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 "01l4jczglkl7yfhgvzx8j0df7k54bk1r8sli9ll16i1mis0d8f37"))
4182 (modules '((guix build utils)))
4185 ;; Delete bundled libraries. We do not replace the bundled seqan
4186 ;; as it is a modified subset of the old version 1.4.1.
4188 ;; We do not replace the bundled MurmurHash as the canonical
4189 ;; repository for this code 'SMHasher' is unsuitable for providing
4191 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
4192 (delete-file-recursively "third-party/zlib")
4193 (delete-file-recursively "third-party/bzip2")
4194 (delete-file-recursively "third-party/seqan")
4195 (substitute* "setup.cfg"
4196 (("# libraries = z,bz2")
4197 "libraries = z,bz2")
4198 (("include:third-party/zlib:third-party/bzip2")
4201 (build-system python-build-system)
4204 (modify-phases %standard-phases
4205 (add-after 'unpack 'set-cc
4206 (lambda _ (setenv "CC" "gcc") #t))
4207 ;; FIXME: This fails with "permission denied".
4208 (delete 'reset-gzip-timestamps))))
4210 `(("python-cython" ,python-cython)
4211 ("python-pytest" ,python-pytest)
4212 ("python-pytest-runner" ,python-pytest-runner)))
4217 ("python-screed" ,python-screed)
4218 ("python-bz2file" ,python-bz2file)))
4219 (home-page "https://khmer.readthedocs.org/")
4220 (synopsis "K-mer counting, filtering and graph traversal library")
4221 (description "The khmer software is a set of command-line tools for
4222 working with DNA shotgun sequencing data from genomes, transcriptomes,
4223 metagenomes and single cells. Khmer can make de novo assemblies faster, and
4224 sometimes better. Khmer can also identify and fix problems with shotgun
4226 ;; When building on i686, armhf and mips64el, we get the following error:
4227 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
4228 (supported-systems '("x86_64-linux" "aarch64-linux"))
4229 (license license:bsd-3)))
4231 (define-public kaiju
4238 (url "https://github.com/bioinformatics-centre/kaiju")
4239 (commit (string-append "v" version))))
4240 (file-name (git-file-name name version))
4243 "119pzi0ddzv9mjg4wwa6han0cwr3k3ssn7kirvsjfcq05mi5ka0x"))))
4244 (build-system gnu-build-system)
4246 `(#:tests? #f ; There are no tests.
4248 (modify-phases %standard-phases
4250 (add-before 'build 'move-to-src-dir
4251 (lambda _ (chdir "src") #t))
4253 (lambda* (#:key inputs outputs #:allow-other-keys)
4254 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
4257 (copy-recursively "bin" bin))
4262 (home-page "http://kaiju.binf.ku.dk/")
4263 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
4264 (description "Kaiju is a program for sensitive taxonomic classification
4265 of high-throughput sequencing reads from metagenomic whole genome sequencing
4267 (license license:gpl3+)))
4272 (version "2.1.1.20160309")
4275 (uri (pypi-uri "MACS2" version))
4278 "09ixspd1vcqmz1c81ih70xs4m7qml2iy5vyx1y74zww3iy1vl210"))))
4279 (build-system python-build-system)
4281 `(#:python ,python-2 ; only compatible with Python 2.7
4282 #:tests? #f)) ; no test target
4284 `(("python-numpy" ,python2-numpy)))
4285 (home-page "https://github.com/taoliu/MACS/")
4286 (synopsis "Model based analysis for ChIP-Seq data")
4288 "MACS is an implementation of a ChIP-Seq analysis algorithm for
4289 identifying transcript factor binding sites named Model-based Analysis of
4290 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
4291 the significance of enriched ChIP regions and it improves the spatial
4292 resolution of binding sites through combining the information of both
4293 sequencing tag position and orientation.")
4294 (license license:bsd-3)))
4296 (define-public mafft
4303 "https://mafft.cbrc.jp/alignment/software/mafft-" version
4304 "-without-extensions-src.tgz"))
4305 (file-name (string-append name "-" version ".tgz"))
4308 "0bacjkxfg944p5khhyh5rd4y7wkjc9qk4v2jjj442sqlq0f8ar7b"))))
4309 (build-system gnu-build-system)
4311 `(#:tests? #f ; no automated tests, though there are tests in the read me
4312 #:make-flags (let ((out (assoc-ref %outputs "out")))
4313 (list (string-append "PREFIX=" out)
4314 (string-append "BINDIR="
4315 (string-append out "/bin"))))
4317 (modify-phases %standard-phases
4318 (add-after 'unpack 'enter-dir
4319 (lambda _ (chdir "core") #t))
4320 (add-after 'enter-dir 'patch-makefile
4322 ;; on advice from the MAFFT authors, there is no need to
4323 ;; distribute mafft-profile, mafft-distance, or
4324 ;; mafft-homologs.rb as they are too "specialised".
4325 (substitute* "Makefile"
4326 ;; remove mafft-homologs.rb from SCRIPTS
4327 (("^SCRIPTS = mafft mafft-homologs.rb")
4329 ;; remove mafft-homologs from MANPAGES
4330 (("^MANPAGES = mafft.1 mafft-homologs.1")
4331 "MANPAGES = mafft.1")
4332 ;; remove mafft-distance from PROGS
4333 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
4334 "PROGS = dvtditr dndfast7 dndblast sextet5")
4335 ;; remove mafft-profile from PROGS
4336 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
4337 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
4338 (("^rm -f mafft-profile mafft-profile.exe") "#")
4339 (("^rm -f mafft-distance mafft-distance.exe") ")#")
4340 ;; do not install MAN pages in libexec folder
4341 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
4342 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
4344 (add-after 'enter-dir 'patch-paths
4345 (lambda* (#:key inputs #:allow-other-keys)
4346 (substitute* '("pairash.c"
4348 (("perl") (which "perl"))
4349 (("([\"`| ])awk" _ prefix)
4350 (string-append prefix (which "awk")))
4351 (("grep") (which "grep")))
4354 (add-after 'install 'wrap-programs
4355 (lambda* (#:key outputs #:allow-other-keys)
4356 (let* ((out (assoc-ref outputs "out"))
4357 (bin (string-append out "/bin"))
4358 (path (string-append
4359 (assoc-ref %build-inputs "coreutils") "/bin:")))
4360 (for-each (lambda (file)
4362 `("PATH" ":" prefix (,path))))
4370 ("coreutils" ,coreutils)))
4371 (home-page "http://mafft.cbrc.jp/alignment/software/")
4372 (synopsis "Multiple sequence alignment program")
4374 "MAFFT offers a range of multiple alignment methods for nucleotide and
4375 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
4376 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
4378 (license (license:non-copyleft
4379 "http://mafft.cbrc.jp/alignment/software/license.txt"
4380 "BSD-3 with different formatting"))))
4389 (url "https://github.com/marbl/mash.git")
4390 (commit (string-append "v" version))))
4391 (file-name (git-file-name name version))
4394 "049hwcc059p2fd9vwndn63laifvvsi0wmv84i6y1fr79k15dxwy6"))
4395 (modules '((guix build utils)))
4398 ;; Delete bundled kseq.
4399 ;; TODO: Also delete bundled murmurhash and open bloom filter.
4400 (delete-file "src/mash/kseq.h")
4402 (build-system gnu-build-system)
4404 `(#:tests? #f ; No tests.
4407 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
4408 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
4409 #:make-flags (list "CC=gcc")
4411 (modify-phases %standard-phases
4412 (add-after 'unpack 'fix-includes
4414 (substitute* '("src/mash/Sketch.cpp"
4415 "src/mash/CommandFind.cpp"
4416 "src/mash/CommandScreen.cpp")
4417 (("^#include \"kseq\\.h\"")
4418 "#include \"htslib/kseq.h\""))
4420 (add-after 'fix-includes 'use-c++14
4422 ;; capnproto 0.7 requires c++14 to build
4423 (substitute* "configure.ac"
4424 (("c\\+\\+11") "c++14"))
4425 (substitute* "Makefile.in"
4426 (("c\\+\\+11") "c++14"))
4429 `(("autoconf" ,autoconf)
4430 ;; Capnproto and htslib are statically embedded in the final
4431 ;; application. Therefore we also list their licenses, below.
4432 ("capnproto" ,capnproto)
4433 ("htslib" ,htslib)))
4437 (supported-systems '("x86_64-linux"))
4438 (home-page "https://mash.readthedocs.io")
4439 (synopsis "Fast genome and metagenome distance estimation using MinHash")
4440 (description "Mash is a fast sequence distance estimator that uses the
4441 MinHash algorithm and is designed to work with genomes and metagenomes in the
4442 form of assemblies or reads.")
4443 (license (list license:bsd-3 ; Mash
4444 license:expat ; HTSlib and capnproto
4445 license:public-domain ; MurmurHash 3
4446 license:cpl1.0)))) ; Open Bloom Filter
4448 (define-public metabat
4456 (url "https://bitbucket.org/berkeleylab/metabat.git")
4457 (commit (string-append "v" version))))
4458 (file-name (git-file-name name version))
4461 "0hyg2smw1nz69mfvjpk45xyyychmda92c80a0cv7baji84ri4iyn"))
4462 (patches (search-patches "metabat-fix-compilation.patch"))))
4463 (build-system scons-build-system)
4465 `(#:scons ,scons-python2
4467 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
4468 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
4469 #:tests? #f ;; Tests are run during the build phase.
4471 (modify-phases %standard-phases
4472 (add-after 'unpack 'fix-includes
4474 (substitute* "src/BamUtils.h"
4475 (("^#include \"bam/bam\\.h\"")
4476 "#include \"samtools/bam.h\"")
4477 (("^#include \"bam/sam\\.h\"")
4478 "#include \"samtools/sam.h\""))
4479 (substitute* "src/KseqReader.h"
4480 (("^#include \"bam/kseq\\.h\"")
4481 "#include \"htslib/kseq.h\""))
4483 (add-after 'unpack 'fix-scons
4484 (lambda* (#:key inputs #:allow-other-keys)
4485 (substitute* "SConstruct"
4486 (("^htslib_dir += 'samtools'")
4487 (string-append "htslib_dir = '"
4488 (assoc-ref inputs "htslib")
4490 (("^samtools_dir = 'samtools'")
4491 (string-append "samtools_dir = '"
4492 (assoc-ref inputs "samtools")
4494 (("^findStaticOrShared\\('bam', hts_lib")
4495 (string-append "findStaticOrShared('bam', '"
4496 (assoc-ref inputs "samtools")
4498 ;; Do not distribute README.
4499 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
4504 ("samtools" ,samtools)
4507 (home-page "https://bitbucket.org/berkeleylab/metabat")
4509 "Reconstruction of single genomes from complex microbial communities")
4511 "Grouping large genomic fragments assembled from shotgun metagenomic
4512 sequences to deconvolute complex microbial communities, or metagenome binning,
4513 enables the study of individual organisms and their interactions. MetaBAT is
4514 an automated metagenome binning software, which integrates empirical
4515 probabilistic distances of genome abundance and tetranucleotide frequency.")
4516 ;; The source code contains inline assembly.
4517 (supported-systems '("x86_64-linux" "i686-linux"))
4518 (license (license:non-copyleft "file://license.txt"
4519 "See license.txt in the distribution."))))
4521 (define-public minced
4528 (url "https://github.com/ctSkennerton/minced.git")
4530 (file-name (git-file-name name version))
4533 "1f5h9him0gd355cnx7p6pnxpknhckd4g0v62mg8zyhfbx9as25fv"))))
4534 (build-system gnu-build-system)
4536 `(#:test-target "test"
4538 (modify-phases %standard-phases
4540 (add-before 'check 'fix-test
4542 ;; Fix test for latest version.
4543 (substitute* "t/Aquifex_aeolicus_VF5.expected"
4544 (("minced:0.1.6") "minced:0.2.0"))
4546 (replace 'install ; No install target.
4547 (lambda* (#:key inputs outputs #:allow-other-keys)
4548 (let* ((out (assoc-ref outputs "out"))
4549 (bin (string-append out "/bin"))
4550 (wrapper (string-append bin "/minced")))
4551 ;; Minced comes with a wrapper script that tries to figure out where
4552 ;; it is located before running the JAR. Since these paths are known
4553 ;; to us, we build our own wrapper to avoid coreutils dependency.
4554 (install-file "minced.jar" bin)
4555 (with-output-to-file wrapper
4559 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
4560 (assoc-ref inputs "jre") "/bin/java -jar "
4561 bin "/minced.jar \"$@\"\n"))))
4562 (chmod wrapper #o555))
4565 `(("jdk" ,icedtea "jdk")))
4568 ("jre" ,icedtea "out")))
4569 (home-page "https://github.com/ctSkennerton/minced")
4570 (synopsis "Mining CRISPRs in Environmental Datasets")
4572 "MinCED is a program to find Clustered Regularly Interspaced Short
4573 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
4574 unassembled metagenomic reads, but is mainly designed for full genomes and
4575 assembled metagenomic sequence.")
4576 (license license:gpl3+)))
4584 (uri (pypi-uri "misopy" version))
4587 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
4588 (modules '((guix build utils)))
4590 (substitute* "setup.py"
4591 ;; Use setuptools, or else the executables are not
4593 (("distutils.core") "setuptools")
4594 ;; use "gcc" instead of "cc" for compilation
4596 "cc.set_executables(
4600 linker_so='gcc -shared'); defines"))
4602 (build-system python-build-system)
4604 `(#:python ,python-2 ; only Python 2 is supported
4605 #:tests? #f)) ; no "test" target
4607 `(("samtools" ,samtools)
4608 ("python-numpy" ,python2-numpy)
4609 ("python-pysam" ,python2-pysam)
4610 ("python-scipy" ,python2-scipy)
4611 ("python-matplotlib" ,python2-matplotlib)))
4613 `(("python-mock" ,python2-mock) ;for tests
4614 ("python-pytz" ,python2-pytz))) ;for tests
4615 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
4616 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
4618 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
4619 the expression level of alternatively spliced genes from RNA-Seq data, and
4620 identifies differentially regulated isoforms or exons across samples. By
4621 modeling the generative process by which reads are produced from isoforms in
4622 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
4623 that a read originated from a particular isoform.")
4624 (license license:gpl2)))
4626 (define-public muscle
4629 (version "3.8.1551")
4631 (method url-fetch/tarbomb)
4633 "http://www.drive5.com/muscle/muscle_src_"
4637 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
4638 (build-system gnu-build-system)
4640 `(#:make-flags (list "LDLIBS = -lm")
4642 (modify-phases %standard-phases
4645 ;; There are no tests, so just test if it runs.
4646 (lambda _ (invoke "./muscle" "-version") #t))
4648 (lambda* (#:key outputs #:allow-other-keys)
4649 (let* ((out (assoc-ref outputs "out"))
4650 (bin (string-append out "/bin")))
4651 (install-file "muscle" bin)
4653 (home-page "http://www.drive5.com/muscle")
4654 (synopsis "Multiple sequence alignment program")
4656 "MUSCLE aims to be a fast and accurate multiple sequence alignment
4657 program for nucleotide and protein sequences.")
4658 ;; License information found in 'muscle -h' and usage.cpp.
4659 (license license:public-domain)))
4661 (define-public newick-utils
4662 ;; There are no recent releases so we package from git.
4663 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
4665 (name "newick-utils")
4666 (version (string-append "1.6-1." (string-take commit 8)))
4670 (url "https://github.com/tjunier/newick_utils.git")
4672 (file-name (string-append name "-" version "-checkout"))
4675 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4676 (build-system gnu-build-system)
4678 ;; XXX: TODO: Enable Lua and Guile bindings.
4679 ;; https://github.com/tjunier/newick_utils/issues/13
4680 `(("libxml2" ,libxml2)
4684 `(("autoconf" ,autoconf)
4685 ("automake" ,automake)
4686 ("libtool" ,libtool)))
4687 (synopsis "Programs for working with newick format phylogenetic trees")
4689 "Newick-utils is a suite of utilities for processing phylogenetic trees
4690 in Newick format. Functions include re-rooting, extracting subtrees,
4691 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4692 (home-page "https://github.com/tjunier/newick_utils")
4693 (license license:bsd-3))))
4702 "https://github.com/wwood/OrfM/releases/download/v"
4703 version "/orfm-" version ".tar.gz"))
4706 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4707 (build-system gnu-build-system)
4708 (inputs `(("zlib" ,zlib)))
4710 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4711 ("ruby-rspec" ,ruby-rspec)
4713 (synopsis "Simple and not slow open reading frame (ORF) caller")
4715 "An ORF caller finds stretches of DNA that, when translated, are not
4716 interrupted by stop codons. OrfM finds and prints these ORFs.")
4717 (home-page "https://github.com/wwood/OrfM")
4718 (license license:lgpl3+)))
4720 (define-public python2-pbcore
4722 (name "python2-pbcore")
4726 (uri (pypi-uri "pbcore" version))
4729 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4730 (build-system python-build-system)
4731 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
4733 `(("python-cython" ,python2-cython)
4734 ("python-numpy" ,python2-numpy)
4735 ("python-pysam" ,python2-pysam)
4736 ("python-h5py" ,python2-h5py)))
4738 `(("python-nose" ,python2-nose)
4739 ("python-sphinx" ,python2-sphinx)
4740 ("python-pyxb" ,python2-pyxb)))
4741 (home-page "http://pacificbiosciences.github.io/pbcore/")
4742 (synopsis "Library for reading and writing PacBio data files")
4744 "The pbcore package provides Python APIs for interacting with PacBio data
4745 files and writing bioinformatics applications.")
4746 (license license:bsd-3)))
4748 (define-public python2-warpedlmm
4750 (name "python2-warpedlmm")
4755 (uri (pypi-uri "WarpedLMM" version ".zip"))
4758 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4759 (build-system python-build-system)
4761 `(#:python ,python-2)) ; requires Python 2.7
4763 `(("python-scipy" ,python2-scipy)
4764 ("python-numpy" ,python2-numpy)
4765 ("python-matplotlib" ,python2-matplotlib)
4766 ("python-fastlmm" ,python2-fastlmm)
4767 ("python-pandas" ,python2-pandas)
4768 ("python-pysnptools" ,python2-pysnptools)))
4770 `(("python-mock" ,python2-mock)
4771 ("python-nose" ,python2-nose)
4773 (home-page "https://github.com/PMBio/warpedLMM")
4774 (synopsis "Implementation of warped linear mixed models")
4776 "WarpedLMM is a Python implementation of the warped linear mixed model,
4777 which automatically learns an optimal warping function (or transformation) for
4778 the phenotype as it models the data.")
4779 (license license:asl2.0)))
4781 (define-public pbtranscript-tofu
4782 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
4784 (name "pbtranscript-tofu")
4785 (version (string-append "2.2.3." (string-take commit 7)))
4789 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
4791 (file-name (string-append name "-" version "-checkout"))
4794 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
4795 (modules '((guix build utils)))
4798 ;; remove bundled Cython sources
4799 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
4801 (build-system python-build-system)
4803 `(#:python ,python-2
4804 ;; FIXME: Tests fail with "No such file or directory:
4805 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
4808 (modify-phases %standard-phases
4809 (add-after 'unpack 'enter-directory
4811 (chdir "pbtranscript-tofu/pbtranscript/")
4813 ;; With setuptools version 18.0 and later this setup.py hack causes
4814 ;; a build error, so we disable it.
4815 (add-after 'enter-directory 'patch-setuppy
4817 (substitute* "setup.py"
4818 (("if 'setuptools.extension' in sys.modules:")
4822 `(("python-numpy" ,python2-numpy)
4823 ("python-bx-python" ,python2-bx-python)
4824 ("python-networkx" ,python2-networkx)
4825 ("python-scipy" ,python2-scipy)
4826 ("python-pbcore" ,python2-pbcore)
4827 ("python-h5py" ,python2-h5py)))
4829 `(("python-cython" ,python2-cython)
4830 ("python-nose" ,python2-nose)))
4831 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4832 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4834 "pbtranscript-tofu contains scripts to analyze transcriptome data
4835 generated using the PacBio Iso-Seq protocol.")
4836 (license license:bsd-3))))
4838 (define-public prank
4845 "http://wasabiapp.org/download/prank/prank.source."
4849 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
4850 (build-system gnu-build-system)
4853 (modify-phases %standard-phases
4854 (add-after 'unpack 'enter-src-dir
4858 (add-after 'unpack 'remove-m64-flag
4859 ;; Prank will build with the correct 'bit-ness' without this flag
4860 ;; and this allows building on 32-bit machines.
4861 (lambda _ (substitute* "src/Makefile"
4866 (lambda* (#:key outputs #:allow-other-keys)
4867 (let* ((out (assoc-ref outputs "out"))
4868 (bin (string-append out "/bin"))
4869 (man (string-append out "/share/man/man1"))
4870 (path (string-append
4871 (assoc-ref %build-inputs "mafft") "/bin:"
4872 (assoc-ref %build-inputs "exonerate") "/bin:"
4873 (assoc-ref %build-inputs "bppsuite") "/bin")))
4874 (install-file "prank" bin)
4875 (wrap-program (string-append bin "/prank")
4876 `("PATH" ":" prefix (,path)))
4877 (install-file "prank.1" man))
4881 ("exonerate" ,exonerate)
4882 ("bppsuite" ,bppsuite)))
4883 (home-page "http://wasabiapp.org/software/prank/")
4884 (synopsis "Probabilistic multiple sequence alignment program")
4886 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4887 codon and amino-acid sequences. It is based on a novel algorithm that treats
4888 insertions correctly and avoids over-estimation of the number of deletion
4889 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4890 in phylogenetics and correctly takes into account the evolutionary distances
4891 between sequences. Lastly, PRANK allows for defining a potential structure
4892 for sequences to be aligned and then, simultaneously with the alignment,
4893 predicts the locations of structural units in the sequences.")
4894 (license license:gpl2+)))
4896 (define-public proteinortho
4898 (name "proteinortho")
4905 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4906 version "_src.tar.gz"))
4909 "1wl0dawpssqwfjvr651r4wlww8hhjin8nba6xh71ks7sbypx886j"))))
4910 (build-system gnu-build-system)
4912 `(#:test-target "test"
4914 (modify-phases %standard-phases
4916 ;; There is no configure script, so we modify the Makefile directly.
4917 (lambda* (#:key outputs #:allow-other-keys)
4918 (substitute* "Makefile"
4921 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4923 (add-before 'install 'make-install-directory
4924 ;; The install directory is not created during 'make install'.
4925 (lambda* (#:key outputs #:allow-other-keys)
4926 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4928 (add-after 'install 'wrap-programs
4929 (lambda* (#:key inputs outputs #:allow-other-keys)
4930 (let* ((path (getenv "PATH"))
4931 (out (assoc-ref outputs "out"))
4932 (binary (string-append out "/bin/proteinortho5.pl")))
4933 (wrap-program binary `("PATH" ":" prefix (,path))))
4937 ("python" ,python-2)
4938 ("blast+" ,blast+)))
4939 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4940 (synopsis "Detect orthologous genes across species")
4942 "Proteinortho is a tool to detect orthologous genes across different
4943 species. For doing so, it compares similarities of given gene sequences and
4944 clusters them to find significant groups. The algorithm was designed to handle
4945 large-scale data and can be applied to hundreds of species at once.")
4946 (license license:gpl2+)))
4948 (define-public pyicoteo
4956 (url "https://bitbucket.org/regulatorygenomicsupf/pyicoteo.git")
4957 (commit (string-append "v" version))))
4958 (file-name (git-file-name name version))
4961 "0hz5g8d25lbjy1wpscr490l0lmyvaix893hhax4fxnh1h9w34w8p"))))
4962 (build-system python-build-system)
4964 `(#:python ,python-2 ; does not work with Python 3
4965 #:tests? #f)) ; there are no tests
4967 `(("python2-matplotlib" ,python2-matplotlib)))
4968 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4969 (synopsis "Analyze high-throughput genetic sequencing data")
4971 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4972 sequencing data. It works with genomic coordinates. There are currently six
4973 different command-line tools:
4976 @item pyicoregion: for generating exploratory regions automatically;
4977 @item pyicoenrich: for differential enrichment between two conditions;
4978 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4979 @item pyicos: for genomic coordinates manipulation;
4980 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4981 @item pyicount: to count how many reads from N experiment files overlap in a
4983 @item pyicotrocol: to combine operations from pyicoteo.
4985 (license license:gpl3+)))
4987 (define-public prodigal
4994 (url "https://github.com/hyattpd/Prodigal.git")
4995 (commit (string-append "v" version))))
4996 (file-name (git-file-name name version))
4999 "1fs1hqk83qjbjhrvhw6ni75zakx5ki1ayy3v6wwkn3xvahc9hi5s"))))
5000 (build-system gnu-build-system)
5002 `(#:tests? #f ;no check target
5003 #:make-flags (list (string-append "INSTALLDIR="
5004 (assoc-ref %outputs "out")
5007 (modify-phases %standard-phases
5008 (delete 'configure))))
5009 (home-page "http://prodigal.ornl.gov")
5010 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
5012 "Prodigal runs smoothly on finished genomes, draft genomes, and
5013 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
5014 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
5015 partial genes, and identifies translation initiation sites.")
5016 (license license:gpl3+)))
5018 (define-public roary
5026 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
5030 "0qxrds9wx7cfhlkihrp6697kx0flhhxymap9fwan0b3rbdhcnmff"))))
5031 (build-system perl-build-system)
5034 (modify-phases %standard-phases
5039 ;; The tests are not run by default, so we run each test file
5041 (setenv "PATH" (string-append (getcwd) "/bin" ":"
5043 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
5044 (getenv "PERL5LIB")))
5045 (for-each (lambda (file)
5046 (display file)(display "\n")
5047 (invoke "perl" file))
5048 (find-files "t" ".*\\.t$"))
5051 ;; There is no 'install' target in the Makefile.
5052 (lambda* (#:key outputs #:allow-other-keys)
5053 (let* ((out (assoc-ref outputs "out"))
5054 (bin (string-append out "/bin"))
5055 (perl (string-append out "/lib/perl5/site_perl"))
5056 (roary-plots "contrib/roary_plots"))
5059 (copy-recursively "bin" bin)
5060 (copy-recursively "lib" perl)
5062 (add-after 'install 'wrap-programs
5063 (lambda* (#:key inputs outputs #:allow-other-keys)
5064 (let* ((out (assoc-ref outputs "out"))
5065 (perl5lib (getenv "PERL5LIB"))
5066 (path (getenv "PATH")))
5067 (for-each (lambda (prog)
5068 (let ((binary (string-append out "/" prog)))
5069 (wrap-program binary
5070 `("PERL5LIB" ":" prefix
5071 (,(string-append perl5lib ":" out
5072 "/lib/perl5/site_perl"))))
5073 (wrap-program binary
5075 (,(string-append path ":" out "/bin"))))))
5076 (find-files "bin" ".*[^R]$"))
5078 (string-append out "/bin/roary-create_pan_genome_plots.R"))
5079 (r-site-lib (getenv "R_LIBS_SITE"))
5081 (string-append (assoc-ref inputs "coreutils") "/bin")))
5083 `("R_LIBS_SITE" ":" prefix
5084 (,(string-append r-site-lib ":" out "/site-library/"))))
5087 (,(string-append coreutils-path ":" out "/bin"))))))
5090 `(("perl-env-path" ,perl-env-path)
5091 ("perl-test-files" ,perl-test-files)
5092 ("perl-test-most" ,perl-test-most)
5093 ("perl-test-output" ,perl-test-output)))
5095 `(("perl-array-utils" ,perl-array-utils)
5096 ("bioperl" ,bioperl-minimal)
5097 ("perl-digest-md5-file" ,perl-digest-md5-file)
5098 ("perl-exception-class" ,perl-exception-class)
5099 ("perl-file-find-rule" ,perl-file-find-rule)
5100 ("perl-file-grep" ,perl-file-grep)
5101 ("perl-file-slurper" ,perl-file-slurper)
5102 ("perl-file-which" ,perl-file-which)
5103 ("perl-graph" ,perl-graph)
5104 ("perl-graph-readwrite" ,perl-graph-readwrite)
5105 ("perl-log-log4perl" ,perl-log-log4perl)
5106 ("perl-moose" ,perl-moose)
5107 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
5108 ("perl-text-csv" ,perl-text-csv)
5109 ("bedtools" ,bedtools)
5113 ("parallel" ,parallel)
5116 ("fasttree" ,fasttree)
5120 ("r-minimal" ,r-minimal)
5121 ("r-ggplot2" ,r-ggplot2)
5122 ("coreutils" ,coreutils)))
5123 (home-page "http://sanger-pathogens.github.io/Roary")
5124 (synopsis "High speed stand-alone pan genome pipeline")
5126 "Roary is a high speed stand alone pan genome pipeline, which takes
5127 annotated assemblies in GFF3 format (produced by the Prokka program) and
5128 calculates the pan genome. Using a standard desktop PC, it can analyse
5129 datasets with thousands of samples, without compromising the quality of the
5130 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
5131 single processor. Roary is not intended for metagenomics or for comparing
5132 extremely diverse sets of genomes.")
5133 (license license:gpl3)))
5135 (define-public raxml
5143 (url "https://github.com/stamatak/standard-RAxML.git")
5144 (commit (string-append "v" version))))
5145 (file-name (git-file-name name version))
5148 "1jqjzhch0rips0vp04prvb8vmc20c5pdmsqn8knadcf91yy859fh"))))
5149 (build-system gnu-build-system)
5151 `(#:tests? #f ; There are no tests.
5152 ;; Use 'standard' Makefile rather than SSE or AVX ones.
5153 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
5155 (modify-phases %standard-phases
5158 (lambda* (#:key outputs #:allow-other-keys)
5159 (let* ((out (assoc-ref outputs "out"))
5160 (bin (string-append out "/bin"))
5161 (executable "raxmlHPC-HYBRID"))
5162 (install-file executable bin)
5163 (symlink (string-append bin "/" executable) "raxml"))
5166 `(("openmpi" ,openmpi)))
5167 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
5168 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
5170 "RAxML is a tool for phylogenetic analysis and post-analysis of large
5172 ;; The source includes x86 specific code
5173 (supported-systems '("x86_64-linux" "i686-linux"))
5174 (license license:gpl2+)))
5184 (url "https://github.com/deweylab/RSEM.git")
5185 (commit (string-append "v" version))))
5187 (base32 "1jlq11d1p8qp64w75yj8cnbbd1a93viq10pzsbwal7vdn8fg13j1"))
5188 (file-name (git-file-name name version))
5189 (modules '((guix build utils)))
5192 ;; remove bundled copy of boost and samtools
5193 (delete-file-recursively "boost")
5194 (delete-file-recursively "samtools-1.3")
5196 (build-system gnu-build-system)
5198 `(#:tests? #f ;no "check" target
5200 (list (string-append "BOOST="
5201 (assoc-ref %build-inputs "boost")
5203 (string-append "SAMHEADERS="
5204 (assoc-ref %build-inputs "htslib")
5205 "/include/htslib/sam.h")
5206 (string-append "SAMLIBS="
5207 (assoc-ref %build-inputs "htslib")
5210 (modify-phases %standard-phases
5211 ;; No "configure" script.
5212 ;; Do not build bundled samtools library.
5215 (substitute* "Makefile"
5216 (("^all : \\$\\(PROGRAMS\\).*") "all: $(PROGRAMS)\n")
5217 (("^\\$\\(SAMLIBS\\).*") ""))
5220 (lambda* (#:key outputs #:allow-other-keys)
5221 (let* ((out (string-append (assoc-ref outputs "out")))
5222 (bin (string-append out "/bin/"))
5223 (perl (string-append out "/lib/perl5/site_perl")))
5226 (for-each (lambda (file)
5227 (install-file file bin))
5228 (find-files "." "rsem-.*"))
5229 (install-file "rsem_perl_utils.pm" perl))
5231 (add-after 'install 'wrap-program
5232 (lambda* (#:key outputs #:allow-other-keys)
5233 (let ((out (assoc-ref outputs "out")))
5234 (for-each (lambda (prog)
5235 (wrap-program (string-append out "/bin/" prog)
5236 `("PERL5LIB" ":" prefix
5237 (,(string-append out "/lib/perl5/site_perl")))))
5238 '("rsem-calculate-expression"
5240 "rsem-generate-data-matrix"
5241 "rsem-generate-ngvector"
5242 "rsem-plot-transcript-wiggles"
5243 "rsem-prepare-reference"
5245 "rsem-run-prsem-testing-procedure")))
5249 ("r-minimal" ,r-minimal)
5251 ("htslib" ,htslib-1.3)
5253 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
5254 (synopsis "Estimate gene expression levels from RNA-Seq data")
5256 "RSEM is a software package for estimating gene and isoform expression
5257 levels from RNA-Seq data. The RSEM package provides a user-friendly
5258 interface, supports threads for parallel computation of the EM algorithm,
5259 single-end and paired-end read data, quality scores, variable-length reads and
5260 RSPD estimation. In addition, it provides posterior mean and 95% credibility
5261 interval estimates for expression levels. For visualization, it can generate
5262 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
5263 (license license:gpl3+)))
5265 (define-public rseqc
5273 (string-append "mirror://sourceforge/rseqc/"
5274 "RSeQC-" version ".tar.gz"))
5276 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
5277 (modules '((guix build utils)))
5280 ;; remove bundled copy of pysam
5281 (delete-file-recursively "lib/pysam")
5282 (substitute* "setup.py"
5283 ;; remove dependency on outdated "distribute" module
5284 (("^from distribute_setup import use_setuptools") "")
5285 (("^use_setuptools\\(\\)") "")
5286 ;; do not use bundled copy of pysam
5287 (("^have_pysam = False") "have_pysam = True"))
5289 (build-system python-build-system)
5290 (arguments `(#:python ,python-2))
5292 `(("python-cython" ,python2-cython)
5293 ("python-pysam" ,python2-pysam)
5294 ("python-numpy" ,python2-numpy)
5297 `(("python-nose" ,python2-nose)))
5298 (home-page "http://rseqc.sourceforge.net/")
5299 (synopsis "RNA-seq quality control package")
5301 "RSeQC provides a number of modules that can comprehensively evaluate
5302 high throughput sequence data, especially RNA-seq data. Some basic modules
5303 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
5304 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
5305 distribution, coverage uniformity, strand specificity, etc.")
5306 (license license:gpl3+)))
5309 ;; There are no release tarballs. According to the installation
5310 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
5311 ;; stable release is identified by this changeset ID.
5312 (let ((changeset "2329130")
5316 (version (string-append "0-" revision "." changeset))
5320 (url "https://bitbucket.org/libsleipnir/sleipnir")
5321 (changeset changeset)))
5322 (file-name (string-append name "-" version "-checkout"))
5325 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
5326 (build-system gnu-build-system)
5328 `(#:modules ((srfi srfi-1)
5329 (guix build gnu-build-system)
5332 (let ((dirs '("SeekMiner"
5338 (modify-phases %standard-phases
5341 (substitute* "gen_tools_am"
5342 (("/usr/bin/env.*") (which "perl")))
5343 (invoke "bash" "gen_auto")
5345 (add-after 'build 'build-additional-tools
5346 (lambda* (#:key make-flags #:allow-other-keys)
5347 (for-each (lambda (dir)
5348 (with-directory-excursion (string-append "tools/" dir)
5349 (apply invoke "make" make-flags)))
5352 (add-after 'install 'install-additional-tools
5353 (lambda* (#:key make-flags #:allow-other-keys)
5354 (for-each (lambda (dir)
5355 (with-directory-excursion (string-append "tools/" dir)
5356 (apply invoke `("make" ,@make-flags "install"))))
5363 ("readline" ,readline)
5364 ("gengetopt" ,gengetopt)
5365 ("log4cpp" ,log4cpp)))
5367 `(("autoconf" ,autoconf)
5368 ("automake" ,automake)
5370 (home-page "http://seek.princeton.edu")
5371 (synopsis "Gene co-expression search engine")
5373 "SEEK is a computational gene co-expression search engine. SEEK provides
5374 biologists with a way to navigate the massive human expression compendium that
5375 now contains thousands of expression datasets. SEEK returns a robust ranking
5376 of co-expressed genes in the biological area of interest defined by the user's
5377 query genes. It also prioritizes thousands of expression datasets according
5378 to the user's query of interest.")
5379 (license license:cc-by3.0))))
5381 (define-public samtools
5389 (string-append "mirror://sourceforge/samtools/samtools/"
5390 version "/samtools-" version ".tar.bz2"))
5393 "10ilqbmm7ri8z431sn90lvbjwizd0hhkf9rcqw8j823hf26nhgq8"))
5394 (modules '((guix build utils)))
5396 ;; Delete bundled htslib.
5397 (delete-file-recursively "htslib-1.9")
5399 (build-system gnu-build-system)
5401 `(#:modules ((ice-9 ftw)
5403 (guix build gnu-build-system)
5405 #:configure-flags (list "--with-ncurses")
5407 (modify-phases %standard-phases
5408 (add-after 'unpack 'patch-tests
5410 (substitute* "test/test.pl"
5411 ;; The test script calls out to /bin/bash
5412 (("/bin/bash") (which "bash")))
5414 (add-after 'install 'install-library
5415 (lambda* (#:key outputs #:allow-other-keys)
5416 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
5417 (install-file "libbam.a" lib)
5419 (add-after 'install 'install-headers
5420 (lambda* (#:key outputs #:allow-other-keys)
5421 (let ((include (string-append (assoc-ref outputs "out")
5422 "/include/samtools/")))
5423 (for-each (lambda (file)
5424 (install-file file include))
5425 (scandir "." (lambda (name) (string-match "\\.h$" name))))
5427 (native-inputs `(("pkg-config" ,pkg-config)))
5429 `(("htslib" ,htslib)
5430 ("ncurses" ,ncurses)
5434 (home-page "http://samtools.sourceforge.net")
5435 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
5437 "Samtools implements various utilities for post-processing nucleotide
5438 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
5439 variant calling (in conjunction with bcftools), and a simple alignment
5441 (license license:expat)))
5443 (define-public samtools-0.1
5444 ;; This is the most recent version of the 0.1 line of samtools. The input
5445 ;; and output formats differ greatly from that used and produced by samtools
5446 ;; 1.x and is still used in many bioinformatics pipelines.
5447 (package (inherit samtools)
5453 (string-append "mirror://sourceforge/samtools/samtools/"
5454 version "/samtools-" version ".tar.bz2"))
5456 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
5458 `(#:tests? #f ;no "check" target
5460 (list "LIBCURSES=-lncurses")
5461 ,@(substitute-keyword-arguments (package-arguments samtools)
5463 `(modify-phases ,phases
5465 (lambda* (#:key outputs #:allow-other-keys)
5466 (let ((bin (string-append
5467 (assoc-ref outputs "out") "/bin")))
5469 (install-file "samtools" bin)
5471 (delete 'patch-tests)
5472 (delete 'configure))))))))
5474 (define-public mosaik
5475 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
5480 ;; There are no release tarballs nor tags.
5483 (url "https://github.com/wanpinglee/MOSAIK.git")
5485 (file-name (string-append name "-" version))
5488 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
5489 (build-system gnu-build-system)
5491 `(#:tests? #f ; no tests
5492 #:make-flags (list "CC=gcc")
5494 (modify-phases %standard-phases
5496 (lambda _ (chdir "src") #t))
5498 (lambda* (#:key outputs #:allow-other-keys)
5499 (let ((bin (string-append (assoc-ref outputs "out")
5502 (copy-recursively "../bin" bin)
5506 ("zlib:static" ,zlib "static")
5508 (supported-systems '("x86_64-linux"))
5509 (home-page "https://github.com/wanpinglee/MOSAIK")
5510 (synopsis "Map nucleotide sequence reads to reference genomes")
5512 "MOSAIK is a program for mapping second and third-generation sequencing
5513 reads to a reference genome. MOSAIK can align reads generated by all the
5514 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
5515 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
5516 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
5517 ;; code released into the public domain:
5518 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
5519 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
5520 (license (list license:gpl2+ license:public-domain)))))
5522 (define-public ngs-sdk
5529 (url "https://github.com/ncbi/ngs.git")
5531 (file-name (git-file-name name version))
5534 "0d5k5kabgl15as37kj9x65xc92j4gcqms86hvihw3yb6wag0r0q3"))))
5535 (build-system gnu-build-system)
5537 `(#:parallel-build? #f ; not supported
5538 #:tests? #f ; no "check" target
5540 (modify-phases %standard-phases
5542 (lambda* (#:key outputs #:allow-other-keys)
5543 (let ((out (assoc-ref outputs "out")))
5544 ;; Allow 'konfigure.perl' to find 'package.prl'.
5546 (string-append ".:" (getenv "PERL5LIB")))
5548 ;; The 'configure' script doesn't recognize things like
5549 ;; '--enable-fast-install'.
5550 (invoke "./configure"
5551 (string-append "--build-prefix=" (getcwd) "/build")
5552 (string-append "--prefix=" out))
5554 (add-after 'unpack 'enter-dir
5555 (lambda _ (chdir "ngs-sdk") #t)))))
5556 (native-inputs `(("perl" ,perl)))
5557 ;; According to the test
5558 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
5559 ;; in ngs-sdk/setup/konfigure.perl
5560 (supported-systems '("i686-linux" "x86_64-linux"))
5561 (home-page "https://github.com/ncbi/ngs")
5562 (synopsis "API for accessing Next Generation Sequencing data")
5564 "NGS is a domain-specific API for accessing reads, alignments and pileups
5565 produced from Next Generation Sequencing. The API itself is independent from
5566 any particular back-end implementation, and supports use of multiple back-ends
5568 (license license:public-domain)))
5570 (define-public java-ngs
5571 (package (inherit ngs-sdk)
5574 `(,@(substitute-keyword-arguments
5575 `(#:modules ((guix build gnu-build-system)
5579 ,@(package-arguments ngs-sdk))
5581 `(modify-phases ,phases
5582 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5584 `(("jdk" ,icedtea "jdk")
5585 ("ngs-sdk" ,ngs-sdk)))
5586 (synopsis "Java bindings for NGS SDK")))
5588 (define-public ncbi-vdb
5595 (url "https://github.com/ncbi/ncbi-vdb.git")
5597 (file-name (git-file-name name version))
5600 "0knkj1sq34hlivgv5qd6jlczqrs3ldmfgn6vbbw7p4mqxvb9mirk"))))
5601 (build-system gnu-build-system)
5603 `(#:parallel-build? #f ; not supported
5604 #:tests? #f ; no "check" target
5605 #:make-flags '("HAVE_HDF5=1")
5607 (modify-phases %standard-phases
5608 (add-after 'unpack 'make-files-writable
5609 (lambda _ (for-each make-file-writable (find-files "." ".*")) #t))
5610 (add-before 'configure 'set-perl-search-path
5612 ;; Work around "dotless @INC" build failure.
5614 (string-append (getcwd) "/setup:"
5615 (getenv "PERL5LIB")))
5617 ;; See https://github.com/ncbi/ncbi-vdb/issues/14
5618 (add-after 'unpack 'patch-krypto-flags
5620 (substitute* "libs/krypto/Makefile"
5621 (("-Wa,-march=generic64\\+aes") "")
5622 (("-Wa,-march=generic64\\+sse4") ""))
5625 (lambda* (#:key inputs outputs #:allow-other-keys)
5626 (let ((out (assoc-ref outputs "out")))
5627 ;; Override include path for libmagic
5628 (substitute* "setup/package.prl"
5629 (("name => 'magic', Include => '/usr/include'")
5630 (string-append "name=> 'magic', Include => '"
5631 (assoc-ref inputs "libmagic")
5634 ;; Install kdf5 library (needed by sra-tools)
5635 (substitute* "build/Makefile.install"
5636 (("LIBRARIES_TO_INSTALL =")
5637 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5639 (substitute* "build/Makefile.env"
5640 (("CFLAGS =" prefix)
5641 (string-append prefix "-msse2 ")))
5643 ;; Override search path for ngs-java
5644 (substitute* "setup/package.prl"
5645 (("/usr/local/ngs/ngs-java")
5646 (assoc-ref inputs "java-ngs")))
5648 ;; The 'configure' script doesn't recognize things like
5649 ;; '--enable-fast-install'.
5650 (invoke "./configure"
5651 (string-append "--build-prefix=" (getcwd) "/build")
5652 (string-append "--prefix=" (assoc-ref outputs "out"))
5653 (string-append "--debug")
5654 (string-append "--with-xml2-prefix="
5655 (assoc-ref inputs "libxml2"))
5656 (string-append "--with-ngs-sdk-prefix="
5657 (assoc-ref inputs "ngs-sdk"))
5658 (string-append "--with-hdf5-prefix="
5659 (assoc-ref inputs "hdf5")))
5661 (add-after 'install 'install-interfaces
5662 (lambda* (#:key outputs #:allow-other-keys)
5663 ;; Install interface libraries. On i686 the interface libraries
5664 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5665 ;; architecture name ("i386") instead of the target system prefix
5667 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5668 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5669 ,(system->linux-architecture
5670 (or (%current-target-system)
5673 (string-append (assoc-ref outputs "out")
5675 ;; Install interface headers
5676 (copy-recursively "interfaces"
5677 (string-append (assoc-ref outputs "out")
5680 ;; These files are needed by sra-tools.
5681 (add-after 'install 'install-configuration-files
5682 (lambda* (#:key outputs #:allow-other-keys)
5683 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5685 (install-file "libs/kfg/default.kfg" target)
5686 (install-file "libs/kfg/certs.kfg" target))
5689 `(("libxml2" ,libxml2)
5690 ("ngs-sdk" ,ngs-sdk)
5691 ("java-ngs" ,java-ngs)
5694 (native-inputs `(("perl" ,perl)))
5695 ;; NCBI-VDB requires SSE capability.
5696 (supported-systems '("i686-linux" "x86_64-linux"))
5697 (home-page "https://github.com/ncbi/ncbi-vdb")
5698 (synopsis "Database engine for genetic information")
5700 "The NCBI-VDB library implements a highly compressed columnar data
5701 warehousing engine that is most often used to store genetic information.
5702 Databases are stored in a portable image within the file system, and can be
5703 accessed/downloaded on demand across HTTP.")
5704 (license license:public-domain)))
5706 (define-public plink
5714 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5715 version "-src.zip"))
5717 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5718 (patches (search-patches "plink-1.07-unclobber-i.patch"
5719 "plink-endian-detection.patch"))))
5720 (build-system gnu-build-system)
5722 '(#:tests? #f ;no "check" target
5723 #:make-flags (list (string-append "LIB_LAPACK="
5724 (assoc-ref %build-inputs "lapack")
5725 "/lib/liblapack.so")
5728 ;; disable phoning home
5731 (modify-phases %standard-phases
5732 ;; no "configure" script
5735 (lambda* (#:key outputs #:allow-other-keys)
5736 (let ((bin (string-append (assoc-ref outputs "out")
5738 (install-file "plink" bin)
5742 ("lapack" ,lapack)))
5744 `(("unzip" ,unzip)))
5745 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5746 (synopsis "Whole genome association analysis toolset")
5748 "PLINK is a whole genome association analysis toolset, designed to
5749 perform a range of basic, large-scale analyses in a computationally efficient
5750 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5751 so there is no support for steps prior to this (e.g. study design and
5752 planning, generating genotype or CNV calls from raw data). Through
5753 integration with gPLINK and Haploview, there is some support for the
5754 subsequent visualization, annotation and storage of results.")
5755 ;; Code is released under GPLv2, except for fisher.h, which is under
5757 (license (list license:gpl2 license:lgpl2.1+))))
5759 (define-public plink-ng
5760 (package (inherit plink)
5767 (url "https://github.com/chrchang/plink-ng.git")
5768 (commit (string-append "v" version))))
5769 (file-name (git-file-name name version))
5771 (base32 "02npdwgkpfkdnhw819rhj5kw02a5k5m90b14zq9zzya4hyg929c0"))))
5772 (build-system gnu-build-system)
5774 '(#:tests? #f ;no "check" target
5775 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5776 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5778 "-f" "Makefile.std")
5780 (modify-phases %standard-phases
5781 (add-after 'unpack 'chdir
5782 (lambda _ (chdir "1.9") #t))
5783 (delete 'configure) ; no "configure" script
5785 (lambda* (#:key outputs #:allow-other-keys)
5786 (let ((bin (string-append (assoc-ref outputs "out")
5788 (install-file "plink" bin)
5793 ("openblas" ,openblas)))
5794 (home-page "https://www.cog-genomics.org/plink/")
5795 (license license:gpl3+)))
5797 (define-public smithlab-cpp
5798 (let ((revision "1")
5799 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
5801 (name "smithlab-cpp")
5802 (version (string-append "0." revision "." (string-take commit 7)))
5806 (url "https://github.com/smithlabcode/smithlab_cpp.git")
5808 (file-name (string-append name "-" version "-checkout"))
5811 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
5812 (build-system gnu-build-system)
5814 `(#:modules ((guix build gnu-build-system)
5817 #:tests? #f ;no "check" target
5819 (modify-phases %standard-phases
5820 (add-after 'unpack 'use-samtools-headers
5822 (substitute* '("SAM.cpp"
5824 (("sam.h") "samtools/sam.h"))
5827 (lambda* (#:key outputs #:allow-other-keys)
5828 (let* ((out (assoc-ref outputs "out"))
5829 (lib (string-append out "/lib"))
5830 (include (string-append out "/include/smithlab-cpp")))
5833 (for-each (cut install-file <> lib)
5834 (find-files "." "\\.o$"))
5835 (for-each (cut install-file <> include)
5836 (find-files "." "\\.hpp$")))
5838 (delete 'configure))))
5840 `(("samtools" ,samtools-0.1)
5842 (home-page "https://github.com/smithlabcode/smithlab_cpp")
5843 (synopsis "C++ helper library for functions used in Smith lab projects")
5845 "Smithlab CPP is a C++ library that includes functions used in many of
5846 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
5847 structures, classes for genomic regions, mapped sequencing reads, etc.")
5848 (license license:gpl3+))))
5850 (define-public preseq
5856 (uri (string-append "https://github.com/smithlabcode/preseq/"
5857 "releases/download/v" version
5858 "/preseq_v" version ".tar.bz2"))
5860 (base32 "149x9xmk1wy1gff85325yfzqc0qk4sgp1w6gbyj9cnji4x1dszbl"))
5861 (modules '((guix build utils)))
5863 ;; Remove bundled samtools.
5864 (delete-file-recursively "samtools")
5866 (build-system gnu-build-system)
5868 `(#:tests? #f ;no "check" target
5870 (modify-phases %standard-phases
5871 (delete 'configure))
5873 (list (string-append "PREFIX="
5874 (assoc-ref %outputs "out"))
5875 (string-append "LIBBAM="
5876 (assoc-ref %build-inputs "samtools")
5878 (string-append "SMITHLAB_CPP="
5879 (assoc-ref %build-inputs "smithlab-cpp")
5882 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
5885 ("samtools" ,samtools-0.1)
5886 ("smithlab-cpp" ,smithlab-cpp)
5888 (home-page "http://smithlabresearch.org/software/preseq/")
5889 (synopsis "Program for analyzing library complexity")
5891 "The preseq package is aimed at predicting and estimating the complexity
5892 of a genomic sequencing library, equivalent to predicting and estimating the
5893 number of redundant reads from a given sequencing depth and how many will be
5894 expected from additional sequencing using an initial sequencing experiment.
5895 The estimates can then be used to examine the utility of further sequencing,
5896 optimize the sequencing depth, or to screen multiple libraries to avoid low
5897 complexity samples.")
5898 (license license:gpl3+)))
5900 (define-public python-screed
5902 (name "python-screed")
5907 (uri (pypi-uri "screed" version))
5910 "148vcb7w2wr6a4w6vs2bsxanbqibxfk490zbcbg4m61s8669zdjx"))))
5911 (build-system python-build-system)
5914 (modify-phases %standard-phases
5915 ;; Tests must be run after installation, as the "screed" command does
5916 ;; not exist right after building.
5918 (add-after 'install 'check
5919 (lambda* (#:key inputs outputs #:allow-other-keys)
5920 (let ((out (assoc-ref outputs "out")))
5921 (setenv "PYTHONPATH"
5922 (string-append out "/lib/python"
5923 (string-take (string-take-right
5924 (assoc-ref inputs "python")
5927 (getenv "PYTHONPATH")))
5928 (setenv "PATH" (string-append out "/bin:" (getenv "PATH"))))
5929 (invoke "python" "setup.py" "test")
5932 `(("python-pytest" ,python-pytest)
5933 ("python-pytest-cov" ,python-pytest-cov)
5934 ("python-pytest-runner" ,python-pytest-runner)))
5936 `(("python-bz2file" ,python-bz2file)))
5937 (home-page "https://github.com/dib-lab/screed/")
5938 (synopsis "Short read sequence database utilities")
5939 (description "Screed parses FASTA and FASTQ files and generates databases.
5940 Values such as sequence name, sequence description, sequence quality and the
5941 sequence itself can be retrieved from these databases.")
5942 (license license:bsd-3)))
5944 (define-public python2-screed
5945 (package-with-python2 python-screed))
5947 (define-public sra-tools
5955 (url "https://github.com/ncbi/sra-tools.git")
5957 (file-name (git-file-name name version))
5960 "0vqzap68v81k0zif2mnqfy8pnw2nrhsg87p6mgq8qk3nk2jv2rgy"))))
5961 (build-system gnu-build-system)
5963 `(#:parallel-build? #f ; not supported
5964 #:tests? #f ; no "check" target
5966 (list (string-append "DEFAULT_CRT="
5967 (assoc-ref %build-inputs "ncbi-vdb")
5969 (string-append "DEFAULT_KFG="
5970 (assoc-ref %build-inputs "ncbi-vdb")
5972 (string-append "VDB_LIBDIR="
5973 (assoc-ref %build-inputs "ncbi-vdb")
5974 ,(if (string-prefix? "x86_64"
5975 (or (%current-target-system)
5980 (modify-phases %standard-phases
5981 (add-before 'configure 'set-perl-search-path
5983 ;; Work around "dotless @INC" build failure.
5985 (string-append (getcwd) "/setup:"
5986 (getenv "PERL5LIB")))
5989 (lambda* (#:key inputs outputs #:allow-other-keys)
5990 ;; The build system expects a directory containing the sources and
5991 ;; raw build output of ncbi-vdb, including files that are not
5992 ;; installed. Since we are building against an installed version of
5993 ;; ncbi-vdb, the following modifications are needed.
5994 (substitute* "setup/konfigure.perl"
5995 ;; Make the configure script look for the "ilib" directory of
5996 ;; "ncbi-vdb" without first checking for the existence of a
5997 ;; matching library in its "lib" directory.
5998 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5999 "my $f = File::Spec->catdir($ilibdir, $ilib);")
6000 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
6001 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
6002 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
6005 (substitute* "tools/copycat/Makefile"
6006 (("smagic-static") "lmagic"))
6008 ;; The 'configure' script doesn't recognize things like
6009 ;; '--enable-fast-install'.
6010 (invoke "./configure"
6011 (string-append "--build-prefix=" (getcwd) "/build")
6012 (string-append "--prefix=" (assoc-ref outputs "out"))
6013 (string-append "--debug")
6014 (string-append "--with-fuse-prefix="
6015 (assoc-ref inputs "fuse"))
6016 (string-append "--with-magic-prefix="
6017 (assoc-ref inputs "libmagic"))
6018 ;; TODO: building with libxml2 fails with linker errors
6019 ;; (string-append "--with-xml2-prefix="
6020 ;; (assoc-ref inputs "libxml2"))
6021 (string-append "--with-ncbi-vdb-sources="
6022 (assoc-ref inputs "ncbi-vdb"))
6023 (string-append "--with-ncbi-vdb-build="
6024 (assoc-ref inputs "ncbi-vdb"))
6025 (string-append "--with-ngs-sdk-prefix="
6026 (assoc-ref inputs "ngs-sdk"))
6027 (string-append "--with-hdf5-prefix="
6028 (assoc-ref inputs "hdf5")))
6030 (native-inputs `(("perl" ,perl)))
6032 `(("ngs-sdk" ,ngs-sdk)
6033 ("ncbi-vdb" ,ncbi-vdb)
6038 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
6039 (synopsis "Tools and libraries for reading and writing sequencing data")
6041 "The SRA Toolkit from NCBI is a collection of tools and libraries for
6042 reading of sequencing files from the Sequence Read Archive (SRA) database and
6043 writing files into the .sra format.")
6044 (license license:public-domain)))
6046 (define-public seqan
6052 (uri (string-append "https://github.com/seqan/seqan/releases/"
6053 "download/seqan-v" version
6054 "/seqan-library-" version ".tar.xz"))
6057 "19a1rlxx03qy1i1iriicly68w64yjxbv24g9gdywnfmq998v35yx"))))
6058 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6059 ;; makes sense to split the outputs.
6060 (outputs '("out" "doc"))
6061 (build-system trivial-build-system)
6063 `(#:modules ((guix build utils))
6066 (use-modules (guix build utils))
6067 (let ((tar (assoc-ref %build-inputs "tar"))
6068 (xz (assoc-ref %build-inputs "xz"))
6069 (out (assoc-ref %outputs "out"))
6070 (doc (assoc-ref %outputs "doc")))
6071 (setenv "PATH" (string-append tar "/bin:" xz "/bin"))
6072 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6073 (chdir (string-append "seqan-library-" ,version))
6074 (copy-recursively "include" (string-append out "/include"))
6075 (copy-recursively "share" (string-append doc "/share"))
6078 `(("source" ,source)
6081 (home-page "http://www.seqan.de")
6082 (synopsis "Library for nucleotide sequence analysis")
6084 "SeqAn is a C++ library of efficient algorithms and data structures for
6085 the analysis of sequences with the focus on biological data. It contains
6086 algorithms and data structures for string representation and their
6087 manipulation, online and indexed string search, efficient I/O of
6088 bioinformatics file formats, sequence alignment, and more.")
6089 (license license:bsd-3)))
6091 (define-public seqan-1
6092 (package (inherit seqan)
6097 (uri (string-append "http://packages.seqan.de/seqan-library/"
6098 "seqan-library-" version ".tar.bz2"))
6101 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
6102 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6103 ;; makes sense to split the outputs.
6104 (outputs '("out" "doc"))
6105 (build-system trivial-build-system)
6107 `(#:modules ((guix build utils))
6110 (use-modules (guix build utils))
6111 (let ((tar (assoc-ref %build-inputs "tar"))
6112 (bzip (assoc-ref %build-inputs "bzip2"))
6113 (out (assoc-ref %outputs "out"))
6114 (doc (assoc-ref %outputs "doc")))
6115 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
6116 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6117 (chdir (string-append "seqan-library-" ,version))
6118 (copy-recursively "include" (string-append out "/include"))
6119 (copy-recursively "share" (string-append doc "/share"))
6122 `(("source" ,source)
6124 ("bzip2" ,bzip2)))))
6126 (define-public seqmagick
6133 (uri (pypi-uri "seqmagick" version))
6136 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
6137 (build-system python-build-system)
6139 `(("python-biopython" ,python-biopython)))
6141 `(("python-nose" ,python-nose)))
6142 (home-page "https://github.com/fhcrc/seqmagick")
6143 (synopsis "Tools for converting and modifying sequence files")
6145 "Bioinformaticians often have to convert sequence files between formats
6146 and do little manipulations on them, and it's not worth writing scripts for
6147 that. Seqmagick is a utility to expose the file format conversion in
6148 BioPython in a convenient way. Instead of having a big mess of scripts, there
6149 is one that takes arguments.")
6150 (license license:gpl3)))
6152 (define-public seqtk
6159 (url "https://github.com/lh3/seqtk.git")
6160 (commit (string-append "v" version))))
6161 (file-name (git-file-name name version))
6164 "1bfzlqa84b5s1qi22blmmw2s8xdyp9h9ydcq22pfjhh5gab3yz6l"))))
6165 (build-system gnu-build-system)
6168 (modify-phases %standard-phases
6171 ;; There are no tests, so we just run a sanity check.
6172 (lambda _ (invoke "./seqtk" "seq") #t))
6174 (lambda* (#:key outputs #:allow-other-keys)
6175 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6176 (install-file "seqtk" bin)
6180 (home-page "https://github.com/lh3/seqtk")
6181 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
6183 "Seqtk is a fast and lightweight tool for processing sequences in the
6184 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
6185 optionally compressed by gzip.")
6186 (license license:expat)))
6188 (define-public snap-aligner
6190 (name "snap-aligner")
6191 (version "1.0beta.18")
6195 (url "https://github.com/amplab/snap.git")
6196 (commit (string-append "v" version))))
6197 (file-name (git-file-name name version))
6200 "01w3qq4wm07z73vky0cfwlmrbf50n3w722cxrlzxfi99mnb808d8"))))
6201 (build-system gnu-build-system)
6204 (modify-phases %standard-phases
6206 (replace 'check (lambda _ (invoke "./unit_tests") #t))
6208 (lambda* (#:key outputs #:allow-other-keys)
6209 (let* ((out (assoc-ref outputs "out"))
6210 (bin (string-append out "/bin")))
6211 (install-file "snap-aligner" bin)
6212 (install-file "SNAPCommand" bin)
6216 (home-page "http://snap.cs.berkeley.edu/")
6217 (synopsis "Short read DNA sequence aligner")
6219 "SNAP is a fast and accurate aligner for short DNA reads. It is
6220 optimized for modern read lengths of 100 bases or higher, and takes advantage
6221 of these reads to align data quickly through a hash-based indexing scheme.")
6222 ;; 32-bit systems are not supported by the unpatched code.
6223 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
6224 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
6225 ;; systems without a lot of memory cannot make good use of this program.
6226 (supported-systems '("x86_64-linux"))
6227 (license license:asl2.0)))
6229 (define-public sortmerna
6237 (url "https://github.com/biocore/sortmerna.git")
6239 (file-name (git-file-name name version))
6242 "0j3mbz4n25738yijmjbr5r4fyvkgm8v5vn3sshyfvmyqf5q9byqf"))))
6243 (build-system gnu-build-system)
6244 (outputs '("out" ;for binaries
6245 "db")) ;for sequence databases
6248 (modify-phases %standard-phases
6250 (lambda* (#:key outputs #:allow-other-keys)
6251 (let* ((out (assoc-ref outputs "out"))
6252 (bin (string-append out "/bin"))
6253 (db (assoc-ref outputs "db"))
6255 (string-append db "/share/sortmerna/rRNA_databases")))
6256 (install-file "sortmerna" bin)
6257 (install-file "indexdb_rna" bin)
6258 (for-each (lambda (file)
6259 (install-file file share))
6260 (find-files "rRNA_databases" ".*fasta"))
6264 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
6265 (synopsis "Biological sequence analysis tool for NGS reads")
6267 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
6268 and operational taxonomic unit (OTU) picking of next generation
6269 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
6270 allows for fast and sensitive analyses of nucleotide sequences. The main
6271 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
6272 ;; The source includes x86 specific code
6273 (supported-systems '("x86_64-linux" "i686-linux"))
6274 (license license:lgpl3)))
6283 (url "https://github.com/alexdobin/STAR.git")
6285 (file-name (string-append name "-" version "-checkout"))
6288 "0n6g4s4hgw7qygs1z97j7a2dgz8gfaa4cv5pjvvvmarvk0x07hyg"))
6289 (modules '((guix build utils)))
6292 (substitute* "source/Makefile"
6294 ;; Remove pre-built binaries and bundled htslib sources.
6295 (delete-file-recursively "bin/MacOSX_x86_64")
6296 (delete-file-recursively "bin/Linux_x86_64")
6297 (delete-file-recursively "bin/Linux_x86_64_static")
6298 (delete-file-recursively "source/htslib")
6300 (build-system gnu-build-system)
6302 '(#:tests? #f ;no check target
6303 #:make-flags '("STAR")
6305 (modify-phases %standard-phases
6306 (add-after 'unpack 'enter-source-dir
6307 (lambda _ (chdir "source") #t))
6308 (add-after 'enter-source-dir 'make-reproducible
6310 (substitute* "Makefile"
6311 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
6312 (string-append pre "Built with Guix" post)))
6314 ;; See https://github.com/alexdobin/STAR/pull/562
6315 (add-after 'enter-source-dir 'add-missing-header
6317 (substitute* "SoloReadFeature_inputRecords.cpp"
6318 (("#include \"binarySearch2.h\"" h)
6319 (string-append h "\n#include <math.h>")))
6321 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
6323 (substitute* "Makefile"
6324 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
6326 (substitute* '("BAMfunctions.cpp"
6331 "bamRemoveDuplicates.cpp")
6332 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
6333 (string-append "#include <" header ">")))
6334 (substitute* "IncludeDefine.h"
6335 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
6336 (string-append "<" header ">")))
6339 (lambda* (#:key outputs #:allow-other-keys)
6340 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6341 (install-file "STAR" bin))
6343 (delete 'configure))))
6347 `(("htslib" ,htslib)
6349 (home-page "https://github.com/alexdobin/STAR")
6350 (synopsis "Universal RNA-seq aligner")
6352 "The Spliced Transcripts Alignment to a Reference (STAR) software is
6353 based on a previously undescribed RNA-seq alignment algorithm that uses
6354 sequential maximum mappable seed search in uncompressed suffix arrays followed
6355 by seed clustering and stitching procedure. In addition to unbiased de novo
6356 detection of canonical junctions, STAR can discover non-canonical splices and
6357 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
6359 ;; Only 64-bit systems are supported according to the README.
6360 (supported-systems '("x86_64-linux" "mips64el-linux"))
6361 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
6362 (license license:gpl3+)))
6364 (define-public starlong
6365 (package (inherit star)
6368 (substitute-keyword-arguments (package-arguments star)
6369 ((#:make-flags flags)
6372 `(modify-phases ,phases
6373 ;; Allow extra long sequence reads.
6374 (add-after 'unpack 'make-extra-long
6376 (substitute* "source/IncludeDefine.h"
6377 (("(#define DEF_readNameLengthMax ).*" _ match)
6378 (string-append match "900000\n")))
6381 (lambda* (#:key outputs #:allow-other-keys)
6382 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6383 (install-file "STARlong" bin))
6386 (define-public subread
6392 (uri (string-append "mirror://sourceforge/subread/subread-"
6393 version "/subread-" version "-source.tar.gz"))
6396 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
6397 (build-system gnu-build-system)
6399 `(#:tests? #f ;no "check" target
6400 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
6401 ;; optimizations by default, so we override these flags such that x86_64
6402 ;; flags are only added when the build target is an x86_64 system.
6404 (list (let ((system ,(or (%current-target-system)
6406 (flags '("-ggdb" "-fomit-frame-pointer"
6407 "-ffast-math" "-funroll-loops"
6408 "-fmessage-length=0"
6409 "-O9" "-Wall" "-DMAKE_FOR_EXON"
6411 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
6412 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
6413 (if (string-prefix? "x86_64" system)
6414 (string-append "CCFLAGS=" (string-join (append flags flags64)))
6415 (string-append "CCFLAGS=" (string-join flags))))
6416 "-f" "Makefile.Linux"
6417 "CC=gcc ${CCFLAGS}")
6419 (modify-phases %standard-phases
6420 (add-after 'unpack 'enter-dir
6421 (lambda _ (chdir "src") #t))
6423 (lambda* (#:key outputs #:allow-other-keys)
6424 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6426 (copy-recursively "../bin" bin))
6428 ;; no "configure" script
6429 (delete 'configure))))
6430 (inputs `(("zlib" ,zlib)))
6431 (home-page "http://bioinf.wehi.edu.au/subread-package/")
6432 (synopsis "Tool kit for processing next-gen sequencing data")
6434 "The subread package contains the following tools: subread aligner, a
6435 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
6436 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
6437 features; exactSNP: a SNP caller that discovers SNPs by testing signals
6438 against local background noises.")
6439 (license license:gpl3+)))
6441 (define-public stringtie
6447 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
6448 "stringtie-" version ".tar.gz"))
6451 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
6452 (modules '((guix build utils)))
6455 (delete-file-recursively "samtools-0.1.18")
6457 (build-system gnu-build-system)
6459 `(#:tests? #f ;no test suite
6461 (modify-phases %standard-phases
6462 ;; no configure script
6464 (add-before 'build 'use-system-samtools
6466 (substitute* "Makefile"
6467 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
6469 (substitute* '("gclib/GBam.h"
6471 (("#include \"(bam|sam|kstring).h\"" _ header)
6472 (string-append "#include <samtools/" header ".h>")))
6474 (add-after 'unpack 'remove-duplicate-typedef
6476 ;; This typedef conflicts with the typedef in
6477 ;; glibc-2.25/include/bits/types.h
6478 (substitute* "gclib/GThreads.h"
6479 (("typedef long long __intmax_t;") ""))
6482 (lambda* (#:key outputs #:allow-other-keys)
6483 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6484 (install-file "stringtie" bin)
6487 `(("samtools" ,samtools-0.1)
6489 (home-page "http://ccb.jhu.edu/software/stringtie/")
6490 (synopsis "Transcript assembly and quantification for RNA-Seq data")
6492 "StringTie is a fast and efficient assembler of RNA-Seq sequence
6493 alignments into potential transcripts. It uses a novel network flow algorithm
6494 as well as an optional de novo assembly step to assemble and quantitate
6495 full-length transcripts representing multiple splice variants for each gene
6496 locus. Its input can include not only the alignments of raw reads used by
6497 other transcript assemblers, but also alignments of longer sequences that have
6498 been assembled from those reads. To identify differentially expressed genes
6499 between experiments, StringTie's output can be processed either by the
6500 Cuffdiff or Ballgown programs.")
6501 (license license:artistic2.0)))
6503 (define-public taxtastic
6509 (uri (pypi-uri "taxtastic" version))
6512 "03pysw79lsrvz4lwzis88j15067ffqbi4cid5pqhrlxmd6bh8rrk"))))
6513 (build-system python-build-system)
6515 `(#:python ,python-2
6517 (modify-phases %standard-phases
6519 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t)))))
6521 `(("python-sqlalchemy" ,python2-sqlalchemy)
6522 ("python-decorator" ,python2-decorator)
6523 ("python-biopython" ,python2-biopython)
6524 ("python-pandas" ,python2-pandas)
6525 ("python-psycopg2" ,python2-psycopg2)
6526 ("python-fastalite" ,python2-fastalite)
6527 ("python-pyyaml" ,python2-pyyaml)
6528 ("python-six" ,python2-six)
6529 ("python-jinja2" ,python2-jinja2)
6530 ("python-dendropy" ,python2-dendropy)))
6531 (home-page "https://github.com/fhcrc/taxtastic")
6532 (synopsis "Tools for taxonomic naming and annotation")
6534 "Taxtastic is software written in python used to build and maintain
6535 reference packages i.e. collections of reference trees, reference alignments,
6536 profiles, and associated taxonomic information.")
6537 (license license:gpl3+)))
6539 (define-public vcftools
6546 "https://github.com/vcftools/vcftools/releases/download/v"
6547 version "/vcftools-" version ".tar.gz"))
6550 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
6551 (build-system gnu-build-system)
6553 `(#:tests? #f ; no "check" target
6555 "CFLAGS=-O2" ; override "-m64" flag
6556 (string-append "PREFIX=" (assoc-ref %outputs "out"))
6557 (string-append "MANDIR=" (assoc-ref %outputs "out")
6558 "/share/man/man1"))))
6560 `(("pkg-config" ,pkg-config)))
6564 (home-page "https://vcftools.github.io/")
6565 (synopsis "Tools for working with VCF files")
6567 "VCFtools is a program package designed for working with VCF files, such
6568 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
6569 provide easily accessible methods for working with complex genetic variation
6570 data in the form of VCF files.")
6571 ;; The license is declared as LGPLv3 in the README and
6572 ;; at https://vcftools.github.io/license.html
6573 (license license:lgpl3)))
6575 (define-public infernal
6581 (uri (string-append "http://eddylab.org/software/infernal/"
6582 "infernal-" version ".tar.gz"))
6585 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
6586 (build-system gnu-build-system)
6588 `(("perl" ,perl))) ; for tests
6589 (home-page "http://eddylab.org/infernal/")
6590 (synopsis "Inference of RNA alignments")
6591 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
6592 searching DNA sequence databases for RNA structure and sequence similarities.
6593 It is an implementation of a special case of profile stochastic context-free
6594 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
6595 profile, but it scores a combination of sequence consensus and RNA secondary
6596 structure consensus, so in many cases, it is more capable of identifying RNA
6597 homologs that conserve their secondary structure more than their primary
6599 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
6600 (supported-systems '("i686-linux" "x86_64-linux"))
6601 (license license:bsd-3)))
6603 (define-public r-scde
6610 (url "https://github.com/hms-dbmi/scde.git")
6612 (file-name (git-file-name name version))
6615 "10na2gyka24mszdxf92wz9h2c13hdf1ww30c68gfsw53lvvhhhxb"))))
6616 (build-system r-build-system)
6618 `(("r-rcpp" ,r-rcpp)
6619 ("r-rcpparmadillo" ,r-rcpparmadillo)
6622 ("r-rjson" ,r-rjson)
6623 ("r-cairo" ,r-cairo)
6624 ("r-rcolorbrewer" ,r-rcolorbrewer)
6625 ("r-edger" ,r-edger)
6626 ("r-quantreg" ,r-quantreg)
6628 ("r-rmtstat" ,r-rmtstat)
6629 ("r-extremes" ,r-extremes)
6630 ("r-pcamethods" ,r-pcamethods)
6631 ("r-biocparallel" ,r-biocparallel)
6632 ("r-flexmix" ,r-flexmix)))
6633 (home-page "https://hms-dbmi.github.io/scde/")
6634 (synopsis "R package for analyzing single-cell RNA-seq data")
6635 (description "The SCDE package implements a set of statistical methods for
6636 analyzing single-cell RNA-seq data. SCDE fits individual error models for
6637 single-cell RNA-seq measurements. These models can then be used for
6638 assessment of differential expression between groups of cells, as well as
6639 other types of analysis. The SCDE package also contains the pagoda framework
6640 which applies pathway and gene set overdispersion analysis to identify aspects
6641 of transcriptional heterogeneity among single cells.")
6642 ;; See https://github.com/hms-dbmi/scde/issues/38
6643 (license license:gpl2)))
6645 (define-public r-centipede
6647 (name "r-centipede")
6651 (uri (string-append "http://download.r-forge.r-project.org/"
6652 "src/contrib/CENTIPEDE_" version ".tar.gz"))
6655 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
6656 (build-system r-build-system)
6657 (home-page "http://centipede.uchicago.edu/")
6658 (synopsis "Predict transcription factor binding sites")
6660 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
6661 of the genome that are bound by particular transcription factors. It starts
6662 by identifying a set of candidate binding sites, and then aims to classify the
6663 sites according to whether each site is bound or not bound by a transcription
6664 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
6665 between two different types of motif instances using as much relevant
6666 information as possible.")
6667 (license (list license:gpl2+ license:gpl3+))))
6669 (define-public r-genefilter
6671 (name "r-genefilter")
6676 (uri (bioconductor-uri "genefilter" version))
6679 "1jq7lam4dnbvz55lx93kcl9afl8xfjd6xs374d35m21bkay418kj"))))
6680 (build-system r-build-system)
6682 `(("gfortran" ,gfortran)))
6684 `(("r-annotate" ,r-annotate)
6685 ("r-annotationdbi" ,r-annotationdbi)
6686 ("r-biobase" ,r-biobase)
6687 ("r-s4vectors" ,r-s4vectors)
6688 ("r-survival" ,r-survival)))
6689 (home-page "https://bioconductor.org/packages/genefilter")
6690 (synopsis "Filter genes from high-throughput experiments")
6692 "This package provides basic functions for filtering genes from
6693 high-throughput sequencing experiments.")
6694 (license license:artistic2.0)))
6696 (define-public r-deseq2
6703 (uri (bioconductor-uri "DESeq2" version))
6706 "0fkk326addm2cw688gnmdzsmri5qx8j6ldnr4xin6kjnwicqhlqd"))))
6707 (properties `((upstream-name . "DESeq2")))
6708 (build-system r-build-system)
6710 `(("r-biobase" ,r-biobase)
6711 ("r-biocgenerics" ,r-biocgenerics)
6712 ("r-biocparallel" ,r-biocparallel)
6713 ("r-genefilter" ,r-genefilter)
6714 ("r-geneplotter" ,r-geneplotter)
6715 ("r-genomicranges" ,r-genomicranges)
6716 ("r-ggplot2" ,r-ggplot2)
6717 ("r-hmisc" ,r-hmisc)
6718 ("r-iranges" ,r-iranges)
6719 ("r-locfit" ,r-locfit)
6721 ("r-rcpparmadillo" ,r-rcpparmadillo)
6722 ("r-s4vectors" ,r-s4vectors)
6723 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6724 (home-page "https://bioconductor.org/packages/DESeq2")
6725 (synopsis "Differential gene expression analysis")
6727 "This package provides functions to estimate variance-mean dependence in
6728 count data from high-throughput nucleotide sequencing assays and test for
6729 differential expression based on a model using the negative binomial
6731 (license license:lgpl3+)))
6733 (define-public r-dexseq
6740 (uri (bioconductor-uri "DEXSeq" version))
6743 "1b2s0vwm97g0wgm4ms0f4pqkqiqmxscnhg700aybl5vx0m2fa8xm"))))
6744 (properties `((upstream-name . "DEXSeq")))
6745 (build-system r-build-system)
6747 `(("r-annotationdbi" ,r-annotationdbi)
6748 ("r-biobase" ,r-biobase)
6749 ("r-biocgenerics" ,r-biocgenerics)
6750 ("r-biocparallel" ,r-biocparallel)
6751 ("r-biomart" ,r-biomart)
6752 ("r-deseq2" ,r-deseq2)
6753 ("r-genefilter" ,r-genefilter)
6754 ("r-geneplotter" ,r-geneplotter)
6755 ("r-genomicranges" ,r-genomicranges)
6756 ("r-hwriter" ,r-hwriter)
6757 ("r-iranges" ,r-iranges)
6758 ("r-rcolorbrewer" ,r-rcolorbrewer)
6759 ("r-rsamtools" ,r-rsamtools)
6760 ("r-s4vectors" ,r-s4vectors)
6761 ("r-statmod" ,r-statmod)
6762 ("r-stringr" ,r-stringr)
6763 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6764 (home-page "https://bioconductor.org/packages/DEXSeq")
6765 (synopsis "Inference of differential exon usage in RNA-Seq")
6767 "This package is focused on finding differential exon usage using RNA-seq
6768 exon counts between samples with different experimental designs. It provides
6769 functions that allows the user to make the necessary statistical tests based
6770 on a model that uses the negative binomial distribution to estimate the
6771 variance between biological replicates and generalized linear models for
6772 testing. The package also provides functions for the visualization and
6773 exploration of the results.")
6774 (license license:gpl3+)))
6776 (define-public r-annotationforge
6778 (name "r-annotationforge")
6783 (uri (bioconductor-uri "AnnotationForge" version))
6786 "0m4w8n2711wr28znv646cfc7m5jqlr8friz334zdyjmhg7m2xkb7"))))
6788 `((upstream-name . "AnnotationForge")))
6789 (build-system r-build-system)
6791 `(("r-annotationdbi" ,r-annotationdbi)
6792 ("r-biobase" ,r-biobase)
6793 ("r-biocgenerics" ,r-biocgenerics)
6795 ("r-rcurl" ,r-rcurl)
6796 ("r-rsqlite" ,r-rsqlite)
6797 ("r-s4vectors" ,r-s4vectors)
6799 (home-page "https://bioconductor.org/packages/AnnotationForge")
6800 (synopsis "Code for building annotation database packages")
6802 "This package provides code for generating Annotation packages and their
6803 databases. Packages produced are intended to be used with AnnotationDbi.")
6804 (license license:artistic2.0)))
6806 (define-public r-rbgl
6813 (uri (bioconductor-uri "RBGL" version))
6816 "06brn9hl6lybx6hdfp1sycwj6wn1bjfi8xyhpy0v122v1z8d5mbz"))))
6817 (properties `((upstream-name . "RBGL")))
6818 (build-system r-build-system)
6821 ("r-graph" ,r-graph)))
6822 (home-page "https://www.bioconductor.org/packages/RBGL")
6823 (synopsis "Interface to the Boost graph library")
6825 "This package provides a fairly extensive and comprehensive interface to
6826 the graph algorithms contained in the Boost library.")
6827 (license license:artistic2.0)))
6829 (define-public r-gseabase
6836 (uri (bioconductor-uri "GSEABase" version))
6839 "0vh53xk2prjbdkbr3hwfiflx1gh7ilrqs3j1p3lyd6syy3rn9n83"))))
6840 (properties `((upstream-name . "GSEABase")))
6841 (build-system r-build-system)
6843 `(("r-annotate" ,r-annotate)
6844 ("r-annotationdbi" ,r-annotationdbi)
6845 ("r-biobase" ,r-biobase)
6846 ("r-biocgenerics" ,r-biocgenerics)
6847 ("r-graph" ,r-graph)
6849 (home-page "https://bioconductor.org/packages/GSEABase")
6850 (synopsis "Gene set enrichment data structures and methods")
6852 "This package provides classes and methods to support @dfn{Gene Set
6853 Enrichment Analysis} (GSEA).")
6854 (license license:artistic2.0)))
6856 (define-public r-category
6863 (uri (bioconductor-uri "Category" version))
6866 "1n36xfnwn2np5f0lix9abvv9w6jb25jqz3xzvqzklz9s1af4k6x4"))))
6867 (properties `((upstream-name . "Category")))
6868 (build-system r-build-system)
6870 `(("r-annotate" ,r-annotate)
6871 ("r-annotationdbi" ,r-annotationdbi)
6872 ("r-biobase" ,r-biobase)
6873 ("r-biocgenerics" ,r-biocgenerics)
6874 ("r-genefilter" ,r-genefilter)
6875 ("r-graph" ,r-graph)
6876 ("r-gseabase" ,r-gseabase)
6877 ("r-matrix" ,r-matrix)
6880 (home-page "https://bioconductor.org/packages/Category")
6881 (synopsis "Category analysis")
6883 "This package provides a collection of tools for performing category
6885 (license license:artistic2.0)))
6887 (define-public r-gostats
6894 (uri (bioconductor-uri "GOstats" version))
6897 "1a95i6awm2a8xv42fg2z3n29fg9z29i45kd80hxf6mvqqgzj80xp"))))
6898 (properties `((upstream-name . "GOstats")))
6899 (build-system r-build-system)
6901 `(("r-annotate" ,r-annotate)
6902 ("r-annotationdbi" ,r-annotationdbi)
6903 ("r-annotationforge" ,r-annotationforge)
6904 ("r-biobase" ,r-biobase)
6905 ("r-category" ,r-category)
6906 ("r-go-db" ,r-go-db)
6907 ("r-graph" ,r-graph)
6908 ("r-rgraphviz" ,r-rgraphviz)
6909 ("r-rbgl" ,r-rbgl)))
6910 (home-page "https://bioconductor.org/packages/GOstats")
6911 (synopsis "Tools for manipulating GO and microarrays")
6913 "This package provides a set of tools for interacting with GO and
6914 microarray data. A variety of basic manipulation tools for graphs, hypothesis
6915 testing and other simple calculations.")
6916 (license license:artistic2.0)))
6918 (define-public r-shortread
6920 (name "r-shortread")
6925 (uri (bioconductor-uri "ShortRead" version))
6928 "1irqzdgsavjqsq0vva4966qh8qgn7xn9382dmhahm1hxb94qmi59"))))
6929 (properties `((upstream-name . "ShortRead")))
6930 (build-system r-build-system)
6934 `(("r-biobase" ,r-biobase)
6935 ("r-biocgenerics" ,r-biocgenerics)
6936 ("r-biocparallel" ,r-biocparallel)
6937 ("r-biostrings" ,r-biostrings)
6938 ("r-genomeinfodb" ,r-genomeinfodb)
6939 ("r-genomicalignments" ,r-genomicalignments)
6940 ("r-genomicranges" ,r-genomicranges)
6941 ("r-hwriter" ,r-hwriter)
6942 ("r-iranges" ,r-iranges)
6943 ("r-lattice" ,r-lattice)
6944 ("r-latticeextra" ,r-latticeextra)
6945 ("r-rsamtools" ,r-rsamtools)
6946 ("r-s4vectors" ,r-s4vectors)
6947 ("r-xvector" ,r-xvector)
6948 ("r-zlibbioc" ,r-zlibbioc)))
6949 (home-page "https://bioconductor.org/packages/ShortRead")
6950 (synopsis "FASTQ input and manipulation tools")
6952 "This package implements sampling, iteration, and input of FASTQ files.
6953 It includes functions for filtering and trimming reads, and for generating a
6954 quality assessment report. Data are represented as
6955 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6956 purposes. The package also contains legacy support for early single-end,
6957 ungapped alignment formats.")
6958 (license license:artistic2.0)))
6960 (define-public r-systempiper
6962 (name "r-systempiper")
6967 (uri (bioconductor-uri "systemPipeR" version))
6970 "18s5vpmw766pm64w7bwwfgpsv9yzhwclf0ya1rpqz8qslw7bbdjf"))))
6971 (properties `((upstream-name . "systemPipeR")))
6972 (build-system r-build-system)
6974 `(("r-annotate" ,r-annotate)
6975 ("r-batchtools" ,r-batchtools)
6976 ("r-biocgenerics" ,r-biocgenerics)
6977 ("r-biostrings" ,r-biostrings)
6978 ("r-deseq2" ,r-deseq2)
6979 ("r-edger" ,r-edger)
6980 ("r-genomicfeatures" ,r-genomicfeatures)
6981 ("r-genomicranges" ,r-genomicranges)
6982 ("r-ggplot2" ,r-ggplot2)
6983 ("r-go-db" ,r-go-db)
6984 ("r-gostats" ,r-gostats)
6985 ("r-limma" ,r-limma)
6986 ("r-pheatmap" ,r-pheatmap)
6987 ("r-rjson" ,r-rjson)
6988 ("r-rsamtools" ,r-rsamtools)
6989 ("r-shortread" ,r-shortread)
6990 ("r-summarizedexperiment" ,r-summarizedexperiment)
6992 ("r-variantannotation" ,r-variantannotation)))
6993 (home-page "https://github.com/tgirke/systemPipeR")
6994 (synopsis "Next generation sequencing workflow and reporting environment")
6996 "This R package provides tools for building and running automated
6997 end-to-end analysis workflows for a wide range of @dfn{next generation
6998 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6999 Important features include a uniform workflow interface across different NGS
7000 applications, automated report generation, and support for running both R and
7001 command-line software, such as NGS aligners or peak/variant callers, on local
7002 computers or compute clusters. Efficient handling of complex sample sets and
7003 experimental designs is facilitated by a consistently implemented sample
7004 annotation infrastructure.")
7005 (license license:artistic2.0)))
7007 (define-public r-grohmm
7014 (uri (bioconductor-uri "groHMM" version))
7017 "1p368qf8ab1vy8gl2j7rx0l7bvva4m7w06i364rqzs0sdyzlbm3y"))))
7018 (properties `((upstream-name . "groHMM")))
7019 (build-system r-build-system)
7021 `(("r-genomeinfodb" ,r-genomeinfodb)
7022 ("r-genomicalignments" ,r-genomicalignments)
7023 ("r-genomicranges" ,r-genomicranges)
7024 ("r-iranges" ,r-iranges)
7026 ("r-rtracklayer" ,r-rtracklayer)
7027 ("r-s4vectors" ,r-s4vectors)))
7028 (home-page "https://github.com/Kraus-Lab/groHMM")
7029 (synopsis "GRO-seq analysis pipeline")
7031 "This package provides a pipeline for the analysis of GRO-seq data.")
7032 (license license:gpl3+)))
7034 (define-public vsearch
7042 (url "https://github.com/torognes/vsearch.git")
7043 (commit (string-append "v" version))))
7044 (file-name (git-file-name name version))
7047 "0vhrpjfdf75ba04b24xknp41790cvcgwl0vgpy7qbzj5xh2521ss"))
7048 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
7051 ;; Remove bundled cityhash sources. The vsearch source is adjusted
7052 ;; for this in the patch.
7053 (delete-file "src/city.h")
7054 (delete-file "src/citycrc.h")
7055 (delete-file "src/city.cc")
7057 (build-system gnu-build-system)
7061 ("cityhash" ,cityhash)))
7063 `(("autoconf" ,autoconf)
7064 ("automake" ,automake)))
7065 (synopsis "Sequence search tools for metagenomics")
7067 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
7068 dereplication, pairwise alignment, shuffling, subsampling, sorting and
7069 masking. The tool takes advantage of parallelism in the form of SIMD
7070 vectorization as well as multiple threads to perform accurate alignments at
7071 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
7072 Needleman-Wunsch).")
7073 (home-page "https://github.com/torognes/vsearch")
7074 ;; vsearch uses non-portable SSE intrinsics so building fails on other
7076 (supported-systems '("x86_64-linux"))
7077 ;; Dual licensed; also includes public domain source.
7078 (license (list license:gpl3 license:bsd-2))))
7080 (define-public pardre
7083 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
7088 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
7092 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
7093 (build-system gnu-build-system)
7095 `(#:tests? #f ; no tests included
7097 (modify-phases %standard-phases
7100 (lambda* (#:key outputs #:allow-other-keys)
7101 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
7102 (install-file "ParDRe" bin)
7105 `(("openmpi" ,openmpi)
7107 (synopsis "Parallel tool to remove duplicate DNA reads")
7109 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
7110 Duplicate reads can be seen as identical or nearly identical sequences with
7111 some mismatches. This tool lets users avoid the analysis of unnecessary
7112 reads, reducing the time of subsequent procedures with the
7113 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
7114 in order to exploit the parallel capabilities of multicore clusters. It is
7115 faster than multithreaded counterparts (end of 2015) for the same number of
7116 cores and, thanks to the message-passing technology, it can be executed on
7118 (home-page "https://sourceforge.net/projects/pardre/")
7119 (license license:gpl3+)))
7121 (define-public ruby-bio-kseq
7123 (name "ruby-bio-kseq")
7128 (uri (rubygems-uri "bio-kseq" version))
7131 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
7132 (build-system ruby-build-system)
7134 `(#:test-target "spec"))
7136 `(("bundler" ,bundler)
7137 ("ruby-rspec" ,ruby-rspec)
7138 ("ruby-rake-compiler" ,ruby-rake-compiler)))
7141 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
7143 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
7144 FASTQ parsing code. It provides a fast iterator over sequences and their
7146 (home-page "https://github.com/gusevfe/bio-kseq")
7147 (license license:expat)))
7149 (define-public bio-locus
7156 (uri (rubygems-uri "bio-locus" version))
7159 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
7160 (build-system ruby-build-system)
7162 `(("ruby-rspec" ,ruby-rspec)))
7163 (synopsis "Tool for fast querying of genome locations")
7165 "Bio-locus is a tabix-like tool for fast querying of genome
7166 locations. Many file formats in bioinformatics contain records that
7167 start with a chromosome name and a position for a SNP, or a start-end
7168 position for indels. Bio-locus allows users to store this chr+pos or
7169 chr+pos+alt information in a database.")
7170 (home-page "https://github.com/pjotrp/bio-locus")
7171 (license license:expat)))
7173 (define-public bio-blastxmlparser
7175 (name "bio-blastxmlparser")
7179 (uri (rubygems-uri "bio-blastxmlparser" version))
7182 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
7183 (build-system ruby-build-system)
7185 `(("ruby-bio-logger" ,ruby-bio-logger)
7186 ("ruby-nokogiri" ,ruby-nokogiri)))
7188 `(("ruby-rspec" ,ruby-rspec)))
7189 (synopsis "Fast big data BLAST XML parser and library")
7191 "Very fast parallel big-data BLAST XML file parser which can be used as
7192 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
7193 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
7194 (home-page "https://github.com/pjotrp/blastxmlparser")
7195 (license license:expat)))
7197 (define-public bioruby
7204 (uri (rubygems-uri "bio" version))
7207 "1d56amdsjv1mag7m6gv2w0xij8hqx1v5xbdjsix8sp3yp36m7938"))))
7208 (build-system ruby-build-system)
7210 `(("ruby-libxml" ,ruby-libxml)))
7212 `(("which" ,which))) ; required for test phase
7215 (modify-phases %standard-phases
7216 (add-before 'build 'patch-test-command
7218 (substitute* '("test/functional/bio/test_command.rb")
7219 (("/bin/sh") (which "sh")))
7220 (substitute* '("test/functional/bio/test_command.rb")
7221 (("/bin/ls") (which "ls")))
7222 (substitute* '("test/functional/bio/test_command.rb")
7223 (("which") (which "which")))
7224 (substitute* '("test/functional/bio/test_command.rb",
7225 "test/data/command/echoarg2.sh")
7226 (("/bin/echo") (which "echo")))
7228 (synopsis "Ruby library, shell and utilities for bioinformatics")
7229 (description "BioRuby comes with a comprehensive set of Ruby development
7230 tools and libraries for bioinformatics and molecular biology. BioRuby has
7231 components for sequence analysis, pathway analysis, protein modelling and
7232 phylogenetic analysis; it supports many widely used data formats and provides
7233 easy access to databases, external programs and public web services, including
7234 BLAST, KEGG, GenBank, MEDLINE and GO.")
7235 (home-page "http://bioruby.org/")
7236 ;; Code is released under Ruby license, except for setup
7237 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
7238 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
7240 (define-public r-biocinstaller
7242 (name "r-biocinstaller")
7246 (uri (bioconductor-uri "BiocInstaller" version))
7249 "1s1f9qhyf3mc73ir25x2zlgi9hf45a37lg4z8fbva4i21hqisgsl"))))
7251 `((upstream-name . "BiocInstaller")))
7252 (build-system r-build-system)
7253 (home-page "https://bioconductor.org/packages/BiocInstaller")
7254 (synopsis "Install Bioconductor packages")
7255 (description "This package is used to install and update R packages from
7256 Bioconductor, CRAN, and Github.")
7257 (license license:artistic2.0)))
7259 (define-public r-biocviews
7261 (name "r-biocviews")
7265 (uri (bioconductor-uri "biocViews" version))
7268 "0qwrsd9fcpkv7hhzy1scnj7ahdxi6cjary28kqk6b36gkzmnrw4r"))))
7270 `((upstream-name . "biocViews")))
7271 (build-system r-build-system)
7273 `(("r-biobase" ,r-biobase)
7274 ("r-biocmanager" ,r-biocmanager)
7275 ("r-graph" ,r-graph)
7277 ("r-rcurl" ,r-rcurl)
7279 ("r-runit" ,r-runit)))
7280 (home-page "https://bioconductor.org/packages/biocViews")
7281 (synopsis "Bioconductor package categorization helper")
7282 (description "The purpose of biocViews is to create HTML pages that
7283 categorize packages in a Bioconductor package repository according to keywords,
7284 also known as views, in a controlled vocabulary.")
7285 (license license:artistic2.0)))
7287 (define-public r-biocstyle
7289 (name "r-biocstyle")
7293 (uri (bioconductor-uri "BiocStyle" version))
7296 "029x8r9rcx6zy0xixdpwxai4jv4ynb161821fzac6z4r8k418398"))))
7298 `((upstream-name . "BiocStyle")))
7299 (build-system r-build-system)
7301 `(("r-biocmanager" ,r-biocmanager)
7302 ("r-bookdown" ,r-bookdown)
7303 ("r-knitr" ,r-knitr)
7304 ("r-rmarkdown" ,r-rmarkdown)
7305 ("r-yaml" ,r-yaml)))
7306 (home-page "https://bioconductor.org/packages/BiocStyle")
7307 (synopsis "Bioconductor formatting styles")
7308 (description "This package provides standard formatting styles for
7309 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
7311 (license license:artistic2.0)))
7313 (define-public r-bioccheck
7315 (name "r-bioccheck")
7319 (uri (bioconductor-uri "BiocCheck" version))
7322 "1gkw9s6dhdryga9ap5yhvcqg9jsy4cn417ayqk1qiv6fy91fd124"))))
7324 `((upstream-name . "BiocCheck")))
7325 (build-system r-build-system)
7328 (modify-phases %standard-phases
7329 ;; This package can be used by calling BiocCheck(<package>) from
7330 ;; within R, or by running R CMD BiocCheck <package>. This phase
7331 ;; makes sure the latter works. For this to work, the BiocCheck
7332 ;; script must be somewhere on the PATH (not the R bin directory).
7333 (add-after 'install 'install-bioccheck-subcommand
7334 (lambda* (#:key outputs #:allow-other-keys)
7335 (let* ((out (assoc-ref outputs "out"))
7336 (dest-dir (string-append out "/bin"))
7338 (string-append out "/site-library/BiocCheck/script/")))
7340 (symlink (string-append script-dir "/checkBadDeps.R")
7341 (string-append dest-dir "/checkBadDeps.R"))
7342 (symlink (string-append script-dir "/BiocCheck")
7343 (string-append dest-dir "/BiocCheck")))
7346 `(("r-codetools" ,r-codetools)
7347 ("r-graph" ,r-graph)
7349 ("r-knitr" ,r-knitr)
7350 ("r-optparse" ,r-optparse)
7351 ("r-biocmanager" ,r-biocmanager)
7352 ("r-biocviews" ,r-biocviews)
7353 ("r-stringdist" ,r-stringdist)))
7354 (home-page "https://bioconductor.org/packages/BiocCheck")
7355 (synopsis "Executes Bioconductor-specific package checks")
7356 (description "This package contains tools to perform additional quality
7357 checks on R packages that are to be submitted to the Bioconductor repository.")
7358 (license license:artistic2.0)))
7360 (define-public r-s4vectors
7362 (name "r-s4vectors")
7366 (uri (bioconductor-uri "S4Vectors" version))
7369 "1wkqmpy0d0fab9bjfc7i5wh2zng75pg9rn9c1z1lkki7fpwaw2jb"))))
7371 `((upstream-name . "S4Vectors")))
7372 (build-system r-build-system)
7374 `(("r-biocgenerics" ,r-biocgenerics)))
7375 (home-page "https://bioconductor.org/packages/S4Vectors")
7376 (synopsis "S4 implementation of vectors and lists")
7378 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7379 classes and a set of generic functions that extend the semantic of ordinary
7380 vectors and lists in R. Package developers can easily implement vector-like
7381 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7382 In addition, a few low-level concrete subclasses of general interest (e.g.
7383 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7384 S4Vectors package itself.")
7385 (license license:artistic2.0)))
7387 (define-public r-iranges
7393 (uri (bioconductor-uri "IRanges" version))
7396 "1d64sh43pfc9vj2l7y7x6sb44l67wlnn3dzygp7ws0smn06mardq"))))
7398 `((upstream-name . "IRanges")))
7399 (build-system r-build-system)
7401 `(("r-biocgenerics" ,r-biocgenerics)
7402 ("r-s4vectors" ,r-s4vectors)))
7403 (home-page "https://bioconductor.org/packages/IRanges")
7404 (synopsis "Infrastructure for manipulating intervals on sequences")
7406 "This package provides efficient low-level and highly reusable S4 classes
7407 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7408 generally, data that can be organized sequentially (formally defined as
7409 @code{Vector} objects), as well as views on these @code{Vector} objects.
7410 Efficient list-like classes are also provided for storing big collections of
7411 instances of the basic classes. All classes in the package use consistent
7412 naming and share the same rich and consistent \"Vector API\" as much as
7414 (license license:artistic2.0)))
7416 (define-public r-genomeinfodbdata
7418 (name "r-genomeinfodbdata")
7422 ;; We cannot use bioconductor-uri here because this tarball is
7423 ;; located under "data/annotation/" instead of "bioc/".
7424 (uri (string-append "https://bioconductor.org/packages/release/"
7425 "data/annotation/src/contrib/GenomeInfoDbData_"
7429 "0di6nlqpsyqf693k2na65ayqldih563x3zfrczpqc5q2hl5kg35c"))))
7431 `((upstream-name . "GenomeInfoDbData")))
7432 (build-system r-build-system)
7433 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7434 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7435 (description "This package contains data for mapping between NCBI taxonomy
7436 ID and species. It is used by functions in the GenomeInfoDb package.")
7437 (license license:artistic2.0)))
7439 (define-public r-genomeinfodb
7441 (name "r-genomeinfodb")
7445 (uri (bioconductor-uri "GenomeInfoDb" version))
7448 "0zkhms81b3jz30q7ag81a1mq1rgqg4izyfdvcni68gvn8gm7kdyk"))))
7450 `((upstream-name . "GenomeInfoDb")))
7451 (build-system r-build-system)
7453 `(("r-biocgenerics" ,r-biocgenerics)
7454 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7455 ("r-iranges" ,r-iranges)
7456 ("r-rcurl" ,r-rcurl)
7457 ("r-s4vectors" ,r-s4vectors)))
7458 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7459 (synopsis "Utilities for manipulating chromosome identifiers")
7461 "This package contains data and functions that define and allow
7462 translation between different chromosome sequence naming conventions (e.g.,
7463 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7464 names in their natural, rather than lexicographic, order.")
7465 (license license:artistic2.0)))
7467 (define-public r-edger
7473 (uri (bioconductor-uri "edgeR" version))
7476 "0iba4krz30dx5b0s89n5cfkwn64867s7vmvvfqms9lbcr4kj439m"))))
7477 (properties `((upstream-name . "edgeR")))
7478 (build-system r-build-system)
7480 `(("r-limma" ,r-limma)
7481 ("r-locfit" ,r-locfit)
7483 ("r-statmod" ,r-statmod))) ;for estimateDisp
7484 (home-page "http://bioinf.wehi.edu.au/edgeR")
7485 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7486 (description "This package can do differential expression analysis of
7487 RNA-seq expression profiles with biological replication. It implements a range
7488 of statistical methodology based on the negative binomial distributions,
7489 including empirical Bayes estimation, exact tests, generalized linear models
7490 and quasi-likelihood tests. It be applied to differential signal analysis of
7491 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7493 (license license:gpl2+)))
7495 (define-public r-variantannotation
7497 (name "r-variantannotation")
7501 (uri (bioconductor-uri "VariantAnnotation" version))
7504 "144x3d3b9a3q5jy4aqrk1nf2yavwjhwlf71s7qyr4x3ms3wmvf8i"))))
7506 `((upstream-name . "VariantAnnotation")))
7510 `(("r-annotationdbi" ,r-annotationdbi)
7511 ("r-biobase" ,r-biobase)
7512 ("r-biocgenerics" ,r-biocgenerics)
7513 ("r-biostrings" ,r-biostrings)
7514 ("r-bsgenome" ,r-bsgenome)
7516 ("r-genomeinfodb" ,r-genomeinfodb)
7517 ("r-genomicfeatures" ,r-genomicfeatures)
7518 ("r-genomicranges" ,r-genomicranges)
7519 ("r-iranges" ,r-iranges)
7520 ("r-summarizedexperiment" ,r-summarizedexperiment)
7521 ("r-rhtslib" ,r-rhtslib)
7522 ("r-rsamtools" ,r-rsamtools)
7523 ("r-rtracklayer" ,r-rtracklayer)
7524 ("r-s4vectors" ,r-s4vectors)
7525 ("r-xvector" ,r-xvector)
7526 ("r-zlibbioc" ,r-zlibbioc)))
7527 (build-system r-build-system)
7528 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7529 (synopsis "Package for annotation of genetic variants")
7530 (description "This R package can annotate variants, compute amino acid
7531 coding changes and predict coding outcomes.")
7532 (license license:artistic2.0)))
7534 (define-public r-limma
7540 (uri (bioconductor-uri "limma" version))
7543 "1d4ig2b7fa9mwja52isxrwmprfdjdk1mlcf2skhdp51l24z6wbk7"))))
7544 (build-system r-build-system)
7545 (home-page "http://bioinf.wehi.edu.au/limma")
7546 (synopsis "Package for linear models for microarray and RNA-seq data")
7547 (description "This package can be used for the analysis of gene expression
7548 studies, especially the use of linear models for analysing designed experiments
7549 and the assessment of differential expression. The analysis methods apply to
7550 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7551 (license license:gpl2+)))
7553 (define-public r-xvector
7559 (uri (bioconductor-uri "XVector" version))
7562 "12y09pwy86h1za6cmaxs960r7fs0vjzhl0li8jn59vqq9liza1ap"))))
7564 `((upstream-name . "XVector")))
7565 (build-system r-build-system)
7568 (modify-phases %standard-phases
7569 (add-after 'unpack 'use-system-zlib
7571 (substitute* "DESCRIPTION"
7572 (("zlibbioc, ") ""))
7573 (substitute* "NAMESPACE"
7574 (("import\\(zlibbioc\\)") ""))
7579 `(("r-biocgenerics" ,r-biocgenerics)
7580 ("r-iranges" ,r-iranges)
7581 ("r-s4vectors" ,r-s4vectors)))
7582 (home-page "https://bioconductor.org/packages/XVector")
7583 (synopsis "Representation and manpulation of external sequences")
7585 "This package provides memory efficient S4 classes for storing sequences
7586 \"externally\" (behind an R external pointer, or on disk).")
7587 (license license:artistic2.0)))
7589 (define-public r-genomicranges
7591 (name "r-genomicranges")
7595 (uri (bioconductor-uri "GenomicRanges" version))
7598 "1285fr8qjd7d0ixpv7d5imi0n6wzc4k6yia1rkmig71qd2gg556k"))))
7600 `((upstream-name . "GenomicRanges")))
7601 (build-system r-build-system)
7603 `(("r-biocgenerics" ,r-biocgenerics)
7604 ("r-genomeinfodb" ,r-genomeinfodb)
7605 ("r-iranges" ,r-iranges)
7606 ("r-s4vectors" ,r-s4vectors)
7607 ("r-xvector" ,r-xvector)))
7608 (home-page "https://bioconductor.org/packages/GenomicRanges")
7609 (synopsis "Representation and manipulation of genomic intervals")
7611 "This package provides tools to efficiently represent and manipulate
7612 genomic annotations and alignments is playing a central role when it comes to
7613 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7614 GenomicRanges package defines general purpose containers for storing and
7615 manipulating genomic intervals and variables defined along a genome.")
7616 (license license:artistic2.0)))
7618 (define-public r-biobase
7624 (uri (bioconductor-uri "Biobase" version))
7627 "15yl92niqamx3lmwd11zlk0xniibqnh1gi280iadxicmchi83npc"))))
7629 `((upstream-name . "Biobase")))
7630 (build-system r-build-system)
7632 `(("r-biocgenerics" ,r-biocgenerics)))
7633 (home-page "https://bioconductor.org/packages/Biobase")
7634 (synopsis "Base functions for Bioconductor")
7636 "This package provides functions that are needed by many other packages
7637 on Bioconductor or which replace R functions.")
7638 (license license:artistic2.0)))
7640 (define-public r-annotationdbi
7642 (name "r-annotationdbi")
7646 (uri (bioconductor-uri "AnnotationDbi" version))
7649 "0lfq5668a6sq4kqhxx78hl3jcaqdsaaliiybl9xyya2scdk8c29c"))))
7651 `((upstream-name . "AnnotationDbi")))
7652 (build-system r-build-system)
7654 `(("r-biobase" ,r-biobase)
7655 ("r-biocgenerics" ,r-biocgenerics)
7657 ("r-iranges" ,r-iranges)
7658 ("r-rsqlite" ,r-rsqlite)
7659 ("r-s4vectors" ,r-s4vectors)))
7660 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7661 (synopsis "Annotation database interface")
7663 "This package provides user interface and database connection code for
7664 annotation data packages using SQLite data storage.")
7665 (license license:artistic2.0)))
7667 (define-public r-biomart
7673 (uri (bioconductor-uri "biomaRt" version))
7676 "1abl0c4qbhfqf9ixdp74183phm7s8rszrr5ldczm59b8vyng8rhx"))))
7678 `((upstream-name . "biomaRt")))
7679 (build-system r-build-system)
7681 `(("r-annotationdbi" ,r-annotationdbi)
7683 ("r-progress" ,r-progress)
7684 ("r-rcurl" ,r-rcurl)
7685 ("r-stringr" ,r-stringr)
7687 (home-page "https://bioconductor.org/packages/biomaRt")
7688 (synopsis "Interface to BioMart databases")
7690 "biomaRt provides an interface to a growing collection of databases
7691 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7692 package enables retrieval of large amounts of data in a uniform way without
7693 the need to know the underlying database schemas or write complex SQL queries.
7694 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7695 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7696 users direct access to a diverse set of data and enable a wide range of
7697 powerful online queries from gene annotation to database mining.")
7698 (license license:artistic2.0)))
7700 (define-public r-biocparallel
7702 (name "r-biocparallel")
7706 (uri (bioconductor-uri "BiocParallel" version))
7709 "0v8rhf3hbgb3v32h2pmsv1y6q2x4airmpp50fk7z6ardcn4aza7x"))))
7711 `((upstream-name . "BiocParallel")))
7712 (build-system r-build-system)
7714 `(("r-futile-logger" ,r-futile-logger)
7717 (home-page "https://bioconductor.org/packages/BiocParallel")
7718 (synopsis "Bioconductor facilities for parallel evaluation")
7720 "This package provides modified versions and novel implementation of
7721 functions for parallel evaluation, tailored to use with Bioconductor
7723 (license (list license:gpl2+ license:gpl3+))))
7725 (define-public r-biostrings
7727 (name "r-biostrings")
7731 (uri (bioconductor-uri "Biostrings" version))
7734 "0inrl97hli3qz6cfxcikc4picmbrqc8phdgqi18ynlvxy5ql64h4"))))
7736 `((upstream-name . "Biostrings")))
7737 (build-system r-build-system)
7739 `(("r-biocgenerics" ,r-biocgenerics)
7740 ("r-iranges" ,r-iranges)
7741 ("r-s4vectors" ,r-s4vectors)
7742 ("r-xvector" ,r-xvector)))
7743 (home-page "https://bioconductor.org/packages/Biostrings")
7744 (synopsis "String objects and algorithms for biological sequences")
7746 "This package provides memory efficient string containers, string
7747 matching algorithms, and other utilities, for fast manipulation of large
7748 biological sequences or sets of sequences.")
7749 (license license:artistic2.0)))
7751 (define-public r-rsamtools
7753 (name "r-rsamtools")
7757 (uri (bioconductor-uri "Rsamtools" version))
7760 "1nv5idyjk75mvl4np5sig0xa6qygm1ivj33k041ffyj19q8jf7ij"))))
7762 `((upstream-name . "Rsamtools")))
7763 (build-system r-build-system)
7766 (modify-phases %standard-phases
7767 (add-after 'unpack 'use-system-zlib
7769 (substitute* "DESCRIPTION"
7770 (("zlibbioc, ") ""))
7771 (substitute* "NAMESPACE"
7772 (("import\\(zlibbioc\\)") ""))
7777 `(("r-biocgenerics" ,r-biocgenerics)
7778 ("r-biocparallel" ,r-biocparallel)
7779 ("r-biostrings" ,r-biostrings)
7780 ("r-bitops" ,r-bitops)
7781 ("r-genomeinfodb" ,r-genomeinfodb)
7782 ("r-genomicranges" ,r-genomicranges)
7783 ("r-iranges" ,r-iranges)
7784 ("r-rhtslib" ,r-rhtslib)
7785 ("r-s4vectors" ,r-s4vectors)
7786 ("r-xvector" ,r-xvector)))
7787 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7788 (synopsis "Interface to samtools, bcftools, and tabix")
7790 "This package provides an interface to the @code{samtools},
7791 @code{bcftools}, and @code{tabix} utilities for manipulating SAM (Sequence
7792 Alignment / Map), FASTA, binary variant call (BCF) and compressed indexed
7793 tab-delimited (tabix) files.")
7794 (license license:expat)))
7796 (define-public r-delayedarray
7798 (name "r-delayedarray")
7802 (uri (bioconductor-uri "DelayedArray" version))
7805 "0l907ggxndn3f29zvsd5pppmp4c31rb22r6zkhvgph7xdxahyy6z"))))
7807 `((upstream-name . "DelayedArray")))
7808 (build-system r-build-system)
7810 `(("r-biocgenerics" ,r-biocgenerics)
7811 ("r-biocparallel" ,r-biocparallel)
7812 ("r-s4vectors" ,r-s4vectors)
7813 ("r-iranges" ,r-iranges)
7814 ("r-matrix" ,r-matrix)
7815 ("r-matrixstats" ,r-matrixstats)))
7816 (home-page "https://bioconductor.org/packages/DelayedArray")
7817 (synopsis "Delayed operations on array-like objects")
7819 "Wrapping an array-like object (typically an on-disk object) in a
7820 @code{DelayedArray} object allows one to perform common array operations on it
7821 without loading the object in memory. In order to reduce memory usage and
7822 optimize performance, operations on the object are either delayed or executed
7823 using a block processing mechanism. Note that this also works on in-memory
7824 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7825 @code{Matrix} objects, and ordinary arrays and data frames.")
7826 (license license:artistic2.0)))
7828 (define-public r-summarizedexperiment
7830 (name "r-summarizedexperiment")
7834 (uri (bioconductor-uri "SummarizedExperiment" version))
7837 "1ypk63pdml89y81pr41i2zq0fimsaxsa5lgpg6xs5cwikyaq0pci"))))
7839 `((upstream-name . "SummarizedExperiment")))
7840 (build-system r-build-system)
7842 `(("r-biobase" ,r-biobase)
7843 ("r-biocgenerics" ,r-biocgenerics)
7844 ("r-delayedarray" ,r-delayedarray)
7845 ("r-genomeinfodb" ,r-genomeinfodb)
7846 ("r-genomicranges" ,r-genomicranges)
7847 ("r-iranges" ,r-iranges)
7848 ("r-matrix" ,r-matrix)
7849 ("r-s4vectors" ,r-s4vectors)))
7850 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
7851 (synopsis "Container for representing genomic ranges by sample")
7853 "The SummarizedExperiment container contains one or more assays, each
7854 represented by a matrix-like object of numeric or other mode. The rows
7855 typically represent genomic ranges of interest and the columns represent
7857 (license license:artistic2.0)))
7859 (define-public r-genomicalignments
7861 (name "r-genomicalignments")
7865 (uri (bioconductor-uri "GenomicAlignments" version))
7868 "0s3q97q4pgj5jwn4g95al44rahrwsncsf45v01v4071msx3xmjxq"))))
7870 `((upstream-name . "GenomicAlignments")))
7871 (build-system r-build-system)
7873 `(("r-biocgenerics" ,r-biocgenerics)
7874 ("r-biocparallel" ,r-biocparallel)
7875 ("r-biostrings" ,r-biostrings)
7876 ("r-genomeinfodb" ,r-genomeinfodb)
7877 ("r-genomicranges" ,r-genomicranges)
7878 ("r-iranges" ,r-iranges)
7879 ("r-rsamtools" ,r-rsamtools)
7880 ("r-s4vectors" ,r-s4vectors)
7881 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7882 (home-page "https://bioconductor.org/packages/GenomicAlignments")
7883 (synopsis "Representation and manipulation of short genomic alignments")
7885 "This package provides efficient containers for storing and manipulating
7886 short genomic alignments (typically obtained by aligning short reads to a
7887 reference genome). This includes read counting, computing the coverage,
7888 junction detection, and working with the nucleotide content of the
7890 (license license:artistic2.0)))
7892 (define-public r-rtracklayer
7894 (name "r-rtracklayer")
7898 (uri (bioconductor-uri "rtracklayer" version))
7901 "161gcks9b12993g9k27gf7wfh8lgd8m8rr7x2slgfqqssk0yrmpd"))))
7902 (build-system r-build-system)
7905 (modify-phases %standard-phases
7906 (add-after 'unpack 'use-system-zlib
7908 (substitute* "DESCRIPTION"
7909 ((" zlibbioc,") ""))
7910 (substitute* "NAMESPACE"
7911 (("import\\(zlibbioc\\)") ""))
7914 `(("pkg-config" ,pkg-config)))
7918 `(("r-biocgenerics" ,r-biocgenerics)
7919 ("r-biostrings" ,r-biostrings)
7920 ("r-genomeinfodb" ,r-genomeinfodb)
7921 ("r-genomicalignments" ,r-genomicalignments)
7922 ("r-genomicranges" ,r-genomicranges)
7923 ("r-iranges" ,r-iranges)
7924 ("r-rcurl" ,r-rcurl)
7925 ("r-rsamtools" ,r-rsamtools)
7926 ("r-s4vectors" ,r-s4vectors)
7928 ("r-xvector" ,r-xvector)))
7929 (home-page "https://bioconductor.org/packages/rtracklayer")
7930 (synopsis "R interface to genome browsers and their annotation tracks")
7932 "rtracklayer is an extensible framework for interacting with multiple
7933 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7934 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7935 built-in). The user may export/import tracks to/from the supported browsers,
7936 as well as query and modify the browser state, such as the current viewport.")
7937 (license license:artistic2.0)))
7939 (define-public r-genomicfeatures
7941 (name "r-genomicfeatures")
7945 (uri (bioconductor-uri "GenomicFeatures" version))
7948 "0zkd57i5qjxsravv0gbyckc0wrnqzgxd61ibh3jmhmrccrr9ihn3"))))
7950 `((upstream-name . "GenomicFeatures")))
7951 (build-system r-build-system)
7953 `(("r-annotationdbi" ,r-annotationdbi)
7954 ("r-biobase" ,r-biobase)
7955 ("r-biocgenerics" ,r-biocgenerics)
7956 ("r-biomart" ,r-biomart)
7957 ("r-biostrings" ,r-biostrings)
7959 ("r-genomeinfodb" ,r-genomeinfodb)
7960 ("r-genomicranges" ,r-genomicranges)
7961 ("r-iranges" ,r-iranges)
7962 ("r-rcurl" ,r-rcurl)
7963 ("r-rsqlite" ,r-rsqlite)
7964 ("r-rtracklayer" ,r-rtracklayer)
7965 ("r-s4vectors" ,r-s4vectors)
7966 ("r-xvector" ,r-xvector)))
7967 (home-page "https://bioconductor.org/packages/GenomicFeatures")
7968 (synopsis "Tools for working with transcript centric annotations")
7970 "This package provides a set of tools and methods for making and
7971 manipulating transcript centric annotations. With these tools the user can
7972 easily download the genomic locations of the transcripts, exons and cds of a
7973 given organism, from either the UCSC Genome Browser or a BioMart
7974 database (more sources will be supported in the future). This information is
7975 then stored in a local database that keeps track of the relationship between
7976 transcripts, exons, cds and genes. Flexible methods are provided for
7977 extracting the desired features in a convenient format.")
7978 (license license:artistic2.0)))
7980 (define-public r-go-db
7986 (uri (string-append "https://www.bioconductor.org/packages/"
7987 "release/data/annotation/src/contrib/GO.db_"
7991 "0i3wcf5h3n0dawzc1hy0kv74f06j80c47n4p3g3fmrcxlhi3jpa5"))))
7993 `((upstream-name . "GO.db")))
7994 (build-system r-build-system)
7996 `(("r-annotationdbi" ,r-annotationdbi)))
7997 (home-page "https://bioconductor.org/packages/GO.db")
7998 (synopsis "Annotation maps describing the entire Gene Ontology")
8000 "The purpose of this GO.db annotation package is to provide detailed
8001 information about the latest version of the Gene Ontologies.")
8002 (license license:artistic2.0)))
8004 (define-public r-topgo
8010 (uri (bioconductor-uri "topGO" version))
8013 "09z42jwz5vh289ijz3x68zv5vmgkgcbhlp73vvmna1gld5lh5kz1"))))
8015 `((upstream-name . "topGO")))
8016 (build-system r-build-system)
8018 `(("r-annotationdbi" ,r-annotationdbi)
8020 ("r-biobase" ,r-biobase)
8021 ("r-biocgenerics" ,r-biocgenerics)
8022 ("r-go-db" ,r-go-db)
8023 ("r-graph" ,r-graph)
8024 ("r-lattice" ,r-lattice)
8025 ("r-matrixstats" ,r-matrixstats)
8026 ("r-sparsem" ,r-sparsem)))
8027 (home-page "https://bioconductor.org/packages/topGO")
8028 (synopsis "Enrichment analysis for gene ontology")
8030 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
8031 terms while accounting for the topology of the GO graph. Different test
8032 statistics and different methods for eliminating local similarities and
8033 dependencies between GO terms can be implemented and applied.")
8034 ;; Any version of the LGPL applies.
8035 (license license:lgpl2.1+)))
8037 (define-public r-bsgenome
8043 (uri (bioconductor-uri "BSgenome" version))
8046 "0zwx42s73hc1vhn0v82i67mcixdwwc6n6q5h5vpnhpxlm4qwgqzp"))))
8048 `((upstream-name . "BSgenome")))
8049 (build-system r-build-system)
8051 `(("r-biocgenerics" ,r-biocgenerics)
8052 ("r-biostrings" ,r-biostrings)
8053 ("r-genomeinfodb" ,r-genomeinfodb)
8054 ("r-genomicranges" ,r-genomicranges)
8055 ("r-iranges" ,r-iranges)
8056 ("r-rsamtools" ,r-rsamtools)
8057 ("r-rtracklayer" ,r-rtracklayer)
8058 ("r-s4vectors" ,r-s4vectors)
8059 ("r-xvector" ,r-xvector)))
8060 (home-page "https://bioconductor.org/packages/BSgenome")
8061 (synopsis "Infrastructure for Biostrings-based genome data packages")
8063 "This package provides infrastructure shared by all Biostrings-based
8064 genome data packages and support for efficient SNP representation.")
8065 (license license:artistic2.0)))
8067 (define-public r-impute
8073 (uri (bioconductor-uri "impute" version))
8076 "144jb889979cv3il2zxqk724v3sj1wnzjm3lkspxcvk29dbb9q8j"))))
8078 `(("gfortran" ,gfortran)))
8079 (build-system r-build-system)
8080 (home-page "https://bioconductor.org/packages/impute")
8081 (synopsis "Imputation for microarray data")
8083 "This package provides a function to impute missing gene expression
8084 microarray data, using nearest neighbor averaging.")
8085 (license license:gpl2+)))
8087 (define-public r-seqpattern
8089 (name "r-seqpattern")
8093 (uri (bioconductor-uri "seqPattern" version))
8096 "1ljqscbmrmi5d4lzzvg2d86sqzch26yxw57d33qyid300wm60db2"))))
8098 `((upstream-name . "seqPattern")))
8099 (build-system r-build-system)
8101 `(("r-biostrings" ,r-biostrings)
8102 ("r-genomicranges" ,r-genomicranges)
8103 ("r-iranges" ,r-iranges)
8104 ("r-kernsmooth" ,r-kernsmooth)
8105 ("r-plotrix" ,r-plotrix)))
8106 (home-page "https://bioconductor.org/packages/seqPattern")
8107 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
8109 "This package provides tools to visualize oligonucleotide patterns and
8110 sequence motif occurrences across a large set of sequences centred at a common
8111 reference point and sorted by a user defined feature.")
8112 (license license:gpl3+)))
8114 (define-public r-genomation
8116 (name "r-genomation")
8120 (uri (bioconductor-uri "genomation" version))
8123 "06i711pwq9znd7plh0p25skxnnh5dyl61c33k9gma243wvlzmlkj"))))
8124 (build-system r-build-system)
8126 `(("r-biostrings" ,r-biostrings)
8127 ("r-bsgenome" ,r-bsgenome)
8128 ("r-data-table" ,r-data-table)
8129 ("r-genomeinfodb" ,r-genomeinfodb)
8130 ("r-genomicalignments" ,r-genomicalignments)
8131 ("r-genomicranges" ,r-genomicranges)
8132 ("r-ggplot2" ,r-ggplot2)
8133 ("r-gridbase" ,r-gridbase)
8134 ("r-impute" ,r-impute)
8135 ("r-iranges" ,r-iranges)
8136 ("r-matrixstats" ,r-matrixstats)
8137 ("r-plotrix" ,r-plotrix)
8140 ("r-readr" ,r-readr)
8141 ("r-reshape2" ,r-reshape2)
8142 ("r-rsamtools" ,r-rsamtools)
8143 ("r-rtracklayer" ,r-rtracklayer)
8144 ("r-runit" ,r-runit)
8145 ("r-s4vectors" ,r-s4vectors)
8146 ("r-seqpattern" ,r-seqpattern)))
8147 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8148 (synopsis "Summary, annotation and visualization of genomic data")
8150 "This package provides a package for summary and annotation of genomic
8151 intervals. Users can visualize and quantify genomic intervals over
8152 pre-defined functional regions, such as promoters, exons, introns, etc. The
8153 genomic intervals represent regions with a defined chromosome position, which
8154 may be associated with a score, such as aligned reads from HT-seq experiments,
8155 TF binding sites, methylation scores, etc. The package can use any tabular
8156 genomic feature data as long as it has minimal information on the locations of
8157 genomic intervals. In addition, it can use BAM or BigWig files as input.")
8158 (license license:artistic2.0)))
8160 (define-public r-genomationdata
8162 (name "r-genomationdata")
8166 ;; We cannot use bioconductor-uri here because this tarball is
8167 ;; located under "data/annotation/" instead of "bioc/".
8168 (uri (string-append "https://bioconductor.org/packages/"
8169 "release/data/experiment/src/contrib/"
8170 "genomationData_" version ".tar.gz"))
8173 "10xyb8akjrhmak2i0mnv1agny2ipy364q9nlibyplpzc7vdb6bw7"))))
8174 (build-system r-build-system)
8175 ;; As this package provides little more than large data files, it doesn't
8176 ;; make sense to build substitutes.
8177 (arguments `(#:substitutable? #f))
8179 `(("r-knitr" ,r-knitr)))
8180 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8181 (synopsis "Experimental data for use with the genomation package")
8183 "This package contains experimental genetic data for use with the
8184 genomation package. Included are Chip Seq, Methylation and Cage data,
8185 downloaded from Encode.")
8186 (license license:gpl3+)))
8188 (define-public r-seqlogo
8195 (uri (bioconductor-uri "seqLogo" version))
8198 "1z63imr1a24nqijpvxaxlakykcsadfqyxl2b3vlllncxnjjvb52b"))))
8199 (properties `((upstream-name . "seqLogo")))
8200 (build-system r-build-system)
8201 (home-page "https://bioconductor.org/packages/seqLogo")
8202 (synopsis "Sequence logos for DNA sequence alignments")
8204 "seqLogo takes the position weight matrix of a DNA sequence motif and
8205 plots the corresponding sequence logo as introduced by Schneider and
8207 (license license:lgpl2.0+)))
8209 (define-public r-motifrg
8216 (uri (bioconductor-uri "motifRG" version))
8219 "02c7fbjwdq7pk96bd2rn07l9r2hqy00s3hfpli5ybmwgvc9h9z4z"))))
8220 (properties `((upstream-name . "motifRG")))
8221 (build-system r-build-system)
8223 `(("r-biostrings" ,r-biostrings)
8224 ("r-bsgenome" ,r-bsgenome)
8225 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8226 ("r-iranges" ,r-iranges)
8227 ("r-seqlogo" ,r-seqlogo)
8228 ("r-xvector" ,r-xvector)))
8229 (home-page "https://bioconductor.org/packages/motifRG")
8230 (synopsis "Discover motifs in high throughput sequencing data")
8232 "This package provides tools for discriminative motif discovery in high
8233 throughput genetic sequencing data sets using regression methods.")
8234 (license license:artistic2.0)))
8236 (define-public r-qtl
8243 (uri (string-append "mirror://cran/src/contrib/qtl_"
8247 "03lmvydln8b7666b6w46qbryhf83vsd11d4y2v95rfgvqgq66l1i"))))
8248 (build-system r-build-system)
8249 (home-page "http://rqtl.org/")
8250 (synopsis "R package for analyzing QTL experiments in genetics")
8251 (description "R/qtl is an extension library for the R statistics
8252 system. It is used to analyze experimental crosses for identifying
8253 genes contributing to variation in quantitative traits (so-called
8254 quantitative trait loci, QTLs).
8256 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
8257 identify genotyping errors, and to perform single-QTL and two-QTL,
8258 two-dimensional genome scans.")
8259 (license license:gpl3)))
8261 (define-public r-zlibbioc
8267 (uri (bioconductor-uri "zlibbioc" version))
8270 "1h0a2ps2rfk9azzps7p23sxj5z1giv8gcx0ypzgyz7fkr4xi9z7k"))))
8272 `((upstream-name . "zlibbioc")))
8273 (build-system r-build-system)
8274 (home-page "https://bioconductor.org/packages/zlibbioc")
8275 (synopsis "Provider for zlib-1.2.5 to R packages")
8276 (description "This package uses the source code of zlib-1.2.5 to create
8277 libraries for systems that do not have these available via other means.")
8278 (license license:artistic2.0)))
8280 (define-public r-r4rna
8287 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8291 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8292 (build-system r-build-system)
8294 `(("r-optparse" ,r-optparse)
8295 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8296 (home-page "http://www.e-rna.org/r-chie/index.cgi")
8297 (synopsis "Analysis framework for RNA secondary structure")
8299 "The R4RNA package aims to be a general framework for the analysis of RNA
8300 secondary structure and comparative analysis in R.")
8301 (license license:gpl3+)))
8303 (define-public r-rhtslib
8310 (uri (bioconductor-uri "Rhtslib" version))
8313 "178zbrm221rwhbjk7j2v9g5ra44k0xg7c5abhd810m3g7snma8k8"))))
8314 (properties `((upstream-name . "Rhtslib")))
8315 (build-system r-build-system)
8316 ;; Without this a temporary directory ends up in the Rhtslib.so binary,
8317 ;; which makes R abort the build.
8318 (arguments '(#:configure-flags '("--no-staged-install")))
8320 `(("r-zlibbioc" ,r-zlibbioc)))
8324 `(("pkg-config" ,pkg-config)))
8325 (home-page "https://github.com/nhayden/Rhtslib")
8326 (synopsis "High-throughput sequencing library as an R package")
8328 "This package provides the HTSlib C library for high-throughput
8329 nucleotide sequence analysis. The package is primarily useful to developers
8330 of other R packages who wish to make use of HTSlib.")
8331 (license license:lgpl2.0+)))
8333 (define-public r-bamsignals
8335 (name "r-bamsignals")
8340 (uri (bioconductor-uri "bamsignals" version))
8343 "15q1q51dwl9qxfkf10yppw4m194ba03nq9plsrbj8fqj00v4729i"))))
8344 (build-system r-build-system)
8346 `(("r-biocgenerics" ,r-biocgenerics)
8347 ("r-genomicranges" ,r-genomicranges)
8348 ("r-iranges" ,r-iranges)
8350 ("r-rhtslib" ,r-rhtslib)
8351 ("r-zlibbioc" ,r-zlibbioc)))
8354 (home-page "https://bioconductor.org/packages/bamsignals")
8355 (synopsis "Extract read count signals from bam files")
8357 "This package allows to efficiently obtain count vectors from indexed bam
8358 files. It counts the number of nucleotide sequence reads in given genomic
8359 ranges and it computes reads profiles and coverage profiles. It also handles
8361 (license license:gpl2+)))
8363 (define-public r-rcas
8369 (uri (bioconductor-uri "RCAS" version))
8372 "1h4vf5gzilqbdrd8m9l3zc2m4sca8cir8366a7njgd558k7ld5kl"))))
8373 (properties `((upstream-name . "RCAS")))
8374 (build-system r-build-system)
8376 `(("r-annotationdbi" ,r-annotationdbi)
8377 ("r-biocgenerics" ,r-biocgenerics)
8378 ("r-biomart" ,r-biomart)
8379 ("r-biostrings" ,r-biostrings)
8380 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8381 ("r-cowplot" ,r-cowplot)
8382 ("r-data-table" ,r-data-table)
8385 ("r-genomation" ,r-genomation)
8386 ("r-genomeinfodb" ,r-genomeinfodb)
8387 ("r-genomicfeatures" ,r-genomicfeatures)
8388 ("r-genomicranges" ,r-genomicranges)
8389 ("r-ggplot2" ,r-ggplot2)
8390 ("r-ggseqlogo" ,r-ggseqlogo)
8391 ("r-knitr" ,r-knitr)
8392 ("r-motifrg" ,r-motifrg)
8393 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8394 ("r-pbapply" ,r-pbapply)
8395 ("r-pheatmap" ,r-pheatmap)
8396 ("r-plotly" ,r-plotly)
8397 ("r-plotrix" ,r-plotrix)
8398 ("r-proxy" ,r-proxy)
8399 ("r-rsqlite" ,r-rsqlite)
8400 ("r-rtracklayer" ,r-rtracklayer)
8401 ("r-rmarkdown" ,r-rmarkdown)
8402 ("r-s4vectors" ,r-s4vectors)
8403 ("r-topgo" ,r-topgo)
8404 ("pandoc" ,ghc-pandoc)))
8405 (synopsis "RNA-centric annotation system")
8407 "RCAS aims to be a standalone RNA-centric annotation system that provides
8408 intuitive reports and publication-ready graphics. This package provides the R
8409 library implementing most of the pipeline's features.")
8410 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8411 (license license:artistic2.0)))
8413 (define-public rcas-web
8420 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8421 "releases/download/v" version
8422 "/rcas-web-" version ".tar.gz"))
8425 "0wq951aj45gqki1bickg876i993lmawkp8x24agg264br5x716db"))))
8426 (build-system gnu-build-system)
8429 (modify-phases %standard-phases
8430 (add-after 'install 'wrap-executable
8431 (lambda* (#:key inputs outputs #:allow-other-keys)
8432 (let* ((out (assoc-ref outputs "out"))
8433 (json (assoc-ref inputs "guile-json"))
8434 (redis (assoc-ref inputs "guile-redis"))
8435 (path (string-append
8436 json "/share/guile/site/2.2:"
8437 redis "/share/guile/site/2.2")))
8438 (wrap-program (string-append out "/bin/rcas-web")
8439 `("GUILE_LOAD_PATH" ":" = (,path))
8440 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8441 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8444 `(("r-minimal" ,r-minimal)
8446 ("guile-next" ,guile-2.2)
8447 ("guile-json" ,guile-json)
8448 ("guile-redis" ,guile-redis)))
8450 `(("pkg-config" ,pkg-config)))
8451 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8452 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8453 (description "This package provides a simple web interface for the
8454 @dfn{RNA-centric annotation system} (RCAS).")
8455 (license license:agpl3+)))
8457 (define-public r-mutationalpatterns
8459 (name "r-mutationalpatterns")
8464 (uri (bioconductor-uri "MutationalPatterns" version))
8467 "1k3r06xj1nim1s8as1i7fykfa6fbb4x456kslbzdvbf83ppx34z3"))))
8468 (build-system r-build-system)
8470 `(("r-biocgenerics" ,r-biocgenerics)
8471 ("r-biostrings" ,r-biostrings)
8472 ;; These two packages are suggested packages
8473 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8474 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8475 ("r-genomicranges" ,r-genomicranges)
8476 ("r-genomeinfodb" ,r-genomeinfodb)
8477 ("r-ggplot2" ,r-ggplot2)
8478 ("r-iranges" ,r-iranges)
8481 ("r-pracma" ,r-pracma)
8482 ("r-reshape2" ,r-reshape2)
8483 ("r-cowplot" ,r-cowplot)
8484 ("r-ggdendro" ,r-ggdendro)
8485 ("r-s4vectors" ,r-s4vectors)
8486 ("r-summarizedexperiment" ,r-summarizedexperiment)
8487 ("r-variantannotation" ,r-variantannotation)))
8488 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8489 (synopsis "Extract and visualize mutational patterns in genomic data")
8490 (description "This package provides an extensive toolset for the
8491 characterization and visualization of a wide range of mutational patterns
8492 in SNV base substitution data.")
8493 (license license:expat)))
8495 (define-public r-chipkernels
8496 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8499 (name "r-chipkernels")
8500 (version (string-append "1.1-" revision "." (string-take commit 9)))
8505 (url "https://github.com/ManuSetty/ChIPKernels.git")
8507 (file-name (string-append name "-" version))
8510 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8511 (build-system r-build-system)
8513 `(("r-iranges" ,r-iranges)
8514 ("r-xvector" ,r-xvector)
8515 ("r-biostrings" ,r-biostrings)
8516 ("r-bsgenome" ,r-bsgenome)
8517 ("r-gtools" ,r-gtools)
8518 ("r-genomicranges" ,r-genomicranges)
8519 ("r-sfsmisc" ,r-sfsmisc)
8520 ("r-kernlab" ,r-kernlab)
8521 ("r-s4vectors" ,r-s4vectors)
8522 ("r-biocgenerics" ,r-biocgenerics)))
8523 (home-page "https://github.com/ManuSetty/ChIPKernels")
8524 (synopsis "Build string kernels for DNA Sequence analysis")
8525 (description "ChIPKernels is an R package for building different string
8526 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8527 must be built and this dictionary can be used for determining kernels for DNA
8529 (license license:gpl2+))))
8531 (define-public r-seqgl
8539 (url "https://github.com/ManuSetty/SeqGL.git")
8541 (file-name (git-file-name name version))
8544 "1r6ywvhxl3ffv48lgj7sbd582mcc6dha3ksgc2qjlvjrnkbj3799"))))
8545 (build-system r-build-system)
8547 `(("r-biostrings" ,r-biostrings)
8548 ("r-chipkernels" ,r-chipkernels)
8549 ("r-genomicranges" ,r-genomicranges)
8550 ("r-spams" ,r-spams)
8551 ("r-wgcna" ,r-wgcna)
8552 ("r-fastcluster" ,r-fastcluster)))
8553 (home-page "https://github.com/ManuSetty/SeqGL")
8554 (synopsis "Group lasso for Dnase/ChIP-seq data")
8555 (description "SeqGL is a group lasso based algorithm to extract
8556 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8557 This package presents a method which uses group lasso to discriminate between
8558 bound and non bound genomic regions to accurately identify transcription
8559 factors bound at the specific regions.")
8560 (license license:gpl2+)))
8562 (define-public r-tximport
8568 (uri (bioconductor-uri "tximport" version))
8571 "070nx0blvvfhsnkbb5j899wy7dgalrh4xfcciir9l2xl67lna1zf"))))
8572 (build-system r-build-system)
8573 (home-page "https://bioconductor.org/packages/tximport")
8574 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8576 "This package provides tools to import transcript-level abundance,
8577 estimated counts and transcript lengths, and to summarize them into matrices
8578 for use with downstream gene-level analysis packages. Average transcript
8579 length, weighted by sample-specific transcript abundance estimates, is
8580 provided as a matrix which can be used as an offset for different expression
8581 of gene-level counts.")
8582 (license license:gpl2+)))
8584 (define-public r-rhdf5
8590 (uri (bioconductor-uri "rhdf5" version))
8593 "0y1w3cs7wg2b3jlkd6wyyz6626xg011nrg36si8gg371iqck9a1i"))))
8594 (build-system r-build-system)
8596 `(("r-rhdf5lib" ,r-rhdf5lib)))
8599 (home-page "https://bioconductor.org/packages/rhdf5")
8600 (synopsis "HDF5 interface to R")
8602 "This R/Bioconductor package provides an interface between HDF5 and R.
8603 HDF5's main features are the ability to store and access very large and/or
8604 complex datasets and a wide variety of metadata on mass storage (disk) through
8605 a completely portable file format. The rhdf5 package is thus suited for the
8606 exchange of large and/or complex datasets between R and other software
8607 package, and for letting R applications work on datasets that are larger than
8608 the available RAM.")
8609 (license license:artistic2.0)))
8611 (define-public r-annotationfilter
8613 (name "r-annotationfilter")
8617 (uri (bioconductor-uri "AnnotationFilter" version))
8620 "15qh4jwxxqsnb308nxzj99gckfk18rhp8g26q1xwgkr57zc5kcrx"))))
8622 `((upstream-name . "AnnotationFilter")))
8623 (build-system r-build-system)
8625 `(("r-genomicranges" ,r-genomicranges)
8626 ("r-lazyeval" ,r-lazyeval)))
8627 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8628 (synopsis "Facilities for filtering Bioconductor annotation resources")
8630 "This package provides classes and other infrastructure to implement
8631 filters for manipulating Bioconductor annotation resources. The filters are
8632 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8633 (license license:artistic2.0)))
8635 (define-public emboss
8641 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8642 (version-major+minor version) ".0/"
8643 "EMBOSS-" version ".tar.gz"))
8646 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8647 (build-system gnu-build-system)
8650 (list (string-append "--with-hpdf="
8651 (assoc-ref %build-inputs "libharu")))
8653 (modify-phases %standard-phases
8654 (add-after 'unpack 'fix-checks
8656 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8657 ;; and zlib, but assume that they are all found at the same
8659 (substitute* "configure.in"
8660 (("CHECK_PNGDRIVER")
8661 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8662 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8663 AM_CONDITIONAL(AMPNG, true)"))
8665 (add-after 'fix-checks 'disable-update-check
8667 ;; At build time there is no connection to the Internet, so
8668 ;; looking for updates will not work.
8669 (substitute* "Makefile.am"
8670 (("\\$\\(bindir\\)/embossupdate") ""))
8672 (add-after 'disable-update-check 'autogen
8673 (lambda _ (invoke "autoreconf" "-vif") #t)))))
8679 ("libharu" ,libharu)
8682 `(("autoconf" ,autoconf)
8683 ("automake" ,automake)
8684 ("libtool" ,libtool)
8685 ("pkg-config" ,pkg-config)))
8686 (home-page "http://emboss.sourceforge.net")
8687 (synopsis "Molecular biology analysis suite")
8688 (description "EMBOSS is the \"European Molecular Biology Open Software
8689 Suite\". EMBOSS is an analysis package specially developed for the needs of
8690 the molecular biology (e.g. EMBnet) user community. The software
8691 automatically copes with data in a variety of formats and even allows
8692 transparent retrieval of sequence data from the web. It also provides a
8693 number of libraries for the development of software in the field of molecular
8694 biology. EMBOSS also integrates a range of currently available packages and
8695 tools for sequence analysis into a seamless whole.")
8696 (license license:gpl2+)))
8699 (let ((revision "1")
8700 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8703 ;; The version is 2.13.0 even though no release archives have been
8704 ;; published as yet.
8705 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8709 (url "https://github.com/arq5x/bits.git")
8711 (file-name (string-append name "-" version "-checkout"))
8714 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8715 (build-system gnu-build-system)
8717 `(#:tests? #f ;no tests included
8719 (modify-phases %standard-phases
8721 (add-after 'unpack 'remove-cuda
8723 (substitute* "Makefile"
8725 (("(bits_test_intersections) \\\\" _ match) match))
8728 (lambda* (#:key outputs #:allow-other-keys)
8730 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8735 (home-page "https://github.com/arq5x/bits")
8736 (synopsis "Implementation of binary interval search algorithm")
8737 (description "This package provides an implementation of the
8738 BITS (Binary Interval Search) algorithm, an approach to interval set
8739 intersection. It is especially suited for the comparison of diverse genomic
8740 datasets and the exploration of large datasets of genome
8741 intervals (e.g. genes, sequence alignments).")
8742 (license license:gpl2))))
8744 (define-public piranha
8745 ;; There is no release tarball for the latest version. The latest commit is
8746 ;; older than one year at the time of this writing.
8747 (let ((revision "1")
8748 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8751 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8755 (url "https://github.com/smithlabcode/piranha.git")
8757 (file-name (git-file-name name version))
8760 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
8761 (build-system gnu-build-system)
8763 `(#:test-target "test"
8765 (modify-phases %standard-phases
8766 (add-after 'unpack 'copy-smithlab-cpp
8767 (lambda* (#:key inputs #:allow-other-keys)
8768 (for-each (lambda (file)
8769 (install-file file "./src/smithlab_cpp/"))
8770 (find-files (assoc-ref inputs "smithlab-cpp")))
8772 (add-after 'install 'install-to-store
8773 (lambda* (#:key outputs #:allow-other-keys)
8774 (let* ((out (assoc-ref outputs "out"))
8775 (bin (string-append out "/bin")))
8776 (for-each (lambda (file)
8777 (install-file file bin))
8778 (find-files "bin" ".*")))
8781 (list (string-append "--with-bam_tools_headers="
8782 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
8783 (string-append "--with-bam_tools_library="
8784 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
8786 `(("bamtools" ,bamtools)
8787 ("samtools" ,samtools-0.1)
8790 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8794 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8796 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8799 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8801 `(("python" ,python-2)))
8802 (home-page "https://github.com/smithlabcode/piranha")
8803 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
8805 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
8806 RIP-seq experiments. It takes input in BED or BAM format and identifies
8807 regions of statistically significant read enrichment. Additional covariates
8808 may optionally be provided to further inform the peak-calling process.")
8809 (license license:gpl3+))))
8817 (uri (pypi-uri "PePr" version))
8820 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
8821 (build-system python-build-system)
8823 `(#:python ,python-2 ; python2 only
8824 #:tests? #f)) ; no tests included
8826 `(("python2-numpy" ,python2-numpy)
8827 ("python2-scipy" ,python2-scipy)
8828 ("python2-pysam" ,python2-pysam)))
8829 (home-page "https://github.com/shawnzhangyx/PePr")
8830 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
8832 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
8833 that is primarily designed for data with biological replicates. It uses a
8834 negative binomial distribution to model the read counts among the samples in
8835 the same group, and look for consistent differences between ChIP and control
8836 group or two ChIP groups run under different conditions.")
8837 (license license:gpl3+)))
8839 (define-public filevercmp
8840 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
8843 (version (string-append "0-1." (string-take commit 7)))
8847 (url "https://github.com/ekg/filevercmp.git")
8849 (file-name (git-file-name name commit))
8852 "1j9vxsy0y050v59h0q1d6501fcw1kjvj0d18l1xk2zyg0jzj247c"))))
8853 (build-system gnu-build-system)
8855 `(#:tests? #f ; There are no tests to run.
8857 (modify-phases %standard-phases
8858 (delete 'configure) ; There is no configure phase.
8860 (lambda* (#:key outputs #:allow-other-keys)
8861 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
8862 (install-file "filevercmp" bin)
8864 (home-page "https://github.com/ekg/filevercmp")
8865 (synopsis "This program compares version strings")
8866 (description "This program compares version strings. It intends to be a
8867 replacement for strverscmp.")
8868 (license license:gpl3+))))
8870 (define-public multiqc
8877 (uri (pypi-uri "multiqc" version))
8880 "02iihfl0w0hpnr4pa0sbd1y9qxrg3ycyhjp5lidkcrqh1lmzs3zy"))))
8881 (build-system python-build-system)
8883 `(("python-jinja2" ,python-jinja2)
8884 ("python-simplejson" ,python-simplejson)
8885 ("python-pyyaml" ,python-pyyaml)
8886 ("python-click" ,python-click)
8887 ("python-spectra" ,python-spectra)
8888 ("python-requests" ,python-requests)
8889 ("python-markdown" ,python-markdown)
8890 ("python-lzstring" ,python-lzstring)
8891 ("python-matplotlib" ,python-matplotlib)
8892 ("python-numpy" ,python-numpy)
8893 ;; MultQC checks for the presence of nose at runtime.
8894 ("python-nose" ,python-nose)))
8897 (modify-phases %standard-phases
8898 (add-after 'unpack 'relax-requirements
8900 (substitute* "setup.py"
8901 ;; MultiQC 1.5 ‘requires’ a version of python-matplotlib older
8902 ;; than the one in Guix, but should work fine with 2.2.2.
8903 ;; See <https://github.com/ewels/MultiQC/issues/725> and
8904 ;; <https://github.com/ewels/MultiQC/issues/732> for details.
8905 (("['\"]matplotlib.*?['\"]")
8908 (home-page "http://multiqc.info")
8909 (synopsis "Aggregate bioinformatics analysis reports")
8911 "MultiQC is a tool to aggregate bioinformatics results across many
8912 samples into a single report. It contains modules for a large number of
8913 common bioinformatics tools.")
8914 (license license:gpl3+)))
8916 (define-public r-chipseq
8923 (uri (bioconductor-uri "chipseq" version))
8926 "1835nhrxcaqpqf1kxrsk1js8bf7x33z1n3bqjvm8404091acqyma"))))
8927 (build-system r-build-system)
8929 `(("r-biocgenerics" ,r-biocgenerics)
8930 ("r-genomicranges" ,r-genomicranges)
8931 ("r-iranges" ,r-iranges)
8932 ("r-lattice" ,r-lattice)
8933 ("r-s4vectors" ,r-s4vectors)
8934 ("r-shortread" ,r-shortread)))
8935 (home-page "https://bioconductor.org/packages/chipseq")
8936 (synopsis "Package for analyzing ChIPseq data")
8938 "This package provides tools for processing short read data from ChIPseq
8940 (license license:artistic2.0)))
8942 (define-public r-copyhelper
8944 (name "r-copyhelper")
8949 (uri (string-append "https://bioconductor.org/packages/release/"
8950 "data/experiment/src/contrib/CopyhelpeR_"
8954 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
8955 (properties `((upstream-name . "CopyhelpeR")))
8956 (build-system r-build-system)
8957 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
8958 (synopsis "Helper files for CopywriteR")
8960 "This package contains the helper files that are required to run the
8961 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
8962 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
8963 mm10. In addition, it contains a blacklist filter to remove regions that
8964 display copy number variation. Files are stored as GRanges objects from the
8965 GenomicRanges Bioconductor package.")
8966 (license license:gpl2)))
8968 (define-public r-copywriter
8970 (name "r-copywriter")
8975 (uri (bioconductor-uri "CopywriteR" version))
8978 "0kv3k58wyyicq1hhq7bddh0v3b2ksz6fa47skvnp8f193csza9g6"))))
8979 (properties `((upstream-name . "CopywriteR")))
8980 (build-system r-build-system)
8982 `(("r-biocparallel" ,r-biocparallel)
8983 ("r-chipseq" ,r-chipseq)
8984 ("r-copyhelper" ,r-copyhelper)
8985 ("r-data-table" ,r-data-table)
8986 ("r-dnacopy" ,r-dnacopy)
8987 ("r-futile-logger" ,r-futile-logger)
8988 ("r-genomeinfodb" ,r-genomeinfodb)
8989 ("r-genomicalignments" ,r-genomicalignments)
8990 ("r-genomicranges" ,r-genomicranges)
8991 ("r-gtools" ,r-gtools)
8992 ("r-iranges" ,r-iranges)
8993 ("r-matrixstats" ,r-matrixstats)
8994 ("r-rsamtools" ,r-rsamtools)
8995 ("r-s4vectors" ,r-s4vectors)))
8996 (home-page "https://github.com/PeeperLab/CopywriteR")
8997 (synopsis "Copy number information from targeted sequencing")
8999 "CopywriteR extracts DNA copy number information from targeted sequencing
9000 by utilizing off-target reads. It allows for extracting uniformly distributed
9001 copy number information, can be used without reference, and can be applied to
9002 sequencing data obtained from various techniques including chromatin
9003 immunoprecipitation and target enrichment on small gene panels. Thereby,
9004 CopywriteR constitutes a widely applicable alternative to available copy
9005 number detection tools.")
9006 (license license:gpl2)))
9008 (define-public r-methylkit
9010 (name "r-methylkit")
9014 (uri (bioconductor-uri "methylKit" version))
9017 "1z687vpi5kwcqpnd6r74c5y72hcsbqlwg0bk95kksgpi81q710qj"))))
9018 (properties `((upstream-name . "methylKit")))
9019 (build-system r-build-system)
9021 `(("r-data-table" ,r-data-table)
9022 ("r-emdbook" ,r-emdbook)
9023 ("r-fastseg" ,r-fastseg)
9024 ("r-genomeinfodb" ,r-genomeinfodb)
9025 ("r-genomicranges" ,r-genomicranges)
9026 ("r-gtools" ,r-gtools)
9027 ("r-iranges" ,r-iranges)
9028 ("r-kernsmooth" ,r-kernsmooth)
9029 ("r-limma" ,r-limma)
9030 ("r-mclust" ,r-mclust)
9032 ("r-qvalue" ,r-qvalue)
9033 ("r-r-utils" ,r-r-utils)
9035 ("r-rhtslib" ,r-rhtslib)
9036 ("r-rsamtools" ,r-rsamtools)
9037 ("r-rtracklayer" ,r-rtracklayer)
9038 ("r-s4vectors" ,r-s4vectors)
9039 ("r-zlibbioc" ,r-zlibbioc)))
9042 (home-page "https://github.com/al2na/methylKit")
9044 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9046 "MethylKit is an R package for DNA methylation analysis and annotation
9047 from high-throughput bisulfite sequencing. The package is designed to deal
9048 with sequencing data from @dfn{Reduced representation bisulfite
9049 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9050 genome bisulfite sequencing. It also has functions to analyze base-pair
9051 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9053 (license license:artistic2.0)))
9055 (define-public r-sva
9062 (uri (bioconductor-uri "sva" version))
9065 "0jj6klfha5v5qmx2sjblf1an6s2zqd7mmgsp7sfmh4k2jpqi3jm9"))))
9066 (build-system r-build-system)
9068 `(("r-genefilter" ,r-genefilter)
9070 ("r-biocparallel" ,r-biocparallel)
9071 ("r-matrixstats" ,r-matrixstats)
9072 ("r-limma" ,r-limma)))
9073 (home-page "https://bioconductor.org/packages/sva")
9074 (synopsis "Surrogate variable analysis")
9076 "This package contains functions for removing batch effects and other
9077 unwanted variation in high-throughput experiment. It also contains functions
9078 for identifying and building surrogate variables for high-dimensional data
9079 sets. Surrogate variables are covariates constructed directly from
9080 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9081 imaging data that can be used in subsequent analyses to adjust for unknown,
9082 unmodeled, or latent sources of noise.")
9083 (license license:artistic2.0)))
9085 (define-public r-seqminer
9092 (uri (cran-uri "seqminer" version))
9095 "1jydcpkw4rwfp983j83kipvsvr10as9pb49zzn3c2v09k1gh3ymy"))))
9096 (build-system r-build-system)
9099 (home-page "http://seqminer.genomic.codes")
9100 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9102 "This package provides tools to integrate nucleotide sequencing
9103 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9104 ;; Any version of the GPL is acceptable
9105 (license (list license:gpl2+ license:gpl3+))))
9107 (define-public r-raremetals2
9109 (name "r-raremetals2")
9114 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9115 "b/b7/RareMETALS2_" version ".tar.gz"))
9118 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9119 (properties `((upstream-name . "RareMETALS2")))
9120 (build-system r-build-system)
9122 `(("r-seqminer" ,r-seqminer)
9123 ("r-mvtnorm" ,r-mvtnorm)
9125 ("r-compquadform" ,r-compquadform)
9126 ("r-getopt" ,r-getopt)))
9127 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9128 (synopsis "Analyze gene-level association tests for binary trait")
9130 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9131 It was designed to meta-analyze gene-level association tests for binary trait.
9132 While rareMETALS offers a near-complete solution for meta-analysis of
9133 gene-level tests for quantitative trait, it does not offer the optimal
9134 solution for binary trait. The package rareMETALS2 offers improved features
9135 for analyzing gene-level association tests in meta-analyses for binary
9137 (license license:gpl3)))
9139 (define-public r-maldiquant
9141 (name "r-maldiquant")
9146 (uri (cran-uri "MALDIquant" version))
9149 "0b7kdz3x4sdq413h1q09l1qhcvdnnwv6fqsqwllks1cd3xy34c57"))))
9150 (properties `((upstream-name . "MALDIquant")))
9151 (build-system r-build-system)
9152 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9153 (synopsis "Quantitative analysis of mass spectrometry data")
9155 "This package provides a complete analysis pipeline for matrix-assisted
9156 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9157 two-dimensional mass spectrometry data. In addition to commonly used plotting
9158 and processing methods it includes distinctive features, namely baseline
9159 subtraction methods such as morphological filters (TopHat) or the
9160 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9161 alignment using warping functions, handling of replicated measurements as well
9162 as allowing spectra with different resolutions.")
9163 (license license:gpl3+)))
9165 (define-public r-protgenerics
9167 (name "r-protgenerics")
9172 (uri (bioconductor-uri "ProtGenerics" version))
9175 "12jjwmg58b4xbivxlw4pffq0qfi2c1c5hyrci0sfyphrc99fvx0i"))))
9176 (properties `((upstream-name . "ProtGenerics")))
9177 (build-system r-build-system)
9178 (home-page "https://github.com/lgatto/ProtGenerics")
9179 (synopsis "S4 generic functions for proteomics infrastructure")
9181 "This package provides S4 generic functions needed by Bioconductor
9182 proteomics packages.")
9183 (license license:artistic2.0)))
9185 (define-public r-mzr
9192 (uri (bioconductor-uri "mzR" version))
9195 "0g5r6yk4gyz0xdwlmrcij4zv7apdgsgygr043095l33hard6nsl5"))
9196 (modules '((guix build utils)))
9199 (delete-file-recursively "src/boost")
9201 (properties `((upstream-name . "mzR")))
9202 (build-system r-build-system)
9205 (modify-phases %standard-phases
9206 (add-after 'unpack 'use-system-boost
9208 (substitute* "src/Makevars"
9209 (("\\./boost/libs.*") "")
9210 (("ARCH_OBJS=" line)
9212 "\nARCH_LIBS=-lboost_system -lboost_regex \
9213 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9216 `(;; XXX Boost 1.69 will not work here.
9217 ("boost" ,boost-for-mysql) ; use this instead of the bundled boost sources
9220 `(("r-biobase" ,r-biobase)
9221 ("r-biocgenerics" ,r-biocgenerics)
9222 ("r-ncdf4" ,r-ncdf4)
9223 ("r-protgenerics" ,r-protgenerics)
9225 ("r-rhdf5lib" ,r-rhdf5lib)
9226 ("r-zlibbioc" ,r-zlibbioc)))
9227 (home-page "https://github.com/sneumann/mzR/")
9228 (synopsis "Parser for mass spectrometry data files")
9230 "The mzR package provides a unified API to the common file formats and
9231 parsers available for mass spectrometry data. It comes with a wrapper for the
9232 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9233 The package contains the original code written by the ISB, and a subset of the
9234 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9235 previously been used in XCMS.")
9236 (license license:artistic2.0)))
9238 (define-public r-affyio
9245 (uri (bioconductor-uri "affyio" version))
9248 "1s78hm51fgac3i2j4bbdy0z6g14370154s6km8lldc9zpahx8b6p"))))
9249 (build-system r-build-system)
9251 `(("r-zlibbioc" ,r-zlibbioc)))
9254 (home-page "https://github.com/bmbolstad/affyio")
9255 (synopsis "Tools for parsing Affymetrix data files")
9257 "This package provides routines for parsing Affymetrix data files based
9258 upon file format information. The primary focus is on accessing the CEL and
9260 (license license:lgpl2.0+)))
9262 (define-public r-affy
9269 (uri (bioconductor-uri "affy" version))
9272 "05vz0vf3472s1ivfhc0gc8yz98y4rvvp7cf6kfbxhy1b23im1bgk"))))
9273 (build-system r-build-system)
9275 `(("r-affyio" ,r-affyio)
9276 ("r-biobase" ,r-biobase)
9277 ("r-biocgenerics" ,r-biocgenerics)
9278 ("r-biocmanager" ,r-biocmanager)
9279 ("r-preprocesscore" ,r-preprocesscore)
9280 ("r-zlibbioc" ,r-zlibbioc)))
9283 (home-page "https://bioconductor.org/packages/affy")
9284 (synopsis "Methods for affymetrix oligonucleotide arrays")
9286 "This package contains functions for exploratory oligonucleotide array
9288 (license license:lgpl2.0+)))
9290 (define-public r-vsn
9297 (uri (bioconductor-uri "vsn" version))
9300 "1vqmyxg06kgq9m3w6n0jykqm4jgsjw879r4s216wlcq4xc94dh1r"))))
9301 (build-system r-build-system)
9303 `(("r-affy" ,r-affy)
9304 ("r-biobase" ,r-biobase)
9305 ("r-ggplot2" ,r-ggplot2)
9306 ("r-lattice" ,r-lattice)
9307 ("r-limma" ,r-limma)))
9308 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9309 (synopsis "Variance stabilization and calibration for microarray data")
9311 "The package implements a method for normalising microarray intensities,
9312 and works for single- and multiple-color arrays. It can also be used for data
9313 from other technologies, as long as they have similar format. The method uses
9314 a robust variant of the maximum-likelihood estimator for an
9315 additive-multiplicative error model and affine calibration. The model
9316 incorporates data calibration step (a.k.a. normalization), a model for the
9317 dependence of the variance on the mean intensity and a variance stabilizing
9318 data transformation. Differences between transformed intensities are
9319 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9320 their variance is independent of the mean, and they are usually more sensitive
9321 and specific in detecting differential transcription.")
9322 (license license:artistic2.0)))
9324 (define-public r-mzid
9331 (uri (bioconductor-uri "mzID" version))
9334 "0vnyg7jlmy7ain7gmjwhqyqr664znrvrdlh7zd63563vhb87qarn"))))
9335 (properties `((upstream-name . "mzID")))
9336 (build-system r-build-system)
9338 `(("r-doparallel" ,r-doparallel)
9339 ("r-foreach" ,r-foreach)
9340 ("r-iterators" ,r-iterators)
9342 ("r-protgenerics" ,r-protgenerics)
9345 (home-page "https://bioconductor.org/packages/mzID")
9346 (synopsis "Parser for mzIdentML files")
9348 "This package provides a parser for mzIdentML files implemented using the
9349 XML package. The parser tries to be general and able to handle all types of
9350 mzIdentML files with the drawback of having less pretty output than a vendor
9352 (license license:gpl2+)))
9354 (define-public r-pcamethods
9356 (name "r-pcamethods")
9361 (uri (bioconductor-uri "pcaMethods" version))
9364 "0svf4n7l0afy4wwgs6x8x4dm330r3311l5vmsxw2f0r4axkh3bzk"))))
9365 (properties `((upstream-name . "pcaMethods")))
9366 (build-system r-build-system)
9368 `(("r-biobase" ,r-biobase)
9369 ("r-biocgenerics" ,r-biocgenerics)
9371 ("r-rcpp" ,r-rcpp)))
9372 (home-page "https://github.com/hredestig/pcamethods")
9373 (synopsis "Collection of PCA methods")
9375 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9376 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9377 for missing value estimation is included for comparison. BPCA, PPCA and
9378 NipalsPCA may be used to perform PCA on incomplete data as well as for
9379 accurate missing value estimation. A set of methods for printing and plotting
9380 the results is also provided. All PCA methods make use of the same data
9381 structure (pcaRes) to provide a common interface to the PCA results.")
9382 (license license:gpl3+)))
9384 (define-public r-msnbase
9391 (uri (bioconductor-uri "MSnbase" version))
9394 "0z63yqazkycq0zbbarq9ida6al35hv3g7g9g7s7bss4gh0hk7lhd"))))
9395 (properties `((upstream-name . "MSnbase")))
9396 (build-system r-build-system)
9398 `(("r-affy" ,r-affy)
9399 ("r-biobase" ,r-biobase)
9400 ("r-biocgenerics" ,r-biocgenerics)
9401 ("r-biocparallel" ,r-biocparallel)
9402 ("r-digest" ,r-digest)
9403 ("r-ggplot2" ,r-ggplot2)
9404 ("r-impute" ,r-impute)
9405 ("r-iranges" ,r-iranges)
9406 ("r-lattice" ,r-lattice)
9407 ("r-maldiquant" ,r-maldiquant)
9411 ("r-pcamethods" ,r-pcamethods)
9413 ("r-preprocesscore" ,r-preprocesscore)
9414 ("r-protgenerics" ,r-protgenerics)
9416 ("r-s4vectors" ,r-s4vectors)
9417 ("r-scales" ,r-scales)
9420 (home-page "https://github.com/lgatto/MSnbase")
9421 (synopsis "Base functions and classes for MS-based proteomics")
9423 "This package provides basic plotting, data manipulation and processing
9424 of mass spectrometry based proteomics data.")
9425 (license license:artistic2.0)))
9427 (define-public r-msnid
9434 (uri (bioconductor-uri "MSnID" version))
9437 "18mp8zacawhfapfwpq8czbswxix2ykvqhwjga54v0a99zg3k87h3"))))
9438 (properties `((upstream-name . "MSnID")))
9439 (build-system r-build-system)
9441 `(("r-biobase" ,r-biobase)
9442 ("r-data-table" ,r-data-table)
9443 ("r-doparallel" ,r-doparallel)
9444 ("r-dplyr" ,r-dplyr)
9445 ("r-foreach" ,r-foreach)
9446 ("r-iterators" ,r-iterators)
9447 ("r-msnbase" ,r-msnbase)
9450 ("r-protgenerics" ,r-protgenerics)
9451 ("r-r-cache" ,r-r-cache)
9453 ("r-reshape2" ,r-reshape2)))
9454 (home-page "https://bioconductor.org/packages/MSnID")
9455 (synopsis "Utilities for LC-MSn proteomics identifications")
9457 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9458 from mzIdentML (leveraging the mzID package) or text files. After collating
9459 the search results from multiple datasets it assesses their identification
9460 quality and optimize filtering criteria to achieve the maximum number of
9461 identifications while not exceeding a specified false discovery rate. It also
9462 contains a number of utilities to explore the MS/MS results and assess missed
9463 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9464 (license license:artistic2.0)))
9466 (define-public r-seurat
9472 (uri (cran-uri "Seurat" version))
9475 "016fgcmjz3sjfxdvam5hd7mdxpmpnc7f6p5zqlh97m21dgn5vpqn"))))
9476 (properties `((upstream-name . "Seurat")))
9477 (build-system r-build-system)
9480 ("r-cluster" ,r-cluster)
9481 ("r-cowplot" ,r-cowplot)
9482 ("r-fitdistrplus" ,r-fitdistrplus)
9483 ("r-future" ,r-future)
9484 ("r-future-apply" ,r-future-apply)
9485 ("r-ggplot2" ,r-ggplot2)
9486 ("r-ggrepel" ,r-ggrepel)
9487 ("r-ggridges" ,r-ggridges)
9489 ("r-igraph" ,r-igraph)
9490 ("r-irlba" ,r-irlba)
9491 ("r-kernsmooth" ,r-kernsmooth)
9492 ("r-lmtest" ,r-lmtest)
9494 ("r-matrix" ,r-matrix)
9495 ("r-metap" ,r-metap)
9496 ("r-pbapply" ,r-pbapply)
9497 ("r-plotly" ,r-plotly)
9500 ("r-rcolorbrewer" ,r-rcolorbrewer)
9502 ("r-rcppeigen" ,r-rcppeigen)
9503 ("r-rcppprogress" ,r-rcppprogress)
9504 ("r-reticulate" ,r-reticulate)
9505 ("r-rlang" ,r-rlang)
9508 ("r-rtsne" ,r-rtsne)
9509 ("r-scales" ,r-scales)
9510 ("r-sctransform" ,r-sctransform)
9511 ("r-sdmtools" ,r-sdmtools)
9512 ("r-tsne" ,r-tsne)))
9513 (home-page "http://www.satijalab.org/seurat")
9514 (synopsis "Seurat is an R toolkit for single cell genomics")
9516 "This package is an R package designed for QC, analysis, and
9517 exploration of single cell RNA-seq data. It easily enables widely-used
9518 analytical techniques, including the identification of highly variable genes,
9519 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9520 algorithms; density clustering, hierarchical clustering, k-means, and the
9521 discovery of differentially expressed genes and markers.")
9522 (license license:gpl3)))
9524 (define-public r-aroma-light
9526 (name "r-aroma-light")
9531 (uri (bioconductor-uri "aroma.light" version))
9534 "0a1prl4jhbqpa85i2vyia1ks9iippzl8np50fvm9wx8kbjxna5l6"))))
9535 (properties `((upstream-name . "aroma.light")))
9536 (build-system r-build-system)
9538 `(("r-matrixstats" ,r-matrixstats)
9539 ("r-r-methodss3" ,r-r-methodss3)
9541 ("r-r-utils" ,r-r-utils)))
9542 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9543 (synopsis "Methods for normalization and visualization of microarray data")
9545 "This package provides methods for microarray analysis that take basic
9546 data types such as matrices and lists of vectors. These methods can be used
9547 standalone, be utilized in other packages, or be wrapped up in higher-level
9549 (license license:gpl2+)))
9551 (define-public r-deseq
9558 (uri (bioconductor-uri "DESeq" version))
9561 "0jppqrikg9qfqcfw5qd3m5c7bag9g23bc0kcpk5zfkk1wv09mnlm"))))
9562 (properties `((upstream-name . "DESeq")))
9563 (build-system r-build-system)
9565 `(("r-biobase" ,r-biobase)
9566 ("r-biocgenerics" ,r-biocgenerics)
9567 ("r-genefilter" ,r-genefilter)
9568 ("r-geneplotter" ,r-geneplotter)
9569 ("r-lattice" ,r-lattice)
9570 ("r-locfit" ,r-locfit)
9572 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9573 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9574 (synopsis "Differential gene expression analysis")
9576 "This package provides tools for estimating variance-mean dependence in
9577 count data from high-throughput genetic sequencing assays and for testing for
9578 differential expression based on a model using the negative binomial
9580 (license license:gpl3+)))
9582 (define-public r-edaseq
9589 (uri (bioconductor-uri "EDASeq" version))
9592 "0mmc9bij17w4mfwcc566zbj5fvqgl8gfqs0qvj6ri4mbcql9jxb3"))))
9593 (properties `((upstream-name . "EDASeq")))
9594 (build-system r-build-system)
9596 `(("r-annotationdbi" ,r-annotationdbi)
9597 ("r-aroma-light" ,r-aroma-light)
9598 ("r-biobase" ,r-biobase)
9599 ("r-biocgenerics" ,r-biocgenerics)
9600 ("r-biocmanager" ,r-biocmanager)
9601 ("r-biomart" ,r-biomart)
9602 ("r-biostrings" ,r-biostrings)
9603 ("r-deseq" ,r-deseq)
9604 ("r-genomicfeatures" ,r-genomicfeatures)
9605 ("r-genomicranges" ,r-genomicranges)
9606 ("r-iranges" ,r-iranges)
9607 ("r-rsamtools" ,r-rsamtools)
9608 ("r-shortread" ,r-shortread)))
9609 (home-page "https://github.com/drisso/EDASeq")
9610 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9612 "This package provides support for numerical and graphical summaries of
9613 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9614 adjust for GC-content effect (or other gene-level effects) on read counts:
9615 loess robust local regression, global-scaling, and full-quantile
9616 normalization. Between-lane normalization procedures to adjust for
9617 distributional differences between lanes (e.g., sequencing depth):
9618 global-scaling and full-quantile normalization.")
9619 (license license:artistic2.0)))
9621 (define-public r-interactivedisplaybase
9623 (name "r-interactivedisplaybase")
9628 (uri (bioconductor-uri "interactiveDisplayBase" version))
9631 "1kkyv7hkygacmksvld9gs3ycf6wlblqcwi11nny0hq3l0ha265v5"))))
9633 `((upstream-name . "interactiveDisplayBase")))
9634 (build-system r-build-system)
9636 `(("r-biocgenerics" ,r-biocgenerics)
9637 ("r-shiny" ,r-shiny)))
9638 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9639 (synopsis "Base package for web displays of Bioconductor objects")
9641 "This package contains the basic methods needed to generate interactive
9642 Shiny-based display methods for Bioconductor objects.")
9643 (license license:artistic2.0)))
9645 (define-public r-annotationhub
9647 (name "r-annotationhub")
9652 (uri (bioconductor-uri "AnnotationHub" version))
9655 "1rpzl4x5mrwxrrf1jzm4zni6li6x34fjfyybsdvplb0ixa48zhn4"))))
9656 (properties `((upstream-name . "AnnotationHub")))
9657 (build-system r-build-system)
9659 `(("r-annotationdbi" ,r-annotationdbi)
9660 ("r-biocfilecache" ,r-biocfilecache)
9661 ("r-biocgenerics" ,r-biocgenerics)
9662 ("r-biocmanager" ,r-biocmanager)
9664 ("r-dplyr" ,r-dplyr)
9666 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9667 ("r-rappdirs" ,r-rappdirs)
9668 ("r-rsqlite" ,r-rsqlite)
9669 ("r-s4vectors" ,r-s4vectors)
9670 ("r-yaml" ,r-yaml)))
9671 (home-page "https://bioconductor.org/packages/AnnotationHub")
9672 (synopsis "Client to access AnnotationHub resources")
9674 "This package provides a client for the Bioconductor AnnotationHub web
9675 resource. The AnnotationHub web resource provides a central location where
9676 genomic files (e.g. VCF, bed, wig) and other resources from standard
9677 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9678 metadata about each resource, e.g., a textual description, tags, and date of
9679 modification. The client creates and manages a local cache of files retrieved
9680 by the user, helping with quick and reproducible access.")
9681 (license license:artistic2.0)))
9683 (define-public r-fastseg
9690 (uri (bioconductor-uri "fastseg" version))
9693 "03gggz29nf8kyy9clkifqr0xm8v0yb0kl0gjfb5c0vrjmwkfqvdf"))))
9694 (build-system r-build-system)
9696 `(("r-biobase" ,r-biobase)
9697 ("r-biocgenerics" ,r-biocgenerics)
9698 ("r-genomicranges" ,r-genomicranges)
9699 ("r-iranges" ,r-iranges)
9700 ("r-s4vectors" ,r-s4vectors)))
9701 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
9702 (synopsis "Fast segmentation algorithm for genetic sequencing data")
9704 "Fastseg implements a very fast and efficient segmentation algorithm.
9705 It can segment data from DNA microarrays and data from next generation
9706 sequencing for example to detect copy number segments. Further it can segment
9707 data from RNA microarrays like tiling arrays to identify transcripts. Most
9708 generally, it can segment data given as a matrix or as a vector. Various data
9709 formats can be used as input to fastseg like expression set objects for
9710 microarrays or GRanges for sequencing data.")
9711 (license license:lgpl2.0+)))
9713 (define-public r-keggrest
9720 (uri (bioconductor-uri "KEGGREST" version))
9723 "1yjrpbm5zfg0h3nb5gg06q2f19ydbhjqwi0jb6q3p8dyrgww9mqp"))))
9724 (properties `((upstream-name . "KEGGREST")))
9725 (build-system r-build-system)
9727 `(("r-biostrings" ,r-biostrings)
9730 (home-page "https://bioconductor.org/packages/KEGGREST")
9731 (synopsis "Client-side REST access to KEGG")
9733 "This package provides a package that provides a client interface to the
9734 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
9735 (license license:artistic2.0)))
9737 (define-public r-gage
9744 (uri (bioconductor-uri "gage" version))
9747 "08d5yg7n4rx4xsginc8bx0sycpj06pi1k7i44ff757444p20srwq"))))
9748 (build-system r-build-system)
9750 `(("r-annotationdbi" ,r-annotationdbi)
9751 ("r-graph" ,r-graph)
9752 ("r-keggrest" ,r-keggrest)))
9753 (home-page "http://www.biomedcentral.com/1471-2105/10/161")
9754 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
9756 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
9757 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
9758 data attributes including sample sizes, experimental designs, assay platforms,
9759 and other types of heterogeneity. The gage package provides functions for
9760 basic GAGE analysis, result processing and presentation. In addition, it
9761 provides demo microarray data and commonly used gene set data based on KEGG
9762 pathways and GO terms. These functions and data are also useful for gene set
9763 analysis using other methods.")
9764 (license license:gpl2+)))
9766 (define-public r-genomicfiles
9768 (name "r-genomicfiles")
9773 (uri (bioconductor-uri "GenomicFiles" version))
9776 "122g0yhpsm6fyvv38agp57clagl13h324rk06mlgb2xz104a1j4i"))))
9777 (properties `((upstream-name . "GenomicFiles")))
9778 (build-system r-build-system)
9780 `(("r-biocgenerics" ,r-biocgenerics)
9781 ("r-biocparallel" ,r-biocparallel)
9782 ("r-genomeinfodb" ,r-genomeinfodb)
9783 ("r-genomicalignments" ,r-genomicalignments)
9784 ("r-genomicranges" ,r-genomicranges)
9785 ("r-iranges" ,r-iranges)
9786 ("r-rsamtools" ,r-rsamtools)
9787 ("r-rtracklayer" ,r-rtracklayer)
9788 ("r-s4vectors" ,r-s4vectors)
9789 ("r-summarizedexperiment" ,r-summarizedexperiment)
9790 ("r-variantannotation" ,r-variantannotation)))
9791 (home-page "https://bioconductor.org/packages/GenomicFiles")
9792 (synopsis "Distributed computing by file or by range")
9794 "This package provides infrastructure for parallel computations
9795 distributed by file or by range. User defined mapper and reducer functions
9796 provide added flexibility for data combination and manipulation.")
9797 (license license:artistic2.0)))
9799 (define-public r-complexheatmap
9801 (name "r-complexheatmap")
9806 (uri (bioconductor-uri "ComplexHeatmap" version))
9809 "1imnb72r10csl2h12sckic7hcsb8v2z0y3dyw1ax2fpykmsmq776"))))
9811 `((upstream-name . "ComplexHeatmap")))
9812 (build-system r-build-system)
9814 `(("r-circlize" ,r-circlize)
9816 ("r-colorspace" ,r-colorspace)
9817 ("r-getoptlong" ,r-getoptlong)
9818 ("r-globaloptions" ,r-globaloptions)
9820 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9822 "https://github.com/jokergoo/ComplexHeatmap")
9823 (synopsis "Making Complex Heatmaps")
9825 "Complex heatmaps are efficient to visualize associations between
9826 different sources of data sets and reveal potential structures. This package
9827 provides a highly flexible way to arrange multiple heatmaps and supports
9828 self-defined annotation graphics.")
9829 (license license:gpl2+)))
9831 (define-public r-dirichletmultinomial
9833 (name "r-dirichletmultinomial")
9838 (uri (bioconductor-uri "DirichletMultinomial" version))
9841 "0qirvhnbv4wd50ln4pqbk4dj6h2935ipf9p4sw1x62qqhwxidqk4"))))
9843 `((upstream-name . "DirichletMultinomial")))
9844 (build-system r-build-system)
9848 `(("r-biocgenerics" ,r-biocgenerics)
9849 ("r-iranges" ,r-iranges)
9850 ("r-s4vectors" ,r-s4vectors)))
9851 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
9852 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
9854 "Dirichlet-multinomial mixture models can be used to describe variability
9855 in microbial metagenomic data. This package is an interface to code
9856 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
9858 (license license:lgpl3)))
9860 (define-public r-ensembldb
9862 (name "r-ensembldb")
9867 (uri (bioconductor-uri "ensembldb" version))
9870 "09s5g9xm9m8mqvzk6pkp9fyhx3zyb4p8yziz49mhfji5n35nydjr"))))
9871 (build-system r-build-system)
9873 `(("r-annotationdbi" ,r-annotationdbi)
9874 ("r-annotationfilter" ,r-annotationfilter)
9875 ("r-biobase" ,r-biobase)
9876 ("r-biocgenerics" ,r-biocgenerics)
9877 ("r-biostrings" ,r-biostrings)
9880 ("r-genomeinfodb" ,r-genomeinfodb)
9881 ("r-genomicfeatures" ,r-genomicfeatures)
9882 ("r-genomicranges" ,r-genomicranges)
9883 ("r-iranges" ,r-iranges)
9884 ("r-protgenerics" ,r-protgenerics)
9885 ("r-rsamtools" ,r-rsamtools)
9886 ("r-rsqlite" ,r-rsqlite)
9887 ("r-rtracklayer" ,r-rtracklayer)
9888 ("r-s4vectors" ,r-s4vectors)))
9889 (home-page "https://github.com/jotsetung/ensembldb")
9890 (synopsis "Utilities to create and use Ensembl-based annotation databases")
9892 "The package provides functions to create and use transcript-centric
9893 annotation databases/packages. The annotation for the databases are directly
9894 fetched from Ensembl using their Perl API. The functionality and data is
9895 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
9896 but, in addition to retrieve all gene/transcript models and annotations from
9897 the database, the @code{ensembldb} package also provides a filter framework
9898 allowing to retrieve annotations for specific entries like genes encoded on a
9899 chromosome region or transcript models of lincRNA genes.")
9900 ;; No version specified
9901 (license license:lgpl3+)))
9903 (define-public r-organismdbi
9905 (name "r-organismdbi")
9910 (uri (bioconductor-uri "OrganismDbi" version))
9913 "14azk69pmwlhza0mhsxigsg127w3mgsx9hhrbdcdqmy3vzfbfaqq"))))
9914 (properties `((upstream-name . "OrganismDbi")))
9915 (build-system r-build-system)
9917 `(("r-annotationdbi" ,r-annotationdbi)
9918 ("r-biobase" ,r-biobase)
9919 ("r-biocgenerics" ,r-biocgenerics)
9920 ("r-biocmanager" ,r-biocmanager)
9922 ("r-genomicfeatures" ,r-genomicfeatures)
9923 ("r-genomicranges" ,r-genomicranges)
9924 ("r-graph" ,r-graph)
9925 ("r-iranges" ,r-iranges)
9927 ("r-s4vectors" ,r-s4vectors)))
9928 (home-page "https://bioconductor.org/packages/OrganismDbi")
9929 (synopsis "Software to enable the smooth interfacing of database packages")
9930 (description "The package enables a simple unified interface to several
9931 annotation packages each of which has its own schema by taking advantage of
9932 the fact that each of these packages implements a select methods.")
9933 (license license:artistic2.0)))
9935 (define-public r-biovizbase
9937 (name "r-biovizbase")
9942 (uri (bioconductor-uri "biovizBase" version))
9945 "1lba1801ak0a4vz6f8jffp9d525q27p0dhi2bp4f68mvdwwl2994"))))
9946 (properties `((upstream-name . "biovizBase")))
9947 (build-system r-build-system)
9949 `(("r-annotationdbi" ,r-annotationdbi)
9950 ("r-annotationfilter" ,r-annotationfilter)
9951 ("r-biocgenerics" ,r-biocgenerics)
9952 ("r-biostrings" ,r-biostrings)
9953 ("r-dichromat" ,r-dichromat)
9954 ("r-ensembldb" ,r-ensembldb)
9955 ("r-genomeinfodb" ,r-genomeinfodb)
9956 ("r-genomicalignments" ,r-genomicalignments)
9957 ("r-genomicfeatures" ,r-genomicfeatures)
9958 ("r-genomicranges" ,r-genomicranges)
9959 ("r-hmisc" ,r-hmisc)
9960 ("r-iranges" ,r-iranges)
9961 ("r-rcolorbrewer" ,r-rcolorbrewer)
9962 ("r-rlang" ,r-rlang)
9963 ("r-rsamtools" ,r-rsamtools)
9964 ("r-s4vectors" ,r-s4vectors)
9965 ("r-scales" ,r-scales)
9966 ("r-summarizedexperiment" ,r-summarizedexperiment)
9967 ("r-variantannotation" ,r-variantannotation)))
9968 (home-page "https://bioconductor.org/packages/biovizBase")
9969 (synopsis "Basic graphic utilities for visualization of genomic data")
9971 "The biovizBase package is designed to provide a set of utilities, color
9972 schemes and conventions for genomic data. It serves as the base for various
9973 high-level packages for biological data visualization. This saves development
9974 effort and encourages consistency.")
9975 (license license:artistic2.0)))
9977 (define-public r-ggbio
9984 (uri (bioconductor-uri "ggbio" version))
9987 "10s6hnffnrrsx3896adqdc5g55fzd5y6qhnp1mq0c641nw833rwd"))))
9988 (build-system r-build-system)
9991 (modify-phases %standard-phases
9992 ;; See https://github.com/tengfei/ggbio/issues/117
9993 ;; This fix will be included in the next release.
9994 (add-after 'unpack 'fix-typo
9996 (substitute* "R/GGbio-class.R"
9997 (("fechable") "fetchable"))
10000 `(("r-annotationdbi" ,r-annotationdbi)
10001 ("r-annotationfilter" ,r-annotationfilter)
10002 ("r-biobase" ,r-biobase)
10003 ("r-biocgenerics" ,r-biocgenerics)
10004 ("r-biostrings" ,r-biostrings)
10005 ("r-biovizbase" ,r-biovizbase)
10006 ("r-bsgenome" ,r-bsgenome)
10007 ("r-ensembldb" ,r-ensembldb)
10008 ("r-genomeinfodb" ,r-genomeinfodb)
10009 ("r-genomicalignments" ,r-genomicalignments)
10010 ("r-genomicfeatures" ,r-genomicfeatures)
10011 ("r-genomicranges" ,r-genomicranges)
10012 ("r-ggally" ,r-ggally)
10013 ("r-ggplot2" ,r-ggplot2)
10014 ("r-gridextra" ,r-gridextra)
10015 ("r-gtable" ,r-gtable)
10016 ("r-hmisc" ,r-hmisc)
10017 ("r-iranges" ,r-iranges)
10018 ("r-organismdbi" ,r-organismdbi)
10019 ("r-reshape2" ,r-reshape2)
10020 ("r-rlang" ,r-rlang)
10021 ("r-rsamtools" ,r-rsamtools)
10022 ("r-rtracklayer" ,r-rtracklayer)
10023 ("r-s4vectors" ,r-s4vectors)
10024 ("r-scales" ,r-scales)
10025 ("r-summarizedexperiment" ,r-summarizedexperiment)
10026 ("r-variantannotation" ,r-variantannotation)))
10027 (home-page "http://www.tengfei.name/ggbio/")
10028 (synopsis "Visualization tools for genomic data")
10030 "The ggbio package extends and specializes the grammar of graphics for
10031 biological data. The graphics are designed to answer common scientific
10032 questions, in particular those often asked of high throughput genomics data.
10033 All core Bioconductor data structures are supported, where appropriate. The
10034 package supports detailed views of particular genomic regions, as well as
10035 genome-wide overviews. Supported overviews include ideograms and grand linear
10036 views. High-level plots include sequence fragment length, edge-linked
10037 interval to data view, mismatch pileup, and several splicing summaries.")
10038 (license license:artistic2.0)))
10040 (define-public r-gprofiler
10042 (name "r-gprofiler")
10047 (uri (cran-uri "gProfileR" version))
10050 "12nwidbnqmnfy5dnqga26byslvdnkrpz2fi19qfcby6xx0wbndk7"))))
10051 (properties `((upstream-name . "gProfileR")))
10052 (build-system r-build-system)
10054 `(("r-plyr" ,r-plyr)
10055 ("r-rcurl" ,r-rcurl)))
10056 (home-page "https://cran.r-project.org/web/packages/gProfileR/")
10057 (synopsis "Interface to the g:Profiler toolkit")
10059 "This package provides tools for functional enrichment analysis,
10060 gene identifier conversion and mapping homologous genes across related
10061 organisms via the @code{g:Profiler} toolkit.")
10062 (license license:gpl2+)))
10064 (define-public r-gqtlbase
10066 (name "r-gqtlbase")
10071 (uri (bioconductor-uri "gQTLBase" version))
10074 "1n2cizb88g2ankngvhxv377gizg80y3fhlx67sgm0z4ilm6a30ql"))))
10075 (properties `((upstream-name . "gQTLBase")))
10076 (build-system r-build-system)
10078 `(("r-batchjobs" ,r-batchjobs)
10079 ("r-bbmisc" ,r-bbmisc)
10080 ("r-biocgenerics" ,r-biocgenerics)
10082 ("r-doparallel" ,r-doparallel)
10084 ("r-ffbase" ,r-ffbase)
10085 ("r-foreach" ,r-foreach)
10086 ("r-genomicfiles" ,r-genomicfiles)
10087 ("r-genomicranges" ,r-genomicranges)
10088 ("r-rtracklayer" ,r-rtracklayer)
10089 ("r-s4vectors" ,r-s4vectors)
10090 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10091 (home-page "https://bioconductor.org/packages/gQTLBase")
10092 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10094 "The purpose of this package is to simplify the storage and interrogation
10095 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10097 (license license:artistic2.0)))
10099 (define-public r-snpstats
10101 (name "r-snpstats")
10106 (uri (bioconductor-uri "snpStats" version))
10109 "0drfd24a5pkrhzmpidlh717bgh2dm68mpn6vj1vlpkilfbkifl34"))))
10110 (properties `((upstream-name . "snpStats")))
10111 (build-system r-build-system)
10112 (inputs `(("zlib" ,zlib)))
10114 `(("r-biocgenerics" ,r-biocgenerics)
10115 ("r-matrix" ,r-matrix)
10116 ("r-survival" ,r-survival)
10117 ("r-zlibbioc" ,r-zlibbioc)))
10118 (home-page "https://bioconductor.org/packages/snpStats")
10119 (synopsis "Methods for SNP association studies")
10121 "This package provides classes and statistical methods for large
10122 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10123 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10124 (license license:gpl3)))
10126 (define-public r-homo-sapiens
10128 (name "r-homo-sapiens")
10132 ;; We cannot use bioconductor-uri here because this tarball is
10133 ;; located under "data/annotation/" instead of "bioc/".
10134 (uri (string-append "http://www.bioconductor.org/packages/"
10135 "release/data/annotation/src/contrib/"
10137 version ".tar.gz"))
10140 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10142 `((upstream-name . "Homo.sapiens")))
10143 (build-system r-build-system)
10145 `(("r-genomicfeatures" ,r-genomicfeatures)
10146 ("r-go-db" ,r-go-db)
10147 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10148 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10149 ("r-organismdbi" ,r-organismdbi)
10150 ("r-annotationdbi" ,r-annotationdbi)))
10151 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10152 (synopsis "Annotation package for the Homo.sapiens object")
10154 "This package contains the Homo.sapiens object to access data from
10155 several related annotation packages.")
10156 (license license:artistic2.0)))
10158 (define-public r-erma
10165 (uri (bioconductor-uri "erma" version))
10168 "0j7ggp63m5y88cxgi49vcql1s1avzifwvvd2hydj4lj3yrmzib48"))))
10169 (build-system r-build-system)
10171 `(("r-annotationdbi" ,r-annotationdbi)
10172 ("r-biobase" ,r-biobase)
10173 ("r-biocgenerics" ,r-biocgenerics)
10174 ("r-biocparallel" ,r-biocparallel)
10175 ("r-genomeinfodb" ,r-genomeinfodb)
10176 ("r-genomicfiles" ,r-genomicfiles)
10177 ("r-genomicranges" ,r-genomicranges)
10178 ("r-ggplot2" ,r-ggplot2)
10179 ("r-homo-sapiens" ,r-homo-sapiens)
10180 ("r-iranges" ,r-iranges)
10181 ("r-rtracklayer" ,r-rtracklayer)
10182 ("r-s4vectors" ,r-s4vectors)
10183 ("r-shiny" ,r-shiny)
10184 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10185 (home-page "https://bioconductor.org/packages/erma")
10186 (synopsis "Epigenomic road map adventures")
10188 "The epigenomics road map describes locations of epigenetic marks in DNA
10189 from a variety of cell types. Of interest are locations of histone
10190 modifications, sites of DNA methylation, and regions of accessible chromatin.
10191 This package presents a selection of elements of the road map including
10192 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10193 by Ernst and Kellis.")
10194 (license license:artistic2.0)))
10196 (define-public r-ldblock
10203 (uri (bioconductor-uri "ldblock" version))
10206 "0lraxhq9ny3468534klrl64nx0dpaf9cbd5bir6m5qma8j7kfnyd"))))
10207 (build-system r-build-system)
10209 `(("r-biocgenerics" ,r-biocgenerics)
10211 ("r-genomeinfodb" ,r-genomeinfodb)
10212 ("r-genomicfiles" ,r-genomicfiles)
10213 ("r-go-db" ,r-go-db)
10214 ("r-homo-sapiens" ,r-homo-sapiens)
10215 ("r-matrix" ,r-matrix)
10216 ("r-rsamtools" ,r-rsamtools)
10217 ("r-snpstats" ,r-snpstats)
10218 ("r-variantannotation" ,r-variantannotation)))
10219 (home-page "https://bioconductor.org/packages/ldblock")
10220 (synopsis "Data structures for linkage disequilibrium measures in populations")
10222 "This package defines data structures for @dfn{linkage
10223 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10224 handling of existing population-level data for the purpose of flexibly
10225 defining LD blocks.")
10226 (license license:artistic2.0)))
10228 (define-public r-gqtlstats
10230 (name "r-gqtlstats")
10235 (uri (bioconductor-uri "gQTLstats" version))
10238 "17xadfn8qh1pwzlpcbds5wrjr9bzhsnmv90wffxmp02hq20qkrh5"))))
10239 (properties `((upstream-name . "gQTLstats")))
10240 (build-system r-build-system)
10242 `(("r-annotationdbi" ,r-annotationdbi)
10243 ("r-batchjobs" ,r-batchjobs)
10244 ("r-bbmisc" ,r-bbmisc)
10245 ("r-beeswarm" ,r-beeswarm)
10246 ("r-biobase" ,r-biobase)
10247 ("r-biocgenerics" ,r-biocgenerics)
10248 ("r-doparallel" ,r-doparallel)
10249 ("r-dplyr" ,r-dplyr)
10251 ("r-ffbase" ,r-ffbase)
10252 ("r-foreach" ,r-foreach)
10253 ("r-genomeinfodb" ,r-genomeinfodb)
10254 ("r-genomicfeatures" ,r-genomicfeatures)
10255 ("r-genomicfiles" ,r-genomicfiles)
10256 ("r-genomicranges" ,r-genomicranges)
10257 ("r-ggbeeswarm" ,r-ggbeeswarm)
10258 ("r-ggplot2" ,r-ggplot2)
10259 ("r-gqtlbase" ,r-gqtlbase)
10260 ("r-hardyweinberg" ,r-hardyweinberg)
10261 ("r-homo-sapiens" ,r-homo-sapiens)
10262 ("r-iranges" ,r-iranges)
10263 ("r-limma" ,r-limma)
10265 ("r-plotly" ,r-plotly)
10266 ("r-reshape2" ,r-reshape2)
10267 ("r-s4vectors" ,r-s4vectors)
10268 ("r-shiny" ,r-shiny)
10269 ("r-snpstats" ,r-snpstats)
10270 ("r-summarizedexperiment" ,r-summarizedexperiment)
10271 ("r-variantannotation" ,r-variantannotation)))
10272 (home-page "https://bioconductor.org/packages/gQTLstats")
10273 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10275 "This package provides tools for the computationally efficient analysis
10276 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10277 The software in this package aims to support refinements and functional
10278 interpretation of members of a collection of association statistics on a
10279 family of feature/genome hypotheses.")
10280 (license license:artistic2.0)))
10282 (define-public r-gviz
10289 (uri (bioconductor-uri "Gviz" version))
10292 "02alz27w8fnnm2ga71g3jg2b94f95ccv6r1fyszj4yb1k2g7rkxk"))))
10293 (properties `((upstream-name . "Gviz")))
10294 (build-system r-build-system)
10296 `(("r-annotationdbi" ,r-annotationdbi)
10297 ("r-biobase" ,r-biobase)
10298 ("r-biocgenerics" ,r-biocgenerics)
10299 ("r-biomart" ,r-biomart)
10300 ("r-biostrings" ,r-biostrings)
10301 ("r-biovizbase" ,r-biovizbase)
10302 ("r-bsgenome" ,r-bsgenome)
10303 ("r-digest" ,r-digest)
10304 ("r-genomeinfodb" ,r-genomeinfodb)
10305 ("r-genomicalignments" ,r-genomicalignments)
10306 ("r-genomicfeatures" ,r-genomicfeatures)
10307 ("r-genomicranges" ,r-genomicranges)
10308 ("r-iranges" ,r-iranges)
10309 ("r-lattice" ,r-lattice)
10310 ("r-latticeextra" ,r-latticeextra)
10311 ("r-matrixstats" ,r-matrixstats)
10312 ("r-rcolorbrewer" ,r-rcolorbrewer)
10313 ("r-rsamtools" ,r-rsamtools)
10314 ("r-rtracklayer" ,r-rtracklayer)
10315 ("r-s4vectors" ,r-s4vectors)
10316 ("r-xvector" ,r-xvector)))
10317 (home-page "https://bioconductor.org/packages/Gviz")
10318 (synopsis "Plotting data and annotation information along genomic coordinates")
10320 "Genomic data analyses requires integrated visualization of known genomic
10321 information and new experimental data. Gviz uses the biomaRt and the
10322 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10323 and translates this to e.g. gene/transcript structures in viewports of the
10324 grid graphics package. This results in genomic information plotted together
10326 (license license:artistic2.0)))
10328 (define-public r-gwascat
10335 (uri (bioconductor-uri "gwascat" version))
10338 "0akb36mrybmxbb1bc9kgxbnj3cdypfylj3yzrmhjwqxml03mg61i"))))
10339 (build-system r-build-system)
10341 `(("r-annotationdbi" ,r-annotationdbi)
10342 ("r-biocgenerics" ,r-biocgenerics)
10343 ("r-biostrings" ,r-biostrings)
10344 ("r-genomeinfodb" ,r-genomeinfodb)
10345 ("r-genomicfeatures" ,r-genomicfeatures)
10346 ("r-genomicranges" ,r-genomicranges)
10347 ("r-homo-sapiens" ,r-homo-sapiens)
10348 ("r-iranges" ,r-iranges)
10349 ("r-rsamtools" ,r-rsamtools)
10350 ("r-rtracklayer" ,r-rtracklayer)
10351 ("r-s4vectors" ,r-s4vectors)))
10352 (home-page "https://bioconductor.org/packages/gwascat")
10353 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10355 "This package provides tools for representing and modeling data in the
10356 EMBL-EBI GWAS catalog.")
10357 (license license:artistic2.0)))
10359 (define-public r-sushi
10365 (uri (bioconductor-uri "Sushi" version))
10368 "1hgh3jfcx0bh3fyvp85v7435hvsk3ah1hxx5117ss93v03iwjf1g"))))
10369 (properties `((upstream-name . "Sushi")))
10370 (build-system r-build-system)
10372 `(("r-biomart" ,r-biomart)
10374 (home-page "https://bioconductor.org/packages/Sushi")
10375 (synopsis "Tools for visualizing genomics data")
10377 "This package provides flexible, quantitative, and integrative genomic
10378 visualizations for publication-quality multi-panel figures.")
10379 (license license:gpl2+)))
10381 (define-public r-fithic
10387 (uri (bioconductor-uri "FitHiC" version))
10390 "1qrxy4v8vmykrk8y6g3bs5wh5xhbs6pxyydbxy3vnj2mjirnxr6d"))))
10391 (properties `((upstream-name . "FitHiC")))
10392 (build-system r-build-system)
10394 `(("r-data-table" ,r-data-table)
10395 ("r-fdrtool" ,r-fdrtool)
10396 ("r-rcpp" ,r-rcpp)))
10397 (home-page "https://bioconductor.org/packages/FitHiC")
10398 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10400 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10401 intra-chromosomal contact maps produced by genome-wide genome architecture
10402 assays such as Hi-C.")
10403 (license license:gpl2+)))
10405 (define-public r-hitc
10411 (uri (bioconductor-uri "HiTC" version))
10414 "059a1xxv2kb0bb32flymg2s8ylhavnv3j8l4125rfidagcgxgzjq"))))
10415 (properties `((upstream-name . "HiTC")))
10416 (build-system r-build-system)
10418 `(("r-biostrings" ,r-biostrings)
10419 ("r-genomeinfodb" ,r-genomeinfodb)
10420 ("r-genomicranges" ,r-genomicranges)
10421 ("r-iranges" ,r-iranges)
10422 ("r-matrix" ,r-matrix)
10423 ("r-rcolorbrewer" ,r-rcolorbrewer)
10424 ("r-rtracklayer" ,r-rtracklayer)))
10425 (home-page "https://bioconductor.org/packages/HiTC")
10426 (synopsis "High throughput chromosome conformation capture analysis")
10428 "The HiTC package was developed to explore high-throughput \"C\" data
10429 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10430 quality controls, normalization, visualization, and further analysis are also
10432 (license license:artistic2.0)))
10434 (define-public r-hdf5array
10436 (name "r-hdf5array")
10441 (uri (bioconductor-uri "HDF5Array" version))
10444 "0n8zc1x582vwb0zfhrjmnqbnpqky9zbhjc2j836i0a4yisklwdcp"))))
10445 (properties `((upstream-name . "HDF5Array")))
10446 (build-system r-build-system)
10450 `(("r-biocgenerics" ,r-biocgenerics)
10451 ("r-delayedarray" ,r-delayedarray)
10452 ("r-iranges" ,r-iranges)
10453 ("r-rhdf5" ,r-rhdf5)
10454 ("r-rhdf5lib" ,r-rhdf5lib)
10455 ("r-s4vectors" ,r-s4vectors)))
10456 (home-page "https://bioconductor.org/packages/HDF5Array")
10457 (synopsis "HDF5 back end for DelayedArray objects")
10458 (description "This package provides an array-like container for convenient
10459 access and manipulation of HDF5 datasets. It supports delayed operations and
10460 block processing.")
10461 (license license:artistic2.0)))
10463 (define-public r-rhdf5lib
10465 (name "r-rhdf5lib")
10470 (uri (bioconductor-uri "Rhdf5lib" version))
10473 "1lpmyxlwwcy92hyxqag321ssc5z6yw3a0ws9r058jwgzyjg7i2gm"))
10474 (modules '((guix build utils)))
10477 ;; Delete bundled binaries
10478 (delete-file-recursively "src/winlib/")
10480 (properties `((upstream-name . "Rhdf5lib")))
10481 (build-system r-build-system)
10484 (modify-phases %standard-phases
10485 (add-after 'unpack 'do-not-use-bundled-hdf5
10486 (lambda* (#:key inputs #:allow-other-keys)
10487 (for-each delete-file '("configure" "configure.ac"))
10488 ;; Do not make other packages link with the proprietary libsz.
10489 (substitute* "R/zzz.R"
10490 (("'%s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a -lz'")
10491 "'%s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a -lz'")
10492 (("'%s/libhdf5.a %s/libsz.a -lz'")
10493 "'%s/libhdf5.a %s/libhdf5.a -lz'"))
10494 (with-directory-excursion "src"
10495 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10496 (rename-file (string-append "hdf5-" ,(package-version hdf5-1.10))
10498 ;; Remove timestamp and host system information to make
10499 ;; the build reproducible.
10500 (substitute* "hdf5/src/libhdf5.settings.in"
10501 (("Configured on: @CONFIG_DATE@")
10502 "Configured on: Guix")
10503 (("Uname information:.*")
10504 "Uname information: Linux\n")
10505 ;; Remove unnecessary store reference.
10507 "C Compiler: GCC\n"))
10508 (rename-file "Makevars.in" "Makevars")
10509 (substitute* "Makevars"
10510 (("HDF5_CXX_LIB=.*")
10511 (string-append "HDF5_CXX_LIB="
10512 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10514 (string-append "HDF5_LIB="
10515 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10516 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10517 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10518 ;; szip is non-free software
10519 (("cp \\$\\{SZIP_LIB\\}.*") "")
10520 (("\\$\\{USER_LIB_DIR\\}libsz.a") "")))
10525 `(("hdf5" ,hdf5-1.10)))
10527 `(("hdf5-source" ,(package-source hdf5-1.10))))
10528 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10529 (synopsis "HDF5 library as an R package")
10530 (description "This package provides C and C++ HDF5 libraries for use in R
10532 (license license:artistic2.0)))
10534 (define-public r-beachmat
10536 (name "r-beachmat")
10541 (uri (bioconductor-uri "beachmat" version))
10544 "14cz19fw97s8mhm9r2n5li44vckx069k8nqsyy64c3lkfm4vy4zx"))))
10545 (build-system r-build-system)
10547 `(("r-biocgenerics" ,r-biocgenerics)
10548 ("r-delayedarray" ,r-delayedarray)))
10549 (home-page "https://bioconductor.org/packages/beachmat")
10550 (synopsis "Compiling Bioconductor to handle each matrix type")
10551 (description "This package provides a consistent C++ class interface for a
10552 variety of commonly used matrix types, including sparse and HDF5-backed
10554 (license license:gpl3)))
10556 (define-public r-singlecellexperiment
10558 (name "r-singlecellexperiment")
10563 (uri (bioconductor-uri "SingleCellExperiment" version))
10566 "0m3yjnv1njb4gyzcjfk7a0lz2vgggp2wjz382gqrb0qhhwcgfkj5"))))
10568 `((upstream-name . "SingleCellExperiment")))
10569 (build-system r-build-system)
10571 `(("r-biocgenerics" ,r-biocgenerics)
10572 ("r-s4vectors" ,r-s4vectors)
10573 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10574 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10575 (synopsis "S4 classes for single cell data")
10576 (description "This package defines an S4 class for storing data from
10577 single-cell experiments. This includes specialized methods to store and
10578 retrieve spike-in information, dimensionality reduction coordinates and size
10579 factors for each cell, along with the usual metadata for genes and
10581 (license license:gpl3)))
10583 (define-public r-scater
10589 (uri (bioconductor-uri "scater" version))
10592 "16a17161xlhh6qpna9qxph3anlc7ydgyrczmy4alfiw8si7pzmxa"))))
10593 (build-system r-build-system)
10595 `(("r-beachmat" ,r-beachmat)
10596 ("r-biocgenerics" ,r-biocgenerics)
10597 ("r-biocneighbors" ,r-biocneighbors)
10598 ("r-biocparallel" ,r-biocparallel)
10599 ("r-biocsingular" ,r-biocsingular)
10600 ("r-delayedarray" ,r-delayedarray)
10601 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10602 ("r-dplyr" ,r-dplyr)
10603 ("r-ggbeeswarm" ,r-ggbeeswarm)
10604 ("r-ggplot2" ,r-ggplot2)
10605 ("r-matrix" ,r-matrix)
10607 ("r-s4vectors" ,r-s4vectors)
10608 ("r-singlecellexperiment" ,r-singlecellexperiment)
10609 ("r-summarizedexperiment" ,r-summarizedexperiment)
10610 ("r-viridis" ,r-viridis)))
10611 (home-page "https://github.com/davismcc/scater")
10612 (synopsis "Single-cell analysis toolkit for gene expression data in R")
10613 (description "This package provides a collection of tools for doing
10614 various analyses of single-cell RNA-seq gene expression data, with a focus on
10616 (license license:gpl2+)))
10618 (define-public r-scran
10625 (uri (bioconductor-uri "scran" version))
10628 "17mknpkvs7mgnlbf2hv9k7rwbx2vlg60yrwfyb8nn3nxsb6vm7yn"))))
10629 (build-system r-build-system)
10631 `(("r-beachmat" ,r-beachmat)
10633 ("r-biocgenerics" ,r-biocgenerics)
10634 ("r-biocneighbors" ,r-biocneighbors)
10635 ("r-biocparallel" ,r-biocparallel)
10636 ("r-biocsingular" ,r-biocsingular)
10637 ("r-delayedarray" ,r-delayedarray)
10638 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10639 ("r-dqrng" ,r-dqrng)
10640 ("r-dynamictreecut" ,r-dynamictreecut)
10641 ("r-edger" ,r-edger)
10642 ("r-igraph" ,r-igraph)
10643 ("r-limma" ,r-limma)
10644 ("r-matrix" ,r-matrix)
10646 ("r-s4vectors" ,r-s4vectors)
10647 ("r-scater" ,r-scater)
10648 ("r-singlecellexperiment" ,r-singlecellexperiment)
10649 ("r-statmod" ,r-statmod)
10650 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10651 (home-page "https://bioconductor.org/packages/scran")
10652 (synopsis "Methods for single-cell RNA-Seq data analysis")
10653 (description "This package implements a variety of low-level analyses of
10654 single-cell RNA-seq data. Methods are provided for normalization of
10655 cell-specific biases, assignment of cell cycle phase, and detection of highly
10656 variable and significantly correlated genes.")
10657 (license license:gpl3)))
10659 (define-public r-delayedmatrixstats
10661 (name "r-delayedmatrixstats")
10666 (uri (bioconductor-uri "DelayedMatrixStats" version))
10669 "0632ypndblrgzfk8k98rr8c6m2r0zwzf02pzvlrhcp9bj1pvqbrz"))))
10671 `((upstream-name . "DelayedMatrixStats")))
10672 (build-system r-build-system)
10674 `(("r-biocparallel" ,r-biocparallel)
10675 ("r-delayedarray" ,r-delayedarray)
10676 ("r-hdf5array" ,r-hdf5array)
10677 ("r-iranges" ,r-iranges)
10678 ("r-matrix" ,r-matrix)
10679 ("r-matrixstats" ,r-matrixstats)
10680 ("r-s4vectors" ,r-s4vectors)))
10681 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
10682 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
10684 "This package provides a port of the @code{matrixStats} API for use with
10685 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
10686 contains high-performing functions operating on rows and columns of
10687 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
10688 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
10689 are optimized per data type and for subsetted calculations such that both
10690 memory usage and processing time is minimized.")
10691 (license license:expat)))
10693 (define-public r-phangorn
10695 (name "r-phangorn")
10700 (uri (cran-uri "phangorn" version))
10703 "0ihkaykqjmf80d8wrk3saphxvnv58zma6pd13633bd3cwanc33f5"))))
10704 (build-system r-build-system)
10707 ("r-fastmatch" ,r-fastmatch)
10708 ("r-igraph" ,r-igraph)
10709 ("r-magrittr" ,r-magrittr)
10710 ("r-matrix" ,r-matrix)
10711 ("r-quadprog" ,r-quadprog)
10712 ("r-rcpp" ,r-rcpp)))
10713 (home-page "https://github.com/KlausVigo/phangorn")
10714 (synopsis "Phylogenetic analysis in R")
10716 "Phangorn is a package for phylogenetic analysis in R. It supports
10717 estimation of phylogenetic trees and networks using Maximum Likelihood,
10718 Maximum Parsimony, distance methods and Hadamard conjugation.")
10719 (license license:gpl2+)))
10721 (define-public r-dropbead
10722 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
10725 (name "r-dropbead")
10726 (version (string-append "0-" revision "." (string-take commit 7)))
10730 (uri (git-reference
10731 (url "https://github.com/rajewsky-lab/dropbead.git")
10733 (file-name (git-file-name name version))
10736 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
10737 (build-system r-build-system)
10739 `(("r-ggplot2" ,r-ggplot2)
10740 ("r-rcolorbrewer" ,r-rcolorbrewer)
10741 ("r-gridextra" ,r-gridextra)
10742 ("r-gplots" ,r-gplots)
10743 ("r-plyr" ,r-plyr)))
10744 (home-page "https://github.com/rajewsky-lab/dropbead")
10745 (synopsis "Basic exploration and analysis of Drop-seq data")
10746 (description "This package offers a quick and straight-forward way to
10747 explore and perform basic analysis of single cell sequencing data coming from
10748 droplet sequencing. It has been particularly tailored for Drop-seq.")
10749 (license license:gpl3))))
10751 (define htslib-for-sambamba
10752 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
10755 (name "htslib-for-sambamba")
10756 (version (string-append "1.3.1-1." (string-take commit 9)))
10760 (uri (git-reference
10761 (url "https://github.com/lomereiter/htslib.git")
10763 (file-name (string-append "htslib-" version "-checkout"))
10766 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
10768 `(("autoconf" ,autoconf)
10769 ("automake" ,automake)
10770 ,@(package-native-inputs htslib))))))
10772 (define-public sambamba
10779 (uri (git-reference
10780 (url "https://github.com/lomereiter/sambamba.git")
10781 (commit (string-append "v" version))))
10782 (file-name (string-append name "-" version "-checkout"))
10785 "0k0cz3qcv98p6cq09zlbgnjsggxcqbcmzxg5zikgcgbr2nfq4lry"))))
10786 (build-system gnu-build-system)
10788 `(#:tests? #f ; there is no test target
10789 #:parallel-build? #f ; not supported
10791 (modify-phases %standard-phases
10792 (delete 'configure)
10793 (add-after 'unpack 'fix-ldc-version
10795 (substitute* "gen_ldc_version_info.py"
10796 (("/usr/bin/env.*") (which "python3")))
10797 (substitute* "Makefile"
10798 ;; We use ldc2 instead of ldmd2 to compile sambamba.
10799 (("\\$\\(shell which ldmd2\\)") (which "ldc2")))
10801 (add-after 'unpack 'place-biod-and-undead
10802 (lambda* (#:key inputs #:allow-other-keys)
10803 (copy-recursively (assoc-ref inputs "biod") "BioD")
10804 (copy-recursively (assoc-ref inputs "undead") "undeaD")
10806 (add-after 'unpack 'unbundle-prerequisites
10808 (substitute* "Makefile"
10809 (("htslib/libhts.a lz4/lib/liblz4.a")
10811 ((" lz4-static htslib-static") ""))
10814 (lambda* (#:key outputs #:allow-other-keys)
10815 (let* ((out (assoc-ref outputs "out"))
10816 (bin (string-append out "/bin")))
10818 (install-file "bin/sambamba" bin)
10825 ,(let ((commit "4f1a7d2fb7ef3dfe962aa357d672f354ebfbe42e"))
10828 (uri (git-reference
10829 (url "https://github.com/biod/BioD.git")
10831 (file-name (string-append "biod-"
10832 (string-take commit 9)
10836 "1k5pdjv1qvi0a3rwd1sfq6zbj37l86i7bf710m4c0y6737lxj426")))))
10838 ,(let ((commit "9be93876982b5f14fcca60832563b3cd767dd84d"))
10841 (uri (git-reference
10842 (url "https://github.com/biod/undeaD.git")
10844 (file-name (string-append "undead-"
10845 (string-take commit 9)
10849 "1xfarj0nqlmi5jd1vmcmm7pabzaf9hxyvk6hp0d6jslb5k9r8r3d")))))))
10852 ("htslib" ,htslib-for-sambamba)))
10853 (home-page "http://lomereiter.github.io/sambamba")
10854 (synopsis "Tools for working with SAM/BAM data")
10855 (description "Sambamba is a high performance modern robust and
10856 fast tool (and library), written in the D programming language, for
10857 working with SAM and BAM files. Current parallelised functionality is
10858 an important subset of samtools functionality, including view, index,
10859 sort, markdup, and depth.")
10860 (license license:gpl2+)))
10862 (define-public ritornello
10864 (name "ritornello")
10868 (uri (git-reference
10869 (url "https://github.com/KlugerLab/Ritornello.git")
10870 (commit (string-append "v" version))))
10871 (file-name (git-file-name name version))
10874 "1xahvq215qld7x1w8vpa5zbrsj6p9crb9shqa2x89sb0aaxa02jk"))))
10875 (build-system gnu-build-system)
10877 `(#:tests? #f ; there are no tests
10879 (modify-phases %standard-phases
10880 (add-after 'unpack 'patch-samtools-references
10881 (lambda* (#:key inputs #:allow-other-keys)
10882 (substitute* '("src/SamStream.h"
10884 (("<sam.h>") "<samtools/sam.h>"))
10886 (delete 'configure)
10888 (lambda* (#:key inputs outputs #:allow-other-keys)
10889 (let* ((out (assoc-ref outputs "out"))
10890 (bin (string-append out "/bin/")))
10892 (install-file "bin/Ritornello" bin)
10895 `(("samtools" ,samtools-0.1)
10899 (home-page "https://github.com/KlugerLab/Ritornello")
10900 (synopsis "Control-free peak caller for ChIP-seq data")
10901 (description "Ritornello is a ChIP-seq peak calling algorithm based on
10902 signal processing that can accurately call binding events without the need to
10903 do a pair total DNA input or IgG control sample. It has been tested for use
10904 with narrow binding events such as transcription factor ChIP-seq.")
10905 (license license:gpl3+)))
10907 (define-public trim-galore
10909 (name "trim-galore")
10914 (uri (git-reference
10915 (url "https://github.com/FelixKrueger/TrimGalore.git")
10917 (file-name (git-file-name name version))
10920 "1y31wbxwkm9xqzr5zv1pk5q418whnmlmgmfyxxpnl12h83m2i9iv"))))
10921 (build-system gnu-build-system)
10923 `(#:tests? #f ; no tests
10925 (modify-phases %standard-phases
10926 (replace 'configure
10928 ;; Trim Galore tries to figure out what version of Python
10929 ;; cutadapt is using by looking at the shebang. Of course that
10930 ;; doesn't work, because cutadapt is wrapped in a shell script.
10931 (substitute* "trim_galore"
10932 (("my \\$python_return.*")
10933 "my $python_return = \"Python 3.999\";\n"))
10936 (add-after 'unpack 'hardcode-tool-references
10937 (lambda* (#:key inputs #:allow-other-keys)
10938 (substitute* "trim_galore"
10939 (("\\$path_to_cutadapt = 'cutadapt'")
10940 (string-append "$path_to_cutadapt = '"
10941 (assoc-ref inputs "cutadapt")
10943 (("\\$compression_path = \"gzip\"")
10944 (string-append "$compression_path = \""
10945 (assoc-ref inputs "gzip")
10948 (string-append "\""
10949 (assoc-ref inputs "gzip")
10952 (string-append "\""
10953 (assoc-ref inputs "pigz")
10957 (lambda* (#:key outputs #:allow-other-keys)
10958 (let ((bin (string-append (assoc-ref outputs "out")
10961 (install-file "trim_galore" bin)
10967 ("cutadapt" ,cutadapt)))
10969 `(("unzip" ,unzip)))
10970 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
10971 (synopsis "Wrapper around Cutadapt and FastQC")
10972 (description "Trim Galore! is a wrapper script to automate quality and
10973 adapter trimming as well as quality control, with some added functionality to
10974 remove biased methylation positions for RRBS sequence files.")
10975 (license license:gpl3+)))
10977 (define-public gess
10983 (uri (string-append "http://compbio.uthscsa.edu/"
10985 "gess-" version ".src.tar.gz"))
10988 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
10989 (build-system gnu-build-system)
10991 `(#:tests? #f ; no tests
10993 (modify-phases %standard-phases
10994 (delete 'configure)
10997 (lambda* (#:key inputs outputs #:allow-other-keys)
10998 (let* ((python (assoc-ref inputs "python"))
10999 (out (assoc-ref outputs "out"))
11000 (bin (string-append out "/bin/"))
11001 (target (string-append
11003 ,(version-major+minor
11004 (package-version python))
11005 "/site-packages/gess/")))
11007 (copy-recursively "." target)
11008 ;; Make GESS.py executable
11009 (chmod (string-append target "GESS.py") #o555)
11010 ;; Add Python shebang to the top and make Matplotlib
11012 (substitute* (string-append target "GESS.py")
11013 (("\"\"\"Description:" line)
11014 (string-append "#!" (which "python") "
11016 matplotlib.use('Agg')
11018 ;; Make sure GESS has all modules in its path
11019 (wrap-program (string-append target "GESS.py")
11020 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
11022 (symlink (string-append target "GESS.py")
11023 (string-append bin "GESS.py"))
11026 `(("python" ,python-2)
11027 ("python2-pysam" ,python2-pysam)
11028 ("python2-scipy" ,python2-scipy)
11029 ("python2-numpy" ,python2-numpy)
11030 ("python2-networkx" ,python2-networkx)
11031 ("python2-biopython" ,python2-biopython)))
11032 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
11033 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11035 "GESS is an implementation of a novel computational method to detect de
11036 novo exon-skipping events directly from raw RNA-seq data without the prior
11037 knowledge of gene annotation information. GESS stands for the graph-based
11038 exon-skipping scanner detection scheme.")
11039 (license license:bsd-3)))
11041 (define-public phylip
11048 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11049 "download/phylip-" version ".tar.gz"))
11052 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11053 (build-system gnu-build-system)
11055 `(#:tests? #f ; no check target
11056 #:make-flags (list "-f" "Makefile.unx" "install")
11057 #:parallel-build? #f ; not supported
11059 (modify-phases %standard-phases
11060 (add-after 'unpack 'enter-dir
11061 (lambda _ (chdir "src") #t))
11062 (delete 'configure)
11064 (lambda* (#:key inputs outputs #:allow-other-keys)
11065 (let ((target (string-append (assoc-ref outputs "out")
11068 (for-each (lambda (file)
11069 (install-file file target))
11070 (find-files "../exe" ".*")))
11072 (home-page "http://evolution.genetics.washington.edu/phylip/")
11073 (synopsis "Tools for inferring phylogenies")
11074 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11075 programs for inferring phylogenies (evolutionary trees).")
11076 (license license:bsd-2)))
11085 (uri (string-append "https://integrativemodeling.org/"
11086 version "/download/imp-" version ".tar.gz"))
11089 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
11090 (build-system cmake-build-system)
11092 `(;; FIXME: Some tests fail because they produce warnings, others fail
11093 ;; because the PYTHONPATH does not include the modeller's directory.
11101 ("python" ,python-2)))
11103 `(("python2-numpy" ,python2-numpy)
11104 ("python2-scipy" ,python2-scipy)
11105 ("python2-pandas" ,python2-pandas)
11106 ("python2-scikit-learn" ,python2-scikit-learn)
11107 ("python2-networkx" ,python2-networkx)))
11108 (home-page "https://integrativemodeling.org")
11109 (synopsis "Integrative modeling platform")
11110 (description "IMP's broad goal is to contribute to a comprehensive
11111 structural characterization of biomolecules ranging in size and complexity
11112 from small peptides to large macromolecular assemblies, by integrating data
11113 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11114 Python toolbox for solving complex modeling problems, and a number of
11115 applications for tackling some common problems in a user-friendly way.")
11116 ;; IMP is largely available under the GNU Lesser GPL; see the file
11117 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11118 ;; available under the GNU GPL (see the file COPYING.GPL).
11119 (license (list license:lgpl2.1+
11122 (define-public tadbit
11128 (uri (git-reference
11129 (url "https://github.com/3DGenomes/TADbit.git")
11130 (commit (string-append "v" version))))
11131 (file-name (git-file-name name version))
11134 "07g3aj648prmsvxp9caz5yl41k0y0647vxh0f5p3w8376mfiljd0"))))
11135 (build-system python-build-system)
11137 `(;; Tests are included and must be run after installation, but
11138 ;; they are incomplete and thus cannot be run.
11142 (modify-phases %standard-phases
11143 (add-after 'unpack 'fix-problems-with-setup.py
11144 (lambda* (#:key outputs #:allow-other-keys)
11145 ;; setup.py opens these files for writing
11146 (chmod "_pytadbit/_version.py" #o664)
11147 (chmod "README.rst" #o664)
11149 ;; Don't attempt to install the bash completions to
11150 ;; the home directory.
11151 (rename-file "extras/.bash_completion"
11153 (substitute* "setup.py"
11154 (("\\(path.expanduser\\('~'\\)")
11155 (string-append "(\""
11156 (assoc-ref outputs "out")
11157 "/etc/bash_completion.d\""))
11158 (("extras/\\.bash_completion")
11162 ;; TODO: add Chimera for visualization
11165 ("python2-scipy" ,python2-scipy)
11166 ("python2-numpy" ,python2-numpy)
11167 ("python2-matplotlib" ,python2-matplotlib)
11168 ("python2-pysam" ,python2-pysam)))
11169 (home-page "https://3dgenomes.github.io/TADbit/")
11170 (synopsis "Analyze, model, and explore 3C-based data")
11172 "TADbit is a complete Python library to deal with all steps to analyze,
11173 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11174 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11175 correct interaction matrices, identify and compare the so-called
11176 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11177 interaction matrices, and finally, extract structural properties from the
11178 models. TADbit is complemented by TADkit for visualizing 3D models.")
11179 (license license:gpl3+)))
11181 (define-public kentutils
11184 ;; 302.1.0 is out, but the only difference is the inclusion of
11185 ;; pre-built binaries.
11186 (version "302.0.0")
11190 (uri (git-reference
11191 (url "https://github.com/ENCODE-DCC/kentUtils.git")
11192 (commit (string-append "v" version))))
11193 (file-name (git-file-name name version))
11196 "0n1wbyjpzii2b9qhyp9r1q76j623cggpg3y8fmw78ld3z4y7ivha"))
11197 (modules '((guix build utils)
11202 ;; Only the contents of the specified directories are free
11203 ;; for all uses, so we remove the rest. "hg/autoSql" and
11204 ;; "hg/autoXml" are nominally free, but they depend on a
11205 ;; library that is built from the sources in "hg/lib",
11206 ;; which is nonfree.
11207 (let ((free (list "." ".."
11208 "utils" "lib" "inc" "tagStorm"
11209 "parasol" "htslib"))
11210 (directory? (lambda (file)
11211 (eq? 'directory (stat:type (stat file))))))
11212 (for-each (lambda (file)
11213 (and (directory? file)
11214 (delete-file-recursively file)))
11215 (map (cut string-append "src/" <>)
11218 (not (member file free)))))))
11219 ;; Only make the utils target, not the userApps target,
11220 ;; because that requires libraries we won't build.
11221 (substitute* "Makefile"
11222 ((" userApps") " utils"))
11223 ;; Only build libraries that are free.
11224 (substitute* "src/makefile"
11225 (("DIRS =.*") "DIRS =\n")
11226 (("cd jkOwnLib.*") "")
11229 (substitute* "src/utils/makefile"
11230 ;; These tools depend on "jkhgap.a", which is part of the
11231 ;; nonfree "src/hg/lib" directory.
11232 (("raSqlQuery") "")
11233 (("pslLiftSubrangeBlat") "")
11235 ;; Do not build UCSC tools, which may require nonfree
11237 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11239 (build-system gnu-build-system)
11241 `( ;; There is no global test target and the test target for
11242 ;; individual tools depends on input files that are not
11246 (modify-phases %standard-phases
11247 (add-after 'unpack 'fix-permissions
11248 (lambda _ (make-file-writable "src/inc/localEnvironment.mk") #t))
11249 (add-after 'unpack 'fix-paths
11251 (substitute* "Makefile"
11252 (("/bin/echo") (which "echo")))
11254 (add-after 'unpack 'prepare-samtabix
11255 (lambda* (#:key inputs #:allow-other-keys)
11256 (copy-recursively (assoc-ref inputs "samtabix")
11259 (delete 'configure)
11261 (lambda* (#:key outputs #:allow-other-keys)
11262 (let ((bin (string-append (assoc-ref outputs "out")
11264 (copy-recursively "bin" bin))
11270 (uri (git-reference
11271 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11272 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11275 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11281 ("mariadb" ,mariadb)
11282 ("openssl" ,openssl)))
11283 (home-page "http://genome.cse.ucsc.edu/index.html")
11284 (synopsis "Assorted bioinformatics utilities")
11285 (description "This package provides the kentUtils, a selection of
11286 bioinformatics utilities used in combination with the UCSC genome
11288 ;; Only a subset of the sources are released under a non-copyleft
11289 ;; free software license. All other sources are removed in a
11290 ;; snippet. See this bug report for an explanation of how the
11291 ;; license statements apply:
11292 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11293 (license (license:non-copyleft
11294 "http://genome.ucsc.edu/license/"
11295 "The contents of this package are free for all uses."))))
11297 (define-public f-seq
11298 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11302 (version (string-append "1.1-" revision "." (string-take commit 7)))
11305 (uri (git-reference
11306 (url "https://github.com/aboyle/F-seq.git")
11308 (file-name (string-append name "-" version))
11311 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11312 (modules '((guix build utils)))
11313 ;; Remove bundled Java library archives.
11316 (for-each delete-file (find-files "lib" ".*"))
11318 (build-system ant-build-system)
11320 `(#:tests? #f ; no tests included
11322 (modify-phases %standard-phases
11324 (lambda* (#:key inputs outputs #:allow-other-keys)
11325 (let* ((target (assoc-ref outputs "out"))
11326 (bin (string-append target "/bin"))
11327 (doc (string-append target "/share/doc/f-seq"))
11328 (lib (string-append target "/lib")))
11331 (substitute* "bin/linux/fseq"
11332 (("java") (which "java"))
11333 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11334 (string-append (assoc-ref inputs "java-commons-cli")
11335 "/share/java/commons-cli.jar"))
11337 (string-append "REALDIR=" bin "\n")))
11338 (install-file "README.txt" doc)
11339 (install-file "bin/linux/fseq" bin)
11340 (install-file "build~/fseq.jar" lib)
11341 (copy-recursively "lib" lib)
11345 ("java-commons-cli" ,java-commons-cli)))
11346 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11347 (synopsis "Feature density estimator for high-throughput sequence tags")
11349 "F-Seq is a software package that generates a continuous tag sequence
11350 density estimation allowing identification of biologically meaningful sites
11351 such as transcription factor binding sites (ChIP-seq) or regions of open
11352 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11354 (license license:gpl3+))))
11356 (define-public bismark
11363 (uri (git-reference
11364 (url "https://github.com/FelixKrueger/Bismark.git")
11366 (file-name (string-append name "-" version "-checkout"))
11369 "0xchm3rgilj6vfjnyzfzzymfd7djr64sbrmrvs3njbwi66jqbzw9"))))
11370 (build-system perl-build-system)
11372 `(#:tests? #f ; there are no tests
11373 #:modules ((guix build utils)
11376 (guix build perl-build-system))
11378 (modify-phases %standard-phases
11379 ;; The bundled plotly.js is minified.
11380 (add-after 'unpack 'replace-plotly.js
11381 (lambda* (#:key inputs #:allow-other-keys)
11382 (let* ((file (assoc-ref inputs "plotly.js"))
11383 (installed "plotly/plotly.js"))
11384 (let ((minified (open-pipe* OPEN_READ "uglify-js" file)))
11385 (call-with-output-file installed
11386 (cut dump-port minified <>))))
11388 (delete 'configure)
11391 (lambda* (#:key inputs outputs #:allow-other-keys)
11392 (let* ((out (assoc-ref outputs "out"))
11393 (bin (string-append out "/bin"))
11394 (share (string-append out "/share/bismark"))
11395 (docdir (string-append out "/share/doc/bismark"))
11396 (docs '("Docs/Bismark_User_Guide.html"))
11397 (scripts '("bismark"
11398 "bismark_genome_preparation"
11399 "bismark_methylation_extractor"
11402 "coverage2cytosine"
11403 "deduplicate_bismark"
11404 "filter_non_conversion"
11407 "NOMe_filtering")))
11408 (substitute* "bismark2report"
11409 (("\\$RealBin/plotly")
11410 (string-append share "/plotly")))
11414 (for-each (lambda (file) (install-file file bin))
11416 (for-each (lambda (file) (install-file file docdir))
11418 (copy-recursively "Docs/Images" (string-append docdir "/Images"))
11419 (copy-recursively "plotly"
11420 (string-append share "/plotly"))
11422 ;; Fix references to gunzip
11423 (substitute* (map (lambda (file)
11424 (string-append bin "/" file))
11427 (string-append "\"" (assoc-ref inputs "gzip")
11428 "/bin/gunzip -c")))
11432 ("perl-carp" ,perl-carp)
11433 ("perl-getopt-long" ,perl-getopt-long)))
11438 (uri (string-append "https://raw.githubusercontent.com/plotly/plotly.js/"
11439 "v1.39.4/dist/plotly.js"))
11441 (base32 "138mwsr4nf5qif4mrxx286mpnagxd1xwl6k8aidrjgknaqg88zyr"))))
11442 ("uglify-js" ,uglify-js)))
11443 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11444 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11445 (description "Bismark is a program to map bisulfite treated sequencing
11446 reads to a genome of interest and perform methylation calls in a single step.
11447 The output can be easily imported into a genome viewer, such as SeqMonk, and
11448 enables a researcher to analyse the methylation levels of their samples
11449 straight away. Its main features are:
11452 @item Bisulfite mapping and methylation calling in one single step
11453 @item Supports single-end and paired-end read alignments
11454 @item Supports ungapped and gapped alignments
11455 @item Alignment seed length, number of mismatches etc are adjustable
11456 @item Output discriminates between cytosine methylation in CpG, CHG
11459 (license license:gpl3+)))
11461 (define-public paml
11467 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11468 "paml" version ".tgz"))
11471 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11472 (modules '((guix build utils)))
11473 ;; Remove Windows binaries
11476 (for-each delete-file (find-files "." "\\.exe$"))
11478 (build-system gnu-build-system)
11480 `(#:tests? #f ; there are no tests
11481 #:make-flags '("CC=gcc")
11483 (modify-phases %standard-phases
11484 (replace 'configure
11486 (substitute* "src/BFdriver.c"
11487 (("/bin/bash") (which "bash")))
11491 (lambda* (#:key outputs #:allow-other-keys)
11492 (let ((tools '("baseml" "basemlg" "codeml"
11493 "pamp" "evolver" "yn00" "chi2"))
11494 (bin (string-append (assoc-ref outputs "out") "/bin"))
11495 (docdir (string-append (assoc-ref outputs "out")
11496 "/share/doc/paml")))
11498 (for-each (lambda (file) (install-file file bin)) tools)
11499 (copy-recursively "../doc" docdir)
11501 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11502 (synopsis "Phylogentic analysis by maximum likelihood")
11503 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11504 contains a few programs for model fitting and phylogenetic tree reconstruction
11505 using nucleotide or amino-acid sequence data.")
11507 (license license:gpl3)))
11509 (define-public kallisto
11515 (uri (git-reference
11516 (url "https://github.com/pachterlab/kallisto.git")
11517 (commit (string-append "v" version))))
11518 (file-name (git-file-name name version))
11521 "0nj382jiywqnpgvyhichajpkkh5r0bapn43f4dx40zdaq5v4m40m"))))
11522 (build-system cmake-build-system)
11524 `(#:tests? #f ; no "check" target
11526 (modify-phases %standard-phases
11527 (add-after 'unpack 'do-not-use-bundled-htslib
11529 (substitute* "CMakeLists.txt"
11530 (("^ExternalProject_Add" m)
11531 (string-append "if (NEVER)\n" m))
11533 (string-append ")\nendif(NEVER)"))
11534 (("include_directories\\(\\$\\{htslib_PREFIX.*" m)
11535 (string-append "# " m)))
11536 (substitute* "src/CMakeLists.txt"
11537 (("target_link_libraries\\(kallisto kallisto_core pthread \
11538 \\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/../ext/htslib/libhts.a\\)")
11539 "target_link_libraries(kallisto kallisto_core pthread hts)")
11540 (("include_directories\\(\\.\\./ext/htslib\\)") ""))
11546 (home-page "http://pachterlab.github.io/kallisto/")
11547 (synopsis "Near-optimal RNA-Seq quantification")
11549 "Kallisto is a program for quantifying abundances of transcripts from
11550 RNA-Seq data, or more generally of target sequences using high-throughput
11551 sequencing reads. It is based on the novel idea of pseudoalignment for
11552 rapidly determining the compatibility of reads with targets, without the need
11553 for alignment. Pseudoalignment of reads preserves the key information needed
11554 for quantification, and kallisto is therefore not only fast, but also as
11555 accurate as existing quantification tools.")
11556 (license license:bsd-2)))
11558 (define-public libgff
11564 (uri (git-reference
11565 (url "https://github.com/Kingsford-Group/libgff.git")
11566 (commit (string-append "v" version))))
11567 (file-name (git-file-name name version))
11570 "0n6vfjnq7a2mianipscbshrvbncss8z4zkgkbjw754p9043nfkps"))))
11571 (build-system cmake-build-system)
11572 (arguments `(#:tests? #f)) ; no tests included
11573 (home-page "https://github.com/Kingsford-Group/libgff")
11574 (synopsis "Parser library for reading/writing GFF files")
11575 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11576 code that is used in the Cufflinks codebase. The goal of this library is to
11577 provide this functionality without the necessity of drawing in a heavy-weight
11578 dependency like SeqAn.")
11579 (license (license:x11-style "https://www.boost.org/LICENSE_1_0.txt"))))
11581 (define-public libdivsufsort
11583 (name "libdivsufsort")
11587 (uri (git-reference
11588 (url "https://github.com/y-256/libdivsufsort.git")
11590 (file-name (git-file-name name version))
11593 "0fgdz9fzihlvjjrxy01md1bv9vh12rkgkwbm90b1hj5xpbaqp7z2"))))
11594 (build-system cmake-build-system)
11596 '(#:tests? #f ; there are no tests
11598 ;; Needed for rapmap and sailfish.
11599 '("-DBUILD_DIVSUFSORT64=ON")))
11600 (home-page "https://github.com/y-256/libdivsufsort")
11601 (synopsis "Lightweight suffix-sorting library")
11602 (description "libdivsufsort is a software library that implements a
11603 lightweight suffix array construction algorithm. This library provides a
11604 simple and an efficient C API to construct a suffix array and a
11605 Burrows-Wheeler transformed string from a given string over a constant-size
11606 alphabet. The algorithm runs in O(n log n) worst-case time using only 5n+O(1)
11607 bytes of memory space, where n is the length of the string.")
11608 (license license:expat)))
11610 (define-public sailfish
11616 (uri (git-reference
11617 (url "https://github.com/kingsfordgroup/sailfish.git")
11618 (commit (string-append "v" version))))
11619 (file-name (git-file-name name version))
11622 "1amcc5hqvsl42hg4x19bi9vy47cl874s0lw1fmi0hwsdk9i8c03v"))
11623 (modules '((guix build utils)))
11626 ;; Delete bundled headers for eigen3.
11627 (delete-file-recursively "include/eigen3/")
11629 (build-system cmake-build-system)
11631 `(#:configure-flags
11632 (list (string-append "-DBOOST_INCLUDEDIR="
11633 (assoc-ref %build-inputs "boost")
11635 (string-append "-DBOOST_LIBRARYDIR="
11636 (assoc-ref %build-inputs "boost")
11638 (string-append "-DBoost_LIBRARIES="
11639 "-lboost_iostreams "
11640 "-lboost_filesystem "
11645 "-lboost_program_options")
11646 "-DBoost_FOUND=TRUE"
11647 ;; Don't download RapMap---we already have it!
11648 "-DFETCHED_RAPMAP=1")
11649 ;; Tests must be run after installation and the location of the test
11650 ;; data file must be overridden. But the tests fail. It looks like
11651 ;; they are not really meant to be run.
11654 (modify-phases %standard-phases
11655 ;; Boost cannot be found, even though it's right there.
11656 (add-after 'unpack 'do-not-look-for-boost
11657 (lambda* (#:key inputs #:allow-other-keys)
11658 (substitute* "CMakeLists.txt"
11659 (("find_package\\(Boost 1\\.53\\.0") "#"))
11661 (add-after 'unpack 'do-not-assign-to-macro
11663 (substitute* "include/spdlog/details/format.cc"
11664 (("const unsigned CHAR_WIDTH = 1;") ""))
11666 (add-after 'unpack 'prepare-rapmap
11667 (lambda* (#:key inputs #:allow-other-keys)
11668 (let ((src "external/install/src/rapmap/")
11669 (include "external/install/include/rapmap/")
11670 (rapmap (assoc-ref inputs "rapmap")))
11671 (mkdir-p "/tmp/rapmap")
11673 (assoc-ref inputs "rapmap")
11675 "--strip-components=1")
11678 (for-each (lambda (file)
11679 (install-file file src))
11680 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
11681 (copy-recursively "/tmp/rapmap/include" include))
11683 (add-after 'unpack 'use-system-libraries
11684 (lambda* (#:key inputs #:allow-other-keys)
11685 (substitute* '("src/SailfishIndexer.cpp"
11686 "src/SailfishUtils.cpp"
11687 "src/SailfishQuantify.cpp"
11688 "src/FASTAParser.cpp"
11690 "include/SailfishUtils.hpp"
11691 "include/SailfishIndex.hpp"
11692 "include/CollapsedEMOptimizer.hpp"
11693 "src/CollapsedEMOptimizer.cpp")
11694 (("#include \"jellyfish/config.h\"") ""))
11695 (substitute* "src/CMakeLists.txt"
11696 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11697 (string-append (assoc-ref inputs "jellyfish")
11698 "/include/jellyfish-" ,(package-version jellyfish)))
11699 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11700 (string-append (assoc-ref inputs "jellyfish")
11701 "/lib/libjellyfish-2.0.a"))
11702 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11703 (string-append (assoc-ref inputs "libdivsufsort")
11704 "/lib/libdivsufsort.so"))
11705 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11706 (string-append (assoc-ref inputs "libdivsufsort")
11707 "/lib/libdivsufsort64.so")))
11708 (substitute* "CMakeLists.txt"
11709 ;; Don't prefer static libs
11710 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11711 (("find_package\\(Jellyfish.*") "")
11712 (("ExternalProject_Add\\(libjellyfish") "message(")
11713 (("ExternalProject_Add\\(libgff") "message(")
11714 (("ExternalProject_Add\\(libsparsehash") "message(")
11715 (("ExternalProject_Add\\(libdivsufsort") "message("))
11717 ;; Ensure that Eigen headers can be found
11718 (setenv "CPLUS_INCLUDE_PATH"
11719 (string-append (getenv "CPLUS_INCLUDE_PATH")
11721 (assoc-ref inputs "eigen")
11722 "/include/eigen3"))
11727 ("jemalloc" ,jemalloc)
11728 ("jellyfish" ,jellyfish)
11729 ("sparsehash" ,sparsehash)
11732 (uri (git-reference
11733 (url "https://github.com/COMBINE-lab/RapMap.git")
11734 (commit (string-append "sf-v" version))))
11735 (file-name (string-append "rapmap-sf-v" version "-checkout"))
11738 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
11739 (modules '((guix build utils)))
11740 ;; These files are expected to be excluded.
11742 '(begin (delete-file-recursively "include/spdlog")
11743 (for-each delete-file '("include/xxhash.h"
11746 ("libdivsufsort" ,libdivsufsort)
11751 `(("pkg-config" ,pkg-config)))
11752 (home-page "http://www.cs.cmu.edu/~ckingsf/software/sailfish")
11753 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
11754 (description "Sailfish is a tool for genomic transcript quantification
11755 from RNA-seq data. It requires a set of target transcripts (either from a
11756 reference or de-novo assembly) to quantify. All you need to run sailfish is a
11757 fasta file containing your reference transcripts and a (set of) fasta/fastq
11758 file(s) containing your reads.")
11759 (license license:gpl3+)))
11761 (define libstadenio-for-salmon
11763 (name "libstadenio")
11767 (uri (git-reference
11768 (url "https://github.com/COMBINE-lab/staden-io_lib.git")
11769 (commit (string-append "v" version))))
11770 (file-name (string-append name "-" version "-checkout"))
11773 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
11774 (build-system gnu-build-system)
11775 (arguments '(#:parallel-tests? #f)) ; not supported
11779 `(("perl" ,perl))) ; for tests
11780 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
11781 (synopsis "General purpose trace and experiment file library")
11782 (description "This package provides a library of file reading and writing
11783 code to provide a general purpose Trace file (and Experiment File) reading
11786 The following file formats are supported:
11789 @item SCF trace files
11790 @item ABI trace files
11791 @item ALF trace files
11792 @item ZTR trace files
11793 @item SFF trace archives
11794 @item SRF trace archives
11795 @item Experiment files
11796 @item Plain text files
11797 @item SAM/BAM sequence files
11798 @item CRAM sequence files
11800 (license license:bsd-3)))
11802 (define-public salmon
11808 (uri (git-reference
11809 (url "https://github.com/COMBINE-lab/salmon.git")
11810 (commit (string-append "v" version))))
11811 (file-name (git-file-name name version))
11814 "1i2z4aivicmiixdz9bxalp7vmfzi3k92fxa63iqa8kgvfw5a4aq5"))
11815 (modules '((guix build utils)))
11818 ;; Delete bundled headers for eigen3.
11819 (delete-file-recursively "include/eigen3/")
11821 (build-system cmake-build-system)
11823 `(#:configure-flags
11824 (list (string-append "-DBOOST_INCLUDEDIR="
11825 (assoc-ref %build-inputs "boost")
11827 (string-append "-DBOOST_LIBRARYDIR="
11828 (assoc-ref %build-inputs "boost")
11830 (string-append "-DBoost_LIBRARIES="
11831 "-lboost_iostreams "
11832 "-lboost_filesystem "
11837 "-lboost_program_options")
11838 "-DBoost_FOUND=TRUE"
11839 "-DTBB_LIBRARIES=tbb tbbmalloc"
11840 ;; Don't download RapMap---we already have it!
11841 "-DFETCHED_RAPMAP=1")
11843 (modify-phases %standard-phases
11844 ;; Boost cannot be found, even though it's right there.
11845 (add-after 'unpack 'do-not-look-for-boost
11846 (lambda* (#:key inputs #:allow-other-keys)
11847 (substitute* "CMakeLists.txt"
11848 (("find_package\\(Boost 1\\.59\\.0") "#"))
11850 (add-after 'unpack 'do-not-phone-home
11852 (substitute* "src/Salmon.cpp"
11853 (("getVersionMessage\\(\\)") "\"\""))
11855 (add-after 'unpack 'prepare-rapmap
11856 (lambda* (#:key inputs #:allow-other-keys)
11857 (let ((src "external/install/src/rapmap/")
11858 (include "external/install/include/rapmap/")
11859 (rapmap (assoc-ref inputs "rapmap")))
11862 (copy-recursively (string-append rapmap "/src") src)
11863 (copy-recursively (string-append rapmap "/include") include)
11864 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
11865 "external/install/include/rapmap/FastxParser.hpp"
11866 "external/install/include/rapmap/concurrentqueue.h"
11867 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
11868 "external/install/src/rapmap/FastxParser.cpp"
11869 "external/install/src/rapmap/xxhash.c"))
11870 (delete-file-recursively "external/install/include/rapmap/spdlog"))
11872 (add-after 'unpack 'use-system-libraries
11873 (lambda* (#:key inputs #:allow-other-keys)
11874 (substitute* "CMakeLists.txt"
11875 ;; Don't prefer static libs
11876 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11877 (("set\\(TBB_LIBRARIES") "message(")
11878 ;; Don't download anything
11879 (("DOWNLOAD_COMMAND") "DOWNLOAD_COMMAND echo")
11880 (("externalproject_add\\(libcereal") "message(")
11881 (("externalproject_add\\(libgff") "message(")
11882 (("externalproject_add\\(libtbb") "message(")
11883 (("externalproject_add\\(libdivsufsort") "message(")
11884 (("externalproject_add\\(libstadenio") "message(")
11885 (("externalproject_add_step\\(") "message("))
11886 (substitute* "src/CMakeLists.txt"
11887 (("add_dependencies") "#")
11888 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
11889 (string-append (assoc-ref inputs "libstadenio-for-salmon")
11890 "/lib/libstaden-read.so"))
11891 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11892 (string-append (assoc-ref inputs "libdivsufsort")
11893 "/lib/libdivsufsort.so"))
11894 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11895 (string-append (assoc-ref inputs "libdivsufsort")
11896 "/lib/libdivsufsort64.so"))
11897 (("lib/libdivsufsort.a") "/lib/libdivsufsort.so"))
11899 ;; Ensure that all headers can be found
11900 (setenv "CPLUS_INCLUDE_PATH"
11901 (string-append (getenv "CPLUS_INCLUDE_PATH")
11903 (assoc-ref inputs "eigen")
11904 "/include/eigen3"))
11906 (string-append (assoc-ref inputs "eigen")
11907 "/include/eigen3"))
11909 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
11910 ;; run. It only exists after the install phase.
11911 (add-after 'unpack 'fix-tests
11913 (substitute* "src/CMakeLists.txt"
11914 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
11915 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
11924 (uri (git-reference
11925 (url "https://github.com/COMBINE-lab/RapMap.git")
11926 (commit (string-append "salmon-v" version))))
11927 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
11930 "1biplxf0csc7a8h1wf219b0vmjkvw6wk2zylhdklb577kgmihdms"))))
11931 ("jemalloc" ,jemalloc)
11934 ("libdivsufsort" ,libdivsufsort)
11935 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
11939 `(("pkg-config" ,pkg-config)))
11940 (home-page "https://github.com/COMBINE-lab/salmon")
11941 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
11942 (description "Salmon is a program to produce highly-accurate,
11943 transcript-level quantification estimates from RNA-seq data. Salmon achieves
11944 its accuracy and speed via a number of different innovations, including the
11945 use of lightweight alignments (accurate but fast-to-compute proxies for
11946 traditional read alignments) and massively-parallel stochastic collapsed
11947 variational inference.")
11948 (license license:gpl3+)))
11950 (define-public python-loompy
11952 (name "python-loompy")
11954 ;; The tarball on Pypi does not include the tests.
11957 (uri (git-reference
11958 (url "https://github.com/linnarsson-lab/loompy.git")
11960 (file-name (git-file-name name version))
11963 "12a5kjgiikapv93wahfw0frszx1lblnppyz3vs5gy8fgmgngra07"))))
11964 (build-system python-build-system)
11967 (modify-phases %standard-phases
11970 (setenv "PYTHONPATH"
11971 (string-append (getcwd) ":"
11972 (getenv "PYTHONPATH")))
11973 (invoke "pytest" "tests")
11976 `(("python-h5py" ,python-h5py)
11977 ("python-numpy" ,python-numpy)
11978 ("python-pandas" ,python-pandas)
11979 ("python-scipy" ,python-scipy)))
11981 `(("python-pytest" ,python-pytest)))
11982 (home-page "https://github.com/linnarsson-lab/loompy")
11983 (synopsis "Work with .loom files for single-cell RNA-seq data")
11984 (description "The loom file format is an efficient format for very large
11985 omics datasets, consisting of a main matrix, optional additional layers, a
11986 variable number of row and column annotations. Loom also supports sparse
11987 graphs. This library makes it easy to work with @file{.loom} files for
11988 single-cell RNA-seq data.")
11989 (license license:bsd-3)))
11991 ;; pigx-scrnaseq does not work with the latest version of loompy.
11992 (define-public python-loompy-for-pigx-scrnaseq
11993 (package (inherit python-loompy)
11994 (name "python-loompy")
11998 (uri (git-reference
11999 (url "https://github.com/linnarsson-lab/loompy.git")
12000 (commit (string-append "v" version))))
12001 (file-name (git-file-name name version))
12004 "0pjyl532pl8sbv71yci6h0agchn0naw2qjcwj50n6afrsahbsag3"))))
12006 (arguments '(#:tests? #f))))
12008 ;; We cannot use the latest commit because it requires Java 9.
12009 (define-public java-forester
12010 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
12013 (name "java-forester")
12014 (version (string-append "0-" revision "." (string-take commit 7)))
12017 (uri (git-reference
12018 (url "https://github.com/cmzmasek/forester.git")
12020 (file-name (string-append name "-" version "-checkout"))
12023 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12024 (modules '((guix build utils)))
12027 ;; Delete bundled jars and pre-built classes
12028 (delete-file-recursively "forester/java/resources")
12029 (delete-file-recursively "forester/java/classes")
12030 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12031 ;; Delete bundled applications
12032 (delete-file-recursively "forester_applications")
12034 (build-system ant-build-system)
12036 `(#:tests? #f ; there are none
12038 #:modules ((guix build ant-build-system)
12040 (guix build java-utils)
12044 (modify-phases %standard-phases
12045 (add-after 'unpack 'chdir
12046 (lambda _ (chdir "forester/java") #t))
12047 (add-after 'chdir 'fix-dependencies
12049 (chmod "build.xml" #o664)
12050 (call-with-output-file "build.xml.new"
12054 (with-input-from-file "build.xml"
12055 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12056 `(;; Remove all unjar tags to avoid repacking classes.
12057 (unjar . ,(lambda _ '()))
12058 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12059 (*text* . ,(lambda (_ txt) txt))))
12061 (rename-file "build.xml.new" "build.xml")
12063 ;; FIXME: itext is difficult to package as it depends on a few
12064 ;; unpackaged libraries.
12065 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12067 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12068 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12069 (("pdf_written_to = PdfExporter.*")
12070 "throw new IOException(\"PDF export is not available.\");"))
12072 ;; There is no install target
12073 (replace 'install (install-jars ".")))))
12075 `(("java-commons-codec" ,java-commons-codec)
12076 ("java-openchart2" ,java-openchart2)))
12077 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12078 (synopsis "Phylogenomics libraries for Java")
12079 (description "Forester is a collection of Java libraries for
12080 phylogenomics and evolutionary biology research. It includes support for
12081 reading, writing, and exporting phylogenetic trees.")
12082 (license license:lgpl2.1+))))
12084 (define-public java-forester-1.005
12086 (name "java-forester")
12090 (uri (string-append "http://search.maven.org/remotecontent?"
12091 "filepath=org/biojava/thirdparty/forester/"
12092 version "/forester-" version "-sources.jar"))
12093 (file-name (string-append name "-" version ".jar"))
12096 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12097 (build-system ant-build-system)
12099 `(#:tests? #f ; there are none
12101 #:modules ((guix build ant-build-system)
12103 (guix build java-utils)
12107 (modify-phases %standard-phases
12108 (add-after 'unpack 'fix-dependencies
12109 (lambda* (#:key inputs #:allow-other-keys)
12110 (call-with-output-file "build.xml"
12114 (with-input-from-file "src/build.xml"
12115 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12116 `(;; Remove all unjar tags to avoid repacking classes.
12117 (unjar . ,(lambda _ '()))
12118 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12119 (*text* . ,(lambda (_ txt) txt))))
12121 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12122 "synth_look_and_feel_1.xml")
12123 (copy-file (assoc-ref inputs "phyloxml.xsd")
12125 (substitute* "build.xml"
12126 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12127 "synth_look_and_feel_1.xml")
12128 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12131 ;; FIXME: itext is difficult to package as it depends on a few
12132 ;; unpackaged libraries.
12133 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12135 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12136 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12137 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12138 (("pdf_written_to = PdfExporter.*")
12139 "throw new IOException(\"PDF export is not available.\"); /*")
12140 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12141 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12143 (add-after 'unpack 'delete-pre-built-classes
12144 (lambda _ (delete-file-recursively "src/classes") #t))
12145 ;; There is no install target
12146 (replace 'install (install-jars ".")))))
12148 `(("java-commons-codec" ,java-commons-codec)
12149 ("java-openchart2" ,java-openchart2)))
12150 ;; The source archive does not contain the resources.
12155 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12156 "b61cc2dcede0bede317db362472333115756b8c6/"
12157 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12158 (file-name (string-append name "-phyloxml-" version ".xsd"))
12161 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12162 ("synth_look_and_feel_1.xml"
12165 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12166 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12167 "forester/java/classes/resources/synth_look_and_feel_1.xml"))
12168 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12171 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12172 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12173 (synopsis "Phylogenomics libraries for Java")
12174 (description "Forester is a collection of Java libraries for
12175 phylogenomics and evolutionary biology research. It includes support for
12176 reading, writing, and exporting phylogenetic trees.")
12177 (license license:lgpl2.1+)))
12179 (define-public java-biojava-core
12181 (name "java-biojava-core")
12185 (uri (git-reference
12186 (url "https://github.com/biojava/biojava")
12187 (commit (string-append "biojava-" version))))
12188 (file-name (string-append name "-" version "-checkout"))
12191 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12192 (build-system ant-build-system)
12195 #:jar-name "biojava-core.jar"
12196 #:source-dir "biojava-core/src/main/java/"
12197 #:test-dir "biojava-core/src/test"
12198 ;; These tests seem to require internet access.
12199 #:test-exclude (list "**/SearchIOTest.java"
12200 "**/BlastXMLParserTest.java"
12201 "**/GenbankCookbookTest.java"
12202 "**/GenbankProxySequenceReaderTest.java")
12204 (modify-phases %standard-phases
12205 (add-before 'build 'copy-resources
12207 (copy-recursively "biojava-core/src/main/resources"
12210 (add-before 'check 'copy-test-resources
12212 (copy-recursively "biojava-core/src/test/resources"
12213 "build/test-classes")
12216 `(("java-log4j-api" ,java-log4j-api)
12217 ("java-log4j-core" ,java-log4j-core)
12218 ("java-slf4j-api" ,java-slf4j-api)
12219 ("java-slf4j-simple" ,java-slf4j-simple)))
12221 `(("java-junit" ,java-junit)
12222 ("java-hamcrest-core" ,java-hamcrest-core)))
12223 (home-page "http://biojava.org")
12224 (synopsis "Core libraries of Java framework for processing biological data")
12225 (description "BioJava is a project dedicated to providing a Java framework
12226 for processing biological data. It provides analytical and statistical
12227 routines, parsers for common file formats, reference implementations of
12228 popular algorithms, and allows the manipulation of sequences and 3D
12229 structures. The goal of the biojava project is to facilitate rapid
12230 application development for bioinformatics.
12232 This package provides the core libraries.")
12233 (license license:lgpl2.1+)))
12235 (define-public java-biojava-phylo
12236 (package (inherit java-biojava-core)
12237 (name "java-biojava-phylo")
12238 (build-system ant-build-system)
12241 #:jar-name "biojava-phylo.jar"
12242 #:source-dir "biojava-phylo/src/main/java/"
12243 #:test-dir "biojava-phylo/src/test"
12245 (modify-phases %standard-phases
12246 (add-before 'build 'copy-resources
12248 (copy-recursively "biojava-phylo/src/main/resources"
12251 (add-before 'check 'copy-test-resources
12253 (copy-recursively "biojava-phylo/src/test/resources"
12254 "build/test-classes")
12257 `(("java-log4j-api" ,java-log4j-api)
12258 ("java-log4j-core" ,java-log4j-core)
12259 ("java-slf4j-api" ,java-slf4j-api)
12260 ("java-slf4j-simple" ,java-slf4j-simple)
12261 ("java-biojava-core" ,java-biojava-core)
12262 ("java-forester" ,java-forester)))
12264 `(("java-junit" ,java-junit)
12265 ("java-hamcrest-core" ,java-hamcrest-core)))
12266 (home-page "http://biojava.org")
12267 (synopsis "Biojava interface to the forester phylogenomics library")
12268 (description "The phylo module provides a biojava interface layer to the
12269 forester phylogenomics library for constructing phylogenetic trees.")))
12271 (define-public java-biojava-alignment
12272 (package (inherit java-biojava-core)
12273 (name "java-biojava-alignment")
12274 (build-system ant-build-system)
12277 #:jar-name "biojava-alignment.jar"
12278 #:source-dir "biojava-alignment/src/main/java/"
12279 #:test-dir "biojava-alignment/src/test"
12281 (modify-phases %standard-phases
12282 (add-before 'build 'copy-resources
12284 (copy-recursively "biojava-alignment/src/main/resources"
12287 (add-before 'check 'copy-test-resources
12289 (copy-recursively "biojava-alignment/src/test/resources"
12290 "build/test-classes")
12293 `(("java-log4j-api" ,java-log4j-api)
12294 ("java-log4j-core" ,java-log4j-core)
12295 ("java-slf4j-api" ,java-slf4j-api)
12296 ("java-slf4j-simple" ,java-slf4j-simple)
12297 ("java-biojava-core" ,java-biojava-core)
12298 ("java-biojava-phylo" ,java-biojava-phylo)
12299 ("java-forester" ,java-forester)))
12301 `(("java-junit" ,java-junit)
12302 ("java-hamcrest-core" ,java-hamcrest-core)))
12303 (home-page "http://biojava.org")
12304 (synopsis "Biojava API for genetic sequence alignment")
12305 (description "The alignment module of BioJava provides an API that
12309 @item implementations of dynamic programming algorithms for sequence
12311 @item reading and writing of popular alignment file formats;
12312 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12315 (define-public java-biojava-core-4.0
12316 (package (inherit java-biojava-core)
12317 (name "java-biojava-core")
12321 (uri (git-reference
12322 (url "https://github.com/biojava/biojava")
12323 (commit (string-append "biojava-" version))))
12324 (file-name (string-append name "-" version "-checkout"))
12327 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12329 (define-public java-biojava-phylo-4.0
12330 (package (inherit java-biojava-core-4.0)
12331 (name "java-biojava-phylo")
12332 (build-system ant-build-system)
12335 #:jar-name "biojava-phylo.jar"
12336 #:source-dir "biojava-phylo/src/main/java/"
12337 #:test-dir "biojava-phylo/src/test"
12339 (modify-phases %standard-phases
12340 (add-before 'build 'copy-resources
12342 (copy-recursively "biojava-phylo/src/main/resources"
12345 (add-before 'check 'copy-test-resources
12347 (copy-recursively "biojava-phylo/src/test/resources"
12348 "build/test-classes")
12351 `(("java-log4j-api" ,java-log4j-api)
12352 ("java-log4j-core" ,java-log4j-core)
12353 ("java-slf4j-api" ,java-slf4j-api)
12354 ("java-slf4j-simple" ,java-slf4j-simple)
12355 ("java-biojava-core" ,java-biojava-core-4.0)
12356 ("java-forester" ,java-forester-1.005)))
12358 `(("java-junit" ,java-junit)
12359 ("java-hamcrest-core" ,java-hamcrest-core)))
12360 (home-page "http://biojava.org")
12361 (synopsis "Biojava interface to the forester phylogenomics library")
12362 (description "The phylo module provides a biojava interface layer to the
12363 forester phylogenomics library for constructing phylogenetic trees.")))
12365 (define-public java-biojava-alignment-4.0
12366 (package (inherit java-biojava-core-4.0)
12367 (name "java-biojava-alignment")
12368 (build-system ant-build-system)
12371 #:jar-name "biojava-alignment.jar"
12372 #:source-dir "biojava-alignment/src/main/java/"
12373 #:test-dir "biojava-alignment/src/test"
12375 (modify-phases %standard-phases
12376 (add-before 'build 'copy-resources
12378 (copy-recursively "biojava-alignment/src/main/resources"
12381 (add-before 'check 'copy-test-resources
12383 (copy-recursively "biojava-alignment/src/test/resources"
12384 "build/test-classes")
12387 `(("java-log4j-api" ,java-log4j-api)
12388 ("java-log4j-core" ,java-log4j-core)
12389 ("java-slf4j-api" ,java-slf4j-api)
12390 ("java-slf4j-simple" ,java-slf4j-simple)
12391 ("java-biojava-core" ,java-biojava-core-4.0)
12392 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12393 ("java-forester" ,java-forester-1.005)))
12395 `(("java-junit" ,java-junit)
12396 ("java-hamcrest-core" ,java-hamcrest-core)))
12397 (home-page "http://biojava.org")
12398 (synopsis "Biojava API for genetic sequence alignment")
12399 (description "The alignment module of BioJava provides an API that
12403 @item implementations of dynamic programming algorithms for sequence
12405 @item reading and writing of popular alignment file formats;
12406 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12409 (define-public dropseq-tools
12411 (name "dropseq-tools")
12416 (uri "http://mccarrolllab.com/download/1276/")
12417 (file-name (string-append "dropseq-tools-" version ".zip"))
12420 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12421 ;; Delete bundled libraries
12422 (modules '((guix build utils)))
12425 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12426 (delete-file-recursively "3rdParty")
12428 (build-system ant-build-system)
12430 `(#:tests? #f ; test data are not included
12431 #:test-target "test"
12432 #:build-target "all"
12433 #:source-dir "public/src/"
12436 (list (string-append "-Dpicard.executable.dir="
12437 (assoc-ref %build-inputs "java-picard")
12439 #:modules ((ice-9 match)
12442 (guix build java-utils)
12443 (guix build ant-build-system))
12445 (modify-phases %standard-phases
12446 ;; FIXME: fails with "java.io.FileNotFoundException:
12447 ;; /gnu/store/…-dropseq-tools-1.13/share/java/lib/biojava-alignment.jar"
12448 (delete 'generate-jar-indices)
12449 ;; All dependencies must be linked to "lib", because that's where
12450 ;; they will be searched for when the Class-Path property of the
12451 ;; manifest is computed.
12452 (add-after 'unpack 'record-references
12453 (lambda* (#:key inputs #:allow-other-keys)
12454 (mkdir-p "jar/lib")
12455 (let ((dirs (filter-map (match-lambda
12457 (if (and (string-prefix? "java-" name)
12458 (not (string=? name "java-testng")))
12461 (for-each (lambda (jar)
12462 (symlink jar (string-append "jar/lib/" (basename jar))))
12463 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12466 ;; There is no installation target
12468 (lambda* (#:key inputs outputs #:allow-other-keys)
12469 (let* ((out (assoc-ref outputs "out"))
12470 (bin (string-append out "/bin"))
12471 (share (string-append out "/share/java/"))
12472 (lib (string-append share "/lib/"))
12473 (scripts (list "BAMTagHistogram"
12474 "BAMTagofTagCounts"
12475 "BaseDistributionAtReadPosition"
12476 "CollapseBarcodesInPlace"
12477 "CollapseTagWithContext"
12479 "CreateIntervalsFiles"
12480 "DetectBeadSynthesisErrors"
12481 "DigitalExpression"
12482 "Drop-seq_alignment.sh"
12485 "GatherGeneGCLength"
12486 "GatherMolecularBarcodeDistributionByGene"
12487 "GatherReadQualityMetrics"
12490 "SelectCellsByNumTranscripts"
12491 "SingleCellRnaSeqMetricsCollector"
12492 "TagBamWithReadSequenceExtended"
12493 "TagReadWithGeneExon"
12494 "TagReadWithInterval"
12495 "TrimStartingSequence"
12496 "ValidateReference")))
12497 (for-each mkdir-p (list bin share lib))
12498 (install-file "dist/dropseq.jar" share)
12499 (for-each (lambda (script)
12500 (chmod script #o555)
12501 (install-file script bin))
12503 (substitute* (map (lambda (script)
12504 (string-append bin "/" script))
12506 (("^java") (which "java"))
12507 (("jar_deploy_dir=.*")
12508 (string-append "jar_deploy_dir=" share "\n"))))
12510 ;; FIXME: We do this after stripping jars because we don't want it to
12511 ;; copy all these jars and strip them. We only want to install
12512 ;; links. Arguably, this is a problem with the ant-build-system.
12513 (add-after 'strip-jar-timestamps 'install-links
12514 (lambda* (#:key outputs #:allow-other-keys)
12515 (let* ((out (assoc-ref outputs "out"))
12516 (share (string-append out "/share/java/"))
12517 (lib (string-append share "/lib/")))
12518 (for-each (lambda (jar)
12519 (symlink (readlink jar)
12520 (string-append lib (basename jar))))
12521 (find-files "jar/lib" "\\.jar$")))
12524 `(("jdk" ,icedtea-8)
12525 ("java-picard" ,java-picard-2.10.3)
12526 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12527 ("java-commons-math3" ,java-commons-math3)
12528 ("java-commons-jexl2" ,java-commons-jexl-2)
12529 ("java-commons-collections4" ,java-commons-collections4)
12530 ("java-commons-lang2" ,java-commons-lang)
12531 ("java-commons-io" ,java-commons-io)
12532 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12533 ("java-guava" ,java-guava)
12534 ("java-la4j" ,java-la4j)
12535 ("java-biojava-core" ,java-biojava-core-4.0)
12536 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12537 ("java-jdistlib" ,java-jdistlib)
12538 ("java-simple-xml" ,java-simple-xml)
12539 ("java-snakeyaml" ,java-snakeyaml)))
12542 ("java-testng" ,java-testng)))
12543 (home-page "http://mccarrolllab.com/dropseq/")
12544 (synopsis "Tools for Drop-seq analyses")
12545 (description "Drop-seq is a technology to enable biologists to
12546 analyze RNA expression genome-wide in thousands of individual cells at
12547 once. This package provides tools to perform Drop-seq analyses.")
12548 (license license:expat)))
12550 (define-public pigx-rnaseq
12552 (name "pigx-rnaseq")
12556 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12557 "releases/download/v" version
12558 "/pigx_rnaseq-" version ".tar.gz"))
12561 "19nhflzs6k5c7yhi7gkwggq237cjdd1s4b4qkj5x5fkwg0rhn33i"))))
12562 (build-system gnu-build-system)
12564 `(#:parallel-tests? #f ; not supported
12566 (modify-phases %standard-phases
12567 ;; "test.sh" runs STAR, which requires excessive amounts of memory.
12568 (add-after 'unpack 'disable-resource-intensive-test
12570 (substitute* "Makefile.in"
12571 (("(^ tests/test_trim_galore/test.sh).*" _ m) m)
12572 (("^ tests/test_multiqc/test.sh") "")
12573 (("^ test.sh") ""))
12576 `(("coreutils" ,coreutils)
12579 ("snakemake" ,snakemake)
12581 ("multiqc" ,multiqc)
12583 ("trim-galore" ,trim-galore)
12585 ("samtools" ,samtools)
12586 ("r-minimal" ,r-minimal)
12587 ("r-rmarkdown" ,r-rmarkdown)
12588 ("r-ggplot2" ,r-ggplot2)
12589 ("r-ggrepel" ,r-ggrepel)
12590 ("r-gprofiler" ,r-gprofiler)
12591 ("r-deseq2" ,r-deseq2)
12593 ("r-knitr" ,r-knitr)
12594 ("r-pheatmap" ,r-pheatmap)
12595 ("r-corrplot" ,r-corrplot)
12596 ("r-reshape2" ,r-reshape2)
12597 ("r-plotly" ,r-plotly)
12598 ("r-scales" ,r-scales)
12599 ("r-summarizedexperiment" ,r-summarizedexperiment)
12600 ("r-crosstalk" ,r-crosstalk)
12601 ("r-tximport" ,r-tximport)
12602 ("r-rtracklayer" ,r-rtracklayer)
12603 ("r-rjson" ,r-rjson)
12605 ("ghc-pandoc" ,ghc-pandoc)
12606 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12607 ("python-wrapper" ,python-wrapper)
12608 ("python-pyyaml" ,python-pyyaml)))
12609 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12610 (synopsis "Analysis pipeline for RNA sequencing experiments")
12611 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
12612 reporting for RNA sequencing experiments. It is easy to use and produces high
12613 quality reports. The inputs are reads files from the sequencing experiment,
12614 and a configuration file which describes the experiment. In addition to
12615 quality control of the experiment, the pipeline produces a differential
12616 expression report comparing samples in an easily configurable manner.")
12617 (license license:gpl3+)))
12619 (define-public pigx-chipseq
12621 (name "pigx-chipseq")
12625 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
12626 "releases/download/v" version
12627 "/pigx_chipseq-" version ".tar.gz"))
12630 "0akbxdmsjsq5fzbwaap04hqjpsfgv1l6yrc2pwgbya1xgqvcq6vy"))))
12631 (build-system gnu-build-system)
12632 ;; parts of the tests rely on access to the network
12633 (arguments '(#:tests? #f))
12636 ("coreutils" ,coreutils)
12637 ("r-minimal" ,r-minimal)
12638 ("r-argparser" ,r-argparser)
12639 ("r-biocparallel" ,r-biocparallel)
12640 ("r-biostrings" ,r-biostrings)
12641 ("r-chipseq" ,r-chipseq)
12642 ("r-data-table" ,r-data-table)
12643 ("r-dplyr" ,r-dplyr)
12644 ("r-genomation" ,r-genomation)
12645 ("r-genomicalignments" ,r-genomicalignments)
12646 ("r-genomicranges" ,r-genomicranges)
12647 ("r-rsamtools" ,r-rsamtools)
12648 ("r-rtracklayer" ,r-rtracklayer)
12649 ("r-s4vectors" ,r-s4vectors)
12650 ("r-stringr" ,r-stringr)
12651 ("r-tibble" ,r-tibble)
12652 ("r-tidyr" ,r-tidyr)
12653 ("r-jsonlite" ,r-jsonlite)
12654 ("r-heatmaply" ,r-heatmaply)
12655 ("r-htmlwidgets" ,r-htmlwidgets)
12656 ("r-ggplot2" ,r-ggplot2)
12657 ("r-plotly" ,r-plotly)
12658 ("r-rmarkdown" ,r-rmarkdown)
12659 ("python-wrapper" ,python-wrapper)
12660 ("python-pyyaml" ,python-pyyaml)
12661 ("python-magic" ,python-magic)
12662 ("python-xlrd" ,python-xlrd)
12663 ("trim-galore" ,trim-galore)
12665 ("multiqc" ,multiqc)
12667 ("ghc-pandoc" ,ghc-pandoc)
12668 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12672 ("snakemake" ,snakemake)
12673 ("samtools" ,samtools)
12674 ("bedtools" ,bedtools)
12675 ("kentutils" ,kentutils)))
12677 `(("python-pytest" ,python-pytest)))
12678 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12679 (synopsis "Analysis pipeline for ChIP sequencing experiments")
12680 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
12681 calling and reporting for ChIP sequencing experiments. It is easy to use and
12682 produces high quality reports. The inputs are reads files from the sequencing
12683 experiment, and a configuration file which describes the experiment. In
12684 addition to quality control of the experiment, the pipeline enables to set up
12685 multiple peak calling analysis and allows the generation of a UCSC track hub
12686 in an easily configurable manner.")
12687 (license license:gpl3+)))
12689 (define-public pigx-bsseq
12691 (name "pigx-bsseq")
12695 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
12696 "releases/download/v" version
12697 "/pigx_bsseq-" version ".tar.gz"))
12700 "0l97wvkq4diq8lcarraj33bby1zzf0w804jwi8mlc5qddp8idwhy"))))
12701 (build-system gnu-build-system)
12704 (modify-phases %standard-phases
12705 (add-before 'check 'set-timezone
12706 ;; The readr package is picky about timezones.
12707 (lambda* (#:key inputs #:allow-other-keys)
12708 (setenv "TZ" "UTC+1")
12710 (string-append (assoc-ref inputs "tzdata")
12711 "/share/zoneinfo"))
12714 `(("tzdata" ,tzdata)))
12716 `(("coreutils" ,coreutils)
12719 ("r-minimal" ,r-minimal)
12720 ("r-annotationhub" ,r-annotationhub)
12722 ("r-genomation" ,r-genomation)
12723 ("r-methylkit" ,r-methylkit)
12724 ("r-rtracklayer" ,r-rtracklayer)
12725 ("r-rmarkdown" ,r-rmarkdown)
12726 ("r-bookdown" ,r-bookdown)
12727 ("r-ggplot2" ,r-ggplot2)
12728 ("r-ggbio" ,r-ggbio)
12729 ("ghc-pandoc" ,ghc-pandoc)
12730 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12731 ("python-wrapper" ,python-wrapper)
12732 ("python-pyyaml" ,python-pyyaml)
12733 ("snakemake" ,snakemake)
12734 ("bismark" ,bismark)
12737 ("trim-galore" ,trim-galore)
12738 ("cutadapt" ,cutadapt)
12739 ("samtools" ,samtools)))
12740 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12741 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
12742 (description "PiGx BSseq is a data processing pipeline for raw fastq read
12743 data of bisulfite experiments; it produces reports on aggregate methylation
12744 and coverage and can be used to produce information on differential
12745 methylation and segmentation.")
12746 (license license:gpl3+)))
12748 (define-public pigx-scrnaseq
12750 (name "pigx-scrnaseq")
12754 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/"
12755 "releases/download/v" version
12756 "/pigx_scrnaseq-" version ".tar.gz"))
12759 "0zv0sc5amivxhb95vx2gfx6l9bh7n80fh7h47dalnwxxnfvnzai4"))))
12760 (build-system gnu-build-system)
12762 `(#:configure-flags
12763 (list (string-append "PICARDJAR=" (assoc-ref %build-inputs "java-picard")
12764 "/share/java/picard.jar")
12765 (string-append "DROPSEQJAR=" (assoc-ref %build-inputs "dropseq-tools")
12766 "/share/java/dropseq.jar"))))
12768 `(("coreutils" ,coreutils)
12770 ("dropseq-tools" ,dropseq-tools)
12772 ("java-picard" ,java-picard-2.10.3) ; same as for dropseq
12773 ("java" ,icedtea-8)
12774 ("python-wrapper" ,python-wrapper)
12775 ("python-pyyaml" ,python-pyyaml)
12776 ("python-pandas" ,python-pandas)
12777 ("python-magic" ,python-magic)
12778 ("python-numpy" ,python-numpy)
12779 ("python-loompy" ,python-loompy-for-pigx-scrnaseq)
12780 ("ghc-pandoc" ,ghc-pandoc)
12781 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12782 ("samtools" ,samtools)
12783 ("snakemake" ,snakemake)
12785 ("r-minimal" ,r-minimal)
12786 ("r-argparser" ,r-argparser)
12787 ("r-cowplot" ,r-cowplot)
12788 ("r-data-table" ,r-data-table)
12789 ("r-delayedarray" ,r-delayedarray)
12790 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
12791 ("r-dplyr" ,r-dplyr)
12792 ("r-dropbead" ,r-dropbead)
12794 ("r-genomicalignments" ,r-genomicalignments)
12795 ("r-genomicfiles" ,r-genomicfiles)
12796 ("r-genomicranges" ,r-genomicranges)
12797 ("r-ggplot2" ,r-ggplot2)
12798 ("r-hdf5array" ,r-hdf5array)
12799 ("r-pheatmap" ,r-pheatmap)
12800 ("r-rmarkdown" ,r-rmarkdown)
12801 ("r-rsamtools" ,r-rsamtools)
12802 ("r-rtracklayer" ,r-rtracklayer)
12803 ("r-rtsne" ,r-rtsne)
12804 ("r-scater" ,r-scater)
12805 ("r-scran" ,r-scran)
12806 ("r-singlecellexperiment" ,r-singlecellexperiment)
12807 ("r-stringr" ,r-stringr)
12808 ("r-yaml" ,r-yaml)))
12809 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12810 (synopsis "Analysis pipeline for single-cell RNA sequencing experiments")
12811 (description "PiGX scRNAseq is an analysis pipeline for preprocessing and
12812 quality control for single cell RNA sequencing experiments. The inputs are
12813 read files from the sequencing experiment, and a configuration file which
12814 describes the experiment. It produces processed files for downstream analysis
12815 and interactive quality reports. The pipeline is designed to work with UMI
12817 (license license:gpl3+)))
12819 (define-public pigx
12825 (uri (string-append "https://github.com/BIMSBbioinfo/pigx/"
12826 "releases/download/v" version
12827 "/pigx-" version ".tar.gz"))
12830 "1i5njdy1clj5ncw45d16p7mwmqvb1ilikl9n797pxklc3f4s7mq7"))))
12831 (build-system gnu-build-system)
12833 `(("python" ,python)
12834 ("pigx-bsseq" ,pigx-bsseq)
12835 ("pigx-chipseq" ,pigx-chipseq)
12836 ("pigx-rnaseq" ,pigx-rnaseq)
12837 ("pigx-scrnaseq" ,pigx-scrnaseq)))
12838 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12839 (synopsis "Analysis pipelines for genomics")
12840 (description "PiGx is a collection of genomics pipelines. It includes the
12841 following pipelines:
12844 @item PiGx BSseq for raw fastq read data of bisulfite experiments
12845 @item PiGx RNAseq for RNAseq samples
12846 @item PiGx scRNAseq for single cell dropseq analysis
12847 @item PiGx ChIPseq for reads from ChIPseq experiments
12850 All pipelines are easily configured with a simple sample sheet and a
12851 descriptive settings file. The result is a set of comprehensive, interactive
12852 HTML reports with interesting findings about your samples.")
12853 (license license:gpl3+)))
12855 (define-public genrich
12861 (uri (git-reference
12862 (url "https://github.com/jsh58/Genrich.git")
12863 (commit (string-append "v" version))))
12866 "0x0q6z0208n3cxzqjla4rgjqpyqgwpmz27852lcvzkzaigymq4zp"))))
12867 (build-system gnu-build-system)
12869 `(#:tests? #f ; there are none
12871 (modify-phases %standard-phases
12872 (delete 'configure)
12874 (lambda* (#:key outputs #:allow-other-keys)
12875 (install-file "Genrich" (string-append (assoc-ref outputs "out") "/bin"))
12879 (home-page "https://github.com/jsh58/Genrich")
12880 (synopsis "Detecting sites of genomic enrichment")
12881 (description "Genrich is a peak-caller for genomic enrichment
12882 assays (e.g. ChIP-seq, ATAC-seq). It analyzes alignment files generated
12883 following the assay and produces a file detailing peaks of significant
12885 (license license:expat)))
12887 (define-public mantis
12888 (let ((commit "4ffd171632c2cb0056a86d709dfd2bf21bc69b84")
12892 (version (git-version "0" revision commit))
12895 (uri (git-reference
12896 (url "https://github.com/splatlab/mantis.git")
12898 (file-name (git-file-name name version))
12901 "0iqbr0dhmlc8mzpirmm2s4pkzkwdgrcx50yx6cv3wlr2qi064p55"))))
12902 (build-system cmake-build-system)
12903 (arguments '(#:tests? #f)) ; there are none
12905 `(("sdsl-lite" ,sdsl-lite)
12906 ("openssl" ,openssl)
12908 (home-page "https://github.com/splatlab/mantis")
12909 (synopsis "Large-scale sequence-search index data structure")
12910 (description "Mantis is a space-efficient data structure that can be
12911 used to index thousands of raw-read genomics experiments and facilitate
12912 large-scale sequence searches on those experiments. Mantis uses counting
12913 quotient filters instead of Bloom filters, enabling rapid index builds and
12914 queries, small indexes, and exact results, i.e., no false positives or
12915 negatives. Furthermore, Mantis is also a colored de Bruijn graph
12916 representation, so it supports fast graph traversal and other topological
12917 analyses in addition to large-scale sequence-level searches.")
12918 ;; uses __uint128_t and inline assembly
12919 (supported-systems '("x86_64-linux"))
12920 (license license:bsd-3))))
12922 (define-public r-diversitree
12924 (name "r-diversitree")
12929 (uri (cran-uri "diversitree" version))
12932 "1jqfjmmaigq581l4zxysmkhld0xv6izlbr1hihf9zplkix36majc"))))
12933 (build-system r-build-system)
12935 `(("gfortran" ,gfortran)))
12936 (inputs `(("fftw" ,fftw) ("gsl" ,gsl)))
12939 ("r-desolve" ,r-desolve)
12941 ("r-subplex" ,r-subplex)))
12942 (home-page "https://www.zoology.ubc.ca/prog/diversitree")
12943 (synopsis "Comparative 'phylogenetic' analyses of diversification")
12944 (description "This package contains a number of comparative \"phylogenetic\"
12945 methods, mostly focusing on analysing diversification and character evolution.
12946 Contains implementations of \"BiSSE\" (Binary State Speciation and Extinction)
12947 and its unresolved tree extensions, \"MuSSE\" (Multiple State Speciation and
12948 Extinction), \"QuaSSE\", \"GeoSSE\", and \"BiSSE-ness\" Other included methods
12949 include Markov models of discrete and continuous trait evolution and constant
12950 rate speciation and extinction.")
12951 (license license:gpl2+)))
12953 (define-public sjcount
12954 ;; There is no tag for version 3.2, nor is there a release archive.
12955 (let ((commit "292d3917cadb3f6834c81e509c30e61cd7ead6e5")
12959 (version (git-version "3.2" revision commit))
12962 (uri (git-reference
12963 (url "https://github.com/pervouchine/sjcount-full.git")
12965 (file-name (string-append name "-" version "-checkout"))
12968 "0gdgj35j249f04rqgq8ymcc1xg1vi9kzbajnjqpaq2wpbh8bl234"))))
12969 (build-system gnu-build-system)
12971 `(#:tests? #f ; requires a 1.4G test file
12973 (list (string-append "SAMTOOLS_DIR="
12974 (assoc-ref %build-inputs "samtools")
12977 (modify-phases %standard-phases
12978 (replace 'configure
12979 (lambda* (#:key inputs #:allow-other-keys)
12980 (substitute* "makefile"
12981 (("-I \\$\\{SAMTOOLS_DIR\\}")
12982 (string-append "-I" (assoc-ref inputs "samtools")
12983 "/include/samtools"))
12984 (("-lz ") "-lz -lpthread "))
12987 (lambda* (#:key outputs #:allow-other-keys)
12988 (for-each (lambda (tool)
12990 (string-append (assoc-ref outputs "out")
12992 '("j_count" "b_count" "sjcount"))
12995 `(("samtools" ,samtools-0.1)
12997 (home-page "https://github.com/pervouchine/sjcount-full/")
12998 (synopsis "Annotation-agnostic splice junction counting pipeline")
12999 (description "Sjcount is a utility for fast quantification of splice
13000 junctions in RNA-seq data. It is annotation-agnostic and offset-aware. This
13001 version does count multisplits.")
13002 (license license:gpl3+))))
13004 (define-public minimap2
13011 (uri (string-append "https://github.com/lh3/minimap2/"
13012 "releases/download/v" version "/"
13013 "minimap2-" version ".tar.bz2"))
13016 "080w9066irkbhbyr4nmf19pzkdd2s4v31hpzlajgq2y0drr6zcsj"))))
13017 (build-system gnu-build-system)
13019 `(#:tests? #f ; there are none
13022 (let ((system ,(or (%current-target-system)
13023 (%current-system))))
13025 ((string-prefix? "x86_64" system)
13027 ((or (string-prefix? "armhf" system)
13028 (string-prefix? "aarch64" system))
13030 (_ "sse2only=1"))))
13032 (modify-phases %standard-phases
13033 (delete 'configure)
13035 (lambda* (#:key outputs #:allow-other-keys)
13036 (let* ((out (assoc-ref outputs "out"))
13037 (bin (string-append out "/bin"))
13038 (man (string-append out "/share/man/man1")))
13039 (install-file "minimap2" bin)
13041 (install-file "minimap2.1" man))
13045 (home-page "https://lh3.github.io/minimap2/")
13046 (synopsis "Pairwise aligner for genomic and spliced nucleotide sequences")
13047 (description "Minimap2 is a versatile sequence alignment program that
13048 aligns DNA or mRNA sequences against a large reference database. Typical use
13052 @item mapping PacBio or Oxford Nanopore genomic reads to the human genome;
13053 @item finding overlaps between long reads with error rate up to ~15%;
13054 @item splice-aware alignment of PacBio Iso-Seq or Nanopore cDNA or Direct RNA
13055 reads against a reference genome;
13056 @item aligning Illumina single- or paired-end reads;
13057 @item assembly-to-assembly alignment;
13058 @item full-genome alignment between two closely related species with
13059 divergence below ~15%.
13061 (license license:expat)))
13063 (define-public r-circus
13070 (uri (git-reference
13071 (url "https://github.com/BIMSBbioinfo/ciRcus.git")
13072 (commit (string-append "v" version))))
13073 (file-name (git-file-name name version))
13076 "0jhjn3ilb057hbf6yzrihj13ifxxs32y7nkby8l3lkm28dg4p97h"))))
13077 (build-system r-build-system)
13079 `(("r-annotationdbi" ,r-annotationdbi)
13080 ("r-annotationhub" ,r-annotationhub)
13081 ("r-biomart" ,r-biomart)
13082 ("r-data-table" ,r-data-table)
13084 ("r-genomicfeatures" ,r-genomicfeatures)
13085 ("r-genomicranges" ,r-genomicranges)
13086 ("r-ggplot2" ,r-ggplot2)
13088 ("r-iranges" ,r-iranges)
13089 ("r-rcolorbrewer" ,r-rcolorbrewer)
13090 ("r-rmysql" ,r-rmysql)
13091 ("r-s4vectors" ,r-s4vectors)
13092 ("r-stringr" ,r-stringr)
13093 ("r-summarizedexperiment" ,r-summarizedexperiment)))
13095 `(("r-knitr" ,r-knitr)))
13096 (home-page "https://github.com/BIMSBbioinfo/ciRcus")
13097 (synopsis "Annotation, analysis and visualization of circRNA data")
13098 (description "Circus is an R package for annotation, analysis and
13099 visualization of circRNA data. Users can annotate their circRNA candidates
13100 with host genes, gene featrues they are spliced from, and discriminate between
13101 known and yet unknown splice junctions. Circular-to-linear ratios of circRNAs
13102 can be calculated, and a number of descriptive plots easily generated.")
13103 (license license:artistic2.0)))
13105 (define-public gffread
13106 ;; We cannot use the tagged release because it is not in sync with gclib.
13107 ;; See https://github.com/gpertea/gffread/issues/26
13108 (let ((commit "ba7535fcb3cea55a6e5a491d916e93b454e87fd0")
13112 (version (git-version "0.9.12" revision commit))
13116 (uri (git-reference
13117 (url "https://github.com/gpertea/gffread.git")
13119 (file-name (git-file-name name version))
13122 "1dl2nbcg96lxpd0drg48ssa8343nf7pw9s9mkrc4mjjmfwsin3ki"))))
13123 (build-system gnu-build-system)
13125 `(#:tests? #f ; no check target
13127 (list "GCLDIR=gclib")
13129 (modify-phases %standard-phases
13130 (delete 'configure)
13131 (add-after 'unpack 'copy-gclib-source
13132 (lambda* (#:key inputs #:allow-other-keys)
13134 (copy-recursively (assoc-ref inputs "gclib-source") "gclib")
13136 ;; There is no install target
13138 (lambda* (#:key outputs #:allow-other-keys)
13139 (let* ((out (assoc-ref outputs "out"))
13140 (bin (string-append out "/bin")))
13141 (install-file "gffread" bin))
13145 ,(let ((version "0.10.3")
13146 (commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13150 (uri (git-reference
13151 (url "https://github.com/gpertea/gclib.git")
13153 (file-name (git-file-name "gclib" version))
13156 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13157 (home-page "https://github.com/gpertea/gffread/")
13158 (synopsis "Parse and convert GFF/GTF files")
13160 "This package provides a GFF/GTF file parsing utility providing format
13161 conversions, region filtering, FASTA sequence extraction and more.")
13162 ;; gffread is under Expat, but gclib is under Artistic 2.0
13163 (license (list license:expat
13164 license:artistic2.0)))))
13166 (define-public find-circ
13167 ;; The last release was in 2015. The license was clarified in 2017, so we
13168 ;; take the latest commit.
13169 (let ((commit "8655dca54970fcf7e92e22fbf57e1188724dda7d")
13173 (version (git-version "1.2" revision commit))
13177 (uri (git-reference
13178 (url "https://github.com/marvin-jens/find_circ.git")
13180 (file-name (git-file-name name version))
13183 "0p77pbqbclqr4srms34y1b9b4njybfpjiknc11ki84f3p8skb3cg"))))
13184 (build-system gnu-build-system)
13186 `(#:tests? #f ; there are none
13188 ;; There is no actual build system.
13189 (modify-phases %standard-phases
13190 (delete 'configure)
13193 (lambda* (#:key outputs #:allow-other-keys)
13194 (let* ((out (assoc-ref outputs "out"))
13195 (bin (string-append out "/bin"))
13196 (path (getenv "PYTHONPATH")))
13197 (for-each (lambda (script)
13198 (install-file script bin)
13199 (wrap-program (string-append bin "/" script)
13200 `("PYTHONPATH" ":" prefix (,path))))
13205 "unmapped2anchors.py")))
13208 `(("python2" ,python-2)
13209 ("python2-pysam" ,python2-pysam)
13210 ("python2-numpy" ,python2-numpy)))
13211 (home-page "https://github.com/marvin-jens/find_circ")
13212 (synopsis "circRNA detection from RNA-seq reads")
13213 (description "This package provides tools to detect head-to-tail
13214 spliced (back-spliced) sequencing reads, indicative of circular RNA (circRNA)
13216 (license license:gpl3))))
13218 (define-public python-scanpy
13220 (name "python-scanpy")
13222 ;; Fetch from git because the pypi tarball does not include tests.
13226 (uri (git-reference
13227 (url "https://github.com/theislab/scanpy.git")
13229 (file-name (git-file-name name version))
13232 "0zn6x6c0cnm1a20i6isigwb51g3pr9zpjk8r1minjqnxi5yc9pm4"))))
13233 (build-system python-build-system)
13236 (modify-phases %standard-phases
13238 (lambda* (#:key inputs #:allow-other-keys)
13239 ;; These tests require Internet access.
13240 (delete-file-recursively "scanpy/tests/notebooks")
13241 (delete-file "scanpy/tests/test_clustering.py")
13243 ;; TODO: I can't get the plotting tests to work, even with Xvfb.
13244 (delete-file "scanpy/tests/test_plotting.py")
13245 (delete-file "scanpy/tests/test_preprocessing.py")
13246 (delete-file "scanpy/tests/test_read_10x.py")
13248 (setenv "PYTHONPATH"
13249 (string-append (getcwd) ":"
13250 (getenv "PYTHONPATH")))
13254 `(("python-anndata" ,python-anndata)
13255 ("python-h5py" ,python-h5py)
13256 ("python-igraph" ,python-igraph)
13257 ("python-joblib" ,python-joblib)
13258 ("python-louvain" ,python-louvain)
13259 ("python-matplotlib" ,python-matplotlib)
13260 ("python-natsort" ,python-natsort)
13261 ("python-networkx" ,python-networkx)
13262 ("python-numba" ,python-numba)
13263 ("python-pandas" ,python-pandas)
13264 ("python-scikit-learn" ,python-scikit-learn)
13265 ("python-scipy" ,python-scipy)
13266 ("python-seaborn" ,python-seaborn)
13267 ("python-statsmodels" ,python-statsmodels)
13268 ("python-tables" ,python-tables)))
13270 `(("python-pytest" ,python-pytest)))
13271 (home-page "https://github.com/theislab/scanpy")
13272 (synopsis "Single-Cell Analysis in Python.")
13273 (description "Scanpy is a scalable toolkit for analyzing single-cell gene
13274 expression data. It includes preprocessing, visualization, clustering,
13275 pseudotime and trajectory inference and differential expression testing. The
13276 Python-based implementation efficiently deals with datasets of more than one
13278 (license license:bsd-3)))
13280 (define-public python-bbknn
13282 (name "python-bbknn")
13287 (uri (pypi-uri "bbknn" version))
13290 "1qgdganvj3lyxj84v7alm23b9vqhwpn8z0115qndpnpy90qxynwz"))))
13291 (build-system python-build-system)
13293 `(("python-annoy" ,python-annoy)
13294 ("python-cython" ,python-cython)
13295 ("python-faiss" ,python-faiss)
13296 ("python-numpy" ,python-numpy)
13297 ("python-scanpy" ,python-scanpy)))
13298 (home-page "https://github.com/Teichlab/bbknn")
13299 (synopsis "Batch balanced KNN")
13300 (description "BBKNN is a batch effect removal tool that can be directly
13301 used in the Scanpy workflow. It serves as an alternative to
13302 @code{scanpy.api.pp.neighbors()}, with both functions creating a neighbour
13303 graph for subsequent use in clustering, pseudotime and UMAP visualisation. If
13304 technical artifacts are present in the data, they will make it challenging to
13305 link corresponding cell types across different batches. BBKNN actively
13306 combats this effect by splitting your data into batches and finding a smaller
13307 number of neighbours for each cell within each of the groups. This helps
13308 create connections between analogous cells in different batches without
13309 altering the counts or PCA space.")
13310 (license license:expat)))
13312 (define-public gffcompare
13313 (let ((commit "be56ef4349ea3966c12c6397f85e49e047361c41")
13316 (name "gffcompare")
13317 (version (git-version "0.10.15" revision commit))
13321 (uri (git-reference
13322 (url "https://github.com/gpertea/gffcompare/")
13324 (file-name (git-file-name name version))
13326 (base32 "0cp5qpxdhw4mxpya5dld8wi3jk00zyklm6rcri426wydinrnfmkg"))))
13327 (build-system gnu-build-system)
13329 `(#:tests? #f ; no check target
13331 (modify-phases %standard-phases
13332 (delete 'configure)
13333 (add-before 'build 'copy-gclib-source
13334 (lambda* (#:key inputs #:allow-other-keys)
13337 (assoc-ref inputs "gclib-source") "../gclib")
13340 (lambda* (#:key outputs #:allow-other-keys)
13341 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
13342 (install-file "gffcompare" bin)
13345 `(("gclib-source" ; see 'README.md' of gffcompare
13346 ,(let ((commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13349 (version (git-version "0.10.3" revision commit)))
13352 (uri (git-reference
13353 (url "https://github.com/gpertea/gclib/")
13355 (file-name (git-file-name name version))
13357 (base32 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13358 (home-page "https://github.com/gpertea/gffcompare/")
13359 (synopsis "Tool for comparing or classifing transcripts of RNA-Seq")
13361 "@code{gffcompare} is a tool that can:
13363 @item compare and evaluate the accuracy of RNA-Seq transcript assemblers
13364 (Cufflinks, Stringtie);
13365 @item collapse (merge) duplicate transcripts from multiple GTF/GFF3 files (e.g.
13366 resulted from assembly of different samples);
13367 @item classify transcripts from one or multiple GTF/GFF3 files as they relate to
13368 reference transcripts provided in a annotation file (also in GTF/GFF3 format).
13372 license:expat ;license for gffcompare
13373 license:artistic2.0))))) ;license for gclib
13375 (define-public python-intervaltree
13377 (name "python-intervaltree")
13382 (uri (pypi-uri "intervaltree" version))
13385 "02w191m9zxkcjqr1kv2slxvhymwhj3jnsyy3a28b837pi15q19dc"))))
13386 (build-system python-build-system)
13387 ;; FIXME: error when collecting tests
13388 (arguments '(#:tests? #f))
13390 `(("python-sortedcontainers" ,python-sortedcontainers)))
13392 `(("python-pytest" ,python-pytest)))
13393 (home-page "https://github.com/chaimleib/intervaltree")
13394 (synopsis "Editable interval tree data structure")
13396 "This package provides a mutable, self-balancing interval tree
13397 implementation for Python. Queries may be by point, by range overlap, or by
13398 range envelopment. This library was designed to allow tagging text and time
13399 intervals, where the intervals include the lower bound but not the upper
13401 (license license:asl2.0)))
13403 (define-public python-pypairix
13405 (name "python-pypairix")
13410 (uri (pypi-uri "pypairix" version))
13413 "0zs92b74s5v4xy2h16s15f3z6l4nnbw8x8zyif7xx5xpafjn0xss"))))
13414 (build-system python-build-system)
13415 ;; FIXME: the tests fail because test.support cannot be loaded:
13416 ;; ImportError: cannot import name 'support'
13417 (arguments '(#:tests? #f))
13420 (home-page "https://github.com/4dn-dcic/pairix")
13421 (synopsis "Support for querying pairix-indexed bgzipped text files")
13423 "Pypairix is a Python module for fast querying on a pairix-indexed
13424 bgzipped text file that contains a pair of genomic coordinates per line.")
13425 (license license:expat)))
13427 (define-public python-pyfaidx
13429 (name "python-pyfaidx")
13430 (version "0.5.4.2")
13434 (uri (pypi-uri "pyfaidx" version))
13437 "0y5zyjksj1rdglj601xd2bbni5abhdh622y3ck76chyzxz9z4rx8"))))
13438 (build-system python-build-system)
13440 `(("python-setuptools" ,python-setuptools)
13441 ("python-six" ,python-six)))
13442 (home-page "http://mattshirley.com")
13443 (synopsis "Random access to fasta subsequences")
13445 "This package provides procedures for efficient pythonic random access to
13446 fasta subsequences.")
13447 (license license:bsd-3)))
13449 (define-public python-cooler
13451 (name "python-cooler")
13456 (uri (pypi-uri "cooler" version))
13459 "08k5nxnxa6qsbk15z5z0q01n28042k87wi4905hh95rzqib15mhx"))))
13460 (build-system python-build-system)
13462 `(("python-biopython" ,python-biopython)
13463 ("python-click" ,python-click)
13464 ("python-cytoolz" ,python-cytoolz)
13465 ("python-dask" ,python-dask)
13466 ("python-h5py" ,python-h5py)
13467 ("python-multiprocess" ,python-multiprocess)
13468 ("python-pandas" ,python-pandas)
13469 ("python-pyfaidx" ,python-pyfaidx)
13470 ("python-pypairix" ,python-pypairix)
13471 ("python-pysam" ,python-pysam)
13472 ("python-scipy" ,python-scipy)))
13474 `(("python-mock" ,python-mock)
13475 ("python-nose" ,python-nose)
13476 ("python-numpydoc" ,python-numpydoc)
13477 ("python-sphinx" ,python-sphinx)))
13478 (home-page "https://github.com/mirnylab/cooler")
13479 (synopsis "Sparse binary format for genomic interaction matrices")
13481 "Cooler is a support library for a sparse, compressed, binary persistent
13482 storage format, called @code{cool}, used to store genomic interaction data,
13483 such as Hi-C contact matrices.")
13484 (license license:bsd-3)))
13486 (define-public python-hicexplorer
13488 (name "python-hicexplorer")
13492 ;; The latest version is not available on Pypi.
13494 (uri (git-reference
13495 (url "https://github.com/deeptools/HiCExplorer.git")
13497 (file-name (git-file-name name version))
13500 "0q5gpbzmrkvygqgw524q36b4nrivcmyi5v194vsx0qw7b3gcmq08"))))
13501 (build-system python-build-system)
13504 (modify-phases %standard-phases
13505 (add-after 'unpack 'loosen-up-requirements
13507 (substitute* "setup.py"
13511 `(("python-biopython" ,python-biopython)
13512 ("python-configparser" ,python-configparser)
13513 ("python-cooler" ,python-cooler)
13514 ("python-future" ,python-future)
13515 ("python-intervaltree" ,python-intervaltree)
13516 ("python-jinja2" ,python-jinja2)
13517 ("python-matplotlib" ,python-matplotlib)
13518 ("python-numpy" ,python-numpy)
13519 ("python-pandas" ,python-pandas)
13520 ("python-pybigwig" ,python-pybigwig)
13521 ("python-pysam" ,python-pysam)
13522 ("python-scipy" ,python-scipy)
13523 ("python-six" ,python-six)
13524 ("python-tables" ,python-tables)
13525 ("python-unidecode" ,python-unidecode)))
13526 (home-page "http://hicexplorer.readthedocs.io")
13527 (synopsis "Process, analyze and visualize Hi-C data")
13529 "HiCExplorer is a powerful and easy to use set of tools to process,
13530 normalize and visualize Hi-C data. HiCExplorer facilitates the creation of
13531 contact matrices, correction of contacts, TAD detection, A/B compartments,
13532 merging, reordering or chromosomes, conversion from different formats
13533 including cooler and detection of long-range contacts. Moreover, it allows
13534 the visualization of multiple contact matrices along with other types of data
13535 like genes, compartments, ChIP-seq coverage tracks (and in general any type of
13536 genomic scores), long range contacts and the visualization of viewpoints.")
13537 (license license:gpl3)))
13539 (define-public python-pygenometracks
13541 (name "python-pygenometracks")
13546 (uri (pypi-uri "pyGenomeTracks" version))
13549 "1fws6bqsyy9kj3qiabhkqx4wd4i775gsxnhszqd3zg7w67sc1ic5"))))
13550 (build-system python-build-system)
13552 `(("python-configparser" ,python-configparser)
13553 ("python-future" ,python-future)
13554 ("python-hicexplorer" ,python-hicexplorer)
13555 ("python-intervaltree" ,python-intervaltree)
13556 ("python-matplotlib" ,python-matplotlib)
13557 ("python-numpy" ,python-numpy)
13558 ("python-pybigwig" ,python-pybigwig)))
13560 `(("python-pytest" ,python-pytest)))
13561 (home-page "https://pygenometracks.readthedocs.io")
13562 (synopsis "Program and library to plot beautiful genome browser tracks")
13564 "This package aims to produce high-quality genome browser tracks that
13565 are highly customizable. Currently, it is possible to plot: bigwig, bed (many
13566 options), bedgraph, links (represented as arcs), and Hi-C matrices.
13567 pyGenomeTracks can make plots with or without Hi-C data.")
13568 (license license:gpl3+)))
13570 (define-public python-hic2cool
13572 (name "python-hic2cool")
13577 (uri (pypi-uri "hic2cool" version))
13580 "0xy6mhfns2lzib1kcr6419jjp6pmh0qx8z8na55lmiwn0ds8q9cl"))))
13581 (build-system python-build-system)
13582 (arguments '(#:tests? #f)) ; no tests included
13584 `(("python-cooler" ,python-cooler)))
13585 (home-page "https://github.com/4dn-dcic/hic2cool")
13586 (synopsis "Converter for .hic and .cool files")
13588 "This package provides a converter between @code{.hic} files (from
13589 juicer) and single-resolution or multi-resolution @code{.cool} files (for
13590 cooler). Both @code{hic} and @code{cool} files describe Hi-C contact
13592 (license license:expat)))
13594 (define-public r-pore
13602 (string-append "mirror://sourceforge/rpore/" version
13603 "/poRe_" version ".tar.gz"))
13605 (base32 "0pih9nljbv8g4x8rkk29i7aqq681b782r5s5ynp4nw9yzqnmmksv"))))
13606 (properties `((upstream-name . "poRe")))
13607 (build-system r-build-system)
13609 `(("r-bit64" ,r-bit64)
13610 ("r-data-table" ,r-data-table)
13611 ("r-rhdf5" ,r-rhdf5)
13612 ("r-shiny" ,r-shiny)
13613 ("r-svdialogs" ,r-svdialogs)))
13614 (home-page "https://sourceforge.net/projects/rpore/")
13615 (synopsis "Visualize Nanopore sequencing data")
13617 "This package provides graphical user interfaces to organize and visualize Nanopore
13619 ;; This is free software but the license variant is unclear:
13620 ;; <https://github.com/mw55309/poRe_docs/issues/10>.
13621 (license license:bsd-3)))
13623 (define-public r-xbioc
13624 (let ((revision "1")
13625 (commit "f798c187e376fd1ba27abd559f47bbae7e3e466b"))
13628 (version (git-version "0.1.15" revision commit))
13631 (uri (git-reference
13632 (url "https://github.com/renozao/xbioc.git")
13634 (file-name (git-file-name name version))
13637 "03hffh2f6z71y6l6dqpa5cql3hdaw7zigdi8sm2dzgx379k9rgrr"))))
13638 (build-system r-build-system)
13640 `(("r-annotationdbi" ,r-annotationdbi)
13641 ("r-assertthat" ,r-assertthat)
13642 ("r-biobase" ,r-biobase)
13643 ("r-biocinstaller" ,r-biocinstaller)
13644 ("r-digest" ,r-digest)
13645 ("r-pkgmaker" ,r-pkgmaker)
13647 ("r-reshape2" ,r-reshape2)
13648 ("r-stringr" ,r-stringr)))
13649 (home-page "https://github.com/renozao/xbioc/")
13650 (synopsis "Extra base functions for Bioconductor")
13651 (description "This package provides extra utility functions to perform
13652 common tasks in the analysis of omics data, leveraging and enhancing features
13653 provided by Bioconductor packages.")
13654 (license license:gpl3+))))
13656 (define-public r-cssam
13657 (let ((revision "1")
13658 (commit "9ec58c982fa551af0d80b1a266890d92954833f2"))
13661 (version (git-version "1.4" revision commit))
13664 (uri (git-reference
13665 (url "https://github.com/shenorrLab/csSAM.git")
13667 (file-name (git-file-name name version))
13670 "128syf9v39gk0z3ip000qpsjbg6l1siyq6c8b0hz41dzg5achyb3"))))
13671 (build-system r-build-system)
13673 `(("r-formula" ,r-formula)
13674 ("r-ggplot2" ,r-ggplot2)
13675 ("r-pkgmaker" ,r-pkgmaker)
13677 ("r-rngtools" ,r-rngtools)
13678 ("r-scales" ,r-scales)))
13679 (home-page "https://github.com/shenorrLab/csSAM/")
13680 (synopsis "Cell type-specific statistical analysis of microarray")
13681 (description "This package implements the method csSAM that computes
13682 cell-specific differential expression from measured cell proportions using
13685 (license license:lgpl2.1+))))
13687 (define-public r-bseqsc
13688 (let ((revision "1")
13689 (commit "fef3f3e38dcf3df37103348b5780937982b43b98"))
13692 (version (git-version "1.0" revision commit))
13695 (uri (git-reference
13696 (url "https://github.com/shenorrLab/bseqsc.git")
13698 (file-name (git-file-name name version))
13701 "1prw13wa20f7wlc3gkkls66n1kxz8d28qrb8icfqdwdnnv8w5qg8"))))
13702 (build-system r-build-system)
13704 `(("r-abind" ,r-abind)
13705 ("r-annotationdbi" ,r-annotationdbi)
13706 ("r-biobase" ,r-biobase)
13707 ("r-cssam" ,r-cssam)
13708 ("r-dplyr" ,r-dplyr)
13709 ("r-e1071" ,r-e1071)
13710 ("r-edger" ,r-edger)
13711 ("r-ggplot2" ,r-ggplot2)
13713 ("r-openxlsx" ,r-openxlsx)
13714 ("r-pkgmaker" ,r-pkgmaker)
13716 ("r-preprocesscore" ,r-preprocesscore)
13717 ("r-rngtools" ,r-rngtools)
13718 ("r-scales" ,r-scales)
13719 ("r-stringr" ,r-stringr)
13720 ("r-xbioc" ,r-xbioc)))
13721 (home-page "https://github.com/shenorrLab/bseqsc")
13722 (synopsis "Deconvolution of bulk sequencing experiments using single cell data")
13723 (description "BSeq-sc is a bioinformatics analysis pipeline that
13724 leverages single-cell sequencing data to estimate cell type proportion and
13725 cell type-specific gene expression differences from RNA-seq data from bulk
13726 tissue samples. This is a companion package to the publication \"A
13727 single-cell transcriptomic map of the human and mouse pancreas reveals inter-
13728 and intra-cell population structure.\" Baron et al. Cell Systems (2016)
13729 @url{https://www.ncbi.nlm.nih.gov/pubmed/27667365}.")
13730 (license license:gpl2+))))
13732 (define-public porechop
13733 ;; The recommended way to install is to clone the git repository
13734 ;; https://github.com/rrwick/Porechop#installation
13735 (let ((commit "289d5dca4a5fc327f97b3f8cecb68ecaf1014861")
13739 (version (git-version "0.2.3" revision commit))
13743 (uri (git-reference
13744 (url "https://github.com/rrwick/Porechop.git")
13746 (file-name (git-file-name name version))
13748 (base32 "05ps43gig0d3ia9x5lj84lb00hbsl6ba9n7y7jz927npxbr2ym23"))))
13749 (build-system python-build-system)
13750 (home-page "https://github.com/rrwick/porechop")
13751 (synopsis "Finding, trimming or splitting adapters, in Oxford Nanopore reads")
13753 "The porechop package is a tool for finding and removing adapters from Oxford
13754 Nanopore reads. Adapters on the ends of reads are trimmed off, and when a read
13755 has an adapter in its middle, it is treated as chimeric and chopped into
13756 separate reads. Porechop performs thorough alignments to effectively find
13757 adapters, even at low sequence identity. Porechop also supports demultiplexing
13758 of Nanopore reads that were barcoded with the Native Barcoding Kit, PCR
13759 Barcoding Kit or Rapid Barcoding Kit.")
13760 (license license:gpl3+))))
13762 (define-public poretools
13763 ;; The latest release was in 2016 and the latest commit is from 2017
13764 ;; the recommended way to install is to clone the git repository
13765 ;; https://poretools.readthedocs.io/en/latest/content/installation.html
13766 (let ((commit "e426b1f09e86ac259a00c261c79df91510777407")
13770 (version (git-version "0.6.0" revision commit))
13774 (uri (git-reference
13775 (url "https://github.com/arq5x/poretools.git")
13777 (file-name (git-file-name name version))
13779 (base32 "0bglj833wxpp3cq430p1d3xp085ls221js2y90w7ir2x5ay8l7am"))))
13780 (build-system python-build-system)
13781 ;; requires python >=2.7, <3.0, and the same for python dependencies
13782 (arguments `(#:python ,python-2))
13786 `(("python-dateutil" ,python2-dateutil)
13787 ("python-h5py" ,python2-h5py)
13788 ("python-matplotlib" ,python2-matplotlib)
13789 ("python-pandas" ,python2-pandas)
13790 ("python-seaborn" ,python2-seaborn)))
13791 (home-page "https://poretools.readthedocs.io")
13792 (synopsis "Toolkit for working with nanopore sequencing data")
13794 "The MinION from Oxford Nanopore Technologies is a nanopore sequencer.
13795 This @code{poretools} package is a flexible toolkit for exploring datasets
13796 generated by nanopore sequencing devices for the purposes of quality control and
13797 downstream analysis. Poretools operates directly on the native FAST5, a variant
13798 of the Hierarchical Data Format (HDF5) standard.")
13799 (license license:expat))))
13801 (define-public r-absfiltergsea
13803 (name "r-absfiltergsea")
13808 (uri (cran-uri "AbsFilterGSEA" version))
13810 (base32 "15srxkxsvn38kd5frdrwfdf0ad8gskrd0h01wmdf9hglq8fjrp7w"))))
13811 (properties `((upstream-name . "AbsFilterGSEA")))
13812 (build-system r-build-system)
13814 `(("r-biobase" ,r-biobase)
13815 ("r-deseq" ,r-deseq)
13816 ("r-limma" ,r-limma)
13818 ("r-rcpparmadillo" ,r-rcpparmadillo)))
13819 (home-page "https://cran.r-project.org/web/packages/AbsFilterGSEA/")
13820 (synopsis "Improved false positive control of gene-permuting with absolute filtering")
13822 "This package provides a function that performs gene-permuting of a gene-set
13823 enrichment analysis (GSEA) calculation with or without the absolute filtering.
13824 Without filtering, users can perform (original) two-tailed or one-tailed
13826 (license license:gpl2)))
13828 (define-public jamm
13831 (version "1.0.7.5")
13835 (uri (git-reference
13836 (url "https://github.com/mahmoudibrahim/JAMM.git")
13837 (commit (string-append "JAMMv" version))))
13838 (file-name (git-file-name name version))
13841 "0ls889jcma1ch9h21jjhnkadgszgqj41842hhcjh6cg88f85qf3i"))))
13842 (build-system gnu-build-system)
13844 `(#:tests? #f ; there are none
13846 (modify-phases %standard-phases
13847 (delete 'configure)
13850 (lambda* (#:key inputs outputs #:allow-other-keys)
13851 (let* ((out (assoc-ref outputs "out"))
13852 (libexec (string-append out "/libexec/jamm"))
13853 (bin (string-append out "/bin")))
13854 (substitute* '("JAMM.sh"
13855 "SignalGenerator.sh")
13857 (string-append "sPath=\"" libexec "\"\n")))
13858 (for-each (lambda (file)
13859 (install-file file libexec))
13860 (list "bincalculator.r"
13872 (chmod script #o555)
13873 (install-file script bin)
13874 (wrap-program (string-append bin "/" script)
13875 `("PATH" ":" prefix
13876 (,(string-append (assoc-ref inputs "coreutils") "/bin")
13877 ,(string-append (assoc-ref inputs "gawk") "/bin")
13878 ,(string-append (assoc-ref inputs "perl") "/bin")
13879 ,(string-append (assoc-ref inputs "r-minimal") "/bin")))
13880 `("PERL5LIB" ":" prefix (,(getenv "PERL5LIB")))
13881 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
13882 (list "JAMM.sh" "SignalGenerator.sh")))
13886 ("coreutils" ,coreutils)
13889 ("r-minimal" ,r-minimal)
13890 ;;("r-parallel" ,r-parallel)
13891 ("r-signal" ,r-signal)
13892 ("r-mclust" ,r-mclust)))
13893 (home-page "https://github.com/mahmoudibrahim/JAMM")
13894 (synopsis "Peak finder for NGS datasets")
13896 "JAMM is a peak finder for next generation sequencing datasets (ChIP-Seq,
13897 ATAC-Seq, DNase-Seq, etc.) that can integrate replicates and assign peak
13898 boundaries accurately. JAMM is applicable to both broad and narrow
13900 (license license:gpl3+)))
13902 (define-public ngless
13909 (uri (git-reference
13910 (url "https://gitlab.com/ngless/ngless.git")
13911 (commit (string-append "v" version))))
13912 (file-name (git-file-name name version))
13915 "0mc2gi7h4lx74zylvyp76mvc0w6706j858ii9vlgzqsw6acpr117"))))
13916 (build-system haskell-build-system)
13918 `(#:haddock? #f ; The haddock phase fails with: NGLess/CmdArgs.hs:20:1:
13919 ; error: parse error on input import
13920 ; import Options.Applicative
13922 (modify-phases %standard-phases
13923 (add-after 'unpack 'create-cabal-file
13924 (lambda _ (invoke "hpack") #t))
13925 ;; These tools are expected to be installed alongside ngless.
13926 (add-after 'install 'link-tools
13927 (lambda* (#:key inputs outputs #:allow-other-keys)
13928 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
13929 (symlink (string-append (assoc-ref inputs "prodigal")
13931 (string-append bin "ngless-" ,version "-prodigal"))
13932 (symlink (string-append (assoc-ref inputs "minimap2")
13934 (string-append bin "ngless-" ,version "-minimap2"))
13935 (symlink (string-append (assoc-ref inputs "samtools")
13937 (string-append bin "ngless-" ,version "-samtools"))
13938 (symlink (string-append (assoc-ref inputs "bwa")
13940 (string-append bin "ngless-" ,version "-bwa"))
13943 `(("prodigal" ,prodigal)
13945 ("samtools" ,samtools)
13946 ("minimap2" ,minimap2)
13947 ("ghc-aeson" ,ghc-aeson)
13948 ("ghc-ansi-terminal" ,ghc-ansi-terminal)
13949 ("ghc-async" ,ghc-async)
13950 ("ghc-atomic-write" ,ghc-atomic-write)
13951 ("ghc-bytestring-lexing" ,ghc-bytestring-lexing)
13952 ("ghc-chart" ,ghc-chart)
13953 ("ghc-chart-cairo" ,ghc-chart-cairo)
13954 ("ghc-conduit" ,ghc-conduit)
13955 ("ghc-conduit-algorithms" ,ghc-conduit-algorithms)
13956 ("ghc-conduit-combinators" ,ghc-conduit-combinators)
13957 ("ghc-conduit-extra" ,ghc-conduit-extra)
13958 ("ghc-configurator" ,ghc-configurator)
13959 ("ghc-convertible" ,ghc-convertible)
13960 ("ghc-data-default" ,ghc-data-default)
13961 ("ghc-double-conversion" ,ghc-double-conversion)
13962 ("ghc-edit-distance" ,ghc-edit-distance)
13963 ("ghc-either" ,ghc-either)
13964 ("ghc-errors" ,ghc-errors)
13965 ("ghc-extra" ,ghc-extra)
13966 ("ghc-filemanip" ,ghc-filemanip)
13967 ("ghc-file-embed" ,ghc-file-embed)
13968 ("ghc-gitrev" ,ghc-gitrev)
13969 ("ghc-hashtables" ,ghc-hashtables)
13970 ("ghc-http-conduit" ,ghc-http-conduit)
13971 ("ghc-inline-c" ,ghc-inline-c)
13972 ("ghc-inline-c-cpp" ,ghc-inline-c-cpp)
13973 ("ghc-intervalmap" ,ghc-intervalmap)
13974 ("ghc-missingh" ,ghc-missingh)
13975 ("ghc-optparse-applicative" ,ghc-optparse-applicative)
13976 ("ghc-parsec" ,ghc-parsec)
13977 ("ghc-regex" ,ghc-regex)
13978 ("ghc-safe" ,ghc-safe)
13979 ("ghc-safeio" ,ghc-safeio)
13980 ("ghc-strict" ,ghc-strict)
13981 ("ghc-tar" ,ghc-tar)
13982 ("ghc-text" ,ghc-text)
13983 ("ghc-unliftio" ,ghc-unliftio)
13984 ("ghc-unliftio-core" ,ghc-unliftio-core)
13985 ("ghc-vector" ,ghc-vector)
13986 ("ghc-yaml" ,ghc-yaml)
13987 ("ghc-zlib" ,ghc-zlib)))
13990 ("r-hdf5r" ,r-hdf5r)
13991 ("r-iterators" ,r-iterators)
13992 ("r-itertools" ,r-itertools)
13993 ("r-matrix" ,r-matrix)))
13995 `(("ghc-hpack" ,ghc-hpack)
13996 ("ghc-quickcheck" ,ghc-quickcheck)
13997 ("ghc-test-framework" ,ghc-test-framework)
13998 ("ghc-test-framework-hunit",ghc-test-framework-hunit)
13999 ("ghc-test-framework-quickcheck2" ,ghc-test-framework-quickcheck2)
14000 ("ghc-test-framework-th" ,ghc-test-framework-th)))
14001 (home-page "https://gitlab.com/ngless/ngless")
14002 (synopsis "DSL for processing next-generation sequencing data")
14003 (description "Ngless is a domain-specific language for
14004 @dfn{next-generation sequencing} (NGS) data processing.")
14005 (license license:expat)))
14007 (define-public filtlong
14008 ;; The recommended way to install is to clone the git repository
14009 ;; https://github.com/rrwick/Filtlong#installation
14010 ;; and the lastest release is more than nine months old
14011 (let ((commit "d1bb46dfe8bc7efe6257b5ce222c04bfe8aedaab")
14015 (version (git-version "0.2.0" revision commit))
14019 (uri (git-reference
14020 (url "https://github.com/rrwick/Filtlong.git")
14022 (file-name (git-file-name name version))
14024 (base32 "1xr92r820x8qlkcr3b57iw223yq8vjgyi42jr79w2xgw47qzr575"))))
14025 (build-system gnu-build-system)
14027 `(#:tests? #f ; no check target
14029 (modify-phases %standard-phases
14030 (delete 'configure)
14032 (lambda* (#:key outputs #:allow-other-keys)
14033 (let* ((out (assoc-ref outputs "out"))
14034 (bin (string-append out "/bin"))
14035 (scripts (string-append out "/share/filtlong/scripts")))
14036 (install-file "bin/filtlong" bin)
14037 (install-file "scripts/histogram.py" scripts)
14038 (install-file "scripts/read_info_histograms.sh" scripts))
14040 (add-after 'install 'wrap-program
14041 (lambda* (#:key inputs outputs #:allow-other-keys)
14042 (let* ((out (assoc-ref outputs "out"))
14043 (path (getenv "PYTHONPATH")))
14044 (wrap-program (string-append out
14045 "/share/filtlong/scripts/histogram.py")
14046 `("PYTHONPATH" ":" prefix (,path))))
14048 (add-before 'check 'patch-tests
14050 (substitute* "scripts/read_info_histograms.sh"
14051 (("awk") (which "gawk")))
14054 `(("gawk" ,gawk) ;for read_info_histograms.sh
14055 ("python" ,python-2) ;required for histogram.py
14057 (home-page "https://github.com/rrwick/Filtlong/")
14058 (synopsis "Tool for quality filtering of Nanopore and PacBio data")
14060 "The Filtlong package is a tool for filtering long reads by quality.
14061 It can take a set of long reads and produce a smaller, better subset. It uses
14062 both read length (longer is better) and read identity (higher is better) when
14063 choosing which reads pass the filter.")
14064 (license (list license:gpl3 ;filtlong
14065 license:asl2.0))))) ;histogram.py
14067 (define-public nanopolish
14068 ;; The recommended way to install is to clone the git repository
14069 ;; <https://github.com/jts/nanopolish#installing-a-particular-release>.
14070 ;; Also, the differences between release and current version seem to be
14072 (let ((commit "6331dc4f15b9dfabb954ba3fae9d76b6c3ca6377")
14075 (name "nanopolish")
14076 (version (git-version "0.11.1" revision commit))
14080 (uri (git-reference
14081 (url "https://github.com/jts/nanopolish.git")
14084 (file-name (git-file-name name version))
14086 (base32 "15ikl3d37y49pwd7vx36xksgsqajhf24q7qqsnpl15dqqyy5qgbc"))
14087 (modules '((guix build utils)))
14090 (delete-file-recursively "htslib")
14092 (build-system gnu-build-system)
14095 `("HDF5=noinstall" "EIGEN=noinstall" "HTS=noinstall" "CC=gcc")
14096 #:tests? #f ; no check target
14098 (modify-phases %standard-phases
14099 (add-after 'unpack 'find-eigen
14100 (lambda* (#:key inputs #:allow-other-keys)
14102 (string-append (assoc-ref inputs "eigen")
14103 "/include/eigen3"))
14105 (delete 'configure)
14107 (lambda* (#:key outputs #:allow-other-keys)
14108 (let* ((out (assoc-ref outputs "out"))
14109 (bin (string-append out "/bin"))
14110 (scripts (string-append out "/share/nanopolish/scripts")))
14112 (install-file "nanopolish" bin)
14113 (for-each (lambda (file) (install-file file scripts))
14114 (find-files "scripts" ".*"))
14116 (add-after 'install 'wrap-programs
14117 (lambda* (#:key outputs #:allow-other-keys)
14118 (for-each (lambda (file)
14119 (wrap-program file `("PYTHONPATH" ":" prefix (,path))))
14120 (find-files "/share/nanopolish/scripts" "\\.py"))
14121 (for-each (lambda (file)
14122 (wrap-program file `("PERL5LIB" ":" prefix (,path))))
14123 (find-files "/share/nanopolish/scripts" "\\.pl"))
14130 ("python" ,python-wrapper)
14131 ("python-biopython" ,python-biopython)
14132 ("python-numpy" ,python-numpy)
14133 ("python-pysam" ,python-pysam)
14134 ("python-scikit-learn" , python-scikit-learn)
14135 ("python-scipy" ,python-scipy)
14137 (home-page "https://github.com/jts/nanopolish")
14138 (synopsis "Signal-level analysis of Oxford Nanopore sequencing data")
14140 "This package analyses the Oxford Nanopore sequencing data at signal-level.
14141 Nanopolish can calculate an improved consensus sequence for a draft genome
14142 assembly, detect base modifications, call SNPs (Single nucleotide
14143 polymorphisms) and indels with respect to a reference genome and more.")
14144 (license license:expat))))
14146 (define-public cnvkit
14153 (uri (git-reference
14154 (url "https://github.com/etal/cnvkit.git")
14155 (commit (string-append "v" version))))
14156 (file-name (git-file-name name version))
14158 (base32 "0g2f78k68yglmj4fsfmgs8idqv3di9aj53fg0ld0hqljg8chhh82"))))
14159 (build-system python-build-system)
14161 `(("python-biopython" ,python-biopython)
14162 ("python-future" ,python-future)
14163 ("python-matplotlib" ,python-matplotlib)
14164 ("python-numpy" ,python-numpy)
14165 ("python-reportlab" ,python-reportlab)
14166 ("python-pandas" ,python-pandas)
14167 ("python-pysam" ,python-pysam)
14168 ("python-pyfaidx" ,python-pyfaidx)
14169 ("python-scipy" ,python-scipy)
14171 ("r-dnacopy" ,r-dnacopy)))
14172 (home-page "https://cnvkit.readthedocs.org/")
14173 (synopsis "Copy number variant detection from targeted DNA sequencing")
14175 "CNVkit is a Python library and command-line software toolkit to infer
14176 and visualize copy number from high-throughput DNA sequencing data. It is
14177 designed for use with hybrid capture, including both whole-exome and custom
14178 target panels, and short-read sequencing platforms such as Illumina and Ion
14180 (license license:asl2.0)))
14182 (define-public python-pyfit-sne
14184 (name "python-pyfit-sne")
14189 (uri (git-reference
14190 (url "https://github.com/KlugerLab/pyFIt-SNE.git")
14192 (file-name (git-file-name name version))
14194 (base32 "13wh3qkzs56azmmgnxib6xfr29g7xh09sxylzjpni5j0pp0rc5qw"))))
14195 (build-system python-build-system)
14197 `(("python-numpy" ,python-numpy)))
14201 `(("python-cython" ,python-cython)))
14202 (home-page "https://github.com/KlugerLab/pyFIt-SNE")
14203 (synopsis "FFT-accelerated Interpolation-based t-SNE")
14205 "t-Stochastic Neighborhood Embedding (t-SNE) is a highly successful
14206 method for dimensionality reduction and visualization of high dimensional
14207 datasets. A popular implementation of t-SNE uses the Barnes-Hut algorithm to
14208 approximate the gradient at each iteration of gradient descent. This package
14209 is a Cython wrapper for FIt-SNE.")
14210 (license license:bsd-4)))
14212 (define-public bbmap
14218 (uri (string-append
14219 "mirror://sourceforge/bbmap/BBMap_" version ".tar.gz"))
14222 "1q4rfhxcb6z3gm8zg2davjz98w22lkf4hm9ikxz9kdl93pil3wkd"))))
14223 (build-system ant-build-system)
14225 `(#:build-target "dist"
14226 #:tests? #f ; there are none
14228 (list (string-append "-Dmpijar="
14229 (assoc-ref %build-inputs "java-openmpi")
14231 #:modules ((guix build ant-build-system)
14233 (guix build java-utils))
14235 (modify-phases %standard-phases
14236 (add-after 'build 'build-jni-library
14238 (with-directory-excursion "jni"
14239 (invoke "make" "-f" "makefile.linux"))))
14240 ;; There is no install target
14241 (replace 'install (install-jars "dist"))
14242 (add-after 'install 'install-scripts-and-documentation
14243 (lambda* (#:key outputs #:allow-other-keys)
14244 (substitute* "calcmem.sh"
14245 (("\\| awk ") (string-append "| " (which "awk") " ")))
14246 (let* ((scripts (find-files "." "\\.sh$"))
14247 (out (assoc-ref outputs "out"))
14248 (bin (string-append out "/bin"))
14249 (doc (string-append out "/share/doc/bbmap"))
14250 (jni (string-append out "/lib/jni")))
14251 (substitute* scripts
14252 (("\\$DIR\"\"docs") doc)
14254 (string-append "CP=" out "/share/java/BBTools.jar\n"))
14255 (("^NATIVELIBDIR.*")
14256 (string-append "NATIVELIBDIR=" jni "\n"))
14258 (string-append "CMD=\"" (which "java"))))
14259 (for-each (lambda (script) (install-file script bin)) scripts)
14261 ;; Install JNI library
14262 (install-file "jni/libbbtoolsjni.so" jni)
14264 ;; Install documentation
14265 (install-file "docs/readme.txt" doc)
14266 (copy-recursively "docs/guides" doc))
14271 ("java-eclipse-jdt-core" ,java-eclipse-jdt-core)
14272 ("java-eclipse-jdt-compiler-apt" ,java-eclipse-jdt-compiler-apt)
14273 ("java-openmpi" ,java-openmpi)))
14274 (home-page "http://sourceforge.net/projects/bbmap/")
14275 (synopsis "Aligner and other tools for short sequencing reads")
14277 "This package provides bioinformatic tools to align, deduplicate,
14278 reformat, filter and normalize DNA and RNA-seq data. It includes the
14279 following tools: BBMap, a short read aligner for DNA and RNA-seq data; BBNorm,
14280 a kmer-based error-correction and normalization tool; Dedupe, a tool to
14281 simplify assemblies by removing duplicate or contained subsequences that share
14282 a target percent identity; Reformat, to convert reads between
14283 fasta/fastq/scarf/fasta+qual/sam, interleaved/paired, and ASCII-33/64, at over
14284 500 MB/s; and BBDuk, a tool to filter, trim, or mask reads with kmer matches
14285 to an artifact/contaminant file.")
14286 (license license:bsd-3)))
14288 (define-public velvet
14294 (uri (string-append "https://www.ebi.ac.uk/~zerbino/velvet/"
14295 "velvet_" version ".tgz"))
14298 "0h3njwy66p6bx14r3ar1byb0ccaxmxka4c65rn4iybyiqa4d8kc8"))
14299 ;; Delete bundled libraries
14300 (modules '((guix build utils)))
14303 (delete-file "Manual.pdf")
14304 (delete-file-recursively "third-party")
14306 (build-system gnu-build-system)
14308 `(#:make-flags '("OPENMP=t")
14309 #:test-target "test"
14311 (modify-phases %standard-phases
14312 (delete 'configure)
14313 (add-after 'unpack 'fix-zlib-include
14315 (substitute* "src/binarySequences.c"
14316 (("../third-party/zlib-1.2.3/zlib.h") "zlib.h"))
14319 (lambda* (#:key outputs #:allow-other-keys)
14320 (let* ((out (assoc-ref outputs "out"))
14321 (bin (string-append out "/bin"))
14322 (doc (string-append out "/share/doc/velvet")))
14325 (install-file "velveth" bin)
14326 (install-file "velvetg" bin)
14327 (install-file "Manual.pdf" doc)
14328 (install-file "Columbus_manual.pdf" doc)
14331 `(("openmpi" ,openmpi)
14334 `(("texlive" ,(texlive-union (list texlive-latex-graphics
14335 texlive-latex-hyperref)))))
14336 (home-page "https://www.ebi.ac.uk/~zerbino/velvet/")
14337 (synopsis "Nucleic acid sequence assembler for very short reads")
14339 "Velvet is a de novo genomic assembler specially designed for short read
14340 sequencing technologies, such as Solexa or 454. Velvet currently takes in
14341 short read sequences, removes errors then produces high quality unique
14342 contigs. It then uses paired read information, if available, to retrieve the
14343 repeated areas between contigs.")
14344 (license license:gpl2+)))
14346 (define-public python-velocyto
14348 (name "python-velocyto")
14349 (version "0.17.17")
14353 (uri (pypi-uri "velocyto" version))
14356 "0fgygyzqgrq32dv6a00biq1p1cwi6kbl5iqblxq1kklj6b2mzmhs"))))
14357 (build-system python-build-system)
14359 `(("python-click" ,python-click)
14360 ("python-cython" ,python-cython)
14361 ("python-h5py" ,python-h5py)
14362 ("python-loompy" ,python-loompy)
14363 ("python-matplotlib" ,python-matplotlib)
14364 ("python-numba" ,python-numba)
14365 ("python-numpy" ,python-numpy)
14366 ("python-pandas" ,python-pandas)
14367 ("python-pysam" ,python-pysam)
14368 ("python-scikit-learn" ,python-scikit-learn)
14369 ("python-scipy" ,python-scipy)))
14370 (home-page "https://github.com/velocyto-team/velocyto.py")
14371 (synopsis "RNA velocity analysis for single cell RNA-seq data")
14373 "Velocyto is a library for the analysis of RNA velocity. Velocyto
14374 includes a command line tool and an analysis pipeline.")
14375 (license license:bsd-2)))
14377 (define-public arriba
14384 (uri (string-append "https://github.com/suhrig/arriba/releases/"
14385 "download/v" version "/arriba_v" version ".tar.gz"))
14388 "0jx9656ry766vb8z08m1c3im87b0c82qpnjby9wz4kcz8vn87dx2"))))
14389 (build-system gnu-build-system)
14391 `(#:tests? #f ; there are none
14393 (modify-phases %standard-phases
14394 (replace 'configure
14395 (lambda* (#:key inputs #:allow-other-keys)
14396 (let ((htslib (assoc-ref inputs "htslib")))
14397 (substitute* "Makefile"
14398 (("-I\\$\\(HTSLIB\\)/htslib")
14399 (string-append "-I" htslib "/include/htslib"))
14400 ((" \\$\\(HTSLIB\\)/libhts.a")
14401 (string-append " " htslib "/lib/libhts.so"))))
14402 (substitute* "run_arriba.sh"
14403 (("^STAR ") (string-append (which "STAR") " "))
14404 (("samtools --version-only")
14405 (string-append (which "samtools") " --version-only"))
14406 (("samtools index")
14407 (string-append (which "samtools") " index"))
14409 (string-append (which "samtools") " sort")))
14412 (lambda* (#:key outputs #:allow-other-keys)
14413 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
14414 (install-file "arriba" bin)
14415 (install-file "run_arriba.sh" bin)
14416 (install-file "draw_fusions.R" bin)
14417 (wrap-program (string-append bin "/draw_fusions.R")
14418 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
14421 `(("htslib" ,htslib)
14422 ("r-minimal" ,r-minimal)
14423 ("r-circlize" ,r-circlize)
14424 ("r-genomicalignments" ,r-genomicalignments)
14425 ("r-genomicranges" ,r-genomicranges)
14426 ("samtools" ,samtools)
14429 (home-page "https://github.com/suhrig/arriba")
14430 (synopsis "Gene fusion detection from RNA-Seq data ")
14432 "Arriba is a command-line tool for the detection of gene fusions from
14433 RNA-Seq data. It was developed for the use in a clinical research setting.
14434 Therefore, short runtimes and high sensitivity were important design criteria.
14435 It is based on the fast STAR aligner and the post-alignment runtime is
14436 typically just around two minutes. In contrast to many other fusion detection
14437 tools which build on STAR, Arriba does not require to reduce the
14438 @code{alignIntronMax} parameter of STAR to detect small deletions.")
14439 ;; All code is under the Expat license with the exception of
14440 ;; "draw_fusions.R", which is under GPLv3.
14441 (license (list license:expat license:gpl3))))
14443 (define-public adapterremoval
14445 (name "adapterremoval")
14450 (uri (git-reference
14451 (url "https://github.com/MikkelSchubert/adapterremoval.git")
14452 (commit (string-append "v" version))))
14453 (file-name (git-file-name name version))
14456 "1nf3ki5pfzalhrx2fr1y6pfqfi133yj2m7q4fj9irf5fb94bapwr"))))
14457 (build-system gnu-build-system)
14459 `(#:make-flags (list "COLOR_BUILD=no"
14460 (string-append "PREFIX="
14461 (assoc-ref %outputs "out")))
14462 #:test-target "test"
14464 (modify-phases %standard-phases
14465 (delete 'configure))))
14468 (home-page "https://adapterremoval.readthedocs.io/")
14469 (synopsis "Rapid sequence adapter trimming, identification, and read merging")
14471 "This program searches for and removes remnant adapter sequences from
14472 @dfn{High-Throughput Sequencing} (HTS) data and (optionally) trims low quality
14473 bases from the 3' end of reads following adapter removal. AdapterRemoval can
14474 analyze both single end and paired end data, and can be used to merge
14475 overlapping paired-ended reads into (longer) consensus sequences.
14476 Additionally, the AdapterRemoval may be used to recover a consensus adapter
14477 sequence for paired-ended data, for which this information is not available.")
14478 (license license:gpl3+)))
14480 (define-public pplacer
14481 (let ((commit "807f6f3"))
14484 ;; The commit should be updated with each version change.
14485 (version "1.1.alpha19")
14489 (uri (git-reference
14490 (url "https://github.com/matsen/pplacer.git")
14491 (commit (string-append "v" version))))
14492 (file-name (git-file-name name version))
14494 (base32 "11ppbbbx20p2g9wj3ff64dhnarb12q79v7qh4rk0gj6lkbz4n7cn"))))
14495 (build-system ocaml-build-system)
14497 `(#:modules ((guix build ocaml-build-system)
14501 (modify-phases %standard-phases
14502 (delete 'configure)
14503 (add-after 'unpack 'fix-build-with-latest-ocaml
14505 (substitute* "myocamlbuild.ml"
14506 (("dep \\[\"c_pam\"\\]" m)
14507 (string-append "flag [\"ocaml\"; \"compile\"] (A \"-unsafe-string\");\n"
14509 (("let run_and_read" m)
14514 let pos = String.index s ch in
14515 x := (String.before s pos)::!x;
14516 go (String.after s (pos + 1))
14519 with Not_found -> !x
14520 let split_nl s = split s '\\n'
14521 let before_space s =
14522 try String.before s (String.index s ' ')
14523 with Not_found -> s
14526 (("run_and_read \"ocamlfind list \\| cut -d' ' -f1\"" m)
14527 (string-append "List.map before_space (split_nl & " m ")"))
14528 ((" blank_sep_strings &") "")
14529 ((" Lexing.from_string &") ""))
14531 (add-after 'unpack 'replace-bundled-cddlib
14532 (lambda* (#:key inputs #:allow-other-keys)
14533 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
14534 (local-dir "cddlib_guix"))
14536 (with-directory-excursion local-dir
14537 (invoke "tar" "xvf" cddlib-src))
14538 (let ((cddlib-src-folder
14539 (string-append local-dir "/"
14540 (list-ref (scandir local-dir) 2)
14542 (for-each make-file-writable (find-files "cdd_src" ".*"))
14546 (string-append "cdd_src/" (basename file))))
14547 (find-files cddlib-src-folder ".*[ch]$")))
14549 (add-after 'unpack 'fix-makefile
14551 ;; Remove system calls to 'git'.
14552 (substitute* "Makefile"
14553 (("^DESCRIPT:=pplacer-.*")
14555 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
14556 (substitute* "myocamlbuild.ml"
14557 (("git describe --tags --long .*\\\" with")
14559 "echo -n v" ,version "-" ,commit "\" with")))
14562 (lambda* (#:key outputs #:allow-other-keys)
14563 (let* ((out (assoc-ref outputs "out"))
14564 (bin (string-append out "/bin")))
14565 (copy-recursively "bin" bin))
14568 `(("zlib" ,zlib "static")
14570 ("ocaml-ounit" ,ocaml-ounit)
14571 ("ocaml-batteries" ,ocaml-batteries)
14572 ("ocaml-camlzip" ,camlzip)
14573 ("ocaml-csv" ,ocaml-csv)
14574 ("ocaml-sqlite3" ,ocaml-sqlite3)
14575 ("ocaml-xmlm" ,ocaml-xmlm)
14576 ("ocaml-mcl" ,ocaml-mcl)
14577 ("ocaml-gsl" ,ocaml-gsl-1)))
14579 `(("cddlib-src" ,(package-source cddlib))
14580 ("ocamlbuild" ,ocamlbuild)
14581 ("pkg-config" ,pkg-config)))
14583 `(("pplacer-scripts" ,pplacer-scripts)))
14584 (synopsis "Phylogenetic placement of biological sequences")
14586 "Pplacer places query sequences on a fixed reference phylogenetic tree
14587 to maximize phylogenetic likelihood or posterior probability according to a
14588 reference alignment. Pplacer is designed to be fast, to give useful
14589 information about uncertainty, and to offer advanced visualization and
14590 downstream analysis.")
14591 (home-page "http://matsen.fhcrc.org/pplacer")
14592 (license license:gpl3))))
14594 ;; This package is installed alongside 'pplacer'. It is a separate package so
14595 ;; that it can use the python-build-system for the scripts that are
14596 ;; distributed alongside the main OCaml binaries.
14597 (define pplacer-scripts
14600 (name "pplacer-scripts")
14601 (build-system python-build-system)
14603 `(#:python ,python-2
14605 (modify-phases %standard-phases
14606 (add-after 'unpack 'enter-scripts-dir
14607 (lambda _ (chdir "scripts") #t))
14609 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t))
14610 (add-after 'install 'wrap-executables
14611 (lambda* (#:key inputs outputs #:allow-other-keys)
14612 (let* ((out (assoc-ref outputs "out"))
14613 (bin (string-append out "/bin")))
14614 (let ((path (string-append
14615 (assoc-ref inputs "hmmer") "/bin:"
14616 (assoc-ref inputs "infernal") "/bin")))
14618 (wrap-program (string-append bin "/refpkg_align.py")
14619 `("PATH" ":" prefix (,path))))
14620 (let ((path (string-append
14621 (assoc-ref inputs "hmmer") "/bin")))
14622 (wrap-program (string-append bin "/hrefpkg_query.py")
14623 `("PATH" ":" prefix (,path)))))
14626 `(("infernal" ,infernal)
14629 `(("python-biopython" ,python2-biopython)
14630 ("taxtastic" ,taxtastic)))
14631 (synopsis "Pplacer Python scripts")))
14633 (define-public python2-checkm-genome
14635 (name "python2-checkm-genome")
14640 (uri (pypi-uri "checkm-genome" version))
14643 "0bm8gpxjmzxsxxl8lzwqhgx8g1dlnmp6znz7wv3hgb0gdjbf9dzz"))))
14644 (build-system python-build-system)
14646 `(#:python ,python-2
14647 #:tests? #f)) ; some tests are interactive
14649 `(("python-dendropy" ,python2-dendropy)
14650 ("python-matplotlib" ,python2-matplotlib)
14651 ("python-numpy" ,python2-numpy)
14652 ("python-pysam" ,python2-pysam)
14653 ("python-scipy" ,python2-scipy)))
14654 (home-page "http://pypi.python.org/pypi/checkm/")
14655 (synopsis "Assess the quality of putative genome bins")
14657 "CheckM provides a set of tools for assessing the quality of genomes
14658 recovered from isolates, single cells, or metagenomes. It provides robust
14659 estimates of genome completeness and contamination by using collocated sets of
14660 genes that are ubiquitous and single-copy within a phylogenetic lineage.
14661 Assessment of genome quality can also be examined using plots depicting key
14662 genomic characteristics (e.g., GC, coding density) which highlight sequences
14663 outside the expected distributions of a typical genome. CheckM also provides
14664 tools for identifying genome bins that are likely candidates for merging based
14665 on marker set compatibility, similarity in genomic characteristics, and
14666 proximity within a reference genome.")
14667 (license license:gpl3+)))
14669 (define-public umi-tools
14676 (uri (pypi-uri "umi_tools" version))
14679 "08y3vz1vcx09whmbsn722lcs6jl9wyrh9i4p3k8j4cb1i32bij4a"))))
14680 (build-system python-build-system)
14682 `(("python-setuptools" ,python-setuptools)
14683 ("python-pandas" ,python-pandas)
14684 ("python-future" ,python-future)
14685 ("python-scipy" ,python-scipy)
14686 ("python-matplotlib" ,python-matplotlib)
14687 ("python-regex" ,python-regex)
14688 ("python-pysam" ,python-pysam)))
14690 `(("python-setuptools" ,python-setuptools)
14691 ("python-cython" ,python-cython)))
14692 (home-page "https://github.com/CGATOxford/UMI-tools")
14693 (synopsis "Tools for analyzing unique modular identifiers")
14694 (description "This package provides tools for dealing with @dfn{Unique
14695 Molecular Identifiers} (UMIs) and @dfn{Random Molecular Tags} (RMTs) in
14696 genetic sequences. There are six tools: the @code{extract} and
14697 @code{whitelist} commands are used to prepare a fastq containing UMIs @code{+/-}
14698 cell barcodes for alignment. The remaining commands, @code{group},
14699 @code{dedup}, and @{count}/@code{count_tab}, are used to identify PCR
14700 duplicates using the UMIs and perform different levels of analysis depending
14701 on the needs of the user.")
14702 (license license:expat)))
14704 (define-public ataqv
14711 (uri (git-reference
14712 (url "https://github.com/ParkerLab/ataqv.git")
14714 (file-name (git-file-name name version))
14717 "031xr6jx1aprh26y5b1lv3gzrlmzg4alfl73vvshymx8cq8asrqi"))))
14718 (build-system gnu-build-system)
14721 (list (string-append "prefix=" (assoc-ref %outputs "out"))
14722 (string-append "BOOST_ROOT="
14723 (assoc-ref %build-inputs "boost"))
14724 (string-append "HTSLIB_ROOT="
14725 (assoc-ref %build-inputs "htslib")))
14726 #:test-target "test"
14728 (modify-phases %standard-phases
14729 (delete 'configure))))
14733 ("ncurses" ,ncurses)
14737 (home-page "https://github.com/ParkerLab/ataqv")
14738 (synopsis "Toolkit for quality control and visualization of ATAC-seq data")
14739 (description "This package provides a toolkit for measuring and comparing
14740 ATAC-seq results. It was written to make it easier to spot differences that
14741 might be caused by ATAC-seq library prep or sequencing. The main program,
14742 @code{ataqv}, examines aligned reads and reports some basic metrics.")
14743 (license license:gpl3+)))
14745 (define-public r-psiplot
14752 (uri (git-reference
14753 (url "https://github.com/kcha/psiplot.git")
14754 (commit (string-append "v" version))))
14755 (file-name (git-file-name name version))
14757 (base32 "08438h16cfry5kqh3y9hs8q1b1a8bxhblsm75knviz5r6q0n1jxh"))))
14758 (build-system r-build-system)
14760 `(("r-mass" ,r-mass)
14761 ("r-dplyr" ,r-dplyr)
14762 ("r-tidyr" ,r-tidyr)
14763 ("r-purrr" ,r-purrr)
14764 ("r-readr" ,r-readr)
14765 ("r-magrittr" ,r-magrittr)
14766 ("r-ggplot2" ,r-ggplot2)))
14767 (home-page "https://github.com/kcha/psiplot")
14768 (synopsis "Plot percent spliced-in values of alternatively-spliced exons")
14770 "PSIplot is an R package for generating plots of @dfn{percent
14771 spliced-in} (PSI) values of alternatively-spliced exons that were computed by
14772 vast-tools, an RNA-Seq pipeline for alternative splicing analysis. The plots
14773 are generated using @code{ggplot2}.")
14774 (license license:expat)))
14776 (define-public tbsp
14777 (let ((commit "ec8fff4410cfb13a677dbbb95cbbc60217e64907")
14781 (version (git-version "1.0.0" revision commit))
14785 (uri (git-reference
14786 (url "https://github.com/phoenixding/tbsp.git")
14790 "025ym14x8gbd6hb55lsinqj6f5qzw36i10klgs7ldzxxd7s39ki1"))))
14791 (build-system python-build-system)
14792 (arguments '(#:tests? #f)) ; no tests included
14794 `(("python-matplotlib" ,python-matplotlib)
14795 ("python-networkx" ,python-networkx)
14796 ("python-numpy" ,python-numpy)
14797 ("python-pybigwig" ,python-pybigwig)
14798 ("python-biopython" ,python-biopython)
14799 ("python-scikit-learn" ,python-scikit-learn)
14800 ("python-scipy" ,python-scipy)))
14801 (home-page "https://github.com/phoenixding/tbsp/")
14802 (synopsis "SNP-based trajectory inference")
14804 "Several studies focus on the inference of developmental and response
14805 trajectories from single cell RNA-Seq (scRNA-Seq) data. A number of
14806 computational methods, often referred to as pseudo-time ordering, have been
14807 developed for this task. CRISPR has also been used to reconstruct lineage
14808 trees by inserting random mutations. The tbsp package implements an
14809 alternative method to detect significant, cell type specific sequence
14810 mutations from scRNA-Seq data.")
14811 (license license:expat))))