))))
9961 (build-system r-build-system)
9963 `(("r-annotationdbi" ,r-annotationdbi)
9964 ("r-annotationfilter" ,r-annotationfilter)
9965 ("r-biobase" ,r-biobase)
9966 ("r-biocgenerics" ,r-biocgenerics)
9967 ("r-biostrings" ,r-biostrings)
9970 ("r-genomeinfodb" ,r-genomeinfodb)
9971 ("r-genomicfeatures" ,r-genomicfeatures)
9972 ("r-genomicranges" ,r-genomicranges)
9973 ("r-iranges" ,r-iranges)
9974 ("r-protgenerics" ,r-protgenerics)
9975 ("r-rsamtools" ,r-rsamtools)
9976 ("r-rsqlite" ,r-rsqlite)
9977 ("r-rtracklayer" ,r-rtracklayer)
9978 ("r-s4vectors" ,r-s4vectors)))
9979 (home-page "https://github.com/jotsetung/ensembldb")
9980 (synopsis "Utilities to create and use Ensembl-based annotation databases")
9982 "The package provides functions to create and use transcript-centric
9983 annotation databases/packages. The annotation for the databases are directly
9984 fetched from Ensembl using their Perl API. The functionality and data is
9985 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
9986 but, in addition to retrieve all gene/transcript models and annotations from
9987 the database, the @code{ensembldb} package also provides a filter framework
9988 allowing to retrieve annotations for specific entries like genes encoded on a
9989 chromosome region or transcript models of lincRNA genes.")
9990 ;; No version specified
9991 (license license:lgpl3+)))
9993 (define-public r-organismdbi
9995 (name "r-organismdbi")
10000 (uri (bioconductor-uri "OrganismDbi" version))
10003 "1bvfyh733mhka9zd00hrzpalgjs255c2blnxyf60ipzk5jg7yllb"))))
10004 (properties `((upstream-name . "OrganismDbi")))
10005 (build-system r-build-system)
10007 `(("r-annotationdbi" ,r-annotationdbi)
10008 ("r-biobase" ,r-biobase)
10009 ("r-biocgenerics" ,r-biocgenerics)
10010 ("r-biocmanager" ,r-biocmanager)
10012 ("r-genomicfeatures" ,r-genomicfeatures)
10013 ("r-genomicranges" ,r-genomicranges)
10014 ("r-graph" ,r-graph)
10015 ("r-iranges" ,r-iranges)
10017 ("r-s4vectors" ,r-s4vectors)))
10018 (home-page "https://bioconductor.org/packages/OrganismDbi")
10019 (synopsis "Software to enable the smooth interfacing of database packages")
10020 (description "The package enables a simple unified interface to several
10021 annotation packages each of which has its own schema by taking advantage of
10022 the fact that each of these packages implements a select methods.")
10023 (license license:artistic2.0)))
10025 (define-public r-biovizbase
10027 (name "r-biovizbase")
10032 (uri (bioconductor-uri "biovizBase" version))
10035 "04vvj907bgs67w8rb7n1haf80p6cd0qj5fdxw0dwryb455y35vir"))))
10036 (properties `((upstream-name . "biovizBase")))
10037 (build-system r-build-system)
10039 `(("r-annotationdbi" ,r-annotationdbi)
10040 ("r-annotationfilter" ,r-annotationfilter)
10041 ("r-biocgenerics" ,r-biocgenerics)
10042 ("r-biostrings" ,r-biostrings)
10043 ("r-dichromat" ,r-dichromat)
10044 ("r-ensembldb" ,r-ensembldb)
10045 ("r-genomeinfodb" ,r-genomeinfodb)
10046 ("r-genomicalignments" ,r-genomicalignments)
10047 ("r-genomicfeatures" ,r-genomicfeatures)
10048 ("r-genomicranges" ,r-genomicranges)
10049 ("r-hmisc" ,r-hmisc)
10050 ("r-iranges" ,r-iranges)
10051 ("r-rcolorbrewer" ,r-rcolorbrewer)
10052 ("r-rlang" ,r-rlang)
10053 ("r-rsamtools" ,r-rsamtools)
10054 ("r-s4vectors" ,r-s4vectors)
10055 ("r-scales" ,r-scales)
10056 ("r-summarizedexperiment" ,r-summarizedexperiment)
10057 ("r-variantannotation" ,r-variantannotation)))
10058 (home-page "https://bioconductor.org/packages/biovizBase")
10059 (synopsis "Basic graphic utilities for visualization of genomic data")
10061 "The biovizBase package is designed to provide a set of utilities, color
10062 schemes and conventions for genomic data. It serves as the base for various
10063 high-level packages for biological data visualization. This saves development
10064 effort and encourages consistency.")
10065 (license license:artistic2.0)))
10067 (define-public r-ggbio
10074 (uri (bioconductor-uri "ggbio" version))
10077 "13wzwh40anh8l53yp19bg4w5cpxykcaf228dc8cxvjndyib711qb"))))
10078 (build-system r-build-system)
10081 (modify-phases %standard-phases
10082 ;; See https://github.com/tengfei/ggbio/issues/117
10083 ;; This fix will be included in the next release.
10084 (add-after 'unpack 'fix-typo
10086 (substitute* "R/GGbio-class.R"
10087 (("fechable") "fetchable"))
10090 `(("r-annotationdbi" ,r-annotationdbi)
10091 ("r-annotationfilter" ,r-annotationfilter)
10092 ("r-biobase" ,r-biobase)
10093 ("r-biocgenerics" ,r-biocgenerics)
10094 ("r-biostrings" ,r-biostrings)
10095 ("r-biovizbase" ,r-biovizbase)
10096 ("r-bsgenome" ,r-bsgenome)
10097 ("r-ensembldb" ,r-ensembldb)
10098 ("r-genomeinfodb" ,r-genomeinfodb)
10099 ("r-genomicalignments" ,r-genomicalignments)
10100 ("r-genomicfeatures" ,r-genomicfeatures)
10101 ("r-genomicranges" ,r-genomicranges)
10102 ("r-ggally" ,r-ggally)
10103 ("r-ggplot2" ,r-ggplot2)
10104 ("r-gridextra" ,r-gridextra)
10105 ("r-gtable" ,r-gtable)
10106 ("r-hmisc" ,r-hmisc)
10107 ("r-iranges" ,r-iranges)
10108 ("r-organismdbi" ,r-organismdbi)
10109 ("r-reshape2" ,r-reshape2)
10110 ("r-rlang" ,r-rlang)
10111 ("r-rsamtools" ,r-rsamtools)
10112 ("r-rtracklayer" ,r-rtracklayer)
10113 ("r-s4vectors" ,r-s4vectors)
10114 ("r-scales" ,r-scales)
10115 ("r-summarizedexperiment" ,r-summarizedexperiment)
10116 ("r-variantannotation" ,r-variantannotation)))
10117 (home-page "http://www.tengfei.name/ggbio/")
10118 (synopsis "Visualization tools for genomic data")
10120 "The ggbio package extends and specializes the grammar of graphics for
10121 biological data. The graphics are designed to answer common scientific
10122 questions, in particular those often asked of high throughput genomics data.
10123 All core Bioconductor data structures are supported, where appropriate. The
10124 package supports detailed views of particular genomic regions, as well as
10125 genome-wide overviews. Supported overviews include ideograms and grand linear
10126 views. High-level plots include sequence fragment length, edge-linked
10127 interval to data view, mismatch pileup, and several splicing summaries.")
10128 (license license:artistic2.0)))
10130 (define-public r-gprofiler
10132 (name "r-gprofiler")
10137 (uri (cran-uri "gProfileR" version))
10140 "1h1v0kgpsn04ald2izznh7fr2riwisj5hcgz4k7h3qc931rf0r4k"))))
10141 (properties `((upstream-name . "gProfileR")))
10142 (build-system r-build-system)
10144 `(("r-plyr" ,r-plyr)
10145 ("r-rcurl" ,r-rcurl)))
10146 (home-page "https://cran.r-project.org/web/packages/gProfileR/")
10147 (synopsis "Interface to the g:Profiler toolkit")
10149 "This package provides tools for functional enrichment analysis,
10150 gene identifier conversion and mapping homologous genes across related
10151 organisms via the @code{g:Profiler} toolkit.")
10152 (license license:gpl2+)))
10154 (define-public r-gqtlbase
10156 (name "r-gqtlbase")
10161 (uri (bioconductor-uri "gQTLBase" version))
10164 "1qr8dqjbmj1mdjbzbnxwzfrm8f02wqfsgic8ws5kv7pmsby63y4x"))))
10165 (properties `((upstream-name . "gQTLBase")))
10166 (build-system r-build-system)
10168 `(("r-batchjobs" ,r-batchjobs)
10169 ("r-bbmisc" ,r-bbmisc)
10170 ("r-biocgenerics" ,r-biocgenerics)
10172 ("r-doparallel" ,r-doparallel)
10174 ("r-ffbase" ,r-ffbase)
10175 ("r-foreach" ,r-foreach)
10176 ("r-genomicfiles" ,r-genomicfiles)
10177 ("r-genomicranges" ,r-genomicranges)
10178 ("r-rtracklayer" ,r-rtracklayer)
10179 ("r-s4vectors" ,r-s4vectors)
10180 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10181 (home-page "https://bioconductor.org/packages/gQTLBase")
10182 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10184 "The purpose of this package is to simplify the storage and interrogation
10185 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10187 (license license:artistic2.0)))
10189 (define-public r-snpstats
10191 (name "r-snpstats")
10196 (uri (bioconductor-uri "snpStats" version))
10199 "1xq1rjljg70h5mshdza56dis0iv1a20sivs6dav3w5jbdd1l5qkh"))))
10200 (properties `((upstream-name . "snpStats")))
10201 (build-system r-build-system)
10202 (inputs `(("zlib" ,zlib)))
10204 `(("r-biocgenerics" ,r-biocgenerics)
10205 ("r-matrix" ,r-matrix)
10206 ("r-survival" ,r-survival)
10207 ("r-zlibbioc" ,r-zlibbioc)))
10208 (home-page "https://bioconductor.org/packages/snpStats")
10209 (synopsis "Methods for SNP association studies")
10211 "This package provides classes and statistical methods for large
10212 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10213 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10214 (license license:gpl3)))
10216 (define-public r-homo-sapiens
10218 (name "r-homo-sapiens")
10222 ;; We cannot use bioconductor-uri here because this tarball is
10223 ;; located under "data/annotation/" instead of "bioc/".
10224 (uri (string-append "https://www.bioconductor.org/packages/"
10225 "release/data/annotation/src/contrib/"
10227 version ".tar.gz"))
10230 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10232 `((upstream-name . "Homo.sapiens")))
10233 (build-system r-build-system)
10235 `(("r-genomicfeatures" ,r-genomicfeatures)
10236 ("r-go-db" ,r-go-db)
10237 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10238 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10239 ("r-organismdbi" ,r-organismdbi)
10240 ("r-annotationdbi" ,r-annotationdbi)))
10241 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10242 (synopsis "Annotation package for the Homo.sapiens object")
10244 "This package contains the Homo.sapiens object to access data from
10245 several related annotation packages.")
10246 (license license:artistic2.0)))
10248 (define-public r-erma
10255 (uri (bioconductor-uri "erma" version))
10258 "085qsr73p8nyp435f15l4l1jkfd64bfd9gl4z496nfxdnqn95srz"))))
10259 (build-system r-build-system)
10261 `(("r-annotationdbi" ,r-annotationdbi)
10262 ("r-biobase" ,r-biobase)
10263 ("r-biocgenerics" ,r-biocgenerics)
10264 ("r-biocparallel" ,r-biocparallel)
10265 ("r-genomeinfodb" ,r-genomeinfodb)
10266 ("r-genomicfiles" ,r-genomicfiles)
10267 ("r-genomicranges" ,r-genomicranges)
10268 ("r-ggplot2" ,r-ggplot2)
10269 ("r-homo-sapiens" ,r-homo-sapiens)
10270 ("r-iranges" ,r-iranges)
10271 ("r-rtracklayer" ,r-rtracklayer)
10272 ("r-s4vectors" ,r-s4vectors)
10273 ("r-shiny" ,r-shiny)
10274 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10275 (home-page "https://bioconductor.org/packages/erma")
10276 (synopsis "Epigenomic road map adventures")
10278 "The epigenomics road map describes locations of epigenetic marks in DNA
10279 from a variety of cell types. Of interest are locations of histone
10280 modifications, sites of DNA methylation, and regions of accessible chromatin.
10281 This package presents a selection of elements of the road map including
10282 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10283 by Ernst and Kellis.")
10284 (license license:artistic2.0)))
10286 (define-public r-ldblock
10293 (uri (bioconductor-uri "ldblock" version))
10296 "0xpigfidmylfawy6vzshqnsw1lzjs4qms8q7zffij6bkvkv7920x"))))
10297 (build-system r-build-system)
10299 `(("r-biocgenerics" ,r-biocgenerics)
10300 ("r-ensdb-hsapiens-v75" ,r-ensdb-hsapiens-v75)
10301 ("r-ensembldb" ,r-ensembldb)
10302 ("r-genomeinfodb" ,r-genomeinfodb)
10303 ("r-genomicfiles" ,r-genomicfiles)
10305 ("r-matrix" ,r-matrix)
10306 ("r-rsamtools" ,r-rsamtools)
10307 ("r-snpstats" ,r-snpstats)
10308 ("r-variantannotation" ,r-variantannotation)))
10309 (home-page "https://bioconductor.org/packages/ldblock")
10310 (synopsis "Data structures for linkage disequilibrium measures in populations")
10312 "This package defines data structures for @dfn{linkage
10313 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10314 handling of existing population-level data for the purpose of flexibly
10315 defining LD blocks.")
10316 (license license:artistic2.0)))
10318 (define-public r-gqtlstats
10320 (name "r-gqtlstats")
10325 (uri (bioconductor-uri "gQTLstats" version))
10328 "1dly4p9r4231hf31xg1nzqiyvjbcfjljfmhb88ic1jxwnvniyv2f"))))
10329 (properties `((upstream-name . "gQTLstats")))
10330 (build-system r-build-system)
10332 `(("r-annotationdbi" ,r-annotationdbi)
10333 ("r-batchjobs" ,r-batchjobs)
10334 ("r-bbmisc" ,r-bbmisc)
10335 ("r-beeswarm" ,r-beeswarm)
10336 ("r-biobase" ,r-biobase)
10337 ("r-biocgenerics" ,r-biocgenerics)
10338 ("r-doparallel" ,r-doparallel)
10339 ("r-dplyr" ,r-dplyr)
10341 ("r-ffbase" ,r-ffbase)
10342 ("r-foreach" ,r-foreach)
10343 ("r-genomeinfodb" ,r-genomeinfodb)
10344 ("r-genomicfeatures" ,r-genomicfeatures)
10345 ("r-genomicfiles" ,r-genomicfiles)
10346 ("r-genomicranges" ,r-genomicranges)
10347 ("r-ggbeeswarm" ,r-ggbeeswarm)
10348 ("r-ggplot2" ,r-ggplot2)
10349 ("r-gqtlbase" ,r-gqtlbase)
10350 ("r-hardyweinberg" ,r-hardyweinberg)
10351 ("r-homo-sapiens" ,r-homo-sapiens)
10352 ("r-iranges" ,r-iranges)
10353 ("r-limma" ,r-limma)
10355 ("r-plotly" ,r-plotly)
10356 ("r-reshape2" ,r-reshape2)
10357 ("r-s4vectors" ,r-s4vectors)
10358 ("r-shiny" ,r-shiny)
10359 ("r-snpstats" ,r-snpstats)
10360 ("r-summarizedexperiment" ,r-summarizedexperiment)
10361 ("r-variantannotation" ,r-variantannotation)))
10362 (home-page "https://bioconductor.org/packages/gQTLstats")
10363 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10365 "This package provides tools for the computationally efficient analysis
10366 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10367 The software in this package aims to support refinements and functional
10368 interpretation of members of a collection of association statistics on a
10369 family of feature/genome hypotheses.")
10370 (license license:artistic2.0)))
10372 (define-public r-gviz
10379 (uri (bioconductor-uri "Gviz" version))
10382 "0c9i26h5czm60n1bxzmdxxpywcj0sig6wcj913pb41mr83bbgra3"))))
10383 (properties `((upstream-name . "Gviz")))
10384 (build-system r-build-system)
10386 `(("r-annotationdbi" ,r-annotationdbi)
10387 ("r-biobase" ,r-biobase)
10388 ("r-biocgenerics" ,r-biocgenerics)
10389 ("r-biomart" ,r-biomart)
10390 ("r-biostrings" ,r-biostrings)
10391 ("r-biovizbase" ,r-biovizbase)
10392 ("r-bsgenome" ,r-bsgenome)
10393 ("r-digest" ,r-digest)
10394 ("r-genomeinfodb" ,r-genomeinfodb)
10395 ("r-genomicalignments" ,r-genomicalignments)
10396 ("r-genomicfeatures" ,r-genomicfeatures)
10397 ("r-genomicranges" ,r-genomicranges)
10398 ("r-iranges" ,r-iranges)
10399 ("r-lattice" ,r-lattice)
10400 ("r-latticeextra" ,r-latticeextra)
10401 ("r-matrixstats" ,r-matrixstats)
10402 ("r-rcolorbrewer" ,r-rcolorbrewer)
10403 ("r-rsamtools" ,r-rsamtools)
10404 ("r-rtracklayer" ,r-rtracklayer)
10405 ("r-s4vectors" ,r-s4vectors)
10406 ("r-xvector" ,r-xvector)))
10407 (home-page "https://bioconductor.org/packages/Gviz")
10408 (synopsis "Plotting data and annotation information along genomic coordinates")
10410 "Genomic data analyses requires integrated visualization of known genomic
10411 information and new experimental data. Gviz uses the biomaRt and the
10412 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10413 and translates this to e.g. gene/transcript structures in viewports of the
10414 grid graphics package. This results in genomic information plotted together
10416 (license license:artistic2.0)))
10418 (define-public r-gwascat
10425 (uri (bioconductor-uri "gwascat" version))
10428 "038vhfsk2vs7inn5di093cmjbb81k7j0af385sg7l01jj70bdqq1"))))
10429 (build-system r-build-system)
10431 `(("r-annotationdbi" ,r-annotationdbi)
10432 ("r-biocgenerics" ,r-biocgenerics)
10433 ("r-biostrings" ,r-biostrings)
10434 ("r-genomeinfodb" ,r-genomeinfodb)
10435 ("r-genomicfeatures" ,r-genomicfeatures)
10436 ("r-genomicranges" ,r-genomicranges)
10437 ("r-homo-sapiens" ,r-homo-sapiens)
10438 ("r-iranges" ,r-iranges)
10439 ("r-rsamtools" ,r-rsamtools)
10440 ("r-rtracklayer" ,r-rtracklayer)
10441 ("r-s4vectors" ,r-s4vectors)))
10442 (home-page "https://bioconductor.org/packages/gwascat")
10443 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10445 "This package provides tools for representing and modeling data in the
10446 EMBL-EBI GWAS catalog.")
10447 (license license:artistic2.0)))
10449 (define-public r-sushi
10455 (uri (bioconductor-uri "Sushi" version))
10458 "15xng21hd09fb234ravrry3b872zg82w8x9lijxab9n96xihcpz5"))))
10459 (properties `((upstream-name . "Sushi")))
10460 (build-system r-build-system)
10462 `(("r-biomart" ,r-biomart)
10464 (home-page "https://bioconductor.org/packages/Sushi")
10465 (synopsis "Tools for visualizing genomics data")
10467 "This package provides flexible, quantitative, and integrative genomic
10468 visualizations for publication-quality multi-panel figures.")
10469 (license license:gpl2+)))
10471 (define-public r-fithic
10477 (uri (bioconductor-uri "FitHiC" version))
10480 "1irwkwi4afdj395134k31mvx7c2vpdd0rv8zrblnldascdsb04kc"))))
10481 (properties `((upstream-name . "FitHiC")))
10482 (build-system r-build-system)
10484 `(("r-data-table" ,r-data-table)
10485 ("r-fdrtool" ,r-fdrtool)
10486 ("r-rcpp" ,r-rcpp)))
10487 (home-page "https://bioconductor.org/packages/FitHiC")
10488 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10490 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10491 intra-chromosomal contact maps produced by genome-wide genome architecture
10492 assays such as Hi-C.")
10493 (license license:gpl2+)))
10495 (define-public r-hitc
10501 (uri (bioconductor-uri "HiTC" version))
10504 "0byahi0fz0dzjyklz8v9whax9ygg7gwb4pl1j3zbl6z8a9qx8pps"))))
10505 (properties `((upstream-name . "HiTC")))
10506 (build-system r-build-system)
10508 `(("r-biostrings" ,r-biostrings)
10509 ("r-genomeinfodb" ,r-genomeinfodb)
10510 ("r-genomicranges" ,r-genomicranges)
10511 ("r-iranges" ,r-iranges)
10512 ("r-matrix" ,r-matrix)
10513 ("r-rcolorbrewer" ,r-rcolorbrewer)
10514 ("r-rtracklayer" ,r-rtracklayer)))
10515 (home-page "https://bioconductor.org/packages/HiTC")
10516 (synopsis "High throughput chromosome conformation capture analysis")
10518 "The HiTC package was developed to explore high-throughput \"C\" data
10519 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10520 quality controls, normalization, visualization, and further analysis are also
10522 (license license:artistic2.0)))
10524 (define-public r-hdf5array
10526 (name "r-hdf5array")
10531 (uri (bioconductor-uri "HDF5Array" version))
10534 "1z153a7nxmlml72pl1saasj2il9g5ahpynkpv3mkhhsvl5kbwbh6"))))
10535 (properties `((upstream-name . "HDF5Array")))
10536 (build-system r-build-system)
10540 `(("r-biocgenerics" ,r-biocgenerics)
10541 ("r-delayedarray" ,r-delayedarray)
10542 ("r-iranges" ,r-iranges)
10543 ("r-matrix" ,r-matrix)
10544 ("r-rhdf5" ,r-rhdf5)
10545 ("r-rhdf5lib" ,r-rhdf5lib)
10546 ("r-s4vectors" ,r-s4vectors)))
10547 (home-page "https://bioconductor.org/packages/HDF5Array")
10548 (synopsis "HDF5 back end for DelayedArray objects")
10549 (description "This package provides an array-like container for convenient
10550 access and manipulation of HDF5 datasets. It supports delayed operations and
10551 block processing.")
10552 (license license:artistic2.0)))
10554 (define-public r-rhdf5lib
10556 (name "r-rhdf5lib")
10561 (uri (bioconductor-uri "Rhdf5lib" version))
10564 "17lhwnm9rqsvbqkvwp0m07vjrk63a4389p2y39zffv8fgznxqzd7"))
10565 (modules '((guix build utils)))
10568 ;; Delete bundled binaries
10569 (delete-file-recursively "src/winlib/")
10571 (properties `((upstream-name . "Rhdf5lib")))
10572 (build-system r-build-system)
10575 (modify-phases %standard-phases
10576 (add-after 'unpack 'do-not-use-bundled-hdf5
10577 (lambda* (#:key inputs #:allow-other-keys)
10578 (for-each delete-file '("configure" "configure.ac"))
10579 ;; Do not make other packages link with the proprietary libsz.
10580 (substitute* "R/zzz.R"
10581 (("'\"%s/libhdf5.a\" \"%s/libsz.a\" -lz'")
10582 "'\"%s/libhdf5.a\" \"%s/libhdf5.a\" -lz'")
10583 (("'\"%s/libhdf5_cpp.a\" \"%s/libhdf5.a\" \"%s/libsz.a\" -lz'")
10584 "'\"%s/libhdf5_cpp.a\" \"%s/libhdf5.a\" \"%s/libhdf5.a\" -lz'")
10585 (("'%s/libhdf5_hl.a %s/libhdf5.a %s/libsz.a -lz'")
10586 "'%s/libhdf5_hl.a %s/libhdf5.a %s/libhdf5.a -lz'")
10587 (("'%s/libhdf5_hl_cpp.a %s/libhdf5_hl.a %s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a -lz'")
10588 "'%s/libhdf5_hl_cpp.a %s/libhdf5_hl.a %s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a -lz'"))
10589 (with-directory-excursion "src"
10590 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10591 (rename-file (string-append "hdf5-" ,(package-version hdf5-1.10))
10593 ;; Remove timestamp and host system information to make
10594 ;; the build reproducible.
10595 (substitute* "hdf5/src/libhdf5.settings.in"
10596 (("Configured on: @CONFIG_DATE@")
10597 "Configured on: Guix")
10598 (("Uname information:.*")
10599 "Uname information: Linux\n")
10600 ;; Remove unnecessary store reference.
10602 "C Compiler: GCC\n"))
10603 (rename-file "Makevars.in" "Makevars")
10604 (substitute* "Makevars"
10605 (("HDF5_CXX_LIB=.*")
10606 (string-append "HDF5_CXX_LIB="
10607 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10609 (string-append "HDF5_LIB="
10610 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10611 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10612 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10613 (("HDF5_HL_INCLUDE=.*") "HDF5_HL_INCLUDE=./hdf5/hl/src\n")
10614 (("HDF5_HL_CXX_INCLUDE=.*") "HDF5_HL_CXX_INCLUDE=./hdf5/hl/c++/src\n")
10615 (("HDF5_HL_LIB=.*")
10616 (string-append "HDF5_HL_LIB="
10617 (assoc-ref inputs "hdf5") "/lib/libhdf5_hl.a\n"))
10618 (("HDF5_HL_CXX_LIB=.*")
10619 (string-append "HDF5_HL_CXX_LIB="
10620 (assoc-ref inputs "hdf5") "/lib/libhdf5_hl_cpp.a\n"))
10621 ;; szip is non-free software
10622 (("cp \"\\$\\{SZIP_LIB\\}.*") "")
10623 (("PKG_LIBS =.*") "PKG_LIBS = -lz -lhdf5\n")))
10628 `(("hdf5" ,hdf5-1.10)))
10630 `(("hdf5-source" ,(package-source hdf5-1.10))))
10631 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10632 (synopsis "HDF5 library as an R package")
10633 (description "This package provides C and C++ HDF5 libraries for use in R
10635 (license license:artistic2.0)))
10637 (define-public r-beachmat
10639 (name "r-beachmat")
10644 (uri (bioconductor-uri "beachmat" version))
10647 "1bpnlw2kdy9yc2vq948k980r0j25ipb80llhvn0j3kxjiwyfgs3i"))))
10648 (build-system r-build-system)
10650 `(("r-biocgenerics" ,r-biocgenerics)
10651 ("r-delayedarray" ,r-delayedarray)
10652 ("r-matrix" ,r-matrix)))
10653 (home-page "https://bioconductor.org/packages/beachmat")
10654 (synopsis "Compiling Bioconductor to handle each matrix type")
10655 (description "This package provides a consistent C++ class interface for a
10656 variety of commonly used matrix types, including sparse and HDF5-backed
10658 (license license:gpl3)))
10660 (define-public r-singlecellexperiment
10662 (name "r-singlecellexperiment")
10667 (uri (bioconductor-uri "SingleCellExperiment" version))
10670 "11pqb3cigi9xbhxq2k3n7z23v1ibd03ws1lcrh5c5ffgb33nlyw5"))))
10672 `((upstream-name . "SingleCellExperiment")))
10673 (build-system r-build-system)
10675 `(("r-biocgenerics" ,r-biocgenerics)
10676 ("r-s4vectors" ,r-s4vectors)
10677 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10678 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10679 (synopsis "S4 classes for single cell data")
10680 (description "This package defines an S4 class for storing data from
10681 single-cell experiments. This includes specialized methods to store and
10682 retrieve spike-in information, dimensionality reduction coordinates and size
10683 factors for each cell, along with the usual metadata for genes and
10685 (license license:gpl3)))
10687 (define-public r-scater
10693 (uri (bioconductor-uri "scater" version))
10696 "0sxd1s8wdlj9926bagq4crjrk1nnmh3j3bhgrw160zfgc3y8pzck"))))
10697 (build-system r-build-system)
10699 `(("r-beachmat" ,r-beachmat)
10700 ("r-biocgenerics" ,r-biocgenerics)
10701 ("r-biocneighbors" ,r-biocneighbors)
10702 ("r-biocparallel" ,r-biocparallel)
10703 ("r-biocsingular" ,r-biocsingular)
10704 ("r-delayedarray" ,r-delayedarray)
10705 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10706 ("r-ggbeeswarm" ,r-ggbeeswarm)
10707 ("r-ggplot2" ,r-ggplot2)
10708 ("r-matrix" ,r-matrix)
10710 ("r-s4vectors" ,r-s4vectors)
10711 ("r-singlecellexperiment" ,r-singlecellexperiment)
10712 ("r-summarizedexperiment" ,r-summarizedexperiment)
10713 ("r-viridis" ,r-viridis)))
10714 (home-page "https://github.com/davismcc/scater")
10715 (synopsis "Single-cell analysis toolkit for gene expression data in R")
10716 (description "This package provides a collection of tools for doing
10717 various analyses of single-cell RNA-seq gene expression data, with a focus on
10719 (license license:gpl2+)))
10721 (define-public r-scran
10728 (uri (bioconductor-uri "scran" version))
10731 "1y8wlgk5zbv7c7gcp0ahfpbh9lifab7y3zwf0093fzaw7vr1y6cr"))))
10732 (build-system r-build-system)
10734 `(("r-beachmat" ,r-beachmat)
10736 ("r-biocgenerics" ,r-biocgenerics)
10737 ("r-biocneighbors" ,r-biocneighbors)
10738 ("r-biocparallel" ,r-biocparallel)
10739 ("r-biocsingular" ,r-biocsingular)
10740 ("r-delayedarray" ,r-delayedarray)
10741 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10742 ("r-dqrng" ,r-dqrng)
10743 ("r-edger" ,r-edger)
10744 ("r-igraph" ,r-igraph)
10745 ("r-limma" ,r-limma)
10746 ("r-matrix" ,r-matrix)
10748 ("r-s4vectors" ,r-s4vectors)
10749 ("r-scater" ,r-scater)
10750 ("r-singlecellexperiment" ,r-singlecellexperiment)
10751 ("r-statmod" ,r-statmod)
10752 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10753 (home-page "https://bioconductor.org/packages/scran")
10754 (synopsis "Methods for single-cell RNA-Seq data analysis")
10755 (description "This package implements a variety of low-level analyses of
10756 single-cell RNA-seq data. Methods are provided for normalization of
10757 cell-specific biases, assignment of cell cycle phase, and detection of highly
10758 variable and significantly correlated genes.")
10759 (license license:gpl3)))
10761 (define-public r-delayedmatrixstats
10763 (name "r-delayedmatrixstats")
10768 (uri (bioconductor-uri "DelayedMatrixStats" version))
10771 "0mv2rl6a6l404piabcazxz1s6ars016pxhjf5v40hhr6y1r0wbqy"))))
10773 `((upstream-name . "DelayedMatrixStats")))
10774 (build-system r-build-system)
10776 `(("r-biocparallel" ,r-biocparallel)
10777 ("r-delayedarray" ,r-delayedarray)
10778 ("r-hdf5array" ,r-hdf5array)
10779 ("r-iranges" ,r-iranges)
10780 ("r-matrix" ,r-matrix)
10781 ("r-matrixstats" ,r-matrixstats)
10782 ("r-s4vectors" ,r-s4vectors)))
10783 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
10784 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
10786 "This package provides a port of the @code{matrixStats} API for use with
10787 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
10788 contains high-performing functions operating on rows and columns of
10789 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
10790 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
10791 are optimized per data type and for subsetted calculations such that both
10792 memory usage and processing time is minimized.")
10793 (license license:expat)))
10795 (define-public r-phangorn
10797 (name "r-phangorn")
10802 (uri (cran-uri "phangorn" version))
10805 "0ihkaykqjmf80d8wrk3saphxvnv58zma6pd13633bd3cwanc33f5"))))
10806 (build-system r-build-system)
10809 ("r-fastmatch" ,r-fastmatch)
10810 ("r-igraph" ,r-igraph)
10811 ("r-magrittr" ,r-magrittr)
10812 ("r-matrix" ,r-matrix)
10813 ("r-quadprog" ,r-quadprog)
10814 ("r-rcpp" ,r-rcpp)))
10815 (home-page "https://github.com/KlausVigo/phangorn")
10816 (synopsis "Phylogenetic analysis in R")
10818 "Phangorn is a package for phylogenetic analysis in R. It supports
10819 estimation of phylogenetic trees and networks using Maximum Likelihood,
10820 Maximum Parsimony, distance methods and Hadamard conjugation.")
10821 (license license:gpl2+)))
10823 (define-public r-dropbead
10824 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
10827 (name "r-dropbead")
10828 (version (string-append "0-" revision "." (string-take commit 7)))
10832 (uri (git-reference
10833 (url "https://github.com/rajewsky-lab/dropbead.git")
10835 (file-name (git-file-name name version))
10838 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
10839 (build-system r-build-system)
10841 `(("r-ggplot2" ,r-ggplot2)
10842 ("r-rcolorbrewer" ,r-rcolorbrewer)
10843 ("r-gridextra" ,r-gridextra)
10844 ("r-gplots" ,r-gplots)
10845 ("r-plyr" ,r-plyr)))
10846 (home-page "https://github.com/rajewsky-lab/dropbead")
10847 (synopsis "Basic exploration and analysis of Drop-seq data")
10848 (description "This package offers a quick and straight-forward way to
10849 explore and perform basic analysis of single cell sequencing data coming from
10850 droplet sequencing. It has been particularly tailored for Drop-seq.")
10851 (license license:gpl3))))
10853 (define htslib-for-sambamba
10854 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
10857 (name "htslib-for-sambamba")
10858 (version (string-append "1.3.1-1." (string-take commit 9)))
10862 (uri (git-reference
10863 (url "https://github.com/lomereiter/htslib.git")
10865 (file-name (string-append "htslib-" version "-checkout"))
10868 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
10870 `(("autoconf" ,autoconf)
10871 ("automake" ,automake)
10872 ,@(package-native-inputs htslib))))))
10874 (define-public sambamba
10881 (uri (git-reference
10882 (url "https://github.com/lomereiter/sambamba.git")
10883 (commit (string-append "v" version))))
10884 (file-name (string-append name "-" version "-checkout"))
10887 "0k0cz3qcv98p6cq09zlbgnjsggxcqbcmzxg5zikgcgbr2nfq4lry"))))
10888 (build-system gnu-build-system)
10890 `(#:tests? #f ; there is no test target
10891 #:parallel-build? #f ; not supported
10893 (modify-phases %standard-phases
10894 (delete 'configure)
10895 (add-after 'unpack 'fix-ldc-version
10897 (substitute* "gen_ldc_version_info.py"
10898 (("/usr/bin/env.*") (which "python3")))
10899 (substitute* "Makefile"
10900 ;; We use ldc2 instead of ldmd2 to compile sambamba.
10901 (("\\$\\(shell which ldmd2\\)") (which "ldc2")))
10903 (add-after 'unpack 'place-biod-and-undead
10904 (lambda* (#:key inputs #:allow-other-keys)
10905 (copy-recursively (assoc-ref inputs "biod") "BioD")
10906 (copy-recursively (assoc-ref inputs "undead") "undeaD")
10908 (add-after 'unpack 'unbundle-prerequisites
10910 (substitute* "Makefile"
10911 (("htslib/libhts.a lz4/lib/liblz4.a")
10913 ((" lz4-static htslib-static") ""))
10916 (lambda* (#:key outputs #:allow-other-keys)
10917 (let* ((out (assoc-ref outputs "out"))
10918 (bin (string-append out "/bin")))
10920 (install-file "bin/sambamba" bin)
10927 ,(let ((commit "4f1a7d2fb7ef3dfe962aa357d672f354ebfbe42e"))
10930 (uri (git-reference
10931 (url "https://github.com/biod/BioD.git")
10933 (file-name (string-append "biod-"
10934 (string-take commit 9)
10938 "1k5pdjv1qvi0a3rwd1sfq6zbj37l86i7bf710m4c0y6737lxj426")))))
10940 ,(let ((commit "9be93876982b5f14fcca60832563b3cd767dd84d"))
10943 (uri (git-reference
10944 (url "https://github.com/biod/undeaD.git")
10946 (file-name (string-append "undead-"
10947 (string-take commit 9)
10951 "1xfarj0nqlmi5jd1vmcmm7pabzaf9hxyvk6hp0d6jslb5k9r8r3d")))))))
10954 ("htslib" ,htslib-for-sambamba)))
10955 (home-page "https://lomereiter.github.io/sambamba/")
10956 (synopsis "Tools for working with SAM/BAM data")
10957 (description "Sambamba is a high performance modern robust and
10958 fast tool (and library), written in the D programming language, for
10959 working with SAM and BAM files. Current parallelised functionality is
10960 an important subset of samtools functionality, including view, index,
10961 sort, markdup, and depth.")
10962 (license license:gpl2+)))
10964 (define-public ritornello
10966 (name "ritornello")
10970 (uri (git-reference
10971 (url "https://github.com/KlugerLab/Ritornello.git")
10972 (commit (string-append "v" version))))
10973 (file-name (git-file-name name version))
10976 "1xahvq215qld7x1w8vpa5zbrsj6p9crb9shqa2x89sb0aaxa02jk"))))
10977 (build-system gnu-build-system)
10979 `(#:tests? #f ; there are no tests
10981 (modify-phases %standard-phases
10982 (add-after 'unpack 'patch-samtools-references
10983 (lambda* (#:key inputs #:allow-other-keys)
10984 (substitute* '("src/SamStream.h"
10986 (("<sam.h>") "<samtools/sam.h>"))
10988 (delete 'configure)
10990 (lambda* (#:key inputs outputs #:allow-other-keys)
10991 (let* ((out (assoc-ref outputs "out"))
10992 (bin (string-append out "/bin/")))
10994 (install-file "bin/Ritornello" bin)
10997 `(("samtools" ,samtools-0.1)
11001 (home-page "https://github.com/KlugerLab/Ritornello")
11002 (synopsis "Control-free peak caller for ChIP-seq data")
11003 (description "Ritornello is a ChIP-seq peak calling algorithm based on
11004 signal processing that can accurately call binding events without the need to
11005 do a pair total DNA input or IgG control sample. It has been tested for use
11006 with narrow binding events such as transcription factor ChIP-seq.")
11007 (license license:gpl3+)))
11009 (define-public trim-galore
11011 (name "trim-galore")
11016 (uri (git-reference
11017 (url "https://github.com/FelixKrueger/TrimGalore.git")
11019 (file-name (git-file-name name version))
11022 "1y31wbxwkm9xqzr5zv1pk5q418whnmlmgmfyxxpnl12h83m2i9iv"))))
11023 (build-system gnu-build-system)
11025 `(#:tests? #f ; no tests
11027 (modify-phases %standard-phases
11028 (replace 'configure
11030 ;; Trim Galore tries to figure out what version of Python
11031 ;; cutadapt is using by looking at the shebang. Of course that
11032 ;; doesn't work, because cutadapt is wrapped in a shell script.
11033 (substitute* "trim_galore"
11034 (("my \\$python_return.*")
11035 "my $python_return = \"Python 3.999\";\n"))
11038 (add-after 'unpack 'hardcode-tool-references
11039 (lambda* (#:key inputs #:allow-other-keys)
11040 (substitute* "trim_galore"
11041 (("\\$path_to_cutadapt = 'cutadapt'")
11042 (string-append "$path_to_cutadapt = '"
11043 (assoc-ref inputs "cutadapt")
11045 (("\\$compression_path = \"gzip\"")
11046 (string-append "$compression_path = \""
11047 (assoc-ref inputs "gzip")
11050 (string-append "\""
11051 (assoc-ref inputs "gzip")
11054 (string-append "\""
11055 (assoc-ref inputs "pigz")
11059 (lambda* (#:key outputs #:allow-other-keys)
11060 (let ((bin (string-append (assoc-ref outputs "out")
11063 (install-file "trim_galore" bin)
11069 ("cutadapt" ,cutadapt)))
11071 `(("unzip" ,unzip)))
11072 (home-page "https://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
11073 (synopsis "Wrapper around Cutadapt and FastQC")
11074 (description "Trim Galore! is a wrapper script to automate quality and
11075 adapter trimming as well as quality control, with some added functionality to
11076 remove biased methylation positions for RRBS sequence files.")
11077 (license license:gpl3+)))
11079 (define-public gess
11085 (uri (string-append "http://compbio.uthscsa.edu/"
11087 "gess-" version ".src.tar.gz"))
11090 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
11091 (build-system gnu-build-system)
11093 `(#:tests? #f ; no tests
11095 (modify-phases %standard-phases
11096 (delete 'configure)
11099 (lambda* (#:key inputs outputs #:allow-other-keys)
11100 (let* ((python (assoc-ref inputs "python"))
11101 (out (assoc-ref outputs "out"))
11102 (bin (string-append out "/bin/"))
11103 (target (string-append
11105 ,(version-major+minor
11106 (package-version python))
11107 "/site-packages/gess/")))
11109 (copy-recursively "." target)
11110 ;; Make GESS.py executable
11111 (chmod (string-append target "GESS.py") #o555)
11112 ;; Add Python shebang to the top and make Matplotlib
11114 (substitute* (string-append target "GESS.py")
11115 (("\"\"\"Description:" line)
11116 (string-append "#!" (which "python") "
11118 matplotlib.use('Agg')
11120 ;; Make sure GESS has all modules in its path
11121 (wrap-script (string-append target "GESS.py")
11122 `("PYTHONPATH" ":" = (,target ,(getenv "PYTHONPATH"))))
11124 (symlink (string-append target "GESS.py")
11125 (string-append bin "GESS.py"))
11128 `(("python" ,python-2)
11129 ("python2-pysam" ,python2-pysam)
11130 ("python2-scipy" ,python2-scipy)
11131 ("python2-numpy" ,python2-numpy)
11132 ("python2-networkx" ,python2-networkx)
11133 ("python2-biopython" ,python2-biopython)
11134 ("guile" ,guile-3.0))) ; for the script wrapper
11135 (home-page "https://compbio.uthscsa.edu/GESS_Web/")
11136 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11138 "GESS is an implementation of a novel computational method to detect de
11139 novo exon-skipping events directly from raw RNA-seq data without the prior
11140 knowledge of gene annotation information. GESS stands for the graph-based
11141 exon-skipping scanner detection scheme.")
11142 (license license:bsd-3)))
11144 (define-public phylip
11151 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11152 "download/phylip-" version ".tar.gz"))
11155 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11156 (build-system gnu-build-system)
11158 `(#:tests? #f ; no check target
11159 #:make-flags (list "-f" "Makefile.unx" "install")
11160 #:parallel-build? #f ; not supported
11162 (modify-phases %standard-phases
11163 (add-after 'unpack 'enter-dir
11164 (lambda _ (chdir "src") #t))
11165 (delete 'configure)
11167 (lambda* (#:key inputs outputs #:allow-other-keys)
11168 (let ((target (string-append (assoc-ref outputs "out")
11171 (for-each (lambda (file)
11172 (install-file file target))
11173 (find-files "../exe" ".*")))
11175 (home-page "http://evolution.genetics.washington.edu/phylip/")
11176 (synopsis "Tools for inferring phylogenies")
11177 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11178 programs for inferring phylogenies (evolutionary trees).")
11179 (license license:bsd-2)))
11188 (uri (string-append "https://integrativemodeling.org/"
11189 version "/download/imp-" version ".tar.gz"))
11192 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
11193 (build-system cmake-build-system)
11195 `(;; FIXME: Some tests fail because they produce warnings, others fail
11196 ;; because the PYTHONPATH does not include the modeller's directory.
11204 ("python" ,python-2)))
11206 `(("python2-numpy" ,python2-numpy)
11207 ("python2-scipy" ,python2-scipy)
11208 ("python2-pandas" ,python2-pandas)
11209 ("python2-scikit-learn" ,python2-scikit-learn)
11210 ("python2-networkx" ,python2-networkx)))
11211 (home-page "https://integrativemodeling.org")
11212 (synopsis "Integrative modeling platform")
11213 (description "IMP's broad goal is to contribute to a comprehensive
11214 structural characterization of biomolecules ranging in size and complexity
11215 from small peptides to large macromolecular assemblies, by integrating data
11216 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11217 Python toolbox for solving complex modeling problems, and a number of
11218 applications for tackling some common problems in a user-friendly way.")
11219 ;; IMP is largely available under the GNU Lesser GPL; see the file
11220 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11221 ;; available under the GNU GPL (see the file COPYING.GPL).
11222 (license (list license:lgpl2.1+
11225 (define-public tadbit
11231 (uri (git-reference
11232 (url "https://github.com/3DGenomes/TADbit.git")
11233 (commit (string-append "v" version))))
11234 (file-name (git-file-name name version))
11237 "07g3aj648prmsvxp9caz5yl41k0y0647vxh0f5p3w8376mfiljd0"))))
11238 (build-system python-build-system)
11240 `(;; Tests are included and must be run after installation, but
11241 ;; they are incomplete and thus cannot be run.
11245 (modify-phases %standard-phases
11246 (add-after 'unpack 'fix-problems-with-setup.py
11247 (lambda* (#:key outputs #:allow-other-keys)
11248 ;; setup.py opens these files for writing
11249 (chmod "_pytadbit/_version.py" #o664)
11250 (chmod "README.rst" #o664)
11252 ;; Don't attempt to install the bash completions to
11253 ;; the home directory.
11254 (rename-file "extras/.bash_completion"
11256 (substitute* "setup.py"
11257 (("\\(path.expanduser\\('~'\\)")
11258 (string-append "(\""
11259 (assoc-ref outputs "out")
11260 "/etc/bash_completion.d\""))
11261 (("extras/\\.bash_completion")
11265 ;; TODO: add Chimera for visualization
11268 ("python2-scipy" ,python2-scipy)
11269 ("python2-numpy" ,python2-numpy)
11270 ("python2-matplotlib" ,python2-matplotlib)
11271 ("python2-pysam" ,python2-pysam)))
11272 (home-page "https://3dgenomes.github.io/TADbit/")
11273 (synopsis "Analyze, model, and explore 3C-based data")
11275 "TADbit is a complete Python library to deal with all steps to analyze,
11276 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11277 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11278 correct interaction matrices, identify and compare the so-called
11279 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11280 interaction matrices, and finally, extract structural properties from the
11281 models. TADbit is complemented by TADkit for visualizing 3D models.")
11282 (license license:gpl3+)))
11284 (define-public kentutils
11287 ;; 302.1.0 is out, but the only difference is the inclusion of
11288 ;; pre-built binaries.
11289 (version "302.0.0")
11293 (uri (git-reference
11294 (url "https://github.com/ENCODE-DCC/kentUtils.git")
11295 (commit (string-append "v" version))))
11296 (file-name (git-file-name name version))
11299 "0n1wbyjpzii2b9qhyp9r1q76j623cggpg3y8fmw78ld3z4y7ivha"))
11300 (modules '((guix build utils)
11305 ;; Only the contents of the specified directories are free
11306 ;; for all uses, so we remove the rest. "hg/autoSql" and
11307 ;; "hg/autoXml" are nominally free, but they depend on a
11308 ;; library that is built from the sources in "hg/lib",
11309 ;; which is nonfree.
11310 (let ((free (list "." ".."
11311 "utils" "lib" "inc" "tagStorm"
11312 "parasol" "htslib"))
11313 (directory? (lambda (file)
11314 (eq? 'directory (stat:type (stat file))))))
11315 (for-each (lambda (file)
11316 (and (directory? file)
11317 (delete-file-recursively file)))
11318 (map (cut string-append "src/" <>)
11321 (not (member file free)))))))
11322 ;; Only make the utils target, not the userApps target,
11323 ;; because that requires libraries we won't build.
11324 (substitute* "Makefile"
11325 ((" userApps") " utils"))
11326 ;; Only build libraries that are free.
11327 (substitute* "src/makefile"
11328 (("DIRS =.*") "DIRS =\n")
11329 (("cd jkOwnLib.*") "")
11332 (substitute* "src/utils/makefile"
11333 ;; These tools depend on "jkhgap.a", which is part of the
11334 ;; nonfree "src/hg/lib" directory.
11335 (("raSqlQuery") "")
11336 (("pslLiftSubrangeBlat") "")
11338 ;; Do not build UCSC tools, which may require nonfree
11340 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11342 (build-system gnu-build-system)
11344 `( ;; There is no global test target and the test target for
11345 ;; individual tools depends on input files that are not
11349 (modify-phases %standard-phases
11350 (add-after 'unpack 'fix-permissions
11351 (lambda _ (make-file-writable "src/inc/localEnvironment.mk") #t))
11352 (add-after 'unpack 'fix-paths
11354 (substitute* "Makefile"
11355 (("/bin/echo") (which "echo")))
11357 (add-after 'unpack 'prepare-samtabix
11358 (lambda* (#:key inputs #:allow-other-keys)
11359 (copy-recursively (assoc-ref inputs "samtabix")
11362 (delete 'configure)
11364 (lambda* (#:key outputs #:allow-other-keys)
11365 (let ((bin (string-append (assoc-ref outputs "out")
11367 (copy-recursively "bin" bin))
11373 (uri (git-reference
11374 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11375 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11378 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11384 ("mariadb" ,mariadb "lib")
11385 ("mariadb-dev" ,mariadb "dev")
11386 ("openssl" ,openssl-1.0)))
11387 (home-page "https://genome.cse.ucsc.edu/index.html")
11388 (synopsis "Assorted bioinformatics utilities")
11389 (description "This package provides the kentUtils, a selection of
11390 bioinformatics utilities used in combination with the UCSC genome
11392 ;; Only a subset of the sources are released under a non-copyleft
11393 ;; free software license. All other sources are removed in a
11394 ;; snippet. See this bug report for an explanation of how the
11395 ;; license statements apply:
11396 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11397 (license (license:non-copyleft
11398 "http://genome.ucsc.edu/license/"
11399 "The contents of this package are free for all uses."))))
11401 (define-public f-seq
11402 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11406 (version (string-append "1.1-" revision "." (string-take commit 7)))
11409 (uri (git-reference
11410 (url "https://github.com/aboyle/F-seq.git")
11412 (file-name (string-append name "-" version))
11415 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11416 (modules '((guix build utils)))
11417 ;; Remove bundled Java library archives.
11420 (for-each delete-file (find-files "lib" ".*"))
11422 (build-system ant-build-system)
11424 `(#:tests? #f ; no tests included
11426 (modify-phases %standard-phases
11428 (lambda* (#:key inputs outputs #:allow-other-keys)
11429 (let* ((target (assoc-ref outputs "out"))
11430 (bin (string-append target "/bin"))
11431 (doc (string-append target "/share/doc/f-seq"))
11432 (lib (string-append target "/lib")))
11435 (substitute* "bin/linux/fseq"
11436 (("java") (which "java"))
11437 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11438 (string-append (assoc-ref inputs "java-commons-cli")
11439 "/share/java/commons-cli.jar"))
11441 (string-append "REALDIR=" bin "\n")))
11442 (install-file "README.txt" doc)
11443 (install-file "bin/linux/fseq" bin)
11444 (install-file "build~/fseq.jar" lib)
11445 (copy-recursively "lib" lib)
11449 ("java-commons-cli" ,java-commons-cli)))
11450 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11451 (synopsis "Feature density estimator for high-throughput sequence tags")
11453 "F-Seq is a software package that generates a continuous tag sequence
11454 density estimation allowing identification of biologically meaningful sites
11455 such as transcription factor binding sites (ChIP-seq) or regions of open
11456 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11458 (license license:gpl3+))))
11460 (define-public bismark
11467 (uri (git-reference
11468 (url "https://github.com/FelixKrueger/Bismark.git")
11470 (file-name (string-append name "-" version "-checkout"))
11473 "0xchm3rgilj6vfjnyzfzzymfd7djr64sbrmrvs3njbwi66jqbzw9"))))
11474 (build-system perl-build-system)
11476 `(#:tests? #f ; there are no tests
11477 #:modules ((guix build utils)
11480 (guix build perl-build-system))
11482 (modify-phases %standard-phases
11483 ;; The bundled plotly.js is minified.
11484 (add-after 'unpack 'replace-plotly.js
11485 (lambda* (#:key inputs #:allow-other-keys)
11486 (let* ((file (assoc-ref inputs "plotly.js"))
11487 (installed "plotly/plotly.js"))
11488 (let ((minified (open-pipe* OPEN_READ "uglify-js" file)))
11489 (call-with-output-file installed
11490 (cut dump-port minified <>))))
11492 (delete 'configure)
11495 (lambda* (#:key inputs outputs #:allow-other-keys)
11496 (let* ((out (assoc-ref outputs "out"))
11497 (bin (string-append out "/bin"))
11498 (share (string-append out "/share/bismark"))
11499 (docdir (string-append out "/share/doc/bismark"))
11500 (docs '("Docs/Bismark_User_Guide.html"))
11501 (scripts '("bismark"
11502 "bismark_genome_preparation"
11503 "bismark_methylation_extractor"
11506 "coverage2cytosine"
11507 "deduplicate_bismark"
11508 "filter_non_conversion"
11511 "NOMe_filtering")))
11512 (substitute* "bismark2report"
11513 (("\\$RealBin/plotly")
11514 (string-append share "/plotly")))
11518 (for-each (lambda (file) (install-file file bin))
11520 (for-each (lambda (file) (install-file file docdir))
11522 (copy-recursively "Docs/Images" (string-append docdir "/Images"))
11523 (copy-recursively "plotly"
11524 (string-append share "/plotly"))
11526 ;; Fix references to gunzip
11527 (substitute* (map (lambda (file)
11528 (string-append bin "/" file))
11531 (string-append "\"" (assoc-ref inputs "gzip")
11532 "/bin/gunzip -c")))
11536 ("perl-carp" ,perl-carp)
11537 ("perl-getopt-long" ,perl-getopt-long)))
11542 (uri (string-append "https://raw.githubusercontent.com/plotly/plotly.js/"
11543 "v1.39.4/dist/plotly.js"))
11545 (base32 "138mwsr4nf5qif4mrxx286mpnagxd1xwl6k8aidrjgknaqg88zyr"))))
11546 ("uglify-js" ,uglify-js)))
11547 (home-page "https://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11548 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11549 (description "Bismark is a program to map bisulfite treated sequencing
11550 reads to a genome of interest and perform methylation calls in a single step.
11551 The output can be easily imported into a genome viewer, such as SeqMonk, and
11552 enables a researcher to analyse the methylation levels of their samples
11553 straight away. Its main features are:
11556 @item Bisulfite mapping and methylation calling in one single step
11557 @item Supports single-end and paired-end read alignments
11558 @item Supports ungapped and gapped alignments
11559 @item Alignment seed length, number of mismatches etc are adjustable
11560 @item Output discriminates between cytosine methylation in CpG, CHG
11563 (license license:gpl3+)))
11565 (define-public paml
11571 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11572 "paml" version ".tgz"))
11575 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11576 (modules '((guix build utils)))
11577 ;; Remove Windows binaries
11580 (for-each delete-file (find-files "." "\\.exe$"))
11582 (build-system gnu-build-system)
11584 `(#:tests? #f ; there are no tests
11585 #:make-flags '("CC=gcc")
11587 (modify-phases %standard-phases
11588 (replace 'configure
11590 (substitute* "src/BFdriver.c"
11591 (("/bin/bash") (which "bash")))
11595 (lambda* (#:key outputs #:allow-other-keys)
11596 (let ((tools '("baseml" "basemlg" "codeml"
11597 "pamp" "evolver" "yn00" "chi2"))
11598 (bin (string-append (assoc-ref outputs "out") "/bin"))
11599 (docdir (string-append (assoc-ref outputs "out")
11600 "/share/doc/paml")))
11602 (for-each (lambda (file) (install-file file bin)) tools)
11603 (copy-recursively "../doc" docdir)
11605 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11606 (synopsis "Phylogentic analysis by maximum likelihood")
11607 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11608 contains a few programs for model fitting and phylogenetic tree reconstruction
11609 using nucleotide or amino-acid sequence data.")
11611 (license license:gpl3)))
11613 (define-public kallisto
11619 (uri (git-reference
11620 (url "https://github.com/pachterlab/kallisto.git")
11621 (commit (string-append "v" version))))
11622 (file-name (git-file-name name version))
11625 "0nj382jiywqnpgvyhichajpkkh5r0bapn43f4dx40zdaq5v4m40m"))))
11626 (build-system cmake-build-system)
11628 `(#:tests? #f ; no "check" target
11630 (modify-phases %standard-phases
11631 (add-after 'unpack 'do-not-use-bundled-htslib
11633 (substitute* "CMakeLists.txt"
11634 (("^ExternalProject_Add" m)
11635 (string-append "if (NEVER)\n" m))
11637 (string-append ")\nendif(NEVER)"))
11638 (("include_directories\\(\\$\\{htslib_PREFIX.*" m)
11639 (string-append "# " m)))
11640 (substitute* "src/CMakeLists.txt"
11641 (("target_link_libraries\\(kallisto kallisto_core pthread \
11642 \\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/../ext/htslib/libhts.a\\)")
11643 "target_link_libraries(kallisto kallisto_core pthread hts)")
11644 (("include_directories\\(\\.\\./ext/htslib\\)") ""))
11650 (home-page "https://pachterlab.github.io/kallisto/")
11651 (synopsis "Near-optimal RNA-Seq quantification")
11653 "Kallisto is a program for quantifying abundances of transcripts from
11654 RNA-Seq data, or more generally of target sequences using high-throughput
11655 sequencing reads. It is based on the novel idea of pseudoalignment for
11656 rapidly determining the compatibility of reads with targets, without the need
11657 for alignment. Pseudoalignment of reads preserves the key information needed
11658 for quantification, and kallisto is therefore not only fast, but also as
11659 accurate as existing quantification tools.")
11660 (license license:bsd-2)))
11662 (define-public libgff
11668 (uri (git-reference
11669 (url "https://github.com/Kingsford-Group/libgff.git")
11670 (commit (string-append "v" version))))
11671 (file-name (git-file-name name version))
11674 "0n6vfjnq7a2mianipscbshrvbncss8z4zkgkbjw754p9043nfkps"))))
11675 (build-system cmake-build-system)
11676 (arguments `(#:tests? #f)) ; no tests included
11677 (home-page "https://github.com/Kingsford-Group/libgff")
11678 (synopsis "Parser library for reading/writing GFF files")
11679 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11680 code that is used in the Cufflinks codebase. The goal of this library is to
11681 provide this functionality without the necessity of drawing in a heavy-weight
11682 dependency like SeqAn.")
11683 (license (license:x11-style "https://www.boost.org/LICENSE_1_0.txt"))))
11685 (define-public sailfish
11691 (uri (git-reference
11692 (url "https://github.com/kingsfordgroup/sailfish.git")
11693 (commit (string-append "v" version))))
11694 (file-name (git-file-name name version))
11697 "1amcc5hqvsl42hg4x19bi9vy47cl874s0lw1fmi0hwsdk9i8c03v"))
11698 (modules '((guix build utils)))
11701 ;; Delete bundled headers for eigen3.
11702 (delete-file-recursively "include/eigen3/")
11704 (build-system cmake-build-system)
11706 `(#:configure-flags
11707 (list (string-append "-DBOOST_INCLUDEDIR="
11708 (assoc-ref %build-inputs "boost")
11710 (string-append "-DBOOST_LIBRARYDIR="
11711 (assoc-ref %build-inputs "boost")
11713 (string-append "-DBoost_LIBRARIES="
11714 "-lboost_iostreams "
11715 "-lboost_filesystem "
11720 "-lboost_program_options")
11721 "-DBoost_FOUND=TRUE"
11722 ;; Don't download RapMap---we already have it!
11723 "-DFETCHED_RAPMAP=1")
11724 ;; Tests must be run after installation and the location of the test
11725 ;; data file must be overridden. But the tests fail. It looks like
11726 ;; they are not really meant to be run.
11729 (modify-phases %standard-phases
11730 ;; Boost cannot be found, even though it's right there.
11731 (add-after 'unpack 'do-not-look-for-boost
11732 (lambda* (#:key inputs #:allow-other-keys)
11733 (substitute* "CMakeLists.txt"
11734 (("find_package\\(Boost 1\\.53\\.0") "#"))
11736 (add-after 'unpack 'do-not-assign-to-macro
11738 (substitute* "include/spdlog/details/format.cc"
11739 (("const unsigned CHAR_WIDTH = 1;") ""))
11741 (add-after 'unpack 'prepare-rapmap
11742 (lambda* (#:key inputs #:allow-other-keys)
11743 (let ((src "external/install/src/rapmap/")
11744 (include "external/install/include/rapmap/")
11745 (rapmap (assoc-ref inputs "rapmap")))
11746 (mkdir-p "/tmp/rapmap")
11748 (assoc-ref inputs "rapmap")
11750 "--strip-components=1")
11753 (for-each (lambda (file)
11754 (install-file file src))
11755 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
11756 (copy-recursively "/tmp/rapmap/include" include))
11758 (add-after 'unpack 'use-system-libraries
11759 (lambda* (#:key inputs #:allow-other-keys)
11760 (substitute* '("src/SailfishIndexer.cpp"
11761 "src/SailfishUtils.cpp"
11762 "src/SailfishQuantify.cpp"
11763 "src/FASTAParser.cpp"
11765 "include/SailfishUtils.hpp"
11766 "include/SailfishIndex.hpp"
11767 "include/CollapsedEMOptimizer.hpp"
11768 "src/CollapsedEMOptimizer.cpp")
11769 (("#include \"jellyfish/config.h\"") ""))
11770 (substitute* "src/CMakeLists.txt"
11771 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11772 (string-append (assoc-ref inputs "jellyfish")
11773 "/include/jellyfish-" ,(package-version jellyfish)))
11774 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11775 (string-append (assoc-ref inputs "jellyfish")
11776 "/lib/libjellyfish-2.0.a"))
11777 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11778 (string-append (assoc-ref inputs "libdivsufsort")
11779 "/lib/libdivsufsort.so"))
11780 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11781 (string-append (assoc-ref inputs "libdivsufsort")
11782 "/lib/libdivsufsort64.so")))
11783 (substitute* "CMakeLists.txt"
11784 ;; Don't prefer static libs
11785 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11786 (("find_package\\(Jellyfish.*") "")
11787 (("ExternalProject_Add\\(libjellyfish") "message(")
11788 (("ExternalProject_Add\\(libgff") "message(")
11789 (("ExternalProject_Add\\(libsparsehash") "message(")
11790 (("ExternalProject_Add\\(libdivsufsort") "message("))
11792 ;; Ensure that Eigen headers can be found
11793 (setenv "CPLUS_INCLUDE_PATH"
11794 (string-append (assoc-ref inputs "eigen")
11795 "/include/eigen3"))
11800 ("jemalloc" ,jemalloc)
11801 ("jellyfish" ,jellyfish)
11802 ("sparsehash" ,sparsehash)
11805 (uri (git-reference
11806 (url "https://github.com/COMBINE-lab/RapMap.git")
11807 (commit (string-append "sf-v" version))))
11808 (file-name (string-append "rapmap-sf-v" version "-checkout"))
11811 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
11812 (modules '((guix build utils)))
11813 ;; These files are expected to be excluded.
11815 '(begin (delete-file-recursively "include/spdlog")
11816 (for-each delete-file '("include/xxhash.h"
11819 ("libdivsufsort" ,libdivsufsort)
11824 `(("pkg-config" ,pkg-config)))
11825 (home-page "https://www.cs.cmu.edu/~ckingsf/software/sailfish/")
11826 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
11827 (description "Sailfish is a tool for genomic transcript quantification
11828 from RNA-seq data. It requires a set of target transcripts (either from a
11829 reference or de-novo assembly) to quantify. All you need to run sailfish is a
11830 fasta file containing your reference transcripts and a (set of) fasta/fastq
11831 file(s) containing your reads.")
11832 (license license:gpl3+)))
11834 (define libstadenio-for-salmon
11836 (name "libstadenio")
11840 (uri (git-reference
11841 (url "https://github.com/COMBINE-lab/staden-io_lib.git")
11842 (commit (string-append "v" version))))
11843 (file-name (string-append name "-" version "-checkout"))
11846 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
11847 (build-system gnu-build-system)
11848 (arguments '(#:parallel-tests? #f)) ; not supported
11852 `(("perl" ,perl))) ; for tests
11853 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
11854 (synopsis "General purpose trace and experiment file library")
11855 (description "This package provides a library of file reading and writing
11856 code to provide a general purpose Trace file (and Experiment File) reading
11859 The following file formats are supported:
11862 @item SCF trace files
11863 @item ABI trace files
11864 @item ALF trace files
11865 @item ZTR trace files
11866 @item SFF trace archives
11867 @item SRF trace archives
11868 @item Experiment files
11869 @item Plain text files
11870 @item SAM/BAM sequence files
11871 @item CRAM sequence files
11873 (license license:bsd-3)))
11875 (define-public salmon
11881 (uri (git-reference
11882 (url "https://github.com/COMBINE-lab/salmon.git")
11883 (commit (string-append "v" version))))
11884 (file-name (git-file-name name version))
11887 "1i2z4aivicmiixdz9bxalp7vmfzi3k92fxa63iqa8kgvfw5a4aq5"))
11888 (modules '((guix build utils)))
11891 ;; Delete bundled headers for eigen3.
11892 (delete-file-recursively "include/eigen3/")
11894 (build-system cmake-build-system)
11896 `(#:configure-flags
11897 (list (string-append "-DBOOST_INCLUDEDIR="
11898 (assoc-ref %build-inputs "boost")
11900 (string-append "-DBOOST_LIBRARYDIR="
11901 (assoc-ref %build-inputs "boost")
11903 (string-append "-DBoost_LIBRARIES="
11904 "-lboost_iostreams "
11905 "-lboost_filesystem "
11910 "-lboost_program_options")
11911 "-DBoost_FOUND=TRUE"
11912 "-DTBB_LIBRARIES=tbb tbbmalloc"
11913 ;; Don't download RapMap---we already have it!
11914 "-DFETCHED_RAPMAP=1")
11916 (modify-phases %standard-phases
11917 ;; Boost cannot be found, even though it's right there.
11918 (add-after 'unpack 'do-not-look-for-boost
11919 (lambda* (#:key inputs #:allow-other-keys)
11920 (substitute* "CMakeLists.txt"
11921 (("find_package\\(Boost 1\\.59\\.0") "#"))
11923 (add-after 'unpack 'do-not-phone-home
11925 (substitute* "src/Salmon.cpp"
11926 (("getVersionMessage\\(\\)") "\"\""))
11928 (add-after 'unpack 'prepare-rapmap
11929 (lambda* (#:key inputs #:allow-other-keys)
11930 (let ((src "external/install/src/rapmap/")
11931 (include "external/install/include/rapmap/")
11932 (rapmap (assoc-ref inputs "rapmap")))
11935 (copy-recursively (string-append rapmap "/src") src)
11936 (copy-recursively (string-append rapmap "/include") include)
11937 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
11938 "external/install/include/rapmap/FastxParser.hpp"
11939 "external/install/include/rapmap/concurrentqueue.h"
11940 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
11941 "external/install/src/rapmap/FastxParser.cpp"
11942 "external/install/src/rapmap/xxhash.c"))
11943 (delete-file-recursively "external/install/include/rapmap/spdlog"))
11945 (add-after 'unpack 'use-system-libraries
11946 (lambda* (#:key inputs #:allow-other-keys)
11947 (substitute* "CMakeLists.txt"
11948 ;; Don't prefer static libs
11949 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11950 (("set\\(TBB_LIBRARIES") "message(")
11951 ;; Don't download anything
11952 (("DOWNLOAD_COMMAND") "DOWNLOAD_COMMAND echo")
11953 (("externalproject_add\\(libcereal") "message(")
11954 (("externalproject_add\\(libgff") "message(")
11955 (("externalproject_add\\(libtbb") "message(")
11956 (("externalproject_add\\(libdivsufsort") "message(")
11957 (("externalproject_add\\(libstadenio") "message(")
11958 (("externalproject_add_step\\(") "message("))
11959 (substitute* "src/CMakeLists.txt"
11960 (("add_dependencies") "#")
11961 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
11962 (string-append (assoc-ref inputs "libstadenio-for-salmon")
11963 "/lib/libstaden-read.so"))
11964 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11965 (string-append (assoc-ref inputs "libdivsufsort")
11966 "/lib/libdivsufsort.so"))
11967 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11968 (string-append (assoc-ref inputs "libdivsufsort")
11969 "/lib/libdivsufsort64.so"))
11970 (("lib/libdivsufsort.a") "/lib/libdivsufsort.so"))
11972 ;; Ensure that all headers can be found
11974 (string-append (getenv "CPATH")
11976 (assoc-ref inputs "eigen")
11977 "/include/eigen3"))
11979 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
11980 ;; run. It only exists after the install phase.
11981 (add-after 'unpack 'fix-tests
11983 (substitute* "src/CMakeLists.txt"
11984 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
11985 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
11994 (uri (git-reference
11995 (url "https://github.com/COMBINE-lab/RapMap.git")
11996 (commit (string-append "salmon-v" version))))
11997 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
12000 "1biplxf0csc7a8h1wf219b0vmjkvw6wk2zylhdklb577kgmihdms"))))
12001 ("jemalloc" ,jemalloc)
12004 ("libdivsufsort" ,libdivsufsort)
12005 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
12009 `(("pkg-config" ,pkg-config)))
12010 (home-page "https://github.com/COMBINE-lab/salmon")
12011 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
12012 (description "Salmon is a program to produce highly-accurate,
12013 transcript-level quantification estimates from RNA-seq data. Salmon achieves
12014 its accuracy and speed via a number of different innovations, including the
12015 use of lightweight alignments (accurate but fast-to-compute proxies for
12016 traditional read alignments) and massively-parallel stochastic collapsed
12017 variational inference.")
12018 (license license:gpl3+)))
12020 (define-public python-loompy
12022 (name "python-loompy")
12024 ;; The tarball on Pypi does not include the tests.
12027 (uri (git-reference
12028 (url "https://github.com/linnarsson-lab/loompy.git")
12030 (file-name (git-file-name name version))
12033 "12a5kjgiikapv93wahfw0frszx1lblnppyz3vs5gy8fgmgngra07"))))
12034 (build-system python-build-system)
12037 (modify-phases %standard-phases
12040 (setenv "PYTHONPATH"
12041 (string-append (getcwd) ":"
12042 (getenv "PYTHONPATH")))
12043 (invoke "pytest" "tests")
12046 `(("python-h5py" ,python-h5py)
12047 ("python-numpy" ,python-numpy)
12048 ("python-pandas" ,python-pandas)
12049 ("python-scipy" ,python-scipy)))
12051 `(("python-pytest" ,python-pytest)))
12052 (home-page "https://github.com/linnarsson-lab/loompy")
12053 (synopsis "Work with .loom files for single-cell RNA-seq data")
12054 (description "The loom file format is an efficient format for very large
12055 omics datasets, consisting of a main matrix, optional additional layers, a
12056 variable number of row and column annotations. Loom also supports sparse
12057 graphs. This library makes it easy to work with @file{.loom} files for
12058 single-cell RNA-seq data.")
12059 (license license:bsd-3)))
12061 ;; We cannot use the latest commit because it requires Java 9.
12062 (define-public java-forester
12063 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
12066 (name "java-forester")
12067 (version (string-append "0-" revision "." (string-take commit 7)))
12070 (uri (git-reference
12071 (url "https://github.com/cmzmasek/forester.git")
12073 (file-name (string-append name "-" version "-checkout"))
12076 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12077 (modules '((guix build utils)))
12080 ;; Delete bundled jars and pre-built classes
12081 (delete-file-recursively "forester/java/resources")
12082 (delete-file-recursively "forester/java/classes")
12083 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12084 ;; Delete bundled applications
12085 (delete-file-recursively "forester_applications")
12087 (build-system ant-build-system)
12089 `(#:tests? #f ; there are none
12091 #:modules ((guix build ant-build-system)
12093 (guix build java-utils)
12097 (modify-phases %standard-phases
12098 (add-after 'unpack 'chdir
12099 (lambda _ (chdir "forester/java") #t))
12100 (add-after 'chdir 'fix-dependencies
12102 (chmod "build.xml" #o664)
12103 (call-with-output-file "build.xml.new"
12107 (with-input-from-file "build.xml"
12108 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12109 `(;; Remove all unjar tags to avoid repacking classes.
12110 (unjar . ,(lambda _ '()))
12111 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12112 (*text* . ,(lambda (_ txt) txt))))
12114 (rename-file "build.xml.new" "build.xml")
12116 ;; FIXME: itext is difficult to package as it depends on a few
12117 ;; unpackaged libraries.
12118 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12120 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12121 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12122 (("pdf_written_to = PdfExporter.*")
12123 "throw new IOException(\"PDF export is not available.\");"))
12125 ;; There is no install target
12126 (replace 'install (install-jars ".")))))
12128 `(("java-commons-codec" ,java-commons-codec)
12129 ("java-openchart2" ,java-openchart2)))
12130 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12131 (synopsis "Phylogenomics libraries for Java")
12132 (description "Forester is a collection of Java libraries for
12133 phylogenomics and evolutionary biology research. It includes support for
12134 reading, writing, and exporting phylogenetic trees.")
12135 (license license:lgpl2.1+))))
12137 (define-public java-forester-1.005
12139 (name "java-forester")
12143 (uri (string-append "http://search.maven.org/remotecontent?"
12144 "filepath=org/biojava/thirdparty/forester/"
12145 version "/forester-" version "-sources.jar"))
12146 (file-name (string-append name "-" version ".jar"))
12149 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12150 (build-system ant-build-system)
12152 `(#:tests? #f ; there are none
12154 #:modules ((guix build ant-build-system)
12156 (guix build java-utils)
12160 (modify-phases %standard-phases
12161 (add-after 'unpack 'fix-dependencies
12162 (lambda* (#:key inputs #:allow-other-keys)
12163 (call-with-output-file "build.xml"
12167 (with-input-from-file "src/build.xml"
12168 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12169 `(;; Remove all unjar tags to avoid repacking classes.
12170 (unjar . ,(lambda _ '()))
12171 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12172 (*text* . ,(lambda (_ txt) txt))))
12174 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12175 "synth_look_and_feel_1.xml")
12176 (copy-file (assoc-ref inputs "phyloxml.xsd")
12178 (substitute* "build.xml"
12179 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12180 "synth_look_and_feel_1.xml")
12181 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12184 ;; FIXME: itext is difficult to package as it depends on a few
12185 ;; unpackaged libraries.
12186 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12188 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12189 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12190 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12191 (("pdf_written_to = PdfExporter.*")
12192 "throw new IOException(\"PDF export is not available.\"); /*")
12193 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12194 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12196 (add-after 'unpack 'delete-pre-built-classes
12197 (lambda _ (delete-file-recursively "src/classes") #t))
12198 ;; There is no install target
12199 (replace 'install (install-jars ".")))))
12201 `(("java-commons-codec" ,java-commons-codec)
12202 ("java-openchart2" ,java-openchart2)))
12203 ;; The source archive does not contain the resources.
12208 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12209 "b61cc2dcede0bede317db362472333115756b8c6/"
12210 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12211 (file-name (string-append name "-phyloxml-" version ".xsd"))
12214 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12215 ("synth_look_and_feel_1.xml"
12218 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12219 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12220 "forester/java/classes/resources/synth_look_and_feel_1.xml"))
12221 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12224 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12225 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12226 (synopsis "Phylogenomics libraries for Java")
12227 (description "Forester is a collection of Java libraries for
12228 phylogenomics and evolutionary biology research. It includes support for
12229 reading, writing, and exporting phylogenetic trees.")
12230 (license license:lgpl2.1+)))
12232 (define-public java-biojava-core
12234 (name "java-biojava-core")
12238 (uri (git-reference
12239 (url "https://github.com/biojava/biojava")
12240 (commit (string-append "biojava-" version))))
12241 (file-name (string-append name "-" version "-checkout"))
12244 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12245 (build-system ant-build-system)
12248 #:jar-name "biojava-core.jar"
12249 #:source-dir "biojava-core/src/main/java/"
12250 #:test-dir "biojava-core/src/test"
12251 ;; These tests seem to require internet access.
12252 #:test-exclude (list "**/SearchIOTest.java"
12253 "**/BlastXMLParserTest.java"
12254 "**/GenbankCookbookTest.java"
12255 "**/GenbankProxySequenceReaderTest.java")
12257 (modify-phases %standard-phases
12258 (add-before 'build 'copy-resources
12260 (copy-recursively "biojava-core/src/main/resources"
12263 (add-before 'check 'copy-test-resources
12265 (copy-recursively "biojava-core/src/test/resources"
12266 "build/test-classes")
12269 `(("java-log4j-api" ,java-log4j-api)
12270 ("java-log4j-core" ,java-log4j-core)
12271 ("java-slf4j-api" ,java-slf4j-api)
12272 ("java-slf4j-simple" ,java-slf4j-simple)))
12274 `(("java-junit" ,java-junit)
12275 ("java-hamcrest-core" ,java-hamcrest-core)))
12276 (home-page "http://biojava.org")
12277 (synopsis "Core libraries of Java framework for processing biological data")
12278 (description "BioJava is a project dedicated to providing a Java framework
12279 for processing biological data. It provides analytical and statistical
12280 routines, parsers for common file formats, reference implementations of
12281 popular algorithms, and allows the manipulation of sequences and 3D
12282 structures. The goal of the biojava project is to facilitate rapid
12283 application development for bioinformatics.
12285 This package provides the core libraries.")
12286 (license license:lgpl2.1+)))
12288 (define-public java-biojava-phylo
12289 (package (inherit java-biojava-core)
12290 (name "java-biojava-phylo")
12291 (build-system ant-build-system)
12294 #:jar-name "biojava-phylo.jar"
12295 #:source-dir "biojava-phylo/src/main/java/"
12296 #:test-dir "biojava-phylo/src/test"
12298 (modify-phases %standard-phases
12299 (add-before 'build 'copy-resources
12301 (copy-recursively "biojava-phylo/src/main/resources"
12304 (add-before 'check 'copy-test-resources
12306 (copy-recursively "biojava-phylo/src/test/resources"
12307 "build/test-classes")
12310 `(("java-log4j-api" ,java-log4j-api)
12311 ("java-log4j-core" ,java-log4j-core)
12312 ("java-slf4j-api" ,java-slf4j-api)
12313 ("java-slf4j-simple" ,java-slf4j-simple)
12314 ("java-biojava-core" ,java-biojava-core)
12315 ("java-forester" ,java-forester)))
12317 `(("java-junit" ,java-junit)
12318 ("java-hamcrest-core" ,java-hamcrest-core)))
12319 (home-page "http://biojava.org")
12320 (synopsis "Biojava interface to the forester phylogenomics library")
12321 (description "The phylo module provides a biojava interface layer to the
12322 forester phylogenomics library for constructing phylogenetic trees.")))
12324 (define-public java-biojava-alignment
12325 (package (inherit java-biojava-core)
12326 (name "java-biojava-alignment")
12327 (build-system ant-build-system)
12330 #:jar-name "biojava-alignment.jar"
12331 #:source-dir "biojava-alignment/src/main/java/"
12332 #:test-dir "biojava-alignment/src/test"
12334 (modify-phases %standard-phases
12335 (add-before 'build 'copy-resources
12337 (copy-recursively "biojava-alignment/src/main/resources"
12340 (add-before 'check 'copy-test-resources
12342 (copy-recursively "biojava-alignment/src/test/resources"
12343 "build/test-classes")
12346 `(("java-log4j-api" ,java-log4j-api)
12347 ("java-log4j-core" ,java-log4j-core)
12348 ("java-slf4j-api" ,java-slf4j-api)
12349 ("java-slf4j-simple" ,java-slf4j-simple)
12350 ("java-biojava-core" ,java-biojava-core)
12351 ("java-biojava-phylo" ,java-biojava-phylo)
12352 ("java-forester" ,java-forester)))
12354 `(("java-junit" ,java-junit)
12355 ("java-hamcrest-core" ,java-hamcrest-core)))
12356 (home-page "http://biojava.org")
12357 (synopsis "Biojava API for genetic sequence alignment")
12358 (description "The alignment module of BioJava provides an API that
12362 @item implementations of dynamic programming algorithms for sequence
12364 @item reading and writing of popular alignment file formats;
12365 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12368 (define-public java-biojava-core-4.0
12369 (package (inherit java-biojava-core)
12370 (name "java-biojava-core")
12374 (uri (git-reference
12375 (url "https://github.com/biojava/biojava")
12376 (commit (string-append "biojava-" version))))
12377 (file-name (string-append name "-" version "-checkout"))
12380 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12382 (define-public java-biojava-phylo-4.0
12383 (package (inherit java-biojava-core-4.0)
12384 (name "java-biojava-phylo")
12385 (build-system ant-build-system)
12388 #:jar-name "biojava-phylo.jar"
12389 #:source-dir "biojava-phylo/src/main/java/"
12390 #:test-dir "biojava-phylo/src/test"
12392 (modify-phases %standard-phases
12393 (add-before 'build 'copy-resources
12395 (copy-recursively "biojava-phylo/src/main/resources"
12398 (add-before 'check 'copy-test-resources
12400 (copy-recursively "biojava-phylo/src/test/resources"
12401 "build/test-classes")
12404 `(("java-log4j-api" ,java-log4j-api)
12405 ("java-log4j-core" ,java-log4j-core)
12406 ("java-slf4j-api" ,java-slf4j-api)
12407 ("java-slf4j-simple" ,java-slf4j-simple)
12408 ("java-biojava-core" ,java-biojava-core-4.0)
12409 ("java-forester" ,java-forester-1.005)))
12411 `(("java-junit" ,java-junit)
12412 ("java-hamcrest-core" ,java-hamcrest-core)))
12413 (home-page "http://biojava.org")
12414 (synopsis "Biojava interface to the forester phylogenomics library")
12415 (description "The phylo module provides a biojava interface layer to the
12416 forester phylogenomics library for constructing phylogenetic trees.")))
12418 (define-public java-biojava-alignment-4.0
12419 (package (inherit java-biojava-core-4.0)
12420 (name "java-biojava-alignment")
12421 (build-system ant-build-system)
12424 #:jar-name "biojava-alignment.jar"
12425 #:source-dir "biojava-alignment/src/main/java/"
12426 #:test-dir "biojava-alignment/src/test"
12428 (modify-phases %standard-phases
12429 (add-before 'build 'copy-resources
12431 (copy-recursively "biojava-alignment/src/main/resources"
12434 (add-before 'check 'copy-test-resources
12436 (copy-recursively "biojava-alignment/src/test/resources"
12437 "build/test-classes")
12440 `(("java-log4j-api" ,java-log4j-api)
12441 ("java-log4j-core" ,java-log4j-core)
12442 ("java-slf4j-api" ,java-slf4j-api)
12443 ("java-slf4j-simple" ,java-slf4j-simple)
12444 ("java-biojava-core" ,java-biojava-core-4.0)
12445 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12446 ("java-forester" ,java-forester-1.005)))
12448 `(("java-junit" ,java-junit)
12449 ("java-hamcrest-core" ,java-hamcrest-core)))
12450 (home-page "http://biojava.org")
12451 (synopsis "Biojava API for genetic sequence alignment")
12452 (description "The alignment module of BioJava provides an API that
12456 @item implementations of dynamic programming algorithms for sequence
12458 @item reading and writing of popular alignment file formats;
12459 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12462 (define-public dropseq-tools
12464 (name "dropseq-tools")
12469 (uri "http://mccarrolllab.com/download/1276/")
12470 (file-name (string-append "dropseq-tools-" version ".zip"))
12473 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12474 ;; Delete bundled libraries
12475 (modules '((guix build utils)))
12478 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12479 (delete-file-recursively "3rdParty")
12481 (build-system ant-build-system)
12483 `(#:tests? #f ; test data are not included
12484 #:test-target "test"
12485 #:build-target "all"
12486 #:source-dir "public/src/"
12489 (list (string-append "-Dpicard.executable.dir="
12490 (assoc-ref %build-inputs "java-picard")
12492 #:modules ((ice-9 match)
12495 (guix build java-utils)
12496 (guix build ant-build-system))
12498 (modify-phases %standard-phases
12499 ;; FIXME: fails with "java.io.FileNotFoundException:
12500 ;; /gnu/store/…-dropseq-tools-1.13/share/java/lib/biojava-alignment.jar"
12501 (delete 'generate-jar-indices)
12502 ;; All dependencies must be linked to "lib", because that's where
12503 ;; they will be searched for when the Class-Path property of the
12504 ;; manifest is computed.
12505 (add-after 'unpack 'record-references
12506 (lambda* (#:key inputs #:allow-other-keys)
12507 (mkdir-p "jar/lib")
12508 (let ((dirs (filter-map (match-lambda
12510 (if (and (string-prefix? "java-" name)
12511 (not (string=? name "java-testng")))
12514 (for-each (lambda (jar)
12515 (symlink jar (string-append "jar/lib/" (basename jar))))
12516 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12519 ;; There is no installation target
12521 (lambda* (#:key inputs outputs #:allow-other-keys)
12522 (let* ((out (assoc-ref outputs "out"))
12523 (bin (string-append out "/bin"))
12524 (share (string-append out "/share/java/"))
12525 (lib (string-append share "/lib/"))
12526 (scripts (list "BAMTagHistogram"
12527 "BAMTagofTagCounts"
12528 "BaseDistributionAtReadPosition"
12529 "CollapseBarcodesInPlace"
12530 "CollapseTagWithContext"
12532 "CreateIntervalsFiles"
12533 "DetectBeadSynthesisErrors"
12534 "DigitalExpression"
12535 "Drop-seq_alignment.sh"
12538 "GatherGeneGCLength"
12539 "GatherMolecularBarcodeDistributionByGene"
12540 "GatherReadQualityMetrics"
12543 "SelectCellsByNumTranscripts"
12544 "SingleCellRnaSeqMetricsCollector"
12545 "TagBamWithReadSequenceExtended"
12546 "TagReadWithGeneExon"
12547 "TagReadWithInterval"
12548 "TrimStartingSequence"
12549 "ValidateReference")))
12550 (for-each mkdir-p (list bin share lib))
12551 (install-file "dist/dropseq.jar" share)
12552 (for-each (lambda (script)
12553 (chmod script #o555)
12554 (install-file script bin))
12556 (substitute* (map (lambda (script)
12557 (string-append bin "/" script))
12559 (("^java") (which "java"))
12560 (("jar_deploy_dir=.*")
12561 (string-append "jar_deploy_dir=" share "\n"))))
12563 ;; FIXME: We do this after stripping jars because we don't want it to
12564 ;; copy all these jars and strip them. We only want to install
12565 ;; links. Arguably, this is a problem with the ant-build-system.
12566 (add-after 'strip-jar-timestamps 'install-links
12567 (lambda* (#:key outputs #:allow-other-keys)
12568 (let* ((out (assoc-ref outputs "out"))
12569 (share (string-append out "/share/java/"))
12570 (lib (string-append share "/lib/")))
12571 (for-each (lambda (jar)
12572 (symlink (readlink jar)
12573 (string-append lib (basename jar))))
12574 (find-files "jar/lib" "\\.jar$")))
12577 `(("jdk" ,icedtea-8)
12578 ("java-picard" ,java-picard-2.10.3)
12579 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12580 ("java-commons-math3" ,java-commons-math3)
12581 ("java-commons-jexl2" ,java-commons-jexl-2)
12582 ("java-commons-collections4" ,java-commons-collections4)
12583 ("java-commons-lang2" ,java-commons-lang)
12584 ("java-commons-io" ,java-commons-io)
12585 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12586 ("java-guava" ,java-guava)
12587 ("java-la4j" ,java-la4j)
12588 ("java-biojava-core" ,java-biojava-core-4.0)
12589 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12590 ("java-jdistlib" ,java-jdistlib)
12591 ("java-simple-xml" ,java-simple-xml)
12592 ("java-snakeyaml" ,java-snakeyaml)))
12595 ("java-testng" ,java-testng)))
12596 (home-page "http://mccarrolllab.com/dropseq/")
12597 (synopsis "Tools for Drop-seq analyses")
12598 (description "Drop-seq is a technology to enable biologists to
12599 analyze RNA expression genome-wide in thousands of individual cells at
12600 once. This package provides tools to perform Drop-seq analyses.")
12601 (license license:expat)))
12603 (define-public pigx-rnaseq
12605 (name "pigx-rnaseq")
12609 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12610 "releases/download/v" version
12611 "/pigx_rnaseq-" version ".tar.gz"))
12614 "0z3hr120wk2vrlmlpz1vp3n9wy3rq4y2mnzh2vf08qgqn2xfdwcw"))))
12615 (build-system gnu-build-system)
12617 `(#:parallel-tests? #f ; not supported
12619 (modify-phases %standard-phases
12620 ;; "test.sh" runs STAR, which requires excessive amounts of memory.
12621 (add-after 'unpack 'disable-resource-intensive-test
12623 (substitute* "Makefile.in"
12624 (("(^ tests/test_trim_galore/test.sh).*" _ m) m)
12625 (("^ tests/test_multiqc/test.sh") "")
12626 (("^ test.sh") ""))
12629 `(("coreutils" ,coreutils)
12632 ("snakemake" ,snakemake)
12634 ("multiqc" ,multiqc)
12636 ("trim-galore" ,trim-galore)
12638 ("samtools" ,samtools)
12639 ("r-minimal" ,r-minimal)
12640 ("r-rmarkdown" ,r-rmarkdown)
12641 ("r-ggplot2" ,r-ggplot2)
12642 ("r-ggrepel" ,r-ggrepel)
12643 ("r-gprofiler" ,r-gprofiler)
12644 ("r-deseq2" ,r-deseq2)
12646 ("r-knitr" ,r-knitr)
12647 ("r-pheatmap" ,r-pheatmap)
12648 ("r-corrplot" ,r-corrplot)
12649 ("r-reshape2" ,r-reshape2)
12650 ("r-plotly" ,r-plotly)
12651 ("r-scales" ,r-scales)
12652 ("r-summarizedexperiment" ,r-summarizedexperiment)
12653 ("r-crosstalk" ,r-crosstalk)
12654 ("r-tximport" ,r-tximport)
12655 ("r-rtracklayer" ,r-rtracklayer)
12656 ("r-rjson" ,r-rjson)
12658 ("ghc-pandoc" ,ghc-pandoc)
12659 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12660 ("python-wrapper" ,python-wrapper)
12661 ("python-pyyaml" ,python-pyyaml)))
12662 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12663 (synopsis "Analysis pipeline for RNA sequencing experiments")
12664 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
12665 reporting for RNA sequencing experiments. It is easy to use and produces high
12666 quality reports. The inputs are reads files from the sequencing experiment,
12667 and a configuration file which describes the experiment. In addition to
12668 quality control of the experiment, the pipeline produces a differential
12669 expression report comparing samples in an easily configurable manner.")
12670 (license license:gpl3+)))
12672 (define-public pigx-chipseq
12674 (name "pigx-chipseq")
12678 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
12679 "releases/download/v" version
12680 "/pigx_chipseq-" version ".tar.gz"))
12683 "0akbxdmsjsq5fzbwaap04hqjpsfgv1l6yrc2pwgbya1xgqvcq6vy"))))
12684 (build-system gnu-build-system)
12685 ;; parts of the tests rely on access to the network
12686 (arguments '(#:tests? #f))
12689 ("coreutils" ,coreutils)
12690 ("r-minimal" ,r-minimal)
12691 ("r-argparser" ,r-argparser)
12692 ("r-biocparallel" ,r-biocparallel)
12693 ("r-biostrings" ,r-biostrings)
12694 ("r-chipseq" ,r-chipseq)
12695 ("r-data-table" ,r-data-table)
12696 ("r-dplyr" ,r-dplyr)
12697 ("r-genomation" ,r-genomation)
12698 ("r-genomicalignments" ,r-genomicalignments)
12699 ("r-genomicranges" ,r-genomicranges)
12700 ("r-rsamtools" ,r-rsamtools)
12701 ("r-rtracklayer" ,r-rtracklayer)
12702 ("r-s4vectors" ,r-s4vectors)
12703 ("r-stringr" ,r-stringr)
12704 ("r-tibble" ,r-tibble)
12705 ("r-tidyr" ,r-tidyr)
12706 ("r-jsonlite" ,r-jsonlite)
12707 ("r-heatmaply" ,r-heatmaply)
12708 ("r-htmlwidgets" ,r-htmlwidgets)
12709 ("r-ggplot2" ,r-ggplot2)
12710 ("r-plotly" ,r-plotly)
12711 ("r-rmarkdown" ,r-rmarkdown)
12712 ("python-wrapper" ,python-wrapper)
12713 ("python-pyyaml" ,python-pyyaml)
12714 ("python-magic" ,python-magic)
12715 ("python-xlrd" ,python-xlrd)
12716 ("trim-galore" ,trim-galore)
12718 ("multiqc" ,multiqc)
12720 ("ghc-pandoc" ,ghc-pandoc)
12721 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12725 ("snakemake" ,snakemake)
12726 ("samtools" ,samtools)
12727 ("bedtools" ,bedtools)
12728 ("kentutils" ,kentutils)))
12730 `(("python-pytest" ,python-pytest)))
12731 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12732 (synopsis "Analysis pipeline for ChIP sequencing experiments")
12733 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
12734 calling and reporting for ChIP sequencing experiments. It is easy to use and
12735 produces high quality reports. The inputs are reads files from the sequencing
12736 experiment, and a configuration file which describes the experiment. In
12737 addition to quality control of the experiment, the pipeline enables to set up
12738 multiple peak calling analysis and allows the generation of a UCSC track hub
12739 in an easily configurable manner.")
12740 (license license:gpl3+)))
12742 (define-public pigx-bsseq
12744 (name "pigx-bsseq")
12748 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
12749 "releases/download/v" version
12750 "/pigx_bsseq-" version ".tar.gz"))
12753 "0l97wvkq4diq8lcarraj33bby1zzf0w804jwi8mlc5qddp8idwhy"))))
12754 (build-system gnu-build-system)
12757 (modify-phases %standard-phases
12758 (add-before 'check 'set-timezone
12759 ;; The readr package is picky about timezones.
12760 (lambda* (#:key inputs #:allow-other-keys)
12761 (setenv "TZ" "UTC+1")
12763 (string-append (assoc-ref inputs "tzdata")
12764 "/share/zoneinfo"))
12767 `(("tzdata" ,tzdata)))
12769 `(("coreutils" ,coreutils)
12772 ("r-minimal" ,r-minimal)
12773 ("r-annotationhub" ,r-annotationhub)
12775 ("r-genomation" ,r-genomation)
12776 ("r-methylkit" ,r-methylkit)
12777 ("r-rtracklayer" ,r-rtracklayer)
12778 ("r-rmarkdown" ,r-rmarkdown)
12779 ("r-bookdown" ,r-bookdown)
12780 ("r-ggplot2" ,r-ggplot2)
12781 ("r-ggbio" ,r-ggbio)
12782 ("ghc-pandoc" ,ghc-pandoc)
12783 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12784 ("python-wrapper" ,python-wrapper)
12785 ("python-pyyaml" ,python-pyyaml)
12786 ("snakemake" ,snakemake)
12787 ("bismark" ,bismark)
12790 ("trim-galore" ,trim-galore)
12791 ("cutadapt" ,cutadapt)
12792 ("samtools" ,samtools)))
12793 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12794 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
12795 (description "PiGx BSseq is a data processing pipeline for raw fastq read
12796 data of bisulfite experiments; it produces reports on aggregate methylation
12797 and coverage and can be used to produce information on differential
12798 methylation and segmentation.")
12799 (license license:gpl3+)))
12801 (define-public pigx-scrnaseq
12803 (name "pigx-scrnaseq")
12807 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/"
12808 "releases/download/v" version
12809 "/pigx_scrnaseq-" version ".tar.gz"))
12812 "0ga2jr4968qzwml6aycky4603q64lny3y7lzw6dmafch5pydl1qi"))))
12813 (build-system gnu-build-system)
12815 `(("coreutils" ,coreutils)
12818 ("flexbar" ,flexbar)
12819 ("java" ,icedtea-8)
12820 ("jellyfish" ,jellyfish)
12821 ("python-wrapper" ,python-wrapper)
12822 ("python-pyyaml" ,python-pyyaml)
12823 ("python-pandas" ,python-pandas)
12824 ("python-magic" ,python-magic)
12825 ("python-numpy" ,python-numpy)
12826 ("python-loompy" ,python-loompy)
12827 ("ghc-pandoc" ,ghc-pandoc)
12828 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12829 ("samtools" ,samtools)
12830 ("snakemake" ,snakemake)
12832 ("r-minimal" ,r-minimal)
12833 ("r-argparser" ,r-argparser)
12834 ("r-cowplot" ,r-cowplot)
12835 ("r-data-table" ,r-data-table)
12836 ("r-delayedarray" ,r-delayedarray)
12837 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
12838 ("r-dplyr" ,r-dplyr)
12839 ("r-dropbead" ,r-dropbead)
12841 ("r-genomicalignments" ,r-genomicalignments)
12842 ("r-genomicfiles" ,r-genomicfiles)
12843 ("r-genomicranges" ,r-genomicranges)
12844 ("r-ggplot2" ,r-ggplot2)
12845 ("r-hdf5array" ,r-hdf5array)
12846 ("r-pheatmap" ,r-pheatmap)
12847 ("r-rmarkdown" ,r-rmarkdown)
12848 ("r-rsamtools" ,r-rsamtools)
12849 ("r-rtracklayer" ,r-rtracklayer)
12850 ("r-rtsne" ,r-rtsne)
12851 ("r-scater" ,r-scater)
12852 ("r-scran" ,r-scran)
12853 ("r-seurat" ,r-seurat)
12854 ("r-singlecellexperiment" ,r-singlecellexperiment)
12855 ("r-stringr" ,r-stringr)
12856 ("r-yaml" ,r-yaml)))
12857 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12858 (synopsis "Analysis pipeline for single-cell RNA sequencing experiments")
12859 (description "PiGX scRNAseq is an analysis pipeline for preprocessing and
12860 quality control for single cell RNA sequencing experiments. The inputs are
12861 read files from the sequencing experiment, and a configuration file which
12862 describes the experiment. It produces processed files for downstream analysis
12863 and interactive quality reports. The pipeline is designed to work with UMI
12865 (license license:gpl3+)))
12867 (define-public pigx
12873 (uri (string-append "https://github.com/BIMSBbioinfo/pigx/"
12874 "releases/download/v" version
12875 "/pigx-" version ".tar.gz"))
12878 "1i5njdy1clj5ncw45d16p7mwmqvb1ilikl9n797pxklc3f4s7mq7"))))
12879 (build-system gnu-build-system)
12881 `(("python" ,python)
12882 ("pigx-bsseq" ,pigx-bsseq)
12883 ("pigx-chipseq" ,pigx-chipseq)
12884 ("pigx-rnaseq" ,pigx-rnaseq)
12885 ("pigx-scrnaseq" ,pigx-scrnaseq)))
12886 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12887 (synopsis "Analysis pipelines for genomics")
12888 (description "PiGx is a collection of genomics pipelines. It includes the
12889 following pipelines:
12892 @item PiGx BSseq for raw fastq read data of bisulfite experiments
12893 @item PiGx RNAseq for RNAseq samples
12894 @item PiGx scRNAseq for single cell dropseq analysis
12895 @item PiGx ChIPseq for reads from ChIPseq experiments
12898 All pipelines are easily configured with a simple sample sheet and a
12899 descriptive settings file. The result is a set of comprehensive, interactive
12900 HTML reports with interesting findings about your samples.")
12901 (license license:gpl3+)))
12903 (define-public genrich
12909 (uri (git-reference
12910 (url "https://github.com/jsh58/Genrich.git")
12911 (commit (string-append "v" version))))
12912 (file-name (git-file-name name version))
12915 "0x0q6z0208n3cxzqjla4rgjqpyqgwpmz27852lcvzkzaigymq4zp"))))
12916 (build-system gnu-build-system)
12918 `(#:tests? #f ; there are none
12920 (modify-phases %standard-phases
12921 (delete 'configure)
12923 (lambda* (#:key outputs #:allow-other-keys)
12924 (install-file "Genrich" (string-append (assoc-ref outputs "out") "/bin"))
12928 (home-page "https://github.com/jsh58/Genrich")
12929 (synopsis "Detecting sites of genomic enrichment")
12930 (description "Genrich is a peak-caller for genomic enrichment
12931 assays (e.g. ChIP-seq, ATAC-seq). It analyzes alignment files generated
12932 following the assay and produces a file detailing peaks of significant
12934 (license license:expat)))
12936 (define-public mantis
12937 (let ((commit "4ffd171632c2cb0056a86d709dfd2bf21bc69b84")
12941 (version (git-version "0" revision commit))
12944 (uri (git-reference
12945 (url "https://github.com/splatlab/mantis.git")
12947 (file-name (git-file-name name version))
12950 "0iqbr0dhmlc8mzpirmm2s4pkzkwdgrcx50yx6cv3wlr2qi064p55"))))
12951 (build-system cmake-build-system)
12952 (arguments '(#:tests? #f)) ; there are none
12954 `(("sdsl-lite" ,sdsl-lite)
12955 ("openssl" ,openssl)
12957 (home-page "https://github.com/splatlab/mantis")
12958 (synopsis "Large-scale sequence-search index data structure")
12959 (description "Mantis is a space-efficient data structure that can be
12960 used to index thousands of raw-read genomics experiments and facilitate
12961 large-scale sequence searches on those experiments. Mantis uses counting
12962 quotient filters instead of Bloom filters, enabling rapid index builds and
12963 queries, small indexes, and exact results, i.e., no false positives or
12964 negatives. Furthermore, Mantis is also a colored de Bruijn graph
12965 representation, so it supports fast graph traversal and other topological
12966 analyses in addition to large-scale sequence-level searches.")
12967 ;; uses __uint128_t and inline assembly
12968 (supported-systems '("x86_64-linux"))
12969 (license license:bsd-3))))
12971 (define-public r-diversitree
12973 (name "r-diversitree")
12978 (uri (cran-uri "diversitree" version))
12981 "00vi4klywi35hd170ksjv3xja3hqqbkcidcnrrlpgv4179k0azix"))))
12982 (build-system r-build-system)
12984 `(("gfortran" ,gfortran)))
12985 (inputs `(("fftw" ,fftw) ("gsl" ,gsl)))
12988 ("r-desolve" ,r-desolve)
12990 ("r-subplex" ,r-subplex)))
12991 (home-page "https://www.zoology.ubc.ca/prog/diversitree")
12992 (synopsis "Comparative 'phylogenetic' analyses of diversification")
12993 (description "This package contains a number of comparative \"phylogenetic\"
12994 methods, mostly focusing on analysing diversification and character evolution.
12995 Contains implementations of \"BiSSE\" (Binary State Speciation and Extinction)
12996 and its unresolved tree extensions, \"MuSSE\" (Multiple State Speciation and
12997 Extinction), \"QuaSSE\", \"GeoSSE\", and \"BiSSE-ness\" Other included methods
12998 include Markov models of discrete and continuous trait evolution and constant
12999 rate speciation and extinction.")
13000 (license license:gpl2+)))
13002 (define-public sjcount
13003 ;; There is no tag for version 3.2, nor is there a release archive.
13004 (let ((commit "292d3917cadb3f6834c81e509c30e61cd7ead6e5")
13008 (version (git-version "3.2" revision commit))
13011 (uri (git-reference
13012 (url "https://github.com/pervouchine/sjcount-full.git")
13014 (file-name (string-append name "-" version "-checkout"))
13017 "0gdgj35j249f04rqgq8ymcc1xg1vi9kzbajnjqpaq2wpbh8bl234"))))
13018 (build-system gnu-build-system)
13020 `(#:tests? #f ; requires a 1.4G test file
13022 (list (string-append "SAMTOOLS_DIR="
13023 (assoc-ref %build-inputs "samtools")
13026 (modify-phases %standard-phases
13027 (replace 'configure
13028 (lambda* (#:key inputs #:allow-other-keys)
13029 (substitute* "makefile"
13030 (("-I \\$\\{SAMTOOLS_DIR\\}")
13031 (string-append "-I" (assoc-ref inputs "samtools")
13032 "/include/samtools"))
13033 (("-lz ") "-lz -lpthread "))
13036 (lambda* (#:key outputs #:allow-other-keys)
13037 (for-each (lambda (tool)
13039 (string-append (assoc-ref outputs "out")
13041 '("j_count" "b_count" "sjcount"))
13044 `(("samtools" ,samtools-0.1)
13046 (home-page "https://github.com/pervouchine/sjcount-full/")
13047 (synopsis "Annotation-agnostic splice junction counting pipeline")
13048 (description "Sjcount is a utility for fast quantification of splice
13049 junctions in RNA-seq data. It is annotation-agnostic and offset-aware. This
13050 version does count multisplits.")
13051 (license license:gpl3+))))
13053 (define-public minimap2
13060 (uri (string-append "https://github.com/lh3/minimap2/"
13061 "releases/download/v" version "/"
13062 "minimap2-" version ".tar.bz2"))
13065 "080w9066irkbhbyr4nmf19pzkdd2s4v31hpzlajgq2y0drr6zcsj"))))
13066 (build-system gnu-build-system)
13068 `(#:tests? #f ; there are none
13071 (let ((system ,(or (%current-target-system)
13072 (%current-system))))
13074 ((string-prefix? "x86_64" system)
13076 ((or (string-prefix? "armhf" system)
13077 (string-prefix? "aarch64" system))
13079 (_ "sse2only=1"))))
13081 (modify-phases %standard-phases
13082 (delete 'configure)
13084 (lambda* (#:key outputs #:allow-other-keys)
13085 (let* ((out (assoc-ref outputs "out"))
13086 (bin (string-append out "/bin"))
13087 (man (string-append out "/share/man/man1")))
13088 (install-file "minimap2" bin)
13090 (install-file "minimap2.1" man))
13094 (home-page "https://lh3.github.io/minimap2/")
13095 (synopsis "Pairwise aligner for genomic and spliced nucleotide sequences")
13096 (description "Minimap2 is a versatile sequence alignment program that
13097 aligns DNA or mRNA sequences against a large reference database. Typical use
13101 @item mapping PacBio or Oxford Nanopore genomic reads to the human genome;
13102 @item finding overlaps between long reads with error rate up to ~15%;
13103 @item splice-aware alignment of PacBio Iso-Seq or Nanopore cDNA or Direct RNA
13104 reads against a reference genome;
13105 @item aligning Illumina single- or paired-end reads;
13106 @item assembly-to-assembly alignment;
13107 @item full-genome alignment between two closely related species with
13108 divergence below ~15%.
13110 (license license:expat)))
13112 (define-public r-circus
13119 (uri (git-reference
13120 (url "https://github.com/BIMSBbioinfo/ciRcus.git")
13121 (commit (string-append "v" version))))
13122 (file-name (git-file-name name version))
13125 "0jhjn3ilb057hbf6yzrihj13ifxxs32y7nkby8l3lkm28dg4p97h"))))
13126 (build-system r-build-system)
13128 `(("r-annotationdbi" ,r-annotationdbi)
13129 ("r-annotationhub" ,r-annotationhub)
13130 ("r-biomart" ,r-biomart)
13131 ("r-data-table" ,r-data-table)
13133 ("r-genomicfeatures" ,r-genomicfeatures)
13134 ("r-genomicranges" ,r-genomicranges)
13135 ("r-ggplot2" ,r-ggplot2)
13137 ("r-iranges" ,r-iranges)
13138 ("r-rcolorbrewer" ,r-rcolorbrewer)
13139 ("r-rmysql" ,r-rmysql)
13140 ("r-s4vectors" ,r-s4vectors)
13141 ("r-stringr" ,r-stringr)
13142 ("r-summarizedexperiment" ,r-summarizedexperiment)))
13144 `(("r-knitr" ,r-knitr)))
13145 (home-page "https://github.com/BIMSBbioinfo/ciRcus")
13146 (synopsis "Annotation, analysis and visualization of circRNA data")
13147 (description "Circus is an R package for annotation, analysis and
13148 visualization of circRNA data. Users can annotate their circRNA candidates
13149 with host genes, gene featrues they are spliced from, and discriminate between
13150 known and yet unknown splice junctions. Circular-to-linear ratios of circRNAs
13151 can be calculated, and a number of descriptive plots easily generated.")
13152 (license license:artistic2.0)))
13154 (define-public gffread
13155 ;; We cannot use the tagged release because it is not in sync with gclib.
13156 ;; See https://github.com/gpertea/gffread/issues/26
13157 (let ((commit "ba7535fcb3cea55a6e5a491d916e93b454e87fd0")
13161 (version (git-version "0.9.12" revision commit))
13165 (uri (git-reference
13166 (url "https://github.com/gpertea/gffread.git")
13168 (file-name (git-file-name name version))
13171 "1dl2nbcg96lxpd0drg48ssa8343nf7pw9s9mkrc4mjjmfwsin3ki"))))
13172 (build-system gnu-build-system)
13174 `(#:tests? #f ; no check target
13176 (list "GCLDIR=gclib")
13178 (modify-phases %standard-phases
13179 (delete 'configure)
13180 (add-after 'unpack 'copy-gclib-source
13181 (lambda* (#:key inputs #:allow-other-keys)
13183 (copy-recursively (assoc-ref inputs "gclib-source") "gclib")
13185 ;; There is no install target
13187 (lambda* (#:key outputs #:allow-other-keys)
13188 (let* ((out (assoc-ref outputs "out"))
13189 (bin (string-append out "/bin")))
13190 (install-file "gffread" bin))
13194 ,(let ((version "0.10.3")
13195 (commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13199 (uri (git-reference
13200 (url "https://github.com/gpertea/gclib.git")
13202 (file-name (git-file-name "gclib" version))
13205 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13206 (home-page "https://github.com/gpertea/gffread/")
13207 (synopsis "Parse and convert GFF/GTF files")
13209 "This package provides a GFF/GTF file parsing utility providing format
13210 conversions, region filtering, FASTA sequence extraction and more.")
13211 ;; gffread is under Expat, but gclib is under Artistic 2.0
13212 (license (list license:expat
13213 license:artistic2.0)))))
13215 (define-public find-circ
13216 ;; The last release was in 2015. The license was clarified in 2017, so we
13217 ;; take the latest commit.
13218 (let ((commit "8655dca54970fcf7e92e22fbf57e1188724dda7d")
13222 (version (git-version "1.2" revision commit))
13226 (uri (git-reference
13227 (url "https://github.com/marvin-jens/find_circ.git")
13229 (file-name (git-file-name name version))
13232 "0p77pbqbclqr4srms34y1b9b4njybfpjiknc11ki84f3p8skb3cg"))))
13233 (build-system gnu-build-system)
13235 `(#:tests? #f ; there are none
13237 ;; There is no actual build system.
13238 (modify-phases %standard-phases
13239 (delete 'configure)
13242 (lambda* (#:key outputs #:allow-other-keys)
13243 (let* ((out (assoc-ref outputs "out"))
13244 (bin (string-append out "/bin"))
13245 (path (getenv "PYTHONPATH")))
13246 (for-each (lambda (script)
13247 (install-file script bin)
13248 (wrap-program (string-append bin "/" script)
13249 `("PYTHONPATH" ":" prefix (,path))))
13254 "unmapped2anchors.py")))
13257 `(("python2" ,python-2)
13258 ("python2-pysam" ,python2-pysam)
13259 ("python2-numpy" ,python2-numpy)))
13260 (home-page "https://github.com/marvin-jens/find_circ")
13261 (synopsis "circRNA detection from RNA-seq reads")
13262 (description "This package provides tools to detect head-to-tail
13263 spliced (back-spliced) sequencing reads, indicative of circular RNA (circRNA)
13265 (license license:gpl3))))
13267 (define-public python-scanpy
13269 (name "python-scanpy")
13270 (version "1.4.5.1")
13274 (uri (pypi-uri "scanpy" version))
13277 "14kh1ji70xxhmri5q8sgcibsidhr6f221wxrcw8a5xvibj5da17j"))))
13278 (build-system python-build-system)
13281 (modify-phases %standard-phases
13283 (lambda* (#:key inputs #:allow-other-keys)
13284 ;; These tests require Internet access.
13285 (delete-file-recursively "scanpy/tests/notebooks")
13286 (delete-file "scanpy/tests/test_clustering.py")
13288 ;; TODO: I can't get the plotting tests to work, even with Xvfb.
13289 (delete-file "scanpy/tests/test_plotting.py")
13290 (delete-file "scanpy/tests/test_preprocessing.py")
13291 (delete-file "scanpy/tests/test_read_10x.py")
13293 (setenv "PYTHONPATH"
13294 (string-append (getcwd) ":"
13295 (getenv "PYTHONPATH")))
13299 `(("python-anndata" ,python-anndata)
13300 ("python-h5py" ,python-h5py)
13301 ("python-igraph" ,python-igraph)
13302 ("python-joblib" ,python-joblib)
13303 ("python-louvain" ,python-louvain)
13304 ("python-legacy-api-wrap" ,python-legacy-api-wrap)
13305 ("python-matplotlib" ,python-matplotlib)
13306 ("python-natsort" ,python-natsort)
13307 ("python-networkx" ,python-networkx)
13308 ("python-numba" ,python-numba)
13309 ("python-packaging" ,python-packaging)
13310 ("python-pandas" ,python-pandas)
13311 ("python-patsy" ,python-patsy)
13312 ("python-scikit-learn" ,python-scikit-learn)
13313 ("python-scipy" ,python-scipy)
13314 ("python-seaborn" ,python-seaborn)
13315 ("python-statsmodels" ,python-statsmodels)
13316 ("python-tables" ,python-tables)
13317 ("python-umap-learn" ,python-umap-learn)))
13319 `(("python-pytest" ,python-pytest)
13320 ("python-setuptools-scm" ,python-setuptools-scm)))
13321 (home-page "https://github.com/theislab/scanpy")
13322 (synopsis "Single-Cell Analysis in Python.")
13323 (description "Scanpy is a scalable toolkit for analyzing single-cell gene
13324 expression data. It includes preprocessing, visualization, clustering,
13325 pseudotime and trajectory inference and differential expression testing. The
13326 Python-based implementation efficiently deals with datasets of more than one
13328 (license license:bsd-3)))
13330 (define-public python-bbknn
13332 (name "python-bbknn")
13337 (uri (pypi-uri "bbknn" version))
13340 "1jbsh01f57zj4bhvjr3jh4532zznqd6nccmgrl3qi9gnhkf7c4y0"))))
13341 (build-system python-build-system)
13343 `(#:tests? #f)) ; TODO: Enable after migration to scikit-learn.
13345 `(("python-annoy" ,python-annoy)
13346 ("python-cython" ,python-cython)
13347 ("python-numpy" ,python-numpy)
13348 ("python-scipy" ,python-scipy)
13349 ("python-umap-learn" ,python-umap-learn)))
13350 (home-page "https://github.com/Teichlab/bbknn")
13351 (synopsis "Batch balanced KNN")
13352 (description "BBKNN is a batch effect removal tool that can be directly
13353 used in the Scanpy workflow. It serves as an alternative to
13354 @code{scanpy.api.pp.neighbors()}, with both functions creating a neighbour
13355 graph for subsequent use in clustering, pseudotime and UMAP visualisation. If
13356 technical artifacts are present in the data, they will make it challenging to
13357 link corresponding cell types across different batches. BBKNN actively
13358 combats this effect by splitting your data into batches and finding a smaller
13359 number of neighbours for each cell within each of the groups. This helps
13360 create connections between analogous cells in different batches without
13361 altering the counts or PCA space.")
13362 (license license:expat)))
13364 (define-public gffcompare
13365 (let ((commit "be56ef4349ea3966c12c6397f85e49e047361c41")
13368 (name "gffcompare")
13369 (version (git-version "0.10.15" revision commit))
13373 (uri (git-reference
13374 (url "https://github.com/gpertea/gffcompare/")
13376 (file-name (git-file-name name version))
13378 (base32 "0cp5qpxdhw4mxpya5dld8wi3jk00zyklm6rcri426wydinrnfmkg"))))
13379 (build-system gnu-build-system)
13381 `(#:tests? #f ; no check target
13383 (modify-phases %standard-phases
13384 (delete 'configure)
13385 (add-before 'build 'copy-gclib-source
13386 (lambda* (#:key inputs #:allow-other-keys)
13389 (assoc-ref inputs "gclib-source") "../gclib")
13392 (lambda* (#:key outputs #:allow-other-keys)
13393 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
13394 (install-file "gffcompare" bin)
13397 `(("gclib-source" ; see 'README.md' of gffcompare
13398 ,(let ((commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13401 (version (git-version "0.10.3" revision commit)))
13404 (uri (git-reference
13405 (url "https://github.com/gpertea/gclib/")
13407 (file-name (git-file-name name version))
13409 (base32 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13410 (home-page "https://github.com/gpertea/gffcompare/")
13411 (synopsis "Tool for comparing or classifing transcripts of RNA-Seq")
13413 "@code{gffcompare} is a tool that can:
13415 @item compare and evaluate the accuracy of RNA-Seq transcript assemblers
13416 (Cufflinks, Stringtie);
13417 @item collapse (merge) duplicate transcripts from multiple GTF/GFF3 files (e.g.
13418 resulted from assembly of different samples);
13419 @item classify transcripts from one or multiple GTF/GFF3 files as they relate to
13420 reference transcripts provided in a annotation file (also in GTF/GFF3 format).
13424 license:expat ;license for gffcompare
13425 license:artistic2.0))))) ;license for gclib
13427 (define-public intervaltree
13428 (let ((commit "b90527f9e6d51cd36ecbb50429e4524d3a418ea5"))
13430 (name "intervaltree")
13431 (version (git-version "0.0.0" "1" commit))
13435 (uri (git-reference
13436 (url "https://github.com/ekg/intervaltree/")
13438 (file-name (git-file-name name version))
13440 (base32 "0rgv6q5fl4x5d74n6p5wvdna6zmbdbqpb4jqqh6vq3670gn08xad"))))
13441 (build-system gnu-build-system)
13443 '(#:tests? #f ; No tests.
13444 #:make-flags (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
13447 (modify-phases %standard-phases
13448 (delete 'configure)))) ; There is no configure phase.
13449 (home-page "https://github.com/ekg/intervaltree")
13450 (synopsis "Minimal C++ interval tree implementation")
13451 (description "An interval tree can be used to efficiently find a set of
13452 numeric intervals overlapping or containing another interval. This library
13453 provides a basic implementation of an interval tree using C++ templates,
13454 allowing the insertion of arbitrary types into the tree.")
13455 (license license:expat))))
13457 (define-public python-intervaltree
13459 (name "python-intervaltree")
13464 (uri (pypi-uri "intervaltree" version))
13467 "02w191m9zxkcjqr1kv2slxvhymwhj3jnsyy3a28b837pi15q19dc"))))
13468 (build-system python-build-system)
13469 ;; FIXME: error when collecting tests
13470 (arguments '(#:tests? #f))
13472 `(("python-sortedcontainers" ,python-sortedcontainers)))
13474 `(("python-pytest" ,python-pytest)))
13475 (home-page "https://github.com/chaimleib/intervaltree")
13476 (synopsis "Editable interval tree data structure")
13478 "This package provides a mutable, self-balancing interval tree
13479 implementation for Python. Queries may be by point, by range overlap, or by
13480 range envelopment. This library was designed to allow tagging text and time
13481 intervals, where the intervals include the lower bound but not the upper
13483 (license license:asl2.0)))
13485 (define-public python-pypairix
13487 (name "python-pypairix")
13492 (uri (pypi-uri "pypairix" version))
13495 "0zs92b74s5v4xy2h16s15f3z6l4nnbw8x8zyif7xx5xpafjn0xss"))))
13496 (build-system python-build-system)
13497 ;; FIXME: the tests fail because test.support cannot be loaded:
13498 ;; ImportError: cannot import name 'support'
13499 (arguments '(#:tests? #f))
13502 (home-page "https://github.com/4dn-dcic/pairix")
13503 (synopsis "Support for querying pairix-indexed bgzipped text files")
13505 "Pypairix is a Python module for fast querying on a pairix-indexed
13506 bgzipped text file that contains a pair of genomic coordinates per line.")
13507 (license license:expat)))
13509 (define-public python-pyfaidx
13511 (name "python-pyfaidx")
13516 (uri (pypi-uri "pyfaidx" version))
13519 "02jvdx3ksy6w5gd29i1d0g0zsabbz7c14qg482ff7pza6sdl0b2i"))))
13520 (build-system python-build-system)
13522 `(("python-six" ,python-six)))
13523 (home-page "http://mattshirley.com")
13524 (synopsis "Random access to fasta subsequences")
13526 "This package provides procedures for efficient pythonic random access to
13527 fasta subsequences.")
13528 (license license:bsd-3)))
13530 (define-public python-cooler
13532 (name "python-cooler")
13537 (uri (pypi-uri "cooler" version))
13540 "08k5nxnxa6qsbk15z5z0q01n28042k87wi4905hh95rzqib15mhx"))))
13541 (build-system python-build-system)
13543 `(("python-biopython" ,python-biopython)
13544 ("python-click" ,python-click)
13545 ("python-cytoolz" ,python-cytoolz)
13546 ("python-dask" ,python-dask)
13547 ("python-h5py" ,python-h5py)
13548 ("python-multiprocess" ,python-multiprocess)
13549 ("python-pandas" ,python-pandas)
13550 ("python-pyfaidx" ,python-pyfaidx)
13551 ("python-pypairix" ,python-pypairix)
13552 ("python-pysam" ,python-pysam)
13553 ("python-scipy" ,python-scipy)))
13555 `(("python-mock" ,python-mock)
13556 ("python-nose" ,python-nose)
13557 ("python-numpydoc" ,python-numpydoc)
13558 ("python-sphinx" ,python-sphinx)))
13559 (home-page "https://github.com/mirnylab/cooler")
13560 (synopsis "Sparse binary format for genomic interaction matrices")
13562 "Cooler is a support library for a sparse, compressed, binary persistent
13563 storage format, called @code{cool}, used to store genomic interaction data,
13564 such as Hi-C contact matrices.")
13565 (license license:bsd-3)))
13567 (define-public python-hicexplorer
13569 (name "python-hicexplorer")
13573 ;; The latest version is not available on Pypi.
13575 (uri (git-reference
13576 (url "https://github.com/deeptools/HiCExplorer.git")
13578 (file-name (git-file-name name version))
13581 "0q5gpbzmrkvygqgw524q36b4nrivcmyi5v194vsx0qw7b3gcmq08"))))
13582 (build-system python-build-system)
13585 (modify-phases %standard-phases
13586 (add-after 'unpack 'loosen-up-requirements
13588 (substitute* "setup.py"
13592 `(("python-biopython" ,python-biopython)
13593 ("python-configparser" ,python-configparser)
13594 ("python-cooler" ,python-cooler)
13595 ("python-future" ,python-future)
13596 ("python-intervaltree" ,python-intervaltree)
13597 ("python-jinja2" ,python-jinja2)
13598 ("python-matplotlib" ,python-matplotlib)
13599 ("python-numpy" ,python-numpy)
13600 ("python-pandas" ,python-pandas)
13601 ("python-pybigwig" ,python-pybigwig)
13602 ("python-pysam" ,python-pysam)
13603 ("python-scipy" ,python-scipy)
13604 ("python-six" ,python-six)
13605 ("python-tables" ,python-tables)
13606 ("python-unidecode" ,python-unidecode)))
13607 (home-page "https://hicexplorer.readthedocs.io")
13608 (synopsis "Process, analyze and visualize Hi-C data")
13610 "HiCExplorer is a powerful and easy to use set of tools to process,
13611 normalize and visualize Hi-C data. HiCExplorer facilitates the creation of
13612 contact matrices, correction of contacts, TAD detection, A/B compartments,
13613 merging, reordering or chromosomes, conversion from different formats
13614 including cooler and detection of long-range contacts. Moreover, it allows
13615 the visualization of multiple contact matrices along with other types of data
13616 like genes, compartments, ChIP-seq coverage tracks (and in general any type of
13617 genomic scores), long range contacts and the visualization of viewpoints.")
13618 (license license:gpl3)))
13620 (define-public python-pygenometracks
13622 (name "python-pygenometracks")
13627 (uri (pypi-uri "pyGenomeTracks" version))
13630 "1fws6bqsyy9kj3qiabhkqx4wd4i775gsxnhszqd3zg7w67sc1ic5"))))
13631 (build-system python-build-system)
13633 `(("python-configparser" ,python-configparser)
13634 ("python-future" ,python-future)
13635 ("python-hicexplorer" ,python-hicexplorer)
13636 ("python-intervaltree" ,python-intervaltree)
13637 ("python-matplotlib" ,python-matplotlib)
13638 ("python-numpy" ,python-numpy)
13639 ("python-pybigwig" ,python-pybigwig)))
13641 `(("python-pytest" ,python-pytest)))
13642 (home-page "https://pygenometracks.readthedocs.io")
13643 (synopsis "Program and library to plot beautiful genome browser tracks")
13645 "This package aims to produce high-quality genome browser tracks that
13646 are highly customizable. Currently, it is possible to plot: bigwig, bed (many
13647 options), bedgraph, links (represented as arcs), and Hi-C matrices.
13648 pyGenomeTracks can make plots with or without Hi-C data.")
13649 (license license:gpl3+)))
13651 (define-public python-hic2cool
13653 (name "python-hic2cool")
13658 (uri (pypi-uri "hic2cool" version))
13661 "0xy6mhfns2lzib1kcr6419jjp6pmh0qx8z8na55lmiwn0ds8q9cl"))))
13662 (build-system python-build-system)
13663 (arguments '(#:tests? #f)) ; no tests included
13665 `(("python-cooler" ,python-cooler)))
13666 (home-page "https://github.com/4dn-dcic/hic2cool")
13667 (synopsis "Converter for .hic and .cool files")
13669 "This package provides a converter between @code{.hic} files (from
13670 juicer) and single-resolution or multi-resolution @code{.cool} files (for
13671 cooler). Both @code{hic} and @code{cool} files describe Hi-C contact
13673 (license license:expat)))
13675 (define-public r-pore
13683 (string-append "mirror://sourceforge/rpore/" version
13684 "/poRe_" version ".tar.gz"))
13686 (base32 "0pih9nljbv8g4x8rkk29i7aqq681b782r5s5ynp4nw9yzqnmmksv"))))
13687 (properties `((upstream-name . "poRe")))
13688 (build-system r-build-system)
13690 `(("r-bit64" ,r-bit64)
13691 ("r-data-table" ,r-data-table)
13692 ("r-rhdf5" ,r-rhdf5)
13693 ("r-shiny" ,r-shiny)
13694 ("r-svdialogs" ,r-svdialogs)))
13695 (home-page "https://sourceforge.net/projects/rpore/")
13696 (synopsis "Visualize Nanopore sequencing data")
13698 "This package provides graphical user interfaces to organize and visualize Nanopore
13700 ;; This is free software but the license variant is unclear:
13701 ;; <https://github.com/mw55309/poRe_docs/issues/10>.
13702 (license license:bsd-3)))
13704 (define-public r-xbioc
13705 (let ((revision "1")
13706 (commit "6ff0670a37ab3036aaf1d94aa4b208310946b0b5"))
13709 (version (git-version "0.1.16" revision commit))
13712 (uri (git-reference
13713 (url "https://github.com/renozao/xbioc.git")
13715 (file-name (git-file-name name version))
13718 "0w8bsq5myiwkfhh83nm6is5ichiyvwa1axx2szvxnzq39x6knf66"))))
13719 (build-system r-build-system)
13721 `(("r-annotationdbi" ,r-annotationdbi)
13722 ("r-assertthat" ,r-assertthat)
13723 ("r-biobase" ,r-biobase)
13724 ("r-biocmanager" ,r-biocmanager)
13725 ("r-digest" ,r-digest)
13726 ("r-pkgmaker" ,r-pkgmaker)
13728 ("r-reshape2" ,r-reshape2)
13729 ("r-stringr" ,r-stringr)))
13730 (home-page "https://github.com/renozao/xbioc/")
13731 (synopsis "Extra base functions for Bioconductor")
13732 (description "This package provides extra utility functions to perform
13733 common tasks in the analysis of omics data, leveraging and enhancing features
13734 provided by Bioconductor packages.")
13735 (license license:gpl3+))))
13737 (define-public r-cssam
13738 (let ((revision "1")
13739 (commit "9ec58c982fa551af0d80b1a266890d92954833f2"))
13742 (version (git-version "1.4" revision commit))
13745 (uri (git-reference
13746 (url "https://github.com/shenorrLab/csSAM.git")
13748 (file-name (git-file-name name version))
13751 "128syf9v39gk0z3ip000qpsjbg6l1siyq6c8b0hz41dzg5achyb3"))))
13752 (build-system r-build-system)
13754 `(("r-formula" ,r-formula)
13755 ("r-ggplot2" ,r-ggplot2)
13756 ("r-pkgmaker" ,r-pkgmaker)
13758 ("r-rngtools" ,r-rngtools)
13759 ("r-scales" ,r-scales)))
13760 (home-page "https://github.com/shenorrLab/csSAM/")
13761 (synopsis "Cell type-specific statistical analysis of microarray")
13762 (description "This package implements the method csSAM that computes
13763 cell-specific differential expression from measured cell proportions using
13766 (license license:lgpl2.1+))))
13768 (define-public r-bseqsc
13769 (let ((revision "1")
13770 (commit "fef3f3e38dcf3df37103348b5780937982b43b98"))
13773 (version (git-version "1.0" revision commit))
13776 (uri (git-reference
13777 (url "https://github.com/shenorrLab/bseqsc.git")
13779 (file-name (git-file-name name version))
13782 "1prw13wa20f7wlc3gkkls66n1kxz8d28qrb8icfqdwdnnv8w5qg8"))))
13783 (build-system r-build-system)
13785 `(("r-abind" ,r-abind)
13786 ("r-annotationdbi" ,r-annotationdbi)
13787 ("r-biobase" ,r-biobase)
13788 ("r-cssam" ,r-cssam)
13789 ("r-dplyr" ,r-dplyr)
13790 ("r-e1071" ,r-e1071)
13791 ("r-edger" ,r-edger)
13792 ("r-ggplot2" ,r-ggplot2)
13794 ("r-openxlsx" ,r-openxlsx)
13795 ("r-pkgmaker" ,r-pkgmaker)
13797 ("r-preprocesscore" ,r-preprocesscore)
13798 ("r-rngtools" ,r-rngtools)
13799 ("r-scales" ,r-scales)
13800 ("r-stringr" ,r-stringr)
13801 ("r-xbioc" ,r-xbioc)))
13802 (home-page "https://github.com/shenorrLab/bseqsc")
13803 (synopsis "Deconvolution of bulk sequencing experiments using single cell data")
13804 (description "BSeq-sc is a bioinformatics analysis pipeline that
13805 leverages single-cell sequencing data to estimate cell type proportion and
13806 cell type-specific gene expression differences from RNA-seq data from bulk
13807 tissue samples. This is a companion package to the publication \"A
13808 single-cell transcriptomic map of the human and mouse pancreas reveals inter-
13809 and intra-cell population structure.\" Baron et al. Cell Systems (2016)
13810 @url{https://www.ncbi.nlm.nih.gov/pubmed/27667365}.")
13811 (license license:gpl2+))))
13813 (define-public porechop
13814 ;; The recommended way to install is to clone the git repository
13815 ;; https://github.com/rrwick/Porechop#installation
13816 (let ((commit "289d5dca4a5fc327f97b3f8cecb68ecaf1014861")
13820 (version (git-version "0.2.3" revision commit))
13824 (uri (git-reference
13825 (url "https://github.com/rrwick/Porechop.git")
13827 (file-name (git-file-name name version))
13829 (base32 "05ps43gig0d3ia9x5lj84lb00hbsl6ba9n7y7jz927npxbr2ym23"))))
13830 (build-system python-build-system)
13831 (home-page "https://github.com/rrwick/porechop")
13832 (synopsis "Finding, trimming or splitting adapters, in Oxford Nanopore reads")
13834 "The porechop package is a tool for finding and removing adapters from Oxford
13835 Nanopore reads. Adapters on the ends of reads are trimmed off, and when a read
13836 has an adapter in its middle, it is treated as chimeric and chopped into
13837 separate reads. Porechop performs thorough alignments to effectively find
13838 adapters, even at low sequence identity. Porechop also supports demultiplexing
13839 of Nanopore reads that were barcoded with the Native Barcoding Kit, PCR
13840 Barcoding Kit or Rapid Barcoding Kit.")
13841 (license license:gpl3+))))
13843 (define-public poretools
13844 ;; The latest release was in 2016 and the latest commit is from 2017
13845 ;; the recommended way to install is to clone the git repository
13846 ;; https://poretools.readthedocs.io/en/latest/content/installation.html
13847 (let ((commit "e426b1f09e86ac259a00c261c79df91510777407")
13851 (version (git-version "0.6.0" revision commit))
13855 (uri (git-reference
13856 (url "https://github.com/arq5x/poretools.git")
13858 (file-name (git-file-name name version))
13860 (base32 "0bglj833wxpp3cq430p1d3xp085ls221js2y90w7ir2x5ay8l7am"))))
13861 (build-system python-build-system)
13862 ;; requires python >=2.7, <3.0, and the same for python dependencies
13863 (arguments `(#:python ,python-2))
13867 `(("python-dateutil" ,python2-dateutil)
13868 ("python-h5py" ,python2-h5py)
13869 ("python-matplotlib" ,python2-matplotlib)
13870 ("python-pandas" ,python2-pandas)
13871 ("python-seaborn" ,python2-seaborn)))
13872 (home-page "https://poretools.readthedocs.io")
13873 (synopsis "Toolkit for working with nanopore sequencing data")
13875 "The MinION from Oxford Nanopore Technologies is a nanopore sequencer.
13876 This @code{poretools} package is a flexible toolkit for exploring datasets
13877 generated by nanopore sequencing devices for the purposes of quality control and
13878 downstream analysis. Poretools operates directly on the native FAST5, a variant
13879 of the Hierarchical Data Format (HDF5) standard.")
13880 (license license:expat))))
13882 (define-public r-absfiltergsea
13884 (name "r-absfiltergsea")
13889 (uri (cran-uri "AbsFilterGSEA" version))
13891 (base32 "15srxkxsvn38kd5frdrwfdf0ad8gskrd0h01wmdf9hglq8fjrp7w"))))
13892 (properties `((upstream-name . "AbsFilterGSEA")))
13893 (build-system r-build-system)
13895 `(("r-biobase" ,r-biobase)
13896 ("r-deseq" ,r-deseq)
13897 ("r-limma" ,r-limma)
13899 ("r-rcpparmadillo" ,r-rcpparmadillo)))
13900 (home-page "https://cran.r-project.org/web/packages/AbsFilterGSEA/")
13901 (synopsis "Improved false positive control of gene-permuting with absolute filtering")
13903 "This package provides a function that performs gene-permuting of a gene-set
13904 enrichment analysis (GSEA) calculation with or without the absolute filtering.
13905 Without filtering, users can perform (original) two-tailed or one-tailed
13907 (license license:gpl2)))
13909 (define-public jamm
13912 (version "1.0.7.6")
13916 (uri (git-reference
13917 (url "https://github.com/mahmoudibrahim/JAMM.git")
13918 (commit (string-append "JAMMv" version))))
13919 (file-name (git-file-name name version))
13922 "0bsa5mf9n9q5jz7mmacrra41l7r8rac5vgsn6wv1fb52ya58b970"))))
13923 (build-system gnu-build-system)
13925 `(#:tests? #f ; there are none
13927 (modify-phases %standard-phases
13928 (delete 'configure)
13931 (lambda* (#:key inputs outputs #:allow-other-keys)
13932 (let* ((out (assoc-ref outputs "out"))
13933 (libexec (string-append out "/libexec/jamm"))
13934 (bin (string-append out "/bin")))
13935 (substitute* '("JAMM.sh"
13936 "SignalGenerator.sh")
13938 (string-append "sPath=\"" libexec "\"\n")))
13939 (for-each (lambda (file)
13940 (install-file file libexec))
13941 (list "bincalculator.r"
13953 (chmod script #o555)
13954 (install-file script bin)
13955 (wrap-program (string-append bin "/" script)
13956 `("PATH" ":" prefix
13957 (,(string-append (assoc-ref inputs "coreutils") "/bin")
13958 ,(string-append (assoc-ref inputs "gawk") "/bin")
13959 ,(string-append (assoc-ref inputs "perl") "/bin")
13960 ,(string-append (assoc-ref inputs "r-minimal") "/bin")))
13961 `("PERL5LIB" ":" prefix (,(getenv "PERL5LIB")))
13962 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
13963 (list "JAMM.sh" "SignalGenerator.sh")))
13967 ("coreutils" ,coreutils)
13970 ("r-minimal" ,r-minimal)
13971 ;;("r-parallel" ,r-parallel)
13972 ("r-signal" ,r-signal)
13973 ("r-mclust" ,r-mclust)))
13974 (home-page "https://github.com/mahmoudibrahim/JAMM")
13975 (synopsis "Peak finder for NGS datasets")
13977 "JAMM is a peak finder for next generation sequencing datasets (ChIP-Seq,
13978 ATAC-Seq, DNase-Seq, etc.) that can integrate replicates and assign peak
13979 boundaries accurately. JAMM is applicable to both broad and narrow
13981 (license license:gpl3+)))
13983 (define-public ngless
13990 (uri (git-reference
13991 (url "https://gitlab.com/ngless/ngless.git")
13992 (commit (string-append "v" version))))
13993 (file-name (git-file-name name version))
13996 "1wim8wpqyff080dfcazynrmjwqas38m24m0v350w245mmhrapdma"))))
13997 (build-system haskell-build-system)
13999 `(#:haddock? #f ; The haddock phase fails with: NGLess/CmdArgs.hs:20:1:
14000 ; error: parse error on input import
14001 ; import Options.Applicative
14003 (modify-phases %standard-phases
14004 (add-after 'unpack 'create-Versions.hs
14006 (substitute* "Makefile"
14007 (("BWA_VERSION = .*")
14008 (string-append "BWA_VERSION = "
14009 ,(package-version bwa) "\n"))
14010 (("SAM_VERSION = .*")
14011 (string-append "SAM_VERSION = "
14012 ,(package-version samtools) "\n"))
14013 (("PRODIGAL_VERSION = .*")
14014 (string-append "PRODIGAL_VERSION = "
14015 ,(package-version prodigal) "\n"))
14016 (("MINIMAP2_VERSION = .*")
14017 (string-append "MINIMAP2_VERSION = "
14018 ,(package-version minimap2) "\n")))
14019 (invoke "make" "NGLess/Dependencies/Versions.hs")
14021 (add-after 'create-Versions.hs 'create-cabal-file
14022 (lambda _ (invoke "hpack") #t))
14023 ;; These tools are expected to be installed alongside ngless.
14024 (add-after 'install 'link-tools
14025 (lambda* (#:key inputs outputs #:allow-other-keys)
14026 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
14027 (symlink (string-append (assoc-ref inputs "prodigal")
14029 (string-append bin "ngless-" ,version "-prodigal"))
14030 (symlink (string-append (assoc-ref inputs "minimap2")
14032 (string-append bin "ngless-" ,version "-minimap2"))
14033 (symlink (string-append (assoc-ref inputs "samtools")
14035 (string-append bin "ngless-" ,version "-samtools"))
14036 (symlink (string-append (assoc-ref inputs "bwa")
14038 (string-append bin "ngless-" ,version "-bwa"))
14041 `(("prodigal" ,prodigal)
14043 ("samtools" ,samtools)
14044 ("minimap2" ,minimap2)
14045 ("ghc-aeson" ,ghc-aeson)
14046 ("ghc-ansi-terminal" ,ghc-ansi-terminal)
14047 ("ghc-async" ,ghc-async)
14048 ("ghc-atomic-write" ,ghc-atomic-write)
14049 ("ghc-bytestring-lexing" ,ghc-bytestring-lexing)
14050 ("ghc-conduit" ,ghc-conduit)
14051 ("ghc-conduit-algorithms" ,ghc-conduit-algorithms)
14052 ("ghc-conduit-extra" ,ghc-conduit-extra)
14053 ("ghc-configurator" ,ghc-configurator)
14054 ("ghc-convertible" ,ghc-convertible)
14055 ("ghc-data-default" ,ghc-data-default)
14056 ("ghc-diagrams-core" ,ghc-diagrams-core)
14057 ("ghc-diagrams-lib" ,ghc-diagrams-lib)
14058 ("ghc-diagrams-svg" ,ghc-diagrams-svg)
14059 ("ghc-double-conversion" ,ghc-double-conversion)
14060 ("ghc-edit-distance" ,ghc-edit-distance)
14061 ("ghc-either" ,ghc-either)
14062 ("ghc-errors" ,ghc-errors)
14063 ("ghc-extra" ,ghc-extra)
14064 ("ghc-filemanip" ,ghc-filemanip)
14065 ("ghc-file-embed" ,ghc-file-embed)
14066 ("ghc-gitrev" ,ghc-gitrev)
14067 ("ghc-hashtables" ,ghc-hashtables)
14068 ("ghc-http-conduit" ,ghc-http-conduit)
14069 ("ghc-inline-c" ,ghc-inline-c)
14070 ("ghc-inline-c-cpp" ,ghc-inline-c-cpp)
14071 ("ghc-intervalmap" ,ghc-intervalmap)
14072 ("ghc-missingh" ,ghc-missingh)
14073 ("ghc-optparse-applicative" ,ghc-optparse-applicative)
14074 ("ghc-regex" ,ghc-regex)
14075 ("ghc-safe" ,ghc-safe)
14076 ("ghc-safeio" ,ghc-safeio)
14077 ("ghc-strict" ,ghc-strict)
14078 ("ghc-tar" ,ghc-tar)
14079 ("ghc-tar-conduit" ,ghc-tar-conduit)
14080 ("ghc-unliftio" ,ghc-unliftio)
14081 ("ghc-unliftio-core" ,ghc-unliftio-core)
14082 ("ghc-vector" ,ghc-vector)
14083 ("ghc-yaml" ,ghc-yaml)
14084 ("ghc-zlib" ,ghc-zlib)))
14087 ("r-hdf5r" ,r-hdf5r)
14088 ("r-iterators" ,r-iterators)
14089 ("r-itertools" ,r-itertools)
14090 ("r-matrix" ,r-matrix)))
14092 `(("ghc-hpack" ,ghc-hpack)
14093 ("ghc-quickcheck" ,ghc-quickcheck)
14094 ("ghc-test-framework" ,ghc-test-framework)
14095 ("ghc-test-framework-hunit",ghc-test-framework-hunit)
14096 ("ghc-test-framework-quickcheck2" ,ghc-test-framework-quickcheck2)
14097 ("ghc-test-framework-th" ,ghc-test-framework-th)))
14098 (home-page "https://gitlab.com/ngless/ngless")
14099 (synopsis "DSL for processing next-generation sequencing data")
14100 (description "Ngless is a domain-specific language for
14101 @dfn{next-generation sequencing} (NGS) data processing.")
14102 (license license:expat)))
14104 (define-public filtlong
14105 ;; The recommended way to install is to clone the git repository
14106 ;; https://github.com/rrwick/Filtlong#installation
14107 ;; and the lastest release is more than nine months old
14108 (let ((commit "d1bb46dfe8bc7efe6257b5ce222c04bfe8aedaab")
14112 (version (git-version "0.2.0" revision commit))
14116 (uri (git-reference
14117 (url "https://github.com/rrwick/Filtlong.git")
14119 (file-name (git-file-name name version))
14121 (base32 "1xr92r820x8qlkcr3b57iw223yq8vjgyi42jr79w2xgw47qzr575"))))
14122 (build-system gnu-build-system)
14124 `(#:tests? #f ; no check target
14126 (modify-phases %standard-phases
14127 (delete 'configure)
14129 (lambda* (#:key outputs #:allow-other-keys)
14130 (let* ((out (assoc-ref outputs "out"))
14131 (bin (string-append out "/bin"))
14132 (scripts (string-append out "/share/filtlong/scripts")))
14133 (install-file "bin/filtlong" bin)
14134 (install-file "scripts/histogram.py" scripts)
14135 (install-file "scripts/read_info_histograms.sh" scripts))
14137 (add-after 'install 'wrap-program
14138 (lambda* (#:key inputs outputs #:allow-other-keys)
14139 (let* ((out (assoc-ref outputs "out"))
14140 (path (getenv "PYTHONPATH")))
14141 (wrap-program (string-append out
14142 "/share/filtlong/scripts/histogram.py")
14143 `("PYTHONPATH" ":" prefix (,path))))
14145 (add-before 'check 'patch-tests
14147 (substitute* "scripts/read_info_histograms.sh"
14148 (("awk") (which "gawk")))
14151 `(("gawk" ,gawk) ;for read_info_histograms.sh
14152 ("python" ,python-2) ;required for histogram.py
14154 (home-page "https://github.com/rrwick/Filtlong/")
14155 (synopsis "Tool for quality filtering of Nanopore and PacBio data")
14157 "The Filtlong package is a tool for filtering long reads by quality.
14158 It can take a set of long reads and produce a smaller, better subset. It uses
14159 both read length (longer is better) and read identity (higher is better) when
14160 choosing which reads pass the filter.")
14161 (license (list license:gpl3 ;filtlong
14162 license:asl2.0))))) ;histogram.py
14164 (define-public nanopolish
14165 ;; The recommended way to install is to clone the git repository
14166 ;; <https://github.com/jts/nanopolish#installing-a-particular-release>.
14167 ;; Also, the differences between release and current version seem to be
14169 (let ((commit "6331dc4f15b9dfabb954ba3fae9d76b6c3ca6377")
14172 (name "nanopolish")
14173 (version (git-version "0.11.1" revision commit))
14177 (uri (git-reference
14178 (url "https://github.com/jts/nanopolish.git")
14181 (file-name (git-file-name name version))
14183 (base32 "15ikl3d37y49pwd7vx36xksgsqajhf24q7qqsnpl15dqqyy5qgbc"))
14184 (modules '((guix build utils)))
14187 (delete-file-recursively "htslib")
14189 (build-system gnu-build-system)
14192 `("HDF5=noinstall" "EIGEN=noinstall" "HTS=noinstall" "CC=gcc")
14193 #:tests? #f ; no check target
14195 (modify-phases %standard-phases
14196 (add-after 'unpack 'find-eigen
14197 (lambda* (#:key inputs #:allow-other-keys)
14199 (string-append (assoc-ref inputs "eigen")
14201 (or (getenv "CPATH") "")))
14203 (delete 'configure)
14205 (lambda* (#:key outputs #:allow-other-keys)
14206 (let* ((out (assoc-ref outputs "out"))
14207 (bin (string-append out "/bin"))
14208 (scripts (string-append out "/share/nanopolish/scripts")))
14210 (install-file "nanopolish" bin)
14211 (for-each (lambda (file) (install-file file scripts))
14212 (find-files "scripts" ".*"))
14214 (add-after 'install 'wrap-programs
14215 (lambda* (#:key outputs #:allow-other-keys)
14216 (for-each (lambda (file)
14217 (wrap-program file `("PYTHONPATH" ":" prefix (,path))))
14218 (find-files "/share/nanopolish/scripts" "\\.py"))
14219 (for-each (lambda (file)
14220 (wrap-program file `("PERL5LIB" ":" prefix (,path))))
14221 (find-files "/share/nanopolish/scripts" "\\.pl"))
14228 ("python" ,python-wrapper)
14229 ("python-biopython" ,python-biopython)
14230 ("python-numpy" ,python-numpy)
14231 ("python-pysam" ,python-pysam)
14232 ("python-scikit-learn" , python-scikit-learn)
14233 ("python-scipy" ,python-scipy)
14235 (home-page "https://github.com/jts/nanopolish")
14236 (synopsis "Signal-level analysis of Oxford Nanopore sequencing data")
14238 "This package analyses the Oxford Nanopore sequencing data at signal-level.
14239 Nanopolish can calculate an improved consensus sequence for a draft genome
14240 assembly, detect base modifications, call SNPs (Single nucleotide
14241 polymorphisms) and indels with respect to a reference genome and more.")
14242 (license license:expat))))
14244 (define-public cnvkit
14251 (uri (git-reference
14252 (url "https://github.com/etal/cnvkit.git")
14253 (commit (string-append "v" version))))
14254 (file-name (git-file-name name version))
14256 (base32 "0g2f78k68yglmj4fsfmgs8idqv3di9aj53fg0ld0hqljg8chhh82"))))
14257 (build-system python-build-system)
14259 `(("python-biopython" ,python-biopython)
14260 ("python-future" ,python-future)
14261 ("python-matplotlib" ,python-matplotlib)
14262 ("python-numpy" ,python-numpy)
14263 ("python-reportlab" ,python-reportlab)
14264 ("python-pandas" ,python-pandas)
14265 ("python-pysam" ,python-pysam)
14266 ("python-pyfaidx" ,python-pyfaidx)
14267 ("python-scipy" ,python-scipy)
14269 ("r-dnacopy" ,r-dnacopy)))
14270 (home-page "https://cnvkit.readthedocs.org/")
14271 (synopsis "Copy number variant detection from targeted DNA sequencing")
14273 "CNVkit is a Python library and command-line software toolkit to infer
14274 and visualize copy number from high-throughput DNA sequencing data. It is
14275 designed for use with hybrid capture, including both whole-exome and custom
14276 target panels, and short-read sequencing platforms such as Illumina and Ion
14278 (license license:asl2.0)))
14280 (define-public python-pyfit-sne
14282 (name "python-pyfit-sne")
14287 (uri (git-reference
14288 (url "https://github.com/KlugerLab/pyFIt-SNE.git")
14290 (file-name (git-file-name name version))
14292 (base32 "13wh3qkzs56azmmgnxib6xfr29g7xh09sxylzjpni5j0pp0rc5qw"))))
14293 (build-system python-build-system)
14295 `(("python-numpy" ,python-numpy)))
14299 `(("python-cython" ,python-cython)))
14300 (home-page "https://github.com/KlugerLab/pyFIt-SNE")
14301 (synopsis "FFT-accelerated Interpolation-based t-SNE")
14303 "t-Stochastic Neighborhood Embedding (t-SNE) is a highly successful
14304 method for dimensionality reduction and visualization of high dimensional
14305 datasets. A popular implementation of t-SNE uses the Barnes-Hut algorithm to
14306 approximate the gradient at each iteration of gradient descent. This package
14307 is a Cython wrapper for FIt-SNE.")
14308 (license license:bsd-4)))
14310 (define-public bbmap
14316 (uri (string-append
14317 "mirror://sourceforge/bbmap/BBMap_" version ".tar.gz"))
14320 "1q4rfhxcb6z3gm8zg2davjz98w22lkf4hm9ikxz9kdl93pil3wkd"))))
14321 (build-system ant-build-system)
14323 `(#:build-target "dist"
14324 #:tests? #f ; there are none
14326 (list (string-append "-Dmpijar="
14327 (assoc-ref %build-inputs "java-openmpi")
14329 #:modules ((guix build ant-build-system)
14331 (guix build java-utils))
14333 (modify-phases %standard-phases
14334 (add-after 'build 'build-jni-library
14336 (with-directory-excursion "jni"
14337 (invoke "make" "-f" "makefile.linux"))))
14338 ;; There is no install target
14339 (replace 'install (install-jars "dist"))
14340 (add-after 'install 'install-scripts-and-documentation
14341 (lambda* (#:key outputs #:allow-other-keys)
14342 (substitute* "calcmem.sh"
14343 (("\\| awk ") (string-append "| " (which "awk") " ")))
14344 (let* ((scripts (find-files "." "\\.sh$"))
14345 (out (assoc-ref outputs "out"))
14346 (bin (string-append out "/bin"))
14347 (doc (string-append out "/share/doc/bbmap"))
14348 (jni (string-append out "/lib/jni")))
14349 (substitute* scripts
14350 (("\\$DIR\"\"docs") doc)
14352 (string-append "CP=" out "/share/java/BBTools.jar\n"))
14353 (("^NATIVELIBDIR.*")
14354 (string-append "NATIVELIBDIR=" jni "\n"))
14356 (string-append "CMD=\"" (which "java"))))
14357 (for-each (lambda (script) (install-file script bin)) scripts)
14359 ;; Install JNI library
14360 (install-file "jni/libbbtoolsjni.so" jni)
14362 ;; Install documentation
14363 (install-file "docs/readme.txt" doc)
14364 (copy-recursively "docs/guides" doc))
14369 ("java-eclipse-jdt-core" ,java-eclipse-jdt-core)
14370 ("java-eclipse-jdt-compiler-apt" ,java-eclipse-jdt-compiler-apt)
14371 ("java-openmpi" ,java-openmpi)))
14372 (home-page "http://sourceforge.net/projects/bbmap/")
14373 (synopsis "Aligner and other tools for short sequencing reads")
14375 "This package provides bioinformatic tools to align, deduplicate,
14376 reformat, filter and normalize DNA and RNA-seq data. It includes the
14377 following tools: BBMap, a short read aligner for DNA and RNA-seq data; BBNorm,
14378 a kmer-based error-correction and normalization tool; Dedupe, a tool to
14379 simplify assemblies by removing duplicate or contained subsequences that share
14380 a target percent identity; Reformat, to convert reads between
14381 fasta/fastq/scarf/fasta+qual/sam, interleaved/paired, and ASCII-33/64, at over
14382 500 MB/s; and BBDuk, a tool to filter, trim, or mask reads with kmer matches
14383 to an artifact/contaminant file.")
14384 (license license:bsd-3)))
14386 (define-public velvet
14392 (uri (string-append "https://www.ebi.ac.uk/~zerbino/velvet/"
14393 "velvet_" version ".tgz"))
14396 "0h3njwy66p6bx14r3ar1byb0ccaxmxka4c65rn4iybyiqa4d8kc8"))
14397 ;; Delete bundled libraries
14398 (modules '((guix build utils)))
14401 (delete-file "Manual.pdf")
14402 (delete-file-recursively "third-party")
14404 (build-system gnu-build-system)
14406 `(#:make-flags '("OPENMP=t")
14407 #:test-target "test"
14409 (modify-phases %standard-phases
14410 (delete 'configure)
14411 (add-after 'unpack 'fix-zlib-include
14413 (substitute* "src/binarySequences.c"
14414 (("../third-party/zlib-1.2.3/zlib.h") "zlib.h"))
14417 (lambda* (#:key outputs #:allow-other-keys)
14418 (let* ((out (assoc-ref outputs "out"))
14419 (bin (string-append out "/bin"))
14420 (doc (string-append out "/share/doc/velvet")))
14423 (install-file "velveth" bin)
14424 (install-file "velvetg" bin)
14425 (install-file "Manual.pdf" doc)
14426 (install-file "Columbus_manual.pdf" doc)
14429 `(("openmpi" ,openmpi)
14432 `(("texlive" ,(texlive-union (list texlive-latex-graphics
14433 texlive-latex-hyperref)))))
14434 (home-page "https://www.ebi.ac.uk/~zerbino/velvet/")
14435 (synopsis "Nucleic acid sequence assembler for very short reads")
14437 "Velvet is a de novo genomic assembler specially designed for short read
14438 sequencing technologies, such as Solexa or 454. Velvet currently takes in
14439 short read sequences, removes errors then produces high quality unique
14440 contigs. It then uses paired read information, if available, to retrieve the
14441 repeated areas between contigs.")
14442 (license license:gpl2+)))
14444 (define-public python-velocyto
14446 (name "python-velocyto")
14447 (version "0.17.17")
14451 (uri (pypi-uri "velocyto" version))
14454 "0fgygyzqgrq32dv6a00biq1p1cwi6kbl5iqblxq1kklj6b2mzmhs"))))
14455 (build-system python-build-system)
14457 `(("python-click" ,python-click)
14458 ("python-cython" ,python-cython)
14459 ("python-h5py" ,python-h5py)
14460 ("python-loompy" ,python-loompy)
14461 ("python-matplotlib" ,python-matplotlib)
14462 ("python-numba" ,python-numba)
14463 ("python-numpy" ,python-numpy)
14464 ("python-pandas" ,python-pandas)
14465 ("python-pysam" ,python-pysam)
14466 ("python-scikit-learn" ,python-scikit-learn)
14467 ("python-scipy" ,python-scipy)))
14468 (home-page "https://github.com/velocyto-team/velocyto.py")
14469 (synopsis "RNA velocity analysis for single cell RNA-seq data")
14471 "Velocyto is a library for the analysis of RNA velocity. Velocyto
14472 includes a command line tool and an analysis pipeline.")
14473 (license license:bsd-2)))
14475 (define-public arriba
14482 (uri (string-append "https://github.com/suhrig/arriba/releases/"
14483 "download/v" version "/arriba_v" version ".tar.gz"))
14486 "0jx9656ry766vb8z08m1c3im87b0c82qpnjby9wz4kcz8vn87dx2"))))
14487 (build-system gnu-build-system)
14489 `(#:tests? #f ; there are none
14491 (modify-phases %standard-phases
14492 (replace 'configure
14493 (lambda* (#:key inputs #:allow-other-keys)
14494 (let ((htslib (assoc-ref inputs "htslib")))
14495 (substitute* "Makefile"
14496 (("-I\\$\\(HTSLIB\\)/htslib")
14497 (string-append "-I" htslib "/include/htslib"))
14498 ((" \\$\\(HTSLIB\\)/libhts.a")
14499 (string-append " " htslib "/lib/libhts.so"))))
14500 (substitute* "run_arriba.sh"
14501 (("^STAR ") (string-append (which "STAR") " "))
14502 (("samtools --version-only")
14503 (string-append (which "samtools") " --version-only"))
14504 (("samtools index")
14505 (string-append (which "samtools") " index"))
14507 (string-append (which "samtools") " sort")))
14510 (lambda* (#:key outputs #:allow-other-keys)
14511 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
14512 (install-file "arriba" bin)
14513 (install-file "run_arriba.sh" bin)
14514 (install-file "draw_fusions.R" bin)
14515 (wrap-program (string-append bin "/draw_fusions.R")
14516 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
14519 `(("htslib" ,htslib)
14520 ("r-minimal" ,r-minimal)
14521 ("r-circlize" ,r-circlize)
14522 ("r-genomicalignments" ,r-genomicalignments)
14523 ("r-genomicranges" ,r-genomicranges)
14524 ("samtools" ,samtools)
14527 (home-page "https://github.com/suhrig/arriba")
14528 (synopsis "Gene fusion detection from RNA-Seq data ")
14530 "Arriba is a command-line tool for the detection of gene fusions from
14531 RNA-Seq data. It was developed for the use in a clinical research setting.
14532 Therefore, short runtimes and high sensitivity were important design criteria.
14533 It is based on the fast STAR aligner and the post-alignment runtime is
14534 typically just around two minutes. In contrast to many other fusion detection
14535 tools which build on STAR, Arriba does not require to reduce the
14536 @code{alignIntronMax} parameter of STAR to detect small deletions.")
14537 ;; All code is under the Expat license with the exception of
14538 ;; "draw_fusions.R", which is under GPLv3.
14539 (license (list license:expat license:gpl3))))
14541 (define-public adapterremoval
14543 (name "adapterremoval")
14548 (uri (git-reference
14549 (url "https://github.com/MikkelSchubert/adapterremoval.git")
14550 (commit (string-append "v" version))))
14551 (file-name (git-file-name name version))
14554 "1nf3ki5pfzalhrx2fr1y6pfqfi133yj2m7q4fj9irf5fb94bapwr"))))
14555 (build-system gnu-build-system)
14557 `(#:make-flags (list "COLOR_BUILD=no"
14558 (string-append "PREFIX="
14559 (assoc-ref %outputs "out")))
14560 #:test-target "test"
14562 (modify-phases %standard-phases
14563 (delete 'configure))))
14566 (home-page "https://adapterremoval.readthedocs.io/")
14567 (synopsis "Rapid sequence adapter trimming, identification, and read merging")
14569 "This program searches for and removes remnant adapter sequences from
14570 @dfn{High-Throughput Sequencing} (HTS) data and (optionally) trims low quality
14571 bases from the 3' end of reads following adapter removal. AdapterRemoval can
14572 analyze both single end and paired end data, and can be used to merge
14573 overlapping paired-ended reads into (longer) consensus sequences.
14574 Additionally, the AdapterRemoval may be used to recover a consensus adapter
14575 sequence for paired-ended data, for which this information is not available.")
14576 (license license:gpl3+)))
14578 (define-public pplacer
14579 (let ((commit "807f6f3"))
14582 ;; The commit should be updated with each version change.
14583 (version "1.1.alpha19")
14587 (uri (git-reference
14588 (url "https://github.com/matsen/pplacer.git")
14589 (commit (string-append "v" version))))
14590 (file-name (git-file-name name version))
14592 (base32 "11ppbbbx20p2g9wj3ff64dhnarb12q79v7qh4rk0gj6lkbz4n7cn"))))
14593 (build-system ocaml-build-system)
14595 `(#:modules ((guix build ocaml-build-system)
14599 (modify-phases %standard-phases
14600 (delete 'configure)
14601 (add-after 'unpack 'fix-build-with-latest-ocaml
14603 (substitute* "myocamlbuild.ml"
14604 (("dep \\[\"c_pam\"\\]" m)
14605 (string-append "flag [\"ocaml\"; \"compile\"] (A \"-unsafe-string\");\n"
14607 (("let run_and_read" m)
14612 let pos = String.index s ch in
14613 x := (String.before s pos)::!x;
14614 go (String.after s (pos + 1))
14617 with Not_found -> !x
14618 let split_nl s = split s '\\n'
14619 let before_space s =
14620 try String.before s (String.index s ' ')
14621 with Not_found -> s
14624 (("run_and_read \"ocamlfind list \\| cut -d' ' -f1\"" m)
14625 (string-append "List.map before_space (split_nl & " m ")"))
14626 ((" blank_sep_strings &") "")
14627 ((" Lexing.from_string &") ""))
14629 (add-after 'unpack 'replace-bundled-cddlib
14630 (lambda* (#:key inputs #:allow-other-keys)
14631 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
14632 (local-dir "cddlib_guix"))
14634 (with-directory-excursion local-dir
14635 (invoke "tar" "xvf" cddlib-src))
14636 (let ((cddlib-src-folder
14637 (string-append local-dir "/"
14638 (list-ref (scandir local-dir) 2)
14640 (for-each make-file-writable (find-files "cdd_src" ".*"))
14644 (string-append "cdd_src/" (basename file))))
14645 (find-files cddlib-src-folder ".*[ch]$")))
14647 (add-after 'unpack 'fix-makefile
14649 ;; Remove system calls to 'git'.
14650 (substitute* "Makefile"
14651 (("^DESCRIPT:=pplacer-.*")
14653 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
14654 (substitute* "myocamlbuild.ml"
14655 (("git describe --tags --long .*\\\" with")
14657 "echo -n v" ,version "-" ,commit "\" with")))
14660 (lambda* (#:key outputs #:allow-other-keys)
14661 (let* ((out (assoc-ref outputs "out"))
14662 (bin (string-append out "/bin")))
14663 (copy-recursively "bin" bin))
14665 #:ocaml ,ocaml-4.07
14666 #:findlib ,ocaml4.07-findlib))
14668 `(("zlib" ,zlib "static")
14670 ("ocaml-ounit" ,(package-with-ocaml4.07 ocaml-ounit))
14671 ("ocaml-batteries" ,(package-with-ocaml4.07 ocaml-batteries))
14672 ("ocaml-camlzip" ,(package-with-ocaml4.07 camlzip))
14673 ("ocaml-csv" ,(package-with-ocaml4.07 ocaml-csv))
14674 ("ocaml-sqlite3" ,ocaml4.07-sqlite3)
14675 ("ocaml-xmlm" ,(package-with-ocaml4.07 ocaml-xmlm))
14676 ("ocaml-mcl" ,(package-with-ocaml4.07 ocaml-mcl))
14677 ("ocaml-gsl" ,ocaml4.07-gsl-1)))
14679 `(("cddlib-src" ,(package-source cddlib))
14680 ("ocamlbuild" ,(package-with-ocaml4.07 ocamlbuild))
14681 ("pkg-config" ,pkg-config)))
14683 `(("pplacer-scripts" ,pplacer-scripts)))
14684 (synopsis "Phylogenetic placement of biological sequences")
14686 "Pplacer places query sequences on a fixed reference phylogenetic tree
14687 to maximize phylogenetic likelihood or posterior probability according to a
14688 reference alignment. Pplacer is designed to be fast, to give useful
14689 information about uncertainty, and to offer advanced visualization and
14690 downstream analysis.")
14691 (home-page "https://matsen.fhcrc.org/pplacer/")
14692 (license license:gpl3))))
14694 ;; This package is installed alongside 'pplacer'. It is a separate package so
14695 ;; that it can use the python-build-system for the scripts that are
14696 ;; distributed alongside the main OCaml binaries.
14697 (define pplacer-scripts
14700 (name "pplacer-scripts")
14701 (build-system python-build-system)
14703 `(#:python ,python-2
14705 (modify-phases %standard-phases
14706 (add-after 'unpack 'enter-scripts-dir
14707 (lambda _ (chdir "scripts") #t))
14709 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t))
14710 (add-after 'install 'wrap-executables
14711 (lambda* (#:key inputs outputs #:allow-other-keys)
14712 (let* ((out (assoc-ref outputs "out"))
14713 (bin (string-append out "/bin")))
14714 (let ((path (string-append
14715 (assoc-ref inputs "hmmer") "/bin:"
14716 (assoc-ref inputs "infernal") "/bin")))
14718 (wrap-program (string-append bin "/refpkg_align.py")
14719 `("PATH" ":" prefix (,path))))
14720 (let ((path (string-append
14721 (assoc-ref inputs "hmmer") "/bin")))
14722 (wrap-program (string-append bin "/hrefpkg_query.py")
14723 `("PATH" ":" prefix (,path)))))
14726 `(("infernal" ,infernal)
14729 `(("python-biopython" ,python2-biopython)
14730 ("taxtastic" ,taxtastic)))
14731 (synopsis "Pplacer Python scripts")))
14733 (define-public python2-checkm-genome
14735 (name "python2-checkm-genome")
14740 (uri (pypi-uri "checkm-genome" version))
14743 "0bm8gpxjmzxsxxl8lzwqhgx8g1dlnmp6znz7wv3hgb0gdjbf9dzz"))))
14744 (build-system python-build-system)
14746 `(#:python ,python-2
14747 #:tests? #f)) ; some tests are interactive
14749 `(("python-dendropy" ,python2-dendropy)
14750 ("python-matplotlib" ,python2-matplotlib)
14751 ("python-numpy" ,python2-numpy)
14752 ("python-pysam" ,python2-pysam)
14753 ("python-scipy" ,python2-scipy)))
14754 (home-page "https://pypi.org/project/Checkm/")
14755 (synopsis "Assess the quality of putative genome bins")
14757 "CheckM provides a set of tools for assessing the quality of genomes
14758 recovered from isolates, single cells, or metagenomes. It provides robust
14759 estimates of genome completeness and contamination by using collocated sets of
14760 genes that are ubiquitous and single-copy within a phylogenetic lineage.
14761 Assessment of genome quality can also be examined using plots depicting key
14762 genomic characteristics (e.g., GC, coding density) which highlight sequences
14763 outside the expected distributions of a typical genome. CheckM also provides
14764 tools for identifying genome bins that are likely candidates for merging based
14765 on marker set compatibility, similarity in genomic characteristics, and
14766 proximity within a reference genome.")
14767 (license license:gpl3+)))
14769 (define-public umi-tools
14776 (uri (pypi-uri "umi_tools" version))
14779 "08y3vz1vcx09whmbsn722lcs6jl9wyrh9i4p3k8j4cb1i32bij4a"))))
14780 (build-system python-build-system)
14782 `(("python-pandas" ,python-pandas)
14783 ("python-future" ,python-future)
14784 ("python-scipy" ,python-scipy)
14785 ("python-matplotlib" ,python-matplotlib)
14786 ("python-regex" ,python-regex)
14787 ("python-pysam" ,python-pysam)))
14789 `(("python-cython" ,python-cython)))
14790 (home-page "https://github.com/CGATOxford/UMI-tools")
14791 (synopsis "Tools for analyzing unique modular identifiers")
14792 (description "This package provides tools for dealing with @dfn{Unique
14793 Molecular Identifiers} (UMIs) and @dfn{Random Molecular Tags} (RMTs) in
14794 genetic sequences. There are six tools: the @code{extract} and
14795 @code{whitelist} commands are used to prepare a fastq containing UMIs @code{+/-}
14796 cell barcodes for alignment. The remaining commands, @code{group},
14797 @code{dedup}, and @{count}/@code{count_tab}, are used to identify PCR
14798 duplicates using the UMIs and perform different levels of analysis depending
14799 on the needs of the user.")
14800 (license license:expat)))
14802 (define-public ataqv
14809 (uri (git-reference
14810 (url "https://github.com/ParkerLab/ataqv.git")
14812 (file-name (git-file-name name version))
14815 "031xr6jx1aprh26y5b1lv3gzrlmzg4alfl73vvshymx8cq8asrqi"))))
14816 (build-system gnu-build-system)
14819 (list (string-append "prefix=" (assoc-ref %outputs "out"))
14820 (string-append "BOOST_ROOT="
14821 (assoc-ref %build-inputs "boost"))
14822 (string-append "HTSLIB_ROOT="
14823 (assoc-ref %build-inputs "htslib")))
14824 #:test-target "test"
14826 (modify-phases %standard-phases
14827 (delete 'configure))))
14831 ("ncurses" ,ncurses)
14835 (home-page "https://github.com/ParkerLab/ataqv")
14836 (synopsis "Toolkit for quality control and visualization of ATAC-seq data")
14837 (description "This package provides a toolkit for measuring and comparing
14838 ATAC-seq results. It was written to make it easier to spot differences that
14839 might be caused by ATAC-seq library prep or sequencing. The main program,
14840 @code{ataqv}, examines aligned reads and reports some basic metrics.")
14841 (license license:gpl3+)))
14843 (define-public r-psiplot
14850 (uri (git-reference
14851 (url "https://github.com/kcha/psiplot.git")
14852 (commit (string-append "v" version))))
14853 (file-name (git-file-name name version))
14855 (base32 "08438h16cfry5kqh3y9hs8q1b1a8bxhblsm75knviz5r6q0n1jxh"))))
14856 (build-system r-build-system)
14858 `(("r-mass" ,r-mass)
14859 ("r-dplyr" ,r-dplyr)
14860 ("r-tidyr" ,r-tidyr)
14861 ("r-purrr" ,r-purrr)
14862 ("r-readr" ,r-readr)
14863 ("r-magrittr" ,r-magrittr)
14864 ("r-ggplot2" ,r-ggplot2)))
14865 (home-page "https://github.com/kcha/psiplot")
14866 (synopsis "Plot percent spliced-in values of alternatively-spliced exons")
14868 "PSIplot is an R package for generating plots of @dfn{percent
14869 spliced-in} (PSI) values of alternatively-spliced exons that were computed by
14870 vast-tools, an RNA-Seq pipeline for alternative splicing analysis. The plots
14871 are generated using @code{ggplot2}.")
14872 (license license:expat)))
14874 (define-public python-ont-fast5-api
14876 (name "python-ont-fast5-api")
14881 (uri (git-reference
14882 (url "https://github.com/nanoporetech/ont_fast5_api.git")
14883 (commit (string-append "release_" version))))
14884 (file-name (git-file-name name version))
14887 "03cbq4zbbwhll8ml2m9k8sa31mirsvcbjkrq1yna0kkzz9fad5fm"))))
14888 (build-system python-build-system)
14890 `(("python-numpy" ,python-numpy)
14891 ("python-six" ,python-six)
14892 ("python-h5py" ,python-h5py)
14893 ("python-progressbar33" ,python-progressbar33)))
14894 (home-page "https://github.com/nanoporetech/ont_fast5_api")
14895 (synopsis "Interface to HDF5 files of the Oxford Nanopore fast5 file format")
14897 "This package provides a concrete implementation of the fast5 file schema
14898 using the generic @code{h5py} library, plain-named methods to interact with
14899 and reflect the fast5 file schema, and tools to convert between
14900 @code{multi_read} and @code{single_read} formats.")
14901 (license license:mpl2.0)))
14903 (define-public tbsp
14904 (let ((commit "ec8fff4410cfb13a677dbbb95cbbc60217e64907")
14908 (version (git-version "1.0.0" revision commit))
14912 (uri (git-reference
14913 (url "https://github.com/phoenixding/tbsp.git")
14915 (file-name (git-file-name name version))
14918 "025ym14x8gbd6hb55lsinqj6f5qzw36i10klgs7ldzxxd7s39ki1"))))
14919 (build-system python-build-system)
14920 (arguments '(#:tests? #f)) ; no tests included
14922 `(("python-matplotlib" ,python-matplotlib)
14923 ("python-networkx" ,python-networkx)
14924 ("python-numpy" ,python-numpy)
14925 ("python-pybigwig" ,python-pybigwig)
14926 ("python-biopython" ,python-biopython)
14927 ("python-scikit-learn" ,python-scikit-learn)
14928 ("python-scipy" ,python-scipy)))
14929 (home-page "https://github.com/phoenixding/tbsp/")
14930 (synopsis "SNP-based trajectory inference")
14932 "Several studies focus on the inference of developmental and response
14933 trajectories from single cell RNA-Seq (scRNA-Seq) data. A number of
14934 computational methods, often referred to as pseudo-time ordering, have been
14935 developed for this task. CRISPR has also been used to reconstruct lineage
14936 trees by inserting random mutations. The tbsp package implements an
14937 alternative method to detect significant, cell type specific sequence
14938 mutations from scRNA-Seq data.")
14939 (license license:expat))))
14941 (define-public tabixpp
14947 (uri (git-reference
14948 (url "https://github.com/ekg/tabixpp")
14949 (commit (string-append "v" version))))
14950 (file-name (git-file-name name version))
14952 (base32 "1k2a3vbq96ic4lw72iwp5s3mwwc4xhdffjj584yn6l9637q9j1yd"))
14953 (modules '((guix build utils)))
14956 (delete-file-recursively "htslib") #t))))
14957 (build-system gnu-build-system)
14959 `(("htslib" ,htslib)
14962 `(#:tests? #f ; There are no tests to run.
14964 (modify-phases %standard-phases
14965 (delete 'configure) ; There is no configure phase.
14966 ;; The build phase needs overriding the location of htslib.
14968 (lambda* (#:key inputs #:allow-other-keys)
14969 (let ((htslib-ref (assoc-ref inputs "htslib")))
14971 (string-append "HTS_LIB=" htslib-ref "/lib/libhts.a")
14972 (string-append "INCLUDES= -I" htslib-ref "/include/htslib")
14973 "HTS_HEADERS=" ; No need to check for headers here.
14974 (string-append "LIBPATH=-L. -L" htslib-ref "/include")))))
14976 (lambda* (#:key outputs #:allow-other-keys)
14977 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
14978 (install-file "tabix++" bin))
14980 (home-page "https://github.com/ekg/tabixpp")
14981 (synopsis "C++ wrapper around tabix project")
14982 (description "This is a C++ wrapper around the Tabix project which abstracts
14983 some of the details of opening and jumping in tabix-indexed files.")
14984 (license license:expat)))
14986 (define-public smithwaterman
14987 (let ((commit "2610e259611ae4cde8f03c72499d28f03f6d38a7"))
14989 (name "smithwaterman")
14990 (version (git-version "0.0.0" "2" commit))
14993 (uri (git-reference
14994 (url "https://github.com/ekg/smithwaterman/")
14996 (file-name (git-file-name name version))
14998 (base32 "0i9d8zrxpiracw3mxzd9siybpy62p06rqz9mc2w93arajgbk45bs"))))
14999 (build-system gnu-build-system)
15001 `(#:tests? #f ; There are no tests to run.
15002 #:make-flags '("libsw.a" "all")
15004 (modify-phases %standard-phases
15005 (delete 'configure) ; There is no configure phase.
15007 (lambda* (#:key outputs #:allow-other-keys)
15008 (let* ((out (assoc-ref outputs "out"))
15009 (bin (string-append out "/bin"))
15010 (lib (string-append out "/lib")))
15011 (install-file "smithwaterman" bin)
15012 (install-file "libsw.a" lib))
15014 (home-page "https://github.com/ekg/smithwaterman")
15015 (synopsis "Implementation of the Smith-Waterman algorithm")
15016 (description "Implementation of the Smith-Waterman algorithm.")
15017 ;; The licensing terms are unclear: https://github.com/ekg/smithwaterman/issues/9.
15018 (license (list license:gpl2 license:expat)))))
15020 (define-public multichoose
15022 (name "multichoose")
15026 (uri (git-reference
15027 (url "https://github.com/ekg/multichoose/")
15028 (commit (string-append "v" version))))
15029 (file-name (git-file-name name version))
15031 (base32 "0ci5fqvmpamwgxvmyd79ygj6n3bnbl3vc7b6h1sxz58186sm3pfs"))))
15032 (build-system gnu-build-system)
15034 `(#:tests? #f ; Tests require node.
15036 (modify-phases %standard-phases
15037 (delete 'configure) ; There is no configure phase.
15039 (lambda* (#:key outputs #:allow-other-keys)
15040 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15041 ;; TODO: There are Python modules for these programs too.
15042 (install-file "multichoose" bin)
15043 (install-file "multipermute" bin))
15045 (home-page "https://github.com/ekg/multichoose")
15046 (synopsis "Efficient loopless multiset combination generation algorithm")
15047 (description "This library implements an efficient loopless multiset
15048 combination generation algorithm which is (approximately) described in
15049 \"Loopless algorithms for generating permutations, combinations, and other
15050 combinatorial configurations.\", G. Ehrlich - Journal of the ACM (JACM),
15051 1973. (Algorithm 7.)")
15052 (license license:expat)))
15054 (define-public fsom
15055 (let ((commit "a6ef318fbd347c53189384aef7f670c0e6ce89a3"))
15058 (version (git-version "0.0.0" "1" commit))
15061 (uri (git-reference
15062 (url "https://github.com/ekg/fsom/")
15064 (file-name (git-file-name name version))
15066 (base32 "0gw1lpvr812pywg9y546x0h1hhj261xwls41r6kqhddjlrcjc0pi"))))
15067 (build-system gnu-build-system)
15069 `(#:tests? #f ; There are no tests to run.
15071 (modify-phases %standard-phases
15072 (delete 'configure) ; There is no configure phase.
15074 (lambda* (#:key outputs #:allow-other-keys)
15075 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15076 (install-file "fsom" bin))
15078 (home-page "https://github.com/ekg/fsom")
15079 (synopsis "Manage SOM (Self-Organizing Maps) neural networks")
15080 (description "A tiny C library for managing SOM (Self-Organizing Maps)
15082 (license license:gpl3))))
15084 (define-public fastahack
15090 (uri (git-reference
15091 (url "https://github.com/ekg/fastahack/")
15092 (commit (string-append "v" version))))
15093 (file-name (git-file-name name version))
15095 (base32 "0rp1blskhzxf7vbh253ibpxbgl9wwgyzf1wbkxndi08d3j4vcss9"))))
15096 (build-system gnu-build-system)
15098 `(#:tests? #f ; Unclear how to run tests: https://github.com/ekg/fastahack/issues/15
15100 (modify-phases %standard-phases
15101 (delete 'configure) ; There is no configure phase.
15103 (lambda* (#:key outputs #:allow-other-keys)
15104 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15105 (install-file "fastahack" bin))
15107 (home-page "https://github.com/ekg/fastahack")
15108 (synopsis "Indexing and sequence extraction from FASTA files")
15109 (description "Fastahack is a small application for indexing and
15110 extracting sequences and subsequences from FASTA files. The included library
15111 provides a FASTA reader and indexer that can be embedded into applications
15112 which would benefit from directly reading subsequences from FASTA files. The
15113 library automatically handles index file generation and use.")
15114 (license (list license:expat license:gpl2))))
15116 (define-public vcflib
15123 (uri (string-append "https://github.com/vcflib/vcflib/releases/"
15124 "download/v" version
15125 "/vcflib-" version "-src.tar.gz"))
15127 (base32 "14zzrg8hg8cq9cvq2wdvp21j7nmxxkjrbagw2apd2yqv2kyx42lm"))
15128 (modules '((guix build utils)))
15131 (for-each delete-file-recursively
15132 '("fastahack" "filevercmp" "fsom" "googletest" "intervaltree"
15133 "libVCFH" "multichoose" "smithwaterman" "tabixpp"))
15135 (build-system gnu-build-system)
15137 `(("htslib" ,htslib)
15143 ;; This package builds against the .o files so we need to extract the source.
15144 ("fastahack-src" ,(package-source fastahack))
15145 ("filevercmp-src" ,(package-source filevercmp))
15146 ("fsom-src" ,(package-source fsom))
15147 ("intervaltree-src" ,(package-source intervaltree))
15148 ("multichoose-src" ,(package-source multichoose))
15149 ("smithwaterman-src" ,(package-source smithwaterman))
15150 ("tabixpp-src" ,(package-source tabixpp))))
15152 `(#:tests? #f ; no tests
15153 #:make-flags (list (string-append "HTS_LIB="
15154 (assoc-ref %build-inputs "htslib")
15156 (string-append "HTS_INCLUDES= -I"
15157 (assoc-ref %build-inputs "htslib")
15159 (string-append "HTS_LDFLAGS= -L"
15160 (assoc-ref %build-inputs "htslib")
15161 "/include/htslib" " -lhts"))
15163 (modify-phases %standard-phases
15164 (delete 'configure)
15166 (add-after 'unpack 'unpack-submodule-sources
15167 (lambda* (#:key inputs #:allow-other-keys)
15168 (let ((unpack (lambda (source target)
15170 (with-directory-excursion target
15171 (if (file-is-directory? (assoc-ref inputs source))
15172 (copy-recursively (assoc-ref inputs source) ".")
15173 (invoke "tar" "xvf"
15174 (assoc-ref inputs source)
15175 "--strip-components=1"))))))
15177 (unpack "fastahack-src" "fastahack")
15178 (unpack "filevercmp-src" "filevercmp")
15179 (unpack "fsom-src" "fsom")
15180 (unpack "intervaltree-src" "intervaltree")
15181 (unpack "multichoose-src" "multichoose")
15182 (unpack "smithwaterman-src" "smithwaterman")
15183 (unpack "tabixpp-src" "tabixpp")))))
15185 (lambda* (#:key inputs make-flags #:allow-other-keys)
15186 (let ((htslib (assoc-ref inputs "htslib")))
15187 (with-directory-excursion "tabixpp"
15188 (substitute* "Makefile"
15189 (("-Ihtslib") (string-append "-I" htslib "/include/htslib"))
15190 (("-Lhtslib") (string-append "-L" htslib "/lib/htslib"))
15191 (("htslib/htslib") (string-append htslib "/include/htslib")))
15193 (string-append "HTS_LIB=" htslib "/lib/libhts.a")))
15194 (apply invoke "make" "CC=gcc" "CFLAGS=-Itabixpp" make-flags))))
15196 (lambda* (#:key outputs #:allow-other-keys)
15197 (let ((bin (string-append (assoc-ref outputs "out") "/bin"))
15198 (lib (string-append (assoc-ref outputs "out") "/lib")))
15199 (for-each (lambda (file)
15200 (install-file file bin))
15201 (find-files "bin" ".*"))
15202 ;; The header files in src/ do not interface libvcflib,
15203 ;; therefore they are left out.
15204 (install-file "libvcflib.a" lib))
15206 (home-page "https://github.com/vcflib/vcflib/")
15207 (synopsis "Library for parsing and manipulating VCF files")
15208 (description "Vcflib provides methods to manipulate and interpret
15209 sequence variation as it can be described by VCF. It is both an API for parsing
15210 and operating on records of genomic variation as it can be described by the VCF
15211 format, and a collection of command-line utilities for executing complex
15212 manipulations on VCF files.")
15213 (license license:expat)))
15215 (define-public freebayes
15216 (let ((commit "3ce827d8ebf89bb3bdc097ee0fe7f46f9f30d5fb")
15221 (version (git-version version revision commit))
15224 (uri (git-reference
15225 (url "https://github.com/ekg/freebayes.git")
15227 (file-name (git-file-name name version))
15229 (base32 "1sbzwmcbn78ybymjnhwk7qc5r912azy5vqz2y7y81616yc3ba2a2"))))
15230 (build-system gnu-build-system)
15232 `(("bamtools" ,bamtools)
15236 `(("bc" ,bc) ; Needed for running tests.
15237 ("samtools" ,samtools) ; Needed for running tests.
15238 ("parallel" ,parallel) ; Needed for running tests.
15239 ("perl" ,perl) ; Needed for running tests.
15240 ("procps" ,procps) ; Needed for running tests.
15241 ("python" ,python-2) ; Needed for running tests.
15242 ("vcflib-src" ,(package-source vcflib))
15243 ;; These are submodules for the vcflib version used in freebayes.
15244 ;; This package builds against the .o files so we need to extract the source.
15245 ("tabixpp-src" ,(package-source tabixpp))
15246 ("smithwaterman-src" ,(package-source smithwaterman))
15247 ("multichoose-src" ,(package-source multichoose))
15248 ("fsom-src" ,(package-source fsom))
15249 ("filevercmp-src" ,(package-source filevercmp))
15250 ("fastahack-src" ,(package-source fastahack))
15251 ("intervaltree-src" ,(package-source intervaltree))
15252 ;; These submodules are needed to run the tests.
15253 ("bash-tap-src" ,(package-source bash-tap))
15254 ("test-simple-bash-src"
15257 (uri (git-reference
15258 (url "https://github.com/ingydotnet/test-simple-bash/")
15259 (commit "124673ff204b01c8e96b7fc9f9b32ee35d898acc")))
15260 (file-name "test-simple-bash-src-checkout")
15262 (base32 "043plp6z0x9yf7mdpky1fw7zcpwn1p47px95w9mh16603zqqqpga"))))))
15266 (string-append "BAMTOOLS_ROOT="
15267 (assoc-ref %build-inputs "bamtools")))
15268 #:test-target "test"
15270 (modify-phases %standard-phases
15271 (delete 'configure)
15272 (add-after 'unpack 'fix-tests
15274 (substitute* "test/t/01_call_variants.t"
15275 (("grep -P \"\\(\\\\t500\\$\\|\\\\t11000\\$\\|\\\\t1000\\$\\)\"")
15276 "grep -E ' (500|11000|1000)$'"))
15278 (add-after 'unpack 'unpack-submodule-sources
15279 (lambda* (#:key inputs #:allow-other-keys)
15280 (let ((unpack (lambda (source target)
15281 (with-directory-excursion target
15282 (if (file-is-directory? (assoc-ref inputs source))
15283 (copy-recursively (assoc-ref inputs source) ".")
15284 (invoke "tar" "xvf"
15285 (assoc-ref inputs source)
15286 "--strip-components=1"))))))
15288 (unpack "vcflib-src" "vcflib")
15289 (unpack "fastahack-src" "vcflib/fastahack")
15290 (unpack "filevercmp-src" "vcflib/filevercmp")
15291 (unpack "fsom-src" "vcflib/fsom")
15292 (unpack "intervaltree-src" "vcflib/intervaltree")
15293 (unpack "multichoose-src" "vcflib/multichoose")
15294 (unpack "smithwaterman-src" "vcflib/smithwaterman")
15295 (unpack "tabixpp-src" "vcflib/tabixpp")
15296 (unpack "test-simple-bash-src" "test/test-simple-bash")
15297 (unpack "bash-tap-src" "test/bash-tap")))))
15298 (add-after 'unpack-submodule-sources 'fix-makefiles
15300 ;; We don't have the .git folder to get the version tag from.
15301 (substitute* "vcflib/Makefile"
15302 (("^GIT_VERSION.*")
15303 (string-append "GIT_VERSION = v" ,version)))
15304 (substitute* "src/Makefile"
15305 (("-I\\$\\(BAMTOOLS_ROOT\\)/src")
15306 "-I$(BAMTOOLS_ROOT)/include/bamtools"))
15308 (add-before 'build 'build-tabixpp-and-vcflib
15309 (lambda* (#:key inputs make-flags #:allow-other-keys)
15310 (with-directory-excursion "vcflib"
15311 (with-directory-excursion "tabixpp"
15312 (apply invoke "make"
15313 (string-append "HTS_LIB="
15314 (assoc-ref inputs "htslib")
15317 (apply invoke "make"
15318 (string-append "CFLAGS=-Itabixpp")
15322 (lambda* (#:key outputs #:allow-other-keys)
15323 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
15324 (install-file "bin/freebayes" bin)
15325 (install-file "bin/bamleftalign" bin))
15327 (home-page "https://github.com/ekg/freebayes")
15328 (synopsis "Haplotype-based variant detector")
15329 (description "FreeBayes is a Bayesian genetic variant detector designed to
15330 find small polymorphisms, specifically SNPs (single-nucleotide polymorphisms),
15331 indels (insertions and deletions), MNPs (multi-nucleotide polymorphisms), and
15332 complex events (composite insertion and substitution events) smaller than the
15333 length of a short-read sequencing alignment.")
15334 (license license:expat))))
15336 (define-public samblaster
15338 (name "samblaster")
15342 (uri (git-reference
15343 (url "https://github.com/GregoryFaust/samblaster.git")
15344 (commit (string-append "v." version))))
15345 (file-name (git-file-name name version))
15348 "0iv2ddfw8363vb2x8gr3p8g88whb6mb9m0pf71i2cqsbv6jghap7"))))
15349 (build-system gnu-build-system)
15351 `(#:tests? #f ; there are none
15353 (modify-phases %standard-phases
15354 (delete 'configure) ; There is no configure phase.
15356 (lambda* (#:key outputs #:allow-other-keys)
15357 (install-file "samblaster"
15358 (string-append (assoc-ref outputs "out") "/bin"))
15360 (home-page "https://github.com/GregoryFaust/samblaster")
15361 (synopsis "Mark duplicates in paired-end SAM files")
15362 (description "Samblaster is a fast and flexible program for marking
15363 duplicates in read-id grouped paired-end SAM files. It can also optionally
15364 output discordant read pairs and/or split read mappings to separate SAM files,
15365 and/or unmapped/clipped reads to a separate FASTQ file. When marking
15366 duplicates, samblaster will require approximately 20MB of memory per 1M read
15368 (license license:expat)))
15370 (define-public r-velocyto
15371 (let ((commit "d7790346cb99f49ab9c2b23ba70dcf9d2c9fc350")
15374 (name "r-velocyto")
15375 (version (git-version "0.6" revision commit))
15379 (uri (git-reference
15380 (url "https://github.com/velocyto-team/velocyto.R.git")
15382 (file-name (git-file-name name version))
15385 "16wqf70j7rd7pay2q513iyz12i8n9vrpg1bisah4lddbcpx5dz1n"))))
15386 (build-system r-build-system)
15388 `(("boost" ,boost)))
15390 `(("r-hdf5r" ,r-hdf5r)
15393 ("r-pcamethods" ,r-pcamethods)
15395 ("r-rcpparmadillo" ,r-rcpparmadillo)
15396 ;; Suggested packages
15397 ("r-rtsne" ,r-rtsne)
15398 ("r-cluster" ,r-cluster)
15399 ("r-abind" ,r-abind)
15401 ("r-biocgenerics" ,r-biocgenerics)
15402 ("r-genomicalignments" ,r-genomicalignments)
15403 ("r-rsamtools" ,r-rsamtools)
15404 ("r-edger" ,r-edger)
15405 ("r-igraph" ,r-igraph)))
15406 (home-page "https://velocyto.org")
15407 (synopsis "RNA velocity estimation in R")
15409 "This package provides basic routines for estimation of gene-specific
15410 transcriptional derivatives and visualization of the resulting velocity
15412 (license license:gpl3))))
15414 (define-public methyldackel
15416 (name "methyldackel")
15420 (uri (git-reference
15421 (url "https://github.com/dpryan79/MethylDackel.git")
15423 (file-name (git-file-name name version))
15426 "10gh8k0ca92kywnrw5pkacq3g6r8s976s12k8jhp8g3g49q9a97g"))))
15427 (build-system gnu-build-system)
15429 `(#:test-target "test"
15432 (string-append "prefix="
15433 (assoc-ref %outputs "out") "/bin/"))
15435 (modify-phases %standard-phases
15436 (replace 'configure
15437 (lambda* (#:key outputs #:allow-other-keys)
15438 (substitute* "Makefile"
15439 (("install MethylDackel \\$\\(prefix\\)" match)
15440 (string-append "install -d $(prefix); " match)))
15443 `(("htslib" ,htslib)
15445 ;; Needed for tests
15447 `(("python" ,python-wrapper)))
15448 (home-page "https://github.com/dpryan79/MethylDackel")
15449 (synopsis "Universal methylation extractor for BS-seq experiments")
15451 "MethylDackel will process a coordinate-sorted and indexed BAM or CRAM
15452 file containing some form of BS-seq alignments and extract per-base
15453 methylation metrics from them. MethylDackel requires an indexed fasta file
15454 containing the reference genome as well.")
15455 ;; See https://github.com/dpryan79/MethylDackel/issues/85
15456 (license license:expat)))
15458 (define-public python-gffutils
15459 ;; The latest release is older more than a year than the latest commit
15460 (let ((commit "4034c54600813b1402945e12faa91b3a53162cf1")
15463 (name "python-gffutils")
15464 (version (git-version "0.9" revision commit))
15468 (uri (git-reference
15469 (url "https://github.com/daler/gffutils.git")
15471 (file-name (git-file-name name version))
15474 "1rwafjdnbir5wnk0ap06ww4lra3p5frhy7mfs03rlldgfnwxymsn"))))
15475 (build-system python-build-system)
15478 (modify-phases %standard-phases
15481 ;; Tests need to access the HOME directory
15482 (setenv "HOME" "/tmp")
15483 (invoke "nosetests" "-a" "!slow")))
15484 (add-after 'unpack 'make-gz-files-writable
15486 (for-each make-file-writable
15487 (find-files "." "\\.gz"))
15490 `(("python-argcomplete" ,python-argcomplete)
15491 ("python-argh" ,python-argh)
15492 ("python-biopython" ,python-biopython)
15493 ("python-pybedtools" ,python-pybedtools)
15494 ("python-pyfaidx" ,python-pyfaidx)
15495 ("python-simplejson" ,python-simplejson)
15496 ("python-six" ,python-six)))
15498 `(("python-nose" , python-nose)))
15499 (home-page "https://github.com/daler/gffutils")
15500 (synopsis "Tool for manipulation of GFF and GTF files")
15502 "python-gffutils is a Python package for working with and manipulating
15503 the GFF and GTF format files typically used for genomic annotations. The
15504 files are loaded into a SQLite database, allowing much more complex
15505 manipulation of hierarchical features (e.g., genes, transcripts, and exons)
15506 than is possible with plain-text methods alone.")
15507 (license license:expat))))
15509 (define-public libsbml
15515 (uri (string-append "mirror://sourceforge/sbml/libsbml/"
15516 version "/stable/libSBML-"
15517 version "-core-src.tar.gz"))
15520 "0slkagrk3nfi2qsksv6b1brj6zhx4bj4bkib2sdycvrcd10ql2lh"))))
15521 (build-system cmake-build-system)
15523 `(#:test-target "test"
15525 (list "-DWITH_CHECK=ON"
15526 (string-append "-DLIBXML_LIBRARY="
15527 (assoc-ref %build-inputs "libxml2")
15529 (string-append "-DLIBXML_INCLUDE_DIR="
15530 (assoc-ref %build-inputs "libxml2")
15531 "/include/libxml2"))))
15533 `(("libxml2" ,libxml2)))
15537 (home-page "http://sbml.org/Software/libSBML")
15538 (synopsis "Process SBML files and data streams")
15539 (description "LibSBML is a library to help you read, write, manipulate,
15540 translate, and validate SBML files and data streams. The @dfn{Systems Biology
15541 Markup Language} (SBML) is an interchange format for computer models of
15542 biological processes. SBML is useful for models of metabolism, cell
15543 signaling, and more. It continues to be evolved and expanded by an
15544 international community.")
15545 (license license:lgpl2.1+)))