1 ;;; GNU Guix --- Functional package management for GNU
2 ;;; Copyright © 2014, 2015, 2016, 2017, 2018, 2019 Ricardo Wurmus <rekado@elephly.net>
3 ;;; Copyright © 2015, 2016, 2017, 2018 Ben Woodcroft <donttrustben@gmail.com>
4 ;;; Copyright © 2015, 2016 Pjotr Prins <pjotr.guix@thebird.nl>
5 ;;; Copyright © 2015 Andreas Enge <andreas@enge.fr>
6 ;;; Copyright © 2016 Roel Janssen <roel@gnu.org>
7 ;;; Copyright © 2016, 2017, 2018, 2019 Efraim Flashner <efraim@flashner.co.il>
8 ;;; Copyright © 2016 Marius Bakke <mbakke@fastmail.com>
9 ;;; Copyright © 2016, 2018 Raoul Bonnal <ilpuccio.febo@gmail.com>
10 ;;; Copyright © 2017, 2018 Tobias Geerinckx-Rice <me@tobias.gr>
11 ;;; Copyright © 2017 Arun Isaac <arunisaac@systemreboot.net>
12 ;;; Copyright © 2018 Joshua Sierles, Nextjournal <joshua@nextjournal.com>
13 ;;; Copyright © 2018 Gábor Boskovits <boskovits@gmail.com>
14 ;;; Copyright © 2018 Mădălin Ionel Patrașcu <madalinionel.patrascu@mdc-berlin.de>
15 ;;; Copyright © 2019 Maxim Cournoyer <maxim.cournoyer@gmail.com>
17 ;;; This file is part of GNU Guix.
19 ;;; GNU Guix is free software; you can redistribute it and/or modify it
20 ;;; under the terms of the GNU General Public License as published by
21 ;;; the Free Software Foundation; either version 3 of the License, or (at
22 ;;; your option) any later version.
24 ;;; GNU Guix is distributed in the hope that it will be useful, but
25 ;;; WITHOUT ANY WARRANTY; without even the implied warranty of
26 ;;; MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
27 ;;; GNU General Public License for more details.
29 ;;; You should have received a copy of the GNU General Public License
30 ;;; along with GNU Guix. If not, see <http://www.gnu.org/licenses/>.
32 (define-module (gnu packages bioinformatics)
33 #:use-module ((guix licenses) #:prefix license:)
34 #:use-module (guix packages)
35 #:use-module (guix utils)
36 #:use-module (guix download)
37 #:use-module (guix git-download)
38 #:use-module (guix hg-download)
39 #:use-module (guix build-system ant)
40 #:use-module (guix build-system gnu)
41 #:use-module (guix build-system cmake)
42 #:use-module (guix build-system haskell)
43 #:use-module (guix build-system meson)
44 #:use-module (guix build-system ocaml)
45 #:use-module (guix build-system perl)
46 #:use-module (guix build-system python)
47 #:use-module (guix build-system r)
48 #:use-module (guix build-system ruby)
49 #:use-module (guix build-system scons)
50 #:use-module (guix build-system trivial)
51 #:use-module (gnu packages)
52 #:use-module (gnu packages autotools)
53 #:use-module (gnu packages algebra)
54 #:use-module (gnu packages base)
55 #:use-module (gnu packages bash)
56 #:use-module (gnu packages bison)
57 #:use-module (gnu packages bioconductor)
58 #:use-module (gnu packages boost)
59 #:use-module (gnu packages check)
60 #:use-module (gnu packages compression)
61 #:use-module (gnu packages cpio)
62 #:use-module (gnu packages cran)
63 #:use-module (gnu packages curl)
64 #:use-module (gnu packages documentation)
65 #:use-module (gnu packages databases)
66 #:use-module (gnu packages datastructures)
67 #:use-module (gnu packages file)
68 #:use-module (gnu packages flex)
69 #:use-module (gnu packages gawk)
70 #:use-module (gnu packages gcc)
71 #:use-module (gnu packages gd)
72 #:use-module (gnu packages gtk)
73 #:use-module (gnu packages glib)
74 #:use-module (gnu packages graph)
75 #:use-module (gnu packages groff)
76 #:use-module (gnu packages guile)
77 #:use-module (gnu packages guile-xyz)
78 #:use-module (gnu packages haskell)
79 #:use-module (gnu packages haskell-check)
80 #:use-module (gnu packages haskell-web)
81 #:use-module (gnu packages image)
82 #:use-module (gnu packages imagemagick)
83 #:use-module (gnu packages java)
84 #:use-module (gnu packages java-compression)
85 #:use-module (gnu packages jemalloc)
86 #:use-module (gnu packages dlang)
87 #:use-module (gnu packages linux)
88 #:use-module (gnu packages lisp)
89 #:use-module (gnu packages logging)
90 #:use-module (gnu packages machine-learning)
91 #:use-module (gnu packages man)
92 #:use-module (gnu packages maths)
93 #:use-module (gnu packages mpi)
94 #:use-module (gnu packages ncurses)
95 #:use-module (gnu packages ocaml)
96 #:use-module (gnu packages pcre)
97 #:use-module (gnu packages parallel)
98 #:use-module (gnu packages pdf)
99 #:use-module (gnu packages perl)
100 #:use-module (gnu packages perl-check)
101 #:use-module (gnu packages pkg-config)
102 #:use-module (gnu packages popt)
103 #:use-module (gnu packages protobuf)
104 #:use-module (gnu packages python)
105 #:use-module (gnu packages python-compression)
106 #:use-module (gnu packages python-web)
107 #:use-module (gnu packages python-xyz)
108 #:use-module (gnu packages readline)
109 #:use-module (gnu packages ruby)
110 #:use-module (gnu packages serialization)
111 #:use-module (gnu packages shells)
112 #:use-module (gnu packages statistics)
113 #:use-module (gnu packages swig)
114 #:use-module (gnu packages tbb)
115 #:use-module (gnu packages tex)
116 #:use-module (gnu packages texinfo)
117 #:use-module (gnu packages textutils)
118 #:use-module (gnu packages time)
119 #:use-module (gnu packages tls)
120 #:use-module (gnu packages vim)
121 #:use-module (gnu packages web)
122 #:use-module (gnu packages xml)
123 #:use-module (gnu packages xorg)
124 #:use-module (srfi srfi-1)
125 #:use-module (ice-9 match))
127 (define-public aragorn
134 "http://mbio-serv2.mbioekol.lu.se/ARAGORN/Downloads/aragorn"
138 "09i1rg716smlbnixfm7q1ml2mfpaa2fpn3hwjg625ysmfwwy712b"))))
139 (build-system gnu-build-system)
141 `(#:tests? #f ; there are no tests
143 (modify-phases %standard-phases
153 (string-append "aragorn" ,version ".c"))
156 (lambda* (#:key outputs #:allow-other-keys)
157 (let* ((out (assoc-ref outputs "out"))
158 (bin (string-append out "/bin"))
159 (man (string-append out "/share/man/man1")))
160 (install-file "aragorn" bin)
161 (install-file "aragorn.1" man))
163 (home-page "http://mbio-serv2.mbioekol.lu.se/ARAGORN")
164 (synopsis "Detect tRNA, mtRNA and tmRNA genes in nucleotide sequences")
166 "Aragorn identifies transfer RNA, mitochondrial RNA and
167 transfer-messenger RNA from nucleotide sequences, based on homology to known
168 tRNA consensus sequences and RNA structure. It also outputs the secondary
169 structure of the predicted RNA.")
170 (license license:gpl2)))
178 ;; BamM is not available on pypi.
180 (url "https://github.com/Ecogenomics/BamM.git")
183 (file-name (git-file-name name version))
186 "1p83ahi984ipslxlg4yqy1gdnya9rkn1v71z8djgxkm9d2chw4c5"))
187 (modules '((guix build utils)))
190 ;; Delete bundled htslib.
191 (delete-file-recursively "c/htslib-1.3.1")
193 (build-system python-build-system)
195 `(#:python ,python-2 ; BamM is Python 2 only.
196 ;; Do not use bundled libhts. Do use the bundled libcfu because it has
197 ;; been modified from its original form.
199 (let ((htslib (assoc-ref %build-inputs "htslib")))
200 (list "--with-libhts-lib" (string-append htslib "/lib")
201 "--with-libhts-inc" (string-append htslib "/include/htslib")))
203 (modify-phases %standard-phases
204 (add-after 'unpack 'autogen
206 (with-directory-excursion "c"
207 (let ((sh (which "sh")))
208 (for-each make-file-writable (find-files "." ".*"))
209 ;; Use autogen so that 'configure' works.
210 (substitute* "autogen.sh" (("/bin/sh") sh))
211 (setenv "CONFIG_SHELL" sh)
212 (invoke "./autogen.sh")))
215 ;; Run tests after installation so compilation only happens once.
217 (add-after 'install 'wrap-executable
218 (lambda* (#:key outputs #:allow-other-keys)
219 (let* ((out (assoc-ref outputs "out"))
220 (path (getenv "PATH")))
221 (wrap-program (string-append out "/bin/bamm")
222 `("PATH" ":" prefix (,path))))
224 (add-after 'wrap-executable 'post-install-check
225 (lambda* (#:key inputs outputs #:allow-other-keys)
227 (string-append (assoc-ref outputs "out")
232 (assoc-ref outputs "out")
234 (string-take (string-take-right
235 (assoc-ref inputs "python") 5) 3)
237 (getenv "PYTHONPATH")))
238 ;; There are 2 errors printed, but they are safe to ignore:
239 ;; 1) [E::hts_open_format] fail to open file ...
240 ;; 2) samtools view: failed to open ...
244 `(("autoconf" ,autoconf)
245 ("automake" ,automake)
248 ("python-nose" ,python2-nose)
249 ("python-pysam" ,python2-pysam)))
251 `(("htslib" ,htslib-1.3) ; At least one test fails on htslib-1.4+.
252 ("samtools" ,samtools)
256 ("coreutils" ,coreutils)))
258 `(("python-numpy" ,python2-numpy)))
259 (home-page "http://ecogenomics.github.io/BamM/")
260 (synopsis "Metagenomics-focused BAM file manipulator")
262 "BamM is a C library, wrapped in python, to efficiently generate and
263 parse BAM files, specifically for the analysis of metagenomic data. For
264 instance, it implements several methods to assess contig-wise read coverage.")
265 (license license:lgpl3+)))
267 (define-public bamtools
274 (url "https://github.com/pezmaster31/bamtools.git")
275 (commit (string-append "v" version))))
276 (file-name (git-file-name name version))
279 "0nfb2ypcx9959xnbz6wxh6py3xfizgmg8nrknxl95c507m9hmq8b"))))
280 (build-system cmake-build-system)
282 `(#:tests? #f ;no "check" target
284 (modify-phases %standard-phases
286 'configure 'set-ldflags
287 (lambda* (#:key outputs #:allow-other-keys)
291 (assoc-ref outputs "out") "/lib/bamtools"))
293 (inputs `(("zlib" ,zlib)))
294 (home-page "https://github.com/pezmaster31/bamtools")
295 (synopsis "C++ API and command-line toolkit for working with BAM data")
297 "BamTools provides both a C++ API and a command-line toolkit for handling
299 (license license:expat)))
301 (define-public bcftools
307 (uri (string-append "https://github.com/samtools/bcftools/"
309 version "/bcftools-" version ".tar.bz2"))
312 "1j3h638i8kgihzyrlnpj82xg1b23sijibys9hvwari3fy7kd0dkg"))
313 (modules '((guix build utils)))
315 ;; Delete bundled htslib.
316 (delete-file-recursively "htslib-1.9")
318 (build-system gnu-build-system)
321 (list "--enable-libgsl")
324 (modify-phases %standard-phases
325 (add-before 'check 'patch-tests
327 (substitute* "test/test.pl"
328 (("/bin/bash") (which "bash")))
336 (home-page "https://samtools.github.io/bcftools/")
337 (synopsis "Utilities for variant calling and manipulating VCFs and BCFs")
339 "BCFtools is a set of utilities that manipulate variant calls in the
340 Variant Call Format (VCF) and its binary counterpart BCF. All commands work
341 transparently with both VCFs and BCFs, both uncompressed and BGZF-compressed.")
342 ;; The sources are dual MIT/GPL, but becomes GPL-only when USE_GPL=1.
343 (license (list license:gpl3+ license:expat))))
345 (define-public bedops
352 (url "https://github.com/bedops/bedops.git")
353 (commit (string-append "v" version))))
354 (file-name (git-file-name name version))
357 "0mmgsgwz5r9w76hzgxkxc9s9lkdhhaf7vr6i02b09vbswvs1fyqx"))))
358 (build-system gnu-build-system)
361 #:make-flags (list (string-append "BINDIR=" %output "/bin"))
363 (modify-phases %standard-phases
364 (add-after 'unpack 'unpack-tarballs
366 ;; FIXME: Bedops includes tarballs of minimally patched upstream
367 ;; libraries jansson, zlib, and bzip2. We cannot just use stock
368 ;; libraries because at least one of the libraries (zlib) is
369 ;; patched to add a C++ function definition (deflateInit2cpp).
370 ;; Until the Bedops developers offer a way to link against system
371 ;; libraries we have to build the in-tree copies of these three
374 ;; See upstream discussion:
375 ;; https://github.com/bedops/bedops/issues/124
377 ;; Unpack the tarballs to benefit from shebang patching.
378 (with-directory-excursion "third-party"
379 (invoke "tar" "xvf" "jansson-2.6.tar.bz2")
380 (invoke "tar" "xvf" "zlib-1.2.7.tar.bz2")
381 (invoke "tar" "xvf" "bzip2-1.0.6.tar.bz2"))
382 ;; Disable unpacking of tarballs in Makefile.
383 (substitute* "system.mk/Makefile.linux"
384 (("^\tbzcat .*") "\t@echo \"not unpacking\"\n")
385 (("\\./configure") "CONFIG_SHELL=bash ./configure"))
386 (substitute* "third-party/zlib-1.2.7/Makefile.in"
387 (("^SHELL=.*$") "SHELL=bash\n"))
389 (delete 'configure))))
390 (home-page "https://github.com/bedops/bedops")
391 (synopsis "Tools for high-performance genomic feature operations")
393 "BEDOPS is a suite of tools to address common questions raised in genomic
394 studies---mostly with regard to overlap and proximity relationships between
395 data sets. It aims to be scalable and flexible, facilitating the efficient
396 and accurate analysis and management of large-scale genomic data.
398 BEDOPS provides tools that perform highly efficient and scalable Boolean and
399 other set operations, statistical calculations, archiving, conversion and
400 other management of genomic data of arbitrary scale. Tasks can be easily
401 split by chromosome for distributing whole-genome analyses across a
402 computational cluster.")
403 (license license:gpl2+)))
405 (define-public bedtools
411 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
412 "download/v" version "/"
413 "bedtools-" version ".tar.gz"))
416 "1ndg5yknrxl4djx8ddzgk12rrbiidfpmkkg5z3f95jzryfxarhn8"))))
417 (build-system gnu-build-system)
419 '(#:test-target "test"
421 (list (string-append "prefix=" (assoc-ref %outputs "out")))
423 (modify-phases %standard-phases
424 (delete 'configure))))
425 (native-inputs `(("python" ,python-2)))
427 `(("samtools" ,samtools)
429 (home-page "https://github.com/arq5x/bedtools2")
430 (synopsis "Tools for genome analysis and arithmetic")
432 "Collectively, the bedtools utilities are a swiss-army knife of tools for
433 a wide-range of genomics analysis tasks. The most widely-used tools enable
434 genome arithmetic: that is, set theory on the genome. For example, bedtools
435 allows one to intersect, merge, count, complement, and shuffle genomic
436 intervals from multiple files in widely-used genomic file formats such as BAM,
438 (license license:gpl2)))
440 ;; Later releases of bedtools produce files with more columns than
441 ;; what Ribotaper expects.
442 (define-public bedtools-2.18
443 (package (inherit bedtools)
448 (uri (string-append "https://github.com/arq5x/bedtools2/"
449 "releases/download/v" version
450 "/bedtools-" version ".tar.gz"))
453 "11rvca19ncg03kxd0wzlfx5ws7r3nisd0z8s9j9n182d8ksp2pxz"))))
455 '(#:test-target "test"
457 (modify-phases %standard-phases
460 (lambda* (#:key outputs #:allow-other-keys)
461 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
462 (for-each (lambda (file)
463 (install-file file bin))
464 (find-files "bin" ".*")))
467 ;; Needed for pybedtools.
468 (define-public bedtools-2.26
469 (package (inherit bedtools)
474 (uri (string-append "https://github.com/arq5x/bedtools2/releases/"
475 "download/v" version "/"
476 "bedtools-" version ".tar.gz"))
479 "0jhavwifnf7lmkb11h9y7dynr8d699h0rd2l52j1pfgircr2zwv5"))))))
488 (url "https://github.com/PacificBiosciences/pbbam.git")
490 (file-name (git-file-name name version))
493 "0h9gkrpf2lrxklxp72xfl5bi3h5zcm5hprrya9gf0hr3xwlbpp0x"))))
494 (build-system meson-build-system)
497 (modify-phases %standard-phases
498 (add-after 'unpack 'find-googletest
499 (lambda* (#:key inputs #:allow-other-keys)
500 ;; It doesn't find gtest_main because there's no pkg-config file
501 ;; for it. Find it another way.
502 (substitute* "tests/meson.build"
503 (("pbbam_gtest_dep = dependency\\('gtest_main'.*")
504 (format #f "cpp = meson.get_compiler('cpp')
505 pbbam_gtest_dep = cpp.find_library('gtest_main', dirs : '~a')\n"
506 (assoc-ref inputs "googletest"))))
508 ;; TODO: tests/pbbam_test cannot be linked
509 ;; ld: tests/59830eb@@pbbam_test@exe/src_test_Accuracy.cpp.o:
510 ;; undefined reference to symbol '_ZTIN7testing4TestE'
511 ;; ld: /gnu/store/...-googletest-1.8.0/lib/libgtest.so:
512 ;; error adding symbols: DSO missing from command line
514 #:configure-flags '("-Dtests=false")))
515 ;; These libraries are listed as "Required" in the pkg-config file.
521 ("samtools" ,samtools)))
523 `(("googletest" ,googletest)
524 ("pkg-config" ,pkg-config)
525 ("python" ,python-wrapper))) ; for tests
526 (home-page "https://github.com/PacificBiosciences/pbbam")
527 (synopsis "Work with PacBio BAM files")
529 "The pbbam software package provides components to create, query, and
530 edit PacBio BAM files and associated indices. These components include a core
531 C++ library, bindings for additional languages, and command-line utilities.
532 This library is not intended to be used as a general-purpose BAM utility - all
533 input and output BAMs must adhere to the PacBio BAM format specification.
534 Non-PacBio BAMs will cause exceptions to be thrown.")
535 (license license:bsd-3)))
537 (define-public blasr-libcpp
539 (name "blasr-libcpp")
544 (url "https://github.com/PacificBiosciences/blasr_libcpp.git")
546 (file-name (git-file-name name version))
549 "0cn5l42zyq67sj0g2imqkhayz2iqvv0a1pgpbmlq0qynjmsrbfd2"))))
550 (build-system meson-build-system)
553 (modify-phases %standard-phases
554 (add-after 'unpack 'link-with-hdf5
555 (lambda* (#:key inputs #:allow-other-keys)
556 (let ((hdf5 (assoc-ref inputs "hdf5")))
557 (substitute* "meson.build"
558 (("libblasr_deps = \\[" m)
561 (format #f "cpp.find_library('hdf5', dirs : '~a'), \
562 cpp.find_library('hdf5_cpp', dirs : '~a'), "
565 (add-after 'unpack 'find-googletest
566 (lambda* (#:key inputs #:allow-other-keys)
567 ;; It doesn't find gtest_main because there's no pkg-config file
568 ;; for it. Find it another way.
569 (substitute* "unittest/meson.build"
570 (("libblasr_gtest_dep = dependency\\('gtest_main'.*")
571 (format #f "cpp = meson.get_compiler('cpp')
572 libblasr_gtest_dep = cpp.find_library('gtest_main', dirs : '~a')\n"
573 (assoc-ref inputs "googletest"))))
575 ;; TODO: unittest/libblasr_unittest cannot be linked
576 ;; ld: ;; unittest/df08227@@libblasr_unittest@exe/alignment_utils_FileUtils_gtest.cpp.o:
577 ;; undefined reference to symbol
578 ;; '_ZN7testing8internal9DeathTest6CreateEPKcPKNS0_2REES3_iPPS1_'
579 ;; ld: /gnu/store/...-googletest-1.8.0/lib/libgtest.so:
580 ;; error adding symbols: DSO missing from command line
582 #:configure-flags '("-Dtests=false")))
589 `(("googletest" ,googletest)
590 ("pkg-config" ,pkg-config)))
591 (home-page "https://github.com/PacificBiosciences/blasr_libcpp")
592 (synopsis "Library for analyzing PacBio genomic sequences")
594 "This package provides three libraries used by applications for analyzing
595 PacBio genomic sequences. This library contains three sub-libraries: pbdata,
597 (license license:bsd-3)))
606 (url "https://github.com/PacificBiosciences/blasr.git")
608 (file-name (git-file-name name version))
611 "1skgy2mvz8gsgfh1gc2nfgwvpyzb1hpmp2cf2773h5wsj8nw22kl"))))
612 (build-system meson-build-system)
615 (modify-phases %standard-phases
616 (add-after 'unpack 'link-with-hdf5
617 (lambda* (#:key inputs #:allow-other-keys)
618 (let ((hdf5 (assoc-ref inputs "hdf5")))
619 (substitute* "meson.build"
620 (("blasr_deps = \\[" m)
623 (format #f "cpp.find_library('hdf5', dirs : '~a'), \
624 cpp.find_library('hdf5_cpp', dirs : '~a'), "
627 ;; Tests require "cram" executable, which is not packaged.
629 #:configure-flags '("-Dtests=false")))
632 ("blasr-libcpp" ,blasr-libcpp)
637 `(("pkg-config" ,pkg-config)))
638 (home-page "https://github.com/PacificBiosciences/blasr")
639 (synopsis "PacBio long read aligner")
641 "Blasr is a genomic sequence aligner for processing PacBio long reads.")
642 (license license:bsd-3)))
644 (define-public ribotaper
650 (uri (string-append "https://ohlerlab.mdc-berlin.de/"
651 "files/RiboTaper/RiboTaper_Version_"
655 "0ykjbps1y3z3085q94npw8i9x5gldc6shy8vlc08v76zljsm07hv"))))
656 (build-system gnu-build-system)
659 (modify-phases %standard-phases
660 (add-after 'install 'wrap-executables
661 (lambda* (#:key inputs outputs #:allow-other-keys)
662 (let* ((out (assoc-ref outputs "out")))
665 (wrap-program (string-append out "/bin/" script)
666 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
667 '("create_annotations_files.bash"
668 "create_metaplots.bash"
669 "Ribotaper_ORF_find.sh"
673 `(("bedtools" ,bedtools-2.18)
674 ("samtools" ,samtools-0.1)
675 ("r-minimal" ,r-minimal)
676 ("r-foreach" ,r-foreach)
677 ("r-xnomial" ,r-xnomial)
679 ("r-multitaper" ,r-multitaper)
680 ("r-seqinr" ,r-seqinr)))
681 (home-page "https://ohlerlab.mdc-berlin.de/software/RiboTaper_126/")
682 (synopsis "Define translated ORFs using ribosome profiling data")
684 "Ribotaper is a method for defining translated @dfn{open reading
685 frames} (ORFs) using ribosome profiling (ribo-seq) data. This package
686 provides the Ribotaper pipeline.")
687 (license license:gpl3+)))
689 (define-public ribodiff
697 (url "https://github.com/ratschlab/RiboDiff.git")
698 (commit (string-append "v" version))))
699 (file-name (git-file-name name version))
702 "0x75nlp7qnmm64jasbi6l21f2cy99r2cjyl6b4hr8zf2bq22drnz"))))
703 (build-system python-build-system)
707 (modify-phases %standard-phases
708 ;; Generate an installable executable script wrapper.
709 (add-after 'unpack 'patch-setup.py
711 (substitute* "setup.py"
712 (("^(.*)packages=.*" line prefix)
713 (string-append line "\n"
714 prefix "scripts=['scripts/TE.py'],\n")))
717 `(("python-numpy" ,python2-numpy)
718 ("python-matplotlib" ,python2-matplotlib)
719 ("python-scipy" ,python2-scipy)
720 ("python-statsmodels" ,python2-statsmodels)))
722 `(("python-mock" ,python2-mock)
723 ("python-nose" ,python2-nose)))
724 (home-page "http://public.bmi.inf.ethz.ch/user/zhongy/RiboDiff/")
725 (synopsis "Detect translation efficiency changes from ribosome footprints")
726 (description "RiboDiff is a statistical tool that detects the protein
727 translational efficiency change from Ribo-Seq (ribosome footprinting) and
728 RNA-Seq data. It uses a generalized linear model to detect genes showing
729 difference in translational profile taking mRNA abundance into account. It
730 facilitates us to decipher the translational regulation that behave
731 independently with transcriptional regulation.")
732 (license license:gpl3+)))
734 (define-public bioawk
741 (url "https://github.com/lh3/bioawk.git")
742 (commit (string-append "v" version))))
743 (file-name (git-file-name name version))
746 "1pxc3zdnirxbf9a0az698hd8xdik7qkhypm7v6hn922x8y9qmspm"))))
747 (build-system gnu-build-system)
753 `(#:tests? #f ; There are no tests to run.
754 ;; Bison must generate files, before other targets can build.
757 (modify-phases %standard-phases
758 (delete 'configure) ; There is no configure phase.
760 (lambda* (#:key outputs #:allow-other-keys)
761 (let* ((out (assoc-ref outputs "out"))
762 (bin (string-append out "/bin"))
763 (man (string-append out "/share/man/man1")))
765 (copy-file "awk.1" (string-append man "/bioawk.1"))
766 (install-file "bioawk" bin))
768 (home-page "https://github.com/lh3/bioawk")
769 (synopsis "AWK with bioinformatics extensions")
770 (description "Bioawk is an extension to Brian Kernighan's awk, adding the
771 support of several common biological data formats, including optionally gzip'ed
772 BED, GFF, SAM, VCF, FASTA/Q and TAB-delimited formats with column names. It
773 also adds a few built-in functions and a command line option to use TAB as the
774 input/output delimiter. When the new functionality is not used, bioawk is
775 intended to behave exactly the same as the original BWK awk.")
776 (license license:x11)))
778 (define-public python-pybedtools
780 (name "python-pybedtools")
784 (uri (pypi-uri "pybedtools" version))
787 "1xl454ijvd4dzfvqgfahad49b49j7qy710fq9xh1rvk42z6x5ssf"))))
788 (build-system python-build-system)
790 `(#:modules ((ice-9 ftw)
794 (guix build python-build-system))
795 ;; See https://github.com/daler/pybedtools/issues/192
797 (modify-phases %standard-phases
798 ;; See https://github.com/daler/pybedtools/issues/261
799 (add-after 'unpack 'disable-broken-tests
801 ;; This test (pybedtools.test.test_scripts.test_venn_mpl) needs a
802 ;; graphical environment.
803 (substitute* "pybedtools/test/test_scripts.py"
804 (("def test_venn_mpl")
805 "def _do_not_test_venn_mpl"))
806 (substitute* "pybedtools/test/test_helpers.py"
807 ;; Requires internet access.
808 (("def test_chromsizes")
809 "def _do_not_test_chromsizes")
810 ;; Broken as a result of the workaround used in the check phase
811 ;; (see: https://github.com/daler/pybedtools/issues/192).
812 (("def test_getting_example_beds")
813 "def _do_not_test_getting_example_beds"))
815 ;; TODO: Remove phase after it's part of PYTHON-BUILD-SYSTEM.
817 ;; Force the Cythonization of C++ files to guard against compilation
819 (add-after 'unpack 'remove-cython-generated-files
821 (let ((cython-sources (map (cut string-drop-right <> 4)
822 (find-files "." "\\.pyx$")))
823 (c/c++-files (find-files "." "\\.(c|cpp|cxx)$")))
824 (define (strip-extension filename)
825 (string-take filename (string-index-right filename #\.)))
826 (define (cythonized? c/c++-file)
827 (member (strip-extension c/c++-file) cython-sources))
828 (for-each delete-file (filter cythonized? c/c++-files))
830 (add-after 'remove-cython-generated-files 'generate-cython-extensions
832 (invoke "python" "setup.py" "cythonize")))
835 (let* ((cwd (getcwd))
836 (build-root-directory (string-append cwd "/build/"))
837 (build (string-append
839 (find (cut string-prefix? "lib" <>)
840 (scandir (string-append
841 build-root-directory)))))
842 (scripts (string-append
844 (find (cut string-prefix? "scripts" <>)
845 (scandir build-root-directory)))))
847 (string-append build ":" (getenv "PYTHONPATH")))
848 ;; Executable scripts such as 'intron_exon_reads.py' must be
849 ;; available in the PATH.
851 (string-append scripts ":" (getenv "PATH"))))
852 ;; The tests need to be run from elsewhere...
853 (mkdir-p "/tmp/test")
854 (copy-recursively "pybedtools/test" "/tmp/test")
855 (with-directory-excursion "/tmp/test"
856 (invoke "pytest")))))))
858 `(("bedtools" ,bedtools)
859 ("samtools" ,samtools)
860 ("python-matplotlib" ,python-matplotlib)
861 ("python-pysam" ,python-pysam)
862 ("python-pyyaml" ,python-pyyaml)))
864 `(("python-numpy" ,python-numpy)
865 ("python-pandas" ,python-pandas)
866 ("python-cython" ,python-cython)
867 ("kentutils" ,kentutils) ; for bedGraphToBigWig
868 ("python-six" ,python-six)
869 ;; For the test suite.
870 ("python-pytest" ,python-pytest)
871 ("python-psutil" ,python-psutil)))
872 (home-page "https://pythonhosted.org/pybedtools/")
873 (synopsis "Python wrapper for BEDtools programs")
875 "pybedtools is a Python wrapper for Aaron Quinlan's BEDtools programs,
876 which are widely used for genomic interval manipulation or \"genome algebra\".
877 pybedtools extends BEDTools by offering feature-level manipulations from with
879 (license license:gpl2+)))
881 (define-public python2-pybedtools
882 (package-with-python2 python-pybedtools))
884 (define-public python-biom-format
886 (name "python-biom-format")
891 ;; Use GitHub as source because PyPI distribution does not contain
892 ;; test data: https://github.com/biocore/biom-format/issues/693
894 (url "https://github.com/biocore/biom-format.git")
896 (file-name (git-file-name name version))
899 "1rna16lyk5aqhnv0dp77wwaplias93f1vw28ad3jmyw6hwkai05v"))
900 (modules '((guix build utils)))
902 ;; Delete generated C files.
903 (for-each delete-file (find-files "." "\\.c"))
905 (build-system python-build-system)
908 (modify-phases %standard-phases
909 (add-after 'unpack 'use-cython
910 (lambda _ (setenv "USE_CYTHON" "1") #t))
911 (add-after 'unpack 'disable-broken-tests
913 (substitute* "biom/tests/test_cli/test_validate_table.py"
914 (("^(.+)def test_invalid_hdf5" m indent)
915 (string-append indent
916 "@npt.dec.skipif(True, msg='Guix')\n"
918 (substitute* "biom/tests/test_table.py"
919 (("^(.+)def test_from_hdf5_issue_731" m indent)
920 (string-append indent
921 "@npt.dec.skipif(True, msg='Guix')\n"
924 (add-before 'reset-gzip-timestamps 'make-files-writable
925 (lambda* (#:key outputs #:allow-other-keys)
926 (let ((out (assoc-ref outputs "out")))
927 (for-each (lambda (file) (chmod file #o644))
928 (find-files out "\\.gz"))
931 `(("python-numpy" ,python-numpy)
932 ("python-scipy" ,python-scipy)
933 ("python-flake8" ,python-flake8)
934 ("python-future" ,python-future)
935 ("python-click" ,python-click)
936 ("python-h5py" ,python-h5py)
937 ("python-pandas" ,python-pandas)))
939 `(("python-cython" ,python-cython)
940 ("python-pytest" ,python-pytest)
941 ("python-pytest-cov" ,python-pytest-cov)
942 ("python-nose" ,python-nose)))
943 (home-page "http://www.biom-format.org")
944 (synopsis "Biological Observation Matrix (BIOM) format utilities")
946 "The BIOM file format is designed to be a general-use format for
947 representing counts of observations e.g. operational taxonomic units, KEGG
948 orthology groups or lipid types, in one or more biological samples
949 e.g. microbiome samples, genomes, metagenomes.")
950 (license license:bsd-3)
951 (properties `((python2-variant . ,(delay python2-biom-format))))))
953 (define-public python2-biom-format
954 (let ((base (package-with-python2 (strip-python2-variant python-biom-format))))
958 (substitute-keyword-arguments (package-arguments base)
960 `(modify-phases ,phases
961 ;; Do not require the unmaintained pyqi library.
962 (add-after 'unpack 'remove-pyqi
964 (substitute* "setup.py"
965 (("install_requires.append\\(\"pyqi\"\\)") "pass"))
968 (define-public bioperl-minimal
969 (let* ((inputs `(("perl-module-build" ,perl-module-build)
970 ("perl-data-stag" ,perl-data-stag)
971 ("perl-libwww" ,perl-libwww)
972 ("perl-uri" ,perl-uri)))
974 (map (compose package-name cadr)
977 (map (compose package-transitive-target-inputs cadr) inputs))))))
979 (name "bioperl-minimal")
984 (uri (string-append "https://github.com/bioperl/bioperl-live/"
986 (string-map (lambda (c)
992 "12phgpxwgkqflkwfb9dcqg7a31dpjlfhar8wcgv0aj5ln4akfz06"))))
993 (build-system perl-build-system)
996 (modify-phases %standard-phases
998 'install 'wrap-programs
999 (lambda* (#:key outputs #:allow-other-keys)
1000 ;; Make sure all executables in "bin" find the required Perl
1001 ;; modules at runtime. As the PERL5LIB variable contains also
1002 ;; the paths of native inputs, we pick the transitive target
1003 ;; inputs from %build-inputs.
1004 (let* ((out (assoc-ref outputs "out"))
1005 (bin (string-append out "/bin/"))
1007 (cons (string-append out "/lib/perl5/site_perl")
1009 (assoc-ref %build-inputs name))
1010 ',transitive-inputs))
1012 (for-each (lambda (file)
1014 `("PERL5LIB" ":" prefix (,path))))
1015 (find-files bin "\\.pl$"))
1019 `(("perl-test-most" ,perl-test-most)))
1020 (home-page "https://metacpan.org/release/BioPerl")
1021 (synopsis "Bioinformatics toolkit")
1023 "BioPerl is the product of a community effort to produce Perl code which
1024 is useful in biology. Examples include Sequence objects, Alignment objects
1025 and database searching objects. These objects not only do what they are
1026 advertised to do in the documentation, but they also interact - Alignment
1027 objects are made from the Sequence objects, Sequence objects have access to
1028 Annotation and SeqFeature objects and databases, Blast objects can be
1029 converted to Alignment objects, and so on. This means that the objects
1030 provide a coordinated and extensible framework to do computational biology.")
1031 (license license:perl-license))))
1033 (define-public python-biopython
1035 (name "python-biopython")
1039 ;; use PyPi rather than biopython.org to ease updating
1040 (uri (pypi-uri "biopython" version))
1043 "0nz4n9d2y2dg849gn1z0vjlkwcpzzkzy3fij7x94a6ixy2c54z2a"))))
1044 (build-system python-build-system)
1047 (modify-phases %standard-phases
1048 (add-before 'check 'set-home
1049 ;; Some tests require a home directory to be set.
1050 (lambda _ (setenv "HOME" "/tmp") #t)))))
1052 `(("python-numpy" ,python-numpy)))
1053 (home-page "http://biopython.org/")
1054 (synopsis "Tools for biological computation in Python")
1056 "Biopython is a set of tools for biological computation including parsers
1057 for bioinformatics files into Python data structures; interfaces to common
1058 bioinformatics programs; a standard sequence class and tools for performing
1059 common operations on them; code to perform data classification; code for
1060 dealing with alignments; code making it easy to split up parallelizable tasks
1061 into separate processes; and more.")
1062 (license (license:non-copyleft "http://www.biopython.org/DIST/LICENSE"))))
1064 (define-public python2-biopython
1065 (package-with-python2 python-biopython))
1067 (define-public python-fastalite
1069 (name "python-fastalite")
1074 (uri (pypi-uri "fastalite" version))
1077 "1qli6pxp77i9xn2wfciq2zaxhl82bdxb33cpzqzj1z25yd036wqj"))))
1078 (build-system python-build-system)
1080 `(#:tests? #f)) ; Test data is not distributed.
1081 (home-page "https://github.com/nhoffman/fastalite")
1082 (synopsis "Simplest possible FASTA parser")
1083 (description "This library implements a FASTA and a FASTQ parser without
1084 relying on a complex dependency tree.")
1085 (license license:expat)))
1087 (define-public python2-fastalite
1088 (package-with-python2 python-fastalite))
1090 (define-public bpp-core
1091 ;; The last release was in 2014 and the recommended way to install from source
1092 ;; is to clone the git repository, so we do this.
1093 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1094 (let ((commit "7d8bced0d1a87291ea8dd7046b7fb5ff9c35c582"))
1097 (version (string-append "2.2.0-1." (string-take commit 7)))
1101 (url "http://biopp.univ-montp2.fr/git/bpp-core")
1103 (file-name (string-append name "-" version "-checkout"))
1106 "10djsq5vlnkilv436gnmh4irpk49v29pa69r6xiryg32xmvn909j"))))
1107 (build-system cmake-build-system)
1109 `(#:parallel-build? #f))
1111 `(("gcc" ,gcc-5))) ; Compilation of bpp-phyl fails with GCC 4.9 so we
1112 ; compile all of the bpp packages with GCC 5.
1113 (home-page "http://biopp.univ-montp2.fr")
1114 (synopsis "C++ libraries for Bioinformatics")
1116 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1117 analysis, phylogenetics, molecular evolution and population genetics. It is
1118 Object Oriented and is designed to be both easy to use and computer efficient.
1119 Bio++ intends to help programmers to write computer expensive programs, by
1120 providing them a set of re-usable tools.")
1121 (license license:cecill-c))))
1123 (define-public bpp-phyl
1124 ;; The last release was in 2014 and the recommended way to install from source
1125 ;; is to clone the git repository, so we do this.
1126 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1127 (let ((commit "0c07167b629f68b569bf274d1ad0c4af83276ae2"))
1130 (version (string-append "2.2.0-1." (string-take commit 7)))
1134 (url "http://biopp.univ-montp2.fr/git/bpp-phyl")
1136 (file-name (string-append name "-" version "-checkout"))
1139 "1ssjgchzwj3iai26kyly7gwkdv8sk59nqhkb1wpap3sf5m6kyllh"))))
1140 (build-system cmake-build-system)
1142 `(#:parallel-build? #f
1143 ;; If out-of-source, test data is not copied into the build directory
1144 ;; so the tests fail.
1145 #:out-of-source? #f))
1147 `(("bpp-core" ,bpp-core)
1148 ("bpp-seq" ,bpp-seq)
1149 ;; GCC 4.8 fails due to an 'internal compiler error', so we use a more
1152 (home-page "http://biopp.univ-montp2.fr")
1153 (synopsis "Bio++ phylogenetic Library")
1155 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1156 analysis, phylogenetics, molecular evolution and population genetics. This
1157 library provides phylogenetics-related modules.")
1158 (license license:cecill-c))))
1160 (define-public bpp-popgen
1161 ;; The last release was in 2014 and the recommended way to install from source
1162 ;; is to clone the git repository, so we do this.
1163 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1164 (let ((commit "e472bac9b1a148803895d747cd6d0c5904f85d9f"))
1167 (version (string-append "2.2.0-1." (string-take commit 7)))
1171 (url "http://biopp.univ-montp2.fr/git/bpp-popgen")
1173 (file-name (string-append name "-" version "-checkout"))
1176 "0yn82dzn1n5629nzja68xfrhi655709rjanyryb36vzkmymy6dw5"))))
1177 (build-system cmake-build-system)
1179 `(#:parallel-build? #f
1180 #:tests? #f)) ; There are no tests.
1182 `(("bpp-core" ,bpp-core)
1183 ("bpp-seq" ,bpp-seq)
1185 (home-page "http://biopp.univ-montp2.fr")
1186 (synopsis "Bio++ population genetics library")
1188 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1189 analysis, phylogenetics, molecular evolution and population genetics. This
1190 library provides population genetics-related modules.")
1191 (license license:cecill-c))))
1193 (define-public bpp-seq
1194 ;; The last release was in 2014 and the recommended way to install from source
1195 ;; is to clone the git repository, so we do this.
1196 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1197 (let ((commit "6cfa07965ce152e5598a89df2fa80a75973bfa33"))
1200 (version (string-append "2.2.0-1." (string-take commit 7)))
1204 (url "http://biopp.univ-montp2.fr/git/bpp-seq")
1206 (file-name (string-append name "-" version "-checkout"))
1209 "1nys5jq7jqvdg40d91wsmj3q2yzy4276cp7sp44n67p468f27zf2"))))
1210 (build-system cmake-build-system)
1212 `(#:parallel-build? #f
1213 ;; If out-of-source, test data is not copied into the build directory
1214 ;; so the tests fail.
1215 #:out-of-source? #f))
1217 `(("bpp-core" ,bpp-core)
1218 ("gcc" ,gcc-5))) ; Use GCC 5 as per 'bpp-core'.
1219 (home-page "http://biopp.univ-montp2.fr")
1220 (synopsis "Bio++ sequence library")
1222 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1223 analysis, phylogenetics, molecular evolution and population genetics. This
1224 library provides sequence-related modules.")
1225 (license license:cecill-c))))
1227 (define-public bppsuite
1228 ;; The last release was in 2014 and the recommended way to install from source
1229 ;; is to clone the git repository, so we do this.
1230 ;; http://biopp.univ-montp2.fr/wiki/index.php/Main_Page
1231 (let ((commit "c516147f57aa50961121cd505bed52cd7603698b"))
1234 (version (string-append "2.2.0-1." (string-take commit 7)))
1238 (url "http://biopp.univ-montp2.fr/git/bppsuite")
1240 (file-name (string-append name "-" version "-checkout"))
1243 "1y87pxvw0jxjizhq2dr9g2r91md45k1p9ih2sl1yy1y3p934l2kb"))))
1244 (build-system cmake-build-system)
1246 `(#:parallel-build? #f
1247 #:tests? #f)) ; There are no tests.
1251 ("texinfo" ,texinfo)))
1253 `(("bpp-core" ,bpp-core)
1254 ("bpp-seq" ,bpp-seq)
1255 ("bpp-phyl" ,bpp-phyl)
1256 ("bpp-phyl" ,bpp-popgen)
1258 (home-page "http://biopp.univ-montp2.fr")
1259 (synopsis "Bioinformatics tools written with the Bio++ libraries")
1261 "Bio++ is a set of C++ libraries for Bioinformatics, including sequence
1262 analysis, phylogenetics, molecular evolution and population genetics. This
1263 package provides command line tools using the Bio++ library.")
1264 (license license:cecill-c))))
1266 (define-public blast+
1273 "ftp://ftp.ncbi.nlm.nih.gov/blast/executables/blast+/"
1274 version "/ncbi-blast-" version "+-src.tar.gz"))
1277 "1jlq0afxxgczpp35k6mxh8mn4jzq7vqcnaixk166sfj10wq8v9qh"))
1278 (modules '((guix build utils)))
1281 ;; Remove bundled bzip2, zlib and pcre.
1282 (delete-file-recursively "c++/src/util/compress/bzip2")
1283 (delete-file-recursively "c++/src/util/compress/zlib")
1284 (delete-file-recursively "c++/src/util/regexp")
1285 (substitute* "c++/src/util/compress/Makefile.in"
1286 (("bzip2 zlib api") "api"))
1287 ;; Remove useless msbuild directory
1288 (delete-file-recursively
1289 "c++/src/build-system/project_tree_builder/msbuild")
1291 (build-system gnu-build-system)
1293 `(;; There are two(!) tests for this massive library, and both fail with
1294 ;; "unparsable timing stats".
1295 ;; ERR [127] -- [serial/datatool] datatool.sh (unparsable timing stats)
1296 ;; ERR [127] -- [serial/datatool] datatool_xml.sh (unparsable timing stats)
1299 #:parallel-build? #f ; not supported
1301 (modify-phases %standard-phases
1302 (add-before 'configure 'set-HOME
1303 ;; $HOME needs to be set at some point during the configure phase
1304 (lambda _ (setenv "HOME" "/tmp") #t))
1305 (add-after 'unpack 'enter-dir
1306 (lambda _ (chdir "c++") #t))
1307 (add-after 'enter-dir 'fix-build-system
1309 (define (which* cmd)
1310 (cond ((string=? cmd "date")
1311 ;; make call to "date" deterministic
1316 (format (current-error-port)
1317 "WARNING: Unable to find absolute path for ~s~%"
1321 ;; Rewrite hardcoded paths to various tools
1322 (substitute* (append '("src/build-system/configure.ac"
1323 "src/build-system/configure"
1324 "src/build-system/helpers/run_with_lock.c"
1325 "scripts/common/impl/if_diff.sh"
1326 "scripts/common/impl/run_with_lock.sh"
1327 "src/build-system/Makefile.configurables.real"
1328 "src/build-system/Makefile.in.top"
1329 "src/build-system/Makefile.meta.gmake=no"
1330 "src/build-system/Makefile.meta.in"
1331 "src/build-system/Makefile.meta_l"
1332 "src/build-system/Makefile.meta_p"
1333 "src/build-system/Makefile.meta_r"
1334 "src/build-system/Makefile.mk.in"
1335 "src/build-system/Makefile.requirements"
1336 "src/build-system/Makefile.rules_with_autodep.in")
1337 (find-files "scripts/common/check" "\\.sh$"))
1338 (("(/usr/bin/|/bin/)([a-z][-_.a-z]*)" all dir cmd)
1339 (or (which* cmd) all)))
1341 (substitute* (find-files "src/build-system" "^config.*")
1342 (("LN_S=/bin/\\$LN_S") (string-append "LN_S=" (which "ln")))
1345 ;; rewrite "/var/tmp" in check script
1346 (substitute* "scripts/common/check/check_make_unix.sh"
1347 (("/var/tmp") "/tmp"))
1349 ;; do not reset PATH
1350 (substitute* (find-files "scripts/common/impl/" "\\.sh$")
1352 (("action=/bin/") "action=")
1353 (("export PATH") ":"))
1356 (lambda* (#:key inputs outputs #:allow-other-keys)
1357 (let ((out (assoc-ref outputs "out"))
1358 (lib (string-append (assoc-ref outputs "lib") "/lib"))
1359 (include (string-append (assoc-ref outputs "include")
1360 "/include/ncbi-tools++")))
1361 ;; The 'configure' script doesn't recognize things like
1362 ;; '--enable-fast-install'.
1363 (invoke "./configure.orig"
1364 (string-append "--with-build-root=" (getcwd) "/build")
1365 (string-append "--prefix=" out)
1366 (string-append "--libdir=" lib)
1367 (string-append "--includedir=" include)
1368 (string-append "--with-bz2="
1369 (assoc-ref inputs "bzip2"))
1370 (string-append "--with-z="
1371 (assoc-ref inputs "zlib"))
1372 (string-append "--with-pcre="
1373 (assoc-ref inputs "pcre"))
1374 ;; Each library is built twice by default, once
1375 ;; with "-static" in its name, and again
1380 (outputs '("out" ; 21 MB
1389 ("python" ,python-wrapper)))
1392 (home-page "http://blast.ncbi.nlm.nih.gov")
1393 (synopsis "Basic local alignment search tool")
1395 "BLAST is a popular method of performing a DNA or protein sequence
1396 similarity search, using heuristics to produce results quickly. It also
1397 calculates an “expect value” that estimates how many matches would have
1398 occurred at a given score by chance, which can aid a user in judging how much
1399 confidence to have in an alignment.")
1400 ;; Most of the sources are in the public domain, with the following
1403 ;; * ./c++/include/util/bitset/
1404 ;; * ./c++/src/html/ncbi_menu*.js
1406 ;; * ./c++/include/util/impl/floating_point_comparison.hpp
1408 ;; * ./c++/include/dbapi/driver/odbc/unix_odbc/
1410 ;; * ./c++/src/corelib/teamcity_*
1411 (license (list license:public-domain
1417 (define-public bless
1423 (uri (string-append "mirror://sourceforge/bless-ec/bless.v"
1427 "0rm0gw2s18dqwzzpl3c2x1z05ni2v0xz5dmfk3d33j6g4cgrlrdd"))
1428 (modules '((guix build utils)))
1431 ;; Remove bundled boost, pigz, zlib, and .git directory
1432 ;; FIXME: also remove bundled sources for murmurhash3 and
1433 ;; kmc once packaged.
1434 (delete-file-recursively "boost")
1435 (delete-file-recursively "pigz")
1436 (delete-file-recursively "google-sparsehash")
1437 (delete-file-recursively "zlib")
1438 (delete-file-recursively ".git")
1440 (build-system gnu-build-system)
1442 '(#:tests? #f ;no "check" target
1444 (list (string-append "ZLIB="
1445 (assoc-ref %build-inputs "zlib:static")
1447 (string-append "LDFLAGS="
1448 (string-join '("-lboost_filesystem"
1455 (modify-phases %standard-phases
1456 (add-after 'unpack 'do-not-build-bundled-pigz
1457 (lambda* (#:key inputs outputs #:allow-other-keys)
1458 (substitute* "Makefile"
1459 (("cd pigz/pigz-2.3.3; make") ""))
1461 (add-after 'unpack 'patch-paths-to-executables
1462 (lambda* (#:key inputs outputs #:allow-other-keys)
1463 (substitute* "parse_args.cpp"
1464 (("kmc_binary = .*")
1465 (string-append "kmc_binary = \""
1466 (assoc-ref outputs "out")
1468 (("pigz_binary = .*")
1469 (string-append "pigz_binary = \""
1470 (assoc-ref inputs "pigz")
1474 (lambda* (#:key outputs #:allow-other-keys)
1475 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
1476 (for-each (lambda (file)
1477 (install-file file bin))
1478 '("bless" "kmc/bin/kmc"))
1480 (delete 'configure))))
1484 `(("openmpi" ,openmpi)
1486 ("sparsehash" ,sparsehash)
1488 ("zlib:static" ,zlib "static")
1490 (supported-systems '("x86_64-linux"))
1491 (home-page "https://sourceforge.net/p/bless-ec/wiki/Home/")
1492 (synopsis "Bloom-filter-based error correction tool for NGS reads")
1494 "@dfn{Bloom-filter-based error correction solution for high-throughput
1495 sequencing reads} (BLESS) uses a single minimum-sized bloom filter is a
1496 correction tool for genomic reads produced by @dfn{Next-generation
1497 sequencing} (NGS). BLESS produces accurate correction results with much less
1498 memory compared with previous solutions and is also able to tolerate a higher
1499 false-positive rate. BLESS can extend reads like DNA assemblers to correct
1500 errors at the end of reads.")
1501 (license license:gpl3+)))
1503 (define-public bowtie
1510 (url "https://github.com/BenLangmead/bowtie2.git")
1511 (commit (string-append "v" version))))
1512 (file-name (git-file-name name version))
1515 "1zl3cf327y2p7p03cavymbh7b00djc7lncfaqih33n96iy9q8ibp"))
1516 (modules '((guix build utils)))
1519 (substitute* "Makefile"
1520 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1521 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1522 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
1524 (build-system gnu-build-system)
1529 (string-append "prefix=" (assoc-ref %outputs "out")))
1531 (modify-phases %standard-phases
1536 "scripts/test/simple_tests.pl"
1537 "--bowtie2=./bowtie2"
1538 "--bowtie2-build=./bowtie2-build")
1543 ("python" ,python-wrapper)))
1546 ("perl-clone" ,perl-clone)
1547 ("perl-test-deep" ,perl-test-deep)
1548 ("perl-test-simple" ,perl-test-simple)))
1549 (home-page "http://bowtie-bio.sourceforge.net/bowtie2/index.shtml")
1550 (synopsis "Fast and sensitive nucleotide sequence read aligner")
1552 "Bowtie 2 is a fast and memory-efficient tool for aligning sequencing
1553 reads to long reference sequences. It is particularly good at aligning reads
1554 of about 50 up to 100s or 1,000s of characters, and particularly good at
1555 aligning to relatively long (e.g. mammalian) genomes. Bowtie 2 indexes the
1556 genome with an FM Index to keep its memory footprint small: for the human
1557 genome, its memory footprint is typically around 3.2 GB. Bowtie 2 supports
1558 gapped, local, and paired-end alignment modes.")
1559 (supported-systems '("x86_64-linux"))
1560 (license license:gpl3+)))
1562 (define-public bowtie1
1568 (uri (string-append "mirror://sourceforge/bowtie-bio/bowtie/"
1569 version "/bowtie-" version "-src.zip"))
1572 "1jl2cj9bz8lwz8dwnxbycn8yp8g4kky62fkcxifyf1ri0y6n2vc0"))
1573 (modules '((guix build utils)))
1575 '(substitute* "Makefile"
1576 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
1577 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
1578 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\"")))))
1579 (build-system gnu-build-system)
1581 '(#:tests? #f ; no "check" target
1584 (string-append "prefix=" (assoc-ref %outputs "out")))
1586 (modify-phases %standard-phases
1587 (delete 'configure))))
1591 (supported-systems '("x86_64-linux"))
1592 (home-page "http://bowtie-bio.sourceforge.net/index.shtml")
1593 (synopsis "Fast aligner for short nucleotide sequence reads")
1595 "Bowtie is a fast, memory-efficient short read aligner. It aligns short
1596 DNA sequences (reads) to the human genome at a rate of over 25 million 35-bp
1597 reads per hour. Bowtie indexes the genome with a Burrows-Wheeler index to
1598 keep its memory footprint small: typically about 2.2 GB for the human
1599 genome (2.9 GB for paired-end).")
1600 (license license:artistic2.0)))
1602 (define-public tophat
1609 "http://ccb.jhu.edu/software/tophat/downloads/tophat-"
1613 "19add02kv2xhd6ihd779dr7x35ggym3jqr0m5c4315i1yfb0p11p"))
1614 (modules '((guix build utils)))
1617 ;; Remove bundled SeqAn and samtools
1618 (delete-file-recursively "src/SeqAn-1.4.2")
1619 (delete-file-recursively "src/samtools-0.1.18")
1621 (build-system gnu-build-system)
1623 '(#:parallel-build? #f ; not supported
1625 (modify-phases %standard-phases
1626 (add-after 'unpack 'use-system-samtools
1627 (lambda* (#:key inputs #:allow-other-keys)
1628 (substitute* "src/Makefile.in"
1629 (("(noinst_LIBRARIES = )\\$\\(SAMLIB\\)" _ prefix) prefix)
1630 (("\\$\\(SAMPROG\\): \\$\\(SAMLIB\\)") "")
1631 (("SAMPROG = samtools_0\\.1\\.18") "")
1632 (("\\$\\(samtools_0_1_18_SOURCES\\)") "")
1633 (("am__EXEEXT_1 = samtools_0\\.1\\.18\\$\\(EXEEXT\\)") ""))
1634 (substitute* '("src/common.cpp"
1636 (("samtools_0.1.18") (which "samtools")))
1637 (substitute* '("src/common.h"
1638 "src/bam2fastx.cpp")
1639 (("#include \"bam.h\"") "#include <samtools/bam.h>")
1640 (("#include \"sam.h\"") "#include <samtools/sam.h>"))
1641 (substitute* '("src/bwt_map.h"
1643 "src/align_status.h")
1644 (("#include <bam.h>") "#include <samtools/bam.h>")
1645 (("#include <sam.h>") "#include <samtools/sam.h>"))
1650 ("samtools" ,samtools-0.1)
1651 ("ncurses" ,ncurses)
1652 ("python" ,python-2)
1655 ("seqan" ,seqan-1)))
1656 (home-page "http://ccb.jhu.edu/software/tophat/index.shtml")
1657 (synopsis "Spliced read mapper for RNA-Seq data")
1659 "TopHat is a fast splice junction mapper for nucleotide sequence
1660 reads produced by the RNA-Seq method. It aligns RNA-Seq reads to
1661 mammalian-sized genomes using the ultra high-throughput short read
1662 aligner Bowtie, and then analyzes the mapping results to identify
1663 splice junctions between exons.")
1664 ;; TopHat is released under the Boost Software License, Version 1.0
1665 ;; See https://github.com/infphilo/tophat/issues/11#issuecomment-121589893
1666 (license license:boost1.0)))
1675 "https://github.com/lh3/bwa/releases/download/v"
1676 version "/bwa-" version ".tar.bz2"))
1679 "1zfhv2zg9v1icdlq4p9ssc8k01mca5d1bd87w71py2swfi74s6yy"))))
1680 (build-system gnu-build-system)
1682 '(#:tests? #f ;no "check" target
1684 (modify-phases %standard-phases
1686 (lambda* (#:key outputs #:allow-other-keys)
1687 (let ((bin (string-append
1688 (assoc-ref outputs "out") "/bin"))
1690 (assoc-ref outputs "out") "/share/doc/bwa"))
1692 (assoc-ref outputs "out") "/share/man/man1")))
1693 (install-file "bwa" bin)
1694 (install-file "README.md" doc)
1695 (install-file "bwa.1" man))
1697 ;; no "configure" script
1698 (delete 'configure))))
1699 (inputs `(("zlib" ,zlib)))
1700 ;; Non-portable SSE instructions are used so building fails on platforms
1701 ;; other than x86_64.
1702 (supported-systems '("x86_64-linux"))
1703 (home-page "http://bio-bwa.sourceforge.net/")
1704 (synopsis "Burrows-Wheeler sequence aligner")
1706 "BWA is a software package for mapping low-divergent sequences against a
1707 large reference genome, such as the human genome. It consists of three
1708 algorithms: BWA-backtrack, BWA-SW and BWA-MEM. The first algorithm is
1709 designed for Illumina sequence reads up to 100bp, while the rest two for
1710 longer sequences ranged from 70bp to 1Mbp. BWA-MEM and BWA-SW share similar
1711 features such as long-read support and split alignment, but BWA-MEM, which is
1712 the latest, is generally recommended for high-quality queries as it is faster
1713 and more accurate. BWA-MEM also has better performance than BWA-backtrack for
1714 70-100bp Illumina reads.")
1715 (license license:gpl3+)))
1717 (define-public bwa-pssm
1718 (package (inherit bwa)
1724 (url "https://github.com/pkerpedjiev/bwa-pssm.git")
1726 (file-name (git-file-name name version))
1729 "076c4q0cdqz8jgylb067y9zmvxglppnzi3qiscn0xiypgc6lgb5r"))))
1730 (build-system gnu-build-system)
1735 (home-page "http://bwa-pssm.binf.ku.dk/")
1736 (synopsis "Burrows-Wheeler transform-based probabilistic short read mapper")
1738 "BWA-PSSM is a probabilistic short genomic sequence read aligner based on
1739 the use of @dfn{position specific scoring matrices} (PSSM). Like many of the
1740 existing aligners it is fast and sensitive. Unlike most other aligners,
1741 however, it is also adaptible in the sense that one can direct the alignment
1742 based on known biases within the data set. It is coded as a modification of
1743 the original BWA alignment program and shares the genome index structure as
1744 well as many of the command line options.")
1745 (license license:gpl3+)))
1747 (define-public bwa-meth
1754 (url "https://github.com/brentp/bwa-meth.git")
1755 (commit (string-append "v" version))))
1756 (file-name (git-file-name name version))
1759 "17j31i7zws5j7mhsq9x3qgkxly6mlmrgwhfq0qbflgxrmx04yaiz"))))
1760 (build-system python-build-system)
1763 (modify-phases %standard-phases
1764 (add-after 'unpack 'keep-references-to-bwa
1765 (lambda* (#:key inputs #:allow-other-keys)
1766 (substitute* "bwameth.py"
1768 (string-append (which "bwa") " mem"))
1769 ;; There's an ill-advised check for "samtools" on PATH.
1775 `(("python-toolshed" ,python-toolshed)))
1776 (home-page "https://github.com/brentp/bwa-meth")
1777 (synopsis "Fast and accurante alignment of BS-Seq reads")
1779 "BWA-Meth works for single-end reads and for paired-end reads from the
1780 directional protocol (most common). It uses the method employed by
1781 methylcoder and Bismark of in silico conversion of all C's to T's in both
1782 reference and reads. It recovers the original read (needed to tabulate
1783 methylation) by attaching it as a comment which BWA appends as a tag to the
1784 read. It performs favorably to existing aligners gauged by number of on and
1785 off-target reads for a capture method that targets CpG-rich region.")
1786 (license license:expat)))
1788 (define-public python-bx-python
1790 (name "python-bx-python")
1794 (uri (pypi-uri "bx-python" version))
1797 "11kksg2rbzihpmcid823xvg42xi88m7sz58rzk29abybkxy0rszs"))))
1798 (build-system python-build-system)
1799 ;; Tests fail because test data are not included
1800 (arguments '(#:tests? #f))
1802 `(("python-numpy" ,python-numpy)
1803 ("python-six" ,python-six)))
1807 `(("python-lzo" ,python-lzo)
1808 ("python-nose" ,python-nose)
1809 ("python-cython" ,python-cython)))
1810 (home-page "https://github.com/bxlab/bx-python")
1811 (synopsis "Tools for manipulating biological data")
1813 "bx-python provides tools for manipulating biological data, particularly
1814 multiple sequence alignments.")
1815 (license license:expat)))
1817 (define-public python2-bx-python
1818 (package-with-python2 python-bx-python))
1820 (define-public python-pysam
1822 (name "python-pysam")
1826 ;; Test data is missing on PyPi.
1828 (url "https://github.com/pysam-developers/pysam.git")
1829 (commit (string-append "v" version))))
1830 (file-name (git-file-name name version))
1833 "1vj367w6xbn9bpmksm162l1aipf7cj97h1q83y7jcpm33ihwpf7x"))
1834 (modules '((guix build utils)))
1836 ;; Drop bundled htslib. TODO: Also remove samtools
1838 (delete-file-recursively "htslib")
1840 (build-system python-build-system)
1842 `(#:modules ((ice-9 ftw)
1844 (guix build python-build-system)
1847 (modify-phases %standard-phases
1848 (add-before 'build 'set-flags
1849 (lambda* (#:key inputs #:allow-other-keys)
1850 (setenv "HTSLIB_MODE" "external")
1851 (setenv "HTSLIB_LIBRARY_DIR"
1852 (string-append (assoc-ref inputs "htslib") "/lib"))
1853 (setenv "HTSLIB_INCLUDE_DIR"
1854 (string-append (assoc-ref inputs "htslib") "/include"))
1855 (setenv "LDFLAGS" "-lncurses")
1856 (setenv "CFLAGS" "-D_CURSES_LIB=1")
1859 (lambda* (#:key inputs outputs #:allow-other-keys)
1860 ;; This file contains tests that require a connection to the
1862 (delete-file "tests/tabix_test.py")
1863 ;; FIXME: This test fails
1864 (delete-file "tests/AlignmentFile_test.py")
1865 ;; Add first subdirectory of "build" directory to PYTHONPATH.
1866 (setenv "PYTHONPATH"
1868 (getenv "PYTHONPATH")
1869 ":" (getcwd) "/build/"
1870 (car (scandir "build"
1871 (negate (cut string-prefix? "." <>))))))
1872 ;; Step out of source dir so python does not import from CWD.
1873 (with-directory-excursion "tests"
1874 (setenv "HOME" "/tmp")
1875 (invoke "make" "-C" "pysam_data")
1876 (invoke "make" "-C" "cbcf_data")
1877 ;; Running nosetests without explicitly asking for a single
1878 ;; process leads to a crash. Running with multiple processes
1879 ;; fails because the tests are not designed to run in parallel.
1881 ;; FIXME: tests keep timing out on some systems.
1882 (invoke "nosetests" "-v" "--processes" "1")))))))
1884 `(("htslib" ,htslib))) ; Included from installed header files.
1886 `(("ncurses" ,ncurses)
1890 `(("python-cython" ,python-cython)
1891 ;; Dependencies below are are for tests only.
1892 ("samtools" ,samtools)
1893 ("bcftools" ,bcftools)
1894 ("python-nose" ,python-nose)))
1895 (home-page "https://github.com/pysam-developers/pysam")
1896 (synopsis "Python bindings to the SAMtools C API")
1898 "Pysam is a Python module for reading and manipulating files in the
1899 SAM/BAM format. Pysam is a lightweight wrapper of the SAMtools C API. It
1900 also includes an interface for tabix.")
1901 (license license:expat)))
1903 (define-public python2-pysam
1904 (package-with-python2 python-pysam))
1906 (define-public python-twobitreader
1908 (name "python-twobitreader")
1913 (url "https://github.com/benjschiller/twobitreader")
1915 (file-name (git-file-name name version))
1918 "1qbxvv1h58cismbk1anpjrkpghsaiy64a11ir3lhy6qch6xf8n62"))))
1919 (build-system python-build-system)
1920 ;; Tests are not included
1921 (arguments '(#:tests? #f))
1923 `(("python-sphinx" ,python-sphinx)))
1924 (home-page "https://github.com/benjschiller/twobitreader")
1925 (synopsis "Python library for reading .2bit files")
1927 "twobitreader is a Python library for reading .2bit files as used by the
1928 UCSC genome browser.")
1929 (license license:artistic2.0)))
1931 (define-public python2-twobitreader
1932 (package-with-python2 python-twobitreader))
1934 (define-public python-plastid
1936 (name "python-plastid")
1940 (uri (pypi-uri "plastid" version))
1943 "0l24dd3q66if8yj042m4s0g95n6acn7im1imqd3p6h8ns43kxhj8"))))
1944 (build-system python-build-system)
1946 ;; Some test files are not included.
1949 `(("python-numpy" ,python-numpy)
1950 ("python-scipy" ,python-scipy)
1951 ("python-pandas" ,python-pandas)
1952 ("python-pysam" ,python-pysam)
1953 ("python-matplotlib" ,python-matplotlib)
1954 ("python-biopython" ,python-biopython)
1955 ("python-twobitreader" ,python-twobitreader)
1956 ("python-termcolor" ,python-termcolor)))
1958 `(("python-cython" ,python-cython)
1959 ("python-nose" ,python-nose)))
1960 (home-page "https://github.com/joshuagryphon/plastid")
1961 (synopsis "Python library for genomic analysis")
1963 "plastid is a Python library for genomic analysis – in particular,
1964 high-throughput sequencing data – with an emphasis on simplicity.")
1965 (license license:bsd-3)))
1967 (define-public python2-plastid
1968 (package-with-python2 python-plastid))
1970 (define-public tetoolkit
1977 (url "https://github.com/mhammell-laboratory/tetoolkit.git")
1979 (file-name (git-file-name name version))
1982 "1yzi0kfpzip8zpjb82x1ik6h22yzfyjiz2dv85v6as2awwqvk807"))))
1983 (build-system python-build-system)
1985 `(#:python ,python-2 ; not guaranteed to work with Python 3
1987 (modify-phases %standard-phases
1988 (add-after 'unpack 'make-writable
1990 (for-each make-file-writable (find-files "."))
1992 (add-after 'unpack 'patch-invocations
1993 (lambda* (#:key inputs #:allow-other-keys)
1994 (substitute* '("bin/TEtranscripts"
1997 (string-append "'" (which "sort") " "))
1999 (string-append "'" (which "rm") " -f "))
2000 (("'Rscript'") (string-append "'" (which "Rscript") "'")))
2001 (substitute* "TEToolkit/IO/ReadInputs.py"
2002 (("BamToBED") (which "bamToBed")))
2003 (substitute* "TEToolkit/Normalization.py"
2005 (string-append "\"" (which "Rscript") "\"")))
2007 (add-after 'install 'wrap-program
2008 (lambda* (#:key outputs #:allow-other-keys)
2009 ;; Make sure the executables find R packages.
2010 (let ((out (assoc-ref outputs "out")))
2013 (wrap-program (string-append out "/bin/" script)
2014 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
2019 `(("coreutils" ,coreutils)
2020 ("bedtools" ,bedtools)
2021 ("python-argparse" ,python2-argparse)
2022 ("python-pysam" ,python2-pysam)
2023 ("r-minimal" ,r-minimal)
2024 ("r-deseq2" ,r-deseq2)))
2025 (home-page "https://github.com/mhammell-laboratory/tetoolkit")
2026 (synopsis "Transposable elements in differential enrichment analysis")
2028 "This is package for including transposable elements in differential
2029 enrichment analysis of sequencing datasets. TEtranscripts and TEcount take
2030 RNA-seq (and similar data) and annotates reads to both genes and transposable
2031 elements. TEtranscripts then performs differential analysis using DESeq2.
2032 Note that TEtranscripts and TEcount rely on specially curated GTF files, which
2033 are not included due to their size.")
2034 (license license:gpl3+)))
2036 (define-public cd-hit
2042 (uri (string-append "https://github.com/weizhongli/cdhit"
2043 "/releases/download/V" version
2045 "-2017-0621-source.tar.gz"))
2048 "1b4mwm2520ixjbw57sil20f9iixzw4bkdqqwgg1fc3pzm6rz4zmn"))))
2049 (build-system gnu-build-system)
2051 `(#:tests? #f ; there are no tests
2053 ;; Executables are copied directly to the PREFIX.
2054 (list (string-append "PREFIX=" (assoc-ref %outputs "out") "/bin")
2055 ;; Support longer sequences (e.g. Pacbio sequences)
2058 (modify-phases %standard-phases
2059 ;; No "configure" script
2061 ;; Remove sources of non-determinism
2062 (add-after 'unpack 'be-timeless
2064 (substitute* "cdhit-utility.c++"
2065 ((" \\(built on \" __DATE__ \"\\)") ""))
2066 (substitute* "cdhit-common.c++"
2067 (("__DATE__") "\"0\"")
2068 (("\", %s, \" __TIME__ \"\\\\n\", date") ""))
2070 ;; The "install" target does not create the target directory.
2071 (add-before 'install 'create-target-dir
2072 (lambda* (#:key outputs #:allow-other-keys)
2073 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
2077 (home-page "http://weizhongli-lab.org/cd-hit/")
2078 (synopsis "Cluster and compare protein or nucleotide sequences")
2080 "CD-HIT is a program for clustering and comparing protein or nucleotide
2081 sequences. CD-HIT is designed to be fast and handle extremely large
2083 ;; The manual says: "It can be copied under the GNU General Public License
2084 ;; version 2 (GPLv2)."
2085 (license license:gpl2)))
2087 (define-public clipper
2094 (url "https://github.com/YeoLab/clipper.git")
2096 (file-name (git-file-name name version))
2099 "0fja1rj84wp9vpj8rxpj3n8zqzcqq454m904yp9as1w4phccirjb"))
2100 (modules '((guix build utils)))
2103 ;; remove unnecessary setup dependency
2104 (substitute* "setup.py"
2105 (("setup_requires = .*") ""))
2107 (build-system python-build-system)
2109 `(#:python ,python-2 ; only Python 2 is supported
2111 (modify-phases %standard-phases
2112 ;; This is fixed in upstream commit
2113 ;; f6c2990198f906bf97730d95695b4bd5a6d01ddb.
2114 (add-after 'unpack 'fix-typo
2116 (substitute* "clipper/src/readsToWiggle.pyx"
2120 `(("htseq" ,python2-htseq)
2121 ("python-pybedtools" ,python2-pybedtools)
2122 ("python-cython" ,python2-cython)
2123 ("python-scikit-learn" ,python2-scikit-learn)
2124 ("python-matplotlib" ,python2-matplotlib)
2125 ("python-pandas" ,python2-pandas)
2126 ("python-pysam" ,python2-pysam)
2127 ("python-numpy" ,python2-numpy)
2128 ("python-scipy" ,python2-scipy)))
2130 `(("python-mock" ,python2-mock) ; for tests
2131 ("python-nose" ,python2-nose) ; for tests
2132 ("python-pytz" ,python2-pytz))) ; for tests
2133 (home-page "https://github.com/YeoLab/clipper")
2134 (synopsis "CLIP peak enrichment recognition")
2136 "CLIPper is a tool to define peaks in CLIP-seq datasets.")
2137 (license license:gpl2)))
2139 (define-public codingquarry
2141 (name "codingquarry")
2146 "mirror://sourceforge/codingquarry/CodingQuarry_v"
2150 "0115hkjflsnfzn36xppwf9h9avfxlavr43djqmshkkzbgjzsz60i"))))
2151 (build-system gnu-build-system)
2153 '(#:tests? #f ; no "check" target
2155 (modify-phases %standard-phases
2158 (lambda* (#:key outputs #:allow-other-keys)
2159 (let* ((out (assoc-ref outputs "out"))
2160 (bin (string-append out "/bin"))
2161 (doc (string-append out "/share/doc/codingquarry")))
2162 (install-file "INSTRUCTIONS.pdf" doc)
2163 (copy-recursively "QuarryFiles"
2164 (string-append out "/QuarryFiles"))
2165 (install-file "CodingQuarry" bin)
2166 (install-file "CufflinksGTF_to_CodingQuarryGFF3.py" bin))
2168 (inputs `(("openmpi" ,openmpi)))
2169 (native-search-paths
2170 (list (search-path-specification
2171 (variable "QUARRY_PATH")
2172 (files '("QuarryFiles")))))
2173 (native-inputs `(("python" ,python-2))) ; Only Python 2 is supported
2174 (synopsis "Fungal gene predictor")
2175 (description "CodingQuarry is a highly accurate, self-training GHMM fungal
2176 gene predictor designed to work with assembled, aligned RNA-seq transcripts.")
2177 (home-page "https://sourceforge.net/projects/codingquarry/")
2178 (license license:gpl3+)))
2180 (define-public couger
2187 "http://couger.oit.duke.edu/static/assets/COUGER"
2191 "04p2b14nmhzxw5h72mpzdhalv21bx4w9b87z0wpw0xzxpysyncmq"))))
2192 (build-system gnu-build-system)
2196 (modify-phases %standard-phases
2201 (lambda* (#:key outputs #:allow-other-keys)
2202 (let* ((out (assoc-ref outputs "out"))
2203 (bin (string-append out "/bin")))
2204 (copy-recursively "src" (string-append out "/src"))
2206 ;; Add "src" directory to module lookup path.
2207 (substitute* "couger"
2209 (string-append "import sys\nsys.path.append(\""
2210 out "\")\nfrom argparse")))
2211 (install-file "couger" bin))
2214 'install 'wrap-program
2215 (lambda* (#:key inputs outputs #:allow-other-keys)
2216 ;; Make sure 'couger' runs with the correct PYTHONPATH.
2217 (let* ((out (assoc-ref outputs "out"))
2218 (path (getenv "PYTHONPATH")))
2219 (wrap-program (string-append out "/bin/couger")
2220 `("PYTHONPATH" ":" prefix (,path))))
2223 `(("python" ,python-2)
2224 ("python2-pillow" ,python2-pillow)
2225 ("python2-numpy" ,python2-numpy)
2226 ("python2-scipy" ,python2-scipy)
2227 ("python2-matplotlib" ,python2-matplotlib)))
2229 `(("r-minimal" ,r-minimal)
2231 ("randomjungle" ,randomjungle)))
2233 `(("unzip" ,unzip)))
2234 (home-page "http://couger.oit.duke.edu")
2235 (synopsis "Identify co-factors in sets of genomic regions")
2237 "COUGER can be applied to any two sets of genomic regions bound by
2238 paralogous TFs (e.g., regions derived from ChIP-seq experiments) to identify
2239 putative co-factors that provide specificity to each TF. The framework
2240 determines the genomic targets uniquely-bound by each TF, and identifies a
2241 small set of co-factors that best explain the in vivo binding differences
2242 between the two TFs.
2244 COUGER uses classification algorithms (support vector machines and random
2245 forests) with features that reflect the DNA binding specificities of putative
2246 co-factors. The features are generated either from high-throughput TF-DNA
2247 binding data (from protein binding microarray experiments), or from large
2248 collections of DNA motifs.")
2249 (license license:gpl3+)))
2251 (define-public clustal-omega
2253 (name "clustal-omega")
2257 (uri (string-append "http://www.clustal.org/omega/clustal-omega-"
2261 "1vm30mzncwdv881vrcwg11vzvrsmwy4wg80j5i0lcfk6dlld50w6"))))
2262 (build-system gnu-build-system)
2264 `(("argtable" ,argtable)))
2265 (home-page "http://www.clustal.org/omega/")
2266 (synopsis "Multiple sequence aligner for protein and DNA/RNA")
2268 "Clustal-Omega is a general purpose multiple sequence alignment (MSA)
2269 program for protein and DNA/RNA. It produces high quality MSAs and is capable
2270 of handling data-sets of hundreds of thousands of sequences in reasonable
2272 (license license:gpl2+)))
2274 (define-public crossmap
2280 (uri (pypi-uri "CrossMap" version))
2283 "1byhclrqnqpvc1rqkfh4jwj6yhn0x9y7jk47i0qcjlhk0pjkw92p"))))
2284 (build-system python-build-system)
2285 (arguments `(#:python ,python-2))
2287 `(("python-bx-python" ,python2-bx-python)
2288 ("python-numpy" ,python2-numpy)
2289 ("python-pysam" ,python2-pysam)
2292 `(("python-cython" ,python2-cython)
2293 ("python-nose" ,python2-nose)))
2294 (home-page "http://crossmap.sourceforge.net/")
2295 (synopsis "Convert genome coordinates between assemblies")
2297 "CrossMap is a program for conversion of genome coordinates or annotation
2298 files between different genome assemblies. It supports most commonly used
2299 file formats including SAM/BAM, Wiggle/BigWig, BED, GFF/GTF, VCF.")
2300 (license license:gpl2+)))
2302 (define-public python-dnaio
2304 (name "python-dnaio")
2309 (uri (pypi-uri "dnaio" version))
2312 "0f16m7hdlm0fz1n7y5asy0v9ghyrq17ni1p9iybq22ddzyd49r27"))))
2313 (build-system python-build-system)
2315 `(("python-cython" ,python-cython)
2316 ("python-pytest" ,python-pytest)
2317 ("python-xopen" ,python-xopen)))
2318 (home-page "https://github.com/marcelm/dnaio/")
2319 (synopsis "Read FASTA and FASTQ files efficiently")
2321 "dnaio is a Python library for fast parsing of FASTQ and also FASTA
2322 files. The code was previously part of the cutadapt tool.")
2323 (license license:expat)))
2325 (define-public cutadapt
2331 (uri (pypi-uri "cutadapt" version))
2334 "1vqmsfkm6llxzmsz9wcfcvzx9a9f8iabvwik2rbyn7nc4wm25z89"))))
2335 (build-system python-build-system)
2337 `(("python-dnaio" ,python-dnaio)
2338 ("python-xopen" ,python-xopen)))
2340 `(("python-cython" ,python-cython)
2341 ("python-pytest" ,python-pytest)
2342 ("python-setuptools-scm" ,python-setuptools-scm)))
2343 (home-page "https://cutadapt.readthedocs.io/en/stable/")
2344 (synopsis "Remove adapter sequences from nucleotide sequencing reads")
2346 "Cutadapt finds and removes adapter sequences, primers, poly-A tails and
2347 other types of unwanted sequence from high-throughput sequencing reads.")
2348 (license license:expat)))
2350 (define-public libbigwig
2357 (url "https://github.com/dpryan79/libBigWig.git")
2359 (file-name (string-append name "-" version "-checkout"))
2362 "0h2smg24v5srdcqzrmz2g23cmlp4va465mgx8r2z571sfz8pv454"))))
2363 (build-system gnu-build-system)
2365 `(#:test-target "test"
2366 #:tests? #f ; tests require access to the web
2369 (string-append "prefix=" (assoc-ref %outputs "out")))
2371 (modify-phases %standard-phases
2372 (delete 'configure))))
2377 `(("doxygen" ,doxygen)
2379 ("python" ,python-2)))
2380 (home-page "https://github.com/dpryan79/libBigWig")
2381 (synopsis "C library for handling bigWig files")
2383 "This package provides a C library for parsing local and remote BigWig
2385 (license license:expat)))
2387 (define-public python-pybigwig
2389 (name "python-pybigwig")
2393 (uri (pypi-uri "pyBigWig" version))
2396 "00w4kfnm2c5l7wdwr2nj1z5djv8kzgf7h1zhsgv6njff1rwr26g0"))
2397 (modules '((guix build utils)))
2400 ;; Delete bundled libBigWig sources
2401 (delete-file-recursively "libBigWig")
2403 (build-system python-build-system)
2406 (modify-phases %standard-phases
2407 (add-after 'unpack 'link-with-libBigWig
2408 (lambda* (#:key inputs #:allow-other-keys)
2409 (substitute* "setup.py"
2410 (("libs=\\[") "libs=[\"BigWig\", "))
2413 `(("python-numpy" ,python-numpy)))
2415 `(("libbigwig" ,libbigwig)
2418 (home-page "https://github.com/dpryan79/pyBigWig")
2419 (synopsis "Access bigWig files in Python using libBigWig")
2421 "This package provides Python bindings to the libBigWig library for
2422 accessing bigWig files.")
2423 (license license:expat)))
2425 (define-public python2-pybigwig
2426 (package-with-python2 python-pybigwig))
2428 (define-public python-dendropy
2430 (name "python-dendropy")
2435 ;; Source from GitHub so that tests are included.
2437 (url "https://github.com/jeetsukumaran/DendroPy.git")
2438 (commit (string-append "v" version))))
2439 (file-name (git-file-name name version))
2442 "097hfyv2kaf4x92i4rjx0paw2cncxap48qivv8zxng4z7nhid0x9"))))
2443 (build-system python-build-system)
2444 (home-page "http://packages.python.org/DendroPy/")
2445 (synopsis "Library for phylogenetics and phylogenetic computing")
2447 "DendroPy is a library for phylogenetics and phylogenetic computing: reading,
2448 writing, simulation, processing and manipulation of phylogenetic
2449 trees (phylogenies) and characters.")
2450 (license license:bsd-3)))
2452 (define-public python2-dendropy
2453 (let ((base (package-with-python2 python-dendropy)))
2458 (modify-phases %standard-phases
2459 (add-after 'unpack 'remove-failing-test
2461 ;; This test fails when the full test suite is run, as documented
2462 ;; at https://github.com/jeetsukumaran/DendroPy/issues/74
2463 (substitute* "tests/test_dataio_nexml_reader_tree_list.py"
2464 (("test_collection_comments_and_annotations")
2465 "do_not_test_collection_comments_and_annotations"))
2467 ,@(package-arguments base))))))
2469 (define-public python-py2bit
2471 (name "python-py2bit")
2476 (uri (pypi-uri "py2bit" version))
2479 "1vw2nvw1yrl7ikkqsqs1pg239yr5nspvd969r1x9arms1k25a1a5"))))
2480 (build-system python-build-system)
2481 (home-page "https://github.com/dpryan79/py2bit")
2482 (synopsis "Access 2bit files using lib2bit")
2484 "This package provides Python bindings for lib2bit to access 2bit files
2486 (license license:expat)))
2488 (define-public deeptools
2495 (url "https://github.com/deeptools/deepTools.git")
2497 (file-name (git-file-name name version))
2500 "1vggnf52g6q2vifdl4cyi7s2fnfqq0ky2zrkj5zv2qfzsc3p3siw"))))
2501 (build-system python-build-system)
2504 (modify-phases %standard-phases
2505 ;; This phase fails, but it's not needed.
2506 (delete 'reset-gzip-timestamps))))
2508 `(("python-plotly" ,python-plotly)
2509 ("python-scipy" ,python-scipy)
2510 ("python-numpy" ,python-numpy)
2511 ("python-numpydoc" ,python-numpydoc)
2512 ("python-matplotlib" ,python-matplotlib)
2513 ("python-pysam" ,python-pysam)
2514 ("python-py2bit" ,python-py2bit)
2515 ("python-pybigwig" ,python-pybigwig)))
2517 `(("python-mock" ,python-mock) ;for tests
2518 ("python-nose" ,python-nose) ;for tests
2519 ("python-pytz" ,python-pytz))) ;for tests
2520 (home-page "https://github.com/deeptools/deepTools")
2521 (synopsis "Tools for normalizing and visualizing deep-sequencing data")
2523 "DeepTools addresses the challenge of handling the large amounts of data
2524 that are now routinely generated from DNA sequencing centers. To do so,
2525 deepTools contains useful modules to process the mapped reads data to create
2526 coverage files in standard bedGraph and bigWig file formats. By doing so,
2527 deepTools allows the creation of normalized coverage files or the comparison
2528 between two files (for example, treatment and control). Finally, using such
2529 normalized and standardized files, multiple visualizations can be created to
2530 identify enrichments with functional annotations of the genome.")
2531 (license license:gpl3+)))
2533 (define-public delly
2540 (url "https://github.com/dellytools/delly.git")
2541 (commit (string-append "v" version))))
2542 (file-name (git-file-name name version))
2544 (base32 "034jqsxswy9gqdh2zkgc1js99qkv75ks4xvzgmh0284sraagv61z"))
2545 (modules '((guix build utils)))
2548 (delete-file-recursively "src/htslib")
2550 (build-system gnu-build-system)
2552 `(#:tests? #f ; There are no tests to run.
2554 (list "PARALLEL=1" ; Allow parallel execution at run-time.
2555 (string-append "prefix=" (assoc-ref %outputs "out")))
2557 (modify-phases %standard-phases
2558 (delete 'configure) ; There is no configure phase.
2559 (add-after 'install 'install-templates
2560 (lambda* (#:key outputs #:allow-other-keys)
2561 (let ((templates (string-append (assoc-ref outputs "out")
2562 "/share/delly/templates")))
2564 (copy-recursively "excludeTemplates" templates)
2571 (home-page "https://github.com/dellytools/delly")
2572 (synopsis "Integrated structural variant prediction method")
2573 (description "Delly is an integrated structural variant prediction method
2574 that can discover and genotype deletions, tandem duplications, inversions and
2575 translocations at single-nucleotide resolution in short-read massively parallel
2576 sequencing data. It uses paired-ends and split-reads to sensitively and
2577 accurately delineate genomic rearrangements throughout the genome.")
2578 (license license:gpl3+)))
2580 (define-public diamond
2587 (url "https://github.com/bbuchfink/diamond.git")
2588 (commit (string-append "v" version))))
2589 (file-name (git-file-name name version))
2592 "0bky78v79g3wmdpsd706cscckgw1v09fg8vdd0z8z0d5b97aj9zl"))))
2593 (build-system cmake-build-system)
2595 '(#:tests? #f ; no "check" target
2597 (modify-phases %standard-phases
2598 (add-after 'unpack 'remove-native-compilation
2600 (substitute* "CMakeLists.txt" (("-march=native") ""))
2604 (home-page "https://github.com/bbuchfink/diamond")
2605 (synopsis "Accelerated BLAST compatible local sequence aligner")
2607 "DIAMOND is a BLAST-compatible local aligner for mapping protein and
2608 translated DNA query sequences against a protein reference database (BLASTP
2609 and BLASTX alignment mode). The speedup over BLAST is up to 20,000 on short
2610 reads at a typical sensitivity of 90-99% relative to BLAST depending on the
2611 data and settings.")
2612 (license license:agpl3+)))
2614 (define-public discrover
2622 (url "https://github.com/maaskola/discrover.git")
2624 (file-name (git-file-name name version))
2627 "173fwi2vb6a5kp406hm3jj6j7v4whww796f2qcygp4rpvamh307y"))))
2628 (build-system cmake-build-system)
2630 `(#:tests? #f ; there are no tests
2632 (modify-phases %standard-phases
2633 (add-after 'unpack 'fix-latex-errors
2635 (with-fluids ((%default-port-encoding #f))
2636 (substitute* "doc/references.bib"
2637 (("\\{S\\}illanp[^,]+,")
2638 "{S}illanp{\\\"a}{\\\"a},")))
2639 ;; XXX: I just can't get pdflatex to not complain about these
2640 ;; characters. They end up in the manual via the generated
2641 ;; discrover-cli-help.txt.
2642 (substitute* "src/hmm/cli.cpp"
2646 ;; This seems to be a syntax error.
2647 (substitute* "doc/discrover-manual.tex"
2648 (("theverbbox\\[t\\]") "theverbbox"))
2650 (add-after 'unpack 'add-missing-includes
2652 (substitute* "src/executioninformation.hpp"
2653 (("#define EXECUTIONINFORMATION_HPP" line)
2654 (string-append line "\n#include <random>")))
2655 (substitute* "src/plasma/fasta.hpp"
2656 (("#define FASTA_HPP" line)
2657 (string-append line "\n#include <random>")))
2659 ;; FIXME: this is needed because we're using texlive-union, which
2660 ;; doesn't handle fonts correctly. It expects to be able to generate
2661 ;; fonts in the home directory.
2662 (add-before 'build 'setenv-HOME
2663 (lambda _ (setenv "HOME" "/tmp") #t)))))
2667 ("rmath-standalone" ,rmath-standalone)))
2669 `(("texlive" ,(texlive-union (list texlive-fonts-cm
2670 texlive-fonts-amsfonts
2673 texlive-latex-examplep
2674 texlive-latex-hyperref
2676 texlive-latex-natbib
2677 texlive-bibtex ; style files used by natbib
2678 texlive-latex-pgf ; tikz
2679 texlive-latex-verbatimbox)))
2680 ("imagemagick" ,imagemagick)))
2681 (home-page "http://dorina.mdc-berlin.de/public/rajewsky/discrover/")
2682 (synopsis "Discover discriminative nucleotide sequence motifs")
2683 (description "Discrover is a motif discovery method to find binding sites
2684 of nucleic acid binding proteins.")
2685 (license license:gpl3+)))
2687 (define-public eigensoft
2695 (url "https://github.com/DReichLab/EIG.git")
2696 (commit (string-append "v" version))))
2697 (file-name (git-file-name name version))
2700 "1c141fqvhnzibmnf22sv23vbmzm20kjjyrib44cfh75wyndp2d9k"))
2701 (modules '((guix build utils)))
2702 ;; Remove pre-built binaries.
2704 (delete-file-recursively "bin")
2707 (build-system gnu-build-system)
2709 `(#:tests? #f ; There are no tests.
2710 #:make-flags '("CC=gcc")
2712 (modify-phases %standard-phases
2713 ;; There is no configure phase, but the Makefile is in a
2716 (lambda _ (chdir "src") #t))
2717 ;; The provided install target only copies executables to
2718 ;; the "bin" directory in the build root.
2719 (add-after 'install 'actually-install
2720 (lambda* (#:key outputs #:allow-other-keys)
2721 (let* ((out (assoc-ref outputs "out"))
2722 (bin (string-append out "/bin")))
2723 (for-each (lambda (file)
2724 (install-file file bin))
2725 (find-files "../bin" ".*"))
2730 ("openblas" ,openblas)
2732 ("gfortran" ,gfortran "lib")))
2733 (home-page "https://github.com/DReichLab/EIG")
2734 (synopsis "Tools for population genetics")
2735 (description "The EIGENSOFT package provides tools for population
2736 genetics and stratification correction. EIGENSOFT implements methods commonly
2737 used in population genetics analyses such as PCA, computation of Tracy-Widom
2738 statistics, and finding related individuals in structured populations. It
2739 comes with a built-in plotting script and supports multiple file formats and
2740 quantitative phenotypes.")
2741 ;; The license of the eigensoft tools is Expat, but since it's
2742 ;; linking with the GNU Scientific Library (GSL) the effective
2743 ;; license is the GPL.
2744 (license license:gpl3+)))
2746 (define-public edirect
2749 (version "10.2.20181018")
2752 (uri (string-append "ftp://ftp.ncbi.nlm.nih.gov/entrez/entrezdirect"
2753 "/versions/" version
2754 "/edirect-" version ".tar.gz"))
2757 "091f4aigzpbqih6h82nq566gkp3y07i72yqndmqskfgar1vwgci7"))))
2758 (build-system perl-build-system)
2761 (modify-phases %standard-phases
2764 (delete 'check) ; simple check after install
2766 (lambda* (#:key outputs #:allow-other-keys)
2767 (install-file "edirect.pl"
2768 (string-append (assoc-ref outputs "out") "/bin"))
2770 (add-after 'install 'wrap-program
2771 (lambda* (#:key outputs #:allow-other-keys)
2772 ;; Make sure 'edirect.pl' finds all perl inputs at runtime.
2773 (let* ((out (assoc-ref outputs "out"))
2774 (path (getenv "PERL5LIB")))
2775 (wrap-program (string-append out "/bin/edirect.pl")
2776 `("PERL5LIB" ":" prefix (,path))))
2778 (add-after 'wrap-program 'check
2779 (lambda* (#:key outputs #:allow-other-keys)
2780 (invoke (string-append (assoc-ref outputs "out")
2785 `(("perl-html-parser" ,perl-html-parser)
2786 ("perl-encode-locale" ,perl-encode-locale)
2787 ("perl-file-listing" ,perl-file-listing)
2788 ("perl-html-tagset" ,perl-html-tagset)
2789 ("perl-html-tree" ,perl-html-tree)
2790 ("perl-http-cookies" ,perl-http-cookies)
2791 ("perl-http-date" ,perl-http-date)
2792 ("perl-http-message" ,perl-http-message)
2793 ("perl-http-negotiate" ,perl-http-negotiate)
2794 ("perl-lwp-mediatypes" ,perl-lwp-mediatypes)
2795 ("perl-lwp-protocol-https" ,perl-lwp-protocol-https)
2796 ("perl-net-http" ,perl-net-http)
2797 ("perl-uri" ,perl-uri)
2798 ("perl-www-robotrules" ,perl-www-robotrules)
2799 ("perl-xml-simple" ,perl-xml-simple)
2801 (home-page "http://www.ncbi.nlm.nih.gov/books/NBK179288/")
2802 (synopsis "Tools for accessing the NCBI's set of databases")
2804 "Entrez Direct (EDirect) is a method for accessing the National Center
2805 for Biotechnology Information's (NCBI) set of interconnected
2806 databases (publication, sequence, structure, gene, variation, expression,
2807 etc.) from a terminal. Functions take search terms from command-line
2808 arguments. Individual operations are combined to build multi-step queries.
2809 Record retrieval and formatting normally complete the process.
2811 EDirect also provides an argument-driven function that simplifies the
2812 extraction of data from document summaries or other results that are returned
2813 in structured XML format. This can eliminate the need for writing custom
2814 software to answer ad hoc questions.")
2815 (license license:public-domain)))
2817 (define-public exonerate
2826 "http://ftp.ebi.ac.uk/pub/software/vertebrategenomics/exonerate/"
2827 "exonerate-" version ".tar.gz"))
2830 "0hj0m9xygiqsdxvbg79wq579kbrx1mdrabi2bzqz2zn9qwfjcjgq"))))
2831 (build-system gnu-build-system)
2833 `(#:parallel-build? #f)) ; Building in parallel fails on some machines.
2835 `(("pkg-config" ,pkg-config)))
2839 "https://www.ebi.ac.uk/about/vertebrate-genomics/software/exonerate")
2840 (synopsis "Generic tool for biological sequence alignment")
2842 "Exonerate is a generic tool for pairwise sequence comparison. It allows
2843 the alignment of sequences using a many alignment models, either exhaustive
2844 dynamic programming or a variety of heuristics.")
2845 (license license:gpl3)))
2847 (define-public express
2855 "http://bio.math.berkeley.edu/eXpress/downloads/express-"
2856 version "/express-" version "-src.tgz"))
2859 "03rczxd0gjp2l1jxcmjfmf5j94j77zqyxa6x063zsc585nj40n0c"))))
2860 (build-system cmake-build-system)
2862 `(#:tests? #f ;no "check" target
2864 (modify-phases %standard-phases
2865 (add-after 'unpack 'use-shared-boost-libs-and-set-bamtools-paths
2866 (lambda* (#:key inputs #:allow-other-keys)
2867 (substitute* "CMakeLists.txt"
2868 (("set\\(Boost_USE_STATIC_LIBS ON\\)")
2869 "set(Boost_USE_STATIC_LIBS OFF)")
2870 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/bamtools/include")
2871 (string-append (assoc-ref inputs "bamtools") "/include/bamtools")))
2872 (substitute* "src/CMakeLists.txt"
2873 (("\\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/\\.\\./bamtools/lib")
2874 (string-append (assoc-ref inputs "bamtools") "/lib"))
2875 (("libprotobuf.a") "libprotobuf.so"))
2879 ("bamtools" ,bamtools)
2880 ("protobuf" ,protobuf)
2882 (home-page "http://bio.math.berkeley.edu/eXpress")
2883 (synopsis "Streaming quantification for high-throughput genomic sequencing")
2885 "eXpress is a streaming tool for quantifying the abundances of a set of
2886 target sequences from sampled subsequences. Example applications include
2887 transcript-level RNA-Seq quantification, allele-specific/haplotype expression
2888 analysis (from RNA-Seq), transcription factor binding quantification in
2889 ChIP-Seq, and analysis of metagenomic data.")
2890 (license license:artistic2.0)))
2892 (define-public express-beta-diversity
2894 (name "express-beta-diversity")
2899 (url "https://github.com/dparks1134/ExpressBetaDiversity.git")
2900 (commit (string-append "v" version))))
2901 (file-name (git-file-name name version))
2904 "0s0yzg5c21349rh7x4w9266jsvnp7j1hp9cf8sk32hz8nvrj745x"))))
2905 (build-system gnu-build-system)
2908 (modify-phases %standard-phases
2910 (add-before 'build 'enter-source (lambda _ (chdir "source") #t))
2912 (lambda _ (invoke "../bin/ExpressBetaDiversity" "-u") #t))
2914 (lambda* (#:key outputs #:allow-other-keys)
2915 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
2916 (install-file "../scripts/convertToEBD.py" bin)
2917 (install-file "../bin/ExpressBetaDiversity" bin)
2920 `(("python" ,python-2)))
2921 (home-page "http://kiwi.cs.dal.ca/Software/ExpressBetaDiversity")
2922 (synopsis "Taxon- and phylogenetic-based beta diversity measures")
2924 "Express Beta Diversity (EBD) calculates ecological beta diversity
2925 (dissimilarity) measures between biological communities. EBD implements a
2926 variety of diversity measures including those that make use of phylogenetic
2927 similarity of community members.")
2928 (license license:gpl3+)))
2930 (define-public fasttree
2937 "http://www.microbesonline.org/fasttree/FastTree-"
2941 "0vcjdvy1j4m702vmak4svbfkrpcw63k7wymfksjp9a982zy8kjsl"))))
2942 (build-system gnu-build-system)
2944 `(#:tests? #f ; no "check" target
2946 (modify-phases %standard-phases
2950 (lambda* (#:key source #:allow-other-keys)
2953 "-finline-functions"
2964 "-finline-functions"
2973 (lambda* (#:key outputs #:allow-other-keys)
2974 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
2975 (install-file "FastTree" bin)
2976 (install-file "FastTreeMP" bin)
2978 (home-page "http://www.microbesonline.org/fasttree")
2979 (synopsis "Infers approximately-maximum-likelihood phylogenetic trees")
2981 "FastTree can handle alignments with up to a million of sequences in a
2982 reasonable amount of time and memory. For large alignments, FastTree is
2983 100-1,000 times faster than PhyML 3.0 or RAxML 7.")
2984 (license license:gpl2+)))
2986 (define-public fastx-toolkit
2988 (name "fastx-toolkit")
2994 "https://github.com/agordon/fastx_toolkit/releases/download/"
2995 version "/fastx_toolkit-" version ".tar.bz2"))
2998 "01jqzw386873sr0pjp1wr4rn8fsga2vxs1qfmicvx1pjr72007wy"))))
2999 (build-system gnu-build-system)
3001 `(("libgtextutils" ,libgtextutils)))
3003 `(("pkg-config" ,pkg-config)))
3004 (home-page "http://hannonlab.cshl.edu/fastx_toolkit/")
3005 (synopsis "Tools for FASTA/FASTQ file preprocessing")
3007 "The FASTX-Toolkit is a collection of command line tools for Short-Reads
3008 FASTA/FASTQ files preprocessing.
3010 Next-Generation sequencing machines usually produce FASTA or FASTQ files,
3011 containing multiple short-reads sequences. The main processing of such
3012 FASTA/FASTQ files is mapping the sequences to reference genomes. However, it
3013 is sometimes more productive to preprocess the files before mapping the
3014 sequences to the genome---manipulating the sequences to produce better mapping
3015 results. The FASTX-Toolkit tools perform some of these preprocessing tasks.")
3016 (license license:agpl3+)))
3018 (define-public flexbar
3025 (url "https://github.com/seqan/flexbar.git")
3026 (commit (string-append "v" version))))
3027 (file-name (git-file-name name version))
3030 "1pq9sxvdnldl14libk234m72dqhwgzs3acgl943wchwdqlcsi5r2"))))
3031 (build-system cmake-build-system)
3034 (modify-phases %standard-phases
3035 (add-after 'unpack 'do-not-tune-to-CPU
3037 (substitute* "src/CMakeLists.txt"
3038 ((" -march=native") ""))
3041 (lambda* (#:key outputs #:allow-other-keys)
3042 (setenv "PATH" (string-append (getcwd) ":" (getenv "PATH")))
3043 (with-directory-excursion "../source/test"
3044 (invoke "bash" "flexbar_test.sh"))
3047 (lambda* (#:key outputs #:allow-other-keys)
3048 (let* ((out (string-append (assoc-ref outputs "out")))
3049 (bin (string-append out "/bin/")))
3050 (install-file "flexbar" bin))
3056 `(("pkg-config" ,pkg-config)
3058 (home-page "https://github.com/seqan/flexbar")
3059 (synopsis "Barcode and adapter removal tool for sequencing platforms")
3061 "Flexbar preprocesses high-throughput nucleotide sequencing data
3062 efficiently. It demultiplexes barcoded runs and removes adapter sequences.
3063 Moreover, trimming and filtering features are provided. Flexbar increases
3064 read mapping rates and improves genome and transcriptome assemblies. It
3065 supports next-generation sequencing data in fasta/q and csfasta/q format from
3066 Illumina, Roche 454, and the SOLiD platform.")
3067 (license license:bsd-3)))
3069 (define-public fraggenescan
3071 (name "fraggenescan")
3077 (string-append "mirror://sourceforge/fraggenescan/"
3078 "FragGeneScan" version ".tar.gz"))
3080 (base32 "158dcnwczgcyhwm4qlx19sanrwgdpzf6bn2y57mbpx55lkgz1mzj"))))
3081 (build-system gnu-build-system)
3084 (modify-phases %standard-phases
3086 (add-before 'build 'patch-paths
3087 (lambda* (#:key outputs #:allow-other-keys)
3088 (let* ((out (string-append (assoc-ref outputs "out")))
3089 (share (string-append out "/share/fraggenescan/")))
3090 (substitute* "run_FragGeneScan.pl"
3092 (string-append "system(\"" (which "rm")))
3094 (string-append "system(\"" (which "mv")))
3095 (("\\\"awk") (string-append "\"" (which "awk")))
3096 ;; This script and other programs expect the training files
3097 ;; to be in the non-standard location bin/train/XXX. Change
3098 ;; this to be share/fraggenescan/train/XXX instead.
3099 (("^\\$train.file = \\$dir.*")
3100 (string-append "$train_file = \""
3102 "train/\".$FGS_train_file;")))
3103 (substitute* "run_hmm.c"
3104 (("^ strcat\\(train_dir, \\\"train/\\\"\\);")
3105 (string-append " strcpy(train_dir, \"" share "/train/\");"))))
3109 (invoke "make" "clean")
3110 (invoke "make" "fgs")
3113 (lambda* (#:key outputs #:allow-other-keys)
3114 (let* ((out (string-append (assoc-ref outputs "out")))
3115 (bin (string-append out "/bin/"))
3116 (share (string-append out "/share/fraggenescan/train")))
3117 (install-file "run_FragGeneScan.pl" bin)
3118 (install-file "FragGeneScan" bin)
3119 (copy-recursively "train" share))
3122 (add-after 'install 'post-install-check
3123 ;; In lieu of 'make check', run one of the examples and check the
3124 ;; output files gets created.
3125 (lambda* (#:key outputs #:allow-other-keys)
3126 (let* ((out (string-append (assoc-ref outputs "out")))
3127 (bin (string-append out "/bin/"))
3128 (frag (string-append bin "run_FragGeneScan.pl")))
3129 ;; Test complete genome.
3131 "-genome=./example/NC_000913.fna"
3135 (unless (and (file-exists? "test2.faa")
3136 (file-exists? "test2.ffn")
3137 (file-exists? "test2.gff")
3138 (file-exists? "test2.out"))
3139 (error "Expected files do not exist."))
3140 ;; Test incomplete sequences.
3142 "-genome=./example/NC_000913-fgs.ffn"
3149 ("python" ,python-2))) ;not compatible with python 3.
3150 (home-page "https://sourceforge.net/projects/fraggenescan/")
3151 (synopsis "Finds potentially fragmented genes in short reads")
3153 "FragGeneScan is a program for predicting bacterial and archaeal genes in
3154 short and error-prone DNA sequencing reads. It can also be applied to predict
3155 genes in incomplete assemblies or complete genomes.")
3156 ;; GPL3+ according to private correspondense with the authors.
3157 (license license:gpl3+)))
3159 (define-public fxtract
3160 (let ((util-commit "776ca85a18a47492af3794745efcb4a905113115"))
3168 (url "https://github.com/ctSkennerton/fxtract.git")
3170 (file-name (git-file-name name version))
3173 "0hab3gpwf4w9s87qlbswq6ws1qqybh4dcqk79q1ahyldzai5fgp5"))))
3174 (build-system gnu-build-system)
3176 `(#:make-flags (list
3177 (string-append "PREFIX=" (assoc-ref %outputs "out"))
3179 #:test-target "fxtract_test"
3181 (modify-phases %standard-phases
3183 (add-before 'build 'copy-util
3184 (lambda* (#:key inputs #:allow-other-keys)
3186 (copy-recursively (assoc-ref inputs "ctskennerton-util") "util")
3188 ;; Do not use make install as this requires additional dependencies.
3190 (lambda* (#:key outputs #:allow-other-keys)
3191 (let* ((out (assoc-ref outputs "out"))
3192 (bin (string-append out"/bin")))
3193 (install-file "fxtract" bin)
3199 ;; ctskennerton-util is licensed under GPL2.
3200 `(("ctskennerton-util"
3204 (url "https://github.com/ctSkennerton/util.git")
3205 (commit util-commit)))
3206 (file-name (string-append
3207 "ctstennerton-util-" util-commit "-checkout"))
3210 "0cls1hd4vgj3f36fpzzg4xc77d6f3hpc60cbpfmn2gdr7ykzzad7"))))))
3211 (home-page "https://github.com/ctSkennerton/fxtract")
3212 (synopsis "Extract sequences from FASTA and FASTQ files")
3214 "Fxtract extracts sequences from a protein or nucleotide fastx (FASTA
3215 or FASTQ) file given a subsequence. It uses a simple substring search for
3216 basic tasks but can change to using POSIX regular expressions, PCRE, hash
3217 lookups or multi-pattern searching as required. By default fxtract looks in
3218 the sequence of each record but can also be told to look in the header,
3219 comment or quality sections.")
3220 ;; 'util' requires SSE instructions.
3221 (supported-systems '("x86_64-linux"))
3222 (license license:expat))))
3224 (define-public gemma
3231 (url "https://github.com/xiangzhou/GEMMA.git")
3232 (commit (string-append "v" version))))
3233 (file-name (git-file-name name version))
3236 "1s3ncnbn45r2hh1cvrqky1kbqq6546biypr4f5mkw1kqlrgyh0yg"))))
3239 ("gfortran" ,gfortran "lib")
3242 ("openblas" ,openblas)
3244 (build-system gnu-build-system)
3247 '(,@(match (%current-system)
3249 '("FORCE_DYNAMIC=1"))
3251 '("FORCE_DYNAMIC=1" "FORCE_32BIT=1"))
3253 '("FORCE_DYNAMIC=1" "NO_INTEL_COMPAT=1"))))
3255 (modify-phases %standard-phases
3257 (add-after 'unpack 'find-eigen
3258 (lambda* (#:key inputs #:allow-other-keys)
3259 ;; Ensure that Eigen headers can be found
3260 (setenv "CPLUS_INCLUDE_PATH"
3261 (string-append (getenv "CPLUS_INCLUDE_PATH")
3263 (assoc-ref inputs "eigen")
3266 (add-before 'build 'bin-mkdir
3271 (lambda* (#:key outputs #:allow-other-keys)
3272 (let ((out (assoc-ref outputs "out")))
3273 (install-file "bin/gemma"
3277 #:tests? #f)) ; no tests included yet
3278 (home-page "https://github.com/xiangzhou/GEMMA")
3279 (synopsis "Tool for genome-wide efficient mixed model association")
3281 "Genome-wide Efficient Mixed Model Association (GEMMA) provides a
3282 standard linear mixed model resolver with application in genome-wide
3283 association studies (GWAS).")
3284 (license license:gpl3)))
3293 (url "https://github.com/nboley/grit.git")
3295 (file-name (git-file-name name version))
3298 "1l5v8vfvfbrpmgnrvbrbv40d0arhxcnmxgv2f1mlcqfa3q6bkqm9"))))
3299 (build-system python-build-system)
3301 `(#:python ,python-2
3303 (modify-phases %standard-phases
3304 (add-after 'unpack 'generate-from-cython-sources
3305 (lambda* (#:key inputs outputs #:allow-other-keys)
3306 ;; Delete these C files to force fresh generation from pyx sources.
3307 (delete-file "grit/sparsify_support_fns.c")
3308 (delete-file "grit/call_peaks_support_fns.c")
3309 (substitute* "setup.py"
3310 (("Cython.Setup") "Cython.Build"))
3313 `(("python-scipy" ,python2-scipy)
3314 ("python-numpy" ,python2-numpy)
3315 ("python-pysam" ,python2-pysam)
3316 ("python-networkx" ,python2-networkx)))
3318 `(("python-cython" ,python2-cython)))
3319 (home-page "http://grit-bio.org")
3320 (synopsis "Tool for integrative analysis of RNA-seq type assays")
3322 "GRIT is designed to use RNA-seq, TES, and TSS data to build and quantify
3323 full length transcript models. When none of these data sources are available,
3324 GRIT can be run by providing a candidate set of TES or TSS sites. In
3325 addition, GRIT can merge in reference junctions and gene boundaries. GRIT can
3326 also be run in quantification mode, where it uses a provided GTF file and just
3327 estimates transcript expression.")
3328 (license license:gpl3+)))
3330 (define-public hisat
3337 "http://ccb.jhu.edu/software/hisat/downloads/hisat-"
3338 version "-beta-source.zip"))
3341 "1k381ydranqxp09yf2y7w1d0chz5d59vb6jchi89hbb0prq19lk5"))))
3342 (build-system gnu-build-system)
3344 `(#:tests? #f ;no check target
3345 #:make-flags '("allall"
3346 ;; Disable unsupported `popcnt' instructions on
3347 ;; architectures other than x86_64
3348 ,@(if (string-prefix? "x86_64"
3349 (or (%current-target-system)
3352 '("POPCNT_CAPABILITY=0")))
3354 (modify-phases %standard-phases
3355 (add-after 'unpack 'patch-sources
3357 ;; XXX Cannot use snippet because zip files are not supported
3358 (substitute* "Makefile"
3359 (("^CC = .*$") "CC = gcc")
3360 (("^CPP = .*$") "CPP = g++")
3361 ;; replace BUILD_HOST and BUILD_TIME for deterministic build
3362 (("-DBUILD_HOST=.*") "-DBUILD_HOST=\"\\\"guix\\\"\"")
3363 (("-DBUILD_TIME=.*") "-DBUILD_TIME=\"\\\"0\\\"\""))
3364 (substitute* '("hisat-build" "hisat-inspect")
3365 (("/usr/bin/env") (which "env")))
3368 (lambda* (#:key outputs #:allow-other-keys)
3369 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
3370 (for-each (lambda (file)
3371 (install-file file bin))
3374 "hisat(-(build|align|inspect)(-(s|l)(-debug)*)*)*$")))
3376 (delete 'configure))))
3378 `(("unzip" ,unzip)))
3383 ;; Non-portable SSE instructions are used so building fails on platforms
3384 ;; other than x86_64.
3385 (supported-systems '("x86_64-linux"))
3386 (home-page "http://ccb.jhu.edu/software/hisat/index.shtml")
3387 (synopsis "Hierarchical indexing for spliced alignment of transcripts")
3389 "HISAT is a fast and sensitive spliced alignment program for mapping
3390 RNA-seq reads. In addition to one global FM index that represents a whole
3391 genome, HISAT uses a large set of small FM indexes that collectively cover the
3392 whole genome. These small indexes (called local indexes) combined with
3393 several alignment strategies enable effective alignment of RNA-seq reads, in
3394 particular, reads spanning multiple exons.")
3395 (license license:gpl3+)))
3397 (define-public hisat2
3404 (uri (string-append "ftp://ftp.ccb.jhu.edu/pub/infphilo/hisat2"
3405 "/downloads/hisat2-" version "-source.zip"))
3408 "0lywnr8kijwsc2aw10dwxic0n0yvip6fl3rjlvc8zzwahamy4x7g"))))
3409 (build-system gnu-build-system)
3411 `(#:tests? #f ; no check target
3412 #:make-flags (list "CC=gcc" "CXX=g++" "allall")
3413 #:modules ((guix build gnu-build-system)
3417 (modify-phases %standard-phases
3418 (add-after 'unpack 'make-deterministic
3420 (substitute* "Makefile"
3425 (lambda* (#:key outputs #:allow-other-keys)
3426 (let* ((out (assoc-ref outputs "out"))
3427 (bin (string-append out "/bin/"))
3428 (doc (string-append out "/share/doc/hisat2/")))
3430 (cut install-file <> bin)
3432 "hisat2(-(build|align|inspect)(-(s|l)(-debug)*)*)*$"))
3434 (install-file "doc/manual.inc.html" doc))
3437 `(("unzip" ,unzip) ; needed for archive from ftp
3439 ("pandoc" ,ghc-pandoc))) ; for documentation
3440 (home-page "http://ccb.jhu.edu/software/hisat2/index.shtml")
3441 (synopsis "Graph-based alignment of genomic sequencing reads")
3442 (description "HISAT2 is a fast and sensitive alignment program for mapping
3443 next-generation sequencing reads (both DNA and RNA) to a population of human
3444 genomes (as well as to a single reference genome). In addition to using one
3445 global @dfn{graph FM} (GFM) index that represents a population of human
3446 genomes, HISAT2 uses a large set of small GFM indexes that collectively cover
3447 the whole genome. These small indexes, combined with several alignment
3448 strategies, enable rapid and accurate alignment of sequencing reads. This new
3449 indexing scheme is called a @dfn{Hierarchical Graph FM index} (HGFM).")
3450 ;; HISAT2 contains files from Bowtie2, which is released under
3451 ;; GPLv2 or later. The HISAT2 source files are released under
3453 (license license:gpl3+)))
3455 (define-public hmmer
3463 "http://eddylab.org/software/hmmer/hmmer-" version ".tar.gz"))
3466 "171bivy6xhgjsz5nv53n81pc3frnwz29ylblawk2bv46szwjjqd5"))))
3467 (build-system gnu-build-system)
3468 (native-inputs `(("perl" ,perl)))
3469 (home-page "http://hmmer.org/")
3470 (synopsis "Biosequence analysis using profile hidden Markov models")
3472 "HMMER is used for searching sequence databases for homologs of protein
3473 sequences, and for making protein sequence alignments. It implements methods
3474 using probabilistic models called profile hidden Markov models (profile
3476 ;; hmmer uses non-portable SSE intrinsics so building fails on other
3478 (supported-systems '("x86_64-linux" "i686-linux"))
3479 (license license:bsd-3)))
3481 (define-public htseq
3487 (uri (pypi-uri "HTSeq" version))
3490 "11flgb1381xdhk43bzbfm3vhnszkpqg6jk76rpa5xd1zbrvvlnxg"))))
3491 (build-system python-build-system)
3493 `(("python-cython" ,python-cython)))
3494 ;; Numpy needs to be propagated when htseq is used as a Python library.
3496 `(("python-numpy" ,python-numpy)))
3498 `(("python-pysam" ,python-pysam)
3499 ("python-matplotlib" ,python-matplotlib)))
3500 (home-page "http://www-huber.embl.de/users/anders/HTSeq/")
3501 (synopsis "Analysing high-throughput sequencing data with Python")
3503 "HTSeq is a Python package that provides infrastructure to process data
3504 from high-throughput sequencing assays.")
3505 (license license:gpl3+)))
3507 (define-public python2-htseq
3508 (package-with-python2 htseq))
3510 (define-public java-htsjdk
3512 (name "java-htsjdk")
3513 (version "2.3.0") ; last version without build dependency on gradle
3517 (url "https://github.com/samtools/htsjdk.git")
3519 (file-name (git-file-name name version))
3522 "1b178ixcabanm834ydjl3jiakpyxdmki32hqfv2abrzn3rcwa28i"))
3523 (modules '((guix build utils)))
3525 ;; Delete pre-built binaries
3527 (delete-file-recursively "lib")
3530 (build-system ant-build-system)
3532 `(#:tests? #f ; test require Internet access
3535 (list (string-append "-Ddist=" (assoc-ref %outputs "out")
3536 "/share/java/htsjdk/"))
3537 #:build-target "all"
3539 (modify-phases %standard-phases
3540 ;; The build phase also installs the jars
3541 (delete 'install))))
3543 `(("java-ngs" ,java-ngs)
3544 ("java-snappy-1" ,java-snappy-1)
3545 ("java-commons-compress" ,java-commons-compress)
3546 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3547 ("java-commons-jexl-2" ,java-commons-jexl-2)
3548 ("java-xz" ,java-xz)))
3550 `(("java-testng" ,java-testng)))
3551 (home-page "http://samtools.github.io/htsjdk/")
3552 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3554 "HTSJDK is an implementation of a unified Java library for accessing
3555 common file formats, such as SAM and VCF, used for high-throughput
3556 sequencing (HTS) data. There are also an number of useful utilities for
3557 manipulating HTS data.")
3558 (license license:expat)))
3560 (define-public java-htsjdk-latest
3562 (name "java-htsjdk")
3567 (url "https://github.com/samtools/htsjdk.git")
3569 (file-name (string-append name "-" version "-checkout"))
3572 "1lmya1fdjy03mz6zmdmd86j9v9vfhqb3952mqq075navx1i6g4bc"))))
3573 (build-system ant-build-system)
3575 `(#:tests? #f ; test require Scala
3577 #:jar-name "htsjdk.jar"
3579 (modify-phases %standard-phases
3580 (add-after 'unpack 'remove-useless-build.xml
3581 (lambda _ (delete-file "build.xml") #t))
3582 ;; The tests require the scalatest package.
3583 (add-after 'unpack 'remove-tests
3584 (lambda _ (delete-file-recursively "src/test") #t)))))
3586 `(("java-ngs" ,java-ngs)
3587 ("java-snappy-1" ,java-snappy-1)
3588 ("java-commons-compress" ,java-commons-compress)
3589 ("java-commons-logging-minimal" ,java-commons-logging-minimal)
3590 ("java-commons-jexl-2" ,java-commons-jexl-2)
3591 ("java-xz" ,java-xz)))
3593 `(("java-junit" ,java-junit)))
3594 (home-page "http://samtools.github.io/htsjdk/")
3595 (synopsis "Java API for high-throughput sequencing data (HTS) formats")
3597 "HTSJDK is an implementation of a unified Java library for accessing
3598 common file formats, such as SAM and VCF, used for high-throughput
3599 sequencing (HTS) data. There are also an number of useful utilities for
3600 manipulating HTS data.")
3601 (license license:expat)))
3603 ;; This is needed for picard 2.10.3
3604 (define-public java-htsjdk-2.10.1
3605 (package (inherit java-htsjdk-latest)
3606 (name "java-htsjdk")
3611 (url "https://github.com/samtools/htsjdk.git")
3613 (file-name (string-append name "-" version "-checkout"))
3616 "1kxh7slm2pm3x9p6jxa1wqsq9a31dhiiflhxnxqcisan4k3rwia2"))))
3617 (build-system ant-build-system)
3619 `(#:tests? #f ; tests require Scala
3621 #:jar-name "htsjdk.jar"
3623 (modify-phases %standard-phases
3624 (add-after 'unpack 'remove-useless-build.xml
3625 (lambda _ (delete-file "build.xml") #t))
3626 ;; The tests require the scalatest package.
3627 (add-after 'unpack 'remove-tests
3628 (lambda _ (delete-file-recursively "src/test") #t)))))))
3630 ;; This version matches java-htsjdk 2.3.0. Later versions also require a more
3631 ;; recent version of java-htsjdk, which depends on gradle.
3632 (define-public java-picard
3634 (name "java-picard")
3639 (url "https://github.com/broadinstitute/picard.git")
3641 (file-name (string-append "java-picard-" version "-checkout"))
3644 "1ll7mf4r3by92w2nhlmpa591xd1f46xlkwh59mq6fvbb5pdwzvx6"))
3645 (modules '((guix build utils)))
3648 ;; Delete pre-built binaries.
3649 (delete-file-recursively "lib")
3651 (substitute* "build.xml"
3652 ;; Remove build-time dependency on git.
3653 (("failifexecutionfails=\"true\"")
3654 "failifexecutionfails=\"false\"")
3656 (("depends=\"compile-htsjdk, ")
3658 (("depends=\"compile-htsjdk-tests, ")
3660 ;; Build picard-lib.jar before building picard.jar
3661 (("name=\"picard-jar\" depends=\"" line)
3662 (string-append line "picard-lib-jar, ")))
3664 (build-system ant-build-system)
3666 `(#:build-target "picard-jar"
3667 #:test-target "test"
3668 ;; Tests require jacoco:coverage.
3671 (list (string-append "-Dhtsjdk_lib_dir="
3672 (assoc-ref %build-inputs "java-htsjdk")
3673 "/share/java/htsjdk/")
3674 "-Dhtsjdk-classes=dist/tmp"
3675 (string-append "-Dhtsjdk-version="
3676 ,(package-version java-htsjdk)))
3679 (modify-phases %standard-phases
3680 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3681 (delete 'generate-jar-indices)
3682 (add-after 'unpack 'use-our-htsjdk
3683 (lambda* (#:key inputs #:allow-other-keys)
3684 (substitute* "build.xml"
3685 (("\\$\\{htsjdk\\}/lib")
3686 (string-append (assoc-ref inputs "java-htsjdk")
3687 "/share/java/htsjdk/")))
3689 (add-after 'unpack 'make-test-target-independent
3690 (lambda* (#:key inputs #:allow-other-keys)
3691 (substitute* "build.xml"
3692 (("name=\"test\" depends=\"compile, ")
3693 "name=\"test\" depends=\""))
3695 (replace 'install (install-jars "dist")))))
3697 `(("java-htsjdk" ,java-htsjdk)
3698 ("java-guava" ,java-guava)))
3700 `(("java-testng" ,java-testng)))
3701 (home-page "http://broadinstitute.github.io/picard/")
3702 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3703 (description "Picard is a set of Java command line tools for manipulating
3704 high-throughput sequencing (HTS) data and formats. Picard is implemented
3705 using the HTSJDK Java library to support accessing file formats that are
3706 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3708 (license license:expat)))
3710 ;; This is needed for dropseq-tools
3711 (define-public java-picard-2.10.3
3713 (name "java-picard")
3718 (url "https://github.com/broadinstitute/picard.git")
3720 (file-name (string-append "java-picard-" version "-checkout"))
3723 "1ajlx31l6i1k3y2rhnmgq07sz99g2czqfqgkr9mihmdjp3gwjhvi"))))
3724 (build-system ant-build-system)
3726 `(#:jar-name "picard.jar"
3727 ;; Tests require jacoco:coverage.
3730 #:main-class "picard.cmdline.PicardCommandLine"
3731 #:modules ((guix build ant-build-system)
3733 (guix build java-utils)
3738 (modify-phases %standard-phases
3739 ;; FIXME: this phase fails with "duplicate entry: htsjdk/samtools/AbstractBAMFileIndex$1.class"
3740 (delete 'generate-jar-indices)
3741 (add-after 'unpack 'remove-useless-build.xml
3742 (lambda _ (delete-file "build.xml") #t))
3743 ;; This is necessary to ensure that htsjdk is found when using
3744 ;; picard.jar as an executable.
3745 (add-before 'build 'edit-classpath-in-manifest
3746 (lambda* (#:key inputs #:allow-other-keys)
3747 (chmod "build.xml" #o664)
3748 (call-with-output-file "build.xml.new"
3752 (with-input-from-file "build.xml"
3753 (lambda _ (xml->sxml #:trim-whitespace? #t)))
3754 `((target . ,(lambda (tag . kids)
3755 (let ((name ((sxpath '(name *text*))
3757 ;; FIXME: We're breaking the line
3758 ;; early with a dummy path to
3759 ;; ensure that the store reference
3760 ;; isn't broken apart and can still
3761 ;; be found by the reference
3766 ~a/share/java/htsjdk.jar${line.separator}${line.separator}"
3767 ;; maximum line length is 70
3768 (string-tabulate (const #\b) 57)
3769 (assoc-ref inputs "java-htsjdk"))))
3770 (if (member "manifest" name)
3773 (@ (file "${manifest.file}")
3774 (match "\\r\\n\\r\\n")
3775 (replace "${line.separator}")))
3778 (file "${manifest.file}")
3781 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
3782 (*text* . ,(lambda (_ txt) txt))))
3784 (rename-file "build.xml.new" "build.xml")
3787 `(("java-htsjdk" ,java-htsjdk-2.10.1)))
3789 `(("java-testng" ,java-testng)
3790 ("java-guava" ,java-guava)))
3791 (home-page "http://broadinstitute.github.io/picard/")
3792 (synopsis "Tools for manipulating high-throughput sequencing data and formats")
3793 (description "Picard is a set of Java command line tools for manipulating
3794 high-throughput sequencing (HTS) data and formats. Picard is implemented
3795 using the HTSJDK Java library to support accessing file formats that are
3796 commonly used for high-throughput sequencing data such as SAM, BAM, CRAM and
3798 (license license:expat)))
3800 ;; This is the last version of Picard to provide net.sf.samtools
3801 (define-public java-picard-1.113
3802 (package (inherit java-picard)
3803 (name "java-picard")
3808 (url "https://github.com/broadinstitute/picard.git")
3810 (file-name (string-append "java-picard-" version "-checkout"))
3813 "0lkpvin2fz3hhly4l02kk56fqy8lmlgyzr9kmvljk6ry6l1hw973"))
3814 (modules '((guix build utils)))
3817 ;; Delete pre-built binaries.
3818 (delete-file-recursively "lib")
3821 (build-system ant-build-system)
3823 `(#:build-target "picard-jar"
3824 #:test-target "test"
3825 ;; FIXME: the class path at test time is wrong.
3826 ;; [testng] Error: A JNI error has occurred, please check your installation and try again
3827 ;; [testng] Exception in thread "main" java.lang.NoClassDefFoundError: com/beust/jcommander/ParameterException
3830 ;; This is only used for tests.
3832 (list "-Dsamjdk.intel_deflater_so_path=lib/jni/libIntelDeflater.so")
3834 (modify-phases %standard-phases
3835 ;; FIXME: This phase fails.
3836 (delete 'generate-jar-indices)
3837 ;; Do not use bundled ant bzip2.
3838 (add-after 'unpack 'use-ant-bzip
3839 (lambda* (#:key inputs #:allow-other-keys)
3840 (substitute* "build.xml"
3841 (("\\$\\{lib\\}/apache-ant-1.8.2-bzip2.jar")
3842 (string-append (assoc-ref inputs "ant")
3845 (add-after 'unpack 'make-test-target-independent
3846 (lambda* (#:key inputs #:allow-other-keys)
3847 (substitute* "build.xml"
3848 (("name=\"test\" depends=\"compile, ")
3849 "name=\"test\" depends=\"compile-tests, ")
3850 (("name=\"compile\" depends=\"compile-src, compile-tests\"")
3851 "name=\"compile\" depends=\"compile-src\""))
3853 (add-after 'unpack 'fix-deflater-path
3854 (lambda* (#:key outputs #:allow-other-keys)
3855 (substitute* "src/java/net/sf/samtools/Defaults.java"
3856 (("getStringProperty\\(\"intel_deflater_so_path\", null\\)")
3857 (string-append "getStringProperty(\"intel_deflater_so_path\", \""
3858 (assoc-ref outputs "out")
3859 "/lib/jni/libIntelDeflater.so"
3862 ;; Build the deflater library, because we've previously deleted the
3863 ;; pre-built one. This can only be built with access to the JDK
3865 (add-after 'build 'build-jni
3866 (lambda* (#:key inputs #:allow-other-keys)
3869 (invoke "tar" "--strip-components=1" "-C" "jdk-src"
3870 "-xf" (assoc-ref inputs "jdk-src"))
3871 (invoke "javah" "-jni"
3872 "-classpath" "classes"
3874 "net.sf.samtools.util.zip.IntelDeflater")
3875 (with-directory-excursion "src/c/inteldeflater"
3876 (invoke "gcc" "-I../../../lib" "-I."
3877 (string-append "-I" (assoc-ref inputs "jdk")
3879 "-I../../../jdk-src/src/share/native/common/"
3880 "-I../../../jdk-src/src/solaris/native/common/"
3881 "-c" "-O3" "-fPIC" "IntelDeflater.c")
3882 (invoke "gcc" "-shared"
3883 "-o" "../../../lib/jni/libIntelDeflater.so"
3884 "IntelDeflater.o" "-lz" "-lstdc++"))
3886 ;; We can only build everything else after building the JNI library.
3887 (add-after 'build-jni 'build-rest
3888 (lambda* (#:key make-flags #:allow-other-keys)
3889 (apply invoke `("ant" "all" ,@make-flags))
3891 (add-before 'build 'set-JAVA6_HOME
3893 (setenv "JAVA6_HOME" (getenv "JAVA_HOME"))
3895 (replace 'install (install-jars "dist"))
3896 (add-after 'install 'install-jni-lib
3897 (lambda* (#:key outputs #:allow-other-keys)
3898 (let ((jni (string-append (assoc-ref outputs "out")
3901 (install-file "lib/jni/libIntelDeflater.so" jni)
3904 `(("java-snappy-1" ,java-snappy-1)
3905 ("java-commons-jexl-2" ,java-commons-jexl-2)
3906 ("java-cofoja" ,java-cofoja)
3907 ("ant" ,ant) ; for bzip2 support at runtime
3910 `(("ant-apache-bcel" ,ant-apache-bcel)
3911 ("ant-junit" ,ant-junit)
3912 ("java-testng" ,java-testng)
3913 ("java-commons-bcel" ,java-commons-bcel)
3914 ("java-jcommander" ,java-jcommander)
3915 ("jdk" ,icedtea-8 "jdk")
3916 ("jdk-src" ,(car (assoc-ref (package-native-inputs icedtea-8) "jdk-drop")))))))
3918 (define-public fastqc
3925 (uri (string-append "http://www.bioinformatics.babraham.ac.uk/"
3926 "projects/fastqc/fastqc_v"
3927 version "_source.zip"))
3930 "18rrlkhcrxvvvlapch4dpj6xc6mpayzys8qfppybi8jrpgx5cc5f"))))
3931 (build-system ant-build-system)
3933 `(#:tests? #f ; there are no tests
3934 #:build-target "build"
3936 (modify-phases %standard-phases
3937 (add-after 'unpack 'fix-dependencies
3938 (lambda* (#:key inputs #:allow-other-keys)
3939 (substitute* "build.xml"
3941 (string-append (assoc-ref inputs "java-jbzip2")
3942 "/share/java/jbzip2.jar"))
3944 (string-append (assoc-ref inputs "java-picard-1.113")
3945 "/share/java/sam-1.112.jar"))
3947 (string-append (assoc-ref inputs "java-cisd-jhdf5")
3948 "/share/java/sis-jhdf5.jar")))
3950 ;; There is no installation target
3952 (lambda* (#:key inputs outputs #:allow-other-keys)
3953 (let* ((out (assoc-ref outputs "out"))
3954 (bin (string-append out "/bin"))
3955 (share (string-append out "/share/fastqc/"))
3956 (exe (string-append share "/fastqc")))
3957 (for-each mkdir-p (list bin share))
3958 (copy-recursively "bin" share)
3960 (("my \\$java_bin = 'java';")
3961 (string-append "my $java_bin = '"
3962 (assoc-ref inputs "java")
3965 (symlink exe (string-append bin "/fastqc"))
3969 ("perl" ,perl) ; needed for the wrapper script
3970 ("java-cisd-jhdf5" ,java-cisd-jhdf5)
3971 ("java-picard-1.113" ,java-picard-1.113)
3972 ("java-jbzip2" ,java-jbzip2)))
3974 `(("unzip" ,unzip)))
3975 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/fastqc/")
3976 (synopsis "Quality control tool for high throughput sequence data")
3978 "FastQC aims to provide a simple way to do some quality control
3979 checks on raw sequence data coming from high throughput sequencing
3980 pipelines. It provides a modular set of analyses which you can use to
3981 give a quick impression of whether your data has any problems of which
3982 you should be aware before doing any further analysis.
3984 The main functions of FastQC are:
3987 @item Import of data from BAM, SAM or FastQ files (any variant);
3988 @item Providing a quick overview to tell you in which areas there may
3990 @item Summary graphs and tables to quickly assess your data;
3991 @item Export of results to an HTML based permanent report;
3992 @item Offline operation to allow automated generation of reports
3993 without running the interactive application.
3995 (license license:gpl3+)))
3997 (define-public fastp
4005 (url "https://github.com/OpenGene/fastp.git")
4006 (commit (string-append "v" version))))
4007 (file-name (git-file-name name version))
4010 "1r6ms5zbf5rps4rgp4z73nczadl00b5rqylw8f684isfz27dp0xh"))))
4011 (build-system gnu-build-system)
4013 `(#:tests? #f ; there are none
4015 (list (string-append "BINDIR=" (assoc-ref %outputs "out") "/bin"))
4017 (modify-phases %standard-phases
4019 (add-before 'install 'create-target-dir
4020 (lambda* (#:key outputs #:allow-other-keys)
4021 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4025 (home-page "https://github.com/OpenGene/fastp/")
4026 (synopsis "All-in-one FastQ preprocessor")
4028 "Fastp is a tool designed to provide fast all-in-one preprocessing for
4029 FastQ files. This tool has multi-threading support to afford high
4031 (license license:expat)))
4033 (define-public htslib
4040 "https://github.com/samtools/htslib/releases/download/"
4041 version "/htslib-" version ".tar.bz2"))
4044 "16ljv43sc3fxmv63w7b2ff8m1s7h89xhazwmbm1bicz8axq8fjz0"))))
4045 (build-system gnu-build-system)
4047 `(("openssl" ,openssl)
4052 (home-page "http://www.htslib.org")
4053 (synopsis "C library for reading/writing high-throughput sequencing data")
4055 "HTSlib is a C library for reading/writing high-throughput sequencing
4056 data. It also provides the @command{bgzip}, @command{htsfile}, and
4057 @command{tabix} utilities.")
4058 ;; Files under cram/ are released under the modified BSD license;
4059 ;; the rest is released under the Expat license
4060 (license (list license:expat license:bsd-3))))
4062 ;; This package should be removed once no packages rely upon it.
4070 "https://github.com/samtools/htslib/releases/download/"
4071 version "/htslib-" version ".tar.bz2"))
4074 "1rja282fwdc25ql6izkhdyh8ppw8x2fs0w0js78zgkmqjlikmma9"))))))
4083 (url "https://github.com/nboley/idr.git")
4085 (file-name (git-file-name name version))
4088 "04j876h6z444v2q79drxx283d3k5snd72kj895wbalnl42206x9g"))
4089 ;; Delete generated C code.
4091 '(begin (delete-file "idr/inv_cdf.c") #t))))
4092 (build-system python-build-system)
4093 ;; There is only one test ("test_inv_cdf.py") and it tests features that
4094 ;; are no longer part of this package. It also asserts False, which
4095 ;; causes the tests to always fail.
4096 (arguments `(#:tests? #f))
4098 `(("python-scipy" ,python-scipy)
4099 ("python-sympy" ,python-sympy)
4100 ("python-numpy" ,python-numpy)
4101 ("python-matplotlib" ,python-matplotlib)))
4103 `(("python-cython" ,python-cython)))
4104 (home-page "https://github.com/nboley/idr")
4105 (synopsis "Tool to measure the irreproducible discovery rate (IDR)")
4107 "The IDR (Irreproducible Discovery Rate) framework is a unified approach
4108 to measure the reproducibility of findings identified from replicate
4109 experiments and provide highly stable thresholds based on reproducibility.")
4110 (license license:gpl2+)))
4112 (define-public jellyfish
4118 (uri (string-append "https://github.com/gmarcais/Jellyfish/"
4119 "releases/download/v" version
4120 "/jellyfish-" version ".tar.gz"))
4123 "1k4pc3fvv6w1km2yph4m5sd78fbxp21d6xyzgmy0gjihzc6mb249"))))
4124 (build-system gnu-build-system)
4125 (outputs '("out" ;for library
4126 "ruby" ;for Ruby bindings
4127 "python")) ;for Python bindings
4130 (list (string-append "--enable-ruby-binding="
4131 (assoc-ref %outputs "ruby"))
4132 (string-append "--enable-python-binding="
4133 (assoc-ref %outputs "python")))
4135 (modify-phases %standard-phases
4136 (add-before 'check 'set-SHELL-variable
4138 ;; generator_manager.hpp either uses /bin/sh or $SHELL
4140 (setenv "SHELL" (which "bash"))
4146 ("python" ,python-2)
4147 ("pkg-config" ,pkg-config)))
4149 `(("htslib" ,htslib)))
4150 (synopsis "Tool for fast counting of k-mers in DNA")
4152 "Jellyfish is a tool for fast, memory-efficient counting of k-mers in
4153 DNA. A k-mer is a substring of length k, and counting the occurrences of all
4154 such substrings is a central step in many analyses of DNA sequence. Jellyfish
4155 is a command-line program that reads FASTA and multi-FASTA files containing
4156 DNA sequences. It outputs its k-mer counts in a binary format, which can be
4157 translated into a human-readable text format using the @code{jellyfish dump}
4158 command, or queried for specific k-mers with @code{jellyfish query}.")
4159 (home-page "http://www.genome.umd.edu/jellyfish.html")
4160 ;; JELLYFISH seems to be 64-bit only.
4161 (supported-systems '("x86_64-linux" "aarch64-linux" "mips64el-linux"))
4162 ;; The combined work is published under the GPLv3 or later. Individual
4163 ;; files such as lib/jsoncpp.cpp are released under the Expat license.
4164 (license (list license:gpl3+ license:expat))))
4166 (define-public khmer
4174 (url "https://github.com/dib-lab/khmer.git")
4175 (commit (string-append "v" version))))
4176 (file-name (git-file-name name version))
4179 "02x38d9jw2r58y8dmnj4hffy9wxv1yc1jwbvdbhby9dxndv94r9m"))
4180 (patches (search-patches "khmer-use-libraries.patch"))
4181 (modules '((guix build utils)))
4184 ;; Delete bundled libraries. We do not replace the bundled seqan
4185 ;; as it is a modified subset of the old version 1.4.1.
4187 ;; We do not replace the bundled MurmurHash as the canonical
4188 ;; repository for this code 'SMHasher' is unsuitable for providing
4190 ;; https://lists.gnu.org/archive/html/guix-devel/2016-06/msg00977.html
4191 (delete-file-recursively "third-party/zlib")
4192 (delete-file-recursively "third-party/bzip2")
4194 (build-system python-build-system)
4197 (modify-phases %standard-phases
4198 (add-after 'unpack 'set-cc
4199 (lambda _ (setenv "CC" "gcc") #t))
4200 ;; FIXME: This fails with "permission denied".
4201 (delete 'reset-gzip-timestamps))))
4203 `(("python-cython" ,python-cython)
4204 ("python-pytest" ,python-pytest)
4205 ("python-pytest-runner" ,python-pytest-runner)))
4209 ("python-screed" ,python-screed)
4210 ("python-bz2file" ,python-bz2file)))
4211 (home-page "https://khmer.readthedocs.org/")
4212 (synopsis "K-mer counting, filtering and graph traversal library")
4213 (description "The khmer software is a set of command-line tools for
4214 working with DNA shotgun sequencing data from genomes, transcriptomes,
4215 metagenomes and single cells. Khmer can make de novo assemblies faster, and
4216 sometimes better. Khmer can also identify and fix problems with shotgun
4218 ;; When building on i686, armhf and mips64el, we get the following error:
4219 ;; error: ['khmer', 'khmer.tests', 'oxli'] require 64-bit operating system
4220 (supported-systems '("x86_64-linux" "aarch64-linux"))
4221 (license license:bsd-3)))
4223 (define-public kaiju
4230 (url "https://github.com/bioinformatics-centre/kaiju")
4231 (commit (string-append "v" version))))
4232 (file-name (git-file-name name version))
4235 "119pzi0ddzv9mjg4wwa6han0cwr3k3ssn7kirvsjfcq05mi5ka0x"))))
4236 (build-system gnu-build-system)
4238 `(#:tests? #f ; There are no tests.
4240 (modify-phases %standard-phases
4242 (add-before 'build 'move-to-src-dir
4243 (lambda _ (chdir "src") #t))
4245 (lambda* (#:key inputs outputs #:allow-other-keys)
4246 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
4249 (copy-recursively "bin" bin))
4254 (home-page "http://kaiju.binf.ku.dk/")
4255 (synopsis "Fast and sensitive taxonomic classification for metagenomics")
4256 (description "Kaiju is a program for sensitive taxonomic classification
4257 of high-throughput sequencing reads from metagenomic whole genome sequencing
4259 (license license:gpl3+)))
4264 (version "2.1.1.20160309")
4267 (uri (pypi-uri "MACS2" version))
4270 "09ixspd1vcqmz1c81ih70xs4m7qml2iy5vyx1y74zww3iy1vl210"))))
4271 (build-system python-build-system)
4273 `(#:python ,python-2 ; only compatible with Python 2.7
4274 #:tests? #f)) ; no test target
4276 `(("python-numpy" ,python2-numpy)))
4277 (home-page "https://github.com/taoliu/MACS/")
4278 (synopsis "Model based analysis for ChIP-Seq data")
4280 "MACS is an implementation of a ChIP-Seq analysis algorithm for
4281 identifying transcript factor binding sites named Model-based Analysis of
4282 ChIP-Seq (MACS). MACS captures the influence of genome complexity to evaluate
4283 the significance of enriched ChIP regions and it improves the spatial
4284 resolution of binding sites through combining the information of both
4285 sequencing tag position and orientation.")
4286 (license license:bsd-3)))
4288 (define-public mafft
4295 "https://mafft.cbrc.jp/alignment/software/mafft-" version
4296 "-without-extensions-src.tgz"))
4297 (file-name (string-append name "-" version ".tgz"))
4300 "0bacjkxfg944p5khhyh5rd4y7wkjc9qk4v2jjj442sqlq0f8ar7b"))))
4301 (build-system gnu-build-system)
4303 `(#:tests? #f ; no automated tests, though there are tests in the read me
4304 #:make-flags (let ((out (assoc-ref %outputs "out")))
4305 (list (string-append "PREFIX=" out)
4306 (string-append "BINDIR="
4307 (string-append out "/bin"))))
4309 (modify-phases %standard-phases
4310 (add-after 'unpack 'enter-dir
4311 (lambda _ (chdir "core") #t))
4312 (add-after 'enter-dir 'patch-makefile
4314 ;; on advice from the MAFFT authors, there is no need to
4315 ;; distribute mafft-profile, mafft-distance, or
4316 ;; mafft-homologs.rb as they are too "specialised".
4317 (substitute* "Makefile"
4318 ;; remove mafft-homologs.rb from SCRIPTS
4319 (("^SCRIPTS = mafft mafft-homologs.rb")
4321 ;; remove mafft-homologs from MANPAGES
4322 (("^MANPAGES = mafft.1 mafft-homologs.1")
4323 "MANPAGES = mafft.1")
4324 ;; remove mafft-distance from PROGS
4325 (("^PROGS = dvtditr dndfast7 dndblast sextet5 mafft-distance")
4326 "PROGS = dvtditr dndfast7 dndblast sextet5")
4327 ;; remove mafft-profile from PROGS
4328 (("splittbfast disttbfast tbfast mafft-profile 2cl mccaskillwrap")
4329 "splittbfast disttbfast tbfast f2cl mccaskillwrap")
4330 (("^rm -f mafft-profile mafft-profile.exe") "#")
4331 (("^rm -f mafft-distance mafft-distance.exe") ")#")
4332 ;; do not install MAN pages in libexec folder
4333 (("^\t\\$\\(INSTALL\\) -m 644 \\$\\(MANPAGES\\) \
4334 \\$\\(DESTDIR\\)\\$\\(LIBDIR\\)") "#"))
4336 (add-after 'enter-dir 'patch-paths
4337 (lambda* (#:key inputs #:allow-other-keys)
4338 (substitute* '("pairash.c"
4340 (("perl") (which "perl"))
4341 (("([\"`| ])awk" _ prefix)
4342 (string-append prefix (which "awk")))
4343 (("grep") (which "grep")))
4346 (add-after 'install 'wrap-programs
4347 (lambda* (#:key outputs #:allow-other-keys)
4348 (let* ((out (assoc-ref outputs "out"))
4349 (bin (string-append out "/bin"))
4350 (path (string-append
4351 (assoc-ref %build-inputs "coreutils") "/bin:")))
4352 (for-each (lambda (file)
4354 `("PATH" ":" prefix (,path))))
4362 ("coreutils" ,coreutils)))
4363 (home-page "http://mafft.cbrc.jp/alignment/software/")
4364 (synopsis "Multiple sequence alignment program")
4366 "MAFFT offers a range of multiple alignment methods for nucleotide and
4367 protein sequences. For instance, it offers L-INS-i (accurate; for alignment
4368 of <~200 sequences) and FFT-NS-2 (fast; for alignment of <~30,000
4370 (license (license:non-copyleft
4371 "http://mafft.cbrc.jp/alignment/software/license.txt"
4372 "BSD-3 with different formatting"))))
4381 (url "https://github.com/marbl/mash.git")
4382 (commit (string-append "v" version))))
4383 (file-name (git-file-name name version))
4386 "049hwcc059p2fd9vwndn63laifvvsi0wmv84i6y1fr79k15dxwy6"))
4387 (modules '((guix build utils)))
4390 ;; Delete bundled kseq.
4391 ;; TODO: Also delete bundled murmurhash and open bloom filter.
4392 (delete-file "src/mash/kseq.h")
4394 (build-system gnu-build-system)
4396 `(#:tests? #f ; No tests.
4399 (string-append "--with-capnp=" (assoc-ref %build-inputs "capnproto"))
4400 (string-append "--with-gsl=" (assoc-ref %build-inputs "gsl")))
4401 #:make-flags (list "CC=gcc")
4403 (modify-phases %standard-phases
4404 (add-after 'unpack 'fix-includes
4406 (substitute* '("src/mash/Sketch.cpp"
4407 "src/mash/CommandFind.cpp"
4408 "src/mash/CommandScreen.cpp")
4409 (("^#include \"kseq\\.h\"")
4410 "#include \"htslib/kseq.h\""))
4412 (add-after 'fix-includes 'use-c++14
4414 ;; capnproto 0.7 requires c++14 to build
4415 (substitute* "configure.ac"
4416 (("c\\+\\+11") "c++14"))
4417 (substitute* "Makefile.in"
4418 (("c\\+\\+11") "c++14"))
4421 `(("autoconf" ,autoconf)
4422 ;; Capnproto and htslib are statically embedded in the final
4423 ;; application. Therefore we also list their licenses, below.
4424 ("capnproto" ,capnproto)
4425 ("htslib" ,htslib)))
4429 (supported-systems '("x86_64-linux"))
4430 (home-page "https://mash.readthedocs.io")
4431 (synopsis "Fast genome and metagenome distance estimation using MinHash")
4432 (description "Mash is a fast sequence distance estimator that uses the
4433 MinHash algorithm and is designed to work with genomes and metagenomes in the
4434 form of assemblies or reads.")
4435 (license (list license:bsd-3 ; Mash
4436 license:expat ; HTSlib and capnproto
4437 license:public-domain ; MurmurHash 3
4438 license:cpl1.0)))) ; Open Bloom Filter
4440 (define-public metabat
4448 (url "https://bitbucket.org/berkeleylab/metabat.git")
4449 (commit (string-append "v" version))))
4450 (file-name (git-file-name name version))
4453 "0hyg2smw1nz69mfvjpk45xyyychmda92c80a0cv7baji84ri4iyn"))
4454 (patches (search-patches "metabat-fix-compilation.patch"))))
4455 (build-system scons-build-system)
4457 `(#:scons ,scons-python2
4459 (list (string-append "PREFIX=" (assoc-ref %outputs "out"))
4460 (string-append "BOOST_ROOT=" (assoc-ref %build-inputs "boost")))
4461 #:tests? #f ;; Tests are run during the build phase.
4463 (modify-phases %standard-phases
4464 (add-after 'unpack 'fix-includes
4466 (substitute* "src/BamUtils.h"
4467 (("^#include \"bam/bam\\.h\"")
4468 "#include \"samtools/bam.h\"")
4469 (("^#include \"bam/sam\\.h\"")
4470 "#include \"samtools/sam.h\""))
4471 (substitute* "src/KseqReader.h"
4472 (("^#include \"bam/kseq\\.h\"")
4473 "#include \"htslib/kseq.h\""))
4475 (add-after 'unpack 'fix-scons
4476 (lambda* (#:key inputs #:allow-other-keys)
4477 (substitute* "SConstruct"
4478 (("^htslib_dir += 'samtools'")
4479 (string-append "htslib_dir = '"
4480 (assoc-ref inputs "htslib")
4482 (("^samtools_dir = 'samtools'")
4483 (string-append "samtools_dir = '"
4484 (assoc-ref inputs "samtools")
4486 (("^findStaticOrShared\\('bam', hts_lib")
4487 (string-append "findStaticOrShared('bam', '"
4488 (assoc-ref inputs "samtools")
4490 ;; Do not distribute README.
4491 (("^env\\.Install\\(idir_prefix, 'README\\.md'\\)") ""))
4496 ("samtools" ,samtools)
4499 (home-page "https://bitbucket.org/berkeleylab/metabat")
4501 "Reconstruction of single genomes from complex microbial communities")
4503 "Grouping large genomic fragments assembled from shotgun metagenomic
4504 sequences to deconvolute complex microbial communities, or metagenome binning,
4505 enables the study of individual organisms and their interactions. MetaBAT is
4506 an automated metagenome binning software, which integrates empirical
4507 probabilistic distances of genome abundance and tetranucleotide frequency.")
4508 ;; The source code contains inline assembly.
4509 (supported-systems '("x86_64-linux" "i686-linux"))
4510 (license (license:non-copyleft "file://license.txt"
4511 "See license.txt in the distribution."))))
4513 (define-public minced
4520 (url "https://github.com/ctSkennerton/minced.git")
4522 (file-name (git-file-name name version))
4525 "1f5h9him0gd355cnx7p6pnxpknhckd4g0v62mg8zyhfbx9as25fv"))))
4526 (build-system gnu-build-system)
4528 `(#:test-target "test"
4530 (modify-phases %standard-phases
4532 (add-before 'check 'fix-test
4534 ;; Fix test for latest version.
4535 (substitute* "t/Aquifex_aeolicus_VF5.expected"
4536 (("minced:0.1.6") "minced:0.2.0"))
4538 (replace 'install ; No install target.
4539 (lambda* (#:key inputs outputs #:allow-other-keys)
4540 (let* ((out (assoc-ref outputs "out"))
4541 (bin (string-append out "/bin"))
4542 (wrapper (string-append bin "/minced")))
4543 ;; Minced comes with a wrapper script that tries to figure out where
4544 ;; it is located before running the JAR. Since these paths are known
4545 ;; to us, we build our own wrapper to avoid coreutils dependency.
4546 (install-file "minced.jar" bin)
4547 (with-output-to-file wrapper
4551 "#!" (assoc-ref inputs "bash") "/bin/sh\n\n"
4552 (assoc-ref inputs "jre") "/bin/java -jar "
4553 bin "/minced.jar \"$@\"\n"))))
4554 (chmod wrapper #o555))
4557 `(("jdk" ,icedtea "jdk")))
4560 ("jre" ,icedtea "out")))
4561 (home-page "https://github.com/ctSkennerton/minced")
4562 (synopsis "Mining CRISPRs in Environmental Datasets")
4564 "MinCED is a program to find Clustered Regularly Interspaced Short
4565 Palindromic Repeats (CRISPRs) in DNA sequences. It can be used for
4566 unassembled metagenomic reads, but is mainly designed for full genomes and
4567 assembled metagenomic sequence.")
4568 (license license:gpl3+)))
4576 (uri (pypi-uri "misopy" version))
4579 "1z3x0vd8ma7pdrnywj7i3kgwl89sdkwrrn62zl7r5calqaq2hyip"))
4580 (modules '((guix build utils)))
4582 (substitute* "setup.py"
4583 ;; Use setuptools, or else the executables are not
4585 (("distutils.core") "setuptools")
4586 ;; use "gcc" instead of "cc" for compilation
4588 "cc.set_executables(
4592 linker_so='gcc -shared'); defines"))
4594 (build-system python-build-system)
4596 `(#:python ,python-2 ; only Python 2 is supported
4597 #:tests? #f)) ; no "test" target
4599 `(("samtools" ,samtools)
4600 ("python-numpy" ,python2-numpy)
4601 ("python-pysam" ,python2-pysam)
4602 ("python-scipy" ,python2-scipy)
4603 ("python-matplotlib" ,python2-matplotlib)))
4605 `(("python-mock" ,python2-mock) ;for tests
4606 ("python-pytz" ,python2-pytz))) ;for tests
4607 (home-page "http://genes.mit.edu/burgelab/miso/index.html")
4608 (synopsis "Mixture of Isoforms model for RNA-Seq isoform quantitation")
4610 "MISO (Mixture-of-Isoforms) is a probabilistic framework that quantitates
4611 the expression level of alternatively spliced genes from RNA-Seq data, and
4612 identifies differentially regulated isoforms or exons across samples. By
4613 modeling the generative process by which reads are produced from isoforms in
4614 RNA-Seq, the MISO model uses Bayesian inference to compute the probability
4615 that a read originated from a particular isoform.")
4616 (license license:gpl2)))
4618 (define-public muscle
4621 (version "3.8.1551")
4623 (method url-fetch/tarbomb)
4625 "http://www.drive5.com/muscle/muscle_src_"
4629 "0bj8kj7sdizy3987zx6w7axihk40fk8rn76mpbqqjcnd64i5a367"))))
4630 (build-system gnu-build-system)
4632 `(#:make-flags (list "LDLIBS = -lm")
4634 (modify-phases %standard-phases
4637 ;; There are no tests, so just test if it runs.
4638 (lambda _ (invoke "./muscle" "-version") #t))
4640 (lambda* (#:key outputs #:allow-other-keys)
4641 (let* ((out (assoc-ref outputs "out"))
4642 (bin (string-append out "/bin")))
4643 (install-file "muscle" bin)
4645 (home-page "http://www.drive5.com/muscle")
4646 (synopsis "Multiple sequence alignment program")
4648 "MUSCLE aims to be a fast and accurate multiple sequence alignment
4649 program for nucleotide and protein sequences.")
4650 ;; License information found in 'muscle -h' and usage.cpp.
4651 (license license:public-domain)))
4653 (define-public newick-utils
4654 ;; There are no recent releases so we package from git.
4655 (let ((commit "da121155a977197cab9fbb15953ca1b40b11eb87"))
4657 (name "newick-utils")
4658 (version (string-append "1.6-1." (string-take commit 8)))
4662 (url "https://github.com/tjunier/newick_utils.git")
4664 (file-name (string-append name "-" version "-checkout"))
4667 "1hkw21rq1mwf7xp0rmbb2gqc0i6p11108m69i7mr7xcjl268pxnb"))))
4668 (build-system gnu-build-system)
4670 ;; XXX: TODO: Enable Lua and Guile bindings.
4671 ;; https://github.com/tjunier/newick_utils/issues/13
4672 `(("libxml2" ,libxml2)
4676 `(("autoconf" ,autoconf)
4677 ("automake" ,automake)
4678 ("libtool" ,libtool)))
4679 (synopsis "Programs for working with newick format phylogenetic trees")
4681 "Newick-utils is a suite of utilities for processing phylogenetic trees
4682 in Newick format. Functions include re-rooting, extracting subtrees,
4683 trimming, pruning, condensing, drawing (ASCII graphics or SVG).")
4684 (home-page "https://github.com/tjunier/newick_utils")
4685 (license license:bsd-3))))
4694 "https://github.com/wwood/OrfM/releases/download/v"
4695 version "/orfm-" version ".tar.gz"))
4698 "16iigyr2gd8x0imzkk1dr3k5xsds9bpmwg31ayvjg0f4pir9rwqr"))))
4699 (build-system gnu-build-system)
4700 (inputs `(("zlib" ,zlib)))
4702 `(("ruby-bio-commandeer" ,ruby-bio-commandeer)
4703 ("ruby-rspec" ,ruby-rspec)
4705 (synopsis "Simple and not slow open reading frame (ORF) caller")
4707 "An ORF caller finds stretches of DNA that, when translated, are not
4708 interrupted by stop codons. OrfM finds and prints these ORFs.")
4709 (home-page "https://github.com/wwood/OrfM")
4710 (license license:lgpl3+)))
4712 (define-public python2-pbcore
4714 (name "python2-pbcore")
4718 (uri (pypi-uri "pbcore" version))
4721 "1kjmv891d6qbpp4shhhvkl02ff4q5xlpnls2513sm2cjcrs52f1i"))))
4722 (build-system python-build-system)
4723 (arguments `(#:python ,python-2)) ; pbcore requires Python 2.7
4725 `(("python-cython" ,python2-cython)
4726 ("python-numpy" ,python2-numpy)
4727 ("python-pysam" ,python2-pysam)
4728 ("python-h5py" ,python2-h5py)))
4730 `(("python-nose" ,python2-nose)
4731 ("python-sphinx" ,python2-sphinx)
4732 ("python-pyxb" ,python2-pyxb)))
4733 (home-page "http://pacificbiosciences.github.io/pbcore/")
4734 (synopsis "Library for reading and writing PacBio data files")
4736 "The pbcore package provides Python APIs for interacting with PacBio data
4737 files and writing bioinformatics applications.")
4738 (license license:bsd-3)))
4740 (define-public python2-warpedlmm
4742 (name "python2-warpedlmm")
4747 (uri (pypi-uri "WarpedLMM" version ".zip"))
4750 "1agfz6zqa8nc6cw47yh0s3y14gkpa9wqazwcj7mwwj3ffnw39p3j"))))
4751 (build-system python-build-system)
4753 `(#:python ,python-2)) ; requires Python 2.7
4755 `(("python-scipy" ,python2-scipy)
4756 ("python-numpy" ,python2-numpy)
4757 ("python-matplotlib" ,python2-matplotlib)
4758 ("python-fastlmm" ,python2-fastlmm)
4759 ("python-pandas" ,python2-pandas)
4760 ("python-pysnptools" ,python2-pysnptools)))
4762 `(("python-mock" ,python2-mock)
4763 ("python-nose" ,python2-nose)
4765 (home-page "https://github.com/PMBio/warpedLMM")
4766 (synopsis "Implementation of warped linear mixed models")
4768 "WarpedLMM is a Python implementation of the warped linear mixed model,
4769 which automatically learns an optimal warping function (or transformation) for
4770 the phenotype as it models the data.")
4771 (license license:asl2.0)))
4773 (define-public pbtranscript-tofu
4774 (let ((commit "8f5467fe6a4472bcfb4226c8720993c8507adfe4"))
4776 (name "pbtranscript-tofu")
4777 (version (string-append "2.2.3." (string-take commit 7)))
4781 (url "https://github.com/PacificBiosciences/cDNA_primer.git")
4783 (file-name (string-append name "-" version "-checkout"))
4786 "1lgnpi35ihay42qx0b6yl3kkgra723i413j33kvs0kvs61h82w0f"))
4787 (modules '((guix build utils)))
4790 ;; remove bundled Cython sources
4791 (delete-file "pbtranscript-tofu/pbtranscript/Cython-0.20.1.tar.gz")
4793 (build-system python-build-system)
4795 `(#:python ,python-2
4796 ;; FIXME: Tests fail with "No such file or directory:
4797 ;; pbtools/pbtranscript/modified_bx_intervals/intersection_unique.so"
4800 (modify-phases %standard-phases
4801 (add-after 'unpack 'enter-directory
4803 (chdir "pbtranscript-tofu/pbtranscript/")
4805 ;; With setuptools version 18.0 and later this setup.py hack causes
4806 ;; a build error, so we disable it.
4807 (add-after 'enter-directory 'patch-setuppy
4809 (substitute* "setup.py"
4810 (("if 'setuptools.extension' in sys.modules:")
4814 `(("python-numpy" ,python2-numpy)
4815 ("python-bx-python" ,python2-bx-python)
4816 ("python-networkx" ,python2-networkx)
4817 ("python-scipy" ,python2-scipy)
4818 ("python-pbcore" ,python2-pbcore)
4819 ("python-h5py" ,python2-h5py)))
4821 `(("python-cython" ,python2-cython)
4822 ("python-nose" ,python2-nose)))
4823 (home-page "https://github.com/PacificBiosciences/cDNA_primer")
4824 (synopsis "Analyze transcriptome data generated with the Iso-Seq protocol")
4826 "pbtranscript-tofu contains scripts to analyze transcriptome data
4827 generated using the PacBio Iso-Seq protocol.")
4828 (license license:bsd-3))))
4830 (define-public prank
4837 "http://wasabiapp.org/download/prank/prank.source."
4841 "0am4z94fs3w2n5xpfls9zda61vq7qqz4q2i7b9hlsxz5q4j3kfm4"))))
4842 (build-system gnu-build-system)
4845 (modify-phases %standard-phases
4846 (add-after 'unpack 'enter-src-dir
4850 (add-after 'unpack 'remove-m64-flag
4851 ;; Prank will build with the correct 'bit-ness' without this flag
4852 ;; and this allows building on 32-bit machines.
4853 (lambda _ (substitute* "src/Makefile"
4858 (lambda* (#:key outputs #:allow-other-keys)
4859 (let* ((out (assoc-ref outputs "out"))
4860 (bin (string-append out "/bin"))
4861 (man (string-append out "/share/man/man1"))
4862 (path (string-append
4863 (assoc-ref %build-inputs "mafft") "/bin:"
4864 (assoc-ref %build-inputs "exonerate") "/bin:"
4865 (assoc-ref %build-inputs "bppsuite") "/bin")))
4866 (install-file "prank" bin)
4867 (wrap-program (string-append bin "/prank")
4868 `("PATH" ":" prefix (,path)))
4869 (install-file "prank.1" man))
4873 ("exonerate" ,exonerate)
4874 ("bppsuite" ,bppsuite)))
4875 (home-page "http://wasabiapp.org/software/prank/")
4876 (synopsis "Probabilistic multiple sequence alignment program")
4878 "PRANK is a probabilistic multiple sequence alignment program for DNA,
4879 codon and amino-acid sequences. It is based on a novel algorithm that treats
4880 insertions correctly and avoids over-estimation of the number of deletion
4881 events. In addition, PRANK borrows ideas from maximum likelihood methods used
4882 in phylogenetics and correctly takes into account the evolutionary distances
4883 between sequences. Lastly, PRANK allows for defining a potential structure
4884 for sequences to be aligned and then, simultaneously with the alignment,
4885 predicts the locations of structural units in the sequences.")
4886 (license license:gpl2+)))
4888 (define-public proteinortho
4890 (name "proteinortho")
4897 "http://www.bioinf.uni-leipzig.de/Software/proteinortho/proteinortho_v"
4898 version "_src.tar.gz"))
4901 "1wl0dawpssqwfjvr651r4wlww8hhjin8nba6xh71ks7sbypx886j"))))
4902 (build-system gnu-build-system)
4904 `(#:test-target "test"
4906 (modify-phases %standard-phases
4908 ;; There is no configure script, so we modify the Makefile directly.
4909 (lambda* (#:key outputs #:allow-other-keys)
4910 (substitute* "Makefile"
4913 "INSTALLDIR=" (assoc-ref outputs "out") "/bin\n")))
4915 (add-before 'install 'make-install-directory
4916 ;; The install directory is not created during 'make install'.
4917 (lambda* (#:key outputs #:allow-other-keys)
4918 (mkdir-p (string-append (assoc-ref outputs "out") "/bin"))
4920 (add-after 'install 'wrap-programs
4921 (lambda* (#:key inputs outputs #:allow-other-keys)
4922 (let* ((path (getenv "PATH"))
4923 (out (assoc-ref outputs "out"))
4924 (binary (string-append out "/bin/proteinortho5.pl")))
4925 (wrap-program binary `("PATH" ":" prefix (,path))))
4929 ("python" ,python-2)
4930 ("blast+" ,blast+)))
4931 (home-page "http://www.bioinf.uni-leipzig.de/Software/proteinortho")
4932 (synopsis "Detect orthologous genes across species")
4934 "Proteinortho is a tool to detect orthologous genes across different
4935 species. For doing so, it compares similarities of given gene sequences and
4936 clusters them to find significant groups. The algorithm was designed to handle
4937 large-scale data and can be applied to hundreds of species at once.")
4938 (license license:gpl2+)))
4940 (define-public pyicoteo
4948 (url "https://bitbucket.org/regulatorygenomicsupf/pyicoteo.git")
4949 (commit (string-append "v" version))))
4950 (file-name (git-file-name name version))
4953 "0hz5g8d25lbjy1wpscr490l0lmyvaix893hhax4fxnh1h9w34w8p"))))
4954 (build-system python-build-system)
4956 `(#:python ,python-2 ; does not work with Python 3
4957 #:tests? #f)) ; there are no tests
4959 `(("python2-matplotlib" ,python2-matplotlib)))
4960 (home-page "https://bitbucket.org/regulatorygenomicsupf/pyicoteo")
4961 (synopsis "Analyze high-throughput genetic sequencing data")
4963 "Pyicoteo is a suite of tools for the analysis of high-throughput genetic
4964 sequencing data. It works with genomic coordinates. There are currently six
4965 different command-line tools:
4968 @item pyicoregion: for generating exploratory regions automatically;
4969 @item pyicoenrich: for differential enrichment between two conditions;
4970 @item pyicoclip: for calling CLIP-Seq peaks without a control;
4971 @item pyicos: for genomic coordinates manipulation;
4972 @item pyicoller: for peak calling on punctuated ChIP-Seq;
4973 @item pyicount: to count how many reads from N experiment files overlap in a
4975 @item pyicotrocol: to combine operations from pyicoteo.
4977 (license license:gpl3+)))
4979 (define-public prodigal
4986 (url "https://github.com/hyattpd/Prodigal.git")
4987 (commit (string-append "v" version))))
4988 (file-name (git-file-name name version))
4991 "1fs1hqk83qjbjhrvhw6ni75zakx5ki1ayy3v6wwkn3xvahc9hi5s"))))
4992 (build-system gnu-build-system)
4994 `(#:tests? #f ;no check target
4995 #:make-flags (list (string-append "INSTALLDIR="
4996 (assoc-ref %outputs "out")
4999 (modify-phases %standard-phases
5000 (delete 'configure))))
5001 (home-page "http://prodigal.ornl.gov")
5002 (synopsis "Protein-coding gene prediction for Archaea and Bacteria")
5004 "Prodigal runs smoothly on finished genomes, draft genomes, and
5005 metagenomes, providing gene predictions in GFF3, Genbank, or Sequin table
5006 format. It runs quickly, in an unsupervised fashion, handles gaps, handles
5007 partial genes, and identifies translation initiation sites.")
5008 (license license:gpl3+)))
5010 (define-public roary
5018 "mirror://cpan/authors/id/A/AJ/AJPAGE/Bio-Roary-"
5022 "0qxrds9wx7cfhlkihrp6697kx0flhhxymap9fwan0b3rbdhcnmff"))))
5023 (build-system perl-build-system)
5026 (modify-phases %standard-phases
5031 ;; The tests are not run by default, so we run each test file
5033 (setenv "PATH" (string-append (getcwd) "/bin" ":"
5035 (setenv "PERL5LIB" (string-append (getcwd) "/lib" ":"
5036 (getenv "PERL5LIB")))
5037 (for-each (lambda (file)
5038 (display file)(display "\n")
5039 (invoke "perl" file))
5040 (find-files "t" ".*\\.t$"))
5043 ;; There is no 'install' target in the Makefile.
5044 (lambda* (#:key outputs #:allow-other-keys)
5045 (let* ((out (assoc-ref outputs "out"))
5046 (bin (string-append out "/bin"))
5047 (perl (string-append out "/lib/perl5/site_perl"))
5048 (roary-plots "contrib/roary_plots"))
5051 (copy-recursively "bin" bin)
5052 (copy-recursively "lib" perl)
5054 (add-after 'install 'wrap-programs
5055 (lambda* (#:key inputs outputs #:allow-other-keys)
5056 (let* ((out (assoc-ref outputs "out"))
5057 (perl5lib (getenv "PERL5LIB"))
5058 (path (getenv "PATH")))
5059 (for-each (lambda (prog)
5060 (let ((binary (string-append out "/" prog)))
5061 (wrap-program binary
5062 `("PERL5LIB" ":" prefix
5063 (,(string-append perl5lib ":" out
5064 "/lib/perl5/site_perl"))))
5065 (wrap-program binary
5067 (,(string-append path ":" out "/bin"))))))
5068 (find-files "bin" ".*[^R]$"))
5070 (string-append out "/bin/roary-create_pan_genome_plots.R"))
5071 (r-site-lib (getenv "R_LIBS_SITE"))
5073 (string-append (assoc-ref inputs "coreutils") "/bin")))
5075 `("R_LIBS_SITE" ":" prefix
5076 (,(string-append r-site-lib ":" out "/site-library/"))))
5079 (,(string-append coreutils-path ":" out "/bin"))))))
5082 `(("perl-env-path" ,perl-env-path)
5083 ("perl-test-files" ,perl-test-files)
5084 ("perl-test-most" ,perl-test-most)
5085 ("perl-test-output" ,perl-test-output)))
5087 `(("perl-array-utils" ,perl-array-utils)
5088 ("bioperl" ,bioperl-minimal)
5089 ("perl-digest-md5-file" ,perl-digest-md5-file)
5090 ("perl-exception-class" ,perl-exception-class)
5091 ("perl-file-find-rule" ,perl-file-find-rule)
5092 ("perl-file-grep" ,perl-file-grep)
5093 ("perl-file-slurper" ,perl-file-slurper)
5094 ("perl-file-which" ,perl-file-which)
5095 ("perl-graph" ,perl-graph)
5096 ("perl-graph-readwrite" ,perl-graph-readwrite)
5097 ("perl-log-log4perl" ,perl-log-log4perl)
5098 ("perl-moose" ,perl-moose)
5099 ("perl-perlio-utf8_strict" ,perl-perlio-utf8_strict)
5100 ("perl-text-csv" ,perl-text-csv)
5101 ("bedtools" ,bedtools)
5105 ("parallel" ,parallel)
5108 ("fasttree" ,fasttree)
5112 ("r-minimal" ,r-minimal)
5113 ("r-ggplot2" ,r-ggplot2)
5114 ("coreutils" ,coreutils)))
5115 (home-page "http://sanger-pathogens.github.io/Roary")
5116 (synopsis "High speed stand-alone pan genome pipeline")
5118 "Roary is a high speed stand alone pan genome pipeline, which takes
5119 annotated assemblies in GFF3 format (produced by the Prokka program) and
5120 calculates the pan genome. Using a standard desktop PC, it can analyse
5121 datasets with thousands of samples, without compromising the quality of the
5122 results. 128 samples can be analysed in under 1 hour using 1 GB of RAM and a
5123 single processor. Roary is not intended for metagenomics or for comparing
5124 extremely diverse sets of genomes.")
5125 (license license:gpl3)))
5127 (define-public raxml
5135 (url "https://github.com/stamatak/standard-RAxML.git")
5136 (commit (string-append "v" version))))
5137 (file-name (git-file-name name version))
5140 "1jqjzhch0rips0vp04prvb8vmc20c5pdmsqn8knadcf91yy859fh"))))
5141 (build-system gnu-build-system)
5143 `(#:tests? #f ; There are no tests.
5144 ;; Use 'standard' Makefile rather than SSE or AVX ones.
5145 #:make-flags (list "-f" "Makefile.HYBRID.gcc")
5147 (modify-phases %standard-phases
5150 (lambda* (#:key outputs #:allow-other-keys)
5151 (let* ((out (assoc-ref outputs "out"))
5152 (bin (string-append out "/bin"))
5153 (executable "raxmlHPC-HYBRID"))
5154 (install-file executable bin)
5155 (symlink (string-append bin "/" executable) "raxml"))
5158 `(("openmpi" ,openmpi)))
5159 (home-page "http://sco.h-its.org/exelixis/web/software/raxml/index.html")
5160 (synopsis "Randomized Axelerated Maximum Likelihood phylogenetic trees")
5162 "RAxML is a tool for phylogenetic analysis and post-analysis of large
5164 ;; The source includes x86 specific code
5165 (supported-systems '("x86_64-linux" "i686-linux"))
5166 (license license:gpl2+)))
5176 (url "https://github.com/deweylab/RSEM.git")
5177 (commit (string-append "v" version))))
5179 (base32 "1jlq11d1p8qp64w75yj8cnbbd1a93viq10pzsbwal7vdn8fg13j1"))
5180 (file-name (git-file-name name version))
5181 (modules '((guix build utils)))
5184 ;; remove bundled copy of boost and samtools
5185 (delete-file-recursively "boost")
5186 (delete-file-recursively "samtools-1.3")
5188 (build-system gnu-build-system)
5190 `(#:tests? #f ;no "check" target
5192 (list (string-append "BOOST="
5193 (assoc-ref %build-inputs "boost")
5195 (string-append "SAMHEADERS="
5196 (assoc-ref %build-inputs "htslib")
5197 "/include/htslib/sam.h")
5198 (string-append "SAMLIBS="
5199 (assoc-ref %build-inputs "htslib")
5202 (modify-phases %standard-phases
5203 ;; No "configure" script.
5204 ;; Do not build bundled samtools library.
5207 (substitute* "Makefile"
5208 (("^all : \\$\\(PROGRAMS\\).*") "all: $(PROGRAMS)\n")
5209 (("^\\$\\(SAMLIBS\\).*") ""))
5212 (lambda* (#:key outputs #:allow-other-keys)
5213 (let* ((out (string-append (assoc-ref outputs "out")))
5214 (bin (string-append out "/bin/"))
5215 (perl (string-append out "/lib/perl5/site_perl")))
5218 (for-each (lambda (file)
5219 (install-file file bin))
5220 (find-files "." "rsem-.*"))
5221 (install-file "rsem_perl_utils.pm" perl))
5223 (add-after 'install 'wrap-program
5224 (lambda* (#:key outputs #:allow-other-keys)
5225 (let ((out (assoc-ref outputs "out")))
5226 (for-each (lambda (prog)
5227 (wrap-program (string-append out "/bin/" prog)
5228 `("PERL5LIB" ":" prefix
5229 (,(string-append out "/lib/perl5/site_perl")))))
5230 '("rsem-calculate-expression"
5232 "rsem-generate-data-matrix"
5233 "rsem-generate-ngvector"
5234 "rsem-plot-transcript-wiggles"
5235 "rsem-prepare-reference"
5237 "rsem-run-prsem-testing-procedure")))
5241 ("r-minimal" ,r-minimal)
5243 ("htslib" ,htslib-1.3)
5245 (home-page "http://deweylab.biostat.wisc.edu/rsem/")
5246 (synopsis "Estimate gene expression levels from RNA-Seq data")
5248 "RSEM is a software package for estimating gene and isoform expression
5249 levels from RNA-Seq data. The RSEM package provides a user-friendly
5250 interface, supports threads for parallel computation of the EM algorithm,
5251 single-end and paired-end read data, quality scores, variable-length reads and
5252 RSPD estimation. In addition, it provides posterior mean and 95% credibility
5253 interval estimates for expression levels. For visualization, it can generate
5254 BAM and Wiggle files in both transcript-coordinate and genomic-coordinate.")
5255 (license license:gpl3+)))
5257 (define-public rseqc
5265 (string-append "mirror://sourceforge/rseqc/"
5266 "RSeQC-" version ".tar.gz"))
5268 (base32 "15ly0254yi032qzkdplg00q144qfdsd986gh62829rl5bkxhj330"))
5269 (modules '((guix build utils)))
5272 ;; remove bundled copy of pysam
5273 (delete-file-recursively "lib/pysam")
5274 (substitute* "setup.py"
5275 ;; remove dependency on outdated "distribute" module
5276 (("^from distribute_setup import use_setuptools") "")
5277 (("^use_setuptools\\(\\)") "")
5278 ;; do not use bundled copy of pysam
5279 (("^have_pysam = False") "have_pysam = True"))
5281 (build-system python-build-system)
5282 (arguments `(#:python ,python-2))
5284 `(("python-cython" ,python2-cython)
5285 ("python-pysam" ,python2-pysam)
5286 ("python-numpy" ,python2-numpy)
5289 `(("python-nose" ,python2-nose)))
5290 (home-page "http://rseqc.sourceforge.net/")
5291 (synopsis "RNA-seq quality control package")
5293 "RSeQC provides a number of modules that can comprehensively evaluate
5294 high throughput sequence data, especially RNA-seq data. Some basic modules
5295 inspect sequence quality, nucleotide composition bias, PCR bias and GC bias,
5296 while RNA-seq specific modules evaluate sequencing saturation, mapped reads
5297 distribution, coverage uniformity, strand specificity, etc.")
5298 (license license:gpl3+)))
5301 ;; There are no release tarballs. According to the installation
5302 ;; instructions at http://seek.princeton.edu/installation.jsp, the latest
5303 ;; stable release is identified by this changeset ID.
5304 (let ((changeset "2329130")
5308 (version (string-append "0-" revision "." changeset))
5312 (url "https://bitbucket.org/libsleipnir/sleipnir")
5313 (changeset changeset)))
5314 (file-name (string-append name "-" version "-checkout"))
5317 "0qrvilwh18dpbhkf92qvxbmay0j75ra3jg2wrhz67gf538zzphsx"))))
5318 (build-system gnu-build-system)
5320 `(#:modules ((srfi srfi-1)
5321 (guix build gnu-build-system)
5324 (let ((dirs '("SeekMiner"
5330 (modify-phases %standard-phases
5333 (substitute* "gen_tools_am"
5334 (("/usr/bin/env.*") (which "perl")))
5335 (invoke "bash" "gen_auto")
5337 (add-after 'build 'build-additional-tools
5338 (lambda* (#:key make-flags #:allow-other-keys)
5339 (for-each (lambda (dir)
5340 (with-directory-excursion (string-append "tools/" dir)
5341 (apply invoke "make" make-flags)))
5344 (add-after 'install 'install-additional-tools
5345 (lambda* (#:key make-flags #:allow-other-keys)
5346 (for-each (lambda (dir)
5347 (with-directory-excursion (string-append "tools/" dir)
5348 (apply invoke `("make" ,@make-flags "install"))))
5355 ("readline" ,readline)
5356 ("gengetopt" ,gengetopt)
5357 ("log4cpp" ,log4cpp)))
5359 `(("autoconf" ,autoconf)
5360 ("automake" ,automake)
5362 (home-page "http://seek.princeton.edu")
5363 (synopsis "Gene co-expression search engine")
5365 "SEEK is a computational gene co-expression search engine. SEEK provides
5366 biologists with a way to navigate the massive human expression compendium that
5367 now contains thousands of expression datasets. SEEK returns a robust ranking
5368 of co-expressed genes in the biological area of interest defined by the user's
5369 query genes. It also prioritizes thousands of expression datasets according
5370 to the user's query of interest.")
5371 (license license:cc-by3.0))))
5373 (define-public samtools
5381 (string-append "mirror://sourceforge/samtools/samtools/"
5382 version "/samtools-" version ".tar.bz2"))
5385 "10ilqbmm7ri8z431sn90lvbjwizd0hhkf9rcqw8j823hf26nhgq8"))
5386 (modules '((guix build utils)))
5388 ;; Delete bundled htslib.
5389 (delete-file-recursively "htslib-1.9")
5391 (build-system gnu-build-system)
5393 `(#:modules ((ice-9 ftw)
5395 (guix build gnu-build-system)
5397 #:configure-flags (list "--with-ncurses")
5399 (modify-phases %standard-phases
5400 (add-after 'unpack 'patch-tests
5402 (substitute* "test/test.pl"
5403 ;; The test script calls out to /bin/bash
5404 (("/bin/bash") (which "bash")))
5406 (add-after 'install 'install-library
5407 (lambda* (#:key outputs #:allow-other-keys)
5408 (let ((lib (string-append (assoc-ref outputs "out") "/lib")))
5409 (install-file "libbam.a" lib)
5411 (add-after 'install 'install-headers
5412 (lambda* (#:key outputs #:allow-other-keys)
5413 (let ((include (string-append (assoc-ref outputs "out")
5414 "/include/samtools/")))
5415 (for-each (lambda (file)
5416 (install-file file include))
5417 (scandir "." (lambda (name) (string-match "\\.h$" name))))
5419 (native-inputs `(("pkg-config" ,pkg-config)))
5421 `(("htslib" ,htslib)
5422 ("ncurses" ,ncurses)
5426 (home-page "http://samtools.sourceforge.net")
5427 (synopsis "Utilities to efficiently manipulate nucleotide sequence alignments")
5429 "Samtools implements various utilities for post-processing nucleotide
5430 sequence alignments in the SAM, BAM, and CRAM formats, including indexing,
5431 variant calling (in conjunction with bcftools), and a simple alignment
5433 (license license:expat)))
5435 (define-public samtools-0.1
5436 ;; This is the most recent version of the 0.1 line of samtools. The input
5437 ;; and output formats differ greatly from that used and produced by samtools
5438 ;; 1.x and is still used in many bioinformatics pipelines.
5439 (package (inherit samtools)
5445 (string-append "mirror://sourceforge/samtools/samtools/"
5446 version "/samtools-" version ".tar.bz2"))
5448 (base32 "1m33xsfwz0s8qi45lylagfllqg7fphf4dr0780rsvw75av9wk06h"))))
5450 `(#:tests? #f ;no "check" target
5452 (list "LIBCURSES=-lncurses")
5453 ,@(substitute-keyword-arguments (package-arguments samtools)
5455 `(modify-phases ,phases
5457 (lambda* (#:key outputs #:allow-other-keys)
5458 (let ((bin (string-append
5459 (assoc-ref outputs "out") "/bin")))
5461 (install-file "samtools" bin)
5463 (delete 'patch-tests)
5464 (delete 'configure))))))))
5466 (define-public mosaik
5467 (let ((commit "5c25216d3522d6a33e53875cd76a6d65001e4e67"))
5472 ;; There are no release tarballs nor tags.
5475 (url "https://github.com/wanpinglee/MOSAIK.git")
5477 (file-name (string-append name "-" version))
5480 "17gj3s07cm77r41z92awh0bim7w7q7fbn0sf5nkqmcm1vw052qgw"))))
5481 (build-system gnu-build-system)
5483 `(#:tests? #f ; no tests
5484 #:make-flags (list "CC=gcc")
5486 (modify-phases %standard-phases
5488 (lambda _ (chdir "src") #t))
5490 (lambda* (#:key outputs #:allow-other-keys)
5491 (let ((bin (string-append (assoc-ref outputs "out")
5494 (copy-recursively "../bin" bin)
5498 ("zlib:static" ,zlib "static")
5500 (supported-systems '("x86_64-linux"))
5501 (home-page "https://github.com/wanpinglee/MOSAIK")
5502 (synopsis "Map nucleotide sequence reads to reference genomes")
5504 "MOSAIK is a program for mapping second and third-generation sequencing
5505 reads to a reference genome. MOSAIK can align reads generated by all the
5506 major sequencing technologies, including Illumina, Applied Biosystems SOLiD,
5507 Roche 454, Ion Torrent and Pacific BioSciences SMRT.")
5508 ;; MOSAIK is released under the GPLv2+ with the exception of third-party
5509 ;; code released into the public domain:
5510 ;; 1. fastlz by Ariya Hidayat - http://www.fastlz.org/
5511 ;; 2. MD5 implementation - RSA Data Security, RFC 1321
5512 (license (list license:gpl2+ license:public-domain)))))
5514 (define-public ngs-sdk
5521 (url "https://github.com/ncbi/ngs.git")
5523 (file-name (git-file-name name version))
5526 "17c0v1nah3g3d2ib5bbi0vhma1ghd6vb9xycavqsh64lhp840rk3"))))
5527 (build-system gnu-build-system)
5529 `(#:parallel-build? #f ; not supported
5530 #:tests? #f ; no "check" target
5532 (modify-phases %standard-phases
5534 (lambda* (#:key outputs #:allow-other-keys)
5535 (let ((out (assoc-ref outputs "out")))
5536 ;; Allow 'konfigure.perl' to find 'package.prl'.
5538 (string-append ".:" (getenv "PERL5LIB")))
5540 ;; The 'configure' script doesn't recognize things like
5541 ;; '--enable-fast-install'.
5542 (invoke "./configure"
5543 (string-append "--build-prefix=" (getcwd) "/build")
5544 (string-append "--prefix=" out))
5546 (add-after 'unpack 'enter-dir
5547 (lambda _ (chdir "ngs-sdk") #t)))))
5548 (native-inputs `(("perl" ,perl)))
5549 ;; According to the test
5550 ;; unless ($MARCH =~ /x86_64/i || $MARCH =~ /i?86/i)
5551 ;; in ngs-sdk/setup/konfigure.perl
5552 (supported-systems '("i686-linux" "x86_64-linux"))
5553 (home-page "https://github.com/ncbi/ngs")
5554 (synopsis "API for accessing Next Generation Sequencing data")
5556 "NGS is a domain-specific API for accessing reads, alignments and pileups
5557 produced from Next Generation Sequencing. The API itself is independent from
5558 any particular back-end implementation, and supports use of multiple back-ends
5560 (license license:public-domain)))
5562 (define-public java-ngs
5563 (package (inherit ngs-sdk)
5566 `(,@(substitute-keyword-arguments
5567 `(#:modules ((guix build gnu-build-system)
5571 ,@(package-arguments ngs-sdk))
5573 `(modify-phases ,phases
5574 (replace 'enter-dir (lambda _ (chdir "ngs-java") #t)))))))
5576 `(("jdk" ,icedtea "jdk")
5577 ("ngs-sdk" ,ngs-sdk)))
5578 (synopsis "Java bindings for NGS SDK")))
5580 (define-public ncbi-vdb
5587 (url "https://github.com/ncbi/ncbi-vdb.git")
5589 (file-name (git-file-name name version))
5592 "1l4ny67nxwv1lagk9wwjbrgm7ln7adci6dnpc7k1yaln6shj0qpm"))))
5593 (build-system gnu-build-system)
5595 `(#:parallel-build? #f ; not supported
5596 #:tests? #f ; no "check" target
5598 (modify-phases %standard-phases
5599 (add-after 'unpack 'make-files-writable
5600 (lambda _ (for-each make-file-writable (find-files "." ".*")) #t))
5601 (add-before 'configure 'set-perl-search-path
5603 ;; Work around "dotless @INC" build failure.
5605 (string-append (getcwd) "/setup:"
5606 (getenv "PERL5LIB")))
5609 (lambda* (#:key inputs outputs #:allow-other-keys)
5610 (let ((out (assoc-ref outputs "out")))
5611 ;; Override include path for libmagic
5612 (substitute* "setup/package.prl"
5613 (("name => 'magic', Include => '/usr/include'")
5614 (string-append "name=> 'magic', Include => '"
5615 (assoc-ref inputs "libmagic")
5618 ;; Install kdf5 library (needed by sra-tools)
5619 (substitute* "build/Makefile.install"
5620 (("LIBRARIES_TO_INSTALL =")
5621 "LIBRARIES_TO_INSTALL = kdf5.$(VERSION_LIBX) kdf5.$(VERSION_SHLX)"))
5623 (substitute* "build/Makefile.env"
5624 (("CFLAGS =" prefix)
5625 (string-append prefix "-msse2 ")))
5627 ;; Override search path for ngs-java
5628 (substitute* "setup/package.prl"
5629 (("/usr/local/ngs/ngs-java")
5630 (assoc-ref inputs "java-ngs")))
5632 ;; The 'configure' script doesn't recognize things like
5633 ;; '--enable-fast-install'.
5634 (invoke "./configure"
5635 (string-append "--build-prefix=" (getcwd) "/build")
5636 (string-append "--prefix=" (assoc-ref outputs "out"))
5637 (string-append "--debug")
5638 (string-append "--with-xml2-prefix="
5639 (assoc-ref inputs "libxml2"))
5640 (string-append "--with-ngs-sdk-prefix="
5641 (assoc-ref inputs "ngs-sdk"))
5642 (string-append "--with-hdf5-prefix="
5643 (assoc-ref inputs "hdf5")))
5645 (add-after 'install 'install-interfaces
5646 (lambda* (#:key outputs #:allow-other-keys)
5647 ;; Install interface libraries. On i686 the interface libraries
5648 ;; are installed to "linux/gcc/i386", so we need to use the Linux
5649 ;; architecture name ("i386") instead of the target system prefix
5651 (mkdir (string-append (assoc-ref outputs "out") "/ilib"))
5652 (copy-recursively (string-append "build/ncbi-vdb/linux/gcc/"
5653 ,(system->linux-architecture
5654 (or (%current-target-system)
5657 (string-append (assoc-ref outputs "out")
5659 ;; Install interface headers
5660 (copy-recursively "interfaces"
5661 (string-append (assoc-ref outputs "out")
5664 ;; These files are needed by sra-tools.
5665 (add-after 'install 'install-configuration-files
5666 (lambda* (#:key outputs #:allow-other-keys)
5667 (let ((target (string-append (assoc-ref outputs "out") "/kfg")))
5669 (install-file "libs/kfg/default.kfg" target)
5670 (install-file "libs/kfg/certs.kfg" target))
5673 `(("libxml2" ,libxml2)
5674 ("ngs-sdk" ,ngs-sdk)
5675 ("java-ngs" ,java-ngs)
5678 (native-inputs `(("perl" ,perl)))
5679 ;; NCBI-VDB requires SSE capability.
5680 (supported-systems '("i686-linux" "x86_64-linux"))
5681 (home-page "https://github.com/ncbi/ncbi-vdb")
5682 (synopsis "Database engine for genetic information")
5684 "The NCBI-VDB library implements a highly compressed columnar data
5685 warehousing engine that is most often used to store genetic information.
5686 Databases are stored in a portable image within the file system, and can be
5687 accessed/downloaded on demand across HTTP.")
5688 (license license:public-domain)))
5690 (define-public plink
5698 "http://pngu.mgh.harvard.edu/~purcell/plink/dist/plink-"
5699 version "-src.zip"))
5701 (base32 "0as8gxm4pjyc8dxmm1sl873rrd7wn5qs0l29nqfnl31x8i467xaa"))
5702 (patches (search-patches "plink-1.07-unclobber-i.patch"
5703 "plink-endian-detection.patch"))))
5704 (build-system gnu-build-system)
5706 '(#:tests? #f ;no "check" target
5707 #:make-flags (list (string-append "LIB_LAPACK="
5708 (assoc-ref %build-inputs "lapack")
5709 "/lib/liblapack.so")
5712 ;; disable phoning home
5715 (modify-phases %standard-phases
5716 ;; no "configure" script
5719 (lambda* (#:key outputs #:allow-other-keys)
5720 (let ((bin (string-append (assoc-ref outputs "out")
5722 (install-file "plink" bin)
5726 ("lapack" ,lapack)))
5728 `(("unzip" ,unzip)))
5729 (home-page "http://pngu.mgh.harvard.edu/~purcell/plink/")
5730 (synopsis "Whole genome association analysis toolset")
5732 "PLINK is a whole genome association analysis toolset, designed to
5733 perform a range of basic, large-scale analyses in a computationally efficient
5734 manner. The focus of PLINK is purely on analysis of genotype/phenotype data,
5735 so there is no support for steps prior to this (e.g. study design and
5736 planning, generating genotype or CNV calls from raw data). Through
5737 integration with gPLINK and Haploview, there is some support for the
5738 subsequent visualization, annotation and storage of results.")
5739 ;; Code is released under GPLv2, except for fisher.h, which is under
5741 (license (list license:gpl2 license:lgpl2.1+))))
5743 (define-public plink-ng
5744 (package (inherit plink)
5751 (url "https://github.com/chrchang/plink-ng.git")
5752 (commit (string-append "v" version))))
5753 (file-name (git-file-name name version))
5755 (base32 "02npdwgkpfkdnhw819rhj5kw02a5k5m90b14zq9zzya4hyg929c0"))))
5756 (build-system gnu-build-system)
5758 '(#:tests? #f ;no "check" target
5759 #:make-flags (list "BLASFLAGS=-llapack -lopenblas"
5760 "CFLAGS=-Wall -O2 -DDYNAMIC_ZLIB=1"
5762 "-f" "Makefile.std")
5764 (modify-phases %standard-phases
5765 (add-after 'unpack 'chdir
5766 (lambda _ (chdir "1.9") #t))
5767 (delete 'configure) ; no "configure" script
5769 (lambda* (#:key outputs #:allow-other-keys)
5770 (let ((bin (string-append (assoc-ref outputs "out")
5772 (install-file "plink" bin)
5777 ("openblas" ,openblas)))
5778 (home-page "https://www.cog-genomics.org/plink/")
5779 (license license:gpl3+)))
5781 (define-public smithlab-cpp
5782 (let ((revision "1")
5783 (commit "728a097bec88c6f4b8528b685932049e660eff2e"))
5785 (name "smithlab-cpp")
5786 (version (string-append "0." revision "." (string-take commit 7)))
5790 (url "https://github.com/smithlabcode/smithlab_cpp.git")
5792 (file-name (string-append name "-" version "-checkout"))
5795 "0d476lmj312xk77kr9fzrv7z1bv96yfyx0w7y62ycmnfbx32ll74"))))
5796 (build-system gnu-build-system)
5798 `(#:modules ((guix build gnu-build-system)
5801 #:tests? #f ;no "check" target
5803 (modify-phases %standard-phases
5804 (add-after 'unpack 'use-samtools-headers
5806 (substitute* '("SAM.cpp"
5808 (("sam.h") "samtools/sam.h"))
5811 (lambda* (#:key outputs #:allow-other-keys)
5812 (let* ((out (assoc-ref outputs "out"))
5813 (lib (string-append out "/lib"))
5814 (include (string-append out "/include/smithlab-cpp")))
5817 (for-each (cut install-file <> lib)
5818 (find-files "." "\\.o$"))
5819 (for-each (cut install-file <> include)
5820 (find-files "." "\\.hpp$")))
5822 (delete 'configure))))
5824 `(("samtools" ,samtools-0.1)
5826 (home-page "https://github.com/smithlabcode/smithlab_cpp")
5827 (synopsis "C++ helper library for functions used in Smith lab projects")
5829 "Smithlab CPP is a C++ library that includes functions used in many of
5830 the Smith lab bioinformatics projects, such as a wrapper around Samtools data
5831 structures, classes for genomic regions, mapped sequencing reads, etc.")
5832 (license license:gpl3+))))
5834 (define-public preseq
5840 (uri (string-append "https://github.com/smithlabcode/preseq/"
5841 "releases/download/v" version
5842 "/preseq_v" version ".tar.bz2"))
5844 (base32 "149x9xmk1wy1gff85325yfzqc0qk4sgp1w6gbyj9cnji4x1dszbl"))
5845 (modules '((guix build utils)))
5847 ;; Remove bundled samtools.
5848 (delete-file-recursively "samtools")
5850 (build-system gnu-build-system)
5852 `(#:tests? #f ;no "check" target
5854 (modify-phases %standard-phases
5855 (delete 'configure))
5857 (list (string-append "PREFIX="
5858 (assoc-ref %outputs "out"))
5859 (string-append "LIBBAM="
5860 (assoc-ref %build-inputs "samtools")
5862 (string-append "SMITHLAB_CPP="
5863 (assoc-ref %build-inputs "smithlab-cpp")
5866 "INCLUDEDIRS=$(SMITHLAB_CPP)/../include/smithlab-cpp $(SAMTOOLS_DIR)")))
5869 ("samtools" ,samtools-0.1)
5870 ("smithlab-cpp" ,smithlab-cpp)
5872 (home-page "http://smithlabresearch.org/software/preseq/")
5873 (synopsis "Program for analyzing library complexity")
5875 "The preseq package is aimed at predicting and estimating the complexity
5876 of a genomic sequencing library, equivalent to predicting and estimating the
5877 number of redundant reads from a given sequencing depth and how many will be
5878 expected from additional sequencing using an initial sequencing experiment.
5879 The estimates can then be used to examine the utility of further sequencing,
5880 optimize the sequencing depth, or to screen multiple libraries to avoid low
5881 complexity samples.")
5882 (license license:gpl3+)))
5884 (define-public python-screed
5886 (name "python-screed")
5891 (uri (pypi-uri "screed" version))
5894 "148vcb7w2wr6a4w6vs2bsxanbqibxfk490zbcbg4m61s8669zdjx"))))
5895 (build-system python-build-system)
5898 (modify-phases %standard-phases
5899 ;; Tests must be run after installation, as the "screed" command does
5900 ;; not exist right after building.
5902 (add-after 'install 'check
5903 (lambda* (#:key inputs outputs #:allow-other-keys)
5904 (let ((out (assoc-ref outputs "out")))
5905 (setenv "PYTHONPATH"
5906 (string-append out "/lib/python"
5907 (string-take (string-take-right
5908 (assoc-ref inputs "python")
5911 (getenv "PYTHONPATH")))
5912 (setenv "PATH" (string-append out "/bin:" (getenv "PATH"))))
5913 (invoke "python" "setup.py" "test")
5916 `(("python-pytest" ,python-pytest)
5917 ("python-pytest-cov" ,python-pytest-cov)
5918 ("python-pytest-runner" ,python-pytest-runner)))
5920 `(("python-bz2file" ,python-bz2file)))
5921 (home-page "https://github.com/dib-lab/screed/")
5922 (synopsis "Short read sequence database utilities")
5923 (description "Screed parses FASTA and FASTQ files and generates databases.
5924 Values such as sequence name, sequence description, sequence quality and the
5925 sequence itself can be retrieved from these databases.")
5926 (license license:bsd-3)))
5928 (define-public python2-screed
5929 (package-with-python2 python-screed))
5931 (define-public sra-tools
5939 (url "https://github.com/ncbi/sra-tools.git")
5941 (file-name (git-file-name name version))
5944 "0663gcdxkziwsmlznjxysb00621rllpbz6jwsfifq7z3dj3lwm8b"))))
5945 (build-system gnu-build-system)
5947 `(#:parallel-build? #f ; not supported
5948 #:tests? #f ; no "check" target
5950 (list (string-append "DEFAULT_CRT="
5951 (assoc-ref %build-inputs "ncbi-vdb")
5953 (string-append "DEFAULT_KFG="
5954 (assoc-ref %build-inputs "ncbi-vdb")
5956 (string-append "VDB_LIBDIR="
5957 (assoc-ref %build-inputs "ncbi-vdb")
5958 ,(if (string-prefix? "x86_64"
5959 (or (%current-target-system)
5964 (modify-phases %standard-phases
5965 (add-before 'configure 'set-perl-search-path
5967 ;; Work around "dotless @INC" build failure.
5969 (string-append (getcwd) "/setup:"
5970 (getenv "PERL5LIB")))
5973 (lambda* (#:key inputs outputs #:allow-other-keys)
5974 ;; The build system expects a directory containing the sources and
5975 ;; raw build output of ncbi-vdb, including files that are not
5976 ;; installed. Since we are building against an installed version of
5977 ;; ncbi-vdb, the following modifications are needed.
5978 (substitute* "setup/konfigure.perl"
5979 ;; Make the configure script look for the "ilib" directory of
5980 ;; "ncbi-vdb" without first checking for the existence of a
5981 ;; matching library in its "lib" directory.
5982 (("^ my \\$f = File::Spec->catdir\\(\\$libdir, \\$lib\\);")
5983 "my $f = File::Spec->catdir($ilibdir, $ilib);")
5984 ;; Look for interface libraries in ncbi-vdb's "ilib" directory.
5985 (("my \\$ilibdir = File::Spec->catdir\\(\\$builddir, 'ilib'\\);")
5986 "my $ilibdir = File::Spec->catdir($dir, 'ilib');"))
5989 (substitute* "tools/copycat/Makefile"
5990 (("smagic-static") "lmagic"))
5992 ;; The 'configure' script doesn't recognize things like
5993 ;; '--enable-fast-install'.
5994 (invoke "./configure"
5995 (string-append "--build-prefix=" (getcwd) "/build")
5996 (string-append "--prefix=" (assoc-ref outputs "out"))
5997 (string-append "--debug")
5998 (string-append "--with-fuse-prefix="
5999 (assoc-ref inputs "fuse"))
6000 (string-append "--with-magic-prefix="
6001 (assoc-ref inputs "libmagic"))
6002 ;; TODO: building with libxml2 fails with linker errors
6003 ;; (string-append "--with-xml2-prefix="
6004 ;; (assoc-ref inputs "libxml2"))
6005 (string-append "--with-ncbi-vdb-sources="
6006 (assoc-ref inputs "ncbi-vdb"))
6007 (string-append "--with-ncbi-vdb-build="
6008 (assoc-ref inputs "ncbi-vdb"))
6009 (string-append "--with-ngs-sdk-prefix="
6010 (assoc-ref inputs "ngs-sdk"))
6011 (string-append "--with-hdf5-prefix="
6012 (assoc-ref inputs "hdf5")))
6014 (native-inputs `(("perl" ,perl)))
6016 `(("ngs-sdk" ,ngs-sdk)
6017 ("ncbi-vdb" ,ncbi-vdb)
6022 (home-page "http://www.ncbi.nlm.nih.gov/Traces/sra/sra.cgi?view=software")
6023 (synopsis "Tools and libraries for reading and writing sequencing data")
6025 "The SRA Toolkit from NCBI is a collection of tools and libraries for
6026 reading of sequencing files from the Sequence Read Archive (SRA) database and
6027 writing files into the .sra format.")
6028 (license license:public-domain)))
6030 (define-public seqan
6036 (uri (string-append "https://github.com/seqan/seqan/releases/"
6037 "download/seqan-v" version
6038 "/seqan-library-" version ".tar.xz"))
6041 "19a1rlxx03qy1i1iriicly68w64yjxbv24g9gdywnfmq998v35yx"))))
6042 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6043 ;; makes sense to split the outputs.
6044 (outputs '("out" "doc"))
6045 (build-system trivial-build-system)
6047 `(#:modules ((guix build utils))
6050 (use-modules (guix build utils))
6051 (let ((tar (assoc-ref %build-inputs "tar"))
6052 (xz (assoc-ref %build-inputs "xz"))
6053 (out (assoc-ref %outputs "out"))
6054 (doc (assoc-ref %outputs "doc")))
6055 (setenv "PATH" (string-append tar "/bin:" xz "/bin"))
6056 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6057 (chdir (string-append "seqan-library-" ,version))
6058 (copy-recursively "include" (string-append out "/include"))
6059 (copy-recursively "share" (string-append doc "/share"))
6062 `(("source" ,source)
6065 (home-page "http://www.seqan.de")
6066 (synopsis "Library for nucleotide sequence analysis")
6068 "SeqAn is a C++ library of efficient algorithms and data structures for
6069 the analysis of sequences with the focus on biological data. It contains
6070 algorithms and data structures for string representation and their
6071 manipulation, online and indexed string search, efficient I/O of
6072 bioinformatics file formats, sequence alignment, and more.")
6073 (license license:bsd-3)))
6075 (define-public seqan-1
6076 (package (inherit seqan)
6081 (uri (string-append "http://packages.seqan.de/seqan-library/"
6082 "seqan-library-" version ".tar.bz2"))
6085 "05s3wrrwn50f81aklfm65i4a749zag1vr8z03k21xm0pdxy47yvp"))))
6086 ;; The documentation is 7.8MB and the includes are 3.6MB heavy, so it
6087 ;; makes sense to split the outputs.
6088 (outputs '("out" "doc"))
6089 (build-system trivial-build-system)
6091 `(#:modules ((guix build utils))
6094 (use-modules (guix build utils))
6095 (let ((tar (assoc-ref %build-inputs "tar"))
6096 (bzip (assoc-ref %build-inputs "bzip2"))
6097 (out (assoc-ref %outputs "out"))
6098 (doc (assoc-ref %outputs "doc")))
6099 (setenv "PATH" (string-append tar "/bin:" bzip "/bin"))
6100 (invoke "tar" "xvf" (assoc-ref %build-inputs "source"))
6101 (chdir (string-append "seqan-library-" ,version))
6102 (copy-recursively "include" (string-append out "/include"))
6103 (copy-recursively "share" (string-append doc "/share"))
6106 `(("source" ,source)
6108 ("bzip2" ,bzip2)))))
6110 (define-public seqmagick
6117 (uri (pypi-uri "seqmagick" version))
6120 "12bfyp8nqi0hd36rmj450aygafp01qy3hkbvlwn3bk39pyjjkgg5"))))
6121 (build-system python-build-system)
6123 `(("python-biopython" ,python-biopython)))
6125 `(("python-nose" ,python-nose)))
6126 (home-page "https://github.com/fhcrc/seqmagick")
6127 (synopsis "Tools for converting and modifying sequence files")
6129 "Bioinformaticians often have to convert sequence files between formats
6130 and do little manipulations on them, and it's not worth writing scripts for
6131 that. Seqmagick is a utility to expose the file format conversion in
6132 BioPython in a convenient way. Instead of having a big mess of scripts, there
6133 is one that takes arguments.")
6134 (license license:gpl3)))
6136 (define-public seqtk
6143 (url "https://github.com/lh3/seqtk.git")
6144 (commit (string-append "v" version))))
6145 (file-name (git-file-name name version))
6148 "1bfzlqa84b5s1qi22blmmw2s8xdyp9h9ydcq22pfjhh5gab3yz6l"))))
6149 (build-system gnu-build-system)
6152 (modify-phases %standard-phases
6155 ;; There are no tests, so we just run a sanity check.
6156 (lambda _ (invoke "./seqtk" "seq") #t))
6158 (lambda* (#:key outputs #:allow-other-keys)
6159 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6160 (install-file "seqtk" bin)
6164 (home-page "https://github.com/lh3/seqtk")
6165 (synopsis "Toolkit for processing biological sequences in FASTA/Q format")
6167 "Seqtk is a fast and lightweight tool for processing sequences in the
6168 FASTA or FASTQ format. It parses both FASTA and FASTQ files which can be
6169 optionally compressed by gzip.")
6170 (license license:expat)))
6172 (define-public snap-aligner
6174 (name "snap-aligner")
6175 (version "1.0beta.18")
6179 (url "https://github.com/amplab/snap.git")
6180 (commit (string-append "v" version))))
6181 (file-name (git-file-name name version))
6184 "01w3qq4wm07z73vky0cfwlmrbf50n3w722cxrlzxfi99mnb808d8"))))
6185 (build-system gnu-build-system)
6188 (modify-phases %standard-phases
6190 (replace 'check (lambda _ (invoke "./unit_tests") #t))
6192 (lambda* (#:key outputs #:allow-other-keys)
6193 (let* ((out (assoc-ref outputs "out"))
6194 (bin (string-append out "/bin")))
6195 (install-file "snap-aligner" bin)
6196 (install-file "SNAPCommand" bin)
6200 (home-page "http://snap.cs.berkeley.edu/")
6201 (synopsis "Short read DNA sequence aligner")
6203 "SNAP is a fast and accurate aligner for short DNA reads. It is
6204 optimized for modern read lengths of 100 bases or higher, and takes advantage
6205 of these reads to align data quickly through a hash-based indexing scheme.")
6206 ;; 32-bit systems are not supported by the unpatched code.
6207 ;; Following the bug reports https://github.com/amplab/snap/issues/68 and
6208 ;; https://bugs.debian.org/cgi-bin/bugreport.cgi?bug=812378 we see that
6209 ;; systems without a lot of memory cannot make good use of this program.
6210 (supported-systems '("x86_64-linux"))
6211 (license license:asl2.0)))
6213 (define-public sortmerna
6221 (url "https://github.com/biocore/sortmerna.git")
6223 (file-name (git-file-name name version))
6226 "0j3mbz4n25738yijmjbr5r4fyvkgm8v5vn3sshyfvmyqf5q9byqf"))))
6227 (build-system gnu-build-system)
6228 (outputs '("out" ;for binaries
6229 "db")) ;for sequence databases
6232 (modify-phases %standard-phases
6234 (lambda* (#:key outputs #:allow-other-keys)
6235 (let* ((out (assoc-ref outputs "out"))
6236 (bin (string-append out "/bin"))
6237 (db (assoc-ref outputs "db"))
6239 (string-append db "/share/sortmerna/rRNA_databases")))
6240 (install-file "sortmerna" bin)
6241 (install-file "indexdb_rna" bin)
6242 (for-each (lambda (file)
6243 (install-file file share))
6244 (find-files "rRNA_databases" ".*fasta"))
6248 (home-page "http://bioinfo.lifl.fr/RNA/sortmerna")
6249 (synopsis "Biological sequence analysis tool for NGS reads")
6251 "SortMeRNA is a biological sequence analysis tool for filtering, mapping
6252 and operational taxonomic unit (OTU) picking of next generation
6253 sequencing (NGS) reads. The core algorithm is based on approximate seeds and
6254 allows for fast and sensitive analyses of nucleotide sequences. The main
6255 application of SortMeRNA is filtering rRNA from metatranscriptomic data.")
6256 ;; The source includes x86 specific code
6257 (supported-systems '("x86_64-linux" "i686-linux"))
6258 (license license:lgpl3)))
6267 (url "https://github.com/alexdobin/STAR.git")
6269 (file-name (string-append name "-" version "-checkout"))
6272 "1lih6cbpvnvhyvvswdhy06mwyzvwax96m723378v4z6psqzsh11d"))
6273 (modules '((guix build utils)))
6276 (substitute* "source/Makefile"
6278 ;; Remove pre-built binaries and bundled htslib sources.
6279 (delete-file-recursively "bin/MacOSX_x86_64")
6280 (delete-file-recursively "bin/Linux_x86_64")
6281 (delete-file-recursively "bin/Linux_x86_64_static")
6282 (delete-file-recursively "source/htslib")
6284 (build-system gnu-build-system)
6286 '(#:tests? #f ;no check target
6287 #:make-flags '("STAR")
6289 (modify-phases %standard-phases
6290 (add-after 'unpack 'enter-source-dir
6291 (lambda _ (chdir "source") #t))
6292 (add-after 'enter-source-dir 'make-reproducible
6294 (substitute* "Makefile"
6295 (("(COMPILATION_TIME_PLACE=\")(.*)(\")" _ pre mid post)
6296 (string-append pre "Built with Guix" post)))
6298 ;; See https://github.com/alexdobin/STAR/pull/562
6299 (add-after 'enter-source-dir 'add-missing-header
6301 (substitute* "SoloReadFeature_inputRecords.cpp"
6302 (("#include \"binarySearch2.h\"" h)
6303 (string-append h "\n#include <math.h>")))
6305 (add-after 'enter-source-dir 'do-not-use-bundled-htslib
6307 (substitute* "Makefile"
6308 (("(Depend.list: \\$\\(SOURCES\\) parametersDefault\\.xxd) htslib"
6310 (substitute* '("BAMfunctions.cpp"
6315 "bamRemoveDuplicates.cpp")
6316 (("#include \"htslib/([^\"]+\\.h)\"" _ header)
6317 (string-append "#include <" header ">")))
6318 (substitute* "IncludeDefine.h"
6319 (("\"htslib/(htslib/[^\"]+.h)\"" _ header)
6320 (string-append "<" header ">")))
6323 (lambda* (#:key outputs #:allow-other-keys)
6324 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6325 (install-file "STAR" bin))
6327 (delete 'configure))))
6331 `(("htslib" ,htslib)
6333 (home-page "https://github.com/alexdobin/STAR")
6334 (synopsis "Universal RNA-seq aligner")
6336 "The Spliced Transcripts Alignment to a Reference (STAR) software is
6337 based on a previously undescribed RNA-seq alignment algorithm that uses
6338 sequential maximum mappable seed search in uncompressed suffix arrays followed
6339 by seed clustering and stitching procedure. In addition to unbiased de novo
6340 detection of canonical junctions, STAR can discover non-canonical splices and
6341 chimeric (fusion) transcripts, and is also capable of mapping full-length RNA
6343 ;; Only 64-bit systems are supported according to the README.
6344 (supported-systems '("x86_64-linux" "mips64el-linux"))
6345 ;; STAR is licensed under GPLv3 or later; htslib is MIT-licensed.
6346 (license license:gpl3+)))
6348 (define-public starlong
6349 (package (inherit star)
6352 (substitute-keyword-arguments (package-arguments star)
6353 ((#:make-flags flags)
6356 `(modify-phases ,phases
6357 ;; Allow extra long sequence reads.
6358 (add-after 'unpack 'make-extra-long
6360 (substitute* "source/IncludeDefine.h"
6361 (("(#define DEF_readNameLengthMax ).*" _ match)
6362 (string-append match "900000\n")))
6365 (lambda* (#:key outputs #:allow-other-keys)
6366 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6367 (install-file "STARlong" bin))
6370 (define-public subread
6376 (uri (string-append "mirror://sourceforge/subread/subread-"
6377 version "/subread-" version "-source.tar.gz"))
6380 "0ah0n4jx6ksk2m2j7xk385x2qzmk1y4rfc6a4mfrdqrlq721w99i"))))
6381 (build-system gnu-build-system)
6383 `(#:tests? #f ;no "check" target
6384 ;; The CC and CCFLAGS variables are set to contain a lot of x86_64
6385 ;; optimizations by default, so we override these flags such that x86_64
6386 ;; flags are only added when the build target is an x86_64 system.
6388 (list (let ((system ,(or (%current-target-system)
6390 (flags '("-ggdb" "-fomit-frame-pointer"
6391 "-ffast-math" "-funroll-loops"
6392 "-fmessage-length=0"
6393 "-O9" "-Wall" "-DMAKE_FOR_EXON"
6395 "-DSUBREAD_VERSION=\\\"${SUBREAD_VERSION}\\\""))
6396 (flags64 '("-mmmx" "-msse" "-msse2" "-msse3")))
6397 (if (string-prefix? "x86_64" system)
6398 (string-append "CCFLAGS=" (string-join (append flags flags64)))
6399 (string-append "CCFLAGS=" (string-join flags))))
6400 "-f" "Makefile.Linux"
6401 "CC=gcc ${CCFLAGS}")
6403 (modify-phases %standard-phases
6404 (add-after 'unpack 'enter-dir
6405 (lambda _ (chdir "src") #t))
6407 (lambda* (#:key outputs #:allow-other-keys)
6408 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6410 (copy-recursively "../bin" bin))
6412 ;; no "configure" script
6413 (delete 'configure))))
6414 (inputs `(("zlib" ,zlib)))
6415 (home-page "http://bioinf.wehi.edu.au/subread-package/")
6416 (synopsis "Tool kit for processing next-gen sequencing data")
6418 "The subread package contains the following tools: subread aligner, a
6419 general-purpose read aligner; subjunc aligner: detecting exon-exon junctions
6420 and mapping RNA-seq reads; featureCounts: counting mapped reads for genomic
6421 features; exactSNP: a SNP caller that discovers SNPs by testing signals
6422 against local background noises.")
6423 (license license:gpl3+)))
6425 (define-public stringtie
6431 (uri (string-append "http://ccb.jhu.edu/software/stringtie/dl/"
6432 "stringtie-" version ".tar.gz"))
6435 "1cqllsc1maq4kh92isi8yadgzbmnf042hlnalpk3y59aph1z3bfz"))
6436 (modules '((guix build utils)))
6439 (delete-file-recursively "samtools-0.1.18")
6441 (build-system gnu-build-system)
6443 `(#:tests? #f ;no test suite
6445 (modify-phases %standard-phases
6446 ;; no configure script
6448 (add-before 'build 'use-system-samtools
6450 (substitute* "Makefile"
6451 (("stringtie: \\$\\{BAM\\}/libbam\\.a")
6453 (substitute* '("gclib/GBam.h"
6455 (("#include \"(bam|sam|kstring).h\"" _ header)
6456 (string-append "#include <samtools/" header ".h>")))
6458 (add-after 'unpack 'remove-duplicate-typedef
6460 ;; This typedef conflicts with the typedef in
6461 ;; glibc-2.25/include/bits/types.h
6462 (substitute* "gclib/GThreads.h"
6463 (("typedef long long __intmax_t;") ""))
6466 (lambda* (#:key outputs #:allow-other-keys)
6467 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
6468 (install-file "stringtie" bin)
6471 `(("samtools" ,samtools-0.1)
6473 (home-page "http://ccb.jhu.edu/software/stringtie/")
6474 (synopsis "Transcript assembly and quantification for RNA-Seq data")
6476 "StringTie is a fast and efficient assembler of RNA-Seq sequence
6477 alignments into potential transcripts. It uses a novel network flow algorithm
6478 as well as an optional de novo assembly step to assemble and quantitate
6479 full-length transcripts representing multiple splice variants for each gene
6480 locus. Its input can include not only the alignments of raw reads used by
6481 other transcript assemblers, but also alignments of longer sequences that have
6482 been assembled from those reads. To identify differentially expressed genes
6483 between experiments, StringTie's output can be processed either by the
6484 Cuffdiff or Ballgown programs.")
6485 (license license:artistic2.0)))
6487 (define-public taxtastic
6493 (uri (pypi-uri "taxtastic" version))
6496 "03pysw79lsrvz4lwzis88j15067ffqbi4cid5pqhrlxmd6bh8rrk"))))
6497 (build-system python-build-system)
6499 `(#:python ,python-2
6501 (modify-phases %standard-phases
6503 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t)))))
6505 `(("python-sqlalchemy" ,python2-sqlalchemy)
6506 ("python-decorator" ,python2-decorator)
6507 ("python-biopython" ,python2-biopython)
6508 ("python-pandas" ,python2-pandas)
6509 ("python-psycopg2" ,python2-psycopg2)
6510 ("python-fastalite" ,python2-fastalite)
6511 ("python-pyyaml" ,python2-pyyaml)
6512 ("python-six" ,python2-six)
6513 ("python-jinja2" ,python2-jinja2)
6514 ("python-dendropy" ,python2-dendropy)))
6515 (home-page "https://github.com/fhcrc/taxtastic")
6516 (synopsis "Tools for taxonomic naming and annotation")
6518 "Taxtastic is software written in python used to build and maintain
6519 reference packages i.e. collections of reference trees, reference alignments,
6520 profiles, and associated taxonomic information.")
6521 (license license:gpl3+)))
6523 (define-public vcftools
6530 "https://github.com/vcftools/vcftools/releases/download/v"
6531 version "/vcftools-" version ".tar.gz"))
6534 "1qw30c45wihgy632rbz4rh3njnwj4msj46l1rsgdhyg6bgypmr1i"))))
6535 (build-system gnu-build-system)
6537 `(#:tests? #f ; no "check" target
6539 "CFLAGS=-O2" ; override "-m64" flag
6540 (string-append "PREFIX=" (assoc-ref %outputs "out"))
6541 (string-append "MANDIR=" (assoc-ref %outputs "out")
6542 "/share/man/man1"))))
6544 `(("pkg-config" ,pkg-config)))
6548 (home-page "https://vcftools.github.io/")
6549 (synopsis "Tools for working with VCF files")
6551 "VCFtools is a program package designed for working with VCF files, such
6552 as those generated by the 1000 Genomes Project. The aim of VCFtools is to
6553 provide easily accessible methods for working with complex genetic variation
6554 data in the form of VCF files.")
6555 ;; The license is declared as LGPLv3 in the README and
6556 ;; at https://vcftools.github.io/license.html
6557 (license license:lgpl3)))
6559 (define-public infernal
6565 (uri (string-append "http://eddylab.org/software/infernal/"
6566 "infernal-" version ".tar.gz"))
6569 "0sr2hiz3qxfwqpz3whxr6n82p3x27336v3f34iqznp10hks2935c"))))
6570 (build-system gnu-build-system)
6572 `(("perl" ,perl))) ; for tests
6573 (home-page "http://eddylab.org/infernal/")
6574 (synopsis "Inference of RNA alignments")
6575 (description "Infernal (\"INFERence of RNA ALignment\") is a tool for
6576 searching DNA sequence databases for RNA structure and sequence similarities.
6577 It is an implementation of a special case of profile stochastic context-free
6578 grammars called @dfn{covariance models} (CMs). A CM is like a sequence
6579 profile, but it scores a combination of sequence consensus and RNA secondary
6580 structure consensus, so in many cases, it is more capable of identifying RNA
6581 homologs that conserve their secondary structure more than their primary
6583 ;; Infernal 1.1.2 requires VMX or SSE capability for parallel instructions.
6584 (supported-systems '("i686-linux" "x86_64-linux"))
6585 (license license:bsd-3)))
6587 (define-public r-scde
6594 (url "https://github.com/hms-dbmi/scde.git")
6596 (file-name (git-file-name name version))
6599 "10na2gyka24mszdxf92wz9h2c13hdf1ww30c68gfsw53lvvhhhxb"))))
6600 (build-system r-build-system)
6602 `(("r-rcpp" ,r-rcpp)
6603 ("r-rcpparmadillo" ,r-rcpparmadillo)
6606 ("r-rjson" ,r-rjson)
6607 ("r-cairo" ,r-cairo)
6608 ("r-rcolorbrewer" ,r-rcolorbrewer)
6609 ("r-edger" ,r-edger)
6610 ("r-quantreg" ,r-quantreg)
6612 ("r-rmtstat" ,r-rmtstat)
6613 ("r-extremes" ,r-extremes)
6614 ("r-pcamethods" ,r-pcamethods)
6615 ("r-biocparallel" ,r-biocparallel)
6616 ("r-flexmix" ,r-flexmix)))
6617 (home-page "https://hms-dbmi.github.io/scde/")
6618 (synopsis "R package for analyzing single-cell RNA-seq data")
6619 (description "The SCDE package implements a set of statistical methods for
6620 analyzing single-cell RNA-seq data. SCDE fits individual error models for
6621 single-cell RNA-seq measurements. These models can then be used for
6622 assessment of differential expression between groups of cells, as well as
6623 other types of analysis. The SCDE package also contains the pagoda framework
6624 which applies pathway and gene set overdispersion analysis to identify aspects
6625 of transcriptional heterogeneity among single cells.")
6626 ;; See https://github.com/hms-dbmi/scde/issues/38
6627 (license license:gpl2)))
6629 (define-public r-centipede
6631 (name "r-centipede")
6635 (uri (string-append "http://download.r-forge.r-project.org/"
6636 "src/contrib/CENTIPEDE_" version ".tar.gz"))
6639 "1hsx6qgwr0i67fhy9257zj7s0ppncph2hjgbia5nn6nfmj0ax6l9"))))
6640 (build-system r-build-system)
6641 (home-page "http://centipede.uchicago.edu/")
6642 (synopsis "Predict transcription factor binding sites")
6644 "CENTIPEDE applies a hierarchical Bayesian mixture model to infer regions
6645 of the genome that are bound by particular transcription factors. It starts
6646 by identifying a set of candidate binding sites, and then aims to classify the
6647 sites according to whether each site is bound or not bound by a transcription
6648 factor. CENTIPEDE is an unsupervised learning algorithm that discriminates
6649 between two different types of motif instances using as much relevant
6650 information as possible.")
6651 (license (list license:gpl2+ license:gpl3+))))
6653 (define-public r-genefilter
6655 (name "r-genefilter")
6660 (uri (bioconductor-uri "genefilter" version))
6663 "1jq7lam4dnbvz55lx93kcl9afl8xfjd6xs374d35m21bkay418kj"))))
6664 (build-system r-build-system)
6666 `(("gfortran" ,gfortran)))
6668 `(("r-annotate" ,r-annotate)
6669 ("r-annotationdbi" ,r-annotationdbi)
6670 ("r-biobase" ,r-biobase)
6671 ("r-s4vectors" ,r-s4vectors)
6672 ("r-survival" ,r-survival)))
6673 (home-page "https://bioconductor.org/packages/genefilter")
6674 (synopsis "Filter genes from high-throughput experiments")
6676 "This package provides basic functions for filtering genes from
6677 high-throughput sequencing experiments.")
6678 (license license:artistic2.0)))
6680 (define-public r-deseq2
6687 (uri (bioconductor-uri "DESeq2" version))
6690 "0fkk326addm2cw688gnmdzsmri5qx8j6ldnr4xin6kjnwicqhlqd"))))
6691 (properties `((upstream-name . "DESeq2")))
6692 (build-system r-build-system)
6694 `(("r-biobase" ,r-biobase)
6695 ("r-biocgenerics" ,r-biocgenerics)
6696 ("r-biocparallel" ,r-biocparallel)
6697 ("r-genefilter" ,r-genefilter)
6698 ("r-geneplotter" ,r-geneplotter)
6699 ("r-genomicranges" ,r-genomicranges)
6700 ("r-ggplot2" ,r-ggplot2)
6701 ("r-hmisc" ,r-hmisc)
6702 ("r-iranges" ,r-iranges)
6703 ("r-locfit" ,r-locfit)
6705 ("r-rcpparmadillo" ,r-rcpparmadillo)
6706 ("r-s4vectors" ,r-s4vectors)
6707 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6708 (home-page "https://bioconductor.org/packages/DESeq2")
6709 (synopsis "Differential gene expression analysis")
6711 "This package provides functions to estimate variance-mean dependence in
6712 count data from high-throughput nucleotide sequencing assays and test for
6713 differential expression based on a model using the negative binomial
6715 (license license:lgpl3+)))
6717 (define-public r-dexseq
6724 (uri (bioconductor-uri "DEXSeq" version))
6727 "1b2s0vwm97g0wgm4ms0f4pqkqiqmxscnhg700aybl5vx0m2fa8xm"))))
6728 (properties `((upstream-name . "DEXSeq")))
6729 (build-system r-build-system)
6731 `(("r-annotationdbi" ,r-annotationdbi)
6732 ("r-biobase" ,r-biobase)
6733 ("r-biocgenerics" ,r-biocgenerics)
6734 ("r-biocparallel" ,r-biocparallel)
6735 ("r-biomart" ,r-biomart)
6736 ("r-deseq2" ,r-deseq2)
6737 ("r-genefilter" ,r-genefilter)
6738 ("r-geneplotter" ,r-geneplotter)
6739 ("r-genomicranges" ,r-genomicranges)
6740 ("r-hwriter" ,r-hwriter)
6741 ("r-iranges" ,r-iranges)
6742 ("r-rcolorbrewer" ,r-rcolorbrewer)
6743 ("r-rsamtools" ,r-rsamtools)
6744 ("r-s4vectors" ,r-s4vectors)
6745 ("r-statmod" ,r-statmod)
6746 ("r-stringr" ,r-stringr)
6747 ("r-summarizedexperiment" ,r-summarizedexperiment)))
6748 (home-page "https://bioconductor.org/packages/DEXSeq")
6749 (synopsis "Inference of differential exon usage in RNA-Seq")
6751 "This package is focused on finding differential exon usage using RNA-seq
6752 exon counts between samples with different experimental designs. It provides
6753 functions that allows the user to make the necessary statistical tests based
6754 on a model that uses the negative binomial distribution to estimate the
6755 variance between biological replicates and generalized linear models for
6756 testing. The package also provides functions for the visualization and
6757 exploration of the results.")
6758 (license license:gpl3+)))
6760 (define-public r-annotationforge
6762 (name "r-annotationforge")
6767 (uri (bioconductor-uri "AnnotationForge" version))
6770 "0m4w8n2711wr28znv646cfc7m5jqlr8friz334zdyjmhg7m2xkb7"))))
6772 `((upstream-name . "AnnotationForge")))
6773 (build-system r-build-system)
6775 `(("r-annotationdbi" ,r-annotationdbi)
6776 ("r-biobase" ,r-biobase)
6777 ("r-biocgenerics" ,r-biocgenerics)
6779 ("r-rcurl" ,r-rcurl)
6780 ("r-rsqlite" ,r-rsqlite)
6781 ("r-s4vectors" ,r-s4vectors)
6783 (home-page "https://bioconductor.org/packages/AnnotationForge")
6784 (synopsis "Code for building annotation database packages")
6786 "This package provides code for generating Annotation packages and their
6787 databases. Packages produced are intended to be used with AnnotationDbi.")
6788 (license license:artistic2.0)))
6790 (define-public r-rbgl
6797 (uri (bioconductor-uri "RBGL" version))
6800 "06brn9hl6lybx6hdfp1sycwj6wn1bjfi8xyhpy0v122v1z8d5mbz"))))
6801 (properties `((upstream-name . "RBGL")))
6802 (build-system r-build-system)
6805 ("r-graph" ,r-graph)))
6806 (home-page "https://www.bioconductor.org/packages/RBGL")
6807 (synopsis "Interface to the Boost graph library")
6809 "This package provides a fairly extensive and comprehensive interface to
6810 the graph algorithms contained in the Boost library.")
6811 (license license:artistic2.0)))
6813 (define-public r-gseabase
6820 (uri (bioconductor-uri "GSEABase" version))
6823 "0vh53xk2prjbdkbr3hwfiflx1gh7ilrqs3j1p3lyd6syy3rn9n83"))))
6824 (properties `((upstream-name . "GSEABase")))
6825 (build-system r-build-system)
6827 `(("r-annotate" ,r-annotate)
6828 ("r-annotationdbi" ,r-annotationdbi)
6829 ("r-biobase" ,r-biobase)
6830 ("r-biocgenerics" ,r-biocgenerics)
6831 ("r-graph" ,r-graph)
6833 (home-page "https://bioconductor.org/packages/GSEABase")
6834 (synopsis "Gene set enrichment data structures and methods")
6836 "This package provides classes and methods to support @dfn{Gene Set
6837 Enrichment Analysis} (GSEA).")
6838 (license license:artistic2.0)))
6840 (define-public r-category
6847 (uri (bioconductor-uri "Category" version))
6850 "1n36xfnwn2np5f0lix9abvv9w6jb25jqz3xzvqzklz9s1af4k6x4"))))
6851 (properties `((upstream-name . "Category")))
6852 (build-system r-build-system)
6854 `(("r-annotate" ,r-annotate)
6855 ("r-annotationdbi" ,r-annotationdbi)
6856 ("r-biobase" ,r-biobase)
6857 ("r-biocgenerics" ,r-biocgenerics)
6858 ("r-genefilter" ,r-genefilter)
6859 ("r-graph" ,r-graph)
6860 ("r-gseabase" ,r-gseabase)
6861 ("r-matrix" ,r-matrix)
6864 (home-page "https://bioconductor.org/packages/Category")
6865 (synopsis "Category analysis")
6867 "This package provides a collection of tools for performing category
6869 (license license:artistic2.0)))
6871 (define-public r-gostats
6878 (uri (bioconductor-uri "GOstats" version))
6881 "1a95i6awm2a8xv42fg2z3n29fg9z29i45kd80hxf6mvqqgzj80xp"))))
6882 (properties `((upstream-name . "GOstats")))
6883 (build-system r-build-system)
6885 `(("r-annotate" ,r-annotate)
6886 ("r-annotationdbi" ,r-annotationdbi)
6887 ("r-annotationforge" ,r-annotationforge)
6888 ("r-biobase" ,r-biobase)
6889 ("r-category" ,r-category)
6890 ("r-go-db" ,r-go-db)
6891 ("r-graph" ,r-graph)
6892 ("r-rgraphviz" ,r-rgraphviz)
6893 ("r-rbgl" ,r-rbgl)))
6894 (home-page "https://bioconductor.org/packages/GOstats")
6895 (synopsis "Tools for manipulating GO and microarrays")
6897 "This package provides a set of tools for interacting with GO and
6898 microarray data. A variety of basic manipulation tools for graphs, hypothesis
6899 testing and other simple calculations.")
6900 (license license:artistic2.0)))
6902 (define-public r-shortread
6904 (name "r-shortread")
6909 (uri (bioconductor-uri "ShortRead" version))
6912 "1irqzdgsavjqsq0vva4966qh8qgn7xn9382dmhahm1hxb94qmi59"))))
6913 (properties `((upstream-name . "ShortRead")))
6914 (build-system r-build-system)
6918 `(("r-biobase" ,r-biobase)
6919 ("r-biocgenerics" ,r-biocgenerics)
6920 ("r-biocparallel" ,r-biocparallel)
6921 ("r-biostrings" ,r-biostrings)
6922 ("r-genomeinfodb" ,r-genomeinfodb)
6923 ("r-genomicalignments" ,r-genomicalignments)
6924 ("r-genomicranges" ,r-genomicranges)
6925 ("r-hwriter" ,r-hwriter)
6926 ("r-iranges" ,r-iranges)
6927 ("r-lattice" ,r-lattice)
6928 ("r-latticeextra" ,r-latticeextra)
6929 ("r-rsamtools" ,r-rsamtools)
6930 ("r-s4vectors" ,r-s4vectors)
6931 ("r-xvector" ,r-xvector)
6932 ("r-zlibbioc" ,r-zlibbioc)))
6933 (home-page "https://bioconductor.org/packages/ShortRead")
6934 (synopsis "FASTQ input and manipulation tools")
6936 "This package implements sampling, iteration, and input of FASTQ files.
6937 It includes functions for filtering and trimming reads, and for generating a
6938 quality assessment report. Data are represented as
6939 @code{DNAStringSet}-derived objects, and easily manipulated for a diversity of
6940 purposes. The package also contains legacy support for early single-end,
6941 ungapped alignment formats.")
6942 (license license:artistic2.0)))
6944 (define-public r-systempiper
6946 (name "r-systempiper")
6951 (uri (bioconductor-uri "systemPipeR" version))
6954 "0qzydz87rld2nhwzbfgrw5jfgh8maa9y54mjx9c4285m11qj2shq"))))
6955 (properties `((upstream-name . "systemPipeR")))
6956 (build-system r-build-system)
6958 `(("r-annotate" ,r-annotate)
6959 ("r-batchjobs" ,r-batchjobs)
6960 ("r-biocgenerics" ,r-biocgenerics)
6961 ("r-biostrings" ,r-biostrings)
6962 ("r-deseq2" ,r-deseq2)
6963 ("r-edger" ,r-edger)
6964 ("r-genomicfeatures" ,r-genomicfeatures)
6965 ("r-genomicranges" ,r-genomicranges)
6966 ("r-ggplot2" ,r-ggplot2)
6967 ("r-go-db" ,r-go-db)
6968 ("r-gostats" ,r-gostats)
6969 ("r-limma" ,r-limma)
6970 ("r-pheatmap" ,r-pheatmap)
6971 ("r-rjson" ,r-rjson)
6972 ("r-rsamtools" ,r-rsamtools)
6973 ("r-shortread" ,r-shortread)
6974 ("r-summarizedexperiment" ,r-summarizedexperiment)
6975 ("r-variantannotation" ,r-variantannotation)))
6976 (home-page "https://github.com/tgirke/systemPipeR")
6977 (synopsis "Next generation sequencing workflow and reporting environment")
6979 "This R package provides tools for building and running automated
6980 end-to-end analysis workflows for a wide range of @dfn{next generation
6981 sequence} (NGS) applications such as RNA-Seq, ChIP-Seq, VAR-Seq and Ribo-Seq.
6982 Important features include a uniform workflow interface across different NGS
6983 applications, automated report generation, and support for running both R and
6984 command-line software, such as NGS aligners or peak/variant callers, on local
6985 computers or compute clusters. Efficient handling of complex sample sets and
6986 experimental designs is facilitated by a consistently implemented sample
6987 annotation infrastructure.")
6988 (license license:artistic2.0)))
6990 (define-public r-grohmm
6997 (uri (bioconductor-uri "groHMM" version))
7000 "1p368qf8ab1vy8gl2j7rx0l7bvva4m7w06i364rqzs0sdyzlbm3y"))))
7001 (properties `((upstream-name . "groHMM")))
7002 (build-system r-build-system)
7004 `(("r-genomeinfodb" ,r-genomeinfodb)
7005 ("r-genomicalignments" ,r-genomicalignments)
7006 ("r-genomicranges" ,r-genomicranges)
7007 ("r-iranges" ,r-iranges)
7009 ("r-rtracklayer" ,r-rtracklayer)
7010 ("r-s4vectors" ,r-s4vectors)))
7011 (home-page "https://github.com/Kraus-Lab/groHMM")
7012 (synopsis "GRO-seq analysis pipeline")
7014 "This package provides a pipeline for the analysis of GRO-seq data.")
7015 (license license:gpl3+)))
7017 (define-public vsearch
7025 (url "https://github.com/torognes/vsearch.git")
7026 (commit (string-append "v" version))))
7027 (file-name (git-file-name name version))
7030 "0vhrpjfdf75ba04b24xknp41790cvcgwl0vgpy7qbzj5xh2521ss"))
7031 (patches (search-patches "vsearch-unbundle-cityhash.patch"))
7034 ;; Remove bundled cityhash sources. The vsearch source is adjusted
7035 ;; for this in the patch.
7036 (delete-file "src/city.h")
7037 (delete-file "src/citycrc.h")
7038 (delete-file "src/city.cc")
7040 (build-system gnu-build-system)
7044 ("cityhash" ,cityhash)))
7046 `(("autoconf" ,autoconf)
7047 ("automake" ,automake)))
7048 (synopsis "Sequence search tools for metagenomics")
7050 "VSEARCH supports DNA sequence searching, clustering, chimera detection,
7051 dereplication, pairwise alignment, shuffling, subsampling, sorting and
7052 masking. The tool takes advantage of parallelism in the form of SIMD
7053 vectorization as well as multiple threads to perform accurate alignments at
7054 high speed. VSEARCH uses an optimal global aligner (full dynamic programming
7055 Needleman-Wunsch).")
7056 (home-page "https://github.com/torognes/vsearch")
7057 ;; vsearch uses non-portable SSE intrinsics so building fails on other
7059 (supported-systems '("x86_64-linux"))
7060 ;; Dual licensed; also includes public domain source.
7061 (license (list license:gpl3 license:bsd-2))))
7063 (define-public pardre
7066 ;; The source of 1.1.5 changed in place, so we append "-1" to the version.
7071 (uri (string-append "mirror://sourceforge/pardre/ParDRe-rel"
7075 "17j73nc0viq4f6qj50nrndsrif5d6b71q8fl87m54psiv0ilns2b"))))
7076 (build-system gnu-build-system)
7078 `(#:tests? #f ; no tests included
7080 (modify-phases %standard-phases
7083 (lambda* (#:key outputs #:allow-other-keys)
7084 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
7085 (install-file "ParDRe" bin)
7088 `(("openmpi" ,openmpi)
7090 (synopsis "Parallel tool to remove duplicate DNA reads")
7092 "ParDRe is a parallel tool to remove duplicate genetic sequence reads.
7093 Duplicate reads can be seen as identical or nearly identical sequences with
7094 some mismatches. This tool lets users avoid the analysis of unnecessary
7095 reads, reducing the time of subsequent procedures with the
7096 dataset (e.g. assemblies, mappings, etc.). The tool is implemented with MPI
7097 in order to exploit the parallel capabilities of multicore clusters. It is
7098 faster than multithreaded counterparts (end of 2015) for the same number of
7099 cores and, thanks to the message-passing technology, it can be executed on
7101 (home-page "https://sourceforge.net/projects/pardre/")
7102 (license license:gpl3+)))
7104 (define-public ruby-bio-kseq
7106 (name "ruby-bio-kseq")
7111 (uri (rubygems-uri "bio-kseq" version))
7114 "1xyaha46khb5jc6wzkbf7040jagac49jbimn0vcrzid0j8jdikrz"))))
7115 (build-system ruby-build-system)
7117 `(#:test-target "spec"))
7119 `(("bundler" ,bundler)
7120 ("ruby-rspec" ,ruby-rspec)
7121 ("ruby-rake-compiler" ,ruby-rake-compiler)))
7124 (synopsis "Ruby bindings for the kseq.h FASTA/Q parser")
7126 "@code{Bio::Kseq} provides ruby bindings to the @code{kseq.h} FASTA and
7127 FASTQ parsing code. It provides a fast iterator over sequences and their
7129 (home-page "https://github.com/gusevfe/bio-kseq")
7130 (license license:expat)))
7132 (define-public bio-locus
7139 (uri (rubygems-uri "bio-locus" version))
7142 "02vmrxyimkj9sahsp4zhfhnmbvz6dbbqz1y01vglf8cbwvkajfl0"))))
7143 (build-system ruby-build-system)
7145 `(("ruby-rspec" ,ruby-rspec)))
7146 (synopsis "Tool for fast querying of genome locations")
7148 "Bio-locus is a tabix-like tool for fast querying of genome
7149 locations. Many file formats in bioinformatics contain records that
7150 start with a chromosome name and a position for a SNP, or a start-end
7151 position for indels. Bio-locus allows users to store this chr+pos or
7152 chr+pos+alt information in a database.")
7153 (home-page "https://github.com/pjotrp/bio-locus")
7154 (license license:expat)))
7156 (define-public bio-blastxmlparser
7158 (name "bio-blastxmlparser")
7162 (uri (rubygems-uri "bio-blastxmlparser" version))
7165 "1wf4qygcmdjgcqm6flmvsagfr1gs9lf63mj32qv3z1f481zc5692"))))
7166 (build-system ruby-build-system)
7168 `(("ruby-bio-logger" ,ruby-bio-logger)
7169 ("ruby-nokogiri" ,ruby-nokogiri)))
7171 `(("ruby-rspec" ,ruby-rspec)))
7172 (synopsis "Fast big data BLAST XML parser and library")
7174 "Very fast parallel big-data BLAST XML file parser which can be used as
7175 command line utility. Use blastxmlparser to: Parse BLAST XML; filter output;
7176 generate FASTA, JSON, YAML, RDF, JSON-LD, HTML, CSV, tabular output etc.")
7177 (home-page "https://github.com/pjotrp/blastxmlparser")
7178 (license license:expat)))
7180 (define-public bioruby
7187 (uri (rubygems-uri "bio" version))
7190 "1d56amdsjv1mag7m6gv2w0xij8hqx1v5xbdjsix8sp3yp36m7938"))))
7191 (build-system ruby-build-system)
7193 `(("ruby-libxml" ,ruby-libxml)))
7195 `(("which" ,which))) ; required for test phase
7198 (modify-phases %standard-phases
7199 (add-before 'build 'patch-test-command
7201 (substitute* '("test/functional/bio/test_command.rb")
7202 (("/bin/sh") (which "sh")))
7203 (substitute* '("test/functional/bio/test_command.rb")
7204 (("/bin/ls") (which "ls")))
7205 (substitute* '("test/functional/bio/test_command.rb")
7206 (("which") (which "which")))
7207 (substitute* '("test/functional/bio/test_command.rb",
7208 "test/data/command/echoarg2.sh")
7209 (("/bin/echo") (which "echo")))
7211 (synopsis "Ruby library, shell and utilities for bioinformatics")
7212 (description "BioRuby comes with a comprehensive set of Ruby development
7213 tools and libraries for bioinformatics and molecular biology. BioRuby has
7214 components for sequence analysis, pathway analysis, protein modelling and
7215 phylogenetic analysis; it supports many widely used data formats and provides
7216 easy access to databases, external programs and public web services, including
7217 BLAST, KEGG, GenBank, MEDLINE and GO.")
7218 (home-page "http://bioruby.org/")
7219 ;; Code is released under Ruby license, except for setup
7220 ;; (LGPLv2.1+) and scripts in samples (which have GPL2 and GPL2+)
7221 (license (list license:ruby license:lgpl2.1+ license:gpl2+ ))))
7223 (define-public r-biocinstaller
7225 (name "r-biocinstaller")
7229 (uri (bioconductor-uri "BiocInstaller" version))
7232 "1s1f9qhyf3mc73ir25x2zlgi9hf45a37lg4z8fbva4i21hqisgsl"))))
7234 `((upstream-name . "BiocInstaller")))
7235 (build-system r-build-system)
7236 (home-page "https://bioconductor.org/packages/BiocInstaller")
7237 (synopsis "Install Bioconductor packages")
7238 (description "This package is used to install and update R packages from
7239 Bioconductor, CRAN, and Github.")
7240 (license license:artistic2.0)))
7242 (define-public r-biocviews
7244 (name "r-biocviews")
7248 (uri (bioconductor-uri "biocViews" version))
7251 "1wc7a953n6qrlh9azzg1q68rk99h3xkbs82wq0yk6h2vb2c5r3zk"))))
7253 `((upstream-name . "biocViews")))
7254 (build-system r-build-system)
7256 `(("r-biobase" ,r-biobase)
7257 ("r-graph" ,r-graph)
7259 ("r-rcurl" ,r-rcurl)
7261 ("r-runit" ,r-runit)))
7262 (home-page "https://bioconductor.org/packages/biocViews")
7263 (synopsis "Bioconductor package categorization helper")
7264 (description "The purpose of biocViews is to create HTML pages that
7265 categorize packages in a Bioconductor package repository according to keywords,
7266 also known as views, in a controlled vocabulary.")
7267 (license license:artistic2.0)))
7269 (define-public r-biocstyle
7271 (name "r-biocstyle")
7275 (uri (bioconductor-uri "BiocStyle" version))
7278 "029x8r9rcx6zy0xixdpwxai4jv4ynb161821fzac6z4r8k418398"))))
7280 `((upstream-name . "BiocStyle")))
7281 (build-system r-build-system)
7283 `(("r-biocmanager" ,r-biocmanager)
7284 ("r-bookdown" ,r-bookdown)
7285 ("r-knitr" ,r-knitr)
7286 ("r-rmarkdown" ,r-rmarkdown)
7287 ("r-yaml" ,r-yaml)))
7288 (home-page "https://bioconductor.org/packages/BiocStyle")
7289 (synopsis "Bioconductor formatting styles")
7290 (description "This package provides standard formatting styles for
7291 Bioconductor PDF and HTML documents. Package vignettes illustrate use and
7293 (license license:artistic2.0)))
7295 (define-public r-bioccheck
7297 (name "r-bioccheck")
7301 (uri (bioconductor-uri "BiocCheck" version))
7304 "1gkw9s6dhdryga9ap5yhvcqg9jsy4cn417ayqk1qiv6fy91fd124"))))
7306 `((upstream-name . "BiocCheck")))
7307 (build-system r-build-system)
7310 (modify-phases %standard-phases
7311 ;; This package can be used by calling BiocCheck(<package>) from
7312 ;; within R, or by running R CMD BiocCheck <package>. This phase
7313 ;; makes sure the latter works. For this to work, the BiocCheck
7314 ;; script must be somewhere on the PATH (not the R bin directory).
7315 (add-after 'install 'install-bioccheck-subcommand
7316 (lambda* (#:key outputs #:allow-other-keys)
7317 (let* ((out (assoc-ref outputs "out"))
7318 (dest-dir (string-append out "/bin"))
7320 (string-append out "/site-library/BiocCheck/script/")))
7322 (symlink (string-append script-dir "/checkBadDeps.R")
7323 (string-append dest-dir "/checkBadDeps.R"))
7324 (symlink (string-append script-dir "/BiocCheck")
7325 (string-append dest-dir "/BiocCheck")))
7328 `(("r-codetools" ,r-codetools)
7329 ("r-graph" ,r-graph)
7331 ("r-knitr" ,r-knitr)
7332 ("r-optparse" ,r-optparse)
7333 ("r-biocmanager" ,r-biocmanager)
7334 ("r-biocviews" ,r-biocviews)
7335 ("r-stringdist" ,r-stringdist)))
7336 (home-page "https://bioconductor.org/packages/BiocCheck")
7337 (synopsis "Executes Bioconductor-specific package checks")
7338 (description "This package contains tools to perform additional quality
7339 checks on R packages that are to be submitted to the Bioconductor repository.")
7340 (license license:artistic2.0)))
7342 (define-public r-s4vectors
7344 (name "r-s4vectors")
7348 (uri (bioconductor-uri "S4Vectors" version))
7351 "1wkqmpy0d0fab9bjfc7i5wh2zng75pg9rn9c1z1lkki7fpwaw2jb"))))
7353 `((upstream-name . "S4Vectors")))
7354 (build-system r-build-system)
7356 `(("r-biocgenerics" ,r-biocgenerics)))
7357 (home-page "https://bioconductor.org/packages/S4Vectors")
7358 (synopsis "S4 implementation of vectors and lists")
7360 "The S4Vectors package defines the @code{Vector} and @code{List} virtual
7361 classes and a set of generic functions that extend the semantic of ordinary
7362 vectors and lists in R. Package developers can easily implement vector-like
7363 or list-like objects as concrete subclasses of @code{Vector} or @code{List}.
7364 In addition, a few low-level concrete subclasses of general interest (e.g.
7365 @code{DataFrame}, @code{Rle}, and @code{Hits}) are implemented in the
7366 S4Vectors package itself.")
7367 (license license:artistic2.0)))
7369 (define-public r-iranges
7375 (uri (bioconductor-uri "IRanges" version))
7378 "0g06y6xlm2q7p7g7phfc8qj14pqpgbb0mkyjzkfgsrwjmzvpwy6m"))))
7380 `((upstream-name . "IRanges")))
7381 (build-system r-build-system)
7383 `(("r-biocgenerics" ,r-biocgenerics)
7384 ("r-s4vectors" ,r-s4vectors)))
7385 (home-page "https://bioconductor.org/packages/IRanges")
7386 (synopsis "Infrastructure for manipulating intervals on sequences")
7388 "This package provides efficient low-level and highly reusable S4 classes
7389 for storing ranges of integers, RLE vectors (Run-Length Encoding), and, more
7390 generally, data that can be organized sequentially (formally defined as
7391 @code{Vector} objects), as well as views on these @code{Vector} objects.
7392 Efficient list-like classes are also provided for storing big collections of
7393 instances of the basic classes. All classes in the package use consistent
7394 naming and share the same rich and consistent \"Vector API\" as much as
7396 (license license:artistic2.0)))
7398 (define-public r-genomeinfodbdata
7400 (name "r-genomeinfodbdata")
7404 ;; We cannot use bioconductor-uri here because this tarball is
7405 ;; located under "data/annotation/" instead of "bioc/".
7406 (uri (string-append "https://bioconductor.org/packages/release/"
7407 "data/annotation/src/contrib/GenomeInfoDbData_"
7411 "0di6nlqpsyqf693k2na65ayqldih563x3zfrczpqc5q2hl5kg35c"))))
7413 `((upstream-name . "GenomeInfoDbData")))
7414 (build-system r-build-system)
7415 (home-page "https://bioconductor.org/packages/GenomeInfoDbData")
7416 (synopsis "Species and taxonomy ID look up tables for GenomeInfoDb")
7417 (description "This package contains data for mapping between NCBI taxonomy
7418 ID and species. It is used by functions in the GenomeInfoDb package.")
7419 (license license:artistic2.0)))
7421 (define-public r-genomeinfodb
7423 (name "r-genomeinfodb")
7427 (uri (bioconductor-uri "GenomeInfoDb" version))
7430 "0zkhms81b3jz30q7ag81a1mq1rgqg4izyfdvcni68gvn8gm7kdyk"))))
7432 `((upstream-name . "GenomeInfoDb")))
7433 (build-system r-build-system)
7435 `(("r-biocgenerics" ,r-biocgenerics)
7436 ("r-genomeinfodbdata" ,r-genomeinfodbdata)
7437 ("r-iranges" ,r-iranges)
7438 ("r-rcurl" ,r-rcurl)
7439 ("r-s4vectors" ,r-s4vectors)))
7440 (home-page "https://bioconductor.org/packages/GenomeInfoDb")
7441 (synopsis "Utilities for manipulating chromosome identifiers")
7443 "This package contains data and functions that define and allow
7444 translation between different chromosome sequence naming conventions (e.g.,
7445 \"chr1\" versus \"1\"), including a function that attempts to place sequence
7446 names in their natural, rather than lexicographic, order.")
7447 (license license:artistic2.0)))
7449 (define-public r-edger
7455 (uri (bioconductor-uri "edgeR" version))
7458 "10zhnybcwacgwcdp5p792njzl4kcafvnnnxbd7mszhxrm1sliqr8"))))
7459 (properties `((upstream-name . "edgeR")))
7460 (build-system r-build-system)
7462 `(("r-limma" ,r-limma)
7463 ("r-locfit" ,r-locfit)
7465 ("r-statmod" ,r-statmod))) ;for estimateDisp
7466 (home-page "http://bioinf.wehi.edu.au/edgeR")
7467 (synopsis "EdgeR does empirical analysis of digital gene expression data")
7468 (description "This package can do differential expression analysis of
7469 RNA-seq expression profiles with biological replication. It implements a range
7470 of statistical methodology based on the negative binomial distributions,
7471 including empirical Bayes estimation, exact tests, generalized linear models
7472 and quasi-likelihood tests. It be applied to differential signal analysis of
7473 other types of genomic data that produce counts, including ChIP-seq, SAGE and
7475 (license license:gpl2+)))
7477 (define-public r-variantannotation
7479 (name "r-variantannotation")
7483 (uri (bioconductor-uri "VariantAnnotation" version))
7486 "1sd01yv1hnwc16412ilncrrph4gxsr9ds0nqg1czl69fqaixjn1i"))))
7488 `((upstream-name . "VariantAnnotation")))
7492 `(("r-annotationdbi" ,r-annotationdbi)
7493 ("r-biobase" ,r-biobase)
7494 ("r-biocgenerics" ,r-biocgenerics)
7495 ("r-biostrings" ,r-biostrings)
7496 ("r-bsgenome" ,r-bsgenome)
7498 ("r-genomeinfodb" ,r-genomeinfodb)
7499 ("r-genomicfeatures" ,r-genomicfeatures)
7500 ("r-genomicranges" ,r-genomicranges)
7501 ("r-iranges" ,r-iranges)
7502 ("r-summarizedexperiment" ,r-summarizedexperiment)
7503 ("r-rhtslib" ,r-rhtslib)
7504 ("r-rsamtools" ,r-rsamtools)
7505 ("r-rtracklayer" ,r-rtracklayer)
7506 ("r-s4vectors" ,r-s4vectors)
7507 ("r-xvector" ,r-xvector)
7508 ("r-zlibbioc" ,r-zlibbioc)))
7509 (build-system r-build-system)
7510 (home-page "https://bioconductor.org/packages/VariantAnnotation")
7511 (synopsis "Package for annotation of genetic variants")
7512 (description "This R package can annotate variants, compute amino acid
7513 coding changes and predict coding outcomes.")
7514 (license license:artistic2.0)))
7516 (define-public r-limma
7522 (uri (bioconductor-uri "limma" version))
7525 "03qxn3bs0gxq480vjd26cvhiq7jisw7kpmb3wpkrjk8jnsb10aax"))))
7526 (build-system r-build-system)
7527 (home-page "http://bioinf.wehi.edu.au/limma")
7528 (synopsis "Package for linear models for microarray and RNA-seq data")
7529 (description "This package can be used for the analysis of gene expression
7530 studies, especially the use of linear models for analysing designed experiments
7531 and the assessment of differential expression. The analysis methods apply to
7532 different technologies, including microarrays, RNA-seq, and quantitative PCR.")
7533 (license license:gpl2+)))
7535 (define-public r-xvector
7541 (uri (bioconductor-uri "XVector" version))
7544 "12y09pwy86h1za6cmaxs960r7fs0vjzhl0li8jn59vqq9liza1ap"))))
7546 `((upstream-name . "XVector")))
7547 (build-system r-build-system)
7550 (modify-phases %standard-phases
7551 (add-after 'unpack 'use-system-zlib
7553 (substitute* "DESCRIPTION"
7554 (("zlibbioc, ") ""))
7555 (substitute* "NAMESPACE"
7556 (("import\\(zlibbioc\\)") ""))
7561 `(("r-biocgenerics" ,r-biocgenerics)
7562 ("r-iranges" ,r-iranges)
7563 ("r-s4vectors" ,r-s4vectors)))
7564 (home-page "https://bioconductor.org/packages/XVector")
7565 (synopsis "Representation and manpulation of external sequences")
7567 "This package provides memory efficient S4 classes for storing sequences
7568 \"externally\" (behind an R external pointer, or on disk).")
7569 (license license:artistic2.0)))
7571 (define-public r-genomicranges
7573 (name "r-genomicranges")
7577 (uri (bioconductor-uri "GenomicRanges" version))
7580 "1285fr8qjd7d0ixpv7d5imi0n6wzc4k6yia1rkmig71qd2gg556k"))))
7582 `((upstream-name . "GenomicRanges")))
7583 (build-system r-build-system)
7585 `(("r-biocgenerics" ,r-biocgenerics)
7586 ("r-genomeinfodb" ,r-genomeinfodb)
7587 ("r-iranges" ,r-iranges)
7588 ("r-s4vectors" ,r-s4vectors)
7589 ("r-xvector" ,r-xvector)))
7590 (home-page "https://bioconductor.org/packages/GenomicRanges")
7591 (synopsis "Representation and manipulation of genomic intervals")
7593 "This package provides tools to efficiently represent and manipulate
7594 genomic annotations and alignments is playing a central role when it comes to
7595 analyzing high-throughput sequencing data (a.k.a. NGS data). The
7596 GenomicRanges package defines general purpose containers for storing and
7597 manipulating genomic intervals and variables defined along a genome.")
7598 (license license:artistic2.0)))
7600 (define-public r-biobase
7606 (uri (bioconductor-uri "Biobase" version))
7609 "15yl92niqamx3lmwd11zlk0xniibqnh1gi280iadxicmchi83npc"))))
7611 `((upstream-name . "Biobase")))
7612 (build-system r-build-system)
7614 `(("r-biocgenerics" ,r-biocgenerics)))
7615 (home-page "https://bioconductor.org/packages/Biobase")
7616 (synopsis "Base functions for Bioconductor")
7618 "This package provides functions that are needed by many other packages
7619 on Bioconductor or which replace R functions.")
7620 (license license:artistic2.0)))
7622 (define-public r-annotationdbi
7624 (name "r-annotationdbi")
7628 (uri (bioconductor-uri "AnnotationDbi" version))
7631 "0lfq5668a6sq4kqhxx78hl3jcaqdsaaliiybl9xyya2scdk8c29c"))))
7633 `((upstream-name . "AnnotationDbi")))
7634 (build-system r-build-system)
7636 `(("r-biobase" ,r-biobase)
7637 ("r-biocgenerics" ,r-biocgenerics)
7639 ("r-iranges" ,r-iranges)
7640 ("r-rsqlite" ,r-rsqlite)
7641 ("r-s4vectors" ,r-s4vectors)))
7642 (home-page "https://bioconductor.org/packages/AnnotationDbi")
7643 (synopsis "Annotation database interface")
7645 "This package provides user interface and database connection code for
7646 annotation data packages using SQLite data storage.")
7647 (license license:artistic2.0)))
7649 (define-public r-biomart
7655 (uri (bioconductor-uri "biomaRt" version))
7658 "1i457s91bn7n60bzw3zk4h64xgmawlrr6bq4z4cb7jlm04hdq8qm"))))
7660 `((upstream-name . "biomaRt")))
7661 (build-system r-build-system)
7663 `(("r-annotationdbi" ,r-annotationdbi)
7665 ("r-progress" ,r-progress)
7666 ("r-rcurl" ,r-rcurl)
7667 ("r-stringr" ,r-stringr)
7669 (home-page "https://bioconductor.org/packages/biomaRt")
7670 (synopsis "Interface to BioMart databases")
7672 "biomaRt provides an interface to a growing collection of databases
7673 implementing the @url{BioMart software suite, http://www.biomart.org}. The
7674 package enables retrieval of large amounts of data in a uniform way without
7675 the need to know the underlying database schemas or write complex SQL queries.
7676 Examples of BioMart databases are Ensembl, COSMIC, Uniprot, HGNC, Gramene,
7677 Wormbase and dbSNP mapped to Ensembl. These major databases give biomaRt
7678 users direct access to a diverse set of data and enable a wide range of
7679 powerful online queries from gene annotation to database mining.")
7680 (license license:artistic2.0)))
7682 (define-public r-biocparallel
7684 (name "r-biocparallel")
7688 (uri (bioconductor-uri "BiocParallel" version))
7691 "0v8rhf3hbgb3v32h2pmsv1y6q2x4airmpp50fk7z6ardcn4aza7x"))))
7693 `((upstream-name . "BiocParallel")))
7694 (build-system r-build-system)
7696 `(("r-futile-logger" ,r-futile-logger)
7699 (home-page "https://bioconductor.org/packages/BiocParallel")
7700 (synopsis "Bioconductor facilities for parallel evaluation")
7702 "This package provides modified versions and novel implementation of
7703 functions for parallel evaluation, tailored to use with Bioconductor
7705 (license (list license:gpl2+ license:gpl3+))))
7707 (define-public r-biostrings
7709 (name "r-biostrings")
7713 (uri (bioconductor-uri "Biostrings" version))
7716 "0inrl97hli3qz6cfxcikc4picmbrqc8phdgqi18ynlvxy5ql64h4"))))
7718 `((upstream-name . "Biostrings")))
7719 (build-system r-build-system)
7721 `(("r-biocgenerics" ,r-biocgenerics)
7722 ("r-iranges" ,r-iranges)
7723 ("r-s4vectors" ,r-s4vectors)
7724 ("r-xvector" ,r-xvector)))
7725 (home-page "https://bioconductor.org/packages/Biostrings")
7726 (synopsis "String objects and algorithms for biological sequences")
7728 "This package provides memory efficient string containers, string
7729 matching algorithms, and other utilities, for fast manipulation of large
7730 biological sequences or sets of sequences.")
7731 (license license:artistic2.0)))
7733 (define-public r-rsamtools
7735 (name "r-rsamtools")
7739 (uri (bioconductor-uri "Rsamtools" version))
7742 "02paq7klabdkaf1b8pmmbpmyqsj3yncnfsz62rgka6r4dpsilwk9"))))
7744 `((upstream-name . "Rsamtools")))
7745 (build-system r-build-system)
7748 (modify-phases %standard-phases
7749 (add-after 'unpack 'use-system-zlib
7751 (substitute* "DESCRIPTION"
7752 (("zlibbioc, ") ""))
7753 (substitute* "NAMESPACE"
7754 (("import\\(zlibbioc\\)") ""))
7759 `(("r-biocgenerics" ,r-biocgenerics)
7760 ("r-biocparallel" ,r-biocparallel)
7761 ("r-biostrings" ,r-biostrings)
7762 ("r-bitops" ,r-bitops)
7763 ("r-genomeinfodb" ,r-genomeinfodb)
7764 ("r-genomicranges" ,r-genomicranges)
7765 ("r-iranges" ,r-iranges)
7766 ("r-s4vectors" ,r-s4vectors)
7767 ("r-xvector" ,r-xvector)))
7768 (home-page "https://bioconductor.org/packages/release/bioc/html/Rsamtools.html")
7769 (synopsis "Interface to samtools, bcftools, and tabix")
7771 "This package provides an interface to the @code{samtools},
7772 @code{bcftools}, and @code{tabix} utilities for manipulating SAM (Sequence
7773 Alignment / Map), FASTA, binary variant call (BCF) and compressed indexed
7774 tab-delimited (tabix) files.")
7775 (license license:expat)))
7777 (define-public r-delayedarray
7779 (name "r-delayedarray")
7783 (uri (bioconductor-uri "DelayedArray" version))
7786 "0l907ggxndn3f29zvsd5pppmp4c31rb22r6zkhvgph7xdxahyy6z"))))
7788 `((upstream-name . "DelayedArray")))
7789 (build-system r-build-system)
7791 `(("r-biocgenerics" ,r-biocgenerics)
7792 ("r-biocparallel" ,r-biocparallel)
7793 ("r-s4vectors" ,r-s4vectors)
7794 ("r-iranges" ,r-iranges)
7795 ("r-matrix" ,r-matrix)
7796 ("r-matrixstats" ,r-matrixstats)))
7797 (home-page "https://bioconductor.org/packages/DelayedArray")
7798 (synopsis "Delayed operations on array-like objects")
7800 "Wrapping an array-like object (typically an on-disk object) in a
7801 @code{DelayedArray} object allows one to perform common array operations on it
7802 without loading the object in memory. In order to reduce memory usage and
7803 optimize performance, operations on the object are either delayed or executed
7804 using a block processing mechanism. Note that this also works on in-memory
7805 array-like objects like @code{DataFrame} objects (typically with Rle columns),
7806 @code{Matrix} objects, and ordinary arrays and data frames.")
7807 (license license:artistic2.0)))
7809 (define-public r-summarizedexperiment
7811 (name "r-summarizedexperiment")
7815 (uri (bioconductor-uri "SummarizedExperiment" version))
7818 "1ypk63pdml89y81pr41i2zq0fimsaxsa5lgpg6xs5cwikyaq0pci"))))
7820 `((upstream-name . "SummarizedExperiment")))
7821 (build-system r-build-system)
7823 `(("r-biobase" ,r-biobase)
7824 ("r-biocgenerics" ,r-biocgenerics)
7825 ("r-delayedarray" ,r-delayedarray)
7826 ("r-genomeinfodb" ,r-genomeinfodb)
7827 ("r-genomicranges" ,r-genomicranges)
7828 ("r-iranges" ,r-iranges)
7829 ("r-matrix" ,r-matrix)
7830 ("r-s4vectors" ,r-s4vectors)))
7831 (home-page "https://bioconductor.org/packages/SummarizedExperiment")
7832 (synopsis "Container for representing genomic ranges by sample")
7834 "The SummarizedExperiment container contains one or more assays, each
7835 represented by a matrix-like object of numeric or other mode. The rows
7836 typically represent genomic ranges of interest and the columns represent
7838 (license license:artistic2.0)))
7840 (define-public r-genomicalignments
7842 (name "r-genomicalignments")
7846 (uri (bioconductor-uri "GenomicAlignments" version))
7849 "13zw7bb1adgph9bf9b9y725nr0320b80y70p2yqf3bjb2klfxf55"))))
7851 `((upstream-name . "GenomicAlignments")))
7852 (build-system r-build-system)
7854 `(("r-biocgenerics" ,r-biocgenerics)
7855 ("r-biocparallel" ,r-biocparallel)
7856 ("r-biostrings" ,r-biostrings)
7857 ("r-genomeinfodb" ,r-genomeinfodb)
7858 ("r-genomicranges" ,r-genomicranges)
7859 ("r-iranges" ,r-iranges)
7860 ("r-rsamtools" ,r-rsamtools)
7861 ("r-s4vectors" ,r-s4vectors)
7862 ("r-summarizedexperiment" ,r-summarizedexperiment)))
7863 (home-page "https://bioconductor.org/packages/GenomicAlignments")
7864 (synopsis "Representation and manipulation of short genomic alignments")
7866 "This package provides efficient containers for storing and manipulating
7867 short genomic alignments (typically obtained by aligning short reads to a
7868 reference genome). This includes read counting, computing the coverage,
7869 junction detection, and working with the nucleotide content of the
7871 (license license:artistic2.0)))
7873 (define-public r-rtracklayer
7875 (name "r-rtracklayer")
7879 (uri (bioconductor-uri "rtracklayer" version))
7882 "161gcks9b12993g9k27gf7wfh8lgd8m8rr7x2slgfqqssk0yrmpd"))))
7883 (build-system r-build-system)
7886 (modify-phases %standard-phases
7887 (add-after 'unpack 'use-system-zlib
7889 (substitute* "DESCRIPTION"
7890 ((" zlibbioc,") ""))
7891 (substitute* "NAMESPACE"
7892 (("import\\(zlibbioc\\)") ""))
7895 `(("pkg-config" ,pkg-config)))
7899 `(("r-biocgenerics" ,r-biocgenerics)
7900 ("r-biostrings" ,r-biostrings)
7901 ("r-genomeinfodb" ,r-genomeinfodb)
7902 ("r-genomicalignments" ,r-genomicalignments)
7903 ("r-genomicranges" ,r-genomicranges)
7904 ("r-iranges" ,r-iranges)
7905 ("r-rcurl" ,r-rcurl)
7906 ("r-rsamtools" ,r-rsamtools)
7907 ("r-s4vectors" ,r-s4vectors)
7909 ("r-xvector" ,r-xvector)))
7910 (home-page "https://bioconductor.org/packages/rtracklayer")
7911 (synopsis "R interface to genome browsers and their annotation tracks")
7913 "rtracklayer is an extensible framework for interacting with multiple
7914 genome browsers (currently UCSC built-in) and manipulating annotation tracks
7915 in various formats (currently GFF, BED, bedGraph, BED15, WIG, BigWig and 2bit
7916 built-in). The user may export/import tracks to/from the supported browsers,
7917 as well as query and modify the browser state, such as the current viewport.")
7918 (license license:artistic2.0)))
7920 (define-public r-genomicfeatures
7922 (name "r-genomicfeatures")
7926 (uri (bioconductor-uri "GenomicFeatures" version))
7929 "17jy7lrpdaafd8g5v6j70xsypi0lqljdqmhv9f2r1xpyg3yjd84p"))))
7931 `((upstream-name . "GenomicFeatures")))
7932 (build-system r-build-system)
7934 `(("r-annotationdbi" ,r-annotationdbi)
7935 ("r-biobase" ,r-biobase)
7936 ("r-biocgenerics" ,r-biocgenerics)
7937 ("r-biomart" ,r-biomart)
7938 ("r-biostrings" ,r-biostrings)
7940 ("r-genomeinfodb" ,r-genomeinfodb)
7941 ("r-genomicranges" ,r-genomicranges)
7942 ("r-iranges" ,r-iranges)
7943 ("r-rcurl" ,r-rcurl)
7944 ("r-rsqlite" ,r-rsqlite)
7945 ("r-rtracklayer" ,r-rtracklayer)
7946 ("r-s4vectors" ,r-s4vectors)
7947 ("r-xvector" ,r-xvector)))
7948 (home-page "https://bioconductor.org/packages/GenomicFeatures")
7949 (synopsis "Tools for working with transcript centric annotations")
7951 "This package provides a set of tools and methods for making and
7952 manipulating transcript centric annotations. With these tools the user can
7953 easily download the genomic locations of the transcripts, exons and cds of a
7954 given organism, from either the UCSC Genome Browser or a BioMart
7955 database (more sources will be supported in the future). This information is
7956 then stored in a local database that keeps track of the relationship between
7957 transcripts, exons, cds and genes. Flexible methods are provided for
7958 extracting the desired features in a convenient format.")
7959 (license license:artistic2.0)))
7961 (define-public r-go-db
7967 (uri (string-append "https://www.bioconductor.org/packages/"
7968 "release/data/annotation/src/contrib/GO.db_"
7972 "0i3wcf5h3n0dawzc1hy0kv74f06j80c47n4p3g3fmrcxlhi3jpa5"))))
7974 `((upstream-name . "GO.db")))
7975 (build-system r-build-system)
7977 `(("r-annotationdbi" ,r-annotationdbi)))
7978 (home-page "https://bioconductor.org/packages/GO.db")
7979 (synopsis "Annotation maps describing the entire Gene Ontology")
7981 "The purpose of this GO.db annotation package is to provide detailed
7982 information about the latest version of the Gene Ontologies.")
7983 (license license:artistic2.0)))
7985 (define-public r-topgo
7991 (uri (bioconductor-uri "topGO" version))
7994 "09z42jwz5vh289ijz3x68zv5vmgkgcbhlp73vvmna1gld5lh5kz1"))))
7996 `((upstream-name . "topGO")))
7997 (build-system r-build-system)
7999 `(("r-annotationdbi" ,r-annotationdbi)
8001 ("r-biobase" ,r-biobase)
8002 ("r-biocgenerics" ,r-biocgenerics)
8003 ("r-go-db" ,r-go-db)
8004 ("r-graph" ,r-graph)
8005 ("r-lattice" ,r-lattice)
8006 ("r-matrixstats" ,r-matrixstats)
8007 ("r-sparsem" ,r-sparsem)))
8008 (home-page "https://bioconductor.org/packages/topGO")
8009 (synopsis "Enrichment analysis for gene ontology")
8011 "The topGO package provides tools for testing @dfn{gene ontology} (GO)
8012 terms while accounting for the topology of the GO graph. Different test
8013 statistics and different methods for eliminating local similarities and
8014 dependencies between GO terms can be implemented and applied.")
8015 ;; Any version of the LGPL applies.
8016 (license license:lgpl2.1+)))
8018 (define-public r-bsgenome
8024 (uri (bioconductor-uri "BSgenome" version))
8027 "0zwx42s73hc1vhn0v82i67mcixdwwc6n6q5h5vpnhpxlm4qwgqzp"))))
8029 `((upstream-name . "BSgenome")))
8030 (build-system r-build-system)
8032 `(("r-biocgenerics" ,r-biocgenerics)
8033 ("r-biostrings" ,r-biostrings)
8034 ("r-genomeinfodb" ,r-genomeinfodb)
8035 ("r-genomicranges" ,r-genomicranges)
8036 ("r-iranges" ,r-iranges)
8037 ("r-rsamtools" ,r-rsamtools)
8038 ("r-rtracklayer" ,r-rtracklayer)
8039 ("r-s4vectors" ,r-s4vectors)
8040 ("r-xvector" ,r-xvector)))
8041 (home-page "https://bioconductor.org/packages/BSgenome")
8042 (synopsis "Infrastructure for Biostrings-based genome data packages")
8044 "This package provides infrastructure shared by all Biostrings-based
8045 genome data packages and support for efficient SNP representation.")
8046 (license license:artistic2.0)))
8048 (define-public r-impute
8054 (uri (bioconductor-uri "impute" version))
8057 "08z0pj1dz5iq967nwj67qyka7ir7m5an2ggv7bsrlz3apzfsla33"))))
8059 `(("gfortran" ,gfortran)))
8060 (build-system r-build-system)
8061 (home-page "https://bioconductor.org/packages/impute")
8062 (synopsis "Imputation for microarray data")
8064 "This package provides a function to impute missing gene expression
8065 microarray data, using nearest neighbor averaging.")
8066 (license license:gpl2+)))
8068 (define-public r-seqpattern
8070 (name "r-seqpattern")
8074 (uri (bioconductor-uri "seqPattern" version))
8077 "1ljqscbmrmi5d4lzzvg2d86sqzch26yxw57d33qyid300wm60db2"))))
8079 `((upstream-name . "seqPattern")))
8080 (build-system r-build-system)
8082 `(("r-biostrings" ,r-biostrings)
8083 ("r-genomicranges" ,r-genomicranges)
8084 ("r-iranges" ,r-iranges)
8085 ("r-kernsmooth" ,r-kernsmooth)
8086 ("r-plotrix" ,r-plotrix)))
8087 (home-page "https://bioconductor.org/packages/seqPattern")
8088 (synopsis "Visualising oligonucleotide patterns and motif occurrences")
8090 "This package provides tools to visualize oligonucleotide patterns and
8091 sequence motif occurrences across a large set of sequences centred at a common
8092 reference point and sorted by a user defined feature.")
8093 (license license:gpl3+)))
8095 (define-public r-genomation
8097 (name "r-genomation")
8101 (uri (bioconductor-uri "genomation" version))
8104 "06i711pwq9znd7plh0p25skxnnh5dyl61c33k9gma243wvlzmlkj"))))
8105 (build-system r-build-system)
8107 `(("r-biostrings" ,r-biostrings)
8108 ("r-bsgenome" ,r-bsgenome)
8109 ("r-data-table" ,r-data-table)
8110 ("r-genomeinfodb" ,r-genomeinfodb)
8111 ("r-genomicalignments" ,r-genomicalignments)
8112 ("r-genomicranges" ,r-genomicranges)
8113 ("r-ggplot2" ,r-ggplot2)
8114 ("r-gridbase" ,r-gridbase)
8115 ("r-impute" ,r-impute)
8116 ("r-iranges" ,r-iranges)
8117 ("r-matrixstats" ,r-matrixstats)
8118 ("r-plotrix" ,r-plotrix)
8121 ("r-readr" ,r-readr)
8122 ("r-reshape2" ,r-reshape2)
8123 ("r-rsamtools" ,r-rsamtools)
8124 ("r-rtracklayer" ,r-rtracklayer)
8125 ("r-runit" ,r-runit)
8126 ("r-s4vectors" ,r-s4vectors)
8127 ("r-seqpattern" ,r-seqpattern)))
8128 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8129 (synopsis "Summary, annotation and visualization of genomic data")
8131 "This package provides a package for summary and annotation of genomic
8132 intervals. Users can visualize and quantify genomic intervals over
8133 pre-defined functional regions, such as promoters, exons, introns, etc. The
8134 genomic intervals represent regions with a defined chromosome position, which
8135 may be associated with a score, such as aligned reads from HT-seq experiments,
8136 TF binding sites, methylation scores, etc. The package can use any tabular
8137 genomic feature data as long as it has minimal information on the locations of
8138 genomic intervals. In addition, it can use BAM or BigWig files as input.")
8139 (license license:artistic2.0)))
8141 (define-public r-genomationdata
8143 (name "r-genomationdata")
8147 ;; We cannot use bioconductor-uri here because this tarball is
8148 ;; located under "data/annotation/" instead of "bioc/".
8149 (uri (string-append "https://bioconductor.org/packages/"
8150 "release/data/experiment/src/contrib/"
8151 "genomationData_" version ".tar.gz"))
8154 "10xyb8akjrhmak2i0mnv1agny2ipy364q9nlibyplpzc7vdb6bw7"))))
8155 (build-system r-build-system)
8156 ;; As this package provides little more than large data files, it doesn't
8157 ;; make sense to build substitutes.
8158 (arguments `(#:substitutable? #f))
8160 `(("r-knitr" ,r-knitr)))
8161 (home-page "http://bioinformatics.mdc-berlin.de/genomation/")
8162 (synopsis "Experimental data for use with the genomation package")
8164 "This package contains experimental genetic data for use with the
8165 genomation package. Included are Chip Seq, Methylation and Cage data,
8166 downloaded from Encode.")
8167 (license license:gpl3+)))
8169 (define-public r-seqlogo
8176 (uri (bioconductor-uri "seqLogo" version))
8179 "1z63imr1a24nqijpvxaxlakykcsadfqyxl2b3vlllncxnjjvb52b"))))
8180 (properties `((upstream-name . "seqLogo")))
8181 (build-system r-build-system)
8182 (home-page "https://bioconductor.org/packages/seqLogo")
8183 (synopsis "Sequence logos for DNA sequence alignments")
8185 "seqLogo takes the position weight matrix of a DNA sequence motif and
8186 plots the corresponding sequence logo as introduced by Schneider and
8188 (license license:lgpl2.0+)))
8190 (define-public r-motifrg
8197 (uri (bioconductor-uri "motifRG" version))
8200 "02c7fbjwdq7pk96bd2rn07l9r2hqy00s3hfpli5ybmwgvc9h9z4z"))))
8201 (properties `((upstream-name . "motifRG")))
8202 (build-system r-build-system)
8204 `(("r-biostrings" ,r-biostrings)
8205 ("r-bsgenome" ,r-bsgenome)
8206 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8207 ("r-iranges" ,r-iranges)
8208 ("r-seqlogo" ,r-seqlogo)
8209 ("r-xvector" ,r-xvector)))
8210 (home-page "https://bioconductor.org/packages/motifRG")
8211 (synopsis "Discover motifs in high throughput sequencing data")
8213 "This package provides tools for discriminative motif discovery in high
8214 throughput genetic sequencing data sets using regression methods.")
8215 (license license:artistic2.0)))
8217 (define-public r-qtl
8224 (uri (string-append "mirror://cran/src/contrib/qtl_"
8228 "03lmvydln8b7666b6w46qbryhf83vsd11d4y2v95rfgvqgq66l1i"))))
8229 (build-system r-build-system)
8230 (home-page "http://rqtl.org/")
8231 (synopsis "R package for analyzing QTL experiments in genetics")
8232 (description "R/qtl is an extension library for the R statistics
8233 system. It is used to analyze experimental crosses for identifying
8234 genes contributing to variation in quantitative traits (so-called
8235 quantitative trait loci, QTLs).
8237 Using a hidden Markov model, R/qtl allows to estimate genetic maps, to
8238 identify genotyping errors, and to perform single-QTL and two-QTL,
8239 two-dimensional genome scans.")
8240 (license license:gpl3)))
8242 (define-public r-zlibbioc
8248 (uri (bioconductor-uri "zlibbioc" version))
8251 "1h0a2ps2rfk9azzps7p23sxj5z1giv8gcx0ypzgyz7fkr4xi9z7k"))))
8253 `((upstream-name . "zlibbioc")))
8254 (build-system r-build-system)
8255 (home-page "https://bioconductor.org/packages/zlibbioc")
8256 (synopsis "Provider for zlib-1.2.5 to R packages")
8257 (description "This package uses the source code of zlib-1.2.5 to create
8258 libraries for systems that do not have these available via other means.")
8259 (license license:artistic2.0)))
8261 (define-public r-r4rna
8268 (uri (string-append "http://www.e-rna.org/r-chie/files/R4RNA_"
8272 "1p0i78wh76jfgmn9jphbwwaz6yy6pipzfg08xs54cxavxg2j81p5"))))
8273 (build-system r-build-system)
8275 `(("r-optparse" ,r-optparse)
8276 ("r-rcolorbrewer" ,r-rcolorbrewer)))
8277 (home-page "http://www.e-rna.org/r-chie/index.cgi")
8278 (synopsis "Analysis framework for RNA secondary structure")
8280 "The R4RNA package aims to be a general framework for the analysis of RNA
8281 secondary structure and comparative analysis in R.")
8282 (license license:gpl3+)))
8284 (define-public r-rhtslib
8291 (uri (bioconductor-uri "Rhtslib" version))
8294 "178zbrm221rwhbjk7j2v9g5ra44k0xg7c5abhd810m3g7snma8k8"))))
8295 (properties `((upstream-name . "Rhtslib")))
8296 (build-system r-build-system)
8297 ;; Without this a temporary directory ends up in the Rhtslib.so binary,
8298 ;; which makes R abort the build.
8299 (arguments '(#:configure-flags '("--no-staged-install")))
8301 `(("r-zlibbioc" ,r-zlibbioc)))
8305 `(("pkg-config" ,pkg-config)))
8306 (home-page "https://github.com/nhayden/Rhtslib")
8307 (synopsis "High-throughput sequencing library as an R package")
8309 "This package provides the HTSlib C library for high-throughput
8310 nucleotide sequence analysis. The package is primarily useful to developers
8311 of other R packages who wish to make use of HTSlib.")
8312 (license license:lgpl2.0+)))
8314 (define-public r-bamsignals
8316 (name "r-bamsignals")
8321 (uri (bioconductor-uri "bamsignals" version))
8324 "15q1q51dwl9qxfkf10yppw4m194ba03nq9plsrbj8fqj00v4729i"))))
8325 (build-system r-build-system)
8327 `(("r-biocgenerics" ,r-biocgenerics)
8328 ("r-genomicranges" ,r-genomicranges)
8329 ("r-iranges" ,r-iranges)
8331 ("r-rhtslib" ,r-rhtslib)
8332 ("r-zlibbioc" ,r-zlibbioc)))
8335 (home-page "https://bioconductor.org/packages/bamsignals")
8336 (synopsis "Extract read count signals from bam files")
8338 "This package allows to efficiently obtain count vectors from indexed bam
8339 files. It counts the number of nucleotide sequence reads in given genomic
8340 ranges and it computes reads profiles and coverage profiles. It also handles
8342 (license license:gpl2+)))
8344 (define-public r-rcas
8350 (uri (bioconductor-uri "RCAS" version))
8353 "0ss5hcg2m7gjji6dd23zxa5bd5a7knwcnada4qs5q2l4clgk39ad"))))
8354 (properties `((upstream-name . "RCAS")))
8355 (build-system r-build-system)
8357 `(("r-annotationdbi" ,r-annotationdbi)
8358 ("r-biocgenerics" ,r-biocgenerics)
8359 ("r-biomart" ,r-biomart)
8360 ("r-biostrings" ,r-biostrings)
8361 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8362 ("r-cowplot" ,r-cowplot)
8363 ("r-data-table" ,r-data-table)
8366 ("r-genomation" ,r-genomation)
8367 ("r-genomeinfodb" ,r-genomeinfodb)
8368 ("r-genomicfeatures" ,r-genomicfeatures)
8369 ("r-genomicranges" ,r-genomicranges)
8370 ("r-ggplot2" ,r-ggplot2)
8371 ("r-ggseqlogo" ,r-ggseqlogo)
8372 ("r-knitr" ,r-knitr)
8373 ("r-motifrg" ,r-motifrg)
8374 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
8375 ("r-pbapply" ,r-pbapply)
8376 ("r-pheatmap" ,r-pheatmap)
8377 ("r-plotly" ,r-plotly)
8378 ("r-plotrix" ,r-plotrix)
8379 ("r-proxy" ,r-proxy)
8380 ("r-rsqlite" ,r-rsqlite)
8381 ("r-rtracklayer" ,r-rtracklayer)
8382 ("r-rmarkdown" ,r-rmarkdown)
8383 ("r-s4vectors" ,r-s4vectors)
8384 ("r-topgo" ,r-topgo)))
8385 (synopsis "RNA-centric annotation system")
8387 "RCAS aims to be a standalone RNA-centric annotation system that provides
8388 intuitive reports and publication-ready graphics. This package provides the R
8389 library implementing most of the pipeline's features.")
8390 (home-page "https://github.com/BIMSBbioinfo/RCAS")
8391 (license license:artistic2.0)))
8393 (define-public rcas-web
8400 (uri (string-append "https://github.com/BIMSBbioinfo/rcas-web/"
8401 "releases/download/v" version
8402 "/rcas-web-" version ".tar.gz"))
8405 "0wq951aj45gqki1bickg876i993lmawkp8x24agg264br5x716db"))))
8406 (build-system gnu-build-system)
8409 (modify-phases %standard-phases
8410 (add-after 'install 'wrap-executable
8411 (lambda* (#:key inputs outputs #:allow-other-keys)
8412 (let* ((out (assoc-ref outputs "out"))
8413 (json (assoc-ref inputs "guile-json"))
8414 (redis (assoc-ref inputs "guile-redis"))
8415 (path (string-append
8416 json "/share/guile/site/2.2:"
8417 redis "/share/guile/site/2.2")))
8418 (wrap-program (string-append out "/bin/rcas-web")
8419 `("GUILE_LOAD_PATH" ":" = (,path))
8420 `("GUILE_LOAD_COMPILED_PATH" ":" = (,path))
8421 `("R_LIBS_SITE" ":" = (,(getenv "R_LIBS_SITE")))))
8424 `(("r-minimal" ,r-minimal)
8426 ("guile-next" ,guile-2.2)
8427 ("guile-json" ,guile-json)
8428 ("guile-redis" ,guile-redis)))
8430 `(("pkg-config" ,pkg-config)))
8431 (home-page "https://github.com/BIMSBbioinfo/rcas-web")
8432 (synopsis "Web interface for RNA-centric annotation system (RCAS)")
8433 (description "This package provides a simple web interface for the
8434 @dfn{RNA-centric annotation system} (RCAS).")
8435 (license license:agpl3+)))
8437 (define-public r-mutationalpatterns
8439 (name "r-mutationalpatterns")
8444 (uri (bioconductor-uri "MutationalPatterns" version))
8447 "1k3r06xj1nim1s8as1i7fykfa6fbb4x456kslbzdvbf83ppx34z3"))))
8448 (build-system r-build-system)
8450 `(("r-biocgenerics" ,r-biocgenerics)
8451 ("r-biostrings" ,r-biostrings)
8452 ;; These two packages are suggested packages
8453 ("r-bsgenome-hsapiens-1000g" ,r-bsgenome-hsapiens-1000genomes-hs37d5)
8454 ("r-bsgenome-hsapiens-ucsc-hg19" ,r-bsgenome-hsapiens-ucsc-hg19)
8455 ("r-genomicranges" ,r-genomicranges)
8456 ("r-genomeinfodb" ,r-genomeinfodb)
8457 ("r-ggplot2" ,r-ggplot2)
8458 ("r-iranges" ,r-iranges)
8461 ("r-pracma" ,r-pracma)
8462 ("r-reshape2" ,r-reshape2)
8463 ("r-cowplot" ,r-cowplot)
8464 ("r-ggdendro" ,r-ggdendro)
8465 ("r-s4vectors" ,r-s4vectors)
8466 ("r-summarizedexperiment" ,r-summarizedexperiment)
8467 ("r-variantannotation" ,r-variantannotation)))
8468 (home-page "https://bioconductor.org/packages/MutationalPatterns/")
8469 (synopsis "Extract and visualize mutational patterns in genomic data")
8470 (description "This package provides an extensive toolset for the
8471 characterization and visualization of a wide range of mutational patterns
8472 in SNV base substitution data.")
8473 (license license:expat)))
8475 (define-public r-chipkernels
8476 (let ((commit "c9cfcacb626b1221094fb3490ea7bac0fd625372")
8479 (name "r-chipkernels")
8480 (version (string-append "1.1-" revision "." (string-take commit 9)))
8485 (url "https://github.com/ManuSetty/ChIPKernels.git")
8487 (file-name (string-append name "-" version))
8490 "14bj5qhjm1hsm9ay561nfbqi9wxsa7y487df2idsaaf6z10nw4v0"))))
8491 (build-system r-build-system)
8493 `(("r-iranges" ,r-iranges)
8494 ("r-xvector" ,r-xvector)
8495 ("r-biostrings" ,r-biostrings)
8496 ("r-bsgenome" ,r-bsgenome)
8497 ("r-gtools" ,r-gtools)
8498 ("r-genomicranges" ,r-genomicranges)
8499 ("r-sfsmisc" ,r-sfsmisc)
8500 ("r-kernlab" ,r-kernlab)
8501 ("r-s4vectors" ,r-s4vectors)
8502 ("r-biocgenerics" ,r-biocgenerics)))
8503 (home-page "https://github.com/ManuSetty/ChIPKernels")
8504 (synopsis "Build string kernels for DNA Sequence analysis")
8505 (description "ChIPKernels is an R package for building different string
8506 kernels used for DNA Sequence analysis. A dictionary of the desired kernel
8507 must be built and this dictionary can be used for determining kernels for DNA
8509 (license license:gpl2+))))
8511 (define-public r-seqgl
8519 (url "https://github.com/ManuSetty/SeqGL.git")
8521 (file-name (git-file-name name version))
8524 "1r6ywvhxl3ffv48lgj7sbd582mcc6dha3ksgc2qjlvjrnkbj3799"))))
8525 (build-system r-build-system)
8527 `(("r-biostrings" ,r-biostrings)
8528 ("r-chipkernels" ,r-chipkernels)
8529 ("r-genomicranges" ,r-genomicranges)
8530 ("r-spams" ,r-spams)
8531 ("r-wgcna" ,r-wgcna)
8532 ("r-fastcluster" ,r-fastcluster)))
8533 (home-page "https://github.com/ManuSetty/SeqGL")
8534 (synopsis "Group lasso for Dnase/ChIP-seq data")
8535 (description "SeqGL is a group lasso based algorithm to extract
8536 transcription factor sequence signals from ChIP, DNase and ATAC-seq profiles.
8537 This package presents a method which uses group lasso to discriminate between
8538 bound and non bound genomic regions to accurately identify transcription
8539 factors bound at the specific regions.")
8540 (license license:gpl2+)))
8542 (define-public r-tximport
8548 (uri (bioconductor-uri "tximport" version))
8551 "0nl4imr5klwcd0xnp5y0g61d6mcgd50q60zkl86ymfmc0id368jr"))))
8552 (build-system r-build-system)
8553 (home-page "https://bioconductor.org/packages/tximport")
8554 (synopsis "Import and summarize transcript-level estimates for gene-level analysis")
8556 "This package provides tools to import transcript-level abundance,
8557 estimated counts and transcript lengths, and to summarize them into matrices
8558 for use with downstream gene-level analysis packages. Average transcript
8559 length, weighted by sample-specific transcript abundance estimates, is
8560 provided as a matrix which can be used as an offset for different expression
8561 of gene-level counts.")
8562 (license license:gpl2+)))
8564 (define-public r-rhdf5
8570 (uri (bioconductor-uri "rhdf5" version))
8573 "0y1w3cs7wg2b3jlkd6wyyz6626xg011nrg36si8gg371iqck9a1i"))))
8574 (build-system r-build-system)
8576 `(("r-rhdf5lib" ,r-rhdf5lib)))
8579 (home-page "https://bioconductor.org/packages/rhdf5")
8580 (synopsis "HDF5 interface to R")
8582 "This R/Bioconductor package provides an interface between HDF5 and R.
8583 HDF5's main features are the ability to store and access very large and/or
8584 complex datasets and a wide variety of metadata on mass storage (disk) through
8585 a completely portable file format. The rhdf5 package is thus suited for the
8586 exchange of large and/or complex datasets between R and other software
8587 package, and for letting R applications work on datasets that are larger than
8588 the available RAM.")
8589 (license license:artistic2.0)))
8591 (define-public r-annotationfilter
8593 (name "r-annotationfilter")
8597 (uri (bioconductor-uri "AnnotationFilter" version))
8600 "15qh4jwxxqsnb308nxzj99gckfk18rhp8g26q1xwgkr57zc5kcrx"))))
8602 `((upstream-name . "AnnotationFilter")))
8603 (build-system r-build-system)
8605 `(("r-genomicranges" ,r-genomicranges)
8606 ("r-lazyeval" ,r-lazyeval)))
8607 (home-page "https://github.com/Bioconductor/AnnotationFilter")
8608 (synopsis "Facilities for filtering Bioconductor annotation resources")
8610 "This package provides classes and other infrastructure to implement
8611 filters for manipulating Bioconductor annotation resources. The filters are
8612 used by @code{ensembldb}, @code{Organism.dplyr}, and other packages.")
8613 (license license:artistic2.0)))
8615 (define-public emboss
8621 (uri (string-append "ftp://emboss.open-bio.org/pub/EMBOSS/old/"
8622 (version-major+minor version) ".0/"
8623 "EMBOSS-" version ".tar.gz"))
8626 "0vsmz96gc411yj2iyzdrsmg4l2n1nhgmp7vrgzlxx3xixv9xbf0q"))))
8627 (build-system gnu-build-system)
8630 (list (string-append "--with-hpdf="
8631 (assoc-ref %build-inputs "libharu")))
8633 (modify-phases %standard-phases
8634 (add-after 'unpack 'fix-checks
8636 ;; The PNGDRIVER tests check for the presence of libgd, libpng
8637 ;; and zlib, but assume that they are all found at the same
8639 (substitute* "configure.in"
8640 (("CHECK_PNGDRIVER")
8641 "LIBS=\"$LIBS -lgd -lpng -lz -lm\"
8642 AC_DEFINE([PLD_png], [1], [Define to 1 if PNG support is available])
8643 AM_CONDITIONAL(AMPNG, true)"))
8645 (add-after 'fix-checks 'disable-update-check
8647 ;; At build time there is no connection to the Internet, so
8648 ;; looking for updates will not work.
8649 (substitute* "Makefile.am"
8650 (("\\$\\(bindir\\)/embossupdate") ""))
8652 (add-after 'disable-update-check 'autogen
8653 (lambda _ (invoke "autoreconf" "-vif") #t)))))
8659 ("libharu" ,libharu)
8662 `(("autoconf" ,autoconf)
8663 ("automake" ,automake)
8664 ("libtool" ,libtool)
8665 ("pkg-config" ,pkg-config)))
8666 (home-page "http://emboss.sourceforge.net")
8667 (synopsis "Molecular biology analysis suite")
8668 (description "EMBOSS is the \"European Molecular Biology Open Software
8669 Suite\". EMBOSS is an analysis package specially developed for the needs of
8670 the molecular biology (e.g. EMBnet) user community. The software
8671 automatically copes with data in a variety of formats and even allows
8672 transparent retrieval of sequence data from the web. It also provides a
8673 number of libraries for the development of software in the field of molecular
8674 biology. EMBOSS also integrates a range of currently available packages and
8675 tools for sequence analysis into a seamless whole.")
8676 (license license:gpl2+)))
8679 (let ((revision "1")
8680 (commit "3cc4567896d9d6442923da944beb704750a08d2d"))
8683 ;; The version is 2.13.0 even though no release archives have been
8684 ;; published as yet.
8685 (version (string-append "2.13.0-" revision "." (string-take commit 9)))
8689 (url "https://github.com/arq5x/bits.git")
8691 (file-name (string-append name "-" version "-checkout"))
8694 "17n2kffk4kmhivd8c98g2vr6y1s23vbg4sxlxs689wni66797hbs"))))
8695 (build-system gnu-build-system)
8697 `(#:tests? #f ;no tests included
8699 (modify-phases %standard-phases
8701 (add-after 'unpack 'remove-cuda
8703 (substitute* "Makefile"
8705 (("(bits_test_intersections) \\\\" _ match) match))
8708 (lambda* (#:key outputs #:allow-other-keys)
8710 "bin" (string-append (assoc-ref outputs "out") "/bin"))
8715 (home-page "https://github.com/arq5x/bits")
8716 (synopsis "Implementation of binary interval search algorithm")
8717 (description "This package provides an implementation of the
8718 BITS (Binary Interval Search) algorithm, an approach to interval set
8719 intersection. It is especially suited for the comparison of diverse genomic
8720 datasets and the exploration of large datasets of genome
8721 intervals (e.g. genes, sequence alignments).")
8722 (license license:gpl2))))
8724 (define-public piranha
8725 ;; There is no release tarball for the latest version. The latest commit is
8726 ;; older than one year at the time of this writing.
8727 (let ((revision "1")
8728 (commit "0466d364b71117d01e4471b74c514436cc281233"))
8731 (version (string-append "1.2.1-" revision "." (string-take commit 9)))
8735 (url "https://github.com/smithlabcode/piranha.git")
8737 (file-name (git-file-name name version))
8740 "117dc0zf20c61jam69sk4abl57ah6yi6i7qra7d7y5zrbgk12q5n"))))
8741 (build-system gnu-build-system)
8743 `(#:test-target "test"
8745 (modify-phases %standard-phases
8746 (add-after 'unpack 'copy-smithlab-cpp
8747 (lambda* (#:key inputs #:allow-other-keys)
8748 (for-each (lambda (file)
8749 (install-file file "./src/smithlab_cpp/"))
8750 (find-files (assoc-ref inputs "smithlab-cpp")))
8752 (add-after 'install 'install-to-store
8753 (lambda* (#:key outputs #:allow-other-keys)
8754 (let* ((out (assoc-ref outputs "out"))
8755 (bin (string-append out "/bin")))
8756 (for-each (lambda (file)
8757 (install-file file bin))
8758 (find-files "bin" ".*")))
8761 (list (string-append "--with-bam_tools_headers="
8762 (assoc-ref %build-inputs "bamtools") "/include/bamtools")
8763 (string-append "--with-bam_tools_library="
8764 (assoc-ref %build-inputs "bamtools") "/lib/bamtools"))))
8766 `(("bamtools" ,bamtools)
8767 ("samtools" ,samtools-0.1)
8770 ,(let ((commit "3723e2db438c51501d0423429ff396c3035ba46a"))
8774 (url "https://github.com/smithlabcode/smithlab_cpp.git")
8776 (file-name (string-append "smithlab_cpp-" commit "-checkout"))
8779 "0l4gvbwslw5ngziskja41c00x1r06l3yidv7y0xw9djibhykzy0g")))))))
8781 `(("python" ,python-2)))
8782 (home-page "https://github.com/smithlabcode/piranha")
8783 (synopsis "Peak-caller for CLIP-seq and RIP-seq data")
8785 "Piranha is a peak-caller for genomic data produced by CLIP-seq and
8786 RIP-seq experiments. It takes input in BED or BAM format and identifies
8787 regions of statistically significant read enrichment. Additional covariates
8788 may optionally be provided to further inform the peak-calling process.")
8789 (license license:gpl3+))))
8797 (uri (pypi-uri "PePr" version))
8800 "0qxjfdpl1b1y53nccws2d85f6k74zwmx8y8sd9rszcqhfayx6gdx"))))
8801 (build-system python-build-system)
8803 `(#:python ,python-2 ; python2 only
8804 #:tests? #f)) ; no tests included
8806 `(("python2-numpy" ,python2-numpy)
8807 ("python2-scipy" ,python2-scipy)
8808 ("python2-pysam" ,python2-pysam)))
8809 (home-page "https://github.com/shawnzhangyx/PePr")
8810 (synopsis "Peak-calling and prioritization pipeline for ChIP-Seq data")
8812 "PePr is a ChIP-Seq peak calling or differential binding analysis tool
8813 that is primarily designed for data with biological replicates. It uses a
8814 negative binomial distribution to model the read counts among the samples in
8815 the same group, and look for consistent differences between ChIP and control
8816 group or two ChIP groups run under different conditions.")
8817 (license license:gpl3+)))
8819 (define-public filevercmp
8820 (let ((commit "1a9b779b93d0b244040274794d402106907b71b7"))
8823 (version (string-append "0-1." (string-take commit 7)))
8827 (url "https://github.com/ekg/filevercmp.git")
8829 (file-name (git-file-name name commit))
8832 "1j9vxsy0y050v59h0q1d6501fcw1kjvj0d18l1xk2zyg0jzj247c"))))
8833 (build-system gnu-build-system)
8835 `(#:tests? #f ; There are no tests to run.
8837 (modify-phases %standard-phases
8838 (delete 'configure) ; There is no configure phase.
8840 (lambda* (#:key outputs #:allow-other-keys)
8841 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
8842 (install-file "filevercmp" bin)
8844 (home-page "https://github.com/ekg/filevercmp")
8845 (synopsis "This program compares version strings")
8846 (description "This program compares version strings. It intends to be a
8847 replacement for strverscmp.")
8848 (license license:gpl3+))))
8850 (define-public multiqc
8857 (uri (pypi-uri "multiqc" version))
8860 "02iihfl0w0hpnr4pa0sbd1y9qxrg3ycyhjp5lidkcrqh1lmzs3zy"))))
8861 (build-system python-build-system)
8863 `(("python-jinja2" ,python-jinja2)
8864 ("python-simplejson" ,python-simplejson)
8865 ("python-pyyaml" ,python-pyyaml)
8866 ("python-click" ,python-click)
8867 ("python-spectra" ,python-spectra)
8868 ("python-requests" ,python-requests)
8869 ("python-markdown" ,python-markdown)
8870 ("python-lzstring" ,python-lzstring)
8871 ("python-matplotlib" ,python-matplotlib)
8872 ("python-numpy" ,python-numpy)
8873 ;; MultQC checks for the presence of nose at runtime.
8874 ("python-nose" ,python-nose)))
8877 (modify-phases %standard-phases
8878 (add-after 'unpack 'relax-requirements
8880 (substitute* "setup.py"
8881 ;; MultiQC 1.5 ‘requires’ a version of python-matplotlib older
8882 ;; than the one in Guix, but should work fine with 2.2.2.
8883 ;; See <https://github.com/ewels/MultiQC/issues/725> and
8884 ;; <https://github.com/ewels/MultiQC/issues/732> for details.
8885 (("['\"]matplotlib.*?['\"]")
8888 (home-page "http://multiqc.info")
8889 (synopsis "Aggregate bioinformatics analysis reports")
8891 "MultiQC is a tool to aggregate bioinformatics results across many
8892 samples into a single report. It contains modules for a large number of
8893 common bioinformatics tools.")
8894 (license license:gpl3+)))
8896 (define-public r-chipseq
8903 (uri (bioconductor-uri "chipseq" version))
8906 "1835nhrxcaqpqf1kxrsk1js8bf7x33z1n3bqjvm8404091acqyma"))))
8907 (build-system r-build-system)
8909 `(("r-biocgenerics" ,r-biocgenerics)
8910 ("r-genomicranges" ,r-genomicranges)
8911 ("r-iranges" ,r-iranges)
8912 ("r-lattice" ,r-lattice)
8913 ("r-s4vectors" ,r-s4vectors)
8914 ("r-shortread" ,r-shortread)))
8915 (home-page "https://bioconductor.org/packages/chipseq")
8916 (synopsis "Package for analyzing ChIPseq data")
8918 "This package provides tools for processing short read data from ChIPseq
8920 (license license:artistic2.0)))
8922 (define-public r-copyhelper
8924 (name "r-copyhelper")
8929 (uri (string-append "https://bioconductor.org/packages/release/"
8930 "data/experiment/src/contrib/CopyhelpeR_"
8934 "0x7cyynjmxls9as2gg0iyp9x5fpalxmdjq914ss7i84i9zyk5bhq"))))
8935 (properties `((upstream-name . "CopyhelpeR")))
8936 (build-system r-build-system)
8937 (home-page "https://bioconductor.org/packages/CopyhelpeR/")
8938 (synopsis "Helper files for CopywriteR")
8940 "This package contains the helper files that are required to run the
8941 Bioconductor package CopywriteR. It contains pre-assembled 1kb bin GC-content
8942 and mappability files for the reference genomes hg18, hg19, hg38, mm9 and
8943 mm10. In addition, it contains a blacklist filter to remove regions that
8944 display copy number variation. Files are stored as GRanges objects from the
8945 GenomicRanges Bioconductor package.")
8946 (license license:gpl2)))
8948 (define-public r-copywriter
8950 (name "r-copywriter")
8955 (uri (bioconductor-uri "CopywriteR" version))
8958 "0kv3k58wyyicq1hhq7bddh0v3b2ksz6fa47skvnp8f193csza9g6"))))
8959 (properties `((upstream-name . "CopywriteR")))
8960 (build-system r-build-system)
8962 `(("r-biocparallel" ,r-biocparallel)
8963 ("r-chipseq" ,r-chipseq)
8964 ("r-copyhelper" ,r-copyhelper)
8965 ("r-data-table" ,r-data-table)
8966 ("r-dnacopy" ,r-dnacopy)
8967 ("r-futile-logger" ,r-futile-logger)
8968 ("r-genomeinfodb" ,r-genomeinfodb)
8969 ("r-genomicalignments" ,r-genomicalignments)
8970 ("r-genomicranges" ,r-genomicranges)
8971 ("r-gtools" ,r-gtools)
8972 ("r-iranges" ,r-iranges)
8973 ("r-matrixstats" ,r-matrixstats)
8974 ("r-rsamtools" ,r-rsamtools)
8975 ("r-s4vectors" ,r-s4vectors)))
8976 (home-page "https://github.com/PeeperLab/CopywriteR")
8977 (synopsis "Copy number information from targeted sequencing")
8979 "CopywriteR extracts DNA copy number information from targeted sequencing
8980 by utilizing off-target reads. It allows for extracting uniformly distributed
8981 copy number information, can be used without reference, and can be applied to
8982 sequencing data obtained from various techniques including chromatin
8983 immunoprecipitation and target enrichment on small gene panels. Thereby,
8984 CopywriteR constitutes a widely applicable alternative to available copy
8985 number detection tools.")
8986 (license license:gpl2)))
8988 (define-public r-methylkit
8990 (name "r-methylkit")
8994 (uri (bioconductor-uri "methylKit" version))
8997 "1zcfwy7i10aqgnf7r0c41hakb5aai3s3n9y8pc6a98vimz51ly2z"))))
8998 (properties `((upstream-name . "methylKit")))
8999 (build-system r-build-system)
9001 `(("r-data-table" ,r-data-table)
9002 ("r-emdbook" ,r-emdbook)
9003 ("r-fastseg" ,r-fastseg)
9004 ("r-genomeinfodb" ,r-genomeinfodb)
9005 ("r-genomicranges" ,r-genomicranges)
9006 ("r-gtools" ,r-gtools)
9007 ("r-iranges" ,r-iranges)
9008 ("r-kernsmooth" ,r-kernsmooth)
9009 ("r-limma" ,r-limma)
9010 ("r-mclust" ,r-mclust)
9011 ("r-qvalue" ,r-qvalue)
9012 ("r-r-utils" ,r-r-utils)
9014 ("r-rhtslib" ,r-rhtslib)
9015 ("r-rsamtools" ,r-rsamtools)
9016 ("r-rtracklayer" ,r-rtracklayer)
9017 ("r-s4vectors" ,r-s4vectors)
9018 ("r-zlibbioc" ,r-zlibbioc)))
9021 (home-page "https://github.com/al2na/methylKit")
9023 "DNA methylation analysis from high-throughput bisulfite sequencing results")
9025 "MethylKit is an R package for DNA methylation analysis and annotation
9026 from high-throughput bisulfite sequencing. The package is designed to deal
9027 with sequencing data from @dfn{Reduced representation bisulfite
9028 sequencing} (RRBS) and its variants, but also target-capture methods and whole
9029 genome bisulfite sequencing. It also has functions to analyze base-pair
9030 resolution 5hmC data from experimental protocols such as oxBS-Seq and
9032 (license license:artistic2.0)))
9034 (define-public r-sva
9041 (uri (bioconductor-uri "sva" version))
9044 "100jwi43y4xdqb5lldx1ld58jg9icdjgz6c7ylx95gspipnkbgjp"))))
9045 (build-system r-build-system)
9047 `(("r-genefilter" ,r-genefilter)
9049 ("r-biocparallel" ,r-biocparallel)
9050 ("r-matrixstats" ,r-matrixstats)
9051 ("r-limma" ,r-limma)))
9052 (home-page "https://bioconductor.org/packages/sva")
9053 (synopsis "Surrogate variable analysis")
9055 "This package contains functions for removing batch effects and other
9056 unwanted variation in high-throughput experiment. It also contains functions
9057 for identifying and building surrogate variables for high-dimensional data
9058 sets. Surrogate variables are covariates constructed directly from
9059 high-dimensional data like gene expression/RNA sequencing/methylation/brain
9060 imaging data that can be used in subsequent analyses to adjust for unknown,
9061 unmodeled, or latent sources of noise.")
9062 (license license:artistic2.0)))
9064 (define-public r-seqminer
9071 (uri (cran-uri "seqminer" version))
9074 "1jydcpkw4rwfp983j83kipvsvr10as9pb49zzn3c2v09k1gh3ymy"))))
9075 (build-system r-build-system)
9078 (home-page "http://seqminer.genomic.codes")
9079 (synopsis "Read nucleotide sequence data (VCF, BCF, and METAL formats)")
9081 "This package provides tools to integrate nucleotide sequencing
9082 data (variant call format, e.g. VCF or BCF) or meta-analysis results in R.")
9083 ;; Any version of the GPL is acceptable
9084 (license (list license:gpl2+ license:gpl3+))))
9086 (define-public r-raremetals2
9088 (name "r-raremetals2")
9093 (uri (string-append "http://genome.sph.umich.edu/w/images/"
9094 "b/b7/RareMETALS2_" version ".tar.gz"))
9097 "0z5ljcgvnm06ja9lm85a3cniq7slxcy37aqqkxrdidr79an5fs4s"))))
9098 (properties `((upstream-name . "RareMETALS2")))
9099 (build-system r-build-system)
9101 `(("r-seqminer" ,r-seqminer)
9102 ("r-mvtnorm" ,r-mvtnorm)
9104 ("r-compquadform" ,r-compquadform)
9105 ("r-getopt" ,r-getopt)))
9106 (home-page "http://genome.sph.umich.edu/wiki/RareMETALS2")
9107 (synopsis "Analyze gene-level association tests for binary trait")
9109 "The R package rareMETALS2 is an extension of the R package rareMETALS.
9110 It was designed to meta-analyze gene-level association tests for binary trait.
9111 While rareMETALS offers a near-complete solution for meta-analysis of
9112 gene-level tests for quantitative trait, it does not offer the optimal
9113 solution for binary trait. The package rareMETALS2 offers improved features
9114 for analyzing gene-level association tests in meta-analyses for binary
9116 (license license:gpl3)))
9118 (define-public r-maldiquant
9120 (name "r-maldiquant")
9125 (uri (cran-uri "MALDIquant" version))
9128 "11zbvm1vw8zn2vmymvydgdczvwj961s2knvrn1q4gbziwi5gqvlc"))))
9129 (properties `((upstream-name . "MALDIquant")))
9130 (build-system r-build-system)
9131 (home-page "https://cran.r-project.org/web/packages/MALDIquant")
9132 (synopsis "Quantitative analysis of mass spectrometry data")
9134 "This package provides a complete analysis pipeline for matrix-assisted
9135 laser desorption/ionization-time-of-flight (MALDI-TOF) and other
9136 two-dimensional mass spectrometry data. In addition to commonly used plotting
9137 and processing methods it includes distinctive features, namely baseline
9138 subtraction methods such as morphological filters (TopHat) or the
9139 statistics-sensitive non-linear iterative peak-clipping algorithm (SNIP), peak
9140 alignment using warping functions, handling of replicated measurements as well
9141 as allowing spectra with different resolutions.")
9142 (license license:gpl3+)))
9144 (define-public r-protgenerics
9146 (name "r-protgenerics")
9151 (uri (bioconductor-uri "ProtGenerics" version))
9154 "12jjwmg58b4xbivxlw4pffq0qfi2c1c5hyrci0sfyphrc99fvx0i"))))
9155 (properties `((upstream-name . "ProtGenerics")))
9156 (build-system r-build-system)
9157 (home-page "https://github.com/lgatto/ProtGenerics")
9158 (synopsis "S4 generic functions for proteomics infrastructure")
9160 "This package provides S4 generic functions needed by Bioconductor
9161 proteomics packages.")
9162 (license license:artistic2.0)))
9164 (define-public r-mzr
9171 (uri (bioconductor-uri "mzR" version))
9174 "0g5r6yk4gyz0xdwlmrcij4zv7apdgsgygr043095l33hard6nsl5"))
9175 (modules '((guix build utils)))
9178 (delete-file-recursively "src/boost")
9180 (properties `((upstream-name . "mzR")))
9181 (build-system r-build-system)
9184 (modify-phases %standard-phases
9185 (add-after 'unpack 'use-system-boost
9187 (substitute* "src/Makevars"
9188 (("\\./boost/libs.*") "")
9189 (("ARCH_OBJS=" line)
9191 "\nARCH_LIBS=-lboost_system -lboost_regex \
9192 -lboost_iostreams -lboost_thread -lboost_filesystem -lboost_chrono\n")))
9195 `(;; XXX Boost 1.69 will not work here.
9196 ("boost" ,boost-for-mysql) ; use this instead of the bundled boost sources
9199 `(("r-biobase" ,r-biobase)
9200 ("r-biocgenerics" ,r-biocgenerics)
9201 ("r-ncdf4" ,r-ncdf4)
9202 ("r-protgenerics" ,r-protgenerics)
9204 ("r-rhdf5lib" ,r-rhdf5lib)
9205 ("r-zlibbioc" ,r-zlibbioc)))
9206 (home-page "https://github.com/sneumann/mzR/")
9207 (synopsis "Parser for mass spectrometry data files")
9209 "The mzR package provides a unified API to the common file formats and
9210 parsers available for mass spectrometry data. It comes with a wrapper for the
9211 ISB random access parser for mass spectrometry mzXML, mzData and mzML files.
9212 The package contains the original code written by the ISB, and a subset of the
9213 proteowizard library for mzML and mzIdentML. The netCDF reading code has
9214 previously been used in XCMS.")
9215 (license license:artistic2.0)))
9217 (define-public r-affyio
9224 (uri (bioconductor-uri "affyio" version))
9227 "1s78hm51fgac3i2j4bbdy0z6g14370154s6km8lldc9zpahx8b6p"))))
9228 (build-system r-build-system)
9230 `(("r-zlibbioc" ,r-zlibbioc)))
9233 (home-page "https://github.com/bmbolstad/affyio")
9234 (synopsis "Tools for parsing Affymetrix data files")
9236 "This package provides routines for parsing Affymetrix data files based
9237 upon file format information. The primary focus is on accessing the CEL and
9239 (license license:lgpl2.0+)))
9241 (define-public r-affy
9248 (uri (bioconductor-uri "affy" version))
9251 "05vz0vf3472s1ivfhc0gc8yz98y4rvvp7cf6kfbxhy1b23im1bgk"))))
9252 (build-system r-build-system)
9254 `(("r-affyio" ,r-affyio)
9255 ("r-biobase" ,r-biobase)
9256 ("r-biocgenerics" ,r-biocgenerics)
9257 ("r-biocmanager" ,r-biocmanager)
9258 ("r-preprocesscore" ,r-preprocesscore)
9259 ("r-zlibbioc" ,r-zlibbioc)))
9262 (home-page "https://bioconductor.org/packages/affy")
9263 (synopsis "Methods for affymetrix oligonucleotide arrays")
9265 "This package contains functions for exploratory oligonucleotide array
9267 (license license:lgpl2.0+)))
9269 (define-public r-vsn
9276 (uri (bioconductor-uri "vsn" version))
9279 "1vqmyxg06kgq9m3w6n0jykqm4jgsjw879r4s216wlcq4xc94dh1r"))))
9280 (build-system r-build-system)
9282 `(("r-affy" ,r-affy)
9283 ("r-biobase" ,r-biobase)
9284 ("r-ggplot2" ,r-ggplot2)
9285 ("r-lattice" ,r-lattice)
9286 ("r-limma" ,r-limma)))
9287 (home-page "https://bioconductor.org/packages/release/bioc/html/vsn.html")
9288 (synopsis "Variance stabilization and calibration for microarray data")
9290 "The package implements a method for normalising microarray intensities,
9291 and works for single- and multiple-color arrays. It can also be used for data
9292 from other technologies, as long as they have similar format. The method uses
9293 a robust variant of the maximum-likelihood estimator for an
9294 additive-multiplicative error model and affine calibration. The model
9295 incorporates data calibration step (a.k.a. normalization), a model for the
9296 dependence of the variance on the mean intensity and a variance stabilizing
9297 data transformation. Differences between transformed intensities are
9298 analogous to \"normalized log-ratios\". However, in contrast to the latter,
9299 their variance is independent of the mean, and they are usually more sensitive
9300 and specific in detecting differential transcription.")
9301 (license license:artistic2.0)))
9303 (define-public r-mzid
9310 (uri (bioconductor-uri "mzID" version))
9313 "0vnyg7jlmy7ain7gmjwhqyqr664znrvrdlh7zd63563vhb87qarn"))))
9314 (properties `((upstream-name . "mzID")))
9315 (build-system r-build-system)
9317 `(("r-doparallel" ,r-doparallel)
9318 ("r-foreach" ,r-foreach)
9319 ("r-iterators" ,r-iterators)
9321 ("r-protgenerics" ,r-protgenerics)
9324 (home-page "https://bioconductor.org/packages/mzID")
9325 (synopsis "Parser for mzIdentML files")
9327 "This package provides a parser for mzIdentML files implemented using the
9328 XML package. The parser tries to be general and able to handle all types of
9329 mzIdentML files with the drawback of having less pretty output than a vendor
9331 (license license:gpl2+)))
9333 (define-public r-pcamethods
9335 (name "r-pcamethods")
9340 (uri (bioconductor-uri "pcaMethods" version))
9343 "0svf4n7l0afy4wwgs6x8x4dm330r3311l5vmsxw2f0r4axkh3bzk"))))
9344 (properties `((upstream-name . "pcaMethods")))
9345 (build-system r-build-system)
9347 `(("r-biobase" ,r-biobase)
9348 ("r-biocgenerics" ,r-biocgenerics)
9350 ("r-rcpp" ,r-rcpp)))
9351 (home-page "https://github.com/hredestig/pcamethods")
9352 (synopsis "Collection of PCA methods")
9354 "This package provides Bayesian PCA, Probabilistic PCA, Nipals PCA,
9355 Inverse Non-Linear PCA and the conventional SVD PCA. A cluster based method
9356 for missing value estimation is included for comparison. BPCA, PPCA and
9357 NipalsPCA may be used to perform PCA on incomplete data as well as for
9358 accurate missing value estimation. A set of methods for printing and plotting
9359 the results is also provided. All PCA methods make use of the same data
9360 structure (pcaRes) to provide a common interface to the PCA results.")
9361 (license license:gpl3+)))
9363 (define-public r-msnbase
9370 (uri (bioconductor-uri "MSnbase" version))
9373 "1lqdlyvs2c9g55zf8gnw142ps4jid644fhfvclnax7sjjwrqdjzv"))))
9374 (properties `((upstream-name . "MSnbase")))
9375 (build-system r-build-system)
9377 `(("r-affy" ,r-affy)
9378 ("r-biobase" ,r-biobase)
9379 ("r-biocgenerics" ,r-biocgenerics)
9380 ("r-biocparallel" ,r-biocparallel)
9381 ("r-digest" ,r-digest)
9382 ("r-ggplot2" ,r-ggplot2)
9383 ("r-impute" ,r-impute)
9384 ("r-iranges" ,r-iranges)
9385 ("r-lattice" ,r-lattice)
9386 ("r-maldiquant" ,r-maldiquant)
9390 ("r-pcamethods" ,r-pcamethods)
9392 ("r-preprocesscore" ,r-preprocesscore)
9393 ("r-protgenerics" ,r-protgenerics)
9395 ("r-s4vectors" ,r-s4vectors)
9396 ("r-scales" ,r-scales)
9399 (home-page "https://github.com/lgatto/MSnbase")
9400 (synopsis "Base functions and classes for MS-based proteomics")
9402 "This package provides basic plotting, data manipulation and processing
9403 of mass spectrometry based proteomics data.")
9404 (license license:artistic2.0)))
9406 (define-public r-msnid
9413 (uri (bioconductor-uri "MSnID" version))
9416 "18mp8zacawhfapfwpq8czbswxix2ykvqhwjga54v0a99zg3k87h3"))))
9417 (properties `((upstream-name . "MSnID")))
9418 (build-system r-build-system)
9420 `(("r-biobase" ,r-biobase)
9421 ("r-data-table" ,r-data-table)
9422 ("r-doparallel" ,r-doparallel)
9423 ("r-dplyr" ,r-dplyr)
9424 ("r-foreach" ,r-foreach)
9425 ("r-iterators" ,r-iterators)
9426 ("r-msnbase" ,r-msnbase)
9429 ("r-protgenerics" ,r-protgenerics)
9430 ("r-r-cache" ,r-r-cache)
9432 ("r-reshape2" ,r-reshape2)))
9433 (home-page "https://bioconductor.org/packages/MSnID")
9434 (synopsis "Utilities for LC-MSn proteomics identifications")
9436 "This package extracts @dfn{tandem mass spectrometry} (MS/MS) ID data
9437 from mzIdentML (leveraging the mzID package) or text files. After collating
9438 the search results from multiple datasets it assesses their identification
9439 quality and optimize filtering criteria to achieve the maximum number of
9440 identifications while not exceeding a specified false discovery rate. It also
9441 contains a number of utilities to explore the MS/MS results and assess missed
9442 and irregular enzymatic cleavages, mass measurement accuracy, etc.")
9443 (license license:artistic2.0)))
9445 (define-public r-seurat
9451 (uri (cran-uri "Seurat" version))
9454 "183lm2wk0i3g114jbdf7pb4ssizr48qzqv3cknbsiackr8kvpsvc"))))
9455 (properties `((upstream-name . "Seurat")))
9456 (build-system r-build-system)
9459 ("r-cluster" ,r-cluster)
9460 ("r-cowplot" ,r-cowplot)
9461 ("r-fitdistrplus" ,r-fitdistrplus)
9462 ("r-future" ,r-future)
9463 ("r-future-apply" ,r-future-apply)
9464 ("r-ggplot2" ,r-ggplot2)
9465 ("r-ggrepel" ,r-ggrepel)
9466 ("r-ggridges" ,r-ggridges)
9468 ("r-igraph" ,r-igraph)
9469 ("r-irlba" ,r-irlba)
9470 ("r-kernsmooth" ,r-kernsmooth)
9471 ("r-lmtest" ,r-lmtest)
9473 ("r-matrix" ,r-matrix)
9474 ("r-metap" ,r-metap)
9475 ("r-pbapply" ,r-pbapply)
9476 ("r-plotly" ,r-plotly)
9479 ("r-rcolorbrewer" ,r-rcolorbrewer)
9481 ("r-rcppeigen" ,r-rcppeigen)
9482 ("r-rcppprogress" ,r-rcppprogress)
9483 ("r-reticulate" ,r-reticulate)
9484 ("r-rlang" ,r-rlang)
9487 ("r-rtsne" ,r-rtsne)
9488 ("r-scales" ,r-scales)
9489 ("r-sctransform" ,r-sctransform)
9490 ("r-sdmtools" ,r-sdmtools)
9491 ("r-tsne" ,r-tsne)))
9492 (home-page "http://www.satijalab.org/seurat")
9493 (synopsis "Seurat is an R toolkit for single cell genomics")
9495 "This package is an R package designed for QC, analysis, and
9496 exploration of single cell RNA-seq data. It easily enables widely-used
9497 analytical techniques, including the identification of highly variable genes,
9498 dimensionality reduction; PCA, ICA, t-SNE, standard unsupervised clustering
9499 algorithms; density clustering, hierarchical clustering, k-means, and the
9500 discovery of differentially expressed genes and markers.")
9501 (license license:gpl3)))
9503 (define-public r-aroma-light
9505 (name "r-aroma-light")
9510 (uri (bioconductor-uri "aroma.light" version))
9513 "0a1prl4jhbqpa85i2vyia1ks9iippzl8np50fvm9wx8kbjxna5l6"))))
9514 (properties `((upstream-name . "aroma.light")))
9515 (build-system r-build-system)
9517 `(("r-matrixstats" ,r-matrixstats)
9518 ("r-r-methodss3" ,r-r-methodss3)
9520 ("r-r-utils" ,r-r-utils)))
9521 (home-page "https://github.com/HenrikBengtsson/aroma.light")
9522 (synopsis "Methods for normalization and visualization of microarray data")
9524 "This package provides methods for microarray analysis that take basic
9525 data types such as matrices and lists of vectors. These methods can be used
9526 standalone, be utilized in other packages, or be wrapped up in higher-level
9528 (license license:gpl2+)))
9530 (define-public r-deseq
9537 (uri (bioconductor-uri "DESeq" version))
9540 "0jppqrikg9qfqcfw5qd3m5c7bag9g23bc0kcpk5zfkk1wv09mnlm"))))
9541 (properties `((upstream-name . "DESeq")))
9542 (build-system r-build-system)
9544 `(("r-biobase" ,r-biobase)
9545 ("r-biocgenerics" ,r-biocgenerics)
9546 ("r-genefilter" ,r-genefilter)
9547 ("r-geneplotter" ,r-geneplotter)
9548 ("r-lattice" ,r-lattice)
9549 ("r-locfit" ,r-locfit)
9551 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9552 (home-page "http://www-huber.embl.de/users/anders/DESeq")
9553 (synopsis "Differential gene expression analysis")
9555 "This package provides tools for estimating variance-mean dependence in
9556 count data from high-throughput genetic sequencing assays and for testing for
9557 differential expression based on a model using the negative binomial
9559 (license license:gpl3+)))
9561 (define-public r-edaseq
9568 (uri (bioconductor-uri "EDASeq" version))
9571 "0mmc9bij17w4mfwcc566zbj5fvqgl8gfqs0qvj6ri4mbcql9jxb3"))))
9572 (properties `((upstream-name . "EDASeq")))
9573 (build-system r-build-system)
9575 `(("r-annotationdbi" ,r-annotationdbi)
9576 ("r-aroma-light" ,r-aroma-light)
9577 ("r-biobase" ,r-biobase)
9578 ("r-biocgenerics" ,r-biocgenerics)
9579 ("r-biocmanager" ,r-biocmanager)
9580 ("r-biomart" ,r-biomart)
9581 ("r-biostrings" ,r-biostrings)
9582 ("r-deseq" ,r-deseq)
9583 ("r-genomicfeatures" ,r-genomicfeatures)
9584 ("r-genomicranges" ,r-genomicranges)
9585 ("r-iranges" ,r-iranges)
9586 ("r-rsamtools" ,r-rsamtools)
9587 ("r-shortread" ,r-shortread)))
9588 (home-page "https://github.com/drisso/EDASeq")
9589 (synopsis "Exploratory data analysis and normalization for RNA-Seq")
9591 "This package provides support for numerical and graphical summaries of
9592 RNA-Seq genomic read data. Provided within-lane normalization procedures to
9593 adjust for GC-content effect (or other gene-level effects) on read counts:
9594 loess robust local regression, global-scaling, and full-quantile
9595 normalization. Between-lane normalization procedures to adjust for
9596 distributional differences between lanes (e.g., sequencing depth):
9597 global-scaling and full-quantile normalization.")
9598 (license license:artistic2.0)))
9600 (define-public r-interactivedisplaybase
9602 (name "r-interactivedisplaybase")
9607 (uri (bioconductor-uri "interactiveDisplayBase" version))
9610 "1kkyv7hkygacmksvld9gs3ycf6wlblqcwi11nny0hq3l0ha265v5"))))
9612 `((upstream-name . "interactiveDisplayBase")))
9613 (build-system r-build-system)
9615 `(("r-biocgenerics" ,r-biocgenerics)
9616 ("r-shiny" ,r-shiny)))
9617 (home-page "https://bioconductor.org/packages/interactiveDisplayBase")
9618 (synopsis "Base package for web displays of Bioconductor objects")
9620 "This package contains the basic methods needed to generate interactive
9621 Shiny-based display methods for Bioconductor objects.")
9622 (license license:artistic2.0)))
9624 (define-public r-annotationhub
9626 (name "r-annotationhub")
9631 (uri (bioconductor-uri "AnnotationHub" version))
9634 "0iyrxaijl4614iz5c1j53227xy2g756p3bx7hcwglcybh0k30nki"))))
9635 (properties `((upstream-name . "AnnotationHub")))
9636 (build-system r-build-system)
9638 `(("r-annotationdbi" ,r-annotationdbi)
9639 ("r-biocgenerics" ,r-biocgenerics)
9640 ("r-biocmanager" ,r-biocmanager)
9643 ("r-interactivedisplaybase" ,r-interactivedisplaybase)
9644 ("r-rsqlite" ,r-rsqlite)
9645 ("r-s4vectors" ,r-s4vectors)
9646 ("r-yaml" ,r-yaml)))
9647 (home-page "https://bioconductor.org/packages/AnnotationHub")
9648 (synopsis "Client to access AnnotationHub resources")
9650 "This package provides a client for the Bioconductor AnnotationHub web
9651 resource. The AnnotationHub web resource provides a central location where
9652 genomic files (e.g. VCF, bed, wig) and other resources from standard
9653 locations (e.g. UCSC, Ensembl) can be discovered. The resource includes
9654 metadata about each resource, e.g., a textual description, tags, and date of
9655 modification. The client creates and manages a local cache of files retrieved
9656 by the user, helping with quick and reproducible access.")
9657 (license license:artistic2.0)))
9659 (define-public r-fastseg
9666 (uri (bioconductor-uri "fastseg" version))
9669 "1l8mdjpfpgwqdss2ywjkb8b4h55wf8v6kmyxdlvy04ds2hj16sb1"))))
9670 (build-system r-build-system)
9672 `(("r-biobase" ,r-biobase)
9673 ("r-biocgenerics" ,r-biocgenerics)
9674 ("r-genomicranges" ,r-genomicranges)
9675 ("r-iranges" ,r-iranges)
9676 ("r-s4vectors" ,r-s4vectors)))
9677 (home-page "http://www.bioinf.jku.at/software/fastseg/index.html")
9678 (synopsis "Fast segmentation algorithm for genetic sequencing data")
9680 "Fastseg implements a very fast and efficient segmentation algorithm.
9681 It can segment data from DNA microarrays and data from next generation
9682 sequencing for example to detect copy number segments. Further it can segment
9683 data from RNA microarrays like tiling arrays to identify transcripts. Most
9684 generally, it can segment data given as a matrix or as a vector. Various data
9685 formats can be used as input to fastseg like expression set objects for
9686 microarrays or GRanges for sequencing data.")
9687 (license license:lgpl2.0+)))
9689 (define-public r-keggrest
9696 (uri (bioconductor-uri "KEGGREST" version))
9699 "0blpd5a7whd2sswfhqd17h58hg06ymaf80gapdr9ja43hnnlj309"))))
9700 (properties `((upstream-name . "KEGGREST")))
9701 (build-system r-build-system)
9703 `(("r-biostrings" ,r-biostrings)
9706 (home-page "https://bioconductor.org/packages/KEGGREST")
9707 (synopsis "Client-side REST access to KEGG")
9709 "This package provides a package that provides a client interface to the
9710 @dfn{Kyoto Encyclopedia of Genes and Genomes} (KEGG) REST server.")
9711 (license license:artistic2.0)))
9713 (define-public r-gage
9720 (uri (bioconductor-uri "gage" version))
9723 "02g796sb1800ff0f1mq9f2m5wwzpf8pnfzajs49i68dhq2hm01a8"))))
9724 (build-system r-build-system)
9726 `(("r-annotationdbi" ,r-annotationdbi)
9727 ("r-graph" ,r-graph)
9728 ("r-keggrest" ,r-keggrest)))
9729 (home-page "http://www.biomedcentral.com/1471-2105/10/161")
9730 (synopsis "Generally applicable gene-set enrichment for pathway analysis")
9732 "GAGE is a published method for gene set (enrichment or GSEA) or pathway
9733 analysis. GAGE is generally applicable independent of microarray or RNA-Seq
9734 data attributes including sample sizes, experimental designs, assay platforms,
9735 and other types of heterogeneity. The gage package provides functions for
9736 basic GAGE analysis, result processing and presentation. In addition, it
9737 provides demo microarray data and commonly used gene set data based on KEGG
9738 pathways and GO terms. These funtions and data are also useful for gene set
9739 analysis using other methods.")
9740 (license license:gpl2+)))
9742 (define-public r-genomicfiles
9744 (name "r-genomicfiles")
9749 (uri (bioconductor-uri "GenomicFiles" version))
9752 "0qf2yj4lfnnk64fk125n8sqms01shfqiik04nasx2z3k129ykpxp"))))
9753 (properties `((upstream-name . "GenomicFiles")))
9754 (build-system r-build-system)
9756 `(("r-biocgenerics" ,r-biocgenerics)
9757 ("r-biocparallel" ,r-biocparallel)
9758 ("r-genomeinfodb" ,r-genomeinfodb)
9759 ("r-genomicalignments" ,r-genomicalignments)
9760 ("r-genomicranges" ,r-genomicranges)
9761 ("r-iranges" ,r-iranges)
9762 ("r-rsamtools" ,r-rsamtools)
9763 ("r-rtracklayer" ,r-rtracklayer)
9764 ("r-s4vectors" ,r-s4vectors)
9765 ("r-summarizedexperiment" ,r-summarizedexperiment)
9766 ("r-variantannotation" ,r-variantannotation)))
9767 (home-page "https://bioconductor.org/packages/GenomicFiles")
9768 (synopsis "Distributed computing by file or by range")
9770 "This package provides infrastructure for parallel computations
9771 distributed by file or by range. User defined mapper and reducer functions
9772 provide added flexibility for data combination and manipulation.")
9773 (license license:artistic2.0)))
9775 (define-public r-complexheatmap
9777 (name "r-complexheatmap")
9782 (uri (bioconductor-uri "ComplexHeatmap" version))
9785 "0s01dzcfj1lmpqfpsbqw7r4858krfzy499lz4cwx4fq3mbyvy2aj"))))
9787 `((upstream-name . "ComplexHeatmap")))
9788 (build-system r-build-system)
9790 `(("r-circlize" ,r-circlize)
9791 ("r-colorspace" ,r-colorspace)
9792 ("r-getoptlong" ,r-getoptlong)
9793 ("r-globaloptions" ,r-globaloptions)
9794 ("r-rcolorbrewer" ,r-rcolorbrewer)))
9796 "https://github.com/jokergoo/ComplexHeatmap")
9797 (synopsis "Making Complex Heatmaps")
9799 "Complex heatmaps are efficient to visualize associations between
9800 different sources of data sets and reveal potential structures. This package
9801 provides a highly flexible way to arrange multiple heatmaps and supports
9802 self-defined annotation graphics.")
9803 (license license:gpl2+)))
9805 (define-public r-dirichletmultinomial
9807 (name "r-dirichletmultinomial")
9812 (uri (bioconductor-uri "DirichletMultinomial" version))
9815 "0vazfjzqy78p5g7dnv30lbqbj4bhq4zafd2wh6gdwy2il1fd78xa"))))
9817 `((upstream-name . "DirichletMultinomial")))
9818 (build-system r-build-system)
9822 `(("r-biocgenerics" ,r-biocgenerics)
9823 ("r-iranges" ,r-iranges)
9824 ("r-s4vectors" ,r-s4vectors)))
9825 (home-page "https://bioconductor.org/packages/DirichletMultinomial")
9826 (synopsis "Dirichlet-Multinomial mixture models for microbiome data")
9828 "Dirichlet-multinomial mixture models can be used to describe variability
9829 in microbial metagenomic data. This package is an interface to code
9830 originally made available by Holmes, Harris, and Quince, 2012, PLoS ONE 7(2):
9832 (license license:lgpl3)))
9834 (define-public r-ensembldb
9836 (name "r-ensembldb")
9841 (uri (bioconductor-uri "ensembldb" version))
9844 "0gijx2l2y00h6gfj3gfr7rd4vva6qf2vkfdfy5gdmvqlxy84ka38"))))
9845 (build-system r-build-system)
9847 `(("r-annotationdbi" ,r-annotationdbi)
9848 ("r-annotationfilter" ,r-annotationfilter)
9849 ("r-biobase" ,r-biobase)
9850 ("r-biocgenerics" ,r-biocgenerics)
9851 ("r-biostrings" ,r-biostrings)
9854 ("r-genomeinfodb" ,r-genomeinfodb)
9855 ("r-genomicfeatures" ,r-genomicfeatures)
9856 ("r-genomicranges" ,r-genomicranges)
9857 ("r-iranges" ,r-iranges)
9858 ("r-protgenerics" ,r-protgenerics)
9859 ("r-rsamtools" ,r-rsamtools)
9860 ("r-rsqlite" ,r-rsqlite)
9861 ("r-rtracklayer" ,r-rtracklayer)
9862 ("r-s4vectors" ,r-s4vectors)))
9863 (home-page "https://github.com/jotsetung/ensembldb")
9864 (synopsis "Utilities to create and use Ensembl-based annotation databases")
9866 "The package provides functions to create and use transcript-centric
9867 annotation databases/packages. The annotation for the databases are directly
9868 fetched from Ensembl using their Perl API. The functionality and data is
9869 similar to that of the TxDb packages from the @code{GenomicFeatures} package,
9870 but, in addition to retrieve all gene/transcript models and annotations from
9871 the database, the @code{ensembldb} package also provides a filter framework
9872 allowing to retrieve annotations for specific entries like genes encoded on a
9873 chromosome region or transcript models of lincRNA genes.")
9874 ;; No version specified
9875 (license license:lgpl3+)))
9877 (define-public r-organismdbi
9879 (name "r-organismdbi")
9884 (uri (bioconductor-uri "OrganismDbi" version))
9887 "11pyv56cy4iy095h40k6k0mpjdlh6gsb4ld3s57nfa9nd4ypx3yi"))))
9888 (properties `((upstream-name . "OrganismDbi")))
9889 (build-system r-build-system)
9891 `(("r-annotationdbi" ,r-annotationdbi)
9892 ("r-biobase" ,r-biobase)
9893 ("r-biocgenerics" ,r-biocgenerics)
9894 ("r-biocmanager" ,r-biocmanager)
9896 ("r-genomicfeatures" ,r-genomicfeatures)
9897 ("r-genomicranges" ,r-genomicranges)
9898 ("r-graph" ,r-graph)
9899 ("r-iranges" ,r-iranges)
9901 ("r-s4vectors" ,r-s4vectors)))
9902 (home-page "https://bioconductor.org/packages/OrganismDbi")
9903 (synopsis "Software to enable the smooth interfacing of database packages")
9904 (description "The package enables a simple unified interface to several
9905 annotation packages each of which has its own schema by taking advantage of
9906 the fact that each of these packages implements a select methods.")
9907 (license license:artistic2.0)))
9909 (define-public r-biovizbase
9911 (name "r-biovizbase")
9916 (uri (bioconductor-uri "biovizBase" version))
9919 "0v5gvcx180qn5487i1dph9abadw3ggqwp5yzy41jswzbdc8q6sbm"))))
9920 (properties `((upstream-name . "biovizBase")))
9921 (build-system r-build-system)
9923 `(("r-annotationdbi" ,r-annotationdbi)
9924 ("r-annotationfilter" ,r-annotationfilter)
9925 ("r-biocgenerics" ,r-biocgenerics)
9926 ("r-biostrings" ,r-biostrings)
9927 ("r-dichromat" ,r-dichromat)
9928 ("r-ensembldb" ,r-ensembldb)
9929 ("r-genomeinfodb" ,r-genomeinfodb)
9930 ("r-genomicalignments" ,r-genomicalignments)
9931 ("r-genomicfeatures" ,r-genomicfeatures)
9932 ("r-genomicranges" ,r-genomicranges)
9933 ("r-hmisc" ,r-hmisc)
9934 ("r-iranges" ,r-iranges)
9935 ("r-rcolorbrewer" ,r-rcolorbrewer)
9936 ("r-rlang" ,r-rlang)
9937 ("r-rsamtools" ,r-rsamtools)
9938 ("r-s4vectors" ,r-s4vectors)
9939 ("r-scales" ,r-scales)
9940 ("r-summarizedexperiment" ,r-summarizedexperiment)
9941 ("r-variantannotation" ,r-variantannotation)))
9942 (home-page "https://bioconductor.org/packages/biovizBase")
9943 (synopsis "Basic graphic utilities for visualization of genomic data")
9945 "The biovizBase package is designed to provide a set of utilities, color
9946 schemes and conventions for genomic data. It serves as the base for various
9947 high-level packages for biological data visualization. This saves development
9948 effort and encourages consistency.")
9949 (license license:artistic2.0)))
9951 (define-public r-ggbio
9958 (uri (bioconductor-uri "ggbio" version))
9961 "0wq49qqzkcn8s19xgaxf2s1j1a563d7pbhhvris6fhxfdjsz4934"))))
9962 (build-system r-build-system)
9965 (modify-phases %standard-phases
9966 ;; See https://github.com/tengfei/ggbio/issues/117
9967 ;; This fix will be included in the next release.
9968 (add-after 'unpack 'fix-typo
9970 (substitute* "R/GGbio-class.R"
9971 (("fechable") "fetchable"))
9974 `(("r-annotationdbi" ,r-annotationdbi)
9975 ("r-annotationfilter" ,r-annotationfilter)
9976 ("r-biobase" ,r-biobase)
9977 ("r-biocgenerics" ,r-biocgenerics)
9978 ("r-biostrings" ,r-biostrings)
9979 ("r-biovizbase" ,r-biovizbase)
9980 ("r-bsgenome" ,r-bsgenome)
9981 ("r-ensembldb" ,r-ensembldb)
9982 ("r-genomeinfodb" ,r-genomeinfodb)
9983 ("r-genomicalignments" ,r-genomicalignments)
9984 ("r-genomicfeatures" ,r-genomicfeatures)
9985 ("r-genomicranges" ,r-genomicranges)
9986 ("r-ggally" ,r-ggally)
9987 ("r-ggplot2" ,r-ggplot2)
9988 ("r-gridextra" ,r-gridextra)
9989 ("r-gtable" ,r-gtable)
9990 ("r-hmisc" ,r-hmisc)
9991 ("r-iranges" ,r-iranges)
9992 ("r-organismdbi" ,r-organismdbi)
9993 ("r-reshape2" ,r-reshape2)
9994 ("r-rlang" ,r-rlang)
9995 ("r-rsamtools" ,r-rsamtools)
9996 ("r-rtracklayer" ,r-rtracklayer)
9997 ("r-s4vectors" ,r-s4vectors)
9998 ("r-scales" ,r-scales)
9999 ("r-summarizedexperiment" ,r-summarizedexperiment)
10000 ("r-variantannotation" ,r-variantannotation)))
10001 (home-page "http://www.tengfei.name/ggbio/")
10002 (synopsis "Visualization tools for genomic data")
10004 "The ggbio package extends and specializes the grammar of graphics for
10005 biological data. The graphics are designed to answer common scientific
10006 questions, in particular those often asked of high throughput genomics data.
10007 All core Bioconductor data structures are supported, where appropriate. The
10008 package supports detailed views of particular genomic regions, as well as
10009 genome-wide overviews. Supported overviews include ideograms and grand linear
10010 views. High-level plots include sequence fragment length, edge-linked
10011 interval to data view, mismatch pileup, and several splicing summaries.")
10012 (license license:artistic2.0)))
10014 (define-public r-gprofiler
10016 (name "r-gprofiler")
10021 (uri (cran-uri "gProfileR" version))
10024 "12nwidbnqmnfy5dnqga26byslvdnkrpz2fi19qfcby6xx0wbndk7"))))
10025 (properties `((upstream-name . "gProfileR")))
10026 (build-system r-build-system)
10028 `(("r-plyr" ,r-plyr)
10029 ("r-rcurl" ,r-rcurl)))
10030 (home-page "https://cran.r-project.org/web/packages/gProfileR/")
10031 (synopsis "Interface to the g:Profiler toolkit")
10033 "This package provides tools for functional enrichment analysis,
10034 gene identifier conversion and mapping homologous genes across related
10035 organisms via the @code{g:Profiler} toolkit.")
10036 (license license:gpl2+)))
10038 (define-public r-gqtlbase
10040 (name "r-gqtlbase")
10045 (uri (bioconductor-uri "gQTLBase" version))
10048 "1lbk1m1mkvbk30flk5pf3pcrnm2s0sj5r48kbjgad39dsvd8zgqx"))))
10049 (properties `((upstream-name . "gQTLBase")))
10050 (build-system r-build-system)
10052 `(("r-batchjobs" ,r-batchjobs)
10053 ("r-bbmisc" ,r-bbmisc)
10054 ("r-biocgenerics" ,r-biocgenerics)
10056 ("r-doparallel" ,r-doparallel)
10058 ("r-ffbase" ,r-ffbase)
10059 ("r-foreach" ,r-foreach)
10060 ("r-genomicfiles" ,r-genomicfiles)
10061 ("r-genomicranges" ,r-genomicranges)
10062 ("r-rtracklayer" ,r-rtracklayer)
10063 ("r-s4vectors" ,r-s4vectors)
10064 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10065 (home-page "https://bioconductor.org/packages/gQTLBase")
10066 (synopsis "Infrastructure for eQTL, mQTL and similar studies")
10068 "The purpose of this package is to simplify the storage and interrogation
10069 of @dfn{quantitative trait loci} (QTL) archives, such as eQTL, mQTL, dsQTL,
10071 (license license:artistic2.0)))
10073 (define-public r-snpstats
10075 (name "r-snpstats")
10080 (uri (bioconductor-uri "snpStats" version))
10083 "1pplx4pf9bqi7v5v1l74yknc1s61carvbqkf327ky7vbvp0bck33"))))
10084 (properties `((upstream-name . "snpStats")))
10085 (build-system r-build-system)
10086 (inputs `(("zlib" ,zlib)))
10088 `(("r-biocgenerics" ,r-biocgenerics)
10089 ("r-matrix" ,r-matrix)
10090 ("r-survival" ,r-survival)
10091 ("r-zlibbioc" ,r-zlibbioc)))
10092 (home-page "https://bioconductor.org/packages/snpStats")
10093 (synopsis "Methods for SNP association studies")
10095 "This package provides classes and statistical methods for large
10096 @dfn{single-nucleotide polymorphism} (SNP) association studies. This extends
10097 the earlier snpMatrix package, allowing for uncertainty in genotypes.")
10098 (license license:gpl3)))
10100 (define-public r-homo-sapiens
10102 (name "r-homo-sapiens")
10106 ;; We cannot use bioconductor-uri here because this tarball is
10107 ;; located under "data/annotation/" instead of "bioc/".
10108 (uri (string-append "http://www.bioconductor.org/packages/"
10109 "release/data/annotation/src/contrib/"
10111 version ".tar.gz"))
10114 "151vj7h5p1c8yd5swrchk46z469p135wk50hvkl0nhgndvy0jj01"))))
10116 `((upstream-name . "Homo.sapiens")))
10117 (build-system r-build-system)
10119 `(("r-genomicfeatures" ,r-genomicfeatures)
10120 ("r-go-db" ,r-go-db)
10121 ("r-org-hs-eg-db" ,r-org-hs-eg-db)
10122 ("r-txdb-hsapiens-ucsc-hg19-knowngene" ,r-txdb-hsapiens-ucsc-hg19-knowngene)
10123 ("r-organismdbi" ,r-organismdbi)
10124 ("r-annotationdbi" ,r-annotationdbi)))
10125 (home-page "https://bioconductor.org/packages/Homo.sapiens/")
10126 (synopsis "Annotation package for the Homo.sapiens object")
10128 "This package contains the Homo.sapiens object to access data from
10129 several related annotation packages.")
10130 (license license:artistic2.0)))
10132 (define-public r-erma
10139 (uri (bioconductor-uri "erma" version))
10142 "0hj9iz904rr1y66442lkxjywkw1ydyxxlhmjirawbf09ic5ad4g9"))))
10143 (build-system r-build-system)
10145 `(("r-annotationdbi" ,r-annotationdbi)
10146 ("r-biobase" ,r-biobase)
10147 ("r-biocgenerics" ,r-biocgenerics)
10148 ("r-biocparallel" ,r-biocparallel)
10149 ("r-genomeinfodb" ,r-genomeinfodb)
10150 ("r-genomicfiles" ,r-genomicfiles)
10151 ("r-genomicranges" ,r-genomicranges)
10152 ("r-ggplot2" ,r-ggplot2)
10153 ("r-homo-sapiens" ,r-homo-sapiens)
10154 ("r-iranges" ,r-iranges)
10155 ("r-rtracklayer" ,r-rtracklayer)
10156 ("r-s4vectors" ,r-s4vectors)
10157 ("r-shiny" ,r-shiny)
10158 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10159 (home-page "https://bioconductor.org/packages/erma")
10160 (synopsis "Epigenomic road map adventures")
10162 "The epigenomics road map describes locations of epigenetic marks in DNA
10163 from a variety of cell types. Of interest are locations of histone
10164 modifications, sites of DNA methylation, and regions of accessible chromatin.
10165 This package presents a selection of elements of the road map including
10166 metadata and outputs of the ChromImpute procedure applied to ENCODE cell lines
10167 by Ernst and Kellis.")
10168 (license license:artistic2.0)))
10170 (define-public r-ldblock
10177 (uri (bioconductor-uri "ldblock" version))
10180 "01lf74pby7si2g3kgc10qzr6lkcbigqcgqs2j3anc38vzxv0zhwv"))))
10181 (build-system r-build-system)
10183 `(("r-biocgenerics" ,r-biocgenerics)
10185 ("r-genomeinfodb" ,r-genomeinfodb)
10186 ("r-genomicfiles" ,r-genomicfiles)
10187 ("r-go-db" ,r-go-db)
10188 ("r-homo-sapiens" ,r-homo-sapiens)
10189 ("r-matrix" ,r-matrix)
10190 ("r-rsamtools" ,r-rsamtools)
10191 ("r-snpstats" ,r-snpstats)
10192 ("r-variantannotation" ,r-variantannotation)))
10193 (home-page "https://bioconductor.org/packages/ldblock")
10194 (synopsis "Data structures for linkage disequilibrium measures in populations")
10196 "This package defines data structures for @dfn{linkage
10197 disequilibrium} (LD) measures in populations. Its purpose is to simplify
10198 handling of existing population-level data for the purpose of flexibly
10199 defining LD blocks.")
10200 (license license:artistic2.0)))
10202 (define-public r-gqtlstats
10204 (name "r-gqtlstats")
10209 (uri (bioconductor-uri "gQTLstats" version))
10212 "1rkbnb3h02fdksc4nacqvmq4jgbj9fz4hm7j51yr2ggcgcykwraa"))))
10213 (properties `((upstream-name . "gQTLstats")))
10214 (build-system r-build-system)
10216 `(("r-annotationdbi" ,r-annotationdbi)
10217 ("r-batchjobs" ,r-batchjobs)
10218 ("r-bbmisc" ,r-bbmisc)
10219 ("r-beeswarm" ,r-beeswarm)
10220 ("r-biobase" ,r-biobase)
10221 ("r-biocgenerics" ,r-biocgenerics)
10222 ("r-doparallel" ,r-doparallel)
10223 ("r-dplyr" ,r-dplyr)
10225 ("r-ffbase" ,r-ffbase)
10226 ("r-foreach" ,r-foreach)
10227 ("r-genomeinfodb" ,r-genomeinfodb)
10228 ("r-genomicfeatures" ,r-genomicfeatures)
10229 ("r-genomicfiles" ,r-genomicfiles)
10230 ("r-genomicranges" ,r-genomicranges)
10231 ("r-ggbeeswarm" ,r-ggbeeswarm)
10232 ("r-ggplot2" ,r-ggplot2)
10233 ("r-gqtlbase" ,r-gqtlbase)
10234 ("r-hardyweinberg" ,r-hardyweinberg)
10235 ("r-homo-sapiens" ,r-homo-sapiens)
10236 ("r-iranges" ,r-iranges)
10237 ("r-limma" ,r-limma)
10239 ("r-plotly" ,r-plotly)
10240 ("r-reshape2" ,r-reshape2)
10241 ("r-s4vectors" ,r-s4vectors)
10242 ("r-shiny" ,r-shiny)
10243 ("r-snpstats" ,r-snpstats)
10244 ("r-summarizedexperiment" ,r-summarizedexperiment)
10245 ("r-variantannotation" ,r-variantannotation)))
10246 (home-page "https://bioconductor.org/packages/gQTLstats")
10247 (synopsis "Computationally efficient analysis for eQTL and allied studies")
10249 "This package provides tools for the computationally efficient analysis
10250 of @dfn{quantitative trait loci} (QTL) data, including eQTL, mQTL, dsQTL, etc.
10251 The software in this package aims to support refinements and functional
10252 interpretation of members of a collection of association statistics on a
10253 family of feature/genome hypotheses.")
10254 (license license:artistic2.0)))
10256 (define-public r-gviz
10263 (uri (bioconductor-uri "Gviz" version))
10266 "1dpkcaar7qgzg3vgafvkplprhwmhzpb7ph009kr6ajm36hx4z81c"))))
10267 (properties `((upstream-name . "Gviz")))
10268 (build-system r-build-system)
10270 `(("r-annotationdbi" ,r-annotationdbi)
10271 ("r-biobase" ,r-biobase)
10272 ("r-biocgenerics" ,r-biocgenerics)
10273 ("r-biomart" ,r-biomart)
10274 ("r-biostrings" ,r-biostrings)
10275 ("r-biovizbase" ,r-biovizbase)
10276 ("r-bsgenome" ,r-bsgenome)
10277 ("r-digest" ,r-digest)
10278 ("r-genomeinfodb" ,r-genomeinfodb)
10279 ("r-genomicalignments" ,r-genomicalignments)
10280 ("r-genomicfeatures" ,r-genomicfeatures)
10281 ("r-genomicranges" ,r-genomicranges)
10282 ("r-iranges" ,r-iranges)
10283 ("r-lattice" ,r-lattice)
10284 ("r-latticeextra" ,r-latticeextra)
10285 ("r-matrixstats" ,r-matrixstats)
10286 ("r-rcolorbrewer" ,r-rcolorbrewer)
10287 ("r-rsamtools" ,r-rsamtools)
10288 ("r-rtracklayer" ,r-rtracklayer)
10289 ("r-s4vectors" ,r-s4vectors)
10290 ("r-xvector" ,r-xvector)))
10291 (home-page "https://bioconductor.org/packages/Gviz")
10292 (synopsis "Plotting data and annotation information along genomic coordinates")
10294 "Genomic data analyses requires integrated visualization of known genomic
10295 information and new experimental data. Gviz uses the biomaRt and the
10296 rtracklayer packages to perform live annotation queries to Ensembl and UCSC
10297 and translates this to e.g. gene/transcript structures in viewports of the
10298 grid graphics package. This results in genomic information plotted together
10300 (license license:artistic2.0)))
10302 (define-public r-gwascat
10309 (uri (bioconductor-uri "gwascat" version))
10312 "1fnyjydhicq4ayrv0lqjv48h9bd72h40s6l82g1h2ng0icwz38g0"))))
10313 (build-system r-build-system)
10315 `(("r-annotationdbi" ,r-annotationdbi)
10316 ("r-annotationhub" ,r-annotationhub)
10317 ("r-biocgenerics" ,r-biocgenerics)
10318 ("r-biostrings" ,r-biostrings)
10319 ("r-genomeinfodb" ,r-genomeinfodb)
10320 ("r-genomicfeatures" ,r-genomicfeatures)
10321 ("r-genomicranges" ,r-genomicranges)
10322 ("r-ggbio" ,r-ggbio)
10323 ("r-ggplot2" ,r-ggplot2)
10324 ("r-gqtlstats" ,r-gqtlstats)
10325 ("r-graph" ,r-graph)
10327 ("r-homo-sapiens" ,r-homo-sapiens)
10328 ("r-iranges" ,r-iranges)
10329 ("r-rsamtools" ,r-rsamtools)
10330 ("r-rtracklayer" ,r-rtracklayer)
10331 ("r-s4vectors" ,r-s4vectors)
10332 ("r-snpstats" ,r-snpstats)
10333 ("r-summarizedexperiment" ,r-summarizedexperiment)
10334 ("r-variantannotation" ,r-variantannotation)))
10335 (home-page "https://bioconductor.org/packages/gwascat")
10336 (synopsis "Tools for data in the EMBL-EBI GWAS catalog")
10338 "This package provides tools for representing and modeling data in the
10339 EMBL-EBI GWAS catalog.")
10340 (license license:artistic2.0)))
10342 (define-public r-sushi
10348 (uri (bioconductor-uri "Sushi" version))
10351 "1hgh3jfcx0bh3fyvp85v7435hvsk3ah1hxx5117ss93v03iwjf1g"))))
10352 (properties `((upstream-name . "Sushi")))
10353 (build-system r-build-system)
10355 `(("r-biomart" ,r-biomart)
10357 (home-page "https://bioconductor.org/packages/Sushi")
10358 (synopsis "Tools for visualizing genomics data")
10360 "This package provides flexible, quantitative, and integrative genomic
10361 visualizations for publication-quality multi-panel figures.")
10362 (license license:gpl2+)))
10364 (define-public r-fithic
10370 (uri (bioconductor-uri "FitHiC" version))
10373 "1qrxy4v8vmykrk8y6g3bs5wh5xhbs6pxyydbxy3vnj2mjirnxr6d"))))
10374 (properties `((upstream-name . "FitHiC")))
10375 (build-system r-build-system)
10377 `(("r-data-table" ,r-data-table)
10378 ("r-fdrtool" ,r-fdrtool)
10379 ("r-rcpp" ,r-rcpp)))
10380 (home-page "https://bioconductor.org/packages/FitHiC")
10381 (synopsis "Confidence estimation for intra-chromosomal contact maps")
10383 "Fit-Hi-C is a tool for assigning statistical confidence estimates to
10384 intra-chromosomal contact maps produced by genome-wide genome architecture
10385 assays such as Hi-C.")
10386 (license license:gpl2+)))
10388 (define-public r-hitc
10394 (uri (bioconductor-uri "HiTC" version))
10397 "059a1xxv2kb0bb32flymg2s8ylhavnv3j8l4125rfidagcgxgzjq"))))
10398 (properties `((upstream-name . "HiTC")))
10399 (build-system r-build-system)
10401 `(("r-biostrings" ,r-biostrings)
10402 ("r-genomeinfodb" ,r-genomeinfodb)
10403 ("r-genomicranges" ,r-genomicranges)
10404 ("r-iranges" ,r-iranges)
10405 ("r-matrix" ,r-matrix)
10406 ("r-rcolorbrewer" ,r-rcolorbrewer)
10407 ("r-rtracklayer" ,r-rtracklayer)))
10408 (home-page "https://bioconductor.org/packages/HiTC")
10409 (synopsis "High throughput chromosome conformation capture analysis")
10411 "The HiTC package was developed to explore high-throughput \"C\" data
10412 such as 5C or Hi-C. Dedicated R classes as well as standard methods for
10413 quality controls, normalization, visualization, and further analysis are also
10415 (license license:artistic2.0)))
10417 (define-public r-hdf5array
10419 (name "r-hdf5array")
10424 (uri (bioconductor-uri "HDF5Array" version))
10427 "1ri2iisym4gbzjvihgcnv4dpz34id4691ki904lq26apv2af84cc"))))
10428 (properties `((upstream-name . "HDF5Array")))
10429 (build-system r-build-system)
10433 `(("r-biocgenerics" ,r-biocgenerics)
10434 ("r-delayedarray" ,r-delayedarray)
10435 ("r-iranges" ,r-iranges)
10436 ("r-rhdf5" ,r-rhdf5)
10437 ("r-rhdf5lib" ,r-rhdf5lib)
10438 ("r-s4vectors" ,r-s4vectors)))
10439 (home-page "https://bioconductor.org/packages/HDF5Array")
10440 (synopsis "HDF5 back end for DelayedArray objects")
10441 (description "This package provides an array-like container for convenient
10442 access and manipulation of HDF5 datasets. It supports delayed operations and
10443 block processing.")
10444 (license license:artistic2.0)))
10446 (define-public r-rhdf5lib
10448 (name "r-rhdf5lib")
10453 (uri (bioconductor-uri "Rhdf5lib" version))
10456 "1lpmyxlwwcy92hyxqag321ssc5z6yw3a0ws9r058jwgzyjg7i2gm"))
10457 (modules '((guix build utils)))
10460 ;; Delete bundled binaries
10461 (delete-file-recursively "src/winlib/")
10463 (properties `((upstream-name . "Rhdf5lib")))
10464 (build-system r-build-system)
10467 (modify-phases %standard-phases
10468 (add-after 'unpack 'do-not-use-bundled-hdf5
10469 (lambda* (#:key inputs #:allow-other-keys)
10470 (for-each delete-file '("configure" "configure.ac"))
10471 ;; Do not make other packages link with the proprietary libsz.
10472 (substitute* "R/zzz.R"
10473 (("'%s/libhdf5_cpp.a %s/libhdf5.a %s/libsz.a -lz'")
10474 "'%s/libhdf5_cpp.a %s/libhdf5.a %s/libhdf5.a -lz'")
10475 (("'%s/libhdf5.a %s/libsz.a -lz'")
10476 "'%s/libhdf5.a %s/libhdf5.a -lz'"))
10477 (with-directory-excursion "src"
10478 (invoke "tar" "xvf" (assoc-ref inputs "hdf5-source"))
10479 (rename-file (string-append "hdf5-" ,(package-version hdf5-1.10))
10481 ;; Remove timestamp and host system information to make
10482 ;; the build reproducible.
10483 (substitute* "hdf5/src/libhdf5.settings.in"
10484 (("Configured on: @CONFIG_DATE@")
10485 "Configured on: Guix")
10486 (("Uname information:.*")
10487 "Uname information: Linux\n")
10488 ;; Remove unnecessary store reference.
10490 "C Compiler: GCC\n"))
10491 (rename-file "Makevars.in" "Makevars")
10492 (substitute* "Makevars"
10493 (("HDF5_CXX_LIB=.*")
10494 (string-append "HDF5_CXX_LIB="
10495 (assoc-ref inputs "hdf5") "/lib/libhdf5_cpp.a\n"))
10497 (string-append "HDF5_LIB="
10498 (assoc-ref inputs "hdf5") "/lib/libhdf5.a\n"))
10499 (("HDF5_CXX_INCLUDE=.*") "HDF5_CXX_INCLUDE=./hdf5/c++/src\n")
10500 (("HDF5_INCLUDE=.*") "HDF5_INCLUDE=./hdf5/src\n")
10501 ;; szip is non-free software
10502 (("cp \\$\\{SZIP_LIB\\}.*") "")
10503 (("\\$\\{USER_LIB_DIR\\}libsz.a") "")))
10508 `(("hdf5" ,hdf5-1.10)))
10510 `(("hdf5-source" ,(package-source hdf5-1.10))))
10511 (home-page "https://bioconductor.org/packages/Rhdf5lib")
10512 (synopsis "HDF5 library as an R package")
10513 (description "This package provides C and C++ HDF5 libraries for use in R
10515 (license license:artistic2.0)))
10517 (define-public r-beachmat
10519 (name "r-beachmat")
10524 (uri (bioconductor-uri "beachmat" version))
10527 "14cz19fw97s8mhm9r2n5li44vckx069k8nqsyy64c3lkfm4vy4zx"))))
10528 (build-system r-build-system)
10530 `(("r-biocgenerics" ,r-biocgenerics)
10531 ("r-delayedarray" ,r-delayedarray)))
10532 (home-page "https://bioconductor.org/packages/beachmat")
10533 (synopsis "Compiling Bioconductor to handle each matrix type")
10534 (description "This package provides a consistent C++ class interface for a
10535 variety of commonly used matrix types, including sparse and HDF5-backed
10537 (license license:gpl3)))
10539 (define-public r-singlecellexperiment
10541 (name "r-singlecellexperiment")
10546 (uri (bioconductor-uri "SingleCellExperiment" version))
10549 "0m3yjnv1njb4gyzcjfk7a0lz2vgggp2wjz382gqrb0qhhwcgfkj5"))))
10551 `((upstream-name . "SingleCellExperiment")))
10552 (build-system r-build-system)
10554 `(("r-biocgenerics" ,r-biocgenerics)
10555 ("r-s4vectors" ,r-s4vectors)
10556 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10557 (home-page "https://bioconductor.org/packages/SingleCellExperiment")
10558 (synopsis "S4 classes for single cell data")
10559 (description "This package defines an S4 class for storing data from
10560 single-cell experiments. This includes specialized methods to store and
10561 retrieve spike-in information, dimensionality reduction coordinates and size
10562 factors for each cell, along with the usual metadata for genes and
10564 (license license:gpl3)))
10566 (define-public r-scater
10572 (uri (bioconductor-uri "scater" version))
10575 "0qwwkas9va4gsnn1ghg9wznqgr0wq5y3pnf7ym4h6q9qvhky41vk"))))
10576 (build-system r-build-system)
10578 `(("r-beachmat" ,r-beachmat)
10579 ("r-biocgenerics" ,r-biocgenerics)
10580 ("r-biocneighbors" ,r-biocneighbors)
10581 ("r-biocparallel" ,r-biocparallel)
10582 ("r-biocsingular" ,r-biocsingular)
10583 ("r-delayedarray" ,r-delayedarray)
10584 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10585 ("r-dplyr" ,r-dplyr)
10586 ("r-ggbeeswarm" ,r-ggbeeswarm)
10587 ("r-ggplot2" ,r-ggplot2)
10588 ("r-matrix" ,r-matrix)
10590 ("r-s4vectors" ,r-s4vectors)
10591 ("r-singlecellexperiment" ,r-singlecellexperiment)
10592 ("r-summarizedexperiment" ,r-summarizedexperiment)
10593 ("r-viridis" ,r-viridis)))
10594 (home-page "https://github.com/davismcc/scater")
10595 (synopsis "Single-cell analysis toolkit for gene expression data in R")
10596 (description "This package provides a collection of tools for doing
10597 various analyses of single-cell RNA-seq gene expression data, with a focus on
10599 (license license:gpl2+)))
10601 (define-public r-scran
10608 (uri (bioconductor-uri "scran" version))
10611 "19cyjjzgmhswni6js4bhbj5djp976sl9n648kk7viazgkspql884"))))
10612 (build-system r-build-system)
10614 `(("r-beachmat" ,r-beachmat)
10616 ("r-biocgenerics" ,r-biocgenerics)
10617 ("r-biocneighbors" ,r-biocneighbors)
10618 ("r-biocparallel" ,r-biocparallel)
10619 ("r-biocsingular" ,r-biocsingular)
10620 ("r-delayedarray" ,r-delayedarray)
10621 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
10622 ("r-dqrng" ,r-dqrng)
10623 ("r-dynamictreecut" ,r-dynamictreecut)
10624 ("r-edger" ,r-edger)
10625 ("r-igraph" ,r-igraph)
10626 ("r-limma" ,r-limma)
10627 ("r-matrix" ,r-matrix)
10629 ("r-s4vectors" ,r-s4vectors)
10630 ("r-scater" ,r-scater)
10631 ("r-singlecellexperiment" ,r-singlecellexperiment)
10632 ("r-statmod" ,r-statmod)
10633 ("r-summarizedexperiment" ,r-summarizedexperiment)))
10634 (home-page "https://bioconductor.org/packages/scran")
10635 (synopsis "Methods for single-cell RNA-Seq data analysis")
10636 (description "This package implements a variety of low-level analyses of
10637 single-cell RNA-seq data. Methods are provided for normalization of
10638 cell-specific biases, assignment of cell cycle phase, and detection of highly
10639 variable and significantly correlated genes.")
10640 (license license:gpl3)))
10642 (define-public r-delayedmatrixstats
10644 (name "r-delayedmatrixstats")
10649 (uri (bioconductor-uri "DelayedMatrixStats" version))
10652 "0632ypndblrgzfk8k98rr8c6m2r0zwzf02pzvlrhcp9bj1pvqbrz"))))
10654 `((upstream-name . "DelayedMatrixStats")))
10655 (build-system r-build-system)
10657 `(("r-biocparallel" ,r-biocparallel)
10658 ("r-delayedarray" ,r-delayedarray)
10659 ("r-hdf5array" ,r-hdf5array)
10660 ("r-iranges" ,r-iranges)
10661 ("r-matrix" ,r-matrix)
10662 ("r-matrixstats" ,r-matrixstats)
10663 ("r-s4vectors" ,r-s4vectors)))
10664 (home-page "https://github.com/PeteHaitch/DelayedMatrixStats")
10665 (synopsis "Functions that apply to rows and columns of DelayedMatrix objects")
10667 "This package provides a port of the @code{matrixStats} API for use with
10668 @code{DelayedMatrix} objects from the @code{DelayedArray} package. It
10669 contains high-performing functions operating on rows and columns of
10670 @code{DelayedMatrix} objects, e.g. @code{colMedians}, @code{rowMedians},
10671 @code{colRanks}, @code{rowRanks}, @code{colSds}, and @code{rowSds}. Functions
10672 are optimized per data type and for subsetted calculations such that both
10673 memory usage and processing time is minimized.")
10674 (license license:expat)))
10676 (define-public r-phangorn
10678 (name "r-phangorn")
10683 (uri (cran-uri "phangorn" version))
10686 "1bv86yfk5r015s7ij6v4zz7bagwrw9m13yfs5853drxb19d5h1m3"))))
10687 (build-system r-build-system)
10690 ("r-fastmatch" ,r-fastmatch)
10691 ("r-igraph" ,r-igraph)
10692 ("r-magrittr" ,r-magrittr)
10693 ("r-matrix" ,r-matrix)
10694 ("r-quadprog" ,r-quadprog)
10695 ("r-rcpp" ,r-rcpp)))
10696 (home-page "https://github.com/KlausVigo/phangorn")
10697 (synopsis "Phylogenetic analysis in R")
10699 "Phangorn is a package for phylogenetic analysis in R. It supports
10700 estimation of phylogenetic trees and networks using Maximum Likelihood,
10701 Maximum Parsimony, distance methods and Hadamard conjugation.")
10702 (license license:gpl2+)))
10704 (define-public r-dropbead
10705 (let ((commit "d746c6f3b32110428ea56d6a0001ce52a251c247")
10708 (name "r-dropbead")
10709 (version (string-append "0-" revision "." (string-take commit 7)))
10713 (uri (git-reference
10714 (url "https://github.com/rajewsky-lab/dropbead.git")
10716 (file-name (git-file-name name version))
10719 "0sbzma49aiiyw8b0jpr7fnhzys9nsqmp4hy4hdz1gzyg1lhnca26"))))
10720 (build-system r-build-system)
10722 `(("r-ggplot2" ,r-ggplot2)
10723 ("r-rcolorbrewer" ,r-rcolorbrewer)
10724 ("r-gridextra" ,r-gridextra)
10725 ("r-gplots" ,r-gplots)
10726 ("r-plyr" ,r-plyr)))
10727 (home-page "https://github.com/rajewsky-lab/dropbead")
10728 (synopsis "Basic exploration and analysis of Drop-seq data")
10729 (description "This package offers a quick and straight-forward way to
10730 explore and perform basic analysis of single cell sequencing data coming from
10731 droplet sequencing. It has been particularly tailored for Drop-seq.")
10732 (license license:gpl3))))
10734 (define htslib-for-sambamba
10735 (let ((commit "2f3c3ea7b301f9b45737a793c0b2dcf0240e5ee5"))
10738 (name "htslib-for-sambamba")
10739 (version (string-append "1.3.1-1." (string-take commit 9)))
10743 (uri (git-reference
10744 (url "https://github.com/lomereiter/htslib.git")
10746 (file-name (string-append "htslib-" version "-checkout"))
10749 "0g38g8s3npr0gjm9fahlbhiskyfws9l5i0x1ml3rakzj7az5l9c9"))))
10751 `(("autoconf" ,autoconf)
10752 ("automake" ,automake)
10753 ,@(package-native-inputs htslib))))))
10755 (define-public sambamba
10762 (uri (git-reference
10763 (url "https://github.com/lomereiter/sambamba.git")
10764 (commit (string-append "v" version))))
10765 (file-name (string-append name "-" version "-checkout"))
10768 "0k0cz3qcv98p6cq09zlbgnjsggxcqbcmzxg5zikgcgbr2nfq4lry"))))
10769 (build-system gnu-build-system)
10771 `(#:tests? #f ; there is no test target
10772 #:parallel-build? #f ; not supported
10774 (modify-phases %standard-phases
10775 (delete 'configure)
10776 (add-after 'unpack 'fix-ldc-version
10778 (substitute* "gen_ldc_version_info.py"
10779 (("/usr/bin/env.*") (which "python3")))
10780 (substitute* "Makefile"
10781 ;; We use ldc2 instead of ldmd2 to compile sambamba.
10782 (("\\$\\(shell which ldmd2\\)") (which "ldc2")))
10784 (add-after 'unpack 'place-biod-and-undead
10785 (lambda* (#:key inputs #:allow-other-keys)
10786 (copy-recursively (assoc-ref inputs "biod") "BioD")
10787 (copy-recursively (assoc-ref inputs "undead") "undeaD")
10789 (add-after 'unpack 'unbundle-prerequisites
10791 (substitute* "Makefile"
10792 (("htslib/libhts.a lz4/lib/liblz4.a")
10794 ((" lz4-static htslib-static") ""))
10797 (lambda* (#:key outputs #:allow-other-keys)
10798 (let* ((out (assoc-ref outputs "out"))
10799 (bin (string-append out "/bin")))
10801 (install-file "bin/sambamba" bin)
10808 ,(let ((commit "4f1a7d2fb7ef3dfe962aa357d672f354ebfbe42e"))
10811 (uri (git-reference
10812 (url "https://github.com/biod/BioD.git")
10814 (file-name (string-append "biod-"
10815 (string-take commit 9)
10819 "1k5pdjv1qvi0a3rwd1sfq6zbj37l86i7bf710m4c0y6737lxj426")))))
10821 ,(let ((commit "9be93876982b5f14fcca60832563b3cd767dd84d"))
10824 (uri (git-reference
10825 (url "https://github.com/biod/undeaD.git")
10827 (file-name (string-append "undead-"
10828 (string-take commit 9)
10832 "1xfarj0nqlmi5jd1vmcmm7pabzaf9hxyvk6hp0d6jslb5k9r8r3d")))))))
10835 ("htslib" ,htslib-for-sambamba)))
10836 (home-page "http://lomereiter.github.io/sambamba")
10837 (synopsis "Tools for working with SAM/BAM data")
10838 (description "Sambamba is a high performance modern robust and
10839 fast tool (and library), written in the D programming language, for
10840 working with SAM and BAM files. Current parallelised functionality is
10841 an important subset of samtools functionality, including view, index,
10842 sort, markdup, and depth.")
10843 (license license:gpl2+)))
10845 (define-public ritornello
10847 (name "ritornello")
10851 (uri (git-reference
10852 (url "https://github.com/KlugerLab/Ritornello.git")
10853 (commit (string-append "v" version))))
10854 (file-name (git-file-name name version))
10857 "1xahvq215qld7x1w8vpa5zbrsj6p9crb9shqa2x89sb0aaxa02jk"))))
10858 (build-system gnu-build-system)
10860 `(#:tests? #f ; there are no tests
10862 (modify-phases %standard-phases
10863 (add-after 'unpack 'patch-samtools-references
10864 (lambda* (#:key inputs #:allow-other-keys)
10865 (substitute* '("src/SamStream.h"
10867 (("<sam.h>") "<samtools/sam.h>"))
10869 (delete 'configure)
10871 (lambda* (#:key inputs outputs #:allow-other-keys)
10872 (let* ((out (assoc-ref outputs "out"))
10873 (bin (string-append out "/bin/")))
10875 (install-file "bin/Ritornello" bin)
10878 `(("samtools" ,samtools-0.1)
10882 (home-page "https://github.com/KlugerLab/Ritornello")
10883 (synopsis "Control-free peak caller for ChIP-seq data")
10884 (description "Ritornello is a ChIP-seq peak calling algorithm based on
10885 signal processing that can accurately call binding events without the need to
10886 do a pair total DNA input or IgG control sample. It has been tested for use
10887 with narrow binding events such as transcription factor ChIP-seq.")
10888 (license license:gpl3+)))
10890 (define-public trim-galore
10892 (name "trim-galore")
10897 (uri (git-reference
10898 (url "https://github.com/FelixKrueger/TrimGalore.git")
10900 (file-name (git-file-name name version))
10903 "1y31wbxwkm9xqzr5zv1pk5q418whnmlmgmfyxxpnl12h83m2i9iv"))))
10904 (build-system gnu-build-system)
10906 `(#:tests? #f ; no tests
10908 (modify-phases %standard-phases
10909 (replace 'configure
10911 ;; Trim Galore tries to figure out what version of Python
10912 ;; cutadapt is using by looking at the shebang. Of course that
10913 ;; doesn't work, because cutadapt is wrapped in a shell script.
10914 (substitute* "trim_galore"
10915 (("my \\$python_return.*")
10916 "my $python_return = \"Python 3.999\";\n"))
10919 (add-after 'unpack 'hardcode-tool-references
10920 (lambda* (#:key inputs #:allow-other-keys)
10921 (substitute* "trim_galore"
10922 (("\\$path_to_cutadapt = 'cutadapt'")
10923 (string-append "$path_to_cutadapt = '"
10924 (assoc-ref inputs "cutadapt")
10926 (("\\$compression_path = \"gzip\"")
10927 (string-append "$compression_path = \""
10928 (assoc-ref inputs "gzip")
10931 (string-append "\""
10932 (assoc-ref inputs "gzip")
10935 (string-append "\""
10936 (assoc-ref inputs "pigz")
10940 (lambda* (#:key outputs #:allow-other-keys)
10941 (let ((bin (string-append (assoc-ref outputs "out")
10944 (install-file "trim_galore" bin)
10950 ("cutadapt" ,cutadapt)))
10952 `(("unzip" ,unzip)))
10953 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/trim_galore/")
10954 (synopsis "Wrapper around Cutadapt and FastQC")
10955 (description "Trim Galore! is a wrapper script to automate quality and
10956 adapter trimming as well as quality control, with some added functionality to
10957 remove biased methylation positions for RRBS sequence files.")
10958 (license license:gpl3+)))
10960 (define-public gess
10966 (uri (string-append "http://compbio.uthscsa.edu/"
10968 "gess-" version ".src.tar.gz"))
10971 "0hyk403kxscclzfs24pvdgiv0wm03kjcziqdrp5w46cb049gz0d7"))))
10972 (build-system gnu-build-system)
10974 `(#:tests? #f ; no tests
10976 (modify-phases %standard-phases
10977 (delete 'configure)
10980 (lambda* (#:key inputs outputs #:allow-other-keys)
10981 (let* ((python (assoc-ref inputs "python"))
10982 (out (assoc-ref outputs "out"))
10983 (bin (string-append out "/bin/"))
10984 (target (string-append
10986 ,(version-major+minor
10987 (package-version python))
10988 "/site-packages/gess/")))
10990 (copy-recursively "." target)
10991 ;; Make GESS.py executable
10992 (chmod (string-append target "GESS.py") #o555)
10993 ;; Add Python shebang to the top and make Matplotlib
10995 (substitute* (string-append target "GESS.py")
10996 (("\"\"\"Description:" line)
10997 (string-append "#!" (which "python") "
10999 matplotlib.use('Agg')
11001 ;; Make sure GESS has all modules in its path
11002 (wrap-program (string-append target "GESS.py")
11003 `("PYTHONPATH" ":" prefix (,target ,(getenv "PYTHONPATH"))))
11005 (symlink (string-append target "GESS.py")
11006 (string-append bin "GESS.py"))
11009 `(("python" ,python-2)
11010 ("python2-pysam" ,python2-pysam)
11011 ("python2-scipy" ,python2-scipy)
11012 ("python2-numpy" ,python2-numpy)
11013 ("python2-networkx" ,python2-networkx)
11014 ("python2-biopython" ,python2-biopython)))
11015 (home-page "http://compbio.uthscsa.edu/GESS_Web/")
11016 (synopsis "Detect exon-skipping events from raw RNA-seq data")
11018 "GESS is an implementation of a novel computational method to detect de
11019 novo exon-skipping events directly from raw RNA-seq data without the prior
11020 knowledge of gene annotation information. GESS stands for the graph-based
11021 exon-skipping scanner detection scheme.")
11022 (license license:bsd-3)))
11024 (define-public phylip
11031 (uri (string-append "http://evolution.gs.washington.edu/phylip/"
11032 "download/phylip-" version ".tar.gz"))
11035 "01jar1rayhr2gba2pgbw49m56rc5z4p5wn3ds0m188hrlln4a2nd"))))
11036 (build-system gnu-build-system)
11038 `(#:tests? #f ; no check target
11039 #:make-flags (list "-f" "Makefile.unx" "install")
11040 #:parallel-build? #f ; not supported
11042 (modify-phases %standard-phases
11043 (add-after 'unpack 'enter-dir
11044 (lambda _ (chdir "src") #t))
11045 (delete 'configure)
11047 (lambda* (#:key inputs outputs #:allow-other-keys)
11048 (let ((target (string-append (assoc-ref outputs "out")
11051 (for-each (lambda (file)
11052 (install-file file target))
11053 (find-files "../exe" ".*")))
11055 (home-page "http://evolution.genetics.washington.edu/phylip/")
11056 (synopsis "Tools for inferring phylogenies")
11057 (description "PHYLIP (the PHYLogeny Inference Package) is a package of
11058 programs for inferring phylogenies (evolutionary trees).")
11059 (license license:bsd-2)))
11068 (uri (string-append "https://integrativemodeling.org/"
11069 version "/download/imp-" version ".tar.gz"))
11072 "0lxqx7vh79d771svr611dkilp6sn30qrbw8zvscbrm37v38d2j6h"))))
11073 (build-system cmake-build-system)
11075 `(;; FIXME: Some tests fail because they produce warnings, others fail
11076 ;; because the PYTHONPATH does not include the modeller's directory.
11084 ("python" ,python-2)))
11086 `(("python2-numpy" ,python2-numpy)
11087 ("python2-scipy" ,python2-scipy)
11088 ("python2-pandas" ,python2-pandas)
11089 ("python2-scikit-learn" ,python2-scikit-learn)
11090 ("python2-networkx" ,python2-networkx)))
11091 (home-page "https://integrativemodeling.org")
11092 (synopsis "Integrative modeling platform")
11093 (description "IMP's broad goal is to contribute to a comprehensive
11094 structural characterization of biomolecules ranging in size and complexity
11095 from small peptides to large macromolecular assemblies, by integrating data
11096 from diverse biochemical and biophysical experiments. IMP provides a C++ and
11097 Python toolbox for solving complex modeling problems, and a number of
11098 applications for tackling some common problems in a user-friendly way.")
11099 ;; IMP is largely available under the GNU Lesser GPL; see the file
11100 ;; COPYING.LGPL for the full text of this license. Some IMP modules are
11101 ;; available under the GNU GPL (see the file COPYING.GPL).
11102 (license (list license:lgpl2.1+
11105 (define-public tadbit
11111 (uri (git-reference
11112 (url "https://github.com/3DGenomes/TADbit.git")
11113 (commit (string-append "v" version))))
11114 (file-name (git-file-name name version))
11117 "07g3aj648prmsvxp9caz5yl41k0y0647vxh0f5p3w8376mfiljd0"))))
11118 (build-system python-build-system)
11120 `(;; Tests are included and must be run after installation, but
11121 ;; they are incomplete and thus cannot be run.
11125 (modify-phases %standard-phases
11126 (add-after 'unpack 'fix-problems-with-setup.py
11127 (lambda* (#:key outputs #:allow-other-keys)
11128 ;; setup.py opens these files for writing
11129 (chmod "_pytadbit/_version.py" #o664)
11130 (chmod "README.rst" #o664)
11132 ;; Don't attempt to install the bash completions to
11133 ;; the home directory.
11134 (rename-file "extras/.bash_completion"
11136 (substitute* "setup.py"
11137 (("\\(path.expanduser\\('~'\\)")
11138 (string-append "(\""
11139 (assoc-ref outputs "out")
11140 "/etc/bash_completion.d\""))
11141 (("extras/\\.bash_completion")
11145 ;; TODO: add Chimera for visualization
11148 ("python2-scipy" ,python2-scipy)
11149 ("python2-numpy" ,python2-numpy)
11150 ("python2-matplotlib" ,python2-matplotlib)
11151 ("python2-pysam" ,python2-pysam)))
11152 (home-page "https://3dgenomes.github.io/TADbit/")
11153 (synopsis "Analyze, model, and explore 3C-based data")
11155 "TADbit is a complete Python library to deal with all steps to analyze,
11156 model, and explore 3C-based data. With TADbit the user can map FASTQ files to
11157 obtain raw interaction binned matrices (Hi-C like matrices), normalize and
11158 correct interaction matrices, identify and compare the so-called
11159 @dfn{Topologically Associating Domains} (TADs), build 3D models from the
11160 interaction matrices, and finally, extract structural properties from the
11161 models. TADbit is complemented by TADkit for visualizing 3D models.")
11162 (license license:gpl3+)))
11164 (define-public kentutils
11167 ;; 302.1.0 is out, but the only difference is the inclusion of
11168 ;; pre-built binaries.
11169 (version "302.0.0")
11173 (uri (git-reference
11174 (url "https://github.com/ENCODE-DCC/kentUtils.git")
11175 (commit (string-append "v" version))))
11176 (file-name (git-file-name name version))
11179 "0n1wbyjpzii2b9qhyp9r1q76j623cggpg3y8fmw78ld3z4y7ivha"))
11180 (modules '((guix build utils)
11185 ;; Only the contents of the specified directories are free
11186 ;; for all uses, so we remove the rest. "hg/autoSql" and
11187 ;; "hg/autoXml" are nominally free, but they depend on a
11188 ;; library that is built from the sources in "hg/lib",
11189 ;; which is nonfree.
11190 (let ((free (list "." ".."
11191 "utils" "lib" "inc" "tagStorm"
11192 "parasol" "htslib"))
11193 (directory? (lambda (file)
11194 (eq? 'directory (stat:type (stat file))))))
11195 (for-each (lambda (file)
11196 (and (directory? file)
11197 (delete-file-recursively file)))
11198 (map (cut string-append "src/" <>)
11201 (not (member file free)))))))
11202 ;; Only make the utils target, not the userApps target,
11203 ;; because that requires libraries we won't build.
11204 (substitute* "Makefile"
11205 ((" userApps") " utils"))
11206 ;; Only build libraries that are free.
11207 (substitute* "src/makefile"
11208 (("DIRS =.*") "DIRS =\n")
11209 (("cd jkOwnLib.*") "")
11212 (substitute* "src/utils/makefile"
11213 ;; These tools depend on "jkhgap.a", which is part of the
11214 ;; nonfree "src/hg/lib" directory.
11215 (("raSqlQuery") "")
11216 (("pslLiftSubrangeBlat") "")
11218 ;; Do not build UCSC tools, which may require nonfree
11220 (("ALL_APPS =.*") "ALL_APPS = $(UTILS_APPLIST)\n"))
11222 (build-system gnu-build-system)
11224 `( ;; There is no global test target and the test target for
11225 ;; individual tools depends on input files that are not
11229 (modify-phases %standard-phases
11230 (add-after 'unpack 'fix-permissions
11231 (lambda _ (make-file-writable "src/inc/localEnvironment.mk") #t))
11232 (add-after 'unpack 'fix-paths
11234 (substitute* "Makefile"
11235 (("/bin/echo") (which "echo")))
11237 (add-after 'unpack 'prepare-samtabix
11238 (lambda* (#:key inputs #:allow-other-keys)
11239 (copy-recursively (assoc-ref inputs "samtabix")
11242 (delete 'configure)
11244 (lambda* (#:key outputs #:allow-other-keys)
11245 (let ((bin (string-append (assoc-ref outputs "out")
11247 (copy-recursively "bin" bin))
11253 (uri (git-reference
11254 (url "http://genome-source.cse.ucsc.edu/samtabix.git")
11255 (commit "10fd107909c1ac4d679299908be4262a012965ba")))
11258 "0c1nj64l42v395sa84n7az43xiap4i6f9n9dfz4058aqiwkhkmma"))))))
11264 ("mariadb" ,mariadb)
11265 ("openssl" ,openssl)))
11266 (home-page "http://genome.cse.ucsc.edu/index.html")
11267 (synopsis "Assorted bioinformatics utilities")
11268 (description "This package provides the kentUtils, a selection of
11269 bioinformatics utilities used in combination with the UCSC genome
11271 ;; Only a subset of the sources are released under a non-copyleft
11272 ;; free software license. All other sources are removed in a
11273 ;; snippet. See this bug report for an explanation of how the
11274 ;; license statements apply:
11275 ;; https://github.com/ENCODE-DCC/kentUtils/issues/12
11276 (license (license:non-copyleft
11277 "http://genome.ucsc.edu/license/"
11278 "The contents of this package are free for all uses."))))
11280 (define-public f-seq
11281 (let ((commit "6ccded34cff38cf432deed8503648b4a66953f9b")
11285 (version (string-append "1.1-" revision "." (string-take commit 7)))
11288 (uri (git-reference
11289 (url "https://github.com/aboyle/F-seq.git")
11291 (file-name (string-append name "-" version))
11294 "1nk33k0yajg2id4g59bc4szr58r2q6pdq42vgcw054m8ip9wv26h"))
11295 (modules '((guix build utils)))
11296 ;; Remove bundled Java library archives.
11299 (for-each delete-file (find-files "lib" ".*"))
11301 (build-system ant-build-system)
11303 `(#:tests? #f ; no tests included
11305 (modify-phases %standard-phases
11307 (lambda* (#:key inputs outputs #:allow-other-keys)
11308 (let* ((target (assoc-ref outputs "out"))
11309 (bin (string-append target "/bin"))
11310 (doc (string-append target "/share/doc/f-seq"))
11311 (lib (string-append target "/lib")))
11314 (substitute* "bin/linux/fseq"
11315 (("java") (which "java"))
11316 (("\\$REALDIR/../lib/commons-cli-1.1.jar")
11317 (string-append (assoc-ref inputs "java-commons-cli")
11318 "/share/java/commons-cli.jar"))
11320 (string-append "REALDIR=" bin "\n")))
11321 (install-file "README.txt" doc)
11322 (install-file "bin/linux/fseq" bin)
11323 (install-file "build~/fseq.jar" lib)
11324 (copy-recursively "lib" lib)
11328 ("java-commons-cli" ,java-commons-cli)))
11329 (home-page "http://fureylab.web.unc.edu/software/fseq/")
11330 (synopsis "Feature density estimator for high-throughput sequence tags")
11332 "F-Seq is a software package that generates a continuous tag sequence
11333 density estimation allowing identification of biologically meaningful sites
11334 such as transcription factor binding sites (ChIP-seq) or regions of open
11335 chromatin (DNase-seq). Output can be displayed directly in the UCSC Genome
11337 (license license:gpl3+))))
11339 (define-public bismark
11346 (uri (git-reference
11347 (url "https://github.com/FelixKrueger/Bismark.git")
11349 (file-name (string-append name "-" version "-checkout"))
11352 "0xchm3rgilj6vfjnyzfzzymfd7djr64sbrmrvs3njbwi66jqbzw9"))))
11353 (build-system perl-build-system)
11355 `(#:tests? #f ; there are no tests
11356 #:modules ((guix build utils)
11359 (guix build perl-build-system))
11361 (modify-phases %standard-phases
11362 ;; The bundled plotly.js is minified.
11363 (add-after 'unpack 'replace-plotly.js
11364 (lambda* (#:key inputs #:allow-other-keys)
11365 (let* ((file (assoc-ref inputs "plotly.js"))
11366 (installed "plotly/plotly.js"))
11367 (let ((minified (open-pipe* OPEN_READ "uglify-js" file)))
11368 (call-with-output-file installed
11369 (cut dump-port minified <>))))
11371 (delete 'configure)
11374 (lambda* (#:key inputs outputs #:allow-other-keys)
11375 (let* ((out (assoc-ref outputs "out"))
11376 (bin (string-append out "/bin"))
11377 (share (string-append out "/share/bismark"))
11378 (docdir (string-append out "/share/doc/bismark"))
11379 (docs '("Docs/Bismark_User_Guide.html"))
11380 (scripts '("bismark"
11381 "bismark_genome_preparation"
11382 "bismark_methylation_extractor"
11385 "coverage2cytosine"
11386 "deduplicate_bismark"
11387 "filter_non_conversion"
11390 "NOMe_filtering")))
11391 (substitute* "bismark2report"
11392 (("\\$RealBin/plotly")
11393 (string-append share "/plotly")))
11397 (for-each (lambda (file) (install-file file bin))
11399 (for-each (lambda (file) (install-file file docdir))
11401 (copy-recursively "Docs/Images" (string-append docdir "/Images"))
11402 (copy-recursively "plotly"
11403 (string-append share "/plotly"))
11405 ;; Fix references to gunzip
11406 (substitute* (map (lambda (file)
11407 (string-append bin "/" file))
11410 (string-append "\"" (assoc-ref inputs "gzip")
11411 "/bin/gunzip -c")))
11415 ("perl-carp" ,perl-carp)
11416 ("perl-getopt-long" ,perl-getopt-long)))
11421 (uri (string-append "https://raw.githubusercontent.com/plotly/plotly.js/"
11422 "v1.39.4/dist/plotly.js"))
11424 (base32 "138mwsr4nf5qif4mrxx286mpnagxd1xwl6k8aidrjgknaqg88zyr"))))
11425 ("uglify-js" ,uglify-js)))
11426 (home-page "http://www.bioinformatics.babraham.ac.uk/projects/bismark/")
11427 (synopsis "Map bisulfite treated sequence reads and analyze methylation")
11428 (description "Bismark is a program to map bisulfite treated sequencing
11429 reads to a genome of interest and perform methylation calls in a single step.
11430 The output can be easily imported into a genome viewer, such as SeqMonk, and
11431 enables a researcher to analyse the methylation levels of their samples
11432 straight away. Its main features are:
11435 @item Bisulfite mapping and methylation calling in one single step
11436 @item Supports single-end and paired-end read alignments
11437 @item Supports ungapped and gapped alignments
11438 @item Alignment seed length, number of mismatches etc are adjustable
11439 @item Output discriminates between cytosine methylation in CpG, CHG
11442 (license license:gpl3+)))
11444 (define-public paml
11450 (uri (string-append "http://abacus.gene.ucl.ac.uk/software/"
11451 "paml" version ".tgz"))
11454 "13zf6h9fiqghwhch2h06x1zdr6s42plsnqahflp5g7myr3han3s6"))
11455 (modules '((guix build utils)))
11456 ;; Remove Windows binaries
11459 (for-each delete-file (find-files "." "\\.exe$"))
11461 (build-system gnu-build-system)
11463 `(#:tests? #f ; there are no tests
11464 #:make-flags '("CC=gcc")
11466 (modify-phases %standard-phases
11467 (replace 'configure
11469 (substitute* "src/BFdriver.c"
11470 (("/bin/bash") (which "bash")))
11474 (lambda* (#:key outputs #:allow-other-keys)
11475 (let ((tools '("baseml" "basemlg" "codeml"
11476 "pamp" "evolver" "yn00" "chi2"))
11477 (bin (string-append (assoc-ref outputs "out") "/bin"))
11478 (docdir (string-append (assoc-ref outputs "out")
11479 "/share/doc/paml")))
11481 (for-each (lambda (file) (install-file file bin)) tools)
11482 (copy-recursively "../doc" docdir)
11484 (home-page "http://abacus.gene.ucl.ac.uk/software/paml.html")
11485 (synopsis "Phylogentic analysis by maximum likelihood")
11486 (description "PAML (for Phylogentic Analysis by Maximum Likelihood)
11487 contains a few programs for model fitting and phylogenetic tree reconstruction
11488 using nucleotide or amino-acid sequence data.")
11490 (license license:gpl3)))
11492 (define-public kallisto
11498 (uri (git-reference
11499 (url "https://github.com/pachterlab/kallisto.git")
11500 (commit (string-append "v" version))))
11501 (file-name (git-file-name name version))
11504 "0nj382jiywqnpgvyhichajpkkh5r0bapn43f4dx40zdaq5v4m40m"))))
11505 (build-system cmake-build-system)
11507 `(#:tests? #f ; no "check" target
11509 (modify-phases %standard-phases
11510 (add-after 'unpack 'do-not-use-bundled-htslib
11512 (substitute* "CMakeLists.txt"
11513 (("^ExternalProject_Add" m)
11514 (string-append "if (NEVER)\n" m))
11516 (string-append ")\nendif(NEVER)"))
11517 (("include_directories\\(\\$\\{htslib_PREFIX.*" m)
11518 (string-append "# " m)))
11519 (substitute* "src/CMakeLists.txt"
11520 (("target_link_libraries\\(kallisto kallisto_core pthread \
11521 \\$\\{CMAKE_CURRENT_SOURCE_DIR\\}/../ext/htslib/libhts.a\\)")
11522 "target_link_libraries(kallisto kallisto_core pthread hts)")
11523 (("include_directories\\(\\.\\./ext/htslib\\)") ""))
11529 (home-page "http://pachterlab.github.io/kallisto/")
11530 (synopsis "Near-optimal RNA-Seq quantification")
11532 "Kallisto is a program for quantifying abundances of transcripts from
11533 RNA-Seq data, or more generally of target sequences using high-throughput
11534 sequencing reads. It is based on the novel idea of pseudoalignment for
11535 rapidly determining the compatibility of reads with targets, without the need
11536 for alignment. Pseudoalignment of reads preserves the key information needed
11537 for quantification, and kallisto is therefore not only fast, but also as
11538 accurate as existing quantification tools.")
11539 (license license:bsd-2)))
11541 (define-public libgff
11547 (uri (git-reference
11548 (url "https://github.com/Kingsford-Group/libgff.git")
11549 (commit (string-append "v" version))))
11550 (file-name (git-file-name name version))
11553 "0n6vfjnq7a2mianipscbshrvbncss8z4zkgkbjw754p9043nfkps"))))
11554 (build-system cmake-build-system)
11555 (arguments `(#:tests? #f)) ; no tests included
11556 (home-page "https://github.com/Kingsford-Group/libgff")
11557 (synopsis "Parser library for reading/writing GFF files")
11558 (description "This is a simple \"libraryfication\" of the GFF/GTF parsing
11559 code that is used in the Cufflinks codebase. The goal of this library is to
11560 provide this functionality without the necessity of drawing in a heavy-weight
11561 dependency like SeqAn.")
11562 (license (license:x11-style "https://www.boost.org/LICENSE_1_0.txt"))))
11564 (define-public libdivsufsort
11566 (name "libdivsufsort")
11570 (uri (git-reference
11571 (url "https://github.com/y-256/libdivsufsort.git")
11573 (file-name (git-file-name name version))
11576 "0fgdz9fzihlvjjrxy01md1bv9vh12rkgkwbm90b1hj5xpbaqp7z2"))))
11577 (build-system cmake-build-system)
11579 '(#:tests? #f ; there are no tests
11581 ;; Needed for rapmap and sailfish.
11582 '("-DBUILD_DIVSUFSORT64=ON")))
11583 (home-page "https://github.com/y-256/libdivsufsort")
11584 (synopsis "Lightweight suffix-sorting library")
11585 (description "libdivsufsort is a software library that implements a
11586 lightweight suffix array construction algorithm. This library provides a
11587 simple and an efficient C API to construct a suffix array and a
11588 Burrows-Wheeler transformed string from a given string over a constant-size
11589 alphabet. The algorithm runs in O(n log n) worst-case time using only 5n+O(1)
11590 bytes of memory space, where n is the length of the string.")
11591 (license license:expat)))
11593 (define-public sailfish
11599 (uri (git-reference
11600 (url "https://github.com/kingsfordgroup/sailfish.git")
11601 (commit (string-append "v" version))))
11602 (file-name (git-file-name name version))
11605 "1amcc5hqvsl42hg4x19bi9vy47cl874s0lw1fmi0hwsdk9i8c03v"))
11606 (modules '((guix build utils)))
11609 ;; Delete bundled headers for eigen3.
11610 (delete-file-recursively "include/eigen3/")
11612 (build-system cmake-build-system)
11614 `(#:configure-flags
11615 (list (string-append "-DBOOST_INCLUDEDIR="
11616 (assoc-ref %build-inputs "boost")
11618 (string-append "-DBOOST_LIBRARYDIR="
11619 (assoc-ref %build-inputs "boost")
11621 (string-append "-DBoost_LIBRARIES="
11622 "-lboost_iostreams "
11623 "-lboost_filesystem "
11628 "-lboost_program_options")
11629 "-DBoost_FOUND=TRUE"
11630 ;; Don't download RapMap---we already have it!
11631 "-DFETCHED_RAPMAP=1")
11632 ;; Tests must be run after installation and the location of the test
11633 ;; data file must be overridden. But the tests fail. It looks like
11634 ;; they are not really meant to be run.
11637 (modify-phases %standard-phases
11638 ;; Boost cannot be found, even though it's right there.
11639 (add-after 'unpack 'do-not-look-for-boost
11640 (lambda* (#:key inputs #:allow-other-keys)
11641 (substitute* "CMakeLists.txt"
11642 (("find_package\\(Boost 1\\.53\\.0") "#"))
11644 (add-after 'unpack 'do-not-assign-to-macro
11646 (substitute* "include/spdlog/details/format.cc"
11647 (("const unsigned CHAR_WIDTH = 1;") ""))
11649 (add-after 'unpack 'prepare-rapmap
11650 (lambda* (#:key inputs #:allow-other-keys)
11651 (let ((src "external/install/src/rapmap/")
11652 (include "external/install/include/rapmap/")
11653 (rapmap (assoc-ref inputs "rapmap")))
11654 (mkdir-p "/tmp/rapmap")
11656 (assoc-ref inputs "rapmap")
11658 "--strip-components=1")
11661 (for-each (lambda (file)
11662 (install-file file src))
11663 (find-files "/tmp/rapmap/src" "\\.(c|cpp)"))
11664 (copy-recursively "/tmp/rapmap/include" include))
11666 (add-after 'unpack 'use-system-libraries
11667 (lambda* (#:key inputs #:allow-other-keys)
11668 (substitute* '("src/SailfishIndexer.cpp"
11669 "src/SailfishUtils.cpp"
11670 "src/SailfishQuantify.cpp"
11671 "src/FASTAParser.cpp"
11673 "include/SailfishUtils.hpp"
11674 "include/SailfishIndex.hpp"
11675 "include/CollapsedEMOptimizer.hpp"
11676 "src/CollapsedEMOptimizer.cpp")
11677 (("#include \"jellyfish/config.h\"") ""))
11678 (substitute* "src/CMakeLists.txt"
11679 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11680 (string-append (assoc-ref inputs "jellyfish")
11681 "/include/jellyfish-" ,(package-version jellyfish)))
11682 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11683 (string-append (assoc-ref inputs "jellyfish")
11684 "/lib/libjellyfish-2.0.a"))
11685 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11686 (string-append (assoc-ref inputs "libdivsufsort")
11687 "/lib/libdivsufsort.so"))
11688 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11689 (string-append (assoc-ref inputs "libdivsufsort")
11690 "/lib/libdivsufsort64.so")))
11691 (substitute* "CMakeLists.txt"
11692 ;; Don't prefer static libs
11693 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11694 (("find_package\\(Jellyfish.*") "")
11695 (("ExternalProject_Add\\(libjellyfish") "message(")
11696 (("ExternalProject_Add\\(libgff") "message(")
11697 (("ExternalProject_Add\\(libsparsehash") "message(")
11698 (("ExternalProject_Add\\(libdivsufsort") "message("))
11700 ;; Ensure that Eigen headers can be found
11701 (setenv "CPLUS_INCLUDE_PATH"
11702 (string-append (getenv "CPLUS_INCLUDE_PATH")
11704 (assoc-ref inputs "eigen")
11705 "/include/eigen3"))
11710 ("jemalloc" ,jemalloc)
11711 ("jellyfish" ,jellyfish)
11712 ("sparsehash" ,sparsehash)
11715 (uri (git-reference
11716 (url "https://github.com/COMBINE-lab/RapMap.git")
11717 (commit (string-append "sf-v" version))))
11718 (file-name (string-append "rapmap-sf-v" version "-checkout"))
11721 "1hv79l5i576ykv5a1srj2p0q36yvyl5966m0fcy2lbi169ipjakf"))
11722 (modules '((guix build utils)))
11723 ;; These files are expected to be excluded.
11725 '(begin (delete-file-recursively "include/spdlog")
11726 (for-each delete-file '("include/xxhash.h"
11729 ("libdivsufsort" ,libdivsufsort)
11734 `(("pkg-config" ,pkg-config)))
11735 (home-page "http://www.cs.cmu.edu/~ckingsf/software/sailfish")
11736 (synopsis "Mapping-based isoform quantification from RNA-Seq reads")
11737 (description "Sailfish is a tool for genomic transcript quantification
11738 from RNA-seq data. It requires a set of target transcripts (either from a
11739 reference or de-novo assembly) to quantify. All you need to run sailfish is a
11740 fasta file containing your reference transcripts and a (set of) fasta/fastq
11741 file(s) containing your reads.")
11742 (license license:gpl3+)))
11744 (define libstadenio-for-salmon
11746 (name "libstadenio")
11750 (uri (git-reference
11751 (url "https://github.com/COMBINE-lab/staden-io_lib.git")
11752 (commit (string-append "v" version))))
11753 (file-name (string-append name "-" version "-checkout"))
11756 "1x8kxxqxl892vwfbprlbyfwkkv7c34ggkc94892x9x0g37x5nbwx"))))
11757 (build-system gnu-build-system)
11758 (arguments '(#:parallel-tests? #f)) ; not supported
11762 `(("perl" ,perl))) ; for tests
11763 (home-page "https://github.com/COMBINE-lab/staden-io_lib")
11764 (synopsis "General purpose trace and experiment file library")
11765 (description "This package provides a library of file reading and writing
11766 code to provide a general purpose Trace file (and Experiment File) reading
11769 The following file formats are supported:
11772 @item SCF trace files
11773 @item ABI trace files
11774 @item ALF trace files
11775 @item ZTR trace files
11776 @item SFF trace archives
11777 @item SRF trace archives
11778 @item Experiment files
11779 @item Plain text files
11780 @item SAM/BAM sequence files
11781 @item CRAM sequence files
11783 (license license:bsd-3)))
11785 (define spdlog-for-salmon
11791 (uri (git-reference
11792 (url "https://github.com/COMBINE-lab/spdlog.git")
11793 (commit (string-append "v" version))))
11794 (file-name (string-append name "-" version "-checkout"))
11797 "13730429gwlabi432ilpnja3sfvy0nn2719vnhhmii34xcdyc57q"))))
11798 (build-system cmake-build-system)
11799 (home-page "https://github.com/COMBINE-lab/spdlog")
11800 (synopsis "Very fast C++ logging library")
11801 (description "Spdlog is a very fast header-only C++ logging library with
11802 performance as its primary goal.")
11803 (license license:expat)))
11805 ;; This is a modified variant of bwa for use with Salmon. It installs a
11806 ;; library to avoid having to build this as part of Salmon.
11807 (define bwa-for-salmon
11808 (package (inherit bwa)
11810 (version "0.7.12.5")
11813 (uri (git-reference
11814 (url "https://github.com/COMBINE-lab/bwa.git")
11815 (commit (string-append "v" version))))
11816 (file-name (string-append "bwa-for-salmon-" version "-checkout"))
11819 "1z2qa64y0c5hky10510x137mnzlhz6k8qf27csw4w9j6qihq95gb"))))
11820 (build-system gnu-build-system)
11822 '(#:tests? #f ;no "check" target
11824 (modify-phases %standard-phases
11826 (lambda* (#:key outputs #:allow-other-keys)
11827 (let* ((out (assoc-ref outputs "out"))
11828 (bin (string-append out "/bin"))
11829 (lib (string-append out "/lib"))
11830 (doc (string-append out "/share/doc/bwa"))
11831 (man (string-append out "/share/man/man1"))
11832 (inc (string-append out "/include/bwa")))
11833 (install-file "bwa" bin)
11834 (install-file "README.md" doc)
11835 (install-file "bwa.1" man)
11836 (install-file "libbwa.a" lib)
11839 (for-each (lambda (file)
11840 (install-file file inc))
11841 (find-files "." "\\.h$")))
11843 ;; no "configure" script
11844 (delete 'configure))))))
11846 (define-public salmon
11852 (uri (git-reference
11853 (url "https://github.com/COMBINE-lab/salmon.git")
11854 (commit (string-append "v" version))))
11855 (file-name (string-append name "-" version "-checkout"))
11858 "1zi1ff4i7y2ykk0vdzysgwzzzv166vg2x77pj1mf4baclavxj87a"))
11859 (modules '((guix build utils)))
11862 ;; Delete bundled headers for eigen3.
11863 (delete-file-recursively "include/eigen3/")
11865 (build-system cmake-build-system)
11867 `(#:configure-flags
11868 (list (string-append "-DBOOST_INCLUDEDIR="
11869 (assoc-ref %build-inputs "boost")
11871 (string-append "-DBOOST_LIBRARYDIR="
11872 (assoc-ref %build-inputs "boost")
11874 (string-append "-DBoost_LIBRARIES="
11875 "-lboost_iostreams "
11876 "-lboost_filesystem "
11881 "-lboost_program_options")
11882 "-DBoost_FOUND=TRUE"
11883 "-DTBB_LIBRARIES=tbb tbbmalloc"
11884 ;; Don't download RapMap---we already have it!
11885 "-DFETCHED_RAPMAP=1")
11887 (modify-phases %standard-phases
11888 ;; Boost cannot be found, even though it's right there.
11889 (add-after 'unpack 'do-not-look-for-boost
11890 (lambda* (#:key inputs #:allow-other-keys)
11891 (substitute* "CMakeLists.txt"
11892 (("find_package\\(Boost 1\\.53\\.0") "#"))
11894 (add-after 'unpack 'do-not-phone-home
11896 (substitute* "src/Salmon.cpp"
11897 (("getVersionMessage\\(\\)") "\"\""))
11899 (add-after 'unpack 'prepare-rapmap
11900 (lambda* (#:key inputs #:allow-other-keys)
11901 (let ((src "external/install/src/rapmap/")
11902 (include "external/install/include/rapmap/")
11903 (rapmap (assoc-ref inputs "rapmap")))
11906 (for-each (lambda (file)
11907 (install-file file src))
11908 (find-files (string-append rapmap "/src") "\\.(c|cpp)"))
11909 (copy-recursively (string-append rapmap "/include") include)
11910 (for-each delete-file '("external/install/include/rapmap/xxhash.h"
11911 "external/install/include/rapmap/FastxParser.hpp"
11912 "external/install/include/rapmap/concurrentqueue.h"
11913 "external/install/include/rapmap/FastxParserThreadUtils.hpp"
11914 "external/install/src/rapmap/FastxParser.cpp"
11915 "external/install/src/rapmap/xxhash.c")))
11917 (add-after 'unpack 'use-system-libraries
11918 (lambda* (#:key inputs #:allow-other-keys)
11919 (substitute* "src/CMakeLists.txt"
11920 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/include/jellyfish-2.2..")
11921 (string-append (assoc-ref inputs "jellyfish")
11922 "/include/jellyfish-" ,(package-version jellyfish)))
11923 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libjellyfish-2.0.a")
11924 (string-append (assoc-ref inputs "jellyfish")
11925 "/lib/libjellyfish-2.0.a"))
11926 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort.a")
11927 (string-append (assoc-ref inputs "libdivsufsort")
11928 "/lib/libdivsufsort.so"))
11929 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libstaden-read.a")
11930 (string-append (assoc-ref inputs "libstadenio-for-salmon")
11931 "/lib/libstaden-read.a"))
11932 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libbwa.a")
11933 (string-append (assoc-ref inputs "bwa") "/lib/libbwa.a"))
11934 (("\\$\\{GAT_SOURCE_DIR\\}/external/install/lib/libdivsufsort64.a")
11935 (string-append (assoc-ref inputs "libdivsufsort")
11936 "/lib/libdivsufsort64.so")))
11937 (substitute* "CMakeLists.txt"
11938 ;; Don't prefer static libs
11939 (("SET\\(CMAKE_FIND_LIBRARY_SUFFIXES.*") "")
11940 (("set\\(TBB_LIBRARIES") "message(")
11941 (("find_package\\(Jellyfish.*") "")
11942 (("ExternalProject_Add\\(libcereal") "message(")
11943 (("ExternalProject_Add\\(libbwa") "message(")
11944 (("ExternalProject_Add\\(libjellyfish") "message(")
11945 (("ExternalProject_Add\\(libgff") "message(")
11946 (("ExternalProject_Add\\(libtbb") "message(")
11947 (("ExternalProject_Add\\(libspdlog") "message(")
11948 (("ExternalProject_Add\\(libdivsufsort") "message(")
11949 (("ExternalProject_Add\\(libstadenio") "message(")
11950 (("ExternalProject_Add_Step\\(") "message("))
11952 ;; Ensure that all headers can be found
11953 (setenv "CPLUS_INCLUDE_PATH"
11954 (string-append (getenv "CPLUS_INCLUDE_PATH")
11956 (assoc-ref inputs "bwa")
11959 (assoc-ref inputs "eigen")
11960 "/include/eigen3"))
11962 (string-append (assoc-ref inputs "bwa")
11965 (assoc-ref inputs "eigen")
11966 "/include/eigen3"))
11968 ;; CMAKE_INSTALL_PREFIX does not exist when the tests are
11969 ;; run. It only exists after the install phase.
11970 (add-after 'unpack 'fix-tests
11972 (substitute* "src/CMakeLists.txt"
11973 (("DTOPLEVEL_DIR=\\$\\{CMAKE_INSTALL_PREFIX")
11974 "DTOPLEVEL_DIR=${GAT_SOURCE_DIR"))
11978 ("bwa" ,bwa-for-salmon)
11984 (uri (git-reference
11985 (url "https://github.com/COMBINE-lab/RapMap.git")
11986 (commit (string-append "salmon-v" version))))
11987 (file-name (string-append "rapmap-salmon-v" version "-checkout"))
11990 "1yc12yqsz6f0r8sg1qnk57xg34aqwc9jbqq6gd5ys28xw3plj98p"))))
11991 ("jemalloc" ,jemalloc)
11992 ("jellyfish" ,jellyfish)
11995 ("libdivsufsort" ,libdivsufsort)
11996 ("libstadenio-for-salmon" ,libstadenio-for-salmon)
11997 ("spdlog-for-salmon" ,spdlog-for-salmon)
12000 (home-page "https://github.com/COMBINE-lab/salmon")
12001 (synopsis "Quantification from RNA-seq reads using lightweight alignments")
12002 (description "Salmon is a program to produce highly-accurate,
12003 transcript-level quantification estimates from RNA-seq data. Salmon achieves
12004 its accuracy and speed via a number of different innovations, including the
12005 use of lightweight alignments (accurate but fast-to-compute proxies for
12006 traditional read alignments) and massively-parallel stochastic collapsed
12007 variational inference.")
12008 (license license:gpl3+)))
12010 (define-public python-loompy
12012 (name "python-loompy")
12014 ;; The tarball on Pypi does not include the tests.
12017 (uri (git-reference
12018 (url "https://github.com/linnarsson-lab/loompy.git")
12020 (file-name (git-file-name name version))
12023 "12a5kjgiikapv93wahfw0frszx1lblnppyz3vs5gy8fgmgngra07"))))
12024 (build-system python-build-system)
12027 (modify-phases %standard-phases
12030 (setenv "PYTHONPATH"
12031 (string-append (getcwd) ":"
12032 (getenv "PYTHONPATH")))
12033 (invoke "pytest" "tests")
12036 `(("python-h5py" ,python-h5py)
12037 ("python-numpy" ,python-numpy)
12038 ("python-pandas" ,python-pandas)
12039 ("python-scipy" ,python-scipy)))
12041 `(("python-pytest" ,python-pytest)))
12042 (home-page "https://github.com/linnarsson-lab/loompy")
12043 (synopsis "Work with .loom files for single-cell RNA-seq data")
12044 (description "The loom file format is an efficient format for very large
12045 omics datasets, consisting of a main matrix, optional additional layers, a
12046 variable number of row and column annotations. Loom also supports sparse
12047 graphs. This library makes it easy to work with @file{.loom} files for
12048 single-cell RNA-seq data.")
12049 (license license:bsd-3)))
12051 ;; pigx-scrnaseq does not work with the latest version of loompy.
12052 (define-public python-loompy-for-pigx-scrnaseq
12053 (package (inherit python-loompy)
12054 (name "python-loompy")
12058 (uri (git-reference
12059 (url "https://github.com/linnarsson-lab/loompy.git")
12060 (commit (string-append "v" version))))
12061 (file-name (git-file-name name version))
12064 "0pjyl532pl8sbv71yci6h0agchn0naw2qjcwj50n6afrsahbsag3"))))
12066 (arguments '(#:tests? #f))))
12068 ;; We cannot use the latest commit because it requires Java 9.
12069 (define-public java-forester
12070 (let ((commit "86b07efe302d5094b42deed9260f719a4c4ac2e6")
12073 (name "java-forester")
12074 (version (string-append "0-" revision "." (string-take commit 7)))
12077 (uri (git-reference
12078 (url "https://github.com/cmzmasek/forester.git")
12080 (file-name (string-append name "-" version "-checkout"))
12083 "0vxavc1yrf84yrnf20dq26hi0lglidk8d382xrxsy4qmlbjd276z"))
12084 (modules '((guix build utils)))
12087 ;; Delete bundled jars and pre-built classes
12088 (delete-file-recursively "forester/java/resources")
12089 (delete-file-recursively "forester/java/classes")
12090 (for-each delete-file (find-files "forester/java/" "\\.jar$"))
12091 ;; Delete bundled applications
12092 (delete-file-recursively "forester_applications")
12094 (build-system ant-build-system)
12096 `(#:tests? #f ; there are none
12098 #:modules ((guix build ant-build-system)
12100 (guix build java-utils)
12104 (modify-phases %standard-phases
12105 (add-after 'unpack 'chdir
12106 (lambda _ (chdir "forester/java") #t))
12107 (add-after 'chdir 'fix-dependencies
12109 (chmod "build.xml" #o664)
12110 (call-with-output-file "build.xml.new"
12114 (with-input-from-file "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 (rename-file "build.xml.new" "build.xml")
12123 ;; FIXME: itext is difficult to package as it depends on a few
12124 ;; unpackaged libraries.
12125 (add-after 'chdir 'remove-dependency-on-unpackaged-itext
12127 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12128 (substitute* "src/org/forester/archaeopteryx/MainFrame.java"
12129 (("pdf_written_to = PdfExporter.*")
12130 "throw new IOException(\"PDF export is not available.\");"))
12132 ;; There is no install target
12133 (replace 'install (install-jars ".")))))
12135 `(("java-commons-codec" ,java-commons-codec)
12136 ("java-openchart2" ,java-openchart2)))
12137 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12138 (synopsis "Phylogenomics libraries for Java")
12139 (description "Forester is a collection of Java libraries for
12140 phylogenomics and evolutionary biology research. It includes support for
12141 reading, writing, and exporting phylogenetic trees.")
12142 (license license:lgpl2.1+))))
12144 (define-public java-forester-1.005
12146 (name "java-forester")
12150 (uri (string-append "http://search.maven.org/remotecontent?"
12151 "filepath=org/biojava/thirdparty/forester/"
12152 version "/forester-" version "-sources.jar"))
12153 (file-name (string-append name "-" version ".jar"))
12156 "04r8qv4rk3p71z4ajrvp11py1z46qrx0047j3zzs79s6lnsm3lcv"))))
12157 (build-system ant-build-system)
12159 `(#:tests? #f ; there are none
12161 #:modules ((guix build ant-build-system)
12163 (guix build java-utils)
12167 (modify-phases %standard-phases
12168 (add-after 'unpack 'fix-dependencies
12169 (lambda* (#:key inputs #:allow-other-keys)
12170 (call-with-output-file "build.xml"
12174 (with-input-from-file "src/build.xml"
12175 (lambda _ (xml->sxml #:trim-whitespace? #t)))
12176 `(;; Remove all unjar tags to avoid repacking classes.
12177 (unjar . ,(lambda _ '()))
12178 (*default* . ,(lambda (tag . kids) `(,tag ,@kids)))
12179 (*text* . ,(lambda (_ txt) txt))))
12181 (copy-file (assoc-ref inputs "synth_look_and_feel_1.xml")
12182 "synth_look_and_feel_1.xml")
12183 (copy-file (assoc-ref inputs "phyloxml.xsd")
12185 (substitute* "build.xml"
12186 (("../resources/synth_laf/synth_look_and_feel_1.xml")
12187 "synth_look_and_feel_1.xml")
12188 (("../resources/phyloxml_schema/1.10/phyloxml.xsd")
12191 ;; FIXME: itext is difficult to package as it depends on a few
12192 ;; unpackaged libraries.
12193 (add-after 'unpack 'remove-dependency-on-unpackaged-itext
12195 (delete-file "src/org/forester/archaeopteryx/PdfExporter.java")
12196 (substitute* '("src/org/forester/archaeopteryx/MainFrame.java"
12197 "src/org/forester/archaeopteryx/MainFrameApplication.java")
12198 (("pdf_written_to = PdfExporter.*")
12199 "throw new IOException(\"PDF export is not available.\"); /*")
12200 ((".getPrintSizeX\\(\\), getOptions\\(\\).getPrintSizeY\\(\\) \\);") "*/")
12201 (("getCurrentTreePanel\\(\\).getHeight\\(\\) \\);") "*/"))
12203 (add-after 'unpack 'delete-pre-built-classes
12204 (lambda _ (delete-file-recursively "src/classes") #t))
12205 ;; There is no install target
12206 (replace 'install (install-jars ".")))))
12208 `(("java-commons-codec" ,java-commons-codec)
12209 ("java-openchart2" ,java-openchart2)))
12210 ;; The source archive does not contain the resources.
12215 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12216 "b61cc2dcede0bede317db362472333115756b8c6/"
12217 "forester/resources/phyloxml_schema/1.10/phyloxml.xsd"))
12218 (file-name (string-append name "-phyloxml-" version ".xsd"))
12221 "1zxc4m8sn4n389nqdnpxa8d0k17qnr3pm2y5y6g6vh4k0zm52npv"))))
12222 ("synth_look_and_feel_1.xml"
12225 (uri (string-append "https://raw.githubusercontent.com/cmzmasek/forester/"
12226 "29e04321615da6b35c1e15c60e52caf3f21d8e6a/"
12227 "forester/java/classes/resources/synth_look_and_feel_1.xml"))
12228 (file-name (string-append name "-synth-look-and-feel-" version ".xml"))
12231 "1gv5602gv4k7y7713y75a4jvj7i9s7nildsbdl7n9q10sc2ikg8h"))))))
12232 (home-page "https://sites.google.com/site/cmzmasek/home/software/forester")
12233 (synopsis "Phylogenomics libraries for Java")
12234 (description "Forester is a collection of Java libraries for
12235 phylogenomics and evolutionary biology research. It includes support for
12236 reading, writing, and exporting phylogenetic trees.")
12237 (license license:lgpl2.1+)))
12239 (define-public java-biojava-core
12241 (name "java-biojava-core")
12245 (uri (git-reference
12246 (url "https://github.com/biojava/biojava")
12247 (commit (string-append "biojava-" version))))
12248 (file-name (string-append name "-" version "-checkout"))
12251 "1bvryh2bpsvash8ln79cmc9sqm8qw72hz4xzwqxcrjm8ssxszhqk"))))
12252 (build-system ant-build-system)
12255 #:jar-name "biojava-core.jar"
12256 #:source-dir "biojava-core/src/main/java/"
12257 #:test-dir "biojava-core/src/test"
12258 ;; These tests seem to require internet access.
12259 #:test-exclude (list "**/SearchIOTest.java"
12260 "**/BlastXMLParserTest.java"
12261 "**/GenbankCookbookTest.java"
12262 "**/GenbankProxySequenceReaderTest.java")
12264 (modify-phases %standard-phases
12265 (add-before 'build 'copy-resources
12267 (copy-recursively "biojava-core/src/main/resources"
12270 (add-before 'check 'copy-test-resources
12272 (copy-recursively "biojava-core/src/test/resources"
12273 "build/test-classes")
12276 `(("java-log4j-api" ,java-log4j-api)
12277 ("java-log4j-core" ,java-log4j-core)
12278 ("java-slf4j-api" ,java-slf4j-api)
12279 ("java-slf4j-simple" ,java-slf4j-simple)))
12281 `(("java-junit" ,java-junit)
12282 ("java-hamcrest-core" ,java-hamcrest-core)))
12283 (home-page "http://biojava.org")
12284 (synopsis "Core libraries of Java framework for processing biological data")
12285 (description "BioJava is a project dedicated to providing a Java framework
12286 for processing biological data. It provides analytical and statistical
12287 routines, parsers for common file formats, reference implementations of
12288 popular algorithms, and allows the manipulation of sequences and 3D
12289 structures. The goal of the biojava project is to facilitate rapid
12290 application development for bioinformatics.
12292 This package provides the core libraries.")
12293 (license license:lgpl2.1+)))
12295 (define-public java-biojava-phylo
12296 (package (inherit java-biojava-core)
12297 (name "java-biojava-phylo")
12298 (build-system ant-build-system)
12301 #:jar-name "biojava-phylo.jar"
12302 #:source-dir "biojava-phylo/src/main/java/"
12303 #:test-dir "biojava-phylo/src/test"
12305 (modify-phases %standard-phases
12306 (add-before 'build 'copy-resources
12308 (copy-recursively "biojava-phylo/src/main/resources"
12311 (add-before 'check 'copy-test-resources
12313 (copy-recursively "biojava-phylo/src/test/resources"
12314 "build/test-classes")
12317 `(("java-log4j-api" ,java-log4j-api)
12318 ("java-log4j-core" ,java-log4j-core)
12319 ("java-slf4j-api" ,java-slf4j-api)
12320 ("java-slf4j-simple" ,java-slf4j-simple)
12321 ("java-biojava-core" ,java-biojava-core)
12322 ("java-forester" ,java-forester)))
12324 `(("java-junit" ,java-junit)
12325 ("java-hamcrest-core" ,java-hamcrest-core)))
12326 (home-page "http://biojava.org")
12327 (synopsis "Biojava interface to the forester phylogenomics library")
12328 (description "The phylo module provides a biojava interface layer to the
12329 forester phylogenomics library for constructing phylogenetic trees.")))
12331 (define-public java-biojava-alignment
12332 (package (inherit java-biojava-core)
12333 (name "java-biojava-alignment")
12334 (build-system ant-build-system)
12337 #:jar-name "biojava-alignment.jar"
12338 #:source-dir "biojava-alignment/src/main/java/"
12339 #:test-dir "biojava-alignment/src/test"
12341 (modify-phases %standard-phases
12342 (add-before 'build 'copy-resources
12344 (copy-recursively "biojava-alignment/src/main/resources"
12347 (add-before 'check 'copy-test-resources
12349 (copy-recursively "biojava-alignment/src/test/resources"
12350 "build/test-classes")
12353 `(("java-log4j-api" ,java-log4j-api)
12354 ("java-log4j-core" ,java-log4j-core)
12355 ("java-slf4j-api" ,java-slf4j-api)
12356 ("java-slf4j-simple" ,java-slf4j-simple)
12357 ("java-biojava-core" ,java-biojava-core)
12358 ("java-biojava-phylo" ,java-biojava-phylo)
12359 ("java-forester" ,java-forester)))
12361 `(("java-junit" ,java-junit)
12362 ("java-hamcrest-core" ,java-hamcrest-core)))
12363 (home-page "http://biojava.org")
12364 (synopsis "Biojava API for genetic sequence alignment")
12365 (description "The alignment module of BioJava provides an API that
12369 @item implementations of dynamic programming algorithms for sequence
12371 @item reading and writing of popular alignment file formats;
12372 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12375 (define-public java-biojava-core-4.0
12376 (package (inherit java-biojava-core)
12377 (name "java-biojava-core")
12381 (uri (git-reference
12382 (url "https://github.com/biojava/biojava")
12383 (commit (string-append "biojava-" version))))
12384 (file-name (string-append name "-" version "-checkout"))
12387 "13675f6y9aqi7bi2lk3s1z7a22ynccjiqwa8izh7p97xi9wsfmd8"))))))
12389 (define-public java-biojava-phylo-4.0
12390 (package (inherit java-biojava-core-4.0)
12391 (name "java-biojava-phylo")
12392 (build-system ant-build-system)
12395 #:jar-name "biojava-phylo.jar"
12396 #:source-dir "biojava-phylo/src/main/java/"
12397 #:test-dir "biojava-phylo/src/test"
12399 (modify-phases %standard-phases
12400 (add-before 'build 'copy-resources
12402 (copy-recursively "biojava-phylo/src/main/resources"
12405 (add-before 'check 'copy-test-resources
12407 (copy-recursively "biojava-phylo/src/test/resources"
12408 "build/test-classes")
12411 `(("java-log4j-api" ,java-log4j-api)
12412 ("java-log4j-core" ,java-log4j-core)
12413 ("java-slf4j-api" ,java-slf4j-api)
12414 ("java-slf4j-simple" ,java-slf4j-simple)
12415 ("java-biojava-core" ,java-biojava-core-4.0)
12416 ("java-forester" ,java-forester-1.005)))
12418 `(("java-junit" ,java-junit)
12419 ("java-hamcrest-core" ,java-hamcrest-core)))
12420 (home-page "http://biojava.org")
12421 (synopsis "Biojava interface to the forester phylogenomics library")
12422 (description "The phylo module provides a biojava interface layer to the
12423 forester phylogenomics library for constructing phylogenetic trees.")))
12425 (define-public java-biojava-alignment-4.0
12426 (package (inherit java-biojava-core-4.0)
12427 (name "java-biojava-alignment")
12428 (build-system ant-build-system)
12431 #:jar-name "biojava-alignment.jar"
12432 #:source-dir "biojava-alignment/src/main/java/"
12433 #:test-dir "biojava-alignment/src/test"
12435 (modify-phases %standard-phases
12436 (add-before 'build 'copy-resources
12438 (copy-recursively "biojava-alignment/src/main/resources"
12441 (add-before 'check 'copy-test-resources
12443 (copy-recursively "biojava-alignment/src/test/resources"
12444 "build/test-classes")
12447 `(("java-log4j-api" ,java-log4j-api)
12448 ("java-log4j-core" ,java-log4j-core)
12449 ("java-slf4j-api" ,java-slf4j-api)
12450 ("java-slf4j-simple" ,java-slf4j-simple)
12451 ("java-biojava-core" ,java-biojava-core-4.0)
12452 ("java-biojava-phylo" ,java-biojava-phylo-4.0)
12453 ("java-forester" ,java-forester-1.005)))
12455 `(("java-junit" ,java-junit)
12456 ("java-hamcrest-core" ,java-hamcrest-core)))
12457 (home-page "http://biojava.org")
12458 (synopsis "Biojava API for genetic sequence alignment")
12459 (description "The alignment module of BioJava provides an API that
12463 @item implementations of dynamic programming algorithms for sequence
12465 @item reading and writing of popular alignment file formats;
12466 @item a single-, or multi- threaded multiple sequence alignment algorithm.
12469 (define-public dropseq-tools
12471 (name "dropseq-tools")
12476 (uri "http://mccarrolllab.com/download/1276/")
12477 (file-name (string-append "dropseq-tools-" version ".zip"))
12480 "0yrffckxqk5l8b5xb6z4laq157zd9mdypr2p4b4vq2bhjzi1sj0s"))
12481 ;; Delete bundled libraries
12482 (modules '((guix build utils)))
12485 (for-each delete-file (find-files "jar/lib" "\\.jar$"))
12486 (delete-file-recursively "3rdParty")
12488 (build-system ant-build-system)
12490 `(#:tests? #f ; test data are not included
12491 #:test-target "test"
12492 #:build-target "all"
12493 #:source-dir "public/src/"
12496 (list (string-append "-Dpicard.executable.dir="
12497 (assoc-ref %build-inputs "java-picard")
12499 #:modules ((ice-9 match)
12502 (guix build java-utils)
12503 (guix build ant-build-system))
12505 (modify-phases %standard-phases
12506 ;; FIXME: fails with "java.io.FileNotFoundException:
12507 ;; /gnu/store/…-dropseq-tools-1.13/share/java/lib/biojava-alignment.jar"
12508 (delete 'generate-jar-indices)
12509 ;; All dependencies must be linked to "lib", because that's where
12510 ;; they will be searched for when the Class-Path property of the
12511 ;; manifest is computed.
12512 (add-after 'unpack 'record-references
12513 (lambda* (#:key inputs #:allow-other-keys)
12514 (mkdir-p "jar/lib")
12515 (let ((dirs (filter-map (match-lambda
12517 (if (and (string-prefix? "java-" name)
12518 (not (string=? name "java-testng")))
12521 (for-each (lambda (jar)
12522 (symlink jar (string-append "jar/lib/" (basename jar))))
12523 (append-map (lambda (dir) (find-files dir "\\.jar$"))
12526 ;; There is no installation target
12528 (lambda* (#:key inputs outputs #:allow-other-keys)
12529 (let* ((out (assoc-ref outputs "out"))
12530 (bin (string-append out "/bin"))
12531 (share (string-append out "/share/java/"))
12532 (lib (string-append share "/lib/"))
12533 (scripts (list "BAMTagHistogram"
12534 "BAMTagofTagCounts"
12535 "BaseDistributionAtReadPosition"
12536 "CollapseBarcodesInPlace"
12537 "CollapseTagWithContext"
12539 "CreateIntervalsFiles"
12540 "DetectBeadSynthesisErrors"
12541 "DigitalExpression"
12542 "Drop-seq_alignment.sh"
12545 "GatherGeneGCLength"
12546 "GatherMolecularBarcodeDistributionByGene"
12547 "GatherReadQualityMetrics"
12550 "SelectCellsByNumTranscripts"
12551 "SingleCellRnaSeqMetricsCollector"
12552 "TagBamWithReadSequenceExtended"
12553 "TagReadWithGeneExon"
12554 "TagReadWithInterval"
12555 "TrimStartingSequence"
12556 "ValidateReference")))
12557 (for-each mkdir-p (list bin share lib))
12558 (install-file "dist/dropseq.jar" share)
12559 (for-each (lambda (script)
12560 (chmod script #o555)
12561 (install-file script bin))
12563 (substitute* (map (lambda (script)
12564 (string-append bin "/" script))
12566 (("^java") (which "java"))
12567 (("jar_deploy_dir=.*")
12568 (string-append "jar_deploy_dir=" share "\n"))))
12570 ;; FIXME: We do this after stripping jars because we don't want it to
12571 ;; copy all these jars and strip them. We only want to install
12572 ;; links. Arguably, this is a problem with the ant-build-system.
12573 (add-after 'strip-jar-timestamps 'install-links
12574 (lambda* (#:key outputs #:allow-other-keys)
12575 (let* ((out (assoc-ref outputs "out"))
12576 (share (string-append out "/share/java/"))
12577 (lib (string-append share "/lib/")))
12578 (for-each (lambda (jar)
12579 (symlink (readlink jar)
12580 (string-append lib (basename jar))))
12581 (find-files "jar/lib" "\\.jar$")))
12584 `(("jdk" ,icedtea-8)
12585 ("java-picard" ,java-picard-2.10.3)
12586 ("java-log4j-1.2-api" ,java-log4j-1.2-api)
12587 ("java-commons-math3" ,java-commons-math3)
12588 ("java-commons-jexl2" ,java-commons-jexl-2)
12589 ("java-commons-collections4" ,java-commons-collections4)
12590 ("java-commons-lang2" ,java-commons-lang)
12591 ("java-commons-io" ,java-commons-io)
12592 ("java-snappy-1.0.3-rc3" ,java-snappy-1)
12593 ("java-guava" ,java-guava)
12594 ("java-la4j" ,java-la4j)
12595 ("java-biojava-core" ,java-biojava-core-4.0)
12596 ("java-biojava-alignment" ,java-biojava-alignment-4.0)
12597 ("java-jdistlib" ,java-jdistlib)
12598 ("java-simple-xml" ,java-simple-xml)
12599 ("java-snakeyaml" ,java-snakeyaml)))
12602 ("java-testng" ,java-testng)))
12603 (home-page "http://mccarrolllab.com/dropseq/")
12604 (synopsis "Tools for Drop-seq analyses")
12605 (description "Drop-seq is a technology to enable biologists to
12606 analyze RNA expression genome-wide in thousands of individual cells at
12607 once. This package provides tools to perform Drop-seq analyses.")
12608 (license license:expat)))
12610 (define-public pigx-rnaseq
12612 (name "pigx-rnaseq")
12616 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_rnaseq/"
12617 "releases/download/v" version
12618 "/pigx_rnaseq-" version ".tar.gz"))
12621 "05gn658zpj9xki5dbs728z9zxq1mcm25hkwr5vzwqxsfi15l5f2l"))))
12622 (build-system gnu-build-system)
12624 `(#:parallel-tests? #f ; not supported
12626 (modify-phases %standard-phases
12627 ;; "test.sh" runs STAR, which requires excessive amounts of memory.
12628 (add-after 'unpack 'disable-resource-intensive-test
12630 (substitute* "Makefile.in"
12631 (("(^ tests/test_trim_galore/test.sh).*" _ m) m)
12632 (("^ tests/test_multiqc/test.sh") "")
12633 (("^ test.sh") ""))
12637 ("snakemake" ,snakemake)
12639 ("multiqc" ,multiqc)
12641 ("trim-galore" ,trim-galore)
12643 ("samtools" ,samtools)
12644 ("bedtools" ,bedtools)
12645 ("r-minimal" ,r-minimal)
12646 ("r-rmarkdown" ,r-rmarkdown)
12647 ("r-ggplot2" ,r-ggplot2)
12648 ("r-ggrepel" ,r-ggrepel)
12649 ("r-gprofiler" ,r-gprofiler)
12650 ("r-deseq2" ,r-deseq2)
12652 ("r-knitr" ,r-knitr)
12653 ("r-pheatmap" ,r-pheatmap)
12654 ("r-corrplot" ,r-corrplot)
12655 ("r-reshape2" ,r-reshape2)
12656 ("r-plotly" ,r-plotly)
12657 ("r-scales" ,r-scales)
12658 ("r-summarizedexperiment" ,r-summarizedexperiment)
12659 ("r-crosstalk" ,r-crosstalk)
12660 ("r-tximport" ,r-tximport)
12661 ("r-rtracklayer" ,r-rtracklayer)
12662 ("r-rjson" ,r-rjson)
12664 ("ghc-pandoc" ,ghc-pandoc)
12665 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12666 ("python-wrapper" ,python-wrapper)
12667 ("python-pyyaml" ,python-pyyaml)))
12668 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12669 (synopsis "Analysis pipeline for RNA sequencing experiments")
12670 (description "PiGX RNAseq is an analysis pipeline for preprocessing and
12671 reporting for RNA sequencing experiments. It is easy to use and produces high
12672 quality reports. The inputs are reads files from the sequencing experiment,
12673 and a configuration file which describes the experiment. In addition to
12674 quality control of the experiment, the pipeline produces a differential
12675 expression report comparing samples in an easily configurable manner.")
12676 (license license:gpl3+)))
12678 (define-public pigx-chipseq
12680 (name "pigx-chipseq")
12684 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_chipseq/"
12685 "releases/download/v" version
12686 "/pigx_chipseq-" version ".tar.gz"))
12689 "0y9x62cfwzhsp82imnawyamxp58bcb00yjxdy44spylqnjdlsaj8"))))
12690 (build-system gnu-build-system)
12691 ;; parts of the tests rely on access to the network
12692 (arguments '(#:tests? #f))
12695 ("coreutils" ,coreutils)
12696 ("r-minimal" ,r-minimal)
12697 ("r-argparser" ,r-argparser)
12698 ("r-biocparallel" ,r-biocparallel)
12699 ("r-biostrings" ,r-biostrings)
12700 ("r-chipseq" ,r-chipseq)
12701 ("r-data-table" ,r-data-table)
12702 ("r-dplyr" ,r-dplyr)
12703 ("r-genomation" ,r-genomation)
12704 ("r-genomicalignments" ,r-genomicalignments)
12705 ("r-genomicranges" ,r-genomicranges)
12706 ("r-rsamtools" ,r-rsamtools)
12707 ("r-rtracklayer" ,r-rtracklayer)
12708 ("r-s4vectors" ,r-s4vectors)
12709 ("r-stringr" ,r-stringr)
12710 ("r-tibble" ,r-tibble)
12711 ("r-tidyr" ,r-tidyr)
12712 ("r-jsonlite" ,r-jsonlite)
12713 ("r-heatmaply" ,r-heatmaply)
12714 ("r-htmlwidgets" ,r-htmlwidgets)
12715 ("r-ggplot2" ,r-ggplot2)
12716 ("r-plotly" ,r-plotly)
12717 ("r-rmarkdown" ,r-rmarkdown)
12718 ("python-wrapper" ,python-wrapper)
12719 ("python-pyyaml" ,python-pyyaml)
12720 ("python-magic" ,python-magic)
12721 ("python-xlrd" ,python-xlrd)
12722 ("trim-galore" ,trim-galore)
12724 ("multiqc" ,multiqc)
12726 ("ghc-pandoc" ,ghc-pandoc)
12727 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12731 ("snakemake" ,snakemake)
12732 ("samtools" ,samtools)
12733 ("bedtools" ,bedtools)
12734 ("kentutils" ,kentutils)))
12736 `(("python-pytest" ,python-pytest)))
12737 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12738 (synopsis "Analysis pipeline for ChIP sequencing experiments")
12739 (description "PiGX ChIPseq is an analysis pipeline for preprocessing, peak
12740 calling and reporting for ChIP sequencing experiments. It is easy to use and
12741 produces high quality reports. The inputs are reads files from the sequencing
12742 experiment, and a configuration file which describes the experiment. In
12743 addition to quality control of the experiment, the pipeline enables to set up
12744 multiple peak calling analysis and allows the generation of a UCSC track hub
12745 in an easily configurable manner.")
12746 (license license:gpl3+)))
12748 (define-public pigx-bsseq
12750 (name "pigx-bsseq")
12754 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_bsseq/"
12755 "releases/download/v" version
12756 "/pigx_bsseq-" version ".tar.gz"))
12759 "0l97wvkq4diq8lcarraj33bby1zzf0w804jwi8mlc5qddp8idwhy"))))
12760 (build-system gnu-build-system)
12763 (modify-phases %standard-phases
12764 (add-before 'check 'set-timezone
12765 ;; The readr package is picky about timezones.
12766 (lambda* (#:key inputs #:allow-other-keys)
12767 (setenv "TZ" "UTC+1")
12769 (string-append (assoc-ref inputs "tzdata")
12770 "/share/zoneinfo"))
12773 `(("tzdata" ,tzdata)))
12775 `(("coreutils" ,coreutils)
12778 ("r-minimal" ,r-minimal)
12779 ("r-annotationhub" ,r-annotationhub)
12781 ("r-genomation" ,r-genomation)
12782 ("r-methylkit" ,r-methylkit)
12783 ("r-rtracklayer" ,r-rtracklayer)
12784 ("r-rmarkdown" ,r-rmarkdown)
12785 ("r-bookdown" ,r-bookdown)
12786 ("r-ggplot2" ,r-ggplot2)
12787 ("r-ggbio" ,r-ggbio)
12788 ("ghc-pandoc" ,ghc-pandoc)
12789 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12790 ("python-wrapper" ,python-wrapper)
12791 ("python-pyyaml" ,python-pyyaml)
12792 ("snakemake" ,snakemake)
12793 ("bismark" ,bismark)
12796 ("trim-galore" ,trim-galore)
12797 ("cutadapt" ,cutadapt)
12798 ("samtools" ,samtools)))
12799 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12800 (synopsis "Bisulfite sequencing pipeline from fastq to methylation reports")
12801 (description "PiGx BSseq is a data processing pipeline for raw fastq read
12802 data of bisulfite experiments; it produces reports on aggregate methylation
12803 and coverage and can be used to produce information on differential
12804 methylation and segmentation.")
12805 (license license:gpl3+)))
12807 (define-public pigx-scrnaseq
12809 (name "pigx-scrnaseq")
12813 (uri (string-append "https://github.com/BIMSBbioinfo/pigx_scrnaseq/"
12814 "releases/download/v" version
12815 "/pigx_scrnaseq-" version ".tar.gz"))
12818 "131zarirv16w8653m0d66jgjnwqfsxqc0hix0rypssz4d83bl51j"))))
12819 (build-system gnu-build-system)
12821 `(#:configure-flags
12822 (list (string-append "PICARDJAR=" (assoc-ref %build-inputs "java-picard")
12823 "/share/java/picard.jar")
12824 (string-append "DROPSEQJAR=" (assoc-ref %build-inputs "dropseq-tools")
12825 "/share/java/dropseq.jar"))))
12827 `(("coreutils" ,coreutils)
12829 ("dropseq-tools" ,dropseq-tools)
12831 ("java-picard" ,java-picard-2.10.3) ; same as for dropseq
12832 ("java" ,icedtea-8)
12833 ("python-wrapper" ,python-wrapper)
12834 ("python-pyyaml" ,python-pyyaml)
12835 ("python-pandas" ,python-pandas)
12836 ("python-magic" ,python-magic)
12837 ("python-numpy" ,python-numpy)
12838 ("python-loompy" ,python-loompy-for-pigx-scrnaseq)
12839 ("ghc-pandoc" ,ghc-pandoc)
12840 ("ghc-pandoc-citeproc" ,ghc-pandoc-citeproc)
12841 ("samtools" ,samtools)
12842 ("snakemake" ,snakemake)
12844 ("r-minimal" ,r-minimal)
12845 ("r-argparser" ,r-argparser)
12846 ("r-cowplot" ,r-cowplot)
12847 ("r-data-table" ,r-data-table)
12848 ("r-delayedarray" ,r-delayedarray)
12849 ("r-delayedmatrixstats" ,r-delayedmatrixstats)
12850 ("r-dplyr" ,r-dplyr)
12851 ("r-dropbead" ,r-dropbead)
12853 ("r-genomicalignments" ,r-genomicalignments)
12854 ("r-genomicfiles" ,r-genomicfiles)
12855 ("r-genomicranges" ,r-genomicranges)
12856 ("r-ggplot2" ,r-ggplot2)
12857 ("r-hdf5array" ,r-hdf5array)
12858 ("r-pheatmap" ,r-pheatmap)
12859 ("r-rmarkdown" ,r-rmarkdown)
12860 ("r-rsamtools" ,r-rsamtools)
12861 ("r-rtracklayer" ,r-rtracklayer)
12862 ("r-rtsne" ,r-rtsne)
12863 ("r-scater" ,r-scater)
12864 ("r-scran" ,r-scran)
12865 ("r-singlecellexperiment" ,r-singlecellexperiment)
12866 ("r-stringr" ,r-stringr)
12867 ("r-yaml" ,r-yaml)))
12868 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12869 (synopsis "Analysis pipeline for single-cell RNA sequencing experiments")
12870 (description "PiGX scRNAseq is an analysis pipeline for preprocessing and
12871 quality control for single cell RNA sequencing experiments. The inputs are
12872 read files from the sequencing experiment, and a configuration file which
12873 describes the experiment. It produces processed files for downstream analysis
12874 and interactive quality reports. The pipeline is designed to work with UMI
12876 (license license:gpl3+)))
12878 (define-public pigx
12884 (uri (string-append "https://github.com/BIMSBbioinfo/pigx/"
12885 "releases/download/v" version
12886 "/pigx-" version ".tar.gz"))
12889 "1i5njdy1clj5ncw45d16p7mwmqvb1ilikl9n797pxklc3f4s7mq7"))))
12890 (build-system gnu-build-system)
12892 `(("python" ,python)
12893 ("pigx-bsseq" ,pigx-bsseq)
12894 ("pigx-chipseq" ,pigx-chipseq)
12895 ("pigx-rnaseq" ,pigx-rnaseq)
12896 ("pigx-scrnaseq" ,pigx-scrnaseq)))
12897 (home-page "http://bioinformatics.mdc-berlin.de/pigx/")
12898 (synopsis "Analysis pipelines for genomics")
12899 (description "PiGx is a collection of genomics pipelines. It includes the
12900 following pipelines:
12903 @item PiGx BSseq for raw fastq read data of bisulfite experiments
12904 @item PiGx RNAseq for RNAseq samples
12905 @item PiGx scRNAseq for single cell dropseq analysis
12906 @item PiGx ChIPseq for reads from ChIPseq experiments
12909 All pipelines are easily configured with a simple sample sheet and a
12910 descriptive settings file. The result is a set of comprehensive, interactive
12911 HTML reports with interesting findings about your samples.")
12912 (license license:gpl3+)))
12914 (define-public genrich
12920 (uri (git-reference
12921 (url "https://github.com/jsh58/Genrich.git")
12922 (commit (string-append "v" version))))
12925 "0x0q6z0208n3cxzqjla4rgjqpyqgwpmz27852lcvzkzaigymq4zp"))))
12926 (build-system gnu-build-system)
12928 `(#:tests? #f ; there are none
12930 (modify-phases %standard-phases
12931 (delete 'configure)
12933 (lambda* (#:key outputs #:allow-other-keys)
12934 (install-file "Genrich" (string-append (assoc-ref outputs "out") "/bin"))
12938 (home-page "https://github.com/jsh58/Genrich")
12939 (synopsis "Detecting sites of genomic enrichment")
12940 (description "Genrich is a peak-caller for genomic enrichment
12941 assays (e.g. ChIP-seq, ATAC-seq). It analyzes alignment files generated
12942 following the assay and produces a file detailing peaks of significant
12944 (license license:expat)))
12946 (define-public mantis
12947 (let ((commit "4ffd171632c2cb0056a86d709dfd2bf21bc69b84")
12951 (version (git-version "0" revision commit))
12954 (uri (git-reference
12955 (url "https://github.com/splatlab/mantis.git")
12957 (file-name (git-file-name name version))
12960 "0iqbr0dhmlc8mzpirmm2s4pkzkwdgrcx50yx6cv3wlr2qi064p55"))))
12961 (build-system cmake-build-system)
12962 (arguments '(#:tests? #f)) ; there are none
12964 `(("sdsl-lite" ,sdsl-lite)
12965 ("openssl" ,openssl)
12967 (home-page "https://github.com/splatlab/mantis")
12968 (synopsis "Large-scale sequence-search index data structure")
12969 (description "Mantis is a space-efficient data structure that can be
12970 used to index thousands of raw-read genomics experiments and facilitate
12971 large-scale sequence searches on those experiments. Mantis uses counting
12972 quotient filters instead of Bloom filters, enabling rapid index builds and
12973 queries, small indexes, and exact results, i.e., no false positives or
12974 negatives. Furthermore, Mantis is also a colored de Bruijn graph
12975 representation, so it supports fast graph traversal and other topological
12976 analyses in addition to large-scale sequence-level searches.")
12977 ;; uses __uint128_t and inline assembly
12978 (supported-systems '("x86_64-linux"))
12979 (license license:bsd-3))))
12981 (define-public r-diversitree
12983 (name "r-diversitree")
12988 (uri (cran-uri "diversitree" version))
12991 "1jqfjmmaigq581l4zxysmkhld0xv6izlbr1hihf9zplkix36majc"))))
12992 (build-system r-build-system)
12994 `(("gfortran" ,gfortran)))
12995 (inputs `(("fftw" ,fftw) ("gsl" ,gsl)))
12998 ("r-desolve" ,r-desolve)
13000 ("r-subplex" ,r-subplex)))
13001 (home-page "https://www.zoology.ubc.ca/prog/diversitree")
13002 (synopsis "Comparative 'phylogenetic' analyses of diversification")
13003 (description "This package contains a number of comparative \"phylogenetic\"
13004 methods, mostly focusing on analysing diversification and character evolution.
13005 Contains implementations of \"BiSSE\" (Binary State Speciation and Extinction)
13006 and its unresolved tree extensions, \"MuSSE\" (Multiple State Speciation and
13007 Extinction), \"QuaSSE\", \"GeoSSE\", and \"BiSSE-ness\" Other included methods
13008 include Markov models of discrete and continuous trait evolution and constant
13009 rate speciation and extinction.")
13010 (license license:gpl2+)))
13012 (define-public sjcount
13013 ;; There is no tag for version 3.2, nor is there a release archive.
13014 (let ((commit "292d3917cadb3f6834c81e509c30e61cd7ead6e5")
13018 (version (git-version "3.2" revision commit))
13021 (uri (git-reference
13022 (url "https://github.com/pervouchine/sjcount-full.git")
13024 (file-name (string-append name "-" version "-checkout"))
13027 "0gdgj35j249f04rqgq8ymcc1xg1vi9kzbajnjqpaq2wpbh8bl234"))))
13028 (build-system gnu-build-system)
13030 `(#:tests? #f ; requires a 1.4G test file
13032 (list (string-append "SAMTOOLS_DIR="
13033 (assoc-ref %build-inputs "samtools")
13036 (modify-phases %standard-phases
13037 (replace 'configure
13038 (lambda* (#:key inputs #:allow-other-keys)
13039 (substitute* "makefile"
13040 (("-I \\$\\{SAMTOOLS_DIR\\}")
13041 (string-append "-I" (assoc-ref inputs "samtools")
13042 "/include/samtools"))
13043 (("-lz ") "-lz -lpthread "))
13046 (lambda* (#:key outputs #:allow-other-keys)
13047 (for-each (lambda (tool)
13049 (string-append (assoc-ref outputs "out")
13051 '("j_count" "b_count" "sjcount"))
13054 `(("samtools" ,samtools-0.1)
13056 (home-page "https://github.com/pervouchine/sjcount-full/")
13057 (synopsis "Annotation-agnostic splice junction counting pipeline")
13058 (description "Sjcount is a utility for fast quantification of splice
13059 junctions in RNA-seq data. It is annotation-agnostic and offset-aware. This
13060 version does count multisplits.")
13061 (license license:gpl3+))))
13063 (define-public minimap2
13070 (uri (string-append "https://github.com/lh3/minimap2/"
13071 "releases/download/v" version "/"
13072 "minimap2-" version ".tar.bz2"))
13075 "080w9066irkbhbyr4nmf19pzkdd2s4v31hpzlajgq2y0drr6zcsj"))))
13076 (build-system gnu-build-system)
13078 `(#:tests? #f ; there are none
13081 (let ((system ,(or (%current-target-system)
13082 (%current-system))))
13084 ((string-prefix? "x86_64" system)
13086 ((or (string-prefix? "armhf" system)
13087 (string-prefix? "aarch64" system))
13089 (_ "sse2only=1"))))
13091 (modify-phases %standard-phases
13092 (delete 'configure)
13094 (lambda* (#:key outputs #:allow-other-keys)
13095 (let* ((out (assoc-ref outputs "out"))
13096 (bin (string-append out "/bin"))
13097 (man (string-append out "/share/man/man1")))
13098 (install-file "minimap2" bin)
13100 (install-file "minimap2.1" man))
13104 (home-page "https://lh3.github.io/minimap2/")
13105 (synopsis "Pairwise aligner for genomic and spliced nucleotide sequences")
13106 (description "Minimap2 is a versatile sequence alignment program that
13107 aligns DNA or mRNA sequences against a large reference database. Typical use
13111 @item mapping PacBio or Oxford Nanopore genomic reads to the human genome;
13112 @item finding overlaps between long reads with error rate up to ~15%;
13113 @item splice-aware alignment of PacBio Iso-Seq or Nanopore cDNA or Direct RNA
13114 reads against a reference genome;
13115 @item aligning Illumina single- or paired-end reads;
13116 @item assembly-to-assembly alignment;
13117 @item full-genome alignment between two closely related species with
13118 divergence below ~15%.
13120 (license license:expat)))
13122 (define-public r-circus
13129 (uri (git-reference
13130 (url "https://github.com/BIMSBbioinfo/ciRcus.git")
13131 (commit (string-append "v" version))))
13132 (file-name (git-file-name name version))
13135 "0jhjn3ilb057hbf6yzrihj13ifxxs32y7nkby8l3lkm28dg4p97h"))))
13136 (build-system r-build-system)
13138 `(("r-annotationdbi" ,r-annotationdbi)
13139 ("r-annotationhub" ,r-annotationhub)
13140 ("r-biomart" ,r-biomart)
13141 ("r-data-table" ,r-data-table)
13143 ("r-genomicfeatures" ,r-genomicfeatures)
13144 ("r-genomicranges" ,r-genomicranges)
13145 ("r-ggplot2" ,r-ggplot2)
13147 ("r-iranges" ,r-iranges)
13148 ("r-rcolorbrewer" ,r-rcolorbrewer)
13149 ("r-rmysql" ,r-rmysql)
13150 ("r-s4vectors" ,r-s4vectors)
13151 ("r-stringr" ,r-stringr)
13152 ("r-summarizedexperiment" ,r-summarizedexperiment)))
13154 `(("r-knitr" ,r-knitr)))
13155 (home-page "https://github.com/BIMSBbioinfo/ciRcus")
13156 (synopsis "Annotation, analysis and visualization of circRNA data")
13157 (description "Circus is an R package for annotation, analysis and
13158 visualization of circRNA data. Users can annotate their circRNA candidates
13159 with host genes, gene featrues they are spliced from, and discriminate between
13160 known and yet unknown splice junctions. Circular-to-linear ratios of circRNAs
13161 can be calculated, and a number of descriptive plots easily generated.")
13162 (license license:artistic2.0)))
13164 (define-public r-loomr
13165 (let ((commit "df0144bd2bbceca6fadef9edc1bbc5ca672d4739")
13169 (version (git-version "0.2.0" revision commit))
13173 (uri (git-reference
13174 (url "https://github.com/mojaveazure/loomR.git")
13176 (file-name (git-file-name name version))
13179 "1b1g4dlmfdyhn56bz1mkh9ymirri43wiz7rjhs7py3y7bdw1s3yr"))))
13180 (build-system r-build-system)
13183 ("r-hdf5r" ,r-hdf5r)
13184 ("r-iterators" ,r-iterators)
13185 ("r-itertools" ,r-itertools)
13186 ("r-matrix" ,r-matrix)))
13187 (home-page "https://github.com/mojaveazure/loomR")
13188 (synopsis "R interface for loom files")
13189 (description "This package provides an R interface to access, create,
13190 and modify loom files. loomR aims to be completely compatible with loompy.")
13191 (license license:gpl3))))
13193 (define-public gffread
13194 ;; We cannot use the tagged release because it is not in sync with gclib.
13195 ;; See https://github.com/gpertea/gffread/issues/26
13196 (let ((commit "ba7535fcb3cea55a6e5a491d916e93b454e87fd0")
13200 (version (git-version "0.9.12" revision commit))
13204 (uri (git-reference
13205 (url "https://github.com/gpertea/gffread.git")
13207 (file-name (git-file-name name version))
13210 "1dl2nbcg96lxpd0drg48ssa8343nf7pw9s9mkrc4mjjmfwsin3ki"))))
13211 (build-system gnu-build-system)
13213 `(#:tests? #f ; no check target
13215 (list "GCLDIR=gclib")
13217 (modify-phases %standard-phases
13218 (delete 'configure)
13219 (add-after 'unpack 'copy-gclib-source
13220 (lambda* (#:key inputs #:allow-other-keys)
13222 (copy-recursively (assoc-ref inputs "gclib-source") "gclib")
13224 ;; There is no install target
13226 (lambda* (#:key outputs #:allow-other-keys)
13227 (let* ((out (assoc-ref outputs "out"))
13228 (bin (string-append out "/bin")))
13229 (install-file "gffread" bin))
13233 ,(let ((version "0.10.3")
13234 (commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13238 (uri (git-reference
13239 (url "https://github.com/gpertea/gclib.git")
13241 (file-name (git-file-name "gclib" version))
13244 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13245 (home-page "https://github.com/gpertea/gffread/")
13246 (synopsis "Parse and convert GFF/GTF files")
13248 "This package provides a GFF/GTF file parsing utility providing format
13249 conversions, region filtering, FASTA sequence extraction and more.")
13250 ;; gffread is under Expat, but gclib is under Artistic 2.0
13251 (license (list license:expat
13252 license:artistic2.0)))))
13254 (define-public find-circ
13255 ;; The last release was in 2015. The license was clarified in 2017, so we
13256 ;; take the latest commit.
13257 (let ((commit "8655dca54970fcf7e92e22fbf57e1188724dda7d")
13261 (version (git-version "1.2" revision commit))
13265 (uri (git-reference
13266 (url "https://github.com/marvin-jens/find_circ.git")
13268 (file-name (git-file-name name version))
13271 "0p77pbqbclqr4srms34y1b9b4njybfpjiknc11ki84f3p8skb3cg"))))
13272 (build-system gnu-build-system)
13274 `(#:tests? #f ; there are none
13276 ;; There is no actual build system.
13277 (modify-phases %standard-phases
13278 (delete 'configure)
13281 (lambda* (#:key outputs #:allow-other-keys)
13282 (let* ((out (assoc-ref outputs "out"))
13283 (bin (string-append out "/bin"))
13284 (path (getenv "PYTHONPATH")))
13285 (for-each (lambda (script)
13286 (install-file script bin)
13287 (wrap-program (string-append bin "/" script)
13288 `("PYTHONPATH" ":" prefix (,path))))
13293 "unmapped2anchors.py")))
13296 `(("python2" ,python-2)
13297 ("python2-pysam" ,python2-pysam)
13298 ("python2-numpy" ,python2-numpy)))
13299 (home-page "https://github.com/marvin-jens/find_circ")
13300 (synopsis "circRNA detection from RNA-seq reads")
13301 (description "This package provides tools to detect head-to-tail
13302 spliced (back-spliced) sequencing reads, indicative of circular RNA (circRNA)
13304 (license license:gpl3))))
13306 (define-public python-scanpy
13308 (name "python-scanpy")
13310 ;; Fetch from git because the pypi tarball does not include tests.
13314 (uri (git-reference
13315 (url "https://github.com/theislab/scanpy.git")
13317 (file-name (git-file-name name version))
13320 "0zn6x6c0cnm1a20i6isigwb51g3pr9zpjk8r1minjqnxi5yc9pm4"))))
13321 (build-system python-build-system)
13324 (modify-phases %standard-phases
13326 (lambda* (#:key inputs #:allow-other-keys)
13327 ;; These tests require Internet access.
13328 (delete-file-recursively "scanpy/tests/notebooks")
13329 (delete-file "scanpy/tests/test_clustering.py")
13331 ;; TODO: I can't get the plotting tests to work, even with Xvfb.
13332 (delete-file "scanpy/tests/test_plotting.py")
13333 (delete-file "scanpy/tests/test_preprocessing.py")
13334 (delete-file "scanpy/tests/test_read_10x.py")
13336 (setenv "PYTHONPATH"
13337 (string-append (getcwd) ":"
13338 (getenv "PYTHONPATH")))
13342 `(("python-anndata" ,python-anndata)
13343 ("python-h5py" ,python-h5py)
13344 ("python-igraph" ,python-igraph)
13345 ("python-joblib" ,python-joblib)
13346 ("python-louvain" ,python-louvain)
13347 ("python-matplotlib" ,python-matplotlib)
13348 ("python-natsort" ,python-natsort)
13349 ("python-networkx" ,python-networkx)
13350 ("python-numba" ,python-numba)
13351 ("python-pandas" ,python-pandas)
13352 ("python-scikit-learn" ,python-scikit-learn)
13353 ("python-scipy" ,python-scipy)
13354 ("python-seaborn" ,python-seaborn)
13355 ("python-statsmodels" ,python-statsmodels)
13356 ("python-tables" ,python-tables)))
13358 `(("python-pytest" ,python-pytest)))
13359 (home-page "https://github.com/theislab/scanpy")
13360 (synopsis "Single-Cell Analysis in Python.")
13361 (description "Scanpy is a scalable toolkit for analyzing single-cell gene
13362 expression data. It includes preprocessing, visualization, clustering,
13363 pseudotime and trajectory inference and differential expression testing. The
13364 Python-based implementation efficiently deals with datasets of more than one
13366 (license license:bsd-3)))
13368 (define-public python-bbknn
13370 (name "python-bbknn")
13375 (uri (pypi-uri "bbknn" version))
13378 "1qgdganvj3lyxj84v7alm23b9vqhwpn8z0115qndpnpy90qxynwz"))))
13379 (build-system python-build-system)
13381 `(("python-annoy" ,python-annoy)
13382 ("python-cython" ,python-cython)
13383 ("python-faiss" ,python-faiss)
13384 ("python-numpy" ,python-numpy)
13385 ("python-scanpy" ,python-scanpy)))
13386 (home-page "https://github.com/Teichlab/bbknn")
13387 (synopsis "Batch balanced KNN")
13388 (description "BBKNN is a batch effect removal tool that can be directly
13389 used in the Scanpy workflow. It serves as an alternative to
13390 @code{scanpy.api.pp.neighbors()}, with both functions creating a neighbour
13391 graph for subsequent use in clustering, pseudotime and UMAP visualisation. If
13392 technical artifacts are present in the data, they will make it challenging to
13393 link corresponding cell types across different batches. BBKNN actively
13394 combats this effect by splitting your data into batches and finding a smaller
13395 number of neighbours for each cell within each of the groups. This helps
13396 create connections between analogous cells in different batches without
13397 altering the counts or PCA space.")
13398 (license license:expat)))
13400 (define-public gffcompare
13401 (let ((commit "be56ef4349ea3966c12c6397f85e49e047361c41")
13404 (name "gffcompare")
13405 (version (git-version "0.10.15" revision commit))
13409 (uri (git-reference
13410 (url "https://github.com/gpertea/gffcompare/")
13412 (file-name (git-file-name name version))
13414 (base32 "0cp5qpxdhw4mxpya5dld8wi3jk00zyklm6rcri426wydinrnfmkg"))))
13415 (build-system gnu-build-system)
13417 `(#:tests? #f ; no check target
13419 (modify-phases %standard-phases
13420 (delete 'configure)
13421 (add-before 'build 'copy-gclib-source
13422 (lambda* (#:key inputs #:allow-other-keys)
13425 (assoc-ref inputs "gclib-source") "../gclib")
13428 (lambda* (#:key outputs #:allow-other-keys)
13429 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
13430 (install-file "gffcompare" bin)
13433 `(("gclib-source" ; see 'README.md' of gffcompare
13434 ,(let ((commit "54917d0849c1e83cfb057b5f712e5cb6a35d948f")
13437 (version (git-version "0.10.3" revision commit)))
13440 (uri (git-reference
13441 (url "https://github.com/gpertea/gclib/")
13443 (file-name (git-file-name name version))
13445 (base32 "0b51lc0b8syrv7186fd7n8f15rwnf264qgfmm2palrwks1px24mr")))))))
13446 (home-page "https://github.com/gpertea/gffcompare/")
13447 (synopsis "Tool for comparing or classifing transcripts of RNA-Seq")
13449 "@code{gffcompare} is a tool that can:
13451 @item compare and evaluate the accuracy of RNA-Seq transcript assemblers
13452 (Cufflinks, Stringtie);
13453 @item collapse (merge) duplicate transcripts from multiple GTF/GFF3 files (e.g.
13454 resulted from assembly of different samples);
13455 @item classify transcripts from one or multiple GTF/GFF3 files as they relate to
13456 reference transcripts provided in a annotation file (also in GTF/GFF3 format).
13460 license:expat ;license for gffcompare
13461 license:artistic2.0))))) ;license for gclib
13463 (define-public python-intervaltree
13465 (name "python-intervaltree")
13470 (uri (pypi-uri "intervaltree" version))
13473 "02w191m9zxkcjqr1kv2slxvhymwhj3jnsyy3a28b837pi15q19dc"))))
13474 (build-system python-build-system)
13475 ;; FIXME: error when collecting tests
13476 (arguments '(#:tests? #f))
13478 `(("python-sortedcontainers" ,python-sortedcontainers)))
13480 `(("python-pytest" ,python-pytest)))
13481 (home-page "https://github.com/chaimleib/intervaltree")
13482 (synopsis "Editable interval tree data structure")
13484 "This package provides a mutable, self-balancing interval tree
13485 implementation for Python. Queries may be by point, by range overlap, or by
13486 range envelopment. This library was designed to allow tagging text and time
13487 intervals, where the intervals include the lower bound but not the upper
13489 (license license:asl2.0)))
13491 (define-public python-pypairix
13493 (name "python-pypairix")
13498 (uri (pypi-uri "pypairix" version))
13501 "0zs92b74s5v4xy2h16s15f3z6l4nnbw8x8zyif7xx5xpafjn0xss"))))
13502 (build-system python-build-system)
13503 ;; FIXME: the tests fail because test.support cannot be loaded:
13504 ;; ImportError: cannot import name 'support'
13505 (arguments '(#:tests? #f))
13508 (home-page "https://github.com/4dn-dcic/pairix")
13509 (synopsis "Support for querying pairix-indexed bgzipped text files")
13511 "Pypairix is a Python module for fast querying on a pairix-indexed
13512 bgzipped text file that contains a pair of genomic coordinates per line.")
13513 (license license:expat)))
13515 (define-public python-pyfaidx
13517 (name "python-pyfaidx")
13518 (version "0.5.4.2")
13522 (uri (pypi-uri "pyfaidx" version))
13525 "0y5zyjksj1rdglj601xd2bbni5abhdh622y3ck76chyzxz9z4rx8"))))
13526 (build-system python-build-system)
13528 `(("python-setuptools" ,python-setuptools)
13529 ("python-six" ,python-six)))
13530 (home-page "http://mattshirley.com")
13531 (synopsis "Random access to fasta subsequences")
13533 "This package provides procedures for efficient pythonic random access to
13534 fasta subsequences.")
13535 (license license:bsd-3)))
13537 (define-public python-cooler
13539 (name "python-cooler")
13544 (uri (pypi-uri "cooler" version))
13547 "08k5nxnxa6qsbk15z5z0q01n28042k87wi4905hh95rzqib15mhx"))))
13548 (build-system python-build-system)
13550 `(("python-biopython" ,python-biopython)
13551 ("python-click" ,python-click)
13552 ("python-cytoolz" ,python-cytoolz)
13553 ("python-dask" ,python-dask)
13554 ("python-h5py" ,python-h5py)
13555 ("python-multiprocess" ,python-multiprocess)
13556 ("python-pandas" ,python-pandas)
13557 ("python-pyfaidx" ,python-pyfaidx)
13558 ("python-pypairix" ,python-pypairix)
13559 ("python-pysam" ,python-pysam)
13560 ("python-scipy" ,python-scipy)))
13562 `(("python-mock" ,python-mock)
13563 ("python-nose" ,python-nose)
13564 ("python-numpydoc" ,python-numpydoc)
13565 ("python-sphinx" ,python-sphinx)))
13566 (home-page "https://github.com/mirnylab/cooler")
13567 (synopsis "Sparse binary format for genomic interaction matrices")
13569 "Cooler is a support library for a sparse, compressed, binary persistent
13570 storage format, called @code{cool}, used to store genomic interaction data,
13571 such as Hi-C contact matrices.")
13572 (license license:bsd-3)))
13574 (define-public python-hicexplorer
13576 (name "python-hicexplorer")
13580 ;; The latest version is not available on Pypi.
13582 (uri (git-reference
13583 (url "https://github.com/deeptools/HiCExplorer.git")
13585 (file-name (git-file-name name version))
13588 "0q5gpbzmrkvygqgw524q36b4nrivcmyi5v194vsx0qw7b3gcmq08"))))
13589 (build-system python-build-system)
13592 (modify-phases %standard-phases
13593 (add-after 'unpack 'loosen-up-requirements
13595 (substitute* "setup.py"
13599 `(("python-biopython" ,python-biopython)
13600 ("python-configparser" ,python-configparser)
13601 ("python-cooler" ,python-cooler)
13602 ("python-future" ,python-future)
13603 ("python-intervaltree" ,python-intervaltree)
13604 ("python-jinja2" ,python-jinja2)
13605 ("python-matplotlib" ,python-matplotlib)
13606 ("python-numpy" ,python-numpy)
13607 ("python-pandas" ,python-pandas)
13608 ("python-pybigwig" ,python-pybigwig)
13609 ("python-pysam" ,python-pysam)
13610 ("python-scipy" ,python-scipy)
13611 ("python-six" ,python-six)
13612 ("python-tables" ,python-tables)
13613 ("python-unidecode" ,python-unidecode)))
13614 (home-page "http://hicexplorer.readthedocs.io")
13615 (synopsis "Process, analyze and visualize Hi-C data")
13617 "HiCExplorer is a powerful and easy to use set of tools to process,
13618 normalize and visualize Hi-C data. HiCExplorer facilitates the creation of
13619 contact matrices, correction of contacts, TAD detection, A/B compartments,
13620 merging, reordering or chromosomes, conversion from different formats
13621 including cooler and detection of long-range contacts. Moreover, it allows
13622 the visualization of multiple contact matrices along with other types of data
13623 like genes, compartments, ChIP-seq coverage tracks (and in general any type of
13624 genomic scores), long range contacts and the visualization of viewpoints.")
13625 (license license:gpl3)))
13627 (define-public python-pygenometracks
13629 (name "python-pygenometracks")
13634 (uri (pypi-uri "pyGenomeTracks" version))
13637 "1fws6bqsyy9kj3qiabhkqx4wd4i775gsxnhszqd3zg7w67sc1ic5"))))
13638 (build-system python-build-system)
13640 `(("python-configparser" ,python-configparser)
13641 ("python-future" ,python-future)
13642 ("python-hicexplorer" ,python-hicexplorer)
13643 ("python-intervaltree" ,python-intervaltree)
13644 ("python-matplotlib" ,python-matplotlib)
13645 ("python-numpy" ,python-numpy)
13646 ("python-pybigwig" ,python-pybigwig)))
13648 `(("python-pytest" ,python-pytest)))
13649 (home-page "https://pygenometracks.readthedocs.io")
13650 (synopsis "Program and library to plot beautiful genome browser tracks")
13652 "This package aims to produce high-quality genome browser tracks that
13653 are highly customizable. Currently, it is possible to plot: bigwig, bed (many
13654 options), bedgraph, links (represented as arcs), and Hi-C matrices.
13655 pyGenomeTracks can make plots with or without Hi-C data.")
13656 (license license:gpl3+)))
13658 (define-public python-hic2cool
13660 (name "python-hic2cool")
13665 (uri (pypi-uri "hic2cool" version))
13668 "0xy6mhfns2lzib1kcr6419jjp6pmh0qx8z8na55lmiwn0ds8q9cl"))))
13669 (build-system python-build-system)
13670 (arguments '(#:tests? #f)) ; no tests included
13672 `(("python-cooler" ,python-cooler)))
13673 (home-page "https://github.com/4dn-dcic/hic2cool")
13674 (synopsis "Converter for .hic and .cool files")
13676 "This package provides a converter between @code{.hic} files (from
13677 juicer) and single-resolution or multi-resolution @code{.cool} files (for
13678 cooler). Both @code{hic} and @code{cool} files describe Hi-C contact
13680 (license license:expat)))
13682 (define-public r-pore
13690 (string-append "mirror://sourceforge/rpore/" version
13691 "/poRe_" version ".tar.gz"))
13693 (base32 "0pih9nljbv8g4x8rkk29i7aqq681b782r5s5ynp4nw9yzqnmmksv"))))
13694 (properties `((upstream-name . "poRe")))
13695 (build-system r-build-system)
13697 `(("r-bit64" ,r-bit64)
13698 ("r-data-table" ,r-data-table)
13699 ("r-rhdf5" ,r-rhdf5)
13700 ("r-shiny" ,r-shiny)
13701 ("r-svdialogs" ,r-svdialogs)))
13702 (home-page "https://sourceforge.net/projects/rpore/")
13703 (synopsis "Visualize Nanopore sequencing data")
13705 "This package provides graphical user interfaces to organize and visualize Nanopore
13707 ;; This is free software but the license variant is unclear:
13708 ;; <https://github.com/mw55309/poRe_docs/issues/10>.
13709 (license license:bsd-3)))
13711 (define-public r-xbioc
13712 (let ((revision "1")
13713 (commit "f798c187e376fd1ba27abd559f47bbae7e3e466b"))
13716 (version (git-version "0.1.15" revision commit))
13719 (uri (git-reference
13720 (url "https://github.com/renozao/xbioc.git")
13722 (file-name (git-file-name name version))
13725 "03hffh2f6z71y6l6dqpa5cql3hdaw7zigdi8sm2dzgx379k9rgrr"))))
13726 (build-system r-build-system)
13728 `(("r-annotationdbi" ,r-annotationdbi)
13729 ("r-assertthat" ,r-assertthat)
13730 ("r-biobase" ,r-biobase)
13731 ("r-biocinstaller" ,r-biocinstaller)
13732 ("r-digest" ,r-digest)
13733 ("r-pkgmaker" ,r-pkgmaker)
13735 ("r-reshape2" ,r-reshape2)
13736 ("r-stringr" ,r-stringr)))
13737 (home-page "https://github.com/renozao/xbioc/")
13738 (synopsis "Extra base functions for Bioconductor")
13739 (description "This package provides extra utility functions to perform
13740 common tasks in the analysis of omics data, leveraging and enhancing features
13741 provided by Bioconductor packages.")
13742 (license license:gpl3+))))
13744 (define-public r-cssam
13745 (let ((revision "1")
13746 (commit "9ec58c982fa551af0d80b1a266890d92954833f2"))
13749 (version (git-version "1.4" revision commit))
13752 (uri (git-reference
13753 (url "https://github.com/shenorrLab/csSAM.git")
13755 (file-name (git-file-name name version))
13758 "128syf9v39gk0z3ip000qpsjbg6l1siyq6c8b0hz41dzg5achyb3"))))
13759 (build-system r-build-system)
13761 `(("r-formula" ,r-formula)
13762 ("r-ggplot2" ,r-ggplot2)
13763 ("r-pkgmaker" ,r-pkgmaker)
13765 ("r-rngtools" ,r-rngtools)
13766 ("r-scales" ,r-scales)))
13767 (home-page "https://github.com/shenorrLab/csSAM/")
13768 (synopsis "Cell type-specific statistical analysis of microarray")
13769 (description "This package implements the method csSAM that computes
13770 cell-specific differential expression from measured cell proportions using
13773 (license license:lgpl2.1+))))
13775 (define-public r-bseqsc
13776 (let ((revision "1")
13777 (commit "fef3f3e38dcf3df37103348b5780937982b43b98"))
13780 (version (git-version "1.0" revision commit))
13783 (uri (git-reference
13784 (url "https://github.com/shenorrLab/bseqsc.git")
13786 (file-name (git-file-name name version))
13789 "1prw13wa20f7wlc3gkkls66n1kxz8d28qrb8icfqdwdnnv8w5qg8"))))
13790 (build-system r-build-system)
13792 `(("r-abind" ,r-abind)
13793 ("r-annotationdbi" ,r-annotationdbi)
13794 ("r-biobase" ,r-biobase)
13795 ("r-cssam" ,r-cssam)
13796 ("r-dplyr" ,r-dplyr)
13797 ("r-e1071" ,r-e1071)
13798 ("r-edger" ,r-edger)
13799 ("r-ggplot2" ,r-ggplot2)
13801 ("r-openxlsx" ,r-openxlsx)
13802 ("r-pkgmaker" ,r-pkgmaker)
13804 ("r-preprocesscore" ,r-preprocesscore)
13805 ("r-rngtools" ,r-rngtools)
13806 ("r-scales" ,r-scales)
13807 ("r-stringr" ,r-stringr)
13808 ("r-xbioc" ,r-xbioc)))
13809 (home-page "https://github.com/shenorrLab/bseqsc")
13810 (synopsis "Deconvolution of bulk sequencing experiments using single cell data")
13811 (description "BSeq-sc is a bioinformatics analysis pipeline that
13812 leverages single-cell sequencing data to estimate cell type proportion and
13813 cell type-specific gene expression differences from RNA-seq data from bulk
13814 tissue samples. This is a companion package to the publication \"A
13815 single-cell transcriptomic map of the human and mouse pancreas reveals inter-
13816 and intra-cell population structure.\" Baron et al. Cell Systems (2016)
13817 @url{https://www.ncbi.nlm.nih.gov/pubmed/27667365}.")
13818 (license license:gpl2+))))
13820 (define-public porechop
13821 ;; The recommended way to install is to clone the git repository
13822 ;; https://github.com/rrwick/Porechop#installation
13823 (let ((commit "289d5dca4a5fc327f97b3f8cecb68ecaf1014861")
13827 (version (git-version "0.2.3" revision commit))
13831 (uri (git-reference
13832 (url "https://github.com/rrwick/Porechop.git")
13834 (file-name (git-file-name name version))
13836 (base32 "05ps43gig0d3ia9x5lj84lb00hbsl6ba9n7y7jz927npxbr2ym23"))))
13837 (build-system python-build-system)
13838 (home-page "https://github.com/rrwick/porechop")
13839 (synopsis "Finding, trimming or splitting adapters, in Oxford Nanopore reads")
13841 "The porechop package is a tool for finding and removing adapters from Oxford
13842 Nanopore reads. Adapters on the ends of reads are trimmed off, and when a read
13843 has an adapter in its middle, it is treated as chimeric and chopped into
13844 separate reads. Porechop performs thorough alignments to effectively find
13845 adapters, even at low sequence identity. Porechop also supports demultiplexing
13846 of Nanopore reads that were barcoded with the Native Barcoding Kit, PCR
13847 Barcoding Kit or Rapid Barcoding Kit.")
13848 (license license:gpl3+))))
13850 (define-public poretools
13851 ;; The latest release was in 2016 and the latest commit is from 2017
13852 ;; the recommended way to install is to clone the git repository
13853 ;; https://poretools.readthedocs.io/en/latest/content/installation.html
13854 (let ((commit "e426b1f09e86ac259a00c261c79df91510777407")
13858 (version (git-version "0.6.0" revision commit))
13862 (uri (git-reference
13863 (url "https://github.com/arq5x/poretools.git")
13865 (file-name (git-file-name name version))
13867 (base32 "0bglj833wxpp3cq430p1d3xp085ls221js2y90w7ir2x5ay8l7am"))))
13868 (build-system python-build-system)
13869 ;; requires python >=2.7, <3.0, and the same for python dependencies
13870 (arguments `(#:python ,python-2))
13874 `(("python-dateutil" ,python2-dateutil)
13875 ("python-h5py" ,python2-h5py)
13876 ("python-matplotlib" ,python2-matplotlib)
13877 ("python-pandas" ,python2-pandas)
13878 ("python-seaborn" ,python2-seaborn)))
13879 (home-page "https://poretools.readthedocs.io")
13880 (synopsis "Toolkit for working with nanopore sequencing data")
13882 "The MinION from Oxford Nanopore Technologies is a nanopore sequencer.
13883 This @code{poretools} package is a flexible toolkit for exploring datasets
13884 generated by nanopore sequencing devices for the purposes of quality control and
13885 downstream analysis. Poretools operates directly on the native FAST5, a variant
13886 of the Hierarchical Data Format (HDF5) standard.")
13887 (license license:expat))))
13889 (define-public r-absfiltergsea
13891 (name "r-absfiltergsea")
13896 (uri (cran-uri "AbsFilterGSEA" version))
13898 (base32 "15srxkxsvn38kd5frdrwfdf0ad8gskrd0h01wmdf9hglq8fjrp7w"))))
13899 (properties `((upstream-name . "AbsFilterGSEA")))
13900 (build-system r-build-system)
13902 `(("r-biobase" ,r-biobase)
13903 ("r-deseq" ,r-deseq)
13904 ("r-limma" ,r-limma)
13906 ("r-rcpparmadillo" ,r-rcpparmadillo)))
13907 (home-page "https://cran.r-project.org/web/packages/AbsFilterGSEA/")
13908 (synopsis "Improved false positive control of gene-permuting with absolute filtering")
13910 "This package provides a function that performs gene-permuting of a gene-set
13911 enrichment analysis (GSEA) calculation with or without the absolute filtering.
13912 Without filtering, users can perform (original) two-tailed or one-tailed
13914 (license license:gpl2)))
13916 (define-public jamm
13919 (version "1.0.7.5")
13923 (uri (git-reference
13924 (url "https://github.com/mahmoudibrahim/JAMM.git")
13925 (commit (string-append "JAMMv" version))))
13926 (file-name (git-file-name name version))
13929 "0ls889jcma1ch9h21jjhnkadgszgqj41842hhcjh6cg88f85qf3i"))))
13930 (build-system gnu-build-system)
13932 `(#:tests? #f ; there are none
13934 (modify-phases %standard-phases
13935 (delete 'configure)
13938 (lambda* (#:key inputs outputs #:allow-other-keys)
13939 (let* ((out (assoc-ref outputs "out"))
13940 (libexec (string-append out "/libexec/jamm"))
13941 (bin (string-append out "/bin")))
13942 (substitute* '("JAMM.sh"
13943 "SignalGenerator.sh")
13945 (string-append "sPath=\"" libexec "\"\n")))
13946 (for-each (lambda (file)
13947 (install-file file libexec))
13948 (list "bincalculator.r"
13960 (chmod script #o555)
13961 (install-file script bin)
13962 (wrap-program (string-append bin "/" script)
13963 `("PATH" ":" prefix
13964 (,(string-append (assoc-ref inputs "coreutils") "/bin")
13965 ,(string-append (assoc-ref inputs "gawk") "/bin")
13966 ,(string-append (assoc-ref inputs "perl") "/bin")
13967 ,(string-append (assoc-ref inputs "r-minimal") "/bin")))
13968 `("PERL5LIB" ":" prefix (,(getenv "PERL5LIB")))
13969 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
13970 (list "JAMM.sh" "SignalGenerator.sh")))
13974 ("coreutils" ,coreutils)
13977 ("r-minimal" ,r-minimal)
13978 ;;("r-parallel" ,r-parallel)
13979 ("r-signal" ,r-signal)
13980 ("r-mclust" ,r-mclust)))
13981 (home-page "https://github.com/mahmoudibrahim/JAMM")
13982 (synopsis "Peak finder for NGS datasets")
13984 "JAMM is a peak finder for next generation sequencing datasets (ChIP-Seq,
13985 ATAC-Seq, DNase-Seq, etc.) that can integrate replicates and assign peak
13986 boundaries accurately. JAMM is applicable to both broad and narrow
13988 (license license:gpl3+)))
13990 (define-public ngless
13997 (uri (git-reference
13998 (url "https://gitlab.com/ngless/ngless.git")
13999 (commit (string-append "v" version))))
14000 (file-name (git-file-name name version))
14003 "0mc2gi7h4lx74zylvyp76mvc0w6706j858ii9vlgzqsw6acpr117"))))
14004 (build-system haskell-build-system)
14006 `(#:haddock? #f ; The haddock phase fails with: NGLess/CmdArgs.hs:20:1:
14007 ; error: parse error on input import
14008 ; import Options.Applicative
14010 (modify-phases %standard-phases
14011 (add-after 'unpack 'create-cabal-file
14012 (lambda _ (invoke "hpack") #t))
14013 ;; These tools are expected to be installed alongside ngless.
14014 (add-after 'install 'link-tools
14015 (lambda* (#:key inputs outputs #:allow-other-keys)
14016 (let ((bin (string-append (assoc-ref outputs "out") "/bin/")))
14017 (symlink (string-append (assoc-ref inputs "prodigal")
14019 (string-append bin "ngless-" ,version "-prodigal"))
14020 (symlink (string-append (assoc-ref inputs "minimap2")
14022 (string-append bin "ngless-" ,version "-minimap2"))
14023 (symlink (string-append (assoc-ref inputs "samtools")
14025 (string-append bin "ngless-" ,version "-samtools"))
14026 (symlink (string-append (assoc-ref inputs "bwa")
14028 (string-append bin "ngless-" ,version "-bwa"))
14031 `(("prodigal" ,prodigal)
14033 ("samtools" ,samtools)
14034 ("minimap2" ,minimap2)
14035 ("ghc-aeson" ,ghc-aeson)
14036 ("ghc-ansi-terminal" ,ghc-ansi-terminal)
14037 ("ghc-async" ,ghc-async)
14038 ("ghc-atomic-write" ,ghc-atomic-write)
14039 ("ghc-bytestring-lexing" ,ghc-bytestring-lexing)
14040 ("ghc-chart" ,ghc-chart)
14041 ("ghc-chart-cairo" ,ghc-chart-cairo)
14042 ("ghc-conduit" ,ghc-conduit)
14043 ("ghc-conduit-algorithms" ,ghc-conduit-algorithms)
14044 ("ghc-conduit-combinators" ,ghc-conduit-combinators)
14045 ("ghc-conduit-extra" ,ghc-conduit-extra)
14046 ("ghc-configurator" ,ghc-configurator)
14047 ("ghc-convertible" ,ghc-convertible)
14048 ("ghc-data-default" ,ghc-data-default)
14049 ("ghc-double-conversion" ,ghc-double-conversion)
14050 ("ghc-edit-distance" ,ghc-edit-distance)
14051 ("ghc-either" ,ghc-either)
14052 ("ghc-errors" ,ghc-errors)
14053 ("ghc-extra" ,ghc-extra)
14054 ("ghc-filemanip" ,ghc-filemanip)
14055 ("ghc-file-embed" ,ghc-file-embed)
14056 ("ghc-gitrev" ,ghc-gitrev)
14057 ("ghc-hashtables" ,ghc-hashtables)
14058 ("ghc-http-conduit" ,ghc-http-conduit)
14059 ("ghc-inline-c" ,ghc-inline-c)
14060 ("ghc-inline-c-cpp" ,ghc-inline-c-cpp)
14061 ("ghc-intervalmap" ,ghc-intervalmap)
14062 ("ghc-missingh" ,ghc-missingh)
14063 ("ghc-optparse-applicative" ,ghc-optparse-applicative)
14064 ("ghc-parsec" ,ghc-parsec)
14065 ("ghc-regex" ,ghc-regex)
14066 ("ghc-safe" ,ghc-safe)
14067 ("ghc-safeio" ,ghc-safeio)
14068 ("ghc-strict" ,ghc-strict)
14069 ("ghc-tar" ,ghc-tar)
14070 ("ghc-text" ,ghc-text)
14071 ("ghc-unliftio" ,ghc-unliftio)
14072 ("ghc-unliftio-core" ,ghc-unliftio-core)
14073 ("ghc-vector" ,ghc-vector)
14074 ("ghc-yaml" ,ghc-yaml)
14075 ("ghc-zlib" ,ghc-zlib)))
14078 ("r-hdf5r" ,r-hdf5r)
14079 ("r-iterators" ,r-iterators)
14080 ("r-itertools" ,r-itertools)
14081 ("r-matrix" ,r-matrix)))
14083 `(("ghc-hpack" ,ghc-hpack)
14084 ("ghc-quickcheck" ,ghc-quickcheck)
14085 ("ghc-test-framework" ,ghc-test-framework)
14086 ("ghc-test-framework-hunit",ghc-test-framework-hunit)
14087 ("ghc-test-framework-quickcheck2" ,ghc-test-framework-quickcheck2)
14088 ("ghc-test-framework-th" ,ghc-test-framework-th)))
14089 (home-page "https://gitlab.com/ngless/ngless")
14090 (synopsis "DSL for processing next-generation sequencing data")
14091 (description "Ngless is a domain-specific language for
14092 @dfn{next-generation sequencing} (NGS) data processing.")
14093 (license license:expat)))
14095 (define-public filtlong
14096 ;; The recommended way to install is to clone the git repository
14097 ;; https://github.com/rrwick/Filtlong#installation
14098 ;; and the lastest release is more than nine months old
14099 (let ((commit "d1bb46dfe8bc7efe6257b5ce222c04bfe8aedaab")
14103 (version (git-version "0.2.0" revision commit))
14107 (uri (git-reference
14108 (url "https://github.com/rrwick/Filtlong.git")
14110 (file-name (git-file-name name version))
14112 (base32 "1xr92r820x8qlkcr3b57iw223yq8vjgyi42jr79w2xgw47qzr575"))))
14113 (build-system gnu-build-system)
14115 `(#:tests? #f ; no check target
14117 (modify-phases %standard-phases
14118 (delete 'configure)
14120 (lambda* (#:key outputs #:allow-other-keys)
14121 (let* ((out (assoc-ref outputs "out"))
14122 (bin (string-append out "/bin"))
14123 (scripts (string-append out "/share/filtlong/scripts")))
14124 (install-file "bin/filtlong" bin)
14125 (install-file "scripts/histogram.py" scripts)
14126 (install-file "scripts/read_info_histograms.sh" scripts))
14128 (add-after 'install 'wrap-program
14129 (lambda* (#:key inputs outputs #:allow-other-keys)
14130 (let* ((out (assoc-ref outputs "out"))
14131 (path (getenv "PYTHONPATH")))
14132 (wrap-program (string-append out
14133 "/share/filtlong/scripts/histogram.py")
14134 `("PYTHONPATH" ":" prefix (,path))))
14136 (add-before 'check 'patch-tests
14138 (substitute* "scripts/read_info_histograms.sh"
14139 (("awk") (which "gawk")))
14142 `(("gawk" ,gawk) ;for read_info_histograms.sh
14143 ("python" ,python-2) ;required for histogram.py
14145 (home-page "https://github.com/rrwick/Filtlong/")
14146 (synopsis "Tool for quality filtering of Nanopore and PacBio data")
14148 "The Filtlong package is a tool for filtering long reads by quality.
14149 It can take a set of long reads and produce a smaller, better subset. It uses
14150 both read length (longer is better) and read identity (higher is better) when
14151 choosing which reads pass the filter.")
14152 (license (list license:gpl3 ;filtlong
14153 license:asl2.0))))) ;histogram.py
14155 (define-public nanopolish
14156 ;; The recommended way to install is to clone the git repository
14157 ;; <https://github.com/jts/nanopolish#installing-a-particular-release>.
14158 ;; Also, the differences between release and current version seem to be
14160 (let ((commit "50e8b5cc62f9b46f5445f5c5e8c5ab7263ea6d9d")
14163 (name "nanopolish")
14164 (version (git-version "0.10.2" revision commit))
14168 (uri (git-reference
14169 (url "https://github.com/jts/nanopolish.git")
14172 (file-name (git-file-name name version))
14174 (base32 "09j5gz57yr9i34a27vbl72i4g8syv2zzgmsfyjq02yshmnrvkjs6"))
14175 (modules '((guix build utils)))
14178 (delete-file-recursively "htslib")
14180 (build-system gnu-build-system)
14183 `("HDF5=noinstall" "EIGEN=noinstall" "HTS=noinstall" "CC=gcc")
14184 #:tests? #f ; no check target
14186 (modify-phases %standard-phases
14187 (add-after 'unpack 'find-eigen
14188 (lambda* (#:key inputs #:allow-other-keys)
14190 (string-append (assoc-ref inputs "eigen")
14191 "/include/eigen3"))
14193 (delete 'configure)
14195 (lambda* (#:key outputs #:allow-other-keys)
14196 (let* ((out (assoc-ref outputs "out"))
14197 (bin (string-append out "/bin"))
14198 (scripts (string-append out "/share/nanopolish/scripts")))
14200 (install-file "nanopolish" bin)
14201 (for-each (lambda (file) (install-file file scripts))
14202 (find-files "scripts" ".*"))
14204 (add-after 'install 'wrap-programs
14205 (lambda* (#:key outputs #:allow-other-keys)
14206 (for-each (lambda (file)
14207 (wrap-program file `("PYTHONPATH" ":" prefix (,path))))
14208 (find-files "/share/nanopolish/scripts" "\\.py"))
14209 (for-each (lambda (file)
14210 (wrap-program file `("PERL5LIB" ":" prefix (,path))))
14211 (find-files "/share/nanopolish/scripts" "\\.pl"))
14218 ("python" ,python-wrapper)
14219 ("python-biopython" ,python-biopython)
14220 ("python-numpy" ,python-numpy)
14221 ("python-pysam" ,python-pysam)
14222 ("python-scikit-learn" , python-scikit-learn)
14223 ("python-scipy" ,python-scipy)
14225 (home-page "https://github.com/jts/nanopolish")
14226 (synopsis "Signal-level analysis of Oxford Nanopore sequencing data")
14228 "This package analyses the Oxford Nanopore sequencing data at signal-level.
14229 Nanopolish can calculate an improved consensus sequence for a draft genome
14230 assembly, detect base modifications, call SNPs (Single nucleotide
14231 polymorphisms) and indels with respect to a reference genome and more.")
14232 (license license:expat))))
14234 (define-public cnvkit
14241 (uri (git-reference
14242 (url "https://github.com/etal/cnvkit.git")
14243 (commit (string-append "v" version))))
14244 (file-name (git-file-name name version))
14246 (base32 "0g2f78k68yglmj4fsfmgs8idqv3di9aj53fg0ld0hqljg8chhh82"))))
14247 (build-system python-build-system)
14249 `(("python-biopython" ,python-biopython)
14250 ("python-future" ,python-future)
14251 ("python-matplotlib" ,python-matplotlib)
14252 ("python-numpy" ,python-numpy)
14253 ("python-reportlab" ,python-reportlab)
14254 ("python-pandas" ,python-pandas)
14255 ("python-pysam" ,python-pysam)
14256 ("python-pyfaidx" ,python-pyfaidx)
14257 ("python-scipy" ,python-scipy)
14259 ("r-dnacopy" ,r-dnacopy)))
14260 (home-page "https://cnvkit.readthedocs.org/")
14261 (synopsis "Copy number variant detection from targeted DNA sequencing")
14263 "CNVkit is a Python library and command-line software toolkit to infer
14264 and visualize copy number from high-throughput DNA sequencing data. It is
14265 designed for use with hybrid capture, including both whole-exome and custom
14266 target panels, and short-read sequencing platforms such as Illumina and Ion
14268 (license license:asl2.0)))
14270 (define-public python-pyfit-sne
14272 (name "python-pyfit-sne")
14277 (uri (git-reference
14278 (url "https://github.com/KlugerLab/pyFIt-SNE.git")
14280 (file-name (git-file-name name version))
14282 (base32 "13wh3qkzs56azmmgnxib6xfr29g7xh09sxylzjpni5j0pp0rc5qw"))))
14283 (build-system python-build-system)
14285 `(("python-numpy" ,python-numpy)))
14289 `(("python-cython" ,python-cython)))
14290 (home-page "https://github.com/KlugerLab/pyFIt-SNE")
14291 (synopsis "FFT-accelerated Interpolation-based t-SNE")
14293 "t-Stochastic Neighborhood Embedding (t-SNE) is a highly successful
14294 method for dimensionality reduction and visualization of high dimensional
14295 datasets. A popular implementation of t-SNE uses the Barnes-Hut algorithm to
14296 approximate the gradient at each iteration of gradient descent. This package
14297 is a Cython wrapper for FIt-SNE.")
14298 (license license:bsd-4)))
14300 (define-public bbmap
14306 (uri (string-append
14307 "mirror://sourceforge/bbmap/BBMap_" version ".tar.gz"))
14310 "1q4rfhxcb6z3gm8zg2davjz98w22lkf4hm9ikxz9kdl93pil3wkd"))))
14311 (build-system ant-build-system)
14313 `(#:build-target "dist"
14314 #:tests? #f ; there are none
14316 (list (string-append "-Dmpijar="
14317 (assoc-ref %build-inputs "java-openmpi")
14319 #:modules ((guix build ant-build-system)
14321 (guix build java-utils))
14323 (modify-phases %standard-phases
14324 (add-after 'build 'build-jni-library
14326 (with-directory-excursion "jni"
14327 (invoke "make" "-f" "makefile.linux"))))
14328 ;; There is no install target
14329 (replace 'install (install-jars "dist"))
14330 (add-after 'install 'install-scripts-and-documentation
14331 (lambda* (#:key outputs #:allow-other-keys)
14332 (substitute* "calcmem.sh"
14333 (("\\| awk ") (string-append "| " (which "awk") " ")))
14334 (let* ((scripts (find-files "." "\\.sh$"))
14335 (out (assoc-ref outputs "out"))
14336 (bin (string-append out "/bin"))
14337 (doc (string-append out "/share/doc/bbmap"))
14338 (jni (string-append out "/lib/jni")))
14339 (substitute* scripts
14340 (("\\$DIR\"\"docs") doc)
14342 (string-append "CP=" out "/share/java/BBTools.jar\n"))
14343 (("^NATIVELIBDIR.*")
14344 (string-append "NATIVELIBDIR=" jni "\n"))
14346 (string-append "CMD=\"" (which "java"))))
14347 (for-each (lambda (script) (install-file script bin)) scripts)
14349 ;; Install JNI library
14350 (install-file "jni/libbbtoolsjni.so" jni)
14352 ;; Install documentation
14353 (install-file "docs/readme.txt" doc)
14354 (copy-recursively "docs/guides" doc))
14359 ("java-eclipse-jdt-core" ,java-eclipse-jdt-core)
14360 ("java-eclipse-jdt-compiler-apt" ,java-eclipse-jdt-compiler-apt)
14361 ("java-openmpi" ,java-openmpi)))
14362 (home-page "http://sourceforge.net/projects/bbmap/")
14363 (synopsis "Aligner and other tools for short sequencing reads")
14365 "This package provides bioinformatic tools to align, deduplicate,
14366 reformat, filter and normalize DNA and RNA-seq data. It includes the
14367 following tools: BBMap, a short read aligner for DNA and RNA-seq data; BBNorm,
14368 a kmer-based error-correction and normalization tool; Dedupe, a tool to
14369 simplify assemblies by removing duplicate or contained subsequences that share
14370 a target percent identity; Reformat, to convert reads between
14371 fasta/fastq/scarf/fasta+qual/sam, interleaved/paired, and ASCII-33/64, at over
14372 500 MB/s; and BBDuk, a tool to filter, trim, or mask reads with kmer matches
14373 to an artifact/contaminant file.")
14374 (license license:bsd-3)))
14376 (define-public velvet
14382 (uri (string-append "https://www.ebi.ac.uk/~zerbino/velvet/"
14383 "velvet_" version ".tgz"))
14386 "0h3njwy66p6bx14r3ar1byb0ccaxmxka4c65rn4iybyiqa4d8kc8"))
14387 ;; Delete bundled libraries
14388 (modules '((guix build utils)))
14391 (delete-file "Manual.pdf")
14392 (delete-file-recursively "third-party")
14394 (build-system gnu-build-system)
14396 `(#:make-flags '("OPENMP=t")
14397 #:test-target "test"
14399 (modify-phases %standard-phases
14400 (delete 'configure)
14401 (add-after 'unpack 'fix-zlib-include
14403 (substitute* "src/binarySequences.c"
14404 (("../third-party/zlib-1.2.3/zlib.h") "zlib.h"))
14407 (lambda* (#:key outputs #:allow-other-keys)
14408 (let* ((out (assoc-ref outputs "out"))
14409 (bin (string-append out "/bin"))
14410 (doc (string-append out "/share/doc/velvet")))
14413 (install-file "velveth" bin)
14414 (install-file "velvetg" bin)
14415 (install-file "Manual.pdf" doc)
14416 (install-file "Columbus_manual.pdf" doc)
14419 `(("openmpi" ,openmpi)
14422 `(("texlive" ,(texlive-union (list texlive-latex-graphics
14423 texlive-latex-hyperref)))))
14424 (home-page "https://www.ebi.ac.uk/~zerbino/velvet/")
14425 (synopsis "Nucleic acid sequence assembler for very short reads")
14427 "Velvet is a de novo genomic assembler specially designed for short read
14428 sequencing technologies, such as Solexa or 454. Velvet currently takes in
14429 short read sequences, removes errors then produces high quality unique
14430 contigs. It then uses paired read information, if available, to retrieve the
14431 repeated areas between contigs.")
14432 (license license:gpl2+)))
14434 (define-public python-velocyto
14436 (name "python-velocyto")
14437 (version "0.17.17")
14441 (uri (pypi-uri "velocyto" version))
14444 "0fgygyzqgrq32dv6a00biq1p1cwi6kbl5iqblxq1kklj6b2mzmhs"))))
14445 (build-system python-build-system)
14447 `(("python-click" ,python-click)
14448 ("python-cython" ,python-cython)
14449 ("python-h5py" ,python-h5py)
14450 ("python-loompy" ,python-loompy)
14451 ("python-matplotlib" ,python-matplotlib)
14452 ("python-numba" ,python-numba)
14453 ("python-numpy" ,python-numpy)
14454 ("python-pandas" ,python-pandas)
14455 ("python-pysam" ,python-pysam)
14456 ("python-scikit-learn" ,python-scikit-learn)
14457 ("python-scipy" ,python-scipy)))
14458 (home-page "https://github.com/velocyto-team/velocyto.py")
14459 (synopsis "RNA velocity analysis for single cell RNA-seq data")
14461 "Velocyto is a library for the analysis of RNA velocity. Velocyto
14462 includes a command line tool and an analysis pipeline.")
14463 (license license:bsd-2)))
14465 (define-public arriba
14472 (uri (string-append "https://github.com/suhrig/arriba/releases/"
14473 "download/v" version "/arriba_v" version ".tar.gz"))
14476 "0jx9656ry766vb8z08m1c3im87b0c82qpnjby9wz4kcz8vn87dx2"))))
14477 (build-system gnu-build-system)
14479 `(#:tests? #f ; there are none
14481 (modify-phases %standard-phases
14482 (replace 'configure
14483 (lambda* (#:key inputs #:allow-other-keys)
14484 (let ((htslib (assoc-ref inputs "htslib")))
14485 (substitute* "Makefile"
14486 (("-I\\$\\(HTSLIB\\)/htslib")
14487 (string-append "-I" htslib "/include/htslib"))
14488 ((" \\$\\(HTSLIB\\)/libhts.a")
14489 (string-append " " htslib "/lib/libhts.so"))))
14490 (substitute* "run_arriba.sh"
14491 (("^STAR ") (string-append (which "STAR") " "))
14492 (("samtools --version-only")
14493 (string-append (which "samtools") " --version-only"))
14494 (("samtools index")
14495 (string-append (which "samtools") " index"))
14497 (string-append (which "samtools") " sort")))
14500 (lambda* (#:key outputs #:allow-other-keys)
14501 (let ((bin (string-append (assoc-ref outputs "out") "/bin")))
14502 (install-file "arriba" bin)
14503 (install-file "run_arriba.sh" bin)
14504 (install-file "draw_fusions.R" bin)
14505 (wrap-program (string-append bin "/draw_fusions.R")
14506 `("R_LIBS_SITE" ":" prefix (,(getenv "R_LIBS_SITE")))))
14509 `(("htslib" ,htslib)
14510 ("r-minimal" ,r-minimal)
14511 ("r-circlize" ,r-circlize)
14512 ("r-genomicalignments" ,r-genomicalignments)
14513 ("r-genomicranges" ,r-genomicranges)
14514 ("samtools" ,samtools)
14517 (home-page "https://github.com/suhrig/arriba")
14518 (synopsis "Gene fusion detection from RNA-Seq data ")
14520 "Arriba is a command-line tool for the detection of gene fusions from
14521 RNA-Seq data. It was developed for the use in a clinical research setting.
14522 Therefore, short runtimes and high sensitivity were important design criteria.
14523 It is based on the fast STAR aligner and the post-alignment runtime is
14524 typically just around two minutes. In contrast to many other fusion detection
14525 tools which build on STAR, Arriba does not require to reduce the
14526 @code{alignIntronMax} parameter of STAR to detect small deletions.")
14527 ;; All code is under the Expat license with the exception of
14528 ;; "draw_fusions.R", which is under GPLv3.
14529 (license (list license:expat license:gpl3))))
14531 (define-public adapterremoval
14533 (name "adapterremoval")
14538 (uri (git-reference
14539 (url "https://github.com/MikkelSchubert/adapterremoval.git")
14540 (commit (string-append "v" version))))
14541 (file-name (git-file-name name version))
14544 "1nf3ki5pfzalhrx2fr1y6pfqfi133yj2m7q4fj9irf5fb94bapwr"))))
14545 (build-system gnu-build-system)
14547 `(#:make-flags (list "COLOR_BUILD=no"
14548 (string-append "PREFIX="
14549 (assoc-ref %outputs "out")))
14550 #:test-target "test"
14552 (modify-phases %standard-phases
14553 (delete 'configure))))
14556 (home-page "https://adapterremoval.readthedocs.io/")
14557 (synopsis "Rapid sequence adapter trimming, identification, and read merging")
14559 "This program searches for and removes remnant adapter sequences from
14560 @dfn{High-Throughput Sequencing} (HTS) data and (optionally) trims low quality
14561 bases from the 3' end of reads following adapter removal. AdapterRemoval can
14562 analyze both single end and paired end data, and can be used to merge
14563 overlapping paired-ended reads into (longer) consensus sequences.
14564 Additionally, the AdapterRemoval may be used to recover a consensus adapter
14565 sequence for paired-ended data, for which this information is not available.")
14566 (license license:gpl3+)))
14568 (define-public pplacer
14569 (let ((commit "807f6f3"))
14572 ;; The commit should be updated with each version change.
14573 (version "1.1.alpha19")
14577 (uri (git-reference
14578 (url "https://github.com/matsen/pplacer.git")
14579 (commit (string-append "v" version))))
14580 (file-name (git-file-name name version))
14582 (base32 "11ppbbbx20p2g9wj3ff64dhnarb12q79v7qh4rk0gj6lkbz4n7cn"))))
14583 (build-system ocaml-build-system)
14585 `(#:modules ((guix build ocaml-build-system)
14589 (modify-phases %standard-phases
14590 (delete 'configure)
14591 (add-after 'unpack 'fix-build-with-latest-ocaml
14593 (substitute* "myocamlbuild.ml"
14594 (("dep \\[\"c_pam\"\\]" m)
14595 (string-append "flag [\"ocaml\"; \"compile\"] (A \"-unsafe-string\");\n"
14597 (("let run_and_read" m)
14602 let pos = String.index s ch in
14603 x := (String.before s pos)::!x;
14604 go (String.after s (pos + 1))
14607 with Not_found -> !x
14608 let split_nl s = split s '\\n'
14609 let before_space s =
14610 try String.before s (String.index s ' ')
14611 with Not_found -> s
14614 (("run_and_read \"ocamlfind list \\| cut -d' ' -f1\"" m)
14615 (string-append "List.map before_space (split_nl & " m ")"))
14616 ((" blank_sep_strings &") "")
14617 ((" Lexing.from_string &") ""))
14619 (add-after 'unpack 'replace-bundled-cddlib
14620 (lambda* (#:key inputs #:allow-other-keys)
14621 (let* ((cddlib-src (assoc-ref inputs "cddlib-src"))
14622 (local-dir "cddlib_guix"))
14624 (with-directory-excursion local-dir
14625 (invoke "tar" "xvf" cddlib-src))
14626 (let ((cddlib-src-folder
14627 (string-append local-dir "/"
14628 (list-ref (scandir local-dir) 2)
14630 (for-each make-file-writable (find-files "cdd_src" ".*"))
14634 (string-append "cdd_src/" (basename file))))
14635 (find-files cddlib-src-folder ".*[ch]$")))
14637 (add-after 'unpack 'fix-makefile
14639 ;; Remove system calls to 'git'.
14640 (substitute* "Makefile"
14641 (("^DESCRIPT:=pplacer-.*")
14643 "DESCRIPT:=pplacer-$(shell uname)-v" ,version "\n")))
14644 (substitute* "myocamlbuild.ml"
14645 (("git describe --tags --long .*\\\" with")
14647 "echo -n v" ,version "-" ,commit "\" with")))
14650 (lambda* (#:key outputs #:allow-other-keys)
14651 (let* ((out (assoc-ref outputs "out"))
14652 (bin (string-append out "/bin")))
14653 (copy-recursively "bin" bin))
14656 `(("zlib" ,zlib "static")
14658 ("ocaml-ounit" ,ocaml-ounit)
14659 ("ocaml-batteries" ,ocaml-batteries)
14660 ("ocaml-camlzip" ,camlzip)
14661 ("ocaml-csv" ,ocaml-csv)
14662 ("ocaml-sqlite3" ,ocaml-sqlite3)
14663 ("ocaml-xmlm" ,ocaml-xmlm)
14664 ("ocaml-mcl" ,ocaml-mcl)
14665 ("ocaml-gsl" ,ocaml-gsl-1)))
14667 `(("cddlib-src" ,(package-source cddlib))
14668 ("ocamlbuild" ,ocamlbuild)
14669 ("pkg-config" ,pkg-config)))
14671 `(("pplacer-scripts" ,pplacer-scripts)))
14672 (synopsis "Phylogenetic placement of biological sequences")
14674 "Pplacer places query sequences on a fixed reference phylogenetic tree
14675 to maximize phylogenetic likelihood or posterior probability according to a
14676 reference alignment. Pplacer is designed to be fast, to give useful
14677 information about uncertainty, and to offer advanced visualization and
14678 downstream analysis.")
14679 (home-page "http://matsen.fhcrc.org/pplacer")
14680 (license license:gpl3))))
14682 ;; This package is installed alongside 'pplacer'. It is a separate package so
14683 ;; that it can use the python-build-system for the scripts that are
14684 ;; distributed alongside the main OCaml binaries.
14685 (define pplacer-scripts
14688 (name "pplacer-scripts")
14689 (build-system python-build-system)
14691 `(#:python ,python-2
14693 (modify-phases %standard-phases
14694 (add-after 'unpack 'enter-scripts-dir
14695 (lambda _ (chdir "scripts") #t))
14697 (lambda _ (invoke "python" "-m" "unittest" "discover" "-v") #t))
14698 (add-after 'install 'wrap-executables
14699 (lambda* (#:key inputs outputs #:allow-other-keys)
14700 (let* ((out (assoc-ref outputs "out"))
14701 (bin (string-append out "/bin")))
14702 (let ((path (string-append
14703 (assoc-ref inputs "hmmer") "/bin:"
14704 (assoc-ref inputs "infernal") "/bin")))
14706 (wrap-program (string-append bin "/refpkg_align.py")
14707 `("PATH" ":" prefix (,path))))
14708 (let ((path (string-append
14709 (assoc-ref inputs "hmmer") "/bin")))
14710 (wrap-program (string-append bin "/hrefpkg_query.py")
14711 `("PATH" ":" prefix (,path)))))
14714 `(("infernal" ,infernal)
14717 `(("python-biopython" ,python2-biopython)
14718 ("taxtastic" ,taxtastic)))
14719 (synopsis "Pplacer Python scripts")))
14721 (define-public python2-checkm-genome
14723 (name "python2-checkm-genome")
14728 (uri (pypi-uri "checkm-genome" version))
14731 "0bm8gpxjmzxsxxl8lzwqhgx8g1dlnmp6znz7wv3hgb0gdjbf9dzz"))))
14732 (build-system python-build-system)
14734 `(#:python ,python-2
14735 #:tests? #f)) ; some tests are interactive
14737 `(("python-dendropy" ,python2-dendropy)
14738 ("python-matplotlib" ,python2-matplotlib)
14739 ("python-numpy" ,python2-numpy)
14740 ("python-pysam" ,python2-pysam)
14741 ("python-scipy" ,python2-scipy)))
14742 (home-page "http://pypi.python.org/pypi/checkm/")
14743 (synopsis "Assess the quality of putative genome bins")
14745 "CheckM provides a set of tools for assessing the quality of genomes
14746 recovered from isolates, single cells, or metagenomes. It provides robust
14747 estimates of genome completeness and contamination by using collocated sets of
14748 genes that are ubiquitous and single-copy within a phylogenetic lineage.
14749 Assessment of genome quality can also be examined using plots depicting key
14750 genomic characteristics (e.g., GC, coding density) which highlight sequences
14751 outside the expected distributions of a typical genome. CheckM also provides
14752 tools for identifying genome bins that are likely candidates for merging based
14753 on marker set compatibility, similarity in genomic characteristics, and
14754 proximity within a reference genome.")
14755 (license license:gpl3+)))
14757 (define-public umi-tools
14764 (uri (pypi-uri "umi_tools" version))
14767 "08y3vz1vcx09whmbsn722lcs6jl9wyrh9i4p3k8j4cb1i32bij4a"))))
14768 (build-system python-build-system)
14770 `(("python-setuptools" ,python-setuptools)
14771 ("python-pandas" ,python-pandas)
14772 ("python-future" ,python-future)
14773 ("python-scipy" ,python-scipy)
14774 ("python-matplotlib" ,python-matplotlib)
14775 ("python-regex" ,python-regex)
14776 ("python-pysam" ,python-pysam)))
14778 `(("python-setuptools" ,python-setuptools)
14779 ("python-cython" ,python-cython)))
14780 (home-page "https://github.com/CGATOxford/UMI-tools")
14781 (synopsis "Tools for analyzing unique modular identifiers")
14782 (description "This package provides tools for dealing with @dfn{Unique
14783 Molecular Identifiers} (UMIs) and @dfn{Random Molecular Tags} (RMTs) in
14784 genetic sequences. There are six tools: the @code{extract} and
14785 @code{whitelist} commands are used to prepare a fastq containg UMIs @code{+/-}
14786 cell barcodes for alignment. The remaining commands, @code{group},
14787 @code{dedup}, and @{count}/@code{count_tab}, are used to identify PCR
14788 duplicates using the UMIs and perform different levels of analysis depending
14789 on the needs of the user.")
14790 (license license:expat)))