1 ;;; GNU Guix --- Functional package management for GNU
2 ;;; Copyright © 2014, 2015, 2016, 2017, 2018, 2019 Ricardo Wurmus <rekado@elephly.net>
3 ;;; Copyright © 2015, 2016, 2017, 2018 Ben Woodcroft <donttrustben@gmail.com>
4 ;;; Copyright © 2015, 2016 Pjotr Prins <pjotr.guix@thebird.nl>
5 ;;; Copyright © 2015 Andreas Enge <andreas@enge.fr>
6 ;;; Copyright © 2016 Roel Janssen <roel@gnu.org>
7 ;;; Copyright © 2016, 2017, 2018, 2019 Efraim Flashner <efraim@flashner.co.il>
8 ;;; Copyright © 2016 Marius Bakke <mbakke@fastmail.com>
9 ;;; Copyright © 2016, 2018 Raoul Bonnal <ilpuccio.febo@gmail.com>
10 ;;; Copyright © 2017, 2018 Tobias Geerinckx-Rice <me@tobias.gr>
11 ;;; Copyright © 2017 Arun Isaac <arunisaac@systemreboot.net>
12 ;;; Copyright © 2018 Joshua Sierles, Nextjournal <joshua@nextjournal.com>
13 ;;; Copyright © 2018 Gábor Boskovits <boskovits@gmail.com>
14 ;;; Copyright © 2018 Mădălin Ionel Patrașcu <madalinionel.patrascu@mdc-berlin.de>
15 ;;; Copyright © 2019 Maxim Cournoyer <maxim.cournoyer@gmail.com>
17 ;;; This file is part of GNU Guix.
19 ;;; GNU Guix is free software; you can redistribute it and/or modify it
20 ;;; under the terms of the GNU General Public License as published by
21 ;;; the Free Software Foundation; either version 3 of the License, or (at
22 ;;; your option) any later version.
24 ;;; GNU Guix is distributed in the hope that it will be useful, but
25 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
26 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
27 ;;; GNU General Public License for more details.
29 ;;; You should have received a copy of the GNU General Public License
30 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
32 (define-module (gnu packages bioinformatics)
33 #:use-module ((guix licenses) #:prefix license:)
34 #:use-module (guix packages)
35 #:use-module (guix utils)
36 #:use-module (guix download)
37 #:use-module (guix git-download)
38 #:use-module (guix hg-download)
39 #:use-module (guix build-system ant)
40 #:use-module (guix build-system gnu)
41 #:use-module (guix build-system cmake)
42 #:use-module (guix build-system haskell)
43 #:use-module (guix build-system meson)
44 #:use-module (guix build-system ocaml)
45 #:use-module (guix build-system perl)
46 #:use-module (guix build-system python)
47 #:use-module (guix build-system r)
48 #:use-module (guix build-system ruby)
49 #:use-module (guix build-system scons)
50 #:use-module (guix build-system trivial)
51 #:use-module (gnu packages)
52 #:use-module (gnu packages autotools)
53 #:use-module (gnu packages algebra)
54 #:use-module (gnu packages base)
55 #:use-module (gnu packages bash)
56 #:use-module (gnu packages bison)
57 #:use-module (gnu packages bioconductor)
58 #:use-module (gnu packages boost)
59 #:use-module (gnu packages check)
60 #:use-module (gnu packages code)
61 #:use-module (gnu packages compression)
62 #:use-module (gnu packages cpio)
63 #:use-module (gnu packages cran)
64 #:use-module (gnu packages curl)
65 #:use-module (gnu packages documentation)
66 #:use-module (gnu packages databases)
67 #:use-module (gnu packages datastructures)
68 #:use-module (gnu packages file)
69 #:use-module (gnu packages flex)
70 #:use-module (gnu packages gawk)
71 #:use-module (gnu packages gcc)
72 #:use-module (gnu packages gd)
73 #:use-module (gnu packages gtk)
74 #:use-module (gnu packages glib)
75 #:use-module (gnu packages graph)
76 #:use-module (gnu packages groff)
77 #:use-module (gnu packages guile)
78 #:use-module (gnu packages guile-xyz)
79 #:use-module (gnu packages haskell)
80 #:use-module (gnu packages haskell-check)
81 #:use-module (gnu packages haskell-web)
82 #:use-module (gnu packages image)
83 #:use-module (gnu packages imagemagick)
84 #:use-module (gnu packages java)
85 #:use-module (gnu packages java-compression)
86 #:use-module (gnu packages jemalloc)
87 #:use-module (gnu packages dlang)
88 #:use-module (gnu packages linux)
89 #:use-module (gnu packages lisp)
90 #:use-module (gnu packages logging)
91 #:use-module (gnu packages machine-learning)
92 #:use-module (gnu packages man)
93 #:use-module (gnu packages maths)
94 #:use-module (gnu packages mpi)
95 #:use-module (gnu packages ncurses)
96 #:use-module (gnu packages ocaml)
97 #:use-module (gnu packages pcre)
98 #:use-module (gnu packages parallel)
99 #:use-module (gnu packages pdf)
100 #:use-module (gnu packages perl)
101 #:use-module (gnu packages perl-check)
102 #:use-module (gnu packages pkg-config)
103 #:use-module (gnu packages popt)
104 #:use-module (gnu packages protobuf)
105 #:use-module (gnu packages python)
106 #:use-module (gnu packages python-compression)
107 #:use-module (gnu packages python-web)
108 #:use-module (gnu packages python-xyz)
109 #:use-module (gnu packages readline)
110 #:use-module (gnu packages ruby)
111 #:use-module (gnu packages serialization)
112 #:use-module (gnu packages shells)
113 #:use-module (gnu packages sphinx)
114 #:use-module (gnu packages statistics)
115 #:use-module (gnu packages swig)
116 #:use-module (gnu packages tbb)
117 #:use-module (gnu packages tex)
118 #:use-module (gnu packages texinfo)
119 #:use-module (gnu packages textutils)
120 #:use-module (gnu packages time)
121 #:use-module (gnu packages tls)
122 #:use-module (gnu packages vim)
123 #:use-module (gnu packages web)
124 #:use-module (gnu packages xml)
125 #:use-module (gnu packages xorg)
126 #:use-module (srfi srfi-1)
127 #:use-module (ice-9 match))
129 (define-public aragorn
136 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
140 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
141 (build-system gnu-build-system)
143 `(#:tests? #f ; there are no tests
145 (modify-phases %standard-phases
155 (string-append "aragorn" ,version ".c"))
158 (lambda* (#:key outputs #:allow-other-keys)
159 (let* ((out (assoc-ref outputs "out"))
160 (bin (string-append out "/bin"))
161 (man (string-append out "/share/man/man1")))
162 (install-file "aragorn" bin)
163 (install-file "aragorn.1" man))
165 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
166 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
168 "Aragorn identifies transfer RNA, mitochondrial RNA and
169 transfer-messenger RNA from nucleotide sequences, based on homology to known
170 tRNA consensus sequences and RNA structure. It also outputs the secondary
171 structure of the predicted RNA.")
172 (license license:gpl2)))
180 ;; BamM is not available on pypi.
182 (url "https://github.com/Ecogenomics/BamM.git")
185 (file-name (git-file-name name version))
188 "1p83ahi984ipslxlg4yqy1gdnya9rkn1v71z8djgxkm9d2chw4c5"))
189 (modules '((guix build utils)))
192 ;; Delete bundled htslib.
193 (delete-file-recursively "c/htslib-1.3.1")
195 (build-system python-build-system)
197 `(#:python ,python-2 ; BamM is Python 2 only.
198 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
199 ;; been modified from its original form.
201 (let ((htslib (assoc-ref %build-inputs "htslib")))
202 (list "--with-libhts-lib" (string-append htslib "/lib")
203 "--with-libhts-inc" (string-append htslib "/include/htslib")))
205 (modify-phases %standard-phases
206 (add-after 'unpack 'autogen
208 (with-directory-excursion "c"
209 (let ((sh (which "sh")))
210 (for-each make-file-writable (find-files "." ".*"))
211 ;; Use autogen so that 'configure' works.
212 (substitute* "autogen.sh" (("/bin/sh") sh))
213 (setenv "CONFIG_SHELL" sh)
214 (invoke "./autogen.sh")))
217 ;; Run tests after installation so compilation only happens once.
219 (add-after 'install 'wrap-executable
220 (lambda* (#:key outputs #:allow-other-keys)
221 (let* ((out (assoc-ref outputs "out"))
222 (path (getenv "PATH")))
223 (wrap-program (string-append out "/bin/bamm")
224 `("PATH" ":" prefix (,path))))
226 (add-after 'wrap-executable 'post-install-check
227 (lambda* (#:key inputs outputs #:allow-other-keys)
229 (string-append (assoc-ref outputs "out")
234 (assoc-ref outputs "out")
236 (string-take (string-take-right
237 (assoc-ref inputs "python") 5) 3)
239 (getenv "PYTHONPATH")))
240 ;; There are 2 errors printed, but they are safe to ignore:
241 ;; 1) [E::hts_open_format] fail to open file ...
242 ;; 2) samtools view: failed to open ...
246 `(("autoconf" ,autoconf)
247 ("automake" ,automake)
250 ("python-nose" ,python2-nose)
251 ("python-pysam" ,python2-pysam)))
253 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
254 ("samtools" ,samtools)
258 ("coreutils" ,coreutils)))
260 `(("python-numpy" ,python2-numpy)))
261 (home-page "http://ecogenomics.github.io/BamM/")
262 (synopsis "Metagenomics-focused BAM file manipulator")
264 "BamM is a C library, wrapped in python, to efficiently generate and
265 parse BAM files, specifically for the analysis of metagenomic data. For
266 instance, it implements several methods to assess contig-wise read coverage.")
267 (license license:lgpl3+)))
269 (define-public bamtools
276 (url "https://github.com/pezmaster31/bamtools.git")
277 (commit (string-append "v" version))))
278 (file-name (git-file-name name version))
281 "0nfb2ypcx9959xnbz6wxh6py3xfizgmg8nrknxl95c507m9hmq8b"))))
282 (build-system cmake-build-system)
284 `(#:tests? #f ;no "check" target
286 (modify-phases %standard-phases
288 'configure 'set-ldflags
289 (lambda* (#:key outputs #:allow-other-keys)
293 (assoc-ref outputs "out") "/lib/bamtools"))
295 (inputs `(("zlib" ,zlib)))
296 (home-page "https://github.com/pezmaster31/bamtools")
297 (synopsis "C++ API and command-line toolkit for working with BAM data")
299 "BamTools provides both a C++ API and a command-line toolkit for handling
301 (license license:expat)))
303 (define-public bcftools
309 (uri (string-append "https://github.com/samtools/bcftools/"
311 version "/bcftools-" version ".tar.bz2"))
314 "1j3h638i8kgihzyrlnpj82xg1b23sijibys9hvwari3fy7kd0dkg"))
315 (modules '((guix build utils)))
317 ;; Delete bundled htslib.
318 (delete-file-recursively "htslib-1.9")
320 (build-system gnu-build-system)
323 (list "--enable-libgsl")
326 (modify-phases %standard-phases
327 (add-before 'check 'patch-tests
329 (substitute* "test/test.pl"
330 (("/bin/bash") (which "bash")))
338 (home-page "https://samtools.github.io/bcftools/")
339 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
341 "BCFtools is a set of utilities that manipulate variant calls in the
342 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
343 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
344 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
345 (license (list license:gpl3+ license:expat))))
347 (define-public bedops
354 (url "https://github.com/bedops/bedops.git")
355 (commit (string-append "v" version))))
356 (file-name (git-file-name name version))
359 "0mmgsgwz5r9w76hzgxkxc9s9lkdhhaf7vr6i02b09vbswvs1fyqx"))))
360 (build-system gnu-build-system)
363 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
365 (modify-phases %standard-phases
366 (add-after 'unpack 'unpack-tarballs
368 ;; FIXME: Bedops includes tarballs of minimally patched upstream
369 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
370 ;; libraries because at least one of the libraries (zlib) is
371 ;; patched to add a C++ function definition (deflateInit2cpp).
372 ;; Until the Bedops developers offer a way to link against system
373 ;; libraries we have to build the in-tree copies of these three
376 ;; See upstream discussion:
377 ;; https://github.com/bedops/bedops/issues/124
379 ;; Unpack the tarballs to benefit from shebang patching.
380 (with-directory-excursion "third-party"
381 (invoke "tar" "xvf" "jansson-2.6.tar.bz2")
382 (invoke "tar" "xvf" "zlib-1.2.7.tar.bz2")
383 (invoke "tar" "xvf" "bzip2-1.0.6.tar.bz2"))
384 ;; Disable unpacking of tarballs in Makefile.
385 (substitute* "system.mk/Makefile.linux"
386 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
387 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
388 (substitute* "third-party/zlib-1.2.7/Makefile.in"
389 (("^SHELL=.*$") "SHELL=bash\n"))
391 (delete 'configure))))
392 (home-page "https://github.com/bedops/bedops")
393 (synopsis "Tools for high-performance genomic feature operations")
395 "BEDOPS is a suite of tools to address common questions raised in genomic
396 studies---mostly with regard to overlap and proximity relationships between
397 data sets. It aims to be scalable and flexible, facilitating the efficient
398 and accurate analysis and management of large-scale genomic data.
400 BEDOPS provides tools that perform highly efficient and scalable Boolean and
401 other set operations, statistical calculations, archiving, conversion and
402 other management of genomic data of arbitrary scale. Tasks can be easily
403 split by chromosome for distributing whole-genome analyses across a
404 computational cluster.")
405 (license license:gpl2+)))
407 (define-public bedtools
413 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
414 "download/v" version "/"
415 "bedtools-" version ".tar.gz"))
418 "1ndg5yknrxl4djx8ddzgk12rrbiidfpmkkg5z3f95jzryfxarhn8"))))
419 (build-system gnu-build-system)
421 '(#:test-target "test"
423 (list (string-append "prefix=" (assoc-ref %outputs "out")))
425 (modify-phases %standard-phases
426 (delete 'configure))))
427 (native-inputs `(("python" ,python-2)))
429 `(("samtools" ,samtools)
431 (home-page "https://github.com/arq5x/bedtools2")
432 (synopsis "Tools for genome analysis and arithmetic")
434 "Collectively, the bedtools utilities are a swiss-army knife of tools for
435 a wide-range of genomics analysis tasks. The most widely-used tools enable
436 genome arithmetic: that is, set theory on the genome. For example, bedtools
437 allows one to intersect, merge, count, complement, and shuffle genomic
438 intervals from multiple files in widely-used genomic file formats such as BAM,
440 (license license:gpl2)))
442 ;; Later releases of bedtools produce files with more columns than
443 ;; what Ribotaper expects.
444 (define-public bedtools-2.18
445 (package (inherit bedtools)
450 (uri (string-append "https://github.com/arq5x/bedtools2/"
451 "releases/download/v" version
452 "/bedtools-" version ".tar.gz"))
455 "11rvca19ncg03kxd0wzlfx5ws7r3nisd0z8s9j9n182d8ksp2pxz"))))
457 '(#:test-target "test"
459 (modify-phases %standard-phases
462 (lambda* (#:key outputs #:allow-other-keys)
463 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
464 (for-each (lambda (file)
465 (install-file file bin))
466 (find-files "bin" ".*")))
469 ;; Needed for pybedtools.
470 (define-public bedtools-2.26
471 (package (inherit bedtools)
476 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
477 "download/v" version "/"
478 "bedtools-" version ".tar.gz"))
481 "0jhavwifnf7lmkb11h9y7dynr8d699h0rd2l52j1pfgircr2zwv5"))))))
490 (url "https://github.com/PacificBiosciences/pbbam.git")
492 (file-name (git-file-name name version))
495 "0h9gkrpf2lrxklxp72xfl5bi3h5zcm5hprrya9gf0hr3xwlbpp0x"))))
496 (build-system meson-build-system)
499 (modify-phases %standard-phases
500 (add-after 'unpack 'find-googletest
501 (lambda* (#:key inputs #:allow-other-keys)
502 ;; It doesn't find gtest_main because there's no pkg-config file
503 ;; for it. Find it another way.
504 (substitute* "tests/meson.build"
505 (("pbbam_gtest_dep = dependency\\('gtest_main'.*")
506 (format #f "cpp = meson.get_compiler('cpp')
507 pbbam_gtest_dep = cpp.find_library('gtest_main', dirs : '~a')\n"
508 (assoc-ref inputs "googletest"))))
510 ;; TODO: tests/pbbam_test cannot be linked
511 ;; ld: tests/59830eb@@pbbam_test@exe/src_test_Accuracy.cpp.o:
512 ;; undefined reference to symbol '_ZTIN7testing4TestE'
513 ;; ld: /gnu/store/...-googletest-1.8.0/lib/libgtest.so:
514 ;; error adding symbols: DSO missing from command line
516 #:configure-flags '("-Dtests=false")))
517 ;; These libraries are listed as "Required" in the pkg-config file.
523 ("samtools" ,samtools)))
525 `(("googletest" ,googletest)
526 ("pkg-config" ,pkg-config)
527 ("python" ,python-wrapper))) ; for tests
528 (home-page "https://github.com/PacificBiosciences/pbbam")
529 (synopsis "Work with PacBio BAM files")
531 "The pbbam software package provides components to create, query, and
532 edit PacBio BAM files and associated indices. These components include a core
533 C++ library, bindings for additional languages, and command-line utilities.
534 This library is not intended to be used as a general-purpose BAM utility - all
535 input and output BAMs must adhere to the PacBio BAM format specification.
536 Non-PacBio BAMs will cause exceptions to be thrown.")
537 (license license:bsd-3)))
539 (define-public blasr-libcpp
541 (name "blasr-libcpp")
546 (url "https://github.com/PacificBiosciences/blasr_libcpp.git")
548 (file-name (git-file-name name version))
551 "0cn5l42zyq67sj0g2imqkhayz2iqvv0a1pgpbmlq0qynjmsrbfd2"))))
552 (build-system meson-build-system)
555 (modify-phases %standard-phases
556 (add-after 'unpack 'link-with-hdf5
557 (lambda* (#:key inputs #:allow-other-keys)
558 (let ((hdf5 (assoc-ref inputs "hdf5")))
559 (substitute* "meson.build"
560 (("libblasr_deps = \\[" m)
563 (format #f "cpp.find_library('hdf5', dirs : '~a'), \
564 cpp.find_library('hdf5_cpp', dirs : '~a'), "
567 (add-after 'unpack 'find-googletest
568 (lambda* (#:key inputs #:allow-other-keys)
569 ;; It doesn't find gtest_main because there's no pkg-config file
570 ;; for it. Find it another way.
571 (substitute* "unittest/meson.build"
572 (("libblasr_gtest_dep = dependency\\('gtest_main'.*")
573 (format #f "cpp = meson.get_compiler('cpp')
574 libblasr_gtest_dep = cpp.find_library('gtest_main', dirs : '~a')\n"
575 (assoc-ref inputs "googletest"))))
577 ;; TODO: unittest/libblasr_unittest cannot be linked
578 ;; ld: ;; unittest/df08227@@libblasr_unittest@exe/alignment_utils_FileUtils_gtest.cpp.o:
579 ;; undefined reference to symbol
580 ;; '_ZN7testing8internal9DeathTest6CreateEPKcPKNS0_2REES3_iPPS1_'
581 ;; ld: /gnu/store/...-googletest-1.8.0/lib/libgtest.so:
582 ;; error adding symbols: DSO missing from command line
584 #:configure-flags '("-Dtests=false")))
591 `(("googletest" ,googletest)
592 ("pkg-config" ,pkg-config)))
593 (home-page "https://github.com/PacificBiosciences/blasr_libcpp")
594 (synopsis "Library for analyzing PacBio genomic sequences")
596 "This package provides three libraries used by applications for analyzing
597 PacBio genomic sequences. This library contains three sub-libraries: pbdata,
599 (license license:bsd-3)))
608 (url "https://github.com/PacificBiosciences/blasr.git")
610 (file-name (git-file-name name version))
613 "1skgy2mvz8gsgfh1gc2nfgwvpyzb1hpmp2cf2773h5wsj8nw22kl"))))
614 (build-system meson-build-system)
617 (modify-phases %standard-phases
618 (add-after 'unpack 'link-with-hdf5
619 (lambda* (#:key inputs #:allow-other-keys)
620 (let ((hdf5 (assoc-ref inputs "hdf5")))
621 (substitute* "meson.build"
622 (("blasr_deps = \\[" m)
625 (format #f "cpp.find_library('hdf5', dirs : '~a'), \
626 cpp.find_library('hdf5_cpp', dirs : '~a'), "
629 ;; Tests require "cram" executable, which is not packaged.
631 #:configure-flags '("-Dtests=false")))
634 ("blasr-libcpp" ,blasr-libcpp)
639 `(("pkg-config" ,pkg-config)))
640 (home-page "https://github.com/PacificBiosciences/blasr")
641 (synopsis "PacBio long read aligner")
643 "Blasr is a genomic sequence aligner for processing PacBio long reads.")
644 (license license:bsd-3)))
646 (define-public ribotaper
652 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
653 "files/RiboTaper/RiboTaper_Version_"
657 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
658 (build-system gnu-build-system)
661 (modify-phases %standard-phases
662 (add-after 'install 'wrap-executables
663 (lambda* (#:key inputs outputs #:allow-other-keys)
664 (let* ((out (assoc-ref outputs "out")))
667 (wrap-program (string-append out "/bin/" script)
668 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
669 '("create_annotations_files.bash"
670 "create_metaplots.bash"
671 "Ribotaper_ORF_find.sh"
675 `(("bedtools" ,bedtools-2.18)
676 ("samtools" ,samtools-0.1)
677 ("r-minimal" ,r-minimal)
678 ("r-foreach" ,r-foreach)
679 ("r-xnomial" ,r-xnomial)
681 ("r-multitaper" ,r-multitaper)
682 ("r-seqinr" ,r-seqinr)))
683 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
684 (synopsis "Define translated ORFs using ribosome profiling data")
686 "Ribotaper is a method for defining translated @dfn{open reading
687 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
688 provides the Ribotaper pipeline.")
689 (license license:gpl3+)))
691 (define-public ribodiff
699 (url "https://github.com/ratschlab/RiboDiff.git")
700 (commit (string-append "v" version))))
701 (file-name (git-file-name name version))
704 "0x75nlp7qnmm64jasbi6l21f2cy99r2cjyl6b4hr8zf2bq22drnz"))))
705 (build-system python-build-system)
709 (modify-phases %standard-phases
710 ;; Generate an installable executable script wrapper.
711 (add-after 'unpack 'patch-setup.py
713 (substitute* "setup.py"
714 (("^(.*)packages=.*" line prefix)
715 (string-append line "\n"
716 prefix "scripts=['scripts/TE.py'],\n")))
719 `(("python-numpy" ,python2-numpy)
720 ("python-matplotlib" ,python2-matplotlib)
721 ("python-scipy" ,python2-scipy)
722 ("python-statsmodels" ,python2-statsmodels)))
724 `(("python-mock" ,python2-mock)
725 ("python-nose" ,python2-nose)))
726 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
727 (synopsis "Detect translation efficiency changes from ribosome footprints")
728 (description "RiboDiff is a statistical tool that detects the protein
729 translational efficiency change from Ribo-Seq (ribosome footprinting) and
730 RNA-Seq data. It uses a generalized linear model to detect genes showing
731 difference in translational profile taking mRNA abundance into account. It
732 facilitates us to decipher the translational regulation that behave
733 independently with transcriptional regulation.")
734 (license license:gpl3+)))
736 (define-public bioawk
743 (url "https://github.com/lh3/bioawk.git")
744 (commit (string-append "v" version))))
745 (file-name (git-file-name name version))
748 "1pxc3zdnirxbf9a0az698hd8xdik7qkhypm7v6hn922x8y9qmspm"))))
749 (build-system gnu-build-system)
755 `(#:tests? #f ; There are no tests to run.
756 ;; Bison must generate files, before other targets can build.
759 (modify-phases %standard-phases
760 (delete 'configure) ; There is no configure phase.
762 (lambda* (#:key outputs #:allow-other-keys)
763 (let* ((out (assoc-ref outputs "out"))
764 (bin (string-append out "/bin"))
765 (man (string-append out "/share/man/man1")))
767 (copy-file "awk.1" (string-append man "/bioawk.1"))
768 (install-file "bioawk" bin))
770 (home-page "https://github.com/lh3/bioawk")
771 (synopsis "AWK with bioinformatics extensions")
772 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
773 support of several common biological data formats, including optionally gzip'ed
774 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
775 also adds a few built-in functions and a command line option to use TAB as the
776 input/output delimiter. When the new functionality is not used, bioawk is
777 intended to behave exactly the same as the original BWK awk.")
778 (license license:x11)))
780 (define-public python-pybedtools
782 (name "python-pybedtools")
786 (uri (pypi-uri "pybedtools" version))
789 "1xl454ijvd4dzfvqgfahad49b49j7qy710fq9xh1rvk42z6x5ssf"))))
790 (build-system python-build-system)
792 `(#:modules ((ice-9 ftw)
796 (guix build python-build-system))
797 ;; See https://github.com/daler/pybedtools/issues/192
799 (modify-phases %standard-phases
800 ;; See https://github.com/daler/pybedtools/issues/261
801 (add-after 'unpack 'disable-broken-tests
803 ;; This test (pybedtools.test.test_scripts.test_venn_mpl) needs a
804 ;; graphical environment.
805 (substitute* "pybedtools/test/test_scripts.py"
806 (("def test_venn_mpl")
807 "def _do_not_test_venn_mpl"))
808 (substitute* "pybedtools/test/test_helpers.py"
809 ;; Requires internet access.
810 (("def test_chromsizes")
811 "def _do_not_test_chromsizes")
812 ;; Broken as a result of the workaround used in the check phase
813 ;; (see: https://github.com/daler/pybedtools/issues/192).
814 (("def test_getting_example_beds")
815 "def _do_not_test_getting_example_beds"))
817 ;; TODO: Remove phase after it's part of PYTHON-BUILD-SYSTEM.
819 ;; Force the Cythonization of C++ files to guard against compilation
821 (add-after 'unpack 'remove-cython-generated-files
823 (let ((cython-sources (map (cut string-drop-right <> 4)
824 (find-files "." "\\.pyx$")))
825 (c/c++-files (find-files "." "\\.(c|cpp|cxx)$")))
826 (define (strip-extension filename)
827 (string-take filename (string-index-right filename #\.)))
828 (define (cythonized? c/c++-file)
829 (member (strip-extension c/c++-file) cython-sources))
830 (for-each delete-file (filter cythonized? c/c++-files))
832 (add-after 'remove-cython-generated-files 'generate-cython-extensions
834 (invoke "python" "setup.py" "cythonize")))
837 (let* ((cwd (getcwd))
838 (build-root-directory (string-append cwd "/build/"))
839 (build (string-append
841 (find (cut string-prefix? "lib" <>)
842 (scandir (string-append
843 build-root-directory)))))
844 (scripts (string-append
846 (find (cut string-prefix? "scripts" <>)
847 (scandir build-root-directory)))))
849 (string-append build ":" (getenv "PYTHONPATH")))
850 ;; Executable scripts such as 'intron_exon_reads.py' must be
851 ;; available in the PATH.
853 (string-append scripts ":" (getenv "PATH"))))
854 ;; The tests need to be run from elsewhere...
855 (mkdir-p "/tmp/test")
856 (copy-recursively "pybedtools/test" "/tmp/test")
857 (with-directory-excursion "/tmp/test"
858 (invoke "pytest")))))))
860 `(("bedtools" ,bedtools)
861 ("samtools" ,samtools)
862 ("python-matplotlib" ,python-matplotlib)
863 ("python-pysam" ,python-pysam)
864 ("python-pyyaml" ,python-pyyaml)))
866 `(("python-numpy" ,python-numpy)
867 ("python-pandas" ,python-pandas)
868 ("python-cython" ,python-cython)
869 ("kentutils" ,kentutils) ; for bedGraphToBigWig
870 ("python-six" ,python-six)
871 ;; For the test suite.
872 ("python-pytest" ,python-pytest)
873 ("python-psutil" ,python-psutil)))
874 (home-page "https://pythonhosted.org/pybedtools/")
875 (synopsis "Python wrapper for BEDtools programs")
877 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
878 which are widely used for genomic interval manipulation or \"genome algebra\".
879 pybedtools extends BEDTools by offering feature-level manipulations from with
881 (license license:gpl2+)))
883 (define-public python2-pybedtools
884 (package-with-python2 python-pybedtools))
886 (define-public python-biom-format
888 (name "python-biom-format")
893 ;; Use GitHub as source because PyPI distribution does not contain
894 ;; test data: https://github.com/biocore/biom-format/issues/693
896 (url "https://github.com/biocore/biom-format.git")
898 (file-name (git-file-name name version))
901 "1rna16lyk5aqhnv0dp77wwaplias93f1vw28ad3jmyw6hwkai05v"))
902 (modules '((guix build utils)))
904 ;; Delete generated C files.
905 (for-each delete-file (find-files "." "\\.c"))
907 (build-system python-build-system)
910 (modify-phases %standard-phases
911 (add-after 'unpack 'use-cython
912 (lambda _ (setenv "USE_CYTHON" "1") #t))
913 (add-after 'unpack 'disable-broken-tests
915 (substitute* "biom/tests/test_cli/test_validate_table.py"
916 (("^(.+)def test_invalid_hdf5" m indent)
917 (string-append indent
918 "@npt.dec.skipif(True, msg='Guix')\n"
920 (substitute* "biom/tests/test_table.py"
921 (("^(.+)def test_from_hdf5_issue_731" m indent)
922 (string-append indent
923 "@npt.dec.skipif(True, msg='Guix')\n"
926 (add-before 'reset-gzip-timestamps 'make-files-writable
927 (lambda* (#:key outputs #:allow-other-keys)
928 (let ((out (assoc-ref outputs "out")))
929 (for-each (lambda (file) (chmod file #o644))
930 (find-files out "\\.gz"))
933 `(("python-numpy" ,python-numpy)
934 ("python-scipy" ,python-scipy)
935 ("python-flake8" ,python-flake8)
936 ("python-future" ,python-future)
937 ("python-click" ,python-click)
938 ("python-h5py" ,python-h5py)
939 ("python-pandas" ,python-pandas)))
941 `(("python-cython" ,python-cython)
942 ("python-pytest" ,python-pytest)
943 ("python-pytest-cov" ,python-pytest-cov)
944 ("python-nose" ,python-nose)))
945 (home-page "http://www.biom-format.org")
946 (synopsis "Biological Observation Matrix (BIOM) format utilities")
948 "The BIOM file format is designed to be a general-use format for
949 representing counts of observations e.g. operational taxonomic units, KEGG
950 orthology groups or lipid types, in one or more biological samples
951 e.g. microbiome samples, genomes, metagenomes.")
952 (license license:bsd-3)
953 (properties `((python2-variant . ,(delay python2-biom-format))))))
955 (define-public python2-biom-format
956 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
960 (substitute-keyword-arguments (package-arguments base)
962 `(modify-phases ,phases
963 ;; Do not require the unmaintained pyqi library.
964 (add-after 'unpack 'remove-pyqi
966 (substitute* "setup.py"
967 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
970 (define-public bioperl-minimal
971 (let* ((inputs `(("perl-module-build" ,perl-module-build)
972 ("perl-data-stag" ,perl-data-stag)
973 ("perl-libwww" ,perl-libwww)
974 ("perl-uri" ,perl-uri)))
976 (map (compose package-name cadr)
979 (map (compose package-transitive-target-inputs cadr) inputs))))))
981 (name "bioperl-minimal")
986 (uri (string-append "https://github.com/bioperl/bioperl-live/"
988 (string-map (lambda (c)
994 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
995 (build-system perl-build-system)
998 (modify-phases %standard-phases
1000 'install 'wrap-programs
1001 (lambda* (#:key outputs #:allow-other-keys)
1002 ;; Make sure all executables in "bin" find the required Perl
1003 ;; modules at runtime. As the PERL5LIB variable contains also
1004 ;; the paths of native inputs, we pick the transitive target
1005 ;; inputs from %build-inputs.
1006 (let* ((out (assoc-ref outputs "out"))
1007 (bin (string-append out "/bin/"))
1009 (cons (string-append out "/lib/perl5/site_perl")
1011 (assoc-ref %build-inputs name))
1012 ',transitive-inputs))
1014 (for-each (lambda (file)
1016 `("PERL5LIB" ":" prefix (,path))))
1017 (find-files bin "\\.pl$"))
1021 `(("perl-test-most" ,perl-test-most)))
1022 (home-page "https://metacpan.org/release/BioPerl")
1023 (synopsis "Bioinformatics toolkit")
1025 "BioPerl is the product of a community effort to produce Perl code which
1026 is useful in biology. Examples include Sequence objects, Alignment objects
1027 and database searching objects. These objects not only do what they are
1028 advertised to do in the documentation, but they also interact - Alignment
1029 objects are made from the Sequence objects, Sequence objects have access to
1030 Annotation and SeqFeature objects and databases, Blast objects can be
1031 converted to Alignment objects, and so on. This means that the objects
1032 provide a coordinated and extensible framework to do computational biology.")
1033 (license license:perl-license))))
1035 (define-public python-biopython
1037 (name "python-biopython")
1041 ;; use PyPi rather than biopython.org to ease updating
1042 (uri (pypi-uri "biopython" version))
1045 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
1046 (build-system python-build-system)
1049 (modify-phases %standard-phases
1050 (add-before 'check 'set-home
1051 ;; Some tests require a home directory to be set.
1052 (lambda _ (setenv "HOME" "/tmp") #t)))))
1054 `(("python-numpy" ,python-numpy)))
1055 (home-page "http://biopython.org/")
1056 (synopsis "Tools for biological computation in Python")
1058 "Biopython is a set of tools for biological computation including parsers
1059 for bioinformatics files into Python data structures; interfaces to common
1060 bioinformatics programs; a standard sequence class and tools for performing
1061 common operations on them; code to perform data classification; code for
1062 dealing with alignments; code making it easy to split up parallelizable tasks
1063 into separate processes; and more.")
1064 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
1066 (define-public python2-biopython
1067 (package-with-python2 python-biopython))
1069 (define-public python-fastalite
1071 (name "python-fastalite")
1076 (uri (pypi-uri "fastalite" version))
1079 "1qli6pxp77i9xn2wfciq2zaxhl82bdxb33cpzqzj1z25yd036wqj"))))
1080 (build-system python-build-system)
1082 `(#:tests? #f)) ; Test data is not distributed.
1083 (home-page "https://github.com/nhoffman/fastalite")
1084 (synopsis "Simplest possible FASTA parser")
1085 (description "This library implements a FASTA and a FASTQ parser without
1086 relying on a complex dependency tree.")
1087 (license license:expat)))
1089 (define-public python2-fastalite
1090 (package-with-python2 python-fastalite))
1092 (define-public bpp-core
1093 ;; The last release was in 2014 and the recommended way to install from source
1094 ;; is to clone the git repository, so we do this.
1095 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1096 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
1099 (version (string-append "2.2.0-1." (string-take commit 7)))
1103 (url "http://biopp.univ-montp2.fr/git/bpp-core")
1105 (file-name (string-append name "-" version "-checkout"))
1108 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
1109 (build-system cmake-build-system)
1111 `(#:parallel-build? #f))
1113 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
1114 ; compile all of the bpp packages with GCC 5.
1115 (home-page "http://biopp.univ-montp2.fr")
1116 (synopsis "C++ libraries for Bioinformatics")
1118 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1119 analysis, phylogenetics, molecular evolution and population genetics. It is
1120 Object Oriented and is designed to be both easy to use and computer efficient.
1121 Bio++ intends to help programmers to write computer expensive programs, by
1122 providing them a set of re-usable tools.")
1123 (license license:cecill-c))))
1125 (define-public bpp-phyl
1126 ;; The last release was in 2014 and the recommended way to install from source
1127 ;; is to clone the git repository, so we do this.
1128 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1129 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
1132 (version (string-append "2.2.0-1." (string-take commit 7)))
1136 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
1138 (file-name (string-append name "-" version "-checkout"))
1141 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
1142 (build-system cmake-build-system)
1144 `(#:parallel-build? #f
1145 ;; If out-of-source, test data is not copied into the build directory
1146 ;; so the tests fail.
1147 #:out-of-source? #f))
1149 `(("bpp-core" ,bpp-core)
1150 ("bpp-seq" ,bpp-seq)
1151 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
1154 (home-page "http://biopp.univ-montp2.fr")
1155 (synopsis "Bio++ phylogenetic Library")
1157 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1158 analysis, phylogenetics, molecular evolution and population genetics. This
1159 library provides phylogenetics-related modules.")
1160 (license license:cecill-c))))
1162 (define-public bpp-popgen
1163 ;; The last release was in 2014 and the recommended way to install from source
1164 ;; is to clone the git repository, so we do this.
1165 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1166 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
1169 (version (string-append "2.2.0-1." (string-take commit 7)))
1173 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
1175 (file-name (string-append name "-" version "-checkout"))
1178 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
1179 (build-system cmake-build-system)
1181 `(#:parallel-build? #f
1182 #:tests? #f)) ; There are no tests.
1184 `(("bpp-core" ,bpp-core)
1185 ("bpp-seq" ,bpp-seq)
1187 (home-page "http://biopp.univ-montp2.fr")
1188 (synopsis "Bio++ population genetics library")
1190 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1191 analysis, phylogenetics, molecular evolution and population genetics. This
1192 library provides population genetics-related modules.")
1193 (license license:cecill-c))))
1195 (define-public bpp-seq
1196 ;; The last release was in 2014 and the recommended way to install from source
1197 ;; is to clone the git repository, so we do this.
1198 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1199 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
1202 (version (string-append "2.2.0-1." (string-take commit 7)))
1206 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
1208 (file-name (string-append name "-" version "-checkout"))
1211 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
1212 (build-system cmake-build-system)
1214 `(#:parallel-build? #f
1215 ;; If out-of-source, test data is not copied into the build directory
1216 ;; so the tests fail.
1217 #:out-of-source? #f))
1219 `(("bpp-core" ,bpp-core)
1220 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
1221 (home-page "http://biopp.univ-montp2.fr")
1222 (synopsis "Bio++ sequence library")
1224 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1225 analysis, phylogenetics, molecular evolution and population genetics. This
1226 library provides sequence-related modules.")
1227 (license license:cecill-c))))
1229 (define-public bppsuite
1230 ;; The last release was in 2014 and the recommended way to install from source
1231 ;; is to clone the git repository, so we do this.
1232 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1233 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
1236 (version (string-append "2.2.0-1." (string-take commit 7)))
1240 (url "http://biopp.univ-montp2.fr/git/bppsuite")
1242 (file-name (string-append name "-" version "-checkout"))
1245 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
1246 (build-system cmake-build-system)
1248 `(#:parallel-build? #f
1249 #:tests? #f)) ; There are no tests.
1253 ("texinfo" ,texinfo)))
1255 `(("bpp-core" ,bpp-core)
1256 ("bpp-seq" ,bpp-seq)
1257 ("bpp-phyl" ,bpp-phyl)
1258 ("bpp-phyl" ,bpp-popgen)
1260 (home-page "http://biopp.univ-montp2.fr")
1261 (synopsis "Bioinformatics tools written with the Bio++ libraries")
1263 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1264 analysis, phylogenetics, molecular evolution and population genetics. This
1265 package provides command line tools using the Bio++ library.")
1266 (license license:cecill-c))))
1268 (define-public blast+
1275 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
1276 version "/ncbi-blast-" version "+-src.tar.gz"))
1279 "1jlq0afxxgczpp35k6mxh8mn4jzq7vqcnaixk166sfj10wq8v9qh"))
1280 (modules '((guix build utils)))
1283 ;; Remove bundled bzip2, zlib and pcre.
1284 (delete-file-recursively "c++/src/util/compress/bzip2")
1285 (delete-file-recursively "c++/src/util/compress/zlib")
1286 (delete-file-recursively "c++/src/util/regexp")
1287 (substitute* "c++/src/util/compress/Makefile.in"
1288 (("bzip2 zlib api") "api"))
1289 ;; Remove useless msbuild directory
1290 (delete-file-recursively
1291 "c++/src/build-system/project_tree_builder/msbuild")
1293 (build-system gnu-build-system)
1295 `(;; There are two(!) tests for this massive library, and both fail with
1296 ;; "unparsable timing stats".
1297 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
1298 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
1301 #:parallel-build? #f ; not supported
1303 (modify-phases %standard-phases
1304 (add-before 'configure 'set-HOME
1305 ;; $HOME needs to be set at some point during the configure phase
1306 (lambda _ (setenv "HOME" "/tmp") #t))
1307 (add-after 'unpack 'enter-dir
1308 (lambda _ (chdir "c++") #t))
1309 (add-after 'enter-dir 'fix-build-system
1311 (define (which* cmd)
1312 (cond ((string=? cmd "date")
1313 ;; make call to "date" deterministic
1318 (format (current-error-port)
1319 "WARNING: Unable to find absolute path for ~s~%"
1323 ;; Rewrite hardcoded paths to various tools
1324 (substitute* (append '("src/build-system/configure.ac"
1325 "src/build-system/configure"
1326 "src/build-system/helpers/run_with_lock.c"
1327 "scripts/common/impl/if_diff.sh"
1328 "scripts/common/impl/run_with_lock.sh"
1329 "src/build-system/Makefile.configurables.real"
1330 "src/build-system/Makefile.in.top"
1331 "src/build-system/Makefile.meta.gmake=no"
1332 "src/build-system/Makefile.meta.in"
1333 "src/build-system/Makefile.meta_l"
1334 "src/build-system/Makefile.meta_p"
1335 "src/build-system/Makefile.meta_r"
1336 "src/build-system/Makefile.mk.in"
1337 "src/build-system/Makefile.requirements"
1338 "src/build-system/Makefile.rules_with_autodep.in")
1339 (find-files "scripts/common/check" "\\.sh$"))
1340 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1341 (or (which* cmd) all)))
1343 (substitute* (find-files "src/build-system" "^config.*")
1344 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1347 ;; rewrite "/var/tmp" in check script
1348 (substitute* "scripts/common/check/check_make_unix.sh"
1349 (("/var/tmp") "/tmp"))
1351 ;; do not reset PATH
1352 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1354 (("action=/bin/") "action=")
1355 (("export PATH") ":"))
1358 (lambda* (#:key inputs outputs #:allow-other-keys)
1359 (let ((out (assoc-ref outputs "out"))
1360 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1361 (include (string-append (assoc-ref outputs "include")
1362 "/include/ncbi-tools++")))
1363 ;; The 'configure' script doesn't recognize things like
1364 ;; '--enable-fast-install'.
1365 (invoke "./configure.orig"
1366 (string-append "--with-build-root=" (getcwd) "/build")
1367 (string-append "--prefix=" out)
1368 (string-append "--libdir=" lib)
1369 (string-append "--includedir=" include)
1370 (string-append "--with-bz2="
1371 (assoc-ref inputs "bzip2"))
1372 (string-append "--with-z="
1373 (assoc-ref inputs "zlib"))
1374 (string-append "--with-pcre="
1375 (assoc-ref inputs "pcre"))
1376 ;; Each library is built twice by default, once
1377 ;; with "-static" in its name, and again
1382 (outputs '("out" ; 21 MB
1391 ("python" ,python-wrapper)))
1394 (home-page "http://blast.ncbi.nlm.nih.gov")
1395 (synopsis "Basic local alignment search tool")
1397 "BLAST is a popular method of performing a DNA or protein sequence
1398 similarity search, using heuristics to produce results quickly. It also
1399 calculates an “expect value” that estimates how many matches would have
1400 occurred at a given score by chance, which can aid a user in judging how much
1401 confidence to have in an alignment.")
1402 ;; Most of the sources are in the public domain, with the following
1405 ;; * ./c++/include/util/bitset/
1406 ;; * ./c++/src/html/ncbi_menu*.js
1408 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1410 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1412 ;; * ./c++/src/corelib/teamcity_*
1413 (license (list license:public-domain
1419 (define-public bless
1425 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1429 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1430 (modules '((guix build utils)))
1433 ;; Remove bundled boost, pigz, zlib, and .git directory
1434 ;; FIXME: also remove bundled sources for murmurhash3 and
1435 ;; kmc once packaged.
1436 (delete-file-recursively "boost")
1437 (delete-file-recursively "pigz")
1438 (delete-file-recursively "google-sparsehash")
1439 (delete-file-recursively "zlib")
1440 (delete-file-recursively ".git")
1442 (build-system gnu-build-system)
1444 '(#:tests? #f ;no "check" target
1446 (list (string-append "ZLIB="
1447 (assoc-ref %build-inputs "zlib:static")
1449 (string-append "LDFLAGS="
1450 (string-join '("-lboost_filesystem"
1457 (modify-phases %standard-phases
1458 (add-after 'unpack 'do-not-build-bundled-pigz
1459 (lambda* (#:key inputs outputs #:allow-other-keys)
1460 (substitute* "Makefile"
1461 (("cd pigz/pigz-2.3.3; make") ""))
1463 (add-after 'unpack 'patch-paths-to-executables
1464 (lambda* (#:key inputs outputs #:allow-other-keys)
1465 (substitute* "parse_args.cpp"
1466 (("kmc_binary = .*")
1467 (string-append "kmc_binary = \""
1468 (assoc-ref outputs "out")
1470 (("pigz_binary = .*")
1471 (string-append "pigz_binary = \""
1472 (assoc-ref inputs "pigz")
1476 (lambda* (#:key outputs #:allow-other-keys)
1477 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1478 (for-each (lambda (file)
1479 (install-file file bin))
1480 '("bless" "kmc/bin/kmc"))
1482 (delete 'configure))))
1486 `(("openmpi" ,openmpi)
1488 ("sparsehash" ,sparsehash)
1490 ("zlib:static" ,zlib "static")
1492 (supported-systems '("x86_64-linux"))
1493 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1494 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1496 "@dfn{Bloom-filter-based error correction solution for high-throughput
1497 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1498 correction tool for genomic reads produced by @dfn{Next-generation
1499 sequencing} (NGS). BLESS produces accurate correction results with much less
1500 memory compared with previous solutions and is also able to tolerate a higher
1501 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1502 errors at the end of reads.")
1503 (license license:gpl3+)))
1505 (define-public bowtie
1512 (url "https://github.com/BenLangmead/bowtie2.git")
1513 (commit (string-append "v" version))))
1514 (file-name (git-file-name name version))
1517 "1zl3cf327y2p7p03cavymbh7b00djc7lncfaqih33n96iy9q8ibp"))
1518 (modules '((guix build utils)))
1521 (substitute* "Makefile"
1522 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1523 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1524 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
1526 (build-system gnu-build-system)
1531 (string-append "prefix=" (assoc-ref %outputs "out")))
1533 (modify-phases %standard-phases
1538 "scripts/test/simple_tests.pl"
1539 "--bowtie2=./bowtie2"
1540 "--bowtie2-build=./bowtie2-build")
1545 ("python" ,python-wrapper)))
1548 ("perl-clone" ,perl-clone)
1549 ("perl-test-deep" ,perl-test-deep)
1550 ("perl-test-simple" ,perl-test-simple)))
1551 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1552 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1554 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1555 reads to long reference sequences. It is particularly good at aligning reads
1556 of about 50 up to 100s or 1,000s of characters, and particularly good at
1557 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1558 genome with an FM Index to keep its memory footprint small: for the human
1559 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1560 gapped, local, and paired-end alignment modes.")
1561 (supported-systems '("x86_64-linux"))
1562 (license license:gpl3+)))
1564 (define-public bowtie1
1570 (uri (string-append "mirror://sourceforge/bowtie-bio/bowtie/"
1571 version "/bowtie-" version "-src.zip"))
1574 "1jl2cj9bz8lwz8dwnxbycn8yp8g4kky62fkcxifyf1ri0y6n2vc0"))
1575 (modules '((guix build utils)))
1577 '(substitute* "Makefile"
1578 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1579 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1580 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1581 (build-system gnu-build-system)
1583 '(#:tests? #f ; no "check" target
1586 (string-append "prefix=" (assoc-ref %outputs "out")))
1588 (modify-phases %standard-phases
1589 (delete 'configure))))
1593 (supported-systems '("x86_64-linux"))
1594 (home-page "http://bowtie-bio.sourceforge.net/index.shtml")
1595 (synopsis "Fast aligner for short nucleotide sequence reads")
1597 "Bowtie is a fast, memory-efficient short read aligner. It aligns short
1598 DNA sequences (reads) to the human genome at a rate of over 25 million 35-bp
1599 reads per hour. Bowtie indexes the genome with a Burrows-Wheeler index to
1600 keep its memory footprint small: typically about 2.2 GB for the human
1601 genome (2.9 GB for paired-end).")
1602 (license license:artistic2.0)))
1604 (define-public tophat
1611 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1615 "19add02kv2xhd6ihd779dr7x35ggym3jqr0m5c4315i1yfb0p11p"))
1616 (modules '((guix build utils)))
1619 ;; Remove bundled SeqAn and samtools
1620 (delete-file-recursively "src/SeqAn-1.4.2")
1621 (delete-file-recursively "src/samtools-0.1.18")
1623 (build-system gnu-build-system)
1625 '(#:parallel-build? #f ; not supported
1627 (modify-phases %standard-phases
1628 (add-after 'unpack 'use-system-samtools
1629 (lambda* (#:key inputs #:allow-other-keys)
1630 (substitute* "src/Makefile.in"
1631 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1632 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1633 (("SAMPROG = samtools_0\\.1\\.18") "")
1634 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1635 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1636 (substitute* '("src/common.cpp"
1638 (("samtools_0.1.18") (which "samtools")))
1639 (substitute* '("src/common.h"
1640 "src/bam2fastx.cpp")
1641 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1642 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1643 (substitute* '("src/bwt_map.h"
1645 "src/align_status.h")
1646 (("#include <bam.h>") "#include <samtools/bam.h>")
1647 (("#include <sam.h>") "#include <samtools/sam.h>"))
1652 ("samtools" ,samtools-0.1)
1653 ("ncurses" ,ncurses)
1654 ("python" ,python-2)
1657 ("seqan" ,seqan-1)))
1658 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1659 (synopsis "Spliced read mapper for RNA-Seq data")
1661 "TopHat is a fast splice junction mapper for nucleotide sequence
1662 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1663 mammalian-sized genomes using the ultra high-throughput short read
1664 aligner Bowtie, and then analyzes the mapping results to identify
1665 splice junctions between exons.")
1666 ;; TopHat is released under the Boost Software License, Version 1.0
1667 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1668 (license license:boost1.0)))
1677 "https://github.com/lh3/bwa/releases/download/v"
1678 version "/bwa-" version ".tar.bz2"))
1681 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1682 (build-system gnu-build-system)
1684 '(#:tests? #f ;no "check" target
1686 (modify-phases %standard-phases
1688 (lambda* (#:key outputs #:allow-other-keys)
1689 (let ((bin (string-append
1690 (assoc-ref outputs "out") "/bin"))
1692 (assoc-ref outputs "out") "/share/doc/bwa"))
1694 (assoc-ref outputs "out") "/share/man/man1")))
1695 (install-file "bwa" bin)
1696 (install-file "README.md" doc)
1697 (install-file "bwa.1" man))
1699 ;; no "configure" script
1700 (delete 'configure))))
1701 (inputs `(("zlib" ,zlib)))
1702 ;; Non-portable SSE instructions are used so building fails on platforms
1703 ;; other than x86_64.
1704 (supported-systems '("x86_64-linux"))
1705 (home-page "http://bio-bwa.sourceforge.net/")
1706 (synopsis "Burrows-Wheeler sequence aligner")
1708 "BWA is a software package for mapping low-divergent sequences against a
1709 large reference genome, such as the human genome. It consists of three
1710 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1711 designed for Illumina sequence reads up to 100bp, while the rest two for
1712 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1713 features such as long-read support and split alignment, but BWA-MEM, which is
1714 the latest, is generally recommended for high-quality queries as it is faster
1715 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1716 70-100bp Illumina reads.")
1717 (license license:gpl3+)))
1719 (define-public bwa-pssm
1720 (package (inherit bwa)
1726 (url "https://github.com/pkerpedjiev/bwa-pssm.git")
1728 (file-name (git-file-name name version))
1731 "076c4q0cdqz8jgylb067y9zmvxglppnzi3qiscn0xiypgc6lgb5r"))))
1732 (build-system gnu-build-system)
1737 (home-page "http://bwa-pssm.binf.ku.dk/")
1738 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1740 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1741 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1742 existing aligners it is fast and sensitive. Unlike most other aligners,
1743 however, it is also adaptible in the sense that one can direct the alignment
1744 based on known biases within the data set. It is coded as a modification of
1745 the original BWA alignment program and shares the genome index structure as
1746 well as many of the command line options.")
1747 (license license:gpl3+)))
1749 (define-public bwa-meth
1756 (url "https://github.com/brentp/bwa-meth.git")
1757 (commit (string-append "v" version))))
1758 (file-name (git-file-name name version))
1761 "17j31i7zws5j7mhsq9x3qgkxly6mlmrgwhfq0qbflgxrmx04yaiz"))))
1762 (build-system python-build-system)
1765 (modify-phases %standard-phases
1766 (add-after 'unpack 'keep-references-to-bwa
1767 (lambda* (#:key inputs #:allow-other-keys)
1768 (substitute* "bwameth.py"
1770 (string-append (which "bwa") " mem"))
1771 ;; There's an ill-advised check for "samtools" on PATH.
1777 `(("python-toolshed" ,python-toolshed)))
1778 (home-page "https://github.com/brentp/bwa-meth")
1779 (synopsis "Fast and accurante alignment of BS-Seq reads")
1781 "BWA-Meth works for single-end reads and for paired-end reads from the
1782 directional protocol (most common). It uses the method employed by
1783 methylcoder and Bismark of in silico conversion of all C's to T's in both
1784 reference and reads. It recovers the original read (needed to tabulate
1785 methylation) by attaching it as a comment which BWA appends as a tag to the
1786 read. It performs favorably to existing aligners gauged by number of on and
1787 off-target reads for a capture method that targets CpG-rich region.")
1788 (license license:expat)))
1790 (define-public python-bx-python
1792 (name "python-bx-python")
1796 (uri (pypi-uri "bx-python" version))
1799 "11kksg2rbzihpmcid823xvg42xi88m7sz58rzk29abybkxy0rszs"))))
1800 (build-system python-build-system)
1801 ;; Tests fail because test data are not included
1802 (arguments '(#:tests? #f))
1804 `(("python-numpy" ,python-numpy)
1805 ("python-six" ,python-six)))
1809 `(("python-lzo" ,python-lzo)
1810 ("python-nose" ,python-nose)
1811 ("python-cython" ,python-cython)))
1812 (home-page "https://github.com/bxlab/bx-python")
1813 (synopsis "Tools for manipulating biological data")
1815 "bx-python provides tools for manipulating biological data, particularly
1816 multiple sequence alignments.")
1817 (license license:expat)))
1819 (define-public python2-bx-python
1820 (package-with-python2 python-bx-python))
1822 (define-public python-pysam
1824 (name "python-pysam")
1828 ;; Test data is missing on PyPi.
1830 (url "https://github.com/pysam-developers/pysam.git")
1831 (commit (string-append "v" version))))
1832 (file-name (git-file-name name version))
1835 "1vj367w6xbn9bpmksm162l1aipf7cj97h1q83y7jcpm33ihwpf7x"))
1836 (modules '((guix build utils)))
1838 ;; Drop bundled htslib. TODO: Also remove samtools
1840 (delete-file-recursively "htslib")
1842 (build-system python-build-system)
1844 `(#:modules ((ice-9 ftw)
1846 (guix build python-build-system)
1849 (modify-phases %standard-phases
1850 (add-before 'build 'set-flags
1851 (lambda* (#:key inputs #:allow-other-keys)
1852 (setenv "HTSLIB_MODE" "external")
1853 (setenv "HTSLIB_LIBRARY_DIR"
1854 (string-append (assoc-ref inputs "htslib") "/lib"))
1855 (setenv "HTSLIB_INCLUDE_DIR"
1856 (string-append (assoc-ref inputs "htslib") "/include"))
1857 (setenv "LDFLAGS" "-lncurses")
1858 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1861 (lambda* (#:key inputs outputs #:allow-other-keys)
1862 ;; This file contains tests that require a connection to the
1864 (delete-file "tests/tabix_test.py")
1865 ;; FIXME: This test fails
1866 (delete-file "tests/AlignmentFile_test.py")
1867 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1868 (setenv "PYTHONPATH"
1870 (getenv "PYTHONPATH")
1871 ":" (getcwd) "/build/"
1872 (car (scandir "build"
1873 (negate (cut string-prefix? "." <>))))))
1874 ;; Step out of source dir so python does not import from CWD.
1875 (with-directory-excursion "tests"
1876 (setenv "HOME" "/tmp")
1877 (invoke "make" "-C" "pysam_data")
1878 (invoke "make" "-C" "cbcf_data")
1879 ;; Running nosetests without explicitly asking for a single
1880 ;; process leads to a crash. Running with multiple processes
1881 ;; fails because the tests are not designed to run in parallel.
1883 ;; FIXME: tests keep timing out on some systems.
1884 (invoke "nosetests" "-v" "--processes" "1")))))))
1886 `(("htslib" ,htslib))) ; Included from installed header files.
1888 `(("ncurses" ,ncurses)
1892 `(("python-cython" ,python-cython)
1893 ;; Dependencies below are are for tests only.
1894 ("samtools" ,samtools)
1895 ("bcftools" ,bcftools)
1896 ("python-nose" ,python-nose)))
1897 (home-page "https://github.com/pysam-developers/pysam")
1898 (synopsis "Python bindings to the SAMtools C API")
1900 "Pysam is a Python module for reading and manipulating files in the
1901 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1902 also includes an interface for tabix.")
1903 (license license:expat)))
1905 (define-public python2-pysam
1906 (package-with-python2 python-pysam))
1908 (define-public python-twobitreader
1910 (name "python-twobitreader")
1915 (url "https://github.com/benjschiller/twobitreader")
1917 (file-name (git-file-name name version))
1920 "1qbxvv1h58cismbk1anpjrkpghsaiy64a11ir3lhy6qch6xf8n62"))))
1921 (build-system python-build-system)
1922 ;; Tests are not included
1923 (arguments '(#:tests? #f))
1925 `(("python-sphinx" ,python-sphinx)))
1926 (home-page "https://github.com/benjschiller/twobitreader")
1927 (synopsis "Python library for reading .2bit files")
1929 "twobitreader is a Python library for reading .2bit files as used by the
1930 UCSC genome browser.")
1931 (license license:artistic2.0)))
1933 (define-public python2-twobitreader
1934 (package-with-python2 python-twobitreader))
1936 (define-public python-plastid
1938 (name "python-plastid")
1942 (uri (pypi-uri "plastid" version))
1945 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1946 (build-system python-build-system)
1948 ;; Some test files are not included.
1951 `(("python-numpy" ,python-numpy)
1952 ("python-scipy" ,python-scipy)
1953 ("python-pandas" ,python-pandas)
1954 ("python-pysam" ,python-pysam)
1955 ("python-matplotlib" ,python-matplotlib)
1956 ("python-biopython" ,python-biopython)
1957 ("python-twobitreader" ,python-twobitreader)
1958 ("python-termcolor" ,python-termcolor)))
1960 `(("python-cython" ,python-cython)
1961 ("python-nose" ,python-nose)))
1962 (home-page "https://github.com/joshuagryphon/plastid")
1963 (synopsis "Python library for genomic analysis")
1965 "plastid is a Python library for genomic analysis – in particular,
1966 high-throughput sequencing data – with an emphasis on simplicity.")
1967 (license license:bsd-3)))
1969 (define-public python2-plastid
1970 (package-with-python2 python-plastid))
1972 (define-public tetoolkit
1979 (url "https://github.com/mhammell-laboratory/tetoolkit.git")
1981 (file-name (git-file-name name version))
1984 "1yzi0kfpzip8zpjb82x1ik6h22yzfyjiz2dv85v6as2awwqvk807"))))
1985 (build-system python-build-system)
1987 `(#:python ,python-2 ; not guaranteed to work with Python 3
1989 (modify-phases %standard-phases
1990 (add-after 'unpack 'make-writable
1992 (for-each make-file-writable (find-files "."))
1994 (add-after 'unpack 'patch-invocations
1995 (lambda* (#:key inputs #:allow-other-keys)
1996 (substitute* '("bin/TEtranscripts"
1999 (string-append "'" (which "sort") " "))
2001 (string-append "'" (which "rm") " -f "))
2002 (("'Rscript'") (string-append "'" (which "Rscript") "'")))
2003 (substitute* "TEToolkit/IO/ReadInputs.py"
2004 (("BamToBED") (which "bamToBed")))
2005 (substitute* "TEToolkit/Normalization.py"
2007 (string-append "\"" (which "Rscript") "\"")))
2009 (add-after 'install 'wrap-program
2010 (lambda* (#:key outputs #:allow-other-keys)
2011 ;; Make sure the executables find R packages.
2012 (let ((out (assoc-ref outputs "out")))
2015 (wrap-program (string-append out "/bin/" script)
2016 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
2021 `(("coreutils" ,coreutils)
2022 ("bedtools" ,bedtools)
2023 ("python-argparse" ,python2-argparse)
2024 ("python-pysam" ,python2-pysam)
2025 ("r-minimal" ,r-minimal)
2026 ("r-deseq2" ,r-deseq2)))
2027 (home-page "https://github.com/mhammell-laboratory/tetoolkit")
2028 (synopsis "Transposable elements in differential enrichment analysis")
2030 "This is package for including transposable elements in differential
2031 enrichment analysis of sequencing datasets. TEtranscripts and TEcount take
2032 RNA-seq (and similar data) and annotates reads to both genes and transposable
2033 elements. TEtranscripts then performs differential analysis using DESeq2.
2034 Note that TEtranscripts and TEcount rely on specially curated GTF files, which
2035 are not included due to their size.")
2036 (license license:gpl3+)))
2038 (define-public cd-hit
2044 (uri (string-append "https://github.com/weizhongli/cdhit"
2045 "/releases/download/V" version
2047 "-2017-0621-source.tar.gz"))
2050 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
2051 (build-system gnu-build-system)
2053 `(#:tests? #f ; there are no tests
2055 ;; Executables are copied directly to the PREFIX.
2056 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin")
2057 ;; Support longer sequences (e.g. Pacbio sequences)
2060 (modify-phases %standard-phases
2061 ;; No "configure" script
2063 ;; Remove sources of non-determinism
2064 (add-after 'unpack 'be-timeless
2066 (substitute* "cdhit-utility.c++"
2067 ((" \\(built on \" __DATE__ \"\\)") ""))
2068 (substitute* "cdhit-common.c++"
2069 (("__DATE__") "\"0\"")
2070 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
2072 ;; The "install" target does not create the target directory.
2073 (add-before 'install 'create-target-dir
2074 (lambda* (#:key outputs #:allow-other-keys)
2075 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
2079 (home-page "http://weizhongli-lab.org/cd-hit/")
2080 (synopsis "Cluster and compare protein or nucleotide sequences")
2082 "CD-HIT is a program for clustering and comparing protein or nucleotide
2083 sequences. CD-HIT is designed to be fast and handle extremely large
2085 ;; The manual says: "It can be copied under the GNU General Public License
2086 ;; version 2 (GPLv2)."
2087 (license license:gpl2)))
2089 (define-public clipper
2096 (url "https://github.com/YeoLab/clipper.git")
2098 (file-name (git-file-name name version))
2101 "0fja1rj84wp9vpj8rxpj3n8zqzcqq454m904yp9as1w4phccirjb"))
2102 (modules '((guix build utils)))
2105 ;; remove unnecessary setup dependency
2106 (substitute* "setup.py"
2107 (("setup_requires = .*") ""))
2109 (build-system python-build-system)
2111 `(#:python ,python-2 ; only Python 2 is supported
2113 (modify-phases %standard-phases
2114 ;; This is fixed in upstream commit
2115 ;; f6c2990198f906bf97730d95695b4bd5a6d01ddb.
2116 (add-after 'unpack 'fix-typo
2118 (substitute* "clipper/src/readsToWiggle.pyx"
2122 `(("htseq" ,python2-htseq)
2123 ("python-pybedtools" ,python2-pybedtools)
2124 ("python-cython" ,python2-cython)
2125 ("python-scikit-learn" ,python2-scikit-learn)
2126 ("python-matplotlib" ,python2-matplotlib)
2127 ("python-pandas" ,python2-pandas)
2128 ("python-pysam" ,python2-pysam)
2129 ("python-numpy" ,python2-numpy)
2130 ("python-scipy" ,python2-scipy)))
2132 `(("python-mock" ,python2-mock) ; for tests
2133 ("python-nose" ,python2-nose) ; for tests
2134 ("python-pytz" ,python2-pytz))) ; for tests
2135 (home-page "https://github.com/YeoLab/clipper")
2136 (synopsis "CLIP peak enrichment recognition")
2138 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
2139 (license license:gpl2)))
2141 (define-public codingquarry
2143 (name "codingquarry")
2148 "mirror://sourceforge/codingquarry/CodingQuarry_v"
2152 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
2153 (build-system gnu-build-system)
2155 '(#:tests? #f ; no "check" target
2157 (modify-phases %standard-phases
2160 (lambda* (#:key outputs #:allow-other-keys)
2161 (let* ((out (assoc-ref outputs "out"))
2162 (bin (string-append out "/bin"))
2163 (doc (string-append out "/share/doc/codingquarry")))
2164 (install-file "INSTRUCTIONS.pdf" doc)
2165 (copy-recursively "QuarryFiles"
2166 (string-append out "/QuarryFiles"))
2167 (install-file "CodingQuarry" bin)
2168 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin))
2170 (inputs `(("openmpi" ,openmpi)))
2171 (native-search-paths
2172 (list (search-path-specification
2173 (variable "QUARRY_PATH")
2174 (files '("QuarryFiles")))))
2175 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
2176 (synopsis "Fungal gene predictor")
2177 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
2178 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
2179 (home-page "https://sourceforge.net/projects/codingquarry/")
2180 (license license:gpl3+)))
2182 (define-public couger
2189 "http://couger.oit.duke.edu/static/assets/COUGER"
2193 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
2194 (build-system gnu-build-system)
2198 (modify-phases %standard-phases
2203 (lambda* (#:key outputs #:allow-other-keys)
2204 (let* ((out (assoc-ref outputs "out"))
2205 (bin (string-append out "/bin")))
2206 (copy-recursively "src" (string-append out "/src"))
2208 ;; Add "src" directory to module lookup path.
2209 (substitute* "couger"
2211 (string-append "import sys\nsys.path.append(\""
2212 out "\")\nfrom argparse")))
2213 (install-file "couger" bin))
2216 'install 'wrap-program
2217 (lambda* (#:key inputs outputs #:allow-other-keys)
2218 ;; Make sure 'couger' runs with the correct PYTHONPATH.
2219 (let* ((out (assoc-ref outputs "out"))
2220 (path (getenv "PYTHONPATH")))
2221 (wrap-program (string-append out "/bin/couger")
2222 `("PYTHONPATH" ":" prefix (,path))))
2225 `(("python" ,python-2)
2226 ("python2-pillow" ,python2-pillow)
2227 ("python2-numpy" ,python2-numpy)
2228 ("python2-scipy" ,python2-scipy)
2229 ("python2-matplotlib" ,python2-matplotlib)))
2231 `(("r-minimal" ,r-minimal)
2233 ("randomjungle" ,randomjungle)))
2235 `(("unzip" ,unzip)))
2236 (home-page "http://couger.oit.duke.edu")
2237 (synopsis "Identify co-factors in sets of genomic regions")
2239 "COUGER can be applied to any two sets of genomic regions bound by
2240 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
2241 putative co-factors that provide specificity to each TF. The framework
2242 determines the genomic targets uniquely-bound by each TF, and identifies a
2243 small set of co-factors that best explain the in vivo binding differences
2244 between the two TFs.
2246 COUGER uses classification algorithms (support vector machines and random
2247 forests) with features that reflect the DNA binding specificities of putative
2248 co-factors. The features are generated either from high-throughput TF-DNA
2249 binding data (from protein binding microarray experiments), or from large
2250 collections of DNA motifs.")
2251 (license license:gpl3+)))
2253 (define-public clustal-omega
2255 (name "clustal-omega")
2259 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
2263 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
2264 (build-system gnu-build-system)
2266 `(("argtable" ,argtable)))
2267 (home-page "http://www.clustal.org/omega/")
2268 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
2270 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
2271 program for protein and DNA/RNA. It produces high quality MSAs and is capable
2272 of handling data-sets of hundreds of thousands of sequences in reasonable
2274 (license license:gpl2+)))
2276 (define-public crossmap
2282 (uri (pypi-uri "CrossMap" version))
2285 "1byhclrqnqpvc1rqkfh4jwj6yhn0x9y7jk47i0qcjlhk0pjkw92p"))))
2286 (build-system python-build-system)
2287 (arguments `(#:python ,python-2))
2289 `(("python-bx-python" ,python2-bx-python)
2290 ("python-numpy" ,python2-numpy)
2291 ("python-pysam" ,python2-pysam)
2294 `(("python-cython" ,python2-cython)
2295 ("python-nose" ,python2-nose)))
2296 (home-page "http://crossmap.sourceforge.net/")
2297 (synopsis "Convert genome coordinates between assemblies")
2299 "CrossMap is a program for conversion of genome coordinates or annotation
2300 files between different genome assemblies. It supports most commonly used
2301 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
2302 (license license:gpl2+)))
2304 (define-public python-dnaio
2306 (name "python-dnaio")
2311 (uri (pypi-uri "dnaio" version))
2314 "0f16m7hdlm0fz1n7y5asy0v9ghyrq17ni1p9iybq22ddzyd49r27"))))
2315 (build-system python-build-system)
2317 `(("python-cython" ,python-cython)
2318 ("python-pytest" ,python-pytest)
2319 ("python-xopen" ,python-xopen)))
2320 (home-page "https://github.com/marcelm/dnaio/")
2321 (synopsis "Read FASTA and FASTQ files efficiently")
2323 "dnaio is a Python library for fast parsing of FASTQ and also FASTA
2324 files. The code was previously part of the cutadapt tool.")
2325 (license license:expat)))
2327 (define-public cutadapt
2333 (uri (pypi-uri "cutadapt" version))
2336 "1vqmsfkm6llxzmsz9wcfcvzx9a9f8iabvwik2rbyn7nc4wm25z89"))))
2337 (build-system python-build-system)
2339 `(("python-dnaio" ,python-dnaio)
2340 ("python-xopen" ,python-xopen)))
2342 `(("python-cython" ,python-cython)
2343 ("python-pytest" ,python-pytest)
2344 ("python-setuptools-scm" ,python-setuptools-scm)))
2345 (home-page "https://cutadapt.readthedocs.io/en/stable/")
2346 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
2348 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
2349 other types of unwanted sequence from high-throughput sequencing reads.")
2350 (license license:expat)))
2352 (define-public libbigwig
2359 (url "https://github.com/dpryan79/libBigWig.git")
2361 (file-name (string-append name "-" version "-checkout"))
2364 "0h2smg24v5srdcqzrmz2g23cmlp4va465mgx8r2z571sfz8pv454"))))
2365 (build-system gnu-build-system)
2367 `(#:test-target "test"
2368 #:tests? #f ; tests require access to the web
2371 (string-append "prefix=" (assoc-ref %outputs "out")))
2373 (modify-phases %standard-phases
2374 (delete 'configure))))
2379 `(("doxygen" ,doxygen)
2381 ("python" ,python-2)))
2382 (home-page "https://github.com/dpryan79/libBigWig")
2383 (synopsis "C library for handling bigWig files")
2385 "This package provides a C library for parsing local and remote BigWig
2387 (license license:expat)))
2389 (define-public python-pybigwig
2391 (name "python-pybigwig")
2395 (uri (pypi-uri "pyBigWig" version))
2398 "00w4kfnm2c5l7wdwr2nj1z5djv8kzgf7h1zhsgv6njff1rwr26g0"))
2399 (modules '((guix build utils)))
2402 ;; Delete bundled libBigWig sources
2403 (delete-file-recursively "libBigWig")
2405 (build-system python-build-system)
2408 (modify-phases %standard-phases
2409 (add-after 'unpack 'link-with-libBigWig
2410 (lambda* (#:key inputs #:allow-other-keys)
2411 (substitute* "setup.py"
2412 (("libs=\\[") "libs=[\"BigWig\", "))
2415 `(("python-numpy" ,python-numpy)))
2417 `(("libbigwig" ,libbigwig)
2420 (home-page "https://github.com/dpryan79/pyBigWig")
2421 (synopsis "Access bigWig files in Python using libBigWig")
2423 "This package provides Python bindings to the libBigWig library for
2424 accessing bigWig files.")
2425 (license license:expat)))
2427 (define-public python2-pybigwig
2428 (package-with-python2 python-pybigwig))
2430 (define-public python-dendropy
2432 (name "python-dendropy")
2437 ;; Source from GitHub so that tests are included.
2439 (url "https://github.com/jeetsukumaran/DendroPy.git")
2440 (commit (string-append "v" version))))
2441 (file-name (git-file-name name version))
2444 "097hfyv2kaf4x92i4rjx0paw2cncxap48qivv8zxng4z7nhid0x9"))))
2445 (build-system python-build-system)
2446 (home-page "http://packages.python.org/DendroPy/")
2447 (synopsis "Library for phylogenetics and phylogenetic computing")
2449 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
2450 writing, simulation, processing and manipulation of phylogenetic
2451 trees (phylogenies) and characters.")
2452 (license license:bsd-3)))
2454 (define-public python2-dendropy
2455 (let ((base (package-with-python2 python-dendropy)))
2460 (modify-phases %standard-phases
2461 (add-after 'unpack 'remove-failing-test
2463 ;; This test fails when the full test suite is run, as documented
2464 ;; at https://github.com/jeetsukumaran/DendroPy/issues/74
2465 (substitute* "tests/test_dataio_nexml_reader_tree_list.py"
2466 (("test_collection_comments_and_annotations")
2467 "do_not_test_collection_comments_and_annotations"))
2469 ,@(package-arguments base))))))
2471 (define-public python-py2bit
2473 (name "python-py2bit")
2478 (uri (pypi-uri "py2bit" version))
2481 "1vw2nvw1yrl7ikkqsqs1pg239yr5nspvd969r1x9arms1k25a1a5"))))
2482 (build-system python-build-system)
2483 (home-page "https://github.com/dpryan79/py2bit")
2484 (synopsis "Access 2bit files using lib2bit")
2486 "This package provides Python bindings for lib2bit to access 2bit files
2488 (license license:expat)))
2490 (define-public deeptools
2497 (url "https://github.com/deeptools/deepTools.git")
2499 (file-name (git-file-name name version))
2502 "1vggnf52g6q2vifdl4cyi7s2fnfqq0ky2zrkj5zv2qfzsc3p3siw"))))
2503 (build-system python-build-system)
2506 (modify-phases %standard-phases
2507 ;; This phase fails, but it's not needed.
2508 (delete 'reset-gzip-timestamps))))
2510 `(("python-plotly" ,python-plotly)
2511 ("python-scipy" ,python-scipy)
2512 ("python-numpy" ,python-numpy)
2513 ("python-numpydoc" ,python-numpydoc)
2514 ("python-matplotlib" ,python-matplotlib)
2515 ("python-pysam" ,python-pysam)
2516 ("python-py2bit" ,python-py2bit)
2517 ("python-pybigwig" ,python-pybigwig)))
2519 `(("python-mock" ,python-mock) ;for tests
2520 ("python-nose" ,python-nose) ;for tests
2521 ("python-pytz" ,python-pytz))) ;for tests
2522 (home-page "https://github.com/deeptools/deepTools")
2523 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2525 "DeepTools addresses the challenge of handling the large amounts of data
2526 that are now routinely generated from DNA sequencing centers. To do so,
2527 deepTools contains useful modules to process the mapped reads data to create
2528 coverage files in standard bedGraph and bigWig file formats. By doing so,
2529 deepTools allows the creation of normalized coverage files or the comparison
2530 between two files (for example, treatment and control). Finally, using such
2531 normalized and standardized files, multiple visualizations can be created to
2532 identify enrichments with functional annotations of the genome.")
2533 (license license:gpl3+)))
2535 (define-public delly
2542 (url "https://github.com/dellytools/delly.git")
2543 (commit (string-append "v" version))))
2544 (file-name (git-file-name name version))
2546 (base32 "034jqsxswy9gqdh2zkgc1js99qkv75ks4xvzgmh0284sraagv61z"))
2547 (modules '((guix build utils)))
2550 (delete-file-recursively "src/htslib")
2552 (build-system gnu-build-system)
2554 `(#:tests? #f ; There are no tests to run.
2556 (list "PARALLEL=1" ; Allow parallel execution at run-time.
2557 (string-append "prefix=" (assoc-ref %outputs "out")))
2559 (modify-phases %standard-phases
2560 (delete 'configure) ; There is no configure phase.
2561 (add-after 'install 'install-templates
2562 (lambda* (#:key outputs #:allow-other-keys)
2563 (let ((templates (string-append (assoc-ref outputs "out")
2564 "/share/delly/templates")))
2566 (copy-recursively "excludeTemplates" templates)
2573 (home-page "https://github.com/dellytools/delly")
2574 (synopsis "Integrated structural variant prediction method")
2575 (description "Delly is an integrated structural variant prediction method
2576 that can discover and genotype deletions, tandem duplications, inversions and
2577 translocations at single-nucleotide resolution in short-read massively parallel
2578 sequencing data. It uses paired-ends and split-reads to sensitively and
2579 accurately delineate genomic rearrangements throughout the genome.")
2580 (license license:gpl3+)))
2582 (define-public diamond
2589 (url "https://github.com/bbuchfink/diamond.git")
2590 (commit (string-append "v" version))))
2591 (file-name (git-file-name name version))
2594 "0bky78v79g3wmdpsd706cscckgw1v09fg8vdd0z8z0d5b97aj9zl"))))
2595 (build-system cmake-build-system)
2597 '(#:tests? #f ; no "check" target
2599 (modify-phases %standard-phases
2600 (add-after 'unpack 'remove-native-compilation
2602 (substitute* "CMakeLists.txt" (("-march=native") ""))
2606 (home-page "https://github.com/bbuchfink/diamond")
2607 (synopsis "Accelerated BLAST compatible local sequence aligner")
2609 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2610 translated DNA query sequences against a protein reference database (BLASTP
2611 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2612 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2613 data and settings.")
2614 (license license:agpl3+)))
2616 (define-public discrover
2624 (url "https://github.com/maaskola/discrover.git")
2626 (file-name (git-file-name name version))
2629 "173fwi2vb6a5kp406hm3jj6j7v4whww796f2qcygp4rpvamh307y"))))
2630 (build-system cmake-build-system)
2632 `(#:tests? #f ; there are no tests
2634 (modify-phases %standard-phases
2635 (add-after 'unpack 'fix-latex-errors
2637 (with-fluids ((%default-port-encoding #f))
2638 (substitute* "doc/references.bib"
2639 (("\\{S\\}illanp[^,]+,")
2640 "{S}illanp{\\\"a}{\\\"a},")))
2641 ;; XXX: I just can't get pdflatex to not complain about these
2642 ;; characters. They end up in the manual via the generated
2643 ;; discrover-cli-help.txt.
2644 (substitute* "src/hmm/cli.cpp"
2648 ;; This seems to be a syntax error.
2649 (substitute* "doc/discrover-manual.tex"
2650 (("theverbbox\\[t\\]") "theverbbox"))
2652 (add-after 'unpack 'add-missing-includes
2654 (substitute* "src/executioninformation.hpp"
2655 (("#define EXECUTIONINFORMATION_HPP" line)
2656 (string-append line "\n#include <random>")))
2657 (substitute* "src/plasma/fasta.hpp"
2658 (("#define FASTA_HPP" line)
2659 (string-append line "\n#include <random>")))
2661 ;; FIXME: this is needed because we're using texlive-union, which
2662 ;; doesn't handle fonts correctly. It expects to be able to generate
2663 ;; fonts in the home directory.
2664 (add-before 'build 'setenv-HOME
2665 (lambda _ (setenv "HOME" "/tmp") #t)))))
2669 ("rmath-standalone" ,rmath-standalone)))
2671 `(("texlive" ,(texlive-union (list texlive-fonts-cm
2672 texlive-fonts-amsfonts
2675 texlive-latex-examplep
2676 texlive-latex-hyperref
2678 texlive-latex-natbib
2679 texlive-bibtex ; style files used by natbib
2680 texlive-latex-pgf ; tikz
2681 texlive-latex-verbatimbox)))
2682 ("imagemagick" ,imagemagick)))
2683 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2684 (synopsis "Discover discriminative nucleotide sequence motifs")
2685 (description "Discrover is a motif discovery method to find binding sites
2686 of nucleic acid binding proteins.")
2687 (license license:gpl3+)))
2689 (define-public eigensoft
2697 (url "https://github.com/DReichLab/EIG.git")
2698 (commit (string-append "v" version))))
2699 (file-name (git-file-name name version))
2702 "1c141fqvhnzibmnf22sv23vbmzm20kjjyrib44cfh75wyndp2d9k"))
2703 (modules '((guix build utils)))
2704 ;; Remove pre-built binaries.
2706 (delete-file-recursively "bin")
2709 (build-system gnu-build-system)
2711 `(#:tests? #f ; There are no tests.
2712 #:make-flags '("CC=gcc")
2714 (modify-phases %standard-phases
2715 ;; There is no configure phase, but the Makefile is in a
2718 (lambda _ (chdir "src") #t))
2719 ;; The provided install target only copies executables to
2720 ;; the "bin" directory in the build root.
2721 (add-after 'install 'actually-install
2722 (lambda* (#:key outputs #:allow-other-keys)
2723 (let* ((out (assoc-ref outputs "out"))
2724 (bin (string-append out "/bin")))
2725 (for-each (lambda (file)
2726 (install-file file bin))
2727 (find-files "../bin" ".*"))
2732 ("openblas" ,openblas)
2734 ("gfortran" ,gfortran "lib")))
2735 (home-page "https://github.com/DReichLab/EIG")
2736 (synopsis "Tools for population genetics")
2737 (description "The EIGENSOFT package provides tools for population
2738 genetics and stratification correction. EIGENSOFT implements methods commonly
2739 used in population genetics analyses such as PCA, computation of Tracy-Widom
2740 statistics, and finding related individuals in structured populations. It
2741 comes with a built-in plotting script and supports multiple file formats and
2742 quantitative phenotypes.")
2743 ;; The license of the eigensoft tools is Expat, but since it's
2744 ;; linking with the GNU Scientific Library (GSL) the effective
2745 ;; license is the GPL.
2746 (license license:gpl3+)))
2748 (define-public edirect
2751 (version "10.2.20181018")
2754 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect"
2755 "/versions/" version
2756 "/edirect-" version ".tar.gz"))
2759 "091f4aigzpbqih6h82nq566gkp3y07i72yqndmqskfgar1vwgci7"))))
2760 (build-system perl-build-system)
2763 (modify-phases %standard-phases
2766 (delete 'check) ; simple check after install
2768 (lambda* (#:key outputs #:allow-other-keys)
2769 (install-file "edirect.pl"
2770 (string-append (assoc-ref outputs "out") "/bin"))
2772 (add-after 'install 'wrap-program
2773 (lambda* (#:key outputs #:allow-other-keys)
2774 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2775 (let* ((out (assoc-ref outputs "out"))
2776 (path (getenv "PERL5LIB")))
2777 (wrap-program (string-append out "/bin/edirect.pl")
2778 `("PERL5LIB" ":" prefix (,path))))
2780 (add-after 'wrap-program 'check
2781 (lambda* (#:key outputs #:allow-other-keys)
2782 (invoke (string-append (assoc-ref outputs "out")
2787 `(("perl-html-parser" ,perl-html-parser)
2788 ("perl-encode-locale" ,perl-encode-locale)
2789 ("perl-file-listing" ,perl-file-listing)
2790 ("perl-html-tagset" ,perl-html-tagset)
2791 ("perl-html-tree" ,perl-html-tree)
2792 ("perl-http-cookies" ,perl-http-cookies)
2793 ("perl-http-date" ,perl-http-date)
2794 ("perl-http-message" ,perl-http-message)
2795 ("perl-http-negotiate" ,perl-http-negotiate)
2796 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2797 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2798 ("perl-net-http" ,perl-net-http)
2799 ("perl-uri" ,perl-uri)
2800 ("perl-www-robotrules" ,perl-www-robotrules)
2801 ("perl-xml-simple" ,perl-xml-simple)
2803 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2804 (synopsis "Tools for accessing the NCBI's set of databases")
2806 "Entrez Direct (EDirect) is a method for accessing the National Center
2807 for Biotechnology Information's (NCBI) set of interconnected
2808 databases (publication, sequence, structure, gene, variation, expression,
2809 etc.) from a terminal. Functions take search terms from command-line
2810 arguments. Individual operations are combined to build multi-step queries.
2811 Record retrieval and formatting normally complete the process.
2813 EDirect also provides an argument-driven function that simplifies the
2814 extraction of data from document summaries or other results that are returned
2815 in structured XML format. This can eliminate the need for writing custom
2816 software to answer ad hoc questions.")
2817 (license license:public-domain)))
2819 (define-public exonerate
2828 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2829 "exonerate-" version ".tar.gz"))
2832 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2833 (build-system gnu-build-system)
2835 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2837 `(("pkg-config" ,pkg-config)))
2841 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2842 (synopsis "Generic tool for biological sequence alignment")
2844 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2845 the alignment of sequences using a many alignment models, either exhaustive
2846 dynamic programming or a variety of heuristics.")
2847 (license license:gpl3)))
2849 (define-public express
2857 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2858 version "/express-" version "-src.tgz"))
2861 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2862 (build-system cmake-build-system)
2864 `(#:tests? #f ;no "check" target
2866 (modify-phases %standard-phases
2867 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2868 (lambda* (#:key inputs #:allow-other-keys)
2869 (substitute* "CMakeLists.txt"
2870 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2871 "set(Boost_USE_STATIC_LIBS OFF)")
2872 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2873 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2874 (substitute* "src/CMakeLists.txt"
2875 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2876 (string-append (assoc-ref inputs "bamtools") "/lib"))
2877 (("libprotobuf.a") "libprotobuf.so"))
2881 ("bamtools" ,bamtools)
2882 ("protobuf" ,protobuf)
2884 (home-page "http://bio.math.berkeley.edu/eXpress")
2885 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2887 "eXpress is a streaming tool for quantifying the abundances of a set of
2888 target sequences from sampled subsequences. Example applications include
2889 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2890 analysis (from RNA-Seq), transcription factor binding quantification in
2891 ChIP-Seq, and analysis of metagenomic data.")
2892 (license license:artistic2.0)))
2894 (define-public express-beta-diversity
2896 (name "express-beta-diversity")
2901 (url "https://github.com/dparks1134/ExpressBetaDiversity.git")
2902 (commit (string-append "v" version))))
2903 (file-name (git-file-name name version))
2906 "0s0yzg5c21349rh7x4w9266jsvnp7j1hp9cf8sk32hz8nvrj745x"))))
2907 (build-system gnu-build-system)
2910 (modify-phases %standard-phases
2912 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2914 (lambda _ (invoke "../bin/ExpressBetaDiversity" "-u") #t))
2916 (lambda* (#:key outputs #:allow-other-keys)
2917 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
2918 (install-file "../scripts/convertToEBD.py" bin)
2919 (install-file "../bin/ExpressBetaDiversity" bin)
2922 `(("python" ,python-2)))
2923 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2924 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2926 "Express Beta Diversity (EBD) calculates ecological beta diversity
2927 (dissimilarity) measures between biological communities. EBD implements a
2928 variety of diversity measures including those that make use of phylogenetic
2929 similarity of community members.")
2930 (license license:gpl3+)))
2932 (define-public fasttree
2939 "http://www.microbesonline.org/fasttree/FastTree-"
2943 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2944 (build-system gnu-build-system)
2946 `(#:tests? #f ; no "check" target
2948 (modify-phases %standard-phases
2952 (lambda* (#:key source #:allow-other-keys)
2955 "-finline-functions"
2966 "-finline-functions"
2975 (lambda* (#:key outputs #:allow-other-keys)
2976 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
2977 (install-file "FastTree" bin)
2978 (install-file "FastTreeMP" bin)
2980 (home-page "http://www.microbesonline.org/fasttree")
2981 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2983 "FastTree can handle alignments with up to a million of sequences in a
2984 reasonable amount of time and memory. For large alignments, FastTree is
2985 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2986 (license license:gpl2+)))
2988 (define-public fastx-toolkit
2990 (name "fastx-toolkit")
2996 "https://github.com/agordon/fastx_toolkit/releases/download/"
2997 version "/fastx_toolkit-" version ".tar.bz2"))
3000 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
3001 (build-system gnu-build-system)
3003 `(("libgtextutils" ,libgtextutils)))
3005 `(("pkg-config" ,pkg-config)))
3006 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
3007 (synopsis "Tools for FASTA/FASTQ file preprocessing")
3009 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
3010 FASTA/FASTQ files preprocessing.
3012 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
3013 containing multiple short-reads sequences. The main processing of such
3014 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
3015 is sometimes more productive to preprocess the files before mapping the
3016 sequences to the genome---manipulating the sequences to produce better mapping
3017 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
3018 (license license:agpl3+)))
3020 (define-public flexbar
3027 (url "https://github.com/seqan/flexbar.git")
3028 (commit (string-append "v" version))))
3029 (file-name (git-file-name name version))
3032 "1pq9sxvdnldl14libk234m72dqhwgzs3acgl943wchwdqlcsi5r2"))))
3033 (build-system cmake-build-system)
3036 (modify-phases %standard-phases
3037 (add-after 'unpack 'do-not-tune-to-CPU
3039 (substitute* "src/CMakeLists.txt"
3040 ((" -march=native") ""))
3043 (lambda* (#:key outputs #:allow-other-keys)
3044 (setenv "PATH" (string-append (getcwd) ":" (getenv "PATH")))
3045 (with-directory-excursion "../source/test"
3046 (invoke "bash" "flexbar_test.sh"))
3049 (lambda* (#:key outputs #:allow-other-keys)
3050 (let* ((out (string-append (assoc-ref outputs "out")))
3051 (bin (string-append out "/bin/")))
3052 (install-file "flexbar" bin))
3058 `(("pkg-config" ,pkg-config)
3060 (home-page "https://github.com/seqan/flexbar")
3061 (synopsis "Barcode and adapter removal tool for sequencing platforms")
3063 "Flexbar preprocesses high-throughput nucleotide sequencing data
3064 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
3065 Moreover, trimming and filtering features are provided. Flexbar increases
3066 read mapping rates and improves genome and transcriptome assemblies. It
3067 supports next-generation sequencing data in fasta/q and csfasta/q format from
3068 Illumina, Roche 454, and the SOLiD platform.")
3069 (license license:bsd-3)))
3071 (define-public fraggenescan
3073 (name "fraggenescan")
3079 (string-append "mirror://sourceforge/fraggenescan/"
3080 "FragGeneScan" version ".tar.gz"))
3082 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
3083 (build-system gnu-build-system)
3086 (modify-phases %standard-phases
3088 (add-before 'build 'patch-paths
3089 (lambda* (#:key outputs #:allow-other-keys)
3090 (let* ((out (string-append (assoc-ref outputs "out")))
3091 (share (string-append out "/share/fraggenescan/")))
3092 (substitute* "run_FragGeneScan.pl"
3094 (string-append "system(\"" (which "rm")))
3096 (string-append "system(\"" (which "mv")))
3097 (("\\\"awk") (string-append "\"" (which "awk")))
3098 ;; This script and other programs expect the training files
3099 ;; to be in the non-standard location bin/train/XXX. Change
3100 ;; this to be share/fraggenescan/train/XXX instead.
3101 (("^\\$train.file = \\$dir.*")
3102 (string-append "$train_file = \""
3104 "train/\".$FGS_train_file;")))
3105 (substitute* "run_hmm.c"
3106 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
3107 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
3111 (invoke "make" "clean")
3112 (invoke "make" "fgs")
3115 (lambda* (#:key outputs #:allow-other-keys)
3116 (let* ((out (string-append (assoc-ref outputs "out")))
3117 (bin (string-append out "/bin/"))
3118 (share (string-append out "/share/fraggenescan/train")))
3119 (install-file "run_FragGeneScan.pl" bin)
3120 (install-file "FragGeneScan" bin)
3121 (copy-recursively "train" share))
3124 (add-after 'install 'post-install-check
3125 ;; In lieu of 'make check', run one of the examples and check the
3126 ;; output files gets created.
3127 (lambda* (#:key outputs #:allow-other-keys)
3128 (let* ((out (string-append (assoc-ref outputs "out")))
3129 (bin (string-append out "/bin/"))
3130 (frag (string-append bin "run_FragGeneScan.pl")))
3131 ;; Test complete genome.
3133 "-genome=./example/NC_000913.fna"
3137 (unless (and (file-exists? "test2.faa")
3138 (file-exists? "test2.ffn")
3139 (file-exists? "test2.gff")
3140 (file-exists? "test2.out"))
3141 (error "Expected files do not exist."))
3142 ;; Test incomplete sequences.
3144 "-genome=./example/NC_000913-fgs.ffn"
3151 ("python" ,python-2))) ;not compatible with python 3.
3152 (home-page "https://sourceforge.net/projects/fraggenescan/")
3153 (synopsis "Finds potentially fragmented genes in short reads")
3155 "FragGeneScan is a program for predicting bacterial and archaeal genes in
3156 short and error-prone DNA sequencing reads. It can also be applied to predict
3157 genes in incomplete assemblies or complete genomes.")
3158 ;; GPL3+ according to private correspondense with the authors.
3159 (license license:gpl3+)))
3161 (define-public fxtract
3162 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
3170 (url "https://github.com/ctSkennerton/fxtract.git")
3172 (file-name (git-file-name name version))
3175 "0hab3gpwf4w9s87qlbswq6ws1qqybh4dcqk79q1ahyldzai5fgp5"))))
3176 (build-system gnu-build-system)
3178 `(#:make-flags (list
3179 (string-append "PREFIX=" (assoc-ref %outputs "out"))
3181 #:test-target "fxtract_test"
3183 (modify-phases %standard-phases
3185 (add-before 'build 'copy-util
3186 (lambda* (#:key inputs #:allow-other-keys)
3188 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
3190 ;; Do not use make install as this requires additional dependencies.
3192 (lambda* (#:key outputs #:allow-other-keys)
3193 (let* ((out (assoc-ref outputs "out"))
3194 (bin (string-append out"/bin")))
3195 (install-file "fxtract" bin)
3201 ;; ctskennerton-util is licensed under GPL2.
3202 `(("ctskennerton-util"
3206 (url "https://github.com/ctSkennerton/util.git")
3207 (commit util-commit)))
3208 (file-name (string-append
3209 "ctstennerton-util-" util-commit "-checkout"))
3212 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
3213 (home-page "https://github.com/ctSkennerton/fxtract")
3214 (synopsis "Extract sequences from FASTA and FASTQ files")
3216 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
3217 or FASTQ) file given a subsequence. It uses a simple substring search for
3218 basic tasks but can change to using POSIX regular expressions, PCRE, hash
3219 lookups or multi-pattern searching as required. By default fxtract looks in
3220 the sequence of each record but can also be told to look in the header,
3221 comment or quality sections.")
3222 ;; 'util' requires SSE instructions.
3223 (supported-systems '("x86_64-linux"))
3224 (license license:expat))))
3226 (define-public gemma
3233 (url "https://github.com/xiangzhou/GEMMA.git")
3234 (commit (string-append "v" version))))
3235 (file-name (git-file-name name version))
3238 "1s3ncnbn45r2hh1cvrqky1kbqq6546biypr4f5mkw1kqlrgyh0yg"))))
3241 ("gfortran" ,gfortran "lib")
3244 ("openblas" ,openblas)
3246 (build-system gnu-build-system)
3249 '(,@(match (%current-system)
3251 '("FORCE_DYNAMIC=1"))
3253 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
3255 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
3257 (modify-phases %standard-phases
3259 (add-after 'unpack 'find-eigen
3260 (lambda* (#:key inputs #:allow-other-keys)
3261 ;; Ensure that Eigen headers can be found
3262 (setenv "CPLUS_INCLUDE_PATH"
3263 (string-append (getenv "CPLUS_INCLUDE_PATH")
3265 (assoc-ref inputs "eigen")
3268 (add-before 'build 'bin-mkdir
3273 (lambda* (#:key outputs #:allow-other-keys)
3274 (let ((out (assoc-ref outputs "out")))
3275 (install-file "bin/gemma"
3279 #:tests? #f)) ; no tests included yet
3280 (home-page "https://github.com/xiangzhou/GEMMA")
3281 (synopsis "Tool for genome-wide efficient mixed model association")
3283 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
3284 standard linear mixed model resolver with application in genome-wide
3285 association studies (GWAS).")
3286 (license license:gpl3)))
3295 (url "https://github.com/nboley/grit.git")
3297 (file-name (git-file-name name version))
3300 "1l5v8vfvfbrpmgnrvbrbv40d0arhxcnmxgv2f1mlcqfa3q6bkqm9"))))
3301 (build-system python-build-system)
3303 `(#:python ,python-2
3305 (modify-phases %standard-phases
3306 (add-after 'unpack 'generate-from-cython-sources
3307 (lambda* (#:key inputs outputs #:allow-other-keys)
3308 ;; Delete these C files to force fresh generation from pyx sources.
3309 (delete-file "grit/sparsify_support_fns.c")
3310 (delete-file "grit/call_peaks_support_fns.c")
3311 (substitute* "setup.py"
3312 (("Cython.Setup") "Cython.Build"))
3315 `(("python-scipy" ,python2-scipy)
3316 ("python-numpy" ,python2-numpy)
3317 ("python-pysam" ,python2-pysam)
3318 ("python-networkx" ,python2-networkx)))
3320 `(("python-cython" ,python2-cython)))
3321 (home-page "http://grit-bio.org")
3322 (synopsis "Tool for integrative analysis of RNA-seq type assays")
3324 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
3325 full length transcript models. When none of these data sources are available,
3326 GRIT can be run by providing a candidate set of TES or TSS sites. In
3327 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
3328 also be run in quantification mode, where it uses a provided GTF file and just
3329 estimates transcript expression.")
3330 (license license:gpl3+)))
3332 (define-public hisat
3339 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
3340 version "-beta-source.zip"))
3343 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
3344 (build-system gnu-build-system)
3346 `(#:tests? #f ;no check target
3347 #:make-flags '("allall"
3348 ;; Disable unsupported `popcnt' instructions on
3349 ;; architectures other than x86_64
3350 ,@(if (string-prefix? "x86_64"
3351 (or (%current-target-system)
3354 '("POPCNT_CAPABILITY=0")))
3356 (modify-phases %standard-phases
3357 (add-after 'unpack 'patch-sources
3359 ;; XXX Cannot use snippet because zip files are not supported
3360 (substitute* "Makefile"
3361 (("^CC = .*$") "CC = gcc")
3362 (("^CPP = .*$") "CPP = g++")
3363 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
3364 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
3365 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
3366 (substitute* '("hisat-build" "hisat-inspect")
3367 (("/usr/bin/env") (which "env")))
3370 (lambda* (#:key outputs #:allow-other-keys)
3371 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
3372 (for-each (lambda (file)
3373 (install-file file bin))
3376 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
3378 (delete 'configure))))
3380 `(("unzip" ,unzip)))
3385 ;; Non-portable SSE instructions are used so building fails on platforms
3386 ;; other than x86_64.
3387 (supported-systems '("x86_64-linux"))
3388 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
3389 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
3391 "HISAT is a fast and sensitive spliced alignment program for mapping
3392 RNA-seq reads. In addition to one global FM index that represents a whole
3393 genome, HISAT uses a large set of small FM indexes that collectively cover the
3394 whole genome. These small indexes (called local indexes) combined with
3395 several alignment strategies enable effective alignment of RNA-seq reads, in
3396 particular, reads spanning multiple exons.")
3397 (license license:gpl3+)))
3399 (define-public hisat2
3406 (uri (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
3407 "/downloads/hisat2-" version "-source.zip"))
3410 "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"))))
3411 (build-system gnu-build-system)
3413 `(#:tests? #f ; no check target
3414 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
3415 #:modules ((guix build gnu-build-system)
3419 (modify-phases %standard-phases
3420 (add-after 'unpack 'make-deterministic
3422 (substitute* "Makefile"
3427 (lambda* (#:key outputs #:allow-other-keys)
3428 (let* ((out (assoc-ref outputs "out"))
3429 (bin (string-append out "/bin/"))
3430 (doc (string-append out "/share/doc/hisat2/")))
3432 (cut install-file <> bin)
3434 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
3436 (install-file "doc/manual.inc.html" doc))
3439 `(("unzip" ,unzip) ; needed for archive from ftp
3441 ("pandoc" ,ghc-pandoc))) ; for documentation
3442 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
3443 (synopsis "Graph-based alignment of genomic sequencing reads")
3444 (description "HISAT2 is a fast and sensitive alignment program for mapping
3445 next-generation sequencing reads (both DNA and RNA) to a population of human
3446 genomes (as well as to a single reference genome). In addition to using one
3447 global @dfn{graph FM} (GFM) index that represents a population of human
3448 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
3449 the whole genome. These small indexes, combined with several alignment
3450 strategies, enable rapid and accurate alignment of sequencing reads. This new
3451 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
3452 ;; HISAT2 contains files from Bowtie2, which is released under
3453 ;; GPLv2 or later. The HISAT2 source files are released under
3455 (license license:gpl3+)))
3457 (define-public hmmer
3465 "http://eddylab.org/software/hmmer/hmmer-" version ".tar.gz"))
3468 "171bivy6xhgjsz5nv53n81pc3frnwz29ylblawk2bv46szwjjqd5"))))
3469 (build-system gnu-build-system)
3470 (native-inputs `(("perl" ,perl)))
3471 (home-page "http://hmmer.org/")
3472 (synopsis "Biosequence analysis using profile hidden Markov models")
3474 "HMMER is used for searching sequence databases for homologs of protein
3475 sequences, and for making protein sequence alignments. It implements methods
3476 using probabilistic models called profile hidden Markov models (profile
3478 ;; hmmer uses non-portable SSE intrinsics so building fails on other
3480 (supported-systems '("x86_64-linux" "i686-linux"))
3481 (license license:bsd-3)))
3483 (define-public htseq
3489 (uri (pypi-uri "HTSeq" version))
3492 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
3493 (build-system python-build-system)
3495 `(("python-cython" ,python-cython)))
3496 ;; Numpy needs to be propagated when htseq is used as a Python library.
3498 `(("python-numpy" ,python-numpy)))
3500 `(("python-pysam" ,python-pysam)
3501 ("python-matplotlib" ,python-matplotlib)))
3502 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
3503 (synopsis "Analysing high-throughput sequencing data with Python")
3505 "HTSeq is a Python package that provides infrastructure to process data
3506 from high-throughput sequencing assays.")
3507 (license license:gpl3+)))
3509 (define-public python2-htseq
3510 (package-with-python2 htseq))
3512 (define-public java-htsjdk
3514 (name "java-htsjdk")
3515 (version "2.3.0") ; last version without build dependency on gradle
3519 (url "https://github.com/samtools/htsjdk.git")
3521 (file-name (git-file-name name version))
3524 "1b178ixcabanm834ydjl3jiakpyxdmki32hqfv2abrzn3rcwa28i"))
3525 (modules '((guix build utils)))
3527 ;; Delete pre-built binaries
3529 (delete-file-recursively "lib")
3532 (build-system ant-build-system)
3534 `(#:tests? #f ; test require Internet access
3537 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3538 "/share/java/htsjdk/"))
3539 #:build-target "all"
3541 (modify-phases %standard-phases
3542 ;; The build phase also installs the jars
3543 (delete 'install))))
3545 `(("java-ngs" ,java-ngs)
3546 ("java-snappy-1" ,java-snappy-1)
3547 ("java-commons-compress" ,java-commons-compress)
3548 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3549 ("java-commons-jexl-2" ,java-commons-jexl-2)
3550 ("java-xz" ,java-xz)))
3552 `(("java-testng" ,java-testng)))
3553 (home-page "http://samtools.github.io/htsjdk/")
3554 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3556 "HTSJDK is an implementation of a unified Java library for accessing
3557 common file formats, such as SAM and VCF, used for high-throughput
3558 sequencing (HTS) data. There are also an number of useful utilities for
3559 manipulating HTS data.")
3560 (license license:expat)))
3562 (define-public java-htsjdk-latest
3564 (name "java-htsjdk")
3569 (url "https://github.com/samtools/htsjdk.git")
3571 (file-name (string-append name "-" version "-checkout"))
3574 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
3575 (build-system ant-build-system)
3577 `(#:tests? #f ; test require Scala
3579 #:jar-name "htsjdk.jar"
3581 (modify-phases %standard-phases
3582 (add-after 'unpack 'remove-useless-build.xml
3583 (lambda _ (delete-file "build.xml") #t))
3584 ;; The tests require the scalatest package.
3585 (add-after 'unpack 'remove-tests
3586 (lambda _ (delete-file-recursively "src/test") #t)))))
3588 `(("java-ngs" ,java-ngs)
3589 ("java-snappy-1" ,java-snappy-1)
3590 ("java-commons-compress" ,java-commons-compress)
3591 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3592 ("java-commons-jexl-2" ,java-commons-jexl-2)
3593 ("java-xz" ,java-xz)))
3595 `(("java-junit" ,java-junit)))
3596 (home-page "http://samtools.github.io/htsjdk/")
3597 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3599 "HTSJDK is an implementation of a unified Java library for accessing
3600 common file formats, such as SAM and VCF, used for high-throughput
3601 sequencing (HTS) data. There are also an number of useful utilities for
3602 manipulating HTS data.")
3603 (license license:expat)))
3605 ;; This is needed for picard 2.10.3
3606 (define-public java-htsjdk-2.10.1
3607 (package (inherit java-htsjdk-latest)
3608 (name "java-htsjdk")
3613 (url "https://github.com/samtools/htsjdk.git")
3615 (file-name (string-append name "-" version "-checkout"))
3618 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
3619 (build-system ant-build-system)
3621 `(#:tests? #f ; tests require Scala
3623 #:jar-name "htsjdk.jar"
3625 (modify-phases %standard-phases
3626 (add-after 'unpack 'remove-useless-build.xml
3627 (lambda _ (delete-file "build.xml") #t))
3628 ;; The tests require the scalatest package.
3629 (add-after 'unpack 'remove-tests
3630 (lambda _ (delete-file-recursively "src/test") #t)))))))
3632 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3633 ;; recent version of java-htsjdk, which depends on gradle.
3634 (define-public java-picard
3636 (name "java-picard")
3641 (url "https://github.com/broadinstitute/picard.git")
3643 (file-name (string-append "java-picard-" version "-checkout"))
3646 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3647 (modules '((guix build utils)))
3650 ;; Delete pre-built binaries.
3651 (delete-file-recursively "lib")
3653 (substitute* "build.xml"
3654 ;; Remove build-time dependency on git.
3655 (("failifexecutionfails=\"true\"")
3656 "failifexecutionfails=\"false\"")
3658 (("depends=\"compile-htsjdk, ")
3660 (("depends=\"compile-htsjdk-tests, ")
3662 ;; Build picard-lib.jar before building picard.jar
3663 (("name=\"picard-jar\" depends=\"" line)
3664 (string-append line "picard-lib-jar, ")))
3666 (build-system ant-build-system)
3668 `(#:build-target "picard-jar"
3669 #:test-target "test"
3670 ;; Tests require jacoco:coverage.
3673 (list (string-append "-Dhtsjdk_lib_dir="
3674 (assoc-ref %build-inputs "java-htsjdk")
3675 "/share/java/htsjdk/")
3676 "-Dhtsjdk-classes=dist/tmp"
3677 (string-append "-Dhtsjdk-version="
3678 ,(package-version java-htsjdk)))
3681 (modify-phases %standard-phases
3682 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3683 (delete 'generate-jar-indices)
3684 (add-after 'unpack 'use-our-htsjdk
3685 (lambda* (#:key inputs #:allow-other-keys)
3686 (substitute* "build.xml"
3687 (("\\$\\{htsjdk\\}/lib")
3688 (string-append (assoc-ref inputs "java-htsjdk")
3689 "/share/java/htsjdk/")))
3691 (add-after 'unpack 'make-test-target-independent
3692 (lambda* (#:key inputs #:allow-other-keys)
3693 (substitute* "build.xml"
3694 (("name=\"test\" depends=\"compile, ")
3695 "name=\"test\" depends=\""))
3697 (replace 'install (install-jars "dist")))))
3699 `(("java-htsjdk" ,java-htsjdk)
3700 ("java-guava" ,java-guava)))
3702 `(("java-testng" ,java-testng)))
3703 (home-page "http://broadinstitute.github.io/picard/")
3704 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3705 (description "Picard is a set of Java command line tools for manipulating
3706 high-throughput sequencing (HTS) data and formats. Picard is implemented
3707 using the HTSJDK Java library to support accessing file formats that are
3708 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3710 (license license:expat)))
3712 ;; This is needed for dropseq-tools
3713 (define-public java-picard-2.10.3
3715 (name "java-picard")
3720 (url "https://github.com/broadinstitute/picard.git")
3722 (file-name (string-append "java-picard-" version "-checkout"))
3725 "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi"))))
3726 (build-system ant-build-system)
3728 `(#:jar-name "picard.jar"
3729 ;; Tests require jacoco:coverage.
3732 #:main-class "picard.cmdline.PicardCommandLine"
3733 #:modules ((guix build ant-build-system)
3735 (guix build java-utils)
3740 (modify-phases %standard-phases
3741 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3742 (delete 'generate-jar-indices)
3743 (add-after 'unpack 'remove-useless-build.xml
3744 (lambda _ (delete-file "build.xml") #t))
3745 ;; This is necessary to ensure that htsjdk is found when using
3746 ;; picard.jar as an executable.
3747 (add-before 'build 'edit-classpath-in-manifest
3748 (lambda* (#:key inputs #:allow-other-keys)
3749 (chmod "build.xml" #o664)
3750 (call-with-output-file "build.xml.new"
3754 (with-input-from-file "build.xml"
3755 (lambda _ (xml->sxml #:trim-whitespace? #t)))
3756 `((target . ,(lambda (tag . kids)
3757 (let ((name ((sxpath '(name *text*))
3759 ;; FIXME: We're breaking the line
3760 ;; early with a dummy path to
3761 ;; ensure that the store reference
3762 ;; isn't broken apart and can still
3763 ;; be found by the reference
3768 ~a/share/java/htsjdk.jar${line.separator}${line.separator}"
3769 ;; maximum line length is 70
3770 (string-tabulate (const #\b) 57)
3771 (assoc-ref inputs "java-htsjdk"))))
3772 (if (member "manifest" name)
3775 (@ (file "${manifest.file}")
3776 (match "\\r\\n\\r\\n")
3777 (replace "${line.separator}")))
3780 (file "${manifest.file}")
3783 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
3784 (*text* . ,(lambda (_ txt) txt))))
3786 (rename-file "build.xml.new" "build.xml")
3789 `(("java-htsjdk" ,java-htsjdk-2.10.1)))
3791 `(("java-testng" ,java-testng)
3792 ("java-guava" ,java-guava)))
3793 (home-page "http://broadinstitute.github.io/picard/")
3794 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3795 (description "Picard is a set of Java command line tools for manipulating
3796 high-throughput sequencing (HTS) data and formats. Picard is implemented
3797 using the HTSJDK Java library to support accessing file formats that are
3798 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3800 (license license:expat)))
3802 ;; This is the last version of Picard to provide net.sf.samtools
3803 (define-public java-picard-1.113
3804 (package (inherit java-picard)
3805 (name "java-picard")
3810 (url "https://github.com/broadinstitute/picard.git")
3812 (file-name (string-append "java-picard-" version "-checkout"))
3815 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
3816 (modules '((guix build utils)))
3819 ;; Delete pre-built binaries.
3820 (delete-file-recursively "lib")
3823 (build-system ant-build-system)
3825 `(#:build-target "picard-jar"
3826 #:test-target "test"
3827 ;; FIXME: the class path at test time is wrong.
3828 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
3829 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
3832 ;; This is only used for tests.
3834 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
3836 (modify-phases %standard-phases
3837 ;; FIXME: This phase fails.
3838 (delete 'generate-jar-indices)
3839 ;; Do not use bundled ant bzip2.
3840 (add-after 'unpack 'use-ant-bzip
3841 (lambda* (#:key inputs #:allow-other-keys)
3842 (substitute* "build.xml"
3843 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
3844 (string-append (assoc-ref inputs "ant")
3847 (add-after 'unpack 'make-test-target-independent
3848 (lambda* (#:key inputs #:allow-other-keys)
3849 (substitute* "build.xml"
3850 (("name=\"test\" depends=\"compile, ")
3851 "name=\"test\" depends=\"compile-tests, ")
3852 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
3853 "name=\"compile\" depends=\"compile-src\""))
3855 (add-after 'unpack 'fix-deflater-path
3856 (lambda* (#:key outputs #:allow-other-keys)
3857 (substitute* "src/java/net/sf/samtools/Defaults.java"
3858 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
3859 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
3860 (assoc-ref outputs "out")
3861 "/lib/jni/libIntelDeflater.so"
3864 ;; Build the deflater library, because we've previously deleted the
3865 ;; pre-built one. This can only be built with access to the JDK
3867 (add-after 'build 'build-jni
3868 (lambda* (#:key inputs #:allow-other-keys)
3871 (invoke "tar" "--strip-components=1" "-C" "jdk-src"
3872 "-xf" (assoc-ref inputs "jdk-src"))
3873 (invoke "javah" "-jni"
3874 "-classpath" "classes"
3876 "net.sf.samtools.util.zip.IntelDeflater")
3877 (with-directory-excursion "src/c/inteldeflater"
3878 (invoke "gcc" "-I../../../lib" "-I."
3879 (string-append "-I" (assoc-ref inputs "jdk")
3881 "-I../../../jdk-src/src/share/native/common/"
3882 "-I../../../jdk-src/src/solaris/native/common/"
3883 "-c" "-O3" "-fPIC" "IntelDeflater.c")
3884 (invoke "gcc" "-shared"
3885 "-o" "../../../lib/jni/libIntelDeflater.so"
3886 "IntelDeflater.o" "-lz" "-lstdc++"))
3888 ;; We can only build everything else after building the JNI library.
3889 (add-after 'build-jni 'build-rest
3890 (lambda* (#:key make-flags #:allow-other-keys)
3891 (apply invoke `("ant" "all" ,@make-flags))
3893 (add-before 'build 'set-JAVA6_HOME
3895 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
3897 (replace 'install (install-jars "dist"))
3898 (add-after 'install 'install-jni-lib
3899 (lambda* (#:key outputs #:allow-other-keys)
3900 (let ((jni (string-append (assoc-ref outputs "out")
3903 (install-file "lib/jni/libIntelDeflater.so" jni)
3906 `(("java-snappy-1" ,java-snappy-1)
3907 ("java-commons-jexl-2" ,java-commons-jexl-2)
3908 ("java-cofoja" ,java-cofoja)
3909 ("ant" ,ant) ; for bzip2 support at runtime
3912 `(("ant-apache-bcel" ,ant-apache-bcel)
3913 ("ant-junit" ,ant-junit)
3914 ("java-testng" ,java-testng)
3915 ("java-commons-bcel" ,java-commons-bcel)
3916 ("java-jcommander" ,java-jcommander)
3917 ("jdk" ,icedtea-8 "jdk")
3918 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
3920 (define-public fastqc
3927 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
3928 "projects/fastqc/fastqc_v"
3929 version "_source.zip"))
3932 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
3933 (build-system ant-build-system)
3935 `(#:tests? #f ; there are no tests
3936 #:build-target "build"
3938 (modify-phases %standard-phases
3939 (add-after 'unpack 'fix-dependencies
3940 (lambda* (#:key inputs #:allow-other-keys)
3941 (substitute* "build.xml"
3943 (string-append (assoc-ref inputs "java-jbzip2")
3944 "/share/java/jbzip2.jar"))
3946 (string-append (assoc-ref inputs "java-picard-1.113")
3947 "/share/java/sam-1.112.jar"))
3949 (string-append (assoc-ref inputs "java-cisd-jhdf5")
3950 "/share/java/sis-jhdf5.jar")))
3952 ;; There is no installation target
3954 (lambda* (#:key inputs outputs #:allow-other-keys)
3955 (let* ((out (assoc-ref outputs "out"))
3956 (bin (string-append out "/bin"))
3957 (share (string-append out "/share/fastqc/"))
3958 (exe (string-append share "/fastqc")))
3959 (for-each mkdir-p (list bin share))
3960 (copy-recursively "bin" share)
3962 (("my \\$java_bin = 'java';")
3963 (string-append "my $java_bin = '"
3964 (assoc-ref inputs "java")
3967 (symlink exe (string-append bin "/fastqc"))
3971 ("perl" ,perl) ; needed for the wrapper script
3972 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
3973 ("java-picard-1.113" ,java-picard-1.113)
3974 ("java-jbzip2" ,java-jbzip2)))
3976 `(("unzip" ,unzip)))
3977 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
3978 (synopsis "Quality control tool for high throughput sequence data")
3980 "FastQC aims to provide a simple way to do some quality control
3981 checks on raw sequence data coming from high throughput sequencing
3982 pipelines. It provides a modular set of analyses which you can use to
3983 give a quick impression of whether your data has any problems of which
3984 you should be aware before doing any further analysis.
3986 The main functions of FastQC are:
3989 @item Import of data from BAM, SAM or FastQ files (any variant);
3990 @item Providing a quick overview to tell you in which areas there may
3992 @item Summary graphs and tables to quickly assess your data;
3993 @item Export of results to an HTML based permanent report;
3994 @item Offline operation to allow automated generation of reports
3995 without running the interactive application.
3997 (license license:gpl3+)))
3999 (define-public fastp
4007 (url "https://github.com/OpenGene/fastp.git")
4008 (commit (string-append "v" version))))
4009 (file-name (git-file-name name version))
4012 "1r6ms5zbf5rps4rgp4z73nczadl00b5rqylw8f684isfz27dp0xh"))))
4013 (build-system gnu-build-system)
4015 `(#:tests? #f ; there are none
4017 (list (string-append "BINDIR=" (assoc-ref %outputs "out") "/bin"))
4019 (modify-phases %standard-phases
4021 (add-before 'install 'create-target-dir
4022 (lambda* (#:key outputs #:allow-other-keys)
4023 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4027 (home-page "https://github.com/OpenGene/fastp/")
4028 (synopsis "All-in-one FastQ preprocessor")
4030 "Fastp is a tool designed to provide fast all-in-one preprocessing for
4031 FastQ files. This tool has multi-threading support to afford high
4033 (license license:expat)))
4035 (define-public htslib
4042 "https://github.com/samtools/htslib/releases/download/"
4043 version "/htslib-" version ".tar.bz2"))
4046 "16ljv43sc3fxmv63w7b2ff8m1s7h89xhazwmbm1bicz8axq8fjz0"))))
4047 (build-system gnu-build-system)
4049 `(("openssl" ,openssl)
4054 (home-page "http://www.htslib.org")
4055 (synopsis "C library for reading/writing high-throughput sequencing data")
4057 "HTSlib is a C library for reading/writing high-throughput sequencing
4058 data. It also provides the @command{bgzip}, @command{htsfile}, and
4059 @command{tabix} utilities.")
4060 ;; Files under cram/ are released under the modified BSD license;
4061 ;; the rest is released under the Expat license
4062 (license (list license:expat license:bsd-3))))
4064 ;; This package should be removed once no packages rely upon it.
4072 "https://github.com/samtools/htslib/releases/download/"
4073 version "/htslib-" version ".tar.bz2"))
4076 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
4085 (url "https://github.com/nboley/idr.git")
4087 (file-name (git-file-name name version))
4090 "04j876h6z444v2q79drxx283d3k5snd72kj895wbalnl42206x9g"))
4091 ;; Delete generated C code.
4093 '(begin (delete-file "idr/inv_cdf.c") #t))))
4094 (build-system python-build-system)
4095 ;; There is only one test ("test_inv_cdf.py") and it tests features that
4096 ;; are no longer part of this package. It also asserts False, which
4097 ;; causes the tests to always fail.
4098 (arguments `(#:tests? #f))
4100 `(("python-scipy" ,python-scipy)
4101 ("python-sympy" ,python-sympy)
4102 ("python-numpy" ,python-numpy)
4103 ("python-matplotlib" ,python-matplotlib)))
4105 `(("python-cython" ,python-cython)))
4106 (home-page "https://github.com/nboley/idr")
4107 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
4109 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
4110 to measure the reproducibility of findings identified from replicate
4111 experiments and provide highly stable thresholds based on reproducibility.")
4112 (license license:gpl2+)))
4114 (define-public jellyfish
4120 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
4121 "releases/download/v" version
4122 "/jellyfish-" version ".tar.gz"))
4125 "1k4pc3fvv6w1km2yph4m5sd78fbxp21d6xyzgmy0gjihzc6mb249"))))
4126 (build-system gnu-build-system)
4127 (outputs '("out" ;for library
4128 "ruby" ;for Ruby bindings
4129 "python")) ;for Python bindings
4132 (list (string-append "--enable-ruby-binding="
4133 (assoc-ref %outputs "ruby"))
4134 (string-append "--enable-python-binding="
4135 (assoc-ref %outputs "python")))
4137 (modify-phases %standard-phases
4138 (add-before 'check 'set-SHELL-variable
4140 ;; generator_manager.hpp either uses /bin/sh or $SHELL
4142 (setenv "SHELL" (which "bash"))
4148 ("python" ,python-2)
4149 ("pkg-config" ,pkg-config)))
4151 `(("htslib" ,htslib)))
4152 (synopsis "Tool for fast counting of k-mers in DNA")
4154 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
4155 DNA. A k-mer is a substring of length k, and counting the occurrences of all
4156 such substrings is a central step in many analyses of DNA sequence. Jellyfish
4157 is a command-line program that reads FASTA and multi-FASTA files containing
4158 DNA sequences. It outputs its k-mer counts in a binary format, which can be
4159 translated into a human-readable text format using the @code{jellyfish dump}
4160 command, or queried for specific k-mers with @code{jellyfish query}.")
4161 (home-page "http://www.genome.umd.edu/jellyfish.html")
4162 ;; JELLYFISH seems to be 64-bit only.
4163 (supported-systems '("x86_64-linux" "aarch64-linux" "mips64el-linux"))
4164 ;; The combined work is published under the GPLv3 or later. Individual
4165 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
4166 (license (list license:gpl3+ license:expat))))
4168 (define-public khmer
4176 (url "https://github.com/dib-lab/khmer.git")
4177 (commit (string-append "v" version))))
4178 (file-name (git-file-name name version))
4181 "02x38d9jw2r58y8dmnj4hffy9wxv1yc1jwbvdbhby9dxndv94r9m"))
4182 (patches (search-patches "khmer-use-libraries.patch"))
4183 (modules '((guix build utils)))
4186 ;; Delete bundled libraries. We do not replace the bundled seqan
4187 ;; as it is a modified subset of the old version 1.4.1.
4189 ;; We do not replace the bundled MurmurHash as the canonical
4190 ;; repository for this code 'SMHasher' is unsuitable for providing
4192 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
4193 (delete-file-recursively "third-party/zlib")
4194 (delete-file-recursively "third-party/bzip2")
4196 (build-system python-build-system)
4199 (modify-phases %standard-phases
4200 (add-after 'unpack 'set-cc
4201 (lambda _ (setenv "CC" "gcc") #t))
4202 ;; FIXME: This fails with "permission denied".
4203 (delete 'reset-gzip-timestamps))))
4205 `(("python-cython" ,python-cython)
4206 ("python-pytest" ,python-pytest)
4207 ("python-pytest-runner" ,python-pytest-runner)))
4211 ("python-screed" ,python-screed)
4212 ("python-bz2file" ,python-bz2file)))
4213 (home-page "https://khmer.readthedocs.org/")
4214 (synopsis "K-mer counting, filtering and graph traversal library")
4215 (description "The khmer software is a set of command-line tools for
4216 working with DNA shotgun sequencing data from genomes, transcriptomes,
4217 metagenomes and single cells. Khmer can make de novo assemblies faster, and
4218 sometimes better. Khmer can also identify and fix problems with shotgun
4220 ;; When building on i686, armhf and mips64el, we get the following error:
4221 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
4222 (supported-systems '("x86_64-linux" "aarch64-linux"))
4223 (license license:bsd-3)))
4225 (define-public kaiju
4232 (url "https://github.com/bioinformatics-centre/kaiju")
4233 (commit (string-append "v" version))))
4234 (file-name (git-file-name name version))
4237 "119pzi0ddzv9mjg4wwa6han0cwr3k3ssn7kirvsjfcq05mi5ka0x"))))
4238 (build-system gnu-build-system)
4240 `(#:tests? #f ; There are no tests.
4242 (modify-phases %standard-phases
4244 (add-before 'build 'move-to-src-dir
4245 (lambda _ (chdir "src") #t))
4247 (lambda* (#:key inputs outputs #:allow-other-keys)
4248 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
4251 (copy-recursively "bin" bin))
4256 (home-page "http://kaiju.binf.ku.dk/")
4257 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
4258 (description "Kaiju is a program for sensitive taxonomic classification
4259 of high-throughput sequencing reads from metagenomic whole genome sequencing
4261 (license license:gpl3+)))
4266 (version "2.1.1.20160309")
4269 (uri (pypi-uri "MACS2" version))
4272 "09ixspd1vcqmz1c81ih70xs4m7qml2iy5vyx1y74zww3iy1vl210"))))
4273 (build-system python-build-system)
4275 `(#:python ,python-2 ; only compatible with Python 2.7
4276 #:tests? #f)) ; no test target
4278 `(("python-numpy" ,python2-numpy)))
4279 (home-page "https://github.com/taoliu/MACS/")
4280 (synopsis "Model based analysis for ChIP-Seq data")
4282 "MACS is an implementation of a ChIP-Seq analysis algorithm for
4283 identifying transcript factor binding sites named Model-based Analysis of
4284 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
4285 the significance of enriched ChIP regions and it improves the spatial
4286 resolution of binding sites through combining the information of both
4287 sequencing tag position and orientation.")
4288 (license license:bsd-3)))
4290 (define-public mafft
4297 "https://mafft.cbrc.jp/alignment/software/mafft-" version
4298 "-without-extensions-src.tgz"))
4299 (file-name (string-append name "-" version ".tgz"))
4302 "0bacjkxfg944p5khhyh5rd4y7wkjc9qk4v2jjj442sqlq0f8ar7b"))))
4303 (build-system gnu-build-system)
4305 `(#:tests? #f ; no automated tests, though there are tests in the read me
4306 #:make-flags (let ((out (assoc-ref %outputs "out")))
4307 (list (string-append "PREFIX=" out)
4308 (string-append "BINDIR="
4309 (string-append out "/bin"))))
4311 (modify-phases %standard-phases
4312 (add-after 'unpack 'enter-dir
4313 (lambda _ (chdir "core") #t))
4314 (add-after 'enter-dir 'patch-makefile
4316 ;; on advice from the MAFFT authors, there is no need to
4317 ;; distribute mafft-profile, mafft-distance, or
4318 ;; mafft-homologs.rb as they are too "specialised".
4319 (substitute* "Makefile"
4320 ;; remove mafft-homologs.rb from SCRIPTS
4321 (("^SCRIPTS = mafft mafft-homologs.rb")
4323 ;; remove mafft-homologs from MANPAGES
4324 (("^MANPAGES = mafft.1 mafft-homologs.1")
4325 "MANPAGES = mafft.1")
4326 ;; remove mafft-distance from PROGS
4327 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
4328 "PROGS = dvtditr dndfast7 dndblast sextet5")
4329 ;; remove mafft-profile from PROGS
4330 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
4331 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
4332 (("^rm -f mafft-profile mafft-profile.exe") "#")
4333 (("^rm -f mafft-distance mafft-distance.exe") ")#")
4334 ;; do not install MAN pages in libexec folder
4335 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
4336 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
4338 (add-after 'enter-dir 'patch-paths
4339 (lambda* (#:key inputs #:allow-other-keys)
4340 (substitute* '("pairash.c"
4342 (("perl") (which "perl"))
4343 (("([\"`| ])awk" _ prefix)
4344 (string-append prefix (which "awk")))
4345 (("grep") (which "grep")))
4348 (add-after 'install 'wrap-programs
4349 (lambda* (#:key outputs #:allow-other-keys)
4350 (let* ((out (assoc-ref outputs "out"))
4351 (bin (string-append out "/bin"))
4352 (path (string-append
4353 (assoc-ref %build-inputs "coreutils") "/bin:")))
4354 (for-each (lambda (file)
4356 `("PATH" ":" prefix (,path))))
4364 ("coreutils" ,coreutils)))
4365 (home-page "http://mafft.cbrc.jp/alignment/software/")
4366 (synopsis "Multiple sequence alignment program")
4368 "MAFFT offers a range of multiple alignment methods for nucleotide and
4369 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
4370 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
4372 (license (license:non-copyleft
4373 "http://mafft.cbrc.jp/alignment/software/license.txt"
4374 "BSD-3 with different formatting"))))
4383 (url "https://github.com/marbl/mash.git")
4384 (commit (string-append "v" version))))
4385 (file-name (git-file-name name version))
4388 "049hwcc059p2fd9vwndn63laifvvsi0wmv84i6y1fr79k15dxwy6"))
4389 (modules '((guix build utils)))
4392 ;; Delete bundled kseq.
4393 ;; TODO: Also delete bundled murmurhash and open bloom filter.
4394 (delete-file "src/mash/kseq.h")
4396 (build-system gnu-build-system)
4398 `(#:tests? #f ; No tests.
4401 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
4402 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
4403 #:make-flags (list "CC=gcc")
4405 (modify-phases %standard-phases
4406 (add-after 'unpack 'fix-includes
4408 (substitute* '("src/mash/Sketch.cpp"
4409 "src/mash/CommandFind.cpp"
4410 "src/mash/CommandScreen.cpp")
4411 (("^#include \"kseq\\.h\"")
4412 "#include \"htslib/kseq.h\""))
4414 (add-after 'fix-includes 'use-c++14
4416 ;; capnproto 0.7 requires c++14 to build
4417 (substitute* "configure.ac"
4418 (("c\\+\\+11") "c++14"))
4419 (substitute* "Makefile.in"
4420 (("c\\+\\+11") "c++14"))
4423 `(("autoconf" ,autoconf)
4424 ;; Capnproto and htslib are statically embedded in the final
4425 ;; application. Therefore we also list their licenses, below.
4426 ("capnproto" ,capnproto)
4427 ("htslib" ,htslib)))
4431 (supported-systems '("x86_64-linux"))
4432 (home-page "https://mash.readthedocs.io")
4433 (synopsis "Fast genome and metagenome distance estimation using MinHash")
4434 (description "Mash is a fast sequence distance estimator that uses the
4435 MinHash algorithm and is designed to work with genomes and metagenomes in the
4436 form of assemblies or reads.")
4437 (license (list license:bsd-3 ; Mash
4438 license:expat ; HTSlib and capnproto
4439 license:public-domain ; MurmurHash 3
4440 license:cpl1.0)))) ; Open Bloom Filter
4442 (define-public metabat
4450 (url "https://bitbucket.org/berkeleylab/metabat.git")
4451 (commit (string-append "v" version))))
4452 (file-name (git-file-name name version))
4455 "0hyg2smw1nz69mfvjpk45xyyychmda92c80a0cv7baji84ri4iyn"))
4456 (patches (search-patches "metabat-fix-compilation.patch"))))
4457 (build-system scons-build-system)
4459 `(#:scons ,scons-python2
4461 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
4462 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
4463 #:tests? #f ;; Tests are run during the build phase.
4465 (modify-phases %standard-phases
4466 (add-after 'unpack 'fix-includes
4468 (substitute* "src/BamUtils.h"
4469 (("^#include \"bam/bam\\.h\"")
4470 "#include \"samtools/bam.h\"")
4471 (("^#include \"bam/sam\\.h\"")
4472 "#include \"samtools/sam.h\""))
4473 (substitute* "src/KseqReader.h"
4474 (("^#include \"bam/kseq\\.h\"")
4475 "#include \"htslib/kseq.h\""))
4477 (add-after 'unpack 'fix-scons
4478 (lambda* (#:key inputs #:allow-other-keys)
4479 (substitute* "SConstruct"
4480 (("^htslib_dir += 'samtools'")
4481 (string-append "htslib_dir = '"
4482 (assoc-ref inputs "htslib")
4484 (("^samtools_dir = 'samtools'")
4485 (string-append "samtools_dir = '"
4486 (assoc-ref inputs "samtools")
4488 (("^findStaticOrShared\\('bam', hts_lib")
4489 (string-append "findStaticOrShared('bam', '"
4490 (assoc-ref inputs "samtools")
4492 ;; Do not distribute README.
4493 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
4498 ("samtools" ,samtools)
4501 (home-page "https://bitbucket.org/berkeleylab/metabat")
4503 "Reconstruction of single genomes from complex microbial communities")
4505 "Grouping large genomic fragments assembled from shotgun metagenomic
4506 sequences to deconvolute complex microbial communities, or metagenome binning,
4507 enables the study of individual organisms and their interactions. MetaBAT is
4508 an automated metagenome binning software, which integrates empirical
4509 probabilistic distances of genome abundance and tetranucleotide frequency.")
4510 ;; The source code contains inline assembly.
4511 (supported-systems '("x86_64-linux" "i686-linux"))
4512 (license (license:non-copyleft "file://license.txt"
4513 "See license.txt in the distribution."))))
4515 (define-public minced
4522 (url "https://github.com/ctSkennerton/minced.git")
4524 (file-name (git-file-name name version))
4527 "1f5h9him0gd355cnx7p6pnxpknhckd4g0v62mg8zyhfbx9as25fv"))))
4528 (build-system gnu-build-system)
4530 `(#:test-target "test"
4532 (modify-phases %standard-phases
4534 (add-before 'check 'fix-test
4536 ;; Fix test for latest version.
4537 (substitute* "t/Aquifex_aeolicus_VF5.expected"
4538 (("minced:0.1.6") "minced:0.2.0"))
4540 (replace 'install ; No install target.
4541 (lambda* (#:key inputs outputs #:allow-other-keys)
4542 (let* ((out (assoc-ref outputs "out"))
4543 (bin (string-append out "/bin"))
4544 (wrapper (string-append bin "/minced")))
4545 ;; Minced comes with a wrapper script that tries to figure out where
4546 ;; it is located before running the JAR. Since these paths are known
4547 ;; to us, we build our own wrapper to avoid coreutils dependency.
4548 (install-file "minced.jar" bin)
4549 (with-output-to-file wrapper
4553 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
4554 (assoc-ref inputs "jre") "/bin/java -jar "
4555 bin "/minced.jar \"$@\"\n"))))
4556 (chmod wrapper #o555))
4559 `(("jdk" ,icedtea "jdk")))
4562 ("jre" ,icedtea "out")))
4563 (home-page "https://github.com/ctSkennerton/minced")
4564 (synopsis "Mining CRISPRs in Environmental Datasets")
4566 "MinCED is a program to find Clustered Regularly Interspaced Short
4567 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
4568 unassembled metagenomic reads, but is mainly designed for full genomes and
4569 assembled metagenomic sequence.")
4570 (license license:gpl3+)))
4578 (uri (pypi-uri "misopy" version))
4581 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
4582 (modules '((guix build utils)))
4584 (substitute* "setup.py"
4585 ;; Use setuptools, or else the executables are not
4587 (("distutils.core") "setuptools")
4588 ;; use "gcc" instead of "cc" for compilation
4590 "cc.set_executables(
4594 linker_so='gcc -shared'); defines"))
4596 (build-system python-build-system)
4598 `(#:python ,python-2 ; only Python 2 is supported
4599 #:tests? #f)) ; no "test" target
4601 `(("samtools" ,samtools)
4602 ("python-numpy" ,python2-numpy)
4603 ("python-pysam" ,python2-pysam)
4604 ("python-scipy" ,python2-scipy)
4605 ("python-matplotlib" ,python2-matplotlib)))
4607 `(("python-mock" ,python2-mock) ;for tests
4608 ("python-pytz" ,python2-pytz))) ;for tests
4609 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
4610 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
4612 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
4613 the expression level of alternatively spliced genes from RNA-Seq data, and
4614 identifies differentially regulated isoforms or exons across samples. By
4615 modeling the generative process by which reads are produced from isoforms in
4616 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
4617 that a read originated from a particular isoform.")
4618 (license license:gpl2)))
4620 (define-public muscle
4623 (version "3.8.1551")
4625 (method url-fetch/tarbomb)
4627 "http://www.drive5.com/muscle/muscle_src_"
4631 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
4632 (build-system gnu-build-system)
4634 `(#:make-flags (list "LDLIBS = -lm")
4636 (modify-phases %standard-phases
4639 ;; There are no tests, so just test if it runs.
4640 (lambda _ (invoke "./muscle" "-version") #t))
4642 (lambda* (#:key outputs #:allow-other-keys)
4643 (let* ((out (assoc-ref outputs "out"))
4644 (bin (string-append out "/bin")))
4645 (install-file "muscle" bin)
4647 (home-page "http://www.drive5.com/muscle")
4648 (synopsis "Multiple sequence alignment program")
4650 "MUSCLE aims to be a fast and accurate multiple sequence alignment
4651 program for nucleotide and protein sequences.")
4652 ;; License information found in 'muscle -h' and usage.cpp.
4653 (license license:public-domain)))
4655 (define-public newick-utils
4656 ;; There are no recent releases so we package from git.
4657 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
4659 (name "newick-utils")
4660 (version (string-append "1.6-1." (string-take commit 8)))
4664 (url "https://github.com/tjunier/newick_utils.git")
4666 (file-name (string-append name "-" version "-checkout"))
4669 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4670 (build-system gnu-build-system)
4672 ;; XXX: TODO: Enable Lua and Guile bindings.
4673 ;; https://github.com/tjunier/newick_utils/issues/13
4674 `(("libxml2" ,libxml2)
4678 `(("autoconf" ,autoconf)
4679 ("automake" ,automake)
4680 ("libtool" ,libtool)))
4681 (synopsis "Programs for working with newick format phylogenetic trees")
4683 "Newick-utils is a suite of utilities for processing phylogenetic trees
4684 in Newick format. Functions include re-rooting, extracting subtrees,
4685 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4686 (home-page "https://github.com/tjunier/newick_utils")
4687 (license license:bsd-3))))
4696 "https://github.com/wwood/OrfM/releases/download/v"
4697 version "/orfm-" version ".tar.gz"))
4700 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4701 (build-system gnu-build-system)
4702 (inputs `(("zlib" ,zlib)))
4704 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4705 ("ruby-rspec" ,ruby-rspec)
4707 (synopsis "Simple and not slow open reading frame (ORF) caller")
4709 "An ORF caller finds stretches of DNA that, when translated, are not
4710 interrupted by stop codons. OrfM finds and prints these ORFs.")
4711 (home-page "https://github.com/wwood/OrfM")
4712 (license license:lgpl3+)))
4714 (define-public python2-pbcore
4716 (name "python2-pbcore")
4720 (uri (pypi-uri "pbcore" version))
4723 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4724 (build-system python-build-system)
4725 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
4727 `(("python-cython" ,python2-cython)
4728 ("python-numpy" ,python2-numpy)
4729 ("python-pysam" ,python2-pysam)
4730 ("python-h5py" ,python2-h5py)))
4732 `(("python-nose" ,python2-nose)
4733 ("python-sphinx" ,python2-sphinx)
4734 ("python-pyxb" ,python2-pyxb)))
4735 (home-page "http://pacificbiosciences.github.io/pbcore/")
4736 (synopsis "Library for reading and writing PacBio data files")
4738 "The pbcore package provides Python APIs for interacting with PacBio data
4739 files and writing bioinformatics applications.")
4740 (license license:bsd-3)))
4742 (define-public python2-warpedlmm
4744 (name "python2-warpedlmm")
4749 (uri (pypi-uri "WarpedLMM" version ".zip"))
4752 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4753 (build-system python-build-system)
4755 `(#:python ,python-2)) ; requires Python 2.7
4757 `(("python-scipy" ,python2-scipy)
4758 ("python-numpy" ,python2-numpy)
4759 ("python-matplotlib" ,python2-matplotlib)
4760 ("python-fastlmm" ,python2-fastlmm)
4761 ("python-pandas" ,python2-pandas)
4762 ("python-pysnptools" ,python2-pysnptools)))
4764 `(("python-mock" ,python2-mock)
4765 ("python-nose" ,python2-nose)
4767 (home-page "https://github.com/PMBio/warpedLMM")
4768 (synopsis "Implementation of warped linear mixed models")
4770 "WarpedLMM is a Python implementation of the warped linear mixed model,
4771 which automatically learns an optimal warping function (or transformation) for
4772 the phenotype as it models the data.")
4773 (license license:asl2.0)))
4775 (define-public pbtranscript-tofu
4776 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
4778 (name "pbtranscript-tofu")
4779 (version (string-append "2.2.3." (string-take commit 7)))
4783 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
4785 (file-name (string-append name "-" version "-checkout"))
4788 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
4789 (modules '((guix build utils)))
4792 ;; remove bundled Cython sources
4793 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
4795 (build-system python-build-system)
4797 `(#:python ,python-2
4798 ;; FIXME: Tests fail with "No such file or directory:
4799 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
4802 (modify-phases %standard-phases
4803 (add-after 'unpack 'enter-directory
4805 (chdir "pbtranscript-tofu/pbtranscript/")
4807 ;; With setuptools version 18.0 and later this setup.py hack causes
4808 ;; a build error, so we disable it.
4809 (add-after 'enter-directory 'patch-setuppy
4811 (substitute* "setup.py"
4812 (("if 'setuptools.extension' in sys.modules:")
4816 `(("python-numpy" ,python2-numpy)
4817 ("python-bx-python" ,python2-bx-python)
4818 ("python-networkx" ,python2-networkx)
4819 ("python-scipy" ,python2-scipy)
4820 ("python-pbcore" ,python2-pbcore)
4821 ("python-h5py" ,python2-h5py)))
4823 `(("python-cython" ,python2-cython)
4824 ("python-nose" ,python2-nose)))
4825 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4826 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4828 "pbtranscript-tofu contains scripts to analyze transcriptome data
4829 generated using the PacBio Iso-Seq protocol.")
4830 (license license:bsd-3))))
4832 (define-public prank
4839 "http://wasabiapp.org/download/prank/prank.source."
4843 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
4844 (build-system gnu-build-system)
4847 (modify-phases %standard-phases
4848 (add-after 'unpack 'enter-src-dir
4852 (add-after 'unpack 'remove-m64-flag
4853 ;; Prank will build with the correct 'bit-ness' without this flag
4854 ;; and this allows building on 32-bit machines.
4855 (lambda _ (substitute* "src/Makefile"
4860 (lambda* (#:key outputs #:allow-other-keys)
4861 (let* ((out (assoc-ref outputs "out"))
4862 (bin (string-append out "/bin"))
4863 (man (string-append out "/share/man/man1"))
4864 (path (string-append
4865 (assoc-ref %build-inputs "mafft") "/bin:"
4866 (assoc-ref %build-inputs "exonerate") "/bin:"
4867 (assoc-ref %build-inputs "bppsuite") "/bin")))
4868 (install-file "prank" bin)
4869 (wrap-program (string-append bin "/prank")
4870 `("PATH" ":" prefix (,path)))
4871 (install-file "prank.1" man))
4875 ("exonerate" ,exonerate)
4876 ("bppsuite" ,bppsuite)))
4877 (home-page "http://wasabiapp.org/software/prank/")
4878 (synopsis "Probabilistic multiple sequence alignment program")
4880 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4881 codon and amino-acid sequences. It is based on a novel algorithm that treats
4882 insertions correctly and avoids over-estimation of the number of deletion
4883 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4884 in phylogenetics and correctly takes into account the evolutionary distances
4885 between sequences. Lastly, PRANK allows for defining a potential structure
4886 for sequences to be aligned and then, simultaneously with the alignment,
4887 predicts the locations of structural units in the sequences.")
4888 (license license:gpl2+)))
4890 (define-public proteinortho
4892 (name "proteinortho")
4899 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4900 version "_src.tar.gz"))
4903 "1wl0dawpssqwfjvr651r4wlww8hhjin8nba6xh71ks7sbypx886j"))))
4904 (build-system gnu-build-system)
4906 `(#:test-target "test"
4908 (modify-phases %standard-phases
4910 ;; There is no configure script, so we modify the Makefile directly.
4911 (lambda* (#:key outputs #:allow-other-keys)
4912 (substitute* "Makefile"
4915 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4917 (add-before 'install 'make-install-directory
4918 ;; The install directory is not created during 'make install'.
4919 (lambda* (#:key outputs #:allow-other-keys)
4920 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4922 (add-after 'install 'wrap-programs
4923 (lambda* (#:key inputs outputs #:allow-other-keys)
4924 (let* ((path (getenv "PATH"))
4925 (out (assoc-ref outputs "out"))
4926 (binary (string-append out "/bin/proteinortho5.pl")))
4927 (wrap-program binary `("PATH" ":" prefix (,path))))
4931 ("python" ,python-2)
4932 ("blast+" ,blast+)))
4933 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4934 (synopsis "Detect orthologous genes across species")
4936 "Proteinortho is a tool to detect orthologous genes across different
4937 species. For doing so, it compares similarities of given gene sequences and
4938 clusters them to find significant groups. The algorithm was designed to handle
4939 large-scale data and can be applied to hundreds of species at once.")
4940 (license license:gpl2+)))
4942 (define-public pyicoteo
4950 (url "https://bitbucket.org/regulatorygenomicsupf/pyicoteo.git")
4951 (commit (string-append "v" version))))
4952 (file-name (git-file-name name version))
4955 "0hz5g8d25lbjy1wpscr490l0lmyvaix893hhax4fxnh1h9w34w8p"))))
4956 (build-system python-build-system)
4958 `(#:python ,python-2 ; does not work with Python 3
4959 #:tests? #f)) ; there are no tests
4961 `(("python2-matplotlib" ,python2-matplotlib)))
4962 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4963 (synopsis "Analyze high-throughput genetic sequencing data")
4965 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4966 sequencing data. It works with genomic coordinates. There are currently six
4967 different command-line tools:
4970 @item pyicoregion: for generating exploratory regions automatically;
4971 @item pyicoenrich: for differential enrichment between two conditions;
4972 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4973 @item pyicos: for genomic coordinates manipulation;
4974 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4975 @item pyicount: to count how many reads from N experiment files overlap in a
4977 @item pyicotrocol: to combine operations from pyicoteo.
4979 (license license:gpl3+)))
4981 (define-public prodigal
4988 (url "https://github.com/hyattpd/Prodigal.git")
4989 (commit (string-append "v" version))))
4990 (file-name (git-file-name name version))
4993 "1fs1hqk83qjbjhrvhw6ni75zakx5ki1ayy3v6wwkn3xvahc9hi5s"))))
4994 (build-system gnu-build-system)
4996 `(#:tests? #f ;no check target
4997 #:make-flags (list (string-append "INSTALLDIR="
4998 (assoc-ref %outputs "out")
5001 (modify-phases %standard-phases
5002 (delete 'configure))))
5003 (home-page "http://prodigal.ornl.gov")
5004 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
5006 "Prodigal runs smoothly on finished genomes, draft genomes, and
5007 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
5008 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
5009 partial genes, and identifies translation initiation sites.")
5010 (license license:gpl3+)))
5012 (define-public roary
5020 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
5024 "0qxrds9wx7cfhlkihrp6697kx0flhhxymap9fwan0b3rbdhcnmff"))))
5025 (build-system perl-build-system)
5028 (modify-phases %standard-phases
5033 ;; The tests are not run by default, so we run each test file
5035 (setenv "PATH" (string-append (getcwd) "/bin" ":"
5037 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
5038 (getenv "PERL5LIB")))
5039 (for-each (lambda (file)
5040 (display file)(display "\n")
5041 (invoke "perl" file))
5042 (find-files "t" ".*\\.t$"))
5045 ;; There is no 'install' target in the Makefile.
5046 (lambda* (#:key outputs #:allow-other-keys)
5047 (let* ((out (assoc-ref outputs "out"))
5048 (bin (string-append out "/bin"))
5049 (perl (string-append out "/lib/perl5/site_perl"))
5050 (roary-plots "contrib/roary_plots"))
5053 (copy-recursively "bin" bin)
5054 (copy-recursively "lib" perl)
5056 (add-after 'install 'wrap-programs
5057 (lambda* (#:key inputs outputs #:allow-other-keys)
5058 (let* ((out (assoc-ref outputs "out"))
5059 (perl5lib (getenv "PERL5LIB"))
5060 (path (getenv "PATH")))
5061 (for-each (lambda (prog)
5062 (let ((binary (string-append out "/" prog)))
5063 (wrap-program binary
5064 `("PERL5LIB" ":" prefix
5065 (,(string-append perl5lib ":" out
5066 "/lib/perl5/site_perl"))))
5067 (wrap-program binary
5069 (,(string-append path ":" out "/bin"))))))
5070 (find-files "bin" ".*[^R]$"))
5072 (string-append out "/bin/roary-create_pan_genome_plots.R"))
5073 (r-site-lib (getenv "R_LIBS_SITE"))
5075 (string-append (assoc-ref inputs "coreutils") "/bin")))
5077 `("R_LIBS_SITE" ":" prefix
5078 (,(string-append r-site-lib ":" out "/site-library/"))))
5081 (,(string-append coreutils-path ":" out "/bin"))))))
5084 `(("perl-env-path" ,perl-env-path)
5085 ("perl-test-files" ,perl-test-files)
5086 ("perl-test-most" ,perl-test-most)
5087 ("perl-test-output" ,perl-test-output)))
5089 `(("perl-array-utils" ,perl-array-utils)
5090 ("bioperl" ,bioperl-minimal)
5091 ("perl-digest-md5-file" ,perl-digest-md5-file)
5092 ("perl-exception-class" ,perl-exception-class)
5093 ("perl-file-find-rule" ,perl-file-find-rule)
5094 ("perl-file-grep" ,perl-file-grep)
5095 ("perl-file-slurper" ,perl-file-slurper)
5096 ("perl-file-which" ,perl-file-which)
5097 ("perl-graph" ,perl-graph)
5098 ("perl-graph-readwrite" ,perl-graph-readwrite)
5099 ("perl-log-log4perl" ,perl-log-log4perl)
5100 ("perl-moose" ,perl-moose)
5101 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
5102 ("perl-text-csv" ,perl-text-csv)
5103 ("bedtools" ,bedtools)
5107 ("parallel" ,parallel)
5110 ("fasttree" ,fasttree)
5114 ("r-minimal" ,r-minimal)
5115 ("r-ggplot2" ,r-ggplot2)
5116 ("coreutils" ,coreutils)))
5117 (home-page "http://sanger-pathogens.github.io/Roary")
5118 (synopsis "High speed stand-alone pan genome pipeline")
5120 "Roary is a high speed stand alone pan genome pipeline, which takes
5121 annotated assemblies in GFF3 format (produced by the Prokka program) and
5122 calculates the pan genome. Using a standard desktop PC, it can analyse
5123 datasets with thousands of samples, without compromising the quality of the
5124 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
5125 single processor. Roary is not intended for metagenomics or for comparing
5126 extremely diverse sets of genomes.")
5127 (license license:gpl3)))
5129 (define-public raxml
5137 (url "https://github.com/stamatak/standard-RAxML.git")
5138 (commit (string-append "v" version))))
5139 (file-name (git-file-name name version))
5142 "1jqjzhch0rips0vp04prvb8vmc20c5pdmsqn8knadcf91yy859fh"))))
5143 (build-system gnu-build-system)
5145 `(#:tests? #f ; There are no tests.
5146 ;; Use 'standard' Makefile rather than SSE or AVX ones.
5147 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
5149 (modify-phases %standard-phases
5152 (lambda* (#:key outputs #:allow-other-keys)
5153 (let* ((out (assoc-ref outputs "out"))
5154 (bin (string-append out "/bin"))
5155 (executable "raxmlHPC-HYBRID"))
5156 (install-file executable bin)
5157 (symlink (string-append bin "/" executable) "raxml"))
5160 `(("openmpi" ,openmpi)))
5161 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
5162 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
5164 "RAxML is a tool for phylogenetic analysis and post-analysis of large
5166 ;; The source includes x86 specific code
5167 (supported-systems '("x86_64-linux" "i686-linux"))
5168 (license license:gpl2+)))
5178 (url "https://github.com/deweylab/RSEM.git")
5179 (commit (string-append "v" version))))
5181 (base32 "1jlq11d1p8qp64w75yj8cnbbd1a93viq10pzsbwal7vdn8fg13j1"))
5182 (file-name (git-file-name name version))
5183 (modules '((guix build utils)))
5186 ;; remove bundled copy of boost and samtools
5187 (delete-file-recursively "boost")
5188 (delete-file-recursively "samtools-1.3")
5190 (build-system gnu-build-system)
5192 `(#:tests? #f ;no "check" target
5194 (list (string-append "BOOST="
5195 (assoc-ref %build-inputs "boost")
5197 (string-append "SAMHEADERS="
5198 (assoc-ref %build-inputs "htslib")
5199 "/include/htslib/sam.h")
5200 (string-append "SAMLIBS="
5201 (assoc-ref %build-inputs "htslib")
5204 (modify-phases %standard-phases
5205 ;; No "configure" script.
5206 ;; Do not build bundled samtools library.
5209 (substitute* "Makefile"
5210 (("^all : \\$\\(PROGRAMS\\).*") "all: $(PROGRAMS)\n")
5211 (("^\\$\\(SAMLIBS\\).*") ""))
5214 (lambda* (#:key outputs #:allow-other-keys)
5215 (let* ((out (string-append (assoc-ref outputs "out")))
5216 (bin (string-append out "/bin/"))
5217 (perl (string-append out "/lib/perl5/site_perl")))
5220 (for-each (lambda (file)
5221 (install-file file bin))
5222 (find-files "." "rsem-.*"))
5223 (install-file "rsem_perl_utils.pm" perl))
5225 (add-after 'install 'wrap-program
5226 (lambda* (#:key outputs #:allow-other-keys)
5227 (let ((out (assoc-ref outputs "out")))
5228 (for-each (lambda (prog)
5229 (wrap-program (string-append out "/bin/" prog)
5230 `("PERL5LIB" ":" prefix
5231 (,(string-append out "/lib/perl5/site_perl")))))
5232 '("rsem-calculate-expression"
5234 "rsem-generate-data-matrix"
5235 "rsem-generate-ngvector"
5236 "rsem-plot-transcript-wiggles"
5237 "rsem-prepare-reference"
5239 "rsem-run-prsem-testing-procedure")))
5243 ("r-minimal" ,r-minimal)
5245 ("htslib" ,htslib-1.3)
5247 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
5248 (synopsis "Estimate gene expression levels from RNA-Seq data")
5250 "RSEM is a software package for estimating gene and isoform expression
5251 levels from RNA-Seq data. The RSEM package provides a user-friendly
5252 interface, supports threads for parallel computation of the EM algorithm,
5253 single-end and paired-end read data, quality scores, variable-length reads and
5254 RSPD estimation. In addition, it provides posterior mean and 95% credibility
5255 interval estimates for expression levels. For visualization, it can generate
5256 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
5257 (license license:gpl3+)))
5259 (define-public rseqc
5267 (string-append "mirror://sourceforge/rseqc/"
5268 "RSeQC-" version ".tar.gz"))
5270 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
5271 (modules '((guix build utils)))
5274 ;; remove bundled copy of pysam
5275 (delete-file-recursively "lib/pysam")
5276 (substitute* "setup.py"
5277 ;; remove dependency on outdated "distribute" module
5278 (("^from distribute_setup import use_setuptools") "")
5279 (("^use_setuptools\\(\\)") "")
5280 ;; do not use bundled copy of pysam
5281 (("^have_pysam = False") "have_pysam = True"))
5283 (build-system python-build-system)
5284 (arguments `(#:python ,python-2))
5286 `(("python-cython" ,python2-cython)
5287 ("python-pysam" ,python2-pysam)
5288 ("python-numpy" ,python2-numpy)
5291 `(("python-nose" ,python2-nose)))
5292 (home-page "http://rseqc.sourceforge.net/")
5293 (synopsis "RNA-seq quality control package")
5295 "RSeQC provides a number of modules that can comprehensively evaluate
5296 high throughput sequence data, especially RNA-seq data. Some basic modules
5297 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
5298 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
5299 distribution, coverage uniformity, strand specificity, etc.")
5300 (license license:gpl3+)))
5303 ;; There are no release tarballs. According to the installation
5304 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
5305 ;; stable release is identified by this changeset ID.
5306 (let ((changeset "2329130")
5310 (version (string-append "0-" revision "." changeset))
5314 (url "https://bitbucket.org/libsleipnir/sleipnir")
5315 (changeset changeset)))
5316 (file-name (string-append name "-" version "-checkout"))
5319 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
5320 (build-system gnu-build-system)
5322 `(#:modules ((srfi srfi-1)
5323 (guix build gnu-build-system)
5326 (let ((dirs '("SeekMiner"
5332 (modify-phases %standard-phases
5335 (substitute* "gen_tools_am"
5336 (("/usr/bin/env.*") (which "perl")))
5337 (invoke "bash" "gen_auto")
5339 (add-after 'build 'build-additional-tools
5340 (lambda* (#:key make-flags #:allow-other-keys)
5341 (for-each (lambda (dir)
5342 (with-directory-excursion (string-append "tools/" dir)
5343 (apply invoke "make" make-flags)))
5346 (add-after 'install 'install-additional-tools
5347 (lambda* (#:key make-flags #:allow-other-keys)
5348 (for-each (lambda (dir)
5349 (with-directory-excursion (string-append "tools/" dir)
5350 (apply invoke `("make" ,@make-flags "install"))))
5357 ("readline" ,readline)
5358 ("gengetopt" ,gengetopt)
5359 ("log4cpp" ,log4cpp)))
5361 `(("autoconf" ,autoconf)
5362 ("automake" ,automake)
5364 (home-page "http://seek.princeton.edu")
5365 (synopsis "Gene co-expression search engine")
5367 "SEEK is a computational gene co-expression search engine. SEEK provides
5368 biologists with a way to navigate the massive human expression compendium that
5369 now contains thousands of expression datasets. SEEK returns a robust ranking
5370 of co-expressed genes in the biological area of interest defined by the user's
5371 query genes. It also prioritizes thousands of expression datasets according
5372 to the user's query of interest.")
5373 (license license:cc-by3.0))))
5375 (define-public samtools
5383 (string-append "mirror://sourceforge/samtools/samtools/"
5384 version "/samtools-" version ".tar.bz2"))
5387 "10ilqbmm7ri8z431sn90lvbjwizd0hhkf9rcqw8j823hf26nhgq8"))
5388 (modules '((guix build utils)))
5390 ;; Delete bundled htslib.
5391 (delete-file-recursively "htslib-1.9")
5393 (build-system gnu-build-system)
5395 `(#:modules ((ice-9 ftw)
5397 (guix build gnu-build-system)
5399 #:configure-flags (list "--with-ncurses")
5401 (modify-phases %standard-phases
5402 (add-after 'unpack 'patch-tests
5404 (substitute* "test/test.pl"
5405 ;; The test script calls out to /bin/bash
5406 (("/bin/bash") (which "bash")))
5408 (add-after 'install 'install-library
5409 (lambda* (#:key outputs #:allow-other-keys)
5410 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
5411 (install-file "libbam.a" lib)
5413 (add-after 'install 'install-headers
5414 (lambda* (#:key outputs #:allow-other-keys)
5415 (let ((include (string-append (assoc-ref outputs "out")
5416 "/include/samtools/")))
5417 (for-each (lambda (file)
5418 (install-file file include))
5419 (scandir "." (lambda (name) (string-match "\\.h$" name))))
5421 (native-inputs `(("pkg-config" ,pkg-config)))
5423 `(("htslib" ,htslib)
5424 ("ncurses" ,ncurses)
5428 (home-page "http://samtools.sourceforge.net")
5429 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
5431 "Samtools implements various utilities for post-processing nucleotide
5432 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
5433 variant calling (in conjunction with bcftools), and a simple alignment
5435 (license license:expat)))
5437 (define-public samtools-0.1
5438 ;; This is the most recent version of the 0.1 line of samtools. The input
5439 ;; and output formats differ greatly from that used and produced by samtools
5440 ;; 1.x and is still used in many bioinformatics pipelines.
5441 (package (inherit samtools)
5447 (string-append "mirror://sourceforge/samtools/samtools/"
5448 version "/samtools-" version ".tar.bz2"))
5450 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
5452 `(#:tests? #f ;no "check" target
5454 (list "LIBCURSES=-lncurses")
5455 ,@(substitute-keyword-arguments (package-arguments samtools)
5457 `(modify-phases ,phases
5459 (lambda* (#:key outputs #:allow-other-keys)
5460 (let ((bin (string-append
5461 (assoc-ref outputs "out") "/bin")))
5463 (install-file "samtools" bin)
5465 (delete 'patch-tests)
5466 (delete 'configure))))))))
5468 (define-public mosaik
5469 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
5474 ;; There are no release tarballs nor tags.
5477 (url "https://github.com/wanpinglee/MOSAIK.git")
5479 (file-name (string-append name "-" version))
5482 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
5483 (build-system gnu-build-system)
5485 `(#:tests? #f ; no tests
5486 #:make-flags (list "CC=gcc")
5488 (modify-phases %standard-phases
5490 (lambda _ (chdir "src") #t))
5492 (lambda* (#:key outputs #:allow-other-keys)
5493 (let ((bin (string-append (assoc-ref outputs "out")
5496 (copy-recursively "../bin" bin)
5500 ("zlib:static" ,zlib "static")
5502 (supported-systems '("x86_64-linux"))
5503 (home-page "https://github.com/wanpinglee/MOSAIK")
5504 (synopsis "Map nucleotide sequence reads to reference genomes")
5506 "MOSAIK is a program for mapping second and third-generation sequencing
5507 reads to a reference genome. MOSAIK can align reads generated by all the
5508 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
5509 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
5510 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
5511 ;; code released into the public domain:
5512 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
5513 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
5514 (license (list license:gpl2+ license:public-domain)))))
5516 (define-public ngs-sdk
5523 (url "https://github.com/ncbi/ngs.git")
5525 (file-name (git-file-name name version))
5528 "17c0v1nah3g3d2ib5bbi0vhma1ghd6vb9xycavqsh64lhp840rk3"))))
5529 (build-system gnu-build-system)
5531 `(#:parallel-build? #f ; not supported
5532 #:tests? #f ; no "check" target
5534 (modify-phases %standard-phases
5536 (lambda* (#:key outputs #:allow-other-keys)
5537 (let ((out (assoc-ref outputs "out")))
5538 ;; Allow 'konfigure.perl' to find 'package.prl'.
5540 (string-append ".:" (getenv "PERL5LIB")))
5542 ;; The 'configure' script doesn't recognize things like
5543 ;; '--enable-fast-install'.
5544 (invoke "./configure"
5545 (string-append "--build-prefix=" (getcwd) "/build")
5546 (string-append "--prefix=" out))
5548 (add-after 'unpack 'enter-dir
5549 (lambda _ (chdir "ngs-sdk") #t)))))
5550 (native-inputs `(("perl" ,perl)))
5551 ;; According to the test
5552 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
5553 ;; in ngs-sdk/setup/konfigure.perl
5554 (supported-systems '("i686-linux" "x86_64-linux"))
5555 (home-page "https://github.com/ncbi/ngs")
5556 (synopsis "API for accessing Next Generation Sequencing data")
5558 "NGS is a domain-specific API for accessing reads, alignments and pileups
5559 produced from Next Generation Sequencing. The API itself is independent from
5560 any particular back-end implementation, and supports use of multiple back-ends
5562 (license license:public-domain)))
5564 (define-public java-ngs
5565 (package (inherit ngs-sdk)
5568 `(,@(substitute-keyword-arguments
5569 `(#:modules ((guix build gnu-build-system)
5573 ,@(package-arguments ngs-sdk))
5575 `(modify-phases ,phases
5576 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5578 `(("jdk" ,icedtea "jdk")
5579 ("ngs-sdk" ,ngs-sdk)))
5580 (synopsis "Java bindings for NGS SDK")))
5582 (define-public ncbi-vdb
5589 (url "https://github.com/ncbi/ncbi-vdb.git")
5591 (file-name (git-file-name name version))
5594 "1l4ny67nxwv1lagk9wwjbrgm7ln7adci6dnpc7k1yaln6shj0qpm"))))
5595 (build-system gnu-build-system)
5597 `(#:parallel-build? #f ; not supported
5598 #:tests? #f ; no "check" target
5600 (modify-phases %standard-phases
5601 (add-after 'unpack 'make-files-writable
5602 (lambda _ (for-each make-file-writable (find-files "." ".*")) #t))
5603 (add-before 'configure 'set-perl-search-path
5605 ;; Work around "dotless @INC" build failure.
5607 (string-append (getcwd) "/setup:"
5608 (getenv "PERL5LIB")))
5611 (lambda* (#:key inputs outputs #:allow-other-keys)
5612 (let ((out (assoc-ref outputs "out")))
5613 ;; Override include path for libmagic
5614 (substitute* "setup/package.prl"
5615 (("name => 'magic', Include => '/usr/include'")
5616 (string-append "name=> 'magic', Include => '"
5617 (assoc-ref inputs "libmagic")
5620 ;; Install kdf5 library (needed by sra-tools)
5621 (substitute* "build/Makefile.install"
5622 (("LIBRARIES_TO_INSTALL =")
5623 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5625 (substitute* "build/Makefile.env"
5626 (("CFLAGS =" prefix)
5627 (string-append prefix "-msse2 ")))
5629 ;; Override search path for ngs-java
5630 (substitute* "setup/package.prl"
5631 (("/usr/local/ngs/ngs-java")
5632 (assoc-ref inputs "java-ngs")))
5634 ;; The 'configure' script doesn't recognize things like
5635 ;; '--enable-fast-install'.
5636 (invoke "./configure"
5637 (string-append "--build-prefix=" (getcwd) "/build")
5638 (string-append "--prefix=" (assoc-ref outputs "out"))
5639 (string-append "--debug")
5640 (string-append "--with-xml2-prefix="
5641 (assoc-ref inputs "libxml2"))
5642 (string-append "--with-ngs-sdk-prefix="
5643 (assoc-ref inputs "ngs-sdk"))
5644 (string-append "--with-hdf5-prefix="
5645 (assoc-ref inputs "hdf5")))
5647 (add-after 'install 'install-interfaces
5648 (lambda* (#:key outputs #:allow-other-keys)
5649 ;; Install interface libraries. On i686 the interface libraries
5650 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5651 ;; architecture name ("i386") instead of the target system prefix
5653 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5654 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5655 ,(system->linux-architecture
5656 (or (%current-target-system)
5659 (string-append (assoc-ref outputs "out")
5661 ;; Install interface headers
5662 (copy-recursively "interfaces"
5663 (string-append (assoc-ref outputs "out")
5666 ;; These files are needed by sra-tools.
5667 (add-after 'install 'install-configuration-files
5668 (lambda* (#:key outputs #:allow-other-keys)
5669 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5671 (install-file "libs/kfg/default.kfg" target)
5672 (install-file "libs/kfg/certs.kfg" target))
5675 `(("libxml2" ,libxml2)
5676 ("ngs-sdk" ,ngs-sdk)
5677 ("java-ngs" ,java-ngs)
5680 (native-inputs `(("perl" ,perl)))
5681 ;; NCBI-VDB requires SSE capability.
5682 (supported-systems '("i686-linux" "x86_64-linux"))
5683 (home-page "https://github.com/ncbi/ncbi-vdb")
5684 (synopsis "Database engine for genetic information")
5686 "The NCBI-VDB library implements a highly compressed columnar data
5687 warehousing engine that is most often used to store genetic information.
5688 Databases are stored in a portable image within the file system, and can be
5689 accessed/downloaded on demand across HTTP.")
5690 (license license:public-domain)))
5692 (define-public plink
5700 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5701 version "-src.zip"))
5703 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5704 (patches (search-patches "plink-1.07-unclobber-i.patch"
5705 "plink-endian-detection.patch"))))
5706 (build-system gnu-build-system)
5708 '(#:tests? #f ;no "check" target
5709 #:make-flags (list (string-append "LIB_LAPACK="
5710 (assoc-ref %build-inputs "lapack")
5711 "/lib/liblapack.so")
5714 ;; disable phoning home
5717 (modify-phases %standard-phases
5718 ;; no "configure" script
5721 (lambda* (#:key outputs #:allow-other-keys)
5722 (let ((bin (string-append (assoc-ref outputs "out")
5724 (install-file "plink" bin)
5728 ("lapack" ,lapack)))
5730 `(("unzip" ,unzip)))
5731 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5732 (synopsis "Whole genome association analysis toolset")
5734 "PLINK is a whole genome association analysis toolset, designed to
5735 perform a range of basic, large-scale analyses in a computationally efficient
5736 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5737 so there is no support for steps prior to this (e.g. study design and
5738 planning, generating genotype or CNV calls from raw data). Through
5739 integration with gPLINK and Haploview, there is some support for the
5740 subsequent visualization, annotation and storage of results.")
5741 ;; Code is released under GPLv2, except for fisher.h, which is under
5743 (license (list license:gpl2 license:lgpl2.1+))))
5745 (define-public plink-ng
5746 (package (inherit plink)
5753 (url "https://github.com/chrchang/plink-ng.git")
5754 (commit (string-append "v" version))))
5755 (file-name (git-file-name name version))
5757 (base32 "02npdwgkpfkdnhw819rhj5kw02a5k5m90b14zq9zzya4hyg929c0"))))
5758 (build-system gnu-build-system)
5760 '(#:tests? #f ;no "check" target
5761 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5762 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5764 "-f" "Makefile.std")
5766 (modify-phases %standard-phases
5767 (add-after 'unpack 'chdir
5768 (lambda _ (chdir "1.9") #t))
5769 (delete 'configure) ; no "configure" script
5771 (lambda* (#:key outputs #:allow-other-keys)
5772 (let ((bin (string-append (assoc-ref outputs "out")
5774 (install-file "plink" bin)
5779 ("openblas" ,openblas)))
5780 (home-page "https://www.cog-genomics.org/plink/")
5781 (license license:gpl3+)))
5783 (define-public smithlab-cpp
5784 (let ((revision "1")
5785 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
5787 (name "smithlab-cpp")
5788 (version (string-append "0." revision "." (string-take commit 7)))
5792 (url "https://github.com/smithlabcode/smithlab_cpp.git")
5794 (file-name (string-append name "-" version "-checkout"))
5797 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
5798 (build-system gnu-build-system)
5800 `(#:modules ((guix build gnu-build-system)
5803 #:tests? #f ;no "check" target
5805 (modify-phases %standard-phases
5806 (add-after 'unpack 'use-samtools-headers
5808 (substitute* '("SAM.cpp"
5810 (("sam.h") "samtools/sam.h"))
5813 (lambda* (#:key outputs #:allow-other-keys)
5814 (let* ((out (assoc-ref outputs "out"))
5815 (lib (string-append out "/lib"))
5816 (include (string-append out "/include/smithlab-cpp")))
5819 (for-each (cut install-file <> lib)
5820 (find-files "." "\\.o$"))
5821 (for-each (cut install-file <> include)
5822 (find-files "." "\\.hpp$")))
5824 (delete 'configure))))
5826 `(("samtools" ,samtools-0.1)
5828 (home-page "https://github.com/smithlabcode/smithlab_cpp")
5829 (synopsis "C++ helper library for functions used in Smith lab projects")
5831 "Smithlab CPP is a C++ library that includes functions used in many of
5832 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
5833 structures, classes for genomic regions, mapped sequencing reads, etc.")
5834 (license license:gpl3+))))
5836 (define-public preseq
5842 (uri (string-append "https://github.com/smithlabcode/preseq/"
5843 "releases/download/v" version
5844 "/preseq_v" version ".tar.bz2"))
5846 (base32 "149x9xmk1wy1gff85325yfzqc0qk4sgp1w6gbyj9cnji4x1dszbl"))
5847 (modules '((guix build utils)))
5849 ;; Remove bundled samtools.
5850 (delete-file-recursively "samtools")
5852 (build-system gnu-build-system)
5854 `(#:tests? #f ;no "check" target
5856 (modify-phases %standard-phases
5857 (delete 'configure))
5859 (list (string-append "PREFIX="
5860 (assoc-ref %outputs "out"))
5861 (string-append "LIBBAM="
5862 (assoc-ref %build-inputs "samtools")
5864 (string-append "SMITHLAB_CPP="
5865 (assoc-ref %build-inputs "smithlab-cpp")
5868 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
5871 ("samtools" ,samtools-0.1)
5872 ("smithlab-cpp" ,smithlab-cpp)
5874 (home-page "http://smithlabresearch.org/software/preseq/")
5875 (synopsis "Program for analyzing library complexity")
5877 "The preseq package is aimed at predicting and estimating the complexity
5878 of a genomic sequencing library, equivalent to predicting and estimating the
5879 number of redundant reads from a given sequencing depth and how many will be
5880 expected from additional sequencing using an initial sequencing experiment.
5881 The estimates can then be used to examine the utility of further sequencing,
5882 optimize the sequencing depth, or to screen multiple libraries to avoid low
5883 complexity samples.")
5884 (license license:gpl3+)))
5886 (define-public python-screed
5888 (name "python-screed")
5893 (uri (pypi-uri "screed" version))
5896 "148vcb7w2wr6a4w6vs2bsxanbqibxfk490zbcbg4m61s8669zdjx"))))
5897 (build-system python-build-system)
5900 (modify-phases %standard-phases
5901 ;; Tests must be run after installation, as the "screed" command does
5902 ;; not exist right after building.
5904 (add-after 'install 'check
5905 (lambda* (#:key inputs outputs #:allow-other-keys)
5906 (let ((out (assoc-ref outputs "out")))
5907 (setenv "PYTHONPATH"
5908 (string-append out "/lib/python"
5909 (string-take (string-take-right
5910 (assoc-ref inputs "python")
5913 (getenv "PYTHONPATH")))
5914 (setenv "PATH" (string-append out "/bin:" (getenv "PATH"))))
5915 (invoke "python" "setup.py" "test")
5918 `(("python-pytest" ,python-pytest)
5919 ("python-pytest-cov" ,python-pytest-cov)
5920 ("python-pytest-runner" ,python-pytest-runner)))
5922 `(("python-bz2file" ,python-bz2file)))
5923 (home-page "https://github.com/dib-lab/screed/")
5924 (synopsis "Short read sequence database utilities")
5925 (description "Screed parses FASTA and FASTQ files and generates databases.
5926 Values such as sequence name, sequence description, sequence quality and the
5927 sequence itself can be retrieved from these databases.")
5928 (license license:bsd-3)))
5930 (define-public python2-screed
5931 (package-with-python2 python-screed))
5933 (define-public sra-tools
5941 (url "https://github.com/ncbi/sra-tools.git")
5943 (file-name (git-file-name name version))
5946 "0663gcdxkziwsmlznjxysb00621rllpbz6jwsfifq7z3dj3lwm8b"))))
5947 (build-system gnu-build-system)
5949 `(#:parallel-build? #f ; not supported
5950 #:tests? #f ; no "check" target
5952 (list (string-append "DEFAULT_CRT="
5953 (assoc-ref %build-inputs "ncbi-vdb")
5955 (string-append "DEFAULT_KFG="
5956 (assoc-ref %build-inputs "ncbi-vdb")
5958 (string-append "VDB_LIBDIR="
5959 (assoc-ref %build-inputs "ncbi-vdb")
5960 ,(if (string-prefix? "x86_64"
5961 (or (%current-target-system)
5966 (modify-phases %standard-phases
5967 (add-before 'configure 'set-perl-search-path
5969 ;; Work around "dotless @INC" build failure.
5971 (string-append (getcwd) "/setup:"
5972 (getenv "PERL5LIB")))
5975 (lambda* (#:key inputs outputs #:allow-other-keys)
5976 ;; The build system expects a directory containing the sources and
5977 ;; raw build output of ncbi-vdb, including files that are not
5978 ;; installed. Since we are building against an installed version of
5979 ;; ncbi-vdb, the following modifications are needed.
5980 (substitute* "setup/konfigure.perl"
5981 ;; Make the configure script look for the "ilib" directory of
5982 ;; "ncbi-vdb" without first checking for the existence of a
5983 ;; matching library in its "lib" directory.
5984 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5985 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5986 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5987 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5988 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
5991 (substitute* "tools/copycat/Makefile"
5992 (("smagic-static") "lmagic"))
5994 ;; The 'configure' script doesn't recognize things like
5995 ;; '--enable-fast-install'.
5996 (invoke "./configure"
5997 (string-append "--build-prefix=" (getcwd) "/build")
5998 (string-append "--prefix=" (assoc-ref outputs "out"))
5999 (string-append "--debug")
6000 (string-append "--with-fuse-prefix="
6001 (assoc-ref inputs "fuse"))
6002 (string-append "--with-magic-prefix="
6003 (assoc-ref inputs "libmagic"))
6004 ;; TODO: building with libxml2 fails with linker errors
6005 ;; (string-append "--with-xml2-prefix="
6006 ;; (assoc-ref inputs "libxml2"))
6007 (string-append "--with-ncbi-vdb-sources="
6008 (assoc-ref inputs "ncbi-vdb"))
6009 (string-append "--with-ncbi-vdb-build="
6010 (assoc-ref inputs "ncbi-vdb"))
6011 (string-append "--with-ngs-sdk-prefix="
6012 (assoc-ref inputs "ngs-sdk"))
6013 (string-append "--with-hdf5-prefix="
6014 (assoc-ref inputs "hdf5")))
6016 (native-inputs `(("perl" ,perl)))
6018 `(("ngs-sdk" ,ngs-sdk)
6019 ("ncbi-vdb" ,ncbi-vdb)
6024 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
6025 (synopsis "Tools and libraries for reading and writing sequencing data")
6027 "The SRA Toolkit from NCBI is a collection of tools and libraries for
6028 reading of sequencing files from the Sequence Read Archive (SRA) database and
6029 writing files into the .sra format.")
6030 (license license:public-domain)))
6032 (define-public seqan
6038 (uri (string-append "https://github.com/seqan/seqan/releases/"
6039 "download/seqan-v" version
6040 "/seqan-library-" version ".tar.xz"))
6043 "19a1rlxx03qy1i1iriicly68w64yjxbv24g9gdywnfmq998v35yx"))))
6044 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6045 ;; makes sense to split the outputs.
6046 (outputs '("out" "doc"))
6047 (build-system trivial-build-system)
6049 `(#:modules ((guix build utils))
6052 (use-modules (guix build utils))
6053 (let ((tar (assoc-ref %build-inputs "tar"))
6054 (xz (assoc-ref %build-inputs "xz"))
6055 (out (assoc-ref %outputs "out"))
6056 (doc (assoc-ref %outputs "doc")))
6057 (setenv "PATH" (string-append tar "/bin:" xz "/bin"))
6058 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6059 (chdir (string-append "seqan-library-" ,version))
6060 (copy-recursively "include" (string-append out "/include"))
6061 (copy-recursively "share" (string-append doc "/share"))
6064 `(("source" ,source)
6067 (home-page "http://www.seqan.de")
6068 (synopsis "Library for nucleotide sequence analysis")
6070 "SeqAn is a C++ library of efficient algorithms and data structures for
6071 the analysis of sequences with the focus on biological data. It contains
6072 algorithms and data structures for string representation and their
6073 manipulation, online and indexed string search, efficient I/O of
6074 bioinformatics file formats, sequence alignment, and more.")
6075 (license license:bsd-3)))
6077 (define-public seqan-1
6078 (package (inherit seqan)
6083 (uri (string-append "http://packages.seqan.de/seqan-library/"
6084 "seqan-library-" version ".tar.bz2"))
6087 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
6088 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6089 ;; makes sense to split the outputs.
6090 (outputs '("out" "doc"))
6091 (build-system trivial-build-system)
6093 `(#:modules ((guix build utils))
6096 (use-modules (guix build utils))
6097 (let ((tar (assoc-ref %build-inputs "tar"))
6098 (bzip (assoc-ref %build-inputs "bzip2"))
6099 (out (assoc-ref %outputs "out"))
6100 (doc (assoc-ref %outputs "doc")))
6101 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
6102 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6103 (chdir (string-append "seqan-library-" ,version))
6104 (copy-recursively "include" (string-append out "/include"))
6105 (copy-recursively "share" (string-append doc "/share"))
6108 `(("source" ,source)
6110 ("bzip2" ,bzip2)))))
6112 (define-public seqmagick
6119 (uri (pypi-uri "seqmagick" version))
6122 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
6123 (build-system python-build-system)
6125 `(("python-biopython" ,python-biopython)))
6127 `(("python-nose" ,python-nose)))
6128 (home-page "https://github.com/fhcrc/seqmagick")
6129 (synopsis "Tools for converting and modifying sequence files")
6131 "Bioinformaticians often have to convert sequence files between formats
6132 and do little manipulations on them, and it's not worth writing scripts for
6133 that. Seqmagick is a utility to expose the file format conversion in
6134 BioPython in a convenient way. Instead of having a big mess of scripts, there
6135 is one that takes arguments.")
6136 (license license:gpl3)))
6138 (define-public seqtk
6145 (url "https://github.com/lh3/seqtk.git")
6146 (commit (string-append "v" version))))
6147 (file-name (git-file-name name version))
6150 "1bfzlqa84b5s1qi22blmmw2s8xdyp9h9ydcq22pfjhh5gab3yz6l"))))
6151 (build-system gnu-build-system)
6154 (modify-phases %standard-phases
6157 ;; There are no tests, so we just run a sanity check.
6158 (lambda _ (invoke "./seqtk" "seq") #t))
6160 (lambda* (#:key outputs #:allow-other-keys)
6161 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6162 (install-file "seqtk" bin)
6166 (home-page "https://github.com/lh3/seqtk")
6167 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
6169 "Seqtk is a fast and lightweight tool for processing sequences in the
6170 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
6171 optionally compressed by gzip.")
6172 (license license:expat)))
6174 (define-public snap-aligner
6176 (name "snap-aligner")
6177 (version "1.0beta.18")
6181 (url "https://github.com/amplab/snap.git")
6182 (commit (string-append "v" version))))
6183 (file-name (git-file-name name version))
6186 "01w3qq4wm07z73vky0cfwlmrbf50n3w722cxrlzxfi99mnb808d8"))))
6187 (build-system gnu-build-system)
6190 (modify-phases %standard-phases
6192 (replace 'check (lambda _ (invoke "./unit_tests") #t))
6194 (lambda* (#:key outputs #:allow-other-keys)
6195 (let* ((out (assoc-ref outputs "out"))
6196 (bin (string-append out "/bin")))
6197 (install-file "snap-aligner" bin)
6198 (install-file "SNAPCommand" bin)
6202 (home-page "http://snap.cs.berkeley.edu/")
6203 (synopsis "Short read DNA sequence aligner")
6205 "SNAP is a fast and accurate aligner for short DNA reads. It is
6206 optimized for modern read lengths of 100 bases or higher, and takes advantage
6207 of these reads to align data quickly through a hash-based indexing scheme.")
6208 ;; 32-bit systems are not supported by the unpatched code.
6209 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
6210 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
6211 ;; systems without a lot of memory cannot make good use of this program.
6212 (supported-systems '("x86_64-linux"))
6213 (license license:asl2.0)))
6215 (define-public sortmerna
6223 (url "https://github.com/biocore/sortmerna.git")
6225 (file-name (git-file-name name version))
6228 "0j3mbz4n25738yijmjbr5r4fyvkgm8v5vn3sshyfvmyqf5q9byqf"))))
6229 (build-system gnu-build-system)
6230 (outputs '("out" ;for binaries
6231 "db")) ;for sequence databases
6234 (modify-phases %standard-phases
6236 (lambda* (#:key outputs #:allow-other-keys)
6237 (let* ((out (assoc-ref outputs "out"))
6238 (bin (string-append out "/bin"))
6239 (db (assoc-ref outputs "db"))
6241 (string-append db "/share/sortmerna/rRNA_databases")))
6242 (install-file "sortmerna" bin)
6243 (install-file "indexdb_rna" bin)
6244 (for-each (lambda (file)
6245 (install-file file share))
6246 (find-files "rRNA_databases" ".*fasta"))
6250 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
6251 (synopsis "Biological sequence analysis tool for NGS reads")
6253 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
6254 and operational taxonomic unit (OTU) picking of next generation
6255 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
6256 allows for fast and sensitive analyses of nucleotide sequences. The main
6257 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
6258 ;; The source includes x86 specific code
6259 (supported-systems '("x86_64-linux" "i686-linux"))
6260 (license license:lgpl3)))
6269 (url "https://github.com/alexdobin/STAR.git")
6271 (file-name (string-append name "-" version "-checkout"))
6274 "0n6g4s4hgw7qygs1z97j7a2dgz8gfaa4cv5pjvvvmarvk0x07hyg"))
6275 (modules '((guix build utils)))
6278 (substitute* "source/Makefile"
6280 ;; Remove pre-built binaries and bundled htslib sources.
6281 (delete-file-recursively "bin/MacOSX_x86_64")
6282 (delete-file-recursively "bin/Linux_x86_64")
6283 (delete-file-recursively "bin/Linux_x86_64_static")
6284 (delete-file-recursively "source/htslib")
6286 (build-system gnu-build-system)
6288 '(#:tests? #f ;no check target
6289 #:make-flags '("STAR")
6291 (modify-phases %standard-phases
6292 (add-after 'unpack 'enter-source-dir
6293 (lambda _ (chdir "source") #t))
6294 (add-after 'enter-source-dir 'make-reproducible
6296 (substitute* "Makefile"
6297 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
6298 (string-append pre "Built with Guix" post)))
6300 ;; See https://github.com/alexdobin/STAR/pull/562
6301 (add-after 'enter-source-dir 'add-missing-header
6303 (substitute* "SoloReadFeature_inputRecords.cpp"
6304 (("#include \"binarySearch2.h\"" h)
6305 (string-append h "\n#include <math.h>")))
6307 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
6309 (substitute* "Makefile"
6310 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
6312 (substitute* '("BAMfunctions.cpp"
6317 "bamRemoveDuplicates.cpp")
6318 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
6319 (string-append "#include <" header ">")))
6320 (substitute* "IncludeDefine.h"
6321 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
6322 (string-append "<" header ">")))
6325 (lambda* (#:key outputs #:allow-other-keys)
6326 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6327 (install-file "STAR" bin))
6329 (delete 'configure))))
6333 `(("htslib" ,htslib)
6335 (home-page "https://github.com/alexdobin/STAR")
6336 (synopsis "Universal RNA-seq aligner")
6338 "The Spliced Transcripts Alignment to a Reference (STAR) software is
6339 based on a previously undescribed RNA-seq alignment algorithm that uses
6340 sequential maximum mappable seed search in uncompressed suffix arrays followed
6341 by seed clustering and stitching procedure. In addition to unbiased de novo
6342 detection of canonical junctions, STAR can discover non-canonical splices and
6343 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
6345 ;; Only 64-bit systems are supported according to the README.
6346 (supported-systems '("x86_64-linux" "mips64el-linux"))
6347 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
6348 (license license:gpl3+)))
6350 (define-public starlong
6351 (package (inherit star)
6354 (substitute-keyword-arguments (package-arguments star)
6355 ((#:make-flags flags)
6358 `(modify-phases ,phases
6359 ;; Allow extra long sequence reads.
6360 (add-after 'unpack 'make-extra-long
6362 (substitute* "source/IncludeDefine.h"
6363 (("(#define DEF_readNameLengthMax ).*" _ match)
6364 (string-append match "900000\n")))
6367 (lambda* (#:key outputs #:allow-other-keys)
6368 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6369 (install-file "STARlong" bin))
6372 (define-public subread
6378 (uri (string-append "mirror://sourceforge/subread/subread-"
6379 version "/subread-" version "-source.tar.gz"))
6382 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
6383 (build-system gnu-build-system)
6385 `(#:tests? #f ;no "check" target
6386 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
6387 ;; optimizations by default, so we override these flags such that x86_64
6388 ;; flags are only added when the build target is an x86_64 system.
6390 (list (let ((system ,(or (%current-target-system)
6392 (flags '("-ggdb" "-fomit-frame-pointer"
6393 "-ffast-math" "-funroll-loops"
6394 "-fmessage-length=0"
6395 "-O9" "-Wall" "-DMAKE_FOR_EXON"
6397 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
6398 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
6399 (if (string-prefix? "x86_64" system)
6400 (string-append "CCFLAGS=" (string-join (append flags flags64)))
6401 (string-append "CCFLAGS=" (string-join flags))))
6402 "-f" "Makefile.Linux"
6403 "CC=gcc ${CCFLAGS}")
6405 (modify-phases %standard-phases
6406 (add-after 'unpack 'enter-dir
6407 (lambda _ (chdir "src") #t))
6409 (lambda* (#:key outputs #:allow-other-keys)
6410 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6412 (copy-recursively "../bin" bin))
6414 ;; no "configure" script
6415 (delete 'configure))))
6416 (inputs `(("zlib" ,zlib)))
6417 (home-page "http://bioinf.wehi.edu.au/subread-package/")
6418 (synopsis "Tool kit for processing next-gen sequencing data")
6420 "The subread package contains the following tools: subread aligner, a
6421 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
6422 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
6423 features; exactSNP: a SNP caller that discovers SNPs by testing signals
6424 against local background noises.")
6425 (license license:gpl3+)))
6427 (define-public stringtie
6433 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
6434 "stringtie-" version ".tar.gz"))
6437 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
6438 (modules '((guix build utils)))
6441 (delete-file-recursively "samtools-0.1.18")
6443 (build-system gnu-build-system)
6445 `(#:tests? #f ;no test suite
6447 (modify-phases %standard-phases
6448 ;; no configure script
6450 (add-before 'build 'use-system-samtools
6452 (substitute* "Makefile"
6453 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
6455 (substitute* '("gclib/GBam.h"
6457 (("#include \"(bam|sam|kstring).h\"" _ header)
6458 (string-append "#include <samtools/" header ".h>")))
6460 (add-after 'unpack 'remove-duplicate-typedef
6462 ;; This typedef conflicts with the typedef in
6463 ;; glibc-2.25/include/bits/types.h
6464 (substitute* "gclib/GThreads.h"
6465 (("typedef long long __intmax_t;") ""))
6468 (lambda* (#:key outputs #:allow-other-keys)
6469 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6470 (install-file "stringtie" bin)
6473 `(("samtools" ,samtools-0.1)
6475 (home-page "http://ccb.jhu.edu/software/stringtie/")
6476 (synopsis "Transcript assembly and quantification for RNA-Seq data")
6478 "StringTie is a fast and efficient assembler of RNA-Seq sequence
6479 alignments into potential transcripts. It uses a novel network flow algorithm
6480 as well as an optional de novo assembly step to assemble and quantitate
6481 full-length transcripts representing multiple splice variants for each gene
6482 locus. Its input can include not only the alignments of raw reads used by
6483 other transcript assemblers, but also alignments of longer sequences that have
6484 been assembled from those reads. To identify differentially expressed genes
6485 between experiments, StringTie's output can be processed either by the
6486 Cuffdiff or Ballgown programs.")
6487 (license license:artistic2.0)))
6489 (define-public taxtastic
6495 (uri (pypi-uri "taxtastic" version))
6498 "03pysw79lsrvz4lwzis88j15067ffqbi4cid5pqhrlxmd6bh8rrk"))))
6499 (build-system python-build-system)
6501 `(#:python ,python-2
6503 (modify-phases %standard-phases
6505 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t)))))
6507 `(("python-sqlalchemy" ,python2-sqlalchemy)
6508 ("python-decorator" ,python2-decorator)
6509 ("python-biopython" ,python2-biopython)
6510 ("python-pandas" ,python2-pandas)
6511 ("python-psycopg2" ,python2-psycopg2)
6512 ("python-fastalite" ,python2-fastalite)
6513 ("python-pyyaml" ,python2-pyyaml)
6514 ("python-six" ,python2-six)
6515 ("python-jinja2" ,python2-jinja2)
6516 ("python-dendropy" ,python2-dendropy)))
6517 (home-page "https://github.com/fhcrc/taxtastic")
6518 (synopsis "Tools for taxonomic naming and annotation")
6520 "Taxtastic is software written in python used to build and maintain
6521 reference packages i.e. collections of reference trees, reference alignments,
6522 profiles, and associated taxonomic information.")
6523 (license license:gpl3+)))
6525 (define-public vcftools
6532 "https://github.com/vcftools/vcftools/releases/download/v"
6533 version "/vcftools-" version ".tar.gz"))
6536 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
6537 (build-system gnu-build-system)
6539 `(#:tests? #f ; no "check" target
6541 "CFLAGS=-O2" ; override "-m64" flag
6542 (string-append "PREFIX=" (assoc-ref %outputs "out"))
6543 (string-append "MANDIR=" (assoc-ref %outputs "out")
6544 "/share/man/man1"))))
6546 `(("pkg-config" ,pkg-config)))
6550 (home-page "https://vcftools.github.io/")
6551 (synopsis "Tools for working with VCF files")
6553 "VCFtools is a program package designed for working with VCF files, such
6554 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
6555 provide easily accessible methods for working with complex genetic variation
6556 data in the form of VCF files.")
6557 ;; The license is declared as LGPLv3 in the README and
6558 ;; at https://vcftools.github.io/license.html
6559 (license license:lgpl3)))
6561 (define-public infernal
6567 (uri (string-append "http://eddylab.org/software/infernal/"
6568 "infernal-" version ".tar.gz"))
6571 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
6572 (build-system gnu-build-system)
6574 `(("perl" ,perl))) ; for tests
6575 (home-page "http://eddylab.org/infernal/")
6576 (synopsis "Inference of RNA alignments")
6577 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
6578 searching DNA sequence databases for RNA structure and sequence similarities.
6579 It is an implementation of a special case of profile stochastic context-free
6580 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
6581 profile, but it scores a combination of sequence consensus and RNA secondary
6582 structure consensus, so in many cases, it is more capable of identifying RNA
6583 homologs that conserve their secondary structure more than their primary
6585 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
6586 (supported-systems '("i686-linux" "x86_64-linux"))
6587 (license license:bsd-3)))
6589 (define-public r-scde
6596 (url "https://github.com/hms-dbmi/scde.git")
6598 (file-name (git-file-name name version))
6601 "10na2gyka24mszdxf92wz9h2c13hdf1ww30c68gfsw53lvvhhhxb"))))
6602 (build-system r-build-system)
6604 `(("r-rcpp" ,r-rcpp)
6605 ("r-rcpparmadillo" ,r-rcpparmadillo)
6608 ("r-rjson" ,r-rjson)
6609 ("r-cairo" ,r-cairo)
6610 ("r-rcolorbrewer" ,r-rcolorbrewer)
6611 ("r-edger" ,r-edger)
6612 ("r-quantreg" ,r-quantreg)
6614 ("r-rmtstat" ,r-rmtstat)
6615 ("r-extremes" ,r-extremes)
6616 ("r-pcamethods" ,r-pcamethods)
6617 ("r-biocparallel" ,r-biocparallel)
6618 ("r-flexmix" ,r-flexmix)))
6619 (home-page "https://hms-dbmi.github.io/scde/")
6620 (synopsis "R package for analyzing single-cell RNA-seq data")
6621 (description "The SCDE package implements a set of statistical methods for
6622 analyzing single-cell RNA-seq data. SCDE fits individual error models for
6623 single-cell RNA-seq measurements. These models can then be used for
6624 assessment of differential expression between groups of cells, as well as
6625 other types of analysis. The SCDE package also contains the pagoda framework
6626 which applies pathway and gene set overdispersion analysis to identify aspects
6627 of transcriptional heterogeneity among single cells.")
6628 ;; See https://github.com/hms-dbmi/scde/issues/38
6629 (license license:gpl2)))
6631 (define-public r-centipede
6633 (name "r-centipede")
6637 (uri (string-append "http://download.r-forge.r-project.org/"
6638 "src/contrib/CENTIPEDE_" version ".tar.gz"))
6641 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
6642 (build-system r-build-system)
6643 (home-page "http://centipede.uchicago.edu/")
6644 (synopsis "Predict transcription factor binding sites")
6646 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
6647 of the genome that are bound by particular transcription factors. It starts
6648 by identifying a set of candidate binding sites, and then aims to classify the
6649 sites according to whether each site is bound or not bound by a transcription
6650 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
6651 between two different types of motif instances using as much relevant
6652 information as possible.")
6653 (license (list license:gpl2+ license:gpl3+))))
6655 (define-public r-genefilter
6657 (name "r-genefilter")
6662 (uri (bioconductor-uri "genefilter" version))
6665 "1jq7lam4dnbvz55lx93kcl9afl8xfjd6xs374d35m21bkay418kj"))))
6666 (build-system r-build-system)
6668 `(("gfortran" ,gfortran)))
6670 `(("r-annotate" ,r-annotate)
6671 ("r-annotationdbi" ,r-annotationdbi)
6672 ("r-biobase" ,r-biobase)
6673 ("r-s4vectors" ,r-s4vectors)
6674 ("r-survival" ,r-survival)))
6675 (home-page "https://bioconductor.org/packages/genefilter")
6676 (synopsis "Filter genes from high-throughput experiments")
6678 "This package provides basic functions for filtering genes from
6679 high-throughput sequencing experiments.")
6680 (license license:artistic2.0)))
6682 (define-public r-deseq2
6689 (uri (bioconductor-uri "DESeq2" version))
6692 "0fkk326addm2cw688gnmdzsmri5qx8j6ldnr4xin6kjnwicqhlqd"))))
6693 (properties `((upstream-name . "DESeq2")))
6694 (build-system r-build-system)
6696 `(("r-biobase" ,r-biobase)
6697 ("r-biocgenerics" ,r-biocgenerics)
6698 ("r-biocparallel" ,r-biocparallel)
6699 ("r-genefilter" ,r-genefilter)
6700 ("r-geneplotter" ,r-geneplotter)
6701 ("r-genomicranges" ,r-genomicranges)
6702 ("r-ggplot2" ,r-ggplot2)
6703 ("r-hmisc" ,r-hmisc)
6704 ("r-iranges" ,r-iranges)
6705 ("r-locfit" ,r-locfit)
6707 ("r-rcpparmadillo" ,r-rcpparmadillo)
6708 ("r-s4vectors" ,r-s4vectors)
6709 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6710 (home-page "https://bioconductor.org/packages/DESeq2")
6711 (synopsis "Differential gene expression analysis")
6713 "This package provides functions to estimate variance-mean dependence in
6714 count data from high-throughput nucleotide sequencing assays and test for
6715 differential expression based on a model using the negative binomial
6717 (license license:lgpl3+)))
6719 (define-public r-dexseq
6726 (uri (bioconductor-uri "DEXSeq" version))
6729 "1b2s0vwm97g0wgm4ms0f4pqkqiqmxscnhg700aybl5vx0m2fa8xm"))))
6730 (properties `((upstream-name . "DEXSeq")))
6731 (build-system r-build-system)
6733 `(("r-annotationdbi" ,r-annotationdbi)
6734 ("r-biobase" ,r-biobase)
6735 ("r-biocgenerics" ,r-biocgenerics)
6736 ("r-biocparallel" ,r-biocparallel)
6737 ("r-biomart" ,r-biomart)
6738 ("r-deseq2" ,r-deseq2)
6739 ("r-genefilter" ,r-genefilter)
6740 ("r-geneplotter" ,r-geneplotter)
6741 ("r-genomicranges" ,r-genomicranges)
6742 ("r-hwriter" ,r-hwriter)
6743 ("r-iranges" ,r-iranges)
6744 ("r-rcolorbrewer" ,r-rcolorbrewer)
6745 ("r-rsamtools" ,r-rsamtools)
6746 ("r-s4vectors" ,r-s4vectors)
6747 ("r-statmod" ,r-statmod)
6748 ("r-stringr" ,r-stringr)
6749 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6750 (home-page "https://bioconductor.org/packages/DEXSeq")
6751 (synopsis "Inference of differential exon usage in RNA-Seq")
6753 "This package is focused on finding differential exon usage using RNA-seq
6754 exon counts between samples with different experimental designs. It provides
6755 functions that allows the user to make the necessary statistical tests based
6756 on a model that uses the negative binomial distribution to estimate the
6757 variance between biological replicates and generalized linear models for
6758 testing. The package also provides functions for the visualization and
6759 exploration of the results.")
6760 (license license:gpl3+)))
6762 (define-public r-annotationforge
6764 (name "r-annotationforge")
6769 (uri (bioconductor-uri "AnnotationForge" version))
6772 "0m4w8n2711wr28znv646cfc7m5jqlr8friz334zdyjmhg7m2xkb7"))))
6774 `((upstream-name . "AnnotationForge")))
6775 (build-system r-build-system)
6777 `(("r-annotationdbi" ,r-annotationdbi)
6778 ("r-biobase" ,r-biobase)
6779 ("r-biocgenerics" ,r-biocgenerics)
6781 ("r-rcurl" ,r-rcurl)
6782 ("r-rsqlite" ,r-rsqlite)
6783 ("r-s4vectors" ,r-s4vectors)
6785 (home-page "https://bioconductor.org/packages/AnnotationForge")
6786 (synopsis "Code for building annotation database packages")
6788 "This package provides code for generating Annotation packages and their
6789 databases. Packages produced are intended to be used with AnnotationDbi.")
6790 (license license:artistic2.0)))
6792 (define-public r-rbgl
6799 (uri (bioconductor-uri "RBGL" version))
6802 "06brn9hl6lybx6hdfp1sycwj6wn1bjfi8xyhpy0v122v1z8d5mbz"))))
6803 (properties `((upstream-name . "RBGL")))
6804 (build-system r-build-system)
6807 ("r-graph" ,r-graph)))
6808 (home-page "https://www.bioconductor.org/packages/RBGL")
6809 (synopsis "Interface to the Boost graph library")
6811 "This package provides a fairly extensive and comprehensive interface to
6812 the graph algorithms contained in the Boost library.")
6813 (license license:artistic2.0)))
6815 (define-public r-gseabase
6822 (uri (bioconductor-uri "GSEABase" version))
6825 "0vh53xk2prjbdkbr3hwfiflx1gh7ilrqs3j1p3lyd6syy3rn9n83"))))
6826 (properties `((upstream-name . "GSEABase")))
6827 (build-system r-build-system)
6829 `(("r-annotate" ,r-annotate)
6830 ("r-annotationdbi" ,r-annotationdbi)
6831 ("r-biobase" ,r-biobase)
6832 ("r-biocgenerics" ,r-biocgenerics)
6833 ("r-graph" ,r-graph)
6835 (home-page "https://bioconductor.org/packages/GSEABase")
6836 (synopsis "Gene set enrichment data structures and methods")
6838 "This package provides classes and methods to support @dfn{Gene Set
6839 Enrichment Analysis} (GSEA).")
6840 (license license:artistic2.0)))
6842 (define-public r-category
6849 (uri (bioconductor-uri "Category" version))
6852 "1n36xfnwn2np5f0lix9abvv9w6jb25jqz3xzvqzklz9s1af4k6x4"))))
6853 (properties `((upstream-name . "Category")))
6854 (build-system r-build-system)
6856 `(("r-annotate" ,r-annotate)
6857 ("r-annotationdbi" ,r-annotationdbi)
6858 ("r-biobase" ,r-biobase)
6859 ("r-biocgenerics" ,r-biocgenerics)
6860 ("r-genefilter" ,r-genefilter)
6861 ("r-graph" ,r-graph)
6862 ("r-gseabase" ,r-gseabase)
6863 ("r-matrix" ,r-matrix)
6866 (home-page "https://bioconductor.org/packages/Category")
6867 (synopsis "Category analysis")
6869 "This package provides a collection of tools for performing category
6871 (license license:artistic2.0)))
6873 (define-public r-gostats
6880 (uri (bioconductor-uri "GOstats" version))
6883 "1a95i6awm2a8xv42fg2z3n29fg9z29i45kd80hxf6mvqqgzj80xp"))))
6884 (properties `((upstream-name . "GOstats")))
6885 (build-system r-build-system)
6887 `(("r-annotate" ,r-annotate)
6888 ("r-annotationdbi" ,r-annotationdbi)
6889 ("r-annotationforge" ,r-annotationforge)
6890 ("r-biobase" ,r-biobase)
6891 ("r-category" ,r-category)
6892 ("r-go-db" ,r-go-db)
6893 ("r-graph" ,r-graph)
6894 ("r-rgraphviz" ,r-rgraphviz)
6895 ("r-rbgl" ,r-rbgl)))
6896 (home-page "https://bioconductor.org/packages/GOstats")
6897 (synopsis "Tools for manipulating GO and microarrays")
6899 "This package provides a set of tools for interacting with GO and
6900 microarray data. A variety of basic manipulation tools for graphs, hypothesis
6901 testing and other simple calculations.")
6902 (license license:artistic2.0)))
6904 (define-public r-shortread
6906 (name "r-shortread")
6911 (uri (bioconductor-uri "ShortRead" version))
6914 "1irqzdgsavjqsq0vva4966qh8qgn7xn9382dmhahm1hxb94qmi59"))))
6915 (properties `((upstream-name . "ShortRead")))
6916 (build-system r-build-system)
6920 `(("r-biobase" ,r-biobase)
6921 ("r-biocgenerics" ,r-biocgenerics)
6922 ("r-biocparallel" ,r-biocparallel)
6923 ("r-biostrings" ,r-biostrings)
6924 ("r-genomeinfodb" ,r-genomeinfodb)
6925 ("r-genomicalignments" ,r-genomicalignments)
6926 ("r-genomicranges" ,r-genomicranges)
6927 ("r-hwriter" ,r-hwriter)
6928 ("r-iranges" ,r-iranges)
6929 ("r-lattice" ,r-lattice)
6930 ("r-latticeextra" ,r-latticeextra)
6931 ("r-rsamtools" ,r-rsamtools)
6932 ("r-s4vectors" ,r-s4vectors)
6933 ("r-xvector" ,r-xvector)
6934 ("r-zlibbioc" ,r-zlibbioc)))
6935 (home-page "https://bioconductor.org/packages/ShortRead")
6936 (synopsis "FASTQ input and manipulation tools")
6938 "This package implements sampling, iteration, and input of FASTQ files.
6939 It includes functions for filtering and trimming reads, and for generating a
6940 quality assessment report. Data are represented as
6941 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6942 purposes. The package also contains legacy support for early single-end,
6943 ungapped alignment formats.")
6944 (license license:artistic2.0)))
6946 (define-public r-systempiper
6948 (name "r-systempiper")
6953 (uri (bioconductor-uri "systemPipeR" version))
6956 "1063vdf4g2i5xyabwvzkqfxd2j8s4zs6z4zxf8lx2ccjddhkn37a"))))
6957 (properties `((upstream-name . "systemPipeR")))
6958 (build-system r-build-system)
6960 `(("r-annotate" ,r-annotate)
6961 ("r-batchtools" ,r-batchtools)
6962 ("r-biocgenerics" ,r-biocgenerics)
6963 ("r-biostrings" ,r-biostrings)
6964 ("r-deseq2" ,r-deseq2)
6965 ("r-edger" ,r-edger)
6966 ("r-genomicfeatures" ,r-genomicfeatures)
6967 ("r-genomicranges" ,r-genomicranges)
6968 ("r-ggplot2" ,r-ggplot2)
6969 ("r-go-db" ,r-go-db)
6970 ("r-gostats" ,r-gostats)
6971 ("r-limma" ,r-limma)
6972 ("r-pheatmap" ,r-pheatmap)
6973 ("r-rjson" ,r-rjson)
6974 ("r-rsamtools" ,r-rsamtools)
6975 ("r-shortread" ,r-shortread)
6976 ("r-summarizedexperiment" ,r-summarizedexperiment)
6978 ("r-variantannotation" ,r-variantannotation)))
6979 (home-page "https://github.com/tgirke/systemPipeR")
6980 (synopsis "Next generation sequencing workflow and reporting environment")
6982 "This R package provides tools for building and running automated
6983 end-to-end analysis workflows for a wide range of @dfn{next generation
6984 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6985 Important features include a uniform workflow interface across different NGS
6986 applications, automated report generation, and support for running both R and
6987 command-line software, such as NGS aligners or peak/variant callers, on local
6988 computers or compute clusters. Efficient handling of complex sample sets and
6989 experimental designs is facilitated by a consistently implemented sample
6990 annotation infrastructure.")
6991 (license license:artistic2.0)))
6993 (define-public r-grohmm
7000 (uri (bioconductor-uri "groHMM" version))
7003 "1p368qf8ab1vy8gl2j7rx0l7bvva4m7w06i364rqzs0sdyzlbm3y"))))
7004 (properties `((upstream-name . "groHMM")))
7005 (build-system r-build-system)
7007 `(("r-genomeinfodb" ,r-genomeinfodb)
7008 ("r-genomicalignments" ,r-genomicalignments)
7009 ("r-genomicranges" ,r-genomicranges)
7010 ("r-iranges" ,r-iranges)
7012 ("r-rtracklayer" ,r-rtracklayer)
7013 ("r-s4vectors" ,r-s4vectors)))
7014 (home-page "https://github.com/Kraus-Lab/groHMM")
7015 (synopsis "GRO-seq analysis pipeline")
7017 "This package provides a pipeline for the analysis of GRO-seq data.")
7018 (license license:gpl3+)))
7020 (define-public vsearch
7028 (url "https://github.com/torognes/vsearch.git")
7029 (commit (string-append "v" version))))
7030 (file-name (git-file-name name version))
7033 "0vhrpjfdf75ba04b24xknp41790cvcgwl0vgpy7qbzj5xh2521ss"))
7034 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
7037 ;; Remove bundled cityhash sources. The vsearch source is adjusted
7038 ;; for this in the patch.
7039 (delete-file "src/city.h")
7040 (delete-file "src/citycrc.h")
7041 (delete-file "src/city.cc")
7043 (build-system gnu-build-system)
7047 ("cityhash" ,cityhash)))
7049 `(("autoconf" ,autoconf)
7050 ("automake" ,automake)))
7051 (synopsis "Sequence search tools for metagenomics")
7053 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
7054 dereplication, pairwise alignment, shuffling, subsampling, sorting and
7055 masking. The tool takes advantage of parallelism in the form of SIMD
7056 vectorization as well as multiple threads to perform accurate alignments at
7057 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
7058 Needleman-Wunsch).")
7059 (home-page "https://github.com/torognes/vsearch")
7060 ;; vsearch uses non-portable SSE intrinsics so building fails on other
7062 (supported-systems '("x86_64-linux"))
7063 ;; Dual licensed; also includes public domain source.
7064 (license (list license:gpl3 license:bsd-2))))
7066 (define-public pardre
7069 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
7074 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
7078 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
7079 (build-system gnu-build-system)
7081 `(#:tests? #f ; no tests included
7083 (modify-phases %standard-phases
7086 (lambda* (#:key outputs #:allow-other-keys)
7087 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
7088 (install-file "ParDRe" bin)
7091 `(("openmpi" ,openmpi)
7093 (synopsis "Parallel tool to remove duplicate DNA reads")
7095 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
7096 Duplicate reads can be seen as identical or nearly identical sequences with
7097 some mismatches. This tool lets users avoid the analysis of unnecessary
7098 reads, reducing the time of subsequent procedures with the
7099 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
7100 in order to exploit the parallel capabilities of multicore clusters. It is
7101 faster than multithreaded counterparts (end of 2015) for the same number of
7102 cores and, thanks to the message-passing technology, it can be executed on
7104 (home-page "https://sourceforge.net/projects/pardre/")
7105 (license license:gpl3+)))
7107 (define-public ruby-bio-kseq
7109 (name "ruby-bio-kseq")
7114 (uri (rubygems-uri "bio-kseq" version))
7117 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
7118 (build-system ruby-build-system)
7120 `(#:test-target "spec"))
7122 `(("bundler" ,bundler)
7123 ("ruby-rspec" ,ruby-rspec)
7124 ("ruby-rake-compiler" ,ruby-rake-compiler)))
7127 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
7129 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
7130 FASTQ parsing code. It provides a fast iterator over sequences and their
7132 (home-page "https://github.com/gusevfe/bio-kseq")
7133 (license license:expat)))
7135 (define-public bio-locus
7142 (uri (rubygems-uri "bio-locus" version))
7145 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
7146 (build-system ruby-build-system)
7148 `(("ruby-rspec" ,ruby-rspec)))
7149 (synopsis "Tool for fast querying of genome locations")
7151 "Bio-locus is a tabix-like tool for fast querying of genome
7152 locations. Many file formats in bioinformatics contain records that
7153 start with a chromosome name and a position for a SNP, or a start-end
7154 position for indels. Bio-locus allows users to store this chr+pos or
7155 chr+pos+alt information in a database.")
7156 (home-page "https://github.com/pjotrp/bio-locus")
7157 (license license:expat)))
7159 (define-public bio-blastxmlparser
7161 (name "bio-blastxmlparser")
7165 (uri (rubygems-uri "bio-blastxmlparser" version))
7168 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
7169 (build-system ruby-build-system)
7171 `(("ruby-bio-logger" ,ruby-bio-logger)
7172 ("ruby-nokogiri" ,ruby-nokogiri)))
7174 `(("ruby-rspec" ,ruby-rspec)))
7175 (synopsis "Fast big data BLAST XML parser and library")
7177 "Very fast parallel big-data BLAST XML file parser which can be used as
7178 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
7179 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
7180 (home-page "https://github.com/pjotrp/blastxmlparser")
7181 (license license:expat)))
7183 (define-public bioruby
7190 (uri (rubygems-uri "bio" version))
7193 "1d56amdsjv1mag7m6gv2w0xij8hqx1v5xbdjsix8sp3yp36m7938"))))
7194 (build-system ruby-build-system)
7196 `(("ruby-libxml" ,ruby-libxml)))
7198 `(("which" ,which))) ; required for test phase
7201 (modify-phases %standard-phases
7202 (add-before 'build 'patch-test-command
7204 (substitute* '("test/functional/bio/test_command.rb")
7205 (("/bin/sh") (which "sh")))
7206 (substitute* '("test/functional/bio/test_command.rb")
7207 (("/bin/ls") (which "ls")))
7208 (substitute* '("test/functional/bio/test_command.rb")
7209 (("which") (which "which")))
7210 (substitute* '("test/functional/bio/test_command.rb",
7211 "test/data/command/echoarg2.sh")
7212 (("/bin/echo") (which "echo")))
7214 (synopsis "Ruby library, shell and utilities for bioinformatics")
7215 (description "BioRuby comes with a comprehensive set of Ruby development
7216 tools and libraries for bioinformatics and molecular biology. BioRuby has
7217 components for sequence analysis, pathway analysis, protein modelling and
7218 phylogenetic analysis; it supports many widely used data formats and provides
7219 easy access to databases, external programs and public web services, including
7220 BLAST, KEGG, GenBank, MEDLINE and GO.")
7221 (home-page "http://bioruby.org/")
7222 ;; Code is released under Ruby license, except for setup
7223 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
7224 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
7226 (define-public r-biocinstaller
7228 (name "r-biocinstaller")
7232 (uri (bioconductor-uri "BiocInstaller" version))
7235 "1s1f9qhyf3mc73ir25x2zlgi9hf45a37lg4z8fbva4i21hqisgsl"))))
7237 `((upstream-name . "BiocInstaller")))
7238 (build-system r-build-system)
7239 (home-page "https://bioconductor.org/packages/BiocInstaller")
7240 (synopsis "Install Bioconductor packages")
7241 (description "This package is used to install and update R packages from
7242 Bioconductor, CRAN, and Github.")
7243 (license license:artistic2.0)))
7245 (define-public r-biocviews
7247 (name "r-biocviews")
7251 (uri (bioconductor-uri "biocViews" version))
7254 "0qwrsd9fcpkv7hhzy1scnj7ahdxi6cjary28kqk6b36gkzmnrw4r"))))
7256 `((upstream-name . "biocViews")))
7257 (build-system r-build-system)
7259 `(("r-biobase" ,r-biobase)
7260 ("r-biocmanager" ,r-biocmanager)
7261 ("r-graph" ,r-graph)
7263 ("r-rcurl" ,r-rcurl)
7265 ("r-runit" ,r-runit)))
7266 (home-page "https://bioconductor.org/packages/biocViews")
7267 (synopsis "Bioconductor package categorization helper")
7268 (description "The purpose of biocViews is to create HTML pages that
7269 categorize packages in a Bioconductor package repository according to keywords,
7270 also known as views, in a controlled vocabulary.")
7271 (license license:artistic2.0)))
7273 (define-public r-biocstyle
7275 (name "r-biocstyle")
7279 (uri (bioconductor-uri "BiocStyle" version))
7282 "029x8r9rcx6zy0xixdpwxai4jv4ynb161821fzac6z4r8k418398"))))
7284 `((upstream-name . "BiocStyle")))
7285 (build-system r-build-system)
7287 `(("r-biocmanager" ,r-biocmanager)
7288 ("r-bookdown" ,r-bookdown)
7289 ("r-knitr" ,r-knitr)
7290 ("r-rmarkdown" ,r-rmarkdown)
7291 ("r-yaml" ,r-yaml)))
7292 (home-page "https://bioconductor.org/packages/BiocStyle")
7293 (synopsis "Bioconductor formatting styles")
7294 (description "This package provides standard formatting styles for
7295 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
7297 (license license:artistic2.0)))
7299 (define-public r-bioccheck
7301 (name "r-bioccheck")
7305 (uri (bioconductor-uri "BiocCheck" version))
7308 "1gkw9s6dhdryga9ap5yhvcqg9jsy4cn417ayqk1qiv6fy91fd124"))))
7310 `((upstream-name . "BiocCheck")))
7311 (build-system r-build-system)
7314 (modify-phases %standard-phases
7315 ;; This package can be used by calling BiocCheck(<package>) from
7316 ;; within R, or by running R CMD BiocCheck <package>. This phase
7317 ;; makes sure the latter works. For this to work, the BiocCheck
7318 ;; script must be somewhere on the PATH (not the R bin directory).
7319 (add-after 'install 'install-bioccheck-subcommand
7320 (lambda* (#:key outputs #:allow-other-keys)
7321 (let* ((out (assoc-ref outputs "out"))
7322 (dest-dir (string-append out "/bin"))
7324 (string-append out "/site-library/BiocCheck/script/")))
7326 (symlink (string-append script-dir "/checkBadDeps.R")
7327 (string-append dest-dir "/checkBadDeps.R"))
7328 (symlink (string-append script-dir "/BiocCheck")
7329 (string-append dest-dir "/BiocCheck")))
7332 `(("r-codetools" ,r-codetools)
7333 ("r-graph" ,r-graph)
7335 ("r-knitr" ,r-knitr)
7336 ("r-optparse" ,r-optparse)
7337 ("r-biocmanager" ,r-biocmanager)
7338 ("r-biocviews" ,r-biocviews)
7339 ("r-stringdist" ,r-stringdist)))
7340 (home-page "https://bioconductor.org/packages/BiocCheck")
7341 (synopsis "Executes Bioconductor-specific package checks")
7342 (description "This package contains tools to perform additional quality
7343 checks on R packages that are to be submitted to the Bioconductor repository.")
7344 (license license:artistic2.0)))
7346 (define-public r-s4vectors
7348 (name "r-s4vectors")
7352 (uri (bioconductor-uri "S4Vectors" version))
7355 "1wkqmpy0d0fab9bjfc7i5wh2zng75pg9rn9c1z1lkki7fpwaw2jb"))))
7357 `((upstream-name . "S4Vectors")))
7358 (build-system r-build-system)
7360 `(("r-biocgenerics" ,r-biocgenerics)))
7361 (home-page "https://bioconductor.org/packages/S4Vectors")
7362 (synopsis "S4 implementation of vectors and lists")
7364 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7365 classes and a set of generic functions that extend the semantic of ordinary
7366 vectors and lists in R. Package developers can easily implement vector-like
7367 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7368 In addition, a few low-level concrete subclasses of general interest (e.g.
7369 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7370 S4Vectors package itself.")
7371 (license license:artistic2.0)))
7373 (define-public r-iranges
7379 (uri (bioconductor-uri "IRanges" version))
7382 "1d64sh43pfc9vj2l7y7x6sb44l67wlnn3dzygp7ws0smn06mardq"))))
7384 `((upstream-name . "IRanges")))
7385 (build-system r-build-system)
7387 `(("r-biocgenerics" ,r-biocgenerics)
7388 ("r-s4vectors" ,r-s4vectors)))
7389 (home-page "https://bioconductor.org/packages/IRanges")
7390 (synopsis "Infrastructure for manipulating intervals on sequences")
7392 "This package provides efficient low-level and highly reusable S4 classes
7393 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7394 generally, data that can be organized sequentially (formally defined as
7395 @code{Vector} objects), as well as views on these @code{Vector} objects.
7396 Efficient list-like classes are also provided for storing big collections of
7397 instances of the basic classes. All classes in the package use consistent
7398 naming and share the same rich and consistent \"Vector API\" as much as
7400 (license license:artistic2.0)))
7402 (define-public r-genomeinfodbdata
7404 (name "r-genomeinfodbdata")
7408 ;; We cannot use bioconductor-uri here because this tarball is
7409 ;; located under "data/annotation/" instead of "bioc/".
7410 (uri (string-append "https://bioconductor.org/packages/release/"
7411 "data/annotation/src/contrib/GenomeInfoDbData_"
7415 "0di6nlqpsyqf693k2na65ayqldih563x3zfrczpqc5q2hl5kg35c"))))
7417 `((upstream-name . "GenomeInfoDbData")))
7418 (build-system r-build-system)
7419 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7420 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7421 (description "This package contains data for mapping between NCBI taxonomy
7422 ID and species. It is used by functions in the GenomeInfoDb package.")
7423 (license license:artistic2.0)))
7425 (define-public r-genomeinfodb
7427 (name "r-genomeinfodb")
7431 (uri (bioconductor-uri "GenomeInfoDb" version))
7434 "0zkhms81b3jz30q7ag81a1mq1rgqg4izyfdvcni68gvn8gm7kdyk"))))
7436 `((upstream-name . "GenomeInfoDb")))
7437 (build-system r-build-system)
7439 `(("r-biocgenerics" ,r-biocgenerics)
7440 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7441 ("r-iranges" ,r-iranges)
7442 ("r-rcurl" ,r-rcurl)
7443 ("r-s4vectors" ,r-s4vectors)))
7444 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7445 (synopsis "Utilities for manipulating chromosome identifiers")
7447 "This package contains data and functions that define and allow
7448 translation between different chromosome sequence naming conventions (e.g.,
7449 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7450 names in their natural, rather than lexicographic, order.")
7451 (license license:artistic2.0)))
7453 (define-public r-edger
7459 (uri (bioconductor-uri "edgeR" version))
7462 "013glavk6a1wpyq3q35k343bdp6rf27w30q59i4kf47rp3i37g15"))))
7463 (properties `((upstream-name . "edgeR")))
7464 (build-system r-build-system)
7466 `(("r-limma" ,r-limma)
7467 ("r-locfit" ,r-locfit)
7469 ("r-statmod" ,r-statmod))) ;for estimateDisp
7470 (home-page "http://bioinf.wehi.edu.au/edgeR")
7471 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7472 (description "This package can do differential expression analysis of
7473 RNA-seq expression profiles with biological replication. It implements a range
7474 of statistical methodology based on the negative binomial distributions,
7475 including empirical Bayes estimation, exact tests, generalized linear models
7476 and quasi-likelihood tests. It be applied to differential signal analysis of
7477 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7479 (license license:gpl2+)))
7481 (define-public r-variantannotation
7483 (name "r-variantannotation")
7487 (uri (bioconductor-uri "VariantAnnotation" version))
7490 "144x3d3b9a3q5jy4aqrk1nf2yavwjhwlf71s7qyr4x3ms3wmvf8i"))))
7492 `((upstream-name . "VariantAnnotation")))
7496 `(("r-annotationdbi" ,r-annotationdbi)
7497 ("r-biobase" ,r-biobase)
7498 ("r-biocgenerics" ,r-biocgenerics)
7499 ("r-biostrings" ,r-biostrings)
7500 ("r-bsgenome" ,r-bsgenome)
7502 ("r-genomeinfodb" ,r-genomeinfodb)
7503 ("r-genomicfeatures" ,r-genomicfeatures)
7504 ("r-genomicranges" ,r-genomicranges)
7505 ("r-iranges" ,r-iranges)
7506 ("r-summarizedexperiment" ,r-summarizedexperiment)
7507 ("r-rhtslib" ,r-rhtslib)
7508 ("r-rsamtools" ,r-rsamtools)
7509 ("r-rtracklayer" ,r-rtracklayer)
7510 ("r-s4vectors" ,r-s4vectors)
7511 ("r-xvector" ,r-xvector)
7512 ("r-zlibbioc" ,r-zlibbioc)))
7513 (build-system r-build-system)
7514 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7515 (synopsis "Package for annotation of genetic variants")
7516 (description "This R package can annotate variants, compute amino acid
7517 coding changes and predict coding outcomes.")
7518 (license license:artistic2.0)))
7520 (define-public r-limma
7526 (uri (bioconductor-uri "limma" version))
7529 "1d4ig2b7fa9mwja52isxrwmprfdjdk1mlcf2skhdp51l24z6wbk7"))))
7530 (build-system r-build-system)
7531 (home-page "http://bioinf.wehi.edu.au/limma")
7532 (synopsis "Package for linear models for microarray and RNA-seq data")
7533 (description "This package can be used for the analysis of gene expression
7534 studies, especially the use of linear models for analysing designed experiments
7535 and the assessment of differential expression. The analysis methods apply to
7536 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7537 (license license:gpl2+)))
7539 (define-public r-xvector
7545 (uri (bioconductor-uri "XVector" version))
7548 "12y09pwy86h1za6cmaxs960r7fs0vjzhl0li8jn59vqq9liza1ap"))))
7550 `((upstream-name . "XVector")))
7551 (build-system r-build-system)
7554 (modify-phases %standard-phases
7555 (add-after 'unpack 'use-system-zlib
7557 (substitute* "DESCRIPTION"
7558 (("zlibbioc, ") ""))
7559 (substitute* "NAMESPACE"
7560 (("import\\(zlibbioc\\)") ""))
7565 `(("r-biocgenerics" ,r-biocgenerics)
7566 ("r-iranges" ,r-iranges)
7567 ("r-s4vectors" ,r-s4vectors)))
7568 (home-page "https://bioconductor.org/packages/XVector")
7569 (synopsis "Representation and manpulation of external sequences")
7571 "This package provides memory efficient S4 classes for storing sequences
7572 \"externally\" (behind an R external pointer, or on disk).")
7573 (license license:artistic2.0)))
7575 (define-public r-genomicranges
7577 (name "r-genomicranges")
7581 (uri (bioconductor-uri "GenomicRanges" version))
7584 "1285fr8qjd7d0ixpv7d5imi0n6wzc4k6yia1rkmig71qd2gg556k"))))
7586 `((upstream-name . "GenomicRanges")))
7587 (build-system r-build-system)
7589 `(("r-biocgenerics" ,r-biocgenerics)
7590 ("r-genomeinfodb" ,r-genomeinfodb)
7591 ("r-iranges" ,r-iranges)
7592 ("r-s4vectors" ,r-s4vectors)
7593 ("r-xvector" ,r-xvector)))
7594 (home-page "https://bioconductor.org/packages/GenomicRanges")
7595 (synopsis "Representation and manipulation of genomic intervals")
7597 "This package provides tools to efficiently represent and manipulate
7598 genomic annotations and alignments is playing a central role when it comes to
7599 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7600 GenomicRanges package defines general purpose containers for storing and
7601 manipulating genomic intervals and variables defined along a genome.")
7602 (license license:artistic2.0)))
7604 (define-public r-biobase
7610 (uri (bioconductor-uri "Biobase" version))
7613 "15yl92niqamx3lmwd11zlk0xniibqnh1gi280iadxicmchi83npc"))))
7615 `((upstream-name . "Biobase")))
7616 (build-system r-build-system)
7618 `(("r-biocgenerics" ,r-biocgenerics)))
7619 (home-page "https://bioconductor.org/packages/Biobase")
7620 (synopsis "Base functions for Bioconductor")
7622 "This package provides functions that are needed by many other packages
7623 on Bioconductor or which replace R functions.")
7624 (license license:artistic2.0)))
7626 (define-public r-annotationdbi
7628 (name "r-annotationdbi")
7632 (uri (bioconductor-uri "AnnotationDbi" version))
7635 "0lfq5668a6sq4kqhxx78hl3jcaqdsaaliiybl9xyya2scdk8c29c"))))
7637 `((upstream-name . "AnnotationDbi")))
7638 (build-system r-build-system)
7640 `(("r-biobase" ,r-biobase)
7641 ("r-biocgenerics" ,r-biocgenerics)
7643 ("r-iranges" ,r-iranges)
7644 ("r-rsqlite" ,r-rsqlite)
7645 ("r-s4vectors" ,r-s4vectors)))
7646 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7647 (synopsis "Annotation database interface")
7649 "This package provides user interface and database connection code for
7650 annotation data packages using SQLite data storage.")
7651 (license license:artistic2.0)))
7653 (define-public r-biomart
7659 (uri (bioconductor-uri "biomaRt" version))
7662 "1i457s91bn7n60bzw3zk4h64xgmawlrr6bq4z4cb7jlm04hdq8qm"))))
7664 `((upstream-name . "biomaRt")))
7665 (build-system r-build-system)
7667 `(("r-annotationdbi" ,r-annotationdbi)
7669 ("r-progress" ,r-progress)
7670 ("r-rcurl" ,r-rcurl)
7671 ("r-stringr" ,r-stringr)
7673 (home-page "https://bioconductor.org/packages/biomaRt")
7674 (synopsis "Interface to BioMart databases")
7676 "biomaRt provides an interface to a growing collection of databases
7677 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7678 package enables retrieval of large amounts of data in a uniform way without
7679 the need to know the underlying database schemas or write complex SQL queries.
7680 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7681 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7682 users direct access to a diverse set of data and enable a wide range of
7683 powerful online queries from gene annotation to database mining.")
7684 (license license:artistic2.0)))
7686 (define-public r-biocparallel
7688 (name "r-biocparallel")
7692 (uri (bioconductor-uri "BiocParallel" version))
7695 "0v8rhf3hbgb3v32h2pmsv1y6q2x4airmpp50fk7z6ardcn4aza7x"))))
7697 `((upstream-name . "BiocParallel")))
7698 (build-system r-build-system)
7700 `(("r-futile-logger" ,r-futile-logger)
7703 (home-page "https://bioconductor.org/packages/BiocParallel")
7704 (synopsis "Bioconductor facilities for parallel evaluation")
7706 "This package provides modified versions and novel implementation of
7707 functions for parallel evaluation, tailored to use with Bioconductor
7709 (license (list license:gpl2+ license:gpl3+))))
7711 (define-public r-biostrings
7713 (name "r-biostrings")
7717 (uri (bioconductor-uri "Biostrings" version))
7720 "0inrl97hli3qz6cfxcikc4picmbrqc8phdgqi18ynlvxy5ql64h4"))))
7722 `((upstream-name . "Biostrings")))
7723 (build-system r-build-system)
7725 `(("r-biocgenerics" ,r-biocgenerics)
7726 ("r-iranges" ,r-iranges)
7727 ("r-s4vectors" ,r-s4vectors)
7728 ("r-xvector" ,r-xvector)))
7729 (home-page "https://bioconductor.org/packages/Biostrings")
7730 (synopsis "String objects and algorithms for biological sequences")
7732 "This package provides memory efficient string containers, string
7733 matching algorithms, and other utilities, for fast manipulation of large
7734 biological sequences or sets of sequences.")
7735 (license license:artistic2.0)))
7737 (define-public r-rsamtools
7739 (name "r-rsamtools")
7743 (uri (bioconductor-uri "Rsamtools" version))
7746 "1nv5idyjk75mvl4np5sig0xa6qygm1ivj33k041ffyj19q8jf7ij"))))
7748 `((upstream-name . "Rsamtools")))
7749 (build-system r-build-system)
7752 (modify-phases %standard-phases
7753 (add-after 'unpack 'use-system-zlib
7755 (substitute* "DESCRIPTION"
7756 (("zlibbioc, ") ""))
7757 (substitute* "NAMESPACE"
7758 (("import\\(zlibbioc\\)") ""))
7763 `(("r-biocgenerics" ,r-biocgenerics)
7764 ("r-biocparallel" ,r-biocparallel)
7765 ("r-biostrings" ,r-biostrings)
7766 ("r-bitops" ,r-bitops)
7767 ("r-genomeinfodb" ,r-genomeinfodb)
7768 ("r-genomicranges" ,r-genomicranges)
7769 ("r-iranges" ,r-iranges)
7770 ("r-rhtslib" ,r-rhtslib)
7771 ("r-s4vectors" ,r-s4vectors)
7772 ("r-xvector" ,r-xvector)))
7773 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7774 (synopsis "Interface to samtools, bcftools, and tabix")
7776 "This package provides an interface to the @code{samtools},
7777 @code{bcftools}, and @code{tabix} utilities for manipulating SAM (Sequence
7778 Alignment / Map), FASTA, binary variant call (BCF) and compressed indexed
7779 tab-delimited (tabix) files.")
7780 (license license:expat)))
7782 (define-public r-delayedarray
7784 (name "r-delayedarray")
7788 (uri (bioconductor-uri "DelayedArray" version))
7791 "0l907ggxndn3f29zvsd5pppmp4c31rb22r6zkhvgph7xdxahyy6z"))))
7793 `((upstream-name . "DelayedArray")))
7794 (build-system r-build-system)
7796 `(("r-biocgenerics" ,r-biocgenerics)
7797 ("r-biocparallel" ,r-biocparallel)
7798 ("r-s4vectors" ,r-s4vectors)
7799 ("r-iranges" ,r-iranges)
7800 ("r-matrix" ,r-matrix)
7801 ("r-matrixstats" ,r-matrixstats)))
7802 (home-page "https://bioconductor.org/packages/DelayedArray")
7803 (synopsis "Delayed operations on array-like objects")
7805 "Wrapping an array-like object (typically an on-disk object) in a
7806 @code{DelayedArray} object allows one to perform common array operations on it
7807 without loading the object in memory. In order to reduce memory usage and
7808 optimize performance, operations on the object are either delayed or executed
7809 using a block processing mechanism. Note that this also works on in-memory
7810 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7811 @code{Matrix} objects, and ordinary arrays and data frames.")
7812 (license license:artistic2.0)))
7814 (define-public r-summarizedexperiment
7816 (name "r-summarizedexperiment")
7820 (uri (bioconductor-uri "SummarizedExperiment" version))
7823 "1ypk63pdml89y81pr41i2zq0fimsaxsa5lgpg6xs5cwikyaq0pci"))))
7825 `((upstream-name . "SummarizedExperiment")))
7826 (build-system r-build-system)
7828 `(("r-biobase" ,r-biobase)
7829 ("r-biocgenerics" ,r-biocgenerics)
7830 ("r-delayedarray" ,r-delayedarray)
7831 ("r-genomeinfodb" ,r-genomeinfodb)
7832 ("r-genomicranges" ,r-genomicranges)
7833 ("r-iranges" ,r-iranges)
7834 ("r-matrix" ,r-matrix)
7835 ("r-s4vectors" ,r-s4vectors)))
7836 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
7837 (synopsis "Container for representing genomic ranges by sample")
7839 "The SummarizedExperiment container contains one or more assays, each
7840 represented by a matrix-like object of numeric or other mode. The rows
7841 typically represent genomic ranges of interest and the columns represent
7843 (license license:artistic2.0)))
7845 (define-public r-genomicalignments
7847 (name "r-genomicalignments")
7851 (uri (bioconductor-uri "GenomicAlignments" version))
7854 "13zw7bb1adgph9bf9b9y725nr0320b80y70p2yqf3bjb2klfxf55"))))
7856 `((upstream-name . "GenomicAlignments")))
7857 (build-system r-build-system)
7859 `(("r-biocgenerics" ,r-biocgenerics)
7860 ("r-biocparallel" ,r-biocparallel)
7861 ("r-biostrings" ,r-biostrings)
7862 ("r-genomeinfodb" ,r-genomeinfodb)
7863 ("r-genomicranges" ,r-genomicranges)
7864 ("r-iranges" ,r-iranges)
7865 ("r-rsamtools" ,r-rsamtools)
7866 ("r-s4vectors" ,r-s4vectors)
7867 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7868 (home-page "https://bioconductor.org/packages/GenomicAlignments")
7869 (synopsis "Representation and manipulation of short genomic alignments")
7871 "This package provides efficient containers for storing and manipulating
7872 short genomic alignments (typically obtained by aligning short reads to a
7873 reference genome). This includes read counting, computing the coverage,
7874 junction detection, and working with the nucleotide content of the
7876 (license license:artistic2.0)))
7878 (define-public r-rtracklayer
7880 (name "r-rtracklayer")
7884 (uri (bioconductor-uri "rtracklayer" version))
7887 "161gcks9b12993g9k27gf7wfh8lgd8m8rr7x2slgfqqssk0yrmpd"))))
7888 (build-system r-build-system)
7891 (modify-phases %standard-phases
7892 (add-after 'unpack 'use-system-zlib
7894 (substitute* "DESCRIPTION"
7895 ((" zlibbioc,") ""))
7896 (substitute* "NAMESPACE"
7897 (("import\\(zlibbioc\\)") ""))
7900 `(("pkg-config" ,pkg-config)))
7904 `(("r-biocgenerics" ,r-biocgenerics)
7905 ("r-biostrings" ,r-biostrings)
7906 ("r-genomeinfodb" ,r-genomeinfodb)
7907 ("r-genomicalignments" ,r-genomicalignments)
7908 ("r-genomicranges" ,r-genomicranges)
7909 ("r-iranges" ,r-iranges)
7910 ("r-rcurl" ,r-rcurl)
7911 ("r-rsamtools" ,r-rsamtools)
7912 ("r-s4vectors" ,r-s4vectors)
7914 ("r-xvector" ,r-xvector)))
7915 (home-page "https://bioconductor.org/packages/rtracklayer")
7916 (synopsis "R interface to genome browsers and their annotation tracks")
7918 "rtracklayer is an extensible framework for interacting with multiple
7919 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7920 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7921 built-in). The user may export/import tracks to/from the supported browsers,
7922 as well as query and modify the browser state, such as the current viewport.")
7923 (license license:artistic2.0)))
7925 (define-public r-genomicfeatures
7927 (name "r-genomicfeatures")
7931 (uri (bioconductor-uri "GenomicFeatures" version))
7934 "02psq3jfgghdydwbydb1j792lvfg44l5npb44mx8d54ckr8658dd"))))
7936 `((upstream-name . "GenomicFeatures")))
7937 (build-system r-build-system)
7939 `(("r-annotationdbi" ,r-annotationdbi)
7940 ("r-biobase" ,r-biobase)
7941 ("r-biocgenerics" ,r-biocgenerics)
7942 ("r-biomart" ,r-biomart)
7943 ("r-biostrings" ,r-biostrings)
7945 ("r-genomeinfodb" ,r-genomeinfodb)
7946 ("r-genomicranges" ,r-genomicranges)
7947 ("r-iranges" ,r-iranges)
7948 ("r-rcurl" ,r-rcurl)
7949 ("r-rsqlite" ,r-rsqlite)
7950 ("r-rtracklayer" ,r-rtracklayer)
7951 ("r-s4vectors" ,r-s4vectors)
7952 ("r-xvector" ,r-xvector)))
7953 (home-page "https://bioconductor.org/packages/GenomicFeatures")
7954 (synopsis "Tools for working with transcript centric annotations")
7956 "This package provides a set of tools and methods for making and
7957 manipulating transcript centric annotations. With these tools the user can
7958 easily download the genomic locations of the transcripts, exons and cds of a
7959 given organism, from either the UCSC Genome Browser or a BioMart
7960 database (more sources will be supported in the future). This information is
7961 then stored in a local database that keeps track of the relationship between
7962 transcripts, exons, cds and genes. Flexible methods are provided for
7963 extracting the desired features in a convenient format.")
7964 (license license:artistic2.0)))
7966 (define-public r-go-db
7972 (uri (string-append "https://www.bioconductor.org/packages/"
7973 "release/data/annotation/src/contrib/GO.db_"
7977 "0i3wcf5h3n0dawzc1hy0kv74f06j80c47n4p3g3fmrcxlhi3jpa5"))))
7979 `((upstream-name . "GO.db")))
7980 (build-system r-build-system)
7982 `(("r-annotationdbi" ,r-annotationdbi)))
7983 (home-page "https://bioconductor.org/packages/GO.db")
7984 (synopsis "Annotation maps describing the entire Gene Ontology")
7986 "The purpose of this GO.db annotation package is to provide detailed
7987 information about the latest version of the Gene Ontologies.")
7988 (license license:artistic2.0)))
7990 (define-public r-topgo
7996 (uri (bioconductor-uri "topGO" version))
7999 "09z42jwz5vh289ijz3x68zv5vmgkgcbhlp73vvmna1gld5lh5kz1"))))
8001 `((upstream-name . "topGO")))
8002 (build-system r-build-system)
8004 `(("r-annotationdbi" ,r-annotationdbi)
8006 ("r-biobase" ,r-biobase)
8007 ("r-biocgenerics" ,r-biocgenerics)
8008 ("r-go-db" ,r-go-db)
8009 ("r-graph" ,r-graph)
8010 ("r-lattice" ,r-lattice)
8011 ("r-matrixstats" ,r-matrixstats)
8012 ("r-sparsem" ,r-sparsem)))
8013 (home-page "https://bioconductor.org/packages/topGO")
8014 (synopsis "Enrichment analysis for gene ontology")
8016 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
8017 terms while accounting for the topology of the GO graph. Different test
8018 statistics and different methods for eliminating local similarities and
8019 dependencies between GO terms can be implemented and applied.")
8020 ;; Any version of the LGPL applies.
8021 (license license:lgpl2.1+)))
8023 (define-public r-bsgenome
8029 (uri (bioconductor-uri "BSgenome" version))
8032 "0zwx42s73hc1vhn0v82i67mcixdwwc6n6q5h5vpnhpxlm4qwgqzp"))))
8034 `((upstream-name . "BSgenome")))
8035 (build-system r-build-system)
8037 `(("r-biocgenerics" ,r-biocgenerics)
8038 ("r-biostrings" ,r-biostrings)
8039 ("r-genomeinfodb" ,r-genomeinfodb)
8040 ("r-genomicranges" ,r-genomicranges)
8041 ("r-iranges" ,r-iranges)
8042 ("r-rsamtools" ,r-rsamtools)
8043 ("r-rtracklayer" ,r-rtracklayer)
8044 ("r-s4vectors" ,r-s4vectors)
8045 ("r-xvector" ,r-xvector)))
8046 (home-page "https://bioconductor.org/packages/BSgenome")
8047 (synopsis "Infrastructure for Biostrings-based genome data packages")
8049 "This package provides infrastructure shared by all Biostrings-based
8050 genome data packages and support for efficient SNP representation.")
8051 (license license:artistic2.0)))
8053 (define-public r-impute
8059 (uri (bioconductor-uri "impute" version))
8062 "144jb889979cv3il2zxqk724v3sj1wnzjm3lkspxcvk29dbb9q8j"))))
8064 `(("gfortran" ,gfortran)))
8065 (build-system r-build-system)
8066 (home-page "https://bioconductor.org/packages/impute")
8067 (synopsis "Imputation for microarray data")
8069 "This package provides a function to impute missing gene expression
8070 microarray data, using nearest neighbor averaging.")
8071 (license license:gpl2+)))
8073 (define-public r-seqpattern
8075 (name "r-seqpattern")
8079 (uri (bioconductor-uri "seqPattern" version))
8082 "1ljqscbmrmi5d4lzzvg2d86sqzch26yxw57d33qyid300wm60db2"))))
8084 `((upstream-name . "seqPattern")))
8085 (build-system r-build-system)
8087 `(("r-biostrings" ,r-biostrings)
8088 ("r-genomicranges" ,r-genomicranges)
8089 ("r-iranges" ,r-iranges)
8090 ("r-kernsmooth" ,r-kernsmooth)
8091 ("r-plotrix" ,r-plotrix)))
8092 (home-page "https://bioconductor.org/packages/seqPattern")
8093 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
8095 "This package provides tools to visualize oligonucleotide patterns and
8096 sequence motif occurrences across a large set of sequences centred at a common
8097 reference point and sorted by a user defined feature.")
8098 (license license:gpl3+)))
8100 (define-public r-genomation
8102 (name "r-genomation")
8106 (uri (bioconductor-uri "genomation" version))
8109 "06i711pwq9znd7plh0p25skxnnh5dyl61c33k9gma243wvlzmlkj"))))
8110 (build-system r-build-system)
8112 `(("r-biostrings" ,r-biostrings)
8113 ("r-bsgenome" ,r-bsgenome)
8114 ("r-data-table" ,r-data-table)
8115 ("r-genomeinfodb" ,r-genomeinfodb)
8116 ("r-genomicalignments" ,r-genomicalignments)
8117 ("r-genomicranges" ,r-genomicranges)
8118 ("r-ggplot2" ,r-ggplot2)
8119 ("r-gridbase" ,r-gridbase)
8120 ("r-impute" ,r-impute)
8121 ("r-iranges" ,r-iranges)
8122 ("r-matrixstats" ,r-matrixstats)
8123 ("r-plotrix" ,r-plotrix)
8126 ("r-readr" ,r-readr)
8127 ("r-reshape2" ,r-reshape2)
8128 ("r-rsamtools" ,r-rsamtools)
8129 ("r-rtracklayer" ,r-rtracklayer)
8130 ("r-runit" ,r-runit)
8131 ("r-s4vectors" ,r-s4vectors)
8132 ("r-seqpattern" ,r-seqpattern)))
8133 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8134 (synopsis "Summary, annotation and visualization of genomic data")
8136 "This package provides a package for summary and annotation of genomic
8137 intervals. Users can visualize and quantify genomic intervals over
8138 pre-defined functional regions, such as promoters, exons, introns, etc. The
8139 genomic intervals represent regions with a defined chromosome position, which
8140 may be associated with a score, such as aligned reads from HT-seq experiments,
8141 TF binding sites, methylation scores, etc. The package can use any tabular
8142 genomic feature data as long as it has minimal information on the locations of
8143 genomic intervals. In addition, it can use BAM or BigWig files as input.")
8144 (license license:artistic2.0)))
8146 (define-public r-genomationdata
8148 (name "r-genomationdata")
8152 ;; We cannot use bioconductor-uri here because this tarball is
8153 ;; located under "data/annotation/" instead of "bioc/".
8154 (uri (string-append "https://bioconductor.org/packages/"
8155 "release/data/experiment/src/contrib/"
8156 "genomationData_" version ".tar.gz"))
8159 "10xyb8akjrhmak2i0mnv1agny2ipy364q9nlibyplpzc7vdb6bw7"))))
8160 (build-system r-build-system)
8161 ;; As this package provides little more than large data files, it doesn't
8162 ;; make sense to build substitutes.
8163 (arguments `(#:substitutable? #f))
8165 `(("r-knitr" ,r-knitr)))
8166 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8167 (synopsis "Experimental data for use with the genomation package")
8169 "This package contains experimental genetic data for use with the
8170 genomation package. Included are Chip Seq, Methylation and Cage data,
8171 downloaded from Encode.")
8172 (license license:gpl3+)))
8174 (define-public r-seqlogo
8181 (uri (bioconductor-uri "seqLogo" version))
8184 "1z63imr1a24nqijpvxaxlakykcsadfqyxl2b3vlllncxnjjvb52b"))))
8185 (properties `((upstream-name . "seqLogo")))
8186 (build-system r-build-system)
8187 (home-page "https://bioconductor.org/packages/seqLogo")
8188 (synopsis "Sequence logos for DNA sequence alignments")
8190 "seqLogo takes the position weight matrix of a DNA sequence motif and
8191 plots the corresponding sequence logo as introduced by Schneider and
8193 (license license:lgpl2.0+)))
8195 (define-public r-motifrg
8202 (uri (bioconductor-uri "motifRG" version))
8205 "02c7fbjwdq7pk96bd2rn07l9r2hqy00s3hfpli5ybmwgvc9h9z4z"))))
8206 (properties `((upstream-name . "motifRG")))
8207 (build-system r-build-system)
8209 `(("r-biostrings" ,r-biostrings)
8210 ("r-bsgenome" ,r-bsgenome)
8211 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8212 ("r-iranges" ,r-iranges)
8213 ("r-seqlogo" ,r-seqlogo)
8214 ("r-xvector" ,r-xvector)))
8215 (home-page "https://bioconductor.org/packages/motifRG")
8216 (synopsis "Discover motifs in high throughput sequencing data")
8218 "This package provides tools for discriminative motif discovery in high
8219 throughput genetic sequencing data sets using regression methods.")
8220 (license license:artistic2.0)))
8222 (define-public r-qtl
8229 (uri (string-append "mirror://cran/src/contrib/qtl_"
8233 "03lmvydln8b7666b6w46qbryhf83vsd11d4y2v95rfgvqgq66l1i"))))
8234 (build-system r-build-system)
8235 (home-page "http://rqtl.org/")
8236 (synopsis "R package for analyzing QTL experiments in genetics")
8237 (description "R/qtl is an extension library for the R statistics
8238 system. It is used to analyze experimental crosses for identifying
8239 genes contributing to variation in quantitative traits (so-called
8240 quantitative trait loci, QTLs).
8242 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
8243 identify genotyping errors, and to perform single-QTL and two-QTL,
8244 two-dimensional genome scans.")
8245 (license license:gpl3)))
8247 (define-public r-zlibbioc
8253 (uri (bioconductor-uri "zlibbioc" version))
8256 "1h0a2ps2rfk9azzps7p23sxj5z1giv8gcx0ypzgyz7fkr4xi9z7k"))))
8258 `((upstream-name . "zlibbioc")))
8259 (build-system r-build-system)
8260 (home-page "https://bioconductor.org/packages/zlibbioc")
8261 (synopsis "Provider for zlib-1.2.5 to R packages")
8262 (description "This package uses the source code of zlib-1.2.5 to create
8263 libraries for systems that do not have these available via other means.")
8264 (license license:artistic2.0)))
8266 (define-public r-r4rna
8273 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8277 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8278 (build-system r-build-system)
8280 `(("r-optparse" ,r-optparse)
8281 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8282 (home-page "http://www.e-rna.org/r-chie/index.cgi")
8283 (synopsis "Analysis framework for RNA secondary structure")
8285 "The R4RNA package aims to be a general framework for the analysis of RNA
8286 secondary structure and comparative analysis in R.")
8287 (license license:gpl3+)))
8289 (define-public r-rhtslib
8296 (uri (bioconductor-uri "Rhtslib" version))
8299 "178zbrm221rwhbjk7j2v9g5ra44k0xg7c5abhd810m3g7snma8k8"))))
8300 (properties `((upstream-name . "Rhtslib")))
8301 (build-system r-build-system)
8302 ;; Without this a temporary directory ends up in the Rhtslib.so binary,
8303 ;; which makes R abort the build.
8304 (arguments '(#:configure-flags '("--no-staged-install")))
8306 `(("r-zlibbioc" ,r-zlibbioc)))
8310 `(("pkg-config" ,pkg-config)))
8311 (home-page "https://github.com/nhayden/Rhtslib")
8312 (synopsis "High-throughput sequencing library as an R package")
8314 "This package provides the HTSlib C library for high-throughput
8315 nucleotide sequence analysis. The package is primarily useful to developers
8316 of other R packages who wish to make use of HTSlib.")
8317 (license license:lgpl2.0+)))
8319 (define-public r-bamsignals
8321 (name "r-bamsignals")
8326 (uri (bioconductor-uri "bamsignals" version))
8329 "15q1q51dwl9qxfkf10yppw4m194ba03nq9plsrbj8fqj00v4729i"))))
8330 (build-system r-build-system)
8332 `(("r-biocgenerics" ,r-biocgenerics)
8333 ("r-genomicranges" ,r-genomicranges)
8334 ("r-iranges" ,r-iranges)
8336 ("r-rhtslib" ,r-rhtslib)
8337 ("r-zlibbioc" ,r-zlibbioc)))
8340 (home-page "https://bioconductor.org/packages/bamsignals")
8341 (synopsis "Extract read count signals from bam files")
8343 "This package allows to efficiently obtain count vectors from indexed bam
8344 files. It counts the number of nucleotide sequence reads in given genomic
8345 ranges and it computes reads profiles and coverage profiles. It also handles
8347 (license license:gpl2+)))
8349 (define-public r-rcas
8355 (uri (bioconductor-uri "RCAS" version))
8358 "1h4vf5gzilqbdrd8m9l3zc2m4sca8cir8366a7njgd558k7ld5kl"))))
8359 (properties `((upstream-name . "RCAS")))
8360 (build-system r-build-system)
8362 `(("r-annotationdbi" ,r-annotationdbi)
8363 ("r-biocgenerics" ,r-biocgenerics)
8364 ("r-biomart" ,r-biomart)
8365 ("r-biostrings" ,r-biostrings)
8366 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8367 ("r-cowplot" ,r-cowplot)
8368 ("r-data-table" ,r-data-table)
8371 ("r-genomation" ,r-genomation)
8372 ("r-genomeinfodb" ,r-genomeinfodb)
8373 ("r-genomicfeatures" ,r-genomicfeatures)
8374 ("r-genomicranges" ,r-genomicranges)
8375 ("r-ggplot2" ,r-ggplot2)
8376 ("r-ggseqlogo" ,r-ggseqlogo)
8377 ("r-knitr" ,r-knitr)
8378 ("r-motifrg" ,r-motifrg)
8379 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8380 ("r-pbapply" ,r-pbapply)
8381 ("r-pheatmap" ,r-pheatmap)
8382 ("r-plotly" ,r-plotly)
8383 ("r-plotrix" ,r-plotrix)
8384 ("r-proxy" ,r-proxy)
8385 ("r-rsqlite" ,r-rsqlite)
8386 ("r-rtracklayer" ,r-rtracklayer)
8387 ("r-rmarkdown" ,r-rmarkdown)
8388 ("r-s4vectors" ,r-s4vectors)
8389 ("r-topgo" ,r-topgo)
8390 ("pandoc" ,ghc-pandoc)))
8391 (synopsis "RNA-centric annotation system")
8393 "RCAS aims to be a standalone RNA-centric annotation system that provides
8394 intuitive reports and publication-ready graphics. This package provides the R
8395 library implementing most of the pipeline's features.")
8396 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8397 (license license:artistic2.0)))
8399 (define-public rcas-web
8406 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8407 "releases/download/v" version
8408 "/rcas-web-" version ".tar.gz"))
8411 "0wq951aj45gqki1bickg876i993lmawkp8x24agg264br5x716db"))))
8412 (build-system gnu-build-system)
8415 (modify-phases %standard-phases
8416 (add-after 'install 'wrap-executable
8417 (lambda* (#:key inputs outputs #:allow-other-keys)
8418 (let* ((out (assoc-ref outputs "out"))
8419 (json (assoc-ref inputs "guile-json"))
8420 (redis (assoc-ref inputs "guile-redis"))
8421 (path (string-append
8422 json "/share/guile/site/2.2:"
8423 redis "/share/guile/site/2.2")))
8424 (wrap-program (string-append out "/bin/rcas-web")
8425 `("GUILE_LOAD_PATH" ":" = (,path))
8426 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8427 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8430 `(("r-minimal" ,r-minimal)
8432 ("guile-next" ,guile-2.2)
8433 ("guile-json" ,guile-json)
8434 ("guile-redis" ,guile-redis)))
8436 `(("pkg-config" ,pkg-config)))
8437 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8438 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8439 (description "This package provides a simple web interface for the
8440 @dfn{RNA-centric annotation system} (RCAS).")
8441 (license license:agpl3+)))
8443 (define-public r-mutationalpatterns
8445 (name "r-mutationalpatterns")
8450 (uri (bioconductor-uri "MutationalPatterns" version))
8453 "1k3r06xj1nim1s8as1i7fykfa6fbb4x456kslbzdvbf83ppx34z3"))))
8454 (build-system r-build-system)
8456 `(("r-biocgenerics" ,r-biocgenerics)
8457 ("r-biostrings" ,r-biostrings)
8458 ;; These two packages are suggested packages
8459 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8460 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8461 ("r-genomicranges" ,r-genomicranges)
8462 ("r-genomeinfodb" ,r-genomeinfodb)
8463 ("r-ggplot2" ,r-ggplot2)
8464 ("r-iranges" ,r-iranges)
8467 ("r-pracma" ,r-pracma)
8468 ("r-reshape2" ,r-reshape2)
8469 ("r-cowplot" ,r-cowplot)
8470 ("r-ggdendro" ,r-ggdendro)
8471 ("r-s4vectors" ,r-s4vectors)
8472 ("r-summarizedexperiment" ,r-summarizedexperiment)
8473 ("r-variantannotation" ,r-variantannotation)))
8474 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8475 (synopsis "Extract and visualize mutational patterns in genomic data")
8476 (description "This package provides an extensive toolset for the
8477 characterization and visualization of a wide range of mutational patterns
8478 in SNV base substitution data.")
8479 (license license:expat)))
8481 (define-public r-chipkernels
8482 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8485 (name "r-chipkernels")
8486 (version (string-append "1.1-" revision "." (string-take commit 9)))
8491 (url "https://github.com/ManuSetty/ChIPKernels.git")
8493 (file-name (string-append name "-" version))
8496 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8497 (build-system r-build-system)
8499 `(("r-iranges" ,r-iranges)
8500 ("r-xvector" ,r-xvector)
8501 ("r-biostrings" ,r-biostrings)
8502 ("r-bsgenome" ,r-bsgenome)
8503 ("r-gtools" ,r-gtools)
8504 ("r-genomicranges" ,r-genomicranges)
8505 ("r-sfsmisc" ,r-sfsmisc)
8506 ("r-kernlab" ,r-kernlab)
8507 ("r-s4vectors" ,r-s4vectors)
8508 ("r-biocgenerics" ,r-biocgenerics)))
8509 (home-page "https://github.com/ManuSetty/ChIPKernels")
8510 (synopsis "Build string kernels for DNA Sequence analysis")
8511 (description "ChIPKernels is an R package for building different string
8512 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8513 must be built and this dictionary can be used for determining kernels for DNA
8515 (license license:gpl2+))))
8517 (define-public r-seqgl
8525 (url "https://github.com/ManuSetty/SeqGL.git")
8527 (file-name (git-file-name name version))
8530 "1r6ywvhxl3ffv48lgj7sbd582mcc6dha3ksgc2qjlvjrnkbj3799"))))
8531 (build-system r-build-system)
8533 `(("r-biostrings" ,r-biostrings)
8534 ("r-chipkernels" ,r-chipkernels)
8535 ("r-genomicranges" ,r-genomicranges)
8536 ("r-spams" ,r-spams)
8537 ("r-wgcna" ,r-wgcna)
8538 ("r-fastcluster" ,r-fastcluster)))
8539 (home-page "https://github.com/ManuSetty/SeqGL")
8540 (synopsis "Group lasso for Dnase/ChIP-seq data")
8541 (description "SeqGL is a group lasso based algorithm to extract
8542 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8543 This package presents a method which uses group lasso to discriminate between
8544 bound and non bound genomic regions to accurately identify transcription
8545 factors bound at the specific regions.")
8546 (license license:gpl2+)))
8548 (define-public r-tximport
8554 (uri (bioconductor-uri "tximport" version))
8557 "0nl4imr5klwcd0xnp5y0g61d6mcgd50q60zkl86ymfmc0id368jr"))))
8558 (build-system r-build-system)
8559 (home-page "https://bioconductor.org/packages/tximport")
8560 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8562 "This package provides tools to import transcript-level abundance,
8563 estimated counts and transcript lengths, and to summarize them into matrices
8564 for use with downstream gene-level analysis packages. Average transcript
8565 length, weighted by sample-specific transcript abundance estimates, is
8566 provided as a matrix which can be used as an offset for different expression
8567 of gene-level counts.")
8568 (license license:gpl2+)))
8570 (define-public r-rhdf5
8576 (uri (bioconductor-uri "rhdf5" version))
8579 "0y1w3cs7wg2b3jlkd6wyyz6626xg011nrg36si8gg371iqck9a1i"))))
8580 (build-system r-build-system)
8582 `(("r-rhdf5lib" ,r-rhdf5lib)))
8585 (home-page "https://bioconductor.org/packages/rhdf5")
8586 (synopsis "HDF5 interface to R")
8588 "This R/Bioconductor package provides an interface between HDF5 and R.
8589 HDF5's main features are the ability to store and access very large and/or
8590 complex datasets and a wide variety of metadata on mass storage (disk) through
8591 a completely portable file format. The rhdf5 package is thus suited for the
8592 exchange of large and/or complex datasets between R and other software
8593 package, and for letting R applications work on datasets that are larger than
8594 the available RAM.")
8595 (license license:artistic2.0)))
8597 (define-public r-annotationfilter
8599 (name "r-annotationfilter")
8603 (uri (bioconductor-uri "AnnotationFilter" version))
8606 "15qh4jwxxqsnb308nxzj99gckfk18rhp8g26q1xwgkr57zc5kcrx"))))
8608 `((upstream-name . "AnnotationFilter")))
8609 (build-system r-build-system)
8611 `(("r-genomicranges" ,r-genomicranges)
8612 ("r-lazyeval" ,r-lazyeval)))
8613 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8614 (synopsis "Facilities for filtering Bioconductor annotation resources")
8616 "This package provides classes and other infrastructure to implement
8617 filters for manipulating Bioconductor annotation resources. The filters are
8618 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8619 (license license:artistic2.0)))
8621 (define-public emboss
8627 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8628 (version-major+minor version) ".0/"
8629 "EMBOSS-" version ".tar.gz"))
8632 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8633 (build-system gnu-build-system)
8636 (list (string-append "--with-hpdf="
8637 (assoc-ref %build-inputs "libharu")))
8639 (modify-phases %standard-phases
8640 (add-after 'unpack 'fix-checks
8642 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8643 ;; and zlib, but assume that they are all found at the same
8645 (substitute* "configure.in"
8646 (("CHECK_PNGDRIVER")
8647 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8648 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8649 AM_CONDITIONAL(AMPNG, true)"))
8651 (add-after 'fix-checks 'disable-update-check
8653 ;; At build time there is no connection to the Internet, so
8654 ;; looking for updates will not work.
8655 (substitute* "Makefile.am"
8656 (("\\$\\(bindir\\)/embossupdate") ""))
8658 (add-after 'disable-update-check 'autogen
8659 (lambda _ (invoke "autoreconf" "-vif") #t)))))
8665 ("libharu" ,libharu)
8668 `(("autoconf" ,autoconf)
8669 ("automake" ,automake)
8670 ("libtool" ,libtool)
8671 ("pkg-config" ,pkg-config)))
8672 (home-page "http://emboss.sourceforge.net")
8673 (synopsis "Molecular biology analysis suite")
8674 (description "EMBOSS is the \"European Molecular Biology Open Software
8675 Suite\". EMBOSS is an analysis package specially developed for the needs of
8676 the molecular biology (e.g. EMBnet) user community. The software
8677 automatically copes with data in a variety of formats and even allows
8678 transparent retrieval of sequence data from the web. It also provides a
8679 number of libraries for the development of software in the field of molecular
8680 biology. EMBOSS also integrates a range of currently available packages and
8681 tools for sequence analysis into a seamless whole.")
8682 (license license:gpl2+)))
8685 (let ((revision "1")
8686 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8689 ;; The version is 2.13.0 even though no release archives have been
8690 ;; published as yet.
8691 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8695 (url "https://github.com/arq5x/bits.git")
8697 (file-name (string-append name "-" version "-checkout"))
8700 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8701 (build-system gnu-build-system)
8703 `(#:tests? #f ;no tests included
8705 (modify-phases %standard-phases
8707 (add-after 'unpack 'remove-cuda
8709 (substitute* "Makefile"
8711 (("(bits_test_intersections) \\\\" _ match) match))
8714 (lambda* (#:key outputs #:allow-other-keys)
8716 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8721 (home-page "https://github.com/arq5x/bits")
8722 (synopsis "Implementation of binary interval search algorithm")
8723 (description "This package provides an implementation of the
8724 BITS (Binary Interval Search) algorithm, an approach to interval set
8725 intersection. It is especially suited for the comparison of diverse genomic
8726 datasets and the exploration of large datasets of genome
8727 intervals (e.g. genes, sequence alignments).")
8728 (license license:gpl2))))
8730 (define-public piranha
8731 ;; There is no release tarball for the latest version. The latest commit is
8732 ;; older than one year at the time of this writing.
8733 (let ((revision "1")
8734 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8737 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8741 (url "https://github.com/smithlabcode/piranha.git")
8743 (file-name (git-file-name name version))
8746 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
8747 (build-system gnu-build-system)
8749 `(#:test-target "test"
8751 (modify-phases %standard-phases
8752 (add-after 'unpack 'copy-smithlab-cpp
8753 (lambda* (#:key inputs #:allow-other-keys)
8754 (for-each (lambda (file)
8755 (install-file file "./src/smithlab_cpp/"))
8756 (find-files (assoc-ref inputs "smithlab-cpp")))
8758 (add-after 'install 'install-to-store
8759 (lambda* (#:key outputs #:allow-other-keys)
8760 (let* ((out (assoc-ref outputs "out"))
8761 (bin (string-append out "/bin")))
8762 (for-each (lambda (file)
8763 (install-file file bin))
8764 (find-files "bin" ".*")))
8767 (list (string-append "--with-bam_tools_headers="
8768 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
8769 (string-append "--with-bam_tools_library="
8770 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
8772 `(("bamtools" ,bamtools)
8773 ("samtools" ,samtools-0.1)
8776 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8780 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8782 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8785 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8787 `(("python" ,python-2)))
8788 (home-page "https://github.com/smithlabcode/piranha")
8789 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
8791 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
8792 RIP-seq experiments. It takes input in BED or BAM format and identifies
8793 regions of statistically significant read enrichment. Additional covariates
8794 may optionally be provided to further inform the peak-calling process.")
8795 (license license:gpl3+))))
8803 (uri (pypi-uri "PePr" version))
8806 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
8807 (build-system python-build-system)
8809 `(#:python ,python-2 ; python2 only
8810 #:tests? #f)) ; no tests included
8812 `(("python2-numpy" ,python2-numpy)
8813 ("python2-scipy" ,python2-scipy)
8814 ("python2-pysam" ,python2-pysam)))
8815 (home-page "https://github.com/shawnzhangyx/PePr")
8816 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
8818 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
8819 that is primarily designed for data with biological replicates. It uses a
8820 negative binomial distribution to model the read counts among the samples in
8821 the same group, and look for consistent differences between ChIP and control
8822 group or two ChIP groups run under different conditions.")
8823 (license license:gpl3+)))
8825 (define-public filevercmp
8826 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
8829 (version (string-append "0-1." (string-take commit 7)))
8833 (url "https://github.com/ekg/filevercmp.git")
8835 (file-name (git-file-name name commit))
8838 "1j9vxsy0y050v59h0q1d6501fcw1kjvj0d18l1xk2zyg0jzj247c"))))
8839 (build-system gnu-build-system)
8841 `(#:tests? #f ; There are no tests to run.
8843 (modify-phases %standard-phases
8844 (delete 'configure) ; There is no configure phase.
8846 (lambda* (#:key outputs #:allow-other-keys)
8847 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
8848 (install-file "filevercmp" bin)
8850 (home-page "https://github.com/ekg/filevercmp")
8851 (synopsis "This program compares version strings")
8852 (description "This program compares version strings. It intends to be a
8853 replacement for strverscmp.")
8854 (license license:gpl3+))))
8856 (define-public multiqc
8863 (uri (pypi-uri "multiqc" version))
8866 "02iihfl0w0hpnr4pa0sbd1y9qxrg3ycyhjp5lidkcrqh1lmzs3zy"))))
8867 (build-system python-build-system)
8869 `(("python-jinja2" ,python-jinja2)
8870 ("python-simplejson" ,python-simplejson)
8871 ("python-pyyaml" ,python-pyyaml)
8872 ("python-click" ,python-click)
8873 ("python-spectra" ,python-spectra)
8874 ("python-requests" ,python-requests)
8875 ("python-markdown" ,python-markdown)
8876 ("python-lzstring" ,python-lzstring)
8877 ("python-matplotlib" ,python-matplotlib)
8878 ("python-numpy" ,python-numpy)
8879 ;; MultQC checks for the presence of nose at runtime.
8880 ("python-nose" ,python-nose)))
8883 (modify-phases %standard-phases
8884 (add-after 'unpack 'relax-requirements
8886 (substitute* "setup.py"
8887 ;; MultiQC 1.5 ‘requires’ a version of python-matplotlib older
8888 ;; than the one in Guix, but should work fine with 2.2.2.
8889 ;; See <https://github.com/ewels/MultiQC/issues/725> and
8890 ;; <https://github.com/ewels/MultiQC/issues/732> for details.
8891 (("['\"]matplotlib.*?['\"]")
8894 (home-page "http://multiqc.info")
8895 (synopsis "Aggregate bioinformatics analysis reports")
8897 "MultiQC is a tool to aggregate bioinformatics results across many
8898 samples into a single report. It contains modules for a large number of
8899 common bioinformatics tools.")
8900 (license license:gpl3+)))
8902 (define-public r-chipseq
8909 (uri (bioconductor-uri "chipseq" version))
8912 "1835nhrxcaqpqf1kxrsk1js8bf7x33z1n3bqjvm8404091acqyma"))))
8913 (build-system r-build-system)
8915 `(("r-biocgenerics" ,r-biocgenerics)
8916 ("r-genomicranges" ,r-genomicranges)
8917 ("r-iranges" ,r-iranges)
8918 ("r-lattice" ,r-lattice)
8919 ("r-s4vectors" ,r-s4vectors)
8920 ("r-shortread" ,r-shortread)))
8921 (home-page "https://bioconductor.org/packages/chipseq")
8922 (synopsis "Package for analyzing ChIPseq data")
8924 "This package provides tools for processing short read data from ChIPseq
8926 (license license:artistic2.0)))
8928 (define-public r-copyhelper
8930 (name "r-copyhelper")
8935 (uri (string-append "https://bioconductor.org/packages/release/"
8936 "data/experiment/src/contrib/CopyhelpeR_"
8940 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
8941 (properties `((upstream-name . "CopyhelpeR")))
8942 (build-system r-build-system)
8943 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
8944 (synopsis "Helper files for CopywriteR")
8946 "This package contains the helper files that are required to run the
8947 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
8948 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
8949 mm10. In addition, it contains a blacklist filter to remove regions that
8950 display copy number variation. Files are stored as GRanges objects from the
8951 GenomicRanges Bioconductor package.")
8952 (license license:gpl2)))
8954 (define-public r-copywriter
8956 (name "r-copywriter")
8961 (uri (bioconductor-uri "CopywriteR" version))
8964 "0kv3k58wyyicq1hhq7bddh0v3b2ksz6fa47skvnp8f193csza9g6"))))
8965 (properties `((upstream-name . "CopywriteR")))
8966 (build-system r-build-system)
8968 `(("r-biocparallel" ,r-biocparallel)
8969 ("r-chipseq" ,r-chipseq)
8970 ("r-copyhelper" ,r-copyhelper)
8971 ("r-data-table" ,r-data-table)
8972 ("r-dnacopy" ,r-dnacopy)
8973 ("r-futile-logger" ,r-futile-logger)
8974 ("r-genomeinfodb" ,r-genomeinfodb)
8975 ("r-genomicalignments" ,r-genomicalignments)
8976 ("r-genomicranges" ,r-genomicranges)
8977 ("r-gtools" ,r-gtools)
8978 ("r-iranges" ,r-iranges)
8979 ("r-matrixstats" ,r-matrixstats)
8980 ("r-rsamtools" ,r-rsamtools)
8981 ("r-s4vectors" ,r-s4vectors)))
8982 (home-page "https://github.com/PeeperLab/CopywriteR")
8983 (synopsis "Copy number information from targeted sequencing")
8985 "CopywriteR extracts DNA copy number information from targeted sequencing
8986 by utilizing off-target reads. It allows for extracting uniformly distributed
8987 copy number information, can be used without reference, and can be applied to
8988 sequencing data obtained from various techniques including chromatin
8989 immunoprecipitation and target enrichment on small gene panels. Thereby,
8990 CopywriteR constitutes a widely applicable alternative to available copy
8991 number detection tools.")
8992 (license license:gpl2)))
8994 (define-public r-methylkit
8996 (name "r-methylkit")
9000 (uri (bioconductor-uri "methylKit" version))
9003 "1z687vpi5kwcqpnd6r74c5y72hcsbqlwg0bk95kksgpi81q710qj"))))
9004 (properties `((upstream-name . "methylKit")))
9005 (build-system r-build-system)
9007 `(("r-data-table" ,r-data-table)
9008 ("r-emdbook" ,r-emdbook)
9009 ("r-fastseg" ,r-fastseg)
9010 ("r-genomeinfodb" ,r-genomeinfodb)
9011 ("r-genomicranges" ,r-genomicranges)
9012 ("r-gtools" ,r-gtools)
9013 ("r-iranges" ,r-iranges)
9014 ("r-kernsmooth" ,r-kernsmooth)
9015 ("r-limma" ,r-limma)
9016 ("r-mclust" ,r-mclust)
9018 ("r-qvalue" ,r-qvalue)
9019 ("r-r-utils" ,r-r-utils)
9021 ("r-rhtslib" ,r-rhtslib)
9022 ("r-rsamtools" ,r-rsamtools)
9023 ("r-rtracklayer" ,r-rtracklayer)
9024 ("r-s4vectors" ,r-s4vectors)
9025 ("r-zlibbioc" ,r-zlibbioc)))
9028 (home-page "https://github.com/al2na/methylKit")
9030 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9032 "MethylKit is an R package for DNA methylation analysis and annotation
9033 from high-throughput bisulfite sequencing. The package is designed to deal
9034 with sequencing data from @dfn{Reduced representation bisulfite
9035 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9036 genome bisulfite sequencing. It also has functions to analyze base-pair
9037 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9039 (license license:artistic2.0)))
9041 (define-public r-sva
9048 (uri (bioconductor-uri "sva" version))
9051 "0jj6klfha5v5qmx2sjblf1an6s2zqd7mmgsp7sfmh4k2jpqi3jm9"))))
9052 (build-system r-build-system)
9054 `(("r-genefilter" ,r-genefilter)
9056 ("r-biocparallel" ,r-biocparallel)
9057 ("r-matrixstats" ,r-matrixstats)
9058 ("r-limma" ,r-limma)))
9059 (home-page "https://bioconductor.org/packages/sva")
9060 (synopsis "Surrogate variable analysis")
9062 "This package contains functions for removing batch effects and other
9063 unwanted variation in high-throughput experiment. It also contains functions
9064 for identifying and building surrogate variables for high-dimensional data
9065 sets. Surrogate variables are covariates constructed directly from
9066 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9067 imaging data that can be used in subsequent analyses to adjust for unknown,
9068 unmodeled, or latent sources of noise.")
9069 (license license:artistic2.0)))
9071 (define-public r-seqminer
9078 (uri (cran-uri "seqminer" version))
9081 "1jydcpkw4rwfp983j83kipvsvr10as9pb49zzn3c2v09k1gh3ymy"))))
9082 (build-system r-build-system)
9085 (home-page "http://seqminer.genomic.codes")
9086 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9088 "This package provides tools to integrate nucleotide sequencing
9089 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9090 ;; Any version of the GPL is acceptable
9091 (license (list license:gpl2+ license:gpl3+))))
9093 (define-public r-raremetals2
9095 (name "r-raremetals2")
9100 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9101 "b/b7/RareMETALS2_" version ".tar.gz"))
9104 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9105 (properties `((upstream-name . "RareMETALS2")))
9106 (build-system r-build-system)
9108 `(("r-seqminer" ,r-seqminer)
9109 ("r-mvtnorm" ,r-mvtnorm)
9111 ("r-compquadform" ,r-compquadform)
9112 ("r-getopt" ,r-getopt)))
9113 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9114 (synopsis "Analyze gene-level association tests for binary trait")
9116 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9117 It was designed to meta-analyze gene-level association tests for binary trait.
9118 While rareMETALS offers a near-complete solution for meta-analysis of
9119 gene-level tests for quantitative trait, it does not offer the optimal
9120 solution for binary trait. The package rareMETALS2 offers improved features
9121 for analyzing gene-level association tests in meta-analyses for binary
9123 (license license:gpl3)))
9125 (define-public r-maldiquant
9127 (name "r-maldiquant")
9132 (uri (cran-uri "MALDIquant" version))
9135 "0b7kdz3x4sdq413h1q09l1qhcvdnnwv6fqsqwllks1cd3xy34c57"))))
9136 (properties `((upstream-name . "MALDIquant")))
9137 (build-system r-build-system)
9138 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9139 (synopsis "Quantitative analysis of mass spectrometry data")
9141 "This package provides a complete analysis pipeline for matrix-assisted
9142 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9143 two-dimensional mass spectrometry data. In addition to commonly used plotting
9144 and processing methods it includes distinctive features, namely baseline
9145 subtraction methods such as morphological filters (TopHat) or the
9146 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9147 alignment using warping functions, handling of replicated measurements as well
9148 as allowing spectra with different resolutions.")
9149 (license license:gpl3+)))
9151 (define-public r-protgenerics
9153 (name "r-protgenerics")
9158 (uri (bioconductor-uri "ProtGenerics" version))
9161 "12jjwmg58b4xbivxlw4pffq0qfi2c1c5hyrci0sfyphrc99fvx0i"))))
9162 (properties `((upstream-name . "ProtGenerics")))
9163 (build-system r-build-system)
9164 (home-page "https://github.com/lgatto/ProtGenerics")
9165 (synopsis "S4 generic functions for proteomics infrastructure")
9167 "This package provides S4 generic functions needed by Bioconductor
9168 proteomics packages.")
9169 (license license:artistic2.0)))
9171 (define-public r-mzr
9178 (uri (bioconductor-uri "mzR" version))
9181 "0g5r6yk4gyz0xdwlmrcij4zv7apdgsgygr043095l33hard6nsl5"))
9182 (modules '((guix build utils)))
9185 (delete-file-recursively "src/boost")
9187 (properties `((upstream-name . "mzR")))
9188 (build-system r-build-system)
9191 (modify-phases %standard-phases
9192 (add-after 'unpack 'use-system-boost
9194 (substitute* "src/Makevars"
9195 (("\\./boost/libs.*") "")
9196 (("ARCH_OBJS=" line)
9198 "\nARCH_LIBS=-lboost_system -lboost_regex \
9199 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9202 `(;; XXX Boost 1.69 will not work here.
9203 ("boost" ,boost-for-mysql) ; use this instead of the bundled boost sources
9206 `(("r-biobase" ,r-biobase)
9207 ("r-biocgenerics" ,r-biocgenerics)
9208 ("r-ncdf4" ,r-ncdf4)
9209 ("r-protgenerics" ,r-protgenerics)
9211 ("r-rhdf5lib" ,r-rhdf5lib)
9212 ("r-zlibbioc" ,r-zlibbioc)))
9213 (home-page "https://github.com/sneumann/mzR/")
9214 (synopsis "Parser for mass spectrometry data files")
9216 "The mzR package provides a unified API to the common file formats and
9217 parsers available for mass spectrometry data. It comes with a wrapper for the
9218 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9219 The package contains the original code written by the ISB, and a subset of the
9220 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9221 previously been used in XCMS.")
9222 (license license:artistic2.0)))
9224 (define-public r-affyio
9231 (uri (bioconductor-uri "affyio" version))
9234 "1s78hm51fgac3i2j4bbdy0z6g14370154s6km8lldc9zpahx8b6p"))))
9235 (build-system r-build-system)
9237 `(("r-zlibbioc" ,r-zlibbioc)))
9240 (home-page "https://github.com/bmbolstad/affyio")
9241 (synopsis "Tools for parsing Affymetrix data files")
9243 "This package provides routines for parsing Affymetrix data files based
9244 upon file format information. The primary focus is on accessing the CEL and
9246 (license license:lgpl2.0+)))
9248 (define-public r-affy
9255 (uri (bioconductor-uri "affy" version))
9258 "05vz0vf3472s1ivfhc0gc8yz98y4rvvp7cf6kfbxhy1b23im1bgk"))))
9259 (build-system r-build-system)
9261 `(("r-affyio" ,r-affyio)
9262 ("r-biobase" ,r-biobase)
9263 ("r-biocgenerics" ,r-biocgenerics)
9264 ("r-biocmanager" ,r-biocmanager)
9265 ("r-preprocesscore" ,r-preprocesscore)
9266 ("r-zlibbioc" ,r-zlibbioc)))
9269 (home-page "https://bioconductor.org/packages/affy")
9270 (synopsis "Methods for affymetrix oligonucleotide arrays")
9272 "This package contains functions for exploratory oligonucleotide array
9274 (license license:lgpl2.0+)))
9276 (define-public r-vsn
9283 (uri (bioconductor-uri "vsn" version))
9286 "1vqmyxg06kgq9m3w6n0jykqm4jgsjw879r4s216wlcq4xc94dh1r"))))
9287 (build-system r-build-system)
9289 `(("r-affy" ,r-affy)
9290 ("r-biobase" ,r-biobase)
9291 ("r-ggplot2" ,r-ggplot2)
9292 ("r-lattice" ,r-lattice)
9293 ("r-limma" ,r-limma)))
9294 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9295 (synopsis "Variance stabilization and calibration for microarray data")
9297 "The package implements a method for normalising microarray intensities,
9298 and works for single- and multiple-color arrays. It can also be used for data
9299 from other technologies, as long as they have similar format. The method uses
9300 a robust variant of the maximum-likelihood estimator for an
9301 additive-multiplicative error model and affine calibration. The model
9302 incorporates data calibration step (a.k.a. normalization), a model for the
9303 dependence of the variance on the mean intensity and a variance stabilizing
9304 data transformation. Differences between transformed intensities are
9305 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9306 their variance is independent of the mean, and they are usually more sensitive
9307 and specific in detecting differential transcription.")
9308 (license license:artistic2.0)))
9310 (define-public r-mzid
9317 (uri (bioconductor-uri "mzID" version))
9320 "0vnyg7jlmy7ain7gmjwhqyqr664znrvrdlh7zd63563vhb87qarn"))))
9321 (properties `((upstream-name . "mzID")))
9322 (build-system r-build-system)
9324 `(("r-doparallel" ,r-doparallel)
9325 ("r-foreach" ,r-foreach)
9326 ("r-iterators" ,r-iterators)
9328 ("r-protgenerics" ,r-protgenerics)
9331 (home-page "https://bioconductor.org/packages/mzID")
9332 (synopsis "Parser for mzIdentML files")
9334 "This package provides a parser for mzIdentML files implemented using the
9335 XML package. The parser tries to be general and able to handle all types of
9336 mzIdentML files with the drawback of having less pretty output than a vendor
9338 (license license:gpl2+)))
9340 (define-public r-pcamethods
9342 (name "r-pcamethods")
9347 (uri (bioconductor-uri "pcaMethods" version))
9350 "0svf4n7l0afy4wwgs6x8x4dm330r3311l5vmsxw2f0r4axkh3bzk"))))
9351 (properties `((upstream-name . "pcaMethods")))
9352 (build-system r-build-system)
9354 `(("r-biobase" ,r-biobase)
9355 ("r-biocgenerics" ,r-biocgenerics)
9357 ("r-rcpp" ,r-rcpp)))
9358 (home-page "https://github.com/hredestig/pcamethods")
9359 (synopsis "Collection of PCA methods")
9361 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9362 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9363 for missing value estimation is included for comparison. BPCA, PPCA and
9364 NipalsPCA may be used to perform PCA on incomplete data as well as for
9365 accurate missing value estimation. A set of methods for printing and plotting
9366 the results is also provided. All PCA methods make use of the same data
9367 structure (pcaRes) to provide a common interface to the PCA results.")
9368 (license license:gpl3+)))
9370 (define-public r-msnbase
9377 (uri (bioconductor-uri "MSnbase" version))
9380 "0z63yqazkycq0zbbarq9ida6al35hv3g7g9g7s7bss4gh0hk7lhd"))))
9381 (properties `((upstream-name . "MSnbase")))
9382 (build-system r-build-system)
9384 `(("r-affy" ,r-affy)
9385 ("r-biobase" ,r-biobase)
9386 ("r-biocgenerics" ,r-biocgenerics)
9387 ("r-biocparallel" ,r-biocparallel)
9388 ("r-digest" ,r-digest)
9389 ("r-ggplot2" ,r-ggplot2)
9390 ("r-impute" ,r-impute)
9391 ("r-iranges" ,r-iranges)
9392 ("r-lattice" ,r-lattice)
9393 ("r-maldiquant" ,r-maldiquant)
9397 ("r-pcamethods" ,r-pcamethods)
9399 ("r-preprocesscore" ,r-preprocesscore)
9400 ("r-protgenerics" ,r-protgenerics)
9402 ("r-s4vectors" ,r-s4vectors)
9403 ("r-scales" ,r-scales)
9406 (home-page "https://github.com/lgatto/MSnbase")
9407 (synopsis "Base functions and classes for MS-based proteomics")
9409 "This package provides basic plotting, data manipulation and processing
9410 of mass spectrometry based proteomics data.")
9411 (license license:artistic2.0)))
9413 (define-public r-msnid
9420 (uri (bioconductor-uri "MSnID" version))
9423 "18mp8zacawhfapfwpq8czbswxix2ykvqhwjga54v0a99zg3k87h3"))))
9424 (properties `((upstream-name . "MSnID")))
9425 (build-system r-build-system)
9427 `(("r-biobase" ,r-biobase)
9428 ("r-data-table" ,r-data-table)
9429 ("r-doparallel" ,r-doparallel)
9430 ("r-dplyr" ,r-dplyr)
9431 ("r-foreach" ,r-foreach)
9432 ("r-iterators" ,r-iterators)
9433 ("r-msnbase" ,r-msnbase)
9436 ("r-protgenerics" ,r-protgenerics)
9437 ("r-r-cache" ,r-r-cache)
9439 ("r-reshape2" ,r-reshape2)))
9440 (home-page "https://bioconductor.org/packages/MSnID")
9441 (synopsis "Utilities for LC-MSn proteomics identifications")
9443 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9444 from mzIdentML (leveraging the mzID package) or text files. After collating
9445 the search results from multiple datasets it assesses their identification
9446 quality and optimize filtering criteria to achieve the maximum number of
9447 identifications while not exceeding a specified false discovery rate. It also
9448 contains a number of utilities to explore the MS/MS results and assess missed
9449 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9450 (license license:artistic2.0)))
9452 (define-public r-seurat
9458 (uri (cran-uri "Seurat" version))
9461 "0mx2fvhdswbcsgqxhfc6d0gr92bkibwpz2bavqdzbbxrzpdpnilc"))))
9462 (properties `((upstream-name . "Seurat")))
9463 (build-system r-build-system)
9466 ("r-cluster" ,r-cluster)
9467 ("r-cowplot" ,r-cowplot)
9468 ("r-fitdistrplus" ,r-fitdistrplus)
9469 ("r-future" ,r-future)
9470 ("r-future-apply" ,r-future-apply)
9471 ("r-ggplot2" ,r-ggplot2)
9472 ("r-ggrepel" ,r-ggrepel)
9473 ("r-ggridges" ,r-ggridges)
9475 ("r-igraph" ,r-igraph)
9476 ("r-irlba" ,r-irlba)
9477 ("r-kernsmooth" ,r-kernsmooth)
9478 ("r-lmtest" ,r-lmtest)
9480 ("r-matrix" ,r-matrix)
9481 ("r-metap" ,r-metap)
9482 ("r-pbapply" ,r-pbapply)
9483 ("r-plotly" ,r-plotly)
9486 ("r-rcolorbrewer" ,r-rcolorbrewer)
9488 ("r-rcppeigen" ,r-rcppeigen)
9489 ("r-rcppprogress" ,r-rcppprogress)
9490 ("r-reticulate" ,r-reticulate)
9491 ("r-rlang" ,r-rlang)
9494 ("r-rtsne" ,r-rtsne)
9495 ("r-scales" ,r-scales)
9496 ("r-sctransform" ,r-sctransform)
9497 ("r-sdmtools" ,r-sdmtools)
9498 ("r-tsne" ,r-tsne)))
9499 (home-page "http://www.satijalab.org/seurat")
9500 (synopsis "Seurat is an R toolkit for single cell genomics")
9502 "This package is an R package designed for QC, analysis, and
9503 exploration of single cell RNA-seq data. It easily enables widely-used
9504 analytical techniques, including the identification of highly variable genes,
9505 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9506 algorithms; density clustering, hierarchical clustering, k-means, and the
9507 discovery of differentially expressed genes and markers.")
9508 (license license:gpl3)))
9510 (define-public r-aroma-light
9512 (name "r-aroma-light")
9517 (uri (bioconductor-uri "aroma.light" version))
9520 "0a1prl4jhbqpa85i2vyia1ks9iippzl8np50fvm9wx8kbjxna5l6"))))
9521 (properties `((upstream-name . "aroma.light")))
9522 (build-system r-build-system)
9524 `(("r-matrixstats" ,r-matrixstats)
9525 ("r-r-methodss3" ,r-r-methodss3)
9527 ("r-r-utils" ,r-r-utils)))
9528 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9529 (synopsis "Methods for normalization and visualization of microarray data")
9531 "This package provides methods for microarray analysis that take basic
9532 data types such as matrices and lists of vectors. These methods can be used
9533 standalone, be utilized in other packages, or be wrapped up in higher-level
9535 (license license:gpl2+)))
9537 (define-public r-deseq
9544 (uri (bioconductor-uri "DESeq" version))
9547 "0jppqrikg9qfqcfw5qd3m5c7bag9g23bc0kcpk5zfkk1wv09mnlm"))))
9548 (properties `((upstream-name . "DESeq")))
9549 (build-system r-build-system)
9551 `(("r-biobase" ,r-biobase)
9552 ("r-biocgenerics" ,r-biocgenerics)
9553 ("r-genefilter" ,r-genefilter)
9554 ("r-geneplotter" ,r-geneplotter)
9555 ("r-lattice" ,r-lattice)
9556 ("r-locfit" ,r-locfit)
9558 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9559 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9560 (synopsis "Differential gene expression analysis")
9562 "This package provides tools for estimating variance-mean dependence in
9563 count data from high-throughput genetic sequencing assays and for testing for
9564 differential expression based on a model using the negative binomial
9566 (license license:gpl3+)))
9568 (define-public r-edaseq
9575 (uri (bioconductor-uri "EDASeq" version))
9578 "0mmc9bij17w4mfwcc566zbj5fvqgl8gfqs0qvj6ri4mbcql9jxb3"))))
9579 (properties `((upstream-name . "EDASeq")))
9580 (build-system r-build-system)
9582 `(("r-annotationdbi" ,r-annotationdbi)
9583 ("r-aroma-light" ,r-aroma-light)
9584 ("r-biobase" ,r-biobase)
9585 ("r-biocgenerics" ,r-biocgenerics)
9586 ("r-biocmanager" ,r-biocmanager)
9587 ("r-biomart" ,r-biomart)
9588 ("r-biostrings" ,r-biostrings)
9589 ("r-deseq" ,r-deseq)
9590 ("r-genomicfeatures" ,r-genomicfeatures)
9591 ("r-genomicranges" ,r-genomicranges)
9592 ("r-iranges" ,r-iranges)
9593 ("r-rsamtools" ,r-rsamtools)
9594 ("r-shortread" ,r-shortread)))
9595 (home-page "https://github.com/drisso/EDASeq")
9596 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9598 "This package provides support for numerical and graphical summaries of
9599 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9600 adjust for GC-content effect (or other gene-level effects) on read counts:
9601 loess robust local regression, global-scaling, and full-quantile
9602 normalization. Between-lane normalization procedures to adjust for
9603 distributional differences between lanes (e.g., sequencing depth):
9604 global-scaling and full-quantile normalization.")
9605 (license license:artistic2.0)))
9607 (define-public r-interactivedisplaybase
9609 (name "r-interactivedisplaybase")
9614 (uri (bioconductor-uri "interactiveDisplayBase" version))
9617 "1kkyv7hkygacmksvld9gs3ycf6wlblqcwi11nny0hq3l0ha265v5"))))
9619 `((upstream-name . "interactiveDisplayBase")))
9620 (build-system r-build-system)
9622 `(("r-biocgenerics" ,r-biocgenerics)
9623 ("r-shiny" ,r-shiny)))
9624 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9625 (synopsis "Base package for web displays of Bioconductor objects")
9627 "This package contains the basic methods needed to generate interactive
9628 Shiny-based display methods for Bioconductor objects.")
9629 (license license:artistic2.0)))
9631 (define-public r-annotationhub
9633 (name "r-annotationhub")
9638 (uri (bioconductor-uri "AnnotationHub" version))
9641 "1rpzl4x5mrwxrrf1jzm4zni6li6x34fjfyybsdvplb0ixa48zhn4"))))
9642 (properties `((upstream-name . "AnnotationHub")))
9643 (build-system r-build-system)
9645 `(("r-annotationdbi" ,r-annotationdbi)
9646 ("r-biocfilecache" ,r-biocfilecache)
9647 ("r-biocgenerics" ,r-biocgenerics)
9648 ("r-biocmanager" ,r-biocmanager)
9650 ("r-dplyr" ,r-dplyr)
9652 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9653 ("r-rappdirs" ,r-rappdirs)
9654 ("r-rsqlite" ,r-rsqlite)
9655 ("r-s4vectors" ,r-s4vectors)
9656 ("r-yaml" ,r-yaml)))
9657 (home-page "https://bioconductor.org/packages/AnnotationHub")
9658 (synopsis "Client to access AnnotationHub resources")
9660 "This package provides a client for the Bioconductor AnnotationHub web
9661 resource. The AnnotationHub web resource provides a central location where
9662 genomic files (e.g. VCF, bed, wig) and other resources from standard
9663 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9664 metadata about each resource, e.g., a textual description, tags, and date of
9665 modification. The client creates and manages a local cache of files retrieved
9666 by the user, helping with quick and reproducible access.")
9667 (license license:artistic2.0)))
9669 (define-public r-fastseg
9676 (uri (bioconductor-uri "fastseg" version))
9679 "03gggz29nf8kyy9clkifqr0xm8v0yb0kl0gjfb5c0vrjmwkfqvdf"))))
9680 (build-system r-build-system)
9682 `(("r-biobase" ,r-biobase)
9683 ("r-biocgenerics" ,r-biocgenerics)
9684 ("r-genomicranges" ,r-genomicranges)
9685 ("r-iranges" ,r-iranges)
9686 ("r-s4vectors" ,r-s4vectors)))
9687 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
9688 (synopsis "Fast segmentation algorithm for genetic sequencing data")
9690 "Fastseg implements a very fast and efficient segmentation algorithm.
9691 It can segment data from DNA microarrays and data from next generation
9692 sequencing for example to detect copy number segments. Further it can segment
9693 data from RNA microarrays like tiling arrays to identify transcripts. Most
9694 generally, it can segment data given as a matrix or as a vector. Various data
9695 formats can be used as input to fastseg like expression set objects for
9696 microarrays or GRanges for sequencing data.")
9697 (license license:lgpl2.0+)))
9699 (define-public r-keggrest
9706 (uri (bioconductor-uri "KEGGREST" version))
9709 "1yjrpbm5zfg0h3nb5gg06q2f19ydbhjqwi0jb6q3p8dyrgww9mqp"))))
9710 (properties `((upstream-name . "KEGGREST")))
9711 (build-system r-build-system)
9713 `(("r-biostrings" ,r-biostrings)
9716 (home-page "https://bioconductor.org/packages/KEGGREST")
9717 (synopsis "Client-side REST access to KEGG")
9719 "This package provides a package that provides a client interface to the
9720 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
9721 (license license:artistic2.0)))
9723 (define-public r-gage
9730 (uri (bioconductor-uri "gage" version))
9733 "08d5yg7n4rx4xsginc8bx0sycpj06pi1k7i44ff757444p20srwq"))))
9734 (build-system r-build-system)
9736 `(("r-annotationdbi" ,r-annotationdbi)
9737 ("r-graph" ,r-graph)
9738 ("r-keggrest" ,r-keggrest)))
9739 (home-page "http://www.biomedcentral.com/1471-2105/10/161")
9740 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
9742 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
9743 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
9744 data attributes including sample sizes, experimental designs, assay platforms,
9745 and other types of heterogeneity. The gage package provides functions for
9746 basic GAGE analysis, result processing and presentation. In addition, it
9747 provides demo microarray data and commonly used gene set data based on KEGG
9748 pathways and GO terms. These functions and data are also useful for gene set
9749 analysis using other methods.")
9750 (license license:gpl2+)))
9752 (define-public r-genomicfiles
9754 (name "r-genomicfiles")
9759 (uri (bioconductor-uri "GenomicFiles" version))
9762 "122g0yhpsm6fyvv38agp57clagl13h324rk06mlgb2xz104a1j4i"))))
9763 (properties `((upstream-name . "GenomicFiles")))
9764 (build-system r-build-system)
9766 `(("r-biocgenerics" ,r-biocgenerics)
9767 ("r-biocparallel" ,r-biocparallel)
9768 ("r-genomeinfodb" ,r-genomeinfodb)
9769 ("r-genomicalignments" ,r-genomicalignments)
9770 ("r-genomicranges" ,r-genomicranges)
9771 ("r-iranges" ,r-iranges)
9772 ("r-rsamtools" ,r-rsamtools)
9773 ("r-rtracklayer" ,r-rtracklayer)
9774 ("r-s4vectors" ,r-s4vectors)
9775 ("r-summarizedexperiment" ,r-summarizedexperiment)
9776 ("r-variantannotation" ,r-variantannotation)))
9777 (home-page "https://bioconductor.org/packages/GenomicFiles")
9778 (synopsis "Distributed computing by file or by range")
9780 "This package provides infrastructure for parallel computations
9781 distributed by file or by range. User defined mapper and reducer functions
9782 provide added flexibility for data combination and manipulation.")
9783 (license license:artistic2.0)))
9785 (define-public r-complexheatmap
9787 (name "r-complexheatmap")
9792 (uri (bioconductor-uri "ComplexHeatmap" version))
9795 "1imnb72r10csl2h12sckic7hcsb8v2z0y3dyw1ax2fpykmsmq776"))))
9797 `((upstream-name . "ComplexHeatmap")))
9798 (build-system r-build-system)
9800 `(("r-circlize" ,r-circlize)
9802 ("r-colorspace" ,r-colorspace)
9803 ("r-getoptlong" ,r-getoptlong)
9804 ("r-globaloptions" ,r-globaloptions)
9806 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9808 "https://github.com/jokergoo/ComplexHeatmap")
9809 (synopsis "Making Complex Heatmaps")
9811 "Complex heatmaps are efficient to visualize associations between
9812 different sources of data sets and reveal potential structures. This package
9813 provides a highly flexible way to arrange multiple heatmaps and supports
9814 self-defined annotation graphics.")
9815 (license license:gpl2+)))
9817 (define-public r-dirichletmultinomial
9819 (name "r-dirichletmultinomial")
9824 (uri (bioconductor-uri "DirichletMultinomial" version))
9827 "0qirvhnbv4wd50ln4pqbk4dj6h2935ipf9p4sw1x62qqhwxidqk4"))))
9829 `((upstream-name . "DirichletMultinomial")))
9830 (build-system r-build-system)
9834 `(("r-biocgenerics" ,r-biocgenerics)
9835 ("r-iranges" ,r-iranges)
9836 ("r-s4vectors" ,r-s4vectors)))
9837 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
9838 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
9840 "Dirichlet-multinomial mixture models can be used to describe variability
9841 in microbial metagenomic data. This package is an interface to code
9842 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
9844 (license license:lgpl3)))
9846 (define-public r-ensembldb
9848 (name "r-ensembldb")
9853 (uri (bioconductor-uri "ensembldb" version))
9856 "09s5g9xm9m8mqvzk6pkp9fyhx3zyb4p8yziz49mhfji5n35nydjr"))))
9857 (build-system r-build-system)
9859 `(("r-annotationdbi" ,r-annotationdbi)
9860 ("r-annotationfilter" ,r-annotationfilter)
9861 ("r-biobase" ,r-biobase)
9862 ("r-biocgenerics" ,r-biocgenerics)
9863 ("r-biostrings" ,r-biostrings)
9866 ("r-genomeinfodb" ,r-genomeinfodb)
9867 ("r-genomicfeatures" ,r-genomicfeatures)
9868 ("r-genomicranges" ,r-genomicranges)
9869 ("r-iranges" ,r-iranges)
9870 ("r-protgenerics" ,r-protgenerics)
9871 ("r-rsamtools" ,r-rsamtools)
9872 ("r-rsqlite" ,r-rsqlite)
9873 ("r-rtracklayer" ,r-rtracklayer)
9874 ("r-s4vectors" ,r-s4vectors)))
9875 (home-page "https://github.com/jotsetung/ensembldb")
9876 (synopsis "Utilities to create and use Ensembl-based annotation databases")
9878 "The package provides functions to create and use transcript-centric
9879 annotation databases/packages. The annotation for the databases are directly
9880 fetched from Ensembl using their Perl API. The functionality and data is
9881 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
9882 but, in addition to retrieve all gene/transcript models and annotations from
9883 the database, the @code{ensembldb} package also provides a filter framework
9884 allowing to retrieve annotations for specific entries like genes encoded on a
9885 chromosome region or transcript models of lincRNA genes.")
9886 ;; No version specified
9887 (license license:lgpl3+)))
9889 (define-public r-organismdbi
9891 (name "r-organismdbi")
9896 (uri (bioconductor-uri "OrganismDbi" version))
9899 "14azk69pmwlhza0mhsxigsg127w3mgsx9hhrbdcdqmy3vzfbfaqq"))))
9900 (properties `((upstream-name . "OrganismDbi")))
9901 (build-system r-build-system)
9903 `(("r-annotationdbi" ,r-annotationdbi)
9904 ("r-biobase" ,r-biobase)
9905 ("r-biocgenerics" ,r-biocgenerics)
9906 ("r-biocmanager" ,r-biocmanager)
9908 ("r-genomicfeatures" ,r-genomicfeatures)
9909 ("r-genomicranges" ,r-genomicranges)
9910 ("r-graph" ,r-graph)
9911 ("r-iranges" ,r-iranges)
9913 ("r-s4vectors" ,r-s4vectors)))
9914 (home-page "https://bioconductor.org/packages/OrganismDbi")
9915 (synopsis "Software to enable the smooth interfacing of database packages")
9916 (description "The package enables a simple unified interface to several
9917 annotation packages each of which has its own schema by taking advantage of
9918 the fact that each of these packages implements a select methods.")
9919 (license license:artistic2.0)))
9921 (define-public r-biovizbase
9923 (name "r-biovizbase")
9928 (uri (bioconductor-uri "biovizBase" version))
9931 "1lba1801ak0a4vz6f8jffp9d525q27p0dhi2bp4f68mvdwwl2994"))))
9932 (properties `((upstream-name . "biovizBase")))
9933 (build-system r-build-system)
9935 `(("r-annotationdbi" ,r-annotationdbi)
9936 ("r-annotationfilter" ,r-annotationfilter)
9937 ("r-biocgenerics" ,r-biocgenerics)
9938 ("r-biostrings" ,r-biostrings)
9939 ("r-dichromat" ,r-dichromat)
9940 ("r-ensembldb" ,r-ensembldb)
9941 ("r-genomeinfodb" ,r-genomeinfodb)
9942 ("r-genomicalignments" ,r-genomicalignments)
9943 ("r-genomicfeatures" ,r-genomicfeatures)
9944 ("r-genomicranges" ,r-genomicranges)
9945 ("r-hmisc" ,r-hmisc)
9946 ("r-iranges" ,r-iranges)
9947 ("r-rcolorbrewer" ,r-rcolorbrewer)
9948 ("r-rlang" ,r-rlang)
9949 ("r-rsamtools" ,r-rsamtools)
9950 ("r-s4vectors" ,r-s4vectors)
9951 ("r-scales" ,r-scales)
9952 ("r-summarizedexperiment" ,r-summarizedexperiment)
9953 ("r-variantannotation" ,r-variantannotation)))
9954 (home-page "https://bioconductor.org/packages/biovizBase")
9955 (synopsis "Basic graphic utilities for visualization of genomic data")
9957 "The biovizBase package is designed to provide a set of utilities, color
9958 schemes and conventions for genomic data. It serves as the base for various
9959 high-level packages for biological data visualization. This saves development
9960 effort and encourages consistency.")
9961 (license license:artistic2.0)))
9963 (define-public r-ggbio
9970 (uri (bioconductor-uri "ggbio" version))
9973 "10s6hnffnrrsx3896adqdc5g55fzd5y6qhnp1mq0c641nw833rwd"))))
9974 (build-system r-build-system)
9977 (modify-phases %standard-phases
9978 ;; See https://github.com/tengfei/ggbio/issues/117
9979 ;; This fix will be included in the next release.
9980 (add-after 'unpack 'fix-typo
9982 (substitute* "R/GGbio-class.R"
9983 (("fechable") "fetchable"))
9986 `(("r-annotationdbi" ,r-annotationdbi)
9987 ("r-annotationfilter" ,r-annotationfilter)
9988 ("r-biobase" ,r-biobase)
9989 ("r-biocgenerics" ,r-biocgenerics)
9990 ("r-biostrings" ,r-biostrings)
9991 ("r-biovizbase" ,r-biovizbase)
9992 ("r-bsgenome" ,r-bsgenome)
9993 ("r-ensembldb" ,r-ensembldb)
9994 ("r-genomeinfodb" ,r-genomeinfodb)
9995 ("r-genomicalignments" ,r-genomicalignments)
9996 ("r-genomicfeatures" ,r-genomicfeatures)
9997 ("r-genomicranges" ,r-genomicranges)
9998 ("r-ggally" ,r-ggally)
9999 ("r-ggplot2" ,r-ggplot2)
10000 ("r-gridextra" ,r-gridextra)
10001 ("r-gtable" ,r-gtable)
10002 ("r-hmisc" ,r-hmisc)
10003 ("r-iranges" ,r-iranges)
10004 ("r-organismdbi" ,r-organismdbi)
10005 ("r-reshape2" ,r-reshape2)
10006 ("r-rlang" ,r-rlang)
10007 ("r-rsamtools" ,r-rsamtools)
10008 ("r-rtracklayer" ,r-rtracklayer)
10009 ("r-s4vectors" ,r-s4vectors)
10010 ("r-scales" ,r-scales)
10011 ("r-summarizedexperiment" ,r-summarizedexperiment)
10012 ("r-variantannotation" ,r-variantannotation)))
10013 (home-page "http://www.tengfei.name/ggbio/")
10014 (synopsis "Visualization tools for genomic data")
10016 "The ggbio package extends and specializes the grammar of graphics for
10017 biological data. The graphics are designed to answer common scientific
10018 questions, in particular those often asked of high throughput genomics data.
10019 All core Bioconductor data structures are supported, where appropriate. The
10020 package supports detailed views of particular genomic regions, as well as
10021 genome-wide overviews. Supported overviews include ideograms and grand linear
10022 views. High-level plots include sequence fragment length, edge-linked
10023 interval to data view, mismatch pileup, and several splicing summaries.")
10024 (license license:artistic2.0)))
10026 (define-public r-gprofiler
10028 (name "r-gprofiler")
10033 (uri (cran-uri "gProfileR" version))
10036 "12nwidbnqmnfy5dnqga26byslvdnkrpz2fi19qfcby6xx0wbndk7"))))
10037 (properties `((upstream-name . "gProfileR")))
10038 (build-system r-build-system)
10040 `(("r-plyr" ,r-plyr)
10041 ("r-rcurl" ,r-rcurl)))
10042 (home-page "https://cran.r-project.org/web/packages/gProfileR/")
10043 (synopsis "Interface to the g:Profiler toolkit")
10045 "This package provides tools for functional enrichment analysis,
10046 gene identifier conversion and mapping homologous genes across related
10047 organisms via the @code{g:Profiler} toolkit.")
10048 (license license:gpl2+)))
10050 (define-public r-gqtlbase
10052 (name "r-gqtlbase")
10057 (uri (bioconductor-uri "gQTLBase" version))
10060 "1n2cizb88g2ankngvhxv377gizg80y3fhlx67sgm0z4ilm6a30ql"))))
10061 (properties `((upstream-name . "gQTLBase")))
10062 (build-system r-build-system)
10064 `(("r-batchjobs" ,r-batchjobs)
10065 ("r-bbmisc" ,r-bbmisc)
10066 ("r-biocgenerics" ,r-biocgenerics)
10068 ("r-doparallel" ,r-doparallel)
10070 ("r-ffbase" ,r-ffbase)
10071 ("r-foreach" ,r-foreach)
10072 ("r-genomicfiles" ,r-genomicfiles)
10073 ("r-genomicranges" ,r-genomicranges)
10074 ("r-rtracklayer" ,r-rtracklayer)
10075 ("r-s4vectors" ,r-s4vectors)
10076 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10077 (home-page "https://bioconductor.org/packages/gQTLBase")
10078 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10080 "The purpose of this package is to simplify the storage and interrogation
10081 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10083 (license license:artistic2.0)))
10085 (define-public r-snpstats
10087 (name "r-snpstats")
10092 (uri (bioconductor-uri "snpStats" version))
10095 "0drfd24a5pkrhzmpidlh717bgh2dm68mpn6vj1vlpkilfbkifl34"))))
10096 (properties `((upstream-name . "snpStats")))
10097 (build-system r-build-system)
10098 (inputs `(("zlib" ,zlib)))
10100 `(("r-biocgenerics" ,r-biocgenerics)
10101 ("r-matrix" ,r-matrix)
10102 ("r-survival" ,r-survival)
10103 ("r-zlibbioc" ,r-zlibbioc)))
10104 (home-page "https://bioconductor.org/packages/snpStats")
10105 (synopsis "Methods for SNP association studies")
10107 "This package provides classes and statistical methods for large
10108 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10109 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10110 (license license:gpl3)))
10112 (define-public r-homo-sapiens
10114 (name "r-homo-sapiens")
10118 ;; We cannot use bioconductor-uri here because this tarball is
10119 ;; located under "data/annotation/" instead of "bioc/".
10120 (uri (string-append "http://www.bioconductor.org/packages/"
10121 "release/data/annotation/src/contrib/"
10123 version ".tar.gz"))
10126 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10128 `((upstream-name . "Homo.sapiens")))
10129 (build-system r-build-system)
10131 `(("r-genomicfeatures" ,r-genomicfeatures)
10132 ("r-go-db" ,r-go-db)
10133 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10134 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10135 ("r-organismdbi" ,r-organismdbi)
10136 ("r-annotationdbi" ,r-annotationdbi)))
10137 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10138 (synopsis "Annotation package for the Homo.sapiens object")
10140 "This package contains the Homo.sapiens object to access data from
10141 several related annotation packages.")
10142 (license license:artistic2.0)))
10144 (define-public r-erma
10151 (uri (bioconductor-uri "erma" version))
10154 "0j7ggp63m5y88cxgi49vcql1s1avzifwvvd2hydj4lj3yrmzib48"))))
10155 (build-system r-build-system)
10157 `(("r-annotationdbi" ,r-annotationdbi)
10158 ("r-biobase" ,r-biobase)
10159 ("r-biocgenerics" ,r-biocgenerics)
10160 ("r-biocparallel" ,r-biocparallel)
10161 ("r-genomeinfodb" ,r-genomeinfodb)
10162 ("r-genomicfiles" ,r-genomicfiles)
10163 ("r-genomicranges" ,r-genomicranges)
10164 ("r-ggplot2" ,r-ggplot2)
10165 ("r-homo-sapiens" ,r-homo-sapiens)
10166 ("r-iranges" ,r-iranges)
10167 ("r-rtracklayer" ,r-rtracklayer)
10168 ("r-s4vectors" ,r-s4vectors)
10169 ("r-shiny" ,r-shiny)
10170 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10171 (home-page "https://bioconductor.org/packages/erma")
10172 (synopsis "Epigenomic road map adventures")
10174 "The epigenomics road map describes locations of epigenetic marks in DNA
10175 from a variety of cell types. Of interest are locations of histone
10176 modifications, sites of DNA methylation, and regions of accessible chromatin.
10177 This package presents a selection of elements of the road map including
10178 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10179 by Ernst and Kellis.")
10180 (license license:artistic2.0)))
10182 (define-public r-ldblock
10189 (uri (bioconductor-uri "ldblock" version))
10192 "0lraxhq9ny3468534klrl64nx0dpaf9cbd5bir6m5qma8j7kfnyd"))))
10193 (build-system r-build-system)
10195 `(("r-biocgenerics" ,r-biocgenerics)
10197 ("r-genomeinfodb" ,r-genomeinfodb)
10198 ("r-genomicfiles" ,r-genomicfiles)
10199 ("r-go-db" ,r-go-db)
10200 ("r-homo-sapiens" ,r-homo-sapiens)
10201 ("r-matrix" ,r-matrix)
10202 ("r-rsamtools" ,r-rsamtools)
10203 ("r-snpstats" ,r-snpstats)
10204 ("r-variantannotation" ,r-variantannotation)))
10205 (home-page "https://bioconductor.org/packages/ldblock")
10206 (synopsis "Data structures for linkage disequilibrium measures in populations")
10208 "This package defines data structures for @dfn{linkage
10209 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10210 handling of existing population-level data for the purpose of flexibly
10211 defining LD blocks.")
10212 (license license:artistic2.0)))
10214 (define-public r-gqtlstats
10216 (name "r-gqtlstats")
10221 (uri (bioconductor-uri "gQTLstats" version))
10224 "17xadfn8qh1pwzlpcbds5wrjr9bzhsnmv90wffxmp02hq20qkrh5"))))
10225 (properties `((upstream-name . "gQTLstats")))
10226 (build-system r-build-system)
10228 `(("r-annotationdbi" ,r-annotationdbi)
10229 ("r-batchjobs" ,r-batchjobs)
10230 ("r-bbmisc" ,r-bbmisc)
10231 ("r-beeswarm" ,r-beeswarm)
10232 ("r-biobase" ,r-biobase)
10233 ("r-biocgenerics" ,r-biocgenerics)
10234 ("r-doparallel" ,r-doparallel)
10235 ("r-dplyr" ,r-dplyr)
10237 ("r-ffbase" ,r-ffbase)
10238 ("r-foreach" ,r-foreach)
10239 ("r-genomeinfodb" ,r-genomeinfodb)
10240 ("r-genomicfeatures" ,r-genomicfeatures)
10241 ("r-genomicfiles" ,r-genomicfiles)
10242 ("r-genomicranges" ,r-genomicranges)
10243 ("r-ggbeeswarm" ,r-ggbeeswarm)
10244 ("r-ggplot2" ,r-ggplot2)
10245 ("r-gqtlbase" ,r-gqtlbase)
10246 ("r-hardyweinberg" ,r-hardyweinberg)
10247 ("r-homo-sapiens" ,r-homo-sapiens)
10248 ("r-iranges" ,r-iranges)
10249 ("r-limma" ,r-limma)
10251 ("r-plotly" ,r-plotly)
10252 ("r-reshape2" ,r-reshape2)
10253 ("r-s4vectors" ,r-s4vectors)
10254 ("r-shiny" ,r-shiny)
10255 ("r-snpstats" ,r-snpstats)
10256 ("r-summarizedexperiment" ,r-summarizedexperiment)
10257 ("r-variantannotation" ,r-variantannotation)))
10258 (home-page "https://bioconductor.org/packages/gQTLstats")
10259 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10261 "This package provides tools for the computationally efficient analysis
10262 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10263 The software in this package aims to support refinements and functional
10264 interpretation of members of a collection of association statistics on a
10265 family of feature/genome hypotheses.")
10266 (license license:artistic2.0)))
10268 (define-public r-gviz
10275 (uri (bioconductor-uri "Gviz" version))
10278 "02alz27w8fnnm2ga71g3jg2b94f95ccv6r1fyszj4yb1k2g7rkxk"))))
10279 (properties `((upstream-name . "Gviz")))
10280 (build-system r-build-system)
10282 `(("r-annotationdbi" ,r-annotationdbi)
10283 ("r-biobase" ,r-biobase)
10284 ("r-biocgenerics" ,r-biocgenerics)
10285 ("r-biomart" ,r-biomart)
10286 ("r-biostrings" ,r-biostrings)
10287 ("r-biovizbase" ,r-biovizbase)
10288 ("r-bsgenome" ,r-bsgenome)
10289 ("r-digest" ,r-digest)
10290 ("r-genomeinfodb" ,r-genomeinfodb)
10291 ("r-genomicalignments" ,r-genomicalignments)
10292 ("r-genomicfeatures" ,r-genomicfeatures)
10293 ("r-genomicranges" ,r-genomicranges)
10294 ("r-iranges" ,r-iranges)
10295 ("r-lattice" ,r-lattice)
10296 ("r-latticeextra" ,r-latticeextra)
10297 ("r-matrixstats" ,r-matrixstats)
10298 ("r-rcolorbrewer" ,r-rcolorbrewer)
10299 ("r-rsamtools" ,r-rsamtools)
10300 ("r-rtracklayer" ,r-rtracklayer)
10301 ("r-s4vectors" ,r-s4vectors)
10302 ("r-xvector" ,r-xvector)))
10303 (home-page "https://bioconductor.org/packages/Gviz")
10304 (synopsis "Plotting data and annotation information along genomic coordinates")
10306 "Genomic data analyses requires integrated visualization of known genomic
10307 information and new experimental data. Gviz uses the biomaRt and the
10308 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10309 and translates this to e.g. gene/transcript structures in viewports of the
10310 grid graphics package. This results in genomic information plotted together
10312 (license license:artistic2.0)))
10314 (define-public r-gwascat
10321 (uri (bioconductor-uri "gwascat" version))
10324 "0akb36mrybmxbb1bc9kgxbnj3cdypfylj3yzrmhjwqxml03mg61i"))))
10325 (build-system r-build-system)
10327 `(("r-annotationdbi" ,r-annotationdbi)
10328 ("r-biocgenerics" ,r-biocgenerics)
10329 ("r-biostrings" ,r-biostrings)
10330 ("r-genomeinfodb" ,r-genomeinfodb)
10331 ("r-genomicfeatures" ,r-genomicfeatures)
10332 ("r-genomicranges" ,r-genomicranges)
10333 ("r-homo-sapiens" ,r-homo-sapiens)
10334 ("r-iranges" ,r-iranges)
10335 ("r-rsamtools" ,r-rsamtools)
10336 ("r-rtracklayer" ,r-rtracklayer)
10337 ("r-s4vectors" ,r-s4vectors)))
10338 (home-page "https://bioconductor.org/packages/gwascat")
10339 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10341 "This package provides tools for representing and modeling data in the
10342 EMBL-EBI GWAS catalog.")
10343 (license license:artistic2.0)))
10345 (define-public r-sushi
10351 (uri (bioconductor-uri "Sushi" version))
10354 "1hgh3jfcx0bh3fyvp85v7435hvsk3ah1hxx5117ss93v03iwjf1g"))))
10355 (properties `((upstream-name . "Sushi")))
10356 (build-system r-build-system)
10358 `(("r-biomart" ,r-biomart)
10360 (home-page "https://bioconductor.org/packages/Sushi")
10361 (synopsis "Tools for visualizing genomics data")
10363 "This package provides flexible, quantitative, and integrative genomic
10364 visualizations for publication-quality multi-panel figures.")
10365 (license license:gpl2+)))
10367 (define-public r-fithic
10373 (uri (bioconductor-uri "FitHiC" version))
10376 "1qrxy4v8vmykrk8y6g3bs5wh5xhbs6pxyydbxy3vnj2mjirnxr6d"))))
10377 (properties `((upstream-name . "FitHiC")))
10378 (build-system r-build-system)
10380 `(("r-data-table" ,r-data-table)
10381 ("r-fdrtool" ,r-fdrtool)
10382 ("r-rcpp" ,r-rcpp)))
10383 (home-page "https://bioconductor.org/packages/FitHiC")
10384 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10386 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10387 intra-chromosomal contact maps produced by genome-wide genome architecture
10388 assays such as Hi-C.")
10389 (license license:gpl2+)))
10391 (define-public r-hitc
10397 (uri (bioconductor-uri "HiTC" version))
10400 "059a1xxv2kb0bb32flymg2s8ylhavnv3j8l4125rfidagcgxgzjq"))))
10401 (properties `((upstream-name . "HiTC")))
10402 (build-system r-build-system)
10404 `(("r-biostrings" ,r-biostrings)
10405 ("r-genomeinfodb" ,r-genomeinfodb)
10406 ("r-genomicranges" ,r-genomicranges)
10407 ("r-iranges" ,r-iranges)
10408 ("r-matrix" ,r-matrix)
10409 ("r-rcolorbrewer" ,r-rcolorbrewer)
10410 ("r-rtracklayer" ,r-rtracklayer)))
10411 (home-page "https://bioconductor.org/packages/HiTC")
10412 (synopsis "High throughput chromosome conformation capture analysis")
10414 "The HiTC package was developed to explore high-throughput \"C\" data
10415 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10416 quality controls, normalization, visualization, and further analysis are also
10418 (license license:artistic2.0)))
10420 (define-public r-hdf5array
10422 (name "r-hdf5array")
10427 (uri (bioconductor-uri "HDF5Array" version))
10430 "0n8zc1x582vwb0zfhrjmnqbnpqky9zbhjc2j836i0a4yisklwdcp"))))
10431 (properties `((upstream-name . "HDF5Array")))
10432 (build-system r-build-system)
10436 `(("r-biocgenerics" ,r-biocgenerics)
10437 ("r-delayedarray" ,r-delayedarray)
10438 ("r-iranges" ,r-iranges)
10439 ("r-rhdf5" ,r-rhdf5)
10440 ("r-rhdf5lib" ,r-rhdf5lib)
10441 ("r-s4vectors" ,r-s4vectors)))
10442 (home-page "https://bioconductor.org/packages/HDF5Array")
10443 (synopsis "HDF5 back end for DelayedArray objects")
10444 (description "This package provides an array-like container for convenient
10445 access and manipulation of HDF5 datasets. It supports delayed operations and
10446 block processing.")
10447 (license license:artistic2.0)))
10449 (define-public r-rhdf5lib
10451 (name "r-rhdf5lib")
10456 (uri (bioconductor-uri "Rhdf5lib" version))
10459 "1lpmyxlwwcy92hyxqag321ssc5z6yw3a0ws9r058jwgzyjg7i2gm"))
10460 (modules '((guix build utils)))
10463 ;; Delete bundled binaries
10464 (delete-file-recursively "src/winlib/")
10466 (properties `((upstream-name . "Rhdf5lib")))
10467 (build-system r-build-system)
10470 (modify-phases %standard-phases
10471 (add-after 'unpack 'do-not-use-bundled-hdf5
10472 (lambda* (#:key inputs #:allow-other-keys)
10473 (for-each delete-file '("configure" "configure.ac"))
10474 ;; Do not make other packages link with the proprietary libsz.
10475 (substitute* "R/zzz.R"
10476 (("'%s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a -lz'")
10477 "'%s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a -lz'")
10478 (("'%s/libhdf5.a %s/libsz.a -lz'")
10479 "'%s/libhdf5.a %s/libhdf5.a -lz'"))
10480 (with-directory-excursion "src"
10481 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10482 (rename-file (string-append "hdf5-" ,(package-version hdf5-1.10))
10484 ;; Remove timestamp and host system information to make
10485 ;; the build reproducible.
10486 (substitute* "hdf5/src/libhdf5.settings.in"
10487 (("Configured on: @CONFIG_DATE@")
10488 "Configured on: Guix")
10489 (("Uname information:.*")
10490 "Uname information: Linux\n")
10491 ;; Remove unnecessary store reference.
10493 "C Compiler: GCC\n"))
10494 (rename-file "Makevars.in" "Makevars")
10495 (substitute* "Makevars"
10496 (("HDF5_CXX_LIB=.*")
10497 (string-append "HDF5_CXX_LIB="
10498 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10500 (string-append "HDF5_LIB="
10501 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10502 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10503 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10504 ;; szip is non-free software
10505 (("cp \\$\\{SZIP_LIB\\}.*") "")
10506 (("\\$\\{USER_LIB_DIR\\}libsz.a") "")))
10511 `(("hdf5" ,hdf5-1.10)))
10513 `(("hdf5-source" ,(package-source hdf5-1.10))))
10514 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10515 (synopsis "HDF5 library as an R package")
10516 (description "This package provides C and C++ HDF5 libraries for use in R
10518 (license license:artistic2.0)))
10520 (define-public r-beachmat
10522 (name "r-beachmat")
10527 (uri (bioconductor-uri "beachmat" version))
10530 "14cz19fw97s8mhm9r2n5li44vckx069k8nqsyy64c3lkfm4vy4zx"))))
10531 (build-system r-build-system)
10533 `(("r-biocgenerics" ,r-biocgenerics)
10534 ("r-delayedarray" ,r-delayedarray)))
10535 (home-page "https://bioconductor.org/packages/beachmat")
10536 (synopsis "Compiling Bioconductor to handle each matrix type")
10537 (description "This package provides a consistent C++ class interface for a
10538 variety of commonly used matrix types, including sparse and HDF5-backed
10540 (license license:gpl3)))
10542 (define-public r-singlecellexperiment
10544 (name "r-singlecellexperiment")
10549 (uri (bioconductor-uri "SingleCellExperiment" version))
10552 "0m3yjnv1njb4gyzcjfk7a0lz2vgggp2wjz382gqrb0qhhwcgfkj5"))))
10554 `((upstream-name . "SingleCellExperiment")))
10555 (build-system r-build-system)
10557 `(("r-biocgenerics" ,r-biocgenerics)
10558 ("r-s4vectors" ,r-s4vectors)
10559 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10560 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10561 (synopsis "S4 classes for single cell data")
10562 (description "This package defines an S4 class for storing data from
10563 single-cell experiments. This includes specialized methods to store and
10564 retrieve spike-in information, dimensionality reduction coordinates and size
10565 factors for each cell, along with the usual metadata for genes and
10567 (license license:gpl3)))
10569 (define-public r-scater
10575 (uri (bioconductor-uri "scater" version))
10578 "16a17161xlhh6qpna9qxph3anlc7ydgyrczmy4alfiw8si7pzmxa"))))
10579 (build-system r-build-system)
10581 `(("r-beachmat" ,r-beachmat)
10582 ("r-biocgenerics" ,r-biocgenerics)
10583 ("r-biocneighbors" ,r-biocneighbors)
10584 ("r-biocparallel" ,r-biocparallel)
10585 ("r-biocsingular" ,r-biocsingular)
10586 ("r-delayedarray" ,r-delayedarray)
10587 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10588 ("r-dplyr" ,r-dplyr)
10589 ("r-ggbeeswarm" ,r-ggbeeswarm)
10590 ("r-ggplot2" ,r-ggplot2)
10591 ("r-matrix" ,r-matrix)
10593 ("r-s4vectors" ,r-s4vectors)
10594 ("r-singlecellexperiment" ,r-singlecellexperiment)
10595 ("r-summarizedexperiment" ,r-summarizedexperiment)
10596 ("r-viridis" ,r-viridis)))
10597 (home-page "https://github.com/davismcc/scater")
10598 (synopsis "Single-cell analysis toolkit for gene expression data in R")
10599 (description "This package provides a collection of tools for doing
10600 various analyses of single-cell RNA-seq gene expression data, with a focus on
10602 (license license:gpl2+)))
10604 (define-public r-scran
10611 (uri (bioconductor-uri "scran" version))
10614 "17mknpkvs7mgnlbf2hv9k7rwbx2vlg60yrwfyb8nn3nxsb6vm7yn"))))
10615 (build-system r-build-system)
10617 `(("r-beachmat" ,r-beachmat)
10619 ("r-biocgenerics" ,r-biocgenerics)
10620 ("r-biocneighbors" ,r-biocneighbors)
10621 ("r-biocparallel" ,r-biocparallel)
10622 ("r-biocsingular" ,r-biocsingular)
10623 ("r-delayedarray" ,r-delayedarray)
10624 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10625 ("r-dqrng" ,r-dqrng)
10626 ("r-dynamictreecut" ,r-dynamictreecut)
10627 ("r-edger" ,r-edger)
10628 ("r-igraph" ,r-igraph)
10629 ("r-limma" ,r-limma)
10630 ("r-matrix" ,r-matrix)
10632 ("r-s4vectors" ,r-s4vectors)
10633 ("r-scater" ,r-scater)
10634 ("r-singlecellexperiment" ,r-singlecellexperiment)
10635 ("r-statmod" ,r-statmod)
10636 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10637 (home-page "https://bioconductor.org/packages/scran")
10638 (synopsis "Methods for single-cell RNA-Seq data analysis")
10639 (description "This package implements a variety of low-level analyses of
10640 single-cell RNA-seq data. Methods are provided for normalization of
10641 cell-specific biases, assignment of cell cycle phase, and detection of highly
10642 variable and significantly correlated genes.")
10643 (license license:gpl3)))
10645 (define-public r-delayedmatrixstats
10647 (name "r-delayedmatrixstats")
10652 (uri (bioconductor-uri "DelayedMatrixStats" version))
10655 "0632ypndblrgzfk8k98rr8c6m2r0zwzf02pzvlrhcp9bj1pvqbrz"))))
10657 `((upstream-name . "DelayedMatrixStats")))
10658 (build-system r-build-system)
10660 `(("r-biocparallel" ,r-biocparallel)
10661 ("r-delayedarray" ,r-delayedarray)
10662 ("r-hdf5array" ,r-hdf5array)
10663 ("r-iranges" ,r-iranges)
10664 ("r-matrix" ,r-matrix)
10665 ("r-matrixstats" ,r-matrixstats)
10666 ("r-s4vectors" ,r-s4vectors)))
10667 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
10668 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
10670 "This package provides a port of the @code{matrixStats} API for use with
10671 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
10672 contains high-performing functions operating on rows and columns of
10673 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
10674 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
10675 are optimized per data type and for subsetted calculations such that both
10676 memory usage and processing time is minimized.")
10677 (license license:expat)))
10679 (define-public r-phangorn
10681 (name "r-phangorn")
10686 (uri (cran-uri "phangorn" version))
10689 "1bv86yfk5r015s7ij6v4zz7bagwrw9m13yfs5853drxb19d5h1m3"))))
10690 (build-system r-build-system)
10693 ("r-fastmatch" ,r-fastmatch)
10694 ("r-igraph" ,r-igraph)
10695 ("r-magrittr" ,r-magrittr)
10696 ("r-matrix" ,r-matrix)
10697 ("r-quadprog" ,r-quadprog)
10698 ("r-rcpp" ,r-rcpp)))
10699 (home-page "https://github.com/KlausVigo/phangorn")
10700 (synopsis "Phylogenetic analysis in R")
10702 "Phangorn is a package for phylogenetic analysis in R. It supports
10703 estimation of phylogenetic trees and networks using Maximum Likelihood,
10704 Maximum Parsimony, distance methods and Hadamard conjugation.")
10705 (license license:gpl2+)))
10707 (define-public r-dropbead
10708 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
10711 (name "r-dropbead")
10712 (version (string-append "0-" revision "." (string-take commit 7)))
10716 (uri (git-reference
10717 (url "https://github.com/rajewsky-lab/dropbead.git")
10719 (file-name (git-file-name name version))
10722 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
10723 (build-system r-build-system)
10725 `(("r-ggplot2" ,r-ggplot2)
10726 ("r-rcolorbrewer" ,r-rcolorbrewer)
10727 ("r-gridextra" ,r-gridextra)
10728 ("r-gplots" ,r-gplots)
10729 ("r-plyr" ,r-plyr)))
10730 (home-page "https://github.com/rajewsky-lab/dropbead")
10731 (synopsis "Basic exploration and analysis of Drop-seq data")
10732 (description "This package offers a quick and straight-forward way to
10733 explore and perform basic analysis of single cell sequencing data coming from
10734 droplet sequencing. It has been particularly tailored for Drop-seq.")
10735 (license license:gpl3))))
10737 (define htslib-for-sambamba
10738 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
10741 (name "htslib-for-sambamba")
10742 (version (string-append "1.3.1-1." (string-take commit 9)))
10746 (uri (git-reference
10747 (url "https://github.com/lomereiter/htslib.git")
10749 (file-name (string-append "htslib-" version "-checkout"))
10752 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
10754 `(("autoconf" ,autoconf)
10755 ("automake" ,automake)
10756 ,@(package-native-inputs htslib))))))
10758 (define-public sambamba
10765 (uri (git-reference
10766 (url "https://github.com/lomereiter/sambamba.git")
10767 (commit (string-append "v" version))))
10768 (file-name (string-append name "-" version "-checkout"))
10771 "0k0cz3qcv98p6cq09zlbgnjsggxcqbcmzxg5zikgcgbr2nfq4lry"))))
10772 (build-system gnu-build-system)
10774 `(#:tests? #f ; there is no test target
10775 #:parallel-build? #f ; not supported
10777 (modify-phases %standard-phases
10778 (delete 'configure)
10779 (add-after 'unpack 'fix-ldc-version
10781 (substitute* "gen_ldc_version_info.py"
10782 (("/usr/bin/env.*") (which "python3")))
10783 (substitute* "Makefile"
10784 ;; We use ldc2 instead of ldmd2 to compile sambamba.
10785 (("\\$\\(shell which ldmd2\\)") (which "ldc2")))
10787 (add-after 'unpack 'place-biod-and-undead
10788 (lambda* (#:key inputs #:allow-other-keys)
10789 (copy-recursively (assoc-ref inputs "biod") "BioD")
10790 (copy-recursively (assoc-ref inputs "undead") "undeaD")
10792 (add-after 'unpack 'unbundle-prerequisites
10794 (substitute* "Makefile"
10795 (("htslib/libhts.a lz4/lib/liblz4.a")
10797 ((" lz4-static htslib-static") ""))
10800 (lambda* (#:key outputs #:allow-other-keys)
10801 (let* ((out (assoc-ref outputs "out"))
10802 (bin (string-append out "/bin")))
10804 (install-file "bin/sambamba" bin)
10811 ,(let ((commit "4f1a7d2fb7ef3dfe962aa357d672f354ebfbe42e"))
10814 (uri (git-reference
10815 (url "https://github.com/biod/BioD.git")
10817 (file-name (string-append "biod-"
10818 (string-take commit 9)
10822 "1k5pdjv1qvi0a3rwd1sfq6zbj37l86i7bf710m4c0y6737lxj426")))))
10824 ,(let ((commit "9be93876982b5f14fcca60832563b3cd767dd84d"))
10827 (uri (git-reference
10828 (url "https://github.com/biod/undeaD.git")
10830 (file-name (string-append "undead-"
10831 (string-take commit 9)
10835 "1xfarj0nqlmi5jd1vmcmm7pabzaf9hxyvk6hp0d6jslb5k9r8r3d")))))))
10838 ("htslib" ,htslib-for-sambamba)))
10839 (home-page "http://lomereiter.github.io/sambamba")
10840 (synopsis "Tools for working with SAM/BAM data")
10841 (description "Sambamba is a high performance modern robust and
10842 fast tool (and library), written in the D programming language, for
10843 working with SAM and BAM files. Current parallelised functionality is
10844 an important subset of samtools functionality, including view, index,
10845 sort, markdup, and depth.")
10846 (license license:gpl2+)))
10848 (define-public ritornello
10850 (name "ritornello")
10854 (uri (git-reference
10855 (url "https://github.com/KlugerLab/Ritornello.git")
10856 (commit (string-append "v" version))))
10857 (file-name (git-file-name name version))
10860 "1xahvq215qld7x1w8vpa5zbrsj6p9crb9shqa2x89sb0aaxa02jk"))))
10861 (build-system gnu-build-system)
10863 `(#:tests? #f ; there are no tests
10865 (modify-phases %standard-phases
10866 (add-after 'unpack 'patch-samtools-references
10867 (lambda* (#:key inputs #:allow-other-keys)
10868 (substitute* '("src/SamStream.h"
10870 (("<sam.h>") "<samtools/sam.h>"))
10872 (delete 'configure)
10874 (lambda* (#:key inputs outputs #:allow-other-keys)
10875 (let* ((out (assoc-ref outputs "out"))
10876 (bin (string-append out "/bin/")))
10878 (install-file "bin/Ritornello" bin)
10881 `(("samtools" ,samtools-0.1)
10885 (home-page "https://github.com/KlugerLab/Ritornello")
10886 (synopsis "Control-free peak caller for ChIP-seq data")
10887 (description "Ritornello is a ChIP-seq peak calling algorithm based on
10888 signal processing that can accurately call binding events without the need to
10889 do a pair total DNA input or IgG control sample. It has been tested for use
10890 with narrow binding events such as transcription factor ChIP-seq.")
10891 (license license:gpl3+)))
10893 (define-public trim-galore
10895 (name "trim-galore")
10900 (uri (git-reference
10901 (url "https://github.com/FelixKrueger/TrimGalore.git")
10903 (file-name (git-file-name name version))
10906 "1y31wbxwkm9xqzr5zv1pk5q418whnmlmgmfyxxpnl12h83m2i9iv"))))
10907 (build-system gnu-build-system)
10909 `(#:tests? #f ; no tests
10911 (modify-phases %standard-phases
10912 (replace 'configure
10914 ;; Trim Galore tries to figure out what version of Python
10915 ;; cutadapt is using by looking at the shebang. Of course that
10916 ;; doesn't work, because cutadapt is wrapped in a shell script.
10917 (substitute* "trim_galore"
10918 (("my \\$python_return.*")
10919 "my $python_return = \"Python 3.999\";\n"))
10922 (add-after 'unpack 'hardcode-tool-references
10923 (lambda* (#:key inputs #:allow-other-keys)
10924 (substitute* "trim_galore"
10925 (("\\$path_to_cutadapt = 'cutadapt'")
10926 (string-append "$path_to_cutadapt = '"
10927 (assoc-ref inputs "cutadapt")
10929 (("\\$compression_path = \"gzip\"")
10930 (string-append "$compression_path = \""
10931 (assoc-ref inputs "gzip")
10934 (string-append "\""
10935 (assoc-ref inputs "gzip")
10938 (string-append "\""
10939 (assoc-ref inputs "pigz")
10943 (lambda* (#:key outputs #:allow-other-keys)
10944 (let ((bin (string-append (assoc-ref outputs "out")
10947 (install-file "trim_galore" bin)
10953 ("cutadapt" ,cutadapt)))
10955 `(("unzip" ,unzip)))
10956 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
10957 (synopsis "Wrapper around Cutadapt and FastQC")
10958 (description "Trim Galore! is a wrapper script to automate quality and
10959 adapter trimming as well as quality control, with some added functionality to
10960 remove biased methylation positions for RRBS sequence files.")
10961 (license license:gpl3+)))
10963 (define-public gess
10969 (uri (string-append "http://compbio.uthscsa.edu/"
10971 "gess-" version ".src.tar.gz"))
10974 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
10975 (build-system gnu-build-system)
10977 `(#:tests? #f ; no tests
10979 (modify-phases %standard-phases
10980 (delete 'configure)
10983 (lambda* (#:key inputs outputs #:allow-other-keys)
10984 (let* ((python (assoc-ref inputs "python"))
10985 (out (assoc-ref outputs "out"))
10986 (bin (string-append out "/bin/"))
10987 (target (string-append
10989 ,(version-major+minor
10990 (package-version python))
10991 "/site-packages/gess/")))
10993 (copy-recursively "." target)
10994 ;; Make GESS.py executable
10995 (chmod (string-append target "GESS.py") #o555)
10996 ;; Add Python shebang to the top and make Matplotlib
10998 (substitute* (string-append target "GESS.py")
10999 (("\"\"\"Description:" line)
11000 (string-append "#!" (which "python") "
11002 matplotlib.use('Agg')
11004 ;; Make sure GESS has all modules in its path
11005 (wrap-program (string-append target "GESS.py")
11006 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
11008 (symlink (string-append target "GESS.py")
11009 (string-append bin "GESS.py"))
11012 `(("python" ,python-2)
11013 ("python2-pysam" ,python2-pysam)
11014 ("python2-scipy" ,python2-scipy)
11015 ("python2-numpy" ,python2-numpy)
11016 ("python2-networkx" ,python2-networkx)
11017 ("python2-biopython" ,python2-biopython)))
11018 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
11019 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11021 "GESS is an implementation of a novel computational method to detect de
11022 novo exon-skipping events directly from raw RNA-seq data without the prior
11023 knowledge of gene annotation information. GESS stands for the graph-based
11024 exon-skipping scanner detection scheme.")
11025 (license license:bsd-3)))
11027 (define-public phylip
11034 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11035 "download/phylip-" version ".tar.gz"))
11038 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11039 (build-system gnu-build-system)
11041 `(#:tests? #f ; no check target
11042 #:make-flags (list "-f" "Makefile.unx" "install")
11043 #:parallel-build? #f ; not supported
11045 (modify-phases %standard-phases
11046 (add-after 'unpack 'enter-dir
11047 (lambda _ (chdir "src") #t))
11048 (delete 'configure)
11050 (lambda* (#:key inputs outputs #:allow-other-keys)
11051 (let ((target (string-append (assoc-ref outputs "out")
11054 (for-each (lambda (file)
11055 (install-file file target))
11056 (find-files "../exe" ".*")))
11058 (home-page "http://evolution.genetics.washington.edu/phylip/")
11059 (synopsis "Tools for inferring phylogenies")
11060 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11061 programs for inferring phylogenies (evolutionary trees).")
11062 (license license:bsd-2)))
11071 (uri (string-append "https://integrativemodeling.org/"
11072 version "/download/imp-" version ".tar.gz"))
11075 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
11076 (build-system cmake-build-system)
11078 `(;; FIXME: Some tests fail because they produce warnings, others fail
11079 ;; because the PYTHONPATH does not include the modeller's directory.
11087 ("python" ,python-2)))
11089 `(("python2-numpy" ,python2-numpy)
11090 ("python2-scipy" ,python2-scipy)
11091 ("python2-pandas" ,python2-pandas)
11092 ("python2-scikit-learn" ,python2-scikit-learn)
11093 ("python2-networkx" ,python2-networkx)))
11094 (home-page "https://integrativemodeling.org")
11095 (synopsis "Integrative modeling platform")
11096 (description "IMP's broad goal is to contribute to a comprehensive
11097 structural characterization of biomolecules ranging in size and complexity
11098 from small peptides to large macromolecular assemblies, by integrating data
11099 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11100 Python toolbox for solving complex modeling problems, and a number of
11101 applications for tackling some common problems in a user-friendly way.")
11102 ;; IMP is largely available under the GNU Lesser GPL; see the file
11103 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11104 ;; available under the GNU GPL (see the file COPYING.GPL).
11105 (license (list license:lgpl2.1+
11108 (define-public tadbit
11114 (uri (git-reference
11115 (url "https://github.com/3DGenomes/TADbit.git")
11116 (commit (string-append "v" version))))
11117 (file-name (git-file-name name version))
11120 "07g3aj648prmsvxp9caz5yl41k0y0647vxh0f5p3w8376mfiljd0"))))
11121 (build-system python-build-system)
11123 `(;; Tests are included and must be run after installation, but
11124 ;; they are incomplete and thus cannot be run.
11128 (modify-phases %standard-phases
11129 (add-after 'unpack 'fix-problems-with-setup.py
11130 (lambda* (#:key outputs #:allow-other-keys)
11131 ;; setup.py opens these files for writing
11132 (chmod "_pytadbit/_version.py" #o664)
11133 (chmod "README.rst" #o664)
11135 ;; Don't attempt to install the bash completions to
11136 ;; the home directory.
11137 (rename-file "extras/.bash_completion"
11139 (substitute* "setup.py"
11140 (("\\(path.expanduser\\('~'\\)")
11141 (string-append "(\""
11142 (assoc-ref outputs "out")
11143 "/etc/bash_completion.d\""))
11144 (("extras/\\.bash_completion")
11148 ;; TODO: add Chimera for visualization
11151 ("python2-scipy" ,python2-scipy)
11152 ("python2-numpy" ,python2-numpy)
11153 ("python2-matplotlib" ,python2-matplotlib)
11154 ("python2-pysam" ,python2-pysam)))
11155 (home-page "https://3dgenomes.github.io/TADbit/")
11156 (synopsis "Analyze, model, and explore 3C-based data")
11158 "TADbit is a complete Python library to deal with all steps to analyze,
11159 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11160 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11161 correct interaction matrices, identify and compare the so-called
11162 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11163 interaction matrices, and finally, extract structural properties from the
11164 models. TADbit is complemented by TADkit for visualizing 3D models.")
11165 (license license:gpl3+)))
11167 (define-public kentutils
11170 ;; 302.1.0 is out, but the only difference is the inclusion of
11171 ;; pre-built binaries.
11172 (version "302.0.0")
11176 (uri (git-reference
11177 (url "https://github.com/ENCODE-DCC/kentUtils.git")
11178 (commit (string-append "v" version))))
11179 (file-name (git-file-name name version))
11182 "0n1wbyjpzii2b9qhyp9r1q76j623cggpg3y8fmw78ld3z4y7ivha"))
11183 (modules '((guix build utils)
11188 ;; Only the contents of the specified directories are free
11189 ;; for all uses, so we remove the rest. "hg/autoSql" and
11190 ;; "hg/autoXml" are nominally free, but they depend on a
11191 ;; library that is built from the sources in "hg/lib",
11192 ;; which is nonfree.
11193 (let ((free (list "." ".."
11194 "utils" "lib" "inc" "tagStorm"
11195 "parasol" "htslib"))
11196 (directory? (lambda (file)
11197 (eq? 'directory (stat:type (stat file))))))
11198 (for-each (lambda (file)
11199 (and (directory? file)
11200 (delete-file-recursively file)))
11201 (map (cut string-append "src/" <>)
11204 (not (member file free)))))))
11205 ;; Only make the utils target, not the userApps target,
11206 ;; because that requires libraries we won't build.
11207 (substitute* "Makefile"
11208 ((" userApps") " utils"))
11209 ;; Only build libraries that are free.
11210 (substitute* "src/makefile"
11211 (("DIRS =.*") "DIRS =\n")
11212 (("cd jkOwnLib.*") "")
11215 (substitute* "src/utils/makefile"
11216 ;; These tools depend on "jkhgap.a", which is part of the
11217 ;; nonfree "src/hg/lib" directory.
11218 (("raSqlQuery") "")
11219 (("pslLiftSubrangeBlat") "")
11221 ;; Do not build UCSC tools, which may require nonfree
11223 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11225 (build-system gnu-build-system)
11227 `( ;; There is no global test target and the test target for
11228 ;; individual tools depends on input files that are not
11232 (modify-phases %standard-phases
11233 (add-after 'unpack 'fix-permissions
11234 (lambda _ (make-file-writable "src/inc/localEnvironment.mk") #t))
11235 (add-after 'unpack 'fix-paths
11237 (substitute* "Makefile"
11238 (("/bin/echo") (which "echo")))
11240 (add-after 'unpack 'prepare-samtabix
11241 (lambda* (#:key inputs #:allow-other-keys)
11242 (copy-recursively (assoc-ref inputs "samtabix")
11245 (delete 'configure)
11247 (lambda* (#:key outputs #:allow-other-keys)
11248 (let ((bin (string-append (assoc-ref outputs "out")
11250 (copy-recursively "bin" bin))
11256 (uri (git-reference
11257 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11258 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11261 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11267 ("mariadb" ,mariadb)
11268 ("openssl" ,openssl)))
11269 (home-page "http://genome.cse.ucsc.edu/index.html")
11270 (synopsis "Assorted bioinformatics utilities")
11271 (description "This package provides the kentUtils, a selection of
11272 bioinformatics utilities used in combination with the UCSC genome
11274 ;; Only a subset of the sources are released under a non-copyleft
11275 ;; free software license. All other sources are removed in a
11276 ;; snippet. See this bug report for an explanation of how the
11277 ;; license statements apply:
11278 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11279 (license (license:non-copyleft
11280 "http://genome.ucsc.edu/license/"
11281 "The contents of this package are free for all uses."))))
11283 (define-public f-seq
11284 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11288 (version (string-append "1.1-" revision "." (string-take commit 7)))
11291 (uri (git-reference
11292 (url "https://github.com/aboyle/F-seq.git")
11294 (file-name (string-append name "-" version))
11297 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11298 (modules '((guix build utils)))
11299 ;; Remove bundled Java library archives.
11302 (for-each delete-file (find-files "lib" ".*"))
11304 (build-system ant-build-system)
11306 `(#:tests? #f ; no tests included
11308 (modify-phases %standard-phases
11310 (lambda* (#:key inputs outputs #:allow-other-keys)
11311 (let* ((target (assoc-ref outputs "out"))
11312 (bin (string-append target "/bin"))
11313 (doc (string-append target "/share/doc/f-seq"))
11314 (lib (string-append target "/lib")))
11317 (substitute* "bin/linux/fseq"
11318 (("java") (which "java"))
11319 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11320 (string-append (assoc-ref inputs "java-commons-cli")
11321 "/share/java/commons-cli.jar"))
11323 (string-append "REALDIR=" bin "\n")))
11324 (install-file "README.txt" doc)
11325 (install-file "bin/linux/fseq" bin)
11326 (install-file "build~/fseq.jar" lib)
11327 (copy-recursively "lib" lib)
11331 ("java-commons-cli" ,java-commons-cli)))
11332 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11333 (synopsis "Feature density estimator for high-throughput sequence tags")
11335 "F-Seq is a software package that generates a continuous tag sequence
11336 density estimation allowing identification of biologically meaningful sites
11337 such as transcription factor binding sites (ChIP-seq) or regions of open
11338 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11340 (license license:gpl3+))))
11342 (define-public bismark
11349 (uri (git-reference
11350 (url "https://github.com/FelixKrueger/Bismark.git")
11352 (file-name (string-append name "-" version "-checkout"))
11355 "0xchm3rgilj6vfjnyzfzzymfd7djr64sbrmrvs3njbwi66jqbzw9"))))
11356 (build-system perl-build-system)
11358 `(#:tests? #f ; there are no tests
11359 #:modules ((guix build utils)
11362 (guix build perl-build-system))
11364 (modify-phases %standard-phases
11365 ;; The bundled plotly.js is minified.
11366 (add-after 'unpack 'replace-plotly.js
11367 (lambda* (#:key inputs #:allow-other-keys)
11368 (let* ((file (assoc-ref inputs "plotly.js"))
11369 (installed "plotly/plotly.js"))
11370 (let ((minified (open-pipe* OPEN_READ "uglify-js" file)))
11371 (call-with-output-file installed
11372 (cut dump-port minified <>))))
11374 (delete 'configure)
11377 (lambda* (#:key inputs outputs #:allow-other-keys)
11378 (let* ((out (assoc-ref outputs "out"))
11379 (bin (string-append out "/bin"))
11380 (share (string-append out "/share/bismark"))
11381 (docdir (string-append out "/share/doc/bismark"))
11382 (docs '("Docs/Bismark_User_Guide.html"))
11383 (scripts '("bismark"
11384 "bismark_genome_preparation"
11385 "bismark_methylation_extractor"
11388 "coverage2cytosine"
11389 "deduplicate_bismark"
11390 "filter_non_conversion"
11393 "NOMe_filtering")))
11394 (substitute* "bismark2report"
11395 (("\\$RealBin/plotly")
11396 (string-append share "/plotly")))
11400 (for-each (lambda (file) (install-file file bin))
11402 (for-each (lambda (file) (install-file file docdir))
11404 (copy-recursively "Docs/Images" (string-append docdir "/Images"))
11405 (copy-recursively "plotly"
11406 (string-append share "/plotly"))
11408 ;; Fix references to gunzip
11409 (substitute* (map (lambda (file)
11410 (string-append bin "/" file))
11413 (string-append "\"" (assoc-ref inputs "gzip")
11414 "/bin/gunzip -c")))
11418 ("perl-carp" ,perl-carp)
11419 ("perl-getopt-long" ,perl-getopt-long)))
11424 (uri (string-append "https://raw.githubusercontent.com/plotly/plotly.js/"
11425 "v1.39.4/dist/plotly.js"))
11427 (base32 "138mwsr4nf5qif4mrxx286mpnagxd1xwl6k8aidrjgknaqg88zyr"))))
11428 ("uglify-js" ,uglify-js)))
11429 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11430 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11431 (description "Bismark is a program to map bisulfite treated sequencing
11432 reads to a genome of interest and perform methylation calls in a single step.
11433 The output can be easily imported into a genome viewer, such as SeqMonk, and
11434 enables a researcher to analyse the methylation levels of their samples
11435 straight away. Its main features are:
11438 @item Bisulfite mapping and methylation calling in one single step
11439 @item Supports single-end and paired-end read alignments
11440 @item Supports ungapped and gapped alignments
11441 @item Alignment seed length, number of mismatches etc are adjustable
11442 @item Output discriminates between cytosine methylation in CpG, CHG
11445 (license license:gpl3+)))
11447 (define-public paml
11453 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11454 "paml" version ".tgz"))
11457 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11458 (modules '((guix build utils)))
11459 ;; Remove Windows binaries
11462 (for-each delete-file (find-files "." "\\.exe$"))
11464 (build-system gnu-build-system)
11466 `(#:tests? #f ; there are no tests
11467 #:make-flags '("CC=gcc")
11469 (modify-phases %standard-phases
11470 (replace 'configure
11472 (substitute* "src/BFdriver.c"
11473 (("/bin/bash") (which "bash")))
11477 (lambda* (#:key outputs #:allow-other-keys)
11478 (let ((tools '("baseml" "basemlg" "codeml"
11479 "pamp" "evolver" "yn00" "chi2"))
11480 (bin (string-append (assoc-ref outputs "out") "/bin"))
11481 (docdir (string-append (assoc-ref outputs "out")
11482 "/share/doc/paml")))
11484 (for-each (lambda (file) (install-file file bin)) tools)
11485 (copy-recursively "../doc" docdir)
11487 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11488 (synopsis "Phylogentic analysis by maximum likelihood")
11489 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11490 contains a few programs for model fitting and phylogenetic tree reconstruction
11491 using nucleotide or amino-acid sequence data.")
11493 (license license:gpl3)))
11495 (define-public kallisto
11501 (uri (git-reference
11502 (url "https://github.com/pachterlab/kallisto.git")
11503 (commit (string-append "v" version))))
11504 (file-name (git-file-name name version))
11507 "0nj382jiywqnpgvyhichajpkkh5r0bapn43f4dx40zdaq5v4m40m"))))
11508 (build-system cmake-build-system)
11510 `(#:tests? #f ; no "check" target
11512 (modify-phases %standard-phases
11513 (add-after 'unpack 'do-not-use-bundled-htslib
11515 (substitute* "CMakeLists.txt"
11516 (("^ExternalProject_Add" m)
11517 (string-append "if (NEVER)\n" m))
11519 (string-append ")\nendif(NEVER)"))
11520 (("include_directories\\(\\$\\{htslib_PREFIX.*" m)
11521 (string-append "# " m)))
11522 (substitute* "src/CMakeLists.txt"
11523 (("target_link_libraries\\(kallisto kallisto_core pthread \
11524 \\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/../ext/htslib/libhts.a\\)")
11525 "target_link_libraries(kallisto kallisto_core pthread hts)")
11526 (("include_directories\\(\\.\\./ext/htslib\\)") ""))
11532 (home-page "http://pachterlab.github.io/kallisto/")
11533 (synopsis "Near-optimal RNA-Seq quantification")
11535 "Kallisto is a program for quantifying abundances of transcripts from
11536 RNA-Seq data, or more generally of target sequences using high-throughput
11537 sequencing reads. It is based on the novel idea of pseudoalignment for
11538 rapidly determining the compatibility of reads with targets, without the need
11539 for alignment. Pseudoalignment of reads preserves the key information needed
11540 for quantification, and kallisto is therefore not only fast, but also as
11541 accurate as existing quantification tools.")
11542 (license license:bsd-2)))
11544 (define-public libgff
11550 (uri (git-reference
11551 (url "https://github.com/Kingsford-Group/libgff.git")
11552 (commit (string-append "v" version))))
11553 (file-name (git-file-name name version))
11556 "0n6vfjnq7a2mianipscbshrvbncss8z4zkgkbjw754p9043nfkps"))))
11557 (build-system cmake-build-system)
11558 (arguments `(#:tests? #f)) ; no tests included
11559 (home-page "https://github.com/Kingsford-Group/libgff")
11560 (synopsis "Parser library for reading/writing GFF files")
11561 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11562 code that is used in the Cufflinks codebase. The goal of this library is to
11563 provide this functionality without the necessity of drawing in a heavy-weight
11564 dependency like SeqAn.")
11565 (license (license:x11-style "https://www.boost.org/LICENSE_1_0.txt"))))
11567 (define-public libdivsufsort
11569 (name "libdivsufsort")
11573 (uri (git-reference
11574 (url "https://github.com/y-256/libdivsufsort.git")
11576 (file-name (git-file-name name version))
11579 "0fgdz9fzihlvjjrxy01md1bv9vh12rkgkwbm90b1hj5xpbaqp7z2"))))
11580 (build-system cmake-build-system)
11582 '(#:tests? #f ; there are no tests
11584 ;; Needed for rapmap and sailfish.
11585 '("-DBUILD_DIVSUFSORT64=ON")))
11586 (home-page "https://github.com/y-256/libdivsufsort")
11587 (synopsis "Lightweight suffix-sorting library")
11588 (description "libdivsufsort is a software library that implements a
11589 lightweight suffix array construction algorithm. This library provides a
11590 simple and an efficient C API to construct a suffix array and a
11591 Burrows-Wheeler transformed string from a given string over a constant-size
11592 alphabet. The algorithm runs in O(n log n) worst-case time using only 5n+O(1)
11593 bytes of memory space, where n is the length of the string.")
11594 (license license:expat)))
11596 (define-public sailfish
11602 (uri (git-reference
11603 (url "https://github.com/kingsfordgroup/sailfish.git")
11604 (commit (string-append "v" version))))
11605 (file-name (git-file-name name version))
11608 "1amcc5hqvsl42hg4x19bi9vy47cl874s0lw1fmi0hwsdk9i8c03v"))
11609 (modules '((guix build utils)))
11612 ;; Delete bundled headers for eigen3.
11613 (delete-file-recursively "include/eigen3/")
11615 (build-system cmake-build-system)
11617 `(#:configure-flags
11618 (list (string-append "-DBOOST_INCLUDEDIR="
11619 (assoc-ref %build-inputs "boost")
11621 (string-append "-DBOOST_LIBRARYDIR="
11622 (assoc-ref %build-inputs "boost")
11624 (string-append "-DBoost_LIBRARIES="
11625 "-lboost_iostreams "
11626 "-lboost_filesystem "
11631 "-lboost_program_options")
11632 "-DBoost_FOUND=TRUE"
11633 ;; Don't download RapMap---we already have it!
11634 "-DFETCHED_RAPMAP=1")
11635 ;; Tests must be run after installation and the location of the test
11636 ;; data file must be overridden. But the tests fail. It looks like
11637 ;; they are not really meant to be run.
11640 (modify-phases %standard-phases
11641 ;; Boost cannot be found, even though it's right there.
11642 (add-after 'unpack 'do-not-look-for-boost
11643 (lambda* (#:key inputs #:allow-other-keys)
11644 (substitute* "CMakeLists.txt"
11645 (("find_package\\(Boost 1\\.53\\.0") "#"))
11647 (add-after 'unpack 'do-not-assign-to-macro
11649 (substitute* "include/spdlog/details/format.cc"
11650 (("const unsigned CHAR_WIDTH = 1;") ""))
11652 (add-after 'unpack 'prepare-rapmap
11653 (lambda* (#:key inputs #:allow-other-keys)
11654 (let ((src "external/install/src/rapmap/")
11655 (include "external/install/include/rapmap/")
11656 (rapmap (assoc-ref inputs "rapmap")))
11657 (mkdir-p "/tmp/rapmap")
11659 (assoc-ref inputs "rapmap")
11661 "--strip-components=1")
11664 (for-each (lambda (file)
11665 (install-file file src))
11666 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
11667 (copy-recursively "/tmp/rapmap/include" include))
11669 (add-after 'unpack 'use-system-libraries
11670 (lambda* (#:key inputs #:allow-other-keys)
11671 (substitute* '("src/SailfishIndexer.cpp"
11672 "src/SailfishUtils.cpp"
11673 "src/SailfishQuantify.cpp"
11674 "src/FASTAParser.cpp"
11676 "include/SailfishUtils.hpp"
11677 "include/SailfishIndex.hpp"
11678 "include/CollapsedEMOptimizer.hpp"
11679 "src/CollapsedEMOptimizer.cpp")
11680 (("#include \"jellyfish/config.h\"") ""))
11681 (substitute* "src/CMakeLists.txt"
11682 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11683 (string-append (assoc-ref inputs "jellyfish")
11684 "/include/jellyfish-" ,(package-version jellyfish)))
11685 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11686 (string-append (assoc-ref inputs "jellyfish")
11687 "/lib/libjellyfish-2.0.a"))
11688 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11689 (string-append (assoc-ref inputs "libdivsufsort")
11690 "/lib/libdivsufsort.so"))
11691 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11692 (string-append (assoc-ref inputs "libdivsufsort")
11693 "/lib/libdivsufsort64.so")))
11694 (substitute* "CMakeLists.txt"
11695 ;; Don't prefer static libs
11696 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11697 (("find_package\\(Jellyfish.*") "")
11698 (("ExternalProject_Add\\(libjellyfish") "message(")
11699 (("ExternalProject_Add\\(libgff") "message(")
11700 (("ExternalProject_Add\\(libsparsehash") "message(")
11701 (("ExternalProject_Add\\(libdivsufsort") "message("))
11703 ;; Ensure that Eigen headers can be found
11704 (setenv "CPLUS_INCLUDE_PATH"
11705 (string-append (getenv "CPLUS_INCLUDE_PATH")
11707 (assoc-ref inputs "eigen")
11708 "/include/eigen3"))
11713 ("jemalloc" ,jemalloc)
11714 ("jellyfish" ,jellyfish)
11715 ("sparsehash" ,sparsehash)
11718 (uri (git-reference
11719 (url "https://github.com/COMBINE-lab/RapMap.git")
11720 (commit (string-append "sf-v" version))))
11721 (file-name (string-append "rapmap-sf-v" version "-checkout"))
11724 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
11725 (modules '((guix build utils)))
11726 ;; These files are expected to be excluded.
11728 '(begin (delete-file-recursively "include/spdlog")
11729 (for-each delete-file '("include/xxhash.h"
11732 ("libdivsufsort" ,libdivsufsort)
11737 `(("pkg-config" ,pkg-config)))
11738 (home-page "http://www.cs.cmu.edu/~ckingsf/software/sailfish")
11739 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
11740 (description "Sailfish is a tool for genomic transcript quantification
11741 from RNA-seq data. It requires a set of target transcripts (either from a
11742 reference or de-novo assembly) to quantify. All you need to run sailfish is a
11743 fasta file containing your reference transcripts and a (set of) fasta/fastq
11744 file(s) containing your reads.")
11745 (license license:gpl3+)))
11747 (define libstadenio-for-salmon
11749 (name "libstadenio")
11753 (uri (git-reference
11754 (url "https://github.com/COMBINE-lab/staden-io_lib.git")
11755 (commit (string-append "v" version))))
11756 (file-name (string-append name "-" version "-checkout"))
11759 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
11760 (build-system gnu-build-system)
11761 (arguments '(#:parallel-tests? #f)) ; not supported
11765 `(("perl" ,perl))) ; for tests
11766 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
11767 (synopsis "General purpose trace and experiment file library")
11768 (description "This package provides a library of file reading and writing
11769 code to provide a general purpose Trace file (and Experiment File) reading
11772 The following file formats are supported:
11775 @item SCF trace files
11776 @item ABI trace files
11777 @item ALF trace files
11778 @item ZTR trace files
11779 @item SFF trace archives
11780 @item SRF trace archives
11781 @item Experiment files
11782 @item Plain text files
11783 @item SAM/BAM sequence files
11784 @item CRAM sequence files
11786 (license license:bsd-3)))
11788 (define-public salmon
11794 (uri (git-reference
11795 (url "https://github.com/COMBINE-lab/salmon.git")
11796 (commit (string-append "v" version))))
11797 (file-name (git-file-name name version))
11800 "1i2z4aivicmiixdz9bxalp7vmfzi3k92fxa63iqa8kgvfw5a4aq5"))
11801 (modules '((guix build utils)))
11804 ;; Delete bundled headers for eigen3.
11805 (delete-file-recursively "include/eigen3/")
11807 (build-system cmake-build-system)
11809 `(#:configure-flags
11810 (list (string-append "-DBOOST_INCLUDEDIR="
11811 (assoc-ref %build-inputs "boost")
11813 (string-append "-DBOOST_LIBRARYDIR="
11814 (assoc-ref %build-inputs "boost")
11816 (string-append "-DBoost_LIBRARIES="
11817 "-lboost_iostreams "
11818 "-lboost_filesystem "
11823 "-lboost_program_options")
11824 "-DBoost_FOUND=TRUE"
11825 "-DTBB_LIBRARIES=tbb tbbmalloc"
11826 ;; Don't download RapMap---we already have it!
11827 "-DFETCHED_RAPMAP=1")
11829 (modify-phases %standard-phases
11830 ;; Boost cannot be found, even though it's right there.
11831 (add-after 'unpack 'do-not-look-for-boost
11832 (lambda* (#:key inputs #:allow-other-keys)
11833 (substitute* "CMakeLists.txt"
11834 (("find_package\\(Boost 1\\.59\\.0") "#"))
11836 (add-after 'unpack 'do-not-phone-home
11838 (substitute* "src/Salmon.cpp"
11839 (("getVersionMessage\\(\\)") "\"\""))
11841 (add-after 'unpack 'prepare-rapmap
11842 (lambda* (#:key inputs #:allow-other-keys)
11843 (let ((src "external/install/src/rapmap/")
11844 (include "external/install/include/rapmap/")
11845 (rapmap (assoc-ref inputs "rapmap")))
11848 (copy-recursively (string-append rapmap "/src") src)
11849 (copy-recursively (string-append rapmap "/include") include)
11850 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
11851 "external/install/include/rapmap/FastxParser.hpp"
11852 "external/install/include/rapmap/concurrentqueue.h"
11853 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
11854 "external/install/src/rapmap/FastxParser.cpp"
11855 "external/install/src/rapmap/xxhash.c"))
11856 (delete-file-recursively "external/install/include/rapmap/spdlog"))
11858 (add-after 'unpack 'use-system-libraries
11859 (lambda* (#:key inputs #:allow-other-keys)
11860 (substitute* "CMakeLists.txt"
11861 ;; Don't prefer static libs
11862 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11863 (("set\\(TBB_LIBRARIES") "message(")
11864 ;; Don't download anything
11865 (("DOWNLOAD_COMMAND") "DOWNLOAD_COMMAND echo")
11866 (("externalproject_add\\(libcereal") "message(")
11867 (("externalproject_add\\(libgff") "message(")
11868 (("externalproject_add\\(libtbb") "message(")
11869 (("externalproject_add\\(libdivsufsort") "message(")
11870 (("externalproject_add\\(libstadenio") "message(")
11871 (("externalproject_add_step\\(") "message("))
11872 (substitute* "src/CMakeLists.txt"
11873 (("add_dependencies") "#")
11874 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
11875 (string-append (assoc-ref inputs "libstadenio-for-salmon")
11876 "/lib/libstaden-read.so"))
11877 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11878 (string-append (assoc-ref inputs "libdivsufsort")
11879 "/lib/libdivsufsort.so"))
11880 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11881 (string-append (assoc-ref inputs "libdivsufsort")
11882 "/lib/libdivsufsort64.so"))
11883 (("lib/libdivsufsort.a") "/lib/libdivsufsort.so"))
11885 ;; Ensure that all headers can be found
11886 (setenv "CPLUS_INCLUDE_PATH"
11887 (string-append (getenv "CPLUS_INCLUDE_PATH")
11889 (assoc-ref inputs "eigen")
11890 "/include/eigen3"))
11892 (string-append (assoc-ref inputs "eigen")
11893 "/include/eigen3"))
11895 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
11896 ;; run. It only exists after the install phase.
11897 (add-after 'unpack 'fix-tests
11899 (substitute* "src/CMakeLists.txt"
11900 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
11901 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
11910 (uri (git-reference
11911 (url "https://github.com/COMBINE-lab/RapMap.git")
11912 (commit (string-append "salmon-v" version))))
11913 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
11916 "1biplxf0csc7a8h1wf219b0vmjkvw6wk2zylhdklb577kgmihdms"))))
11917 ("jemalloc" ,jemalloc)
11920 ("libdivsufsort" ,libdivsufsort)
11921 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
11925 `(("pkg-config" ,pkg-config)))
11926 (home-page "https://github.com/COMBINE-lab/salmon")
11927 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
11928 (description "Salmon is a program to produce highly-accurate,
11929 transcript-level quantification estimates from RNA-seq data. Salmon achieves
11930 its accuracy and speed via a number of different innovations, including the
11931 use of lightweight alignments (accurate but fast-to-compute proxies for
11932 traditional read alignments) and massively-parallel stochastic collapsed
11933 variational inference.")
11934 (license license:gpl3+)))
11936 (define-public python-loompy
11938 (name "python-loompy")
11940 ;; The tarball on Pypi does not include the tests.
11943 (uri (git-reference
11944 (url "https://github.com/linnarsson-lab/loompy.git")
11946 (file-name (git-file-name name version))
11949 "12a5kjgiikapv93wahfw0frszx1lblnppyz3vs5gy8fgmgngra07"))))
11950 (build-system python-build-system)
11953 (modify-phases %standard-phases
11956 (setenv "PYTHONPATH"
11957 (string-append (getcwd) ":"
11958 (getenv "PYTHONPATH")))
11959 (invoke "pytest" "tests")
11962 `(("python-h5py" ,python-h5py)
11963 ("python-numpy" ,python-numpy)
11964 ("python-pandas" ,python-pandas)
11965 ("python-scipy" ,python-scipy)))
11967 `(("python-pytest" ,python-pytest)))
11968 (home-page "https://github.com/linnarsson-lab/loompy")
11969 (synopsis "Work with .loom files for single-cell RNA-seq data")
11970 (description "The loom file format is an efficient format for very large
11971 omics datasets, consisting of a main matrix, optional additional layers, a
11972 variable number of row and column annotations. Loom also supports sparse
11973 graphs. This library makes it easy to work with @file{.loom} files for
11974 single-cell RNA-seq data.")
11975 (license license:bsd-3)))
11977 ;; pigx-scrnaseq does not work with the latest version of loompy.
11978 (define-public python-loompy-for-pigx-scrnaseq
11979 (package (inherit python-loompy)
11980 (name "python-loompy")
11984 (uri (git-reference
11985 (url "https://github.com/linnarsson-lab/loompy.git")
11986 (commit (string-append "v" version))))
11987 (file-name (git-file-name name version))
11990 "0pjyl532pl8sbv71yci6h0agchn0naw2qjcwj50n6afrsahbsag3"))))
11992 (arguments '(#:tests? #f))))
11994 ;; We cannot use the latest commit because it requires Java 9.
11995 (define-public java-forester
11996 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
11999 (name "java-forester")
12000 (version (string-append "0-" revision "." (string-take commit 7)))
12003 (uri (git-reference
12004 (url "https://github.com/cmzmasek/forester.git")
12006 (file-name (string-append name "-" version "-checkout"))
12009 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12010 (modules '((guix build utils)))
12013 ;; Delete bundled jars and pre-built classes
12014 (delete-file-recursively "forester/java/resources")
12015 (delete-file-recursively "forester/java/classes")
12016 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12017 ;; Delete bundled applications
12018 (delete-file-recursively "forester_applications")
12020 (build-system ant-build-system)
12022 `(#:tests? #f ; there are none
12024 #:modules ((guix build ant-build-system)
12026 (guix build java-utils)
12030 (modify-phases %standard-phases
12031 (add-after 'unpack 'chdir
12032 (lambda _ (chdir "forester/java") #t))
12033 (add-after 'chdir 'fix-dependencies
12035 (chmod "build.xml" #o664)
12036 (call-with-output-file "build.xml.new"
12040 (with-input-from-file "build.xml"
12041 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12042 `(;; Remove all unjar tags to avoid repacking classes.
12043 (unjar . ,(lambda _ '()))
12044 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12045 (*text* . ,(lambda (_ txt) txt))))
12047 (rename-file "build.xml.new" "build.xml")
12049 ;; FIXME: itext is difficult to package as it depends on a few
12050 ;; unpackaged libraries.
12051 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12053 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12054 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12055 (("pdf_written_to = PdfExporter.*")
12056 "throw new IOException(\"PDF export is not available.\");"))
12058 ;; There is no install target
12059 (replace 'install (install-jars ".")))))
12061 `(("java-commons-codec" ,java-commons-codec)
12062 ("java-openchart2" ,java-openchart2)))
12063 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12064 (synopsis "Phylogenomics libraries for Java")
12065 (description "Forester is a collection of Java libraries for
12066 phylogenomics and evolutionary biology research. It includes support for
12067 reading, writing, and exporting phylogenetic trees.")
12068 (license license:lgpl2.1+))))
12070 (define-public java-forester-1.005
12072 (name "java-forester")
12076 (uri (string-append "http://search.maven.org/remotecontent?"
12077 "filepath=org/biojava/thirdparty/forester/"
12078 version "/forester-" version "-sources.jar"))
12079 (file-name (string-append name "-" version ".jar"))
12082 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12083 (build-system ant-build-system)
12085 `(#:tests? #f ; there are none
12087 #:modules ((guix build ant-build-system)
12089 (guix build java-utils)
12093 (modify-phases %standard-phases
12094 (add-after 'unpack 'fix-dependencies
12095 (lambda* (#:key inputs #:allow-other-keys)
12096 (call-with-output-file "build.xml"
12100 (with-input-from-file "src/build.xml"
12101 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12102 `(;; Remove all unjar tags to avoid repacking classes.
12103 (unjar . ,(lambda _ '()))
12104 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12105 (*text* . ,(lambda (_ txt) txt))))
12107 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12108 "synth_look_and_feel_1.xml")
12109 (copy-file (assoc-ref inputs "phyloxml.xsd")
12111 (substitute* "build.xml"
12112 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12113 "synth_look_and_feel_1.xml")
12114 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12117 ;; FIXME: itext is difficult to package as it depends on a few
12118 ;; unpackaged libraries.
12119 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12121 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12122 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12123 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12124 (("pdf_written_to = PdfExporter.*")
12125 "throw new IOException(\"PDF export is not available.\"); /*")
12126 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12127 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12129 (add-after 'unpack 'delete-pre-built-classes
12130 (lambda _ (delete-file-recursively "src/classes") #t))
12131 ;; There is no install target
12132 (replace 'install (install-jars ".")))))
12134 `(("java-commons-codec" ,java-commons-codec)
12135 ("java-openchart2" ,java-openchart2)))
12136 ;; The source archive does not contain the resources.
12141 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12142 "b61cc2dcede0bede317db362472333115756b8c6/"
12143 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12144 (file-name (string-append name "-phyloxml-" version ".xsd"))
12147 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12148 ("synth_look_and_feel_1.xml"
12151 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12152 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12153 "forester/java/classes/resources/synth_look_and_feel_1.xml"))
12154 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12157 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12158 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12159 (synopsis "Phylogenomics libraries for Java")
12160 (description "Forester is a collection of Java libraries for
12161 phylogenomics and evolutionary biology research. It includes support for
12162 reading, writing, and exporting phylogenetic trees.")
12163 (license license:lgpl2.1+)))
12165 (define-public java-biojava-core
12167 (name "java-biojava-core")
12171 (uri (git-reference
12172 (url "https://github.com/biojava/biojava")
12173 (commit (string-append "biojava-" version))))
12174 (file-name (string-append name "-" version "-checkout"))
12177 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12178 (build-system ant-build-system)
12181 #:jar-name "biojava-core.jar"
12182 #:source-dir "biojava-core/src/main/java/"
12183 #:test-dir "biojava-core/src/test"
12184 ;; These tests seem to require internet access.
12185 #:test-exclude (list "**/SearchIOTest.java"
12186 "**/BlastXMLParserTest.java"
12187 "**/GenbankCookbookTest.java"
12188 "**/GenbankProxySequenceReaderTest.java")
12190 (modify-phases %standard-phases
12191 (add-before 'build 'copy-resources
12193 (copy-recursively "biojava-core/src/main/resources"
12196 (add-before 'check 'copy-test-resources
12198 (copy-recursively "biojava-core/src/test/resources"
12199 "build/test-classes")
12202 `(("java-log4j-api" ,java-log4j-api)
12203 ("java-log4j-core" ,java-log4j-core)
12204 ("java-slf4j-api" ,java-slf4j-api)
12205 ("java-slf4j-simple" ,java-slf4j-simple)))
12207 `(("java-junit" ,java-junit)
12208 ("java-hamcrest-core" ,java-hamcrest-core)))
12209 (home-page "http://biojava.org")
12210 (synopsis "Core libraries of Java framework for processing biological data")
12211 (description "BioJava is a project dedicated to providing a Java framework
12212 for processing biological data. It provides analytical and statistical
12213 routines, parsers for common file formats, reference implementations of
12214 popular algorithms, and allows the manipulation of sequences and 3D
12215 structures. The goal of the biojava project is to facilitate rapid
12216 application development for bioinformatics.
12218 This package provides the core libraries.")
12219 (license license:lgpl2.1+)))
12221 (define-public java-biojava-phylo
12222 (package (inherit java-biojava-core)
12223 (name "java-biojava-phylo")
12224 (build-system ant-build-system)
12227 #:jar-name "biojava-phylo.jar"
12228 #:source-dir "biojava-phylo/src/main/java/"
12229 #:test-dir "biojava-phylo/src/test"
12231 (modify-phases %standard-phases
12232 (add-before 'build 'copy-resources
12234 (copy-recursively "biojava-phylo/src/main/resources"
12237 (add-before 'check 'copy-test-resources
12239 (copy-recursively "biojava-phylo/src/test/resources"
12240 "build/test-classes")
12243 `(("java-log4j-api" ,java-log4j-api)
12244 ("java-log4j-core" ,java-log4j-core)
12245 ("java-slf4j-api" ,java-slf4j-api)
12246 ("java-slf4j-simple" ,java-slf4j-simple)
12247 ("java-biojava-core" ,java-biojava-core)
12248 ("java-forester" ,java-forester)))
12250 `(("java-junit" ,java-junit)
12251 ("java-hamcrest-core" ,java-hamcrest-core)))
12252 (home-page "http://biojava.org")
12253 (synopsis "Biojava interface to the forester phylogenomics library")
12254 (description "The phylo module provides a biojava interface layer to the
12255 forester phylogenomics library for constructing phylogenetic trees.")))
12257 (define-public java-biojava-alignment
12258 (package (inherit java-biojava-core)
12259 (name "java-biojava-alignment")
12260 (build-system ant-build-system)
12263 #:jar-name "biojava-alignment.jar"
12264 #:source-dir "biojava-alignment/src/main/java/"
12265 #:test-dir "biojava-alignment/src/test"
12267 (modify-phases %standard-phases
12268 (add-before 'build 'copy-resources
12270 (copy-recursively "biojava-alignment/src/main/resources"
12273 (add-before 'check 'copy-test-resources
12275 (copy-recursively "biojava-alignment/src/test/resources"
12276 "build/test-classes")
12279 `(("java-log4j-api" ,java-log4j-api)
12280 ("java-log4j-core" ,java-log4j-core)
12281 ("java-slf4j-api" ,java-slf4j-api)
12282 ("java-slf4j-simple" ,java-slf4j-simple)
12283 ("java-biojava-core" ,java-biojava-core)
12284 ("java-biojava-phylo" ,java-biojava-phylo)
12285 ("java-forester" ,java-forester)))
12287 `(("java-junit" ,java-junit)
12288 ("java-hamcrest-core" ,java-hamcrest-core)))
12289 (home-page "http://biojava.org")
12290 (synopsis "Biojava API for genetic sequence alignment")
12291 (description "The alignment module of BioJava provides an API that
12295 @item implementations of dynamic programming algorithms for sequence
12297 @item reading and writing of popular alignment file formats;
12298 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12301 (define-public java-biojava-core-4.0
12302 (package (inherit java-biojava-core)
12303 (name "java-biojava-core")
12307 (uri (git-reference
12308 (url "https://github.com/biojava/biojava")
12309 (commit (string-append "biojava-" version))))
12310 (file-name (string-append name "-" version "-checkout"))
12313 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12315 (define-public java-biojava-phylo-4.0
12316 (package (inherit java-biojava-core-4.0)
12317 (name "java-biojava-phylo")
12318 (build-system ant-build-system)
12321 #:jar-name "biojava-phylo.jar"
12322 #:source-dir "biojava-phylo/src/main/java/"
12323 #:test-dir "biojava-phylo/src/test"
12325 (modify-phases %standard-phases
12326 (add-before 'build 'copy-resources
12328 (copy-recursively "biojava-phylo/src/main/resources"
12331 (add-before 'check 'copy-test-resources
12333 (copy-recursively "biojava-phylo/src/test/resources"
12334 "build/test-classes")
12337 `(("java-log4j-api" ,java-log4j-api)
12338 ("java-log4j-core" ,java-log4j-core)
12339 ("java-slf4j-api" ,java-slf4j-api)
12340 ("java-slf4j-simple" ,java-slf4j-simple)
12341 ("java-biojava-core" ,java-biojava-core-4.0)
12342 ("java-forester" ,java-forester-1.005)))
12344 `(("java-junit" ,java-junit)
12345 ("java-hamcrest-core" ,java-hamcrest-core)))
12346 (home-page "http://biojava.org")
12347 (synopsis "Biojava interface to the forester phylogenomics library")
12348 (description "The phylo module provides a biojava interface layer to the
12349 forester phylogenomics library for constructing phylogenetic trees.")))
12351 (define-public java-biojava-alignment-4.0
12352 (package (inherit java-biojava-core-4.0)
12353 (name "java-biojava-alignment")
12354 (build-system ant-build-system)
12357 #:jar-name "biojava-alignment.jar"
12358 #:source-dir "biojava-alignment/src/main/java/"
12359 #:test-dir "biojava-alignment/src/test"
12361 (modify-phases %standard-phases
12362 (add-before 'build 'copy-resources
12364 (copy-recursively "biojava-alignment/src/main/resources"
12367 (add-before 'check 'copy-test-resources
12369 (copy-recursively "biojava-alignment/src/test/resources"
12370 "build/test-classes")
12373 `(("java-log4j-api" ,java-log4j-api)
12374 ("java-log4j-core" ,java-log4j-core)
12375 ("java-slf4j-api" ,java-slf4j-api)
12376 ("java-slf4j-simple" ,java-slf4j-simple)
12377 ("java-biojava-core" ,java-biojava-core-4.0)
12378 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12379 ("java-forester" ,java-forester-1.005)))
12381 `(("java-junit" ,java-junit)
12382 ("java-hamcrest-core" ,java-hamcrest-core)))
12383 (home-page "http://biojava.org")
12384 (synopsis "Biojava API for genetic sequence alignment")
12385 (description "The alignment module of BioJava provides an API that
12389 @item implementations of dynamic programming algorithms for sequence
12391 @item reading and writing of popular alignment file formats;
12392 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12395 (define-public dropseq-tools
12397 (name "dropseq-tools")
12402 (uri "http://mccarrolllab.com/download/1276/")
12403 (file-name (string-append "dropseq-tools-" version ".zip"))
12406 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12407 ;; Delete bundled libraries
12408 (modules '((guix build utils)))
12411 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12412 (delete-file-recursively "3rdParty")
12414 (build-system ant-build-system)
12416 `(#:tests? #f ; test data are not included
12417 #:test-target "test"
12418 #:build-target "all"
12419 #:source-dir "public/src/"
12422 (list (string-append "-Dpicard.executable.dir="
12423 (assoc-ref %build-inputs "java-picard")
12425 #:modules ((ice-9 match)
12428 (guix build java-utils)
12429 (guix build ant-build-system))
12431 (modify-phases %standard-phases
12432 ;; FIXME: fails with "java.io.FileNotFoundException:
12433 ;; /gnu/store/…-dropseq-tools-1.13/share/java/lib/biojava-alignment.jar"
12434 (delete 'generate-jar-indices)
12435 ;; All dependencies must be linked to "lib", because that's where
12436 ;; they will be searched for when the Class-Path property of the
12437 ;; manifest is computed.
12438 (add-after 'unpack 'record-references
12439 (lambda* (#:key inputs #:allow-other-keys)
12440 (mkdir-p "jar/lib")
12441 (let ((dirs (filter-map (match-lambda
12443 (if (and (string-prefix? "java-" name)
12444 (not (string=? name "java-testng")))
12447 (for-each (lambda (jar)
12448 (symlink jar (string-append "jar/lib/" (basename jar))))
12449 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12452 ;; There is no installation target
12454 (lambda* (#:key inputs outputs #:allow-other-keys)
12455 (let* ((out (assoc-ref outputs "out"))
12456 (bin (string-append out "/bin"))
12457 (share (string-append out "/share/java/"))
12458 (lib (string-append share "/lib/"))
12459 (scripts (list "BAMTagHistogram"
12460 "BAMTagofTagCounts"
12461 "BaseDistributionAtReadPosition"
12462 "CollapseBarcodesInPlace"
12463 "CollapseTagWithContext"
12465 "CreateIntervalsFiles"
12466 "DetectBeadSynthesisErrors"
12467 "DigitalExpression"
12468 "Drop-seq_alignment.sh"
12471 "GatherGeneGCLength"
12472 "GatherMolecularBarcodeDistributionByGene"
12473 "GatherReadQualityMetrics"
12476 "SelectCellsByNumTranscripts"
12477 "SingleCellRnaSeqMetricsCollector"
12478 "TagBamWithReadSequenceExtended"
12479 "TagReadWithGeneExon"
12480 "TagReadWithInterval"
12481 "TrimStartingSequence"
12482 "ValidateReference")))
12483 (for-each mkdir-p (list bin share lib))
12484 (install-file "dist/dropseq.jar" share)
12485 (for-each (lambda (script)
12486 (chmod script #o555)
12487 (install-file script bin))
12489 (substitute* (map (lambda (script)
12490 (string-append bin "/" script))
12492 (("^java") (which "java"))
12493 (("jar_deploy_dir=.*")
12494 (string-append "jar_deploy_dir=" share "\n"))))
12496 ;; FIXME: We do this after stripping jars because we don't want it to
12497 ;; copy all these jars and strip them. We only want to install
12498 ;; links. Arguably, this is a problem with the ant-build-system.
12499 (add-after 'strip-jar-timestamps 'install-links
12500 (lambda* (#:key outputs #:allow-other-keys)
12501 (let* ((out (assoc-ref outputs "out"))
12502 (share (string-append out "/share/java/"))
12503 (lib (string-append share "/lib/")))
12504 (for-each (lambda (jar)
12505 (symlink (readlink jar)
12506 (string-append lib (basename jar))))
12507 (find-files "jar/lib" "\\.jar$")))
12510 `(("jdk" ,icedtea-8)
12511 ("java-picard" ,java-picard-2.10.3)
12512 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12513 ("java-commons-math3" ,java-commons-math3)
12514 ("java-commons-jexl2" ,java-commons-jexl-2)
12515 ("java-commons-collections4" ,java-commons-collections4)
12516 ("java-commons-lang2" ,java-commons-lang)
12517 ("java-commons-io" ,java-commons-io)
12518 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12519 ("java-guava" ,java-guava)
12520 ("java-la4j" ,java-la4j)
12521 ("java-biojava-core" ,java-biojava-core-4.0)
12522 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12523 ("java-jdistlib" ,java-jdistlib)
12524 ("java-simple-xml" ,java-simple-xml)
12525 ("java-snakeyaml" ,java-snakeyaml)))
12528 ("java-testng" ,java-testng)))
12529 (home-page "http://mccarrolllab.com/dropseq/")
12530 (synopsis "Tools for Drop-seq analyses")
12531 (description "Drop-seq is a technology to enable biologists to
12532 analyze RNA expression genome-wide in thousands of individual cells at
12533 once. This package provides tools to perform Drop-seq analyses.")
12534 (license license:expat)))
12536 (define-public pigx-rnaseq
12538 (name "pigx-rnaseq")
12542 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12543 "releases/download/v" version
12544 "/pigx_rnaseq-" version ".tar.gz"))
12547 "05gn658zpj9xki5dbs728z9zxq1mcm25hkwr5vzwqxsfi15l5f2l"))))
12548 (build-system gnu-build-system)
12550 `(#:parallel-tests? #f ; not supported
12552 (modify-phases %standard-phases
12553 ;; "test.sh" runs STAR, which requires excessive amounts of memory.
12554 (add-after 'unpack 'disable-resource-intensive-test
12556 (substitute* "Makefile.in"
12557 (("(^ tests/test_trim_galore/test.sh).*" _ m) m)
12558 (("^ tests/test_multiqc/test.sh") "")
12559 (("^ test.sh") ""))
12563 ("snakemake" ,snakemake)
12565 ("multiqc" ,multiqc)
12567 ("trim-galore" ,trim-galore)
12569 ("samtools" ,samtools)
12570 ("bedtools" ,bedtools)
12571 ("r-minimal" ,r-minimal)
12572 ("r-rmarkdown" ,r-rmarkdown)
12573 ("r-ggplot2" ,r-ggplot2)
12574 ("r-ggrepel" ,r-ggrepel)
12575 ("r-gprofiler" ,r-gprofiler)
12576 ("r-deseq2" ,r-deseq2)
12578 ("r-knitr" ,r-knitr)
12579 ("r-pheatmap" ,r-pheatmap)
12580 ("r-corrplot" ,r-corrplot)
12581 ("r-reshape2" ,r-reshape2)
12582 ("r-plotly" ,r-plotly)
12583 ("r-scales" ,r-scales)
12584 ("r-summarizedexperiment" ,r-summarizedexperiment)
12585 ("r-crosstalk" ,r-crosstalk)
12586 ("r-tximport" ,r-tximport)
12587 ("r-rtracklayer" ,r-rtracklayer)
12588 ("r-rjson" ,r-rjson)
12590 ("ghc-pandoc" ,ghc-pandoc)
12591 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12592 ("python-wrapper" ,python-wrapper)
12593 ("python-pyyaml" ,python-pyyaml)))
12594 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12595 (synopsis "Analysis pipeline for RNA sequencing experiments")
12596 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
12597 reporting for RNA sequencing experiments. It is easy to use and produces high
12598 quality reports. The inputs are reads files from the sequencing experiment,
12599 and a configuration file which describes the experiment. In addition to
12600 quality control of the experiment, the pipeline produces a differential
12601 expression report comparing samples in an easily configurable manner.")
12602 (license license:gpl3+)))
12604 (define-public pigx-chipseq
12606 (name "pigx-chipseq")
12610 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
12611 "releases/download/v" version
12612 "/pigx_chipseq-" version ".tar.gz"))
12615 "0akbxdmsjsq5fzbwaap04hqjpsfgv1l6yrc2pwgbya1xgqvcq6vy"))))
12616 (build-system gnu-build-system)
12617 ;; parts of the tests rely on access to the network
12618 (arguments '(#:tests? #f))
12621 ("coreutils" ,coreutils)
12622 ("r-minimal" ,r-minimal)
12623 ("r-argparser" ,r-argparser)
12624 ("r-biocparallel" ,r-biocparallel)
12625 ("r-biostrings" ,r-biostrings)
12626 ("r-chipseq" ,r-chipseq)
12627 ("r-data-table" ,r-data-table)
12628 ("r-dplyr" ,r-dplyr)
12629 ("r-genomation" ,r-genomation)
12630 ("r-genomicalignments" ,r-genomicalignments)
12631 ("r-genomicranges" ,r-genomicranges)
12632 ("r-rsamtools" ,r-rsamtools)
12633 ("r-rtracklayer" ,r-rtracklayer)
12634 ("r-s4vectors" ,r-s4vectors)
12635 ("r-stringr" ,r-stringr)
12636 ("r-tibble" ,r-tibble)
12637 ("r-tidyr" ,r-tidyr)
12638 ("r-jsonlite" ,r-jsonlite)
12639 ("r-heatmaply" ,r-heatmaply)
12640 ("r-htmlwidgets" ,r-htmlwidgets)
12641 ("r-ggplot2" ,r-ggplot2)
12642 ("r-plotly" ,r-plotly)
12643 ("r-rmarkdown" ,r-rmarkdown)
12644 ("python-wrapper" ,python-wrapper)
12645 ("python-pyyaml" ,python-pyyaml)
12646 ("python-magic" ,python-magic)
12647 ("python-xlrd" ,python-xlrd)
12648 ("trim-galore" ,trim-galore)
12650 ("multiqc" ,multiqc)
12652 ("ghc-pandoc" ,ghc-pandoc)
12653 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12657 ("snakemake" ,snakemake)
12658 ("samtools" ,samtools)
12659 ("bedtools" ,bedtools)
12660 ("kentutils" ,kentutils)))
12662 `(("python-pytest" ,python-pytest)))
12663 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12664 (synopsis "Analysis pipeline for ChIP sequencing experiments")
12665 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
12666 calling and reporting for ChIP sequencing experiments. It is easy to use and
12667 produces high quality reports. The inputs are reads files from the sequencing
12668 experiment, and a configuration file which describes the experiment. In
12669 addition to quality control of the experiment, the pipeline enables to set up
12670 multiple peak calling analysis and allows the generation of a UCSC track hub
12671 in an easily configurable manner.")
12672 (license license:gpl3+)))
12674 (define-public pigx-bsseq
12676 (name "pigx-bsseq")
12680 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
12681 "releases/download/v" version
12682 "/pigx_bsseq-" version ".tar.gz"))
12685 "0l97wvkq4diq8lcarraj33bby1zzf0w804jwi8mlc5qddp8idwhy"))))
12686 (build-system gnu-build-system)
12689 (modify-phases %standard-phases
12690 (add-before 'check 'set-timezone
12691 ;; The readr package is picky about timezones.
12692 (lambda* (#:key inputs #:allow-other-keys)
12693 (setenv "TZ" "UTC+1")
12695 (string-append (assoc-ref inputs "tzdata")
12696 "/share/zoneinfo"))
12699 `(("tzdata" ,tzdata)))
12701 `(("coreutils" ,coreutils)
12704 ("r-minimal" ,r-minimal)
12705 ("r-annotationhub" ,r-annotationhub)
12707 ("r-genomation" ,r-genomation)
12708 ("r-methylkit" ,r-methylkit)
12709 ("r-rtracklayer" ,r-rtracklayer)
12710 ("r-rmarkdown" ,r-rmarkdown)
12711 ("r-bookdown" ,r-bookdown)
12712 ("r-ggplot2" ,r-ggplot2)
12713 ("r-ggbio" ,r-ggbio)
12714 ("ghc-pandoc" ,ghc-pandoc)
12715 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12716 ("python-wrapper" ,python-wrapper)
12717 ("python-pyyaml" ,python-pyyaml)
12718 ("snakemake" ,snakemake)
12719 ("bismark" ,bismark)
12722 ("trim-galore" ,trim-galore)
12723 ("cutadapt" ,cutadapt)
12724 ("samtools" ,samtools)))
12725 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12726 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
12727 (description "PiGx BSseq is a data processing pipeline for raw fastq read
12728 data of bisulfite experiments; it produces reports on aggregate methylation
12729 and coverage and can be used to produce information on differential
12730 methylation and segmentation.")
12731 (license license:gpl3+)))
12733 (define-public pigx-scrnaseq
12735 (name "pigx-scrnaseq")
12739 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/"
12740 "releases/download/v" version
12741 "/pigx_scrnaseq-" version ".tar.gz"))
12744 "131zarirv16w8653m0d66jgjnwqfsxqc0hix0rypssz4d83bl51j"))))
12745 (build-system gnu-build-system)
12747 `(#:configure-flags
12748 (list (string-append "PICARDJAR=" (assoc-ref %build-inputs "java-picard")
12749 "/share/java/picard.jar")
12750 (string-append "DROPSEQJAR=" (assoc-ref %build-inputs "dropseq-tools")
12751 "/share/java/dropseq.jar"))))
12753 `(("coreutils" ,coreutils)
12755 ("dropseq-tools" ,dropseq-tools)
12757 ("java-picard" ,java-picard-2.10.3) ; same as for dropseq
12758 ("java" ,icedtea-8)
12759 ("python-wrapper" ,python-wrapper)
12760 ("python-pyyaml" ,python-pyyaml)
12761 ("python-pandas" ,python-pandas)
12762 ("python-magic" ,python-magic)
12763 ("python-numpy" ,python-numpy)
12764 ("python-loompy" ,python-loompy-for-pigx-scrnaseq)
12765 ("ghc-pandoc" ,ghc-pandoc)
12766 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12767 ("samtools" ,samtools)
12768 ("snakemake" ,snakemake)
12770 ("r-minimal" ,r-minimal)
12771 ("r-argparser" ,r-argparser)
12772 ("r-cowplot" ,r-cowplot)
12773 ("r-data-table" ,r-data-table)
12774 ("r-delayedarray" ,r-delayedarray)
12775 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
12776 ("r-dplyr" ,r-dplyr)
12777 ("r-dropbead" ,r-dropbead)
12779 ("r-genomicalignments" ,r-genomicalignments)
12780 ("r-genomicfiles" ,r-genomicfiles)
12781 ("r-genomicranges" ,r-genomicranges)
12782 ("r-ggplot2" ,r-ggplot2)
12783 ("r-hdf5array" ,r-hdf5array)
12784 ("r-pheatmap" ,r-pheatmap)
12785 ("r-rmarkdown" ,r-rmarkdown)
12786 ("r-rsamtools" ,r-rsamtools)
12787 ("r-rtracklayer" ,r-rtracklayer)
12788 ("r-rtsne" ,r-rtsne)
12789 ("r-scater" ,r-scater)
12790 ("r-scran" ,r-scran)
12791 ("r-singlecellexperiment" ,r-singlecellexperiment)
12792 ("r-stringr" ,r-stringr)
12793 ("r-yaml" ,r-yaml)))
12794 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12795 (synopsis "Analysis pipeline for single-cell RNA sequencing experiments")
12796 (description "PiGX scRNAseq is an analysis pipeline for preprocessing and
12797 quality control for single cell RNA sequencing experiments. The inputs are
12798 read files from the sequencing experiment, and a configuration file which
12799 describes the experiment. It produces processed files for downstream analysis
12800 and interactive quality reports. The pipeline is designed to work with UMI
12802 (license license:gpl3+)))
12804 (define-public pigx
12810 (uri (string-append "https://github.com/BIMSBbioinfo/pigx/"
12811 "releases/download/v" version
12812 "/pigx-" version ".tar.gz"))
12815 "1i5njdy1clj5ncw45d16p7mwmqvb1ilikl9n797pxklc3f4s7mq7"))))
12816 (build-system gnu-build-system)
12818 `(("python" ,python)
12819 ("pigx-bsseq" ,pigx-bsseq)
12820 ("pigx-chipseq" ,pigx-chipseq)
12821 ("pigx-rnaseq" ,pigx-rnaseq)
12822 ("pigx-scrnaseq" ,pigx-scrnaseq)))
12823 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12824 (synopsis "Analysis pipelines for genomics")
12825 (description "PiGx is a collection of genomics pipelines. It includes the
12826 following pipelines:
12829 @item PiGx BSseq for raw fastq read data of bisulfite experiments
12830 @item PiGx RNAseq for RNAseq samples
12831 @item PiGx scRNAseq for single cell dropseq analysis
12832 @item PiGx ChIPseq for reads from ChIPseq experiments
12835 All pipelines are easily configured with a simple sample sheet and a
12836 descriptive settings file. The result is a set of comprehensive, interactive
12837 HTML reports with interesting findings about your samples.")
12838 (license license:gpl3+)))
12840 (define-public genrich
12846 (uri (git-reference
12847 (url "https://github.com/jsh58/Genrich.git")
12848 (commit (string-append "v" version))))
12851 "0x0q6z0208n3cxzqjla4rgjqpyqgwpmz27852lcvzkzaigymq4zp"))))
12852 (build-system gnu-build-system)
12854 `(#:tests? #f ; there are none
12856 (modify-phases %standard-phases
12857 (delete 'configure)
12859 (lambda* (#:key outputs #:allow-other-keys)
12860 (install-file "Genrich" (string-append (assoc-ref outputs "out") "/bin"))
12864 (home-page "https://github.com/jsh58/Genrich")
12865 (synopsis "Detecting sites of genomic enrichment")
12866 (description "Genrich is a peak-caller for genomic enrichment
12867 assays (e.g. ChIP-seq, ATAC-seq). It analyzes alignment files generated
12868 following the assay and produces a file detailing peaks of significant
12870 (license license:expat)))
12872 (define-public mantis
12873 (let ((commit "4ffd171632c2cb0056a86d709dfd2bf21bc69b84")
12877 (version (git-version "0" revision commit))
12880 (uri (git-reference
12881 (url "https://github.com/splatlab/mantis.git")
12883 (file-name (git-file-name name version))
12886 "0iqbr0dhmlc8mzpirmm2s4pkzkwdgrcx50yx6cv3wlr2qi064p55"))))
12887 (build-system cmake-build-system)
12888 (arguments '(#:tests? #f)) ; there are none
12890 `(("sdsl-lite" ,sdsl-lite)
12891 ("openssl" ,openssl)
12893 (home-page "https://github.com/splatlab/mantis")
12894 (synopsis "Large-scale sequence-search index data structure")
12895 (description "Mantis is a space-efficient data structure that can be
12896 used to index thousands of raw-read genomics experiments and facilitate
12897 large-scale sequence searches on those experiments. Mantis uses counting
12898 quotient filters instead of Bloom filters, enabling rapid index builds and
12899 queries, small indexes, and exact results, i.e., no false positives or
12900 negatives. Furthermore, Mantis is also a colored de Bruijn graph
12901 representation, so it supports fast graph traversal and other topological
12902 analyses in addition to large-scale sequence-level searches.")
12903 ;; uses __uint128_t and inline assembly
12904 (supported-systems '("x86_64-linux"))
12905 (license license:bsd-3))))
12907 (define-public r-diversitree
12909 (name "r-diversitree")
12914 (uri (cran-uri "diversitree" version))
12917 "1jqfjmmaigq581l4zxysmkhld0xv6izlbr1hihf9zplkix36majc"))))
12918 (build-system r-build-system)
12920 `(("gfortran" ,gfortran)))
12921 (inputs `(("fftw" ,fftw) ("gsl" ,gsl)))
12924 ("r-desolve" ,r-desolve)
12926 ("r-subplex" ,r-subplex)))
12927 (home-page "https://www.zoology.ubc.ca/prog/diversitree")
12928 (synopsis "Comparative 'phylogenetic' analyses of diversification")
12929 (description "This package contains a number of comparative \"phylogenetic\"
12930 methods, mostly focusing on analysing diversification and character evolution.
12931 Contains implementations of \"BiSSE\" (Binary State Speciation and Extinction)
12932 and its unresolved tree extensions, \"MuSSE\" (Multiple State Speciation and
12933 Extinction), \"QuaSSE\", \"GeoSSE\", and \"BiSSE-ness\" Other included methods
12934 include Markov models of discrete and continuous trait evolution and constant
12935 rate speciation and extinction.")
12936 (license license:gpl2+)))
12938 (define-public sjcount
12939 ;; There is no tag for version 3.2, nor is there a release archive.
12940 (let ((commit "292d3917cadb3f6834c81e509c30e61cd7ead6e5")
12944 (version (git-version "3.2" revision commit))
12947 (uri (git-reference
12948 (url "https://github.com/pervouchine/sjcount-full.git")
12950 (file-name (string-append name "-" version "-checkout"))
12953 "0gdgj35j249f04rqgq8ymcc1xg1vi9kzbajnjqpaq2wpbh8bl234"))))
12954 (build-system gnu-build-system)
12956 `(#:tests? #f ; requires a 1.4G test file
12958 (list (string-append "SAMTOOLS_DIR="
12959 (assoc-ref %build-inputs "samtools")
12962 (modify-phases %standard-phases
12963 (replace 'configure
12964 (lambda* (#:key inputs #:allow-other-keys)
12965 (substitute* "makefile"
12966 (("-I \\$\\{SAMTOOLS_DIR\\}")
12967 (string-append "-I" (assoc-ref inputs "samtools")
12968 "/include/samtools"))
12969 (("-lz ") "-lz -lpthread "))
12972 (lambda* (#:key outputs #:allow-other-keys)
12973 (for-each (lambda (tool)
12975 (string-append (assoc-ref outputs "out")
12977 '("j_count" "b_count" "sjcount"))
12980 `(("samtools" ,samtools-0.1)
12982 (home-page "https://github.com/pervouchine/sjcount-full/")
12983 (synopsis "Annotation-agnostic splice junction counting pipeline")
12984 (description "Sjcount is a utility for fast quantification of splice
12985 junctions in RNA-seq data. It is annotation-agnostic and offset-aware. This
12986 version does count multisplits.")
12987 (license license:gpl3+))))
12989 (define-public minimap2
12996 (uri (string-append "https://github.com/lh3/minimap2/"
12997 "releases/download/v" version "/"
12998 "minimap2-" version ".tar.bz2"))
13001 "080w9066irkbhbyr4nmf19pzkdd2s4v31hpzlajgq2y0drr6zcsj"))))
13002 (build-system gnu-build-system)
13004 `(#:tests? #f ; there are none
13007 (let ((system ,(or (%current-target-system)
13008 (%current-system))))
13010 ((string-prefix? "x86_64" system)
13012 ((or (string-prefix? "armhf" system)
13013 (string-prefix? "aarch64" system))
13015 (_ "sse2only=1"))))
13017 (modify-phases %standard-phases
13018 (delete 'configure)
13020 (lambda* (#:key outputs #:allow-other-keys)
13021 (let* ((out (assoc-ref outputs "out"))
13022 (bin (string-append out "/bin"))
13023 (man (string-append out "/share/man/man1")))
13024 (install-file "minimap2" bin)
13026 (install-file "minimap2.1" man))
13030 (home-page "https://lh3.github.io/minimap2/")
13031 (synopsis "Pairwise aligner for genomic and spliced nucleotide sequences")
13032 (description "Minimap2 is a versatile sequence alignment program that
13033 aligns DNA or mRNA sequences against a large reference database. Typical use
13037 @item mapping PacBio or Oxford Nanopore genomic reads to the human genome;
13038 @item finding overlaps between long reads with error rate up to ~15%;
13039 @item splice-aware alignment of PacBio Iso-Seq or Nanopore cDNA or Direct RNA
13040 reads against a reference genome;
13041 @item aligning Illumina single- or paired-end reads;
13042 @item assembly-to-assembly alignment;
13043 @item full-genome alignment between two closely related species with
13044 divergence below ~15%.
13046 (license license:expat)))
13048 (define-public r-circus
13055 (uri (git-reference
13056 (url "https://github.com/BIMSBbioinfo/ciRcus.git")
13057 (commit (string-append "v" version))))
13058 (file-name (git-file-name name version))
13061 "0jhjn3ilb057hbf6yzrihj13ifxxs32y7nkby8l3lkm28dg4p97h"))))
13062 (build-system r-build-system)
13064 `(("r-annotationdbi" ,r-annotationdbi)
13065 ("r-annotationhub" ,r-annotationhub)
13066 ("r-biomart" ,r-biomart)
13067 ("r-data-table" ,r-data-table)
13069 ("r-genomicfeatures" ,r-genomicfeatures)
13070 ("r-genomicranges" ,r-genomicranges)
13071 ("r-ggplot2" ,r-ggplot2)
13073 ("r-iranges" ,r-iranges)
13074 ("r-rcolorbrewer" ,r-rcolorbrewer)
13075 ("r-rmysql" ,r-rmysql)
13076 ("r-s4vectors" ,r-s4vectors)
13077 ("r-stringr" ,r-stringr)
13078 ("r-summarizedexperiment" ,r-summarizedexperiment)))
13080 `(("r-knitr" ,r-knitr)))
13081 (home-page "https://github.com/BIMSBbioinfo/ciRcus")
13082 (synopsis "Annotation, analysis and visualization of circRNA data")
13083 (description "Circus is an R package for annotation, analysis and
13084 visualization of circRNA data. Users can annotate their circRNA candidates
13085 with host genes, gene featrues they are spliced from, and discriminate between
13086 known and yet unknown splice junctions. Circular-to-linear ratios of circRNAs
13087 can be calculated, and a number of descriptive plots easily generated.")
13088 (license license:artistic2.0)))
13090 (define-public r-loomr
13091 (let ((commit "df0144bd2bbceca6fadef9edc1bbc5ca672d4739")
13095 (version (git-version "0.2.0" revision commit))
13099 (uri (git-reference
13100 (url "https://github.com/mojaveazure/loomR.git")
13102 (file-name (git-file-name name version))
13105 "1b1g4dlmfdyhn56bz1mkh9ymirri43wiz7rjhs7py3y7bdw1s3yr"))))
13106 (build-system r-build-system)
13109 ("r-hdf5r" ,r-hdf5r)
13110 ("r-iterators" ,r-iterators)
13111 ("r-itertools" ,r-itertools)
13112 ("r-matrix" ,r-matrix)))
13113 (home-page "https://github.com/mojaveazure/loomR")
13114 (synopsis "R interface for loom files")
13115 (description "This package provides an R interface to access, create,
13116 and modify loom files. loomR aims to be completely compatible with loompy.")
13117 (license license:gpl3))))
13119 (define-public gffread
13120 ;; We cannot use the tagged release because it is not in sync with gclib.
13121 ;; See https://github.com/gpertea/gffread/issues/26
13122 (let ((commit "ba7535fcb3cea55a6e5a491d916e93b454e87fd0")
13126 (version (git-version "0.9.12" revision commit))
13130 (uri (git-reference
13131 (url "https://github.com/gpertea/gffread.git")
13133 (file-name (git-file-name name version))
13136 "1dl2nbcg96lxpd0drg48ssa8343nf7pw9s9mkrc4mjjmfwsin3ki"))))
13137 (build-system gnu-build-system)
13139 `(#:tests? #f ; no check target
13141 (list "GCLDIR=gclib")
13143 (modify-phases %standard-phases
13144 (delete 'configure)
13145 (add-after 'unpack 'copy-gclib-source
13146 (lambda* (#:key inputs #:allow-other-keys)
13148 (copy-recursively (assoc-ref inputs "gclib-source") "gclib")
13150 ;; There is no install target
13152 (lambda* (#:key outputs #:allow-other-keys)
13153 (let* ((out (assoc-ref outputs "out"))
13154 (bin (string-append out "/bin")))
13155 (install-file "gffread" bin))
13159 ,(let ((version "0.10.3")
13160 (commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13164 (uri (git-reference
13165 (url "https://github.com/gpertea/gclib.git")
13167 (file-name (git-file-name "gclib" version))
13170 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13171 (home-page "https://github.com/gpertea/gffread/")
13172 (synopsis "Parse and convert GFF/GTF files")
13174 "This package provides a GFF/GTF file parsing utility providing format
13175 conversions, region filtering, FASTA sequence extraction and more.")
13176 ;; gffread is under Expat, but gclib is under Artistic 2.0
13177 (license (list license:expat
13178 license:artistic2.0)))))
13180 (define-public find-circ
13181 ;; The last release was in 2015. The license was clarified in 2017, so we
13182 ;; take the latest commit.
13183 (let ((commit "8655dca54970fcf7e92e22fbf57e1188724dda7d")
13187 (version (git-version "1.2" revision commit))
13191 (uri (git-reference
13192 (url "https://github.com/marvin-jens/find_circ.git")
13194 (file-name (git-file-name name version))
13197 "0p77pbqbclqr4srms34y1b9b4njybfpjiknc11ki84f3p8skb3cg"))))
13198 (build-system gnu-build-system)
13200 `(#:tests? #f ; there are none
13202 ;; There is no actual build system.
13203 (modify-phases %standard-phases
13204 (delete 'configure)
13207 (lambda* (#:key outputs #:allow-other-keys)
13208 (let* ((out (assoc-ref outputs "out"))
13209 (bin (string-append out "/bin"))
13210 (path (getenv "PYTHONPATH")))
13211 (for-each (lambda (script)
13212 (install-file script bin)
13213 (wrap-program (string-append bin "/" script)
13214 `("PYTHONPATH" ":" prefix (,path))))
13219 "unmapped2anchors.py")))
13222 `(("python2" ,python-2)
13223 ("python2-pysam" ,python2-pysam)
13224 ("python2-numpy" ,python2-numpy)))
13225 (home-page "https://github.com/marvin-jens/find_circ")
13226 (synopsis "circRNA detection from RNA-seq reads")
13227 (description "This package provides tools to detect head-to-tail
13228 spliced (back-spliced) sequencing reads, indicative of circular RNA (circRNA)
13230 (license license:gpl3))))
13232 (define-public python-scanpy
13234 (name "python-scanpy")
13236 ;; Fetch from git because the pypi tarball does not include tests.
13240 (uri (git-reference
13241 (url "https://github.com/theislab/scanpy.git")
13243 (file-name (git-file-name name version))
13246 "0zn6x6c0cnm1a20i6isigwb51g3pr9zpjk8r1minjqnxi5yc9pm4"))))
13247 (build-system python-build-system)
13250 (modify-phases %standard-phases
13252 (lambda* (#:key inputs #:allow-other-keys)
13253 ;; These tests require Internet access.
13254 (delete-file-recursively "scanpy/tests/notebooks")
13255 (delete-file "scanpy/tests/test_clustering.py")
13257 ;; TODO: I can't get the plotting tests to work, even with Xvfb.
13258 (delete-file "scanpy/tests/test_plotting.py")
13259 (delete-file "scanpy/tests/test_preprocessing.py")
13260 (delete-file "scanpy/tests/test_read_10x.py")
13262 (setenv "PYTHONPATH"
13263 (string-append (getcwd) ":"
13264 (getenv "PYTHONPATH")))
13268 `(("python-anndata" ,python-anndata)
13269 ("python-h5py" ,python-h5py)
13270 ("python-igraph" ,python-igraph)
13271 ("python-joblib" ,python-joblib)
13272 ("python-louvain" ,python-louvain)
13273 ("python-matplotlib" ,python-matplotlib)
13274 ("python-natsort" ,python-natsort)
13275 ("python-networkx" ,python-networkx)
13276 ("python-numba" ,python-numba)
13277 ("python-pandas" ,python-pandas)
13278 ("python-scikit-learn" ,python-scikit-learn)
13279 ("python-scipy" ,python-scipy)
13280 ("python-seaborn" ,python-seaborn)
13281 ("python-statsmodels" ,python-statsmodels)
13282 ("python-tables" ,python-tables)))
13284 `(("python-pytest" ,python-pytest)))
13285 (home-page "https://github.com/theislab/scanpy")
13286 (synopsis "Single-Cell Analysis in Python.")
13287 (description "Scanpy is a scalable toolkit for analyzing single-cell gene
13288 expression data. It includes preprocessing, visualization, clustering,
13289 pseudotime and trajectory inference and differential expression testing. The
13290 Python-based implementation efficiently deals with datasets of more than one
13292 (license license:bsd-3)))
13294 (define-public python-bbknn
13296 (name "python-bbknn")
13301 (uri (pypi-uri "bbknn" version))
13304 "1qgdganvj3lyxj84v7alm23b9vqhwpn8z0115qndpnpy90qxynwz"))))
13305 (build-system python-build-system)
13307 `(("python-annoy" ,python-annoy)
13308 ("python-cython" ,python-cython)
13309 ("python-faiss" ,python-faiss)
13310 ("python-numpy" ,python-numpy)
13311 ("python-scanpy" ,python-scanpy)))
13312 (home-page "https://github.com/Teichlab/bbknn")
13313 (synopsis "Batch balanced KNN")
13314 (description "BBKNN is a batch effect removal tool that can be directly
13315 used in the Scanpy workflow. It serves as an alternative to
13316 @code{scanpy.api.pp.neighbors()}, with both functions creating a neighbour
13317 graph for subsequent use in clustering, pseudotime and UMAP visualisation. If
13318 technical artifacts are present in the data, they will make it challenging to
13319 link corresponding cell types across different batches. BBKNN actively
13320 combats this effect by splitting your data into batches and finding a smaller
13321 number of neighbours for each cell within each of the groups. This helps
13322 create connections between analogous cells in different batches without
13323 altering the counts or PCA space.")
13324 (license license:expat)))
13326 (define-public gffcompare
13327 (let ((commit "be56ef4349ea3966c12c6397f85e49e047361c41")
13330 (name "gffcompare")
13331 (version (git-version "0.10.15" revision commit))
13335 (uri (git-reference
13336 (url "https://github.com/gpertea/gffcompare/")
13338 (file-name (git-file-name name version))
13340 (base32 "0cp5qpxdhw4mxpya5dld8wi3jk00zyklm6rcri426wydinrnfmkg"))))
13341 (build-system gnu-build-system)
13343 `(#:tests? #f ; no check target
13345 (modify-phases %standard-phases
13346 (delete 'configure)
13347 (add-before 'build 'copy-gclib-source
13348 (lambda* (#:key inputs #:allow-other-keys)
13351 (assoc-ref inputs "gclib-source") "../gclib")
13354 (lambda* (#:key outputs #:allow-other-keys)
13355 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
13356 (install-file "gffcompare" bin)
13359 `(("gclib-source" ; see 'README.md' of gffcompare
13360 ,(let ((commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13363 (version (git-version "0.10.3" revision commit)))
13366 (uri (git-reference
13367 (url "https://github.com/gpertea/gclib/")
13369 (file-name (git-file-name name version))
13371 (base32 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13372 (home-page "https://github.com/gpertea/gffcompare/")
13373 (synopsis "Tool for comparing or classifing transcripts of RNA-Seq")
13375 "@code{gffcompare} is a tool that can:
13377 @item compare and evaluate the accuracy of RNA-Seq transcript assemblers
13378 (Cufflinks, Stringtie);
13379 @item collapse (merge) duplicate transcripts from multiple GTF/GFF3 files (e.g.
13380 resulted from assembly of different samples);
13381 @item classify transcripts from one or multiple GTF/GFF3 files as they relate to
13382 reference transcripts provided in a annotation file (also in GTF/GFF3 format).
13386 license:expat ;license for gffcompare
13387 license:artistic2.0))))) ;license for gclib
13389 (define-public python-intervaltree
13391 (name "python-intervaltree")
13396 (uri (pypi-uri "intervaltree" version))
13399 "02w191m9zxkcjqr1kv2slxvhymwhj3jnsyy3a28b837pi15q19dc"))))
13400 (build-system python-build-system)
13401 ;; FIXME: error when collecting tests
13402 (arguments '(#:tests? #f))
13404 `(("python-sortedcontainers" ,python-sortedcontainers)))
13406 `(("python-pytest" ,python-pytest)))
13407 (home-page "https://github.com/chaimleib/intervaltree")
13408 (synopsis "Editable interval tree data structure")
13410 "This package provides a mutable, self-balancing interval tree
13411 implementation for Python. Queries may be by point, by range overlap, or by
13412 range envelopment. This library was designed to allow tagging text and time
13413 intervals, where the intervals include the lower bound but not the upper
13415 (license license:asl2.0)))
13417 (define-public python-pypairix
13419 (name "python-pypairix")
13424 (uri (pypi-uri "pypairix" version))
13427 "0zs92b74s5v4xy2h16s15f3z6l4nnbw8x8zyif7xx5xpafjn0xss"))))
13428 (build-system python-build-system)
13429 ;; FIXME: the tests fail because test.support cannot be loaded:
13430 ;; ImportError: cannot import name 'support'
13431 (arguments '(#:tests? #f))
13434 (home-page "https://github.com/4dn-dcic/pairix")
13435 (synopsis "Support for querying pairix-indexed bgzipped text files")
13437 "Pypairix is a Python module for fast querying on a pairix-indexed
13438 bgzipped text file that contains a pair of genomic coordinates per line.")
13439 (license license:expat)))
13441 (define-public python-pyfaidx
13443 (name "python-pyfaidx")
13444 (version "0.5.4.2")
13448 (uri (pypi-uri "pyfaidx" version))
13451 "0y5zyjksj1rdglj601xd2bbni5abhdh622y3ck76chyzxz9z4rx8"))))
13452 (build-system python-build-system)
13454 `(("python-setuptools" ,python-setuptools)
13455 ("python-six" ,python-six)))
13456 (home-page "http://mattshirley.com")
13457 (synopsis "Random access to fasta subsequences")
13459 "This package provides procedures for efficient pythonic random access to
13460 fasta subsequences.")
13461 (license license:bsd-3)))
13463 (define-public python-cooler
13465 (name "python-cooler")
13470 (uri (pypi-uri "cooler" version))
13473 "08k5nxnxa6qsbk15z5z0q01n28042k87wi4905hh95rzqib15mhx"))))
13474 (build-system python-build-system)
13476 `(("python-biopython" ,python-biopython)
13477 ("python-click" ,python-click)
13478 ("python-cytoolz" ,python-cytoolz)
13479 ("python-dask" ,python-dask)
13480 ("python-h5py" ,python-h5py)
13481 ("python-multiprocess" ,python-multiprocess)
13482 ("python-pandas" ,python-pandas)
13483 ("python-pyfaidx" ,python-pyfaidx)
13484 ("python-pypairix" ,python-pypairix)
13485 ("python-pysam" ,python-pysam)
13486 ("python-scipy" ,python-scipy)))
13488 `(("python-mock" ,python-mock)
13489 ("python-nose" ,python-nose)
13490 ("python-numpydoc" ,python-numpydoc)
13491 ("python-sphinx" ,python-sphinx)))
13492 (home-page "https://github.com/mirnylab/cooler")
13493 (synopsis "Sparse binary format for genomic interaction matrices")
13495 "Cooler is a support library for a sparse, compressed, binary persistent
13496 storage format, called @code{cool}, used to store genomic interaction data,
13497 such as Hi-C contact matrices.")
13498 (license license:bsd-3)))
13500 (define-public python-hicexplorer
13502 (name "python-hicexplorer")
13506 ;; The latest version is not available on Pypi.
13508 (uri (git-reference
13509 (url "https://github.com/deeptools/HiCExplorer.git")
13511 (file-name (git-file-name name version))
13514 "0q5gpbzmrkvygqgw524q36b4nrivcmyi5v194vsx0qw7b3gcmq08"))))
13515 (build-system python-build-system)
13518 (modify-phases %standard-phases
13519 (add-after 'unpack 'loosen-up-requirements
13521 (substitute* "setup.py"
13525 `(("python-biopython" ,python-biopython)
13526 ("python-configparser" ,python-configparser)
13527 ("python-cooler" ,python-cooler)
13528 ("python-future" ,python-future)
13529 ("python-intervaltree" ,python-intervaltree)
13530 ("python-jinja2" ,python-jinja2)
13531 ("python-matplotlib" ,python-matplotlib)
13532 ("python-numpy" ,python-numpy)
13533 ("python-pandas" ,python-pandas)
13534 ("python-pybigwig" ,python-pybigwig)
13535 ("python-pysam" ,python-pysam)
13536 ("python-scipy" ,python-scipy)
13537 ("python-six" ,python-six)
13538 ("python-tables" ,python-tables)
13539 ("python-unidecode" ,python-unidecode)))
13540 (home-page "http://hicexplorer.readthedocs.io")
13541 (synopsis "Process, analyze and visualize Hi-C data")
13543 "HiCExplorer is a powerful and easy to use set of tools to process,
13544 normalize and visualize Hi-C data. HiCExplorer facilitates the creation of
13545 contact matrices, correction of contacts, TAD detection, A/B compartments,
13546 merging, reordering or chromosomes, conversion from different formats
13547 including cooler and detection of long-range contacts. Moreover, it allows
13548 the visualization of multiple contact matrices along with other types of data
13549 like genes, compartments, ChIP-seq coverage tracks (and in general any type of
13550 genomic scores), long range contacts and the visualization of viewpoints.")
13551 (license license:gpl3)))
13553 (define-public python-pygenometracks
13555 (name "python-pygenometracks")
13560 (uri (pypi-uri "pyGenomeTracks" version))
13563 "1fws6bqsyy9kj3qiabhkqx4wd4i775gsxnhszqd3zg7w67sc1ic5"))))
13564 (build-system python-build-system)
13566 `(("python-configparser" ,python-configparser)
13567 ("python-future" ,python-future)
13568 ("python-hicexplorer" ,python-hicexplorer)
13569 ("python-intervaltree" ,python-intervaltree)
13570 ("python-matplotlib" ,python-matplotlib)
13571 ("python-numpy" ,python-numpy)
13572 ("python-pybigwig" ,python-pybigwig)))
13574 `(("python-pytest" ,python-pytest)))
13575 (home-page "https://pygenometracks.readthedocs.io")
13576 (synopsis "Program and library to plot beautiful genome browser tracks")
13578 "This package aims to produce high-quality genome browser tracks that
13579 are highly customizable. Currently, it is possible to plot: bigwig, bed (many
13580 options), bedgraph, links (represented as arcs), and Hi-C matrices.
13581 pyGenomeTracks can make plots with or without Hi-C data.")
13582 (license license:gpl3+)))
13584 (define-public python-hic2cool
13586 (name "python-hic2cool")
13591 (uri (pypi-uri "hic2cool" version))
13594 "0xy6mhfns2lzib1kcr6419jjp6pmh0qx8z8na55lmiwn0ds8q9cl"))))
13595 (build-system python-build-system)
13596 (arguments '(#:tests? #f)) ; no tests included
13598 `(("python-cooler" ,python-cooler)))
13599 (home-page "https://github.com/4dn-dcic/hic2cool")
13600 (synopsis "Converter for .hic and .cool files")
13602 "This package provides a converter between @code{.hic} files (from
13603 juicer) and single-resolution or multi-resolution @code{.cool} files (for
13604 cooler). Both @code{hic} and @code{cool} files describe Hi-C contact
13606 (license license:expat)))
13608 (define-public r-pore
13616 (string-append "mirror://sourceforge/rpore/" version
13617 "/poRe_" version ".tar.gz"))
13619 (base32 "0pih9nljbv8g4x8rkk29i7aqq681b782r5s5ynp4nw9yzqnmmksv"))))
13620 (properties `((upstream-name . "poRe")))
13621 (build-system r-build-system)
13623 `(("r-bit64" ,r-bit64)
13624 ("r-data-table" ,r-data-table)
13625 ("r-rhdf5" ,r-rhdf5)
13626 ("r-shiny" ,r-shiny)
13627 ("r-svdialogs" ,r-svdialogs)))
13628 (home-page "https://sourceforge.net/projects/rpore/")
13629 (synopsis "Visualize Nanopore sequencing data")
13631 "This package provides graphical user interfaces to organize and visualize Nanopore
13633 ;; This is free software but the license variant is unclear:
13634 ;; <https://github.com/mw55309/poRe_docs/issues/10>.
13635 (license license:bsd-3)))
13637 (define-public r-xbioc
13638 (let ((revision "1")
13639 (commit "f798c187e376fd1ba27abd559f47bbae7e3e466b"))
13642 (version (git-version "0.1.15" revision commit))
13645 (uri (git-reference
13646 (url "https://github.com/renozao/xbioc.git")
13648 (file-name (git-file-name name version))
13651 "03hffh2f6z71y6l6dqpa5cql3hdaw7zigdi8sm2dzgx379k9rgrr"))))
13652 (build-system r-build-system)
13654 `(("r-annotationdbi" ,r-annotationdbi)
13655 ("r-assertthat" ,r-assertthat)
13656 ("r-biobase" ,r-biobase)
13657 ("r-biocinstaller" ,r-biocinstaller)
13658 ("r-digest" ,r-digest)
13659 ("r-pkgmaker" ,r-pkgmaker)
13661 ("r-reshape2" ,r-reshape2)
13662 ("r-stringr" ,r-stringr)))
13663 (home-page "https://github.com/renozao/xbioc/")
13664 (synopsis "Extra base functions for Bioconductor")
13665 (description "This package provides extra utility functions to perform
13666 common tasks in the analysis of omics data, leveraging and enhancing features
13667 provided by Bioconductor packages.")
13668 (license license:gpl3+))))
13670 (define-public r-cssam
13671 (let ((revision "1")
13672 (commit "9ec58c982fa551af0d80b1a266890d92954833f2"))
13675 (version (git-version "1.4" revision commit))
13678 (uri (git-reference
13679 (url "https://github.com/shenorrLab/csSAM.git")
13681 (file-name (git-file-name name version))
13684 "128syf9v39gk0z3ip000qpsjbg6l1siyq6c8b0hz41dzg5achyb3"))))
13685 (build-system r-build-system)
13687 `(("r-formula" ,r-formula)
13688 ("r-ggplot2" ,r-ggplot2)
13689 ("r-pkgmaker" ,r-pkgmaker)
13691 ("r-rngtools" ,r-rngtools)
13692 ("r-scales" ,r-scales)))
13693 (home-page "https://github.com/shenorrLab/csSAM/")
13694 (synopsis "Cell type-specific statistical analysis of microarray")
13695 (description "This package implements the method csSAM that computes
13696 cell-specific differential expression from measured cell proportions using
13699 (license license:lgpl2.1+))))
13701 (define-public r-bseqsc
13702 (let ((revision "1")
13703 (commit "fef3f3e38dcf3df37103348b5780937982b43b98"))
13706 (version (git-version "1.0" revision commit))
13709 (uri (git-reference
13710 (url "https://github.com/shenorrLab/bseqsc.git")
13712 (file-name (git-file-name name version))
13715 "1prw13wa20f7wlc3gkkls66n1kxz8d28qrb8icfqdwdnnv8w5qg8"))))
13716 (build-system r-build-system)
13718 `(("r-abind" ,r-abind)
13719 ("r-annotationdbi" ,r-annotationdbi)
13720 ("r-biobase" ,r-biobase)
13721 ("r-cssam" ,r-cssam)
13722 ("r-dplyr" ,r-dplyr)
13723 ("r-e1071" ,r-e1071)
13724 ("r-edger" ,r-edger)
13725 ("r-ggplot2" ,r-ggplot2)
13727 ("r-openxlsx" ,r-openxlsx)
13728 ("r-pkgmaker" ,r-pkgmaker)
13730 ("r-preprocesscore" ,r-preprocesscore)
13731 ("r-rngtools" ,r-rngtools)
13732 ("r-scales" ,r-scales)
13733 ("r-stringr" ,r-stringr)
13734 ("r-xbioc" ,r-xbioc)))
13735 (home-page "https://github.com/shenorrLab/bseqsc")
13736 (synopsis "Deconvolution of bulk sequencing experiments using single cell data")
13737 (description "BSeq-sc is a bioinformatics analysis pipeline that
13738 leverages single-cell sequencing data to estimate cell type proportion and
13739 cell type-specific gene expression differences from RNA-seq data from bulk
13740 tissue samples. This is a companion package to the publication \"A
13741 single-cell transcriptomic map of the human and mouse pancreas reveals inter-
13742 and intra-cell population structure.\" Baron et al. Cell Systems (2016)
13743 @url{https://www.ncbi.nlm.nih.gov/pubmed/27667365}.")
13744 (license license:gpl2+))))
13746 (define-public porechop
13747 ;; The recommended way to install is to clone the git repository
13748 ;; https://github.com/rrwick/Porechop#installation
13749 (let ((commit "289d5dca4a5fc327f97b3f8cecb68ecaf1014861")
13753 (version (git-version "0.2.3" revision commit))
13757 (uri (git-reference
13758 (url "https://github.com/rrwick/Porechop.git")
13760 (file-name (git-file-name name version))
13762 (base32 "05ps43gig0d3ia9x5lj84lb00hbsl6ba9n7y7jz927npxbr2ym23"))))
13763 (build-system python-build-system)
13764 (home-page "https://github.com/rrwick/porechop")
13765 (synopsis "Finding, trimming or splitting adapters, in Oxford Nanopore reads")
13767 "The porechop package is a tool for finding and removing adapters from Oxford
13768 Nanopore reads. Adapters on the ends of reads are trimmed off, and when a read
13769 has an adapter in its middle, it is treated as chimeric and chopped into
13770 separate reads. Porechop performs thorough alignments to effectively find
13771 adapters, even at low sequence identity. Porechop also supports demultiplexing
13772 of Nanopore reads that were barcoded with the Native Barcoding Kit, PCR
13773 Barcoding Kit or Rapid Barcoding Kit.")
13774 (license license:gpl3+))))
13776 (define-public poretools
13777 ;; The latest release was in 2016 and the latest commit is from 2017
13778 ;; the recommended way to install is to clone the git repository
13779 ;; https://poretools.readthedocs.io/en/latest/content/installation.html
13780 (let ((commit "e426b1f09e86ac259a00c261c79df91510777407")
13784 (version (git-version "0.6.0" revision commit))
13788 (uri (git-reference
13789 (url "https://github.com/arq5x/poretools.git")
13791 (file-name (git-file-name name version))
13793 (base32 "0bglj833wxpp3cq430p1d3xp085ls221js2y90w7ir2x5ay8l7am"))))
13794 (build-system python-build-system)
13795 ;; requires python >=2.7, <3.0, and the same for python dependencies
13796 (arguments `(#:python ,python-2))
13800 `(("python-dateutil" ,python2-dateutil)
13801 ("python-h5py" ,python2-h5py)
13802 ("python-matplotlib" ,python2-matplotlib)
13803 ("python-pandas" ,python2-pandas)
13804 ("python-seaborn" ,python2-seaborn)))
13805 (home-page "https://poretools.readthedocs.io")
13806 (synopsis "Toolkit for working with nanopore sequencing data")
13808 "The MinION from Oxford Nanopore Technologies is a nanopore sequencer.
13809 This @code{poretools} package is a flexible toolkit for exploring datasets
13810 generated by nanopore sequencing devices for the purposes of quality control and
13811 downstream analysis. Poretools operates directly on the native FAST5, a variant
13812 of the Hierarchical Data Format (HDF5) standard.")
13813 (license license:expat))))
13815 (define-public r-absfiltergsea
13817 (name "r-absfiltergsea")
13822 (uri (cran-uri "AbsFilterGSEA" version))
13824 (base32 "15srxkxsvn38kd5frdrwfdf0ad8gskrd0h01wmdf9hglq8fjrp7w"))))
13825 (properties `((upstream-name . "AbsFilterGSEA")))
13826 (build-system r-build-system)
13828 `(("r-biobase" ,r-biobase)
13829 ("r-deseq" ,r-deseq)
13830 ("r-limma" ,r-limma)
13832 ("r-rcpparmadillo" ,r-rcpparmadillo)))
13833 (home-page "https://cran.r-project.org/web/packages/AbsFilterGSEA/")
13834 (synopsis "Improved false positive control of gene-permuting with absolute filtering")
13836 "This package provides a function that performs gene-permuting of a gene-set
13837 enrichment analysis (GSEA) calculation with or without the absolute filtering.
13838 Without filtering, users can perform (original) two-tailed or one-tailed
13840 (license license:gpl2)))
13842 (define-public jamm
13845 (version "1.0.7.5")
13849 (uri (git-reference
13850 (url "https://github.com/mahmoudibrahim/JAMM.git")
13851 (commit (string-append "JAMMv" version))))
13852 (file-name (git-file-name name version))
13855 "0ls889jcma1ch9h21jjhnkadgszgqj41842hhcjh6cg88f85qf3i"))))
13856 (build-system gnu-build-system)
13858 `(#:tests? #f ; there are none
13860 (modify-phases %standard-phases
13861 (delete 'configure)
13864 (lambda* (#:key inputs outputs #:allow-other-keys)
13865 (let* ((out (assoc-ref outputs "out"))
13866 (libexec (string-append out "/libexec/jamm"))
13867 (bin (string-append out "/bin")))
13868 (substitute* '("JAMM.sh"
13869 "SignalGenerator.sh")
13871 (string-append "sPath=\"" libexec "\"\n")))
13872 (for-each (lambda (file)
13873 (install-file file libexec))
13874 (list "bincalculator.r"
13886 (chmod script #o555)
13887 (install-file script bin)
13888 (wrap-program (string-append bin "/" script)
13889 `("PATH" ":" prefix
13890 (,(string-append (assoc-ref inputs "coreutils") "/bin")
13891 ,(string-append (assoc-ref inputs "gawk") "/bin")
13892 ,(string-append (assoc-ref inputs "perl") "/bin")
13893 ,(string-append (assoc-ref inputs "r-minimal") "/bin")))
13894 `("PERL5LIB" ":" prefix (,(getenv "PERL5LIB")))
13895 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
13896 (list "JAMM.sh" "SignalGenerator.sh")))
13900 ("coreutils" ,coreutils)
13903 ("r-minimal" ,r-minimal)
13904 ;;("r-parallel" ,r-parallel)
13905 ("r-signal" ,r-signal)
13906 ("r-mclust" ,r-mclust)))
13907 (home-page "https://github.com/mahmoudibrahim/JAMM")
13908 (synopsis "Peak finder for NGS datasets")
13910 "JAMM is a peak finder for next generation sequencing datasets (ChIP-Seq,
13911 ATAC-Seq, DNase-Seq, etc.) that can integrate replicates and assign peak
13912 boundaries accurately. JAMM is applicable to both broad and narrow
13914 (license license:gpl3+)))
13916 (define-public ngless
13923 (uri (git-reference
13924 (url "https://gitlab.com/ngless/ngless.git")
13925 (commit (string-append "v" version))))
13926 (file-name (git-file-name name version))
13929 "0mc2gi7h4lx74zylvyp76mvc0w6706j858ii9vlgzqsw6acpr117"))))
13930 (build-system haskell-build-system)
13932 `(#:haddock? #f ; The haddock phase fails with: NGLess/CmdArgs.hs:20:1:
13933 ; error: parse error on input import
13934 ; import Options.Applicative
13936 (modify-phases %standard-phases
13937 (add-after 'unpack 'create-cabal-file
13938 (lambda _ (invoke "hpack") #t))
13939 ;; These tools are expected to be installed alongside ngless.
13940 (add-after 'install 'link-tools
13941 (lambda* (#:key inputs outputs #:allow-other-keys)
13942 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
13943 (symlink (string-append (assoc-ref inputs "prodigal")
13945 (string-append bin "ngless-" ,version "-prodigal"))
13946 (symlink (string-append (assoc-ref inputs "minimap2")
13948 (string-append bin "ngless-" ,version "-minimap2"))
13949 (symlink (string-append (assoc-ref inputs "samtools")
13951 (string-append bin "ngless-" ,version "-samtools"))
13952 (symlink (string-append (assoc-ref inputs "bwa")
13954 (string-append bin "ngless-" ,version "-bwa"))
13957 `(("prodigal" ,prodigal)
13959 ("samtools" ,samtools)
13960 ("minimap2" ,minimap2)
13961 ("ghc-aeson" ,ghc-aeson)
13962 ("ghc-ansi-terminal" ,ghc-ansi-terminal)
13963 ("ghc-async" ,ghc-async)
13964 ("ghc-atomic-write" ,ghc-atomic-write)
13965 ("ghc-bytestring-lexing" ,ghc-bytestring-lexing)
13966 ("ghc-chart" ,ghc-chart)
13967 ("ghc-chart-cairo" ,ghc-chart-cairo)
13968 ("ghc-conduit" ,ghc-conduit)
13969 ("ghc-conduit-algorithms" ,ghc-conduit-algorithms)
13970 ("ghc-conduit-combinators" ,ghc-conduit-combinators)
13971 ("ghc-conduit-extra" ,ghc-conduit-extra)
13972 ("ghc-configurator" ,ghc-configurator)
13973 ("ghc-convertible" ,ghc-convertible)
13974 ("ghc-data-default" ,ghc-data-default)
13975 ("ghc-double-conversion" ,ghc-double-conversion)
13976 ("ghc-edit-distance" ,ghc-edit-distance)
13977 ("ghc-either" ,ghc-either)
13978 ("ghc-errors" ,ghc-errors)
13979 ("ghc-extra" ,ghc-extra)
13980 ("ghc-filemanip" ,ghc-filemanip)
13981 ("ghc-file-embed" ,ghc-file-embed)
13982 ("ghc-gitrev" ,ghc-gitrev)
13983 ("ghc-hashtables" ,ghc-hashtables)
13984 ("ghc-http-conduit" ,ghc-http-conduit)
13985 ("ghc-inline-c" ,ghc-inline-c)
13986 ("ghc-inline-c-cpp" ,ghc-inline-c-cpp)
13987 ("ghc-intervalmap" ,ghc-intervalmap)
13988 ("ghc-missingh" ,ghc-missingh)
13989 ("ghc-optparse-applicative" ,ghc-optparse-applicative)
13990 ("ghc-parsec" ,ghc-parsec)
13991 ("ghc-regex" ,ghc-regex)
13992 ("ghc-safe" ,ghc-safe)
13993 ("ghc-safeio" ,ghc-safeio)
13994 ("ghc-strict" ,ghc-strict)
13995 ("ghc-tar" ,ghc-tar)
13996 ("ghc-text" ,ghc-text)
13997 ("ghc-unliftio" ,ghc-unliftio)
13998 ("ghc-unliftio-core" ,ghc-unliftio-core)
13999 ("ghc-vector" ,ghc-vector)
14000 ("ghc-yaml" ,ghc-yaml)
14001 ("ghc-zlib" ,ghc-zlib)))
14004 ("r-hdf5r" ,r-hdf5r)
14005 ("r-iterators" ,r-iterators)
14006 ("r-itertools" ,r-itertools)
14007 ("r-matrix" ,r-matrix)))
14009 `(("ghc-hpack" ,ghc-hpack)
14010 ("ghc-quickcheck" ,ghc-quickcheck)
14011 ("ghc-test-framework" ,ghc-test-framework)
14012 ("ghc-test-framework-hunit",ghc-test-framework-hunit)
14013 ("ghc-test-framework-quickcheck2" ,ghc-test-framework-quickcheck2)
14014 ("ghc-test-framework-th" ,ghc-test-framework-th)))
14015 (home-page "https://gitlab.com/ngless/ngless")
14016 (synopsis "DSL for processing next-generation sequencing data")
14017 (description "Ngless is a domain-specific language for
14018 @dfn{next-generation sequencing} (NGS) data processing.")
14019 (license license:expat)))
14021 (define-public filtlong
14022 ;; The recommended way to install is to clone the git repository
14023 ;; https://github.com/rrwick/Filtlong#installation
14024 ;; and the lastest release is more than nine months old
14025 (let ((commit "d1bb46dfe8bc7efe6257b5ce222c04bfe8aedaab")
14029 (version (git-version "0.2.0" revision commit))
14033 (uri (git-reference
14034 (url "https://github.com/rrwick/Filtlong.git")
14036 (file-name (git-file-name name version))
14038 (base32 "1xr92r820x8qlkcr3b57iw223yq8vjgyi42jr79w2xgw47qzr575"))))
14039 (build-system gnu-build-system)
14041 `(#:tests? #f ; no check target
14043 (modify-phases %standard-phases
14044 (delete 'configure)
14046 (lambda* (#:key outputs #:allow-other-keys)
14047 (let* ((out (assoc-ref outputs "out"))
14048 (bin (string-append out "/bin"))
14049 (scripts (string-append out "/share/filtlong/scripts")))
14050 (install-file "bin/filtlong" bin)
14051 (install-file "scripts/histogram.py" scripts)
14052 (install-file "scripts/read_info_histograms.sh" scripts))
14054 (add-after 'install 'wrap-program
14055 (lambda* (#:key inputs outputs #:allow-other-keys)
14056 (let* ((out (assoc-ref outputs "out"))
14057 (path (getenv "PYTHONPATH")))
14058 (wrap-program (string-append out
14059 "/share/filtlong/scripts/histogram.py")
14060 `("PYTHONPATH" ":" prefix (,path))))
14062 (add-before 'check 'patch-tests
14064 (substitute* "scripts/read_info_histograms.sh"
14065 (("awk") (which "gawk")))
14068 `(("gawk" ,gawk) ;for read_info_histograms.sh
14069 ("python" ,python-2) ;required for histogram.py
14071 (home-page "https://github.com/rrwick/Filtlong/")
14072 (synopsis "Tool for quality filtering of Nanopore and PacBio data")
14074 "The Filtlong package is a tool for filtering long reads by quality.
14075 It can take a set of long reads and produce a smaller, better subset. It uses
14076 both read length (longer is better) and read identity (higher is better) when
14077 choosing which reads pass the filter.")
14078 (license (list license:gpl3 ;filtlong
14079 license:asl2.0))))) ;histogram.py
14081 (define-public nanopolish
14082 ;; The recommended way to install is to clone the git repository
14083 ;; <https://github.com/jts/nanopolish#installing-a-particular-release>.
14084 ;; Also, the differences between release and current version seem to be
14086 (let ((commit "50e8b5cc62f9b46f5445f5c5e8c5ab7263ea6d9d")
14089 (name "nanopolish")
14090 (version (git-version "0.10.2" revision commit))
14094 (uri (git-reference
14095 (url "https://github.com/jts/nanopolish.git")
14098 (file-name (git-file-name name version))
14100 (base32 "09j5gz57yr9i34a27vbl72i4g8syv2zzgmsfyjq02yshmnrvkjs6"))
14101 (modules '((guix build utils)))
14104 (delete-file-recursively "htslib")
14106 (build-system gnu-build-system)
14109 `("HDF5=noinstall" "EIGEN=noinstall" "HTS=noinstall" "CC=gcc")
14110 #:tests? #f ; no check target
14112 (modify-phases %standard-phases
14113 (add-after 'unpack 'find-eigen
14114 (lambda* (#:key inputs #:allow-other-keys)
14116 (string-append (assoc-ref inputs "eigen")
14117 "/include/eigen3"))
14119 (delete 'configure)
14121 (lambda* (#:key outputs #:allow-other-keys)
14122 (let* ((out (assoc-ref outputs "out"))
14123 (bin (string-append out "/bin"))
14124 (scripts (string-append out "/share/nanopolish/scripts")))
14126 (install-file "nanopolish" bin)
14127 (for-each (lambda (file) (install-file file scripts))
14128 (find-files "scripts" ".*"))
14130 (add-after 'install 'wrap-programs
14131 (lambda* (#:key outputs #:allow-other-keys)
14132 (for-each (lambda (file)
14133 (wrap-program file `("PYTHONPATH" ":" prefix (,path))))
14134 (find-files "/share/nanopolish/scripts" "\\.py"))
14135 (for-each (lambda (file)
14136 (wrap-program file `("PERL5LIB" ":" prefix (,path))))
14137 (find-files "/share/nanopolish/scripts" "\\.pl"))
14144 ("python" ,python-wrapper)
14145 ("python-biopython" ,python-biopython)
14146 ("python-numpy" ,python-numpy)
14147 ("python-pysam" ,python-pysam)
14148 ("python-scikit-learn" , python-scikit-learn)
14149 ("python-scipy" ,python-scipy)
14151 (home-page "https://github.com/jts/nanopolish")
14152 (synopsis "Signal-level analysis of Oxford Nanopore sequencing data")
14154 "This package analyses the Oxford Nanopore sequencing data at signal-level.
14155 Nanopolish can calculate an improved consensus sequence for a draft genome
14156 assembly, detect base modifications, call SNPs (Single nucleotide
14157 polymorphisms) and indels with respect to a reference genome and more.")
14158 (license license:expat))))
14160 (define-public cnvkit
14167 (uri (git-reference
14168 (url "https://github.com/etal/cnvkit.git")
14169 (commit (string-append "v" version))))
14170 (file-name (git-file-name name version))
14172 (base32 "0g2f78k68yglmj4fsfmgs8idqv3di9aj53fg0ld0hqljg8chhh82"))))
14173 (build-system python-build-system)
14175 `(("python-biopython" ,python-biopython)
14176 ("python-future" ,python-future)
14177 ("python-matplotlib" ,python-matplotlib)
14178 ("python-numpy" ,python-numpy)
14179 ("python-reportlab" ,python-reportlab)
14180 ("python-pandas" ,python-pandas)
14181 ("python-pysam" ,python-pysam)
14182 ("python-pyfaidx" ,python-pyfaidx)
14183 ("python-scipy" ,python-scipy)
14185 ("r-dnacopy" ,r-dnacopy)))
14186 (home-page "https://cnvkit.readthedocs.org/")
14187 (synopsis "Copy number variant detection from targeted DNA sequencing")
14189 "CNVkit is a Python library and command-line software toolkit to infer
14190 and visualize copy number from high-throughput DNA sequencing data. It is
14191 designed for use with hybrid capture, including both whole-exome and custom
14192 target panels, and short-read sequencing platforms such as Illumina and Ion
14194 (license license:asl2.0)))
14196 (define-public python-pyfit-sne
14198 (name "python-pyfit-sne")
14203 (uri (git-reference
14204 (url "https://github.com/KlugerLab/pyFIt-SNE.git")
14206 (file-name (git-file-name name version))
14208 (base32 "13wh3qkzs56azmmgnxib6xfr29g7xh09sxylzjpni5j0pp0rc5qw"))))
14209 (build-system python-build-system)
14211 `(("python-numpy" ,python-numpy)))
14215 `(("python-cython" ,python-cython)))
14216 (home-page "https://github.com/KlugerLab/pyFIt-SNE")
14217 (synopsis "FFT-accelerated Interpolation-based t-SNE")
14219 "t-Stochastic Neighborhood Embedding (t-SNE) is a highly successful
14220 method for dimensionality reduction and visualization of high dimensional
14221 datasets. A popular implementation of t-SNE uses the Barnes-Hut algorithm to
14222 approximate the gradient at each iteration of gradient descent. This package
14223 is a Cython wrapper for FIt-SNE.")
14224 (license license:bsd-4)))
14226 (define-public bbmap
14232 (uri (string-append
14233 "mirror://sourceforge/bbmap/BBMap_" version ".tar.gz"))
14236 "1q4rfhxcb6z3gm8zg2davjz98w22lkf4hm9ikxz9kdl93pil3wkd"))))
14237 (build-system ant-build-system)
14239 `(#:build-target "dist"
14240 #:tests? #f ; there are none
14242 (list (string-append "-Dmpijar="
14243 (assoc-ref %build-inputs "java-openmpi")
14245 #:modules ((guix build ant-build-system)
14247 (guix build java-utils))
14249 (modify-phases %standard-phases
14250 (add-after 'build 'build-jni-library
14252 (with-directory-excursion "jni"
14253 (invoke "make" "-f" "makefile.linux"))))
14254 ;; There is no install target
14255 (replace 'install (install-jars "dist"))
14256 (add-after 'install 'install-scripts-and-documentation
14257 (lambda* (#:key outputs #:allow-other-keys)
14258 (substitute* "calcmem.sh"
14259 (("\\| awk ") (string-append "| " (which "awk") " ")))
14260 (let* ((scripts (find-files "." "\\.sh$"))
14261 (out (assoc-ref outputs "out"))
14262 (bin (string-append out "/bin"))
14263 (doc (string-append out "/share/doc/bbmap"))
14264 (jni (string-append out "/lib/jni")))
14265 (substitute* scripts
14266 (("\\$DIR\"\"docs") doc)
14268 (string-append "CP=" out "/share/java/BBTools.jar\n"))
14269 (("^NATIVELIBDIR.*")
14270 (string-append "NATIVELIBDIR=" jni "\n"))
14272 (string-append "CMD=\"" (which "java"))))
14273 (for-each (lambda (script) (install-file script bin)) scripts)
14275 ;; Install JNI library
14276 (install-file "jni/libbbtoolsjni.so" jni)
14278 ;; Install documentation
14279 (install-file "docs/readme.txt" doc)
14280 (copy-recursively "docs/guides" doc))
14285 ("java-eclipse-jdt-core" ,java-eclipse-jdt-core)
14286 ("java-eclipse-jdt-compiler-apt" ,java-eclipse-jdt-compiler-apt)
14287 ("java-openmpi" ,java-openmpi)))
14288 (home-page "http://sourceforge.net/projects/bbmap/")
14289 (synopsis "Aligner and other tools for short sequencing reads")
14291 "This package provides bioinformatic tools to align, deduplicate,
14292 reformat, filter and normalize DNA and RNA-seq data. It includes the
14293 following tools: BBMap, a short read aligner for DNA and RNA-seq data; BBNorm,
14294 a kmer-based error-correction and normalization tool; Dedupe, a tool to
14295 simplify assemblies by removing duplicate or contained subsequences that share
14296 a target percent identity; Reformat, to convert reads between
14297 fasta/fastq/scarf/fasta+qual/sam, interleaved/paired, and ASCII-33/64, at over
14298 500 MB/s; and BBDuk, a tool to filter, trim, or mask reads with kmer matches
14299 to an artifact/contaminant file.")
14300 (license license:bsd-3)))
14302 (define-public velvet
14308 (uri (string-append "https://www.ebi.ac.uk/~zerbino/velvet/"
14309 "velvet_" version ".tgz"))
14312 "0h3njwy66p6bx14r3ar1byb0ccaxmxka4c65rn4iybyiqa4d8kc8"))
14313 ;; Delete bundled libraries
14314 (modules '((guix build utils)))
14317 (delete-file "Manual.pdf")
14318 (delete-file-recursively "third-party")
14320 (build-system gnu-build-system)
14322 `(#:make-flags '("OPENMP=t")
14323 #:test-target "test"
14325 (modify-phases %standard-phases
14326 (delete 'configure)
14327 (add-after 'unpack 'fix-zlib-include
14329 (substitute* "src/binarySequences.c"
14330 (("../third-party/zlib-1.2.3/zlib.h") "zlib.h"))
14333 (lambda* (#:key outputs #:allow-other-keys)
14334 (let* ((out (assoc-ref outputs "out"))
14335 (bin (string-append out "/bin"))
14336 (doc (string-append out "/share/doc/velvet")))
14339 (install-file "velveth" bin)
14340 (install-file "velvetg" bin)
14341 (install-file "Manual.pdf" doc)
14342 (install-file "Columbus_manual.pdf" doc)
14345 `(("openmpi" ,openmpi)
14348 `(("texlive" ,(texlive-union (list texlive-latex-graphics
14349 texlive-latex-hyperref)))))
14350 (home-page "https://www.ebi.ac.uk/~zerbino/velvet/")
14351 (synopsis "Nucleic acid sequence assembler for very short reads")
14353 "Velvet is a de novo genomic assembler specially designed for short read
14354 sequencing technologies, such as Solexa or 454. Velvet currently takes in
14355 short read sequences, removes errors then produces high quality unique
14356 contigs. It then uses paired read information, if available, to retrieve the
14357 repeated areas between contigs.")
14358 (license license:gpl2+)))
14360 (define-public python-velocyto
14362 (name "python-velocyto")
14363 (version "0.17.17")
14367 (uri (pypi-uri "velocyto" version))
14370 "0fgygyzqgrq32dv6a00biq1p1cwi6kbl5iqblxq1kklj6b2mzmhs"))))
14371 (build-system python-build-system)
14373 `(("python-click" ,python-click)
14374 ("python-cython" ,python-cython)
14375 ("python-h5py" ,python-h5py)
14376 ("python-loompy" ,python-loompy)
14377 ("python-matplotlib" ,python-matplotlib)
14378 ("python-numba" ,python-numba)
14379 ("python-numpy" ,python-numpy)
14380 ("python-pandas" ,python-pandas)
14381 ("python-pysam" ,python-pysam)
14382 ("python-scikit-learn" ,python-scikit-learn)
14383 ("python-scipy" ,python-scipy)))
14384 (home-page "https://github.com/velocyto-team/velocyto.py")
14385 (synopsis "RNA velocity analysis for single cell RNA-seq data")
14387 "Velocyto is a library for the analysis of RNA velocity. Velocyto
14388 includes a command line tool and an analysis pipeline.")
14389 (license license:bsd-2)))
14391 (define-public arriba
14398 (uri (string-append "https://github.com/suhrig/arriba/releases/"
14399 "download/v" version "/arriba_v" version ".tar.gz"))
14402 "0jx9656ry766vb8z08m1c3im87b0c82qpnjby9wz4kcz8vn87dx2"))))
14403 (build-system gnu-build-system)
14405 `(#:tests? #f ; there are none
14407 (modify-phases %standard-phases
14408 (replace 'configure
14409 (lambda* (#:key inputs #:allow-other-keys)
14410 (let ((htslib (assoc-ref inputs "htslib")))
14411 (substitute* "Makefile"
14412 (("-I\\$\\(HTSLIB\\)/htslib")
14413 (string-append "-I" htslib "/include/htslib"))
14414 ((" \\$\\(HTSLIB\\)/libhts.a")
14415 (string-append " " htslib "/lib/libhts.so"))))
14416 (substitute* "run_arriba.sh"
14417 (("^STAR ") (string-append (which "STAR") " "))
14418 (("samtools --version-only")
14419 (string-append (which "samtools") " --version-only"))
14420 (("samtools index")
14421 (string-append (which "samtools") " index"))
14423 (string-append (which "samtools") " sort")))
14426 (lambda* (#:key outputs #:allow-other-keys)
14427 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
14428 (install-file "arriba" bin)
14429 (install-file "run_arriba.sh" bin)
14430 (install-file "draw_fusions.R" bin)
14431 (wrap-program (string-append bin "/draw_fusions.R")
14432 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
14435 `(("htslib" ,htslib)
14436 ("r-minimal" ,r-minimal)
14437 ("r-circlize" ,r-circlize)
14438 ("r-genomicalignments" ,r-genomicalignments)
14439 ("r-genomicranges" ,r-genomicranges)
14440 ("samtools" ,samtools)
14443 (home-page "https://github.com/suhrig/arriba")
14444 (synopsis "Gene fusion detection from RNA-Seq data ")
14446 "Arriba is a command-line tool for the detection of gene fusions from
14447 RNA-Seq data. It was developed for the use in a clinical research setting.
14448 Therefore, short runtimes and high sensitivity were important design criteria.
14449 It is based on the fast STAR aligner and the post-alignment runtime is
14450 typically just around two minutes. In contrast to many other fusion detection
14451 tools which build on STAR, Arriba does not require to reduce the
14452 @code{alignIntronMax} parameter of STAR to detect small deletions.")
14453 ;; All code is under the Expat license with the exception of
14454 ;; "draw_fusions.R", which is under GPLv3.
14455 (license (list license:expat license:gpl3))))
14457 (define-public adapterremoval
14459 (name "adapterremoval")
14464 (uri (git-reference
14465 (url "https://github.com/MikkelSchubert/adapterremoval.git")
14466 (commit (string-append "v" version))))
14467 (file-name (git-file-name name version))
14470 "1nf3ki5pfzalhrx2fr1y6pfqfi133yj2m7q4fj9irf5fb94bapwr"))))
14471 (build-system gnu-build-system)
14473 `(#:make-flags (list "COLOR_BUILD=no"
14474 (string-append "PREFIX="
14475 (assoc-ref %outputs "out")))
14476 #:test-target "test"
14478 (modify-phases %standard-phases
14479 (delete 'configure))))
14482 (home-page "https://adapterremoval.readthedocs.io/")
14483 (synopsis "Rapid sequence adapter trimming, identification, and read merging")
14485 "This program searches for and removes remnant adapter sequences from
14486 @dfn{High-Throughput Sequencing} (HTS) data and (optionally) trims low quality
14487 bases from the 3' end of reads following adapter removal. AdapterRemoval can
14488 analyze both single end and paired end data, and can be used to merge
14489 overlapping paired-ended reads into (longer) consensus sequences.
14490 Additionally, the AdapterRemoval may be used to recover a consensus adapter
14491 sequence for paired-ended data, for which this information is not available.")
14492 (license license:gpl3+)))
14494 (define-public pplacer
14495 (let ((commit "807f6f3"))
14498 ;; The commit should be updated with each version change.
14499 (version "1.1.alpha19")
14503 (uri (git-reference
14504 (url "https://github.com/matsen/pplacer.git")
14505 (commit (string-append "v" version))))
14506 (file-name (git-file-name name version))
14508 (base32 "11ppbbbx20p2g9wj3ff64dhnarb12q79v7qh4rk0gj6lkbz4n7cn"))))
14509 (build-system ocaml-build-system)
14511 `(#:modules ((guix build ocaml-build-system)
14515 (modify-phases %standard-phases
14516 (delete 'configure)
14517 (add-after 'unpack 'fix-build-with-latest-ocaml
14519 (substitute* "myocamlbuild.ml"
14520 (("dep \\[\"c_pam\"\\]" m)
14521 (string-append "flag [\"ocaml\"; \"compile\"] (A \"-unsafe-string\");\n"
14523 (("let run_and_read" m)
14528 let pos = String.index s ch in
14529 x := (String.before s pos)::!x;
14530 go (String.after s (pos + 1))
14533 with Not_found -> !x
14534 let split_nl s = split s '\\n'
14535 let before_space s =
14536 try String.before s (String.index s ' ')
14537 with Not_found -> s
14540 (("run_and_read \"ocamlfind list \\| cut -d' ' -f1\"" m)
14541 (string-append "List.map before_space (split_nl & " m ")"))
14542 ((" blank_sep_strings &") "")
14543 ((" Lexing.from_string &") ""))
14545 (add-after 'unpack 'replace-bundled-cddlib
14546 (lambda* (#:key inputs #:allow-other-keys)
14547 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
14548 (local-dir "cddlib_guix"))
14550 (with-directory-excursion local-dir
14551 (invoke "tar" "xvf" cddlib-src))
14552 (let ((cddlib-src-folder
14553 (string-append local-dir "/"
14554 (list-ref (scandir local-dir) 2)
14556 (for-each make-file-writable (find-files "cdd_src" ".*"))
14560 (string-append "cdd_src/" (basename file))))
14561 (find-files cddlib-src-folder ".*[ch]$")))
14563 (add-after 'unpack 'fix-makefile
14565 ;; Remove system calls to 'git'.
14566 (substitute* "Makefile"
14567 (("^DESCRIPT:=pplacer-.*")
14569 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
14570 (substitute* "myocamlbuild.ml"
14571 (("git describe --tags --long .*\\\" with")
14573 "echo -n v" ,version "-" ,commit "\" with")))
14576 (lambda* (#:key outputs #:allow-other-keys)
14577 (let* ((out (assoc-ref outputs "out"))
14578 (bin (string-append out "/bin")))
14579 (copy-recursively "bin" bin))
14582 `(("zlib" ,zlib "static")
14584 ("ocaml-ounit" ,ocaml-ounit)
14585 ("ocaml-batteries" ,ocaml-batteries)
14586 ("ocaml-camlzip" ,camlzip)
14587 ("ocaml-csv" ,ocaml-csv)
14588 ("ocaml-sqlite3" ,ocaml-sqlite3)
14589 ("ocaml-xmlm" ,ocaml-xmlm)
14590 ("ocaml-mcl" ,ocaml-mcl)
14591 ("ocaml-gsl" ,ocaml-gsl-1)))
14593 `(("cddlib-src" ,(package-source cddlib))
14594 ("ocamlbuild" ,ocamlbuild)
14595 ("pkg-config" ,pkg-config)))
14597 `(("pplacer-scripts" ,pplacer-scripts)))
14598 (synopsis "Phylogenetic placement of biological sequences")
14600 "Pplacer places query sequences on a fixed reference phylogenetic tree
14601 to maximize phylogenetic likelihood or posterior probability according to a
14602 reference alignment. Pplacer is designed to be fast, to give useful
14603 information about uncertainty, and to offer advanced visualization and
14604 downstream analysis.")
14605 (home-page "http://matsen.fhcrc.org/pplacer")
14606 (license license:gpl3))))
14608 ;; This package is installed alongside 'pplacer'. It is a separate package so
14609 ;; that it can use the python-build-system for the scripts that are
14610 ;; distributed alongside the main OCaml binaries.
14611 (define pplacer-scripts
14614 (name "pplacer-scripts")
14615 (build-system python-build-system)
14617 `(#:python ,python-2
14619 (modify-phases %standard-phases
14620 (add-after 'unpack 'enter-scripts-dir
14621 (lambda _ (chdir "scripts") #t))
14623 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t))
14624 (add-after 'install 'wrap-executables
14625 (lambda* (#:key inputs outputs #:allow-other-keys)
14626 (let* ((out (assoc-ref outputs "out"))
14627 (bin (string-append out "/bin")))
14628 (let ((path (string-append
14629 (assoc-ref inputs "hmmer") "/bin:"
14630 (assoc-ref inputs "infernal") "/bin")))
14632 (wrap-program (string-append bin "/refpkg_align.py")
14633 `("PATH" ":" prefix (,path))))
14634 (let ((path (string-append
14635 (assoc-ref inputs "hmmer") "/bin")))
14636 (wrap-program (string-append bin "/hrefpkg_query.py")
14637 `("PATH" ":" prefix (,path)))))
14640 `(("infernal" ,infernal)
14643 `(("python-biopython" ,python2-biopython)
14644 ("taxtastic" ,taxtastic)))
14645 (synopsis "Pplacer Python scripts")))
14647 (define-public python2-checkm-genome
14649 (name "python2-checkm-genome")
14654 (uri (pypi-uri "checkm-genome" version))
14657 "0bm8gpxjmzxsxxl8lzwqhgx8g1dlnmp6znz7wv3hgb0gdjbf9dzz"))))
14658 (build-system python-build-system)
14660 `(#:python ,python-2
14661 #:tests? #f)) ; some tests are interactive
14663 `(("python-dendropy" ,python2-dendropy)
14664 ("python-matplotlib" ,python2-matplotlib)
14665 ("python-numpy" ,python2-numpy)
14666 ("python-pysam" ,python2-pysam)
14667 ("python-scipy" ,python2-scipy)))
14668 (home-page "http://pypi.python.org/pypi/checkm/")
14669 (synopsis "Assess the quality of putative genome bins")
14671 "CheckM provides a set of tools for assessing the quality of genomes
14672 recovered from isolates, single cells, or metagenomes. It provides robust
14673 estimates of genome completeness and contamination by using collocated sets of
14674 genes that are ubiquitous and single-copy within a phylogenetic lineage.
14675 Assessment of genome quality can also be examined using plots depicting key
14676 genomic characteristics (e.g., GC, coding density) which highlight sequences
14677 outside the expected distributions of a typical genome. CheckM also provides
14678 tools for identifying genome bins that are likely candidates for merging based
14679 on marker set compatibility, similarity in genomic characteristics, and
14680 proximity within a reference genome.")
14681 (license license:gpl3+)))
14683 (define-public umi-tools
14690 (uri (pypi-uri "umi_tools" version))
14693 "08y3vz1vcx09whmbsn722lcs6jl9wyrh9i4p3k8j4cb1i32bij4a"))))
14694 (build-system python-build-system)
14696 `(("python-setuptools" ,python-setuptools)
14697 ("python-pandas" ,python-pandas)
14698 ("python-future" ,python-future)
14699 ("python-scipy" ,python-scipy)
14700 ("python-matplotlib" ,python-matplotlib)
14701 ("python-regex" ,python-regex)
14702 ("python-pysam" ,python-pysam)))
14704 `(("python-setuptools" ,python-setuptools)
14705 ("python-cython" ,python-cython)))
14706 (home-page "https://github.com/CGATOxford/UMI-tools")
14707 (synopsis "Tools for analyzing unique modular identifiers")
14708 (description "This package provides tools for dealing with @dfn{Unique
14709 Molecular Identifiers} (UMIs) and @dfn{Random Molecular Tags} (RMTs) in
14710 genetic sequences. There are six tools: the @code{extract} and
14711 @code{whitelist} commands are used to prepare a fastq containing UMIs @code{+/-}
14712 cell barcodes for alignment. The remaining commands, @code{group},
14713 @code{dedup}, and @{count}/@code{count_tab}, are used to identify PCR
14714 duplicates using the UMIs and perform different levels of analysis depending
14715 on the needs of the user.")
14716 (license license:expat)))
14718 (define-public ataqv
14725 (uri (git-reference
14726 (url "https://github.com/ParkerLab/ataqv.git")
14728 (file-name (git-file-name name version))
14731 "031xr6jx1aprh26y5b1lv3gzrlmzg4alfl73vvshymx8cq8asrqi"))))
14732 (build-system gnu-build-system)
14735 (list (string-append "prefix=" (assoc-ref %outputs "out"))
14736 (string-append "BOOST_ROOT="
14737 (assoc-ref %build-inputs "boost"))
14738 (string-append "HTSLIB_ROOT="
14739 (assoc-ref %build-inputs "htslib")))
14740 #:test-target "test"
14742 (modify-phases %standard-phases
14743 (delete 'configure))))
14747 ("ncurses" ,ncurses)
14751 (home-page "https://github.com/ParkerLab/ataqv")
14752 (synopsis "Toolkit for quality control and visualization of ATAC-seq data")
14753 (description "This package provides a toolkit for measuring and comparing
14754 ATAC-seq results. It was written to make it easier to spot differences that
14755 might be caused by ATAC-seq library prep or sequencing. The main program,
14756 @code{ataqv}, examines aligned reads and reports some basic metrics.")
14757 (license license:gpl3+)))